diff options
Diffstat (limited to '')
347 files changed, 44304 insertions, 0 deletions
diff --git a/debian/patches-rt/0001-ARM-at91-add-TCB-registers-definitions.patch b/debian/patches-rt/0001-ARM-at91-add-TCB-registers-definitions.patch new file mode 100644 index 000000000..39c411035 --- /dev/null +++ b/debian/patches-rt/0001-ARM-at91-add-TCB-registers-definitions.patch @@ -0,0 +1,210 @@ +From c7b29fd1b38b96426c553ddda13ebf7b8c823fd6 Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:18 +0200 +Subject: [PATCH 001/347] ARM: at91: add TCB registers definitions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Add registers and bits definitions for the timer counter blocks found on +Atmel ARM SoCs. + +Tested-by: Alexander Dahl <ada@thorsis.com> +Tested-by: Andras Szemzo <szemzo.andras@gmail.com> +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/soc/at91/atmel_tcb.h | 183 +++++++++++++++++++++++++++++++++++ + 1 file changed, 183 insertions(+) + create mode 100644 include/soc/at91/atmel_tcb.h + +diff --git a/include/soc/at91/atmel_tcb.h b/include/soc/at91/atmel_tcb.h +new file mode 100644 +index 000000000000..657e234b1483 +--- /dev/null ++++ b/include/soc/at91/atmel_tcb.h +@@ -0,0 +1,183 @@ ++//SPDX-License-Identifier: GPL-2.0 ++/* Copyright (C) 2018 Microchip */ ++ ++#ifndef __SOC_ATMEL_TCB_H ++#define __SOC_ATMEL_TCB_H ++ ++/* Channel registers */ ++#define ATMEL_TC_COFFS(c) ((c) * 0x40) ++#define ATMEL_TC_CCR(c) ATMEL_TC_COFFS(c) ++#define ATMEL_TC_CMR(c) (ATMEL_TC_COFFS(c) + 0x4) ++#define ATMEL_TC_SMMR(c) (ATMEL_TC_COFFS(c) + 0x8) ++#define ATMEL_TC_RAB(c) (ATMEL_TC_COFFS(c) + 0xc) ++#define ATMEL_TC_CV(c) (ATMEL_TC_COFFS(c) + 0x10) ++#define ATMEL_TC_RA(c) (ATMEL_TC_COFFS(c) + 0x14) ++#define ATMEL_TC_RB(c) (ATMEL_TC_COFFS(c) + 0x18) ++#define ATMEL_TC_RC(c) (ATMEL_TC_COFFS(c) + 0x1c) ++#define ATMEL_TC_SR(c) (ATMEL_TC_COFFS(c) + 0x20) ++#define ATMEL_TC_IER(c) (ATMEL_TC_COFFS(c) + 0x24) ++#define ATMEL_TC_IDR(c) (ATMEL_TC_COFFS(c) + 0x28) ++#define ATMEL_TC_IMR(c) (ATMEL_TC_COFFS(c) + 0x2c) ++#define ATMEL_TC_EMR(c) (ATMEL_TC_COFFS(c) + 0x30) ++ ++/* Block registers */ ++#define ATMEL_TC_BCR 0xc0 ++#define ATMEL_TC_BMR 0xc4 ++#define ATMEL_TC_QIER 0xc8 ++#define ATMEL_TC_QIDR 0xcc ++#define ATMEL_TC_QIMR 0xd0 ++#define ATMEL_TC_QISR 0xd4 ++#define ATMEL_TC_FMR 0xd8 ++#define ATMEL_TC_WPMR 0xe4 ++ ++/* CCR fields */ ++#define ATMEL_TC_CCR_CLKEN BIT(0) ++#define ATMEL_TC_CCR_CLKDIS BIT(1) ++#define ATMEL_TC_CCR_SWTRG BIT(2) ++ ++/* Common CMR fields */ ++#define ATMEL_TC_CMR_TCLKS_MSK GENMASK(2, 0) ++#define ATMEL_TC_CMR_TCLK(x) (x) ++#define ATMEL_TC_CMR_XC(x) ((x) + 5) ++#define ATMEL_TC_CMR_CLKI BIT(3) ++#define ATMEL_TC_CMR_BURST_MSK GENMASK(5, 4) ++#define ATMEL_TC_CMR_BURST_XC(x) (((x) + 1) << 4) ++#define ATMEL_TC_CMR_WAVE BIT(15) ++ ++/* Capture mode CMR fields */ ++#define ATMEL_TC_CMR_LDBSTOP BIT(6) ++#define ATMEL_TC_CMR_LDBDIS BIT(7) ++#define ATMEL_TC_CMR_ETRGEDG_MSK GENMASK(9, 8) ++#define ATMEL_TC_CMR_ETRGEDG_NONE (0 << 8) ++#define ATMEL_TC_CMR_ETRGEDG_RISING (1 << 8) ++#define ATMEL_TC_CMR_ETRGEDG_FALLING (2 << 8) ++#define ATMEL_TC_CMR_ETRGEDG_BOTH (3 << 8) ++#define ATMEL_TC_CMR_ABETRG BIT(10) ++#define ATMEL_TC_CMR_CPCTRG BIT(14) ++#define ATMEL_TC_CMR_LDRA_MSK GENMASK(17, 16) ++#define ATMEL_TC_CMR_LDRA_NONE (0 << 16) ++#define ATMEL_TC_CMR_LDRA_RISING (1 << 16) ++#define ATMEL_TC_CMR_LDRA_FALLING (2 << 16) ++#define ATMEL_TC_CMR_LDRA_BOTH (3 << 16) ++#define ATMEL_TC_CMR_LDRB_MSK GENMASK(19, 18) ++#define ATMEL_TC_CMR_LDRB_NONE (0 << 18) ++#define ATMEL_TC_CMR_LDRB_RISING (1 << 18) ++#define ATMEL_TC_CMR_LDRB_FALLING (2 << 18) ++#define ATMEL_TC_CMR_LDRB_BOTH (3 << 18) ++#define ATMEL_TC_CMR_SBSMPLR_MSK GENMASK(22, 20) ++#define ATMEL_TC_CMR_SBSMPLR(x) ((x) << 20) ++ ++/* Waveform mode CMR fields */ ++#define ATMEL_TC_CMR_CPCSTOP BIT(6) ++#define ATMEL_TC_CMR_CPCDIS BIT(7) ++#define ATMEL_TC_CMR_EEVTEDG_MSK GENMASK(9, 8) ++#define ATMEL_TC_CMR_EEVTEDG_NONE (0 << 8) ++#define ATMEL_TC_CMR_EEVTEDG_RISING (1 << 8) ++#define ATMEL_TC_CMR_EEVTEDG_FALLING (2 << 8) ++#define ATMEL_TC_CMR_EEVTEDG_BOTH (3 << 8) ++#define ATMEL_TC_CMR_EEVT_MSK GENMASK(11, 10) ++#define ATMEL_TC_CMR_EEVT_XC(x) (((x) + 1) << 10) ++#define ATMEL_TC_CMR_ENETRG BIT(12) ++#define ATMEL_TC_CMR_WAVESEL_MSK GENMASK(14, 13) ++#define ATMEL_TC_CMR_WAVESEL_UP (0 << 13) ++#define ATMEL_TC_CMR_WAVESEL_UPDOWN (1 << 13) ++#define ATMEL_TC_CMR_WAVESEL_UPRC (2 << 13) ++#define ATMEL_TC_CMR_WAVESEL_UPDOWNRC (3 << 13) ++#define ATMEL_TC_CMR_ACPA_MSK GENMASK(17, 16) ++#define ATMEL_TC_CMR_ACPA(a) (ATMEL_TC_CMR_ACTION_##a << 16) ++#define ATMEL_TC_CMR_ACPC_MSK GENMASK(19, 18) ++#define ATMEL_TC_CMR_ACPC(a) (ATMEL_TC_CMR_ACTION_##a << 18) ++#define ATMEL_TC_CMR_AEEVT_MSK GENMASK(21, 20) ++#define ATMEL_TC_CMR_AEEVT(a) (ATMEL_TC_CMR_ACTION_##a << 20) ++#define ATMEL_TC_CMR_ASWTRG_MSK GENMASK(23, 22) ++#define ATMEL_TC_CMR_ASWTRG(a) (ATMEL_TC_CMR_ACTION_##a << 22) ++#define ATMEL_TC_CMR_BCPB_MSK GENMASK(25, 24) ++#define ATMEL_TC_CMR_BCPB(a) (ATMEL_TC_CMR_ACTION_##a << 24) ++#define ATMEL_TC_CMR_BCPC_MSK GENMASK(27, 26) ++#define ATMEL_TC_CMR_BCPC(a) (ATMEL_TC_CMR_ACTION_##a << 26) ++#define ATMEL_TC_CMR_BEEVT_MSK GENMASK(29, 28) ++#define ATMEL_TC_CMR_BEEVT(a) (ATMEL_TC_CMR_ACTION_##a << 28) ++#define ATMEL_TC_CMR_BSWTRG_MSK GENMASK(31, 30) ++#define ATMEL_TC_CMR_BSWTRG(a) (ATMEL_TC_CMR_ACTION_##a << 30) ++#define ATMEL_TC_CMR_ACTION_NONE 0 ++#define ATMEL_TC_CMR_ACTION_SET 1 ++#define ATMEL_TC_CMR_ACTION_CLEAR 2 ++#define ATMEL_TC_CMR_ACTION_TOGGLE 3 ++ ++/* SMMR fields */ ++#define ATMEL_TC_SMMR_GCEN BIT(0) ++#define ATMEL_TC_SMMR_DOWN BIT(1) ++ ++/* SR/IER/IDR/IMR fields */ ++#define ATMEL_TC_COVFS BIT(0) ++#define ATMEL_TC_LOVRS BIT(1) ++#define ATMEL_TC_CPAS BIT(2) ++#define ATMEL_TC_CPBS BIT(3) ++#define ATMEL_TC_CPCS BIT(4) ++#define ATMEL_TC_LDRAS BIT(5) ++#define ATMEL_TC_LDRBS BIT(6) ++#define ATMEL_TC_ETRGS BIT(7) ++#define ATMEL_TC_CLKSTA BIT(16) ++#define ATMEL_TC_MTIOA BIT(17) ++#define ATMEL_TC_MTIOB BIT(18) ++ ++/* EMR fields */ ++#define ATMEL_TC_EMR_TRIGSRCA_MSK GENMASK(1, 0) ++#define ATMEL_TC_EMR_TRIGSRCA_TIOA 0 ++#define ATMEL_TC_EMR_TRIGSRCA_PWMX 1 ++#define ATMEL_TC_EMR_TRIGSRCB_MSK GENMASK(5, 4) ++#define ATMEL_TC_EMR_TRIGSRCB_TIOB (0 << 4) ++#define ATMEL_TC_EMR_TRIGSRCB_PWM (1 << 4) ++#define ATMEL_TC_EMR_NOCLKDIV BIT(8) ++ ++/* BCR fields */ ++#define ATMEL_TC_BCR_SYNC BIT(0) ++ ++/* BMR fields */ ++#define ATMEL_TC_BMR_TCXC_MSK(c) GENMASK(((c) * 2) + 1, (c) * 2) ++#define ATMEL_TC_BMR_TCXC(x, c) ((x) << (2 * (c))) ++#define ATMEL_TC_BMR_QDEN BIT(8) ++#define ATMEL_TC_BMR_POSEN BIT(9) ++#define ATMEL_TC_BMR_SPEEDEN BIT(10) ++#define ATMEL_TC_BMR_QDTRANS BIT(11) ++#define ATMEL_TC_BMR_EDGPHA BIT(12) ++#define ATMEL_TC_BMR_INVA BIT(13) ++#define ATMEL_TC_BMR_INVB BIT(14) ++#define ATMEL_TC_BMR_INVIDX BIT(15) ++#define ATMEL_TC_BMR_SWAP BIT(16) ++#define ATMEL_TC_BMR_IDXPHB BIT(17) ++#define ATMEL_TC_BMR_AUTOC BIT(18) ++#define ATMEL_TC_MAXFILT_MSK GENMASK(25, 20) ++#define ATMEL_TC_MAXFILT(x) (((x) - 1) << 20) ++#define ATMEL_TC_MAXCMP_MSK GENMASK(29, 26) ++#define ATMEL_TC_MAXCMP(x) ((x) << 26) ++ ++/* QEDC fields */ ++#define ATMEL_TC_QEDC_IDX BIT(0) ++#define ATMEL_TC_QEDC_DIRCHG BIT(1) ++#define ATMEL_TC_QEDC_QERR BIT(2) ++#define ATMEL_TC_QEDC_MPE BIT(3) ++#define ATMEL_TC_QEDC_DIR BIT(8) ++ ++/* FMR fields */ ++#define ATMEL_TC_FMR_ENCF(x) BIT(x) ++ ++/* WPMR fields */ ++#define ATMEL_TC_WPMR_WPKEY (0x54494d << 8) ++#define ATMEL_TC_WPMR_WPEN BIT(0) ++ ++static const u8 atmel_tc_divisors[5] = { 2, 8, 32, 128, 0, }; ++ ++static const struct of_device_id atmel_tcb_dt_ids[] = { ++ { ++ .compatible = "atmel,at91rm9200-tcb", ++ .data = (void *)16, ++ }, { ++ .compatible = "atmel,at91sam9x5-tcb", ++ .data = (void *)32, ++ }, { ++ /* sentinel */ ++ } ++}; ++ ++#endif /* __SOC_ATMEL_TCB_H */ +-- +2.36.1 + diff --git a/debian/patches-rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch b/debian/patches-rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch new file mode 100644 index 000000000..6f8c04a6c --- /dev/null +++ b/debian/patches-rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch @@ -0,0 +1,485 @@ +From ad55e9aff22686f2ddf3d898aac7aef214a5ed82 Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:19 +0200 +Subject: [PATCH 002/347] clocksource/drivers: Add a new driver for the Atmel + ARM TC blocks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Add a driver for the Atmel Timer Counter Blocks. This driver provides a +clocksource and two clockevent devices. + +One of the clockevent device is linked to the clocksource counter and so it +will run at the same frequency. This will be used when there is only on TCB +channel available for timers. + +The other clockevent device runs on a separate TCB channel when available. + +This driver uses regmap and syscon to be able to probe early in the boot +and avoid having to switch on the TCB clocksource later. Using regmap also +means that unused TCB channels may be used by other drivers (PWM for +example). read/writel are still used to access channel specific registers +to avoid the performance impact of regmap (mainly locking). + +Tested-by: Alexander Dahl <ada@thorsis.com> +Tested-by: Andras Szemzo <szemzo.andras@gmail.com> +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/clocksource/Kconfig | 8 + + drivers/clocksource/Makefile | 3 +- + drivers/clocksource/timer-atmel-tcb.c | 410 ++++++++++++++++++++++++++ + 3 files changed, 420 insertions(+), 1 deletion(-) + create mode 100644 drivers/clocksource/timer-atmel-tcb.c + +diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig +index 06504384c376..9422ea3a52ac 100644 +--- a/drivers/clocksource/Kconfig ++++ b/drivers/clocksource/Kconfig +@@ -416,6 +416,14 @@ config ATMEL_ST + help + Support for the Atmel ST timer. + ++config ATMEL_ARM_TCB_CLKSRC ++ bool "Microchip ARM TC Block" if COMPILE_TEST ++ select REGMAP_MMIO ++ depends on GENERIC_CLOCKEVENTS ++ help ++ This enables build of clocksource and clockevent driver for ++ the integrated Timer Counter Blocks in Microchip ARM SoCs. ++ + config CLKSRC_EXYNOS_MCT + bool "Exynos multi core timer driver" if COMPILE_TEST + depends on ARM || ARM64 +diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile +index db51b2427e8a..0df9384a1230 100644 +--- a/drivers/clocksource/Makefile ++++ b/drivers/clocksource/Makefile +@@ -3,7 +3,8 @@ obj-$(CONFIG_TIMER_OF) += timer-of.o + obj-$(CONFIG_TIMER_PROBE) += timer-probe.o + obj-$(CONFIG_ATMEL_PIT) += timer-atmel-pit.o + obj-$(CONFIG_ATMEL_ST) += timer-atmel-st.o +-obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o ++obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o ++obj-$(CONFIG_ATMEL_ARM_TCB_CLKSRC) += timer-atmel-tcb.o + obj-$(CONFIG_X86_PM_TIMER) += acpi_pm.o + obj-$(CONFIG_SCx200HR_TIMER) += scx200_hrt.o + obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC) += cs5535-clockevt.o +diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c +new file mode 100644 +index 000000000000..21fbe430f91b +--- /dev/null ++++ b/drivers/clocksource/timer-atmel-tcb.c +@@ -0,0 +1,410 @@ ++// SPDX-License-Identifier: GPL-2.0 ++#include <linux/clk.h> ++#include <linux/clockchips.h> ++#include <linux/clocksource.h> ++#include <linux/interrupt.h> ++#include <linux/kernel.h> ++#include <linux/mfd/syscon.h> ++#include <linux/of_address.h> ++#include <linux/of_irq.h> ++#include <linux/regmap.h> ++#include <linux/sched_clock.h> ++#include <soc/at91/atmel_tcb.h> ++ ++struct atmel_tcb_clksrc { ++ struct clocksource clksrc; ++ struct clock_event_device clkevt; ++ struct regmap *regmap; ++ void __iomem *base; ++ struct clk *clk[2]; ++ char name[20]; ++ int channels[2]; ++ int bits; ++ int irq; ++ struct { ++ u32 cmr; ++ u32 imr; ++ u32 rc; ++ bool clken; ++ } cache[2]; ++ u32 bmr_cache; ++ bool registered; ++ bool clk_enabled; ++}; ++ ++static struct atmel_tcb_clksrc tc; ++ ++static struct clk *tcb_clk_get(struct device_node *node, int channel) ++{ ++ struct clk *clk; ++ char clk_name[] = "t0_clk"; ++ ++ clk_name[1] += channel; ++ clk = of_clk_get_by_name(node->parent, clk_name); ++ if (!IS_ERR(clk)) ++ return clk; ++ ++ return of_clk_get_by_name(node->parent, "t0_clk"); ++} ++ ++/* ++ * Clocksource and clockevent using the same channel(s) ++ */ ++static u64 tc_get_cycles(struct clocksource *cs) ++{ ++ u32 lower, upper; ++ ++ do { ++ upper = readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[1])); ++ lower = readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[0])); ++ } while (upper != readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[1]))); ++ ++ return (upper << 16) | lower; ++} ++ ++static u64 tc_get_cycles32(struct clocksource *cs) ++{ ++ return readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[0])); ++} ++ ++static u64 notrace tc_sched_clock_read(void) ++{ ++ return tc_get_cycles(&tc.clksrc); ++} ++ ++static u64 notrace tc_sched_clock_read32(void) ++{ ++ return tc_get_cycles32(&tc.clksrc); ++} ++ ++static int tcb_clkevt_next_event(unsigned long delta, ++ struct clock_event_device *d) ++{ ++ u32 old, next, cur; ++ ++ old = readl(tc.base + ATMEL_TC_CV(tc.channels[0])); ++ next = old + delta; ++ writel(next, tc.base + ATMEL_TC_RC(tc.channels[0])); ++ cur = readl(tc.base + ATMEL_TC_CV(tc.channels[0])); ++ ++ /* check whether the delta elapsed while setting the register */ ++ if ((next < old && cur < old && cur > next) || ++ (next > old && (cur < old || cur > next))) { ++ /* ++ * Clear the CPCS bit in the status register to avoid ++ * generating a spurious interrupt next time a valid ++ * timer event is configured. ++ */ ++ old = readl(tc.base + ATMEL_TC_SR(tc.channels[0])); ++ return -ETIME; ++ } ++ ++ writel(ATMEL_TC_CPCS, tc.base + ATMEL_TC_IER(tc.channels[0])); ++ ++ return 0; ++} ++ ++static irqreturn_t tc_clkevt_irq(int irq, void *handle) ++{ ++ unsigned int sr; ++ ++ sr = readl(tc.base + ATMEL_TC_SR(tc.channels[0])); ++ if (sr & ATMEL_TC_CPCS) { ++ tc.clkevt.event_handler(&tc.clkevt); ++ return IRQ_HANDLED; ++ } ++ ++ return IRQ_NONE; ++} ++ ++static int tcb_clkevt_oneshot(struct clock_event_device *dev) ++{ ++ if (clockevent_state_oneshot(dev)) ++ return 0; ++ ++ /* ++ * Because both clockevent devices may share the same IRQ, we don't want ++ * the less likely one to stay requested ++ */ ++ return request_irq(tc.irq, tc_clkevt_irq, IRQF_TIMER | IRQF_SHARED, ++ tc.name, &tc); ++} ++ ++static int tcb_clkevt_shutdown(struct clock_event_device *dev) ++{ ++ writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[0])); ++ if (tc.bits == 16) ++ writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[1])); ++ ++ if (!clockevent_state_detached(dev)) ++ free_irq(tc.irq, &tc); ++ ++ return 0; ++} ++ ++static void __init tcb_setup_dual_chan(struct atmel_tcb_clksrc *tc, ++ int mck_divisor_idx) ++{ ++ /* first channel: waveform mode, input mclk/8, clock TIOA on overflow */ ++ writel(mck_divisor_idx /* likely divide-by-8 */ ++ | ATMEL_TC_CMR_WAVE ++ | ATMEL_TC_CMR_WAVESEL_UP /* free-run */ ++ | ATMEL_TC_CMR_ACPA(SET) /* TIOA rises at 0 */ ++ | ATMEL_TC_CMR_ACPC(CLEAR), /* (duty cycle 50%) */ ++ tc->base + ATMEL_TC_CMR(tc->channels[0])); ++ writel(0x0000, tc->base + ATMEL_TC_RA(tc->channels[0])); ++ writel(0x8000, tc->base + ATMEL_TC_RC(tc->channels[0])); ++ writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[0])); /* no irqs */ ++ writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[0])); ++ ++ /* second channel: waveform mode, input TIOA */ ++ writel(ATMEL_TC_CMR_XC(tc->channels[1]) /* input: TIOA */ ++ | ATMEL_TC_CMR_WAVE ++ | ATMEL_TC_CMR_WAVESEL_UP, /* free-run */ ++ tc->base + ATMEL_TC_CMR(tc->channels[1])); ++ writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[1])); /* no irqs */ ++ writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[1])); ++ ++ /* chain both channel, we assume the previous channel */ ++ regmap_write(tc->regmap, ATMEL_TC_BMR, ++ ATMEL_TC_BMR_TCXC(1 + tc->channels[1], tc->channels[1])); ++ /* then reset all the timers */ ++ regmap_write(tc->regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); ++} ++ ++static void __init tcb_setup_single_chan(struct atmel_tcb_clksrc *tc, ++ int mck_divisor_idx) ++{ ++ /* channel 0: waveform mode, input mclk/8 */ ++ writel(mck_divisor_idx /* likely divide-by-8 */ ++ | ATMEL_TC_CMR_WAVE ++ | ATMEL_TC_CMR_WAVESEL_UP, /* free-run */ ++ tc->base + ATMEL_TC_CMR(tc->channels[0])); ++ writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[0])); /* no irqs */ ++ writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[0])); ++ ++ /* then reset all the timers */ ++ regmap_write(tc->regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); ++} ++ ++static void tc_clksrc_suspend(struct clocksource *cs) ++{ ++ int i; ++ ++ for (i = 0; i < 1 + (tc.bits == 16); i++) { ++ tc.cache[i].cmr = readl(tc.base + ATMEL_TC_CMR(tc.channels[i])); ++ tc.cache[i].imr = readl(tc.base + ATMEL_TC_IMR(tc.channels[i])); ++ tc.cache[i].rc = readl(tc.base + ATMEL_TC_RC(tc.channels[i])); ++ tc.cache[i].clken = !!(readl(tc.base + ++ ATMEL_TC_SR(tc.channels[i])) & ++ ATMEL_TC_CLKSTA); ++ } ++ ++ if (tc.bits == 16) ++ regmap_read(tc.regmap, ATMEL_TC_BMR, &tc.bmr_cache); ++} ++ ++static void tc_clksrc_resume(struct clocksource *cs) ++{ ++ int i; ++ ++ for (i = 0; i < 1 + (tc.bits == 16); i++) { ++ /* Restore registers for the channel, RA and RB are not used */ ++ writel(tc.cache[i].cmr, tc.base + ATMEL_TC_CMR(tc.channels[i])); ++ writel(tc.cache[i].rc, tc.base + ATMEL_TC_RC(tc.channels[i])); ++ writel(0, tc.base + ATMEL_TC_RA(tc.channels[i])); ++ writel(0, tc.base + ATMEL_TC_RB(tc.channels[i])); ++ /* Disable all the interrupts */ ++ writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[i])); ++ /* Reenable interrupts that were enabled before suspending */ ++ writel(tc.cache[i].imr, tc.base + ATMEL_TC_IER(tc.channels[i])); ++ ++ /* Start the clock if it was used */ ++ if (tc.cache[i].clken) ++ writel(ATMEL_TC_CCR_CLKEN, tc.base + ++ ATMEL_TC_CCR(tc.channels[i])); ++ } ++ ++ /* in case of dual channel, chain channels */ ++ if (tc.bits == 16) ++ regmap_write(tc.regmap, ATMEL_TC_BMR, tc.bmr_cache); ++ /* Finally, trigger all the channels*/ ++ regmap_write(tc.regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); ++} ++ ++static int __init tcb_clksrc_register(struct device_node *node, ++ struct regmap *regmap, void __iomem *base, ++ int channel, int channel1, int irq, ++ int bits) ++{ ++ u32 rate, divided_rate = 0; ++ int best_divisor_idx = -1; ++ int i, err = -1; ++ u64 (*tc_sched_clock)(void); ++ ++ tc.regmap = regmap; ++ tc.base = base; ++ tc.channels[0] = channel; ++ tc.channels[1] = channel1; ++ tc.irq = irq; ++ tc.bits = bits; ++ ++ tc.clk[0] = tcb_clk_get(node, tc.channels[0]); ++ if (IS_ERR(tc.clk[0])) ++ return PTR_ERR(tc.clk[0]); ++ err = clk_prepare_enable(tc.clk[0]); ++ if (err) { ++ pr_debug("can't enable T0 clk\n"); ++ goto err_clk; ++ } ++ ++ /* How fast will we be counting? Pick something over 5 MHz. */ ++ rate = (u32)clk_get_rate(tc.clk[0]); ++ for (i = 0; i < 5; i++) { ++ unsigned int divisor = atmel_tc_divisors[i]; ++ unsigned int tmp; ++ ++ if (!divisor) ++ continue; ++ ++ tmp = rate / divisor; ++ pr_debug("TC: %u / %-3u [%d] --> %u\n", rate, divisor, i, tmp); ++ if (best_divisor_idx > 0) { ++ if (tmp < 5 * 1000 * 1000) ++ continue; ++ } ++ divided_rate = tmp; ++ best_divisor_idx = i; ++ } ++ ++ if (tc.bits == 32) { ++ tc.clksrc.read = tc_get_cycles32; ++ tcb_setup_single_chan(&tc, best_divisor_idx); ++ tc_sched_clock = tc_sched_clock_read32; ++ snprintf(tc.name, sizeof(tc.name), "%s:%d", ++ kbasename(node->parent->full_name), tc.channels[0]); ++ } else { ++ tc.clk[1] = tcb_clk_get(node, tc.channels[1]); ++ if (IS_ERR(tc.clk[1])) ++ goto err_disable_t0; ++ ++ err = clk_prepare_enable(tc.clk[1]); ++ if (err) { ++ pr_debug("can't enable T1 clk\n"); ++ goto err_clk1; ++ } ++ tc.clksrc.read = tc_get_cycles, ++ tcb_setup_dual_chan(&tc, best_divisor_idx); ++ tc_sched_clock = tc_sched_clock_read; ++ snprintf(tc.name, sizeof(tc.name), "%s:%d,%d", ++ kbasename(node->parent->full_name), tc.channels[0], ++ tc.channels[1]); ++ } ++ ++ pr_debug("%s at %d.%03d MHz\n", tc.name, ++ divided_rate / 1000000, ++ ((divided_rate + 500000) % 1000000) / 1000); ++ ++ tc.clksrc.name = tc.name; ++ tc.clksrc.suspend = tc_clksrc_suspend; ++ tc.clksrc.resume = tc_clksrc_resume; ++ tc.clksrc.rating = 200; ++ tc.clksrc.mask = CLOCKSOURCE_MASK(32); ++ tc.clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS; ++ ++ err = clocksource_register_hz(&tc.clksrc, divided_rate); ++ if (err) ++ goto err_disable_t1; ++ ++ sched_clock_register(tc_sched_clock, 32, divided_rate); ++ ++ tc.registered = true; ++ ++ /* Set up and register clockevents */ ++ tc.clkevt.name = tc.name; ++ tc.clkevt.cpumask = cpumask_of(0); ++ tc.clkevt.set_next_event = tcb_clkevt_next_event; ++ tc.clkevt.set_state_oneshot = tcb_clkevt_oneshot; ++ tc.clkevt.set_state_shutdown = tcb_clkevt_shutdown; ++ tc.clkevt.features = CLOCK_EVT_FEAT_ONESHOT; ++ tc.clkevt.rating = 125; ++ ++ clockevents_config_and_register(&tc.clkevt, divided_rate, 1, ++ BIT(tc.bits) - 1); ++ ++ return 0; ++ ++err_disable_t1: ++ if (tc.bits == 16) ++ clk_disable_unprepare(tc.clk[1]); ++ ++err_clk1: ++ if (tc.bits == 16) ++ clk_put(tc.clk[1]); ++ ++err_disable_t0: ++ clk_disable_unprepare(tc.clk[0]); ++ ++err_clk: ++ clk_put(tc.clk[0]); ++ ++ pr_err("%s: unable to register clocksource/clockevent\n", ++ tc.clksrc.name); ++ ++ return err; ++} ++ ++static int __init tcb_clksrc_init(struct device_node *node) ++{ ++ const struct of_device_id *match; ++ struct regmap *regmap; ++ void __iomem *tcb_base; ++ u32 channel; ++ int irq, err, chan1 = -1; ++ unsigned bits; ++ ++ if (tc.registered) ++ return -ENODEV; ++ ++ /* ++ * The regmap has to be used to access registers that are shared ++ * between channels on the same TCB but we keep direct IO access for ++ * the counters to avoid the impact on performance ++ */ ++ regmap = syscon_node_to_regmap(node->parent); ++ if (IS_ERR(regmap)) ++ return PTR_ERR(regmap); ++ ++ tcb_base = of_iomap(node->parent, 0); ++ if (!tcb_base) { ++ pr_err("%s +%d %s\n", __FILE__, __LINE__, __func__); ++ return -ENXIO; ++ } ++ ++ match = of_match_node(atmel_tcb_dt_ids, node->parent); ++ bits = (uintptr_t)match->data; ++ ++ err = of_property_read_u32_index(node, "reg", 0, &channel); ++ if (err) ++ return err; ++ ++ irq = of_irq_get(node->parent, channel); ++ if (irq < 0) { ++ irq = of_irq_get(node->parent, 0); ++ if (irq < 0) ++ return irq; ++ } ++ ++ if (bits == 16) { ++ of_property_read_u32_index(node, "reg", 1, &chan1); ++ if (chan1 == -1) { ++ pr_err("%s: clocksource needs two channels\n", ++ node->parent->full_name); ++ return -EINVAL; ++ } ++ } ++ ++ return tcb_clksrc_register(node, regmap, tcb_base, channel, chan1, irq, ++ bits); ++} ++TIMER_OF_DECLARE(atmel_tcb_clksrc, "atmel,tcb-timer", tcb_clksrc_init); +-- +2.36.1 + diff --git a/debian/patches-rt/0003-clocksource-drivers-timer-atmel-tcb-add-clockevent-d.patch b/debian/patches-rt/0003-clocksource-drivers-timer-atmel-tcb-add-clockevent-d.patch new file mode 100644 index 000000000..4d1f366c3 --- /dev/null +++ b/debian/patches-rt/0003-clocksource-drivers-timer-atmel-tcb-add-clockevent-d.patch @@ -0,0 +1,271 @@ +From fd06bfd5716c6f1f5905db9be97507fda425080c Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:20 +0200 +Subject: [PATCH 003/347] clocksource/drivers: timer-atmel-tcb: add clockevent + device on separate channel +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Add an other clockevent device that uses a separate TCB channel when +available. + +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/clocksource/timer-atmel-tcb.c | 217 +++++++++++++++++++++++++- + 1 file changed, 212 insertions(+), 5 deletions(-) + +diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c +index 21fbe430f91b..63ce3b69338a 100644 +--- a/drivers/clocksource/timer-atmel-tcb.c ++++ b/drivers/clocksource/timer-atmel-tcb.c +@@ -32,7 +32,7 @@ struct atmel_tcb_clksrc { + bool clk_enabled; + }; + +-static struct atmel_tcb_clksrc tc; ++static struct atmel_tcb_clksrc tc, tce; + + static struct clk *tcb_clk_get(struct device_node *node, int channel) + { +@@ -47,6 +47,203 @@ static struct clk *tcb_clk_get(struct device_node *node, int channel) + return of_clk_get_by_name(node->parent, "t0_clk"); + } + ++/* ++ * Clockevent device using its own channel ++ */ ++ ++static void tc_clkevt2_clk_disable(struct clock_event_device *d) ++{ ++ clk_disable(tce.clk[0]); ++ tce.clk_enabled = false; ++} ++ ++static void tc_clkevt2_clk_enable(struct clock_event_device *d) ++{ ++ if (tce.clk_enabled) ++ return; ++ clk_enable(tce.clk[0]); ++ tce.clk_enabled = true; ++} ++ ++static int tc_clkevt2_stop(struct clock_event_device *d) ++{ ++ writel(0xff, tce.base + ATMEL_TC_IDR(tce.channels[0])); ++ writel(ATMEL_TC_CCR_CLKDIS, tce.base + ATMEL_TC_CCR(tce.channels[0])); ++ ++ return 0; ++} ++ ++static int tc_clkevt2_shutdown(struct clock_event_device *d) ++{ ++ tc_clkevt2_stop(d); ++ if (!clockevent_state_detached(d)) ++ tc_clkevt2_clk_disable(d); ++ ++ return 0; ++} ++ ++/* For now, we always use the 32K clock ... this optimizes for NO_HZ, ++ * because using one of the divided clocks would usually mean the ++ * tick rate can never be less than several dozen Hz (vs 0.5 Hz). ++ * ++ * A divided clock could be good for high resolution timers, since ++ * 30.5 usec resolution can seem "low". ++ */ ++static int tc_clkevt2_set_oneshot(struct clock_event_device *d) ++{ ++ if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) ++ tc_clkevt2_stop(d); ++ ++ tc_clkevt2_clk_enable(d); ++ ++ /* slow clock, count up to RC, then irq and stop */ ++ writel(ATMEL_TC_CMR_TCLK(4) | ATMEL_TC_CMR_CPCSTOP | ++ ATMEL_TC_CMR_WAVE | ATMEL_TC_CMR_WAVESEL_UPRC, ++ tce.base + ATMEL_TC_CMR(tce.channels[0])); ++ writel(ATMEL_TC_CPCS, tce.base + ATMEL_TC_IER(tce.channels[0])); ++ ++ return 0; ++} ++ ++static int tc_clkevt2_set_periodic(struct clock_event_device *d) ++{ ++ if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) ++ tc_clkevt2_stop(d); ++ ++ /* By not making the gentime core emulate periodic mode on top ++ * of oneshot, we get lower overhead and improved accuracy. ++ */ ++ tc_clkevt2_clk_enable(d); ++ ++ /* slow clock, count up to RC, then irq and restart */ ++ writel(ATMEL_TC_CMR_TCLK(4) | ATMEL_TC_CMR_WAVE | ++ ATMEL_TC_CMR_WAVESEL_UPRC, ++ tce.base + ATMEL_TC_CMR(tce.channels[0])); ++ writel((32768 + HZ / 2) / HZ, tce.base + ATMEL_TC_RC(tce.channels[0])); ++ ++ /* Enable clock and interrupts on RC compare */ ++ writel(ATMEL_TC_CPCS, tce.base + ATMEL_TC_IER(tce.channels[0])); ++ writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, ++ tce.base + ATMEL_TC_CCR(tce.channels[0])); ++ ++ return 0; ++} ++ ++static int tc_clkevt2_next_event(unsigned long delta, ++ struct clock_event_device *d) ++{ ++ writel(delta, tce.base + ATMEL_TC_RC(tce.channels[0])); ++ writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, ++ tce.base + ATMEL_TC_CCR(tce.channels[0])); ++ ++ return 0; ++} ++ ++static irqreturn_t tc_clkevt2_irq(int irq, void *handle) ++{ ++ unsigned int sr; ++ ++ sr = readl(tce.base + ATMEL_TC_SR(tce.channels[0])); ++ if (sr & ATMEL_TC_CPCS) { ++ tce.clkevt.event_handler(&tce.clkevt); ++ return IRQ_HANDLED; ++ } ++ ++ return IRQ_NONE; ++} ++ ++static void tc_clkevt2_suspend(struct clock_event_device *d) ++{ ++ tce.cache[0].cmr = readl(tce.base + ATMEL_TC_CMR(tce.channels[0])); ++ tce.cache[0].imr = readl(tce.base + ATMEL_TC_IMR(tce.channels[0])); ++ tce.cache[0].rc = readl(tce.base + ATMEL_TC_RC(tce.channels[0])); ++ tce.cache[0].clken = !!(readl(tce.base + ATMEL_TC_SR(tce.channels[0])) & ++ ATMEL_TC_CLKSTA); ++} ++ ++static void tc_clkevt2_resume(struct clock_event_device *d) ++{ ++ /* Restore registers for the channel, RA and RB are not used */ ++ writel(tce.cache[0].cmr, tc.base + ATMEL_TC_CMR(tce.channels[0])); ++ writel(tce.cache[0].rc, tc.base + ATMEL_TC_RC(tce.channels[0])); ++ writel(0, tc.base + ATMEL_TC_RA(tce.channels[0])); ++ writel(0, tc.base + ATMEL_TC_RB(tce.channels[0])); ++ /* Disable all the interrupts */ ++ writel(0xff, tc.base + ATMEL_TC_IDR(tce.channels[0])); ++ /* Reenable interrupts that were enabled before suspending */ ++ writel(tce.cache[0].imr, tc.base + ATMEL_TC_IER(tce.channels[0])); ++ ++ /* Start the clock if it was used */ ++ if (tce.cache[0].clken) ++ writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, ++ tc.base + ATMEL_TC_CCR(tce.channels[0])); ++} ++ ++static int __init tc_clkevt_register(struct device_node *node, ++ struct regmap *regmap, void __iomem *base, ++ int channel, int irq, int bits) ++{ ++ int ret; ++ struct clk *slow_clk; ++ ++ tce.regmap = regmap; ++ tce.base = base; ++ tce.channels[0] = channel; ++ tce.irq = irq; ++ ++ slow_clk = of_clk_get_by_name(node->parent, "slow_clk"); ++ if (IS_ERR(slow_clk)) ++ return PTR_ERR(slow_clk); ++ ++ ret = clk_prepare_enable(slow_clk); ++ if (ret) ++ return ret; ++ ++ tce.clk[0] = tcb_clk_get(node, tce.channels[0]); ++ if (IS_ERR(tce.clk[0])) { ++ ret = PTR_ERR(tce.clk[0]); ++ goto err_slow; ++ } ++ ++ snprintf(tce.name, sizeof(tce.name), "%s:%d", ++ kbasename(node->parent->full_name), channel); ++ tce.clkevt.cpumask = cpumask_of(0); ++ tce.clkevt.name = tce.name; ++ tce.clkevt.set_next_event = tc_clkevt2_next_event, ++ tce.clkevt.set_state_shutdown = tc_clkevt2_shutdown, ++ tce.clkevt.set_state_periodic = tc_clkevt2_set_periodic, ++ tce.clkevt.set_state_oneshot = tc_clkevt2_set_oneshot, ++ tce.clkevt.suspend = tc_clkevt2_suspend, ++ tce.clkevt.resume = tc_clkevt2_resume, ++ tce.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; ++ tce.clkevt.rating = 140; ++ ++ /* try to enable clk to avoid future errors in mode change */ ++ ret = clk_prepare_enable(tce.clk[0]); ++ if (ret) ++ goto err_slow; ++ clk_disable(tce.clk[0]); ++ ++ clockevents_config_and_register(&tce.clkevt, 32768, 1, ++ CLOCKSOURCE_MASK(bits)); ++ ++ ret = request_irq(tce.irq, tc_clkevt2_irq, IRQF_TIMER | IRQF_SHARED, ++ tce.clkevt.name, &tce); ++ if (ret) ++ goto err_clk; ++ ++ tce.registered = true; ++ ++ return 0; ++ ++err_clk: ++ clk_unprepare(tce.clk[0]); ++err_slow: ++ clk_disable_unprepare(slow_clk); ++ ++ return ret; ++} ++ + /* + * Clocksource and clockevent using the same channel(s) + */ +@@ -363,7 +560,7 @@ static int __init tcb_clksrc_init(struct device_node *node) + int irq, err, chan1 = -1; + unsigned bits; + +- if (tc.registered) ++ if (tc.registered && tce.registered) + return -ENODEV; + + /* +@@ -395,12 +592,22 @@ static int __init tcb_clksrc_init(struct device_node *node) + return irq; + } + ++ if (tc.registered) ++ return tc_clkevt_register(node, regmap, tcb_base, channel, irq, ++ bits); ++ + if (bits == 16) { + of_property_read_u32_index(node, "reg", 1, &chan1); + if (chan1 == -1) { +- pr_err("%s: clocksource needs two channels\n", +- node->parent->full_name); +- return -EINVAL; ++ if (tce.registered) { ++ pr_err("%s: clocksource needs two channels\n", ++ node->parent->full_name); ++ return -EINVAL; ++ } else { ++ return tc_clkevt_register(node, regmap, ++ tcb_base, channel, ++ irq, bits); ++ } + } + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0004-clocksource-drivers-atmel-pit-make-option-silent.patch b/debian/patches-rt/0004-clocksource-drivers-atmel-pit-make-option-silent.patch new file mode 100644 index 000000000..c506f1465 --- /dev/null +++ b/debian/patches-rt/0004-clocksource-drivers-atmel-pit-make-option-silent.patch @@ -0,0 +1,36 @@ +From e8dbe99dae1d78e7094d87357a904c2e30572fc3 Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:21 +0200 +Subject: [PATCH 004/347] clocksource/drivers: atmel-pit: make option silent +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +To conform with the other option, make the ATMEL_PIT option silent so it +can be selected from the platform + +Tested-by: Alexander Dahl <ada@thorsis.com> +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/clocksource/Kconfig | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig +index 9422ea3a52ac..1dbd40f6c01d 100644 +--- a/drivers/clocksource/Kconfig ++++ b/drivers/clocksource/Kconfig +@@ -405,8 +405,11 @@ config ARMV7M_SYSTICK + This options enables support for the ARMv7M system timer unit + + config ATMEL_PIT ++ bool "Microchip ARM Periodic Interval Timer (PIT)" if COMPILE_TEST + select TIMER_OF if OF +- def_bool SOC_AT91SAM9 || SOC_SAMA5 ++ help ++ This enables build of clocksource and clockevent driver for ++ the integrated PIT in Microchip ARM SoCs. + + config ATMEL_ST + bool "Atmel ST timer support" if COMPILE_TEST +-- +2.36.1 + diff --git a/debian/patches-rt/0005-ARM-at91-Implement-clocksource-selection.patch b/debian/patches-rt/0005-ARM-at91-Implement-clocksource-selection.patch new file mode 100644 index 000000000..561c3c162 --- /dev/null +++ b/debian/patches-rt/0005-ARM-at91-Implement-clocksource-selection.patch @@ -0,0 +1,55 @@ +From 4071bcd6aab6d507cb20f20cfc9f111cfa5a406f Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:22 +0200 +Subject: [PATCH 005/347] ARM: at91: Implement clocksource selection +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Allow selecting and unselecting the PIT clocksource driver so it doesn't +have to be compile when unused. + +Tested-by: Alexander Dahl <ada@thorsis.com> +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/mach-at91/Kconfig | 25 +++++++++++++++++++++++++ + 1 file changed, 25 insertions(+) + +diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig +index 903f23c309df..fa493a86e2bb 100644 +--- a/arch/arm/mach-at91/Kconfig ++++ b/arch/arm/mach-at91/Kconfig +@@ -107,6 +107,31 @@ config SOC_AT91SAM9 + AT91SAM9X35 + AT91SAM9XE + ++comment "Clocksource driver selection" ++ ++config ATMEL_CLOCKSOURCE_PIT ++ bool "Periodic Interval Timer (PIT) support" ++ depends on SOC_AT91SAM9 || SOC_SAMA5 ++ default SOC_AT91SAM9 || SOC_SAMA5 ++ select ATMEL_PIT ++ help ++ Select this to get a clocksource based on the Atmel Periodic Interval ++ Timer. It has a relatively low resolution and the TC Block clocksource ++ should be preferred. ++ ++config ATMEL_CLOCKSOURCE_TCB ++ bool "Timer Counter Blocks (TCB) support" ++ depends on SOC_AT91RM9200 || SOC_AT91SAM9 || SOC_SAMA5 || COMPILE_TEST ++ default SOC_AT91RM9200 || SOC_AT91SAM9 || SOC_SAMA5 ++ depends on !ATMEL_TCLIB ++ select ATMEL_ARM_TCB_CLKSRC ++ help ++ Select this to get a high precision clocksource based on a ++ TC block with a 5+ MHz base clock rate. ++ On platforms with 16-bit counters, two timer channels are combined ++ to make a single 32-bit timer. ++ It can also be used as a clock event device supporting oneshot mode. ++ + config HAVE_AT91_UTMI + bool + +-- +2.36.1 + diff --git a/debian/patches-rt/0006-ARM-configs-at91-use-new-TCB-timer-driver.patch b/debian/patches-rt/0006-ARM-configs-at91-use-new-TCB-timer-driver.patch new file mode 100644 index 000000000..8d93a1f2d --- /dev/null +++ b/debian/patches-rt/0006-ARM-configs-at91-use-new-TCB-timer-driver.patch @@ -0,0 +1,43 @@ +From 39aa1ef47843270c427a2c8f4d787ca29d944140 Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:23 +0200 +Subject: [PATCH 006/347] ARM: configs: at91: use new TCB timer driver +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Unselecting ATMEL_TCLIB switches the TCB timer driver from tcb_clksrc to +timer-atmel-tcb. + +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/configs/at91_dt_defconfig | 1 - + arch/arm/configs/sama5_defconfig | 1 - + 2 files changed, 2 deletions(-) + +diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig +index e4b1be66b3f5..09f262e59fef 100644 +--- a/arch/arm/configs/at91_dt_defconfig ++++ b/arch/arm/configs/at91_dt_defconfig +@@ -64,7 +64,6 @@ CONFIG_BLK_DEV_LOOP=y + CONFIG_BLK_DEV_RAM=y + CONFIG_BLK_DEV_RAM_COUNT=4 + CONFIG_BLK_DEV_RAM_SIZE=8192 +-CONFIG_ATMEL_TCLIB=y + CONFIG_ATMEL_SSC=y + CONFIG_SCSI=y + CONFIG_BLK_DEV_SD=y +diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig +index 2080025556b5..f2bbc6339ca6 100644 +--- a/arch/arm/configs/sama5_defconfig ++++ b/arch/arm/configs/sama5_defconfig +@@ -75,7 +75,6 @@ CONFIG_BLK_DEV_LOOP=y + CONFIG_BLK_DEV_RAM=y + CONFIG_BLK_DEV_RAM_COUNT=4 + CONFIG_BLK_DEV_RAM_SIZE=8192 +-CONFIG_ATMEL_TCLIB=y + CONFIG_ATMEL_SSC=y + CONFIG_EEPROM_AT24=y + CONFIG_SCSI=y +-- +2.36.1 + diff --git a/debian/patches-rt/0007-ARM-configs-at91-unselect-PIT.patch b/debian/patches-rt/0007-ARM-configs-at91-unselect-PIT.patch new file mode 100644 index 000000000..a2e5c5d39 --- /dev/null +++ b/debian/patches-rt/0007-ARM-configs-at91-unselect-PIT.patch @@ -0,0 +1,44 @@ +From 4e7ea26bf6a9dc935b6db1085488bde47f63f68e Mon Sep 17 00:00:00 2001 +From: Alexandre Belloni <alexandre.belloni@bootlin.com> +Date: Thu, 13 Sep 2018 13:30:24 +0200 +Subject: [PATCH 007/347] ARM: configs: at91: unselect PIT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The PIT is not required anymore to successfully boot and may actually harm +in case preempt-rt is used because the PIT interrupt is shared. +Disable it so the TCB clocksource is used. + +Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/configs/at91_dt_defconfig | 1 + + arch/arm/configs/sama5_defconfig | 1 + + 2 files changed, 2 insertions(+) + +diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig +index 09f262e59fef..f4b253bd05ed 100644 +--- a/arch/arm/configs/at91_dt_defconfig ++++ b/arch/arm/configs/at91_dt_defconfig +@@ -19,6 +19,7 @@ CONFIG_ARCH_MULTI_V5=y + CONFIG_ARCH_AT91=y + CONFIG_SOC_AT91RM9200=y + CONFIG_SOC_AT91SAM9=y ++# CONFIG_ATMEL_CLOCKSOURCE_PIT is not set + CONFIG_AEABI=y + CONFIG_UACCESS_WITH_MEMCPY=y + CONFIG_ZBOOT_ROM_TEXT=0x0 +diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig +index f2bbc6339ca6..be92871ab155 100644 +--- a/arch/arm/configs/sama5_defconfig ++++ b/arch/arm/configs/sama5_defconfig +@@ -20,6 +20,7 @@ CONFIG_ARCH_AT91=y + CONFIG_SOC_SAMA5D2=y + CONFIG_SOC_SAMA5D3=y + CONFIG_SOC_SAMA5D4=y ++# CONFIG_ATMEL_CLOCKSOURCE_PIT is not set + CONFIG_AEABI=y + CONFIG_UACCESS_WITH_MEMCPY=y + CONFIG_ZBOOT_ROM_TEXT=0x0 +-- +2.36.1 + diff --git a/debian/patches-rt/0008-irqchip-gic-v3-its-Move-pending-table-allocation-to-.patch b/debian/patches-rt/0008-irqchip-gic-v3-its-Move-pending-table-allocation-to-.patch new file mode 100644 index 000000000..ebeacb299 --- /dev/null +++ b/debian/patches-rt/0008-irqchip-gic-v3-its-Move-pending-table-allocation-to-.patch @@ -0,0 +1,171 @@ +From c85652aaa06764a7d68d8da3c6e146cf2650bff8 Mon Sep 17 00:00:00 2001 +From: Marc Zyngier <marc.zyngier@arm.com> +Date: Fri, 27 Jul 2018 13:38:54 +0100 +Subject: [PATCH 008/347] irqchip/gic-v3-its: Move pending table allocation to + init time +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/irqchip/irq-gic-v3-its.c | 80 +++++++++++++++++++----------- + include/linux/irqchip/arm-gic-v3.h | 1 + + 2 files changed, 53 insertions(+), 28 deletions(-) + +diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c +index 86334aef4bd0..f51970b6b51a 100644 +--- a/drivers/irqchip/irq-gic-v3-its.c ++++ b/drivers/irqchip/irq-gic-v3-its.c +@@ -178,6 +178,7 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock); + static DEFINE_IDA(its_vpeid_ida); + + #define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist)) ++#define gic_data_rdist_cpu(cpu) (per_cpu_ptr(gic_rdists->rdist, cpu)) + #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) + #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K) + +@@ -1658,7 +1659,7 @@ static void its_free_prop_table(struct page *prop_page) + get_order(LPI_PROPBASE_SZ)); + } + +-static int __init its_alloc_lpi_tables(void) ++static int __init its_alloc_lpi_prop_table(void) + { + phys_addr_t paddr; + +@@ -2006,30 +2007,47 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base) + return val; + } + +-static void its_cpu_init_lpis(void) ++static int __init allocate_lpi_tables(void) + { +- void __iomem *rbase = gic_data_rdist_rd_base(); +- struct page *pend_page; +- u64 val, tmp; ++ int err, cpu; + +- /* If we didn't allocate the pending table yet, do it now */ +- pend_page = gic_data_rdist()->pend_page; +- if (!pend_page) { +- phys_addr_t paddr; ++ err = its_alloc_lpi_prop_table(); ++ if (err) ++ return err; ++ ++ /* ++ * We allocate all the pending tables anyway, as we may have a ++ * mix of RDs that have had LPIs enabled, and some that ++ * don't. We'll free the unused ones as each CPU comes online. ++ */ ++ for_each_possible_cpu(cpu) { ++ struct page *pend_page; + + pend_page = its_allocate_pending_table(GFP_NOWAIT); + if (!pend_page) { +- pr_err("Failed to allocate PENDBASE for CPU%d\n", +- smp_processor_id()); +- return; ++ pr_err("Failed to allocate PENDBASE for CPU%d\n", cpu); ++ return -ENOMEM; + } + +- paddr = page_to_phys(pend_page); +- pr_info("CPU%d: using LPI pending table @%pa\n", +- smp_processor_id(), &paddr); +- gic_data_rdist()->pend_page = pend_page; ++ gic_data_rdist_cpu(cpu)->pend_page = pend_page; + } + ++ return 0; ++} ++ ++static void its_cpu_init_lpis(void) ++{ ++ void __iomem *rbase = gic_data_rdist_rd_base(); ++ struct page *pend_page; ++ phys_addr_t paddr; ++ u64 val, tmp; ++ ++ if (gic_data_rdist()->lpi_enabled) ++ return; ++ ++ pend_page = gic_data_rdist()->pend_page; ++ paddr = page_to_phys(pend_page); ++ + /* set PROPBASE */ + val = (page_to_phys(gic_rdists->prop_page) | + GICR_PROPBASER_InnerShareable | +@@ -2105,6 +2123,10 @@ static void its_cpu_init_lpis(void) + + /* Make sure the GIC has seen the above */ + dsb(sy); ++ gic_data_rdist()->lpi_enabled = true; ++ pr_info("GICv3: CPU%d: using LPI pending table @%pa\n", ++ smp_processor_id(), ++ &paddr); + } + + static void its_cpu_init_collection(struct its_node *its) +@@ -3584,16 +3606,6 @@ static int redist_disable_lpis(void) + u64 timeout = USEC_PER_SEC; + u64 val; + +- /* +- * If coming via a CPU hotplug event, we don't need to disable +- * LPIs before trying to re-enable them. They are already +- * configured and all is well in the world. Detect this case +- * by checking the allocation of the pending table for the +- * current CPU. +- */ +- if (gic_data_rdist()->pend_page) +- return 0; +- + if (!gic_rdists_supports_plpis()) { + pr_info("CPU%d: LPIs not supported\n", smp_processor_id()); + return -ENXIO; +@@ -3603,7 +3615,18 @@ static int redist_disable_lpis(void) + if (!(val & GICR_CTLR_ENABLE_LPIS)) + return 0; + +- pr_warn("CPU%d: Booted with LPIs enabled, memory probably corrupted\n", ++ /* ++ * If coming via a CPU hotplug event, we don't need to disable ++ * LPIs before trying to re-enable them. They are already ++ * configured and all is well in the world. ++ */ ++ if (gic_data_rdist()->lpi_enabled) ++ return 0; ++ ++ /* ++ * From that point on, we only try to do some damage control. ++ */ ++ pr_warn("GICv3: CPU%d: Booted with LPIs enabled, memory probably corrupted\n", + smp_processor_id()); + add_taint(TAINT_CRAP, LOCKDEP_STILL_OK); + +@@ -3859,7 +3882,8 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists, + } + + gic_rdists = rdists; +- err = its_alloc_lpi_tables(); ++ ++ err = allocate_lpi_tables(); + if (err) + return err; + +diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h +index 1d21e98d6854..fdddead7e307 100644 +--- a/include/linux/irqchip/arm-gic-v3.h ++++ b/include/linux/irqchip/arm-gic-v3.h +@@ -585,6 +585,7 @@ struct rdists { + void __iomem *rd_base; + struct page *pend_page; + phys_addr_t phys_base; ++ bool lpi_enabled; + } __percpu *rdist; + struct page *prop_page; + u64 flags; +-- +2.36.1 + diff --git a/debian/patches-rt/0009-kthread-convert-worker-lock-to-raw-spinlock.patch b/debian/patches-rt/0009-kthread-convert-worker-lock-to-raw-spinlock.patch new file mode 100644 index 000000000..2d5f5508f --- /dev/null +++ b/debian/patches-rt/0009-kthread-convert-worker-lock-to-raw-spinlock.patch @@ -0,0 +1,203 @@ +From 3384b42fd998f06c79b4536609c48e3147adb1eb Mon Sep 17 00:00:00 2001 +From: Julia Cartwright <julia@ni.com> +Date: Fri, 28 Sep 2018 21:03:51 +0000 +Subject: [PATCH 009/347] kthread: convert worker lock to raw spinlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In order to enable the queuing of kthread work items from hardirq +context even when PREEMPT_RT_FULL is enabled, convert the worker +spin_lock to a raw_spin_lock. + +This is only acceptable to do because the work performed under the lock +is well-bounded and minimal. + +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: Guenter Roeck <linux@roeck-us.net> +Reported-and-tested-by: Steffen Trumtrar <s.trumtrar@pengutronix.de> +Reported-by: Tim Sander <tim@krieglstein.org> +Signed-off-by: Julia Cartwright <julia@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/kthread.h | 2 +- + kernel/kthread.c | 42 ++++++++++++++++++++--------------------- + 2 files changed, 22 insertions(+), 22 deletions(-) + +diff --git a/include/linux/kthread.h b/include/linux/kthread.h +index 72308c38e06c..e0498e46d642 100644 +--- a/include/linux/kthread.h ++++ b/include/linux/kthread.h +@@ -88,7 +88,7 @@ enum { + + struct kthread_worker { + unsigned int flags; +- spinlock_t lock; ++ raw_spinlock_t lock; + struct list_head work_list; + struct list_head delayed_work_list; + struct task_struct *task; +diff --git a/kernel/kthread.c b/kernel/kthread.c +index 9750f4f7f901..c8cf4731ced8 100644 +--- a/kernel/kthread.c ++++ b/kernel/kthread.c +@@ -637,7 +637,7 @@ void __kthread_init_worker(struct kthread_worker *worker, + struct lock_class_key *key) + { + memset(worker, 0, sizeof(struct kthread_worker)); +- spin_lock_init(&worker->lock); ++ raw_spin_lock_init(&worker->lock); + lockdep_set_class_and_name(&worker->lock, key, name); + INIT_LIST_HEAD(&worker->work_list); + INIT_LIST_HEAD(&worker->delayed_work_list); +@@ -679,21 +679,21 @@ int kthread_worker_fn(void *worker_ptr) + + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); +- spin_lock_irq(&worker->lock); ++ raw_spin_lock_irq(&worker->lock); + worker->task = NULL; +- spin_unlock_irq(&worker->lock); ++ raw_spin_unlock_irq(&worker->lock); + return 0; + } + + work = NULL; +- spin_lock_irq(&worker->lock); ++ raw_spin_lock_irq(&worker->lock); + if (!list_empty(&worker->work_list)) { + work = list_first_entry(&worker->work_list, + struct kthread_work, node); + list_del_init(&work->node); + } + worker->current_work = work; +- spin_unlock_irq(&worker->lock); ++ raw_spin_unlock_irq(&worker->lock); + + if (work) { + __set_current_state(TASK_RUNNING); +@@ -850,12 +850,12 @@ bool kthread_queue_work(struct kthread_worker *worker, + bool ret = false; + unsigned long flags; + +- spin_lock_irqsave(&worker->lock, flags); ++ raw_spin_lock_irqsave(&worker->lock, flags); + if (!queuing_blocked(worker, work)) { + kthread_insert_work(worker, work, &worker->work_list); + ret = true; + } +- spin_unlock_irqrestore(&worker->lock, flags); ++ raw_spin_unlock_irqrestore(&worker->lock, flags); + return ret; + } + EXPORT_SYMBOL_GPL(kthread_queue_work); +@@ -881,7 +881,7 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) + if (WARN_ON_ONCE(!worker)) + return; + +- spin_lock(&worker->lock); ++ raw_spin_lock(&worker->lock); + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); + +@@ -891,7 +891,7 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) + if (!work->canceling) + kthread_insert_work(worker, work, &worker->work_list); + +- spin_unlock(&worker->lock); ++ raw_spin_unlock(&worker->lock); + } + EXPORT_SYMBOL(kthread_delayed_work_timer_fn); + +@@ -947,14 +947,14 @@ bool kthread_queue_delayed_work(struct kthread_worker *worker, + unsigned long flags; + bool ret = false; + +- spin_lock_irqsave(&worker->lock, flags); ++ raw_spin_lock_irqsave(&worker->lock, flags); + + if (!queuing_blocked(worker, work)) { + __kthread_queue_delayed_work(worker, dwork, delay); + ret = true; + } + +- spin_unlock_irqrestore(&worker->lock, flags); ++ raw_spin_unlock_irqrestore(&worker->lock, flags); + return ret; + } + EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); +@@ -990,7 +990,7 @@ void kthread_flush_work(struct kthread_work *work) + if (!worker) + return; + +- spin_lock_irq(&worker->lock); ++ raw_spin_lock_irq(&worker->lock); + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); + +@@ -1002,7 +1002,7 @@ void kthread_flush_work(struct kthread_work *work) + else + noop = true; + +- spin_unlock_irq(&worker->lock); ++ raw_spin_unlock_irq(&worker->lock); + + if (!noop) + wait_for_completion(&fwork.done); +@@ -1030,9 +1030,9 @@ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, + * any queuing is blocked by setting the canceling counter. + */ + work->canceling++; +- spin_unlock_irqrestore(&worker->lock, *flags); ++ raw_spin_unlock_irqrestore(&worker->lock, *flags); + del_timer_sync(&dwork->timer); +- spin_lock_irqsave(&worker->lock, *flags); ++ raw_spin_lock_irqsave(&worker->lock, *flags); + work->canceling--; + } + +@@ -1094,7 +1094,7 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, + unsigned long flags; + int ret = false; + +- spin_lock_irqsave(&worker->lock, flags); ++ raw_spin_lock_irqsave(&worker->lock, flags); + + /* Do not bother with canceling when never queued. */ + if (!work->worker) +@@ -1123,7 +1123,7 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, + fast_queue: + __kthread_queue_delayed_work(worker, dwork, delay); + out: +- spin_unlock_irqrestore(&worker->lock, flags); ++ raw_spin_unlock_irqrestore(&worker->lock, flags); + return ret; + } + EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); +@@ -1137,7 +1137,7 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) + if (!worker) + goto out; + +- spin_lock_irqsave(&worker->lock, flags); ++ raw_spin_lock_irqsave(&worker->lock, flags); + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); + +@@ -1154,13 +1154,13 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) + * In the meantime, block any queuing by setting the canceling counter. + */ + work->canceling++; +- spin_unlock_irqrestore(&worker->lock, flags); ++ raw_spin_unlock_irqrestore(&worker->lock, flags); + kthread_flush_work(work); +- spin_lock_irqsave(&worker->lock, flags); ++ raw_spin_lock_irqsave(&worker->lock, flags); + work->canceling--; + + out_fast: +- spin_unlock_irqrestore(&worker->lock, flags); ++ raw_spin_unlock_irqrestore(&worker->lock, flags); + out: + return ret; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0010-crypto-caam-qi-simplify-CGR-allocation-freeing.patch b/debian/patches-rt/0010-crypto-caam-qi-simplify-CGR-allocation-freeing.patch new file mode 100644 index 000000000..924b46797 --- /dev/null +++ b/debian/patches-rt/0010-crypto-caam-qi-simplify-CGR-allocation-freeing.patch @@ -0,0 +1,140 @@ +From c752e0c3b941130c799de323f647d8547ff04a81 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Horia=20Geant=C4=83?= <horia.geanta@nxp.com> +Date: Mon, 8 Oct 2018 14:09:37 +0300 +Subject: [PATCH 010/347] crypto: caam/qi - simplify CGR allocation, freeing +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[Upstream commit 29e83c757006fd751966bdc53392bb22d74179c6] + +CGRs (Congestion Groups) have to be freed by the same CPU that +initialized them. +This is why currently the driver takes special measures; however, using +set_cpus_allowed_ptr() is incorrect - as reported by Sebastian. + +Instead of the generic solution of replacing set_cpus_allowed_ptr() with +work_on_cpu_safe(), we use the qman_delete_cgr_safe() QBMan API instead +of qman_delete_cgr() - which internally takes care of proper CGR +deletion. + +Link: https://lkml.kernel.org/r/20181005125443.dfhd2asqktm22ney@linutronix.de +Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Horia Geantă <horia.geanta@nxp.com> +Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> +--- + drivers/crypto/caam/qi.c | 43 ++++------------------------------------ + drivers/crypto/caam/qi.h | 2 +- + 2 files changed, 5 insertions(+), 40 deletions(-) + +diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c +index 67f7f8c42c93..b84e6c8b1e13 100644 +--- a/drivers/crypto/caam/qi.c ++++ b/drivers/crypto/caam/qi.c +@@ -83,13 +83,6 @@ EXPORT_SYMBOL(caam_congested); + static u64 times_congested; + #endif + +-/* +- * CPU from where the module initialised. This is required because QMan driver +- * requires CGRs to be removed from same CPU from where they were originally +- * allocated. +- */ +-static int mod_init_cpu; +- + /* + * This is a a cache of buffers, from which the users of CAAM QI driver + * can allocate short (CAAM_QI_MEMCACHE_SIZE) buffers. It's faster than +@@ -492,12 +485,11 @@ void caam_drv_ctx_rel(struct caam_drv_ctx *drv_ctx) + } + EXPORT_SYMBOL(caam_drv_ctx_rel); + +-int caam_qi_shutdown(struct device *qidev) ++void caam_qi_shutdown(struct device *qidev) + { +- int i, ret; ++ int i; + struct caam_qi_priv *priv = dev_get_drvdata(qidev); + const cpumask_t *cpus = qman_affine_cpus(); +- struct cpumask old_cpumask = current->cpus_allowed; + + for_each_cpu(i, cpus) { + struct napi_struct *irqtask; +@@ -510,26 +502,12 @@ int caam_qi_shutdown(struct device *qidev) + dev_err(qidev, "Rsp FQ kill failed, cpu: %d\n", i); + } + +- /* +- * QMan driver requires CGRs to be deleted from same CPU from where they +- * were instantiated. Hence we get the module removal execute from the +- * same CPU from where it was originally inserted. +- */ +- set_cpus_allowed_ptr(current, get_cpu_mask(mod_init_cpu)); +- +- ret = qman_delete_cgr(&priv->cgr); +- if (ret) +- dev_err(qidev, "Deletion of CGR failed: %d\n", ret); +- else +- qman_release_cgrid(priv->cgr.cgrid); ++ qman_delete_cgr_safe(&priv->cgr); ++ qman_release_cgrid(priv->cgr.cgrid); + + kmem_cache_destroy(qi_cache); + +- /* Now that we're done with the CGRs, restore the cpus allowed mask */ +- set_cpus_allowed_ptr(current, &old_cpumask); +- + platform_device_unregister(priv->qi_pdev); +- return ret; + } + + static void cgr_cb(struct qman_portal *qm, struct qman_cgr *cgr, int congested) +@@ -718,22 +696,11 @@ int caam_qi_init(struct platform_device *caam_pdev) + struct device *ctrldev = &caam_pdev->dev, *qidev; + struct caam_drv_private *ctrlpriv; + const cpumask_t *cpus = qman_affine_cpus(); +- struct cpumask old_cpumask = current->cpus_allowed; + static struct platform_device_info qi_pdev_info = { + .name = "caam_qi", + .id = PLATFORM_DEVID_NONE + }; + +- /* +- * QMAN requires CGRs to be removed from same CPU+portal from where it +- * was originally allocated. Hence we need to note down the +- * initialisation CPU and use the same CPU for module exit. +- * We select the first CPU to from the list of portal owning CPUs. +- * Then we pin module init to this CPU. +- */ +- mod_init_cpu = cpumask_first(cpus); +- set_cpus_allowed_ptr(current, get_cpu_mask(mod_init_cpu)); +- + qi_pdev_info.parent = ctrldev; + qi_pdev_info.dma_mask = dma_get_mask(ctrldev); + qi_pdev = platform_device_register_full(&qi_pdev_info); +@@ -795,8 +762,6 @@ int caam_qi_init(struct platform_device *caam_pdev) + return -ENOMEM; + } + +- /* Done with the CGRs; restore the cpus allowed mask */ +- set_cpus_allowed_ptr(current, &old_cpumask); + #ifdef CONFIG_DEBUG_FS + debugfs_create_file("qi_congested", 0444, ctrlpriv->ctl, + ×_congested, &caam_fops_u64_ro); +diff --git a/drivers/crypto/caam/qi.h b/drivers/crypto/caam/qi.h +index 357b69f57072..b6c8acc30853 100644 +--- a/drivers/crypto/caam/qi.h ++++ b/drivers/crypto/caam/qi.h +@@ -174,7 +174,7 @@ int caam_drv_ctx_update(struct caam_drv_ctx *drv_ctx, u32 *sh_desc); + void caam_drv_ctx_rel(struct caam_drv_ctx *drv_ctx); + + int caam_qi_init(struct platform_device *pdev); +-int caam_qi_shutdown(struct device *dev); ++void caam_qi_shutdown(struct device *dev); + + /** + * qi_cache_alloc - Allocate buffers from CAAM-QI cache +-- +2.36.1 + diff --git a/debian/patches-rt/0011-sched-fair-Robustify-CFS-bandwidth-timer-locking.patch b/debian/patches-rt/0011-sched-fair-Robustify-CFS-bandwidth-timer-locking.patch new file mode 100644 index 000000000..e250e2aa4 --- /dev/null +++ b/debian/patches-rt/0011-sched-fair-Robustify-CFS-bandwidth-timer-locking.patch @@ -0,0 +1,148 @@ +From e19a4689e9aa66751202caf5aeade89ecb118f2c Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Mon, 7 Jan 2019 13:52:31 +0100 +Subject: [PATCH 011/347] sched/fair: Robustify CFS-bandwidth timer locking +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Traditionally hrtimer callbacks were run with IRQs disabled, but with +the introduction of HRTIMER_MODE_SOFT it is possible they run from +SoftIRQ context, which does _NOT_ have IRQs disabled. + +Allow for the CFS bandwidth timers (period_timer and slack_timer) to +be ran from SoftIRQ context; this entails removing the assumption that +IRQs are already disabled from the locking. + +While mainline doesn't strictly need this, -RT forces all timers not +explicitly marked with MODE_HARD into MODE_SOFT and trips over this. +And marking these timers as MODE_HARD doesn't make sense as they're +not required for RT operation and can potentially be quite expensive. + +Cc: Ingo Molnar <mingo@redhat.com> +Cc: Thomas Gleixner <tglx@linutronix.de> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reported-by: Tom Putzeys <tom.putzeys@be.atlascopco.com> +Tested-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> +Link: https://lkml.kernel.org/r/20190107125231.GE14122@hirez.programming.kicks-ass.net +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/fair.c | 30 ++++++++++++++++-------------- + 1 file changed, 16 insertions(+), 14 deletions(-) + +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 84e7efda98da..e84a056f783f 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -4597,7 +4597,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) + struct rq *rq = rq_of(cfs_rq); + struct rq_flags rf; + +- rq_lock(rq, &rf); ++ rq_lock_irqsave(rq, &rf); + if (!cfs_rq_throttled(cfs_rq)) + goto next; + +@@ -4616,7 +4616,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) + unthrottle_cfs_rq(cfs_rq); + + next: +- rq_unlock(rq, &rf); ++ rq_unlock_irqrestore(rq, &rf); + + if (!remaining) + break; +@@ -4632,7 +4632,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) + * period the timer is deactivated until scheduling resumes; cfs_b->idle is + * used to track this state. + */ +-static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) ++static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) + { + u64 runtime; + int throttled; +@@ -4672,10 +4672,10 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) + while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) { + runtime = cfs_b->runtime; + cfs_b->distribute_running = 1; +- raw_spin_unlock(&cfs_b->lock); ++ raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + /* we can't nest cfs_b->lock while distributing bandwidth */ + runtime = distribute_cfs_runtime(cfs_b, runtime); +- raw_spin_lock(&cfs_b->lock); ++ raw_spin_lock_irqsave(&cfs_b->lock, flags); + + cfs_b->distribute_running = 0; + throttled = !list_empty(&cfs_b->throttled_cfs_rq); +@@ -4783,16 +4783,17 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) + static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) + { + u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); ++ unsigned long flags; + + /* confirm we're still not at a refresh boundary */ +- raw_spin_lock(&cfs_b->lock); ++ raw_spin_lock_irqsave(&cfs_b->lock, flags); + if (cfs_b->distribute_running) { +- raw_spin_unlock(&cfs_b->lock); ++ raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + return; + } + + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { +- raw_spin_unlock(&cfs_b->lock); ++ raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + return; + } + +@@ -4802,17 +4803,17 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) + if (runtime) + cfs_b->distribute_running = 1; + +- raw_spin_unlock(&cfs_b->lock); ++ raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + + if (!runtime) + return; + + runtime = distribute_cfs_runtime(cfs_b, runtime); + +- raw_spin_lock(&cfs_b->lock); ++ raw_spin_lock_irqsave(&cfs_b->lock, flags); + cfs_b->runtime -= min(runtime, cfs_b->runtime); + cfs_b->distribute_running = 0; +- raw_spin_unlock(&cfs_b->lock); ++ raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + } + + /* +@@ -4892,11 +4893,12 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) + { + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, period_timer); ++ unsigned long flags; + int overrun; + int idle = 0; + int count = 0; + +- raw_spin_lock(&cfs_b->lock); ++ raw_spin_lock_irqsave(&cfs_b->lock, flags); + for (;;) { + overrun = hrtimer_forward_now(timer, cfs_b->period); + if (!overrun) +@@ -4932,11 +4934,11 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) + count = 0; + } + +- idle = do_sched_cfs_period_timer(cfs_b, overrun); ++ idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); + } + if (idle) + cfs_b->period_active = 0; +- raw_spin_unlock(&cfs_b->lock); ++ raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0012-arm-Convert-arm-boot_lock-to-raw.patch b/debian/patches-rt/0012-arm-Convert-arm-boot_lock-to-raw.patch new file mode 100644 index 000000000..2ad1e225e --- /dev/null +++ b/debian/patches-rt/0012-arm-Convert-arm-boot_lock-to-raw.patch @@ -0,0 +1,432 @@ +From 794763d18a168f7eb7dd98185021fd74a3d0778f Mon Sep 17 00:00:00 2001 +From: Frank Rowand <frank.rowand@am.sony.com> +Date: Mon, 19 Sep 2011 14:51:14 -0700 +Subject: [PATCH 012/347] arm: Convert arm boot_lock to raw +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The arm boot_lock is used by the secondary processor startup code. The locking +task is the idle thread, which has idle->sched_class == &idle_sched_class. +idle_sched_class->enqueue_task == NULL, so if the idle task blocks on the +lock, the attempt to wake it when the lock becomes available will fail: + +try_to_wake_up() + ... + activate_task() + enqueue_task() + p->sched_class->enqueue_task(rq, p, flags) + +Fix by converting boot_lock to a raw spin lock. + +Signed-off-by: Frank Rowand <frank.rowand@am.sony.com> +Link: http://lkml.kernel.org/r/4E77B952.3010606@am.sony.com +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Tested-by: Tony Lindgren <tony@atomide.com> +Acked-by: Krzysztof Kozlowski <krzk@kernel.org> +Tested-by: Krzysztof Kozlowski <krzk@kernel.org> [Exynos5422 Linaro PM-QA] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/mach-exynos/platsmp.c | 12 ++++++------ + arch/arm/mach-hisi/platmcpm.c | 22 +++++++++++----------- + arch/arm/mach-omap2/omap-smp.c | 10 +++++----- + arch/arm/mach-prima2/platsmp.c | 10 +++++----- + arch/arm/mach-qcom/platsmp.c | 10 +++++----- + arch/arm/mach-spear/platsmp.c | 10 +++++----- + arch/arm/mach-sti/platsmp.c | 10 +++++----- + arch/arm/plat-versatile/platsmp.c | 10 +++++----- + 8 files changed, 47 insertions(+), 47 deletions(-) + +diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c +index 6a1e682371b3..17dca0ff336e 100644 +--- a/arch/arm/mach-exynos/platsmp.c ++++ b/arch/arm/mach-exynos/platsmp.c +@@ -239,7 +239,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void exynos_secondary_init(unsigned int cpu) + { +@@ -252,8 +252,8 @@ static void exynos_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr) +@@ -317,7 +317,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -344,7 +344,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) + + if (timeout == 0) { + printk(KERN_ERR "cpu1 power enable failed"); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return -ETIMEDOUT; + } + } +@@ -390,7 +390,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) + * calibrations, then wait for it to finish + */ + fail: +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? ret : 0; + } +diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c +index f66815c3dd07..00524abd963f 100644 +--- a/arch/arm/mach-hisi/platmcpm.c ++++ b/arch/arm/mach-hisi/platmcpm.c +@@ -61,7 +61,7 @@ + + static void __iomem *sysctrl, *fabric; + static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + static u32 fabric_phys_addr; + /* + * [0]: bootwrapper physical address +@@ -113,7 +113,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle) + if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) + return -EINVAL; + +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + + if (hip04_cpu_table[cluster][cpu]) + goto out; +@@ -147,7 +147,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle) + + out: + hip04_cpu_table[cluster][cpu]++; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + + return 0; + } +@@ -162,11 +162,11 @@ static void hip04_cpu_die(unsigned int l_cpu) + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + hip04_cpu_table[cluster][cpu]--; + if (hip04_cpu_table[cluster][cpu] == 1) { + /* A power_up request went ahead of us. */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return; + } else if (hip04_cpu_table[cluster][cpu] > 1) { + pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); +@@ -174,7 +174,7 @@ static void hip04_cpu_die(unsigned int l_cpu) + } + + last_man = hip04_cluster_is_down(cluster); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + if (last_man) { + /* Since it's Cortex A15, disable L2 prefetching. */ + asm volatile( +@@ -203,7 +203,7 @@ static int hip04_cpu_kill(unsigned int l_cpu) + cpu >= HIP04_MAX_CPUS_PER_CLUSTER); + + count = TIMEOUT_MSEC / POLL_MSEC; +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + for (tries = 0; tries < count; tries++) { + if (hip04_cpu_table[cluster][cpu]) + goto err; +@@ -211,10 +211,10 @@ static int hip04_cpu_kill(unsigned int l_cpu) + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_WFI_STATUS(cpu)) + break; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + /* Wait for clean L2 when the whole cluster is down. */ + msleep(POLL_MSEC); +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + } + if (tries >= count) + goto err; +@@ -231,10 +231,10 @@ static int hip04_cpu_kill(unsigned int l_cpu) + goto err; + if (hip04_cluster_is_down(cluster)) + hip04_set_snoop_filter(cluster, 0); +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 1; + err: +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 0; + } + #endif +diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c +index 1c73694c871a..ac4d2f030b87 100644 +--- a/arch/arm/mach-omap2/omap-smp.c ++++ b/arch/arm/mach-omap2/omap-smp.c +@@ -69,7 +69,7 @@ static const struct omap_smp_config omap5_cfg __initconst = { + .startup_addr = omap5_secondary_startup, + }; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __iomem *omap4_get_scu_base(void) + { +@@ -177,8 +177,8 @@ static void omap4_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -191,7 +191,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Update the AuxCoreBoot0 with boot state for secondary core. +@@ -270,7 +270,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) + * Now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return 0; + } +diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c +index 75ef5d4be554..c17c86e5d860 100644 +--- a/arch/arm/mach-prima2/platsmp.c ++++ b/arch/arm/mach-prima2/platsmp.c +@@ -22,7 +22,7 @@ + + static void __iomem *clk_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sirfsoc_secondary_init(unsigned int cpu) + { +@@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static const struct of_device_id clk_ids[] = { +@@ -75,7 +75,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle) + /* make sure write buffer is drained */ + mb(); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -107,7 +107,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle) + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c +index 5494c9e0c909..e8ce157d3548 100644 +--- a/arch/arm/mach-qcom/platsmp.c ++++ b/arch/arm/mach-qcom/platsmp.c +@@ -46,7 +46,7 @@ + + extern void secondary_startup_arm(void); + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + #ifdef CONFIG_HOTPLUG_CPU + static void qcom_cpu_die(unsigned int cpu) +@@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int scss_release_secondary(unsigned int cpu) +@@ -284,7 +284,7 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int)) + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Send the secondary CPU a soft interrupt, thereby causing +@@ -297,7 +297,7 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int)) + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return ret; + } +diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c +index 39038a03836a..6da5c93872bf 100644 +--- a/arch/arm/mach-spear/platsmp.c ++++ b/arch/arm/mach-spear/platsmp.c +@@ -32,7 +32,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void __iomem *scu_base = IOMEM(VA_SCU_BASE); + +@@ -47,8 +47,8 @@ static void spear13xx_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -59,7 +59,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -84,7 +84,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c +index 231f19e17436..a3419b7003e6 100644 +--- a/arch/arm/mach-sti/platsmp.c ++++ b/arch/arm/mach-sti/platsmp.c +@@ -35,7 +35,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sti_secondary_init(unsigned int cpu) + { +@@ -48,8 +48,8 @@ static void sti_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -60,7 +60,7 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -91,7 +91,7 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c +index c2366510187a..6b60f582b738 100644 +--- a/arch/arm/plat-versatile/platsmp.c ++++ b/arch/arm/plat-versatile/platsmp.c +@@ -32,7 +32,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void versatile_secondary_init(unsigned int cpu) + { +@@ -45,8 +45,8 @@ void versatile_secondary_init(unsigned int cpu) + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -57,7 +57,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * This is really belt and braces; we hold unintended secondary +@@ -87,7 +87,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0013-x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch b/debian/patches-rt/0013-x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch new file mode 100644 index 000000000..5c222cfd8 --- /dev/null +++ b/debian/patches-rt/0013-x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch @@ -0,0 +1,101 @@ +From 39f1823e7293c365e7abdc19c1b15d772fc0dbc1 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 17 Jul 2018 18:25:31 +0200 +Subject: [PATCH 013/347] x86/ioapic: Don't let setaffinity unmask threaded EOI + interrupt too early +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There is an issue with threaded interrupts which are marked ONESHOT +and using the fasteoi handler. + + if (IS_ONESHOT()) + mask_irq(); + + .... + .... + + cond_unmask_eoi_irq() + chip->irq_eoi(); + +So if setaffinity is pending then the interrupt will be moved and then +unmasked, which is wrong as it should be kept masked up to the point where +the threaded handler finished. It's not a real problem, the interrupt will +just be able to fire before the threaded handler has finished, though the irq +masked state will be wrong for a bit. + +The patch below should cure the issue. It also renames the horribly +misnomed functions so it becomes clear what they are supposed to do. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +[bigeasy: add the body of the patch, use the same functions in both + ifdef paths (spotted by Andy Shevchenko)] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/kernel/apic/io_apic.c | 16 ++++++++-------- + 1 file changed, 8 insertions(+), 8 deletions(-) + +diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c +index 677508baf95a..b1a7f453415f 100644 +--- a/arch/x86/kernel/apic/io_apic.c ++++ b/arch/x86/kernel/apic/io_apic.c +@@ -1732,7 +1732,7 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) + return false; + } + +-static inline bool ioapic_irqd_mask(struct irq_data *data) ++static inline bool ioapic_prepare_move(struct irq_data *data) + { + /* If we are moving the IRQ we need to mask it */ + if (unlikely(irqd_is_setaffinity_pending(data))) { +@@ -1743,9 +1743,9 @@ static inline bool ioapic_irqd_mask(struct irq_data *data) + return false; + } + +-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) ++static inline void ioapic_finish_move(struct irq_data *data, bool moveit) + { +- if (unlikely(masked)) { ++ if (unlikely(moveit)) { + /* Only migrate the irq if the ack has been received. + * + * On rare occasions the broadcast level triggered ack gets +@@ -1780,11 +1780,11 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) + } + } + #else +-static inline bool ioapic_irqd_mask(struct irq_data *data) ++static inline bool ioapic_prepare_move(struct irq_data *data) + { + return false; + } +-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) ++static inline void ioapic_finish_move(struct irq_data *data, bool moveit) + { + } + #endif +@@ -1793,11 +1793,11 @@ static void ioapic_ack_level(struct irq_data *irq_data) + { + struct irq_cfg *cfg = irqd_cfg(irq_data); + unsigned long v; +- bool masked; ++ bool moveit; + int i; + + irq_complete_move(cfg); +- masked = ioapic_irqd_mask(irq_data); ++ moveit = ioapic_prepare_move(irq_data); + + /* + * It appears there is an erratum which affects at least version 0x11 +@@ -1852,7 +1852,7 @@ static void ioapic_ack_level(struct irq_data *irq_data) + eoi_ioapic_pin(cfg->vector, irq_data->chip_data); + } + +- ioapic_irqd_unmask(irq_data, masked); ++ ioapic_finish_move(irq_data, moveit); + } + + static void ioapic_ir_ack_level(struct irq_data *irq_data) +-- +2.36.1 + diff --git a/debian/patches-rt/0014-cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch b/debian/patches-rt/0014-cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch new file mode 100644 index 000000000..6d9213b5b --- /dev/null +++ b/debian/patches-rt/0014-cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch @@ -0,0 +1,50 @@ +From 9cbe69b64cc03234634926f56a219900edb90899 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 3 Jul 2018 18:19:48 +0200 +Subject: [PATCH 014/347] cgroup: use irqsave in cgroup_rstat_flush_locked() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +All callers of cgroup_rstat_flush_locked() acquire cgroup_rstat_lock +either with spin_lock_irq() or spin_lock_irqsave(). +cgroup_rstat_flush_locked() itself acquires cgroup_rstat_cpu_lock which +is a raw_spin_lock. This lock is also acquired in cgroup_rstat_updated() +in IRQ context and therefore requires _irqsave() locking suffix in +cgroup_rstat_flush_locked(). +Since there is no difference between spin_lock_t and raw_spin_lock_t +on !RT lockdep does not complain here. On RT lockdep complains because +the interrupts were not disabled here and a deadlock is possible. + +Acquire the raw_spin_lock_t with disabled interrupts. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/cgroup/rstat.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c +index d0ed410b4127..3c949c46c6b3 100644 +--- a/kernel/cgroup/rstat.c ++++ b/kernel/cgroup/rstat.c +@@ -149,8 +149,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, + cpu); + struct cgroup *pos = NULL; ++ unsigned long flags; + +- raw_spin_lock(cpu_lock); ++ raw_spin_lock_irqsave(cpu_lock, flags); + while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + struct cgroup_subsys_state *css; + +@@ -162,7 +163,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) + css->ss->css_rstat_flush(css, cpu); + rcu_read_unlock(); + } +- raw_spin_unlock(cpu_lock); ++ raw_spin_unlock_irqrestore(cpu_lock, flags); + + /* if @may_sleep, play nice and yield if necessary */ + if (may_sleep && (need_resched() || +-- +2.36.1 + diff --git a/debian/patches-rt/0015-fscache-initialize-cookie-hash-table-raw-spinlocks.patch b/debian/patches-rt/0015-fscache-initialize-cookie-hash-table-raw-spinlocks.patch new file mode 100644 index 000000000..1aef96ead --- /dev/null +++ b/debian/patches-rt/0015-fscache-initialize-cookie-hash-table-raw-spinlocks.patch @@ -0,0 +1,64 @@ +From efd6f660496f4a70e788963b4b914791eed32c42 Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Tue, 3 Jul 2018 13:34:30 -0500 +Subject: [PATCH 015/347] fscache: initialize cookie hash table raw spinlocks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The fscache cookie mechanism uses a hash table of hlist_bl_head structures. The +PREEMPT_RT patcheset adds a raw spinlock to this structure and so on PREEMPT_RT +the structures get used uninitialized, causing warnings about bad magic numbers +when spinlock debugging is turned on. + +Use the init function for fscache cookies. + +Signed-off-by: Clark Williams <williams@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/fscache/cookie.c | 8 ++++++++ + fs/fscache/main.c | 1 + + include/linux/fscache.h | 1 + + 3 files changed, 10 insertions(+) + +diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c +index 2ff05adfc22a..b2b9a85a4ba5 100644 +--- a/fs/fscache/cookie.c ++++ b/fs/fscache/cookie.c +@@ -950,3 +950,11 @@ int __fscache_check_consistency(struct fscache_cookie *cookie, + return -ESTALE; + } + EXPORT_SYMBOL(__fscache_check_consistency); ++ ++void __init fscache_cookie_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < (1 << fscache_cookie_hash_shift) - 1; i++) ++ INIT_HLIST_BL_HEAD(&fscache_cookie_hash[i]); ++} +diff --git a/fs/fscache/main.c b/fs/fscache/main.c +index aa49234e9520..95a0798de381 100644 +--- a/fs/fscache/main.c ++++ b/fs/fscache/main.c +@@ -188,6 +188,7 @@ static int __init fscache_init(void) + ret = -ENOMEM; + goto error_cookie_jar; + } ++ fscache_cookie_init(); + + fscache_root = kobject_create_and_add("fscache", kernel_kobj); + if (!fscache_root) +diff --git a/include/linux/fscache.h b/include/linux/fscache.h +index 84b90a79d75a..87a9330eafa2 100644 +--- a/include/linux/fscache.h ++++ b/include/linux/fscache.h +@@ -230,6 +230,7 @@ extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, + extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); + extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, + bool (*)(void *), void *); ++extern void fscache_cookie_init(void); + + /** + * fscache_register_netfs - Register a filesystem as desiring caching services +-- +2.36.1 + diff --git a/debian/patches-rt/0016-Drivers-hv-vmbus-include-header-for-get_irq_regs.patch b/debian/patches-rt/0016-Drivers-hv-vmbus-include-header-for-get_irq_regs.patch new file mode 100644 index 000000000..bdbfbb7d7 --- /dev/null +++ b/debian/patches-rt/0016-Drivers-hv-vmbus-include-header-for-get_irq_regs.patch @@ -0,0 +1,40 @@ +From 8feaa1571755787a4012cb74fbb937f8c436939e Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 29 Aug 2018 21:59:04 +0200 +Subject: [PATCH 016/347] Drivers: hv: vmbus: include header for get_irq_regs() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On !RT the header file get_irq_regs() gets pulled in via other header files. On +RT it does not and the build fails: + + drivers/hv/vmbus_drv.c:975 implicit declaration of function ‘get_irq_regs’ [-Werror=implicit-function-declaration] + drivers/hv/hv.c:115 implicit declaration of function ‘get_irq_regs’ [-Werror=implicit-function-declaration] + +Add the header file for get_irq_regs() in a common header so it used by +vmbus_drv.c by hv.c for their get_irq_regs() usage. + +Reported-by: Bernhard Landauer <oberon@manjaro.org> +Reported-by: Ralf Ramsauer <ralf.ramsauer@oth-regensburg.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/hv/hyperv_vmbus.h | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h +index c4ad51889024..14af29c0ea1c 100644 +--- a/drivers/hv/hyperv_vmbus.h ++++ b/drivers/hv/hyperv_vmbus.h +@@ -32,6 +32,7 @@ + #include <linux/atomic.h> + #include <linux/hyperv.h> + #include <linux/interrupt.h> ++#include <linux/irq.h> + + #include "hv_trace.h" + +-- +2.36.1 + diff --git a/debian/patches-rt/0017-percpu-include-irqflags.h-for-raw_local_irq_save.patch b/debian/patches-rt/0017-percpu-include-irqflags.h-for-raw_local_irq_save.patch new file mode 100644 index 000000000..0b8f0b08b --- /dev/null +++ b/debian/patches-rt/0017-percpu-include-irqflags.h-for-raw_local_irq_save.patch @@ -0,0 +1,33 @@ +From 8af0819c5a38547ea3f6b09ff350092c21c13e73 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 11 Oct 2018 16:39:59 +0200 +Subject: [PATCH 017/347] percpu: include irqflags.h for raw_local_irq_save() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The header percpu.h header file is using raw_local_irq_save() but does +not include irqflags.h for its definition. It compiles because the +header file is included via an other header file. +On -RT the build fails because raw_local_irq_save() is not defined. + +Include irqflags.h in percpu.h. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/asm-generic/percpu.h | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h +index 1817a8415a5e..942d64c0476e 100644 +--- a/include/asm-generic/percpu.h ++++ b/include/asm-generic/percpu.h +@@ -5,6 +5,7 @@ + #include <linux/compiler.h> + #include <linux/threads.h> + #include <linux/percpu-defs.h> ++#include <linux/irqflags.h> + + #ifdef CONFIG_SMP + +-- +2.36.1 + diff --git a/debian/patches-rt/0018-efi-Allow-efi-runtime.patch b/debian/patches-rt/0018-efi-Allow-efi-runtime.patch new file mode 100644 index 000000000..b31c9ad25 --- /dev/null +++ b/debian/patches-rt/0018-efi-Allow-efi-runtime.patch @@ -0,0 +1,32 @@ +From f62b786096a94d0a49da8d0c97bc1d5b6213e6a6 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 26 Jul 2018 15:06:10 +0200 +Subject: [PATCH 018/347] efi: Allow efi=runtime +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In case the option "efi=noruntime" is default at built-time, the user +could overwrite its sate by `efi=runtime' and allow it again. + +Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/firmware/efi/efi.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c +index 7098744f9276..e89932f1ae65 100644 +--- a/drivers/firmware/efi/efi.c ++++ b/drivers/firmware/efi/efi.c +@@ -113,6 +113,9 @@ static int __init parse_efi_cmdline(char *str) + if (parse_option_str(str, "noruntime")) + disable_runtime = true; + ++ if (parse_option_str(str, "runtime")) ++ disable_runtime = false; ++ + return 0; + } + early_param("efi", parse_efi_cmdline); +-- +2.36.1 + diff --git a/debian/patches-rt/0019-x86-efi-drop-task_lock-from-efi_switch_mm.patch b/debian/patches-rt/0019-x86-efi-drop-task_lock-from-efi_switch_mm.patch new file mode 100644 index 000000000..cc5aa4db1 --- /dev/null +++ b/debian/patches-rt/0019-x86-efi-drop-task_lock-from-efi_switch_mm.patch @@ -0,0 +1,55 @@ +From dc7eee776061da65e8343c30c068e3862a192bef Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 24 Jul 2018 14:48:55 +0200 +Subject: [PATCH 019/347] x86/efi: drop task_lock() from efi_switch_mm() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +efi_switch_mm() is a wrapper around switch_mm() which saves current's +->active_mm, sets the requests mm as ->active_mm and invokes +switch_mm(). +I don't think that task_lock() is required during that procedure. It +protects ->mm which isn't changed here. + +It needs to be mentioned that during the whole procedure (switch to +EFI's mm and back) the preemption needs to be disabled. A context switch +at this point would reset the cr3 value based on current->mm. Also, this +function may not be invoked at the same time on a different CPU because +it would overwrite the efi_scratch.prev_mm information. + +Remove task_lock() and also update the comment to reflect it. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/platform/efi/efi_64.c | 10 ++++------ + 1 file changed, 4 insertions(+), 6 deletions(-) + +diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c +index 77d05b56089a..cd7e4bfb43cf 100644 +--- a/arch/x86/platform/efi/efi_64.c ++++ b/arch/x86/platform/efi/efi_64.c +@@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void) + + /* + * Makes the calling thread switch to/from efi_mm context. Can be used +- * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well +- * as during efi runtime calls i.e current->active_mm == current_mm. +- * We are not mm_dropping()/mm_grabbing() any mm, because we are not +- * losing/creating any references. ++ * in a kernel thread and user context. Preemption needs to remain disabled ++ * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm ++ * can not change under us. ++ * It should be ensured that there are no concurent calls to this function. + */ + void efi_switch_mm(struct mm_struct *mm) + { +- task_lock(current); + efi_scratch.prev_mm = current->active_mm; + current->active_mm = mm; + switch_mm(efi_scratch.prev_mm, mm, NULL); +- task_unlock(current); + } + + #ifdef CONFIG_EFI_MIXED +-- +2.36.1 + diff --git a/debian/patches-rt/0020-arm64-KVM-compute_layout-before-altenates-are-applie.patch b/debian/patches-rt/0020-arm64-KVM-compute_layout-before-altenates-are-applie.patch new file mode 100644 index 000000000..9ebe84c33 --- /dev/null +++ b/debian/patches-rt/0020-arm64-KVM-compute_layout-before-altenates-are-applie.patch @@ -0,0 +1,83 @@ +From 67b8d4ae9c2cf65bccbb75f2099bca2da5e78de5 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 26 Jul 2018 09:13:42 +0200 +Subject: [PATCH 020/347] arm64: KVM: compute_layout before altenates are + applied +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +compute_layout() is invoked as part of an alternative fixup under +stop_machine() and needs a sleeping lock as part of get_random_long(). + +Invoke compute_layout() before the alternatives are applied. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm64/include/asm/alternative.h | 6 ++++++ + arch/arm64/kernel/alternative.c | 1 + + arch/arm64/kvm/va_layout.c | 7 +------ + 3 files changed, 8 insertions(+), 6 deletions(-) + +diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h +index 4fbbcdda70d7..99b215602a1a 100644 +--- a/arch/arm64/include/asm/alternative.h ++++ b/arch/arm64/include/asm/alternative.h +@@ -35,6 +35,12 @@ void apply_alternatives_module(void *start, size_t length); + static inline void apply_alternatives_module(void *start, size_t length) { } + #endif + ++#ifdef CONFIG_KVM_ARM_HOST ++void kvm_compute_layout(void); ++#else ++static inline void kvm_compute_layout(void) { } ++#endif ++ + #define ALTINSTR_ENTRY(feature) \ + " .word 661b - .\n" /* label */ \ + " .word 663f - .\n" /* new instruction */ \ +diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c +index 3747c8d87bdb..75ccb5b279a2 100644 +--- a/arch/arm64/kernel/alternative.c ++++ b/arch/arm64/kernel/alternative.c +@@ -212,6 +212,7 @@ static int __apply_alternatives_multi_stop(void *unused) + void __init apply_alternatives_all(void) + { + /* better not try code patching on a live SMP system */ ++ kvm_compute_layout(); + stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask); + } + +diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c +index c712a7376bc1..792da0e125de 100644 +--- a/arch/arm64/kvm/va_layout.c ++++ b/arch/arm64/kvm/va_layout.c +@@ -33,7 +33,7 @@ static u8 tag_lsb; + static u64 tag_val; + static u64 va_mask; + +-static void compute_layout(void) ++__init void kvm_compute_layout(void) + { + phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start); + u64 hyp_va_msb; +@@ -121,8 +121,6 @@ void __init kvm_update_va_mask(struct alt_instr *alt, + + BUG_ON(nr_inst != 5); + +- if (!has_vhe() && !va_mask) +- compute_layout(); + + for (i = 0; i < nr_inst; i++) { + u32 rd, rn, insn, oinsn; +@@ -167,9 +165,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt, + return; + } + +- if (!va_mask) +- compute_layout(); +- + /* + * Compute HYP VA by using the same computation as kern_hyp_va() + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0021-of-allocate-free-phandle-cache-outside-of-the-devtre.patch b/debian/patches-rt/0021-of-allocate-free-phandle-cache-outside-of-the-devtre.patch new file mode 100644 index 000000000..9b53b3722 --- /dev/null +++ b/debian/patches-rt/0021-of-allocate-free-phandle-cache-outside-of-the-devtre.patch @@ -0,0 +1,103 @@ +From aafa075abaa80a17d9ac105e72ab235ddb573aac Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 31 Aug 2018 14:16:30 +0200 +Subject: [PATCH 021/347] of: allocate / free phandle cache outside of the + devtree_lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The phandle cache code allocates memory while holding devtree_lock which +is a raw_spinlock_t. Memory allocation (and free()) is not possible on +RT while a raw_spinlock_t is held. +Invoke the kfree() and kcalloc() while the lock is dropped. + +Cc: Rob Herring <robh+dt@kernel.org> +Cc: Frank Rowand <frowand.list@gmail.com> +Cc: devicetree@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/of/base.c | 19 +++++++++++++------ + 1 file changed, 13 insertions(+), 6 deletions(-) + +diff --git a/drivers/of/base.c b/drivers/of/base.c +index f0dbb7ad88cf..c59b30bab0e0 100644 +--- a/drivers/of/base.c ++++ b/drivers/of/base.c +@@ -130,31 +130,34 @@ static u32 phandle_cache_mask; + /* + * Caller must hold devtree_lock. + */ +-static void __of_free_phandle_cache(void) ++static struct device_node** __of_free_phandle_cache(void) + { + u32 cache_entries = phandle_cache_mask + 1; + u32 k; ++ struct device_node **shadow; + + if (!phandle_cache) +- return; ++ return NULL; + + for (k = 0; k < cache_entries; k++) + of_node_put(phandle_cache[k]); + +- kfree(phandle_cache); ++ shadow = phandle_cache; + phandle_cache = NULL; ++ return shadow; + } + + int of_free_phandle_cache(void) + { + unsigned long flags; ++ struct device_node **shadow; + + raw_spin_lock_irqsave(&devtree_lock, flags); + +- __of_free_phandle_cache(); ++ shadow = __of_free_phandle_cache(); + + raw_spin_unlock_irqrestore(&devtree_lock, flags); +- ++ kfree(shadow); + return 0; + } + #if !defined(CONFIG_MODULES) +@@ -189,10 +192,11 @@ void of_populate_phandle_cache(void) + u32 cache_entries; + struct device_node *np; + u32 phandles = 0; ++ struct device_node **shadow; + + raw_spin_lock_irqsave(&devtree_lock, flags); + +- __of_free_phandle_cache(); ++ shadow = __of_free_phandle_cache(); + + for_each_of_allnodes(np) + if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) +@@ -200,12 +204,14 @@ void of_populate_phandle_cache(void) + + if (!phandles) + goto out; ++ raw_spin_unlock_irqrestore(&devtree_lock, flags); + + cache_entries = roundup_pow_of_two(phandles); + phandle_cache_mask = cache_entries - 1; + + phandle_cache = kcalloc(cache_entries, sizeof(*phandle_cache), + GFP_ATOMIC); ++ raw_spin_lock_irqsave(&devtree_lock, flags); + if (!phandle_cache) + goto out; + +@@ -217,6 +223,7 @@ void of_populate_phandle_cache(void) + + out: + raw_spin_unlock_irqrestore(&devtree_lock, flags); ++ kfree(shadow); + } + + void __init of_core_init(void) +-- +2.36.1 + diff --git a/debian/patches-rt/0022-mm-kasan-make-quarantine_lock-a-raw_spinlock_t.patch b/debian/patches-rt/0022-mm-kasan-make-quarantine_lock-a-raw_spinlock_t.patch new file mode 100644 index 000000000..0d6a6458f --- /dev/null +++ b/debian/patches-rt/0022-mm-kasan-make-quarantine_lock-a-raw_spinlock_t.patch @@ -0,0 +1,98 @@ +From 4613446aa7e0744f1f4895714184b4a5608153bd Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Tue, 18 Sep 2018 10:29:31 -0500 +Subject: [PATCH 022/347] mm/kasan: make quarantine_lock a raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The static lock quarantine_lock is used in quarantine.c to protect the +quarantine queue datastructures. It is taken inside quarantine queue +manipulation routines (quarantine_put(), quarantine_reduce() and +quarantine_remove_cache()), with IRQs disabled. +This is not a problem on a stock kernel but is problematic on an RT +kernel where spin locks are sleeping spinlocks, which can sleep and can +not be acquired with disabled interrupts. + +Convert the quarantine_lock to a raw spinlock_t. The usage of +quarantine_lock is confined to quarantine.c and the work performed while +the lock is held is limited. + +Signed-off-by: Clark Williams <williams@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/kasan/quarantine.c | 18 +++++++++--------- + 1 file changed, 9 insertions(+), 9 deletions(-) + +diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c +index 3a8ddf8baf7d..b209dbaefde8 100644 +--- a/mm/kasan/quarantine.c ++++ b/mm/kasan/quarantine.c +@@ -103,7 +103,7 @@ static int quarantine_head; + static int quarantine_tail; + /* Total size of all objects in global_quarantine across all batches. */ + static unsigned long quarantine_size; +-static DEFINE_SPINLOCK(quarantine_lock); ++static DEFINE_RAW_SPINLOCK(quarantine_lock); + DEFINE_STATIC_SRCU(remove_cache_srcu); + + /* Maximum size of the global queue. */ +@@ -190,7 +190,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) + if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { + qlist_move_all(q, &temp); + +- spin_lock(&quarantine_lock); ++ raw_spin_lock(&quarantine_lock); + WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); + qlist_move_all(&temp, &global_quarantine[quarantine_tail]); + if (global_quarantine[quarantine_tail].bytes >= +@@ -203,7 +203,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) + if (new_tail != quarantine_head) + quarantine_tail = new_tail; + } +- spin_unlock(&quarantine_lock); ++ raw_spin_unlock(&quarantine_lock); + } + + local_irq_restore(flags); +@@ -230,7 +230,7 @@ void quarantine_reduce(void) + * expected case). + */ + srcu_idx = srcu_read_lock(&remove_cache_srcu); +- spin_lock_irqsave(&quarantine_lock, flags); ++ raw_spin_lock_irqsave(&quarantine_lock, flags); + + /* + * Update quarantine size in case of hotplug. Allocate a fraction of +@@ -254,7 +254,7 @@ void quarantine_reduce(void) + quarantine_head = 0; + } + +- spin_unlock_irqrestore(&quarantine_lock, flags); ++ raw_spin_unlock_irqrestore(&quarantine_lock, flags); + + qlist_free_all(&to_free, NULL); + srcu_read_unlock(&remove_cache_srcu, srcu_idx); +@@ -310,17 +310,17 @@ void quarantine_remove_cache(struct kmem_cache *cache) + */ + on_each_cpu(per_cpu_remove_cache, cache, 1); + +- spin_lock_irqsave(&quarantine_lock, flags); ++ raw_spin_lock_irqsave(&quarantine_lock, flags); + for (i = 0; i < QUARANTINE_BATCHES; i++) { + if (qlist_empty(&global_quarantine[i])) + continue; + qlist_move_cache(&global_quarantine[i], &to_free, cache); + /* Scanning whole quarantine can take a while. */ +- spin_unlock_irqrestore(&quarantine_lock, flags); ++ raw_spin_unlock_irqrestore(&quarantine_lock, flags); + cond_resched(); +- spin_lock_irqsave(&quarantine_lock, flags); ++ raw_spin_lock_irqsave(&quarantine_lock, flags); + } +- spin_unlock_irqrestore(&quarantine_lock, flags); ++ raw_spin_unlock_irqrestore(&quarantine_lock, flags); + + qlist_free_all(&to_free, cache); + +-- +2.36.1 + diff --git a/debian/patches-rt/0023-EXP-rcu-Revert-expedited-GP-parallelization-cleverne.patch b/debian/patches-rt/0023-EXP-rcu-Revert-expedited-GP-parallelization-cleverne.patch new file mode 100644 index 000000000..576cef248 --- /dev/null +++ b/debian/patches-rt/0023-EXP-rcu-Revert-expedited-GP-parallelization-cleverne.patch @@ -0,0 +1,51 @@ +From 502b30371ea2dc6a5ba4ec401468053719944d93 Mon Sep 17 00:00:00 2001 +From: "Paul E. McKenney" <paulmck@linux.ibm.com> +Date: Mon, 29 Oct 2018 11:53:01 +0100 +Subject: [PATCH 023/347] EXP rcu: Revert expedited GP parallelization + cleverness +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +(Commit 258ba8e089db23f760139266c232f01bad73f85c from linux-rcu) + +This commit reverts a series of commits starting with fcc635436501 ("rcu: +Make expedited GPs handle CPU 0 being offline") and its successors, thus +queueing each rcu_node structure's expedited grace-period initialization +work on the first CPU of that rcu_node structure. + +Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/rcu/tree_exp.h | 9 +-------- + 1 file changed, 1 insertion(+), 8 deletions(-) + +diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h +index 72770a551c24..ac6d6fdf5783 100644 +--- a/kernel/rcu/tree_exp.h ++++ b/kernel/rcu/tree_exp.h +@@ -472,7 +472,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) + static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, + smp_call_func_t func) + { +- int cpu; + struct rcu_node *rnp; + + trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); +@@ -494,13 +493,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, + continue; + } + INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); +- preempt_disable(); +- cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask); +- /* If all offline, queue the work on an unbound CPU. */ +- if (unlikely(cpu > rnp->grphi)) +- cpu = WORK_CPU_UNBOUND; +- queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); +- preempt_enable(); ++ queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work); + rnp->exp_need_flush = true; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0024-kmemleak-Turn-kmemleak_lock-to-raw-spinlock-on-RT.patch b/debian/patches-rt/0024-kmemleak-Turn-kmemleak_lock-to-raw-spinlock-on-RT.patch new file mode 100644 index 000000000..13c6dabe9 --- /dev/null +++ b/debian/patches-rt/0024-kmemleak-Turn-kmemleak_lock-to-raw-spinlock-on-RT.patch @@ -0,0 +1,169 @@ +From 4de935e0bd7598a837928fb0d15048e5b04c5b05 Mon Sep 17 00:00:00 2001 +From: He Zhe <zhe.he@windriver.com> +Date: Wed, 19 Dec 2018 16:30:57 +0100 +Subject: [PATCH 024/347] kmemleak: Turn kmemleak_lock to raw spinlock on RT +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +kmemleak_lock, as a rwlock on RT, can possibly be held in atomic context and +causes the follow BUG. + +BUG: scheduling while atomic: migration/15/132/0x00000002 +Preemption disabled at: +[<ffffffff8c927c11>] cpu_stopper_thread+0x71/0x100 +CPU: 15 PID: 132 Comm: migration/15 Not tainted 4.19.0-rt1-preempt-rt #1 +Call Trace: + schedule+0x3d/0xe0 + __rt_spin_lock+0x26/0x30 + __write_rt_lock+0x23/0x1a0 + rt_write_lock+0x2a/0x30 + find_and_remove_object+0x1e/0x80 + delete_object_full+0x10/0x20 + kmemleak_free+0x32/0x50 + kfree+0x104/0x1f0 + intel_pmu_cpu_dying+0x67/0x70 + x86_pmu_dying_cpu+0x1a/0x30 + cpuhp_invoke_callback+0x92/0x700 + take_cpu_down+0x70/0xa0 + multi_cpu_stop+0x62/0xc0 + cpu_stopper_thread+0x79/0x100 + smpboot_thread_fn+0x20f/0x2d0 + kthread+0x121/0x140 + +And on v4.18 stable tree the following call trace, caused by grabbing +kmemleak_lock again, is also observed. + +kernel BUG at kernel/locking/rtmutex.c:1048! +CPU: 5 PID: 689 Comm: mkfs.ext4 Not tainted 4.18.16-rt9-preempt-rt #1 +Call Trace: + rt_write_lock+0x2a/0x30 + create_object+0x17d/0x2b0 + kmemleak_alloc+0x34/0x50 + kmem_cache_alloc+0x146/0x220 + mempool_alloc_slab+0x15/0x20 + mempool_alloc+0x65/0x170 + sg_pool_alloc+0x21/0x60 + sg_alloc_table_chained+0x8b/0xb0 +… + blk_flush_plug_list+0x204/0x230 + schedule+0x87/0xe0 + rt_write_lock+0x2a/0x30 + create_object+0x17d/0x2b0 + kmemleak_alloc+0x34/0x50 + __kmalloc_node+0x1cd/0x340 + alloc_request_size+0x30/0x70 + mempool_alloc+0x65/0x170 + get_request+0x4e3/0x8d0 + blk_queue_bio+0x153/0x470 + generic_make_request+0x1dc/0x3f0 + submit_bio+0x49/0x140 +… + +kmemleak is an error detecting feature. We would not expect as good performance +as without it. As there is no raw rwlock defining helpers, we turn kmemleak_lock +to a raw spinlock. + +Signed-off-by: He Zhe <zhe.he@windriver.com> +Cc: catalin.marinas@arm.com +Cc: bigeasy@linutronix.de +Cc: tglx@linutronix.de +Cc: rostedt@goodmis.org +Acked-by: Catalin Marinas <catalin.marinas@arm.com> +Link: https://lkml.kernel.org/r/1542877459-144382-1-git-send-email-zhe.he@windriver.com +Link: https://lkml.kernel.org/r/20181218150744.GB20197@arrakis.emea.arm.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/kmemleak.c | 20 ++++++++++---------- + 1 file changed, 10 insertions(+), 10 deletions(-) + +diff --git a/mm/kmemleak.c b/mm/kmemleak.c +index 639acbb91fd5..5b6718dd3a64 100644 +--- a/mm/kmemleak.c ++++ b/mm/kmemleak.c +@@ -26,7 +26,7 @@ + * + * The following locks and mutexes are used by kmemleak: + * +- * - kmemleak_lock (rwlock): protects the object_list modifications and ++ * - kmemleak_lock (raw spinlock): protects the object_list modifications and + * accesses to the object_tree_root. The object_list is the main list + * holding the metadata (struct kmemleak_object) for the allocated memory + * blocks. The object_tree_root is a red black tree used to look-up +@@ -197,7 +197,7 @@ static LIST_HEAD(gray_list); + /* search tree for object boundaries */ + static struct rb_root object_tree_root = RB_ROOT; + /* rw_lock protecting the access to object_list and object_tree_root */ +-static DEFINE_RWLOCK(kmemleak_lock); ++static DEFINE_RAW_SPINLOCK(kmemleak_lock); + + /* allocation caches for kmemleak internal data */ + static struct kmem_cache *object_cache; +@@ -491,9 +491,9 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) + struct kmemleak_object *object; + + rcu_read_lock(); +- read_lock_irqsave(&kmemleak_lock, flags); ++ raw_spin_lock_irqsave(&kmemleak_lock, flags); + object = lookup_object(ptr, alias); +- read_unlock_irqrestore(&kmemleak_lock, flags); ++ raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + + /* check whether the object is still available */ + if (object && !get_object(object)) +@@ -513,13 +513,13 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali + unsigned long flags; + struct kmemleak_object *object; + +- write_lock_irqsave(&kmemleak_lock, flags); ++ raw_spin_lock_irqsave(&kmemleak_lock, flags); + object = lookup_object(ptr, alias); + if (object) { + rb_erase(&object->rb_node, &object_tree_root); + list_del_rcu(&object->object_list); + } +- write_unlock_irqrestore(&kmemleak_lock, flags); ++ raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + + return object; + } +@@ -593,7 +593,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, + /* kernel backtrace */ + object->trace_len = __save_stack_trace(object->trace); + +- write_lock_irqsave(&kmemleak_lock, flags); ++ raw_spin_lock_irqsave(&kmemleak_lock, flags); + + min_addr = min(min_addr, ptr); + max_addr = max(max_addr, ptr + size); +@@ -624,7 +624,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, + + list_add_tail_rcu(&object->object_list, &object_list); + out: +- write_unlock_irqrestore(&kmemleak_lock, flags); ++ raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + return object; + } + +@@ -1310,7 +1310,7 @@ static void scan_block(void *_start, void *_end, + unsigned long *end = _end - (BYTES_PER_POINTER - 1); + unsigned long flags; + +- read_lock_irqsave(&kmemleak_lock, flags); ++ raw_spin_lock_irqsave(&kmemleak_lock, flags); + for (ptr = start; ptr < end; ptr++) { + struct kmemleak_object *object; + unsigned long pointer; +@@ -1367,7 +1367,7 @@ static void scan_block(void *_start, void *_end, + spin_unlock(&object->lock); + } + } +- read_unlock_irqrestore(&kmemleak_lock, flags); ++ raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + } + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0025-NFSv4-replace-seqcount_t-with-a-seqlock_t.patch b/debian/patches-rt/0025-NFSv4-replace-seqcount_t-with-a-seqlock_t.patch new file mode 100644 index 000000000..837bf02da --- /dev/null +++ b/debian/patches-rt/0025-NFSv4-replace-seqcount_t-with-a-seqlock_t.patch @@ -0,0 +1,136 @@ +From a21527d57f8b1d303be3a91b055080f68bd83448 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 28 Oct 2016 23:05:11 +0200 +Subject: [PATCH 025/347] NFSv4: replace seqcount_t with a seqlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The raw_write_seqcount_begin() in nfs4_reclaim_open_state() bugs me +because it maps to preempt_disable() in -RT which I can't have at this +point. So I took a look at the code. +It the lockdep part was removed in commit abbec2da13f0 ("NFS: Use +raw_write_seqcount_begin/end int nfs4_reclaim_open_state") because +lockdep complained. The whole seqcount thing was introduced in commit +c137afabe330 ("NFSv4: Allow the state manager to mark an open_owner as +being recovered"). +The recovery threads runs only once. +write_seqlock() does not work on !RT because it disables preemption and it the +writer side is preemptible (has to remain so despite the fact that it will +block readers). + +Reported-by: kernel test robot <xiaolong.ye@intel.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/nfs/delegation.c | 4 ++-- + fs/nfs/nfs4_fs.h | 2 +- + fs/nfs/nfs4proc.c | 4 ++-- + fs/nfs/nfs4state.c | 22 ++++++++++++++++------ + 4 files changed, 21 insertions(+), 11 deletions(-) + +diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c +index b0c0c2fc2fba..26565ba05dc1 100644 +--- a/fs/nfs/delegation.c ++++ b/fs/nfs/delegation.c +@@ -162,11 +162,11 @@ static int nfs_delegation_claim_opens(struct inode *inode, + sp = state->owner; + /* Block nfs4_proc_unlck */ + mutex_lock(&sp->so_delegreturn_mutex); +- seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); ++ seq = read_seqbegin(&sp->so_reclaim_seqlock); + err = nfs4_open_delegation_recall(ctx, state, stateid); + if (!err) + err = nfs_delegation_claim_locks(state, stateid); +- if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) ++ if (!err && read_seqretry(&sp->so_reclaim_seqlock, seq)) + err = -EAGAIN; + mutex_unlock(&sp->so_delegreturn_mutex); + put_nfs_open_context(ctx); +diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h +index 5ac7bf24c507..b15a7a2f64fe 100644 +--- a/fs/nfs/nfs4_fs.h ++++ b/fs/nfs/nfs4_fs.h +@@ -114,7 +114,7 @@ struct nfs4_state_owner { + unsigned long so_flags; + struct list_head so_states; + struct nfs_seqid_counter so_seqid; +- seqcount_t so_reclaim_seqcount; ++ seqlock_t so_reclaim_seqlock; + struct mutex so_delegreturn_mutex; + }; + +diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c +index 759c834b60fd..256a4b0c4407 100644 +--- a/fs/nfs/nfs4proc.c ++++ b/fs/nfs/nfs4proc.c +@@ -2874,7 +2874,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, + unsigned int seq; + int ret; + +- seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); ++ seq = raw_seqcount_begin(&sp->so_reclaim_seqlock.seqcount); + + ret = _nfs4_proc_open(opendata, ctx); + if (ret != 0) +@@ -2915,7 +2915,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, + + if (d_inode(dentry) == state->inode) { + nfs_inode_attach_open_context(ctx); +- if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) ++ if (read_seqretry(&sp->so_reclaim_seqlock, seq)) + nfs4_schedule_stateid_recovery(server, state); + } + +diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c +index 30576a10a1f4..e0b94cbce3bf 100644 +--- a/fs/nfs/nfs4state.c ++++ b/fs/nfs/nfs4state.c +@@ -516,7 +516,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, + nfs4_init_seqid_counter(&sp->so_seqid); + atomic_set(&sp->so_count, 1); + INIT_LIST_HEAD(&sp->so_lru); +- seqcount_init(&sp->so_reclaim_seqcount); ++ seqlock_init(&sp->so_reclaim_seqlock); + mutex_init(&sp->so_delegreturn_mutex); + return sp; + } +@@ -1584,8 +1584,12 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs + * recovering after a network partition or a reboot from a + * server that doesn't support a grace period. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ write_seqlock(&sp->so_reclaim_seqlock); ++#else ++ write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount); ++#endif + spin_lock(&sp->so_lock); +- raw_write_seqcount_begin(&sp->so_reclaim_seqcount); + restart: + list_for_each_entry(state, &sp->so_states, open_states) { + if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) +@@ -1672,14 +1676,20 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs + spin_lock(&sp->so_lock); + goto restart; + } +- raw_write_seqcount_end(&sp->so_reclaim_seqcount); + spin_unlock(&sp->so_lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ write_sequnlock(&sp->so_reclaim_seqlock); ++#else ++ write_seqcount_end(&sp->so_reclaim_seqlock.seqcount); ++#endif + return 0; + out_err: + nfs4_put_open_state(state); +- spin_lock(&sp->so_lock); +- raw_write_seqcount_end(&sp->so_reclaim_seqcount); +- spin_unlock(&sp->so_lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ write_sequnlock(&sp->so_reclaim_seqlock); ++#else ++ write_seqcount_end(&sp->so_reclaim_seqlock.seqcount); ++#endif + return status; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0026-kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch b/debian/patches-rt/0026-kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch new file mode 100644 index 000000000..f8d5cd7db --- /dev/null +++ b/debian/patches-rt/0026-kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch @@ -0,0 +1,785 @@ +From 3f55ace58d1fbc90dd64acd3564cb4713f74a45e Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 4 Apr 2017 12:50:16 +0200 +Subject: [PATCH 026/347] kernel: sched: Provide a pointer to the valid CPU + mask +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In commit 4b53a3412d66 ("sched/core: Remove the tsk_nr_cpus_allowed() +wrapper") the tsk_nr_cpus_allowed() wrapper was removed. There was not +much difference in !RT but in RT we used this to implement +migrate_disable(). Within a migrate_disable() section the CPU mask is +restricted to single CPU while the "normal" CPU mask remains untouched. + +As an alternative implementation Ingo suggested to use + struct task_struct { + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; + }; +with + t->cpus_allowed_ptr = &t->cpus_allowed; + +In -RT we then can switch the cpus_ptr to + t->cpus_allowed_ptr = &cpumask_of(task_cpu(p)); + +in a migration disabled region. The rules are simple: +- Code that 'uses' ->cpus_allowed would use the pointer. +- Code that 'modifies' ->cpus_allowed would use the direct mask. + +While converting the existing users I tried to stick with the rules +above however… well mostly CPUFREQ tries to temporary switch the CPU +mask to do something on a certain CPU and then switches the mask back it +its original value. So in theory `cpus_ptr' could or should be used. +However if this is invoked in a migration disabled region (which is not +the case because it would require something like preempt_disable() and +set_cpus_allowed_ptr() might sleep so it can't be) then the "restore" +part would restore the wrong mask. So it only looks strange and I go for +the pointer… + +Some drivers copy the cpumask without cpumask_copy() and others use +cpumask_copy but without alloc_cpumask_var(). I did not fix those as +part of this, could do this as a follow up… + +So is this the way we want it? +Is the usage of `cpus_ptr' vs `cpus_mask' for the set + restore part +(see cpufreq users) what we want? At some point it looks like they +should use a different interface for their doing. I am not sure why +switching to certain CPU is important but maybe it could be done via a +workqueue from the CPUFREQ core (so we have a comment desribing why are +doing this and a get_online_cpus() to ensure that the CPU does not go +offline too early). + +Cc: Peter Zijlstra <peterz@infradead.org> +Cc: Thomas Gleixner <tglx@linutronix.de> +Cc: Mike Galbraith <efault@gmx.de> +Cc: Ingo Molnar <mingo@elte.hu> +Cc: Rafael J. Wysocki <rjw@rjwysocki.net> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/ia64/kernel/mca.c | 2 +- + arch/mips/include/asm/switch_to.h | 4 +-- + arch/mips/kernel/mips-mt-fpaff.c | 2 +- + arch/mips/kernel/traps.c | 6 ++-- + arch/powerpc/platforms/cell/spufs/sched.c | 2 +- + arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 2 +- + drivers/infiniband/hw/hfi1/affinity.c | 6 ++-- + drivers/infiniband/hw/hfi1/sdma.c | 3 +- + drivers/infiniband/hw/qib/qib_file_ops.c | 7 ++-- + fs/proc/array.c | 4 +-- + include/linux/sched.h | 5 +-- + init/init_task.c | 3 +- + kernel/cgroup/cpuset.c | 2 +- + kernel/fork.c | 2 ++ + kernel/sched/core.c | 40 ++++++++++----------- + kernel/sched/cpudeadline.c | 4 +-- + kernel/sched/cpupri.c | 4 +-- + kernel/sched/deadline.c | 6 ++-- + kernel/sched/fair.c | 32 ++++++++--------- + kernel/sched/rt.c | 4 +-- + kernel/trace/trace_hwlat.c | 2 +- + lib/smp_processor_id.c | 2 +- + samples/trace_events/trace-events-sample.c | 2 +- + 23 files changed, 74 insertions(+), 72 deletions(-) + +diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c +index d7400b2844f1..40abc24b3b02 100644 +--- a/arch/ia64/kernel/mca.c ++++ b/arch/ia64/kernel/mca.c +@@ -1824,7 +1824,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset, + ti->cpu = cpu; + p->stack = ti; + p->state = TASK_UNINTERRUPTIBLE; +- cpumask_set_cpu(cpu, &p->cpus_allowed); ++ cpumask_set_cpu(cpu, &p->cpus_mask); + INIT_LIST_HEAD(&p->tasks); + p->parent = p->real_parent = p->group_leader = p; + INIT_LIST_HEAD(&p->children); +diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h +index e610473d61b8..1428b4febbc9 100644 +--- a/arch/mips/include/asm/switch_to.h ++++ b/arch/mips/include/asm/switch_to.h +@@ -42,7 +42,7 @@ extern struct task_struct *ll_task; + * inline to try to keep the overhead down. If we have been forced to run on + * a "CPU" with an FPU because of a previous high level of FP computation, + * but did not actually use the FPU during the most recent time-slice (CU1 +- * isn't set), we undo the restriction on cpus_allowed. ++ * isn't set), we undo the restriction on cpus_mask. + * + * We're not calling set_cpus_allowed() here, because we have no need to + * force prompt migration - we're already switching the current CPU to a +@@ -57,7 +57,7 @@ do { \ + test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) && \ + (!(KSTK_STATUS(prev) & ST0_CU1))) { \ + clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND); \ +- prev->cpus_allowed = prev->thread.user_cpus_allowed; \ ++ prev->cpus_mask = prev->thread.user_cpus_allowed; \ + } \ + next->thread.emulated_fp = 0; \ + } while(0) +diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c +index a7c0f97e4b0d..1a08428eedcf 100644 +--- a/arch/mips/kernel/mips-mt-fpaff.c ++++ b/arch/mips/kernel/mips-mt-fpaff.c +@@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, + if (retval) + goto out_unlock; + +- cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); ++ cpumask_or(&allowed, &p->thread.user_cpus_allowed, p->cpus_ptr); + cpumask_and(&mask, &allowed, cpu_active_mask); + + out_unlock: +diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c +index 0ca4185cc5e3..97bf5291130a 100644 +--- a/arch/mips/kernel/traps.c ++++ b/arch/mips/kernel/traps.c +@@ -1174,12 +1174,12 @@ static void mt_ase_fp_affinity(void) + * restricted the allowed set to exclude any CPUs with FPUs, + * we'll skip the procedure. + */ +- if (cpumask_intersects(¤t->cpus_allowed, &mt_fpu_cpumask)) { ++ if (cpumask_intersects(¤t->cpus_mask, &mt_fpu_cpumask)) { + cpumask_t tmask; + + current->thread.user_cpus_allowed +- = current->cpus_allowed; +- cpumask_and(&tmask, ¤t->cpus_allowed, ++ = current->cpus_mask; ++ cpumask_and(&tmask, ¤t->cpus_mask, + &mt_fpu_cpumask); + set_cpus_allowed_ptr(current, &tmask); + set_thread_flag(TIF_FPUBOUND); +diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c +index c9ef3c532169..cb10249b1125 100644 +--- a/arch/powerpc/platforms/cell/spufs/sched.c ++++ b/arch/powerpc/platforms/cell/spufs/sched.c +@@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_context *ctx) + * runqueue. The context will be rescheduled on the proper node + * if it is timesliced or preempted. + */ +- cpumask_copy(&ctx->cpus_allowed, ¤t->cpus_allowed); ++ cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr); + + /* Save the current cpu id for spu interrupt routing. */ + ctx->last_ran = raw_smp_processor_id(); +diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +index a999a58ca331..d6410d0740ea 100644 +--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c ++++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +@@ -1445,7 +1445,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) + * may be scheduled elsewhere and invalidate entries in the + * pseudo-locked region. + */ +- if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) { ++ if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } +diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c +index 01ed0a667928..2c62de6b5bf1 100644 +--- a/drivers/infiniband/hw/hfi1/affinity.c ++++ b/drivers/infiniband/hw/hfi1/affinity.c +@@ -1039,7 +1039,7 @@ int hfi1_get_proc_affinity(int node) + struct hfi1_affinity_node *entry; + cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask; + const struct cpumask *node_mask, +- *proc_mask = ¤t->cpus_allowed; ++ *proc_mask = current->cpus_ptr; + struct hfi1_affinity_node_list *affinity = &node_affinity; + struct cpu_mask_set *set = &affinity->proc; + +@@ -1047,7 +1047,7 @@ int hfi1_get_proc_affinity(int node) + * check whether process/context affinity has already + * been set + */ +- if (cpumask_weight(proc_mask) == 1) { ++ if (current->nr_cpus_allowed == 1) { + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); +@@ -1058,7 +1058,7 @@ int hfi1_get_proc_affinity(int node) + cpu = cpumask_first(proc_mask); + cpumask_set_cpu(cpu, &set->used); + goto done; +- } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) { ++ } else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) { + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); +diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c +index 38258de75a94..3ee680fc3fda 100644 +--- a/drivers/infiniband/hw/hfi1/sdma.c ++++ b/drivers/infiniband/hw/hfi1/sdma.c +@@ -853,14 +853,13 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd, + { + struct sdma_rht_node *rht_node; + struct sdma_engine *sde = NULL; +- const struct cpumask *current_mask = ¤t->cpus_allowed; + unsigned long cpu_id; + + /* + * To ensure that always the same sdma engine(s) will be + * selected make sure the process is pinned to this CPU only. + */ +- if (cpumask_weight(current_mask) != 1) ++ if (current->nr_cpus_allowed != 1) + goto out; + + cpu_id = smp_processor_id(); +diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c +index 98e1ce14fa2a..5d3828625017 100644 +--- a/drivers/infiniband/hw/qib/qib_file_ops.c ++++ b/drivers/infiniband/hw/qib/qib_file_ops.c +@@ -1142,7 +1142,7 @@ static __poll_t qib_poll(struct file *fp, struct poll_table_struct *pt) + static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd) + { + struct qib_filedata *fd = fp->private_data; +- const unsigned int weight = cpumask_weight(¤t->cpus_allowed); ++ const unsigned int weight = current->nr_cpus_allowed; + const struct cpumask *local_mask = cpumask_of_pcibus(dd->pcidev->bus); + int local_cpu; + +@@ -1623,9 +1623,8 @@ static int qib_assign_ctxt(struct file *fp, const struct qib_user_info *uinfo) + ret = find_free_ctxt(i_minor - 1, fp, uinfo); + else { + int unit; +- const unsigned int cpu = cpumask_first(¤t->cpus_allowed); +- const unsigned int weight = +- cpumask_weight(¤t->cpus_allowed); ++ const unsigned int cpu = cpumask_first(current->cpus_ptr); ++ const unsigned int weight = current->nr_cpus_allowed; + + if (weight == 1 && !test_bit(cpu, qib_cpulist)) + if (!find_hca(cpu, &unit) && unit >= 0) +diff --git a/fs/proc/array.c b/fs/proc/array.c +index 9eb99a43f849..e4d0cfebaac5 100644 +--- a/fs/proc/array.c ++++ b/fs/proc/array.c +@@ -381,9 +381,9 @@ static inline void task_context_switch_counts(struct seq_file *m, + static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) + { + seq_printf(m, "Cpus_allowed:\t%*pb\n", +- cpumask_pr_args(&task->cpus_allowed)); ++ cpumask_pr_args(task->cpus_ptr)); + seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", +- cpumask_pr_args(&task->cpus_allowed)); ++ cpumask_pr_args(task->cpus_ptr)); + } + + static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) +diff --git a/include/linux/sched.h b/include/linux/sched.h +index f92d5ae6d04e..fc5f476c2aca 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -660,7 +660,8 @@ struct task_struct { + + unsigned int policy; + int nr_cpus_allowed; +- cpumask_t cpus_allowed; ++ const cpumask_t *cpus_ptr; ++ cpumask_t cpus_mask; + + #ifdef CONFIG_PREEMPT_RCU + int rcu_read_lock_nesting; +@@ -1398,7 +1399,7 @@ extern struct pid *cad_pid; + #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ + #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ + #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +-#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ ++#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ + #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ + #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ + #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +diff --git a/init/init_task.c b/init/init_task.c +index 994ffe018120..d71054b95528 100644 +--- a/init/init_task.c ++++ b/init/init_task.c +@@ -71,7 +71,8 @@ struct task_struct init_task + .static_prio = MAX_PRIO - 20, + .normal_prio = MAX_PRIO - 20, + .policy = SCHED_NORMAL, +- .cpus_allowed = CPU_MASK_ALL, ++ .cpus_ptr = &init_task.cpus_mask, ++ .cpus_mask = CPU_MASK_ALL, + .nr_cpus_allowed= NR_CPUS, + .mm = NULL, + .active_mm = &init_mm, +diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c +index dcd5755b1fe2..35541e1dfad9 100644 +--- a/kernel/cgroup/cpuset.c ++++ b/kernel/cgroup/cpuset.c +@@ -2096,7 +2096,7 @@ static void cpuset_fork(struct task_struct *task) + if (task_css_is_root(task, cpuset_cgrp_id)) + return; + +- set_cpus_allowed_ptr(task, ¤t->cpus_allowed); ++ set_cpus_allowed_ptr(task, current->cpus_ptr); + task->mems_allowed = current->mems_allowed; + } + +diff --git a/kernel/fork.c b/kernel/fork.c +index b65871600507..a18d695259af 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -850,6 +850,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) + #ifdef CONFIG_STACKPROTECTOR + tsk->stack_canary = get_random_canary(); + #endif ++ if (orig->cpus_ptr == &orig->cpus_mask) ++ tsk->cpus_ptr = &tsk->cpus_mask; + + /* + * One for us, one for whoever does the "release_task()" (usually +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 32af895bd86b..3fb7638a8863 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -878,7 +878,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p) + */ + static inline bool is_cpu_allowed(struct task_struct *p, int cpu) + { +- if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + if (is_per_cpu_kthread(p)) +@@ -973,7 +973,7 @@ static int migration_cpu_stop(void *data) + local_irq_disable(); + /* + * We need to explicitly wake pending tasks before running +- * __migrate_task() such that we will not miss enforcing cpus_allowed ++ * __migrate_task() such that we will not miss enforcing cpus_ptr + * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. + */ + sched_ttwu_pending(); +@@ -1004,7 +1004,7 @@ static int migration_cpu_stop(void *data) + */ + void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) + { +- cpumask_copy(&p->cpus_allowed, new_mask); ++ cpumask_copy(&p->cpus_mask, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + +@@ -1074,7 +1074,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, + goto out; + } + +- if (cpumask_equal(&p->cpus_allowed, new_mask)) ++ if (cpumask_equal(p->cpus_ptr, new_mask)) + goto out; + + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); +@@ -1237,10 +1237,10 @@ static int migrate_swap_stop(void *data) + if (task_cpu(arg->src_task) != arg->src_cpu) + goto unlock; + +- if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr)) + goto unlock; + +- if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) + goto unlock; + + __migrate_swap_task(arg->src_task, arg->dst_cpu); +@@ -1282,10 +1282,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, + if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) + goto out; + +- if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr)) + goto out; + +- if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr)) + goto out; + + trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); +@@ -1430,7 +1430,7 @@ void kick_process(struct task_struct *p) + EXPORT_SYMBOL_GPL(kick_process); + + /* +- * ->cpus_allowed is protected by both rq->lock and p->pi_lock ++ * ->cpus_ptr is protected by both rq->lock and p->pi_lock + * + * A few notes on cpu_active vs cpu_online: + * +@@ -1470,14 +1470,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p) + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_active(dest_cpu)) + continue; +- if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) ++ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) + return dest_cpu; + } + } + + for (;;) { + /* Any allowed, online CPU? */ +- for_each_cpu(dest_cpu, &p->cpus_allowed) { ++ for_each_cpu(dest_cpu, p->cpus_ptr) { + if (!is_cpu_allowed(p, dest_cpu)) + continue; + +@@ -1521,7 +1521,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) + } + + /* +- * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. ++ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable. + */ + static inline + int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) +@@ -1531,11 +1531,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) + if (p->nr_cpus_allowed > 1) + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + else +- cpu = cpumask_any(&p->cpus_allowed); ++ cpu = cpumask_any(p->cpus_ptr); + + /* + * In order not to call set_task_cpu() on a blocking task we need +- * to rely on ttwu() to place the task on a valid ->cpus_allowed ++ * to rely on ttwu() to place the task on a valid ->cpus_ptr + * CPU. + * + * Since this is common to all placement strategies, this lives here. +@@ -2406,7 +2406,7 @@ void wake_up_new_task(struct task_struct *p) + #ifdef CONFIG_SMP + /* + * Fork balancing, do it here and not earlier because: +- * - cpus_allowed can change in the fork path ++ * - cpus_ptr can change in the fork path + * - any previously selected CPU might disappear through hotplug + * + * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, +@@ -4322,7 +4322,7 @@ static int __sched_setscheduler(struct task_struct *p, + * the entire root_domain to become SCHED_DEADLINE. We + * will also fail if there's no bandwidth available. + */ +- if (!cpumask_subset(span, &p->cpus_allowed) || ++ if (!cpumask_subset(span, p->cpus_ptr) || + rq->rd->dl_bw.bw == 0) { + task_rq_unlock(rq, p, &rf); + return -EPERM; +@@ -4921,7 +4921,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) + goto out_unlock; + + raw_spin_lock_irqsave(&p->pi_lock, flags); +- cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); ++ cpumask_and(mask, &p->cpus_mask, cpu_active_mask); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + out_unlock: +@@ -5498,7 +5498,7 @@ int task_can_attach(struct task_struct *p, + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks +- * before cpus_allowed may be changed. ++ * before cpus_mask may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) { + ret = -EINVAL; +@@ -5525,7 +5525,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu) + if (curr_cpu == target_cpu) + return 0; + +- if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) + return -EINVAL; + + /* TODO: This is not properly updating schedstats */ +@@ -5664,7 +5664,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) + put_prev_task(rq, next); + + /* +- * Rules for changing task_struct::cpus_allowed are holding ++ * Rules for changing task_struct::cpus_mask are holding + * both pi_lock and rq->lock, such that holding either + * stabilizes the mask. + * +diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c +index 50316455ea66..d57fb2f8ae67 100644 +--- a/kernel/sched/cpudeadline.c ++++ b/kernel/sched/cpudeadline.c +@@ -124,14 +124,14 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, + const struct sched_dl_entity *dl_se = &p->dl; + + if (later_mask && +- cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { ++ cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) { + return 1; + } else { + int best_cpu = cpudl_maximum(cp); + + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); + +- if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) && ++ if (cpumask_test_cpu(best_cpu, p->cpus_ptr) && + dl_time_before(dl_se->deadline, cp->elements[0].dl)) { + if (later_mask) + cpumask_set_cpu(best_cpu, later_mask); +diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c +index daaadf939ccb..f7d2c10b4c92 100644 +--- a/kernel/sched/cpupri.c ++++ b/kernel/sched/cpupri.c +@@ -98,11 +98,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, + if (skip) + continue; + +- if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) ++ if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids) + continue; + + if (lowest_mask) { +- cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); ++ cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); + + /* + * We have to ensure that we have at least one bit +diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c +index beec5081a55a..95ebbb2074c7 100644 +--- a/kernel/sched/deadline.c ++++ b/kernel/sched/deadline.c +@@ -539,7 +539,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p + * If we cannot preempt any rq, fall back to pick any + * online CPU: + */ +- cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); ++ cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr); + if (cpu >= nr_cpu_ids) { + /* + * Failed to find any suitable CPU. +@@ -1857,7 +1857,7 @@ static void set_curr_task_dl(struct rq *rq) + static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) + { + if (!task_running(rq, p) && +- cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ cpumask_test_cpu(cpu, p->cpus_ptr)) + return 1; + return 0; + } +@@ -2007,7 +2007,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) + /* Retry if something changed. */ + if (double_lock_balance(rq, later_rq)) { + if (unlikely(task_rq(task) != rq || +- !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || ++ !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || + task_running(rq, task) || + !dl_task(task) || + !task_on_rq_queued(task))) { +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index e84a056f783f..16940416d526 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -1691,7 +1691,7 @@ static void task_numa_compare(struct task_numa_env *env, + * be incurred if the tasks were swapped. + */ + /* Skip this swap candidate if cannot move to the source cpu */ +- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) ++ if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) + goto unlock; + + /* +@@ -1789,7 +1789,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, + + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { + /* Skip this CPU if the source task cannot migrate */ +- if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) + continue; + + env->dst_cpu = cpu; +@@ -5803,7 +5803,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, + + /* Skip over this group if it has no CPUs allowed */ + if (!cpumask_intersects(sched_group_span(group), +- &p->cpus_allowed)) ++ p->cpus_ptr)) + continue; + + local_group = cpumask_test_cpu(this_cpu, +@@ -5935,7 +5935,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this + return cpumask_first(sched_group_span(group)); + + /* Traverse only the allowed CPUs */ +- for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { ++ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { + if (available_idle_cpu(i)) { + struct rq *rq = cpu_rq(i); + struct cpuidle_state *idle = idle_get_state(rq); +@@ -5975,7 +5975,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p + { + int new_cpu = cpu; + +- if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) ++ if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr)) + return prev_cpu; + + /* +@@ -6092,7 +6092,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int + if (!test_idle_cores(target, false)) + return -1; + +- cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); ++ cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + + for_each_cpu_wrap(core, cpus, target) { + bool idle = true; +@@ -6126,7 +6126,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t + return -1; + + for_each_cpu(cpu, cpu_smt_mask(target)) { +- if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + continue; + if (available_idle_cpu(cpu)) + return cpu; +@@ -6187,7 +6187,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t + + time = local_clock(); + +- cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); ++ cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + + for_each_cpu_wrap(cpu, cpus, target) { + if (!--nr) +@@ -6227,7 +6227,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) + recent_used_cpu != target && + cpus_share_cache(recent_used_cpu, target) && + available_idle_cpu(recent_used_cpu) && +- cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { ++ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { + /* + * Replace recent_used_cpu with prev as it is a potential + * candidate for the next wake: +@@ -6445,7 +6445,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f + if (sd_flag & SD_BALANCE_WAKE) { + record_wakee(p); + want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) +- && cpumask_test_cpu(cpu, &p->cpus_allowed); ++ && cpumask_test_cpu(cpu, p->cpus_ptr); + } + + rcu_read_lock(); +@@ -7184,14 +7184,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) + /* + * We do not migrate tasks that are: + * 1) throttled_lb_pair, or +- * 2) cannot be migrated to this CPU due to cpus_allowed, or ++ * 2) cannot be migrated to this CPU due to cpus_ptr, or + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. + */ + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + return 0; + +- if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) { ++ if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { + int cpu; + + schedstat_inc(p->se.statistics.nr_failed_migrations_affine); +@@ -7211,7 +7211,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) + + /* Prevent to re-select dst_cpu via env's CPUs: */ + for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { +- if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { ++ if (cpumask_test_cpu(cpu, p->cpus_ptr)) { + env->flags |= LBF_DST_PINNED; + env->new_dst_cpu = cpu; + break; +@@ -7836,7 +7836,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) + + /* + * Group imbalance indicates (and tries to solve) the problem where balancing +- * groups is inadequate due to ->cpus_allowed constraints. ++ * groups is inadequate due to ->cpus_ptr constraints. + * + * Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a + * cpumask covering 1 CPU of the first group and 3 CPUs of the second group. +@@ -8451,7 +8451,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) + /* + * If the busiest group is imbalanced the below checks don't + * work because they assume all things are equal, which typically +- * isn't true due to cpus_allowed constraints and the like. ++ * isn't true due to cpus_ptr constraints and the like. + */ + if (busiest->group_type == group_imbalanced) + goto force_balance; +@@ -8847,7 +8847,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, + * if the curr task on busiest CPU can't be + * moved to this_cpu: + */ +- if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { ++ if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { + raw_spin_unlock_irqrestore(&busiest->lock, + flags); + env.flags |= LBF_ALL_PINNED; +diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c +index 70e8cd395474..52b55144d8ad 100644 +--- a/kernel/sched/rt.c ++++ b/kernel/sched/rt.c +@@ -1620,7 +1620,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) + static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) + { + if (!task_running(rq, p) && +- cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ cpumask_test_cpu(cpu, p->cpus_ptr)) + return 1; + + return 0; +@@ -1757,7 +1757,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) + * Also make sure that it wasn't scheduled on its rq. + */ + if (unlikely(task_rq(task) != rq || +- !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || ++ !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) || + task_running(rq, task) || + !rt_task(task) || + !task_on_rq_queued(task))) { +diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c +index ade6c3070c62..164e5c618cce 100644 +--- a/kernel/trace/trace_hwlat.c ++++ b/kernel/trace/trace_hwlat.c +@@ -280,7 +280,7 @@ static void move_to_next_cpu(void) + * of this thread, than stop migrating for the duration + * of the current test. + */ +- if (!cpumask_equal(current_mask, ¤t->cpus_allowed)) ++ if (!cpumask_equal(current_mask, current->cpus_ptr)) + goto disable; + + get_online_cpus(); +diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c +index 85925aaa4fff..fb35c45b9421 100644 +--- a/lib/smp_processor_id.c ++++ b/lib/smp_processor_id.c +@@ -22,7 +22,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1, + * Kernel threads bound to a single CPU can safely use + * smp_processor_id(): + */ +- if (cpumask_equal(¤t->cpus_allowed, cpumask_of(this_cpu))) ++ if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu))) + goto out; + + /* +diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c +index 5522692100ba..8b4be8e1802a 100644 +--- a/samples/trace_events/trace-events-sample.c ++++ b/samples/trace_events/trace-events-sample.c +@@ -33,7 +33,7 @@ static void simple_thread_func(int cnt) + + /* Silly tracepoints */ + trace_foo_bar("hello", cnt, array, random_strings[len], +- ¤t->cpus_allowed); ++ current->cpus_ptr); + + trace_foo_with_template_simple("HELLO", cnt); + +-- +2.36.1 + diff --git a/debian/patches-rt/0027-kernel-sched-core-add-migrate_disable.patch b/debian/patches-rt/0027-kernel-sched-core-add-migrate_disable.patch new file mode 100644 index 000000000..bd257b53a --- /dev/null +++ b/debian/patches-rt/0027-kernel-sched-core-add-migrate_disable.patch @@ -0,0 +1,266 @@ +From 842b16f6165e848057d292bb2e2a17a5c143bc55 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Sat, 27 May 2017 19:02:06 +0200 +Subject: [PATCH 027/347] kernel/sched/core: add migrate_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +--- + include/linux/preempt.h | 23 +++++++ + include/linux/sched.h | 7 +++ + include/linux/smp.h | 3 + + kernel/sched/core.c | 130 +++++++++++++++++++++++++++++++++++++++- + kernel/sched/debug.c | 4 ++ + 5 files changed, 165 insertions(+), 2 deletions(-) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index c01813c3fbe9..3196d0e76719 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -185,6 +185,22 @@ do { \ + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + ++#ifdef CONFIG_SMP ++ ++extern void migrate_disable(void); ++extern void migrate_enable(void); ++ ++int __migrate_disabled(struct task_struct *p); ++ ++#else ++#define migrate_disable() barrier() ++#define migrate_enable() barrier() ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++ return 0; ++} ++#endif ++ + #ifdef CONFIG_PREEMPT + #define preempt_enable() \ + do { \ +@@ -253,6 +269,13 @@ do { \ + #define preempt_enable_notrace() barrier() + #define preemptible() 0 + ++#define migrate_disable() barrier() ++#define migrate_enable() barrier() ++ ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++ return 0; ++} + #endif /* CONFIG_PREEMPT_COUNT */ + + #ifdef MODULE +diff --git a/include/linux/sched.h b/include/linux/sched.h +index fc5f476c2aca..52069b9ddce8 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -662,6 +662,13 @@ struct task_struct { + int nr_cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ int migrate_disable; ++ int migrate_disable_update; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif + + #ifdef CONFIG_PREEMPT_RCU + int rcu_read_lock_nesting; +diff --git a/include/linux/smp.h b/include/linux/smp.h +index 6bb7f07bc1dd..039da089482c 100644 +--- a/include/linux/smp.h ++++ b/include/linux/smp.h +@@ -202,6 +202,9 @@ static inline int get_boot_cpu_id(void) + #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) + #define put_cpu() preempt_enable() + ++#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) ++#define put_cpu_light() migrate_enable() ++ + /* + * Callback to arch code if there's nosmp or maxcpus=0 on the + * boot command line: +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 3fb7638a8863..5a691d2bfbfe 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1008,7 +1008,15 @@ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_ma + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + +-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++int __migrate_disabled(struct task_struct *p) ++{ ++ return p->migrate_disable; ++} ++#endif ++ ++static void __do_set_cpus_allowed_tail(struct task_struct *p, ++ const struct cpumask *new_mask) + { + struct rq *rq = task_rq(p); + bool queued, running; +@@ -1037,6 +1045,20 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + set_curr_task(rq, p); + } + ++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) ++{ ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ if (__migrate_disabled(p)) { ++ lockdep_assert_held(&p->pi_lock); ++ ++ cpumask_copy(&p->cpus_mask, new_mask); ++ p->migrate_disable_update = 1; ++ return; ++ } ++#endif ++ __do_set_cpus_allowed_tail(p, new_mask); ++} ++ + /* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on +@@ -1096,9 +1118,16 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, + } + + /* Can the task run on the task's current CPU? If so, we're done */ +- if (cpumask_test_cpu(task_cpu(p), new_mask)) ++ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ if (__migrate_disabled(p)) { ++ p->migrate_disable_update = 1; ++ goto out; ++ } ++#endif ++ + if (task_running(rq, p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; + /* Need help from migration thread: drop lock and wait. */ +@@ -7108,3 +7137,100 @@ const u32 sched_prio_to_wmult[40] = { + }; + + #undef CREATE_TRACE_POINTS ++ ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ ++ if (p->migrate_disable) { ++ p->migrate_disable++; ++ return; ++ } ++ ++ preempt_disable(); ++ p->migrate_disable = 1; ++ ++ p->cpus_ptr = cpumask_of(smp_processor_id()); ++ p->nr_cpus_allowed = 1; ++ ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ if (p->migrate_disable > 1) { ++ p->migrate_disable--; ++ return; ++ } ++ ++ preempt_disable(); ++ ++ p->cpus_ptr = &p->cpus_mask; ++ p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); ++ p->migrate_disable = 0; ++ ++ if (p->migrate_disable_update) { ++ struct rq *rq; ++ struct rq_flags rf; ++ ++ rq = task_rq_lock(p, &rf); ++ update_rq_clock(rq); ++ ++ __do_set_cpus_allowed_tail(p, &p->cpus_mask); ++ task_rq_unlock(rq, p, &rf); ++ ++ p->migrate_disable_update = 0; ++ ++ WARN_ON(smp_processor_id() != task_cpu(p)); ++ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { ++ const struct cpumask *cpu_valid_mask = cpu_active_mask; ++ struct migration_arg arg; ++ unsigned int dest_cpu; ++ ++ if (p->flags & PF_KTHREAD) { ++ /* ++ * Kernel threads are allowed on online && !active CPUs ++ */ ++ cpu_valid_mask = cpu_online_mask; ++ } ++ dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask); ++ arg.task = p; ++ arg.dest_cpu = dest_cpu; ++ ++ preempt_enable(); ++ stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); ++ tlb_migrate_finish(p->mm); ++ return; ++ } ++ } ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_enable); ++#endif +diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c +index b1ef4f2e7edc..dc3f3e6fa0bd 100644 +--- a/kernel/sched/debug.c ++++ b/kernel/sched/debug.c +@@ -988,6 +988,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, + P(dl.runtime); + P(dl.deadline); + } ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ P(migrate_disable); ++#endif ++ P(nr_cpus_allowed); + #undef PN_SCHEDSTAT + #undef PN + #undef __PN +-- +2.36.1 + diff --git a/debian/patches-rt/0028-sched-migrate_disable-Add-export_symbol_gpl-for-__mi.patch b/debian/patches-rt/0028-sched-migrate_disable-Add-export_symbol_gpl-for-__mi.patch new file mode 100644 index 000000000..f4980bd69 --- /dev/null +++ b/debian/patches-rt/0028-sched-migrate_disable-Add-export_symbol_gpl-for-__mi.patch @@ -0,0 +1,38 @@ +From 4df960200f0e46c435a32baad0ba0e90ec8db1a5 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 9 Oct 2018 17:34:50 +0200 +Subject: [PATCH 028/347] sched/migrate_disable: Add export_symbol_gpl for + __migrate_disabled +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Jonathan reported that lttng/modules can't use __migrate_disabled(). +This function is only used by sched/core itself and the tracing +infrastructure to report the migrate counter (lttng does probably the +same). Since the rework migrate_disable() it moved from sched.h to +preempt.h and is became an exported function instead of a "static +inline" due to the header recursion of preempt vs sched. + +Since the compiler inlines the function for sched/core usage, add a +EXPORT_SYMBOL_GPL to allow the module/LTTNG usage. + +Reported-by: Jonathan Rajott <jonathan.rajotte-julien@efficios.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/core.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 5a691d2bfbfe..0a51a66f5a63 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1013,6 +1013,7 @@ int __migrate_disabled(struct task_struct *p) + { + return p->migrate_disable; + } ++EXPORT_SYMBOL_GPL(__migrate_disabled); + #endif + + static void __do_set_cpus_allowed_tail(struct task_struct *p, +-- +2.36.1 + diff --git a/debian/patches-rt/0029-arm-at91-do-not-disable-enable-clocks-in-a-row.patch b/debian/patches-rt/0029-arm-at91-do-not-disable-enable-clocks-in-a-row.patch new file mode 100644 index 000000000..8bf2d54e0 --- /dev/null +++ b/debian/patches-rt/0029-arm-at91-do-not-disable-enable-clocks-in-a-row.patch @@ -0,0 +1,98 @@ +From 61b697c120be1e50542dfa879ebb522bf834b8d2 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 9 Mar 2016 10:51:06 +0100 +Subject: [PATCH 029/347] arm: at91: do not disable/enable clocks in a row +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Currently the driver will disable the clock and enable it one line later +if it is switching from periodic mode into one shot. +This can be avoided and causes a needless warning on -RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/clocksource/tcb_clksrc.c | 33 ++++++++++++++++++++++++++++---- + 1 file changed, 29 insertions(+), 4 deletions(-) + +diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c +index 43f4d5c4d6fa..de6baf564dfe 100644 +--- a/drivers/clocksource/tcb_clksrc.c ++++ b/drivers/clocksource/tcb_clksrc.c +@@ -126,6 +126,7 @@ static struct clocksource clksrc = { + struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; ++ bool clk_enabled; + void __iomem *regs; + }; + +@@ -143,6 +144,24 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt) + */ + static u32 timer_clock; + ++static void tc_clk_disable(struct clock_event_device *d) ++{ ++ struct tc_clkevt_device *tcd = to_tc_clkevt(d); ++ ++ clk_disable(tcd->clk); ++ tcd->clk_enabled = false; ++} ++ ++static void tc_clk_enable(struct clock_event_device *d) ++{ ++ struct tc_clkevt_device *tcd = to_tc_clkevt(d); ++ ++ if (tcd->clk_enabled) ++ return; ++ clk_enable(tcd->clk); ++ tcd->clk_enabled = true; ++} ++ + static int tc_shutdown(struct clock_event_device *d) + { + struct tc_clkevt_device *tcd = to_tc_clkevt(d); +@@ -150,8 +169,14 @@ static int tc_shutdown(struct clock_event_device *d) + + writel(0xff, regs + ATMEL_TC_REG(2, IDR)); + writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); ++ return 0; ++} ++ ++static int tc_shutdown_clk_off(struct clock_event_device *d) ++{ ++ tc_shutdown(d); + if (!clockevent_state_detached(d)) +- clk_disable(tcd->clk); ++ tc_clk_disable(d); + + return 0; + } +@@ -164,7 +189,7 @@ static int tc_set_oneshot(struct clock_event_device *d) + if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) + tc_shutdown(d); + +- clk_enable(tcd->clk); ++ tc_clk_enable(d); + + /* slow clock, count up to RC, then irq and stop */ + writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | +@@ -186,7 +211,7 @@ static int tc_set_periodic(struct clock_event_device *d) + /* By not making the gentime core emulate periodic mode on top + * of oneshot, we get lower overhead and improved accuracy. + */ +- clk_enable(tcd->clk); ++ tc_clk_enable(d); + + /* slow clock, count up to RC, then irq and restart */ + writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, +@@ -220,7 +245,7 @@ static struct tc_clkevt_device clkevt = { + /* Should be lower than at91rm9200's system timer */ + .rating = 125, + .set_next_event = tc_next_event, +- .set_state_shutdown = tc_shutdown, ++ .set_state_shutdown = tc_shutdown_clk_off, + .set_state_periodic = tc_set_periodic, + .set_state_oneshot = tc_set_oneshot, + }, +-- +2.36.1 + diff --git a/debian/patches-rt/0030-clocksource-TCLIB-Allow-higher-clock-rates-for-clock.patch b/debian/patches-rt/0030-clocksource-TCLIB-Allow-higher-clock-rates-for-clock.patch new file mode 100644 index 000000000..92ac4b1e3 --- /dev/null +++ b/debian/patches-rt/0030-clocksource-TCLIB-Allow-higher-clock-rates-for-clock.patch @@ -0,0 +1,170 @@ +From 785e3ab127a7476bb4da35910092b0d2fd767a47 Mon Sep 17 00:00:00 2001 +From: Benedikt Spranger <b.spranger@linutronix.de> +Date: Mon, 8 Mar 2010 18:57:04 +0100 +Subject: [PATCH 030/347] clocksource: TCLIB: Allow higher clock rates for + clock events +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +As default the TCLIB uses the 32KiHz base clock rate for clock events. +Add a compile time selection to allow higher clock resulution. + +(fixed up by Sami Pietikäinen <Sami.Pietikainen@wapice.com>) + +Signed-off-by: Benedikt Spranger <b.spranger@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/clocksource/tcb_clksrc.c | 36 +++++++++++++++++++------------- + drivers/misc/Kconfig | 12 +++++++++-- + 2 files changed, 31 insertions(+), 17 deletions(-) + +diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c +index de6baf564dfe..ba15242a6066 100644 +--- a/drivers/clocksource/tcb_clksrc.c ++++ b/drivers/clocksource/tcb_clksrc.c +@@ -25,8 +25,7 @@ + * this 32 bit free-running counter. the second channel is not used. + * + * - The third channel may be used to provide a 16-bit clockevent +- * source, used in either periodic or oneshot mode. This runs +- * at 32 KiHZ, and can handle delays of up to two seconds. ++ * source, used in either periodic or oneshot mode. + * + * A boot clocksource and clockevent source are also currently needed, + * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so +@@ -127,6 +126,7 @@ struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; + bool clk_enabled; ++ u32 freq; + void __iomem *regs; + }; + +@@ -135,13 +135,6 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt) + return container_of(clkevt, struct tc_clkevt_device, clkevt); + } + +-/* For now, we always use the 32K clock ... this optimizes for NO_HZ, +- * because using one of the divided clocks would usually mean the +- * tick rate can never be less than several dozen Hz (vs 0.5 Hz). +- * +- * A divided clock could be good for high resolution timers, since +- * 30.5 usec resolution can seem "low". +- */ + static u32 timer_clock; + + static void tc_clk_disable(struct clock_event_device *d) +@@ -191,7 +184,7 @@ static int tc_set_oneshot(struct clock_event_device *d) + + tc_clk_enable(d); + +- /* slow clock, count up to RC, then irq and stop */ ++ /* count up to RC, then irq and stop */ + writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | + ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); + writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -213,10 +206,10 @@ static int tc_set_periodic(struct clock_event_device *d) + */ + tc_clk_enable(d); + +- /* slow clock, count up to RC, then irq and restart */ ++ /* count up to RC, then irq and restart */ + writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +- writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); ++ writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); + + /* Enable clock and interrupts on RC compare */ + writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -243,7 +236,11 @@ static struct tc_clkevt_device clkevt = { + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + /* Should be lower than at91rm9200's system timer */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + .rating = 125, ++#else ++ .rating = 200, ++#endif + .set_next_event = tc_next_event, + .set_state_shutdown = tc_shutdown_clk_off, + .set_state_periodic = tc_set_periodic, +@@ -265,8 +262,9 @@ static irqreturn_t ch2_irq(int irq, void *handle) + return IRQ_NONE; + } + +-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) ++static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) + { ++ unsigned divisor = atmel_tc_divisors[divisor_idx]; + int ret; + struct clk *t2_clk = tc->clk[2]; + int irq = tc->irq[2]; +@@ -287,7 +285,11 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) + clkevt.regs = tc->regs; + clkevt.clk = t2_clk; + +- timer_clock = clk32k_divisor_idx; ++ timer_clock = divisor_idx; ++ if (!divisor) ++ clkevt.freq = 32768; ++ else ++ clkevt.freq = clk_get_rate(t2_clk) / divisor; + + clkevt.clkevt.cpumask = cpumask_of(0); + +@@ -298,7 +300,7 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) + return ret; + } + +- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); ++ clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); + + return ret; + } +@@ -435,7 +437,11 @@ static int __init tcb_clksrc_init(void) + goto err_disable_t1; + + /* channel 2: periodic and oneshot timer support */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + ret = setup_clkevents(tc, clk32k_divisor_idx); ++#else ++ ret = setup_clkevents(tc, best_divisor_idx); ++#endif + if (ret) + goto err_unregister_clksrc; + +diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig +index 3726eacdf65d..0900dec7ec04 100644 +--- a/drivers/misc/Kconfig ++++ b/drivers/misc/Kconfig +@@ -69,8 +69,7 @@ config ATMEL_TCB_CLKSRC + are combined to make a single 32-bit timer. + + When GENERIC_CLOCKEVENTS is defined, the third timer channel +- may be used as a clock event device supporting oneshot mode +- (delays of up to two seconds) based on the 32 KiHz clock. ++ may be used as a clock event device supporting oneshot mode. + + config ATMEL_TCB_CLKSRC_BLOCK + int +@@ -83,6 +82,15 @@ config ATMEL_TCB_CLKSRC_BLOCK + TC can be used for other purposes, such as PWM generation and + interval timing. + ++config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK ++ bool "TC Block use 32 KiHz clock" ++ depends on ATMEL_TCB_CLKSRC ++ default y ++ help ++ Select this to use 32 KiHz base clock rate as TC block clock ++ source for clock events. ++ ++ + config DUMMY_IRQ + tristate "Dummy IRQ handler" + default n +-- +2.36.1 + diff --git a/debian/patches-rt/0031-timekeeping-Split-jiffies-seqlock.patch b/debian/patches-rt/0031-timekeeping-Split-jiffies-seqlock.patch new file mode 100644 index 000000000..0b4af0dee --- /dev/null +++ b/debian/patches-rt/0031-timekeeping-Split-jiffies-seqlock.patch @@ -0,0 +1,171 @@ +From 8af466b69f15bf4b922703f7b7d6bba72f2ae86c Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 14 Feb 2013 22:36:59 +0100 +Subject: [PATCH 031/347] timekeeping: Split jiffies seqlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Replace jiffies_lock seqlock with a simple seqcounter and a rawlock so +it can be taken in atomic context on RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/time/jiffies.c | 7 ++++--- + kernel/time/tick-common.c | 10 ++++++---- + kernel/time/tick-sched.c | 19 ++++++++++++------- + kernel/time/timekeeping.c | 6 ++++-- + kernel/time/timekeeping.h | 3 ++- + 5 files changed, 28 insertions(+), 17 deletions(-) + +diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c +index 497719127bf9..62acb8914c9e 100644 +--- a/kernel/time/jiffies.c ++++ b/kernel/time/jiffies.c +@@ -74,7 +74,8 @@ static struct clocksource clocksource_jiffies = { + .max_cycles = 10, + }; + +-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); ++__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); ++__cacheline_aligned_in_smp seqcount_t jiffies_seq; + + #if (BITS_PER_LONG < 64) + u64 get_jiffies_64(void) +@@ -83,9 +84,9 @@ u64 get_jiffies_64(void) + u64 ret; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + ret = jiffies_64; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + return ret; + } + EXPORT_SYMBOL(get_jiffies_64); +diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c +index 0a3cc37e4b83..7bd136b646d4 100644 +--- a/kernel/time/tick-common.c ++++ b/kernel/time/tick-common.c +@@ -80,13 +80,15 @@ int tick_is_oneshot_available(void) + static void tick_periodic(int cpu) + { + if (tick_do_timer_cpu == cpu) { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -158,9 +160,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) + ktime_t next; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + next = tick_next_period; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); + +diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c +index 48403fb653c2..e774a49176cc 100644 +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -68,7 +68,8 @@ static void tick_do_update_jiffies64(ktime_t now) + return; + + /* Reevaluate with jiffies_lock held */ +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta >= tick_period) { +@@ -94,10 +95,12 @@ static void tick_do_update_jiffies64(ktime_t now) + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return; + } +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -108,12 +111,14 @@ static ktime_t tick_init_jiffy_update(void) + { + ktime_t period; + +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + /* Did we start the jiffies update yet ? */ + if (last_jiffies_update == 0) + last_jiffies_update = tick_next_period; + period = last_jiffies_update; +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return period; + } + +@@ -656,10 +661,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) + + /* Read jiffies and the time when jiffies were updated last */ + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + basemono = last_jiffies_update; + basejiff = jiffies; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + ts->last_jiffies = basejiff; + ts->timer_expires_base = basemono; + +diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c +index f246818e35db..2cc8a1e8e94f 100644 +--- a/kernel/time/timekeeping.c ++++ b/kernel/time/timekeeping.c +@@ -2392,8 +2392,10 @@ EXPORT_SYMBOL(hardpps); + */ + void xtime_update(unsigned long ticks) + { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + do_timer(ticks); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } +diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h +index 141ab3ab0354..099737f6f10c 100644 +--- a/kernel/time/timekeeping.h ++++ b/kernel/time/timekeeping.h +@@ -25,7 +25,8 @@ static inline void sched_clock_resume(void) { } + extern void do_timer(unsigned long ticks); + extern void update_wall_time(void); + +-extern seqlock_t jiffies_lock; ++extern raw_spinlock_t jiffies_lock; ++extern seqcount_t jiffies_seq; + + #define CS_NAME_LEN 32 + +-- +2.36.1 + diff --git a/debian/patches-rt/0032-signal-Revert-ptrace-preempt-magic.patch b/debian/patches-rt/0032-signal-Revert-ptrace-preempt-magic.patch new file mode 100644 index 000000000..584eaea9c --- /dev/null +++ b/debian/patches-rt/0032-signal-Revert-ptrace-preempt-magic.patch @@ -0,0 +1,38 @@ +From a52b4b412745dea30d5833c35df527de9aceaf70 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 21 Sep 2011 19:57:12 +0200 +Subject: [PATCH 032/347] signal: Revert ptrace preempt magic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Upstream commit '53da1d9456fe7f8 fix ptrace slowness' is nothing more +than a bandaid around the ptrace design trainwreck. It's not a +correctness issue, it's merily a cosmetic bandaid. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/signal.c | 8 -------- + 1 file changed, 8 deletions(-) + +diff --git a/kernel/signal.c b/kernel/signal.c +index 4cc3f3ba13a9..23764988b5d1 100644 +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -2099,15 +2099,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + +- /* +- * Don't want to allow preemption here, because +- * sys_ptrace() needs this task to be inactive. +- * +- * XXX: implement read_unlock_no_resched(). +- */ +- preempt_disable(); + read_unlock(&tasklist_lock); +- preempt_enable_no_resched(); + freezable_schedule(); + } else { + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0033-net-sched-Use-msleep-instead-of-yield.patch b/debian/patches-rt/0033-net-sched-Use-msleep-instead-of-yield.patch new file mode 100644 index 000000000..04ac2a1dd --- /dev/null +++ b/debian/patches-rt/0033-net-sched-Use-msleep-instead-of-yield.patch @@ -0,0 +1,64 @@ +From 6312157ef6ed82e76dfab7c719dc7b5f731eb189 Mon Sep 17 00:00:00 2001 +From: Marc Kleine-Budde <mkl@pengutronix.de> +Date: Wed, 5 Mar 2014 00:49:47 +0100 +Subject: [PATCH 033/347] net: sched: Use msleep() instead of yield() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On PREEMPT_RT enabled systems the interrupt handler run as threads at prio 50 +(by default). If a high priority userspace process tries to shut down a busy +network interface it might spin in a yield loop waiting for the device to +become idle. With the interrupt thread having a lower priority than the +looping process it might never be scheduled and so result in a deadlock on UP +systems. + +With Magic SysRq the following backtrace can be produced: + +> test_app R running 0 174 168 0x00000000 +> [<c02c7070>] (__schedule+0x220/0x3fc) from [<c02c7870>] (preempt_schedule_irq+0x48/0x80) +> [<c02c7870>] (preempt_schedule_irq+0x48/0x80) from [<c0008fa8>] (svc_preempt+0x8/0x20) +> [<c0008fa8>] (svc_preempt+0x8/0x20) from [<c001a984>] (local_bh_enable+0x18/0x88) +> [<c001a984>] (local_bh_enable+0x18/0x88) from [<c025316c>] (dev_deactivate_many+0x220/0x264) +> [<c025316c>] (dev_deactivate_many+0x220/0x264) from [<c023be04>] (__dev_close_many+0x64/0xd4) +> [<c023be04>] (__dev_close_many+0x64/0xd4) from [<c023be9c>] (__dev_close+0x28/0x3c) +> [<c023be9c>] (__dev_close+0x28/0x3c) from [<c023f7f0>] (__dev_change_flags+0x88/0x130) +> [<c023f7f0>] (__dev_change_flags+0x88/0x130) from [<c023f904>] (dev_change_flags+0x10/0x48) +> [<c023f904>] (dev_change_flags+0x10/0x48) from [<c024c140>] (do_setlink+0x370/0x7ec) +> [<c024c140>] (do_setlink+0x370/0x7ec) from [<c024d2f0>] (rtnl_newlink+0x2b4/0x450) +> [<c024d2f0>] (rtnl_newlink+0x2b4/0x450) from [<c024cfa0>] (rtnetlink_rcv_msg+0x158/0x1f4) +> [<c024cfa0>] (rtnetlink_rcv_msg+0x158/0x1f4) from [<c0256740>] (netlink_rcv_skb+0xac/0xc0) +> [<c0256740>] (netlink_rcv_skb+0xac/0xc0) from [<c024bbd8>] (rtnetlink_rcv+0x18/0x24) +> [<c024bbd8>] (rtnetlink_rcv+0x18/0x24) from [<c02561b8>] (netlink_unicast+0x13c/0x198) +> [<c02561b8>] (netlink_unicast+0x13c/0x198) from [<c025651c>] (netlink_sendmsg+0x264/0x2e0) +> [<c025651c>] (netlink_sendmsg+0x264/0x2e0) from [<c022af98>] (sock_sendmsg+0x78/0x98) +> [<c022af98>] (sock_sendmsg+0x78/0x98) from [<c022bb50>] (___sys_sendmsg.part.25+0x268/0x278) +> [<c022bb50>] (___sys_sendmsg.part.25+0x268/0x278) from [<c022cf08>] (__sys_sendmsg+0x48/0x78) +> [<c022cf08>] (__sys_sendmsg+0x48/0x78) from [<c0009320>] (ret_fast_syscall+0x0/0x2c) + +This patch works around the problem by replacing yield() by msleep(1), giving +the interrupt thread time to finish, similar to other changes contained in the +rt patch set. Using wait_for_completion() instead would probably be a better +solution. + + +Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/sched/sch_generic.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c +index 7c1b1eff84f4..42a776abdf2f 100644 +--- a/net/sched/sch_generic.c ++++ b/net/sched/sch_generic.c +@@ -1253,7 +1253,7 @@ void dev_deactivate_many(struct list_head *head) + /* Wait for outstanding qdisc_run calls. */ + list_for_each_entry(dev, head, close_list) { + while (some_qdisc_is_busy(dev)) +- yield(); ++ msleep(1); + /* The new qdisc is assigned at this point so we can safely + * unwind stale skb lists and qdisc statistics + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0034-dm-rq-remove-BUG_ON-irqs_disabled-check.patch b/debian/patches-rt/0034-dm-rq-remove-BUG_ON-irqs_disabled-check.patch new file mode 100644 index 000000000..ee27e4207 --- /dev/null +++ b/debian/patches-rt/0034-dm-rq-remove-BUG_ON-irqs_disabled-check.patch @@ -0,0 +1,37 @@ +From 7437113ac72d093e8ee118ccfd6174f199811e3e Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 27 Mar 2018 16:24:15 +0200 +Subject: [PATCH 034/347] dm rq: remove BUG_ON(!irqs_disabled) check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In commit 052189a2ec95 ("dm: remove superfluous irq disablement in +dm_request_fn") the spin_lock_irq() was replaced with spin_lock() + a +check for disabled interrupts. Later the locking part was removed in +commit 2eb6e1e3aa87 ("dm: submit stacked requests in irq enabled +context") but the BUG_ON() check remained. + +Since the original purpose for the "are-irqs-off" check is gone (the +->queue_lock has been removed) remove it. + +Cc: Keith Busch <keith.busch@intel.com> +Cc: Mike Snitzer <snitzer@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/md/dm-rq.c | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c +index 2957a3763f01..bc8192b4e7b2 100644 +--- a/drivers/md/dm-rq.c ++++ b/drivers/md/dm-rq.c +@@ -689,7 +689,6 @@ static void dm_old_request_fn(struct request_queue *q) + /* Establish tio->ti before queuing work (map_tio_request) */ + tio->ti = ti; + kthread_queue_work(&md->kworker, &tio->work); +- BUG_ON(!irqs_disabled()); + } + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0035-usb-do-no-disable-interrupts-in-giveback.patch b/debian/patches-rt/0035-usb-do-no-disable-interrupts-in-giveback.patch new file mode 100644 index 000000000..07b1ab8e9 --- /dev/null +++ b/debian/patches-rt/0035-usb-do-no-disable-interrupts-in-giveback.patch @@ -0,0 +1,46 @@ +From 58c679541448da375ccc262585f3172e913811f3 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 8 Nov 2013 17:34:54 +0100 +Subject: [PATCH 035/347] usb: do no disable interrupts in giveback +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Since commit 94dfd7ed ("USB: HCD: support giveback of URB in tasklet +context") the USB code disables interrupts before invoking the complete +callback. +This should not be required the HCD completes the URBs either in hard-irq +context or in BH context. Lockdep may report false positives if one has two +HCDs (one completes in IRQ and the other in BH context) and is using the same +USB driver (device) with both HCDs. This is safe since the same URBs are never +mixed with those two HCDs. +Longeterm we should force all HCDs to complete in the same context. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/usb/core/hcd.c | 3 --- + 1 file changed, 3 deletions(-) + +diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c +index df661460e9f9..1a1487d312d0 100644 +--- a/drivers/usb/core/hcd.c ++++ b/drivers/usb/core/hcd.c +@@ -1752,7 +1752,6 @@ static void __usb_hcd_giveback_urb(struct urb *urb) + struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); + struct usb_anchor *anchor = urb->anchor; + int status = urb->unlinked; +- unsigned long flags; + + urb->hcpriv = NULL; + if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && +@@ -1780,9 +1779,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb) + * and no one may trigger the above deadlock situation when + * running complete() in tasklet. + */ +- local_irq_save(flags); + urb->complete(urb); +- local_irq_restore(flags); + + usb_anchor_resume_wakeups(anchor); + atomic_dec(&urb->use_count); +-- +2.36.1 + diff --git a/debian/patches-rt/0036-rt-Provide-PREEMPT_RT_BASE-config-switch.patch b/debian/patches-rt/0036-rt-Provide-PREEMPT_RT_BASE-config-switch.patch new file mode 100644 index 000000000..06f68e211 --- /dev/null +++ b/debian/patches-rt/0036-rt-Provide-PREEMPT_RT_BASE-config-switch.patch @@ -0,0 +1,64 @@ +From a32da1fe301b84a5d1e22c83472290f0f10e8b12 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 17 Jun 2011 12:39:57 +0200 +Subject: [PATCH 036/347] rt: Provide PREEMPT_RT_BASE config switch +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Introduce PREEMPT_RT_BASE which enables parts of +PREEMPT_RT_FULL. Forces interrupt threading and enables some of the RT +substitutions for testing. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/Kconfig.preempt | 21 ++++++++++++++++++--- + 1 file changed, 18 insertions(+), 3 deletions(-) + +diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt +index cd1655122ec0..027db5976c2f 100644 +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -1,3 +1,10 @@ ++config PREEMPT ++ bool ++ select PREEMPT_COUNT ++ ++config PREEMPT_RT_BASE ++ bool ++ select PREEMPT + + choice + prompt "Preemption Model" +@@ -34,10 +41,10 @@ config PREEMPT_VOLUNTARY + + Select this if you are building a kernel for a desktop system. + +-config PREEMPT ++config PREEMPT__LL + bool "Preemptible Kernel (Low-Latency Desktop)" + depends on !ARCH_NO_PREEMPT +- select PREEMPT_COUNT ++ select PREEMPT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + help + This option reduces the latency of the kernel by making +@@ -54,7 +61,15 @@ config PREEMPT + embedded system with latency requirements in the milliseconds + range. + ++config PREEMPT_RTB ++ bool "Preemptible Kernel (Basic RT)" ++ select PREEMPT_RT_BASE ++ help ++ This option is basically the same as (Low-Latency Desktop) but ++ enables changes which are preliminary for the full preemptible ++ RT kernel. ++ + endchoice + + config PREEMPT_COUNT +- bool +\ No newline at end of file ++ bool +-- +2.36.1 + diff --git a/debian/patches-rt/0037-cpumask-Disable-CONFIG_CPUMASK_OFFSTACK-for-RT.patch b/debian/patches-rt/0037-cpumask-Disable-CONFIG_CPUMASK_OFFSTACK-for-RT.patch new file mode 100644 index 000000000..f5e098023 --- /dev/null +++ b/debian/patches-rt/0037-cpumask-Disable-CONFIG_CPUMASK_OFFSTACK-for-RT.patch @@ -0,0 +1,76 @@ +From ecd952b9f170afff929edaa1b5b7a172b07881c8 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 14 Dec 2011 01:03:49 +0100 +Subject: [PATCH 037/347] cpumask: Disable CONFIG_CPUMASK_OFFSTACK for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There are "valid" GFP_ATOMIC allocations such as + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:931 +|in_atomic(): 1, irqs_disabled(): 0, pid: 2130, name: tar +|1 lock held by tar/2130: +| #0: (&mm->mmap_sem){++++++}, at: [<ffffffff811d4e89>] SyS_brk+0x39/0x190 +|Preemption disabled at:[<ffffffff81063048>] flush_tlb_mm_range+0x28/0x350 +| +|CPU: 1 PID: 2130 Comm: tar Tainted: G W 4.8.2-rt2+ #747 +|Call Trace: +| [<ffffffff814d52dc>] dump_stack+0x86/0xca +| [<ffffffff810a26fb>] ___might_sleep+0x14b/0x240 +| [<ffffffff819bc1d4>] rt_spin_lock+0x24/0x60 +| [<ffffffff81194fba>] get_page_from_freelist+0x83a/0x11b0 +| [<ffffffff81195e8b>] __alloc_pages_nodemask+0x15b/0x1190 +| [<ffffffff811f0b81>] alloc_pages_current+0xa1/0x1f0 +| [<ffffffff811f7df5>] new_slab+0x3e5/0x690 +| [<ffffffff811fb0d5>] ___slab_alloc+0x495/0x660 +| [<ffffffff811fb311>] __slab_alloc.isra.79+0x71/0xc0 +| [<ffffffff811fb447>] __kmalloc_node+0xe7/0x240 +| [<ffffffff814d4ee0>] alloc_cpumask_var_node+0x20/0x50 +| [<ffffffff814d4f3e>] alloc_cpumask_var+0xe/0x10 +| [<ffffffff810430c1>] native_send_call_func_ipi+0x21/0x130 +| [<ffffffff8111c13f>] smp_call_function_many+0x22f/0x370 +| [<ffffffff81062b64>] native_flush_tlb_others+0x1a4/0x3a0 +| [<ffffffff8106309b>] flush_tlb_mm_range+0x7b/0x350 +| [<ffffffff811c88e2>] tlb_flush_mmu_tlbonly+0x62/0xd0 +| [<ffffffff811c9af4>] tlb_finish_mmu+0x14/0x50 +| [<ffffffff811d1c84>] unmap_region+0xe4/0x110 +| [<ffffffff811d3db3>] do_munmap+0x293/0x470 +| [<ffffffff811d4f8c>] SyS_brk+0x13c/0x190 +| [<ffffffff810032e2>] do_fast_syscall_32+0xb2/0x2f0 +| [<ffffffff819be181>] entry_SYSENTER_compat+0x51/0x60 + +which forbid allocations at run-time. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/Kconfig | 2 +- + lib/Kconfig | 1 + + 2 files changed, 2 insertions(+), 1 deletion(-) + +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index be4403a8e1b4..a8ec5d0c024e 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -935,7 +935,7 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT + config MAXSMP + bool "Enable Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP && DEBUG_KERNEL +- select CPUMASK_OFFSTACK ++ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL + ---help--- + Enable maximum number of CPUS and NUMA Nodes for this architecture. + If unsure, say N. +diff --git a/lib/Kconfig b/lib/Kconfig +index 714ec2f50bb1..4857bb4c490a 100644 +--- a/lib/Kconfig ++++ b/lib/Kconfig +@@ -440,6 +440,7 @@ config CHECK_SIGNATURE + + config CPUMASK_OFFSTACK + bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS ++ depends on !PREEMPT_RT_FULL + help + Use dynamic allocation for cpumask_var_t, instead of putting + them on the stack. This is a bit more expensive, but avoids +-- +2.36.1 + diff --git a/debian/patches-rt/0038-jump-label-disable-if-stop_machine-is-used.patch b/debian/patches-rt/0038-jump-label-disable-if-stop_machine-is-used.patch new file mode 100644 index 000000000..2492e61a1 --- /dev/null +++ b/debian/patches-rt/0038-jump-label-disable-if-stop_machine-is-used.patch @@ -0,0 +1,42 @@ +From d1a6d4880db516353e443bbe3b11ce97767dd75e Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 8 Jul 2015 17:14:48 +0200 +Subject: [PATCH 038/347] jump-label: disable if stop_machine() is used +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Some architectures are using stop_machine() while switching the opcode which +leads to latency spikes. +The architectures which use stop_machine() atm: +- ARM stop machine +- s390 stop machine + +The architecures which use other sorcery: +- MIPS +- X86 +- powerpc +- sparc +- arm64 + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +[bigeasy: only ARM for now] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index d89d013f586c..32d59b815b52 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -51,7 +51,7 @@ config ARM + select HARDIRQS_SW_RESEND + select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 +- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU ++ select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT_BASE + select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) +-- +2.36.1 + diff --git a/debian/patches-rt/0039-kconfig-Disable-config-options-which-are-not-RT-comp.patch b/debian/patches-rt/0039-kconfig-Disable-config-options-which-are-not-RT-comp.patch new file mode 100644 index 000000000..20f55cc87 --- /dev/null +++ b/debian/patches-rt/0039-kconfig-Disable-config-options-which-are-not-RT-comp.patch @@ -0,0 +1,43 @@ +From 92e84c0530709b63ff982d19ccf2ae0523aa712a Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 24 Jul 2011 12:11:43 +0200 +Subject: [PATCH 039/347] kconfig: Disable config options which are not RT + compatible +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Disable stuff which is known to have issues on RT + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/Kconfig | 1 + + mm/Kconfig | 2 +- + 2 files changed, 2 insertions(+), 1 deletion(-) + +diff --git a/arch/Kconfig b/arch/Kconfig +index dd71b34fe4f5..f53e81602922 100644 +--- a/arch/Kconfig ++++ b/arch/Kconfig +@@ -28,6 +28,7 @@ config OPROFILE + tristate "OProfile system profiling" + depends on PROFILING + depends on HAVE_OPROFILE ++ depends on !PREEMPT_RT_FULL + select RING_BUFFER + select RING_BUFFER_ALLOW_SWAP + help +diff --git a/mm/Kconfig b/mm/Kconfig +index b457e94ae618..0dddbb2a3282 100644 +--- a/mm/Kconfig ++++ b/mm/Kconfig +@@ -377,7 +377,7 @@ config NOMMU_INITIAL_TRIM_EXCESS + + config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" +- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE ++ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL + select COMPACTION + select RADIX_TREE_MULTIORDER + help +-- +2.36.1 + diff --git a/debian/patches-rt/0040-lockdep-disable-self-test.patch b/debian/patches-rt/0040-lockdep-disable-self-test.patch new file mode 100644 index 000000000..ff859feb8 --- /dev/null +++ b/debian/patches-rt/0040-lockdep-disable-self-test.patch @@ -0,0 +1,35 @@ +From 563448c3c6d54ac0304256d02827bd841ba65a2f Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 17 Oct 2017 16:36:18 +0200 +Subject: [PATCH 040/347] lockdep: disable self-test +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The self-test wasn't always 100% accurate for RT. We disabled a few +tests which failed because they had a different semantic for RT. Some +still reported false positives. Now the selftest locks up the system +during boot and it needs to be investigated… + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + lib/Kconfig.debug | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug +index 621859a453f8..02f962c9b199 100644 +--- a/lib/Kconfig.debug ++++ b/lib/Kconfig.debug +@@ -1206,7 +1206,7 @@ config DEBUG_ATOMIC_SLEEP + + config DEBUG_LOCKING_API_SELFTESTS + bool "Locking API boot-time self-tests" +- depends on DEBUG_KERNEL ++ depends on DEBUG_KERNEL && !PREEMPT_RT_FULL + help + Say Y here if you want the kernel to run a short self-test during + bootup. The self-test checks whether common types of locking bugs +-- +2.36.1 + diff --git a/debian/patches-rt/0041-mm-Allow-only-slub-on-RT.patch b/debian/patches-rt/0041-mm-Allow-only-slub-on-RT.patch new file mode 100644 index 000000000..b41b5188e --- /dev/null +++ b/debian/patches-rt/0041-mm-Allow-only-slub-on-RT.patch @@ -0,0 +1,37 @@ +From 8b775963cebd7cc5b3416a9d8f85ef4c343874df Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:44:03 -0500 +Subject: [PATCH 041/347] mm: Allow only slub on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Disable SLAB and SLOB on -RT. Only SLUB is adopted to -RT needs. + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + init/Kconfig | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/init/Kconfig b/init/Kconfig +index 15c02e15d3fd..45a9846f1464 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1650,6 +1650,7 @@ choice + + config SLAB + bool "SLAB" ++ depends on !PREEMPT_RT_FULL + select HAVE_HARDENED_USERCOPY_ALLOCATOR + help + The regular slab allocator that is established and known to work +@@ -1670,6 +1671,7 @@ config SLUB + config SLOB + depends on EXPERT + bool "SLOB (Simple Allocator)" ++ depends on !PREEMPT_RT_FULL + help + SLOB replaces the stock allocator with a drastically simpler + allocator. SLOB is generally more space efficient but +-- +2.36.1 + diff --git a/debian/patches-rt/0042-locking-Disable-spin-on-owner-for-RT.patch b/debian/patches-rt/0042-locking-Disable-spin-on-owner-for-RT.patch new file mode 100644 index 000000000..f17f2534e --- /dev/null +++ b/debian/patches-rt/0042-locking-Disable-spin-on-owner-for-RT.patch @@ -0,0 +1,38 @@ +From 08935fef7d8bf9943412aabcac4133066923333f Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 17 Jul 2011 21:51:45 +0200 +Subject: [PATCH 042/347] locking: Disable spin on owner for RT +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Drop spin on owner for mutex / rwsem. We are most likely not using it +but… + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/Kconfig.locks | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks +index 84d882f3e299..af27c4000812 100644 +--- a/kernel/Kconfig.locks ++++ b/kernel/Kconfig.locks +@@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW + + config MUTEX_SPIN_ON_OWNER + def_bool y +- depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config RWSEM_SPIN_ON_OWNER + def_bool y +- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config LOCK_SPIN_ON_OWNER + def_bool y +-- +2.36.1 + diff --git a/debian/patches-rt/0043-rcu-Disable-RCU_FAST_NO_HZ-on-RT.patch b/debian/patches-rt/0043-rcu-Disable-RCU_FAST_NO_HZ-on-RT.patch new file mode 100644 index 000000000..7f601cc2e --- /dev/null +++ b/debian/patches-rt/0043-rcu-Disable-RCU_FAST_NO_HZ-on-RT.patch @@ -0,0 +1,30 @@ +From bf68f45a17d9185950e69e908fcbff3fe28f7764 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 28 Oct 2012 13:26:09 +0000 +Subject: [PATCH 043/347] rcu: Disable RCU_FAST_NO_HZ on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +This uses a timer_list timer from the irq disabled guts of the idle +code. Disable it for now to prevent wreckage. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/rcu/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig +index 9210379c0353..644264be90f0 100644 +--- a/kernel/rcu/Kconfig ++++ b/kernel/rcu/Kconfig +@@ -172,7 +172,7 @@ config RCU_FANOUT_LEAF + + config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" +- depends on NO_HZ_COMMON && SMP && RCU_EXPERT ++ depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL + default n + help + This option permits CPUs to enter dynticks-idle state even if +-- +2.36.1 + diff --git a/debian/patches-rt/0044-rcu-make-RCU_BOOST-default-on-RT.patch b/debian/patches-rt/0044-rcu-make-RCU_BOOST-default-on-RT.patch new file mode 100644 index 000000000..41c8f5cf1 --- /dev/null +++ b/debian/patches-rt/0044-rcu-make-RCU_BOOST-default-on-RT.patch @@ -0,0 +1,34 @@ +From 54dcdf587a5ea4e590122c0666760e151bb3f122 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 21 Mar 2014 20:19:05 +0100 +Subject: [PATCH 044/347] rcu: make RCU_BOOST default on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Since it is no longer invoked from the softirq people run into OOM more +often if the priority of the RCU thread is too low. Making boosting +default on RT should help in those case and it can be switched off if +someone knows better. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/rcu/Kconfig | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig +index 644264be90f0..a243a78ff38c 100644 +--- a/kernel/rcu/Kconfig ++++ b/kernel/rcu/Kconfig +@@ -190,8 +190,8 @@ config RCU_FAST_NO_HZ + + config RCU_BOOST + bool "Enable RCU priority boosting" +- depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT +- default n ++ depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT_FULL ++ default y if PREEMPT_RT_FULL + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. +-- +2.36.1 + diff --git a/debian/patches-rt/0045-sched-Disable-CONFIG_RT_GROUP_SCHED-on-RT.patch b/debian/patches-rt/0045-sched-Disable-CONFIG_RT_GROUP_SCHED-on-RT.patch new file mode 100644 index 000000000..f7214c126 --- /dev/null +++ b/debian/patches-rt/0045-sched-Disable-CONFIG_RT_GROUP_SCHED-on-RT.patch @@ -0,0 +1,35 @@ +From 99a129e243d912aefe039e78e82c3f39204fd05c Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 18 Jul 2011 17:03:52 +0200 +Subject: [PATCH 045/347] sched: Disable CONFIG_RT_GROUP_SCHED on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Carsten reported problems when running: + + taskset 01 chrt -f 1 sleep 1 + +from within rc.local on a F15 machine. The task stays running and +never gets on the run queue because some of the run queues have +rt_throttled=1 which does not go away. Works nice from a ssh login +shell. Disabling CONFIG_RT_GROUP_SCHED solves that as well. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + init/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/init/Kconfig b/init/Kconfig +index 45a9846f1464..1793e8bd71ef 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -787,6 +787,7 @@ config CFS_BANDWIDTH + config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on CGROUP_SCHED ++ depends on !PREEMPT_RT_FULL + default n + help + This feature lets you explicitly allocate real CPU bandwidth +-- +2.36.1 + diff --git a/debian/patches-rt/0046-net-core-disable-NET_RX_BUSY_POLL.patch b/debian/patches-rt/0046-net-core-disable-NET_RX_BUSY_POLL.patch new file mode 100644 index 000000000..7eb1fc029 --- /dev/null +++ b/debian/patches-rt/0046-net-core-disable-NET_RX_BUSY_POLL.patch @@ -0,0 +1,38 @@ +From ad59d8a0c65befc94d4dc8d0f000ab096011f737 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Sat, 27 May 2017 19:02:06 +0200 +Subject: [PATCH 046/347] net/core: disable NET_RX_BUSY_POLL +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +sk_busy_loop() does preempt_disable() followed by a few operations which can +take sleeping locks and may get long. +I _think_ that we could use preempt_disable_nort() (in sk_busy_loop()) instead +but after a successfull cmpxchg(&napi->state, …) we would gain the ressource +and could be scheduled out. At this point nobody knows who (which context) owns +it and so it could take a while until the state is realeased and napi_poll() +could be invoked again. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/Kconfig b/net/Kconfig +index 228dfa382eec..bc8d01996f22 100644 +--- a/net/Kconfig ++++ b/net/Kconfig +@@ -275,7 +275,7 @@ config CGROUP_NET_CLASSID + + config NET_RX_BUSY_POLL + bool +- default y ++ default y if !PREEMPT_RT_FULL + + config BQL + bool +-- +2.36.1 + diff --git a/debian/patches-rt/0047-arm-disable-NEON-in-kernel-mode.patch b/debian/patches-rt/0047-arm-disable-NEON-in-kernel-mode.patch new file mode 100644 index 000000000..03e38de78 --- /dev/null +++ b/debian/patches-rt/0047-arm-disable-NEON-in-kernel-mode.patch @@ -0,0 +1,166 @@ +From 8cd6e5200e3869218d2da84e16e4638eb6de6923 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 1 Dec 2017 10:42:03 +0100 +Subject: [PATCH 047/347] arm*: disable NEON in kernel mode +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +NEON in kernel mode is used by the crypto algorithms and raid6 code. +While the raid6 code looks okay, the crypto algorithms do not: NEON +is enabled on first invocation and may allocate/free/map memory before +the NEON mode is disabled again. +This needs to be changed until it can be enabled. +On ARM NEON in kernel mode can be simply disabled. on ARM64 it needs to +stay on due to possible EFI callbacks so here I disable each algorithm. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/Kconfig | 2 +- + arch/arm64/crypto/Kconfig | 28 ++++++++++++++-------------- + arch/arm64/crypto/crc32-ce-glue.c | 3 ++- + 3 files changed, 17 insertions(+), 16 deletions(-) + +diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index 32d59b815b52..ec99422059e3 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -2166,7 +2166,7 @@ config NEON + + config KERNEL_MODE_NEON + bool "Support for NEON in kernel mode" +- depends on NEON && AEABI ++ depends on NEON && AEABI && !PREEMPT_RT_BASE + help + Say Y to include support for NEON in kernel mode. + +diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig +index d51944ff9f91..0d4b3f0cfba6 100644 +--- a/arch/arm64/crypto/Kconfig ++++ b/arch/arm64/crypto/Kconfig +@@ -19,43 +19,43 @@ config CRYPTO_SHA512_ARM64 + + config CRYPTO_SHA1_ARM64_CE + tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA1 + + config CRYPTO_SHA2_ARM64_CE + tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA256_ARM64 + + config CRYPTO_SHA512_ARM64_CE + tristate "SHA-384/SHA-512 digest algorithm (ARMv8 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA512_ARM64 + + config CRYPTO_SHA3_ARM64 + tristate "SHA3 digest algorithm (ARMv8.2 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA3 + + config CRYPTO_SM3_ARM64_CE + tristate "SM3 digest algorithm (ARMv8.2 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SM3 + + config CRYPTO_SM4_ARM64_CE + tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_ALGAPI + select CRYPTO_SM4 + + config CRYPTO_GHASH_ARM64_CE + tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_GF128MUL + select CRYPTO_AES +@@ -63,7 +63,7 @@ config CRYPTO_GHASH_ARM64_CE + + config CRYPTO_CRCT10DIF_ARM64_CE + tristate "CRCT10DIF digest algorithm using PMULL instructions" +- depends on KERNEL_MODE_NEON && CRC_T10DIF ++ depends on KERNEL_MODE_NEON && CRC_T10DIF && !PREEMPT_RT_BASE + select CRYPTO_HASH + + config CRYPTO_CRC32_ARM64_CE +@@ -77,13 +77,13 @@ config CRYPTO_AES_ARM64 + + config CRYPTO_AES_ARM64_CE + tristate "AES core cipher using ARMv8 Crypto Extensions" +- depends on ARM64 && KERNEL_MODE_NEON ++ depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_ALGAPI + select CRYPTO_AES_ARM64 + + config CRYPTO_AES_ARM64_CE_CCM + tristate "AES in CCM mode using ARMv8 Crypto Extensions" +- depends on ARM64 && KERNEL_MODE_NEON ++ depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_ALGAPI + select CRYPTO_AES_ARM64_CE + select CRYPTO_AES_ARM64 +@@ -91,7 +91,7 @@ config CRYPTO_AES_ARM64_CE_CCM + + config CRYPTO_AES_ARM64_CE_BLK + tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64_CE + select CRYPTO_AES_ARM64 +@@ -99,7 +99,7 @@ config CRYPTO_AES_ARM64_CE_BLK + + config CRYPTO_AES_ARM64_NEON_BLK + tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64 + select CRYPTO_AES +@@ -107,13 +107,13 @@ config CRYPTO_AES_ARM64_NEON_BLK + + config CRYPTO_CHACHA20_NEON + tristate "NEON accelerated ChaCha20 symmetric cipher" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_CHACHA20 + + config CRYPTO_AES_ARM64_BS + tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64_NEON_BLK + select CRYPTO_AES_ARM64 +diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c +index 34b4e3d46aab..ae055cdad8cf 100644 +--- a/arch/arm64/crypto/crc32-ce-glue.c ++++ b/arch/arm64/crypto/crc32-ce-glue.c +@@ -208,7 +208,8 @@ static struct shash_alg crc32_pmull_algs[] = { { + + static int __init crc32_pmull_mod_init(void) + { +- if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) { ++ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && ++ !IS_ENABLED(CONFIG_PREEMPT_RT_BASE) && (elf_hwcap & HWCAP_PMULL)) { + crc32_pmull_algs[0].update = crc32_pmull_update; + crc32_pmull_algs[1].update = crc32c_pmull_update; + +-- +2.36.1 + diff --git a/debian/patches-rt/0048-powerpc-Use-generic-rwsem-on-RT.patch b/debian/patches-rt/0048-powerpc-Use-generic-rwsem-on-RT.patch new file mode 100644 index 000000000..24e9ef59e --- /dev/null +++ b/debian/patches-rt/0048-powerpc-Use-generic-rwsem-on-RT.patch @@ -0,0 +1,33 @@ +From 030e3aaf44e1d067c8b44227ace30a35b90b1dda Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: [PATCH 048/347] powerpc: Use generic rwsem on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Use generic code which uses rtmutex + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/Kconfig | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig +index f0e09d5f0bed..d6aae022d8c3 100644 +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -105,10 +105,11 @@ config LOCKDEP_SUPPORT + + config RWSEM_GENERIC_SPINLOCK + bool ++ default y if PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM + bool +- default y ++ default y if !PREEMPT_RT_FULL + + config GENERIC_LOCKBREAK + bool +-- +2.36.1 + diff --git a/debian/patches-rt/0049-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch b/debian/patches-rt/0049-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch new file mode 100644 index 000000000..f019d3e49 --- /dev/null +++ b/debian/patches-rt/0049-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch @@ -0,0 +1,45 @@ +From d20454871d553f909f09445def1ccc5edee641de Mon Sep 17 00:00:00 2001 +From: Bogdan Purcareata <bogdan.purcareata@freescale.com> +Date: Fri, 24 Apr 2015 15:53:13 +0000 +Subject: [PATCH 049/347] powerpc/kvm: Disable in-kernel MPIC emulation for + PREEMPT_RT_FULL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +While converting the openpic emulation code to use a raw_spinlock_t enables +guests to run on RT, there's still a performance issue. For interrupts sent in +directed delivery mode with a multiple CPU mask, the emulated openpic will loop +through all of the VCPUs, and for each VCPUs, it call IRQ_check, which will loop +through all the pending interrupts for that VCPU. This is done while holding the +raw_lock, meaning that in all this time the interrupts and preemption are +disabled on the host Linux. A malicious user app can max both these number and +cause a DoS. + +This temporary fix is sent for two reasons. First is so that users who want to +use the in-kernel MPIC emulation are aware of the potential latencies, thus +making sure that the hardware MPIC and their usage scenario does not involve +interrupts sent in directed delivery mode, and the number of possible pending +interrupts is kept small. Secondly, this should incentivize the development of a +proper openpic emulation that would be better suited for RT. + +Acked-by: Scott Wood <scottwood@freescale.com> +Signed-off-by: Bogdan Purcareata <bogdan.purcareata@freescale.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/powerpc/kvm/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig +index 68a0e9d5b440..6f4d5d7615af 100644 +--- a/arch/powerpc/kvm/Kconfig ++++ b/arch/powerpc/kvm/Kconfig +@@ -178,6 +178,7 @@ config KVM_E500MC + config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && E500 ++ depends on !PREEMPT_RT_FULL + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING +-- +2.36.1 + diff --git a/debian/patches-rt/0050-powerpc-Disable-highmem-on-RT.patch b/debian/patches-rt/0050-powerpc-Disable-highmem-on-RT.patch new file mode 100644 index 000000000..75dd3f847 --- /dev/null +++ b/debian/patches-rt/0050-powerpc-Disable-highmem-on-RT.patch @@ -0,0 +1,29 @@ +From fb0a390ea78c69d7d649e3cca6252b3f18659432 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 18 Jul 2011 17:08:34 +0200 +Subject: [PATCH 050/347] powerpc: Disable highmem on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The current highmem handling on -RT is not compatible and needs fixups. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig +index d6aae022d8c3..f4517f4be192 100644 +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -400,7 +400,7 @@ menu "Kernel options" + + config HIGHMEM + bool "High memory support" +- depends on PPC32 ++ depends on PPC32 && !PREEMPT_RT_FULL + + source kernel/Kconfig.hz + +-- +2.36.1 + diff --git a/debian/patches-rt/0051-mips-Disable-highmem-on-RT.patch b/debian/patches-rt/0051-mips-Disable-highmem-on-RT.patch new file mode 100644 index 000000000..775a7da1c --- /dev/null +++ b/debian/patches-rt/0051-mips-Disable-highmem-on-RT.patch @@ -0,0 +1,29 @@ +From 4ee6a41454883114c19ed1d09d6337846d8fe685 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 18 Jul 2011 17:10:12 +0200 +Subject: [PATCH 051/347] mips: Disable highmem on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The current highmem handling on -RT is not compatible and needs fixups. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/mips/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig +index 8a227a80f6bd..bbd790058e46 100644 +--- a/arch/mips/Kconfig ++++ b/arch/mips/Kconfig +@@ -2523,7 +2523,7 @@ config MIPS_CRC_SUPPORT + # + config HIGHMEM + bool "High Memory Support" +- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA ++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL + + config CPU_SUPPORTS_HIGHMEM + bool +-- +2.36.1 + diff --git a/debian/patches-rt/0052-x86-Use-generic-rwsem_spinlocks-on-rt.patch b/debian/patches-rt/0052-x86-Use-generic-rwsem_spinlocks-on-rt.patch new file mode 100644 index 000000000..61295d2a3 --- /dev/null +++ b/debian/patches-rt/0052-x86-Use-generic-rwsem_spinlocks-on-rt.patch @@ -0,0 +1,34 @@ +From ba7790a3c551c3de98d561dbdfc21b1ee3da42b7 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 26 Jul 2009 02:21:32 +0200 +Subject: [PATCH 052/347] x86: Use generic rwsem_spinlocks on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Simplifies the separation of anon_rw_semaphores and rw_semaphores for +-rt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/Kconfig | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index a8ec5d0c024e..6ee7220e7f47 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -264,8 +264,11 @@ config ARCH_MAY_HAVE_PC_FDC + def_bool y + depends on ISA_DMA_API + ++config RWSEM_GENERIC_SPINLOCK ++ def_bool PREEMPT_RT_FULL ++ + config RWSEM_XCHGADD_ALGORITHM +- def_bool y ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_CALIBRATE_DELAY + def_bool y +-- +2.36.1 + diff --git a/debian/patches-rt/0053-leds-trigger-disable-CPU-trigger-on-RT.patch b/debian/patches-rt/0053-leds-trigger-disable-CPU-trigger-on-RT.patch new file mode 100644 index 000000000..d8b93a3b6 --- /dev/null +++ b/debian/patches-rt/0053-leds-trigger-disable-CPU-trigger-on-RT.patch @@ -0,0 +1,41 @@ +From 2f974cb740c62b0919de64dfd6adffd2ee6de05e Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 23 Jan 2014 14:45:59 +0100 +Subject: [PATCH 053/347] leds: trigger: disable CPU trigger on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +as it triggers: +|CPU: 0 PID: 0 Comm: swapper Not tainted 3.12.8-rt10 #141 +|[<c0014aa4>] (unwind_backtrace+0x0/0xf8) from [<c0012788>] (show_stack+0x1c/0x20) +|[<c0012788>] (show_stack+0x1c/0x20) from [<c043c8dc>] (dump_stack+0x20/0x2c) +|[<c043c8dc>] (dump_stack+0x20/0x2c) from [<c004c5e8>] (__might_sleep+0x13c/0x170) +|[<c004c5e8>] (__might_sleep+0x13c/0x170) from [<c043f270>] (__rt_spin_lock+0x28/0x38) +|[<c043f270>] (__rt_spin_lock+0x28/0x38) from [<c043fa00>] (rt_read_lock+0x68/0x7c) +|[<c043fa00>] (rt_read_lock+0x68/0x7c) from [<c036cf74>] (led_trigger_event+0x2c/0x5c) +|[<c036cf74>] (led_trigger_event+0x2c/0x5c) from [<c036e0bc>] (ledtrig_cpu+0x54/0x5c) +|[<c036e0bc>] (ledtrig_cpu+0x54/0x5c) from [<c000ffd8>] (arch_cpu_idle_exit+0x18/0x1c) +|[<c000ffd8>] (arch_cpu_idle_exit+0x18/0x1c) from [<c00590b8>] (cpu_startup_entry+0xa8/0x234) +|[<c00590b8>] (cpu_startup_entry+0xa8/0x234) from [<c043b2cc>] (rest_init+0xb8/0xe0) +|[<c043b2cc>] (rest_init+0xb8/0xe0) from [<c061ebe0>] (start_kernel+0x2c4/0x380) + + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/leds/trigger/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig +index 4018af769969..b4ce8c115949 100644 +--- a/drivers/leds/trigger/Kconfig ++++ b/drivers/leds/trigger/Kconfig +@@ -63,6 +63,7 @@ config LEDS_TRIGGER_BACKLIGHT + + config LEDS_TRIGGER_CPU + bool "LED CPU Trigger" ++ depends on !PREEMPT_RT_BASE + help + This allows LEDs to be controlled by active CPUs. This shows + the active CPUs across an array of LEDs so you can see which +-- +2.36.1 + diff --git a/debian/patches-rt/0054-cpufreq-drop-K8-s-driver-from-beeing-selected.patch b/debian/patches-rt/0054-cpufreq-drop-K8-s-driver-from-beeing-selected.patch new file mode 100644 index 000000000..d93572692 --- /dev/null +++ b/debian/patches-rt/0054-cpufreq-drop-K8-s-driver-from-beeing-selected.patch @@ -0,0 +1,39 @@ +From b7705efed15774a4424b72dc695c15636b458a3b Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 9 Apr 2015 15:23:01 +0200 +Subject: [PATCH 054/347] cpufreq: drop K8's driver from beeing selected +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Ralf posted a picture of a backtrace from + +| powernowk8_target_fn() -> transition_frequency_fidvid() and then at the +| end: +| 932 policy = cpufreq_cpu_get(smp_processor_id()); +| 933 cpufreq_cpu_put(policy); + +crashing the system on -RT. I assumed that policy was a NULL pointer but +was rulled out. Since Ralf can't do any more investigations on this and +I have no machine with this, I simply switch it off. + +Reported-by: Ralf Mardorf <ralf.mardorf@alice-dsl.net> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/cpufreq/Kconfig.x86 | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 +index 35f71825b7f3..bb4a6160d0f7 100644 +--- a/drivers/cpufreq/Kconfig.x86 ++++ b/drivers/cpufreq/Kconfig.x86 +@@ -125,7 +125,7 @@ config X86_POWERNOW_K7_ACPI + + config X86_POWERNOW_K8 + tristate "AMD Opteron/Athlon64 PowerNow!" +- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ ++ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE + help + This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. + Support for K10 and newer processors is now in acpi-cpufreq. +-- +2.36.1 + diff --git a/debian/patches-rt/0055-md-disable-bcache.patch b/debian/patches-rt/0055-md-disable-bcache.patch new file mode 100644 index 000000000..f2de464c8 --- /dev/null +++ b/debian/patches-rt/0055-md-disable-bcache.patch @@ -0,0 +1,41 @@ +From 660157bd8a977bb04e9ef58df7270b51f7e315e1 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 29 Aug 2013 11:48:57 +0200 +Subject: [PATCH 055/347] md: disable bcache +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +It uses anon semaphores +|drivers/md/bcache/request.c: In function ‘cached_dev_write_complete’: +|drivers/md/bcache/request.c:1007:2: error: implicit declaration of function ‘up_read_non_owner’ [-Werror=implicit-function-declaration] +| up_read_non_owner(&dc->writeback_lock); +| ^ +|drivers/md/bcache/request.c: In function ‘request_write’: +|drivers/md/bcache/request.c:1033:2: error: implicit declaration of function ‘down_read_non_owner’ [-Werror=implicit-function-declaration] +| down_read_non_owner(&dc->writeback_lock); +| ^ + +either we get rid of those or we have to introduce them… + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/md/bcache/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig +index f6e0a8b3a61e..18c03d79a442 100644 +--- a/drivers/md/bcache/Kconfig ++++ b/drivers/md/bcache/Kconfig +@@ -1,6 +1,7 @@ + + config BCACHE + tristate "Block device as cache" ++ depends on !PREEMPT_RT_FULL + select CRC64 + help + Allows a block device to be used as cache for other devices; uses +-- +2.36.1 + diff --git a/debian/patches-rt/0056-efi-Disable-runtime-services-on-RT.patch b/debian/patches-rt/0056-efi-Disable-runtime-services-on-RT.patch new file mode 100644 index 000000000..fe647f6c4 --- /dev/null +++ b/debian/patches-rt/0056-efi-Disable-runtime-services-on-RT.patch @@ -0,0 +1,46 @@ +From 6c62319a5f5caaf647997706f6996ce4e8dfc939 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 26 Jul 2018 15:03:16 +0200 +Subject: [PATCH 056/347] efi: Disable runtime services on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Based on meassurements the EFI functions get_variable / +get_next_variable take up to 2us which looks okay. +The functions get_time, set_time take around 10ms. Those 10ms are too +much. Even one ms would be too much. +Ard mentioned that SetVariable might even trigger larger latencies if +the firware will erase flash blocks on NOR. + +The time-functions are used by efi-rtc and can be triggered during +runtimed (either via explicit read/write or ntp sync). + +The variable write could be used by pstore. +These functions can be disabled without much of a loss. The poweroff / +reboot hooks may be provided by PSCI. + +Disable EFI's runtime wrappers. + +This was observed on "EFI v2.60 by SoftIron Overdrive 1000". + +Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/firmware/efi/efi.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c +index e89932f1ae65..221957ccdb0b 100644 +--- a/drivers/firmware/efi/efi.c ++++ b/drivers/firmware/efi/efi.c +@@ -87,7 +87,7 @@ struct mm_struct efi_mm = { + + struct workqueue_struct *efi_rts_wq; + +-static bool disable_runtime; ++static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT_BASE); + static int __init setup_noefi(char *arg) + { + disable_runtime = true; +-- +2.36.1 + diff --git a/debian/patches-rt/0057-printk-Add-a-printk-kill-switch.patch b/debian/patches-rt/0057-printk-Add-a-printk-kill-switch.patch new file mode 100644 index 000000000..54f3d96d2 --- /dev/null +++ b/debian/patches-rt/0057-printk-Add-a-printk-kill-switch.patch @@ -0,0 +1,174 @@ +From 0450159a3552782546de4c88cbeae98683079ee9 Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 22 Jul 2011 17:58:40 +0200 +Subject: [PATCH 057/347] printk: Add a printk kill switch +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Add a prinkt-kill-switch. This is used from (NMI) watchdog to ensure that +it does not dead-lock with the early printk code. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/printk.h | 2 ++ + kernel/printk/printk.c | 79 +++++++++++++++++++++++++++++++----------- + kernel/watchdog_hld.c | 10 ++++++ + 3 files changed, 71 insertions(+), 20 deletions(-) + +diff --git a/include/linux/printk.h b/include/linux/printk.h +index 6dd867e39365..b9d050428456 100644 +--- a/include/linux/printk.h ++++ b/include/linux/printk.h +@@ -140,9 +140,11 @@ struct va_format { + #ifdef CONFIG_EARLY_PRINTK + extern asmlinkage __printf(1, 2) + void early_printk(const char *fmt, ...); ++extern void printk_kill(void); + #else + static inline __printf(1, 2) __cold + void early_printk(const char *s, ...) { } ++static inline void printk_kill(void) { } + #endif + + #ifdef CONFIG_PRINTK_NMI +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index 2ba16c426ba5..963c20ab9548 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -407,6 +407,58 @@ DEFINE_RAW_SPINLOCK(logbuf_lock); + printk_safe_exit_irqrestore(flags); \ + } while (0) + ++#ifdef CONFIG_EARLY_PRINTK ++struct console *early_console; ++ ++static void early_vprintk(const char *fmt, va_list ap) ++{ ++ if (early_console) { ++ char buf[512]; ++ int n = vscnprintf(buf, sizeof(buf), fmt, ap); ++ ++ early_console->write(early_console, buf, n); ++ } ++} ++ ++asmlinkage void early_printk(const char *fmt, ...) ++{ ++ va_list ap; ++ ++ va_start(ap, fmt); ++ early_vprintk(fmt, ap); ++ va_end(ap); ++} ++ ++/* ++ * This is independent of any log levels - a global ++ * kill switch that turns off all of printk. ++ * ++ * Used by the NMI watchdog if early-printk is enabled. ++ */ ++static bool __read_mostly printk_killswitch; ++ ++void printk_kill(void) ++{ ++ printk_killswitch = true; ++} ++ ++#ifdef CONFIG_PRINTK ++static int forced_early_printk(const char *fmt, va_list ap) ++{ ++ if (!printk_killswitch) ++ return 0; ++ early_vprintk(fmt, ap); ++ return 1; ++} ++#endif ++ ++#else ++static inline int forced_early_printk(const char *fmt, va_list ap) ++{ ++ return 0; ++} ++#endif ++ + #ifdef CONFIG_PRINTK + DECLARE_WAIT_QUEUE_HEAD(log_wait); + /* the next printk record to read by syslog(READ) or /proc/kmsg */ +@@ -1935,6 +1987,13 @@ asmlinkage int vprintk_emit(int facility, int level, + unsigned long flags; + u64 curr_log_seq; + ++ /* ++ * Fall back to early_printk if a debugging subsystem has ++ * killed printk output ++ */ ++ if (unlikely(forced_early_printk(fmt, args))) ++ return 1; ++ + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; +@@ -2079,26 +2138,6 @@ static bool suppress_message_printing(int level) { return false; } + + #endif /* CONFIG_PRINTK */ + +-#ifdef CONFIG_EARLY_PRINTK +-struct console *early_console; +- +-asmlinkage __visible void early_printk(const char *fmt, ...) +-{ +- va_list ap; +- char buf[512]; +- int n; +- +- if (!early_console) +- return; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- va_end(ap); +- +- early_console->write(early_console, buf, n); +-} +-#endif +- + static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) + { +diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c +index 71381168dede..685443375dc0 100644 +--- a/kernel/watchdog_hld.c ++++ b/kernel/watchdog_hld.c +@@ -24,6 +24,8 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); + static DEFINE_PER_CPU(bool, watchdog_nmi_touch); + static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); + static DEFINE_PER_CPU(struct perf_event *, dead_event); ++static DEFINE_RAW_SPINLOCK(watchdog_output_lock); ++ + static struct cpumask dead_events_mask; + + static unsigned long hardlockup_allcpu_dumped; +@@ -134,6 +136,13 @@ static void watchdog_overflow_callback(struct perf_event *event, + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; ++ /* ++ * If early-printk is enabled then make sure we do not ++ * lock up in printk() and kill console logging: ++ */ ++ printk_kill(); ++ ++ raw_spin_lock(&watchdog_output_lock); + + pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + print_modules(); +@@ -151,6 +160,7 @@ static void watchdog_overflow_callback(struct perf_event *event, + !test_and_set_bit(0, &hardlockup_allcpu_dumped)) + trigger_allbutself_cpu_backtrace(); + ++ raw_spin_unlock(&watchdog_output_lock); + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); + +-- +2.36.1 + diff --git a/debian/patches-rt/0058-printk-Add-force_early_printk-boot-param-to-help-wit.patch b/debian/patches-rt/0058-printk-Add-force_early_printk-boot-param-to-help-wit.patch new file mode 100644 index 000000000..68fc30c35 --- /dev/null +++ b/debian/patches-rt/0058-printk-Add-force_early_printk-boot-param-to-help-wit.patch @@ -0,0 +1,39 @@ +From fa9f6eea1ebbb987a57d889ad00f142a21aa1843 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Fri, 2 Sep 2011 14:41:29 +0200 +Subject: [PATCH 058/347] printk: Add "force_early_printk" boot param to help + with debugging +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Gives me an option to screw printk and actually see what the machine +says. + +Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> +Link: http://lkml.kernel.org/r/1314967289.1301.11.camel@twins +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Link: http://lkml.kernel.org/n/tip-ykb97nsfmobq44xketrxs977@git.kernel.org +--- + kernel/printk/printk.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index 963c20ab9548..7b774743e1ac 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -437,6 +437,13 @@ asmlinkage void early_printk(const char *fmt, ...) + */ + static bool __read_mostly printk_killswitch; + ++static int __init force_early_printk_setup(char *str) ++{ ++ printk_killswitch = true; ++ return 0; ++} ++early_param("force_early_printk", force_early_printk_setup); ++ + void printk_kill(void) + { + printk_killswitch = true; +-- +2.36.1 + diff --git a/debian/patches-rt/0059-preempt-Provide-preempt_-_-no-rt-variants.patch b/debian/patches-rt/0059-preempt-Provide-preempt_-_-no-rt-variants.patch new file mode 100644 index 000000000..c4b54be3a --- /dev/null +++ b/debian/patches-rt/0059-preempt-Provide-preempt_-_-no-rt-variants.patch @@ -0,0 +1,53 @@ +From 284c759a4a661cea5ac84fac628731f6b79d6b2e Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 24 Jul 2009 12:38:56 +0200 +Subject: [PATCH 059/347] preempt: Provide preempt_*_(no)rt variants +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +RT needs a few preempt_disable/enable points which are not necessary +otherwise. Implement variants to avoid #ifdeffery. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/preempt.h | 18 +++++++++++++++++- + 1 file changed, 17 insertions(+), 1 deletion(-) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index 3196d0e76719..f7a17fcc3fec 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -181,7 +181,11 @@ do { \ + preempt_count_dec(); \ + } while (0) + +-#define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#else ++# define preempt_enable_no_resched() preempt_enable() ++#endif + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + +@@ -298,6 +302,18 @@ do { \ + set_preempt_need_resched(); \ + } while (0) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define preempt_disable_rt() preempt_disable() ++# define preempt_enable_rt() preempt_enable() ++# define preempt_disable_nort() barrier() ++# define preempt_enable_nort() barrier() ++#else ++# define preempt_disable_rt() barrier() ++# define preempt_enable_rt() barrier() ++# define preempt_disable_nort() preempt_disable() ++# define preempt_enable_nort() preempt_enable() ++#endif ++ + #ifdef CONFIG_PREEMPT_NOTIFIERS + + struct preempt_notifier; +-- +2.36.1 + diff --git a/debian/patches-rt/0060-futex-workaround-migrate_disable-enable-in-different.patch b/debian/patches-rt/0060-futex-workaround-migrate_disable-enable-in-different.patch new file mode 100644 index 000000000..373f02a64 --- /dev/null +++ b/debian/patches-rt/0060-futex-workaround-migrate_disable-enable-in-different.patch @@ -0,0 +1,70 @@ +From d142001fdbdd8cc5fb558e9c3fa110f575875355 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 8 Mar 2017 14:23:35 +0100 +Subject: [PATCH 060/347] futex: workaround migrate_disable/enable in different + context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +migrate_disable()/migrate_enable() takes a different path in atomic() vs +!atomic() context. These little hacks ensure that we don't underflow / overflow +the migrate code counts properly while we lock the hb lockwith interrupts +enabled and unlock it with interrupts disabled. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/futex.c | 19 +++++++++++++++++++ + 1 file changed, 19 insertions(+) + +diff --git a/kernel/futex.c b/kernel/futex.c +index 3c67da9b8408..fac994367189 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2998,6 +2998,14 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + * before __rt_mutex_start_proxy_lock() is done. + */ + raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); ++ /* ++ * the migrate_disable() here disables migration in the in_atomic() fast ++ * path which is enabled again in the following spin_unlock(). We have ++ * one migrate_disable() pending in the slow-path which is reversed ++ * after the raw_spin_unlock_irq() where we leave the atomic context. ++ */ ++ migrate_disable(); ++ + spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter +@@ -3006,6 +3014,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + */ + ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); + raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); ++ migrate_enable(); + + if (ret) { + if (ret == 1) +@@ -3140,11 +3149,21 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + * rt_waiter. Also see the WARN in wake_futex_pi(). + */ + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); ++ /* ++ * Magic trickery for now to make the RT migrate disable ++ * logic happy. The following spin_unlock() happens with ++ * interrupts disabled so the internal migrate_enable() ++ * won't undo the migrate_disable() which was issued when ++ * locking hb->lock. ++ */ ++ migrate_disable(); + spin_unlock(&hb->lock); + + /* drops pi_state->pi_mutex.wait_lock */ + ret = wake_futex_pi(uaddr, uval, pi_state); + ++ migrate_enable(); ++ + put_pi_state(pi_state); + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0061-rt-Add-local-irq-locks.patch b/debian/patches-rt/0061-rt-Add-local-irq-locks.patch new file mode 100644 index 000000000..205579b09 --- /dev/null +++ b/debian/patches-rt/0061-rt-Add-local-irq-locks.patch @@ -0,0 +1,341 @@ +From d870e74a28988a6bb802f1e4bffd33297e63053f Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 20 Jun 2011 09:03:47 +0200 +Subject: [PATCH 061/347] rt: Add local irq locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Introduce locallock. For !RT this maps to preempt_disable()/ +local_irq_disable() so there is not much that changes. For RT this will +map to a spinlock. This makes preemption possible and locked "ressource" +gets the lockdep anotation it wouldn't have otherwise. The locks are +recursive for owner == current. Also, all locks user migrate_disable() +which ensures that the task is not migrated to another CPU while the lock +is held and the owner is preempted. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/locallock.h | 271 ++++++++++++++++++++++++++++++++++++++ + include/linux/percpu.h | 29 ++++ + 2 files changed, 300 insertions(+) + create mode 100644 include/linux/locallock.h + +diff --git a/include/linux/locallock.h b/include/linux/locallock.h +new file mode 100644 +index 000000000000..d658c2552601 +--- /dev/null ++++ b/include/linux/locallock.h +@@ -0,0 +1,271 @@ ++#ifndef _LINUX_LOCALLOCK_H ++#define _LINUX_LOCALLOCK_H ++ ++#include <linux/percpu.h> ++#include <linux/spinlock.h> ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define LL_WARN(cond) WARN_ON(cond) ++#else ++# define LL_WARN(cond) do { } while (0) ++#endif ++ ++/* ++ * per cpu lock based substitute for local_irq_*() ++ */ ++struct local_irq_lock { ++ spinlock_t lock; ++ struct task_struct *owner; ++ int nestcnt; ++ unsigned long flags; ++}; ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ ++ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ ++ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } ++ ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ ++ DECLARE_PER_CPU(struct local_irq_lock, lvar) ++ ++#define local_irq_lock_init(lvar) \ ++ do { \ ++ int __cpu; \ ++ for_each_possible_cpu(__cpu) \ ++ spin_lock_init(&per_cpu(lvar, __cpu).lock); \ ++ } while (0) ++ ++static inline void __local_lock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ spin_lock(&lv->lock); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ } ++ lv->nestcnt++; ++} ++ ++#define local_lock(lvar) \ ++ do { __local_lock(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_on(lvar, cpu) \ ++ do { __local_lock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline int __local_trylock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current && spin_trylock(&lv->lock)) { ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++ return 1; ++ } else if (lv->owner == current) { ++ lv->nestcnt++; ++ return 1; ++ } ++ return 0; ++} ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ int __locked; \ ++ __locked = __local_trylock(&get_local_var(lvar)); \ ++ if (!__locked) \ ++ put_local_var(lvar); \ ++ __locked; \ ++ }) ++ ++static inline void __local_unlock(struct local_irq_lock *lv) ++{ ++ LL_WARN(lv->nestcnt == 0); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return; ++ ++ lv->owner = NULL; ++ spin_unlock(&lv->lock); ++} ++ ++#define local_unlock(lvar) \ ++ do { \ ++ __local_unlock(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_on(lvar, cpu) \ ++ do { __local_unlock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_lock_irq(struct local_irq_lock *lv) ++{ ++ spin_lock_irqsave(&lv->lock, lv->flags); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++} ++ ++#define local_lock_irq(lvar) \ ++ do { __local_lock_irq(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_irq_on(lvar, cpu) \ ++ do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_unlock_irq(struct local_irq_lock *lv) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ lv->owner = NULL; ++ lv->nestcnt = 0; ++ spin_unlock_irq(&lv->lock); ++} ++ ++#define local_unlock_irq(lvar) \ ++ do { \ ++ __local_unlock_irq(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irq_on(lvar, cpu) \ ++ do { \ ++ __local_unlock_irq(&per_cpu(lvar, cpu)); \ ++ } while (0) ++ ++static inline int __local_lock_irqsave(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ __local_lock_irq(lv); ++ return 0; ++ } else { ++ lv->nestcnt++; ++ return 1; ++ } ++} ++ ++#define local_lock_irqsave(lvar, _flags) \ ++ do { \ ++ if (__local_lock_irqsave(&get_local_var(lvar))) \ ++ put_local_var(lvar); \ ++ _flags = __this_cpu_read(lvar.flags); \ ++ } while (0) ++ ++#define local_lock_irqsave_on(lvar, _flags, cpu) \ ++ do { \ ++ __local_lock_irqsave(&per_cpu(lvar, cpu)); \ ++ _flags = per_cpu(lvar, cpu).flags; \ ++ } while (0) ++ ++static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, ++ unsigned long flags) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return 0; ++ ++ lv->owner = NULL; ++ spin_unlock_irqrestore(&lv->lock, lv->flags); ++ return 1; ++} ++ ++#define local_unlock_irqrestore(lvar, flags) \ ++ do { \ ++ if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irqrestore_on(lvar, flags, cpu) \ ++ do { \ ++ __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ ++ } while (0) ++ ++#define local_spin_trylock_irq(lvar, lock) \ ++ ({ \ ++ int __locked; \ ++ local_lock_irq(lvar); \ ++ __locked = spin_trylock(lock); \ ++ if (!__locked) \ ++ local_unlock_irq(lvar); \ ++ __locked; \ ++ }) ++ ++#define local_spin_lock_irq(lvar, lock) \ ++ do { \ ++ local_lock_irq(lvar); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irq(lvar, lock) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irq(lvar); \ ++ } while (0) ++ ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ do { \ ++ local_lock_irqsave(lvar, flags); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irqrestore(lvar, flags); \ ++ } while (0) ++ ++#define get_locked_var(lvar, var) \ ++ (*({ \ ++ local_lock(lvar); \ ++ this_cpu_ptr(&var); \ ++ })) ++ ++#define put_locked_var(lvar, var) local_unlock(lvar); ++ ++#define local_lock_cpu(lvar) \ ++ ({ \ ++ local_lock(lvar); \ ++ smp_processor_id(); \ ++ }) ++ ++#define local_unlock_cpu(lvar) local_unlock(lvar) ++ ++#else /* PREEMPT_RT_BASE */ ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar ++ ++static inline void local_irq_lock_init(int lvar) { } ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ preempt_disable(); \ ++ 1; \ ++ }) ++ ++#define local_lock(lvar) preempt_disable() ++#define local_unlock(lvar) preempt_enable() ++#define local_lock_irq(lvar) local_irq_disable() ++#define local_lock_irq_on(lvar, cpu) local_irq_disable() ++#define local_unlock_irq(lvar) local_irq_enable() ++#define local_unlock_irq_on(lvar, cpu) local_irq_enable() ++#define local_lock_irqsave(lvar, flags) local_irq_save(flags) ++#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) ++ ++#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) ++#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) ++#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ spin_lock_irqsave(lock, flags) ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ spin_unlock_irqrestore(lock, flags) ++ ++#define get_locked_var(lvar, var) get_cpu_var(var) ++#define put_locked_var(lvar, var) put_cpu_var(var) ++ ++#define local_lock_cpu(lvar) get_cpu() ++#define local_unlock_cpu(lvar) put_cpu() ++ ++#endif ++ ++#endif +diff --git a/include/linux/percpu.h b/include/linux/percpu.h +index 70b7123f38c7..24421bf8c4b3 100644 +--- a/include/linux/percpu.h ++++ b/include/linux/percpu.h +@@ -19,6 +19,35 @@ + #define PERCPU_MODULE_RESERVE 0 + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++#define get_local_var(var) (*({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(&var); })) ++ ++#define put_local_var(var) do { \ ++ (void)&(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++# define get_local_ptr(var) ({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(var); }) ++ ++# define put_local_ptr(var) do { \ ++ (void)(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++#else ++ ++#define get_local_var(var) get_cpu_var(var) ++#define put_local_var(var) put_cpu_var(var) ++#define get_local_ptr(var) get_cpu_ptr(var) ++#define put_local_ptr(var) put_cpu_ptr(var) ++ ++#endif ++ + /* minimum unit size, also is the maximum supported allocation size */ + #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) + +-- +2.36.1 + diff --git a/debian/patches-rt/0062-locallock-provide-get-put-_locked_ptr-variants.patch b/debian/patches-rt/0062-locallock-provide-get-put-_locked_ptr-variants.patch new file mode 100644 index 000000000..d3d7ffdeb --- /dev/null +++ b/debian/patches-rt/0062-locallock-provide-get-put-_locked_ptr-variants.patch @@ -0,0 +1,49 @@ +From 5b024e1bb773440c6f4c48fdb21090bfadab8a7a Mon Sep 17 00:00:00 2001 +From: Julia Cartwright <julia@ni.com> +Date: Mon, 7 May 2018 08:58:56 -0500 +Subject: [PATCH 062/347] locallock: provide {get,put}_locked_ptr() variants +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Provide a set of locallocked accessors for pointers to per-CPU data; +this is useful for dynamically-allocated per-CPU regions, for example. + +These are symmetric with the {get,put}_cpu_ptr() per-CPU accessor +variants. + +Signed-off-by: Julia Cartwright <julia@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/locallock.h | 10 ++++++++++ + 1 file changed, 10 insertions(+) + +diff --git a/include/linux/locallock.h b/include/linux/locallock.h +index d658c2552601..921eab83cd34 100644 +--- a/include/linux/locallock.h ++++ b/include/linux/locallock.h +@@ -222,6 +222,14 @@ static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, + + #define put_locked_var(lvar, var) local_unlock(lvar); + ++#define get_locked_ptr(lvar, var) \ ++ ({ \ ++ local_lock(lvar); \ ++ this_cpu_ptr(var); \ ++ }) ++ ++#define put_locked_ptr(lvar, var) local_unlock(lvar); ++ + #define local_lock_cpu(lvar) \ + ({ \ + local_lock(lvar); \ +@@ -262,6 +270,8 @@ static inline void local_irq_lock_init(int lvar) { } + + #define get_locked_var(lvar, var) get_cpu_var(var) + #define put_locked_var(lvar, var) put_cpu_var(var) ++#define get_locked_ptr(lvar, var) get_cpu_ptr(var) ++#define put_locked_ptr(lvar, var) put_cpu_ptr(var) + + #define local_lock_cpu(lvar) get_cpu() + #define local_unlock_cpu(lvar) put_cpu() +-- +2.36.1 + diff --git a/debian/patches-rt/0063-mm-scatterlist-Do-not-disable-irqs-on-RT.patch b/debian/patches-rt/0063-mm-scatterlist-Do-not-disable-irqs-on-RT.patch new file mode 100644 index 000000000..368da63b4 --- /dev/null +++ b/debian/patches-rt/0063-mm-scatterlist-Do-not-disable-irqs-on-RT.patch @@ -0,0 +1,30 @@ +From 48680d53abae6cad7df7eb850fb2acb81da70ef8 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 3 Jul 2009 08:44:34 -0500 +Subject: [PATCH 063/347] mm/scatterlist: Do not disable irqs on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +For -RT it is enough to keep pagefault disabled (which is currently handled by +kmap_atomic()). + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + lib/scatterlist.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/lib/scatterlist.c b/lib/scatterlist.c +index 3b859201f84c..093c3aa3d895 100644 +--- a/lib/scatterlist.c ++++ b/lib/scatterlist.c +@@ -777,7 +777,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter) + flush_kernel_dcache_page(miter->page); + + if (miter->__flags & SG_MITER_ATOMIC) { +- WARN_ON_ONCE(preemptible()); ++ WARN_ON_ONCE(!pagefault_disabled()); + kunmap_atomic(miter->addr); + } else + kunmap(miter->page); +-- +2.36.1 + diff --git a/debian/patches-rt/0064-signal-x86-Delay-calling-signals-in-atomic.patch b/debian/patches-rt/0064-signal-x86-Delay-calling-signals-in-atomic.patch new file mode 100644 index 000000000..8acb6a058 --- /dev/null +++ b/debian/patches-rt/0064-signal-x86-Delay-calling-signals-in-atomic.patch @@ -0,0 +1,154 @@ +From 47c69a6b85d4820b49840b1bd914a970e7eb6851 Mon Sep 17 00:00:00 2001 +From: Oleg Nesterov <oleg@redhat.com> +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: [PATCH 064/347] signal/x86: Delay calling signals in atomic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On x86_64 we must disable preemption before we enable interrupts +for stack faults, int3 and debugging, because the current task is using +a per CPU debug stack defined by the IST. If we schedule out, another task +can come in and use the same stack and cause the stack to be corrupted +and crash the kernel on return. + +When CONFIG_PREEMPT_RT_FULL is enabled, spin_locks become mutexes, and +one of these is the spin lock used in signal handling. + +Some of the debug code (int3) causes do_trap() to send a signal. +This function calls a spin lock that has been converted to a mutex +and has the possibility to sleep. If this happens, the above issues with +the corrupted stack is possible. + +Instead of calling the signal right away, for PREEMPT_RT and x86_64, +the signal information is stored on the stacks task_struct and +TIF_NOTIFY_RESUME is set. Then on exit of the trap, the signal resume +code will send the signal when preemption is enabled. + +[ rostedt: Switched from #ifdef CONFIG_PREEMPT_RT_FULL to + ARCH_RT_DELAYS_SIGNAL_SEND and added comments to the code. ] + + +Signed-off-by: Oleg Nesterov <oleg@redhat.com> +Signed-off-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/entry/common.c | 7 +++++++ + arch/x86/include/asm/signal.h | 13 ++++++++++++ + include/linux/sched.h | 4 ++++ + kernel/signal.c | 37 +++++++++++++++++++++++++++++++++-- + 4 files changed, 59 insertions(+), 2 deletions(-) + +diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c +index 8353348ddeaf..91676b0d2d4c 100644 +--- a/arch/x86/entry/common.c ++++ b/arch/x86/entry/common.c +@@ -152,6 +152,13 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) + if (cached_flags & _TIF_NEED_RESCHED) + schedule(); + ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (unlikely(current->forced_info.si_signo)) { ++ struct task_struct *t = current; ++ force_sig_info(t->forced_info.si_signo, &t->forced_info, t); ++ t->forced_info.si_signo = 0; ++ } ++#endif + if (cached_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + +diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h +index 33d3c88a7225..fb0438d06ca7 100644 +--- a/arch/x86/include/asm/signal.h ++++ b/arch/x86/include/asm/signal.h +@@ -28,6 +28,19 @@ typedef struct { + #define SA_IA32_ABI 0x02000000u + #define SA_X32_ABI 0x01000000u + ++/* ++ * Because some traps use the IST stack, we must keep preemption ++ * disabled while calling do_trap(), but do_trap() may call ++ * force_sig_info() which will grab the signal spin_locks for the ++ * task, which in PREEMPT_RT_FULL are mutexes. By defining ++ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set ++ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the ++ * trap. ++ */ ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) ++#define ARCH_RT_DELAYS_SIGNAL_SEND ++#endif ++ + #ifndef CONFIG_COMPAT + typedef sigset_t compat_sigset_t; + #endif +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 52069b9ddce8..56047f57ebc7 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -881,6 +881,10 @@ struct task_struct { + /* Restored if set_restore_sigmask() was used: */ + sigset_t saved_sigmask; + struct sigpending pending; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* TODO: move me into ->restart_block ? */ ++ struct siginfo forced_info; ++#endif + unsigned long sas_ss_sp; + size_t sas_ss_size; + unsigned int sas_ss_flags; +diff --git a/kernel/signal.c b/kernel/signal.c +index 23764988b5d1..58bd3b3dd499 100644 +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -1283,8 +1283,8 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +-int +-force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++static int ++do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) + { + unsigned long int flags; + int ret, blocked, ignored; +@@ -1313,6 +1313,39 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t) + return ret; + } + ++int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++{ ++/* ++ * On some archs, PREEMPT_RT has to delay sending a signal from a trap ++ * since it can not enable preemption, and the signal code's spin_locks ++ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will ++ * send the signal on exit of the trap. ++ */ ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (in_atomic()) { ++ if (WARN_ON_ONCE(t != current)) ++ return 0; ++ if (WARN_ON_ONCE(t->forced_info.si_signo)) ++ return 0; ++ ++ if (is_si_special(info)) { ++ WARN_ON_ONCE(info != SEND_SIG_PRIV); ++ t->forced_info.si_signo = sig; ++ t->forced_info.si_errno = 0; ++ t->forced_info.si_code = SI_KERNEL; ++ t->forced_info.si_pid = 0; ++ t->forced_info.si_uid = 0; ++ } else { ++ t->forced_info = *info; ++ } ++ ++ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); ++ return 0; ++ } ++#endif ++ return do_force_sig_info(sig, info, t); ++} ++ + /* + * Nuke all other threads in the group. + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0065-x86-signal-delay-calling-signals-on-32bit.patch b/debian/patches-rt/0065-x86-signal-delay-calling-signals-on-32bit.patch new file mode 100644 index 000000000..d03ec8bc1 --- /dev/null +++ b/debian/patches-rt/0065-x86-signal-delay-calling-signals-on-32bit.patch @@ -0,0 +1,49 @@ +From b2265189b45c7240033cc856851c5bbf4c2dc323 Mon Sep 17 00:00:00 2001 +From: Yang Shi <yang.shi@linaro.org> +Date: Thu, 10 Dec 2015 10:58:51 -0800 +Subject: [PATCH 065/347] x86/signal: delay calling signals on 32bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When running some ptrace single step tests on x86-32 machine, the below problem +is triggered: + +BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 +in_atomic(): 1, irqs_disabled(): 0, pid: 1041, name: dummy2 +Preemption disabled at:[<c100326f>] do_debug+0x1f/0x1a0 + +CPU: 10 PID: 1041 Comm: dummy2 Tainted: G W 4.1.13-rt13 #1 +Call Trace: + [<c1aa8306>] dump_stack+0x46/0x5c + [<c1080517>] ___might_sleep+0x137/0x220 + [<c1ab0eff>] rt_spin_lock+0x1f/0x80 + [<c1064b5a>] do_force_sig_info+0x2a/0xc0 + [<c106567d>] force_sig_info+0xd/0x10 + [<c1010cff>] send_sigtrap+0x6f/0x80 + [<c10033b1>] do_debug+0x161/0x1a0 + [<c1ab2921>] debug_stack_correct+0x2e/0x35 + +This happens since 959274753857 ("x86, traps: Track entry into and exit +from IST context") which was merged in v4.1-rc1. + +Signed-off-by: Yang Shi <yang.shi@linaro.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/include/asm/signal.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h +index fb0438d06ca7..c00e27af2205 100644 +--- a/arch/x86/include/asm/signal.h ++++ b/arch/x86/include/asm/signal.h +@@ -37,7 +37,7 @@ typedef struct { + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the + * trap. + */ +-#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) ++#if defined(CONFIG_PREEMPT_RT_FULL) + #define ARCH_RT_DELAYS_SIGNAL_SEND + #endif + +-- +2.36.1 + diff --git a/debian/patches-rt/0066-buffer_head-Replace-bh_uptodate_lock-for-rt.patch b/debian/patches-rt/0066-buffer_head-Replace-bh_uptodate_lock-for-rt.patch new file mode 100644 index 000000000..711c91563 --- /dev/null +++ b/debian/patches-rt/0066-buffer_head-Replace-bh_uptodate_lock-for-rt.patch @@ -0,0 +1,197 @@ +From a309856cae0c403bb844c9c89bd345168c2f6ee1 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 18 Mar 2011 09:18:52 +0100 +Subject: [PATCH 066/347] buffer_head: Replace bh_uptodate_lock for -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Wrap the bit_spin_lock calls into a separate inline and add the RT +replacements with a real spinlock. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + fs/buffer.c | 21 +++++++-------------- + fs/ext4/page-io.c | 6 ++---- + fs/ntfs/aops.c | 10 +++------- + include/linux/buffer_head.h | 34 ++++++++++++++++++++++++++++++++++ + 4 files changed, 46 insertions(+), 25 deletions(-) + +diff --git a/fs/buffer.c b/fs/buffer.c +index 356e289d19f2..ab18ec733ed3 100644 +--- a/fs/buffer.c ++++ b/fs/buffer.c +@@ -274,8 +274,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) + * decide that the page is now completely done. + */ + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -288,8 +287,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + + /* + * If none of the buffers had errors and they are all +@@ -301,9 +299,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /* +@@ -330,8 +326,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) + } + + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + + clear_buffer_async_write(bh); + unlock_buffer(bh); +@@ -343,15 +338,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) + } + tmp = tmp->b_this_page; + } +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + end_page_writeback(page); + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + EXPORT_SYMBOL(end_buffer_async_write); + +@@ -3372,6 +3364,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); + if (ret) { + INIT_LIST_HEAD(&ret->b_assoc_buffers); ++ buffer_head_init_locks(ret); + preempt_disable(); + __this_cpu_inc(bh_accounting.nr); + recalc_bh_state(); +diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c +index 3de933354a08..838d9f4fc554 100644 +--- a/fs/ext4/page-io.c ++++ b/fs/ext4/page-io.c +@@ -95,8 +95,7 @@ static void ext4_finish_bio(struct bio *bio) + * We check all buffers in the page under BH_Uptodate_Lock + * to avoid races with other end io clearing async_write flags + */ +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &head->b_state); ++ flags = bh_uptodate_lock_irqsave(head); + do { + if (bh_offset(bh) < bio_start || + bh_offset(bh) + bh->b_size > bio_end) { +@@ -110,8 +109,7 @@ static void ext4_finish_bio(struct bio *bio) + buffer_io_error(bh); + } + } while ((bh = bh->b_this_page) != head); +- bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(head, flags); + if (!under_io) { + #ifdef CONFIG_EXT4_FS_ENCRYPTION + if (data_page) +diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c +index 8946130c87ad..71d0b3ba70f8 100644 +--- a/fs/ntfs/aops.c ++++ b/fs/ntfs/aops.c +@@ -106,8 +106,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) + "0x%llx.", (unsigned long long)bh->b_blocknr); + } + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -122,8 +121,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + /* + * If none of the buffers had errors then we can set the page uptodate, + * but we first have to perform the post read mst fixups, if the +@@ -156,9 +154,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) + unlock_page(page); + return; + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /** +diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h +index 9168fc33a4f7..572541d6cc90 100644 +--- a/include/linux/buffer_head.h ++++ b/include/linux/buffer_head.h +@@ -76,8 +76,42 @@ struct buffer_head { + struct address_space *b_assoc_map; /* mapping this buffer is + associated with */ + atomic_t b_count; /* users using this buffer_head */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t b_uptodate_lock; ++#endif + }; + ++static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) ++{ ++ unsigned long flags; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ local_irq_save(flags); ++ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); ++#else ++ spin_lock_irqsave(&bh->b_uptodate_lock, flags); ++#endif ++ return flags; ++} ++ ++static inline void ++bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) ++{ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); ++ local_irq_restore(flags); ++#else ++ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); ++#endif ++} ++ ++static inline void buffer_head_init_locks(struct buffer_head *bh) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spin_lock_init(&bh->b_uptodate_lock); ++#endif ++} ++ + /* + * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() + * and buffer_foo() functions. +-- +2.36.1 + diff --git a/debian/patches-rt/0067-fs-jbd-jbd2-Make-state-lock-and-journal-head-lock-rt.patch b/debian/patches-rt/0067-fs-jbd-jbd2-Make-state-lock-and-journal-head-lock-rt.patch new file mode 100644 index 000000000..46bb6aca2 --- /dev/null +++ b/debian/patches-rt/0067-fs-jbd-jbd2-Make-state-lock-and-journal-head-lock-rt.patch @@ -0,0 +1,110 @@ +From 18cc82093eb65f5fc2db7ff78b49fd443c52da5c Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 18 Mar 2011 10:11:25 +0100 +Subject: [PATCH 067/347] fs: jbd/jbd2: Make state lock and journal head lock + rt safe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +bit_spin_locks break under RT. + +Based on a previous patch from Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +-- + include/linux/buffer_head.h | 8 ++++++++ + include/linux/jbd2.h | 24 ++++++++++++++++++++++++ + 2 files changed, 32 insertions(+) +--- + include/linux/buffer_head.h | 8 ++++++++ + include/linux/jbd2.h | 24 ++++++++++++++++++++++++ + 2 files changed, 32 insertions(+) + +diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h +index 572541d6cc90..703bf3335a3d 100644 +--- a/include/linux/buffer_head.h ++++ b/include/linux/buffer_head.h +@@ -78,6 +78,10 @@ struct buffer_head { + atomic_t b_count; /* users using this buffer_head */ + #ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t b_uptodate_lock; ++#if IS_ENABLED(CONFIG_JBD2) ++ spinlock_t b_state_lock; ++ spinlock_t b_journal_head_lock; ++#endif + #endif + }; + +@@ -109,6 +113,10 @@ static inline void buffer_head_init_locks(struct buffer_head *bh) + { + #ifdef CONFIG_PREEMPT_RT_BASE + spin_lock_init(&bh->b_uptodate_lock); ++#if IS_ENABLED(CONFIG_JBD2) ++ spin_lock_init(&bh->b_state_lock); ++ spin_lock_init(&bh->b_journal_head_lock); ++#endif + #endif + } + +diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h +index 268f3000d1b3..8f5d6ecb802e 100644 +--- a/include/linux/jbd2.h ++++ b/include/linux/jbd2.h +@@ -347,32 +347,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh) + + static inline void jbd_lock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_State, &bh->b_state); ++#else ++ spin_lock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_trylock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_trylock(BH_State, &bh->b_state); ++#else ++ return spin_trylock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_is_locked_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_is_locked(BH_State, &bh->b_state); ++#else ++ return spin_is_locked(&bh->b_state_lock); ++#endif + } + + static inline void jbd_unlock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_State, &bh->b_state); ++#else ++ spin_unlock(&bh->b_state_lock); ++#endif + } + + static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_JournalHead, &bh->b_state); ++#else ++ spin_lock(&bh->b_journal_head_lock); ++#endif + } + + static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_JournalHead, &bh->b_state); ++#else ++ spin_unlock(&bh->b_journal_head_lock); ++#endif + } + + #define J_ASSERT(assert) BUG_ON(!(assert)) +-- +2.36.1 + diff --git a/debian/patches-rt/0068-list_bl-Make-list-head-locking-RT-safe.patch b/debian/patches-rt/0068-list_bl-Make-list-head-locking-RT-safe.patch new file mode 100644 index 000000000..940959051 --- /dev/null +++ b/debian/patches-rt/0068-list_bl-Make-list-head-locking-RT-safe.patch @@ -0,0 +1,121 @@ +From c1eeae383297bbad06f5e7b6d1dafa5ff5fb286e Mon Sep 17 00:00:00 2001 +From: Paul Gortmaker <paul.gortmaker@windriver.com> +Date: Fri, 21 Jun 2013 15:07:25 -0400 +Subject: [PATCH 068/347] list_bl: Make list head locking RT safe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +As per changes in include/linux/jbd_common.h for avoiding the +bit_spin_locks on RT ("fs: jbd/jbd2: Make state lock and journal +head lock rt safe") we do the same thing here. + +We use the non atomic __set_bit and __clear_bit inside the scope of +the lock to preserve the ability of the existing LIST_DEBUG code to +use the zero'th bit in the sanity checks. + +As a bit spinlock, we had no lockdep visibility into the usage +of the list head locking. Now, if we were to implement it as a +standard non-raw spinlock, we would see: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +in_atomic(): 1, irqs_disabled(): 0, pid: 122, name: udevd +5 locks held by udevd/122: + #0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [<ffffffff811967e8>] lock_rename+0xe8/0xf0 + #1: (rename_lock){+.+...}, at: [<ffffffff811a277c>] d_move+0x2c/0x60 + #2: (&dentry->d_lock){+.+...}, at: [<ffffffff811a0763>] dentry_lock_for_move+0xf3/0x130 + #3: (&dentry->d_lock/2){+.+...}, at: [<ffffffff811a0734>] dentry_lock_for_move+0xc4/0x130 + #4: (&dentry->d_lock/3){+.+...}, at: [<ffffffff811a0747>] dentry_lock_for_move+0xd7/0x130 +Pid: 122, comm: udevd Not tainted 3.4.47-rt62 #7 +Call Trace: + [<ffffffff810b9624>] __might_sleep+0x134/0x1f0 + [<ffffffff817a24d4>] rt_spin_lock+0x24/0x60 + [<ffffffff811a0c4c>] __d_shrink+0x5c/0xa0 + [<ffffffff811a1b2d>] __d_drop+0x1d/0x40 + [<ffffffff811a24be>] __d_move+0x8e/0x320 + [<ffffffff811a278e>] d_move+0x3e/0x60 + [<ffffffff81199598>] vfs_rename+0x198/0x4c0 + [<ffffffff8119b093>] sys_renameat+0x213/0x240 + [<ffffffff817a2de5>] ? _raw_spin_unlock+0x35/0x60 + [<ffffffff8107781c>] ? do_page_fault+0x1ec/0x4b0 + [<ffffffff817a32ca>] ? retint_swapgs+0xe/0x13 + [<ffffffff813eb0e6>] ? trace_hardirqs_on_thunk+0x3a/0x3f + [<ffffffff8119b0db>] sys_rename+0x1b/0x20 + [<ffffffff817a3b96>] system_call_fastpath+0x1a/0x1f + +Since we are only taking the lock during short lived list operations, +lets assume for now that it being raw won't be a significant latency +concern. + + +Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/list_bl.h | 28 ++++++++++++++++++++++++++-- + 1 file changed, 26 insertions(+), 2 deletions(-) + +diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h +index 3fc2cc57ba1b..69b659259bac 100644 +--- a/include/linux/list_bl.h ++++ b/include/linux/list_bl.h +@@ -3,6 +3,7 @@ + #define _LINUX_LIST_BL_H + + #include <linux/list.h> ++#include <linux/spinlock.h> + #include <linux/bit_spinlock.h> + + /* +@@ -33,13 +34,22 @@ + + struct hlist_bl_head { + struct hlist_bl_node *first; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spinlock_t lock; ++#endif + }; + + struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; +-#define INIT_HLIST_BL_HEAD(ptr) \ +- ((ptr)->first = NULL) ++ ++static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) ++{ ++ h->first = NULL; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spin_lock_init(&h->lock); ++#endif ++} + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +@@ -119,12 +129,26 @@ static inline void hlist_bl_del_init(struct hlist_bl_node *n) + + static inline void hlist_bl_lock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(0, (unsigned long *)b); ++#else ++ raw_spin_lock(&b->lock); ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __set_bit(0, (unsigned long *)b); ++#endif ++#endif + } + + static inline void hlist_bl_unlock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + __bit_spin_unlock(0, (unsigned long *)b); ++#else ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __clear_bit(0, (unsigned long *)b); ++#endif ++ raw_spin_unlock(&b->lock); ++#endif + } + + static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) +-- +2.36.1 + diff --git a/debian/patches-rt/0069-list_bl-fixup-bogus-lockdep-warning.patch b/debian/patches-rt/0069-list_bl-fixup-bogus-lockdep-warning.patch new file mode 100644 index 000000000..9fe3abb77 --- /dev/null +++ b/debian/patches-rt/0069-list_bl-fixup-bogus-lockdep-warning.patch @@ -0,0 +1,104 @@ +From 6702144cc338594e14d79ce9dd255f50d21840f9 Mon Sep 17 00:00:00 2001 +From: Josh Cartwright <joshc@ni.com> +Date: Thu, 31 Mar 2016 00:04:25 -0500 +Subject: [PATCH 069/347] list_bl: fixup bogus lockdep warning +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +At first glance, the use of 'static inline' seems appropriate for +INIT_HLIST_BL_HEAD(). + +However, when a 'static inline' function invocation is inlined by gcc, +all callers share any static local data declared within that inline +function. + +This presents a problem for how lockdep classes are setup. raw_spinlocks, for +example, when CONFIG_DEBUG_SPINLOCK, + + # define raw_spin_lock_init(lock) \ + do { \ + static struct lock_class_key __key; \ + \ + __raw_spin_lock_init((lock), #lock, &__key); \ + } while (0) + +When this macro is expanded into a 'static inline' caller, like +INIT_HLIST_BL_HEAD(): + + static inline INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) + { + h->first = NULL; + raw_spin_lock_init(&h->lock); + } + +...the static local lock_class_key object is made a function static. + +For compilation units which initialize invoke INIT_HLIST_BL_HEAD() more +than once, then, all of the invocations share this same static local +object. + +This can lead to some very confusing lockdep splats (example below). +Solve this problem by forcing the INIT_HLIST_BL_HEAD() to be a macro, +which prevents the lockdep class object sharing. + + ============================================= + [ INFO: possible recursive locking detected ] + 4.4.4-rt11 #4 Not tainted + --------------------------------------------- + kswapd0/59 is trying to acquire lock: + (&h->lock#2){+.+.-.}, at: mb_cache_shrink_scan + + but task is already holding lock: + (&h->lock#2){+.+.-.}, at: mb_cache_shrink_scan + + other info that might help us debug this: + Possible unsafe locking scenario: + + CPU0 + ---- + lock(&h->lock#2); + lock(&h->lock#2); + + *** DEADLOCK *** + + May be due to missing lock nesting notation + + 2 locks held by kswapd0/59: + #0: (shrinker_rwsem){+.+...}, at: rt_down_read_trylock + #1: (&h->lock#2){+.+.-.}, at: mb_cache_shrink_scan + +Reported-by: Luis Claudio R. Goncalves <lclaudio@uudg.org> +Tested-by: Luis Claudio R. Goncalves <lclaudio@uudg.org> +Signed-off-by: Josh Cartwright <joshc@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/list_bl.h | 12 +++++++----- + 1 file changed, 7 insertions(+), 5 deletions(-) + +diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h +index 69b659259bac..0b5de7d9ffcf 100644 +--- a/include/linux/list_bl.h ++++ b/include/linux/list_bl.h +@@ -43,13 +43,15 @@ struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; + +-static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) +-{ +- h->first = NULL; + #ifdef CONFIG_PREEMPT_RT_BASE +- raw_spin_lock_init(&h->lock); ++#define INIT_HLIST_BL_HEAD(h) \ ++do { \ ++ (h)->first = NULL; \ ++ raw_spin_lock_init(&(h)->lock); \ ++} while (0) ++#else ++#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL + #endif +-} + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +-- +2.36.1 + diff --git a/debian/patches-rt/0070-genirq-Disable-irqpoll-on-rt.patch b/debian/patches-rt/0070-genirq-Disable-irqpoll-on-rt.patch new file mode 100644 index 000000000..1bb671732 --- /dev/null +++ b/debian/patches-rt/0070-genirq-Disable-irqpoll-on-rt.patch @@ -0,0 +1,43 @@ +From 9e5ed96dec7a2d9bf3359966eec008c2434610d6 Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:29:57 -0500 +Subject: [PATCH 070/347] genirq: Disable irqpoll on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Creates long latencies for no value + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/irq/spurious.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c +index d867d6ddafdd..cd12ee86c01e 100644 +--- a/kernel/irq/spurious.c ++++ b/kernel/irq/spurious.c +@@ -442,6 +442,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); + + static int __init irqfixup_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); +@@ -454,6 +458,10 @@ module_param(irqfixup, int, 0644); + + static int __init irqpoll_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); +-- +2.36.1 + diff --git a/debian/patches-rt/0071-genirq-Force-interrupt-thread-on-RT.patch b/debian/patches-rt/0071-genirq-Force-interrupt-thread-on-RT.patch new file mode 100644 index 000000000..9eb44beb4 --- /dev/null +++ b/debian/patches-rt/0071-genirq-Force-interrupt-thread-on-RT.patch @@ -0,0 +1,54 @@ +From d4c832ada3bdbd395d69e11232761697f6ed9523 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 3 Apr 2011 11:57:29 +0200 +Subject: [PATCH 071/347] genirq: Force interrupt thread on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Force threaded_irqs and optimize the code (force_irqthreads) in regard +to this. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/interrupt.h | 4 ++++ + kernel/irq/manage.c | 2 ++ + 2 files changed, 6 insertions(+) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index eeceac3376fc..315f852b4981 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -427,7 +427,11 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, + bool state); + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifdef CONFIG_PREEMPT_RT_BASE ++# define force_irqthreads (true) ++# else + extern bool force_irqthreads; ++# endif + #else + #define force_irqthreads (0) + #endif +diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c +index 18f3cdbf41fd..f12f50f5b605 100644 +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -24,6 +24,7 @@ + #include "internals.h" + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + __read_mostly bool force_irqthreads; + EXPORT_SYMBOL_GPL(force_irqthreads); + +@@ -33,6 +34,7 @@ static int __init setup_forced_irqthreads(char *arg) + return 0; + } + early_param("threadirqs", setup_forced_irqthreads); ++# endif + #endif + + static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip) +-- +2.36.1 + diff --git a/debian/patches-rt/0072-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch b/debian/patches-rt/0072-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch new file mode 100644 index 000000000..deadce9a4 --- /dev/null +++ b/debian/patches-rt/0072-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch @@ -0,0 +1,173 @@ +From a2351869ba46346be8b541abd8f1ca7a81df2537 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Mon, 28 May 2018 15:24:20 +0200 +Subject: [PATCH 072/347] Split IRQ-off and zone->lock while freeing pages from + PCP list #1 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Split the IRQ-off section while accessing the PCP list from zone->lock +while freeing pages. +Introcude isolate_pcp_pages() which separates the pages from the PCP +list onto a temporary list and then free the temporary list via +free_pcppages_bulk(). + +Signed-off-by: Peter Zijlstra <peterz@infradead.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/page_alloc.c | 82 +++++++++++++++++++++++++++++++------------------ + 1 file changed, 52 insertions(+), 30 deletions(-) + +diff --git a/mm/page_alloc.c b/mm/page_alloc.c +index 9c35403d9646..6763dfc2dde0 100644 +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -1096,7 +1096,7 @@ static inline void prefetch_buddy(struct page *page) + } + + /* +- * Frees a number of pages from the PCP lists ++ * Frees a number of pages which have been collected from the pcp lists. + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + * +@@ -1107,14 +1107,41 @@ static inline void prefetch_buddy(struct page *page) + * pinned" detection logic. + */ + static void free_pcppages_bulk(struct zone *zone, int count, +- struct per_cpu_pages *pcp) ++ struct list_head *head) ++{ ++ bool isolated_pageblocks; ++ struct page *page, *tmp; ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); ++ isolated_pageblocks = has_isolate_pageblock(zone); ++ ++ /* ++ * Use safe version since after __free_one_page(), ++ * page->lru.next will not point to original list. ++ */ ++ list_for_each_entry_safe(page, tmp, head, lru) { ++ int mt = get_pcppage_migratetype(page); ++ /* MIGRATE_ISOLATE page should not go to pcplists */ ++ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); ++ /* Pageblock could have been isolated meanwhile */ ++ if (unlikely(isolated_pageblocks)) ++ mt = get_pageblock_migratetype(page); ++ ++ __free_one_page(page, page_to_pfn(page), zone, 0, mt); ++ trace_mm_page_pcpu_drain(page, 0, mt); ++ } ++ spin_unlock_irqrestore(&zone->lock, flags); ++} ++ ++static void isolate_pcp_pages(int count, struct per_cpu_pages *pcp, ++ struct list_head *dst) ++ + { + int migratetype = 0; + int batch_free = 0; + int prefetch_nr = 0; +- bool isolated_pageblocks; +- struct page *page, *tmp; +- LIST_HEAD(head); ++ struct page *page; + + /* + * Ensure proper count is passed which otherwise would stuck in the +@@ -1151,7 +1178,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, + if (bulkfree_pcp_prepare(page)) + continue; + +- list_add_tail(&page->lru, &head); ++ list_add_tail(&page->lru, dst); + + /* + * We are going to put the page back to the global +@@ -1166,26 +1193,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, + prefetch_buddy(page); + } while (--count && --batch_free && !list_empty(list)); + } +- +- spin_lock(&zone->lock); +- isolated_pageblocks = has_isolate_pageblock(zone); +- +- /* +- * Use safe version since after __free_one_page(), +- * page->lru.next will not point to original list. +- */ +- list_for_each_entry_safe(page, tmp, &head, lru) { +- int mt = get_pcppage_migratetype(page); +- /* MIGRATE_ISOLATE page should not go to pcplists */ +- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); +- /* Pageblock could have been isolated meanwhile */ +- if (unlikely(isolated_pageblocks)) +- mt = get_pageblock_migratetype(page); +- +- __free_one_page(page, page_to_pfn(page), zone, 0, mt); +- trace_mm_page_pcpu_drain(page, 0, mt); +- } +- spin_unlock(&zone->lock); + } + + static void free_one_page(struct zone *zone, +@@ -2546,13 +2553,18 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + { + unsigned long flags; + int to_drain, batch; ++ LIST_HEAD(dst); + + local_irq_save(flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) +- free_pcppages_bulk(zone, to_drain, pcp); ++ isolate_pcp_pages(to_drain, pcp, &dst); ++ + local_irq_restore(flags); ++ ++ if (to_drain > 0) ++ free_pcppages_bulk(zone, to_drain, &dst); + } + #endif + +@@ -2568,14 +2580,21 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) + unsigned long flags; + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; ++ LIST_HEAD(dst); ++ int count; + + local_irq_save(flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +- if (pcp->count) +- free_pcppages_bulk(zone, pcp->count, pcp); ++ count = pcp->count; ++ if (count) ++ isolate_pcp_pages(count, pcp, &dst); ++ + local_irq_restore(flags); ++ ++ if (count) ++ free_pcppages_bulk(zone, count, &dst); + } + + /* +@@ -2797,7 +2816,10 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn) + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- free_pcppages_bulk(zone, batch, pcp); ++ LIST_HEAD(dst); ++ ++ isolate_pcp_pages(batch, pcp, &dst); ++ free_pcppages_bulk(zone, batch, &dst); + } + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0073-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch b/debian/patches-rt/0073-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch new file mode 100644 index 000000000..f19c558a2 --- /dev/null +++ b/debian/patches-rt/0073-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch @@ -0,0 +1,172 @@ +From 2c267f4e1c964c28022ee12c9b86f07854427ac5 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Mon, 28 May 2018 15:24:21 +0200 +Subject: [PATCH 073/347] Split IRQ-off and zone->lock while freeing pages from + PCP list #2 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Split the IRQ-off section while accessing the PCP list from zone->lock +while freeing pages. +Introcude isolate_pcp_pages() which separates the pages from the PCP +list onto a temporary list and then free the temporary list via +free_pcppages_bulk(). + +Signed-off-by: Peter Zijlstra <peterz@infradead.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/page_alloc.c | 60 ++++++++++++++++++++++++++++++++++++++++--------- + 1 file changed, 50 insertions(+), 10 deletions(-) + +diff --git a/mm/page_alloc.c b/mm/page_alloc.c +index 6763dfc2dde0..ba6f9b334073 100644 +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -1106,8 +1106,8 @@ static inline void prefetch_buddy(struct page *page) + * And clear the zone's pages_scanned counter, to hold off the "all pages are + * pinned" detection logic. + */ +-static void free_pcppages_bulk(struct zone *zone, int count, +- struct list_head *head) ++static void free_pcppages_bulk(struct zone *zone, struct list_head *head, ++ bool zone_retry) + { + bool isolated_pageblocks; + struct page *page, *tmp; +@@ -1122,12 +1122,27 @@ static void free_pcppages_bulk(struct zone *zone, int count, + */ + list_for_each_entry_safe(page, tmp, head, lru) { + int mt = get_pcppage_migratetype(page); ++ ++ if (page_zone(page) != zone) { ++ /* ++ * free_unref_page_list() sorts pages by zone. If we end ++ * up with pages from a different NUMA nodes belonging ++ * to the same ZONE index then we need to redo with the ++ * correct ZONE pointer. Skip the page for now, redo it ++ * on the next iteration. ++ */ ++ WARN_ON_ONCE(zone_retry == false); ++ if (zone_retry) ++ continue; ++ } ++ + /* MIGRATE_ISOLATE page should not go to pcplists */ + VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); + /* Pageblock could have been isolated meanwhile */ + if (unlikely(isolated_pageblocks)) + mt = get_pageblock_migratetype(page); + ++ list_del(&page->lru); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); + trace_mm_page_pcpu_drain(page, 0, mt); + } +@@ -2564,7 +2579,7 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + local_irq_restore(flags); + + if (to_drain > 0) +- free_pcppages_bulk(zone, to_drain, &dst); ++ free_pcppages_bulk(zone, &dst, false); + } + #endif + +@@ -2594,7 +2609,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) + local_irq_restore(flags); + + if (count) +- free_pcppages_bulk(zone, count, &dst); ++ free_pcppages_bulk(zone, &dst, false); + } + + /* +@@ -2787,7 +2802,8 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn) + return true; + } + +-static void free_unref_page_commit(struct page *page, unsigned long pfn) ++static void free_unref_page_commit(struct page *page, unsigned long pfn, ++ struct list_head *dst) + { + struct zone *zone = page_zone(page); + struct per_cpu_pages *pcp; +@@ -2816,10 +2832,8 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn) + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- LIST_HEAD(dst); + +- isolate_pcp_pages(batch, pcp, &dst); +- free_pcppages_bulk(zone, batch, &dst); ++ isolate_pcp_pages(batch, pcp, dst); + } + } + +@@ -2830,13 +2844,17 @@ void free_unref_page(struct page *page) + { + unsigned long flags; + unsigned long pfn = page_to_pfn(page); ++ struct zone *zone = page_zone(page); ++ LIST_HEAD(dst); + + if (!free_unref_page_prepare(page, pfn)) + return; + + local_irq_save(flags); +- free_unref_page_commit(page, pfn); ++ free_unref_page_commit(page, pfn, &dst); + local_irq_restore(flags); ++ if (!list_empty(&dst)) ++ free_pcppages_bulk(zone, &dst, false); + } + + /* +@@ -2847,6 +2865,11 @@ void free_unref_page_list(struct list_head *list) + struct page *page, *next; + unsigned long flags, pfn; + int batch_count = 0; ++ struct list_head dsts[__MAX_NR_ZONES]; ++ int i; ++ ++ for (i = 0; i < __MAX_NR_ZONES; i++) ++ INIT_LIST_HEAD(&dsts[i]); + + /* Prepare pages for freeing */ + list_for_each_entry_safe(page, next, list, lru) { +@@ -2859,10 +2882,12 @@ void free_unref_page_list(struct list_head *list) + local_irq_save(flags); + list_for_each_entry_safe(page, next, list, lru) { + unsigned long pfn = page_private(page); ++ enum zone_type type; + + set_page_private(page, 0); + trace_mm_page_free_batched(page); +- free_unref_page_commit(page, pfn); ++ type = page_zonenum(page); ++ free_unref_page_commit(page, pfn, &dsts[type]); + + /* + * Guard against excessive IRQ disabled times when we get +@@ -2875,6 +2900,21 @@ void free_unref_page_list(struct list_head *list) + } + } + local_irq_restore(flags); ++ ++ for (i = 0; i < __MAX_NR_ZONES; ) { ++ struct page *page; ++ struct zone *zone; ++ ++ if (list_empty(&dsts[i])) { ++ i++; ++ continue; ++ } ++ ++ page = list_first_entry(&dsts[i], struct page, lru); ++ zone = page_zone(page); ++ ++ free_pcppages_bulk(zone, &dsts[i], true); ++ } + } + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0074-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch b/debian/patches-rt/0074-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch new file mode 100644 index 000000000..564ebe845 --- /dev/null +++ b/debian/patches-rt/0074-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch @@ -0,0 +1,619 @@ +From 3e8b37b77db38c83eaff3b8fdcd23e91f8d78613 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 28 May 2018 15:24:22 +0200 +Subject: [PATCH 074/347] mm/SLxB: change list_lock to raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The list_lock is used with used with IRQs off on RT. Make it a raw_spinlock_t +otherwise the interrupts won't be disabled on -RT. The locking rules remain +the same on !RT. +This patch changes it for SLAB and SLUB since both share the same header +file for struct kmem_cache_node defintion. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/slab.c | 94 +++++++++++++++++++++++++++---------------------------- + mm/slab.h | 2 +- + mm/slub.c | 50 ++++++++++++++--------------- + 3 files changed, 73 insertions(+), 73 deletions(-) + +diff --git a/mm/slab.c b/mm/slab.c +index 46f21e73db2f..38f6609343b3 100644 +--- a/mm/slab.c ++++ b/mm/slab.c +@@ -233,7 +233,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent) + parent->shared = NULL; + parent->alien = NULL; + parent->colour_next = 0; +- spin_lock_init(&parent->list_lock); ++ raw_spin_lock_init(&parent->list_lock); + parent->free_objects = 0; + parent->free_touched = 0; + } +@@ -600,9 +600,9 @@ static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep, + page_node = page_to_nid(page); + n = get_node(cachep, page_node); + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + free_block(cachep, &objp, 1, page_node, &list); +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + slabs_destroy(cachep, &list); + } +@@ -731,7 +731,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, + struct kmem_cache_node *n = get_node(cachep, node); + + if (ac->avail) { +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + /* + * Stuff objects into the remote nodes shared array first. + * That way we could avoid the overhead of putting the objects +@@ -742,7 +742,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, + + free_block(cachep, ac->entry, ac->avail, node, list); + ac->avail = 0; +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + } + } + +@@ -815,9 +815,9 @@ static int __cache_free_alien(struct kmem_cache *cachep, void *objp, + slabs_destroy(cachep, &list); + } else { + n = get_node(cachep, page_node); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + free_block(cachep, &objp, 1, page_node, &list); +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + } + return 1; +@@ -858,10 +858,10 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) + */ + n = get_node(cachep, node); + if (n) { +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + + cachep->num; +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + return 0; + } +@@ -940,7 +940,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, + goto fail; + + n = get_node(cachep, node); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + if (n->shared && force_change) { + free_block(cachep, n->shared->entry, + n->shared->avail, node, &list); +@@ -958,7 +958,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, + new_alien = NULL; + } + +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + + /* +@@ -997,7 +997,7 @@ static void cpuup_canceled(long cpu) + if (!n) + continue; + +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + + /* Free limit for this kmem_cache_node */ + n->free_limit -= cachep->batchcount; +@@ -1010,7 +1010,7 @@ static void cpuup_canceled(long cpu) + } + + if (!cpumask_empty(mask)) { +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + goto free_slab; + } + +@@ -1024,7 +1024,7 @@ static void cpuup_canceled(long cpu) + alien = n->alien; + n->alien = NULL; + +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + kfree(shared); + if (alien) { +@@ -1208,7 +1208,7 @@ static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node * + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ +- spin_lock_init(&ptr->list_lock); ++ raw_spin_lock_init(&ptr->list_lock); + + MAKE_ALL_LISTS(cachep, ptr, nodeid); + cachep->node[nodeid] = ptr; +@@ -1379,11 +1379,11 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) + for_each_kmem_cache_node(cachep, node, n) { + unsigned long total_slabs, free_slabs, free_objs; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + total_slabs = n->total_slabs; + free_slabs = n->free_slabs; + free_objs = n->free_objects; +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld\n", + node, total_slabs - free_slabs, total_slabs, +@@ -2178,7 +2178,7 @@ static void check_spinlock_acquired(struct kmem_cache *cachep) + { + #ifdef CONFIG_SMP + check_irq_off(); +- assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); ++ assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); + #endif + } + +@@ -2186,7 +2186,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) + { + #ifdef CONFIG_SMP + check_irq_off(); +- assert_spin_locked(&get_node(cachep, node)->list_lock); ++ assert_raw_spin_locked(&get_node(cachep, node)->list_lock); + #endif + } + +@@ -2226,9 +2226,9 @@ static void do_drain(void *arg) + check_irq_off(); + ac = cpu_cache_get(cachep); + n = get_node(cachep, node); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + free_block(cachep, ac->entry, ac->avail, node, &list); +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + ac->avail = 0; + } +@@ -2246,9 +2246,9 @@ static void drain_cpu_caches(struct kmem_cache *cachep) + drain_alien_cache(cachep, n->alien); + + for_each_kmem_cache_node(cachep, node, n) { +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, n->shared, node, true, &list); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); + } +@@ -2270,10 +2270,10 @@ static int drain_freelist(struct kmem_cache *cache, + nr_freed = 0; + while (nr_freed < tofree && !list_empty(&n->slabs_free)) { + +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + p = n->slabs_free.prev; + if (p == &n->slabs_free) { +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + goto out; + } + +@@ -2286,7 +2286,7 @@ static int drain_freelist(struct kmem_cache *cache, + * to the cache. + */ + n->free_objects -= cache->num; +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + slab_destroy(cache, page); + nr_freed++; + } +@@ -2734,7 +2734,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) + INIT_LIST_HEAD(&page->lru); + n = get_node(cachep, page_to_nid(page)); + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + n->total_slabs++; + if (!page->active) { + list_add_tail(&page->lru, &(n->slabs_free)); +@@ -2744,7 +2744,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) + + STATS_INC_GROWN(cachep); + n->free_objects += cachep->num - page->active; +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + fixup_objfreelist_debug(cachep, &list); + } +@@ -2912,7 +2912,7 @@ static struct page *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc) + { + struct page *page; + +- assert_spin_locked(&n->list_lock); ++ assert_raw_spin_locked(&n->list_lock); + page = list_first_entry_or_null(&n->slabs_partial, struct page, lru); + if (!page) { + n->free_touched = 1; +@@ -2938,10 +2938,10 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, + if (!gfp_pfmemalloc_allowed(flags)) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + page = get_first_slab(n, true); + if (!page) { +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return NULL; + } + +@@ -2950,7 +2950,7 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, + + fixup_slab_list(cachep, n, page, &list); + +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + + return obj; +@@ -3009,7 +3009,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) + if (!n->free_objects && (!shared || !shared->avail)) + goto direct_grow; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + shared = READ_ONCE(n->shared); + + /* See if we can refill from the shared array */ +@@ -3033,7 +3033,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) + must_grow: + n->free_objects -= ac->avail; + alloc_done: +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + + direct_grow: +@@ -3258,7 +3258,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, + BUG_ON(!n); + + check_irq_off(); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + page = get_first_slab(n, false); + if (!page) + goto must_grow; +@@ -3276,12 +3276,12 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, + + fixup_slab_list(cachep, n, page, &list); + +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + return obj; + + must_grow: +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid); + if (page) { + /* This slab isn't counted yet so don't update free_objects */ +@@ -3457,7 +3457,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) + + check_irq_off(); + n = get_node(cachep, node); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + if (n->shared) { + struct array_cache *shared_array = n->shared; + int max = shared_array->limit - shared_array->avail; +@@ -3486,7 +3486,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) + STATS_SET_FREEABLE(cachep, i); + } + #endif +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + ac->avail -= batchcount; + memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); +@@ -3896,9 +3896,9 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, + + node = cpu_to_mem(cpu); + n = get_node(cachep, node); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + free_block(cachep, ac->entry, ac->avail, node, &list); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + } + free_percpu(prev); +@@ -4023,9 +4023,9 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, + return; + } + +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, ac, node, false, &list); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); + } +@@ -4109,7 +4109,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) + + for_each_kmem_cache_node(cachep, node, n) { + check_irq_on(); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + + total_slabs += n->total_slabs; + free_slabs += n->free_slabs; +@@ -4118,7 +4118,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) + if (n->shared) + shared_avail += n->shared->avail; + +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + } + num_objs = total_slabs * cachep->num; + active_slabs = total_slabs - free_slabs; +@@ -4338,13 +4338,13 @@ static int leaks_show(struct seq_file *m, void *p) + for_each_kmem_cache_node(cachep, node, n) { + + check_irq_on(); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + + list_for_each_entry(page, &n->slabs_full, lru) + handle_slab(x, cachep, page); + list_for_each_entry(page, &n->slabs_partial, lru) + handle_slab(x, cachep, page); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + } + } while (!is_store_user_clean(cachep)); + +diff --git a/mm/slab.h b/mm/slab.h +index 0ed7a463f476..12b7da32bcd0 100644 +--- a/mm/slab.h ++++ b/mm/slab.h +@@ -454,7 +454,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, + * The slab lists for all objects. + */ + struct kmem_cache_node { +- spinlock_t list_lock; ++ raw_spinlock_t list_lock; + + #ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ +diff --git a/mm/slub.c b/mm/slub.c +index 499fb073d1ff..0e4670add1e9 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1182,7 +1182,7 @@ static noinline int free_debug_processing( + unsigned long uninitialized_var(flags); + int ret = 0; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + slab_lock(page); + + if (s->flags & SLAB_CONSISTENCY_CHECKS) { +@@ -1217,7 +1217,7 @@ static noinline int free_debug_processing( + bulk_cnt, cnt); + + slab_unlock(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + if (!ret) + slab_fix(s, "Object at 0x%p not freed", object); + return ret; +@@ -1829,7 +1829,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, + if (!n || !n->nr_partial) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t; + +@@ -1854,7 +1854,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, + break; + + } +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return object; + } + +@@ -2106,7 +2106,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, + * that acquire_slab() will see a slab page that + * is frozen + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } else { + m = M_FULL; +@@ -2117,7 +2117,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, + * slabs from diagnostic functions will not see + * any frozen slabs. + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } + +@@ -2152,7 +2152,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, + goto redo; + + if (lock) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); +@@ -2187,10 +2187,10 @@ static void unfreeze_partials(struct kmem_cache *s, + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + n = n2; +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + + do { +@@ -2219,7 +2219,7 @@ static void unfreeze_partials(struct kmem_cache *s, + } + + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + while (discard_page) { + page = discard_page; +@@ -2388,10 +2388,10 @@ static unsigned long count_partial(struct kmem_cache_node *n, + unsigned long x = 0; + struct page *page; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + x += get_count(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return x; + } + #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ +@@ -2836,7 +2836,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, + + do { + if (unlikely(n)) { +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + n = NULL; + } + prior = page->freelist; +@@ -2868,7 +2868,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + } + } +@@ -2910,7 +2910,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return; + + slab_empty: +@@ -2925,7 +2925,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, + remove_full(s, n, page); + } + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + stat(s, FREE_SLAB); + discard_slab(s, page); + } +@@ -3323,7 +3323,7 @@ static void + init_kmem_cache_node(struct kmem_cache_node *n) + { + n->nr_partial = 0; +- spin_lock_init(&n->list_lock); ++ raw_spin_lock_init(&n->list_lock); + INIT_LIST_HEAD(&n->partial); + #ifdef CONFIG_SLUB_DEBUG + atomic_long_set(&n->nr_slabs, 0); +@@ -3710,7 +3710,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) + struct page *page, *h; + + BUG_ON(irqs_disabled()); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + list_for_each_entry_safe(page, h, &n->partial, lru) { + if (!page->inuse) { + remove_partial(n, page); +@@ -3720,7 +3720,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) + "Objects remaining in %s on __kmem_cache_shutdown()"); + } + } +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + list_for_each_entry_safe(page, h, &discard, lru) + discard_slab(s, page); +@@ -3993,7 +3993,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + /* + * Build lists of slabs to discard or promote. +@@ -4024,7 +4024,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, &discard, lru) +@@ -4438,7 +4438,7 @@ static int validate_slab_node(struct kmem_cache *s, + struct page *page; + unsigned long flags; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + list_for_each_entry(page, &n->partial, lru) { + validate_slab_slab(s, page, map); +@@ -4460,7 +4460,7 @@ static int validate_slab_node(struct kmem_cache *s, + s->name, count, atomic_long_read(&n->nr_slabs)); + + out: +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return count; + } + +@@ -4650,12 +4650,12 @@ static int list_locations(struct kmem_cache *s, char *buf, + if (!atomic_long_read(&n->nr_slabs)) + continue; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + process_slab(&t, s, page, alloc, map); + list_for_each_entry(page, &n->full, lru) + process_slab(&t, s, page, alloc, map); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + } + + for (i = 0; i < t.count; i++) { +-- +2.36.1 + diff --git a/debian/patches-rt/0075-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch b/debian/patches-rt/0075-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch new file mode 100644 index 000000000..c62fd4658 --- /dev/null +++ b/debian/patches-rt/0075-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch @@ -0,0 +1,223 @@ +From 77ff019039696fc4bd8962110c689eb3520386b1 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 21 Jun 2018 17:29:19 +0200 +Subject: [PATCH 075/347] mm/SLUB: delay giving back empty slubs to IRQ enabled + regions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +__free_slab() is invoked with disabled interrupts which increases the +irq-off time while __free_pages() is doing the work. +Allow __free_slab() to be invoked with enabled interrupts and move +everything from interrupts-off invocations to a temporary per-CPU list +so it can be processed later. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/slub.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++++---- + 1 file changed, 69 insertions(+), 5 deletions(-) + +diff --git a/mm/slub.c b/mm/slub.c +index 0e4670add1e9..a5a086ed4493 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1350,6 +1350,12 @@ static bool freelist_corrupted(struct kmem_cache *s, struct page *page, + } + #endif /* CONFIG_SLUB_DEBUG */ + ++struct slub_free_list { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); ++ + /* + * Hooks for other subsystems that check memory allocations. In a typical + * production configuration these hooks all should produce no code at all. +@@ -1711,6 +1717,16 @@ static void __free_slab(struct kmem_cache *s, struct page *page) + __free_pages(page, order); + } + ++static void free_delayed(struct list_head *h) ++{ ++ while (!list_empty(h)) { ++ struct page *page = list_first_entry(h, struct page, lru); ++ ++ list_del(&page->lru); ++ __free_slab(page->slab_cache, page); ++ } ++} ++ + static void rcu_free_slab(struct rcu_head *h) + { + struct page *page = container_of(h, struct page, rcu_head); +@@ -1722,6 +1738,12 @@ static void free_slab(struct kmem_cache *s, struct page *page) + { + if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) { + call_rcu(&page->rcu_head, rcu_free_slab); ++ } else if (irqs_disabled()) { ++ struct slub_free_list *f = this_cpu_ptr(&slub_free_list); ++ ++ raw_spin_lock(&f->lock); ++ list_add(&page->lru, &f->list); ++ raw_spin_unlock(&f->lock); + } else + __free_slab(s, page); + } +@@ -2256,14 +2278,21 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { ++ struct slub_free_list *f; + unsigned long flags; ++ LIST_HEAD(tofree); + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + oldpage = NULL; + pobjects = 0; + pages = 0; +@@ -2333,7 +2362,22 @@ static bool has_cpu_slab(int cpu, void *info) + + static void flush_all(struct kmem_cache *s) + { ++ LIST_HEAD(tofree); ++ int cpu; ++ + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); ++ for_each_online_cpu(cpu) { ++ struct slub_free_list *f; ++ ++ if (!has_cpu_slab(cpu, s)) ++ continue; ++ ++ f = &per_cpu(slub_free_list, cpu); ++ raw_spin_lock_irq(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock_irq(&f->lock); ++ free_delayed(&tofree); ++ } + } + + /* +@@ -2531,8 +2575,10 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) + * already disabled (which is the case for bulk allocation). + */ + static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +- unsigned long addr, struct kmem_cache_cpu *c) ++ unsigned long addr, struct kmem_cache_cpu *c, ++ struct list_head *to_free) + { ++ struct slub_free_list *f; + void *freelist; + struct page *page; + +@@ -2598,6 +2644,13 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); + c->tid = next_tid(c->tid); ++ ++out: ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, to_free); ++ raw_spin_unlock(&f->lock); ++ + return freelist; + + new_slab: +@@ -2613,7 +2666,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + + if (unlikely(!freelist)) { + slab_out_of_memory(s, gfpflags, node); +- return NULL; ++ goto out; + } + + page = c->page; +@@ -2626,7 +2679,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + goto new_slab; /* Slab failed checks. Next slab needed */ + + deactivate_slab(s, page, get_freepointer(s, freelist), c); +- return freelist; ++ goto out; + } + + /* +@@ -2638,6 +2691,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + { + void *p; + unsigned long flags; ++ LIST_HEAD(tofree); + + local_irq_save(flags); + #ifdef CONFIG_PREEMPT +@@ -2649,8 +2703,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + c = this_cpu_ptr(s->cpu_slab); + #endif + +- p = ___slab_alloc(s, gfpflags, node, addr, c); ++ p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree); + local_irq_restore(flags); ++ free_delayed(&tofree); + return p; + } + +@@ -3130,6 +3185,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + void **p) + { + struct kmem_cache_cpu *c; ++ LIST_HEAD(to_free); + int i; + + /* memcg and kmem_cache debug support */ +@@ -3162,7 +3218,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + * of re-populating per CPU c->freelist + */ + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, +- _RET_IP_, c); ++ _RET_IP_, c, &to_free); + if (unlikely(!p[i])) + goto error; + +@@ -3174,6 +3230,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + } + c->tid = next_tid(c->tid); + local_irq_enable(); ++ free_delayed(&to_free); + + /* Clear memory outside IRQ disabled fastpath loop */ + if (unlikely(flags & __GFP_ZERO)) { +@@ -3188,6 +3245,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + return i; + error: + local_irq_enable(); ++ free_delayed(&to_free); + slab_post_alloc_hook(s, flags, i, p); + __kmem_cache_free_bulk(s, i, p); + return 0; +@@ -4237,6 +4295,12 @@ void __init kmem_cache_init(void) + { + static __initdata struct kmem_cache boot_kmem_cache, + boot_kmem_cache_node; ++ int cpu; ++ ++ for_each_possible_cpu(cpu) { ++ raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); ++ INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); ++ } + + if (debug_guardpage_minorder()) + slub_max_order = 0; +-- +2.36.1 + diff --git a/debian/patches-rt/0076-mm-page_alloc-rt-friendly-per-cpu-pages.patch b/debian/patches-rt/0076-mm-page_alloc-rt-friendly-per-cpu-pages.patch new file mode 100644 index 000000000..819fc71a0 --- /dev/null +++ b/debian/patches-rt/0076-mm-page_alloc-rt-friendly-per-cpu-pages.patch @@ -0,0 +1,239 @@ +From 85f14b575e2fadf9ab80ef7b3e5158833d79939e Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:29:37 -0500 +Subject: [PATCH 076/347] mm: page_alloc: rt-friendly per-cpu pages +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +rt-friendly per-cpu pages: convert the irqs-off per-cpu locking +method into a preemptible, explicit-per-cpu-locks method. + +Contains fixes from: + Peter Zijlstra <a.p.zijlstra@chello.nl> + Thomas Gleixner <tglx@linutronix.de> + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + mm/page_alloc.c | 63 +++++++++++++++++++++++++++++++++---------------- + 1 file changed, 43 insertions(+), 20 deletions(-) + +diff --git a/mm/page_alloc.c b/mm/page_alloc.c +index ba6f9b334073..59ea701ecfe0 100644 +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -60,6 +60,7 @@ + #include <linux/hugetlb.h> + #include <linux/sched/rt.h> + #include <linux/sched/mm.h> ++#include <linux/locallock.h> + #include <linux/page_owner.h> + #include <linux/kthread.h> + #include <linux/memcontrol.h> +@@ -292,6 +293,18 @@ EXPORT_SYMBOL(nr_node_ids); + EXPORT_SYMBOL(nr_online_nodes); + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pa_lock); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define cpu_lock_irqsave(cpu, flags) \ ++ local_lock_irqsave_on(pa_lock, flags, cpu) ++# define cpu_unlock_irqrestore(cpu, flags) \ ++ local_unlock_irqrestore_on(pa_lock, flags, cpu) ++#else ++# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) ++# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) ++#endif ++ + int page_group_by_mobility_disabled __read_mostly; + + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +@@ -1302,10 +1315,10 @@ static void __free_pages_ok(struct page *page, unsigned int order) + return; + + migratetype = get_pfnblock_migratetype(page, pfn); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_events(PGFREE, 1 << order); + free_one_page(page_zone(page), page, pfn, order, migratetype); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + static void __init __free_pages_boot_core(struct page *page, unsigned int order) +@@ -2570,13 +2583,13 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + int to_drain, batch; + LIST_HEAD(dst); + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) + isolate_pcp_pages(to_drain, pcp, &dst); + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + if (to_drain > 0) + free_pcppages_bulk(zone, &dst, false); +@@ -2598,7 +2611,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) + LIST_HEAD(dst); + int count; + +- local_irq_save(flags); ++ cpu_lock_irqsave(cpu, flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +@@ -2606,7 +2619,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) + if (count) + isolate_pcp_pages(count, pcp, &dst); + +- local_irq_restore(flags); ++ cpu_unlock_irqrestore(cpu, flags); + + if (count) + free_pcppages_bulk(zone, &dst, false); +@@ -2644,6 +2657,7 @@ void drain_local_pages(struct zone *zone) + drain_pages(cpu); + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + static void drain_local_pages_wq(struct work_struct *work) + { + /* +@@ -2657,6 +2671,7 @@ static void drain_local_pages_wq(struct work_struct *work) + drain_local_pages(NULL); + preempt_enable(); + } ++#endif + + /* + * Spill all the per-cpu pages from all CPUs back into the buddy allocator. +@@ -2723,7 +2738,14 @@ void drain_all_pages(struct zone *zone) + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++ for_each_cpu(cpu, &cpus_with_pcps) { ++ if (zone) ++ drain_pages_zone(cpu, zone); ++ else ++ drain_pages(cpu); ++ } ++#else + for_each_cpu(cpu, &cpus_with_pcps) { + struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); + INIT_WORK(work, drain_local_pages_wq); +@@ -2731,6 +2753,7 @@ void drain_all_pages(struct zone *zone) + } + for_each_cpu(cpu, &cpus_with_pcps) + flush_work(per_cpu_ptr(&pcpu_drain, cpu)); ++#endif + + mutex_unlock(&pcpu_drain_mutex); + } +@@ -2850,9 +2873,9 @@ void free_unref_page(struct page *page) + if (!free_unref_page_prepare(page, pfn)) + return; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + free_unref_page_commit(page, pfn, &dst); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + if (!list_empty(&dst)) + free_pcppages_bulk(zone, &dst, false); + } +@@ -2879,7 +2902,7 @@ void free_unref_page_list(struct list_head *list) + set_page_private(page, pfn); + } + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + list_for_each_entry_safe(page, next, list, lru) { + unsigned long pfn = page_private(page); + enum zone_type type; +@@ -2894,12 +2917,12 @@ void free_unref_page_list(struct list_head *list) + * a large list of pages to free. + */ + if (++batch_count == SWAP_CLUSTER_MAX) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + batch_count = 0; +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + } + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + for (i = 0; i < __MAX_NR_ZONES; ) { + struct page *page; +@@ -3048,7 +3071,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, + struct page *page; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + page = __rmqueue_pcplist(zone, migratetype, pcp, list); +@@ -3056,7 +3079,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone); + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return page; + } + +@@ -3083,7 +3106,7 @@ struct page *rmqueue(struct zone *preferred_zone, + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); +- spin_lock_irqsave(&zone->lock, flags); ++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + + do { + page = NULL; +@@ -3103,14 +3126,14 @@ struct page *rmqueue(struct zone *preferred_zone, + + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + out: + VM_BUG_ON_PAGE(page && bad_range(zone, page), page); + return page; + + failed: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return NULL; + } + +@@ -8146,7 +8169,7 @@ void zone_pcp_reset(struct zone *zone) + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); +@@ -8155,7 +8178,7 @@ void zone_pcp_reset(struct zone *zone) + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + #ifdef CONFIG_MEMORY_HOTREMOVE +-- +2.36.1 + diff --git a/debian/patches-rt/0077-mm-swap-Convert-to-percpu-locked.patch b/debian/patches-rt/0077-mm-swap-Convert-to-percpu-locked.patch new file mode 100644 index 000000000..a2925871b --- /dev/null +++ b/debian/patches-rt/0077-mm-swap-Convert-to-percpu-locked.patch @@ -0,0 +1,211 @@ +From cba209957a582e2758768ae3c7e5be17d11fc94a Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:29:51 -0500 +Subject: [PATCH 077/347] mm/swap: Convert to percpu locked +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Replace global locks (get_cpu + local_irq_save) with "local_locks()". +Currently there is one of for "rotate" and one for "swap". + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/swap.h | 2 ++ + mm/compaction.c | 6 ++++-- + mm/page_alloc.c | 3 ++- + mm/swap.c | 38 ++++++++++++++++++++++---------------- + 4 files changed, 30 insertions(+), 19 deletions(-) + +diff --git a/include/linux/swap.h b/include/linux/swap.h +index ee8f9f554a9e..2ad000e362bd 100644 +--- a/include/linux/swap.h ++++ b/include/linux/swap.h +@@ -12,6 +12,7 @@ + #include <linux/fs.h> + #include <linux/atomic.h> + #include <linux/page-flags.h> ++#include <linux/locallock.h> + #include <asm/page.h> + + struct notifier_block; +@@ -331,6 +332,7 @@ extern unsigned long nr_free_pagecache_pages(void); + + + /* linux/mm/swap.c */ ++DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); + extern void lru_cache_add(struct page *); + extern void lru_cache_add_anon(struct page *page); + extern void lru_cache_add_file(struct page *page); +diff --git a/mm/compaction.c b/mm/compaction.c +index 5079ddbec8f9..c40d3a13cbbd 100644 +--- a/mm/compaction.c ++++ b/mm/compaction.c +@@ -1668,10 +1668,12 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro + block_start_pfn(cc->migrate_pfn, cc->order); + + if (cc->last_migrated_pfn < current_block_start) { +- cpu = get_cpu(); ++ cpu = get_cpu_light(); ++ local_lock_irq(swapvec_lock); + lru_add_drain_cpu(cpu); ++ local_unlock_irq(swapvec_lock); + drain_local_pages(zone); +- put_cpu(); ++ put_cpu_light(); + /* No more flushing until we migrate again */ + cc->last_migrated_pfn = 0; + } +diff --git a/mm/page_alloc.c b/mm/page_alloc.c +index 59ea701ecfe0..11c08cfd6dfb 100644 +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -7257,8 +7257,9 @@ void __init free_area_init(unsigned long *zones_size) + + static int page_alloc_cpu_dead(unsigned int cpu) + { +- ++ local_lock_irq_on(swapvec_lock, cpu); + lru_add_drain_cpu(cpu); ++ local_unlock_irq_on(swapvec_lock, cpu); + drain_pages(cpu); + + /* +diff --git a/mm/swap.c b/mm/swap.c +index 45fdbfb6b2a6..92f994b962f0 100644 +--- a/mm/swap.c ++++ b/mm/swap.c +@@ -33,6 +33,7 @@ + #include <linux/memcontrol.h> + #include <linux/gfp.h> + #include <linux/uio.h> ++#include <linux/locallock.h> + #include <linux/hugetlb.h> + #include <linux/page_idle.h> + +@@ -51,6 +52,8 @@ static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs); + #ifdef CONFIG_SMP + static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); + #endif ++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); ++DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); + + /* + * This path almost never happens for VM activity - pages are normally +@@ -253,11 +256,11 @@ void rotate_reclaimable_page(struct page *page) + unsigned long flags; + + get_page(page); +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pvec = this_cpu_ptr(&lru_rotate_pvecs); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + } + +@@ -307,12 +310,13 @@ void activate_page(struct page *page) + { + page = compound_head(page); + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ activate_page_pvecs); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +- put_cpu_var(activate_page_pvecs); ++ put_locked_var(swapvec_lock, activate_page_pvecs); + } + } + +@@ -334,7 +338,7 @@ void activate_page(struct page *page) + + static void __lru_cache_activate_page(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + int i; + + /* +@@ -356,7 +360,7 @@ static void __lru_cache_activate_page(struct page *page) + } + } + +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /* +@@ -398,12 +402,12 @@ EXPORT_SYMBOL(mark_page_accessed); + + static void __lru_cache_add(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + __pagevec_lru_add(pvec); +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /** +@@ -581,9 +585,9 @@ void lru_add_drain_cpu(int cpu) + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -615,11 +619,12 @@ void deactivate_file_page(struct page *page) + return; + + if (likely(get_page_unless_zero(page))) { +- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_deactivate_file_pvecs); + + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); +- put_cpu_var(lru_deactivate_file_pvecs); ++ put_locked_var(swapvec_lock, lru_deactivate_file_pvecs); + } + } + +@@ -634,19 +639,20 @@ void mark_page_lazyfree(struct page *page) + { + if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && + !PageSwapCache(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_lazyfree_pvecs); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); +- put_cpu_var(lru_lazyfree_pvecs); ++ put_locked_var(swapvec_lock, lru_lazyfree_pvecs); + } + } + + void lru_add_drain(void) + { +- lru_add_drain_cpu(get_cpu()); +- put_cpu(); ++ lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); ++ local_unlock_cpu(swapvec_lock); + } + + #ifdef CONFIG_SMP +-- +2.36.1 + diff --git a/debian/patches-rt/0078-mm-perform-lru_add_drain_all-remotely.patch b/debian/patches-rt/0078-mm-perform-lru_add_drain_all-remotely.patch new file mode 100644 index 000000000..0983e2795 --- /dev/null +++ b/debian/patches-rt/0078-mm-perform-lru_add_drain_all-remotely.patch @@ -0,0 +1,109 @@ +From 9336f220ffe2a225210342f5977ec2636ffc8717 Mon Sep 17 00:00:00 2001 +From: Luiz Capitulino <lcapitulino@redhat.com> +Date: Fri, 27 May 2016 15:03:28 +0200 +Subject: [PATCH 078/347] mm: perform lru_add_drain_all() remotely +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +lru_add_drain_all() works by scheduling lru_add_drain_cpu() to run +on all CPUs that have non-empty LRU pagevecs and then waiting for +the scheduled work to complete. However, workqueue threads may never +have the chance to run on a CPU that's running a SCHED_FIFO task. +This causes lru_add_drain_all() to block forever. + +This commit solves this problem by changing lru_add_drain_all() +to drain the LRU pagevecs of remote CPUs. This is done by grabbing +swapvec_lock and calling lru_add_drain_cpu(). + +PS: This is based on an idea and initial implementation by + Rik van Riel. + +Signed-off-by: Rik van Riel <riel@redhat.com> +Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/swap.c | 36 ++++++++++++++++++++++++++++++------ + 1 file changed, 30 insertions(+), 6 deletions(-) + +diff --git a/mm/swap.c b/mm/swap.c +index 92f994b962f0..3885645a45ce 100644 +--- a/mm/swap.c ++++ b/mm/swap.c +@@ -585,9 +585,15 @@ void lru_add_drain_cpu(int cpu) + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ local_lock_irqsave_on(rotate_lock, flags, cpu); ++ pagevec_move_tail(pvec); ++ local_unlock_irqrestore_on(rotate_lock, flags, cpu); ++#else + local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); + local_unlock_irqrestore(rotate_lock, flags); ++#endif + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -657,6 +663,16 @@ void lru_add_drain(void) + + #ifdef CONFIG_SMP + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ local_lock_on(swapvec_lock, cpu); ++ lru_add_drain_cpu(cpu); ++ local_unlock_on(swapvec_lock, cpu); ++} ++ ++#else ++ + static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + + static void lru_add_drain_per_cpu(struct work_struct *dummy) +@@ -664,6 +680,16 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) + lru_add_drain(); + } + ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); ++ ++ INIT_WORK(work, lru_add_drain_per_cpu); ++ queue_work_on(cpu, mm_percpu_wq, work); ++ cpumask_set_cpu(cpu, has_work); ++} ++#endif ++ + /* + * Doesn't need any cpu hotplug locking because we do rely on per-cpu + * kworkers being shut down before our page_alloc_cpu_dead callback is +@@ -688,21 +714,19 @@ void lru_add_drain_all(void) + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { +- struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) || +- need_activate_page_drain(cpu)) { +- INIT_WORK(work, lru_add_drain_per_cpu); +- queue_work_on(cpu, mm_percpu_wq, work); +- cpumask_set_cpu(cpu, &has_work); +- } ++ need_activate_page_drain(cpu)) ++ remote_lru_add_drain(cpu, &has_work); + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); ++#endif + + mutex_unlock(&lock); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0079-mm-vmstat-Protect-per-cpu-variables-with-preempt-dis.patch b/debian/patches-rt/0079-mm-vmstat-Protect-per-cpu-variables-with-preempt-dis.patch new file mode 100644 index 000000000..0c7ea39e8 --- /dev/null +++ b/debian/patches-rt/0079-mm-vmstat-Protect-per-cpu-variables-with-preempt-dis.patch @@ -0,0 +1,145 @@ +From a61a39e63a0af178f57da615a22877b00fee0a58 Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:30:13 -0500 +Subject: [PATCH 079/347] mm/vmstat: Protect per cpu variables with preempt + disable on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Disable preemption on -RT for the vmstat code. On vanila the code runs in +IRQ-off regions while on -RT it is not. "preempt_disable" ensures that the +same ressources is not updated in parallel due to preemption. + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/vmstat.h | 4 ++++ + mm/vmstat.c | 12 ++++++++++++ + 2 files changed, 16 insertions(+) + +diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h +index f25cef84b41d..febee8649220 100644 +--- a/include/linux/vmstat.h ++++ b/include/linux/vmstat.h +@@ -54,7 +54,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states); + */ + static inline void __count_vm_event(enum vm_event_item item) + { ++ preempt_disable_rt(); + raw_cpu_inc(vm_event_states.event[item]); ++ preempt_enable_rt(); + } + + static inline void count_vm_event(enum vm_event_item item) +@@ -64,7 +66,9 @@ static inline void count_vm_event(enum vm_event_item item) + + static inline void __count_vm_events(enum vm_event_item item, long delta) + { ++ preempt_disable_rt(); + raw_cpu_add(vm_event_states.event[item], delta); ++ preempt_enable_rt(); + } + + static inline void count_vm_events(enum vm_event_item item, long delta) +diff --git a/mm/vmstat.c b/mm/vmstat.c +index 21e07e71ea2d..ff7c0d08f2b6 100644 +--- a/mm/vmstat.c ++++ b/mm/vmstat.c +@@ -320,6 +320,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -329,6 +330,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_zone_page_state); + +@@ -340,6 +342,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -349,6 +352,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_node_page_state); + +@@ -381,6 +385,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -389,6 +394,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +@@ -397,6 +403,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -405,6 +412,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) + node_page_state_add(v + overstep, pgdat, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +@@ -425,6 +433,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -433,6 +442,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) +@@ -441,6 +451,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -449,6 +460,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) + node_page_state_add(v - overstep, pgdat, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_zone_page_state(struct page *page, enum zone_stat_item item) +-- +2.36.1 + diff --git a/debian/patches-rt/0080-ARM-Initialize-split-page-table-locks-for-vector-pag.patch b/debian/patches-rt/0080-ARM-Initialize-split-page-table-locks-for-vector-pag.patch new file mode 100644 index 000000000..d983a6470 --- /dev/null +++ b/debian/patches-rt/0080-ARM-Initialize-split-page-table-locks-for-vector-pag.patch @@ -0,0 +1,76 @@ +From 2056bb928af7ba7036b8d058c0a52a182cd0b9b6 Mon Sep 17 00:00:00 2001 +From: Frank Rowand <frank.rowand@am.sony.com> +Date: Sat, 1 Oct 2011 18:58:13 -0700 +Subject: [PATCH 080/347] ARM: Initialize split page table locks for vector + page +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Without this patch, ARM can not use SPLIT_PTLOCK_CPUS if +PREEMPT_RT_FULL=y because vectors_user_mapping() creates a +VM_ALWAYSDUMP mapping of the vector page (address 0xffff0000), but no +ptl->lock has been allocated for the page. An attempt to coredump +that page will result in a kernel NULL pointer dereference when +follow_page() attempts to lock the page. + +The call tree to the NULL pointer dereference is: + + do_notify_resume() + get_signal_to_deliver() + do_coredump() + elf_core_dump() + get_dump_page() + __get_user_pages() + follow_page() + pte_offset_map_lock() <----- a #define + ... + rt_spin_lock() + +The underlying problem is exposed by mm-shrink-the-page-frame-to-rt-size.patch. + +Signed-off-by: Frank Rowand <frank.rowand@am.sony.com> +Cc: Frank <Frank_Rowand@sonyusa.com> +Cc: Peter Zijlstra <peterz@infradead.org> +Link: http://lkml.kernel.org/r/4E87C535.2030907@am.sony.com +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm/kernel/process.c | 24 ++++++++++++++++++++++++ + 1 file changed, 24 insertions(+) + +diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c +index 82ab015bf42b..8d3c7ce34c24 100644 +--- a/arch/arm/kernel/process.c ++++ b/arch/arm/kernel/process.c +@@ -324,6 +324,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) + } + + #ifdef CONFIG_MMU ++/* ++ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not ++ * initialized by pgtable_page_ctor() then a coredump of the vector page will ++ * fail. ++ */ ++static int __init vectors_user_mapping_init_page(void) ++{ ++ struct page *page; ++ unsigned long addr = 0xffff0000; ++ pgd_t *pgd; ++ pud_t *pud; ++ pmd_t *pmd; ++ ++ pgd = pgd_offset_k(addr); ++ pud = pud_offset(pgd, addr); ++ pmd = pmd_offset(pud, addr); ++ page = pmd_page(*(pmd)); ++ ++ pgtable_page_ctor(page); ++ ++ return 0; ++} ++late_initcall(vectors_user_mapping_init_page); ++ + #ifdef CONFIG_KUSER_HELPERS + /* + * The vectors page is always readable from user space for the +-- +2.36.1 + diff --git a/debian/patches-rt/0081-mm-Enable-SLUB-for-RT.patch b/debian/patches-rt/0081-mm-Enable-SLUB-for-RT.patch new file mode 100644 index 000000000..4d6e35faa --- /dev/null +++ b/debian/patches-rt/0081-mm-Enable-SLUB-for-RT.patch @@ -0,0 +1,42 @@ +From 24cc0bd393e472cf081687c51f59d2677a0ca367 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 25 Oct 2012 10:32:35 +0100 +Subject: [PATCH 081/347] mm: Enable SLUB for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Avoid the memory allocation in IRQ section + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +[bigeasy: factor out everything except the kcalloc() workaorund ] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/slub.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/mm/slub.c b/mm/slub.c +index a5a086ed4493..959ccf873292 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -3734,6 +3734,11 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, + const char *text) + { + #ifdef CONFIG_SLUB_DEBUG ++#ifdef CONFIG_PREEMPT_RT_BASE ++ /* XXX move out of irq-off section */ ++ slab_err(s, page, text, s->name); ++#else ++ + void *addr = page_address(page); + void *p; + unsigned long *map = kcalloc(BITS_TO_LONGS(page->objects), +@@ -3755,6 +3760,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, + slab_unlock(page); + kfree(map); + #endif ++#endif + } + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0082-slub-Enable-irqs-for-__GFP_WAIT.patch b/debian/patches-rt/0082-slub-Enable-irqs-for-__GFP_WAIT.patch new file mode 100644 index 000000000..05fa462e3 --- /dev/null +++ b/debian/patches-rt/0082-slub-Enable-irqs-for-__GFP_WAIT.patch @@ -0,0 +1,48 @@ +From e2e03d2e904d1df3d1e70dd70d5d939a6f5ccb26 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 9 Jan 2013 12:08:15 +0100 +Subject: [PATCH 082/347] slub: Enable irqs for __GFP_WAIT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +SYSTEM_RUNNING might be too late for enabling interrupts. Allocations +with GFP_WAIT can happen before that. So use this as an indicator. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + mm/slub.c | 9 ++++++++- + 1 file changed, 8 insertions(+), 1 deletion(-) + +diff --git a/mm/slub.c b/mm/slub.c +index 959ccf873292..3b1edb545215 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1597,10 +1597,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) + void *start, *p; + int idx, order; + bool shuffle; ++ bool enableirqs = false; + + flags &= gfp_allowed_mask; + + if (gfpflags_allow_blocking(flags)) ++ enableirqs = true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (system_state > SYSTEM_BOOTING) ++ enableirqs = true; ++#endif ++ if (enableirqs) + local_irq_enable(); + + flags |= s->allocflags; +@@ -1659,7 +1666,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) + page->frozen = 1; + + out: +- if (gfpflags_allow_blocking(flags)) ++ if (enableirqs) + local_irq_disable(); + if (!page) + return NULL; +-- +2.36.1 + diff --git a/debian/patches-rt/0083-slub-Disable-SLUB_CPU_PARTIAL.patch b/debian/patches-rt/0083-slub-Disable-SLUB_CPU_PARTIAL.patch new file mode 100644 index 000000000..12eef9aa5 --- /dev/null +++ b/debian/patches-rt/0083-slub-Disable-SLUB_CPU_PARTIAL.patch @@ -0,0 +1,54 @@ +From 1a6400867d9fa3d3e0c8d816c8ae5bb10c202e8a Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 15 Apr 2015 19:00:47 +0200 +Subject: [PATCH 083/347] slub: Disable SLUB_CPU_PARTIAL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 1, irqs_disabled(): 0, pid: 87, name: rcuop/7 +|1 lock held by rcuop/7/87: +| #0: (rcu_callback){......}, at: [<ffffffff8112c76a>] rcu_nocb_kthread+0x1ca/0x5d0 +|Preemption disabled at:[<ffffffff811eebd9>] put_cpu_partial+0x29/0x220 +| +|CPU: 0 PID: 87 Comm: rcuop/7 Tainted: G W 4.0.0-rt0+ #477 +|Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 +| 000000000007a9fc ffff88013987baf8 ffffffff817441c7 0000000000000007 +| 0000000000000000 ffff88013987bb18 ffffffff810eee51 0000000000000000 +| ffff88013fc10200 ffff88013987bb48 ffffffff8174a1c4 000000000007a9fc +|Call Trace: +| [<ffffffff817441c7>] dump_stack+0x4f/0x90 +| [<ffffffff810eee51>] ___might_sleep+0x121/0x1b0 +| [<ffffffff8174a1c4>] rt_spin_lock+0x24/0x60 +| [<ffffffff811a689a>] __free_pages_ok+0xaa/0x540 +| [<ffffffff811a729d>] __free_pages+0x1d/0x30 +| [<ffffffff811eddd5>] __free_slab+0xc5/0x1e0 +| [<ffffffff811edf46>] free_delayed+0x56/0x70 +| [<ffffffff811eecfd>] put_cpu_partial+0x14d/0x220 +| [<ffffffff811efc98>] __slab_free+0x158/0x2c0 +| [<ffffffff811f0021>] kmem_cache_free+0x221/0x2d0 +| [<ffffffff81204d0c>] file_free_rcu+0x2c/0x40 +| [<ffffffff8112c7e3>] rcu_nocb_kthread+0x243/0x5d0 +| [<ffffffff810e951c>] kthread+0xfc/0x120 +| [<ffffffff8174abc8>] ret_from_fork+0x58/0x90 + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + init/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/init/Kconfig b/init/Kconfig +index 1793e8bd71ef..0c912e74ee40 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1714,7 +1714,7 @@ config SLAB_FREELIST_HARDENED + + config SLUB_CPU_PARTIAL + default y +- depends on SLUB && SMP ++ depends on SLUB && SMP && !PREEMPT_RT_FULL + bool "SLUB per cpu partial cache" + help + Per cpu partial caches accellerate objects allocation and freeing +-- +2.36.1 + diff --git a/debian/patches-rt/0084-mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch b/debian/patches-rt/0084-mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch new file mode 100644 index 000000000..ddb288711 --- /dev/null +++ b/debian/patches-rt/0084-mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch @@ -0,0 +1,75 @@ +From 6b3d7c229967c2b2c01394e4dadcc8f210d52fa0 Mon Sep 17 00:00:00 2001 +From: Yang Shi <yang.shi@windriver.com> +Date: Wed, 30 Oct 2013 11:48:33 -0700 +Subject: [PATCH 084/347] mm/memcontrol: Don't call schedule_work_on in + preemption disabled context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The following trace is triggered when running ltp oom test cases: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 +in_atomic(): 1, irqs_disabled(): 0, pid: 17188, name: oom03 +Preemption disabled at:[<ffffffff8112ba70>] mem_cgroup_reclaim+0x90/0xe0 + +CPU: 2 PID: 17188 Comm: oom03 Not tainted 3.10.10-rt3 #2 +Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010 +ffff88007684d730 ffff880070df9b58 ffffffff8169918d ffff880070df9b70 +ffffffff8106db31 ffff88007688b4a0 ffff880070df9b88 ffffffff8169d9c0 +ffff88007688b4a0 ffff880070df9bc8 ffffffff81059da1 0000000170df9bb0 +Call Trace: +[<ffffffff8169918d>] dump_stack+0x19/0x1b +[<ffffffff8106db31>] __might_sleep+0xf1/0x170 +[<ffffffff8169d9c0>] rt_spin_lock+0x20/0x50 +[<ffffffff81059da1>] queue_work_on+0x61/0x100 +[<ffffffff8112b361>] drain_all_stock+0xe1/0x1c0 +[<ffffffff8112ba70>] mem_cgroup_reclaim+0x90/0xe0 +[<ffffffff8112beda>] __mem_cgroup_try_charge+0x41a/0xc40 +[<ffffffff810f1c91>] ? release_pages+0x1b1/0x1f0 +[<ffffffff8106f200>] ? sched_exec+0x40/0xb0 +[<ffffffff8112cc87>] mem_cgroup_charge_common+0x37/0x70 +[<ffffffff8112e2c6>] mem_cgroup_newpage_charge+0x26/0x30 +[<ffffffff8110af68>] handle_pte_fault+0x618/0x840 +[<ffffffff8103ecf6>] ? unpin_current_cpu+0x16/0x70 +[<ffffffff81070f94>] ? migrate_enable+0xd4/0x200 +[<ffffffff8110cde5>] handle_mm_fault+0x145/0x1e0 +[<ffffffff810301e1>] __do_page_fault+0x1a1/0x4c0 +[<ffffffff8169c9eb>] ? preempt_schedule_irq+0x4b/0x70 +[<ffffffff8169e3b7>] ? retint_kernel+0x37/0x40 +[<ffffffff8103053e>] do_page_fault+0xe/0x10 +[<ffffffff8169e4c2>] page_fault+0x22/0x30 + +So, to prevent schedule_work_on from being called in preempt disabled context, +replace the pair of get/put_cpu() to get/put_cpu_light(). + + +Signed-off-by: Yang Shi <yang.shi@windriver.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/memcontrol.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/mm/memcontrol.c b/mm/memcontrol.c +index f3aa6e6214d5..281d74f86892 100644 +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -2084,7 +2084,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) + * as well as workers from this path always operate on the local + * per-cpu data. CPU up doesn't touch memcg_stock at all. + */ +- curcpu = get_cpu(); ++ curcpu = get_cpu_light(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + struct mem_cgroup *memcg; +@@ -2104,7 +2104,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) + } + css_put(&memcg->css); + } +- put_cpu(); ++ put_cpu_light(); + mutex_unlock(&percpu_charge_mutex); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0085-mm-memcontrol-Replace-local_irq_disable-with-local-l.patch b/debian/patches-rt/0085-mm-memcontrol-Replace-local_irq_disable-with-local-l.patch new file mode 100644 index 000000000..8da70c668 --- /dev/null +++ b/debian/patches-rt/0085-mm-memcontrol-Replace-local_irq_disable-with-local-l.patch @@ -0,0 +1,124 @@ +From d5d11c92081bb9edd9eb11cd752a325f8822a0a5 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 28 Jan 2015 17:14:16 +0100 +Subject: [PATCH 085/347] mm/memcontrol: Replace local_irq_disable with local + locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There are a few local_irq_disable() which then take sleeping locks. This +patch converts them local locks. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/memcontrol.c | 24 ++++++++++++++++-------- + 1 file changed, 16 insertions(+), 8 deletions(-) + +diff --git a/mm/memcontrol.c b/mm/memcontrol.c +index 281d74f86892..239fec6eac9f 100644 +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -69,6 +69,7 @@ + #include <net/sock.h> + #include <net/ip.h> + #include "slab.h" ++#include <linux/locallock.h> + + #include <linux/uaccess.h> + +@@ -94,6 +95,8 @@ int do_swap_account __read_mostly; + #define do_swap_account 0 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(event_lock); ++ + /* Whether legacy memory+swap accounting is active */ + static bool do_memsw_account(void) + { +@@ -4933,12 +4936,12 @@ static int mem_cgroup_move_account(struct page *page, + + ret = 0; + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(to, page, compound, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, compound, -nr_pages); + memcg_check_events(from, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + out_unlock: + unlock_page(page); + out: +@@ -6057,10 +6060,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, + + commit_charge(page, memcg, lrucare); + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); + memcg_check_events(memcg, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + + if (do_memsw_account() && PageSwapCache(page)) { + swp_entry_t entry = { .val = page_private(page) }; +@@ -6129,7 +6132,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) + memcg_oom_recover(ug->memcg); + } + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); + __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file); + __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); +@@ -6137,7 +6140,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) + __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); + __this_cpu_add(ug->memcg->stat_cpu->nr_page_events, nr_pages); + memcg_check_events(ug->memcg, ug->dummy_page); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + + if (!mem_cgroup_is_root(ug->memcg)) + css_put_many(&ug->memcg->css, nr_pages); +@@ -6300,10 +6303,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) + + commit_charge(newpage, memcg, false); + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); + memcg_check_events(memcg, newpage); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + } + + DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); +@@ -6485,6 +6488,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) + struct mem_cgroup *memcg, *swap_memcg; + unsigned int nr_entries; + unsigned short oldid; ++ unsigned long flags; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); +@@ -6530,13 +6534,17 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) + * important here to have the interrupts disabled because it is the + * only synchronisation we have for updating the per-CPU variables. + */ ++ local_lock_irqsave(event_lock, flags); ++#ifndef CONFIG_PREEMPT_RT_BASE + VM_BUG_ON(!irqs_disabled()); ++#endif + mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), + -nr_entries); + memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put_many(&memcg->css, nr_entries); ++ local_unlock_irqrestore(event_lock, flags); + } + + /** +-- +2.36.1 + diff --git a/debian/patches-rt/0086-mm-zsmalloc-copy-with-get_cpu_var-and-locking.patch b/debian/patches-rt/0086-mm-zsmalloc-copy-with-get_cpu_var-and-locking.patch new file mode 100644 index 000000000..a3f158052 --- /dev/null +++ b/debian/patches-rt/0086-mm-zsmalloc-copy-with-get_cpu_var-and-locking.patch @@ -0,0 +1,203 @@ +From 7041bc73c6e3c572934b9c42968151577521955e Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Tue, 22 Mar 2016 11:16:09 +0100 +Subject: [PATCH 086/347] mm/zsmalloc: copy with get_cpu_var() and locking +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +get_cpu_var() disables preemption and triggers a might_sleep() splat later. +This is replaced with get_locked_var(). +This bitspinlocks are replaced with a proper mutex which requires a slightly +larger struct to allocate. + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +[bigeasy: replace the bitspin_lock() with a mutex, get_locked_var(). Mike then +fixed the size magic] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/zsmalloc.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++---- + 1 file changed, 74 insertions(+), 6 deletions(-) + +diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c +index 4d71356ea66a..50c5c3922b07 100644 +--- a/mm/zsmalloc.c ++++ b/mm/zsmalloc.c +@@ -56,6 +56,7 @@ + #include <linux/wait.h> + #include <linux/pagemap.h> + #include <linux/fs.h> ++#include <linux/locallock.h> + + #define ZSPAGE_MAGIC 0x58 + +@@ -73,9 +74,22 @@ + */ + #define ZS_MAX_ZSPAGE_ORDER 2 + #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) +- + #define ZS_HANDLE_SIZE (sizeof(unsigned long)) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct zsmalloc_handle { ++ unsigned long addr; ++ struct mutex lock; ++}; ++ ++#define ZS_HANDLE_ALLOC_SIZE (sizeof(struct zsmalloc_handle)) ++ ++#else ++ ++#define ZS_HANDLE_ALLOC_SIZE (sizeof(unsigned long)) ++#endif ++ + /* + * Object location (<PFN>, <obj_idx>) is encoded as + * as single (unsigned long) handle value. +@@ -325,7 +339,7 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} + + static int create_cache(struct zs_pool *pool) + { +- pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, ++ pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_ALLOC_SIZE, + 0, 0, NULL); + if (!pool->handle_cachep) + return 1; +@@ -349,10 +363,27 @@ static void destroy_cache(struct zs_pool *pool) + + static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp) + { +- return (unsigned long)kmem_cache_alloc(pool->handle_cachep, +- gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); ++ void *p; ++ ++ p = kmem_cache_alloc(pool->handle_cachep, ++ gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (p) { ++ struct zsmalloc_handle *zh = p; ++ ++ mutex_init(&zh->lock); ++ } ++#endif ++ return (unsigned long)p; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct zsmalloc_handle *zs_get_pure_handle(unsigned long handle) ++{ ++ return (void *)(handle &~((1 << OBJ_TAG_BITS) - 1)); ++} ++#endif ++ + static void cache_free_handle(struct zs_pool *pool, unsigned long handle) + { + kmem_cache_free(pool->handle_cachep, (void *)handle); +@@ -371,12 +402,18 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) + + static void record_obj(unsigned long handle, unsigned long obj) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ WRITE_ONCE(zh->addr, obj); ++#else + /* + * lsb of @obj represents handle lock while other bits + * represent object value the handle is pointing so + * updating shouldn't do store tearing. + */ + WRITE_ONCE(*(unsigned long *)handle, obj); ++#endif + } + + /* zpool driver */ +@@ -458,6 +495,7 @@ MODULE_ALIAS("zpool-zsmalloc"); + + /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ + static DEFINE_PER_CPU(struct mapping_area, zs_map_area); ++static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock); + + static bool is_zspage_isolated(struct zspage *zspage) + { +@@ -887,7 +925,13 @@ static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) + + static unsigned long handle_to_obj(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return zh->addr; ++#else + return *(unsigned long *)handle; ++#endif + } + + static unsigned long obj_to_head(struct page *page, void *obj) +@@ -901,22 +945,46 @@ static unsigned long obj_to_head(struct page *page, void *obj) + + static inline int testpin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_is_locked(&zh->lock); ++#else + return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static inline int trypin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_trylock(&zh->lock); ++#else + return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static void pin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_lock(&zh->lock); ++#else + bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static void unpin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_unlock(&zh->lock); ++#else + bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static void reset_page(struct page *page) +@@ -1342,7 +1410,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, + class = pool->size_class[class_idx]; + off = (class->size * obj_idx) & ~PAGE_MASK; + +- area = &get_cpu_var(zs_map_area); ++ area = &get_locked_var(zs_map_area_lock, zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ +@@ -1396,7 +1464,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) + + __zs_unmap_object(area, pages, off, class->size); + } +- put_cpu_var(zs_map_area); ++ put_locked_var(zs_map_area_lock, zs_map_area); + + migrate_read_unlock(zspage); + unpin_tag(handle); +-- +2.36.1 + diff --git a/debian/patches-rt/0087-x86-mm-pat-disable-preemption-__split_large_page-aft.patch b/debian/patches-rt/0087-x86-mm-pat-disable-preemption-__split_large_page-aft.patch new file mode 100644 index 000000000..6f9e4c5a0 --- /dev/null +++ b/debian/patches-rt/0087-x86-mm-pat-disable-preemption-__split_large_page-aft.patch @@ -0,0 +1,62 @@ +From 0d3b3e949716c72656373354c9658f523cf369a2 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 11 Dec 2018 21:53:43 +0100 +Subject: [PATCH 087/347] x86/mm/pat: disable preemption __split_large_page() + after spin_lock() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Commit "x86/mm/pat: Disable preemption around __flush_tlb_all()" added a +warning if __flush_tlb_all() is invoked in preemptible context. On !RT +the warning does not trigger because a spin lock is acquired which +disables preemption. On RT the spin lock does not disable preemption and +so the warning is seen. + +Disable preemption to avoid the warning __flush_tlb_all(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/mm/pageattr.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c +index 101f3ad0d6ad..0b0396261ca1 100644 +--- a/arch/x86/mm/pageattr.c ++++ b/arch/x86/mm/pageattr.c +@@ -687,12 +687,18 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, + pgprot_t ref_prot; + + spin_lock(&pgd_lock); ++ /* ++ * Keep preemption disabled after __flush_tlb_all() which expects not be ++ * preempted during the flush of the local TLB. ++ */ ++ preempt_disable(); + /* + * Check for races, another CPU might have split this page + * up for us already: + */ + tmp = _lookup_address_cpa(cpa, address, &level); + if (tmp != kpte) { ++ preempt_enable(); + spin_unlock(&pgd_lock); + return 1; + } +@@ -726,6 +732,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, + break; + + default: ++ preempt_enable(); + spin_unlock(&pgd_lock); + return 1; + } +@@ -764,6 +771,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, + * going on. + */ + __flush_tlb_all(); ++ preempt_enable(); + spin_unlock(&pgd_lock); + + return 0; +-- +2.36.1 + diff --git a/debian/patches-rt/0088-radix-tree-use-local-locks.patch b/debian/patches-rt/0088-radix-tree-use-local-locks.patch new file mode 100644 index 000000000..97af42757 --- /dev/null +++ b/debian/patches-rt/0088-radix-tree-use-local-locks.patch @@ -0,0 +1,176 @@ +From af6ad9480a842859f957315fdf189b6ad041a4be Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 25 Jan 2017 16:34:27 +0100 +Subject: [PATCH 088/347] radix-tree: use local locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The preload functionality uses per-CPU variables and preempt-disable to +ensure that it does not switch CPUs during its usage. This patch adds +local_locks() instead preempt_disable() for the same purpose and to +remain preemptible on -RT. + +Cc: stable-rt@vger.kernel.org +Reported-and-debugged-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/idr.h | 5 +---- + include/linux/radix-tree.h | 7 ++----- + lib/radix-tree.c | 32 +++++++++++++++++++++++--------- + 3 files changed, 26 insertions(+), 18 deletions(-) + +diff --git a/include/linux/idr.h b/include/linux/idr.h +index b6c6151c7446..81c9df5c04fa 100644 +--- a/include/linux/idr.h ++++ b/include/linux/idr.h +@@ -169,10 +169,7 @@ static inline bool idr_is_empty(const struct idr *idr) + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ +-static inline void idr_preload_end(void) +-{ +- preempt_enable(); +-} ++void idr_preload_end(void); + + /** + * idr_for_each_entry() - Iterate over an IDR's elements of a given type. +diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h +index 34149e8b5f73..affb0fc4c5b6 100644 +--- a/include/linux/radix-tree.h ++++ b/include/linux/radix-tree.h +@@ -330,6 +330,8 @@ unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, + int radix_tree_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); ++void radix_tree_preload_end(void); ++ + void radix_tree_init(void); + void *radix_tree_tag_set(struct radix_tree_root *, + unsigned long index, unsigned int tag); +@@ -349,11 +351,6 @@ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, + unsigned int max_items, unsigned int tag); + int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); + +-static inline void radix_tree_preload_end(void) +-{ +- preempt_enable(); +-} +- + int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); + int radix_tree_split(struct radix_tree_root *, unsigned long index, + unsigned new_order); +diff --git a/lib/radix-tree.c b/lib/radix-tree.c +index e5cab5c4e383..9309e813bc1f 100644 +--- a/lib/radix-tree.c ++++ b/lib/radix-tree.c +@@ -38,7 +38,7 @@ + #include <linux/rcupdate.h> + #include <linux/slab.h> + #include <linux/string.h> +- ++#include <linux/locallock.h> + + /* Number of nodes in fully populated tree of given height */ + static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; +@@ -87,6 +87,7 @@ struct radix_tree_preload { + struct radix_tree_node *nodes; + }; + static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; ++static DEFINE_LOCAL_IRQ_LOCK(radix_tree_preloads_lock); + + static inline struct radix_tree_node *entry_to_node(void *ptr) + { +@@ -405,12 +406,13 @@ radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ +- rtp = this_cpu_ptr(&radix_tree_preloads); ++ rtp = &get_locked_var(radix_tree_preloads_lock, radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes; + rtp->nodes = ret->parent; + rtp->nr--; + } ++ put_locked_var(radix_tree_preloads_lock, radix_tree_preloads); + /* + * Update the allocation stack trace as this is more useful + * for debugging. +@@ -476,14 +478,14 @@ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) + */ + gfp_mask &= ~__GFP_ACCOUNT; + +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + rtp = this_cpu_ptr(&radix_tree_preloads); + while (rtp->nr < nr) { +- preempt_enable(); ++ local_unlock(radix_tree_preloads_lock); + node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); + if (node == NULL) + goto out; +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + rtp = this_cpu_ptr(&radix_tree_preloads); + if (rtp->nr < nr) { + node->parent = rtp->nodes; +@@ -525,7 +527,7 @@ int radix_tree_maybe_preload(gfp_t gfp_mask) + if (gfpflags_allow_blocking(gfp_mask)) + return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); + /* Preloading doesn't help anything with this gfp mask, skip it */ +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + return 0; + } + EXPORT_SYMBOL(radix_tree_maybe_preload); +@@ -563,7 +565,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) + + /* Preloading doesn't help anything with this gfp mask, skip it */ + if (!gfpflags_allow_blocking(gfp_mask)) { +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + return 0; + } + +@@ -597,6 +599,12 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) + return __radix_tree_preload(gfp_mask, nr_nodes); + } + ++void radix_tree_preload_end(void) ++{ ++ local_unlock(radix_tree_preloads_lock); ++} ++EXPORT_SYMBOL(radix_tree_preload_end); ++ + static unsigned radix_tree_load_root(const struct radix_tree_root *root, + struct radix_tree_node **nodep, unsigned long *maxindex) + { +@@ -2102,10 +2110,16 @@ EXPORT_SYMBOL(radix_tree_tagged); + void idr_preload(gfp_t gfp_mask) + { + if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + } + EXPORT_SYMBOL(idr_preload); + ++void idr_preload_end(void) ++{ ++ local_unlock(radix_tree_preloads_lock); ++} ++EXPORT_SYMBOL(idr_preload_end); ++ + int ida_pre_get(struct ida *ida, gfp_t gfp) + { + /* +@@ -2114,7 +2128,7 @@ int ida_pre_get(struct ida *ida, gfp_t gfp) + * to return to the ida_pre_get() step. + */ + if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE)) +- preempt_enable(); ++ local_unlock(radix_tree_preloads_lock); + + if (!this_cpu_read(ida_bitmap)) { + struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp); +-- +2.36.1 + diff --git a/debian/patches-rt/0089-timers-Prepare-for-full-preemption.patch b/debian/patches-rt/0089-timers-Prepare-for-full-preemption.patch new file mode 100644 index 000000000..35a649740 --- /dev/null +++ b/debian/patches-rt/0089-timers-Prepare-for-full-preemption.patch @@ -0,0 +1,176 @@ +From 413cdf16e5561fbf143c28525fe70c1fd441a624 Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:29:34 -0500 +Subject: [PATCH 089/347] timers: Prepare for full preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When softirqs can be preempted we need to make sure that cancelling +the timer from the active thread can not deadlock vs. a running timer +callback. Add a waitqueue to resolve that. + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/timer.h | 2 +- + kernel/sched/core.c | 9 +++++++-- + kernel/time/timer.c | 45 +++++++++++++++++++++++++++++++++++++++---- + 3 files changed, 49 insertions(+), 7 deletions(-) + +diff --git a/include/linux/timer.h b/include/linux/timer.h +index 7b066fd38248..54627d046b3a 100644 +--- a/include/linux/timer.h ++++ b/include/linux/timer.h +@@ -172,7 +172,7 @@ extern void add_timer(struct timer_list *timer); + + extern int try_to_del_timer_sync(struct timer_list *timer); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + extern int del_timer_sync(struct timer_list *timer); + #else + # define del_timer_sync(t) del_timer(t) +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 0a51a66f5a63..974d92afd23e 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -498,11 +498,14 @@ void resched_cpu(int cpu) + */ + int get_nohz_timer_target(void) + { +- int i, cpu = smp_processor_id(); ++ int i, cpu; + struct sched_domain *sd; + ++ preempt_disable_rt(); ++ cpu = smp_processor_id(); ++ + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) +- return cpu; ++ goto preempt_en_rt; + + rcu_read_lock(); + for_each_domain(cpu, sd) { +@@ -521,6 +524,8 @@ int get_nohz_timer_target(void) + cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + unlock: + rcu_read_unlock(); ++preempt_en_rt: ++ preempt_enable_rt(); + return cpu; + } + +diff --git a/kernel/time/timer.c b/kernel/time/timer.c +index a6e88d9bb931..0043bf8e2c90 100644 +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -45,6 +45,7 @@ + #include <linux/slab.h> + #include <linux/compat.h> + #include <linux/random.h> ++#include <linux/swait.h> + + #include <linux/uaccess.h> + #include <asm/unistd.h> +@@ -198,6 +199,9 @@ EXPORT_SYMBOL(jiffies_64); + struct timer_base { + raw_spinlock_t lock; + struct timer_list *running_timer; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct swait_queue_head wait_for_running_timer; ++#endif + unsigned long clk; + unsigned long next_expiry; + unsigned int cpu; +@@ -1190,6 +1194,33 @@ void add_timer_on(struct timer_list *timer, int cpu) + } + EXPORT_SYMBOL_GPL(add_timer_on); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Wait for a running timer ++ */ ++static void wait_for_running_timer(struct timer_list *timer) ++{ ++ struct timer_base *base; ++ u32 tf = timer->flags; ++ ++ if (tf & TIMER_MIGRATING) ++ return; ++ ++ base = get_timer_base(tf); ++ swait_event_exclusive(base->wait_for_running_timer, ++ base->running_timer != timer); ++} ++ ++# define wakeup_timer_waiters(b) swake_up_all(&(b)->wait_for_running_timer) ++#else ++static inline void wait_for_running_timer(struct timer_list *timer) ++{ ++ cpu_relax(); ++} ++ ++# define wakeup_timer_waiters(b) do { } while (0) ++#endif ++ + /** + * del_timer - deactivate a timer. + * @timer: the timer to be deactivated +@@ -1245,7 +1276,7 @@ int try_to_del_timer_sync(struct timer_list *timer) + } + EXPORT_SYMBOL(try_to_del_timer_sync); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + /** + * del_timer_sync - deactivate a timer and wait for the handler to finish. + * @timer: the timer to be deactivated +@@ -1305,7 +1336,7 @@ int del_timer_sync(struct timer_list *timer) + int ret = try_to_del_timer_sync(timer); + if (ret >= 0) + return ret; +- cpu_relax(); ++ wait_for_running_timer(timer); + } + } + EXPORT_SYMBOL(del_timer_sync); +@@ -1366,13 +1397,16 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) + + fn = timer->function; + +- if (timer->flags & TIMER_IRQSAFE) { ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && ++ timer->flags & TIMER_IRQSAFE) { + raw_spin_unlock(&base->lock); + call_timer_fn(timer, fn); ++ base->running_timer = NULL; + raw_spin_lock(&base->lock); + } else { + raw_spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn); ++ base->running_timer = NULL; + raw_spin_lock_irq(&base->lock); + } + } +@@ -1695,8 +1729,8 @@ static inline void __run_timers(struct timer_base *base) + while (levels--) + expire_timers(base, heads + levels); + } +- base->running_timer = NULL; + raw_spin_unlock_irq(&base->lock); ++ wakeup_timer_waiters(base); + } + + /* +@@ -1941,6 +1975,9 @@ static void __init init_timer_cpu(int cpu) + base->cpu = cpu; + raw_spin_lock_init(&base->lock); + base->clk = jiffies; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ init_swait_queue_head(&base->wait_for_running_timer); ++#endif + } + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0090-x86-kvm-Require-const-tsc-for-RT.patch b/debian/patches-rt/0090-x86-kvm-Require-const-tsc-for-RT.patch new file mode 100644 index 000000000..f748cb9d8 --- /dev/null +++ b/debian/patches-rt/0090-x86-kvm-Require-const-tsc-for-RT.patch @@ -0,0 +1,37 @@ +From 53f33d36d7741754ec7b7f2e4a0c62faa30d6902 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 6 Nov 2011 12:26:18 +0100 +Subject: [PATCH 090/347] x86: kvm Require const tsc for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Non constant TSC is a nightmare on bare metal already, but with +virtualization it becomes a complete disaster because the workarounds +are horrible latency wise. That's also a preliminary for running RT in +a guest on top of a RT host. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/kvm/x86.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c +index 417abc9ba1ad..9829e0fbdd41 100644 +--- a/arch/x86/kvm/x86.c ++++ b/arch/x86/kvm/x86.c +@@ -6875,6 +6875,13 @@ int kvm_arch_init(void *opaque) + goto out; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { ++ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); ++ return -EOPNOTSUPP; ++ } ++#endif ++ + r = kvm_mmu_module_init(); + if (r) + goto out_free_percpu; +-- +2.36.1 + diff --git a/debian/patches-rt/0091-pci-switchtec-Don-t-use-completion-s-wait-queue.patch b/debian/patches-rt/0091-pci-switchtec-Don-t-use-completion-s-wait-queue.patch new file mode 100644 index 000000000..c42b306c1 --- /dev/null +++ b/debian/patches-rt/0091-pci-switchtec-Don-t-use-completion-s-wait-queue.patch @@ -0,0 +1,115 @@ +From aec60cbb460a43de9b530e8b08d24c032292c210 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 4 Oct 2017 10:24:23 +0200 +Subject: [PATCH 091/347] pci/switchtec: Don't use completion's wait queue +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The poll callback is using completion's wait_queue_head_t member and +puts it in poll_wait() so the poll() caller gets a wakeup after command +completed. This does not work on RT because we don't have a +wait_queue_head_t in our completion implementation. Nobody in tree does +like that in tree so this is the only driver that breaks. + +Instead of using the completion here is waitqueue with a status flag as +suggested by Logan. + +I don't have the HW so I have no idea if it works as expected, so please +test it. + +Cc: Kurt Schwemmer <kurt.schwemmer@microsemi.com> +Cc: Logan Gunthorpe <logang@deltatee.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/pci/switch/switchtec.c | 22 +++++++++++++--------- + 1 file changed, 13 insertions(+), 9 deletions(-) + +diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c +index 291c0074ad6f..a8df847bedee 100644 +--- a/drivers/pci/switch/switchtec.c ++++ b/drivers/pci/switch/switchtec.c +@@ -43,10 +43,11 @@ struct switchtec_user { + + enum mrpc_state state; + +- struct completion comp; ++ wait_queue_head_t cmd_comp; + struct kref kref; + struct list_head list; + ++ bool cmd_done; + u32 cmd; + u32 status; + u32 return_code; +@@ -68,7 +69,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev) + stuser->stdev = stdev; + kref_init(&stuser->kref); + INIT_LIST_HEAD(&stuser->list); +- init_completion(&stuser->comp); ++ init_waitqueue_head(&stuser->cmd_comp); + stuser->event_cnt = atomic_read(&stdev->event_cnt); + + dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser); +@@ -147,7 +148,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser) + kref_get(&stuser->kref); + stuser->read_len = sizeof(stuser->data); + stuser_set_state(stuser, MRPC_QUEUED); +- reinit_completion(&stuser->comp); ++ stuser->cmd_done = false; + list_add_tail(&stuser->list, &stdev->mrpc_queue); + + mrpc_cmd_submit(stdev); +@@ -184,7 +185,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) + stuser->read_len); + + out: +- complete_all(&stuser->comp); ++ stuser->cmd_done = true; ++ wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + stdev->mrpc_busy = 0; +@@ -454,10 +456,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data, + mutex_unlock(&stdev->mrpc_mutex); + + if (filp->f_flags & O_NONBLOCK) { +- if (!try_wait_for_completion(&stuser->comp)) ++ if (!READ_ONCE(stuser->cmd_done)) + return -EAGAIN; + } else { +- rc = wait_for_completion_interruptible(&stuser->comp); ++ rc = wait_event_interruptible(stuser->cmd_comp, ++ stuser->cmd_done); + if (rc < 0) + return rc; + } +@@ -505,7 +508,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait) + struct switchtec_dev *stdev = stuser->stdev; + __poll_t ret = 0; + +- poll_wait(filp, &stuser->comp.wait, wait); ++ poll_wait(filp, &stuser->cmd_comp, wait); + poll_wait(filp, &stdev->event_wq, wait); + + if (lock_mutex_and_test_alive(stdev)) +@@ -513,7 +516,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait) + + mutex_unlock(&stdev->mrpc_mutex); + +- if (try_wait_for_completion(&stuser->comp)) ++ if (READ_ONCE(stuser->cmd_done)) + ret |= EPOLLIN | EPOLLRDNORM; + + if (stuser->event_cnt != atomic_read(&stdev->event_cnt)) +@@ -1037,7 +1040,8 @@ static void stdev_kill(struct switchtec_dev *stdev) + + /* Wake up and kill any users waiting on an MRPC request */ + list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) { +- complete_all(&stuser->comp); ++ stuser->cmd_done = true; ++ wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0092-wait.h-include-atomic.h.patch b/debian/patches-rt/0092-wait.h-include-atomic.h.patch new file mode 100644 index 000000000..03bf6c567 --- /dev/null +++ b/debian/patches-rt/0092-wait.h-include-atomic.h.patch @@ -0,0 +1,42 @@ +From d06c78959ab56d0307d0d41aa75324ab707d0ca3 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 28 Oct 2013 12:19:57 +0100 +Subject: [PATCH 092/347] wait.h: include atomic.h +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +| CC init/main.o +|In file included from include/linux/mmzone.h:9:0, +| from include/linux/gfp.h:4, +| from include/linux/kmod.h:22, +| from include/linux/module.h:13, +| from init/main.c:15: +|include/linux/wait.h: In function ‘wait_on_atomic_t’: +|include/linux/wait.h:982:2: error: implicit declaration of function ‘atomic_read’ [-Werror=implicit-function-declaration] +| if (atomic_read(val) == 0) +| ^ + +This pops up on ARM. Non-RT gets its atomic.h include from spinlock.h + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/wait.h | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/include/linux/wait.h b/include/linux/wait.h +index 1d726d79063c..189da6e44756 100644 +--- a/include/linux/wait.h ++++ b/include/linux/wait.h +@@ -10,6 +10,7 @@ + + #include <asm/current.h> + #include <uapi/linux/wait.h> ++#include <linux/atomic.h> + + typedef struct wait_queue_entry wait_queue_entry_t; + +-- +2.36.1 + diff --git a/debian/patches-rt/0093-work-simple-Simple-work-queue-implemenation.patch b/debian/patches-rt/0093-work-simple-Simple-work-queue-implemenation.patch new file mode 100644 index 000000000..4c0335469 --- /dev/null +++ b/debian/patches-rt/0093-work-simple-Simple-work-queue-implemenation.patch @@ -0,0 +1,246 @@ +From fd404eb0247d5c8b5574eb138485984a7e7568ef Mon Sep 17 00:00:00 2001 +From: Daniel Wagner <daniel.wagner@bmw-carit.de> +Date: Fri, 11 Jul 2014 15:26:11 +0200 +Subject: [PATCH 093/347] work-simple: Simple work queue implemenation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Provides a framework for enqueuing callbacks from irq context +PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. + +Bases on wait-simple. + +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> +--- + include/linux/swork.h | 24 ++++++ + kernel/sched/Makefile | 2 +- + kernel/sched/swork.c | 173 ++++++++++++++++++++++++++++++++++++++++++ + 3 files changed, 198 insertions(+), 1 deletion(-) + create mode 100644 include/linux/swork.h + create mode 100644 kernel/sched/swork.c + +diff --git a/include/linux/swork.h b/include/linux/swork.h +new file mode 100644 +index 000000000000..f175fa9a6016 +--- /dev/null ++++ b/include/linux/swork.h +@@ -0,0 +1,24 @@ ++#ifndef _LINUX_SWORK_H ++#define _LINUX_SWORK_H ++ ++#include <linux/list.h> ++ ++struct swork_event { ++ struct list_head item; ++ unsigned long flags; ++ void (*func)(struct swork_event *); ++}; ++ ++static inline void INIT_SWORK(struct swork_event *event, ++ void (*func)(struct swork_event *)) ++{ ++ event->flags = 0; ++ event->func = func; ++} ++ ++bool swork_queue(struct swork_event *sev); ++ ++int swork_get(void); ++void swork_put(void); ++ ++#endif /* _LINUX_SWORK_H */ +diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile +index 7fe183404c38..2b765aa4e2c4 100644 +--- a/kernel/sched/Makefile ++++ b/kernel/sched/Makefile +@@ -18,7 +18,7 @@ endif + + obj-y += core.o loadavg.o clock.o cputime.o + obj-y += idle.o fair.o rt.o deadline.o +-obj-y += wait.o wait_bit.o swait.o completion.o ++obj-y += wait.o wait_bit.o swait.o swork.o completion.o + + obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o + obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o +diff --git a/kernel/sched/swork.c b/kernel/sched/swork.c +new file mode 100644 +index 000000000000..a5b89fdacf19 +--- /dev/null ++++ b/kernel/sched/swork.c +@@ -0,0 +1,173 @@ ++/* ++ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de ++ * ++ * Provides a framework for enqueuing callbacks from irq context ++ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. ++ */ ++ ++#include <linux/swait.h> ++#include <linux/swork.h> ++#include <linux/kthread.h> ++#include <linux/slab.h> ++#include <linux/spinlock.h> ++#include <linux/export.h> ++ ++#define SWORK_EVENT_PENDING (1 << 0) ++ ++static DEFINE_MUTEX(worker_mutex); ++static struct sworker *glob_worker; ++ ++struct sworker { ++ struct list_head events; ++ struct swait_queue_head wq; ++ ++ raw_spinlock_t lock; ++ ++ struct task_struct *task; ++ int refs; ++}; ++ ++static bool swork_readable(struct sworker *worker) ++{ ++ bool r; ++ ++ if (kthread_should_stop()) ++ return true; ++ ++ raw_spin_lock_irq(&worker->lock); ++ r = !list_empty(&worker->events); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ return r; ++} ++ ++static int swork_kthread(void *arg) ++{ ++ struct sworker *worker = arg; ++ ++ for (;;) { ++ swait_event_interruptible_exclusive(worker->wq, ++ swork_readable(worker)); ++ if (kthread_should_stop()) ++ break; ++ ++ raw_spin_lock_irq(&worker->lock); ++ while (!list_empty(&worker->events)) { ++ struct swork_event *sev; ++ ++ sev = list_first_entry(&worker->events, ++ struct swork_event, item); ++ list_del(&sev->item); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, ++ &sev->flags)); ++ sev->func(sev); ++ raw_spin_lock_irq(&worker->lock); ++ } ++ raw_spin_unlock_irq(&worker->lock); ++ } ++ return 0; ++} ++ ++static struct sworker *swork_create(void) ++{ ++ struct sworker *worker; ++ ++ worker = kzalloc(sizeof(*worker), GFP_KERNEL); ++ if (!worker) ++ return ERR_PTR(-ENOMEM); ++ ++ INIT_LIST_HEAD(&worker->events); ++ raw_spin_lock_init(&worker->lock); ++ init_swait_queue_head(&worker->wq); ++ ++ worker->task = kthread_run(swork_kthread, worker, "kswork"); ++ if (IS_ERR(worker->task)) { ++ kfree(worker); ++ return ERR_PTR(-ENOMEM); ++ } ++ ++ return worker; ++} ++ ++static void swork_destroy(struct sworker *worker) ++{ ++ kthread_stop(worker->task); ++ ++ WARN_ON(!list_empty(&worker->events)); ++ kfree(worker); ++} ++ ++/** ++ * swork_queue - queue swork ++ * ++ * Returns %false if @work was already on a queue, %true otherwise. ++ * ++ * The work is queued and processed on a random CPU ++ */ ++bool swork_queue(struct swork_event *sev) ++{ ++ unsigned long flags; ++ ++ if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) ++ return false; ++ ++ raw_spin_lock_irqsave(&glob_worker->lock, flags); ++ list_add_tail(&sev->item, &glob_worker->events); ++ raw_spin_unlock_irqrestore(&glob_worker->lock, flags); ++ ++ swake_up_one(&glob_worker->wq); ++ return true; ++} ++EXPORT_SYMBOL_GPL(swork_queue); ++ ++/** ++ * swork_get - get an instance of the sworker ++ * ++ * Returns an negative error code if the initialization if the worker did not ++ * work, %0 otherwise. ++ * ++ */ ++int swork_get(void) ++{ ++ struct sworker *worker; ++ ++ mutex_lock(&worker_mutex); ++ if (!glob_worker) { ++ worker = swork_create(); ++ if (IS_ERR(worker)) { ++ mutex_unlock(&worker_mutex); ++ return -ENOMEM; ++ } ++ ++ glob_worker = worker; ++ } ++ ++ glob_worker->refs++; ++ mutex_unlock(&worker_mutex); ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(swork_get); ++ ++/** ++ * swork_put - puts an instance of the sworker ++ * ++ * Will destroy the sworker thread. This function must not be called until all ++ * queued events have been completed. ++ */ ++void swork_put(void) ++{ ++ mutex_lock(&worker_mutex); ++ ++ glob_worker->refs--; ++ if (glob_worker->refs > 0) ++ goto out; ++ ++ swork_destroy(glob_worker); ++ glob_worker = NULL; ++out: ++ mutex_unlock(&worker_mutex); ++} ++EXPORT_SYMBOL_GPL(swork_put); +-- +2.36.1 + diff --git a/debian/patches-rt/0094-work-simple-drop-a-shit-statement-in-SWORK_EVENT_PEN.patch b/debian/patches-rt/0094-work-simple-drop-a-shit-statement-in-SWORK_EVENT_PEN.patch new file mode 100644 index 000000000..873809a1b --- /dev/null +++ b/debian/patches-rt/0094-work-simple-drop-a-shit-statement-in-SWORK_EVENT_PEN.patch @@ -0,0 +1,37 @@ +From eb5624af6c4a8461799304ee91b9d0fe34acfcb2 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 10 Sep 2018 18:00:31 +0200 +Subject: [PATCH 094/347] work-simple: drop a shit statement in + SWORK_EVENT_PENDING +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Dan Carpenter reported +| smatch warnings: +|kernel/sched/swork.c:63 swork_kthread() warn: test_bit() takes a bit number + +This is not a bug because we shift by zero (and use the same value in +both places). +Nevertheless I'm dropping that shift by zero to keep smatch quiet. + +Cc: Daniel Wagner <daniel.wagner@siemens.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/swork.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/sched/swork.c b/kernel/sched/swork.c +index a5b89fdacf19..c90d14b9b126 100644 +--- a/kernel/sched/swork.c ++++ b/kernel/sched/swork.c +@@ -12,7 +12,7 @@ + #include <linux/spinlock.h> + #include <linux/export.h> + +-#define SWORK_EVENT_PENDING (1 << 0) ++#define SWORK_EVENT_PENDING 1 + + static DEFINE_MUTEX(worker_mutex); + static struct sworker *glob_worker; +-- +2.36.1 + diff --git a/debian/patches-rt/0095-completion-Use-simple-wait-queues.patch b/debian/patches-rt/0095-completion-Use-simple-wait-queues.patch new file mode 100644 index 000000000..34be7740f --- /dev/null +++ b/debian/patches-rt/0095-completion-Use-simple-wait-queues.patch @@ -0,0 +1,391 @@ +From 6a60230ca64d58b651171ad00c84b251a7fd2046 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 11 Jan 2013 11:23:51 +0100 +Subject: [PATCH 095/347] completion: Use simple wait queues +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Completions have no long lasting callbacks and therefor do not need +the complex waitqueue variant. Use simple waitqueues which reduces the +contention on the waitqueue lock. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/platforms/ps3/device-init.c | 4 +-- + .../wireless/intersil/orinoco/orinoco_usb.c | 4 +-- + drivers/usb/gadget/function/f_fs.c | 2 +- + drivers/usb/gadget/legacy/inode.c | 4 +-- + include/linux/completion.h | 8 ++--- + include/linux/suspend.h | 6 ++++ + include/linux/swait.h | 2 ++ + kernel/power/hibernate.c | 7 ++++ + kernel/power/suspend.c | 4 +++ + kernel/sched/completion.c | 34 +++++++++---------- + kernel/sched/core.c | 10 ++++-- + kernel/sched/swait.c | 21 +++++++++++- + 12 files changed, 75 insertions(+), 31 deletions(-) + +diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c +index e7075aaff1bb..1580464a9d5b 100644 +--- a/arch/powerpc/platforms/ps3/device-init.c ++++ b/arch/powerpc/platforms/ps3/device-init.c +@@ -752,8 +752,8 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev, + } + pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); + +- res = wait_event_interruptible(dev->done.wait, +- dev->done.done || kthread_should_stop()); ++ res = swait_event_interruptible_exclusive(dev->done.wait, ++ dev->done.done || kthread_should_stop()); + if (kthread_should_stop()) + res = -EINTR; + if (res) { +diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c +index a04d59843022..e0046c35a0bd 100644 +--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c ++++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c +@@ -697,8 +697,8 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv, + while (!ctx->done.done && msecs--) + udelay(1000); + } else { +- wait_event_interruptible(ctx->done.wait, +- ctx->done.done); ++ swait_event_interruptible_exclusive(ctx->done.wait, ++ ctx->done.done); + } + break; + default: +diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c +index 49eb4e3c760f..49fc75368aa2 100644 +--- a/drivers/usb/gadget/function/f_fs.c ++++ b/drivers/usb/gadget/function/f_fs.c +@@ -1626,7 +1626,7 @@ static void ffs_data_put(struct ffs_data *ffs) + ffs_data_clear(ffs); + ffs_release_dev(ffs->private_data); + BUG_ON(waitqueue_active(&ffs->ev.waitq) || +- waitqueue_active(&ffs->ep0req_completion.wait) || ++ swait_active(&ffs->ep0req_completion.wait) || + waitqueue_active(&ffs->wait)); + destroy_workqueue(ffs->io_completion_wq); + kfree(ffs->dev_name); +diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c +index 3ebcbd199a79..a2240aa9f4ab 100644 +--- a/drivers/usb/gadget/legacy/inode.c ++++ b/drivers/usb/gadget/legacy/inode.c +@@ -345,7 +345,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) + spin_unlock_irq (&epdata->dev->lock); + + if (likely (value == 0)) { +- value = wait_event_interruptible (done.wait, done.done); ++ value = swait_event_interruptible_exclusive(done.wait, done.done); + if (value != 0) { + spin_lock_irq (&epdata->dev->lock); + if (likely (epdata->ep != NULL)) { +@@ -354,7 +354,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) + usb_ep_dequeue (epdata->ep, epdata->req); + spin_unlock_irq (&epdata->dev->lock); + +- wait_event (done.wait, done.done); ++ swait_event_exclusive(done.wait, done.done); + if (epdata->status == -ECONNRESET) + epdata->status = -EINTR; + } else { +diff --git a/include/linux/completion.h b/include/linux/completion.h +index 519e94915d18..bf8e77001f18 100644 +--- a/include/linux/completion.h ++++ b/include/linux/completion.h +@@ -9,7 +9,7 @@ + * See kernel/sched/completion.c for details. + */ + +-#include <linux/wait.h> ++#include <linux/swait.h> + + /* + * struct completion - structure used to maintain state for a "completion" +@@ -25,7 +25,7 @@ + */ + struct completion { + unsigned int done; +- wait_queue_head_t wait; ++ struct swait_queue_head wait; + }; + + #define init_completion_map(x, m) __init_completion(x) +@@ -34,7 +34,7 @@ static inline void complete_acquire(struct completion *x) {} + static inline void complete_release(struct completion *x) {} + + #define COMPLETION_INITIALIZER(work) \ +- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } ++ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) } + + #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \ + (*({ init_completion_map(&(work), &(map)); &(work); })) +@@ -85,7 +85,7 @@ static inline void complete_release(struct completion *x) {} + static inline void __init_completion(struct completion *x) + { + x->done = 0; +- init_waitqueue_head(&x->wait); ++ init_swait_queue_head(&x->wait); + } + + /** +diff --git a/include/linux/suspend.h b/include/linux/suspend.h +index 3f529ad9a9d2..328439ce71f5 100644 +--- a/include/linux/suspend.h ++++ b/include/linux/suspend.h +@@ -196,6 +196,12 @@ struct platform_s2idle_ops { + void (*end)(void); + }; + ++#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) ++extern bool pm_in_action; ++#else ++# define pm_in_action false ++#endif ++ + #ifdef CONFIG_SUSPEND + extern suspend_state_t mem_sleep_current; + extern suspend_state_t mem_sleep_default; +diff --git a/include/linux/swait.h b/include/linux/swait.h +index 73e06e9986d4..f426a0661aa0 100644 +--- a/include/linux/swait.h ++++ b/include/linux/swait.h +@@ -160,7 +160,9 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq) + extern void swake_up_one(struct swait_queue_head *q); + extern void swake_up_all(struct swait_queue_head *q); + extern void swake_up_locked(struct swait_queue_head *q); ++extern void swake_up_all_locked(struct swait_queue_head *q); + ++extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); + extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state); + extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); + +diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c +index 6abdfdf571ee..7020a6582a4c 100644 +--- a/kernel/power/hibernate.c ++++ b/kernel/power/hibernate.c +@@ -690,6 +690,10 @@ static int load_image_and_restore(void) + return error; + } + ++#ifndef CONFIG_SUSPEND ++bool pm_in_action; ++#endif ++ + /** + * hibernate - Carry out system hibernation, including saving the image. + */ +@@ -703,6 +707,8 @@ int hibernate(void) + return -EPERM; + } + ++ pm_in_action = true; ++ + lock_system_sleep(); + /* The snapshot device should not be opened while we're running */ + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { +@@ -781,6 +787,7 @@ int hibernate(void) + atomic_inc(&snapshot_device_available); + Unlock: + unlock_system_sleep(); ++ pm_in_action = false; + pr_info("hibernation exit\n"); + + return error; +diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c +index 0bd595a0b610..a4456772d98e 100644 +--- a/kernel/power/suspend.c ++++ b/kernel/power/suspend.c +@@ -600,6 +600,8 @@ static int enter_state(suspend_state_t state) + return error; + } + ++bool pm_in_action; ++ + /** + * pm_suspend - Externally visible function for suspending the system. + * @state: System sleep state to enter. +@@ -614,6 +616,7 @@ int pm_suspend(suspend_state_t state) + if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) + return -EINVAL; + ++ pm_in_action = true; + pr_info("suspend entry (%s)\n", mem_sleep_labels[state]); + error = enter_state(state); + if (error) { +@@ -623,6 +626,7 @@ int pm_suspend(suspend_state_t state) + suspend_stats.success++; + } + pr_info("suspend exit\n"); ++ pm_in_action = false; + return error; + } + EXPORT_SYMBOL(pm_suspend); +diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c +index a1ad5b7d5521..755a58084978 100644 +--- a/kernel/sched/completion.c ++++ b/kernel/sched/completion.c +@@ -29,12 +29,12 @@ void complete(struct completion *x) + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + + if (x->done != UINT_MAX) + x->done++; +- __wake_up_locked(&x->wait, TASK_NORMAL, 1); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ swake_up_locked(&x->wait); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete); + +@@ -58,10 +58,10 @@ void complete_all(struct completion *x) + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done = UINT_MAX; +- __wake_up_locked(&x->wait, TASK_NORMAL, 0); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ swake_up_all_locked(&x->wait); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete_all); + +@@ -70,20 +70,20 @@ do_wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) + { + if (!x->done) { +- DECLARE_WAITQUEUE(wait, current); ++ DECLARE_SWAITQUEUE(wait); + +- __add_wait_queue_entry_tail_exclusive(&x->wait, &wait); ++ __prepare_to_swait(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); +- __remove_wait_queue(&x->wait, &wait); ++ __finish_swait(&x->wait, &wait); + if (!x->done) + return timeout; + } +@@ -100,9 +100,9 @@ __wait_for_common(struct completion *x, + + complete_acquire(x); + +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + + complete_release(x); + +@@ -291,12 +291,12 @@ bool try_wait_for_completion(struct completion *x) + if (!READ_ONCE(x->done)) + return false; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = false; + else if (x->done != UINT_MAX) + x->done--; +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; + } + EXPORT_SYMBOL(try_wait_for_completion); +@@ -322,8 +322,8 @@ bool completion_done(struct completion *x) + * otherwise we can end up freeing the completion before complete() + * is done referencing it. + */ +- spin_lock_irqsave(&x->wait.lock, flags); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return true; + } + EXPORT_SYMBOL(completion_done); +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 974d92afd23e..3c5999476609 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7157,7 +7157,10 @@ void migrate_disable(void) + return; + } + #ifdef CONFIG_SCHED_DEBUG +- WARN_ON_ONCE(p->migrate_disable_atomic); ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } + #endif + + if (p->migrate_disable) { +@@ -7187,7 +7190,10 @@ void migrate_enable(void) + } + + #ifdef CONFIG_SCHED_DEBUG +- WARN_ON_ONCE(p->migrate_disable_atomic); ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } + #endif + + WARN_ON_ONCE(p->migrate_disable <= 0); +diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c +index 66b59ac77c22..c7cb30cdd1b7 100644 +--- a/kernel/sched/swait.c ++++ b/kernel/sched/swait.c +@@ -32,6 +32,25 @@ void swake_up_locked(struct swait_queue_head *q) + } + EXPORT_SYMBOL(swake_up_locked); + ++void swake_up_all_locked(struct swait_queue_head *q) ++{ ++ struct swait_queue *curr; ++ int wakes = 0; ++ ++ while (!list_empty(&q->task_list)) { ++ ++ curr = list_first_entry(&q->task_list, typeof(*curr), ++ task_list); ++ wake_up_process(curr->task); ++ list_del_init(&curr->task_list); ++ wakes++; ++ } ++ if (pm_in_action) ++ return; ++ WARN(wakes > 2, "complete_all() with %d waiters\n", wakes); ++} ++EXPORT_SYMBOL(swake_up_all_locked); ++ + void swake_up_one(struct swait_queue_head *q) + { + unsigned long flags; +@@ -69,7 +88,7 @@ void swake_up_all(struct swait_queue_head *q) + } + EXPORT_SYMBOL(swake_up_all); + +-static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) ++void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) + { + wait->task = current; + if (list_empty(&wait->task_list)) +-- +2.36.1 + diff --git a/debian/patches-rt/0096-fs-aio-simple-simple-work.patch b/debian/patches-rt/0096-fs-aio-simple-simple-work.patch new file mode 100644 index 000000000..3ac3a9d89 --- /dev/null +++ b/debian/patches-rt/0096-fs-aio-simple-simple-work.patch @@ -0,0 +1,89 @@ +From ccc2aded5c27d9bb441bcbe15f50369c098d4440 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 16 Feb 2015 18:49:10 +0100 +Subject: [PATCH 096/347] fs/aio: simple simple work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:768 +|in_atomic(): 1, irqs_disabled(): 0, pid: 26, name: rcuos/2 +|2 locks held by rcuos/2/26: +| #0: (rcu_callback){.+.+..}, at: [<ffffffff810b1a12>] rcu_nocb_kthread+0x1e2/0x380 +| #1: (rcu_read_lock_sched){.+.+..}, at: [<ffffffff812acd26>] percpu_ref_kill_rcu+0xa6/0x1c0 +|Preemption disabled at:[<ffffffff810b1a93>] rcu_nocb_kthread+0x263/0x380 +|Call Trace: +| [<ffffffff81582e9e>] dump_stack+0x4e/0x9c +| [<ffffffff81077aeb>] __might_sleep+0xfb/0x170 +| [<ffffffff81589304>] rt_spin_lock+0x24/0x70 +| [<ffffffff811c5790>] free_ioctx_users+0x30/0x130 +| [<ffffffff812ace34>] percpu_ref_kill_rcu+0x1b4/0x1c0 +| [<ffffffff810b1a93>] rcu_nocb_kthread+0x263/0x380 +| [<ffffffff8106e046>] kthread+0xd6/0xf0 +| [<ffffffff81591eec>] ret_from_fork+0x7c/0xb0 + +replace this preempt_disable() friendly swork. + +Reported-By: Mike Galbraith <umgwanakikbuti@gmail.com> +Suggested-by: Benjamin LaHaise <bcrl@kvack.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/aio.c | 15 +++++++++++++-- + 1 file changed, 13 insertions(+), 2 deletions(-) + +diff --git a/fs/aio.c b/fs/aio.c +index 9635c29b83da..21eacb0f3f56 100644 +--- a/fs/aio.c ++++ b/fs/aio.c +@@ -42,6 +42,7 @@ + #include <linux/ramfs.h> + #include <linux/percpu-refcount.h> + #include <linux/mount.h> ++#include <linux/swork.h> + + #include <asm/kmap_types.h> + #include <linux/uaccess.h> +@@ -121,6 +122,7 @@ struct kioctx { + long nr_pages; + + struct rcu_work free_rwork; /* see free_ioctx() */ ++ struct swork_event free_swork; /* see free_ioctx() */ + + /* + * signals when all in-flight requests are done +@@ -267,6 +269,7 @@ static int __init aio_setup(void) + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; ++ BUG_ON(swork_get()); + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); +@@ -608,9 +611,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref) + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users(struct percpu_ref *ref) ++static void free_ioctx_users_work(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_swork); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -628,6 +631,14 @@ static void free_ioctx_users(struct percpu_ref *ref) + percpu_ref_put(&ctx->reqs); + } + ++static void free_ioctx_users(struct percpu_ref *ref) ++{ ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ ++ INIT_SWORK(&ctx->free_swork, free_ioctx_users_work); ++ swork_queue(&ctx->free_swork); ++} ++ + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; +-- +2.36.1 + diff --git a/debian/patches-rt/0097-time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch b/debian/patches-rt/0097-time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch new file mode 100644 index 000000000..c3dd3b73e --- /dev/null +++ b/debian/patches-rt/0097-time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch @@ -0,0 +1,60 @@ +From 97abf968e205dd81621ca60a59060f3eda0c7081 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 15 Nov 2017 17:29:51 +0100 +Subject: [PATCH 097/347] time/hrtimer: avoid schedule_work() with interrupts + disabled +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The NOHZ code tries to schedule a workqueue with interrupts disabled. +Since this does not work -RT I am switching it to swork instead. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/timer.c | 15 +++++++++++---- + 1 file changed, 11 insertions(+), 4 deletions(-) + +diff --git a/kernel/time/timer.c b/kernel/time/timer.c +index 0043bf8e2c90..3cb79167852f 100644 +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -218,8 +218,7 @@ static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); + static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); + static DEFINE_MUTEX(timer_keys_mutex); + +-static void timer_update_keys(struct work_struct *work); +-static DECLARE_WORK(timer_update_work, timer_update_keys); ++static struct swork_event timer_update_swork; + + #ifdef CONFIG_SMP + unsigned int sysctl_timer_migration = 1; +@@ -237,7 +236,7 @@ static void timers_update_migration(void) + static inline void timers_update_migration(void) { } + #endif /* !CONFIG_SMP */ + +-static void timer_update_keys(struct work_struct *work) ++static void timer_update_keys(struct swork_event *event) + { + mutex_lock(&timer_keys_mutex); + timers_update_migration(); +@@ -247,9 +246,17 @@ static void timer_update_keys(struct work_struct *work) + + void timers_update_nohz(void) + { +- schedule_work(&timer_update_work); ++ swork_queue(&timer_update_swork); + } + ++static __init int hrtimer_init_thread(void) ++{ ++ WARN_ON(swork_get()); ++ INIT_SWORK(&timer_update_swork, timer_update_keys); ++ return 0; ++} ++early_initcall(hrtimer_init_thread); ++ + int timer_migration_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +-- +2.36.1 + diff --git a/debian/patches-rt/0098-hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch b/debian/patches-rt/0098-hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch new file mode 100644 index 000000000..997af2fb1 --- /dev/null +++ b/debian/patches-rt/0098-hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch @@ -0,0 +1,290 @@ +From 4b2913d980738fe5078dd581af6d6183c40a0616 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 3 Jul 2018 11:25:41 +0200 +Subject: [PATCH 098/347] hrtimer: consolidate hrtimer_init() + + hrtimer_init_sleeper() calls +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +hrtimer_init_sleeper() calls require a prior initialisation of the +hrtimer object with hrtimer_init(). Lets make the initialisation of +the hrtimer object part of hrtimer_init_sleeper(). To remain +consistent consider init_on_stack as well. + +Beside adapting the hrtimer_init_sleeper[_on_stack]() functions, call +sites need to be updated as well. + +Link: http://lkml.kernel.org/r/20180703092541.2870-1-anna-maria@linutronix.de +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +[anna-maria: Updating the commit message, add staging/android/vsoc.c] +Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> +--- + block/blk-mq.c | 3 +-- + drivers/staging/android/vsoc.c | 6 ++--- + include/linux/hrtimer.h | 19 +++++++++++--- + include/linux/wait.h | 4 +-- + kernel/futex.c | 19 ++++++-------- + kernel/time/hrtimer.c | 46 ++++++++++++++++++++++++++-------- + net/core/pktgen.c | 4 +-- + 7 files changed, 67 insertions(+), 34 deletions(-) + +diff --git a/block/blk-mq.c b/block/blk-mq.c +index ae70b4809bec..ffa97d90bde9 100644 +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -3139,10 +3139,9 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, + kt = nsecs; + + mode = HRTIMER_MODE_REL; +- hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode); ++ hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode, current); + hrtimer_set_expires(&hs.timer, kt); + +- hrtimer_init_sleeper(&hs, current); + do { + if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE) + break; +diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c +index 034d86869772..d089b2cb5dd7 100644 +--- a/drivers/staging/android/vsoc.c ++++ b/drivers/staging/android/vsoc.c +@@ -438,12 +438,10 @@ static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg) + return -EINVAL; + wake_time = ktime_set(arg->wake_time_sec, arg->wake_time_nsec); + +- hrtimer_init_on_stack(&to->timer, CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS); ++ hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_range_ns(&to->timer, wake_time, + current->timer_slack_ns); +- +- hrtimer_init_sleeper(to, current); + } + + while (1) { +diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h +index 542b4fa2cda9..cbd041b22088 100644 +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -364,10 +364,17 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device); + /* Initialize timers: */ + extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, + enum hrtimer_mode mode); ++extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task); + + #ifdef CONFIG_DEBUG_OBJECTS_TIMERS + extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, + enum hrtimer_mode mode); ++extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task); + + extern void destroy_hrtimer_on_stack(struct hrtimer *timer); + #else +@@ -377,6 +384,15 @@ static inline void hrtimer_init_on_stack(struct hrtimer *timer, + { + hrtimer_init(timer, which_clock, mode); + } ++ ++static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task) ++{ ++ hrtimer_init_sleeper(sl, clock_id, mode, task); ++} ++ + static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } + #endif + +@@ -486,9 +502,6 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp, + const enum hrtimer_mode mode, + const clockid_t clockid); + +-extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, +- struct task_struct *tsk); +- + extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, + const enum hrtimer_mode mode); + extern int schedule_hrtimeout_range_clock(ktime_t *expires, +diff --git a/include/linux/wait.h b/include/linux/wait.h +index 189da6e44756..523c68edc48a 100644 +--- a/include/linux/wait.h ++++ b/include/linux/wait.h +@@ -515,8 +515,8 @@ do { \ + int __ret = 0; \ + struct hrtimer_sleeper __t; \ + \ +- hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ +- hrtimer_init_sleeper(&__t, current); \ ++ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, HRTIMER_MODE_REL, \ ++ current); \ + if ((timeout) != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ +diff --git a/kernel/futex.c b/kernel/futex.c +index fac994367189..ac015d1dd16c 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2816,10 +2816,9 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, + if (abs_time) { + to = &timeout; + +- hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? +- CLOCK_REALTIME : CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS); +- hrtimer_init_sleeper(to, current); ++ hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ? ++ CLOCK_REALTIME : CLOCK_MONOTONIC, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); + } +@@ -2917,9 +2916,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + + if (time) { + to = &timeout; +- hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, +- HRTIMER_MODE_ABS); +- hrtimer_init_sleeper(to, current); ++ hrtimer_init_sleeper_on_stack(to, CLOCK_REALTIME, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires(&to->timer, *time); + } + +@@ -3349,10 +3347,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + + if (abs_time) { + to = &timeout; +- hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? +- CLOCK_REALTIME : CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS); +- hrtimer_init_sleeper(to, current); ++ hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ? ++ CLOCK_REALTIME : CLOCK_MONOTONIC, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); + } +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 32ee24f5142a..1e03d7fab81c 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1715,13 +1715,44 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) + return HRTIMER_NORESTART; + } + +-void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) ++static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task) + { ++ __hrtimer_init(&sl->timer, clock_id, mode); + sl->timer.function = hrtimer_wakeup; + sl->task = task; + } ++ ++/** ++ * hrtimer_init_sleeper - initialize sleeper to the given clock ++ * @sl: sleeper to be initialized ++ * @clock_id: the clock to be used ++ * @mode: timer mode abs/rel ++ * @task: the task to wake up ++ */ ++void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, ++ enum hrtimer_mode mode, struct task_struct *task) ++{ ++ debug_init(&sl->timer, clock_id, mode); ++ __hrtimer_init_sleeper(sl, clock_id, mode, task); ++ ++} + EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); + ++#ifdef CONFIG_DEBUG_OBJECTS_TIMERS ++void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task) ++{ ++ debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); ++ __hrtimer_init_sleeper(sl, clock_id, mode, task); ++} ++EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); ++#endif ++ + int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) + { + switch(restart->nanosleep.type) { +@@ -1745,8 +1776,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod + { + struct restart_block *restart; + +- hrtimer_init_sleeper(t, current); +- + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t->timer, mode); +@@ -1783,10 +1812,9 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) + struct hrtimer_sleeper t; + int ret; + +- hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, +- HRTIMER_MODE_ABS); ++ hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); +- + ret = do_nanosleep(&t, HRTIMER_MODE_ABS); + destroy_hrtimer_on_stack(&t.timer); + return ret; +@@ -1804,7 +1832,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp, + if (dl_task(current) || rt_task(current)) + slack = 0; + +- hrtimer_init_on_stack(&t.timer, clockid, mode); ++ hrtimer_init_sleeper_on_stack(&t, clockid, mode, current); + hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); + ret = do_nanosleep(&t, mode); + if (ret != -ERESTART_RESTARTBLOCK) +@@ -2003,11 +2031,9 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, + return -EINTR; + } + +- hrtimer_init_on_stack(&t.timer, clock_id, mode); ++ hrtimer_init_sleeper_on_stack(&t, clock_id, mode, current); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + +- hrtimer_init_sleeper(&t, current); +- + hrtimer_start_expires(&t.timer, mode); + + if (likely(t.task)) +diff --git a/net/core/pktgen.c b/net/core/pktgen.c +index 3714cd9e3111..2cea192b1475 100644 +--- a/net/core/pktgen.c ++++ b/net/core/pktgen.c +@@ -2160,7 +2160,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) + s64 remaining; + struct hrtimer_sleeper t; + +- hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS, ++ current); + hrtimer_set_expires(&t.timer, spin_until); + + remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); +@@ -2175,7 +2176,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) + } while (ktime_compare(end_time, spin_until) < 0); + } else { + /* see do_nanosleep */ +- hrtimer_init_sleeper(&t, current); + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); +-- +2.36.1 + diff --git a/debian/patches-rt/0099-hrtimers-Prepare-full-preemption.patch b/debian/patches-rt/0099-hrtimers-Prepare-full-preemption.patch new file mode 100644 index 000000000..897f91d52 --- /dev/null +++ b/debian/patches-rt/0099-hrtimers-Prepare-full-preemption.patch @@ -0,0 +1,290 @@ +From a5aed5c2dd54bdd010ed396577c328505028990d Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Fri, 3 Jul 2009 08:29:34 -0500 +Subject: [PATCH 099/347] hrtimers: Prepare full preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Make cancellation of a running callback in softirq context safe +against preemption. + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + fs/timerfd.c | 5 ++++- + include/linux/hrtimer.h | 13 +++++++++++- + include/linux/posix-timers.h | 2 +- + kernel/time/alarmtimer.c | 2 +- + kernel/time/hrtimer.c | 33 +++++++++++++++++++++++++++++- + kernel/time/itimer.c | 1 + + kernel/time/posix-timers.c | 39 ++++++++++++++++++++++++++++++++++-- + 7 files changed, 88 insertions(+), 7 deletions(-) + +diff --git a/fs/timerfd.c b/fs/timerfd.c +index d69ad801eb80..82d0f52414a6 100644 +--- a/fs/timerfd.c ++++ b/fs/timerfd.c +@@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, int flags, + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- cpu_relax(); ++ if (isalarm(ctx)) ++ hrtimer_wait_for_timer(&ctx->t.alarm.timer); ++ else ++ hrtimer_wait_for_timer(&ctx->t.tmr); + } + + /* +diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h +index cbd041b22088..8714f1a37d84 100644 +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -22,6 +22,7 @@ + #include <linux/percpu.h> + #include <linux/timer.h> + #include <linux/timerqueue.h> ++#include <linux/wait.h> + + struct hrtimer_clock_base; + struct hrtimer_cpu_base; +@@ -216,6 +217,9 @@ struct hrtimer_cpu_base { + ktime_t expires_next; + struct hrtimer *next_timer; + ktime_t softirq_expires_next; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ wait_queue_head_t wait; ++#endif + struct hrtimer *softirq_next_timer; + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + } ____cacheline_aligned; +@@ -433,6 +437,13 @@ static inline void hrtimer_restart(struct hrtimer *timer) + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* Softirq preemption could deadlock timer removal */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ extern void hrtimer_wait_for_timer(const struct hrtimer *timer); ++#else ++# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) ++#endif ++ + /* Query timers: */ + extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +@@ -464,7 +475,7 @@ static inline bool hrtimer_is_queued(struct hrtimer *timer) + * Helper function to check, whether the timer is running the callback + * function + */ +-static inline int hrtimer_callback_running(struct hrtimer *timer) ++static inline int hrtimer_callback_running(const struct hrtimer *timer) + { + return timer->base->running == timer; + } +diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h +index ee7e987ea1b4..0571b498db73 100644 +--- a/include/linux/posix-timers.h ++++ b/include/linux/posix-timers.h +@@ -114,8 +114,8 @@ struct k_itimer { + struct { + struct alarm alarmtimer; + } alarm; +- struct rcu_head rcu; + } it; ++ struct rcu_head rcu; + }; + + void run_posix_cpu_timers(struct task_struct *task); +diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c +index 6a2ba39889bd..f4c8cfde00b0 100644 +--- a/kernel/time/alarmtimer.c ++++ b/kernel/time/alarmtimer.c +@@ -438,7 +438,7 @@ int alarm_cancel(struct alarm *alarm) + int ret = alarm_try_to_cancel(alarm); + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(&alarm->timer); + } + } + EXPORT_SYMBOL_GPL(alarm_cancel); +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 1e03d7fab81c..8bbde17325c7 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -957,6 +957,33 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) + } + EXPORT_SYMBOL_GPL(hrtimer_forward); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define wake_up_timer_waiters(b) wake_up(&(b)->wait) ++ ++/** ++ * hrtimer_wait_for_timer - Wait for a running timer ++ * ++ * @timer: timer to wait for ++ * ++ * The function waits in case the timers callback function is ++ * currently executed on the waitqueue of the timer base. The ++ * waitqueue is woken up after the timer callback function has ++ * finished execution. ++ */ ++void hrtimer_wait_for_timer(const struct hrtimer *timer) ++{ ++ struct hrtimer_clock_base *base = timer->base; ++ ++ if (base && base->cpu_base && ++ base->index >= HRTIMER_BASE_MONOTONIC_SOFT) ++ wait_event(base->cpu_base->wait, ++ !(hrtimer_callback_running(timer))); ++} ++ ++#else ++# define wake_up_timer_waiters(b) do { } while (0) ++#endif ++ + /* + * enqueue_hrtimer - internal function to (re)start a timer + * +@@ -1238,7 +1265,7 @@ int hrtimer_cancel(struct hrtimer *timer) + + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1544,6 +1571,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) + hrtimer_update_softirq_timer(cpu_base, true); + + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); ++ wake_up_timer_waiters(cpu_base); + } + + #ifdef CONFIG_HIGH_RES_TIMERS +@@ -1913,6 +1941,9 @@ int hrtimers_prepare_cpu(unsigned int cpu) + cpu_base->softirq_next_timer = NULL; + cpu_base->expires_next = KTIME_MAX; + cpu_base->softirq_expires_next = KTIME_MAX; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ init_waitqueue_head(&cpu_base->wait); ++#endif + return 0; + } + +diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c +index 2e2b335ef101..7650ee736964 100644 +--- a/kernel/time/itimer.c ++++ b/kernel/time/itimer.c +@@ -211,6 +211,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); ++ hrtimer_wait_for_timer(&tsk->signal->real_timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); +diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c +index 48758108e055..2cf5aa704106 100644 +--- a/kernel/time/posix-timers.c ++++ b/kernel/time/posix-timers.c +@@ -463,7 +463,7 @@ static struct k_itimer * alloc_posix_timer(void) + + static void k_itimer_rcu_free(struct rcu_head *head) + { +- struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu); ++ struct k_itimer *tmr = container_of(head, struct k_itimer, rcu); + + kmem_cache_free(posix_timers_cache, tmr); + } +@@ -480,7 +480,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) + } + put_pid(tmr->it_pid); + sigqueue_free(tmr->sigq); +- call_rcu(&tmr->it.rcu, k_itimer_rcu_free); ++ call_rcu(&tmr->rcu, k_itimer_rcu_free); + } + + static int common_timer_create(struct k_itimer *new_timer) +@@ -821,6 +821,22 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* ++ * Protected by RCU! ++ */ ++static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timr) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (kc->timer_arm == common_hrtimer_arm) ++ hrtimer_wait_for_timer(&timr->it.real.timer); ++ else if (kc == &alarm_clock) ++ hrtimer_wait_for_timer(&timr->it.alarm.alarmtimer.timer); ++ else ++ /* FIXME: Whacky hack for posix-cpu-timers */ ++ schedule_timeout(1); ++#endif ++} ++ + static int common_hrtimer_try_to_cancel(struct k_itimer *timr) + { + return hrtimer_try_to_cancel(&timr->it.real.timer); +@@ -885,6 +901,7 @@ static int do_timer_settime(timer_t timer_id, int flags, + if (!timr) + return -EINVAL; + ++ rcu_read_lock(); + kc = timr->kclock; + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; +@@ -893,9 +910,12 @@ static int do_timer_settime(timer_t timer_id, int flags, + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { ++ timer_wait_for_callback(kc, timr); + old_spec64 = NULL; // We already got the old time... ++ rcu_read_unlock(); + goto retry; + } ++ rcu_read_unlock(); + + return error; + } +@@ -977,10 +997,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) + if (!timer) + return -EINVAL; + ++ rcu_read_lock(); + if (timer_delete_hook(timer) == TIMER_RETRY) { + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } ++ rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); +@@ -1006,8 +1031,18 @@ static void itimer_delete(struct k_itimer *timer) + retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + ++ /* On RT we can race with a deletion */ ++ if (!timer->it_signal) { ++ unlock_timer(timer, flags); ++ return; ++ } ++ + if (timer_delete_hook(timer) == TIMER_RETRY) { ++ rcu_read_lock(); + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } + list_del(&timer->list); +-- +2.36.1 + diff --git a/debian/patches-rt/0100-hrtimer-by-timers-by-default-into-the-softirq-contex.patch b/debian/patches-rt/0100-hrtimer-by-timers-by-default-into-the-softirq-contex.patch new file mode 100644 index 000000000..1b924bac1 --- /dev/null +++ b/debian/patches-rt/0100-hrtimer-by-timers-by-default-into-the-softirq-contex.patch @@ -0,0 +1,237 @@ +From 8a7e45b02f567fa32754c24195d5c0d095069685 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 3 Jul 2009 08:44:31 -0500 +Subject: [PATCH 100/347] hrtimer: by timers by default into the softirq + context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +We can't have hrtimers callbacks running in hardirq context on RT. Therefore +the timers are deferred to the softirq context by default. +There are few timers which expect to be run in hardirq context even on RT. +Those are: +- very short running where low latency is critical (kvm lapic) +- timers which take raw locks and need run in hard-irq context (perf, sched) +- wake up related timer (kernel side of clock_nanosleep() and so on) + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/kvm/lapic.c | 2 +- + include/linux/hrtimer.h | 6 ++++++ + kernel/events/core.c | 4 ++-- + kernel/sched/core.c | 2 +- + kernel/sched/deadline.c | 2 +- + kernel/sched/fair.c | 4 ++-- + kernel/sched/rt.c | 4 ++-- + kernel/time/hrtimer.c | 21 +++++++++++++++++++-- + kernel/time/tick-broadcast-hrtimer.c | 2 +- + kernel/time/tick-sched.c | 2 +- + kernel/watchdog.c | 2 +- + 11 files changed, 37 insertions(+), 14 deletions(-) + +diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c +index 89d07312e58c..037dbe04fda2 100644 +--- a/arch/x86/kvm/lapic.c ++++ b/arch/x86/kvm/lapic.c +@@ -2258,7 +2258,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) + apic->vcpu = vcpu; + + hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS_PINNED); ++ HRTIMER_MODE_ABS_PINNED_HARD); + apic->lapic_timer.timer.function = apic_timer_fn; + + /* +diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h +index 8714f1a37d84..082147c07831 100644 +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -42,6 +42,7 @@ enum hrtimer_mode { + HRTIMER_MODE_REL = 0x01, + HRTIMER_MODE_PINNED = 0x02, + HRTIMER_MODE_SOFT = 0x04, ++ HRTIMER_MODE_HARD = 0x08, + + HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, + HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, +@@ -52,6 +53,11 @@ enum hrtimer_mode { + HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, + HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, + ++ HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, ++ HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, ++ ++ HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, ++ HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, + }; + + /* +diff --git a/kernel/events/core.c b/kernel/events/core.c +index 88dd1398ae88..7f2441f671d3 100644 +--- a/kernel/events/core.c ++++ b/kernel/events/core.c +@@ -1108,7 +1108,7 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) + cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval); + + raw_spin_lock_init(&cpuctx->hrtimer_lock); +- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); ++ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); + timer->function = perf_mux_hrtimer_handler; + } + +@@ -9311,7 +9311,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) + if (!is_sampling_event(event)) + return; + +- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + hwc->hrtimer.function = perf_swevent_hrtimer; + + /* +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 3c5999476609..0f949b7738fd 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -315,7 +315,7 @@ static void hrtick_rq_init(struct rq *rq) + rq->hrtick_csd.info = rq; + #endif + +- hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + rq->hrtick_timer.function = hrtick; + } + #else /* CONFIG_SCHED_HRTICK */ +diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c +index 95ebbb2074c7..1a285367081c 100644 +--- a/kernel/sched/deadline.c ++++ b/kernel/sched/deadline.c +@@ -1086,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) + { + struct hrtimer *timer = &dl_se->dl_timer; + +- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + timer->function = dl_task_timer; + } + +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 16940416d526..d804b5443bb9 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -4951,9 +4951,9 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) + cfs_b->period = ns_to_ktime(default_cfs_period()); + + INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); +- hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); ++ hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); + cfs_b->period_timer.function = sched_cfs_period_timer; +- hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + cfs_b->slack_timer.function = sched_cfs_slack_timer; + cfs_b->distribute_running = 0; + } +diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c +index 52b55144d8ad..a2f2c6c91e05 100644 +--- a/kernel/sched/rt.c ++++ b/kernel/sched/rt.c +@@ -45,8 +45,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) + + raw_spin_lock_init(&rt_b->rt_runtime_lock); + +- hrtimer_init(&rt_b->rt_period_timer, +- CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, ++ HRTIMER_MODE_REL_HARD); + rt_b->rt_period_timer.function = sched_rt_period_timer; + } + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 8bbde17325c7..e947f3b344ac 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1202,7 +1202,9 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft + * match. + */ ++#ifndef CONFIG_PREEMPT_RT_BASE + WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); ++#endif + + base = lock_hrtimer_base(timer, &flags); + +@@ -1362,10 +1364,17 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) + { +- bool softtimer = !!(mode & HRTIMER_MODE_SOFT); +- int base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; ++ bool softtimer; ++ int base; + struct hrtimer_cpu_base *cpu_base; + ++ softtimer = !!(mode & HRTIMER_MODE_SOFT); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!softtimer && !(mode & HRTIMER_MODE_HARD)) ++ softtimer = true; ++#endif ++ base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; ++ + memset(timer, 0, sizeof(struct hrtimer)); + + cpu_base = raw_cpu_ptr(&hrtimer_bases); +@@ -1748,6 +1757,14 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, + enum hrtimer_mode mode, + struct task_struct *task) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!(mode & (HRTIMER_MODE_SOFT | HRTIMER_MODE_HARD))) { ++ if (task_is_realtime(current) || system_state != SYSTEM_RUNNING) ++ mode |= HRTIMER_MODE_HARD; ++ else ++ mode |= HRTIMER_MODE_SOFT; ++ } ++#endif + __hrtimer_init(&sl->timer, clock_id, mode); + sl->timer.function = hrtimer_wakeup; + sl->task = task; +diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c +index a836efd34589..c50e8f3262de 100644 +--- a/kernel/time/tick-broadcast-hrtimer.c ++++ b/kernel/time/tick-broadcast-hrtimer.c +@@ -107,7 +107,7 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) + + void tick_setup_hrtimer_broadcast(void) + { +- hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + bctimer.function = bc_handler; + clockevents_register_device(&ce_broadcast_hrtimer); + } +diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c +index e774a49176cc..012bc81879bf 100644 +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -1314,7 +1314,7 @@ void tick_setup_sched_timer(void) + /* + * Emulate tick processing via per-CPU hrtimers: + */ +- hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + ts->sched_timer.function = tick_sched_timer; + + /* Get the next period (per-CPU) */ +diff --git a/kernel/watchdog.c b/kernel/watchdog.c +index 6d60701dc636..328620fe85f6 100644 +--- a/kernel/watchdog.c ++++ b/kernel/watchdog.c +@@ -485,7 +485,7 @@ static void watchdog_enable(unsigned int cpu) + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ +- hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + hrtimer->function = watchdog_timer_fn; + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); +-- +2.36.1 + diff --git a/debian/patches-rt/0101-sched-fair-Make-the-hrtimers-non-hard-again.patch b/debian/patches-rt/0101-sched-fair-Make-the-hrtimers-non-hard-again.patch new file mode 100644 index 000000000..5e4c29b6b --- /dev/null +++ b/debian/patches-rt/0101-sched-fair-Make-the-hrtimers-non-hard-again.patch @@ -0,0 +1,34 @@ +From 79daa2a0bfdb433f8f4dfb8fe3b3652199bf7cb8 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 8 Jan 2019 12:31:06 +0100 +Subject: [PATCH 101/347] sched/fair: Make the hrtimers non-hard again +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Since commit "sched/fair: Robustify CFS-bandwidth timer locking" both +hrtimer can run in softirq context because now interrupts are disabled +as part of the locking procedure. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/fair.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index d804b5443bb9..16940416d526 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -4951,9 +4951,9 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) + cfs_b->period = ns_to_ktime(default_cfs_period()); + + INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); +- hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); ++ hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + cfs_b->period_timer.function = sched_cfs_period_timer; +- hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); ++ hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->slack_timer.function = sched_cfs_slack_timer; + cfs_b->distribute_running = 0; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0102-hrtimer-Move-schedule_work-call-to-helper-thread.patch b/debian/patches-rt/0102-hrtimer-Move-schedule_work-call-to-helper-thread.patch new file mode 100644 index 000000000..59bec99cb --- /dev/null +++ b/debian/patches-rt/0102-hrtimer-Move-schedule_work-call-to-helper-thread.patch @@ -0,0 +1,98 @@ +From da39809d4f91a8c4a41fdf3f17fc892dc71dd9ae Mon Sep 17 00:00:00 2001 +From: Yang Shi <yang.shi@windriver.com> +Date: Mon, 16 Sep 2013 14:09:19 -0700 +Subject: [PATCH 102/347] hrtimer: Move schedule_work call to helper thread +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When run ltp leapsec_timer test, the following call trace is caught: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 +in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 +Preemption disabled at:[<ffffffff810857f3>] cpu_startup_entry+0x133/0x310 + +CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.10-rt3 #2 +Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010 +ffffffff81c2f800 ffff880076843e40 ffffffff8169918d ffff880076843e58 +ffffffff8106db31 ffff88007684b4a0 ffff880076843e70 ffffffff8169d9c0 +ffff88007684b4a0 ffff880076843eb0 ffffffff81059da1 0000001876851200 +Call Trace: +<IRQ> [<ffffffff8169918d>] dump_stack+0x19/0x1b +[<ffffffff8106db31>] __might_sleep+0xf1/0x170 +[<ffffffff8169d9c0>] rt_spin_lock+0x20/0x50 +[<ffffffff81059da1>] queue_work_on+0x61/0x100 +[<ffffffff81065aa1>] clock_was_set_delayed+0x21/0x30 +[<ffffffff810883be>] do_timer+0x40e/0x660 +[<ffffffff8108f487>] tick_do_update_jiffies64+0xf7/0x140 +[<ffffffff8108fe42>] tick_check_idle+0x92/0xc0 +[<ffffffff81044327>] irq_enter+0x57/0x70 +[<ffffffff816a040e>] smp_apic_timer_interrupt+0x3e/0x9b +[<ffffffff8169f80a>] apic_timer_interrupt+0x6a/0x70 +<EOI> [<ffffffff8155ea1c>] ? cpuidle_enter_state+0x4c/0xc0 +[<ffffffff8155eb68>] cpuidle_idle_call+0xd8/0x2d0 +[<ffffffff8100b59e>] arch_cpu_idle+0xe/0x30 +[<ffffffff8108585e>] cpu_startup_entry+0x19e/0x310 +[<ffffffff8168efa2>] start_secondary+0x1ad/0x1b0 + +The clock_was_set_delayed is called in hard IRQ handler (timer interrupt), which +calls schedule_work. + +Under PREEMPT_RT_FULL, schedule_work calls spinlocks which could sleep, so it's +not safe to call schedule_work in interrupt context. + +Reference upstream commit b68d61c705ef02384c0538b8d9374545097899ca +(rt,ntp: Move call to schedule_delayed_work() to helper thread) +from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git, which +makes a similar change. + +Signed-off-by: Yang Shi <yang.shi@windriver.com> +[bigeasy: use swork_queue() instead a helper thread] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 24 ++++++++++++++++++++++++ + 1 file changed, 24 insertions(+) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index e947f3b344ac..0833e5cf224d 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -748,6 +748,29 @@ static void hrtimer_switch_to_hres(void) + retrigger_next_event(NULL); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++static struct swork_event clock_set_delay_work; ++ ++static void run_clock_set_delay(struct swork_event *event) ++{ ++ clock_was_set(); ++} ++ ++void clock_was_set_delayed(void) ++{ ++ swork_queue(&clock_set_delay_work); ++} ++ ++static __init int create_clock_set_delay_thread(void) ++{ ++ WARN_ON(swork_get()); ++ INIT_SWORK(&clock_set_delay_work, run_clock_set_delay); ++ return 0; ++} ++early_initcall(create_clock_set_delay_thread); ++#else /* PREEMPT_RT_FULL */ ++ + static void clock_was_set_work(struct work_struct *work) + { + clock_was_set(); +@@ -763,6 +786,7 @@ void clock_was_set_delayed(void) + { + schedule_work(&hrtimer_work); + } ++#endif + + #else + +-- +2.36.1 + diff --git a/debian/patches-rt/0103-hrtimer-move-state-change-before-hrtimer_cancel-in-d.patch b/debian/patches-rt/0103-hrtimer-move-state-change-before-hrtimer_cancel-in-d.patch new file mode 100644 index 000000000..d93342369 --- /dev/null +++ b/debian/patches-rt/0103-hrtimer-move-state-change-before-hrtimer_cancel-in-d.patch @@ -0,0 +1,51 @@ +From baa58a4f1714630ef1a780575a907b4f80344e19 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 6 Dec 2018 10:15:13 +0100 +Subject: [PATCH 103/347] hrtimer: move state change before hrtimer_cancel in + do_nanosleep() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There is a small window between setting t->task to NULL and waking the +task up (which would set TASK_RUNNING). So the timer would fire, run and +set ->task to NULL while the other side/do_nanosleep() wouldn't enter +freezable_schedule(). After all we are peemptible here (in +do_nanosleep() and on the timer wake up path) and on KVM/virt the +virt-CPU might get preempted. +So do_nanosleep() wouldn't enter freezable_schedule() but cancel the +timer which is still running and wait for it via +hrtimer_wait_for_timer(). Then wait_event()/might_sleep() would complain +that it is invoked with state != TASK_RUNNING. +This isn't a problem since it would be reset to TASK_RUNNING later +anyway and we don't rely on the previous state. + +Move the state update to TASK_RUNNING before hrtimer_cancel() so there +are no complains from might_sleep() about wrong state. + +Cc: stable-rt@vger.kernel.org +Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 0833e5cf224d..009001f06d33 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1852,12 +1852,12 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod + if (likely(t->task)) + freezable_schedule(); + ++ __set_current_state(TASK_RUNNING); + hrtimer_cancel(&t->timer); + mode = HRTIMER_MODE_ABS; + + } while (t->task && !signal_pending(current)); + +- __set_current_state(TASK_RUNNING); + + if (!t->task) + return 0; +-- +2.36.1 + diff --git a/debian/patches-rt/0104-posix-timers-Thread-posix-cpu-timers-on-rt.patch b/debian/patches-rt/0104-posix-timers-Thread-posix-cpu-timers-on-rt.patch new file mode 100644 index 000000000..36a78b986 --- /dev/null +++ b/debian/patches-rt/0104-posix-timers-Thread-posix-cpu-timers-on-rt.patch @@ -0,0 +1,269 @@ +From 59ac8673b0cb63baa55b3058ba0cb36ecb14a9d7 Mon Sep 17 00:00:00 2001 +From: John Stultz <johnstul@us.ibm.com> +Date: Fri, 3 Jul 2009 08:29:58 -0500 +Subject: [PATCH 104/347] posix-timers: Thread posix-cpu-timers on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +posix-cpu-timer code takes non -rt safe locks in hard irq +context. Move it to a thread. + +[ 3.0 fixes from Peter Zijlstra <peterz@infradead.org> ] + +Signed-off-by: John Stultz <johnstul@us.ibm.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/sched.h | 3 + + init/init_task.c | 7 ++ + kernel/fork.c | 3 + + kernel/time/posix-cpu-timers.c | 154 ++++++++++++++++++++++++++++++++- + 4 files changed, 164 insertions(+), 3 deletions(-) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 56047f57ebc7..5369eb1fd456 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -832,6 +832,9 @@ struct task_struct { + #ifdef CONFIG_POSIX_TIMERS + struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *posix_timer_list; ++#endif + #endif + + /* Process credentials: */ +diff --git a/init/init_task.c b/init/init_task.c +index d71054b95528..634becebd713 100644 +--- a/init/init_task.c ++++ b/init/init_task.c +@@ -50,6 +50,12 @@ static struct sighand_struct init_sighand = { + .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh), + }; + ++#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE) ++# define INIT_TIMER_LIST .posix_timer_list = NULL, ++#else ++# define INIT_TIMER_LIST ++#endif ++ + /* + * Set up the first task table, touch at your own risk!. Base=0, + * limit=0x1fffff (=2MB) +@@ -119,6 +125,7 @@ struct task_struct init_task + INIT_CPU_TIMERS(init_task) + .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock), + .timer_slack_ns = 50000, /* 50 usec default slack */ ++ INIT_TIMER_LIST + .thread_pid = &init_struct_pid, + .thread_group = LIST_HEAD_INIT(init_task.thread_group), + .thread_node = LIST_HEAD_INIT(init_signals.thread_head), +diff --git a/kernel/fork.c b/kernel/fork.c +index a18d695259af..c27c196fd70e 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1587,6 +1587,9 @@ static void rt_mutex_init_task(struct task_struct *p) + */ + static void posix_cpu_timers_init(struct task_struct *tsk) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ tsk->posix_timer_list = NULL; ++#endif + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; + tsk->cputime_expires.sched_exp = 0; +diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c +index bfaa44a80c03..2d29b269dc83 100644 +--- a/kernel/time/posix-cpu-timers.c ++++ b/kernel/time/posix-cpu-timers.c +@@ -3,8 +3,10 @@ + * Implement CPU time clocks for the POSIX clock interface. + */ + ++#include <uapi/linux/sched/types.h> + #include <linux/sched/signal.h> + #include <linux/sched/cputime.h> ++#include <linux/sched/rt.h> + #include <linux/posix-timers.h> + #include <linux/errno.h> + #include <linux/math64.h> +@@ -15,6 +17,7 @@ + #include <linux/workqueue.h> + #include <linux/compat.h> + #include <linux/sched/deadline.h> ++#include <linux/smpboot.h> + + #include "posix-timers.h" + +@@ -1140,14 +1143,12 @@ static inline int fastpath_timer_check(struct task_struct *tsk) + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +-void run_posix_cpu_timers(struct task_struct *tsk) ++static void __run_posix_cpu_timers(struct task_struct *tsk) + { + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; + +- lockdep_assert_irqs_disabled(); +- + /* + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. +@@ -1200,6 +1201,153 @@ void run_posix_cpu_timers(struct task_struct *tsk) + } + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++#include <linux/kthread.h> ++#include <linux/cpu.h> ++DEFINE_PER_CPU(struct task_struct *, posix_timer_task); ++DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); ++DEFINE_PER_CPU(bool, posix_timer_th_active); ++ ++static void posix_cpu_kthread_fn(unsigned int cpu) ++{ ++ struct task_struct *tsk = NULL; ++ struct task_struct *next = NULL; ++ ++ BUG_ON(per_cpu(posix_timer_task, cpu) != current); ++ ++ /* grab task list */ ++ raw_local_irq_disable(); ++ tsk = per_cpu(posix_timer_tasklist, cpu); ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ raw_local_irq_enable(); ++ ++ /* its possible the list is empty, just return */ ++ if (!tsk) ++ return; ++ ++ /* Process task list */ ++ while (1) { ++ /* save next */ ++ next = tsk->posix_timer_list; ++ ++ /* run the task timers, clear its ptr and ++ * unreference it ++ */ ++ __run_posix_cpu_timers(tsk); ++ tsk->posix_timer_list = NULL; ++ put_task_struct(tsk); ++ ++ /* check if this is the last on the list */ ++ if (next == tsk) ++ break; ++ tsk = next; ++ } ++} ++ ++static inline int __fastpath_timer_check(struct task_struct *tsk) ++{ ++ /* tsk == current, ensure it is safe to use ->signal/sighand */ ++ if (unlikely(tsk->exit_state)) ++ return 0; ++ ++ if (!task_cputime_zero(&tsk->cputime_expires)) ++ return 1; ++ ++ if (!task_cputime_zero(&tsk->signal->cputime_expires)) ++ return 1; ++ ++ return 0; ++} ++ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ unsigned int cpu = smp_processor_id(); ++ struct task_struct *tasklist; ++ ++ BUG_ON(!irqs_disabled()); ++ ++ if (per_cpu(posix_timer_th_active, cpu) != true) ++ return; ++ ++ /* get per-cpu references */ ++ tasklist = per_cpu(posix_timer_tasklist, cpu); ++ ++ /* check to see if we're already queued */ ++ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { ++ get_task_struct(tsk); ++ if (tasklist) { ++ tsk->posix_timer_list = tasklist; ++ } else { ++ /* ++ * The list is terminated by a self-pointing ++ * task_struct ++ */ ++ tsk->posix_timer_list = tsk; ++ } ++ per_cpu(posix_timer_tasklist, cpu) = tsk; ++ ++ wake_up_process(per_cpu(posix_timer_task, cpu)); ++ } ++} ++ ++static int posix_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(posix_timer_tasklist) != NULL; ++} ++ ++static void posix_cpu_kthread_park(unsigned int cpu) ++{ ++ this_cpu_write(posix_timer_th_active, false); ++} ++ ++static void posix_cpu_kthread_unpark(unsigned int cpu) ++{ ++ this_cpu_write(posix_timer_th_active, true); ++} ++ ++static void posix_cpu_kthread_setup(unsigned int cpu) ++{ ++ struct sched_param sp; ++ ++ sp.sched_priority = MAX_RT_PRIO - 1; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++ posix_cpu_kthread_unpark(cpu); ++} ++ ++static struct smp_hotplug_thread posix_cpu_thread = { ++ .store = &posix_timer_task, ++ .thread_should_run = posix_cpu_kthread_should_run, ++ .thread_fn = posix_cpu_kthread_fn, ++ .thread_comm = "posixcputmr/%u", ++ .setup = posix_cpu_kthread_setup, ++ .park = posix_cpu_kthread_park, ++ .unpark = posix_cpu_kthread_unpark, ++}; ++ ++static int __init posix_cpu_thread_init(void) ++{ ++ /* Start one for boot CPU. */ ++ unsigned long cpu; ++ int ret; ++ ++ /* init the per-cpu posix_timer_tasklets */ ++ for_each_possible_cpu(cpu) ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ ++ ret = smpboot_register_percpu_thread(&posix_cpu_thread); ++ WARN_ON(ret); ++ ++ return 0; ++} ++early_initcall(posix_cpu_thread_init); ++#else /* CONFIG_PREEMPT_RT_BASE */ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ lockdep_assert_irqs_disabled(); ++ __run_posix_cpu_timers(tsk); ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + /* + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. + * The tsk->sighand->siglock must be held by the caller. +-- +2.36.1 + diff --git a/debian/patches-rt/0105-sched-Move-task_struct-cleanup-to-RCU.patch b/debian/patches-rt/0105-sched-Move-task_struct-cleanup-to-RCU.patch new file mode 100644 index 000000000..8883673e8 --- /dev/null +++ b/debian/patches-rt/0105-sched-Move-task_struct-cleanup-to-RCU.patch @@ -0,0 +1,96 @@ +From 6b5806854133faa2eda014a6553665c6fa393d5e Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 31 May 2011 16:59:16 +0200 +Subject: [PATCH 105/347] sched: Move task_struct cleanup to RCU +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +__put_task_struct() does quite some expensive work. We don't want to +burden random tasks with that. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/sched.h | 3 +++ + include/linux/sched/task.h | 11 ++++++++++- + kernel/fork.c | 15 ++++++++++++++- + 3 files changed, 27 insertions(+), 2 deletions(-) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 5369eb1fd456..5e2ec9c86b4b 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1196,6 +1196,9 @@ struct task_struct { + unsigned int sequential_io; + unsigned int sequential_io_avg; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head put_rcu; ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif +diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h +index 91401309b1aa..5f8c1d53bc11 100644 +--- a/include/linux/sched/task.h ++++ b/include/linux/sched/task.h +@@ -90,6 +90,15 @@ extern void sched_exec(void); + + #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __put_task_struct_cb(struct rcu_head *rhp); ++ ++static inline void put_task_struct(struct task_struct *t) ++{ ++ if (atomic_dec_and_test(&t->usage)) ++ call_rcu(&t->put_rcu, __put_task_struct_cb); ++} ++#else + extern void __put_task_struct(struct task_struct *t); + + static inline void put_task_struct(struct task_struct *t) +@@ -97,7 +106,7 @@ static inline void put_task_struct(struct task_struct *t) + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); + } +- ++#endif + struct task_struct *task_rcu_dereference(struct task_struct **ptask); + + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +diff --git a/kernel/fork.c b/kernel/fork.c +index c27c196fd70e..f5a4c42233f0 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -676,7 +676,9 @@ static inline void put_signal_struct(struct signal_struct *sig) + if (atomic_dec_and_test(&sig->sigcnt)) + free_signal_struct(sig); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++static ++#endif + void __put_task_struct(struct task_struct *tsk) + { + WARN_ON(!tsk->exit_state); +@@ -693,7 +695,18 @@ void __put_task_struct(struct task_struct *tsk) + if (!profile_handoff_task(tsk)) + free_task(tsk); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + EXPORT_SYMBOL_GPL(__put_task_struct); ++#else ++void __put_task_struct_cb(struct rcu_head *rhp) ++{ ++ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); ++ ++ __put_task_struct(tsk); ++ ++} ++EXPORT_SYMBOL_GPL(__put_task_struct_cb); ++#endif + + void __init __weak arch_task_cache_init(void) { } + +-- +2.36.1 + diff --git a/debian/patches-rt/0106-sched-Limit-the-number-of-task-migrations-per-batch.patch b/debian/patches-rt/0106-sched-Limit-the-number-of-task-migrations-per-batch.patch new file mode 100644 index 000000000..7c34d3924 --- /dev/null +++ b/debian/patches-rt/0106-sched-Limit-the-number-of-task-migrations-per-batch.patch @@ -0,0 +1,33 @@ +From 6447e629affa080b84d75e0f685848104a5601ee Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 6 Jun 2011 12:12:51 +0200 +Subject: [PATCH 106/347] sched: Limit the number of task migrations per batch +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Put an upper limit on the number of tasks which are migrated per batch +to avoid large latencies. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/sched/core.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 0f949b7738fd..4cc39856c4c6 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -44,7 +44,11 @@ const_debug unsigned int sysctl_sched_features = + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++const_debug unsigned int sysctl_sched_nr_migrate = 8; ++#else + const_debug unsigned int sysctl_sched_nr_migrate = 32; ++#endif + + /* + * period over which we measure -rt task CPU usage in us. +-- +2.36.1 + diff --git a/debian/patches-rt/0107-sched-Move-mmdrop-to-RCU-on-RT.patch b/debian/patches-rt/0107-sched-Move-mmdrop-to-RCU-on-RT.patch new file mode 100644 index 000000000..9c6b2f686 --- /dev/null +++ b/debian/patches-rt/0107-sched-Move-mmdrop-to-RCU-on-RT.patch @@ -0,0 +1,115 @@ +From 977952ae9f00231e71587f8dc135949a2bed15e2 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 6 Jun 2011 12:20:33 +0200 +Subject: [PATCH 107/347] sched: Move mmdrop to RCU on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Takes sleeping locks and calls into the memory allocator, so nothing +we want to do in task switch and oder atomic contexts. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/mm_types.h | 4 ++++ + include/linux/sched/mm.h | 11 +++++++++++ + kernel/fork.c | 13 +++++++++++++ + kernel/sched/core.c | 7 ++++++- + 4 files changed, 34 insertions(+), 1 deletion(-) + +diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h +index 3a9a996af229..202b736ccbfa 100644 +--- a/include/linux/mm_types.h ++++ b/include/linux/mm_types.h +@@ -12,6 +12,7 @@ + #include <linux/completion.h> + #include <linux/cpumask.h> + #include <linux/uprobes.h> ++#include <linux/rcupdate.h> + #include <linux/page-flags-layout.h> + #include <linux/workqueue.h> + +@@ -487,6 +488,9 @@ struct mm_struct { + bool tlb_flush_batched; + #endif + struct uprobes_state uprobes_state; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head delayed_drop; ++#endif + #ifdef CONFIG_HUGETLB_PAGE + atomic_long_t hugetlb_usage; + #endif +diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h +index ef54f4b3f1e4..88e1a563f762 100644 +--- a/include/linux/sched/mm.h ++++ b/include/linux/sched/mm.h +@@ -49,6 +49,17 @@ static inline void mmdrop(struct mm_struct *mm) + __mmdrop(mm); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __mmdrop_delayed(struct rcu_head *rhp); ++static inline void mmdrop_delayed(struct mm_struct *mm) ++{ ++ if (atomic_dec_and_test(&mm->mm_count)) ++ call_rcu(&mm->delayed_drop, __mmdrop_delayed); ++} ++#else ++# define mmdrop_delayed(mm) mmdrop(mm) ++#endif ++ + void mmdrop(struct mm_struct *mm); + + /* +diff --git a/kernel/fork.c b/kernel/fork.c +index f5a4c42233f0..114ff9724b02 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -642,6 +642,19 @@ void __mmdrop(struct mm_struct *mm) + } + EXPORT_SYMBOL_GPL(__mmdrop); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++/* ++ * RCU callback for delayed mm drop. Not strictly rcu, but we don't ++ * want another facility to make this work. ++ */ ++void __mmdrop_delayed(struct rcu_head *rhp) ++{ ++ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); ++ ++ __mmdrop(mm); ++} ++#endif ++ + static void mmdrop_async_fn(struct work_struct *work) + { + struct mm_struct *mm; +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 4cc39856c4c6..676b9b213991 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2734,9 +2734,13 @@ static struct rq *finish_task_switch(struct task_struct *prev) + * provided by mmdrop(), + * - a sync_core for SYNC_CORE. + */ ++ /* ++ * We use mmdrop_delayed() here so we don't have to do the ++ * full __mmdrop() when we are the last user. ++ */ + if (mm) { + membarrier_mm_sync_core_before_usermode(mm); +- mmdrop(mm); ++ mmdrop_delayed(mm); + } + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) +@@ -5603,6 +5607,7 @@ void sched_setnuma(struct task_struct *p, int nid) + #endif /* CONFIG_NUMA_BALANCING */ + + #ifdef CONFIG_HOTPLUG_CPU ++ + /* + * Ensure that the idle task is using init_mm right before its CPU goes + * offline. +-- +2.36.1 + diff --git a/debian/patches-rt/0108-kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch b/debian/patches-rt/0108-kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch new file mode 100644 index 000000000..da1b8eee6 --- /dev/null +++ b/debian/patches-rt/0108-kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch @@ -0,0 +1,70 @@ +From 3028eeca5a3657762aa36512dac687f987462a80 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 21 Nov 2016 19:31:08 +0100 +Subject: [PATCH 108/347] kernel/sched: move stack + kprobe clean up to + __put_task_struct() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There is no need to free the stack before the task struct (except for reasons +mentioned in commit 68f24b08ee89 ("sched/core: Free the stack early if +CONFIG_THREAD_INFO_IN_TASK")). This also comes handy on -RT because we can't +free memory in preempt disabled region. + +Cc: stable-rt@vger.kernel.org #for kprobe_flush_task() +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/fork.c | 10 ++++++++++ + kernel/sched/core.c | 9 --------- + 2 files changed, 10 insertions(+), 9 deletions(-) + +diff --git a/kernel/fork.c b/kernel/fork.c +index 114ff9724b02..efe690af29f1 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -40,6 +40,7 @@ + #include <linux/hmm.h> + #include <linux/fs.h> + #include <linux/mm.h> ++#include <linux/kprobes.h> + #include <linux/vmacache.h> + #include <linux/nsproxy.h> + #include <linux/capability.h> +@@ -698,6 +699,15 @@ void __put_task_struct(struct task_struct *tsk) + WARN_ON(atomic_read(&tsk->usage)); + WARN_ON(tsk == current); + ++ /* ++ * Remove function-return probe instances associated with this ++ * task and put them back on the free list. ++ */ ++ kprobe_flush_task(tsk); ++ ++ /* Task is done with its stack. */ ++ put_task_stack(tsk); ++ + cgroup_free(tsk); + task_numa_free(tsk, true); + security_task_free(tsk); +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 676b9b213991..089779e18440 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2746,15 +2746,6 @@ static struct rq *finish_task_switch(struct task_struct *prev) + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); + +- /* +- * Remove function-return probe instances associated with this +- * task and put them back on the free list. +- */ +- kprobe_flush_task(prev); +- +- /* Task is done with its stack. */ +- put_task_stack(prev); +- + put_task_struct(prev); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0109-sched-Add-saved_state-for-tasks-blocked-on-sleeping-.patch b/debian/patches-rt/0109-sched-Add-saved_state-for-tasks-blocked-on-sleeping-.patch new file mode 100644 index 000000000..f8b1532fb --- /dev/null +++ b/debian/patches-rt/0109-sched-Add-saved_state-for-tasks-blocked-on-sleeping-.patch @@ -0,0 +1,108 @@ +From 84facacc5994009491bb74f5bee0c8399540c9b5 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sat, 25 Jun 2011 09:21:04 +0200 +Subject: [PATCH 109/347] sched: Add saved_state for tasks blocked on sleeping + locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Spinlocks are state preserving in !RT. RT changes the state when a +task gets blocked on a lock. So we need to remember the state before +the lock contention. If a regular wakeup (not a RTmutex related +wakeup) happens, the saved_state is updated to running. When the lock +sleep is done, the saved state is restored. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/sched.h | 3 +++ + kernel/sched/core.c | 33 ++++++++++++++++++++++++++++++++- + kernel/sched/sched.h | 1 + + 3 files changed, 36 insertions(+), 1 deletion(-) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 5e2ec9c86b4b..1b2884889dd0 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -600,6 +600,8 @@ struct task_struct { + #endif + /* -1 unrunnable, 0 runnable, >0 stopped: */ + volatile long state; ++ /* saved state for "spinlock sleepers" */ ++ volatile long saved_state; + + /* + * This begins the randomizable portion of task_struct. Only +@@ -1621,6 +1623,7 @@ extern struct task_struct *find_get_task_by_vpid(pid_t nr); + + extern int wake_up_state(struct task_struct *tsk, unsigned int state); + extern int wake_up_process(struct task_struct *tsk); ++extern int wake_up_lock_sleeper(struct task_struct *tsk); + extern void wake_up_new_task(struct task_struct *tsk); + + #ifdef CONFIG_SMP +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 089779e18440..3ec69104d0e0 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2002,8 +2002,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + smp_mb__after_spinlock(); +- if (!(p->state & state)) ++ if (!(p->state & state)) { ++ /* ++ * The task might be running due to a spinlock sleeper ++ * wakeup. Check the saved state and set it to running ++ * if the wakeup condition is true. ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) { ++ if (p->saved_state & state) { ++ p->saved_state = TASK_RUNNING; ++ success = 1; ++ } ++ } + goto out; ++ } ++ ++ /* ++ * If this is a regular wakeup, then we can unconditionally ++ * clear the saved state of a "lock sleeper". ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) ++ p->saved_state = TASK_RUNNING; + + trace_sched_waking(p); + +@@ -2167,6 +2186,18 @@ int wake_up_process(struct task_struct *p) + } + EXPORT_SYMBOL(wake_up_process); + ++/** ++ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" ++ * @p: The process to be woken up. ++ * ++ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate ++ * the nature of the wakeup. ++ */ ++int wake_up_lock_sleeper(struct task_struct *p) ++{ ++ return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER); ++} ++ + int wake_up_state(struct task_struct *p, unsigned int state) + { + return try_to_wake_up(p, state, 0); +diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h +index 55e695080fc6..637c408fb2dc 100644 +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -1448,6 +1448,7 @@ static inline int task_on_rq_migrating(struct task_struct *p) + #define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */ + #define WF_FORK 0x02 /* Child wakeup after fork */ + #define WF_MIGRATED 0x4 /* Internal use, task got migrated */ ++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + + /* + * To aid in avoiding the subversion of "niceness" due to uneven distribution +-- +2.36.1 + diff --git a/debian/patches-rt/0110-sched-Do-not-account-rcu_preempt_depth-on-RT-in-migh.patch b/debian/patches-rt/0110-sched-Do-not-account-rcu_preempt_depth-on-RT-in-migh.patch new file mode 100644 index 000000000..f7f28c137 --- /dev/null +++ b/debian/patches-rt/0110-sched-Do-not-account-rcu_preempt_depth-on-RT-in-migh.patch @@ -0,0 +1,57 @@ +From f56cb07175c10678a26521bb7be0f493ffd5d544 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 7 Jun 2011 09:19:06 +0200 +Subject: [PATCH 110/347] sched: Do not account rcu_preempt_depth on RT in + might_sleep() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +RT changes the rcu_preempt_depth semantics, so we cannot check for it +in might_sleep(). + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/rcupdate.h | 7 +++++++ + kernel/sched/core.c | 2 +- + 2 files changed, 8 insertions(+), 1 deletion(-) + +diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h +index 68cbe111420b..027c58cdbb6e 100644 +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -73,6 +73,11 @@ void synchronize_rcu(void); + * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. + */ + #define rcu_preempt_depth() (current->rcu_read_lock_nesting) ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++#else ++static inline int sched_rcu_preempt_depth(void) { return 0; } ++#endif + + #else /* #ifdef CONFIG_PREEMPT_RCU */ + +@@ -96,6 +101,8 @@ static inline int rcu_preempt_depth(void) + return 0; + } + ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++ + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + + /* Internal to kernel */ +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 3ec69104d0e0..52e821ac5872 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -6192,7 +6192,7 @@ void __init sched_init(void) + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + static inline int preempt_count_equals(int preempt_offset) + { +- int nested = preempt_count() + rcu_preempt_depth(); ++ int nested = preempt_count() + sched_rcu_preempt_depth(); + + return (nested == preempt_offset); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0111-sched-Use-the-proper-LOCK_OFFSET-for-cond_resched.patch b/debian/patches-rt/0111-sched-Use-the-proper-LOCK_OFFSET-for-cond_resched.patch new file mode 100644 index 000000000..eccb1e428 --- /dev/null +++ b/debian/patches-rt/0111-sched-Use-the-proper-LOCK_OFFSET-for-cond_resched.patch @@ -0,0 +1,33 @@ +From 5c317385aa997812acc4dd102c34f7d843bd7eb6 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 17 Jul 2011 22:51:33 +0200 +Subject: [PATCH 111/347] sched: Use the proper LOCK_OFFSET for cond_resched() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +RT does not increment preempt count when a 'sleeping' spinlock is +locked. Update PREEMPT_LOCK_OFFSET for that case. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/preempt.h | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index f7a17fcc3fec..b7fe717eb1f4 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -118,7 +118,11 @@ + /* + * The preempt_count offset after spin_lock() + */ ++#if !defined(CONFIG_PREEMPT_RT_FULL) + #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET ++#else ++#define PREEMPT_LOCK_OFFSET 0 ++#endif + + /* + * The preempt_count offset needed for things like: +-- +2.36.1 + diff --git a/debian/patches-rt/0112-sched-Disable-TTWU_QUEUE-on-RT.patch b/debian/patches-rt/0112-sched-Disable-TTWU_QUEUE-on-RT.patch new file mode 100644 index 000000000..8e44536b2 --- /dev/null +++ b/debian/patches-rt/0112-sched-Disable-TTWU_QUEUE-on-RT.patch @@ -0,0 +1,38 @@ +From 31cdcd445b6fbf09238e8e3a25c2dd72be0bb187 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 13 Sep 2011 16:42:35 +0200 +Subject: [PATCH 112/347] sched: Disable TTWU_QUEUE on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The queued remote wakeup mechanism can introduce rather large +latencies if the number of migrated tasks is high. Disable it for RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/sched/features.h | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/kernel/sched/features.h b/kernel/sched/features.h +index 85ae8488039c..68de18405857 100644 +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -46,11 +46,16 @@ SCHED_FEAT(LB_BIAS, true) + */ + SCHED_FEAT(NONTASK_CAPACITY, true) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++SCHED_FEAT(TTWU_QUEUE, false) ++#else ++ + /* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ + SCHED_FEAT(TTWU_QUEUE, true) ++#endif + + /* + * When doing wakeups, attempt to limit superfluous scans of the LLC domain. +-- +2.36.1 + diff --git a/debian/patches-rt/0113-sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch b/debian/patches-rt/0113-sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch new file mode 100644 index 000000000..e02a45c7e --- /dev/null +++ b/debian/patches-rt/0113-sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch @@ -0,0 +1,45 @@ +From 495d970d1b7c60361c296ff0e613787355a1cbd3 Mon Sep 17 00:00:00 2001 +From: Steven Rostedt <rostedt@goodmis.org> +Date: Mon, 18 Mar 2013 15:12:49 -0400 +Subject: [PATCH 113/347] sched/workqueue: Only wake up idle workers if not + blocked on sleeping spin lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In -rt, most spin_locks() turn into mutexes. One of these spin_lock +conversions is performed on the workqueue gcwq->lock. When the idle +worker is worken, the first thing it will do is grab that same lock and +it too will block, possibly jumping into the same code, but because +nr_running would already be decremented it prevents an infinite loop. + +But this is still a waste of CPU cycles, and it doesn't follow the method +of mainline, as new workers should only be woken when a worker thread is +truly going to sleep, and not just blocked on a spin_lock(). + +Check the saved_state too before waking up new workers. + + +Signed-off-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/core.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 52e821ac5872..dadf92046f01 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3544,8 +3544,10 @@ static void __sched notrace __schedule(bool preempt) + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. ++ * Only call wake up if prev isn't blocked on a sleeping ++ * spin lock. + */ +- if (prev->flags & PF_WQ_WORKER) { ++ if (prev->flags & PF_WQ_WORKER && !prev->saved_state) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev); +-- +2.36.1 + diff --git a/debian/patches-rt/0114-rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch b/debian/patches-rt/0114-rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch new file mode 100644 index 000000000..16febe92b --- /dev/null +++ b/debian/patches-rt/0114-rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch @@ -0,0 +1,162 @@ +From fbd999856a435086bb3dced2d54c5ece42c00fd6 Mon Sep 17 00:00:00 2001 +From: Daniel Bristot de Oliveira <bristot@redhat.com> +Date: Mon, 26 Jun 2017 17:07:15 +0200 +Subject: [PATCH 114/347] rt: Increase/decrease the nr of migratory tasks when + enabling/disabling migration +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There is a problem in the migrate_disable()/enable() implementation +regarding the number of migratory tasks in the rt/dl RQs. The problem +is the following: + +When a task is attached to the rt runqueue, it is checked if it either +can run in more than one CPU, or if it is with migration disable. If +either check is true, the rt_rq->rt_nr_migratory counter is not +increased. The counter increases otherwise. + +When the task is detached, the same check is done. If either check is +true, the rt_rq->rt_nr_migratory counter is not decreased. The counter +decreases otherwise. The same check is done in the dl scheduler. + +One important thing is that, migrate disable/enable does not touch this +counter for tasks attached to the rt rq. So suppose the following chain +of events. + +Assumptions: +Task A is the only runnable task in A Task B runs on the CPU B +Task A runs on CFS (non-rt) Task B has RT priority +Thus, rt_nr_migratory is 0 B is running +Task A can run on all CPUS. + +Timeline: + CPU A/TASK A CPU B/TASK B +A takes the rt mutex X . +A disables migration . + . B tries to take the rt mutex X + . As it is held by A { + . A inherits the rt priority of B + . A is dequeued from CFS RQ of CPU A + . A is enqueued in the RT RQ of CPU A + . As migration is disabled + . rt_nr_migratory in A is not increased + . +A enables migration +A releases the rt mutex X { + A returns to its original priority + A ask to be dequeued from RT RQ { + As migration is now enabled and it can run on all CPUS { + rt_nr_migratory should be decreased + As rt_nr_migratory is 0, rt_nr_migratory under flows + } +} + +This variable is important because it notifies if there are more than one +runnable & migratory task in the runqueue. If there are more than one +tasks, the rt_rq is set as overloaded, and then tries to migrate some +tasks. This rule is important to keep the scheduler working conserving, +that is, in a system with M CPUs, the M highest priority tasks should be +running. + +As rt_nr_migratory is unsigned, it will become > 0, notifying that the +RQ is overloaded, activating pushing mechanism without need. + +This patch fixes this problem by decreasing/increasing the +rt/dl_nr_migratory in the migrate disable/enable operations. + +Reported-by: Pei Zhang <pezhang@redhat.com> +Reported-by: Luiz Capitulino <lcapitulino@redhat.com> +Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> +Cc: Luis Claudio R. Goncalves <lgoncalv@redhat.com> +Cc: Clark Williams <williams@redhat.com> +Cc: Luiz Capitulino <lcapitulino@redhat.com> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: Thomas Gleixner <tglx@linutronix.de> +Cc: Steven Rostedt <rostedt@goodmis.org> +Cc: Peter Zijlstra <peterz@infradead.org> +Cc: Ingo Molnar <mingo@kernel.org> +Cc: LKML <linux-kernel@vger.kernel.org> +Cc: linux-rt-users <linux-rt-users@vger.kernel.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/core.c | 49 ++++++++++++++++++++++++++++++++++++++++----- + 1 file changed, 44 insertions(+), 5 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index dadf92046f01..ba6f445ac9e8 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7179,6 +7179,47 @@ const u32 sched_prio_to_wmult[40] = { + + #if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) + ++static inline void ++update_nr_migratory(struct task_struct *p, long delta) ++{ ++ if (unlikely((p->sched_class == &rt_sched_class || ++ p->sched_class == &dl_sched_class) && ++ p->nr_cpus_allowed > 1)) { ++ if (p->sched_class == &rt_sched_class) ++ task_rq(p)->rt.rt_nr_migratory += delta; ++ else ++ task_rq(p)->dl.dl_nr_migratory += delta; ++ } ++} ++ ++static inline void ++migrate_disable_update_cpus_allowed(struct task_struct *p) ++{ ++ struct rq *rq; ++ struct rq_flags rf; ++ ++ p->cpus_ptr = cpumask_of(smp_processor_id()); ++ ++ rq = task_rq_lock(p, &rf); ++ update_nr_migratory(p, -1); ++ p->nr_cpus_allowed = 1; ++ task_rq_unlock(rq, p, &rf); ++} ++ ++static inline void ++migrate_enable_update_cpus_allowed(struct task_struct *p) ++{ ++ struct rq *rq; ++ struct rq_flags rf; ++ ++ p->cpus_ptr = &p->cpus_mask; ++ ++ rq = task_rq_lock(p, &rf); ++ p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); ++ update_nr_migratory(p, 1); ++ task_rq_unlock(rq, p, &rf); ++} ++ + void migrate_disable(void) + { + struct task_struct *p = current; +@@ -7202,10 +7243,9 @@ void migrate_disable(void) + } + + preempt_disable(); +- p->migrate_disable = 1; + +- p->cpus_ptr = cpumask_of(smp_processor_id()); +- p->nr_cpus_allowed = 1; ++ migrate_disable_update_cpus_allowed(p); ++ p->migrate_disable = 1; + + preempt_enable(); + } +@@ -7237,9 +7277,8 @@ void migrate_enable(void) + + preempt_disable(); + +- p->cpus_ptr = &p->cpus_mask; +- p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); + p->migrate_disable = 0; ++ migrate_enable_update_cpus_allowed(p); + + if (p->migrate_disable_update) { + struct rq *rq; +-- +2.36.1 + diff --git a/debian/patches-rt/0115-hotplug-Lightweight-get-online-cpus.patch b/debian/patches-rt/0115-hotplug-Lightweight-get-online-cpus.patch new file mode 100644 index 000000000..5561bbcf7 --- /dev/null +++ b/debian/patches-rt/0115-hotplug-Lightweight-get-online-cpus.patch @@ -0,0 +1,101 @@ +From bf07bc52ad387c3cec5179aac1a8a08bfe0e24f7 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 15 Jun 2011 12:36:06 +0200 +Subject: [PATCH 115/347] hotplug: Lightweight get online cpus +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +get_online_cpus() is a heavy weight function which involves a global +mutex. migrate_disable() wants a simpler construct which prevents only +a CPU from going doing while a task is in a migrate disabled section. + +Implement a per cpu lockless mechanism, which serializes only in the +real unplug case on a global mutex. That serialization affects only +tasks on the cpu which should be brought down. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/cpu.h | 5 +++++ + kernel/cpu.c | 15 +++++++++++++++ + kernel/sched/core.c | 4 ++++ + 3 files changed, 24 insertions(+) + +diff --git a/include/linux/cpu.h b/include/linux/cpu.h +index aab4273810e3..e67645924404 100644 +--- a/include/linux/cpu.h ++++ b/include/linux/cpu.h +@@ -118,6 +118,8 @@ extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); + void clear_tasks_mm_cpumask(int cpu); + int cpu_down(unsigned int cpu); ++extern void pin_current_cpu(void); ++extern void unpin_current_cpu(void); + + #else /* CONFIG_HOTPLUG_CPU */ + +@@ -129,6 +131,9 @@ static inline int cpus_read_trylock(void) { return true; } + static inline void lockdep_assert_cpus_held(void) { } + static inline void cpu_hotplug_disable(void) { } + static inline void cpu_hotplug_enable(void) { } ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } ++ + #endif /* !CONFIG_HOTPLUG_CPU */ + + /* Wrappers which go away once all code is converted */ +diff --git a/kernel/cpu.c b/kernel/cpu.c +index d6fd362afc81..89a96cc14b39 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -283,6 +283,21 @@ static int cpu_hotplug_disabled; + + #ifdef CONFIG_HOTPLUG_CPU + ++/** ++ * pin_current_cpu - Prevent the current cpu from being unplugged ++ */ ++void pin_current_cpu(void) ++{ ++ ++} ++ ++/** ++ * unpin_current_cpu - Allow unplug of current cpu ++ */ ++void unpin_current_cpu(void) ++{ ++} ++ + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); + + void cpus_read_lock(void) +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index ba6f445ac9e8..ed79f921a84e 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7243,6 +7243,7 @@ void migrate_disable(void) + } + + preempt_disable(); ++ pin_current_cpu(); + + migrate_disable_update_cpus_allowed(p); + p->migrate_disable = 1; +@@ -7308,12 +7309,15 @@ void migrate_enable(void) + arg.task = p; + arg.dest_cpu = dest_cpu; + ++ unpin_current_cpu(); + preempt_enable(); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); ++ + return; + } + } ++ unpin_current_cpu(); + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); +-- +2.36.1 + diff --git a/debian/patches-rt/0116-trace-Add-migrate-disabled-counter-to-tracing-output.patch b/debian/patches-rt/0116-trace-Add-migrate-disabled-counter-to-tracing-output.patch new file mode 100644 index 000000000..9f41d515a --- /dev/null +++ b/debian/patches-rt/0116-trace-Add-migrate-disabled-counter-to-tracing-output.patch @@ -0,0 +1,86 @@ +From 54b651a215692cc3d5d07f69dd37f1c3eb1ee353 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 17 Jul 2011 21:56:42 +0200 +Subject: [PATCH 116/347] trace: Add migrate-disabled counter to tracing output +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/trace_events.h | 2 ++ + kernel/trace/trace.c | 9 ++++++--- + kernel/trace/trace_events.c | 2 ++ + kernel/trace/trace_output.c | 5 +++++ + 4 files changed, 15 insertions(+), 3 deletions(-) + +diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h +index 0643c083ed86..1cc4d2da954c 100644 +--- a/include/linux/trace_events.h ++++ b/include/linux/trace_events.h +@@ -62,6 +62,8 @@ struct trace_entry { + unsigned char flags; + unsigned char preempt_count; + int pid; ++ unsigned short migrate_disable; ++ unsigned short padding; + }; + + #define TRACE_EVENT_TYPE_MAX \ +diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c +index 063b434c89d2..2a8b830d42f1 100644 +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -2165,6 +2165,8 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, + ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | + (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); ++ ++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; + } + EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +@@ -3367,9 +3369,10 @@ static void print_lat_help_header(struct seq_file *m) + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" +- "# |||| / delay \n" +- "# cmd pid ||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ "# |||| / _--=> migrate-disable\n" ++ "# ||||| / delay \n" ++ "# cmd pid |||||| time | caller \n" ++ "# \\ / ||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c +index 1ca64a9296d0..fbb04cf1d5bc 100644 +--- a/kernel/trace/trace_events.c ++++ b/kernel/trace/trace_events.c +@@ -188,6 +188,8 @@ static int trace_define_common_fields(void) + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); ++ __common_field(unsigned short, migrate_disable); ++ __common_field(unsigned short, padding); + + return ret; + } +diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c +index 6e6cc64faa38..46c96744f09d 100644 +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -494,6 +494,11 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + else + trace_seq_putc(s, '.'); + ++ if (entry->migrate_disable) ++ trace_seq_printf(s, "%x", entry->migrate_disable); ++ else ++ trace_seq_putc(s, '.'); ++ + return !trace_seq_has_overflowed(s); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0117-lockdep-Make-it-RT-aware.patch b/debian/patches-rt/0117-lockdep-Make-it-RT-aware.patch new file mode 100644 index 000000000..445f08b7b --- /dev/null +++ b/debian/patches-rt/0117-lockdep-Make-it-RT-aware.patch @@ -0,0 +1,78 @@ +From 847045ea96b917f8dab8df5053e66280a83c84e4 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 17 Jul 2011 18:51:23 +0200 +Subject: [PATCH 117/347] lockdep: Make it RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +teach lockdep that we don't really do softirqs on -RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/irqflags.h | 23 +++++++++++++++-------- + kernel/locking/lockdep.c | 2 ++ + 2 files changed, 17 insertions(+), 8 deletions(-) + +diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h +index 21619c92c377..b20eeb25e9fa 100644 +--- a/include/linux/irqflags.h ++++ b/include/linux/irqflags.h +@@ -43,14 +43,6 @@ do { \ + do { \ + current->hardirq_context--; \ + } while (0) +-# define lockdep_softirq_enter() \ +-do { \ +- current->softirq_context++; \ +-} while (0) +-# define lockdep_softirq_exit() \ +-do { \ +- current->softirq_context--; \ +-} while (0) + #else + # define trace_hardirqs_on() do { } while (0) + # define trace_hardirqs_off() do { } while (0) +@@ -64,6 +56,21 @@ do { \ + # define lockdep_softirq_exit() do { } while (0) + #endif + ++#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) ++# define lockdep_softirq_enter() \ ++do { \ ++ current->softirq_context++; \ ++} while (0) ++# define lockdep_softirq_exit() \ ++do { \ ++ current->softirq_context--; \ ++} while (0) ++ ++#else ++# define lockdep_softirq_enter() do { } while (0) ++# define lockdep_softirq_exit() do { } while (0) ++#endif ++ + #if defined(CONFIG_IRQSOFF_TRACER) || \ + defined(CONFIG_PREEMPT_TRACER) + extern void stop_critical_timings(void); +diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c +index 4dc79f57af82..4dd83428b56d 100644 +--- a/kernel/locking/lockdep.c ++++ b/kernel/locking/lockdep.c +@@ -3831,6 +3831,7 @@ static void check_flags(unsigned long flags) + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only +@@ -3845,6 +3846,7 @@ static void check_flags(unsigned long flags) + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } ++#endif + + if (!debug_locks) + print_irqtrace_events(current); +-- +2.36.1 + diff --git a/debian/patches-rt/0118-tasklet-Prevent-tasklets-from-going-into-infinite-sp.patch b/debian/patches-rt/0118-tasklet-Prevent-tasklets-from-going-into-infinite-sp.patch new file mode 100644 index 000000000..2885b4101 --- /dev/null +++ b/debian/patches-rt/0118-tasklet-Prevent-tasklets-from-going-into-infinite-sp.patch @@ -0,0 +1,303 @@ +From ff4b7bd98df1b1100237e3ac2f11c687a486c18b Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Tue, 29 Nov 2011 20:18:22 -0500 +Subject: [PATCH 118/347] tasklet: Prevent tasklets from going into infinite + spin in RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When CONFIG_PREEMPT_RT_FULL is enabled, tasklets run as threads, +and spinlocks turn are mutexes. But this can cause issues with +tasks disabling tasklets. A tasklet runs under ksoftirqd, and +if a tasklets are disabled with tasklet_disable(), the tasklet +count is increased. When a tasklet runs, it checks this counter +and if it is set, it adds itself back on the softirq queue and +returns. + +The problem arises in RT because ksoftirq will see that a softirq +is ready to run (the tasklet softirq just re-armed itself), and will +not sleep, but instead run the softirqs again. The tasklet softirq +will still see that the count is non-zero and will not execute +the tasklet and requeue itself on the softirq again, which will +cause ksoftirqd to run it again and again and again. + +It gets worse because ksoftirqd runs as a real-time thread. +If it preempted the task that disabled tasklets, and that task +has migration disabled, or can't run for other reasons, the tasklet +softirq will never run because the count will never be zero, and +ksoftirqd will go into an infinite loop. As an RT task, it this +becomes a big problem. + +This is a hack solution to have tasklet_disable stop tasklets, and +when a tasklet runs, instead of requeueing the tasklet softirqd +it delays it. When tasklet_enable() is called, and tasklets are +waiting, then the tasklet_enable() will kick the tasklets to continue. +This prevents the lock up from ksoftirq going into an infinite loop. + +[ rostedt@goodmis.org: ported to 3.0-rt ] + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/interrupt.h | 33 +++++----- + kernel/softirq.c | 126 ++++++++++++++++++++++++++++++++------ + 2 files changed, 125 insertions(+), 34 deletions(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index 315f852b4981..35fa335c475b 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -536,8 +536,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void) + to be executed on some cpu at least once after this. + * If the tasklet is already scheduled, but its execution is still not + started, it will be executed only once. +- * If this tasklet is already running on another CPU (or schedule is called +- from tasklet itself), it is rescheduled for later. ++ * If this tasklet is already running on another CPU, it is rescheduled ++ for later. ++ * Schedule must not be called from the tasklet itself (a lockup occurs) + * Tasklet is strictly serialized wrt itself, but not + wrt another tasklets. If client needs some intertask synchronization, + he makes it with spinlocks. +@@ -562,27 +563,36 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data } + enum + { + TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ +- TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_PENDING /* Tasklet is pending */ + }; + +-#ifdef CONFIG_SMP ++#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) ++#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) ++#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) ++ ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static inline int tasklet_trylock(struct tasklet_struct *t) + { + return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); + } + ++static inline int tasklet_tryunlock(struct tasklet_struct *t) ++{ ++ return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; ++} ++ + static inline void tasklet_unlock(struct tasklet_struct *t) + { + smp_mb__before_atomic(); + clear_bit(TASKLET_STATE_RUN, &(t)->state); + } + +-static inline void tasklet_unlock_wait(struct tasklet_struct *t) +-{ +- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } +-} ++extern void tasklet_unlock_wait(struct tasklet_struct *t); ++ + #else + #define tasklet_trylock(t) 1 ++#define tasklet_tryunlock(t) 1 + #define tasklet_unlock_wait(t) do { } while (0) + #define tasklet_unlock(t) do { } while (0) + #endif +@@ -616,12 +626,7 @@ static inline void tasklet_disable(struct tasklet_struct *t) + smp_mb(); + } + +-static inline void tasklet_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic(); +- atomic_dec(&t->count); +-} +- ++extern void tasklet_enable(struct tasklet_struct *t); + extern void tasklet_kill(struct tasklet_struct *t); + extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); + extern void tasklet_init(struct tasklet_struct *t, +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 6f584861d329..1d3a482246cc 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -21,6 +21,7 @@ + #include <linux/freezer.h> + #include <linux/kthread.h> + #include <linux/rcupdate.h> ++#include <linux/delay.h> + #include <linux/ftrace.h> + #include <linux/smp.h> + #include <linux/smpboot.h> +@@ -475,11 +476,38 @@ static void __tasklet_schedule_common(struct tasklet_struct *t, + unsigned long flags; + + local_irq_save(flags); ++ if (!tasklet_trylock(t)) { ++ local_irq_restore(flags); ++ return; ++ } ++ + head = this_cpu_ptr(headp); +- t->next = NULL; +- *head->tail = t; +- head->tail = &(t->next); +- raise_softirq_irqoff(softirq_nr); ++again: ++ /* We may have been preempted before tasklet_trylock ++ * and __tasklet_action may have already run. ++ * So double check the sched bit while the takslet ++ * is locked before adding it to the list. ++ */ ++ if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++ t->next = NULL; ++ *head->tail = t; ++ head->tail = &(t->next); ++ raise_softirq_irqoff(softirq_nr); ++ tasklet_unlock(t); ++ } else { ++ /* This is subtle. If we hit the corner case above ++ * It is possible that we get preempted right here, ++ * and another task has successfully called ++ * tasklet_schedule(), then this function, and ++ * failed on the trylock. Thus we must be sure ++ * before releasing the tasklet lock, that the ++ * SCHED_BIT is clear. Otherwise the tasklet ++ * may get its SCHED_BIT set, but not added to the ++ * list ++ */ ++ if (!tasklet_tryunlock(t)) ++ goto again; ++ } + local_irq_restore(flags); + } + +@@ -497,11 +525,21 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) + } + EXPORT_SYMBOL(__tasklet_hi_schedule); + ++void tasklet_enable(struct tasklet_struct *t) ++{ ++ if (!atomic_dec_and_test(&t->count)) ++ return; ++ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) ++ tasklet_schedule(t); ++} ++EXPORT_SYMBOL(tasklet_enable); ++ + static void tasklet_action_common(struct softirq_action *a, + struct tasklet_head *tl_head, + unsigned int softirq_nr) + { + struct tasklet_struct *list; ++ int loops = 1000000; + + local_irq_disable(); + list = tl_head->head; +@@ -513,25 +551,56 @@ static void tasklet_action_common(struct softirq_action *a, + struct tasklet_struct *t = list; + + list = list->next; ++ /* ++ * Should always succeed - after a tasklist got on the ++ * list (after getting the SCHED bit set from 0 to 1), ++ * nothing but the tasklet softirq it got queued to can ++ * lock it: ++ */ ++ if (!tasklet_trylock(t)) { ++ WARN_ON(1); ++ continue; ++ } + +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, +- &t->state)) +- BUG(); +- t->func(t->data); ++ t->next = NULL; ++ ++ if (unlikely(atomic_read(&t->count))) { ++out_disabled: ++ /* implicit unlock: */ ++ wmb(); ++ t->state = TASKLET_STATEF_PENDING; ++ continue; ++ } ++ /* ++ * After this point on the tasklet might be rescheduled ++ * on another CPU, but it can only be added to another ++ * CPU's tasklet list if we unlock the tasklet (which we ++ * dont do yet). ++ */ ++ if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ WARN_ON(1); ++again: ++ t->func(t->data); ++ ++ while (!tasklet_tryunlock(t)) { ++ /* ++ * If it got disabled meanwhile, bail out: ++ */ ++ if (atomic_read(&t->count)) ++ goto out_disabled; ++ /* ++ * If it got scheduled meanwhile, re-execute ++ * the tasklet function: ++ */ ++ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ goto again; ++ if (!--loops) { ++ printk("hm, tasklet state: %08lx\n", t->state); ++ WARN_ON(1); + tasklet_unlock(t); +- continue; ++ break; + } +- tasklet_unlock(t); + } +- +- local_irq_disable(); +- t->next = NULL; +- *tl_head->tail = t; +- tl_head->tail = &t->next; +- __raise_softirq_irqoff(softirq_nr); +- local_irq_enable(); + } + } + +@@ -563,7 +632,7 @@ void tasklet_kill(struct tasklet_struct *t) + + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + do { +- yield(); ++ msleep(1); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } + tasklet_unlock_wait(t); +@@ -637,6 +706,23 @@ void __init softirq_init(void) + open_softirq(HI_SOFTIRQ, tasklet_hi_action); + } + ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++void tasklet_unlock_wait(struct tasklet_struct *t) ++{ ++ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { ++ /* ++ * Hack for now to avoid this busy-loop: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ msleep(1); ++#else ++ barrier(); ++#endif ++ } ++} ++EXPORT_SYMBOL(tasklet_unlock_wait); ++#endif ++ + static int ksoftirqd_should_run(unsigned int cpu) + { + return local_softirq_pending(); +-- +2.36.1 + diff --git a/debian/patches-rt/0119-softirq-Check-preemption-after-reenabling-interrupts.patch b/debian/patches-rt/0119-softirq-Check-preemption-after-reenabling-interrupts.patch new file mode 100644 index 000000000..fbf761018 --- /dev/null +++ b/debian/patches-rt/0119-softirq-Check-preemption-after-reenabling-interrupts.patch @@ -0,0 +1,180 @@ +From 45feb7680d31346f7a6da9926cdb23a37b640f47 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 13 Nov 2011 17:17:09 +0100 +Subject: [PATCH 119/347] softirq: Check preemption after reenabling interrupts +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +raise_softirq_irqoff() disables interrupts and wakes the softirq +daemon, but after reenabling interrupts there is no preemption check, +so the execution of the softirq thread might be delayed arbitrarily. + +In principle we could add that check to local_irq_enable/restore, but +that's overkill as the rasie_softirq_irqoff() sections are the only +ones which show this behaviour. + +Reported-by: Carsten Emde <cbe@osadl.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + block/blk-softirq.c | 3 +++ + include/linux/preempt.h | 3 +++ + lib/irq_poll.c | 5 +++++ + net/core/dev.c | 7 +++++++ + 4 files changed, 18 insertions(+) + +diff --git a/block/blk-softirq.c b/block/blk-softirq.c +index 15c1f5e12eb8..1628277885a1 100644 +--- a/block/blk-softirq.c ++++ b/block/blk-softirq.c +@@ -53,6 +53,7 @@ static void trigger_softirq(void *data) + raise_softirq_irqoff(BLOCK_SOFTIRQ); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /* +@@ -91,6 +92,7 @@ static int blk_softirq_cpu_dead(unsigned int cpu) + this_cpu_ptr(&blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + return 0; + } +@@ -143,6 +145,7 @@ void __blk_complete_request(struct request *req) + goto do_local; + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__blk_complete_request); + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index b7fe717eb1f4..9984f2b75b73 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -187,8 +187,10 @@ do { \ + + #ifdef CONFIG_PREEMPT_RT_BASE + # define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++# define preempt_check_resched_rt() preempt_check_resched() + #else + # define preempt_enable_no_resched() preempt_enable() ++# define preempt_check_resched_rt() barrier(); + #endif + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) +@@ -275,6 +277,7 @@ do { \ + #define preempt_disable_notrace() barrier() + #define preempt_enable_no_resched_notrace() barrier() + #define preempt_enable_notrace() barrier() ++#define preempt_check_resched_rt() barrier() + #define preemptible() 0 + + #define migrate_disable() barrier() +diff --git a/lib/irq_poll.c b/lib/irq_poll.c +index 86a709954f5a..9c069ef83d6d 100644 +--- a/lib/irq_poll.c ++++ b/lib/irq_poll.c +@@ -37,6 +37,7 @@ void irq_poll_sched(struct irq_poll *iop) + list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(irq_poll_sched); + +@@ -72,6 +73,7 @@ void irq_poll_complete(struct irq_poll *iop) + local_irq_save(flags); + __irq_poll_complete(iop); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(irq_poll_complete); + +@@ -96,6 +98,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h) + } + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Even though interrupts have been re-enabled, this + * access is safe because interrupts can only add new +@@ -133,6 +136,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h) + __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); + + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + /** +@@ -196,6 +200,7 @@ static int irq_poll_cpu_dead(unsigned int cpu) + this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + return 0; + } +diff --git a/net/core/dev.c b/net/core/dev.c +index 42f6ff8b9703..b8e3ae050bcc 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -2725,6 +2725,7 @@ static void __netif_reschedule(struct Qdisc *q) + sd->output_queue_tailp = &q->next_sched; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + void __netif_schedule(struct Qdisc *q) +@@ -2787,6 +2788,7 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__dev_kfree_skb_irq); + +@@ -4269,6 +4271,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + rps_unlock(sd); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); +@@ -5820,12 +5823,14 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) + sd->rps_ipi_list = NULL; + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + net_rps_send_ipi(remsd); + } else + #endif + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) +@@ -5903,6 +5908,7 @@ void __napi_schedule(struct napi_struct *n) + local_irq_save(flags); + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__napi_schedule); + +@@ -9527,6 +9533,7 @@ static int dev_cpu_dead(unsigned int oldcpu) + + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + #ifdef CONFIG_RPS + remsd = oldsd->rps_ipi_list; +-- +2.36.1 + diff --git a/debian/patches-rt/0120-softirq-Disable-softirq-stacks-for-RT.patch b/debian/patches-rt/0120-softirq-Disable-softirq-stacks-for-RT.patch new file mode 100644 index 000000000..3c4ba7e3e --- /dev/null +++ b/debian/patches-rt/0120-softirq-Disable-softirq-stacks-for-RT.patch @@ -0,0 +1,177 @@ +From 7e198889f2947f9bfeecdda6955492f55399a621 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 18 Jul 2011 13:59:17 +0200 +Subject: [PATCH 120/347] softirq: Disable softirq stacks for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Disable extra stacks for softirqs. We want to preempt softirqs and +having them on special IRQ-stack does not make this easier. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/kernel/irq.c | 2 ++ + arch/powerpc/kernel/misc_32.S | 2 ++ + arch/powerpc/kernel/misc_64.S | 2 ++ + arch/sh/kernel/irq.c | 2 ++ + arch/sparc/kernel/irq_64.c | 2 ++ + arch/x86/entry/entry_64.S | 2 ++ + arch/x86/kernel/irq_32.c | 2 ++ + include/linux/interrupt.h | 2 +- + 8 files changed, 15 insertions(+), 1 deletion(-) + +diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c +index d37704ebccdb..b45a9849b687 100644 +--- a/arch/powerpc/kernel/irq.c ++++ b/arch/powerpc/kernel/irq.c +@@ -766,6 +766,7 @@ void irq_ctx_init(void) + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curtp, *irqtp; +@@ -783,6 +784,7 @@ void do_softirq_own_stack(void) + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); + } ++#endif + + irq_hw_number_t virq_to_hw(unsigned int virq) + { +diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S +index 695b24a2d954..032ada21b7bd 100644 +--- a/arch/powerpc/kernel/misc_32.S ++++ b/arch/powerpc/kernel/misc_32.S +@@ -42,6 +42,7 @@ + * We store the saved ksp_limit in the unused part + * of the STACK_FRAME_OVERHEAD + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) +@@ -58,6 +59,7 @@ _GLOBAL(call_do_softirq) + stw r10,THREAD+KSP_LIMIT(r2) + mtlr r0 + blr ++#endif + + /* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); +diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S +index facc02964ab3..8b1774186c68 100644 +--- a/arch/powerpc/kernel/misc_64.S ++++ b/arch/powerpc/kernel/misc_64.S +@@ -32,6 +32,7 @@ + + .text + ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + std r0,16(r1) +@@ -42,6 +43,7 @@ _GLOBAL(call_do_softirq) + ld r0,16(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_do_irq) + mflr r0 +diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c +index 5717c7cbdd97..66dd399b2007 100644 +--- a/arch/sh/kernel/irq.c ++++ b/arch/sh/kernel/irq.c +@@ -148,6 +148,7 @@ void irq_ctx_exit(int cpu) + hardirq_ctx[cpu] = NULL; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curctx; +@@ -175,6 +176,7 @@ void do_softirq_own_stack(void) + "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" + ); + } ++#endif + #else + static inline void handle_one_irq(unsigned int irq) + { +diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c +index 713670e6d13d..5dfc715343f9 100644 +--- a/arch/sparc/kernel/irq_64.c ++++ b/arch/sparc/kernel/irq_64.c +@@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs) + set_irq_regs(old_regs); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + void *orig_sp, *sp = softirq_stack[smp_processor_id()]; +@@ -868,6 +869,7 @@ void do_softirq_own_stack(void) + __asm__ __volatile__("mov %0, %%sp" + : : "r" (orig_sp)); + } ++#endif + + #ifdef CONFIG_HOTPLUG_CPU + void fixup_irqs(void) +diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S +index dfe26f3cfffc..f53d995b1370 100644 +--- a/arch/x86/entry/entry_64.S ++++ b/arch/x86/entry/entry_64.S +@@ -1084,6 +1084,7 @@ EXPORT_SYMBOL(native_load_gs_index) + jmp 2b + .previous + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* Call softirq on interrupt stack. Interrupts are off. */ + ENTRY(do_softirq_own_stack) + pushq %rbp +@@ -1094,6 +1095,7 @@ ENTRY(do_softirq_own_stack) + leaveq + ret + ENDPROC(do_softirq_own_stack) ++#endif + + #ifdef CONFIG_XEN + idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c +index 95600a99ae93..9192d76085ba 100644 +--- a/arch/x86/kernel/irq_32.c ++++ b/arch/x86/kernel/irq_32.c +@@ -130,6 +130,7 @@ void irq_ctx_init(int cpu) + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct irq_stack *irqstk; +@@ -146,6 +147,7 @@ void do_softirq_own_stack(void) + + call_on_stack(__do_softirq, isp); + } ++#endif + + bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) + { +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index 35fa335c475b..eec4bec454b5 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -500,7 +500,7 @@ struct softirq_action + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); + +-#ifdef __ARCH_HAS_DO_SOFTIRQ ++#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT_FULL) + void do_softirq_own_stack(void); + #else + static inline void do_softirq_own_stack(void) +-- +2.36.1 + diff --git a/debian/patches-rt/0121-softirq-Split-softirq-locks.patch b/debian/patches-rt/0121-softirq-Split-softirq-locks.patch new file mode 100644 index 000000000..e3aeafa1d --- /dev/null +++ b/debian/patches-rt/0121-softirq-Split-softirq-locks.patch @@ -0,0 +1,832 @@ +From 4f304d0db14e45c0b23ed9ed8ee6749255dd180a Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 4 Oct 2012 14:20:47 +0100 +Subject: [PATCH 121/347] softirq: Split softirq locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The 3.x RT series removed the split softirq implementation in favour +of pushing softirq processing into the context of the thread which +raised it. Though this prevents us from handling the various softirqs +at different priorities. Now instead of reintroducing the split +softirq threads we split the locks which serialize the softirq +processing. + +If a softirq is raised in context of a thread, then the softirq is +noted on a per thread field, if the thread is in a bh disabled +region. If the softirq is raised from hard interrupt context, then the +bit is set in the flag field of ksoftirqd and ksoftirqd is invoked. +When a thread leaves a bh disabled region, then it tries to execute +the softirqs which have been raised in its own context. It acquires +the per softirq / per cpu lock for the softirq and then checks, +whether the softirq is still pending in the per cpu +local_softirq_pending() field. If yes, it runs the softirq. If no, +then some other task executed it already. This allows for zero config +softirq elevation in the context of user space tasks or interrupt +threads. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/bottom_half.h | 34 +++ + include/linux/interrupt.h | 15 +- + include/linux/preempt.h | 15 +- + include/linux/sched.h | 3 + + init/main.c | 1 + + kernel/softirq.c | 491 ++++++++++++++++++++++++++++++------ + kernel/time/tick-sched.c | 9 +- + 7 files changed, 478 insertions(+), 90 deletions(-) + +diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h +index a19519f4241d..40dd5ef9c154 100644 +--- a/include/linux/bottom_half.h ++++ b/include/linux/bottom_half.h +@@ -4,6 +4,39 @@ + + #include <linux/preempt.h> + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++extern void __local_bh_disable(void); ++extern void _local_bh_enable(void); ++extern void __local_bh_enable(void); ++ ++static inline void local_bh_disable(void) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void local_bh_enable(void) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void local_bh_enable_ip(unsigned long ip) ++{ ++ __local_bh_enable(); ++} ++ ++#else ++ + #ifdef CONFIG_TRACE_IRQFLAGS + extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); + #else +@@ -31,5 +64,6 @@ static inline void local_bh_enable(void) + { + __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); + } ++#endif + + #endif /* _LINUX_BH_H */ +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index eec4bec454b5..cf9860d49d57 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -497,10 +497,11 @@ struct softirq_action + void (*action)(struct softirq_action *); + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); +- +-#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT_FULL) ++static inline void thread_do_softirq(void) { do_softirq(); } ++#ifdef __ARCH_HAS_DO_SOFTIRQ + void do_softirq_own_stack(void); + #else + static inline void do_softirq_own_stack(void) +@@ -508,6 +509,9 @@ static inline void do_softirq_own_stack(void) + __do_softirq(); + } + #endif ++#else ++extern void thread_do_softirq(void); ++#endif + + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); +@@ -515,6 +519,7 @@ extern void __raise_softirq_irqoff(unsigned int nr); + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); ++extern void softirq_check_pending_idle(void); + + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + +@@ -632,6 +637,12 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); + extern void tasklet_init(struct tasklet_struct *t, + void (*func)(unsigned long), unsigned long data); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void softirq_early_init(void); ++#else ++static inline void softirq_early_init(void) { } ++#endif ++ + struct tasklet_hrtimer { + struct hrtimer timer; + struct tasklet_struct tasklet; +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index 9984f2b75b73..27c3176d88d2 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -51,7 +51,11 @@ + #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) + #define NMI_OFFSET (1UL << NMI_SHIFT) + +-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#else ++# define SOFTIRQ_DISABLE_OFFSET (0) ++#endif + + /* We use the MSB mostly because its available */ + #define PREEMPT_NEED_RESCHED 0x80000000 +@@ -81,9 +85,15 @@ + #include <asm/preempt.h> + + #define hardirq_count() (preempt_count() & HARDIRQ_MASK) +-#define softirq_count() (preempt_count() & SOFTIRQ_MASK) + #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define softirq_count() (preempt_count() & SOFTIRQ_MASK) ++# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) ++#else ++# define softirq_count() ((unsigned long)current->softirq_nestcnt) ++extern int in_serving_softirq(void); ++#endif + + /* + * Are we doing bottom half or hardware interrupt processing? +@@ -101,7 +111,6 @@ + #define in_irq() (hardirq_count()) + #define in_softirq() (softirq_count()) + #define in_interrupt() (irq_count()) +-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + #define in_nmi() (preempt_count() & NMI_MASK) + #define in_task() (!(preempt_count() & \ + (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 1b2884889dd0..63a97f24d138 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1200,6 +1200,8 @@ struct task_struct { + #endif + #ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head put_rcu; ++ int softirq_nestcnt; ++ unsigned int softirqs_raised; + #endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; +@@ -1397,6 +1399,7 @@ extern struct pid *cad_pid; + /* + * Per process flags + */ ++#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ + #define PF_IDLE 0x00000002 /* I am an IDLE thread */ + #define PF_EXITING 0x00000004 /* Getting shut down */ + #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +diff --git a/init/main.c b/init/main.c +index 272ec131211c..0d5763c5da28 100644 +--- a/init/main.c ++++ b/init/main.c +@@ -560,6 +560,7 @@ asmlinkage __visible void __init start_kernel(void) + setup_command_line(command_line); + setup_nr_cpu_ids(); + setup_per_cpu_areas(); ++ softirq_early_init(); + smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + boot_cpu_hotplug_init(); + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 1d3a482246cc..fd89f8ab85ac 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -26,7 +26,9 @@ + #include <linux/smp.h> + #include <linux/smpboot.h> + #include <linux/tick.h> ++#include <linux/locallock.h> + #include <linux/irq.h> ++#include <linux/sched/types.h> + + #define CREATE_TRACE_POINTS + #include <trace/events/irq.h> +@@ -63,6 +65,98 @@ const char * const softirq_to_name[NR_SOFTIRQS] = { + "TASKLET", "SCHED", "HRTIMER", "RCU" + }; + ++#ifdef CONFIG_NO_HZ_COMMON ++# ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct softirq_runner { ++ struct task_struct *runner[NR_SOFTIRQS]; ++}; ++ ++static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); ++ ++static inline void softirq_set_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = current; ++} ++ ++static inline void softirq_clr_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = NULL; ++} ++ ++/* ++ * On preempt-rt a softirq running context might be blocked on a ++ * lock. There might be no other runnable task on this CPU because the ++ * lock owner runs on some other CPU. So we have to go into idle with ++ * the pending bit set. Therefor we need to check this otherwise we ++ * warn about false positives which confuses users and defeats the ++ * whole purpose of this test. ++ * ++ * This code is called with interrupts disabled. ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ u32 warnpending; ++ int i; ++ ++ if (rate_limit >= 10) ++ return; ++ ++ warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; ++ for (i = 0; i < NR_SOFTIRQS; i++) { ++ struct task_struct *tsk = sr->runner[i]; ++ ++ /* ++ * The wakeup code in rtmutex.c wakes up the task ++ * _before_ it sets pi_blocked_on to NULL under ++ * tsk->pi_lock. So we need to check for both: state ++ * and pi_blocked_on. ++ */ ++ if (tsk) { ++ raw_spin_lock(&tsk->pi_lock); ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ /* Clear all bits pending in that task */ ++ warnpending &= ~(tsk->softirqs_raised); ++ warnpending &= ~(1 << i); ++ } ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ } ++ ++ if (warnpending) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ warnpending); ++ rate_limit++; ++ } ++} ++# else ++/* ++ * On !PREEMPT_RT we just printk rate limited: ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ ++ if (rate_limit < 10 && ++ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ local_softirq_pending()); ++ rate_limit++; ++ } ++} ++# endif ++ ++#else /* !CONFIG_NO_HZ_COMMON */ ++static inline void softirq_set_runner(unsigned int sirq) { } ++static inline void softirq_clr_runner(unsigned int sirq) { } ++#endif ++ + /* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency +@@ -78,6 +172,27 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + ++static void handle_softirq(unsigned int vec_nr) ++{ ++ struct softirq_action *h = softirq_vec + vec_nr; ++ int prev_count; ++ ++ prev_count = preempt_count(); ++ ++ kstat_incr_softirqs_this_cpu(vec_nr); ++ ++ trace_softirq_entry(vec_nr); ++ h->action(h); ++ trace_softirq_exit(vec_nr); ++ if (unlikely(prev_count != preempt_count())) { ++ pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", ++ vec_nr, softirq_to_name[vec_nr], h->action, ++ prev_count, preempt_count()); ++ preempt_count_set(prev_count); ++ } ++} ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * If ksoftirqd is scheduled, we do not want to process pending softirqs + * right now. Let ksoftirqd handle this at its own rate, to get fairness, +@@ -93,6 +208,47 @@ static bool ksoftirqd_running(unsigned long pending) + return tsk && (tsk->state == TASK_RUNNING); + } + ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return local_softirq_pending(); ++} ++ ++static void handle_pending_softirqs(u32 pending) ++{ ++ struct softirq_action *h = softirq_vec; ++ int softirq_bit; ++ ++ local_irq_enable(); ++ ++ h = softirq_vec; ++ ++ while ((softirq_bit = ffs(pending))) { ++ unsigned int vec_nr; ++ ++ h += softirq_bit - 1; ++ vec_nr = h - softirq_vec; ++ handle_softirq(vec_nr); ++ ++ h++; ++ pending >>= softirq_bit; ++ } ++ ++ rcu_bh_qs(); ++ local_irq_disable(); ++} ++ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ if (ksoftirqd_softirq_pending()) { ++ __do_softirq(); ++ local_irq_enable(); ++ cond_resched(); ++ return; ++ } ++ local_irq_enable(); ++} ++ + /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving +@@ -252,10 +408,8 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; +- struct softirq_action *h; + bool in_hardirq; + __u32 pending; +- int softirq_bit; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the +@@ -274,36 +428,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + +- local_irq_enable(); +- +- h = softirq_vec; +- +- while ((softirq_bit = ffs(pending))) { +- unsigned int vec_nr; +- int prev_count; +- +- h += softirq_bit - 1; +- +- vec_nr = h - softirq_vec; +- prev_count = preempt_count(); +- +- kstat_incr_softirqs_this_cpu(vec_nr); +- +- trace_softirq_entry(vec_nr); +- h->action(h); +- trace_softirq_exit(vec_nr); +- if (unlikely(prev_count != preempt_count())) { +- pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", +- vec_nr, softirq_to_name[vec_nr], h->action, +- prev_count, preempt_count()); +- preempt_count_set(prev_count); +- } +- h++; +- pending >>= softirq_bit; +- } +- +- rcu_bh_qs(); +- local_irq_disable(); ++ handle_pending_softirqs(pending); + + pending = local_softirq_pending(); + if (pending) { +@@ -339,6 +464,248 @@ asmlinkage __visible void do_softirq(void) + local_irq_restore(flags); + } + ++/* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an interrupt or softirq, we're done ++ * (this also catches softirq-disabled code). We will ++ * actually run the softirq once we return from ++ * the irq or softirq. ++ * ++ * Otherwise we wake up ksoftirqd to make sure we ++ * schedule the softirq soon. ++ */ ++ if (!in_interrupt()) ++ wakeup_softirqd(); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++} ++ ++static inline void local_bh_disable_nort(void) { local_bh_disable(); } ++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } ++static void ksoftirqd_set_sched_params(unsigned int cpu) { } ++static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On RT we serialize softirq execution with a cpu local lock per softirq ++ */ ++static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); ++ ++void __init softirq_early_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < NR_SOFTIRQS; i++) ++ local_irq_lock_init(local_softirq_locks[i]); ++} ++ ++static void lock_softirq(int which) ++{ ++ local_lock(local_softirq_locks[which]); ++} ++ ++static void unlock_softirq(int which) ++{ ++ local_unlock(local_softirq_locks[which]); ++} ++ ++static void do_single_softirq(int which) ++{ ++ unsigned long old_flags = current->flags; ++ ++ current->flags &= ~PF_MEMALLOC; ++ vtime_account_irq_enter(current); ++ current->flags |= PF_IN_SOFTIRQ; ++ lockdep_softirq_enter(); ++ local_irq_enable(); ++ handle_softirq(which); ++ local_irq_disable(); ++ lockdep_softirq_exit(); ++ current->flags &= ~PF_IN_SOFTIRQ; ++ vtime_account_irq_enter(current); ++ current_restore_flags(old_flags, PF_MEMALLOC); ++} ++ ++/* ++ * Called with interrupts disabled. Process softirqs which were raised ++ * in current context (or on behalf of ksoftirqd). ++ */ ++static void do_current_softirqs(void) ++{ ++ while (current->softirqs_raised) { ++ int i = __ffs(current->softirqs_raised); ++ unsigned int pending, mask = (1U << i); ++ ++ current->softirqs_raised &= ~mask; ++ local_irq_enable(); ++ ++ /* ++ * If the lock is contended, we boost the owner to ++ * process the softirq or leave the critical section ++ * now. ++ */ ++ lock_softirq(i); ++ local_irq_disable(); ++ softirq_set_runner(i); ++ /* ++ * Check with the local_softirq_pending() bits, ++ * whether we need to process this still or if someone ++ * else took care of it. ++ */ ++ pending = local_softirq_pending(); ++ if (pending & mask) { ++ set_softirq_pending(pending & ~mask); ++ do_single_softirq(i); ++ } ++ softirq_clr_runner(i); ++ WARN_ON(current->softirq_nestcnt != 1); ++ local_irq_enable(); ++ unlock_softirq(i); ++ local_irq_disable(); ++ } ++} ++ ++void __local_bh_disable(void) ++{ ++ if (++current->softirq_nestcnt == 1) ++ migrate_disable(); ++} ++EXPORT_SYMBOL(__local_bh_disable); ++ ++void __local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ ++ local_irq_disable(); ++ if (current->softirq_nestcnt == 1 && current->softirqs_raised) ++ do_current_softirqs(); ++ local_irq_enable(); ++ ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(__local_bh_enable); ++ ++int in_serving_softirq(void) ++{ ++ return current->flags & PF_IN_SOFTIRQ; ++} ++EXPORT_SYMBOL(in_serving_softirq); ++ ++/* Called with preemption disabled */ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ current->softirq_nestcnt++; ++ ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ local_irq_enable(); ++ cond_resched(); ++} ++ ++/* ++ * Called from netif_rx_ni(). Preemption enabled, but migration ++ * disabled. So the cpu can't go away under us. ++ */ ++void thread_do_softirq(void) ++{ ++ if (!in_serving_softirq() && current->softirqs_raised) { ++ current->softirq_nestcnt++; ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ } ++} ++ ++static void do_raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++ ++ /* ++ * If we are not in a hard interrupt and inside a bh disabled ++ * region, we simply raise the flag on current. local_bh_enable() ++ * will make sure that the softirq is executed. Otherwise we ++ * delegate it to ksoftirqd. ++ */ ++ if (!in_irq() && current->softirq_nestcnt) ++ current->softirqs_raised |= (1U << nr); ++ else if (__this_cpu_read(ksoftirqd)) ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ if (!in_irq() && !current->softirq_nestcnt) ++ wakeup_softirqd(); ++} ++ ++/* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an hard interrupt we let irq return code deal ++ * with the wakeup of ksoftirqd. ++ */ ++ if (in_irq()) ++ return; ++ /* ++ * If we are in thread context but outside of a bh disabled ++ * region, we need to wake ksoftirqd as well. ++ * ++ * CHECKME: Some of the places which do that could be wrapped ++ * into local_bh_disable/enable pairs. Though it's unclear ++ * whether this is worth the effort. To find those places just ++ * raise a WARN() if the condition is met. ++ */ ++ if (!current->softirq_nestcnt) ++ wakeup_softirqd(); ++} ++ ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return current->softirqs_raised; ++} ++ ++static inline void local_bh_disable_nort(void) { } ++static inline void _local_bh_enable_nort(void) { } ++ ++static inline void ksoftirqd_set_sched_params(unsigned int cpu) ++{ ++ struct sched_param param = { .sched_priority = 1 }; ++ ++ sched_setscheduler(current, SCHED_FIFO, ¶m); ++ /* Take over all pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending(); ++ local_irq_enable(); ++} ++ ++static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) ++{ ++ struct sched_param param = { .sched_priority = 0 }; ++ ++ sched_setscheduler(current, SCHED_NORMAL, ¶m); ++} ++ ++#endif /* PREEMPT_RT_FULL */ + /* + * Enter an interrupt context. + */ +@@ -350,9 +717,9 @@ void irq_enter(void) + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ +- local_bh_disable(); ++ local_bh_disable_nort(); + tick_irq_enter(); +- _local_bh_enable(); ++ _local_bh_enable_nort(); + } + + __irq_enter(); +@@ -360,6 +727,7 @@ void irq_enter(void) + + static inline void invoke_softirq(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (ksoftirqd_running(local_softirq_pending())) + return; + +@@ -382,6 +750,15 @@ static inline void invoke_softirq(void) + } else { + wakeup_softirqd(); + } ++#else /* PREEMPT_RT_FULL */ ++ unsigned long flags; ++ ++ local_irq_save(flags); ++ if (__this_cpu_read(ksoftirqd) && ++ __this_cpu_read(ksoftirqd)->softirqs_raised) ++ wakeup_softirqd(); ++ local_irq_restore(flags); ++#endif + } + + static inline void tick_irq_exit(void) +@@ -417,26 +794,6 @@ void irq_exit(void) + trace_hardirq_exit(); /* must be last! */ + } + +-/* +- * This function must run with irqs disabled! +- */ +-inline void raise_softirq_irqoff(unsigned int nr) +-{ +- __raise_softirq_irqoff(nr); +- +- /* +- * If we're in an interrupt or softirq, we're done +- * (this also catches softirq-disabled code). We will +- * actually run the softirq once we return from +- * the irq or softirq. +- * +- * Otherwise we wake up ksoftirqd to make sure we +- * schedule the softirq soon. +- */ +- if (!in_interrupt()) +- wakeup_softirqd(); +-} +- + void raise_softirq(unsigned int nr) + { + unsigned long flags; +@@ -446,12 +803,6 @@ void raise_softirq(unsigned int nr) + local_irq_restore(flags); + } + +-void __raise_softirq_irqoff(unsigned int nr) +-{ +- trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); +-} +- + void open_softirq(int nr, void (*action)(struct softirq_action *)) + { + softirq_vec[nr].action = action; +@@ -725,23 +1076,7 @@ EXPORT_SYMBOL(tasklet_unlock_wait); + + static int ksoftirqd_should_run(unsigned int cpu) + { +- return local_softirq_pending(); +-} +- +-static void run_ksoftirqd(unsigned int cpu) +-{ +- local_irq_disable(); +- if (local_softirq_pending()) { +- /* +- * We can safely run softirq on inline stack, as we are not deep +- * in the task stack here. +- */ +- __do_softirq(); +- local_irq_enable(); +- cond_resched(); +- return; +- } +- local_irq_enable(); ++ return ksoftirqd_softirq_pending(); + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -808,6 +1143,8 @@ static int takeover_tasklets(unsigned int cpu) + + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, ++ .setup = ksoftirqd_set_sched_params, ++ .cleanup = ksoftirqd_clr_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", +diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c +index 012bc81879bf..2b0ddd50e879 100644 +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -895,14 +895,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { +- static int ratelimit; +- +- if (ratelimit < 10 && +- (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { +- pr_warn("NOHZ: local_softirq_pending %02x\n", +- (unsigned int) local_softirq_pending()); +- ratelimit++; +- } ++ softirq_check_pending_idle(); + return false; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0122-net-core-use-local_bh_disable-in-netif_rx_ni.patch b/debian/patches-rt/0122-net-core-use-local_bh_disable-in-netif_rx_ni.patch new file mode 100644 index 000000000..6f4fcdbeb --- /dev/null +++ b/debian/patches-rt/0122-net-core-use-local_bh_disable-in-netif_rx_ni.patch @@ -0,0 +1,41 @@ +From 2e2c294b277d487a55a1b9cd56dd172795e0f3f8 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 16 Jun 2017 19:03:16 +0200 +Subject: [PATCH 122/347] net/core: use local_bh_disable() in netif_rx_ni() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In 2004 netif_rx_ni() gained a preempt_disable() section around +netif_rx() and its do_softirq() + testing for it. The do_softirq() part +is required because netif_rx() raises the softirq but does not invoke +it. The preempt_disable() is required to remain on the same CPU which added the +skb to the per-CPU list. +All this can be avoided be putting this into a local_bh_disable()ed +section. The local_bh_enable() part will invoke do_softirq() if +required. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/core/dev.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +diff --git a/net/core/dev.c b/net/core/dev.c +index b8e3ae050bcc..315bdaf00ac8 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -4537,11 +4537,9 @@ int netif_rx_ni(struct sk_buff *skb) + + trace_netif_rx_ni_entry(skb); + +- preempt_disable(); ++ local_bh_disable(); + err = netif_rx_internal(skb); +- if (local_softirq_pending()) +- do_softirq(); +- preempt_enable(); ++ local_bh_enable(); + + return err; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0123-genirq-Allow-disabling-of-softirq-processing-in-irq-.patch b/debian/patches-rt/0123-genirq-Allow-disabling-of-softirq-processing-in-irq-.patch new file mode 100644 index 000000000..d24e2a815 --- /dev/null +++ b/debian/patches-rt/0123-genirq-Allow-disabling-of-softirq-processing-in-irq-.patch @@ -0,0 +1,144 @@ +From 70cfb822ccb0d82006eb62a4774d58021b340151 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 31 Jan 2012 13:01:27 +0100 +Subject: [PATCH 123/347] genirq: Allow disabling of softirq processing in irq + thread context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The processing of softirqs in irq thread context is a performance gain +for the non-rt workloads of a system, but it's counterproductive for +interrupts which are explicitely related to the realtime +workload. Allow such interrupts to prevent softirq processing in their +thread context. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/interrupt.h | 2 ++ + include/linux/irq.h | 4 +++- + kernel/irq/manage.c | 3 +++ + kernel/irq/settings.h | 12 ++++++++++++ + kernel/softirq.c | 9 +++++++++ + 5 files changed, 29 insertions(+), 1 deletion(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index cf9860d49d57..e1438fe66467 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -61,6 +61,7 @@ + * interrupt handler after suspending interrupts. For system + * wakeup devices users need to implement wakeup detection in + * their interrupt handlers. ++ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) + */ + #define IRQF_SHARED 0x00000080 + #define IRQF_PROBE_SHARED 0x00000100 +@@ -74,6 +75,7 @@ + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 + #define IRQF_COND_SUSPEND 0x00040000 ++#define IRQF_NO_SOFTIRQ_CALL 0x00080000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +diff --git a/include/linux/irq.h b/include/linux/irq.h +index 9504267414a4..0f1babb9775a 100644 +--- a/include/linux/irq.h ++++ b/include/linux/irq.h +@@ -69,6 +69,7 @@ enum irqchip_irq_state; + * IRQ_IS_POLLED - Always polled by another interrupt. Exclude + * it from the spurious interrupt detection + * mechanism and from core side polling. ++ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + * IRQ_DISABLE_UNLAZY - Disable lazy irq disable + */ + enum { +@@ -96,13 +97,14 @@ enum { + IRQ_PER_CPU_DEVID = (1 << 17), + IRQ_IS_POLLED = (1 << 18), + IRQ_DISABLE_UNLAZY = (1 << 19), ++ IRQ_NO_SOFTIRQ_CALL = (1 << 20), + }; + + #define IRQF_MODIFY_MASK \ + (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ + IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ +- IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY) ++ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL) + + #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) + +diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c +index f12f50f5b605..2bb77b0ebac8 100644 +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -1533,6 +1533,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + ++ if (new->flags & IRQF_NO_SOFTIRQ_CALL) ++ irq_settings_set_no_softirq_call(desc); ++ + if (irq_settings_can_autoenable(desc)) { + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + } else { +diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h +index e43795cd2ccf..47e2f9e23586 100644 +--- a/kernel/irq/settings.h ++++ b/kernel/irq/settings.h +@@ -17,6 +17,7 @@ enum { + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, ++ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, + }; + +@@ -31,6 +32,7 @@ enum { + #define IRQ_PER_CPU_DEVID GOT_YOU_MORON + #define IRQ_IS_POLLED GOT_YOU_MORON + #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON ++#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON + #undef IRQF_MODIFY_MASK + #define IRQF_MODIFY_MASK GOT_YOU_MORON + +@@ -41,6 +43,16 @@ irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); + } + ++static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) ++{ ++ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; ++} ++ ++static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) ++{ ++ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; ++} ++ + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) + { + return desc->status_use_accessors & _IRQ_PER_CPU; +diff --git a/kernel/softirq.c b/kernel/softirq.c +index fd89f8ab85ac..3e9333d148ad 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -598,6 +598,15 @@ void __local_bh_enable(void) + } + EXPORT_SYMBOL(__local_bh_enable); + ++void _local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(_local_bh_enable); ++ + int in_serving_softirq(void) + { + return current->flags & PF_IN_SOFTIRQ; +-- +2.36.1 + diff --git a/debian/patches-rt/0124-softirq-split-timer-softirqs-out-of-ksoftirqd.patch b/debian/patches-rt/0124-softirq-split-timer-softirqs-out-of-ksoftirqd.patch new file mode 100644 index 000000000..b6bb8cca8 --- /dev/null +++ b/debian/patches-rt/0124-softirq-split-timer-softirqs-out-of-ksoftirqd.patch @@ -0,0 +1,215 @@ +From 883087f48f717058bc203cd47430b55f77275fbd Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 20 Jan 2016 16:34:17 +0100 +Subject: [PATCH 124/347] softirq: split timer softirqs out of ksoftirqd +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The softirqd runs in -RT with SCHED_FIFO (prio 1) and deals mostly with +timer wakeup which can not happen in hardirq context. The prio has been +risen from the normal SCHED_OTHER so the timer wakeup does not happen +too late. +With enough networking load it is possible that the system never goes +idle and schedules ksoftirqd and everything else with a higher priority. +One of the tasks left behind is one of RCU's threads and so we see stalls +and eventually run out of memory. +This patch moves the TIMER and HRTIMER softirqs out of the `ksoftirqd` +thread into its own `ktimersoftd`. The former can now run SCHED_OTHER +(same as mainline) and the latter at SCHED_FIFO due to the wakeups. + +From networking point of view: The NAPI callback runs after the network +interrupt thread completes. If its run time takes too long the NAPI code +itself schedules the `ksoftirqd`. Here in the thread it can run at +SCHED_OTHER priority and it won't defer RCU anymore. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/softirq.c | 85 +++++++++++++++++++++++++++++++++++++++++------- + 1 file changed, 73 insertions(+), 12 deletions(-) + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 3e9333d148ad..fe4e59c80a08 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -59,6 +59,10 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); + static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; + + DEFINE_PER_CPU(struct task_struct *, ksoftirqd); ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ)) ++DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd); ++#endif + + const char * const softirq_to_name[NR_SOFTIRQS] = { + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL", +@@ -172,6 +176,17 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void wakeup_timer_softirqd(void) ++{ ++ /* Interrupts are disabled: no need to stop preemption */ ++ struct task_struct *tsk = __this_cpu_read(ktimer_softirqd); ++ ++ if (tsk && tsk->state != TASK_RUNNING) ++ wake_up_process(tsk); ++} ++#endif ++ + static void handle_softirq(unsigned int vec_nr) + { + struct softirq_action *h = softirq_vec + vec_nr; +@@ -493,7 +508,6 @@ void __raise_softirq_irqoff(unsigned int nr) + static inline void local_bh_disable_nort(void) { local_bh_disable(); } + static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } + static void ksoftirqd_set_sched_params(unsigned int cpu) { } +-static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } + + #else /* !PREEMPT_RT_FULL */ + +@@ -640,8 +654,12 @@ void thread_do_softirq(void) + + static void do_raise_softirq_irqoff(unsigned int nr) + { ++ unsigned int mask; ++ ++ mask = 1UL << nr; ++ + trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); ++ or_softirq_pending(mask); + + /* + * If we are not in a hard interrupt and inside a bh disabled +@@ -650,16 +668,29 @@ static void do_raise_softirq_irqoff(unsigned int nr) + * delegate it to ksoftirqd. + */ + if (!in_irq() && current->softirq_nestcnt) +- current->softirqs_raised |= (1U << nr); +- else if (__this_cpu_read(ksoftirqd)) +- __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); ++ current->softirqs_raised |= mask; ++ else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd)) ++ return; ++ ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++} ++ ++static void wakeup_proper_softirq(unsigned int nr) ++{ ++ if ((1UL << nr) & TIMER_SOFTIRQS) ++ wakeup_timer_softirqd(); ++ else ++ wakeup_softirqd(); + } + + void __raise_softirq_irqoff(unsigned int nr) + { + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) +- wakeup_softirqd(); ++ wakeup_proper_softirq(nr); + } + + /* +@@ -685,7 +716,7 @@ void raise_softirq_irqoff(unsigned int nr) + * raise a WARN() if the condition is met. + */ + if (!current->softirq_nestcnt) +- wakeup_softirqd(); ++ wakeup_proper_softirq(nr); + } + + static inline int ksoftirqd_softirq_pending(void) +@@ -697,23 +728,38 @@ static inline void local_bh_disable_nort(void) { } + static inline void _local_bh_enable_nort(void) { } + + static inline void ksoftirqd_set_sched_params(unsigned int cpu) ++{ ++ /* Take over all but timer pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS; ++ local_irq_enable(); ++} ++ ++static inline void ktimer_softirqd_set_sched_params(unsigned int cpu) + { + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); +- /* Take over all pending softirqs when starting */ ++ ++ /* Take over timer pending softirqs when starting */ + local_irq_disable(); +- current->softirqs_raised = local_softirq_pending(); ++ current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS; + local_irq_enable(); + } + +-static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) ++static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu, ++ bool online) + { + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); + } + ++static int ktimer_softirqd_should_run(unsigned int cpu) ++{ ++ return current->softirqs_raised; ++} ++ + #endif /* PREEMPT_RT_FULL */ + /* + * Enter an interrupt context. +@@ -766,6 +812,9 @@ static inline void invoke_softirq(void) + if (__this_cpu_read(ksoftirqd) && + __this_cpu_read(ksoftirqd)->softirqs_raised) + wakeup_softirqd(); ++ if (__this_cpu_read(ktimer_softirqd) && ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised) ++ wakeup_timer_softirqd(); + local_irq_restore(flags); + #endif + } +@@ -1153,18 +1202,30 @@ static int takeover_tasklets(unsigned int cpu) + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, +- .cleanup = ksoftirqd_clr_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct smp_hotplug_thread softirq_timer_threads = { ++ .store = &ktimer_softirqd, ++ .setup = ktimer_softirqd_set_sched_params, ++ .cleanup = ktimer_softirqd_clr_sched_params, ++ .thread_should_run = ktimer_softirqd_should_run, ++ .thread_fn = run_ksoftirqd, ++ .thread_comm = "ktimersoftd/%u", ++}; ++#endif ++ + static __init int spawn_ksoftirqd(void) + { + cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL, + takeover_tasklets); + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); +- ++#ifdef CONFIG_PREEMPT_RT_FULL ++ BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads)); ++#endif + return 0; + } + early_initcall(spawn_ksoftirqd); +-- +2.36.1 + diff --git a/debian/patches-rt/0125-softirq-Avoid-local_softirq_pending-messages-if-ksof.patch b/debian/patches-rt/0125-softirq-Avoid-local_softirq_pending-messages-if-ksof.patch new file mode 100644 index 000000000..1302bc0ef --- /dev/null +++ b/debian/patches-rt/0125-softirq-Avoid-local_softirq_pending-messages-if-ksof.patch @@ -0,0 +1,112 @@ +From 287a0b153109b1e2d548befe904bc14f3de5f2c8 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 18 Feb 2019 13:19:59 +0100 +Subject: [PATCH 125/347] softirq: Avoid "local_softirq_pending" messages if + ksoftirqd is blocked +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +If the ksoftirqd thread has a softirq pending and is blocked on the +`local_softirq_locks' lock then softirq_check_pending_idle() won't +complain because the "lock owner" will mask away this softirq from the +mask of pending softirqs. +If ksoftirqd has an additional softirq pending then it won't be masked +out because we never look at ksoftirqd's mask. + +If there are still pending softirqs while going to idle check +ksoftirqd's and ktimersfotd's mask before complaining about unhandled +softirqs. + +Cc: stable-rt@vger.kernel.org +Tested-by: Juri Lelli <juri.lelli@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/softirq.c | 57 ++++++++++++++++++++++++++++++++++-------------- + 1 file changed, 41 insertions(+), 16 deletions(-) + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index fe4e59c80a08..1920985eeb09 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -92,6 +92,31 @@ static inline void softirq_clr_runner(unsigned int sirq) + sr->runner[sirq] = NULL; + } + ++static bool softirq_check_runner_tsk(struct task_struct *tsk, ++ unsigned int *pending) ++{ ++ bool ret = false; ++ ++ if (!tsk) ++ return ret; ++ ++ /* ++ * The wakeup code in rtmutex.c wakes up the task ++ * _before_ it sets pi_blocked_on to NULL under ++ * tsk->pi_lock. So we need to check for both: state ++ * and pi_blocked_on. ++ */ ++ raw_spin_lock(&tsk->pi_lock); ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ /* Clear all bits pending in that task */ ++ *pending &= ~(tsk->softirqs_raised); ++ ret = true; ++ } ++ raw_spin_unlock(&tsk->pi_lock); ++ ++ return ret; ++} ++ + /* + * On preempt-rt a softirq running context might be blocked on a + * lock. There might be no other runnable task on this CPU because the +@@ -104,6 +129,7 @@ static inline void softirq_clr_runner(unsigned int sirq) + */ + void softirq_check_pending_idle(void) + { ++ struct task_struct *tsk; + static int rate_limit; + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + u32 warnpending; +@@ -113,24 +139,23 @@ void softirq_check_pending_idle(void) + return; + + warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; ++ if (!warnpending) ++ return; + for (i = 0; i < NR_SOFTIRQS; i++) { +- struct task_struct *tsk = sr->runner[i]; ++ tsk = sr->runner[i]; + +- /* +- * The wakeup code in rtmutex.c wakes up the task +- * _before_ it sets pi_blocked_on to NULL under +- * tsk->pi_lock. So we need to check for both: state +- * and pi_blocked_on. +- */ +- if (tsk) { +- raw_spin_lock(&tsk->pi_lock); +- if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { +- /* Clear all bits pending in that task */ +- warnpending &= ~(tsk->softirqs_raised); +- warnpending &= ~(1 << i); +- } +- raw_spin_unlock(&tsk->pi_lock); +- } ++ if (softirq_check_runner_tsk(tsk, &warnpending)) ++ warnpending &= ~(1 << i); ++ } ++ ++ if (warnpending) { ++ tsk = __this_cpu_read(ksoftirqd); ++ softirq_check_runner_tsk(tsk, &warnpending); ++ } ++ ++ if (warnpending) { ++ tsk = __this_cpu_read(ktimer_softirqd); ++ softirq_check_runner_tsk(tsk, &warnpending); + } + + if (warnpending) { +-- +2.36.1 + diff --git a/debian/patches-rt/0126-softirq-Avoid-local_softirq_pending-messages-if-task.patch b/debian/patches-rt/0126-softirq-Avoid-local_softirq_pending-messages-if-task.patch new file mode 100644 index 000000000..965311d51 --- /dev/null +++ b/debian/patches-rt/0126-softirq-Avoid-local_softirq_pending-messages-if-task.patch @@ -0,0 +1,41 @@ +From 7879ba227dbde103356be2bef58a9733a930c0a0 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 19 Feb 2019 16:49:29 +0100 +Subject: [PATCH 126/347] softirq: Avoid "local_softirq_pending" messages if + task is in cpu_chill() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +If the softirq thread enters cpu_chill() then ->state is UNINTERRUPTIBLE +and has no ->pi_blocked_on set and so its mask is not taken into account. + +->sleeping_lock is increased by cpu_chill() since it is also requried to +avoid a splat by RCU in case cpu_chill() is used while a RCU-read lock +is held. Use the same mechanism for the softirq-pending check. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/softirq.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 1920985eeb09..27a4bb2303d0 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -105,9 +105,12 @@ static bool softirq_check_runner_tsk(struct task_struct *tsk, + * _before_ it sets pi_blocked_on to NULL under + * tsk->pi_lock. So we need to check for both: state + * and pi_blocked_on. ++ * The test against UNINTERRUPTIBLE + ->sleeping_lock is in case the ++ * task does cpu_chill(). + */ + raw_spin_lock(&tsk->pi_lock); +- if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING || ++ (tsk->state == TASK_UNINTERRUPTIBLE && tsk->sleeping_lock)) { + /* Clear all bits pending in that task */ + *pending &= ~(tsk->softirqs_raised); + ret = true; +-- +2.36.1 + diff --git a/debian/patches-rt/0127-rtmutex-trylock-is-okay-on-RT.patch b/debian/patches-rt/0127-rtmutex-trylock-is-okay-on-RT.patch new file mode 100644 index 000000000..292becc02 --- /dev/null +++ b/debian/patches-rt/0127-rtmutex-trylock-is-okay-on-RT.patch @@ -0,0 +1,34 @@ +From 0b94209cb7e2a97538d5f7cf08c0d1433cc83b05 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 2 Dec 2015 11:34:07 +0100 +Subject: [PATCH 127/347] rtmutex: trylock is okay on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +non-RT kernel could deadlock on rt_mutex_trylock() in softirq context. On +-RT we don't run softirqs in IRQ context but in thread context so it is +not a issue here. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index a5ec4f68527e..4bec24dfafc6 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1583,7 +1583,11 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) + { + int ret; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (WARN_ON_ONCE(in_irq() || in_nmi())) ++#else + if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) ++#endif + return 0; + + ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); +-- +2.36.1 + diff --git a/debian/patches-rt/0128-fs-nfs-turn-rmdir_sem-into-a-semaphore.patch b/debian/patches-rt/0128-fs-nfs-turn-rmdir_sem-into-a-semaphore.patch new file mode 100644 index 000000000..4ff90ed43 --- /dev/null +++ b/debian/patches-rt/0128-fs-nfs-turn-rmdir_sem-into-a-semaphore.patch @@ -0,0 +1,151 @@ +From dbfda01f7e6e30541e35b49f6972022917fd685a Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 15 Sep 2016 10:51:27 +0200 +Subject: [PATCH 128/347] fs/nfs: turn rmdir_sem into a semaphore +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The RW semaphore had a reader side which used the _non_owner version +because it most likely took the reader lock in one thread and released it +in another which would cause lockdep to complain if the "regular" +version was used. +On -RT we need the owner because the rw lock is turned into a rtmutex. +The semaphores on the hand are "plain simple" and should work as +expected. We can't have multiple readers but on -RT we don't allow +multiple readers anyway so that is not a loss. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/nfs/dir.c | 8 ++++++++ + fs/nfs/inode.c | 4 ++++ + fs/nfs/unlink.c | 31 +++++++++++++++++++++++++++---- + include/linux/nfs_fs.h | 4 ++++ + 4 files changed, 43 insertions(+), 4 deletions(-) + +diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c +index 10bc04af2882..4999bd148491 100644 +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -1857,7 +1857,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) + + trace_nfs_rmdir_enter(dir, dentry); + if (d_really_is_positive(dentry)) { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ down(&NFS_I(d_inode(dentry))->rmdir_sem); ++#else + down_write(&NFS_I(d_inode(dentry))->rmdir_sem); ++#endif + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + /* Ensure the VFS deletes this inode */ + switch (error) { +@@ -1867,7 +1871,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) + case -ENOENT: + nfs_dentry_handle_enoent(dentry); + } ++#ifdef CONFIG_PREEMPT_RT_BASE ++ up(&NFS_I(d_inode(dentry))->rmdir_sem); ++#else + up_write(&NFS_I(d_inode(dentry))->rmdir_sem); ++#endif + } else + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + trace_nfs_rmdir_exit(dir, dentry, error); +diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c +index 592b95ab378b..4fc14fb50068 100644 +--- a/fs/nfs/inode.c ++++ b/fs/nfs/inode.c +@@ -2105,7 +2105,11 @@ static void init_once(void *foo) + atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->commit_info.ncommit, 0); + atomic_set(&nfsi->commit_info.rpcs_out, 0); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ sema_init(&nfsi->rmdir_sem, 1); ++#else + init_rwsem(&nfsi->rmdir_sem); ++#endif + mutex_init(&nfsi->commit_mutex); + nfs4_init_once(nfsi); + } +diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c +index fd61bf0fce63..ce9100b5604d 100644 +--- a/fs/nfs/unlink.c ++++ b/fs/nfs/unlink.c +@@ -52,6 +52,29 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) + rpc_restart_call_prepare(task); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void nfs_down_anon(struct semaphore *sema) ++{ ++ down(sema); ++} ++ ++static void nfs_up_anon(struct semaphore *sema) ++{ ++ up(sema); ++} ++ ++#else ++static void nfs_down_anon(struct rw_semaphore *rwsem) ++{ ++ down_read_non_owner(rwsem); ++} ++ ++static void nfs_up_anon(struct rw_semaphore *rwsem) ++{ ++ up_read_non_owner(rwsem); ++} ++#endif ++ + /** + * nfs_async_unlink_release - Release the sillydelete data. + * @task: rpc_task of the sillydelete +@@ -65,7 +88,7 @@ static void nfs_async_unlink_release(void *calldata) + struct dentry *dentry = data->dentry; + struct super_block *sb = dentry->d_sb; + +- up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); ++ nfs_up_anon(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); + d_lookup_done(dentry); + nfs_free_unlinkdata(data); + dput(dentry); +@@ -118,10 +141,10 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf + struct inode *dir = d_inode(dentry->d_parent); + struct dentry *alias; + +- down_read_non_owner(&NFS_I(dir)->rmdir_sem); ++ nfs_down_anon(&NFS_I(dir)->rmdir_sem); + alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq); + if (IS_ERR(alias)) { +- up_read_non_owner(&NFS_I(dir)->rmdir_sem); ++ nfs_up_anon(&NFS_I(dir)->rmdir_sem); + return 0; + } + if (!d_in_lookup(alias)) { +@@ -143,7 +166,7 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf + ret = 0; + spin_unlock(&alias->d_lock); + dput(alias); +- up_read_non_owner(&NFS_I(dir)->rmdir_sem); ++ nfs_up_anon(&NFS_I(dir)->rmdir_sem); + /* + * If we'd displaced old cached devname, free it. At that + * point dentry is definitely not a root, so we won't need +diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h +index 8ea7ceed8285..d52dfae05d2a 100644 +--- a/include/linux/nfs_fs.h ++++ b/include/linux/nfs_fs.h +@@ -164,7 +164,11 @@ struct nfs_inode { + + /* Readers: in-flight sillydelete RPC calls */ + /* Writers: rmdir */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct semaphore rmdir_sem; ++#else + struct rw_semaphore rmdir_sem; ++#endif + struct mutex commit_mutex; + + #if IS_ENABLED(CONFIG_NFS_V4) +-- +2.36.1 + diff --git a/debian/patches-rt/0129-rtmutex-Handle-the-various-new-futex-race-conditions.patch b/debian/patches-rt/0129-rtmutex-Handle-the-various-new-futex-race-conditions.patch new file mode 100644 index 000000000..bdf75c3c6 --- /dev/null +++ b/debian/patches-rt/0129-rtmutex-Handle-the-various-new-futex-race-conditions.patch @@ -0,0 +1,254 @@ +From 9c83cf8ce7911f4f00f4fc71b365a30ebed5fdf4 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 10 Jun 2011 11:04:15 +0200 +Subject: [PATCH 129/347] rtmutex: Handle the various new futex race conditions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +RT opens a few new interesting race conditions in the rtmutex/futex +combo due to futex hash bucket lock being a 'sleeping' spinlock and +therefor not disabling preemption. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/futex.c | 77 ++++++++++++++++++++++++++------- + kernel/locking/rtmutex.c | 36 ++++++++++++--- + kernel/locking/rtmutex_common.h | 2 + + 3 files changed, 94 insertions(+), 21 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index ac015d1dd16c..dc2d81d11b17 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2253,6 +2253,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; ++ } else if (ret == -EAGAIN) { ++ /* ++ * Waiter was woken by timeout or ++ * signal and has set pi_blocked_on to ++ * PI_WAKEUP_INPROGRESS before we ++ * tried to enqueue it on the rtmutex. ++ */ ++ this->pi_state = NULL; ++ put_pi_state(pi_state); ++ continue; + } else if (ret) { + /* + * rt_mutex_start_proxy_lock() detected a +@@ -3331,7 +3341,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + { + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; +- struct futex_hash_bucket *hb; ++ struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -3389,20 +3399,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- spin_lock(&hb->lock); +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; ++ /* ++ * On RT we must avoid races with requeue and trying to block ++ * on two mutexes (hb->lock and uaddr2's rtmutex) by ++ * serializing access to pi_blocked_on with pi_lock. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ if (current->pi_blocked_on) { ++ /* ++ * We have been requeued or are in the process of ++ * being requeued. ++ */ ++ raw_spin_unlock_irq(¤t->pi_lock); ++ } else { ++ /* ++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS ++ * prevents a concurrent requeue from moving us to the ++ * uaddr2 rtmutex. After that we can safely acquire ++ * (and possibly block on) hb->lock. ++ */ ++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ spin_lock(&hb->lock); ++ ++ /* ++ * Clean up pi_blocked_on. We might leak it otherwise ++ * when we succeeded with the hb->lock in the fast ++ * path. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ current->pi_blocked_on = NULL; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; ++ } + + /* +- * In order for us to be here, we know our q.key == key2, and since +- * we took the hb->lock above, we also know that futex_requeue() has +- * completed and we no longer have to concern ourselves with a wakeup +- * race with the atomic proxy lock acquisition by the requeue code. The +- * futex_requeue dropped our key1 reference and incremented our key2 +- * reference count. ++ * In order to be here, we have either been requeued, are in ++ * the process of being requeued, or requeue successfully ++ * acquired uaddr2 on our behalf. If pi_blocked_on was ++ * non-null above, we may be racing with a requeue. Do not ++ * rely on q->lock_ptr to be hb2->lock until after blocking on ++ * hb->lock or hb2->lock. The futex_requeue dropped our key1 ++ * reference and incremented our key2 reference count. + */ ++ hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -3411,14 +3456,15 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + put_pi_state(q.pi_state); +- spin_unlock(q.lock_ptr); ++ spin_unlock(&hb2->lock); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. +@@ -3437,7 +3483,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + pi_mutex = &q.pi_state->pi_mutex; + ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); + +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) + ret = 0; + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 4bec24dfafc6..9d472eb48ba7 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -135,6 +135,11 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } + ++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) ++{ ++ return waiter && waiter != PI_WAKEUP_INPROGRESS; ++} ++ + /* + * We can speed up the acquire/release, if there's no debugging state to be + * set up. +@@ -379,7 +384,8 @@ int max_lock_depth = 1024; + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; ++ return rt_mutex_real_waiter(p->pi_blocked_on) ? ++ p->pi_blocked_on->lock : NULL; + } + + /* +@@ -515,7 +521,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!waiter) ++ if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* +@@ -951,6 +957,22 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + return -EDEADLK; + + raw_spin_lock(&task->pi_lock); ++ /* ++ * In the case of futex requeue PI, this will be a proxy ++ * lock. The task will wake unaware that it is enqueueed on ++ * this lock. Avoid blocking on two locks and corrupting ++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS ++ * flag. futex_wait_requeue_pi() sets this when it wakes up ++ * before requeue (due to a signal or timeout). Do not enqueue ++ * the task if PI_WAKEUP_INPROGRESS is set. ++ */ ++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ ++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); ++ + waiter->task = task; + waiter->lock = lock; + waiter->prio = task->prio; +@@ -974,7 +996,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + rt_mutex_enqueue_pi(owner, waiter); + + rt_mutex_adjust_prio(owner); +- if (owner->pi_blocked_on) ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -1070,7 +1092,7 @@ static void remove_waiter(struct rt_mutex *lock, + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock; ++ struct rt_mutex *next_lock = NULL; + + lockdep_assert_held(&lock->wait_lock); + +@@ -1096,7 +1118,8 @@ static void remove_waiter(struct rt_mutex *lock, + rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- next_lock = task_blocked_on_lock(owner); ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock(&owner->pi_lock); + +@@ -1132,7 +1155,8 @@ void rt_mutex_adjust_pi(struct task_struct *task) + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { ++ if (!rt_mutex_real_waiter(waiter) || ++ rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index ca6fb489007b..8f39bc139735 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -130,6 +130,8 @@ enum rtmutex_chainwalk { + /* + * PI-futex support (proxy locking functions, etc.): + */ ++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++ + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); +-- +2.36.1 + diff --git a/debian/patches-rt/0130-futex-Fix-bug-on-when-a-requeued-RT-task-times-out.patch b/debian/patches-rt/0130-futex-Fix-bug-on-when-a-requeued-RT-task-times-out.patch new file mode 100644 index 000000000..1b73b4e00 --- /dev/null +++ b/debian/patches-rt/0130-futex-Fix-bug-on-when-a-requeued-RT-task-times-out.patch @@ -0,0 +1,121 @@ +From e4bd34c056ee1cfe80dbe490977b5496ba5eeb70 Mon Sep 17 00:00:00 2001 +From: Steven Rostedt <rostedt@goodmis.org> +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: [PATCH 130/347] futex: Fix bug on when a requeued RT task times out +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Requeue with timeout causes a bug with PREEMPT_RT_FULL. + +The bug comes from a timed out condition. + + + TASK 1 TASK 2 + ------ ------ + futex_wait_requeue_pi() + futex_wait_queue_me() + <timed out> + + double_lock_hb(); + + raw_spin_lock(pi_lock); + if (current->pi_blocked_on) { + } else { + current->pi_blocked_on = PI_WAKE_INPROGRESS; + run_spin_unlock(pi_lock); + spin_lock(hb->lock); <-- blocked! + + + plist_for_each_entry_safe(this) { + rt_mutex_start_proxy_lock(); + task_blocks_on_rt_mutex(); + BUG_ON(task->pi_blocked_on)!!!! + +The BUG_ON() actually has a check for PI_WAKE_INPROGRESS, but the +problem is that, after TASK 1 sets PI_WAKE_INPROGRESS, it then tries to +grab the hb->lock, which it fails to do so. As the hb->lock is a mutex, +it will block and set the "pi_blocked_on" to the hb->lock. + +When TASK 2 goes to requeue it, the check for PI_WAKE_INPROGESS fails +because the task1's pi_blocked_on is no longer set to that, but instead, +set to the hb->lock. + +The fix: + +When calling rt_mutex_start_proxy_lock() a check is made to see +if the proxy tasks pi_blocked_on is set. If so, exit out early. +Otherwise set it to a new flag PI_REQUEUE_INPROGRESS, which notifies +the proxy task that it is being requeued, and will handle things +appropriately. + + +Signed-off-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/locking/rtmutex.c | 31 ++++++++++++++++++++++++++++++- + kernel/locking/rtmutex_common.h | 1 + + 2 files changed, 31 insertions(+), 1 deletion(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 9d472eb48ba7..069f025180b8 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -137,7 +137,8 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) + + static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) + { +- return waiter && waiter != PI_WAKEUP_INPROGRESS; ++ return waiter && waiter != PI_WAKEUP_INPROGRESS && ++ waiter != PI_REQUEUE_INPROGRESS; + } + + /* +@@ -1783,6 +1784,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + if (try_to_take_rt_mutex(lock, task, NULL)) + return 1; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * In PREEMPT_RT there's an added race. ++ * If the task, that we are about to requeue, times out, ++ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue ++ * to skip this task. But right after the task sets ++ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then ++ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. ++ * This will replace the PI_WAKEUP_INPROGRESS with the actual ++ * lock that it blocks on. We *must not* place this task ++ * on this proxy lock in that case. ++ * ++ * To prevent this race, we first take the task's pi_lock ++ * and check if it has updated its pi_blocked_on. If it has, ++ * we assume that it woke up and we return -EAGAIN. ++ * Otherwise, we set the task's pi_blocked_on to ++ * PI_REQUEUE_INPROGRESS, so that if the task is waking up ++ * it will know that we are in the process of requeuing it. ++ */ ++ raw_spin_lock(&task->pi_lock); ++ if (task->pi_blocked_on) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; ++ raw_spin_unlock(&task->pi_lock); ++#endif ++ + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 8f39bc139735..202e2b0d1251 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -131,6 +131,7 @@ enum rtmutex_chainwalk { + * PI-futex support (proxy locking functions, etc.): + */ + #define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, +-- +2.36.1 + diff --git a/debian/patches-rt/0131-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch b/debian/patches-rt/0131-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch new file mode 100644 index 000000000..385cbe279 --- /dev/null +++ b/debian/patches-rt/0131-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch @@ -0,0 +1,50 @@ +From be3ec67dc13250ace8bd04c65a4fb643d683c9c1 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 1 Mar 2013 11:17:42 +0100 +Subject: [PATCH 131/347] futex: Ensure lock/unlock symetry versus pi_lock and + hash bucket lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In exit_pi_state_list() we have the following locking construct: + + spin_lock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); + + ... + spin_unlock(&hb->lock); + +In !RT this works, but on RT the migrate_enable() function which is +called from spin_unlock() sees atomic context due to the held pi_lock +and just decrements the migrate_disable_atomic counter of the +task. Now the next call to migrate_disable() sees the counter being +negative and issues a warning. That check should be in +migrate_enable() already. + +Fix this by dropping pi_lock before unlocking hb->lock and reaquire +pi_lock after that again. This is safe as the loop code reevaluates +head again under the pi_lock. + +Reported-by: Yong Zhang <yong.zhang@windriver.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/futex.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/kernel/futex.c b/kernel/futex.c +index dc2d81d11b17..0e136045a720 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -962,7 +962,9 @@ static void exit_pi_state_list(struct task_struct *curr) + if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); ++ raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); ++ raw_spin_lock_irq(&curr->pi_lock); + put_pi_state(pi_state); + continue; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0132-pid.h-include-atomic.h.patch b/debian/patches-rt/0132-pid.h-include-atomic.h.patch new file mode 100644 index 000000000..74e014526 --- /dev/null +++ b/debian/patches-rt/0132-pid.h-include-atomic.h.patch @@ -0,0 +1,43 @@ +From 4893375573fc1c881fe9d5f74f5c3199a8adafd7 Mon Sep 17 00:00:00 2001 +From: Grygorii Strashko <Grygorii.Strashko@linaro.org> +Date: Tue, 21 Jul 2015 19:43:56 +0300 +Subject: [PATCH 132/347] pid.h: include atomic.h +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +This patch fixes build error: + CC kernel/pid_namespace.o +In file included from kernel/pid_namespace.c:11:0: +include/linux/pid.h: In function 'get_pid': +include/linux/pid.h:78:3: error: implicit declaration of function 'atomic_inc' [-Werror=implicit-function-declaration] + atomic_inc(&pid->count); + ^ +which happens when + CONFIG_PROVE_LOCKING=n + CONFIG_DEBUG_SPINLOCK=n + CONFIG_DEBUG_MUTEXES=n + CONFIG_DEBUG_LOCK_ALLOC=n + CONFIG_PID_NS=y + +Vanilla gets this via spinlock.h. + +Signed-off-by: Grygorii Strashko <Grygorii.Strashko@linaro.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/pid.h | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/include/linux/pid.h b/include/linux/pid.h +index 14a9a39da9c7..a9026a5da196 100644 +--- a/include/linux/pid.h ++++ b/include/linux/pid.h +@@ -3,6 +3,7 @@ + #define _LINUX_PID_H + + #include <linux/rculist.h> ++#include <linux/atomic.h> + + enum pid_type + { +-- +2.36.1 + diff --git a/debian/patches-rt/0133-arm-include-definition-for-cpumask_t.patch b/debian/patches-rt/0133-arm-include-definition-for-cpumask_t.patch new file mode 100644 index 000000000..770c1d0d6 --- /dev/null +++ b/debian/patches-rt/0133-arm-include-definition-for-cpumask_t.patch @@ -0,0 +1,31 @@ +From 83a90ab3e2bccc269afe608919d57872e41d3518 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 22 Dec 2016 17:28:33 +0100 +Subject: [PATCH 133/347] arm: include definition for cpumask_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +This definition gets pulled in by other files. With the (later) split of +RCU and spinlock.h it won't compile anymore. +The split is done in ("rbtree: don't include the rcu header"). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/include/asm/irq.h | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h +index 46d41140df27..c421b5b81946 100644 +--- a/arch/arm/include/asm/irq.h ++++ b/arch/arm/include/asm/irq.h +@@ -23,6 +23,8 @@ + #endif + + #ifndef __ASSEMBLY__ ++#include <linux/cpumask.h> ++ + struct irqaction; + struct pt_regs; + +-- +2.36.1 + diff --git a/debian/patches-rt/0134-locking-locktorture-Do-NOT-include-rwlock.h-directly.patch b/debian/patches-rt/0134-locking-locktorture-Do-NOT-include-rwlock.h-directly.patch new file mode 100644 index 000000000..2777ffd6a --- /dev/null +++ b/debian/patches-rt/0134-locking-locktorture-Do-NOT-include-rwlock.h-directly.patch @@ -0,0 +1,34 @@ +From 651a6a4d30c878862e8ba912da5d7140d5e23a6e Mon Sep 17 00:00:00 2001 +From: "Wolfgang M. Reimer" <linuxball@gmail.com> +Date: Tue, 21 Jul 2015 16:20:07 +0200 +Subject: [PATCH 134/347] locking: locktorture: Do NOT include rwlock.h + directly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Including rwlock.h directly will cause kernel builds to fail +if CONFIG_PREEMPT_RT_FULL is defined. The correct header file +(rwlock_rt.h OR rwlock.h) will be included by spinlock.h which +is included by locktorture.c anyway. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Wolfgang M. Reimer <linuxball@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/locktorture.c | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c +index 95395ef5922a..5748c1936edb 100644 +--- a/kernel/locking/locktorture.c ++++ b/kernel/locking/locktorture.c +@@ -29,7 +29,6 @@ + #include <linux/kthread.h> + #include <linux/sched/rt.h> + #include <linux/spinlock.h> +-#include <linux/rwlock.h> + #include <linux/mutex.h> + #include <linux/rwsem.h> + #include <linux/smp.h> +-- +2.36.1 + diff --git a/debian/patches-rt/0135-rtmutex-Add-rtmutex_lock_killable.patch b/debian/patches-rt/0135-rtmutex-Add-rtmutex_lock_killable.patch new file mode 100644 index 000000000..92652b7a1 --- /dev/null +++ b/debian/patches-rt/0135-rtmutex-Add-rtmutex_lock_killable.patch @@ -0,0 +1,60 @@ +From 12727f37858de62d47250dc9fcee2ce4ea19dd66 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 9 Jun 2011 11:43:52 +0200 +Subject: [PATCH 135/347] rtmutex: Add rtmutex_lock_killable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Add "killable" type to rtmutex. We need this since rtmutex are used as +"normal" mutexes which do use this type. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/rtmutex.h | 1 + + kernel/locking/rtmutex.c | 19 +++++++++++++++++++ + 2 files changed, 20 insertions(+) + +diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h +index 6fd615a0eea9..81ece6a8291a 100644 +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -115,6 +115,7 @@ extern void rt_mutex_lock(struct rt_mutex *lock); + #endif + + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); ++extern int rt_mutex_lock_killable(struct rt_mutex *lock); + extern int rt_mutex_timed_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *timeout); + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 069f025180b8..81bae2e3d82e 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1562,6 +1562,25 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) + return __rt_mutex_slowtrylock(lock); + } + ++/** ++ * rt_mutex_lock_killable - lock a rt_mutex killable ++ * ++ * @lock: the rt_mutex to be locked ++ * @detect_deadlock: deadlock detection on/off ++ * ++ * Returns: ++ * 0 on success ++ * -EINTR when interrupted by a signal ++ * -EDEADLK when the lock would deadlock (when deadlock detection is on) ++ */ ++int __sched rt_mutex_lock_killable(struct rt_mutex *lock) ++{ ++ might_sleep(); ++ ++ return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++} ++EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); ++ + /** + * rt_mutex_timed_lock - lock a rt_mutex interruptible + * the timeout structure is provided +-- +2.36.1 + diff --git a/debian/patches-rt/0136-rtmutex-Make-lock_killable-work.patch b/debian/patches-rt/0136-rtmutex-Make-lock_killable-work.patch new file mode 100644 index 000000000..605d0286e --- /dev/null +++ b/debian/patches-rt/0136-rtmutex-Make-lock_killable-work.patch @@ -0,0 +1,51 @@ +From 36064ed74738cac8ebb382e5ce34d55a8f2e24a8 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sat, 1 Apr 2017 12:50:59 +0200 +Subject: [PATCH 136/347] rtmutex: Make lock_killable work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Locking an rt mutex killable does not work because signal handling is +restricted to TASK_INTERRUPTIBLE. + +Use signal_pending_state() unconditionaly. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 19 +++++++------------ + 1 file changed, 7 insertions(+), 12 deletions(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 81bae2e3d82e..333c4b7aa8e8 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1201,18 +1201,13 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, + if (try_to_take_rt_mutex(lock, current, waiter)) + break; + +- /* +- * TASK_INTERRUPTIBLE checks for signals and +- * timeout. Ignored otherwise. +- */ +- if (likely(state == TASK_INTERRUPTIBLE)) { +- /* Signal pending? */ +- if (signal_pending(current)) +- ret = -EINTR; +- if (timeout && !timeout->task) +- ret = -ETIMEDOUT; +- if (ret) +- break; ++ if (timeout && !timeout->task) { ++ ret = -ETIMEDOUT; ++ break; ++ } ++ if (signal_pending_state(state, current)) { ++ ret = -EINTR; ++ break; + } + + raw_spin_unlock_irq(&lock->wait_lock); +-- +2.36.1 + diff --git a/debian/patches-rt/0137-spinlock-Split-the-lock-types-header.patch b/debian/patches-rt/0137-spinlock-Split-the-lock-types-header.patch new file mode 100644 index 000000000..472048028 --- /dev/null +++ b/debian/patches-rt/0137-spinlock-Split-the-lock-types-header.patch @@ -0,0 +1,221 @@ +From ea56713a6d4b07d5d16d350f989ea6e4575feb41 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 29 Jun 2011 19:34:01 +0200 +Subject: [PATCH 137/347] spinlock: Split the lock types header +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Split raw_spinlock into its own file and the remaining spinlock_t into +its own non-RT header. The non-RT header will be replaced later by sleeping +spinlocks. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/rwlock_types.h | 4 ++ + include/linux/spinlock_types.h | 71 +---------------------------- + include/linux/spinlock_types_nort.h | 33 ++++++++++++++ + include/linux/spinlock_types_raw.h | 55 ++++++++++++++++++++++ + 4 files changed, 94 insertions(+), 69 deletions(-) + create mode 100644 include/linux/spinlock_types_nort.h + create mode 100644 include/linux/spinlock_types_raw.h + +diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h +index 857a72ceb794..c21683f3e14a 100644 +--- a/include/linux/rwlock_types.h ++++ b/include/linux/rwlock_types.h +@@ -1,6 +1,10 @@ + #ifndef __LINUX_RWLOCK_TYPES_H + #define __LINUX_RWLOCK_TYPES_H + ++#if !defined(__LINUX_SPINLOCK_TYPES_H) ++# error "Do not include directly, include spinlock_types.h" ++#endif ++ + /* + * include/linux/rwlock_types.h - generic rwlock type definitions + * and initializers +diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h +index 24b4e6f2c1a2..5c8664d57fb8 100644 +--- a/include/linux/spinlock_types.h ++++ b/include/linux/spinlock_types.h +@@ -9,76 +9,9 @@ + * Released under the General Public License (GPL). + */ + +-#if defined(CONFIG_SMP) +-# include <asm/spinlock_types.h> +-#else +-# include <linux/spinlock_types_up.h> +-#endif ++#include <linux/spinlock_types_raw.h> + +-#include <linux/lockdep.h> +- +-typedef struct raw_spinlock { +- arch_spinlock_t raw_lock; +-#ifdef CONFIG_DEBUG_SPINLOCK +- unsigned int magic, owner_cpu; +- void *owner; +-#endif +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +- struct lockdep_map dep_map; +-#endif +-} raw_spinlock_t; +- +-#define SPINLOCK_MAGIC 0xdead4ead +- +-#define SPINLOCK_OWNER_INIT ((void *)-1L) +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +-#else +-# define SPIN_DEP_MAP_INIT(lockname) +-#endif +- +-#ifdef CONFIG_DEBUG_SPINLOCK +-# define SPIN_DEBUG_INIT(lockname) \ +- .magic = SPINLOCK_MAGIC, \ +- .owner_cpu = -1, \ +- .owner = SPINLOCK_OWNER_INIT, +-#else +-# define SPIN_DEBUG_INIT(lockname) +-#endif +- +-#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +- { \ +- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ +- SPIN_DEBUG_INIT(lockname) \ +- SPIN_DEP_MAP_INIT(lockname) } +- +-#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ +- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +- +-typedef struct spinlock { +- union { +- struct raw_spinlock rlock; +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) +- struct { +- u8 __padding[LOCK_PADSIZE]; +- struct lockdep_map dep_map; +- }; +-#endif +- }; +-} spinlock_t; +- +-#define __SPIN_LOCK_INITIALIZER(lockname) \ +- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } +- +-#define __SPIN_LOCK_UNLOCKED(lockname) \ +- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++#include <linux/spinlock_types_nort.h> + + #include <linux/rwlock_types.h> + +diff --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h +new file mode 100644 +index 000000000000..f1dac1fb1d6a +--- /dev/null ++++ b/include/linux/spinlock_types_nort.h +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_NORT_H ++#define __LINUX_SPINLOCK_TYPES_NORT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * The non RT version maps spinlocks to raw_spinlocks ++ */ ++typedef struct spinlock { ++ union { ++ struct raw_spinlock rlock; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) ++ struct { ++ u8 __padding[LOCK_PADSIZE]; ++ struct lockdep_map dep_map; ++ }; ++#endif ++ }; ++} spinlock_t; ++ ++#define __SPIN_LOCK_INITIALIZER(lockname) \ ++ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } ++ ++#define __SPIN_LOCK_UNLOCKED(lockname) \ ++ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++ ++#endif +diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h +new file mode 100644 +index 000000000000..822bf64a61d3 +--- /dev/null ++++ b/include/linux/spinlock_types_raw.h +@@ -0,0 +1,55 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RAW_H ++#define __LINUX_SPINLOCK_TYPES_RAW_H ++ ++#include <linux/types.h> ++ ++#if defined(CONFIG_SMP) ++# include <asm/spinlock_types.h> ++#else ++# include <linux/spinlock_types_up.h> ++#endif ++ ++#include <linux/lockdep.h> ++ ++typedef struct raw_spinlock { ++ arch_spinlock_t raw_lock; ++#ifdef CONFIG_DEBUG_SPINLOCK ++ unsigned int magic, owner_cpu; ++ void *owner; ++#endif ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} raw_spinlock_t; ++ ++#define SPINLOCK_MAGIC 0xdead4ead ++ ++#define SPINLOCK_OWNER_INIT ((void *)-1L) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define SPIN_DEP_MAP_INIT(lockname) ++#endif ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define SPIN_DEBUG_INIT(lockname) \ ++ .magic = SPINLOCK_MAGIC, \ ++ .owner_cpu = -1, \ ++ .owner = SPINLOCK_OWNER_INIT, ++#else ++# define SPIN_DEBUG_INIT(lockname) ++#endif ++ ++#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ ++ { \ ++ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ ++ SPIN_DEBUG_INIT(lockname) \ ++ SPIN_DEP_MAP_INIT(lockname) } ++ ++#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ ++ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) ++ ++#endif +-- +2.36.1 + diff --git a/debian/patches-rt/0138-rtmutex-Avoid-include-hell.patch b/debian/patches-rt/0138-rtmutex-Avoid-include-hell.patch new file mode 100644 index 000000000..7ffdecc51 --- /dev/null +++ b/debian/patches-rt/0138-rtmutex-Avoid-include-hell.patch @@ -0,0 +1,30 @@ +From b243e04054c677bb38c429d31e62f64af1db11fe Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 29 Jun 2011 20:06:39 +0200 +Subject: [PATCH 138/347] rtmutex: Avoid include hell +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Include only the required raw types. This avoids pulling in the +complete spinlock header which in turn requires rtmutex.h at some point. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/rtmutex.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h +index 81ece6a8291a..a355289b1fa1 100644 +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -15,7 +15,7 @@ + + #include <linux/linkage.h> + #include <linux/rbtree.h> +-#include <linux/spinlock_types.h> ++#include <linux/spinlock_types_raw.h> + + extern int max_lock_depth; /* for sysctl */ + +-- +2.36.1 + diff --git a/debian/patches-rt/0139-rbtree-don-t-include-the-rcu-header.patch b/debian/patches-rt/0139-rbtree-don-t-include-the-rcu-header.patch new file mode 100644 index 000000000..e300e5d34 --- /dev/null +++ b/debian/patches-rt/0139-rbtree-don-t-include-the-rcu-header.patch @@ -0,0 +1,175 @@ +From 5bd4fe94ce198734cd4b23d3486b154486f137ae Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 26 Feb 2019 16:56:02 +0100 +Subject: [PATCH 139/347] rbtree: don't include the rcu header +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The RCU header pulls in spinlock.h and fails due not yet defined types: + +|In file included from include/linux/spinlock.h:275:0, +| from include/linux/rcupdate.h:38, +| from include/linux/rbtree.h:34, +| from include/linux/rtmutex.h:17, +| from include/linux/spinlock_types.h:18, +| from kernel/bounds.c:13: +|include/linux/rwlock_rt.h:16:38: error: unknown type name ‘rwlock_t’ +| extern void __lockfunc rt_write_lock(rwlock_t *rwlock); +| ^ + +This patch moves the required RCU function from the rcupdate.h header file into +a new header file which can be included by both users. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/rbtree.h | 2 +- + include/linux/rcu_assign_pointer.h | 54 ++++++++++++++++++++++++++++++ + include/linux/rcupdate.h | 49 +-------------------------- + 3 files changed, 56 insertions(+), 49 deletions(-) + create mode 100644 include/linux/rcu_assign_pointer.h + +diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h +index fcbeed4053ef..2aa2aec354c2 100644 +--- a/include/linux/rbtree.h ++++ b/include/linux/rbtree.h +@@ -31,7 +31,7 @@ + + #include <linux/kernel.h> + #include <linux/stddef.h> +-#include <linux/rcupdate.h> ++#include <linux/rcu_assign_pointer.h> + + struct rb_node { + unsigned long __rb_parent_color; +diff --git a/include/linux/rcu_assign_pointer.h b/include/linux/rcu_assign_pointer.h +new file mode 100644 +index 000000000000..7066962a4379 +--- /dev/null ++++ b/include/linux/rcu_assign_pointer.h +@@ -0,0 +1,54 @@ ++#ifndef __LINUX_RCU_ASSIGN_POINTER_H__ ++#define __LINUX_RCU_ASSIGN_POINTER_H__ ++#include <linux/compiler.h> ++#include <asm/barrier.h> ++ ++/** ++ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable ++ * @v: The value to statically initialize with. ++ */ ++#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) ++ ++/** ++ * rcu_assign_pointer() - assign to RCU-protected pointer ++ * @p: pointer to assign to ++ * @v: value to assign (publish) ++ * ++ * Assigns the specified value to the specified RCU-protected ++ * pointer, ensuring that any concurrent RCU readers will see ++ * any prior initialization. ++ * ++ * Inserts memory barriers on architectures that require them ++ * (which is most of them), and also prevents the compiler from ++ * reordering the code that initializes the structure after the pointer ++ * assignment. More importantly, this call documents which pointers ++ * will be dereferenced by RCU read-side code. ++ * ++ * In some special cases, you may use RCU_INIT_POINTER() instead ++ * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due ++ * to the fact that it does not constrain either the CPU or the compiler. ++ * That said, using RCU_INIT_POINTER() when you should have used ++ * rcu_assign_pointer() is a very bad thing that results in ++ * impossible-to-diagnose memory corruption. So please be careful. ++ * See the RCU_INIT_POINTER() comment header for details. ++ * ++ * Note that rcu_assign_pointer() evaluates each of its arguments only ++ * once, appearances notwithstanding. One of the "extra" evaluations ++ * is in typeof() and the other visible only to sparse (__CHECKER__), ++ * neither of which actually execute the argument. As with most cpp ++ * macros, this execute-arguments-only-once property is important, so ++ * please be careful when making changes to rcu_assign_pointer() and the ++ * other macros that it invokes. ++ */ ++#define rcu_assign_pointer(p, v) \ ++({ \ ++ uintptr_t _r_a_p__v = (uintptr_t)(v); \ ++ \ ++ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ ++ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ ++ else \ ++ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ ++ _r_a_p__v; \ ++}) ++ ++#endif +diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h +index 027c58cdbb6e..e6733d7911e9 100644 +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -42,6 +42,7 @@ + #include <linux/lockdep.h> + #include <asm/processor.h> + #include <linux/cpumask.h> ++#include <linux/rcu_assign_pointer.h> + + #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) + #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) +@@ -369,54 +370,6 @@ static inline void rcu_preempt_sleep_check(void) { } + ((typeof(*p) __force __kernel *)(________p1)); \ + }) + +-/** +- * RCU_INITIALIZER() - statically initialize an RCU-protected global variable +- * @v: The value to statically initialize with. +- */ +-#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) +- +-/** +- * rcu_assign_pointer() - assign to RCU-protected pointer +- * @p: pointer to assign to +- * @v: value to assign (publish) +- * +- * Assigns the specified value to the specified RCU-protected +- * pointer, ensuring that any concurrent RCU readers will see +- * any prior initialization. +- * +- * Inserts memory barriers on architectures that require them +- * (which is most of them), and also prevents the compiler from +- * reordering the code that initializes the structure after the pointer +- * assignment. More importantly, this call documents which pointers +- * will be dereferenced by RCU read-side code. +- * +- * In some special cases, you may use RCU_INIT_POINTER() instead +- * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due +- * to the fact that it does not constrain either the CPU or the compiler. +- * That said, using RCU_INIT_POINTER() when you should have used +- * rcu_assign_pointer() is a very bad thing that results in +- * impossible-to-diagnose memory corruption. So please be careful. +- * See the RCU_INIT_POINTER() comment header for details. +- * +- * Note that rcu_assign_pointer() evaluates each of its arguments only +- * once, appearances notwithstanding. One of the "extra" evaluations +- * is in typeof() and the other visible only to sparse (__CHECKER__), +- * neither of which actually execute the argument. As with most cpp +- * macros, this execute-arguments-only-once property is important, so +- * please be careful when making changes to rcu_assign_pointer() and the +- * other macros that it invokes. +- */ +-#define rcu_assign_pointer(p, v) \ +-({ \ +- uintptr_t _r_a_p__v = (uintptr_t)(v); \ +- \ +- if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ +- WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ +- else \ +- smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ +- _r_a_p__v; \ +-}) +- + /** + * rcu_swap_protected() - swap an RCU and a regular pointer + * @rcu_ptr: RCU pointer +-- +2.36.1 + diff --git a/debian/patches-rt/0140-rtmutex-Provide-rt_mutex_slowlock_locked.patch b/debian/patches-rt/0140-rtmutex-Provide-rt_mutex_slowlock_locked.patch new file mode 100644 index 000000000..d63649047 --- /dev/null +++ b/debian/patches-rt/0140-rtmutex-Provide-rt_mutex_slowlock_locked.patch @@ -0,0 +1,145 @@ +From 2263182a5f18a0abbe7ba2d582f42308580bbd31 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 16:14:22 +0200 +Subject: [PATCH 140/347] rtmutex: Provide rt_mutex_slowlock_locked() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +This is the inner-part of rt_mutex_slowlock(), required for rwsem-rt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 67 +++++++++++++++++++-------------- + kernel/locking/rtmutex_common.h | 7 ++++ + 2 files changed, 45 insertions(+), 29 deletions(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 333c4b7aa8e8..e9255b28de8f 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1244,35 +1244,16 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock, + } + } + +-/* +- * Slow path lock function: +- */ +-static int __sched +-rt_mutex_slowlock(struct rt_mutex *lock, int state, +- struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk, ++ struct rt_mutex_waiter *waiter) + { +- struct rt_mutex_waiter waiter; +- unsigned long flags; +- int ret = 0; +- +- rt_mutex_init_waiter(&waiter); +- +- /* +- * Technically we could use raw_spin_[un]lock_irq() here, but this can +- * be called in early boot if the cmpxchg() fast path is disabled +- * (debug, no architecture support). In this case we will acquire the +- * rtmutex with lock->wait_lock held. But we cannot unconditionally +- * enable interrupts in that early boot case. So we need to use the +- * irqsave/restore variants. +- */ +- raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ int ret; + + /* Try to acquire the lock again: */ +- if (try_to_take_rt_mutex(lock, current, NULL)) { +- raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ if (try_to_take_rt_mutex(lock, current, NULL)) + return 0; +- } + + set_current_state(state); + +@@ -1280,16 +1261,16 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, + if (unlikely(timeout)) + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + +- ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); ++ ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk); + + if (likely(!ret)) + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, waiter); + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); +- remove_waiter(lock, &waiter); +- rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ remove_waiter(lock, waiter); ++ rt_mutex_handle_deadlock(ret, chwalk, waiter); + } + + /* +@@ -1297,6 +1278,34 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, + * unconditionally. We might have to fix that up. + */ + fixup_rt_mutex_waiters(lock); ++ return ret; ++} ++ ++/* ++ * Slow path lock function: ++ */ ++static int __sched ++rt_mutex_slowlock(struct rt_mutex *lock, int state, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk) ++{ ++ struct rt_mutex_waiter waiter; ++ unsigned long flags; ++ int ret = 0; ++ ++ rt_mutex_init_waiter(&waiter); ++ ++ /* ++ * Technically we could use raw_spin_[un]lock_irq() here, but this can ++ * be called in early boot if the cmpxchg() fast path is disabled ++ * (debug, no architecture support). In this case we will acquire the ++ * rtmutex with lock->wait_lock held. But we cannot unconditionally ++ * enable interrupts in that early boot case. So we need to use the ++ * irqsave/restore variants. ++ */ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, &waiter); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 202e2b0d1251..66deb94765fb 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -15,6 +15,7 @@ + + #include <linux/rtmutex.h> + #include <linux/sched/wake_q.h> ++#include <linux/sched/debug.h> + + /* + * This is the control structure for tasks blocked on a rt_mutex, +@@ -158,6 +159,12 @@ extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wqh); + + extern void rt_mutex_postunlock(struct wake_q_head *wake_q); ++/* RW semaphore special interface */ ++ ++int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk, ++ struct rt_mutex_waiter *waiter); + + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" +-- +2.36.1 + diff --git a/debian/patches-rt/0141-rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch b/debian/patches-rt/0141-rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch new file mode 100644 index 000000000..23300e884 --- /dev/null +++ b/debian/patches-rt/0141-rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch @@ -0,0 +1,153 @@ +From 1b3711a9fe0b85e927a131441083be32b7879496 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 16:36:39 +0200 +Subject: [PATCH 141/347] rtmutex: export lockdep-less version of rt_mutex's + lock, trylock and unlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Required for lock implementation ontop of rtmutex. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 67 +++++++++++++++++++++------------ + kernel/locking/rtmutex_common.h | 3 ++ + 2 files changed, 46 insertions(+), 24 deletions(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index e9255b28de8f..e24699290bb7 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1494,12 +1494,33 @@ rt_mutex_fastunlock(struct rt_mutex *lock, + rt_mutex_postunlock(&wake_q); + } + +-static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) ++int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) + { + might_sleep(); ++ return rt_mutex_fastlock(lock, state, rt_mutex_slowlock); ++} ++ ++/** ++ * rt_mutex_lock_state - lock a rt_mutex with a given state ++ * ++ * @lock: The rt_mutex to be locked ++ * @state: The state to set when blocking on the rt_mutex ++ */ ++static inline int __sched rt_mutex_lock_state(struct rt_mutex *lock, ++ unsigned int subclass, int state) ++{ ++ int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); ++ ret = __rt_mutex_lock_state(lock, state); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++ ++static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) ++{ ++ rt_mutex_lock_state(lock, subclass, TASK_UNINTERRUPTIBLE); + } + + #ifdef CONFIG_DEBUG_LOCK_ALLOC +@@ -1540,16 +1561,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); + */ + int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) + { +- int ret; +- +- might_sleep(); +- +- mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); +- ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); +- if (ret) +- mutex_release(&lock->dep_map, 1, _RET_IP_); +- +- return ret; ++ return rt_mutex_lock_state(lock, 0, TASK_INTERRUPTIBLE); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +@@ -1575,13 +1587,10 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) + * Returns: + * 0 on success + * -EINTR when interrupted by a signal +- * -EDEADLK when the lock would deadlock (when deadlock detection is on) + */ + int __sched rt_mutex_lock_killable(struct rt_mutex *lock) + { +- might_sleep(); +- +- return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++ return rt_mutex_lock_state(lock, 0, TASK_KILLABLE); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +@@ -1616,6 +1625,18 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) + } + EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); + ++int __sched __rt_mutex_trylock(struct rt_mutex *lock) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (WARN_ON_ONCE(in_irq() || in_nmi())) ++#else ++ if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) ++#endif ++ return 0; ++ ++ return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); ++} ++ + /** + * rt_mutex_trylock - try to lock a rt_mutex + * +@@ -1631,14 +1652,7 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) + { + int ret; + +-#ifdef CONFIG_PREEMPT_RT_FULL +- if (WARN_ON_ONCE(in_irq() || in_nmi())) +-#else +- if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) +-#endif +- return 0; +- +- ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); ++ ret = __rt_mutex_trylock(lock); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + +@@ -1646,6 +1660,11 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) + } + EXPORT_SYMBOL_GPL(rt_mutex_trylock); + ++void __sched __rt_mutex_unlock(struct rt_mutex *lock) ++{ ++ rt_mutex_fastunlock(lock, rt_mutex_slowunlock); ++} ++ + /** + * rt_mutex_unlock - unlock a rt_mutex + * +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 66deb94765fb..53a8c5d03d28 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -161,6 +161,9 @@ extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, + extern void rt_mutex_postunlock(struct wake_q_head *wake_q); + /* RW semaphore special interface */ + ++extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); ++extern int __rt_mutex_trylock(struct rt_mutex *lock); ++extern void __rt_mutex_unlock(struct rt_mutex *lock); + int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, +-- +2.36.1 + diff --git a/debian/patches-rt/0142-rtmutex-add-sleeping-lock-implementation.patch b/debian/patches-rt/0142-rtmutex-add-sleeping-lock-implementation.patch new file mode 100644 index 000000000..1e1934085 --- /dev/null +++ b/debian/patches-rt/0142-rtmutex-add-sleeping-lock-implementation.patch @@ -0,0 +1,1209 @@ +From 16d4ed57212cef457bf87864ffb00f8b297f06e2 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 17:11:19 +0200 +Subject: [PATCH 142/347] rtmutex: add sleeping lock implementation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/kernel.h | 4 + + include/linux/rtmutex.h | 21 +- + include/linux/sched.h | 8 + + include/linux/sched/wake_q.h | 27 +- + include/linux/spinlock_rt.h | 156 +++++++++++ + include/linux/spinlock_types_rt.h | 48 ++++ + kernel/fork.c | 1 + + kernel/futex.c | 10 +- + kernel/locking/rtmutex.c | 436 +++++++++++++++++++++++++++--- + kernel/locking/rtmutex_common.h | 14 +- + kernel/sched/core.c | 28 +- + 11 files changed, 695 insertions(+), 58 deletions(-) + create mode 100644 include/linux/spinlock_rt.h + create mode 100644 include/linux/spinlock_types_rt.h + +diff --git a/include/linux/kernel.h b/include/linux/kernel.h +index 50733abbe548..64ef575435bb 100644 +--- a/include/linux/kernel.h ++++ b/include/linux/kernel.h +@@ -260,6 +260,9 @@ extern int _cond_resched(void); + */ + # define might_sleep() \ + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) ++ ++# define might_sleep_no_state_check() \ ++ do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + # define sched_annotate_sleep() (current->task_state_change = 0) + #else + static inline void ___might_sleep(const char *file, int line, +@@ -267,6 +270,7 @@ extern int _cond_resched(void); + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } + # define might_sleep() do { might_resched(); } while (0) ++# define might_sleep_no_state_check() do { might_resched(); } while (0) + # define sched_annotate_sleep() do { } while (0) + #endif + +diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h +index a355289b1fa1..138bd1e183e0 100644 +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -14,11 +14,15 @@ + #define __LINUX_RT_MUTEX_H + + #include <linux/linkage.h> +-#include <linux/rbtree.h> + #include <linux/spinlock_types_raw.h> ++#include <linux/rbtree.h> + + extern int max_lock_depth; /* for sysctl */ + ++#ifdef CONFIG_DEBUG_MUTEXES ++#include <linux/debug_locks.h> ++#endif ++ + /** + * The rt_mutex structure + * +@@ -31,8 +35,8 @@ struct rt_mutex { + raw_spinlock_t wait_lock; + struct rb_root_cached waiters; + struct task_struct *owner; +-#ifdef CONFIG_DEBUG_RT_MUTEXES + int save_state; ++#ifdef CONFIG_DEBUG_RT_MUTEXES + const char *name, *file; + int line; + void *magic; +@@ -82,16 +86,23 @@ do { \ + #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) + #endif + +-#define __RT_MUTEX_INITIALIZER(mutexname) \ +- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ ++#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ + , .waiters = RB_ROOT_CACHED \ + , .owner = NULL \ + __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ +- __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} ++ __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) ++ ++#define __RT_MUTEX_INITIALIZER(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } + + #define DEFINE_RT_MUTEX(mutexname) \ + struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) + ++#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ , .save_state = 1 } ++ + /** + * rt_mutex_is_locked - is the mutex locked + * @lock: the mutex to be queried +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 63a97f24d138..e4e206a1e7dd 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -134,6 +134,9 @@ struct task_group; + smp_store_mb(current->state, (state_value)); \ + } while (0) + ++#define __set_current_state_no_track(state_value) \ ++ current->state = (state_value); ++ + #define set_special_state(state_value) \ + do { \ + unsigned long flags; /* may shadow */ \ +@@ -143,6 +146,7 @@ struct task_group; + current->state = (state_value); \ + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ + } while (0) ++ + #else + /* + * set_current_state() includes a barrier so that the write of current->state +@@ -187,6 +191,9 @@ struct task_group; + #define set_current_state(state_value) \ + smp_store_mb(current->state, (state_value)) + ++#define __set_current_state_no_track(state_value) \ ++ __set_current_state(state_value) ++ + /* + * set_special_state() should be used for those states when the blocking task + * can not use the regular condition based wait-loop. In that case we must +@@ -914,6 +921,7 @@ struct task_struct { + raw_spinlock_t pi_lock; + + struct wake_q_node wake_q; ++ struct wake_q_node wake_q_sleeper; + + #ifdef CONFIG_RT_MUTEXES + /* PI waiters blocked on a rt_mutex held by this task: */ +diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h +index 10b19a192b2d..ce3ccff3d9d8 100644 +--- a/include/linux/sched/wake_q.h ++++ b/include/linux/sched/wake_q.h +@@ -47,8 +47,29 @@ static inline void wake_q_init(struct wake_q_head *head) + head->lastp = &head->first; + } + +-extern void wake_q_add(struct wake_q_head *head, +- struct task_struct *task); +-extern void wake_up_q(struct wake_q_head *head); ++extern void __wake_q_add(struct wake_q_head *head, ++ struct task_struct *task, bool sleeper); ++static inline void wake_q_add(struct wake_q_head *head, ++ struct task_struct *task) ++{ ++ __wake_q_add(head, task, false); ++} ++ ++static inline void wake_q_add_sleeper(struct wake_q_head *head, ++ struct task_struct *task) ++{ ++ __wake_q_add(head, task, true); ++} ++ ++extern void __wake_up_q(struct wake_q_head *head, bool sleeper); ++static inline void wake_up_q(struct wake_q_head *head) ++{ ++ __wake_up_q(head, false); ++} ++ ++static inline void wake_up_q_sleeper(struct wake_q_head *head) ++{ ++ __wake_up_q(head, true); ++} + + #endif /* _LINUX_SCHED_WAKE_Q_H */ +diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h +new file mode 100644 +index 000000000000..3696a77fa77d +--- /dev/null ++++ b/include/linux/spinlock_rt.h +@@ -0,0 +1,156 @@ ++#ifndef __LINUX_SPINLOCK_RT_H ++#define __LINUX_SPINLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#include <linux/bug.h> ++ ++extern void ++__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key); ++ ++#define spin_lock_init(slock) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(slock)->lock); \ ++ __rt_spin_lock_init(slock, #slock, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_spin_lock(spinlock_t *lock); ++extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); ++extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); ++extern void __lockfunc rt_spin_unlock(spinlock_t *lock); ++extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); ++extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock(spinlock_t *lock); ++extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); ++ ++/* ++ * lockdep-less calls, for derived types like rwlock: ++ * (for trylock they can use rt_mutex_trylock() directly. ++ * Migrate disable handling must be done at the call site. ++ */ ++extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_trylock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); ++ ++#define spin_lock(lock) rt_spin_lock(lock) ++ ++#define spin_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_irq(lock) spin_lock(lock) ++ ++#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) ++ ++#define spin_trylock(lock) \ ++({ \ ++ int __locked; \ ++ __locked = spin_do_trylock(lock); \ ++ __locked; \ ++}) ++ ++#ifdef CONFIG_LOCKDEP ++# define spin_lock_nested(lock, subclass) \ ++ do { \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++#define spin_lock_bh_nested(lock, subclass) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++#else ++# define spin_lock_nested(lock, subclass) spin_lock(lock) ++# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++#endif ++ ++#define spin_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++ ++static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) ++{ ++ unsigned long flags = 0; ++#ifdef CONFIG_TRACE_IRQFLAGS ++ flags = rt_spin_lock_trace_flags(lock); ++#else ++ spin_lock(lock); /* lock_local */ ++#endif ++ return flags; ++} ++ ++/* FIXME: we need rt_spin_lock_nest_lock */ ++#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) ++ ++#define spin_unlock(lock) rt_spin_unlock(lock) ++ ++#define spin_unlock_bh(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define spin_unlock_irq(lock) spin_unlock(lock) ++ ++#define spin_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ spin_unlock(lock); \ ++ } while (0) ++ ++#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) ++#define spin_trylock_irq(lock) spin_trylock(lock) ++ ++#define spin_trylock_irqsave(lock, flags) \ ++ rt_spin_trylock_irqsave(lock, &(flags)) ++ ++#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) ++ ++#ifdef CONFIG_GENERIC_LOCKBREAK ++# define spin_is_contended(lock) ((lock)->break_lock) ++#else ++# define spin_is_contended(lock) (((void)(lock), 0)) ++#endif ++ ++static inline int spin_can_lock(spinlock_t *lock) ++{ ++ return !rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline int spin_is_locked(spinlock_t *lock) ++{ ++ return rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline void assert_spin_locked(spinlock_t *lock) ++{ ++ BUG_ON(!spin_is_locked(lock)); ++} ++ ++#endif +diff --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h +new file mode 100644 +index 000000000000..3e3d8c5f7a9a +--- /dev/null ++++ b/include/linux/spinlock_types_rt.h +@@ -0,0 +1,48 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RT_H ++#define __LINUX_SPINLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++#include <linux/cache.h> ++ ++/* ++ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: ++ */ ++typedef struct spinlock { ++ struct rt_mutex lock; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} spinlock_t; ++ ++#ifdef CONFIG_DEBUG_RT_MUTEXES ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ .file = __FILE__, \ ++ .line = __LINE__ , \ ++ } ++#else ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ } ++#endif ++ ++/* ++.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) ++*/ ++ ++#define __SPIN_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_SPIN_INITIALIZER(name.lock), \ ++ SPIN_DEP_MAP_INIT(name) } ++ ++#define DEFINE_SPINLOCK(name) \ ++ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) ++ ++#endif +diff --git a/kernel/fork.c b/kernel/fork.c +index efe690af29f1..51ec12803c0b 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -900,6 +900,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) + tsk->splice_pipe = NULL; + tsk->task_frag.page = NULL; + tsk->wake_q.next = NULL; ++ tsk->wake_q_sleeper.next = NULL; + + account_kernel_stack(tsk, 1); + +diff --git a/kernel/futex.c b/kernel/futex.c +index 0e136045a720..a5a263a3efbf 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -1575,6 +1575,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ + struct task_struct *new_owner; + bool postunlock = false; + DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); + int ret = 0; + + new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); +@@ -1624,14 +1625,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); +- postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); ++ postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q, ++ &wake_sleeper_q); + } + + out_unlock: + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + + if (postunlock) +- rt_mutex_postunlock(&wake_q); ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); + + return ret; + } +@@ -2992,7 +2994,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + goto no_block; + } + +- rt_mutex_init_waiter(&rt_waiter); ++ rt_mutex_init_waiter(&rt_waiter, false); + + /* + * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not +@@ -3370,7 +3372,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ +- rt_mutex_init_waiter(&rt_waiter); ++ rt_mutex_init_waiter(&rt_waiter, false); + + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index e24699290bb7..5ff2189f1199 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -7,6 +7,11 @@ + * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> + * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt + * Copyright (C) 2006 Esben Nielsen ++ * Adaptive Spinlocks: ++ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, ++ * and Peter Morreale, ++ * Adaptive Spinlocks simplification: ++ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com> + * + * See Documentation/locking/rt-mutex-design.txt for details. + */ +@@ -234,7 +239,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + * Only use with rt_mutex_waiter_{less,equal}() + */ + #define task_to_waiter(p) \ +- &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline } ++ &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline, .task = (p) } + + static inline int + rt_mutex_waiter_less(struct rt_mutex_waiter *left, +@@ -274,6 +279,27 @@ rt_mutex_waiter_equal(struct rt_mutex_waiter *left, + return 1; + } + ++#define STEAL_NORMAL 0 ++#define STEAL_LATERAL 1 ++ ++static inline int ++rt_mutex_steal(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, int mode) ++{ ++ struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock); ++ ++ if (waiter == top_waiter || rt_mutex_waiter_less(waiter, top_waiter)) ++ return 1; ++ ++ /* ++ * Note that RT tasks are excluded from lateral-steals ++ * to prevent the introduction of an unbounded latency. ++ */ ++ if (mode == STEAL_NORMAL || rt_task(waiter->task)) ++ return 0; ++ ++ return rt_mutex_waiter_equal(waiter, top_waiter); ++} ++ + static void + rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) + { +@@ -378,6 +404,14 @@ static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, + return debug_rt_mutex_detect_deadlock(waiter, chwalk); + } + ++static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) ++{ ++ if (waiter->savestate) ++ wake_up_lock_sleeper(waiter->task); ++ else ++ wake_up_process(waiter->task); ++} ++ + /* + * Max number of times we'll walk the boosting chain: + */ +@@ -703,13 +737,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, + * follow here. This is the end of the chain we are walking. + */ + if (!rt_mutex_owner(lock)) { ++ struct rt_mutex_waiter *lock_top_waiter; ++ + /* + * If the requeue [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. + */ +- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) +- wake_up_process(rt_mutex_top_waiter(lock)->task); ++ lock_top_waiter = rt_mutex_top_waiter(lock); ++ if (prerequeue_top_waiter != lock_top_waiter) ++ rt_mutex_wake_waiter(lock_top_waiter); + raw_spin_unlock_irq(&lock->wait_lock); + return 0; + } +@@ -811,9 +848,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, + * @task: The task which wants to acquire the lock + * @waiter: The waiter that is queued to the lock's wait tree if the + * callsite called task_blocked_on_lock(), otherwise NULL ++ * @mode: Lock steal mode (STEAL_NORMAL, STEAL_LATERAL) + */ +-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, +- struct rt_mutex_waiter *waiter) ++static int __try_to_take_rt_mutex(struct rt_mutex *lock, ++ struct task_struct *task, ++ struct rt_mutex_waiter *waiter, int mode) + { + lockdep_assert_held(&lock->wait_lock); + +@@ -849,12 +888,11 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + */ + if (waiter) { + /* +- * If waiter is not the highest priority waiter of +- * @lock, give up. ++ * If waiter is not the highest priority waiter of @lock, ++ * or its peer when lateral steal is allowed, give up. + */ +- if (waiter != rt_mutex_top_waiter(lock)) ++ if (!rt_mutex_steal(lock, waiter, mode)) + return 0; +- + /* + * We can acquire the lock. Remove the waiter from the + * lock waiters tree. +@@ -872,14 +910,12 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + */ + if (rt_mutex_has_waiters(lock)) { + /* +- * If @task->prio is greater than or equal to +- * the top waiter priority (kernel view), +- * @task lost. ++ * If @task->prio is greater than the top waiter ++ * priority (kernel view), or equal to it when a ++ * lateral steal is forbidden, @task lost. + */ +- if (!rt_mutex_waiter_less(task_to_waiter(task), +- rt_mutex_top_waiter(lock))) ++ if (!rt_mutex_steal(lock, task_to_waiter(task), mode)) + return 0; +- + /* + * The current top waiter stays enqueued. We + * don't have to change anything in the lock +@@ -926,6 +962,296 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * preemptible spin_lock functions: ++ */ ++static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ might_sleep_no_state_check(); ++ ++ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) ++ return; ++ else ++ slowfn(lock); ++} ++ ++static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) ++ return; ++ else ++ slowfn(lock); ++} ++#ifdef CONFIG_SMP ++/* ++ * Note that owner is a speculative pointer and dereferencing relies ++ * on rcu_read_lock() and the check against the lock owner. ++ */ ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *owner) ++{ ++ int res = 0; ++ ++ rcu_read_lock(); ++ for (;;) { ++ if (owner != rt_mutex_owner(lock)) ++ break; ++ /* ++ * Ensure that owner->on_cpu is dereferenced _after_ ++ * checking the above to be valid. ++ */ ++ barrier(); ++ if (!owner->on_cpu) { ++ res = 1; ++ break; ++ } ++ cpu_relax(); ++ } ++ rcu_read_unlock(); ++ return res; ++} ++#else ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *orig_owner) ++{ ++ return 1; ++} ++#endif ++ ++static int task_blocks_on_rt_mutex(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ struct task_struct *task, ++ enum rtmutex_chainwalk chwalk); ++/* ++ * Slow path lock function spin_lock style: this variant is very ++ * careful not to miss any non-lock wakeups. ++ * ++ * We store the current state under p->pi_lock in p->saved_state and ++ * the try_to_wake_up() code handles this accordingly. ++ */ ++void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ unsigned long flags) ++{ ++ struct task_struct *lock_owner, *self = current; ++ struct rt_mutex_waiter *top_waiter; ++ int ret; ++ ++ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) ++ return; ++ ++ BUG_ON(rt_mutex_owner(lock) == self); ++ ++ /* ++ * We save whatever state the task is in and we'll restore it ++ * after acquiring the lock taking real wakeups into account ++ * as well. We are serialized via pi_lock against wakeups. See ++ * try_to_wake_up(). ++ */ ++ raw_spin_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ ++ ret = task_blocks_on_rt_mutex(lock, waiter, self, RT_MUTEX_MIN_CHAINWALK); ++ BUG_ON(ret); ++ ++ for (;;) { ++ /* Try to acquire the lock again. */ ++ if (__try_to_take_rt_mutex(lock, self, waiter, STEAL_LATERAL)) ++ break; ++ ++ top_waiter = rt_mutex_top_waiter(lock); ++ lock_owner = rt_mutex_owner(lock); ++ ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ ++ debug_rt_mutex_print_deadlock(waiter); ++ ++ if (top_waiter != waiter || adaptive_wait(lock, lock_owner)) ++ schedule(); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ } ++ ++ /* ++ * Restore the task state to current->saved_state. We set it ++ * to the original state above and the try_to_wake_up() code ++ * has possibly updated it when a real (non-rtmutex) wakeup ++ * happened while we were blocked. Clear saved_state so ++ * try_to_wakeup() does not get confused. ++ */ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ raw_spin_unlock(&self->pi_lock); ++ ++ /* ++ * try_to_take_rt_mutex() sets the waiter bit ++ * unconditionally. We might have to fix that up: ++ */ ++ fixup_rt_mutex_waiters(lock); ++ ++ BUG_ON(rt_mutex_has_waiters(lock) && waiter == rt_mutex_top_waiter(lock)); ++ BUG_ON(!RB_EMPTY_NODE(&waiter->tree_entry)); ++} ++ ++static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) ++{ ++ struct rt_mutex_waiter waiter; ++ unsigned long flags; ++ ++ rt_mutex_init_waiter(&waiter, true); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ rt_spin_lock_slowlock_locked(lock, &waiter, flags); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wq_sleeper); ++/* ++ * Slow path to release a rt_mutex spin_lock style ++ */ ++void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ unsigned long flags; ++ DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); ++ bool postunlock; ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ ++ if (postunlock) ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); ++} ++ ++void __lockfunc rt_spin_lock(spinlock_t *lock) ++{ ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++} ++EXPORT_SYMBOL(rt_spin_lock); ++ ++void __lockfunc __rt_spin_lock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); ++} ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) ++{ ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++} ++EXPORT_SYMBOL(rt_spin_lock_nested); ++#endif ++ ++void __lockfunc rt_spin_unlock(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_spin_unlock); ++ ++void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(__rt_spin_unlock); ++ ++/* ++ * Wait for the lock to get unlocked: instead of polling for an unlock ++ * (like raw spinlocks do), we lock and unlock, to force the kernel to ++ * schedule if there's contention: ++ */ ++void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ spin_unlock(lock); ++} ++EXPORT_SYMBOL(rt_spin_unlock_wait); ++ ++int __lockfunc rt_spin_trylock(spinlock_t *lock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = __rt_mutex_trylock(&lock->lock); ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock); ++ ++int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) ++{ ++ int ret; ++ ++ local_bh_disable(); ++ ret = __rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } else ++ local_bh_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_bh); ++ ++int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ ret = __rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_irqsave); ++ ++void ++__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif ++} ++EXPORT_SYMBOL(__rt_spin_lock_init); ++ ++#endif /* PREEMPT_RT_FULL */ ++ ++static inline int ++try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, ++ struct rt_mutex_waiter *waiter) ++{ ++ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); ++} ++ + /* + * Task blocks on lock. + * +@@ -1039,6 +1365,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + * Called with lock->wait_lock held and interrupts disabled. + */ + static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q, + struct rt_mutex *lock) + { + struct rt_mutex_waiter *waiter; +@@ -1078,7 +1405,10 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, + * Pairs with preempt_enable() in rt_mutex_postunlock(); + */ + preempt_disable(); +- wake_q_add(wake_q, waiter->task); ++ if (waiter->savestate) ++ wake_q_add_sleeper(wake_sleeper_q, waiter->task); ++ else ++ wake_q_add(wake_q, waiter->task); + raw_spin_unlock(¤t->pi_lock); + } + +@@ -1162,21 +1492,22 @@ void rt_mutex_adjust_pi(struct task_struct *task) + return; + } + next_lock = waiter->lock; +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(task); + ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); + } + +-void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) ++void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) + { + debug_rt_mutex_init_waiter(waiter); + RB_CLEAR_NODE(&waiter->pi_tree_entry); + RB_CLEAR_NODE(&waiter->tree_entry); + waiter->task = NULL; ++ waiter->savestate = savestate; + } + + /** +@@ -1293,7 +1624,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, + unsigned long flags; + int ret = 0; + +- rt_mutex_init_waiter(&waiter); ++ rt_mutex_init_waiter(&waiter, false); + + /* + * Technically we could use raw_spin_[un]lock_irq() here, but this can +@@ -1366,7 +1697,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) + * Return whether the current task needs to call rt_mutex_postunlock(). + */ + static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, +- struct wake_q_head *wake_q) ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q) + { + unsigned long flags; + +@@ -1420,7 +1752,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, + * + * Queue the next waiter for wakeup once we release the wait_lock. + */ +- mark_wakeup_next_waiter(wake_q, lock); ++ mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + return true; /* call rt_mutex_postunlock() */ +@@ -1472,9 +1804,11 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, + /* + * Performs the wakeup of the the top-waiter and re-enables preemption. + */ +-void rt_mutex_postunlock(struct wake_q_head *wake_q) ++void rt_mutex_postunlock(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q) + { + wake_up_q(wake_q); ++ wake_up_q_sleeper(wake_sleeper_q); + + /* Pairs with preempt_disable() in rt_mutex_slowunlock() */ + preempt_enable(); +@@ -1483,15 +1817,17 @@ void rt_mutex_postunlock(struct wake_q_head *wake_q) + static inline void + rt_mutex_fastunlock(struct rt_mutex *lock, + bool (*slowfn)(struct rt_mutex *lock, +- struct wake_q_head *wqh)) ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper)) + { + DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); + + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return; + +- if (slowfn(lock, &wake_q)) +- rt_mutex_postunlock(&wake_q); ++ if (slowfn(lock, &wake_q, &wake_sleeper_q)) ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); + } + + int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) +@@ -1673,16 +2009,13 @@ void __sched __rt_mutex_unlock(struct rt_mutex *lock) + void __sched rt_mutex_unlock(struct rt_mutex *lock) + { + mutex_release(&lock->dep_map, 1, _RET_IP_); +- rt_mutex_fastunlock(lock, rt_mutex_slowunlock); ++ __rt_mutex_unlock(lock); + } + EXPORT_SYMBOL_GPL(rt_mutex_unlock); + +-/** +- * Futex variant, that since futex variants do not use the fast-path, can be +- * simple and will not need to retry. +- */ +-bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, +- struct wake_q_head *wake_q) ++static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wq_sleeper) + { + lockdep_assert_held(&lock->wait_lock); + +@@ -1699,23 +2032,35 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, + * avoid inversion prior to the wakeup. preempt_disable() + * therein pairs with rt_mutex_postunlock(). + */ +- mark_wakeup_next_waiter(wake_q, lock); ++ mark_wakeup_next_waiter(wake_q, wq_sleeper, lock); + + return true; /* call postunlock() */ + } + ++/** ++ * Futex variant, that since futex variants do not use the fast-path, can be ++ * simple and will not need to retry. ++ */ ++bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wq_sleeper) ++{ ++ return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper); ++} ++ + void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) + { + DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); + unsigned long flags; + bool postunlock; + + raw_spin_lock_irqsave(&lock->wait_lock, flags); +- postunlock = __rt_mutex_futex_unlock(lock, &wake_q); ++ postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + if (postunlock) +- rt_mutex_postunlock(&wake_q); ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); + } + + /** +@@ -1754,7 +2099,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name, + if (name && key) + debug_rt_mutex_init(lock, name, key); + } +-EXPORT_SYMBOL_GPL(__rt_mutex_init); ++EXPORT_SYMBOL(__rt_mutex_init); + + /** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a +@@ -1948,6 +2293,7 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter) + { ++ struct task_struct *tsk = current; + int ret; + + raw_spin_lock_irq(&lock->wait_lock); +@@ -1959,6 +2305,24 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); ++ /* ++ * RT has a problem here when the wait got interrupted by a timeout ++ * or a signal. task->pi_blocked_on is still set. The task must ++ * acquire the hash bucket lock when returning from this function. ++ * ++ * If the hash bucket lock is contended then the ++ * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in ++ * task_blocks_on_rt_mutex() will trigger. This can be avoided by ++ * clearing task->pi_blocked_on which removes the task from the ++ * boosting chain of the rtmutex. That's correct because the task ++ * is not longer blocked on it. ++ */ ++ if (ret) { ++ raw_spin_lock(&tsk->pi_lock); ++ tsk->pi_blocked_on = NULL; ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ + raw_spin_unlock_irq(&lock->wait_lock); + + return ret; +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 53a8c5d03d28..7c1dd1bd95c7 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -30,6 +30,7 @@ struct rt_mutex_waiter { + struct rb_node pi_tree_entry; + struct task_struct *task; + struct rt_mutex *lock; ++ bool savestate; + #ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; +@@ -138,7 +139,7 @@ extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); + extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); +-extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); ++extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate); + extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task); +@@ -156,9 +157,12 @@ extern int __rt_mutex_futex_trylock(struct rt_mutex *l); + + extern void rt_mutex_futex_unlock(struct rt_mutex *lock); + extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, +- struct wake_q_head *wqh); ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper); ++ ++extern void rt_mutex_postunlock(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q); + +-extern void rt_mutex_postunlock(struct wake_q_head *wake_q); + /* RW semaphore special interface */ + + extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); +@@ -168,6 +172,10 @@ int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *waiter); ++void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ unsigned long flags); ++void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock); + + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index ed79f921a84e..1f450a7649f0 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -401,9 +401,15 @@ static bool set_nr_if_polling(struct task_struct *p) + #endif + #endif + +-void wake_q_add(struct wake_q_head *head, struct task_struct *task) ++void __wake_q_add(struct wake_q_head *head, struct task_struct *task, ++ bool sleeper) + { +- struct wake_q_node *node = &task->wake_q; ++ struct wake_q_node *node; ++ ++ if (sleeper) ++ node = &task->wake_q_sleeper; ++ else ++ node = &task->wake_q; + + /* + * Atomically grab the task, if ->wake_q is !nil already it means +@@ -426,24 +432,32 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) + head->lastp = &node->next; + } + +-void wake_up_q(struct wake_q_head *head) ++void __wake_up_q(struct wake_q_head *head, bool sleeper) + { + struct wake_q_node *node = head->first; + + while (node != WAKE_Q_TAIL) { + struct task_struct *task; + +- task = container_of(node, struct task_struct, wake_q); ++ if (sleeper) ++ task = container_of(node, struct task_struct, wake_q_sleeper); ++ else ++ task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); + /* Task can safely be re-inserted now: */ + node = node->next; +- task->wake_q.next = NULL; +- ++ if (sleeper) ++ task->wake_q_sleeper.next = NULL; ++ else ++ task->wake_q.next = NULL; + /* + * wake_up_process() executes a full barrier, which pairs with + * the queueing in wake_q_add() so as not to miss wakeups. + */ +- wake_up_process(task); ++ if (sleeper) ++ wake_up_lock_sleeper(task); ++ else ++ wake_up_process(task); + put_task_struct(task); + } + } +-- +2.36.1 + diff --git a/debian/patches-rt/0143-rtmutex-add-mutex-implementation-based-on-rtmutex.patch b/debian/patches-rt/0143-rtmutex-add-mutex-implementation-based-on-rtmutex.patch new file mode 100644 index 000000000..268579aea --- /dev/null +++ b/debian/patches-rt/0143-rtmutex-add-mutex-implementation-based-on-rtmutex.patch @@ -0,0 +1,383 @@ +From df07ee70a0dfe4c5f6c6b8a01afd04d748635c84 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 17:17:03 +0200 +Subject: [PATCH 143/347] rtmutex: add mutex implementation based on rtmutex +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/mutex_rt.h | 130 ++++++++++++++++++++++ + kernel/locking/mutex-rt.c | 223 ++++++++++++++++++++++++++++++++++++++ + 2 files changed, 353 insertions(+) + create mode 100644 include/linux/mutex_rt.h + create mode 100644 kernel/locking/mutex-rt.c + +diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h +new file mode 100644 +index 000000000000..3fcb5edb1d2b +--- /dev/null ++++ b/include/linux/mutex_rt.h +@@ -0,0 +1,130 @@ ++#ifndef __LINUX_MUTEX_RT_H ++#define __LINUX_MUTEX_RT_H ++ ++#ifndef __LINUX_MUTEX_H ++#error "Please include mutex.h" ++#endif ++ ++#include <linux/rtmutex.h> ++ ++/* FIXME: Just for __lockfunc */ ++#include <linux/spinlock.h> ++ ++struct mutex { ++ struct rt_mutex lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __MUTEX_INITIALIZER(mutexname) \ ++ { \ ++ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ ++ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ ++ } ++ ++#define DEFINE_MUTEX(mutexname) \ ++ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) ++ ++extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); ++extern void __lockfunc _mutex_lock(struct mutex *lock); ++extern void __lockfunc _mutex_lock_io(struct mutex *lock); ++extern void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); ++extern int __lockfunc _mutex_lock_killable(struct mutex *lock); ++extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); ++extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); ++extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_trylock(struct mutex *lock); ++extern void __lockfunc _mutex_unlock(struct mutex *lock); ++ ++#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) ++#define mutex_lock(l) _mutex_lock(l) ++#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) ++#define mutex_lock_killable(l) _mutex_lock_killable(l) ++#define mutex_trylock(l) _mutex_trylock(l) ++#define mutex_unlock(l) _mutex_unlock(l) ++#define mutex_lock_io(l) _mutex_lock_io(l); ++ ++#define __mutex_owner(l) ((l)->lock.owner) ++ ++#ifdef CONFIG_DEBUG_MUTEXES ++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) ++#else ++static inline void mutex_destroy(struct mutex *lock) {} ++#endif ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible_nested(l, s) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable_nested(l, s) ++# define mutex_lock_io_nested(l, s) _mutex_lock_io_nested(l, s) ++ ++# define mutex_lock_nest_lock(lock, nest_lock) \ ++do { \ ++ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ ++ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ ++} while (0) ++ ++#else ++# define mutex_lock_nested(l, s) _mutex_lock(l) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible(l) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable(l) ++# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) ++# define mutex_lock_io_nested(l, s) _mutex_lock_io(l) ++#endif ++ ++# define mutex_init(mutex) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), #mutex, &__key); \ ++} while (0) ++ ++# define __mutex_init(mutex, name, key) \ ++do { \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), name, key); \ ++} while (0) ++ ++/** ++ * These values are chosen such that FAIL and SUCCESS match the ++ * values of the regular mutex_trylock(). ++ */ ++enum mutex_trylock_recursive_enum { ++ MUTEX_TRYLOCK_FAILED = 0, ++ MUTEX_TRYLOCK_SUCCESS = 1, ++ MUTEX_TRYLOCK_RECURSIVE, ++}; ++/** ++ * mutex_trylock_recursive - trylock variant that allows recursive locking ++ * @lock: mutex to be locked ++ * ++ * This function should not be used, _ever_. It is purely for hysterical GEM ++ * raisins, and once those are gone this will be removed. ++ * ++ * Returns: ++ * MUTEX_TRYLOCK_FAILED - trylock failed, ++ * MUTEX_TRYLOCK_SUCCESS - lock acquired, ++ * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. ++ */ ++int __rt_mutex_owner_current(struct rt_mutex *lock); ++ ++static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum ++mutex_trylock_recursive(struct mutex *lock) ++{ ++ if (unlikely(__rt_mutex_owner_current(&lock->lock))) ++ return MUTEX_TRYLOCK_RECURSIVE; ++ ++ return mutex_trylock(lock); ++} ++ ++extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); ++ ++#endif +diff --git a/kernel/locking/mutex-rt.c b/kernel/locking/mutex-rt.c +new file mode 100644 +index 000000000000..4f81595c0f52 +--- /dev/null ++++ b/kernel/locking/mutex-rt.c +@@ -0,0 +1,223 @@ ++/* ++ * kernel/rt.c ++ * ++ * Real-Time Preemption Support ++ * ++ * started by Ingo Molnar: ++ * ++ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> ++ * ++ * historic credit for proving that Linux spinlocks can be implemented via ++ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow ++ * and others) who prototyped it on 2.4 and did lots of comparative ++ * research and analysis; TimeSys, for proving that you can implement a ++ * fully preemptible kernel via the use of IRQ threading and mutexes; ++ * Bill Huey for persuasively arguing on lkml that the mutex model is the ++ * right one; and to MontaVista, who ported pmutexes to 2.6. ++ * ++ * This code is a from-scratch implementation and is not based on pmutexes, ++ * but the idea of converting spinlocks to mutexes is used here too. ++ * ++ * lock debugging, locking tree, deadlock detection: ++ * ++ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey ++ * Released under the General Public License (GPL). ++ * ++ * Includes portions of the generic R/W semaphore implementation from: ++ * ++ * Copyright (c) 2001 David Howells (dhowells@redhat.com). ++ * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de> ++ * - Derived also from comments by Linus ++ * ++ * Pending ownership of locks and ownership stealing: ++ * ++ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt ++ * ++ * (also by Steven Rostedt) ++ * - Converted single pi_lock to individual task locks. ++ * ++ * By Esben Nielsen: ++ * Doing priority inheritance with help of the scheduler. ++ * ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> ++ * - major rework based on Esben Nielsens initial patch ++ * - replaced thread_info references by task_struct refs ++ * - removed task->pending_owner dependency ++ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks ++ * in the scheduler return path as discussed with Steven Rostedt ++ * ++ * Copyright (C) 2006, Kihon Technologies Inc. ++ * Steven Rostedt <rostedt@goodmis.org> ++ * - debugged and patched Thomas Gleixner's rework. ++ * - added back the cmpxchg to the rework. ++ * - turned atomic require back on for SMP. ++ */ ++ ++#include <linux/spinlock.h> ++#include <linux/rtmutex.h> ++#include <linux/sched.h> ++#include <linux/delay.h> ++#include <linux/module.h> ++#include <linux/kallsyms.h> ++#include <linux/syscalls.h> ++#include <linux/interrupt.h> ++#include <linux/plist.h> ++#include <linux/fs.h> ++#include <linux/futex.h> ++#include <linux/hrtimer.h> ++ ++#include "rtmutex_common.h" ++ ++/* ++ * struct mutex functions ++ */ ++void __mutex_do_init(struct mutex *mutex, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); ++ lockdep_init_map(&mutex->dep_map, name, key, 0); ++#endif ++ mutex->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__mutex_do_init); ++ ++void __lockfunc _mutex_lock(struct mutex *lock) ++{ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++} ++EXPORT_SYMBOL(_mutex_lock); ++ ++void __lockfunc _mutex_lock_io(struct mutex *lock) ++{ ++ int token; ++ ++ token = io_schedule_prepare(); ++ _mutex_lock(lock); ++ io_schedule_finish(token); ++} ++EXPORT_SYMBOL_GPL(_mutex_lock_io); ++ ++int __lockfunc _mutex_lock_interruptible(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible); ++ ++int __lockfunc _mutex_lock_killable(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) ++{ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++} ++EXPORT_SYMBOL(_mutex_lock_nested); ++ ++void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass) ++{ ++ int token; ++ ++ token = io_schedule_prepare(); ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++ ++ io_schedule_finish(token); ++} ++EXPORT_SYMBOL_GPL(_mutex_lock_io_nested); ++ ++void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) ++{ ++ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++} ++EXPORT_SYMBOL(_mutex_lock_nest_lock); ++ ++int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible_nested); ++ ++int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable_nested); ++#endif ++ ++int __lockfunc _mutex_trylock(struct mutex *lock) ++{ ++ int ret = __rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_trylock); ++ ++void __lockfunc _mutex_unlock(struct mutex *lock) ++{ ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ __rt_mutex_unlock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_unlock); ++ ++/** ++ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 ++ * @cnt: the atomic which we are to dec ++ * @lock: the mutex to return holding if we dec to 0 ++ * ++ * return true and hold lock if we dec to 0, return false otherwise ++ */ ++int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) ++{ ++ /* dec if we can't possibly hit 0 */ ++ if (atomic_add_unless(cnt, -1, 1)) ++ return 0; ++ /* we might hit 0, so take the lock */ ++ mutex_lock(lock); ++ if (!atomic_dec_and_test(cnt)) { ++ /* when we actually did the dec, we didn't hit 0 */ ++ mutex_unlock(lock); ++ return 0; ++ } ++ /* we hit 0, and we hold the lock */ ++ return 1; ++} ++EXPORT_SYMBOL(atomic_dec_and_mutex_lock); +-- +2.36.1 + diff --git a/debian/patches-rt/0144-rtmutex-add-rwsem-implementation-based-on-rtmutex.patch b/debian/patches-rt/0144-rtmutex-add-rwsem-implementation-based-on-rtmutex.patch new file mode 100644 index 000000000..b05b5ef45 --- /dev/null +++ b/debian/patches-rt/0144-rtmutex-add-rwsem-implementation-based-on-rtmutex.patch @@ -0,0 +1,427 @@ +From d5648fc940b9d669cad909970b95064ee3634612 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 17:28:34 +0200 +Subject: [PATCH 144/347] rtmutex: add rwsem implementation based on rtmutex +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The RT specific R/W semaphore implementation restricts the number of readers +to one because a writer cannot block on multiple readers and inherit its +priority or budget. + +The single reader restricting is painful in various ways: + + - Performance bottleneck for multi-threaded applications in the page fault + path (mmap sem) + + - Progress blocker for drivers which are carefully crafted to avoid the + potential reader/writer deadlock in mainline. + +The analysis of the writer code pathes shows, that properly written RT tasks +should not take them. Syscalls like mmap(), file access which take mmap sem +write locked have unbound latencies which are completely unrelated to mmap +sem. Other R/W sem users like graphics drivers are not suitable for RT tasks +either. + +So there is little risk to hurt RT tasks when the RT rwsem implementation is +changed in the following way: + + - Allow concurrent readers + + - Make writers block until the last reader left the critical section. This + blocking is not subject to priority/budget inheritance. + + - Readers blocked on a writer inherit their priority/budget in the normal + way. + +There is a drawback with this scheme. R/W semaphores become writer unfair +though the applications which have triggered writer starvation (mostly on +mmap_sem) in the past are not really the typical workloads running on a RT +system. So while it's unlikely to hit writer starvation, it's possible. If +there are unexpected workloads on RT systems triggering it, we need to rethink +the approach. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/rwsem_rt.h | 68 +++++++++ + kernel/locking/rwsem-rt.c | 293 ++++++++++++++++++++++++++++++++++++++ + 2 files changed, 361 insertions(+) + create mode 100644 include/linux/rwsem_rt.h + create mode 100644 kernel/locking/rwsem-rt.c + +diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h +new file mode 100644 +index 000000000000..2018ff77904a +--- /dev/null ++++ b/include/linux/rwsem_rt.h +@@ -0,0 +1,68 @@ ++#ifndef _LINUX_RWSEM_RT_H ++#define _LINUX_RWSEM_RT_H ++ ++#ifndef _LINUX_RWSEM_H ++#error "Include rwsem.h" ++#endif ++ ++#include <linux/rtmutex.h> ++#include <linux/swait.h> ++ ++#define READER_BIAS (1U << 31) ++#define WRITER_BIAS (1U << 30) ++ ++struct rw_semaphore { ++ atomic_t readers; ++ struct rt_mutex rtmutex; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __RWSEM_INITIALIZER(name) \ ++{ \ ++ .readers = ATOMIC_INIT(READER_BIAS), \ ++ .rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex), \ ++ RW_DEP_MAP_INIT(name) \ ++} ++ ++#define DECLARE_RWSEM(lockname) \ ++ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) ++ ++extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, ++ struct lock_class_key *key); ++ ++#define __init_rwsem(sem, name, key) \ ++do { \ ++ rt_mutex_init(&(sem)->rtmutex); \ ++ __rwsem_init((sem), (name), (key)); \ ++} while (0) ++ ++#define init_rwsem(sem) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __init_rwsem((sem), #sem, &__key); \ ++} while (0) ++ ++static inline int rwsem_is_locked(struct rw_semaphore *sem) ++{ ++ return atomic_read(&sem->readers) != READER_BIAS; ++} ++ ++static inline int rwsem_is_contended(struct rw_semaphore *sem) ++{ ++ return atomic_read(&sem->readers) > 0; ++} ++ ++extern void __down_read(struct rw_semaphore *sem); ++extern int __down_read_killable(struct rw_semaphore *sem); ++extern int __down_read_trylock(struct rw_semaphore *sem); ++extern void __down_write(struct rw_semaphore *sem); ++extern int __must_check __down_write_killable(struct rw_semaphore *sem); ++extern int __down_write_trylock(struct rw_semaphore *sem); ++extern void __up_read(struct rw_semaphore *sem); ++extern void __up_write(struct rw_semaphore *sem); ++extern void __downgrade_write(struct rw_semaphore *sem); ++ ++#endif +diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c +new file mode 100644 +index 000000000000..7d3c5cf3d23d +--- /dev/null ++++ b/kernel/locking/rwsem-rt.c +@@ -0,0 +1,293 @@ ++/* ++ */ ++#include <linux/rwsem.h> ++#include <linux/sched/debug.h> ++#include <linux/sched/signal.h> ++#include <linux/export.h> ++ ++#include "rtmutex_common.h" ++ ++/* ++ * RT-specific reader/writer semaphores ++ * ++ * down_write() ++ * 1) Lock sem->rtmutex ++ * 2) Remove the reader BIAS to force readers into the slow path ++ * 3) Wait until all readers have left the critical region ++ * 4) Mark it write locked ++ * ++ * up_write() ++ * 1) Remove the write locked marker ++ * 2) Set the reader BIAS so readers can use the fast path again ++ * 3) Unlock sem->rtmutex to release blocked readers ++ * ++ * down_read() ++ * 1) Try fast path acquisition (reader BIAS is set) ++ * 2) Take sem->rtmutex.wait_lock which protects the writelocked flag ++ * 3) If !writelocked, acquire it for read ++ * 4) If writelocked, block on sem->rtmutex ++ * 5) unlock sem->rtmutex, goto 1) ++ * ++ * up_read() ++ * 1) Try fast path release (reader count != 1) ++ * 2) Wake the writer waiting in down_write()#3 ++ * ++ * down_read()#3 has the consequence, that rw semaphores on RT are not writer ++ * fair, but writers, which should be avoided in RT tasks (think mmap_sem), ++ * are subject to the rtmutex priority/DL inheritance mechanism. ++ * ++ * It's possible to make the rw semaphores writer fair by keeping a list of ++ * active readers. A blocked writer would force all newly incoming readers to ++ * block on the rtmutex, but the rtmutex would have to be proxy locked for one ++ * reader after the other. We can't use multi-reader inheritance because there ++ * is no way to support that with SCHED_DEADLINE. Implementing the one by one ++ * reader boosting/handover mechanism is a major surgery for a very dubious ++ * value. ++ * ++ * The risk of writer starvation is there, but the pathological use cases ++ * which trigger it are not necessarily the typical RT workloads. ++ */ ++ ++void __rwsem_init(struct rw_semaphore *sem, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held semaphore: ++ */ ++ debug_check_no_locks_freed((void *)sem, sizeof(*sem)); ++ lockdep_init_map(&sem->dep_map, name, key, 0); ++#endif ++ atomic_set(&sem->readers, READER_BIAS); ++} ++EXPORT_SYMBOL(__rwsem_init); ++ ++int __down_read_trylock(struct rw_semaphore *sem) ++{ ++ int r, old; ++ ++ /* ++ * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is ++ * set. ++ */ ++ for (r = atomic_read(&sem->readers); r < 0;) { ++ old = atomic_cmpxchg(&sem->readers, r, r + 1); ++ if (likely(old == r)) ++ return 1; ++ r = old; ++ } ++ return 0; ++} ++ ++static int __sched __down_read_common(struct rw_semaphore *sem, int state) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ struct rt_mutex_waiter waiter; ++ int ret; ++ ++ if (__down_read_trylock(sem)) ++ return 0; ++ ++ might_sleep(); ++ raw_spin_lock_irq(&m->wait_lock); ++ /* ++ * Allow readers as long as the writer has not completely ++ * acquired the semaphore for write. ++ */ ++ if (atomic_read(&sem->readers) != WRITER_BIAS) { ++ atomic_inc(&sem->readers); ++ raw_spin_unlock_irq(&m->wait_lock); ++ return 0; ++ } ++ ++ /* ++ * Call into the slow lock path with the rtmutex->wait_lock ++ * held, so this can't result in the following race: ++ * ++ * Reader1 Reader2 Writer ++ * down_read() ++ * down_write() ++ * rtmutex_lock(m) ++ * swait() ++ * down_read() ++ * unlock(m->wait_lock) ++ * up_read() ++ * swake() ++ * lock(m->wait_lock) ++ * sem->writelocked=true ++ * unlock(m->wait_lock) ++ * ++ * up_write() ++ * sem->writelocked=false ++ * rtmutex_unlock(m) ++ * down_read() ++ * down_write() ++ * rtmutex_lock(m) ++ * swait() ++ * rtmutex_lock(m) ++ * ++ * That would put Reader1 behind the writer waiting on ++ * Reader2 to call up_read() which might be unbound. ++ */ ++ rt_mutex_init_waiter(&waiter, false); ++ ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK, ++ &waiter); ++ /* ++ * The slowlock() above is guaranteed to return with the rtmutex (for ++ * ret = 0) is now held, so there can't be a writer active. Increment ++ * the reader count and immediately drop the rtmutex again. ++ * For ret != 0 we don't hold the rtmutex and need unlock the wait_lock. ++ * We don't own the lock then. ++ */ ++ if (!ret) ++ atomic_inc(&sem->readers); ++ raw_spin_unlock_irq(&m->wait_lock); ++ if (!ret) ++ __rt_mutex_unlock(m); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++ return ret; ++} ++ ++void __down_read(struct rw_semaphore *sem) ++{ ++ int ret; ++ ++ ret = __down_read_common(sem, TASK_UNINTERRUPTIBLE); ++ WARN_ON_ONCE(ret); ++} ++ ++int __down_read_killable(struct rw_semaphore *sem) ++{ ++ int ret; ++ ++ ret = __down_read_common(sem, TASK_KILLABLE); ++ if (likely(!ret)) ++ return ret; ++ WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret); ++ return -EINTR; ++} ++ ++void __up_read(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ struct task_struct *tsk; ++ ++ /* ++ * sem->readers can only hit 0 when a writer is waiting for the ++ * active readers to leave the critical region. ++ */ ++ if (!atomic_dec_and_test(&sem->readers)) ++ return; ++ ++ might_sleep(); ++ raw_spin_lock_irq(&m->wait_lock); ++ /* ++ * Wake the writer, i.e. the rtmutex owner. It might release the ++ * rtmutex concurrently in the fast path (due to a signal), but to ++ * clean up the rwsem it needs to acquire m->wait_lock. The worst ++ * case which can happen is a spurious wakeup. ++ */ ++ tsk = rt_mutex_owner(m); ++ if (tsk) ++ wake_up_process(tsk); ++ ++ raw_spin_unlock_irq(&m->wait_lock); ++} ++ ++static void __up_write_unlock(struct rw_semaphore *sem, int bias, ++ unsigned long flags) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ ++ atomic_add(READER_BIAS - bias, &sem->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ __rt_mutex_unlock(m); ++} ++ ++static int __sched __down_write_common(struct rw_semaphore *sem, int state) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ /* Take the rtmutex as a first step */ ++ if (__rt_mutex_lock_state(m, state)) ++ return -EINTR; ++ ++ /* Force readers into slow path */ ++ atomic_sub(READER_BIAS, &sem->readers); ++ might_sleep(); ++ ++ set_current_state(state); ++ for (;;) { ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ /* Have all readers left the critical region? */ ++ if (!atomic_read(&sem->readers)) { ++ atomic_set(&sem->readers, WRITER_BIAS); ++ __set_current_state(TASK_RUNNING); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return 0; ++ } ++ ++ if (signal_pending_state(state, current)) { ++ __set_current_state(TASK_RUNNING); ++ __up_write_unlock(sem, 0, flags); ++ return -EINTR; ++ } ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ ++ if (atomic_read(&sem->readers) != 0) { ++ schedule(); ++ set_current_state(state); ++ } ++ } ++} ++ ++void __sched __down_write(struct rw_semaphore *sem) ++{ ++ __down_write_common(sem, TASK_UNINTERRUPTIBLE); ++} ++ ++int __sched __down_write_killable(struct rw_semaphore *sem) ++{ ++ return __down_write_common(sem, TASK_KILLABLE); ++} ++ ++int __down_write_trylock(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ if (!__rt_mutex_trylock(m)) ++ return 0; ++ ++ atomic_sub(READER_BIAS, &sem->readers); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ if (!atomic_read(&sem->readers)) { ++ atomic_set(&sem->readers, WRITER_BIAS); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return 1; ++ } ++ __up_write_unlock(sem, 0, flags); ++ return 0; ++} ++ ++void __up_write(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ __up_write_unlock(sem, WRITER_BIAS, flags); ++} ++ ++void __downgrade_write(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ /* Release it and account current as reader */ ++ __up_write_unlock(sem, WRITER_BIAS - 1, flags); ++} +-- +2.36.1 + diff --git a/debian/patches-rt/0145-rtmutex-add-rwlock-implementation-based-on-rtmutex.patch b/debian/patches-rt/0145-rtmutex-add-rwlock-implementation-based-on-rtmutex.patch new file mode 100644 index 000000000..3045accc9 --- /dev/null +++ b/debian/patches-rt/0145-rtmutex-add-rwlock-implementation-based-on-rtmutex.patch @@ -0,0 +1,582 @@ +From f6a36a3573a2474292d6b6e71f206f52212b6cd5 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 17:18:06 +0200 +Subject: [PATCH 145/347] rtmutex: add rwlock implementation based on rtmutex +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The implementation is bias-based, similar to the rwsem implementation. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/rwlock_rt.h | 119 +++++++++++ + include/linux/rwlock_types_rt.h | 55 +++++ + kernel/locking/rwlock-rt.c | 368 ++++++++++++++++++++++++++++++++ + 3 files changed, 542 insertions(+) + create mode 100644 include/linux/rwlock_rt.h + create mode 100644 include/linux/rwlock_types_rt.h + create mode 100644 kernel/locking/rwlock-rt.c + +diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h +new file mode 100644 +index 000000000000..a9c4c2ac4d1f +--- /dev/null ++++ b/include/linux/rwlock_rt.h +@@ -0,0 +1,119 @@ ++#ifndef __LINUX_RWLOCK_RT_H ++#define __LINUX_RWLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++extern void __lockfunc rt_write_lock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); ++extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); ++extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); ++extern int __lockfunc rt_read_can_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_can_lock(rwlock_t *rwlock); ++extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); ++ ++#define read_can_lock(rwlock) rt_read_can_lock(rwlock) ++#define write_can_lock(rwlock) rt_write_can_lock(rwlock) ++ ++#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) ++#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) ++ ++static inline int __write_trylock_rt_irqsave(rwlock_t *lock, unsigned long *flags) ++{ ++ /* XXX ARCH_IRQ_ENABLED */ ++ *flags = 0; ++ return rt_write_trylock(lock); ++} ++ ++#define write_trylock_irqsave(lock, flags) \ ++ __cond_lock(lock, __write_trylock_rt_irqsave(lock, &(flags))) ++ ++#define read_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ rt_read_lock(lock); \ ++ flags = 0; \ ++ } while (0) ++ ++#define write_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ rt_write_lock(lock); \ ++ flags = 0; \ ++ } while (0) ++ ++#define read_lock(lock) rt_read_lock(lock) ++ ++#define read_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_irq(lock) read_lock(lock) ++ ++#define write_lock(lock) rt_write_lock(lock) ++ ++#define write_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_irq(lock) write_lock(lock) ++ ++#define read_unlock(lock) rt_read_unlock(lock) ++ ++#define read_unlock_bh(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define read_unlock_irq(lock) read_unlock(lock) ++ ++#define write_unlock(lock) rt_write_unlock(lock) ++ ++#define write_unlock_bh(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define write_unlock_irq(lock) write_unlock(lock) ++ ++#define read_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_read_unlock(lock); \ ++ } while (0) ++ ++#define write_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_write_unlock(lock); \ ++ } while (0) ++ ++#define rwlock_init(rwl) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rt_rwlock_init(rwl, #rwl, &__key); \ ++} while (0) ++ ++/* ++ * Internal functions made global for CPU pinning ++ */ ++void __read_rt_lock(struct rt_rw_lock *lock); ++int __read_rt_trylock(struct rt_rw_lock *lock); ++void __write_rt_lock(struct rt_rw_lock *lock); ++int __write_rt_trylock(struct rt_rw_lock *lock); ++void __read_rt_unlock(struct rt_rw_lock *lock); ++void __write_rt_unlock(struct rt_rw_lock *lock); ++ ++#endif +diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h +new file mode 100644 +index 000000000000..546a1f8f1274 +--- /dev/null ++++ b/include/linux/rwlock_types_rt.h +@@ -0,0 +1,55 @@ ++#ifndef __LINUX_RWLOCK_TYPES_RT_H ++#define __LINUX_RWLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define RW_DEP_MAP_INIT(lockname) ++#endif ++ ++typedef struct rt_rw_lock rwlock_t; ++ ++#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name) ++ ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name = __RW_LOCK_UNLOCKED(name) ++ ++/* ++ * A reader biased implementation primarily for CPU pinning. ++ * ++ * Can be selected as general replacement for the single reader RT rwlock ++ * variant ++ */ ++struct rt_rw_lock { ++ struct rt_mutex rtmutex; ++ atomic_t readers; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define READER_BIAS (1U << 31) ++#define WRITER_BIAS (1U << 30) ++ ++#define __RWLOCK_RT_INITIALIZER(name) \ ++{ \ ++ .readers = ATOMIC_INIT(READER_BIAS), \ ++ .rtmutex = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.rtmutex), \ ++ RW_DEP_MAP_INIT(name) \ ++} ++ ++void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, ++ struct lock_class_key *key); ++ ++#define rwlock_biased_rt_init(rwlock) \ ++ do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rwlock_biased_rt_init((rwlock), #rwlock, &__key); \ ++ } while (0) ++ ++#endif +diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c +new file mode 100644 +index 000000000000..aebb7ce25bc6 +--- /dev/null ++++ b/kernel/locking/rwlock-rt.c +@@ -0,0 +1,368 @@ ++/* ++ */ ++#include <linux/sched/debug.h> ++#include <linux/export.h> ++ ++#include "rtmutex_common.h" ++#include <linux/rwlock_types_rt.h> ++ ++/* ++ * RT-specific reader/writer locks ++ * ++ * write_lock() ++ * 1) Lock lock->rtmutex ++ * 2) Remove the reader BIAS to force readers into the slow path ++ * 3) Wait until all readers have left the critical region ++ * 4) Mark it write locked ++ * ++ * write_unlock() ++ * 1) Remove the write locked marker ++ * 2) Set the reader BIAS so readers can use the fast path again ++ * 3) Unlock lock->rtmutex to release blocked readers ++ * ++ * read_lock() ++ * 1) Try fast path acquisition (reader BIAS is set) ++ * 2) Take lock->rtmutex.wait_lock which protects the writelocked flag ++ * 3) If !writelocked, acquire it for read ++ * 4) If writelocked, block on lock->rtmutex ++ * 5) unlock lock->rtmutex, goto 1) ++ * ++ * read_unlock() ++ * 1) Try fast path release (reader count != 1) ++ * 2) Wake the writer waiting in write_lock()#3 ++ * ++ * read_lock()#3 has the consequence, that rw locks on RT are not writer ++ * fair, but writers, which should be avoided in RT tasks (think tasklist ++ * lock), are subject to the rtmutex priority/DL inheritance mechanism. ++ * ++ * It's possible to make the rw locks writer fair by keeping a list of ++ * active readers. A blocked writer would force all newly incoming readers ++ * to block on the rtmutex, but the rtmutex would have to be proxy locked ++ * for one reader after the other. We can't use multi-reader inheritance ++ * because there is no way to support that with ++ * SCHED_DEADLINE. Implementing the one by one reader boosting/handover ++ * mechanism is a major surgery for a very dubious value. ++ * ++ * The risk of writer starvation is there, but the pathological use cases ++ * which trigger it are not necessarily the typical RT workloads. ++ */ ++ ++void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held semaphore: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif ++ atomic_set(&lock->readers, READER_BIAS); ++ rt_mutex_init(&lock->rtmutex); ++ lock->rtmutex.save_state = 1; ++} ++ ++int __read_rt_trylock(struct rt_rw_lock *lock) ++{ ++ int r, old; ++ ++ /* ++ * Increment reader count, if lock->readers < 0, i.e. READER_BIAS is ++ * set. ++ */ ++ for (r = atomic_read(&lock->readers); r < 0;) { ++ old = atomic_cmpxchg(&lock->readers, r, r + 1); ++ if (likely(old == r)) ++ return 1; ++ r = old; ++ } ++ return 0; ++} ++ ++void __sched __read_rt_lock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ struct rt_mutex_waiter waiter; ++ unsigned long flags; ++ ++ if (__read_rt_trylock(lock)) ++ return; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ /* ++ * Allow readers as long as the writer has not completely ++ * acquired the semaphore for write. ++ */ ++ if (atomic_read(&lock->readers) != WRITER_BIAS) { ++ atomic_inc(&lock->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return; ++ } ++ ++ /* ++ * Call into the slow lock path with the rtmutex->wait_lock ++ * held, so this can't result in the following race: ++ * ++ * Reader1 Reader2 Writer ++ * read_lock() ++ * write_lock() ++ * rtmutex_lock(m) ++ * swait() ++ * read_lock() ++ * unlock(m->wait_lock) ++ * read_unlock() ++ * swake() ++ * lock(m->wait_lock) ++ * lock->writelocked=true ++ * unlock(m->wait_lock) ++ * ++ * write_unlock() ++ * lock->writelocked=false ++ * rtmutex_unlock(m) ++ * read_lock() ++ * write_lock() ++ * rtmutex_lock(m) ++ * swait() ++ * rtmutex_lock(m) ++ * ++ * That would put Reader1 behind the writer waiting on ++ * Reader2 to call read_unlock() which might be unbound. ++ */ ++ rt_mutex_init_waiter(&waiter, false); ++ rt_spin_lock_slowlock_locked(m, &waiter, flags); ++ /* ++ * The slowlock() above is guaranteed to return with the rtmutex is ++ * now held, so there can't be a writer active. Increment the reader ++ * count and immediately drop the rtmutex again. ++ */ ++ atomic_inc(&lock->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ rt_spin_lock_slowunlock(m); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++void __read_rt_unlock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ struct task_struct *tsk; ++ ++ /* ++ * sem->readers can only hit 0 when a writer is waiting for the ++ * active readers to leave the critical region. ++ */ ++ if (!atomic_dec_and_test(&lock->readers)) ++ return; ++ ++ raw_spin_lock_irq(&m->wait_lock); ++ /* ++ * Wake the writer, i.e. the rtmutex owner. It might release the ++ * rtmutex concurrently in the fast path, but to clean up the rw ++ * lock it needs to acquire m->wait_lock. The worst case which can ++ * happen is a spurious wakeup. ++ */ ++ tsk = rt_mutex_owner(m); ++ if (tsk) ++ wake_up_process(tsk); ++ ++ raw_spin_unlock_irq(&m->wait_lock); ++} ++ ++static void __write_unlock_common(struct rt_rw_lock *lock, int bias, ++ unsigned long flags) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ ++ atomic_add(READER_BIAS - bias, &lock->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ rt_spin_lock_slowunlock(m); ++} ++ ++void __sched __write_rt_lock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ struct task_struct *self = current; ++ unsigned long flags; ++ ++ /* Take the rtmutex as a first step */ ++ __rt_spin_lock(m); ++ ++ /* Force readers into slow path */ ++ atomic_sub(READER_BIAS, &lock->readers); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ ++ for (;;) { ++ /* Have all readers left the critical region? */ ++ if (!atomic_read(&lock->readers)) { ++ atomic_set(&lock->readers, WRITER_BIAS); ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ raw_spin_unlock(&self->pi_lock); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return; ++ } ++ ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ ++ if (atomic_read(&lock->readers) != 0) ++ schedule(); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ } ++} ++ ++int __write_rt_trylock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ unsigned long flags; ++ ++ if (!__rt_mutex_trylock(m)) ++ return 0; ++ ++ atomic_sub(READER_BIAS, &lock->readers); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ if (!atomic_read(&lock->readers)) { ++ atomic_set(&lock->readers, WRITER_BIAS); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return 1; ++ } ++ __write_unlock_common(lock, 0, flags); ++ return 0; ++} ++ ++void __write_rt_unlock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ __write_unlock_common(lock, WRITER_BIAS, flags); ++} ++ ++/* Map the reader biased implementation */ ++static inline int do_read_rt_trylock(rwlock_t *rwlock) ++{ ++ return __read_rt_trylock(rwlock); ++} ++ ++static inline int do_write_rt_trylock(rwlock_t *rwlock) ++{ ++ return __write_rt_trylock(rwlock); ++} ++ ++static inline void do_read_rt_lock(rwlock_t *rwlock) ++{ ++ __read_rt_lock(rwlock); ++} ++ ++static inline void do_write_rt_lock(rwlock_t *rwlock) ++{ ++ __write_rt_lock(rwlock); ++} ++ ++static inline void do_read_rt_unlock(rwlock_t *rwlock) ++{ ++ __read_rt_unlock(rwlock); ++} ++ ++static inline void do_write_rt_unlock(rwlock_t *rwlock) ++{ ++ __write_rt_unlock(rwlock); ++} ++ ++static inline void do_rwlock_rt_init(rwlock_t *rwlock, const char *name, ++ struct lock_class_key *key) ++{ ++ __rwlock_biased_rt_init(rwlock, name, key); ++} ++ ++int __lockfunc rt_read_can_lock(rwlock_t *rwlock) ++{ ++ return atomic_read(&rwlock->readers) < 0; ++} ++ ++int __lockfunc rt_write_can_lock(rwlock_t *rwlock) ++{ ++ return atomic_read(&rwlock->readers) == READER_BIAS; ++} ++ ++/* ++ * The common functions which get wrapped into the rwlock API. ++ */ ++int __lockfunc rt_read_trylock(rwlock_t *rwlock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = do_read_rt_trylock(rwlock); ++ if (ret) ++ rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_read_trylock); ++ ++int __lockfunc rt_write_trylock(rwlock_t *rwlock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = do_write_rt_trylock(rwlock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock); ++ ++void __lockfunc rt_read_lock(rwlock_t *rwlock) ++{ ++ migrate_disable(); ++ rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); ++ do_read_rt_lock(rwlock); ++} ++EXPORT_SYMBOL(rt_read_lock); ++ ++void __lockfunc rt_write_lock(rwlock_t *rwlock) ++{ ++ migrate_disable(); ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ do_write_rt_lock(rwlock); ++} ++EXPORT_SYMBOL(rt_write_lock); ++ ++void __lockfunc rt_read_unlock(rwlock_t *rwlock) ++{ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ do_read_rt_unlock(rwlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_read_unlock); ++ ++void __lockfunc rt_write_unlock(rwlock_t *rwlock) ++{ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ do_write_rt_unlock(rwlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_write_unlock); ++ ++void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) ++{ ++ do_rwlock_rt_init(rwlock, name, key); ++} ++EXPORT_SYMBOL(__rt_rwlock_init); +-- +2.36.1 + diff --git a/debian/patches-rt/0146-rtmutex-rwlock-preserve-state-like-a-sleeping-lock.patch b/debian/patches-rt/0146-rtmutex-rwlock-preserve-state-like-a-sleeping-lock.patch new file mode 100644 index 000000000..44b53bba1 --- /dev/null +++ b/debian/patches-rt/0146-rtmutex-rwlock-preserve-state-like-a-sleeping-lock.patch @@ -0,0 +1,33 @@ +From 0e2b5eb41fc6820a80428de4a73ede6f47d74cf0 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 11 Jan 2019 21:16:31 +0100 +Subject: [PATCH 146/347] rtmutex/rwlock: preserve state like a sleeping lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The rwlock is spinning while acquiring a lock. Therefore it must become +a sleeping lock on RT and preserve its task state while sleeping and +waiting for the lock to become available. + +Reported-by: Joe Korty <Joe.Korty@concurrent-rt.com> +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rwlock-rt.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c +index aebb7ce25bc6..8f90afe111ce 100644 +--- a/kernel/locking/rwlock-rt.c ++++ b/kernel/locking/rwlock-rt.c +@@ -128,7 +128,7 @@ void __sched __read_rt_lock(struct rt_rw_lock *lock) + * That would put Reader1 behind the writer waiting on + * Reader2 to call read_unlock() which might be unbound. + */ +- rt_mutex_init_waiter(&waiter, false); ++ rt_mutex_init_waiter(&waiter, true); + rt_spin_lock_slowlock_locked(m, &waiter, flags); + /* + * The slowlock() above is guaranteed to return with the rtmutex is +-- +2.36.1 + diff --git a/debian/patches-rt/0147-rtmutex-wire-up-RT-s-locking.patch b/debian/patches-rt/0147-rtmutex-wire-up-RT-s-locking.patch new file mode 100644 index 000000000..8110605a3 --- /dev/null +++ b/debian/patches-rt/0147-rtmutex-wire-up-RT-s-locking.patch @@ -0,0 +1,271 @@ +From d334127aee6c64a7cdf5e5d3420666bcfdeb8ba6 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 12 Oct 2017 17:31:14 +0200 +Subject: [PATCH 147/347] rtmutex: wire up RT's locking +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/mutex.h | 20 +++++++++++++------- + include/linux/rwsem.h | 11 +++++++++++ + include/linux/spinlock.h | 12 +++++++++++- + include/linux/spinlock_api_smp.h | 4 +++- + include/linux/spinlock_types.h | 11 ++++++++--- + kernel/locking/Makefile | 9 ++++++++- + kernel/locking/spinlock.c | 7 +++++++ + kernel/locking/spinlock_debug.c | 5 +++++ + 8 files changed, 66 insertions(+), 13 deletions(-) + +diff --git a/include/linux/mutex.h b/include/linux/mutex.h +index 8f7cdf83f359..6aa217c6e3ca 100644 +--- a/include/linux/mutex.h ++++ b/include/linux/mutex.h +@@ -22,6 +22,17 @@ + + struct ww_acquire_ctx; + ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ ++ , .dep_map = { .name = #lockname } ++#else ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) ++#endif ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include <linux/mutex_rt.h> ++#else ++ + /* + * Simple, straightforward mutexes with strict semantics: + * +@@ -118,13 +129,6 @@ do { \ + __mutex_init((mutex), #mutex, &__key); \ + } while (0) + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ +- , .dep_map = { .name = #lockname } +-#else +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +-#endif +- + #define __MUTEX_INITIALIZER(lockname) \ + { .owner = ATOMIC_LONG_INIT(0) \ + , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ +@@ -229,4 +233,6 @@ mutex_trylock_recursive(struct mutex *lock) + return mutex_trylock(lock); + } + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* __LINUX_MUTEX_H */ +diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h +index ab93b6eae696..b1e32373f44f 100644 +--- a/include/linux/rwsem.h ++++ b/include/linux/rwsem.h +@@ -20,6 +20,10 @@ + #include <linux/osq_lock.h> + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#include <linux/rwsem_rt.h> ++#else /* PREEMPT_RT_FULL */ ++ + struct rw_semaphore; + + #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +@@ -114,6 +118,13 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) + return !list_empty(&sem->wait_list); + } + ++#endif /* !PREEMPT_RT_FULL */ ++ ++/* ++ * The functions below are the same for all rwsem implementations including ++ * the RT specific variant. ++ */ ++ + /* + * lock for reading + */ +diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h +index e089157dcf97..5f5ad0630a26 100644 +--- a/include/linux/spinlock.h ++++ b/include/linux/spinlock.h +@@ -298,7 +298,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) + }) + + /* Include rwlock functions */ +-#include <linux/rwlock.h> ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include <linux/rwlock_rt.h> ++#else ++# include <linux/rwlock.h> ++#endif + + /* + * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: +@@ -309,6 +313,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) + # include <linux/spinlock_api_up.h> + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include <linux/spinlock_rt.h> ++#else /* PREEMPT_RT_FULL */ ++ + /* + * Map the spin_lock functions to the raw variants for PREEMPT_RT=n + */ +@@ -429,6 +437,8 @@ static __always_inline int spin_is_contended(spinlock_t *lock) + + #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) + ++#endif /* !PREEMPT_RT_FULL */ ++ + /* + * Pull the atomic_t declaration: + * (asm-mips/atomic.h needs above definitions) +diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h +index 42dfab89e740..29d99ae5a8ab 100644 +--- a/include/linux/spinlock_api_smp.h ++++ b/include/linux/spinlock_api_smp.h +@@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) + return 0; + } + +-#include <linux/rwlock_api_smp.h> ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include <linux/rwlock_api_smp.h> ++#endif + + #endif /* __LINUX_SPINLOCK_API_SMP_H */ +diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h +index 5c8664d57fb8..10bac715ea96 100644 +--- a/include/linux/spinlock_types.h ++++ b/include/linux/spinlock_types.h +@@ -11,8 +11,13 @@ + + #include <linux/spinlock_types_raw.h> + +-#include <linux/spinlock_types_nort.h> +- +-#include <linux/rwlock_types.h> ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include <linux/spinlock_types_nort.h> ++# include <linux/rwlock_types.h> ++#else ++# include <linux/rtmutex.h> ++# include <linux/spinlock_types_rt.h> ++# include <linux/rwlock_types_rt.h> ++#endif + + #endif /* __LINUX_SPINLOCK_TYPES_H */ +diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile +index 392c7f23af76..c0bf04b6b965 100644 +--- a/kernel/locking/Makefile ++++ b/kernel/locking/Makefile +@@ -3,7 +3,7 @@ + # and is generally not a function of system call inputs. + KCOV_INSTRUMENT := n + +-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o ++obj-y += semaphore.o percpu-rwsem.o + + ifdef CONFIG_FUNCTION_TRACER + CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +@@ -12,7 +12,11 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE) + CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) + endif + ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) ++obj-y += mutex.o + obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o ++endif ++obj-y += rwsem.o + obj-$(CONFIG_LOCKDEP) += lockdep.o + ifeq ($(CONFIG_PROC_FS),y) + obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +@@ -25,8 +29,11 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o + obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) + obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o + obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o ++endif ++obj-$(CONFIG_PREEMPT_RT_FULL) += mutex-rt.o rwsem-rt.o rwlock-rt.o + obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o + obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o + obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o +diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c +index 936f3d14dd6b..e89b70f474af 100644 +--- a/kernel/locking/spinlock.c ++++ b/kernel/locking/spinlock.c +@@ -117,8 +117,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ + * __[spin|read|write]_lock_bh() + */ + BUILD_LOCK_OPS(spin, raw_spinlock); ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + BUILD_LOCK_OPS(read, rwlock); + BUILD_LOCK_OPS(write, rwlock); ++#endif + + #endif + +@@ -202,6 +205,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) + EXPORT_SYMBOL(_raw_spin_unlock_bh); + #endif + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #ifndef CONFIG_INLINE_READ_TRYLOCK + int __lockfunc _raw_read_trylock(rwlock_t *lock) + { +@@ -346,6 +351,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) + EXPORT_SYMBOL(_raw_write_unlock_bh); + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #ifdef CONFIG_DEBUG_LOCK_ALLOC + + void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) +diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c +index 03595c29c566..d63df281b495 100644 +--- a/kernel/locking/spinlock_debug.c ++++ b/kernel/locking/spinlock_debug.c +@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, + + EXPORT_SYMBOL(__raw_spin_lock_init); + ++#ifndef CONFIG_PREEMPT_RT_FULL + void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) + { +@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name, + } + + EXPORT_SYMBOL(__rwlock_init); ++#endif + + static void spin_dump(raw_spinlock_t *lock, const char *msg) + { +@@ -135,6 +137,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock) + arch_spin_unlock(&lock->raw_lock); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static void rwlock_bug(rwlock_t *lock, const char *msg) + { + if (!debug_locks_off()) +@@ -224,3 +227,5 @@ void do_raw_write_unlock(rwlock_t *lock) + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); + } ++ ++#endif +-- +2.36.1 + diff --git a/debian/patches-rt/0148-rtmutex-add-ww_mutex-addon-for-mutex-rt.patch b/debian/patches-rt/0148-rtmutex-add-ww_mutex-addon-for-mutex-rt.patch new file mode 100644 index 000000000..86e8aed22 --- /dev/null +++ b/debian/patches-rt/0148-rtmutex-add-ww_mutex-addon-for-mutex-rt.patch @@ -0,0 +1,445 @@ +From d33397686c7cab5c3c263709534ec1e58ac42b54 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 12 Oct 2017 17:34:38 +0200 +Subject: [PATCH 148/347] rtmutex: add ww_mutex addon for mutex-rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 271 ++++++++++++++++++++++++++++++-- + kernel/locking/rtmutex_common.h | 2 + + kernel/locking/rwsem-rt.c | 2 +- + 3 files changed, 261 insertions(+), 14 deletions(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 5ff2189f1199..cc47d5aa93a1 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -23,6 +23,7 @@ + #include <linux/sched/wake_q.h> + #include <linux/sched/debug.h> + #include <linux/timer.h> ++#include <linux/ww_mutex.h> + + #include "rtmutex_common.h" + +@@ -1245,6 +1246,40 @@ EXPORT_SYMBOL(__rt_spin_lock_init); + + #endif /* PREEMPT_RT_FULL */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); ++ ++ if (!hold_ctx) ++ return 0; ++ ++ if (unlikely(ctx == hold_ctx)) ++ return -EALREADY; ++ ++ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && ++ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(ctx->contending_lock); ++ ctx->contending_lock = ww; ++#endif ++ return -EDEADLK; ++ } ++ ++ return 0; ++} ++#else ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ BUG(); ++ return 0; ++} ++ ++#endif ++ + static inline int + try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +@@ -1523,7 +1558,8 @@ void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) + static int __sched + __rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- struct rt_mutex_waiter *waiter) ++ struct rt_mutex_waiter *waiter, ++ struct ww_acquire_ctx *ww_ctx) + { + int ret = 0; + +@@ -1541,6 +1577,12 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, + break; + } + ++ if (ww_ctx && ww_ctx->acquired > 0) { ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ if (ret) ++ break; ++ } ++ + raw_spin_unlock_irq(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); +@@ -1575,16 +1617,106 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock, + } + } + ++static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++#ifdef CONFIG_DEBUG_MUTEXES ++ /* ++ * If this WARN_ON triggers, you used ww_mutex_lock to acquire, ++ * but released with a normal mutex_unlock in this call. ++ * ++ * This should never happen, always use ww_mutex_unlock. ++ */ ++ DEBUG_LOCKS_WARN_ON(ww->ctx); ++ ++ /* ++ * Not quite done after calling ww_acquire_done() ? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); ++ ++ if (ww_ctx->contending_lock) { ++ /* ++ * After -EDEADLK you tried to ++ * acquire a different ww_mutex? Bad! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); ++ ++ /* ++ * You called ww_mutex_lock after receiving -EDEADLK, ++ * but 'forgot' to unlock everything else first? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); ++ ww_ctx->contending_lock = NULL; ++ } ++ ++ /* ++ * Naughty, using a different class will lead to undefined behavior! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); ++#endif ++ ww_ctx->acquired++; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct rt_mutex_waiter *waiter, *n; ++ ++ /* ++ * This branch gets optimized out for the common case, ++ * and is only important for ww_mutex_lock. ++ */ ++ ww_mutex_lock_acquired(ww, ww_ctx); ++ ww->ctx = ww_ctx; ++ ++ /* ++ * Give any possible sleeping processes the chance to wake up, ++ * so they can recheck if they have to back off. ++ */ ++ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters.rb_root, ++ tree_entry) { ++ /* XXX debug rt mutex waiter wakeup */ ++ ++ BUG_ON(waiter->lock != lock); ++ rt_mutex_wake_waiter(waiter); ++ } ++} ++ ++#else ++ ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++#endif ++ + int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter) + { + int ret; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (ww_ctx) { ++ struct ww_mutex *ww; ++ ++ ww = container_of(lock, struct ww_mutex, base.lock); ++ if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) ++ return -EALREADY; ++ } ++#endif ++ + /* Try to acquire the lock again: */ +- if (try_to_take_rt_mutex(lock, current, NULL)) ++ if (try_to_take_rt_mutex(lock, current, NULL)) { ++ if (ww_ctx) ++ ww_mutex_account_lock(lock, ww_ctx); + return 0; ++ } + + set_current_state(state); + +@@ -1594,14 +1726,24 @@ int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + + ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk); + +- if (likely(!ret)) ++ if (likely(!ret)) { + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, waiter, ++ ww_ctx); ++ } else if (ww_ctx) { ++ /* ww_mutex received EDEADLK, let it become EALREADY */ ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ BUG_ON(!ret); ++ } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + remove_waiter(lock, waiter); +- rt_mutex_handle_deadlock(ret, chwalk, waiter); ++ /* ww_mutex wants to report EDEADLK/EALREADY, let it */ ++ if (!ww_ctx) ++ rt_mutex_handle_deadlock(ret, chwalk, waiter); ++ } else if (ww_ctx) { ++ ww_mutex_account_lock(lock, ww_ctx); + } + + /* +@@ -1618,7 +1760,8 @@ int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + static int __sched + rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx) + { + struct rt_mutex_waiter waiter; + unsigned long flags; +@@ -1636,7 +1779,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); + +- ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, &waiter); ++ ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx, ++ &waiter); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + +@@ -1766,29 +1910,33 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, + */ + static inline int + rt_mutex_fastlock(struct rt_mutex *lock, int state, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + +- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); ++ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx); + } + + static inline int + rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (chwalk == RT_MUTEX_MIN_CHAINWALK && + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + +- return slowfn(lock, state, timeout, chwalk); ++ return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + + static inline int +@@ -1833,7 +1981,7 @@ rt_mutex_fastunlock(struct rt_mutex *lock, + int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) + { + might_sleep(); +- return rt_mutex_fastlock(lock, state, rt_mutex_slowlock); ++ return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock); + } + + /** +@@ -1953,6 +2101,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_MIN_CHAINWALK, ++ NULL, + rt_mutex_slowlock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); +@@ -2299,7 +2448,7 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + raw_spin_lock_irq(&lock->wait_lock); + /* sleep on the mutex */ + set_current_state(TASK_INTERRUPTIBLE); +- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); ++ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. +@@ -2384,3 +2533,99 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, + + return cleanup; + } ++ ++static inline int ++ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ++ unsigned tmp; ++ ++ if (ctx->deadlock_inject_countdown-- == 0) { ++ tmp = ctx->deadlock_inject_interval; ++ if (tmp > UINT_MAX/4) ++ tmp = UINT_MAX; ++ else ++ tmp = tmp*2 + tmp + tmp/2; ++ ++ ctx->deadlock_inject_interval = tmp; ++ ctx->deadlock_inject_countdown = tmp; ++ ctx->contending_lock = lock; ++ ++ ww_mutex_unlock(lock); ++ ++ return -EDEADLK; ++ } ++#endif ++ ++ return 0; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++int __sched ++ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, ++ ctx ? &ctx->dep_map : NULL, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ++ ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ctx && ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); ++ ++int __sched ++ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, ++ ctx ? &ctx->dep_map : NULL, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ++ ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ctx && ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(ww_mutex_lock); ++ ++void __sched ww_mutex_unlock(struct ww_mutex *lock) ++{ ++ int nest = !!lock->ctx; ++ ++ /* ++ * The unlocking fastpath is the 0->1 transition from 'locked' ++ * into 'unlocked' state: ++ */ ++ if (nest) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); ++#endif ++ if (lock->ctx->acquired > 0) ++ lock->ctx->acquired--; ++ lock->ctx = NULL; ++ } ++ ++ mutex_release(&lock->base.dep_map, nest, _RET_IP_); ++ __rt_mutex_unlock(&lock->base.lock); ++} ++EXPORT_SYMBOL(ww_mutex_unlock); ++ ++int __rt_mutex_owner_current(struct rt_mutex *lock) ++{ ++ return rt_mutex_owner(lock) == current; ++} ++EXPORT_SYMBOL(__rt_mutex_owner_current); ++#endif +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 7c1dd1bd95c7..8e0c592273e6 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -164,6 +164,7 @@ extern void rt_mutex_postunlock(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q); + + /* RW semaphore special interface */ ++struct ww_acquire_ctx; + + extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); + extern int __rt_mutex_trylock(struct rt_mutex *lock); +@@ -171,6 +172,7 @@ extern void __rt_mutex_unlock(struct rt_mutex *lock); + int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter); + void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, +diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c +index 7d3c5cf3d23d..660e22caf709 100644 +--- a/kernel/locking/rwsem-rt.c ++++ b/kernel/locking/rwsem-rt.c +@@ -131,7 +131,7 @@ static int __sched __down_read_common(struct rw_semaphore *sem, int state) + */ + rt_mutex_init_waiter(&waiter, false); + ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK, +- &waiter); ++ NULL, &waiter); + /* + * The slowlock() above is guaranteed to return with the rtmutex (for + * ret = 0) is now held, so there can't be a writer active. Increment +-- +2.36.1 + diff --git a/debian/patches-rt/0149-kconfig-Add-PREEMPT_RT_FULL.patch b/debian/patches-rt/0149-kconfig-Add-PREEMPT_RT_FULL.patch new file mode 100644 index 000000000..a9ee49334 --- /dev/null +++ b/debian/patches-rt/0149-kconfig-Add-PREEMPT_RT_FULL.patch @@ -0,0 +1,69 @@ +From 484511a754ae9320cc61d583c24e811d3cc476ff Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 29 Jun 2011 14:58:57 +0200 +Subject: [PATCH 149/347] kconfig: Add PREEMPT_RT_FULL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Introduce the final symbol for PREEMPT_RT_FULL. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + init/Makefile | 2 +- + kernel/Kconfig.preempt | 8 ++++++++ + scripts/mkcompile_h | 4 +++- + 3 files changed, 12 insertions(+), 2 deletions(-) + +diff --git a/init/Makefile b/init/Makefile +index a3e5ce2bcf08..7779232563ae 100644 +--- a/init/Makefile ++++ b/init/Makefile +@@ -34,4 +34,4 @@ $(obj)/version.o: include/generated/compile.h + include/generated/compile.h: FORCE + @$($(quiet)chk_compile.h) + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ +- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" ++ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" +diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt +index 027db5976c2f..907d72b3ba95 100644 +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -69,6 +69,14 @@ config PREEMPT_RTB + enables changes which are preliminary for the full preemptible + RT kernel. + ++config PREEMPT_RT_FULL ++ bool "Fully Preemptible Kernel (RT)" ++ depends on IRQ_FORCED_THREADING ++ select PREEMPT_RT_BASE ++ select PREEMPT_RCU ++ help ++ All and everything ++ + endchoice + + config PREEMPT_COUNT +diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h +index 662fe19da990..089200debc38 100755 +--- a/scripts/mkcompile_h ++++ b/scripts/mkcompile_h +@@ -5,7 +5,8 @@ TARGET=$1 + ARCH=$2 + SMP=$3 + PREEMPT=$4 +-CC=$5 ++RT=$5 ++CC=$6 + + vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } + +@@ -53,6 +54,7 @@ UTS_VERSION="#$VERSION" + CONFIG_FLAGS="" + if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi + if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi ++if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi + UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" + + # Truncate to maximum length +-- +2.36.1 + diff --git a/debian/patches-rt/0150-locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch b/debian/patches-rt/0150-locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch new file mode 100644 index 000000000..5404d73d6 --- /dev/null +++ b/debian/patches-rt/0150-locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch @@ -0,0 +1,81 @@ +From d6b1373a76eff772848ccbfed73baf94c807e464 Mon Sep 17 00:00:00 2001 +From: Mikulas Patocka <mpatocka@redhat.com> +Date: Mon, 13 Nov 2017 12:56:53 -0500 +Subject: [PATCH 150/347] locking/rt-mutex: fix deadlock in device mapper / + block-IO +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When some block device driver creates a bio and submits it to another +block device driver, the bio is added to current->bio_list (in order to +avoid unbounded recursion). + +However, this queuing of bios can cause deadlocks, in order to avoid them, +device mapper registers a function flush_current_bio_list. This function +is called when device mapper driver blocks. It redirects bios queued on +current->bio_list to helper workqueues, so that these bios can proceed +even if the driver is blocked. + +The problem with CONFIG_PREEMPT_RT_FULL is that when the device mapper +driver blocks, it won't call flush_current_bio_list (because +tsk_is_pi_blocked returns true in sched_submit_work), so deadlocks in +block device stack can happen. + +Note that we can't call blk_schedule_flush_plug if tsk_is_pi_blocked +returns true - that would cause +BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in +task_blocks_on_rt_mutex when flush_current_bio_list attempts to take a +spinlock. + +So the proper fix is to call blk_schedule_flush_plug in rt_mutex_fastlock, +when fast acquire failed and when the task is about to block. + +CC: stable-rt@vger.kernel.org +[bigeasy: The deadlock is not device-mapper specific, it can also occur + in plain EXT4] +Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 13 +++++++++++++ + 1 file changed, 13 insertions(+) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index cc47d5aa93a1..721e3a4916d9 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -24,6 +24,7 @@ + #include <linux/sched/debug.h> + #include <linux/timer.h> + #include <linux/ww_mutex.h> ++#include <linux/blkdev.h> + + #include "rtmutex_common.h" + +@@ -1919,6 +1920,15 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state, + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + ++ /* ++ * If rt_mutex blocks, the function sched_submit_work will not call ++ * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true). ++ * We must call blk_schedule_flush_plug here, if we don't call it, ++ * a deadlock in I/O may happen. ++ */ ++ if (unlikely(blk_needs_flush_plug(current))) ++ blk_schedule_flush_plug(current); ++ + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx); + } + +@@ -1936,6 +1946,9 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + ++ if (unlikely(blk_needs_flush_plug(current))) ++ blk_schedule_flush_plug(current); ++ + return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0151-locking-rt-mutex-Flush-block-plug-on-__down_read.patch b/debian/patches-rt/0151-locking-rt-mutex-Flush-block-plug-on-__down_read.patch new file mode 100644 index 000000000..3128f971d --- /dev/null +++ b/debian/patches-rt/0151-locking-rt-mutex-Flush-block-plug-on-__down_read.patch @@ -0,0 +1,46 @@ +From 229f57115cd91a8632a85152d6e43e781ebd367e Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Fri, 4 Jan 2019 15:33:21 -0500 +Subject: [PATCH 151/347] locking/rt-mutex: Flush block plug on __down_read() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +__down_read() bypasses the rtmutex frontend to call +rt_mutex_slowlock_locked() directly, and thus it needs to call +blk_schedule_flush_flug() itself. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rwsem-rt.c | 9 +++++++++ + 1 file changed, 9 insertions(+) + +diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c +index 660e22caf709..f518495bd6cc 100644 +--- a/kernel/locking/rwsem-rt.c ++++ b/kernel/locking/rwsem-rt.c +@@ -1,5 +1,6 @@ + /* + */ ++#include <linux/blkdev.h> + #include <linux/rwsem.h> + #include <linux/sched/debug.h> + #include <linux/sched/signal.h> +@@ -87,6 +88,14 @@ static int __sched __down_read_common(struct rw_semaphore *sem, int state) + + if (__down_read_trylock(sem)) + return 0; ++ /* ++ * If rt_mutex blocks, the function sched_submit_work will not call ++ * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true). ++ * We must call blk_schedule_flush_plug here, if we don't call it, ++ * a deadlock in I/O may happen. ++ */ ++ if (unlikely(blk_needs_flush_plug(current))) ++ blk_schedule_flush_plug(current); + + might_sleep(); + raw_spin_lock_irq(&m->wait_lock); +-- +2.36.1 + diff --git a/debian/patches-rt/0152-locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch b/debian/patches-rt/0152-locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch new file mode 100644 index 000000000..d3b273dbb --- /dev/null +++ b/debian/patches-rt/0152-locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch @@ -0,0 +1,39 @@ +From b30a729eace6fa1b27e10316b55cfe2d0c7dbf9a Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 16 Nov 2017 16:48:48 +0100 +Subject: [PATCH 152/347] locking/rtmutex: re-init the wait_lock in + rt_mutex_init_proxy_locked() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +We could provide a key-class for the lockdep (and fixup all callers) or +move the init to all callers (like it was) in order to avoid lockdep +seeing a double-lock of the wait_lock. + +Reported-by: Fernando Lopez-Lezcano <nando@ccrma.Stanford.EDU> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/locking/rtmutex.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 721e3a4916d9..11bcae2184c4 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -2281,6 +2281,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner) + { + __rt_mutex_init(lock, NULL, NULL); ++#ifdef CONFIG_DEBUG_SPINLOCK ++ /* ++ * get another key class for the wait_lock. LOCK_PI and UNLOCK_PI is ++ * holding the ->wait_lock of the proxy_lock while unlocking a sleeping ++ * lock. ++ */ ++ raw_spin_lock_init(&lock->wait_lock); ++#endif + debug_rt_mutex_proxy_lock(lock, proxy_owner); + rt_mutex_set_owner(lock, proxy_owner); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0153-ptrace-fix-ptrace-vs-tasklist_lock-race.patch b/debian/patches-rt/0153-ptrace-fix-ptrace-vs-tasklist_lock-race.patch new file mode 100644 index 000000000..fa509ce15 --- /dev/null +++ b/debian/patches-rt/0153-ptrace-fix-ptrace-vs-tasklist_lock-race.patch @@ -0,0 +1,166 @@ +From 590484060b22c2d41b6e33ab142e7bf68ad3d85a Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 29 Aug 2013 18:21:04 +0200 +Subject: [PATCH 153/347] ptrace: fix ptrace vs tasklist_lock race +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +As explained by Alexander Fyodorov <halcy@yandex.ru>: + +|read_lock(&tasklist_lock) in ptrace_stop() is converted to mutex on RT kernel, +|and it can remove __TASK_TRACED from task->state (by moving it to +|task->saved_state). If parent does wait() on child followed by a sys_ptrace +|call, the following race can happen: +| +|- child sets __TASK_TRACED in ptrace_stop() +|- parent does wait() which eventually calls wait_task_stopped() and returns +| child's pid +|- child blocks on read_lock(&tasklist_lock) in ptrace_stop() and moves +| __TASK_TRACED flag to saved_state +|- parent calls sys_ptrace, which calls ptrace_check_attach() and wait_task_inactive() + +The patch is based on his initial patch where an additional check is +added in case the __TASK_TRACED moved to ->saved_state. The pi_lock is +taken in case the caller is interrupted between looking into ->state and +->saved_state. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/sched.h | 49 +++++++++++++++++++++++++++++++++++++++---- + kernel/ptrace.c | 9 +++++++- + kernel/sched/core.c | 17 +++++++++++++-- + 3 files changed, 68 insertions(+), 7 deletions(-) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index e4e206a1e7dd..5374ade34b87 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -101,12 +101,8 @@ struct task_group; + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) + +-#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) +- + #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) + +-#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) +- + #define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0 && \ + (task->state & TASK_NOLOAD) == 0) +@@ -1717,6 +1713,51 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++static inline bool __task_is_stopped_or_traced(struct task_struct *task) ++{ ++ if (task->state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#endif ++ return false; ++} ++ ++static inline bool task_is_stopped_or_traced(struct task_struct *task) ++{ ++ bool traced_stopped; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ traced_stopped = __task_is_stopped_or_traced(task); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++#else ++ traced_stopped = __task_is_stopped_or_traced(task); ++#endif ++ return traced_stopped; ++} ++ ++static inline bool task_is_traced(struct task_struct *task) ++{ ++ bool traced = false; ++ ++ if (task->state & __TASK_TRACED) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* in case the task is sleeping on tasklist_lock */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->state & __TASK_TRACED) ++ traced = true; ++ else if (task->saved_state & __TASK_TRACED) ++ traced = true; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ return traced; ++} ++ + /* + * cond_resched() and cond_resched_lock(): latency reduction via + * explicit rescheduling in places that are safe. The return +diff --git a/kernel/ptrace.c b/kernel/ptrace.c +index 8a98e3e78c70..9c59e523f3cd 100644 +--- a/kernel/ptrace.c ++++ b/kernel/ptrace.c +@@ -190,7 +190,14 @@ static bool ptrace_freeze_traced(struct task_struct *task) + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && + !__fatal_signal_pending(task)) { +- task->state = __TASK_TRACED; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ if (task->state & __TASK_TRACED) ++ task->state = __TASK_TRACED; ++ else ++ task->saved_state = __TASK_TRACED; ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 1f450a7649f0..9494e2007118 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1349,6 +1349,18 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, + } + #endif /* CONFIG_NUMA_BALANCING */ + ++static bool check_task_state(struct task_struct *p, long match_state) ++{ ++ bool match = false; ++ ++ raw_spin_lock_irq(&p->pi_lock); ++ if (p->state == match_state || p->saved_state == match_state) ++ match = true; ++ raw_spin_unlock_irq(&p->pi_lock); ++ ++ return match; ++} ++ + /* + * wait_task_inactive - wait for a thread to unschedule. + * +@@ -1393,7 +1405,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { +- if (match_state && unlikely(p->state != match_state)) ++ if (match_state && !check_task_state(p, match_state)) + return 0; + cpu_relax(); + } +@@ -1408,7 +1420,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) + running = task_running(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; +- if (!match_state || p->state == match_state) ++ if (!match_state || p->state == match_state || ++ p->saved_state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &rf); + +-- +2.36.1 + diff --git a/debian/patches-rt/0154-rtmutex-annotate-sleeping-lock-context.patch b/debian/patches-rt/0154-rtmutex-annotate-sleeping-lock-context.patch new file mode 100644 index 000000000..916d8d802 --- /dev/null +++ b/debian/patches-rt/0154-rtmutex-annotate-sleeping-lock-context.patch @@ -0,0 +1,308 @@ +From ac520c8f628b0eeff2af71b77289199262510960 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 21 Sep 2017 14:25:13 +0200 +Subject: [PATCH 154/347] rtmutex: annotate sleeping lock context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The RCU code complains on schedule() within a rcu_readlock() section. +The valid scenario on -RT is if a sleeping is held. In order to suppress +the warning the mirgrate_disable counter was used to identify the +invocation of schedule() due to lock contention. + +Grygorii Strashko report that during CPU hotplug we might see the +warning via + rt_spin_lock() -> migrate_disable() -> pin_current_cpu() -> __read_rt_lock() + +because the counter is not yet set. +It is also possible to trigger the warning from cpu_chill() +(seen on a kblockd_mod_delayed_work_on() caller). + +To address this RCU warning I annotate the sleeping lock context. The +counter is incremented before migrate_disable() so the warning Grygorii +should not trigger anymore. Additionally I use that counter in +cpu_chill() to avoid the RCU warning from there. + +Reported-by: Grygorii Strashko <grygorii.strashko@ti.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/preempt.h | 9 ++++++++ + include/linux/sched.h | 26 ++++++++++++++++++++++ + kernel/locking/rtmutex.c | 12 ++++++++-- + kernel/locking/rwlock-rt.c | 18 +++++++++++---- + kernel/rcu/tree_plugin.h | 6 ++++- + kernel/sched/core.c | 45 ++++++++++++++++++++++++++++++++++++++ + 6 files changed, 109 insertions(+), 7 deletions(-) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index 27c3176d88d2..9eafc34898b4 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -211,6 +211,15 @@ extern void migrate_enable(void); + + int __migrate_disabled(struct task_struct *p); + ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++ ++extern void migrate_disable(void); ++extern void migrate_enable(void); ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++ return 0; ++} ++ + #else + #define migrate_disable() barrier() + #define migrate_enable() barrier() +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 5374ade34b87..4f8fcba23c1d 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -673,6 +673,15 @@ struct task_struct { + # ifdef CONFIG_SCHED_DEBUG + int migrate_disable_atomic; + # endif ++ ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++ int migrate_disable; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int sleeping_lock; + #endif + + #ifdef CONFIG_PREEMPT_RCU +@@ -1810,6 +1819,23 @@ static __always_inline bool need_resched(void) + return unlikely(tif_need_resched()); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline void sleeping_lock_inc(void) ++{ ++ current->sleeping_lock++; ++} ++ ++static inline void sleeping_lock_dec(void) ++{ ++ current->sleeping_lock--; ++} ++ ++#else ++ ++static inline void sleeping_lock_inc(void) { } ++static inline void sleeping_lock_dec(void) { } ++#endif ++ + /* + * Wrappers for p->thread_info->cpu access. No-op on UP. + */ +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 11bcae2184c4..ded2296f848a 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1141,6 +1141,7 @@ void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) + + void __lockfunc rt_spin_lock(spinlock_t *lock) + { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +@@ -1155,6 +1156,7 @@ void __lockfunc __rt_spin_lock(struct rt_mutex *lock) + #ifdef CONFIG_DEBUG_LOCK_ALLOC + void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) + { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +@@ -1168,6 +1170,7 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock) + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); + migrate_enable(); ++ sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_spin_unlock); + +@@ -1193,12 +1196,15 @@ int __lockfunc rt_spin_trylock(spinlock_t *lock) + { + int ret; + ++ sleeping_lock_inc(); + migrate_disable(); + ret = __rt_mutex_trylock(&lock->lock); +- if (ret) ++ if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); +- else ++ } else { + migrate_enable(); ++ sleeping_lock_dec(); ++ } + return ret; + } + EXPORT_SYMBOL(rt_spin_trylock); +@@ -1210,6 +1216,7 @@ int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) + local_bh_disable(); + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else +@@ -1225,6 +1232,7 @@ int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) + *flags = 0; + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } +diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c +index 8f90afe111ce..c3b91205161c 100644 +--- a/kernel/locking/rwlock-rt.c ++++ b/kernel/locking/rwlock-rt.c +@@ -305,12 +305,15 @@ int __lockfunc rt_read_trylock(rwlock_t *rwlock) + { + int ret; + ++ sleeping_lock_inc(); + migrate_disable(); + ret = do_read_rt_trylock(rwlock); +- if (ret) ++ if (ret) { + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); +- else ++ } else { + migrate_enable(); ++ sleeping_lock_dec(); ++ } + return ret; + } + EXPORT_SYMBOL(rt_read_trylock); +@@ -319,18 +322,22 @@ int __lockfunc rt_write_trylock(rwlock_t *rwlock) + { + int ret; + ++ sleeping_lock_inc(); + migrate_disable(); + ret = do_write_rt_trylock(rwlock); +- if (ret) ++ if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); +- else ++ } else { + migrate_enable(); ++ sleeping_lock_dec(); ++ } + return ret; + } + EXPORT_SYMBOL(rt_write_trylock); + + void __lockfunc rt_read_lock(rwlock_t *rwlock) + { ++ sleeping_lock_inc(); + migrate_disable(); + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + do_read_rt_lock(rwlock); +@@ -339,6 +346,7 @@ EXPORT_SYMBOL(rt_read_lock); + + void __lockfunc rt_write_lock(rwlock_t *rwlock) + { ++ sleeping_lock_inc(); + migrate_disable(); + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + do_write_rt_lock(rwlock); +@@ -350,6 +358,7 @@ void __lockfunc rt_read_unlock(rwlock_t *rwlock) + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_read_rt_unlock(rwlock); + migrate_enable(); ++ sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_read_unlock); + +@@ -358,6 +367,7 @@ void __lockfunc rt_write_unlock(rwlock_t *rwlock) + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_write_rt_unlock(rwlock); + migrate_enable(); ++ sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_write_unlock); + +diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h +index 5f6de49dc78e..35f3552b7463 100644 +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -337,9 +337,13 @@ static void rcu_preempt_note_context_switch(bool preempt) + struct task_struct *t = current; + struct rcu_data *rdp; + struct rcu_node *rnp; ++ int sleeping_l = 0; + + lockdep_assert_irqs_disabled(); +- WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); ++#if defined(CONFIG_PREEMPT_RT_FULL) ++ sleeping_l = t->sleeping_lock; ++#endif ++ WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0 && !sleeping_l); + if (t->rcu_read_lock_nesting > 0 && + !t->rcu_read_unlock_special.b.blocked) { + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 9494e2007118..555dea10764e 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7348,4 +7348,49 @@ void migrate_enable(void) + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); ++ ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++#ifdef CONFIG_SCHED_DEBUG ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ ++ p->migrate_disable++; ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ p->migrate_disable--; ++} ++EXPORT_SYMBOL(migrate_enable); + #endif +-- +2.36.1 + diff --git a/debian/patches-rt/0155-sched-migrate_disable-fallback-to-preempt_disable-in.patch b/debian/patches-rt/0155-sched-migrate_disable-fallback-to-preempt_disable-in.patch new file mode 100644 index 000000000..c471ea20d --- /dev/null +++ b/debian/patches-rt/0155-sched-migrate_disable-fallback-to-preempt_disable-in.patch @@ -0,0 +1,204 @@ +From e85e95b0e59b7d493402419e3a63a06978a06452 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 5 Jul 2018 14:44:51 +0200 +Subject: [PATCH 155/347] sched/migrate_disable: fallback to preempt_disable() + instead barrier() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On SMP + !RT migrate_disable() is still around. It is not part of spin_lock() +anymore so it has almost no users. However the futex code has a workaround for +the !in_atomic() part of migrate disable which fails because the matching +migrade_disable() is no longer part of spin_lock(). + +On !SMP + !RT migrate_disable() is reduced to barrier(). This is not optimal +because we few spots where a "preempt_disable()" statement was replaced with +"migrate_disable()". + +We also used the migration_disable counter to figure out if a sleeping lock is +acquired so RCU does not complain about schedule() during rcu_read_lock() while +a sleeping lock is held. This changed, we no longer use it, we have now a +sleeping_lock counter for the RCU purpose. + +This means we can now: +- for SMP + RT_BASE + full migration program, nothing changes here + +- for !SMP + RT_BASE + the migration counting is no longer required. It used to ensure that the task + is not migrated to another CPU and that this CPU remains online. !SMP ensures + that already. + Move it to CONFIG_SCHED_DEBUG so the counting is done for debugging purpose + only. + +- for all other cases including !RT + fallback to preempt_disable(). The only remaining users of migrate_disable() + are those which were converted from preempt_disable() and the futex + workaround which is already in the preempt_disable() section due to the + spin_lock that is held. + +Cc: stable-rt@vger.kernel.org +Reported-by: joe.korty@concurrent-rt.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/preempt.h | 6 +++--- + include/linux/sched.h | 4 ++-- + kernel/sched/core.c | 23 +++++++++++------------ + kernel/sched/debug.c | 2 +- + 4 files changed, 17 insertions(+), 18 deletions(-) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index 9eafc34898b4..ed8413e7140f 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -204,7 +204,7 @@ do { \ + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + + extern void migrate_disable(void); + extern void migrate_enable(void); +@@ -221,8 +221,8 @@ static inline int __migrate_disabled(struct task_struct *p) + } + + #else +-#define migrate_disable() barrier() +-#define migrate_enable() barrier() ++#define migrate_disable() preempt_disable() ++#define migrate_enable() preempt_enable() + static inline int __migrate_disabled(struct task_struct *p) + { + return 0; +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 4f8fcba23c1d..ceb3bdfb6bc4 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -667,7 +667,7 @@ struct task_struct { + int nr_cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int migrate_disable; + int migrate_disable_update; + # ifdef CONFIG_SCHED_DEBUG +@@ -675,8 +675,8 @@ struct task_struct { + # endif + + #elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +- int migrate_disable; + # ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable; + int migrate_disable_atomic; + # endif + #endif +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 555dea10764e..0c44c16244a1 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1031,7 +1031,7 @@ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_ma + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int __migrate_disabled(struct task_struct *p) + { + return p->migrate_disable; +@@ -1071,7 +1071,7 @@ static void __do_set_cpus_allowed_tail(struct task_struct *p, + + void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + { +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + if (__migrate_disabled(p)) { + lockdep_assert_held(&p->pi_lock); + +@@ -1145,7 +1145,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + if (__migrate_disabled(p)) { + p->migrate_disable_update = 1; + goto out; +@@ -7204,7 +7204,7 @@ const u32 sched_prio_to_wmult[40] = { + + #undef CREATE_TRACE_POINTS + +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + + static inline void + update_nr_migratory(struct task_struct *p, long delta) +@@ -7352,45 +7352,44 @@ EXPORT_SYMBOL(migrate_enable); + #elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + void migrate_disable(void) + { ++#ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { +-#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +-#endif + return; + } +-#ifdef CONFIG_SCHED_DEBUG ++ + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +-#endif + + p->migrate_disable++; ++#endif ++ barrier(); + } + EXPORT_SYMBOL(migrate_disable); + + void migrate_enable(void) + { ++#ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { +-#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +-#endif + return; + } + +-#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +-#endif + + WARN_ON_ONCE(p->migrate_disable <= 0); + p->migrate_disable--; ++#endif ++ barrier(); + } + EXPORT_SYMBOL(migrate_enable); + #endif +diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c +index dc3f3e6fa0bd..169b98c12da7 100644 +--- a/kernel/sched/debug.c ++++ b/kernel/sched/debug.c +@@ -988,7 +988,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, + P(dl.runtime); + P(dl.deadline); + } +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + P(migrate_disable); + #endif + P(nr_cpus_allowed); +-- +2.36.1 + diff --git a/debian/patches-rt/0156-locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch b/debian/patches-rt/0156-locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch new file mode 100644 index 000000000..b8812e5b3 --- /dev/null +++ b/debian/patches-rt/0156-locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch @@ -0,0 +1,182 @@ +From af3f791cb33d8bb0c19a9057198100a3bae10cb9 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 4 Aug 2017 17:40:42 +0200 +Subject: [PATCH 156/347] locking: don't check for __LINUX_SPINLOCK_TYPES_H on + -RT archs +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Upstream uses arch_spinlock_t within spinlock_t and requests that +spinlock_types.h header file is included first. +On -RT we have the rt_mutex with its raw_lock wait_lock which needs +architectures' spinlock_types.h header file for its definition. However +we need rt_mutex first because it is used to build the spinlock_t so +that check does not work for us. +Therefore I am dropping that check. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/alpha/include/asm/spinlock_types.h | 4 ---- + arch/arm/include/asm/spinlock_types.h | 4 ---- + arch/arm64/include/asm/spinlock_types.h | 4 ---- + arch/hexagon/include/asm/spinlock_types.h | 4 ---- + arch/ia64/include/asm/spinlock_types.h | 4 ---- + arch/powerpc/include/asm/spinlock_types.h | 4 ---- + arch/s390/include/asm/spinlock_types.h | 4 ---- + arch/sh/include/asm/spinlock_types.h | 4 ---- + arch/xtensa/include/asm/spinlock_types.h | 4 ---- + include/linux/spinlock_types_up.h | 4 ---- + 10 files changed, 40 deletions(-) + +diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h +index 1d5716bc060b..6883bc952d22 100644 +--- a/arch/alpha/include/asm/spinlock_types.h ++++ b/arch/alpha/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef _ALPHA_SPINLOCK_TYPES_H + #define _ALPHA_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h +index 5976958647fe..a37c0803954b 100644 +--- a/arch/arm/include/asm/spinlock_types.h ++++ b/arch/arm/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + #define TICKET_SHIFT 16 + + typedef struct { +diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h +index a157ff465e27..f952fdda8346 100644 +--- a/arch/arm64/include/asm/spinlock_types.h ++++ b/arch/arm64/include/asm/spinlock_types.h +@@ -16,10 +16,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) +-# error "please don't include this file directly" +-#endif +- + #include <asm-generic/qspinlock_types.h> + #include <asm-generic/qrwlock_types.h> + +diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h +index 7a906b5214a4..d8f596fec022 100644 +--- a/arch/hexagon/include/asm/spinlock_types.h ++++ b/arch/hexagon/include/asm/spinlock_types.h +@@ -21,10 +21,6 @@ + #ifndef _ASM_SPINLOCK_TYPES_H + #define _ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h +index 6e345fefcdca..681408d6816f 100644 +--- a/arch/ia64/include/asm/spinlock_types.h ++++ b/arch/ia64/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef _ASM_IA64_SPINLOCK_TYPES_H + #define _ASM_IA64_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h +index 87adaf13b7e8..7305cb6a53e4 100644 +--- a/arch/powerpc/include/asm/spinlock_types.h ++++ b/arch/powerpc/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H + #define _ASM_POWERPC_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int slock; + } arch_spinlock_t; +diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h +index cfed272e4fd5..8e28e8176ec8 100644 +--- a/arch/s390/include/asm/spinlock_types.h ++++ b/arch/s390/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + int lock; + } __attribute__ ((aligned (4))) arch_spinlock_t; +diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h +index e82369f286a2..22ca9a98bbb8 100644 +--- a/arch/sh/include/asm/spinlock_types.h ++++ b/arch/sh/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SH_SPINLOCK_TYPES_H + #define __ASM_SH_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h +index bb1fe6c1816e..8a22f1e7b6c9 100644 +--- a/arch/xtensa/include/asm/spinlock_types.h ++++ b/arch/xtensa/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int slock; + } arch_spinlock_t; +diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h +index c09b6407ae1b..b0243ba07fb7 100644 +--- a/include/linux/spinlock_types_up.h ++++ b/include/linux/spinlock_types_up.h +@@ -1,10 +1,6 @@ + #ifndef __LINUX_SPINLOCK_TYPES_UP_H + #define __LINUX_SPINLOCK_TYPES_UP_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + /* + * include/linux/spinlock_types_up.h - spinlock type definitions for UP + * +-- +2.36.1 + diff --git a/debian/patches-rt/0157-rcu-Frob-softirq-test.patch b/debian/patches-rt/0157-rcu-Frob-softirq-test.patch new file mode 100644 index 000000000..f69f7c094 --- /dev/null +++ b/debian/patches-rt/0157-rcu-Frob-softirq-test.patch @@ -0,0 +1,173 @@ +From 638391362ce6f052267016840a592cad59ee3eef Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <a.p.zijlstra@chello.nl> +Date: Sat, 13 Aug 2011 00:23:17 +0200 +Subject: [PATCH 157/347] rcu: Frob softirq test +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +With RT_FULL we get the below wreckage: + +[ 126.060484] ======================================================= +[ 126.060486] [ INFO: possible circular locking dependency detected ] +[ 126.060489] 3.0.1-rt10+ #30 +[ 126.060490] ------------------------------------------------------- +[ 126.060492] irq/24-eth0/1235 is trying to acquire lock: +[ 126.060495] (&(lock)->wait_lock#2){+.+...}, at: [<ffffffff81501c81>] rt_mutex_slowunlock+0x16/0x55 +[ 126.060503] +[ 126.060504] but task is already holding lock: +[ 126.060506] (&p->pi_lock){-...-.}, at: [<ffffffff81074fdc>] try_to_wake_up+0x35/0x429 +[ 126.060511] +[ 126.060511] which lock already depends on the new lock. +[ 126.060513] +[ 126.060514] +[ 126.060514] the existing dependency chain (in reverse order) is: +[ 126.060516] +[ 126.060516] -> #1 (&p->pi_lock){-...-.}: +[ 126.060519] [<ffffffff810afe9e>] lock_acquire+0x145/0x18a +[ 126.060524] [<ffffffff8150291e>] _raw_spin_lock_irqsave+0x4b/0x85 +[ 126.060527] [<ffffffff810b5aa4>] task_blocks_on_rt_mutex+0x36/0x20f +[ 126.060531] [<ffffffff815019bb>] rt_mutex_slowlock+0xd1/0x15a +[ 126.060534] [<ffffffff81501ae3>] rt_mutex_lock+0x2d/0x2f +[ 126.060537] [<ffffffff810d9020>] rcu_boost+0xad/0xde +[ 126.060541] [<ffffffff810d90ce>] rcu_boost_kthread+0x7d/0x9b +[ 126.060544] [<ffffffff8109a760>] kthread+0x99/0xa1 +[ 126.060547] [<ffffffff81509b14>] kernel_thread_helper+0x4/0x10 +[ 126.060551] +[ 126.060552] -> #0 (&(lock)->wait_lock#2){+.+...}: +[ 126.060555] [<ffffffff810af1b8>] __lock_acquire+0x1157/0x1816 +[ 126.060558] [<ffffffff810afe9e>] lock_acquire+0x145/0x18a +[ 126.060561] [<ffffffff8150279e>] _raw_spin_lock+0x40/0x73 +[ 126.060564] [<ffffffff81501c81>] rt_mutex_slowunlock+0x16/0x55 +[ 126.060566] [<ffffffff81501ce7>] rt_mutex_unlock+0x27/0x29 +[ 126.060569] [<ffffffff810d9f86>] rcu_read_unlock_special+0x17e/0x1c4 +[ 126.060573] [<ffffffff810da014>] __rcu_read_unlock+0x48/0x89 +[ 126.060576] [<ffffffff8106847a>] select_task_rq_rt+0xc7/0xd5 +[ 126.060580] [<ffffffff8107511c>] try_to_wake_up+0x175/0x429 +[ 126.060583] [<ffffffff81075425>] wake_up_process+0x15/0x17 +[ 126.060585] [<ffffffff81080a51>] wakeup_softirqd+0x24/0x26 +[ 126.060590] [<ffffffff81081df9>] irq_exit+0x49/0x55 +[ 126.060593] [<ffffffff8150a3bd>] smp_apic_timer_interrupt+0x8a/0x98 +[ 126.060597] [<ffffffff81509793>] apic_timer_interrupt+0x13/0x20 +[ 126.060600] [<ffffffff810d5952>] irq_forced_thread_fn+0x1b/0x44 +[ 126.060603] [<ffffffff810d582c>] irq_thread+0xde/0x1af +[ 126.060606] [<ffffffff8109a760>] kthread+0x99/0xa1 +[ 126.060608] [<ffffffff81509b14>] kernel_thread_helper+0x4/0x10 +[ 126.060611] +[ 126.060612] other info that might help us debug this: +[ 126.060614] +[ 126.060615] Possible unsafe locking scenario: +[ 126.060616] +[ 126.060617] CPU0 CPU1 +[ 126.060619] ---- ---- +[ 126.060620] lock(&p->pi_lock); +[ 126.060623] lock(&(lock)->wait_lock); +[ 126.060625] lock(&p->pi_lock); +[ 126.060627] lock(&(lock)->wait_lock); +[ 126.060629] +[ 126.060629] *** DEADLOCK *** +[ 126.060630] +[ 126.060632] 1 lock held by irq/24-eth0/1235: +[ 126.060633] #0: (&p->pi_lock){-...-.}, at: [<ffffffff81074fdc>] try_to_wake_up+0x35/0x429 +[ 126.060638] +[ 126.060638] stack backtrace: +[ 126.060641] Pid: 1235, comm: irq/24-eth0 Not tainted 3.0.1-rt10+ #30 +[ 126.060643] Call Trace: +[ 126.060644] <IRQ> [<ffffffff810acbde>] print_circular_bug+0x289/0x29a +[ 126.060651] [<ffffffff810af1b8>] __lock_acquire+0x1157/0x1816 +[ 126.060655] [<ffffffff810ab3aa>] ? trace_hardirqs_off_caller+0x1f/0x99 +[ 126.060658] [<ffffffff81501c81>] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060661] [<ffffffff810afe9e>] lock_acquire+0x145/0x18a +[ 126.060664] [<ffffffff81501c81>] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060668] [<ffffffff8150279e>] _raw_spin_lock+0x40/0x73 +[ 126.060671] [<ffffffff81501c81>] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060674] [<ffffffff810d9655>] ? rcu_report_qs_rsp+0x87/0x8c +[ 126.060677] [<ffffffff81501c81>] rt_mutex_slowunlock+0x16/0x55 +[ 126.060680] [<ffffffff810d9ea3>] ? rcu_read_unlock_special+0x9b/0x1c4 +[ 126.060683] [<ffffffff81501ce7>] rt_mutex_unlock+0x27/0x29 +[ 126.060687] [<ffffffff810d9f86>] rcu_read_unlock_special+0x17e/0x1c4 +[ 126.060690] [<ffffffff810da014>] __rcu_read_unlock+0x48/0x89 +[ 126.060693] [<ffffffff8106847a>] select_task_rq_rt+0xc7/0xd5 +[ 126.060696] [<ffffffff810683da>] ? select_task_rq_rt+0x27/0xd5 +[ 126.060701] [<ffffffff810a852a>] ? clockevents_program_event+0x8e/0x90 +[ 126.060704] [<ffffffff8107511c>] try_to_wake_up+0x175/0x429 +[ 126.060708] [<ffffffff810a95dc>] ? tick_program_event+0x1f/0x21 +[ 126.060711] [<ffffffff81075425>] wake_up_process+0x15/0x17 +[ 126.060715] [<ffffffff81080a51>] wakeup_softirqd+0x24/0x26 +[ 126.060718] [<ffffffff81081df9>] irq_exit+0x49/0x55 +[ 126.060721] [<ffffffff8150a3bd>] smp_apic_timer_interrupt+0x8a/0x98 +[ 126.060724] [<ffffffff81509793>] apic_timer_interrupt+0x13/0x20 +[ 126.060726] <EOI> [<ffffffff81072855>] ? migrate_disable+0x75/0x12d +[ 126.060733] [<ffffffff81080a61>] ? local_bh_disable+0xe/0x1f +[ 126.060736] [<ffffffff81080a70>] ? local_bh_disable+0x1d/0x1f +[ 126.060739] [<ffffffff810d5952>] irq_forced_thread_fn+0x1b/0x44 +[ 126.060742] [<ffffffff81502ac0>] ? _raw_spin_unlock_irq+0x3b/0x59 +[ 126.060745] [<ffffffff810d582c>] irq_thread+0xde/0x1af +[ 126.060748] [<ffffffff810d5937>] ? irq_thread_fn+0x3a/0x3a +[ 126.060751] [<ffffffff810d574e>] ? irq_finalize_oneshot+0xd1/0xd1 +[ 126.060754] [<ffffffff810d574e>] ? irq_finalize_oneshot+0xd1/0xd1 +[ 126.060757] [<ffffffff8109a760>] kthread+0x99/0xa1 +[ 126.060761] [<ffffffff81509b14>] kernel_thread_helper+0x4/0x10 +[ 126.060764] [<ffffffff81069ed7>] ? finish_task_switch+0x87/0x10a +[ 126.060768] [<ffffffff81502ec4>] ? retint_restore_args+0xe/0xe +[ 126.060771] [<ffffffff8109a6c7>] ? __init_kthread_worker+0x8c/0x8c +[ 126.060774] [<ffffffff81509b10>] ? gs_change+0xb/0xb + +Because irq_exit() does: + +void irq_exit(void) +{ + account_system_vtime(current); + trace_hardirq_exit(); + sub_preempt_count(IRQ_EXIT_OFFSET); + if (!in_interrupt() && local_softirq_pending()) + invoke_softirq(); + + ... +} + +Which triggers a wakeup, which uses RCU, now if the interrupted task has +t->rcu_read_unlock_special set, the rcu usage from the wakeup will end +up in rcu_read_unlock_special(). rcu_read_unlock_special() will test +for in_irq(), which will fail as we just decremented preempt_count +with IRQ_EXIT_OFFSET, and in_sering_softirq(), which for +PREEMPT_RT_FULL reads: + +int in_serving_softirq(void) +{ + int res; + + preempt_disable(); + res = __get_cpu_var(local_softirq_runner) == current; + preempt_enable(); + return res; +} + +Which will thus also fail, resulting in the above wreckage. + +The 'somewhat' ugly solution is to open-code the preempt_count() test +in rcu_read_unlock_special(). + +Also, we're not at all sure how ->rcu_read_unlock_special gets set +here... so this is very likely a bandaid and more thought is required. + +Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> +--- + kernel/rcu/tree_plugin.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h +index 35f3552b7463..e9ce51e19e87 100644 +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -524,7 +524,7 @@ static void rcu_read_unlock_special(struct task_struct *t) + } + + /* Hardware IRQ handlers cannot block, complain if they get here. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", +-- +2.36.1 + diff --git a/debian/patches-rt/0158-rcu-Merge-RCU-bh-into-RCU-preempt.patch b/debian/patches-rt/0158-rcu-Merge-RCU-bh-into-RCU-preempt.patch new file mode 100644 index 000000000..1c3897d25 --- /dev/null +++ b/debian/patches-rt/0158-rcu-Merge-RCU-bh-into-RCU-preempt.patch @@ -0,0 +1,351 @@ +From d21751c3efb035a08326d8a28789b91cb769ea70 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 5 Oct 2011 11:59:38 -0700 +Subject: [PATCH 158/347] rcu: Merge RCU-bh into RCU-preempt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The Linux kernel has long RCU-bh read-side critical sections that +intolerably increase scheduling latency under mainline's RCU-bh rules, +which include RCU-bh read-side critical sections being non-preemptible. +This patch therefore arranges for RCU-bh to be implemented in terms of +RCU-preempt for CONFIG_PREEMPT_RT_FULL=y. + +This has the downside of defeating the purpose of RCU-bh, namely, +handling the case where the system is subjected to a network-based +denial-of-service attack that keeps at least one CPU doing full-time +softirq processing. This issue will be fixed by a later commit. + +The current commit will need some work to make it appropriate for +mainline use, for example, it needs to be extended to cover Tiny RCU. + +[ paulmck: Added a useful changelog ] + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +Link: http://lkml.kernel.org/r/20111005185938.GA20403@linux.vnet.ibm.com +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/rcupdate.h | 19 +++++++++++++++++++ + include/linux/rcutree.h | 8 ++++++++ + kernel/rcu/rcu.h | 11 +++++++++-- + kernel/rcu/rcutorture.c | 7 +++++++ + kernel/rcu/tree.c | 26 ++++++++++++++++++++++++++ + kernel/rcu/tree.h | 2 ++ + kernel/rcu/update.c | 2 ++ + 7 files changed, 73 insertions(+), 2 deletions(-) + +diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h +index e6733d7911e9..08d64e5713fc 100644 +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -56,7 +56,11 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); + #define call_rcu call_rcu_sched + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define call_rcu_bh call_rcu ++#else + void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); ++#endif + void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); + void synchronize_sched(void); + void rcu_barrier_tasks(void); +@@ -261,7 +265,14 @@ extern struct lockdep_map rcu_sched_lock_map; + extern struct lockdep_map rcu_callback_map; + int debug_lockdep_rcu_enabled(void); + int rcu_read_lock_held(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int rcu_read_lock_bh_held(void) ++{ ++ return rcu_read_lock_held(); ++} ++#else + int rcu_read_lock_bh_held(void); ++#endif + int rcu_read_lock_sched_held(void); + + #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +@@ -661,10 +672,14 @@ static inline void rcu_read_unlock(void) + static inline void rcu_read_lock_bh(void) + { + local_bh_disable(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_lock(); ++#else + __acquire(RCU_BH); + rcu_lock_acquire(&rcu_bh_lock_map); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); ++#endif + } + + /* +@@ -674,10 +689,14 @@ static inline void rcu_read_lock_bh(void) + */ + static inline void rcu_read_unlock_bh(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_unlock(); ++#else + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); + rcu_lock_release(&rcu_bh_lock_map); + __release(RCU_BH); ++#endif + local_bh_enable(); + } + +diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h +index 914655848ef6..462ce061bac7 100644 +--- a/include/linux/rcutree.h ++++ b/include/linux/rcutree.h +@@ -44,7 +44,11 @@ static inline void rcu_virt_note_context_switch(int cpu) + rcu_note_context_switch(false); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define synchronize_rcu_bh synchronize_rcu ++#else + void synchronize_rcu_bh(void); ++#endif + void synchronize_sched_expedited(void); + void synchronize_rcu_expedited(void); + +@@ -72,7 +76,11 @@ static inline void synchronize_rcu_bh_expedited(void) + } + + void rcu_barrier(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define rcu_barrier_bh rcu_barrier ++#else + void rcu_barrier_bh(void); ++#endif + void rcu_barrier_sched(void); + bool rcu_eqs_special_set(int cpu); + unsigned long get_state_synchronize_rcu(void); +diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h +index 4d04683c31b2..808cce9a5d43 100644 +--- a/kernel/rcu/rcu.h ++++ b/kernel/rcu/rcu.h +@@ -528,7 +528,6 @@ static inline void show_rcu_gp_kthreads(void) { } + static inline int rcu_get_gp_kthreads_prio(void) { return 0; } + #else /* #ifdef CONFIG_TINY_RCU */ + unsigned long rcu_get_gp_seq(void); +-unsigned long rcu_bh_get_gp_seq(void); + unsigned long rcu_sched_get_gp_seq(void); + unsigned long rcu_exp_batches_completed(void); + unsigned long rcu_exp_batches_completed_sched(void); +@@ -536,10 +535,18 @@ unsigned long srcu_batches_completed(struct srcu_struct *sp); + void show_rcu_gp_kthreads(void); + int rcu_get_gp_kthreads_prio(void); + void rcu_force_quiescent_state(void); +-void rcu_bh_force_quiescent_state(void); + void rcu_sched_force_quiescent_state(void); + extern struct workqueue_struct *rcu_gp_wq; + extern struct workqueue_struct *rcu_par_gp_wq; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define rcu_bh_get_gp_seq rcu_get_gp_seq ++#define rcu_bh_force_quiescent_state rcu_force_quiescent_state ++#else ++unsigned long rcu_bh_get_gp_seq(void); ++void rcu_bh_force_quiescent_state(void); ++#endif ++ + #endif /* #else #ifdef CONFIG_TINY_RCU */ + + #ifdef CONFIG_RCU_NOCB_CPU +diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c +index 0b7af7e2bcbb..e95d121efc80 100644 +--- a/kernel/rcu/rcutorture.c ++++ b/kernel/rcu/rcutorture.c +@@ -434,6 +434,7 @@ static struct rcu_torture_ops rcu_ops = { + .name = "rcu" + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Definitions for rcu_bh torture testing. + */ +@@ -475,6 +476,12 @@ static struct rcu_torture_ops rcu_bh_ops = { + .name = "rcu_bh" + }; + ++#else ++static struct rcu_torture_ops rcu_bh_ops = { ++ .ttype = INVALID_RCU_FLAVOR, ++}; ++#endif ++ + /* + * Don't even think about trying any of these in real life!!! + * The names includes "busted", and they really means it! +diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c +index f7e89c989df7..1456a3d97971 100644 +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -244,6 +244,7 @@ void rcu_sched_qs(void) + this_cpu_ptr(&rcu_sched_data), true); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void rcu_bh_qs(void) + { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); +@@ -254,6 +255,11 @@ void rcu_bh_qs(void) + __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); + } + } ++#else ++void rcu_bh_qs(void) ++{ ++} ++#endif + + /* + * Steal a bit from the bottom of ->dynticks for idle entry/exit +@@ -568,6 +574,7 @@ unsigned long rcu_sched_get_gp_seq(void) + } + EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Return the number of RCU-bh GPs completed thus far for debug & stats. + */ +@@ -576,6 +583,7 @@ unsigned long rcu_bh_get_gp_seq(void) + return READ_ONCE(rcu_bh_state.gp_seq); + } + EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq); ++#endif + + /* + * Return the number of RCU expedited batches completed thus far for +@@ -599,6 +607,7 @@ unsigned long rcu_exp_batches_completed_sched(void) + } + EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Force a quiescent state. + */ +@@ -617,6 +626,13 @@ void rcu_bh_force_quiescent_state(void) + } + EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); + ++#else ++void rcu_force_quiescent_state(void) ++{ ++} ++EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); ++#endif ++ + /* + * Force a quiescent state for RCU-sched. + */ +@@ -674,9 +690,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, + case RCU_FLAVOR: + rsp = rcu_state_p; + break; ++#ifndef CONFIG_PREEMPT_RT_FULL + case RCU_BH_FLAVOR: + rsp = &rcu_bh_state; + break; ++#endif + case RCU_SCHED_FLAVOR: + rsp = &rcu_sched_state; + break; +@@ -3057,6 +3075,7 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. +@@ -3084,6 +3103,7 @@ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) + __call_rcu(head, func, &rcu_bh_state, -1, 0); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif + + /* + * Queue an RCU callback for lazy invocation after a grace period. +@@ -3169,6 +3189,7 @@ void synchronize_sched(void) + } + EXPORT_SYMBOL_GPL(synchronize_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * +@@ -3195,6 +3216,7 @@ void synchronize_rcu_bh(void) + wait_rcu_gp(call_rcu_bh); + } + EXPORT_SYMBOL_GPL(synchronize_rcu_bh); ++#endif + + /** + * get_state_synchronize_rcu - Snapshot current RCU state +@@ -3502,6 +3524,7 @@ static void _rcu_barrier(struct rcu_state *rsp) + mutex_unlock(&rsp->barrier_mutex); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +@@ -3510,6 +3533,7 @@ void rcu_barrier_bh(void) + _rcu_barrier(&rcu_bh_state); + } + EXPORT_SYMBOL_GPL(rcu_barrier_bh); ++#endif + + /** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +@@ -4157,7 +4181,9 @@ void __init rcu_init(void) + + rcu_bootup_announce(); + rcu_init_geometry(); ++#ifndef CONFIG_PREEMPT_RT_FULL + rcu_init_one(&rcu_bh_state); ++#endif + rcu_init_one(&rcu_sched_state); + if (dump_tree) + rcu_dump_rcu_node_tree(&rcu_sched_state); +diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h +index 4e74df768c57..fbbff7c21148 100644 +--- a/kernel/rcu/tree.h ++++ b/kernel/rcu/tree.h +@@ -413,7 +413,9 @@ extern struct list_head rcu_struct_flavors; + */ + extern struct rcu_state rcu_sched_state; + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern struct rcu_state rcu_bh_state; ++#endif + + #ifdef CONFIG_PREEMPT_RCU + extern struct rcu_state rcu_preempt_state; +diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c +index 81688a133552..6ffafb1b1584 100644 +--- a/kernel/rcu/update.c ++++ b/kernel/rcu/update.c +@@ -288,6 +288,7 @@ int rcu_read_lock_held(void) + } + EXPORT_SYMBOL_GPL(rcu_read_lock_held); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * +@@ -314,6 +315,7 @@ int rcu_read_lock_bh_held(void) + return in_softirq() || irqs_disabled(); + } + EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); ++#endif + + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +-- +2.36.1 + diff --git a/debian/patches-rt/0159-rcu-Make-ksoftirqd-do-RCU-quiescent-states.patch b/debian/patches-rt/0159-rcu-Make-ksoftirqd-do-RCU-quiescent-states.patch new file mode 100644 index 000000000..44b6d052a --- /dev/null +++ b/debian/patches-rt/0159-rcu-Make-ksoftirqd-do-RCU-quiescent-states.patch @@ -0,0 +1,117 @@ +From 19f2644a64bbf80c134cc923b59d5448d76af806 Mon Sep 17 00:00:00 2001 +From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +Date: Wed, 5 Oct 2011 11:45:18 -0700 +Subject: [PATCH 159/347] rcu: Make ksoftirqd do RCU quiescent states +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Implementing RCU-bh in terms of RCU-preempt makes the system vulnerable +to network-based denial-of-service attacks. This patch therefore +makes __do_softirq() invoke rcu_bh_qs(), but only when __do_softirq() +is running in ksoftirqd context. A wrapper layer in interposed so that +other calls to __do_softirq() avoid invoking rcu_bh_qs(). The underlying +function __do_softirq_common() does the actual work. + +The reason that rcu_bh_qs() is bad in these non-ksoftirqd contexts is +that there might be a local_bh_enable() inside an RCU-preempt read-side +critical section. This local_bh_enable() can invoke __do_softirq() +directly, so if __do_softirq() were to invoke rcu_bh_qs() (which just +calls rcu_preempt_qs() in the PREEMPT_RT_FULL case), there would be +an illegal RCU-preempt quiescent state in the middle of an RCU-preempt +read-side critical section. Therefore, quiescent states can only happen +in cases where __do_softirq() is invoked directly from ksoftirqd. + +Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +Link: http://lkml.kernel.org/r/20111005184518.GA21601@linux.vnet.ibm.com +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/rcu/tree.c | 18 +++++++++++++----- + kernel/rcu/tree_plugin.h | 8 +++++++- + 2 files changed, 20 insertions(+), 6 deletions(-) + +diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c +index 1456a3d97971..1a40e3d44cb8 100644 +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -244,7 +244,19 @@ void rcu_sched_qs(void) + this_cpu_ptr(&rcu_sched_data), true); + } + +-#ifndef CONFIG_PREEMPT_RT_FULL ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void rcu_preempt_qs(void); ++ ++void rcu_bh_qs(void) ++{ ++ unsigned long flags; ++ ++ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ ++ local_irq_save(flags); ++ rcu_preempt_qs(); ++ local_irq_restore(flags); ++} ++#else + void rcu_bh_qs(void) + { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); +@@ -255,10 +267,6 @@ void rcu_bh_qs(void) + __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); + } + } +-#else +-void rcu_bh_qs(void) +-{ +-} + #endif + + /* +diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h +index e9ce51e19e87..938e64c69d18 100644 +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -29,6 +29,7 @@ + #include <linux/oom.h> + #include <linux/sched/debug.h> + #include <linux/smpboot.h> ++#include <linux/jiffies.h> + #include <linux/sched/isolation.h> + #include <uapi/linux/sched/types.h> + #include "../time/tick-internal.h" +@@ -1408,7 +1409,7 @@ static void rcu_prepare_kthreads(int cpu) + + #endif /* #else #ifdef CONFIG_RCU_BOOST */ + +-#if !defined(CONFIG_RCU_FAST_NO_HZ) ++#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) + + /* + * Check to see if any future RCU-related work will need to be done +@@ -1424,7 +1425,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) + *nextevt = KTIME_MAX; + return rcu_cpu_has_callbacks(NULL); + } ++#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + ++#if !defined(CONFIG_RCU_FAST_NO_HZ) + /* + * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up + * after it. +@@ -1521,6 +1524,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) + return cbs_ready; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready + * to invoke. If the CPU has callbacks, try to advance them. Tell the +@@ -1563,6 +1568,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) + *nextevt = basemono + dj * TICK_NSEC; + return 0; + } ++#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ + + /* + * Prepare a CPU for idle from an RCU perspective. The first major task +-- +2.36.1 + diff --git a/debian/patches-rt/0160-rcu-Eliminate-softirq-processing-from-rcutree.patch b/debian/patches-rt/0160-rcu-Eliminate-softirq-processing-from-rcutree.patch new file mode 100644 index 000000000..d4a6e3195 --- /dev/null +++ b/debian/patches-rt/0160-rcu-Eliminate-softirq-processing-from-rcutree.patch @@ -0,0 +1,423 @@ +From 4fa514eb294144f8698e721f4b5a4de0447be272 Mon Sep 17 00:00:00 2001 +From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +Date: Mon, 4 Nov 2013 13:21:10 -0800 +Subject: [PATCH 160/347] rcu: Eliminate softirq processing from rcutree +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Running RCU out of softirq is a problem for some workloads that would +like to manage RCU core processing independently of other softirq work, +for example, setting kthread priority. This commit therefore moves the +RCU core work from softirq to a per-CPU/per-flavor SCHED_OTHER kthread +named rcuc. The SCHED_OTHER approach avoids the scalability problems +that appeared with the earlier attempt to move RCU core processing to +from softirq to kthreads. That said, kernels built with RCU_BOOST=y +will run the rcuc kthreads at the RCU-boosting priority. + +Reported-by: Thomas Gleixner <tglx@linutronix.de> +Tested-by: Mike Galbraith <bitbucket@online.de> +Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/rcu/tree.c | 114 ++++++++++++++++++++++++++++--- + kernel/rcu/tree.h | 4 +- + kernel/rcu/tree_plugin.h | 142 +++------------------------------------ + 3 files changed, 115 insertions(+), 145 deletions(-) + +diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c +index 1a40e3d44cb8..ae716ca783bc 100644 +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -61,6 +61,13 @@ + #include <linux/trace_events.h> + #include <linux/suspend.h> + #include <linux/ftrace.h> ++#include <linux/delay.h> ++#include <linux/gfp.h> ++#include <linux/oom.h> ++#include <linux/smpboot.h> ++#include <linux/jiffies.h> ++#include <linux/sched/isolation.h> ++#include "../time/tick-internal.h" + + #include "tree.h" + #include "rcu.h" +@@ -2896,18 +2903,17 @@ __rcu_process_callbacks(struct rcu_state *rsp) + /* + * Do RCU core processing for the current CPU. + */ +-static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) ++static __latent_entropy void rcu_process_callbacks(void) + { + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; +- trace_rcu_utilization(TPS("Start RCU core")); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); +- trace_rcu_utilization(TPS("End RCU core")); + } + ++static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + /* + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, +@@ -2919,18 +2925,105 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) + { + if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) + return; +- if (likely(!rsp->boost)) { +- rcu_do_batch(rsp, rdp); +- return; +- } +- invoke_rcu_callbacks_kthread(); ++ rcu_do_batch(rsp, rdp); ++} ++ ++static void rcu_wake_cond(struct task_struct *t, int status) ++{ ++ /* ++ * If the thread is yielding, only wake it when this ++ * is invoked from idle ++ */ ++ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) ++ wake_up_process(t); + } + ++/* ++ * Wake up this CPU's rcuc kthread to do RCU core processing. ++ */ + static void invoke_rcu_core(void) + { +- if (cpu_online(smp_processor_id())) +- raise_softirq(RCU_SOFTIRQ); ++ unsigned long flags; ++ struct task_struct *t; ++ ++ if (!cpu_online(smp_processor_id())) ++ return; ++ local_irq_save(flags); ++ __this_cpu_write(rcu_cpu_has_work, 1); ++ t = __this_cpu_read(rcu_cpu_kthread_task); ++ if (t != NULL && current != t) ++ rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); ++ local_irq_restore(flags); ++} ++ ++static void rcu_cpu_kthread_park(unsigned int cpu) ++{ ++ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; ++} ++ ++static int rcu_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(rcu_cpu_has_work); ++} ++ ++/* ++ * Per-CPU kernel thread that invokes RCU callbacks. This replaces the ++ * RCU softirq used in flavors and configurations of RCU that do not ++ * support RCU priority boosting. ++ */ ++static void rcu_cpu_kthread(unsigned int cpu) ++{ ++ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); ++ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); ++ int spincnt; ++ ++ for (spincnt = 0; spincnt < 10; spincnt++) { ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); ++ local_bh_disable(); ++ *statusp = RCU_KTHREAD_RUNNING; ++ this_cpu_inc(rcu_cpu_kthread_loops); ++ local_irq_disable(); ++ work = *workp; ++ *workp = 0; ++ local_irq_enable(); ++ if (work) ++ rcu_process_callbacks(); ++ local_bh_enable(); ++ if (*workp == 0) { ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); ++ *statusp = RCU_KTHREAD_WAITING; ++ return; ++ } ++ } ++ *statusp = RCU_KTHREAD_YIELDING; ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); ++ schedule_timeout_interruptible(2); ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); ++ *statusp = RCU_KTHREAD_WAITING; ++} ++ ++static struct smp_hotplug_thread rcu_cpu_thread_spec = { ++ .store = &rcu_cpu_kthread_task, ++ .thread_should_run = rcu_cpu_kthread_should_run, ++ .thread_fn = rcu_cpu_kthread, ++ .thread_comm = "rcuc/%u", ++ .setup = rcu_cpu_kthread_setup, ++ .park = rcu_cpu_kthread_park, ++}; ++ ++/* ++ * Spawn per-CPU RCU core processing kthreads. ++ */ ++static int __init rcu_spawn_core_kthreads(void) ++{ ++ int cpu; ++ ++ for_each_possible_cpu(cpu) ++ per_cpu(rcu_cpu_has_work, cpu) = 0; ++ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); ++ return 0; + } ++early_initcall(rcu_spawn_core_kthreads); + + /* + * Handle any core-RCU processing required by a call_rcu() invocation. +@@ -4196,7 +4289,6 @@ void __init rcu_init(void) + if (dump_tree) + rcu_dump_rcu_node_tree(&rcu_sched_state); + __rcu_init_preempt(); +- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + + /* + * We don't need protection against CPU-hotplug here because +diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h +index fbbff7c21148..98257d20feb2 100644 +--- a/kernel/rcu/tree.h ++++ b/kernel/rcu/tree.h +@@ -423,12 +423,10 @@ extern struct rcu_state rcu_preempt_state; + + int rcu_dynticks_snap(struct rcu_dynticks *rdtp); + +-#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DECLARE_PER_CPU(char, rcu_cpu_has_work); +-#endif /* #ifdef CONFIG_RCU_BOOST */ + + #ifndef RCU_TREE_NONCORE + +@@ -451,8 +449,8 @@ static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, + int ncheck); + static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); + static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +-static void invoke_rcu_callbacks_kthread(void); + static bool rcu_is_callbacks_kthread(void); ++static void rcu_cpu_kthread_setup(unsigned int cpu); + #ifdef CONFIG_RCU_BOOST + static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp); +diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h +index 938e64c69d18..56639c8ed550 100644 +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -24,42 +24,16 @@ + * Paul E. McKenney <paulmck@linux.vnet.ibm.com> + */ + +-#include <linux/delay.h> +-#include <linux/gfp.h> +-#include <linux/oom.h> +-#include <linux/sched/debug.h> +-#include <linux/smpboot.h> +-#include <linux/jiffies.h> +-#include <linux/sched/isolation.h> +-#include <uapi/linux/sched/types.h> +-#include "../time/tick-internal.h" +- +-#ifdef CONFIG_RCU_BOOST +- + #include "../locking/rtmutex_common.h" + + /* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DEFINE_PER_CPU(char, rcu_cpu_has_work); + +-#else /* #ifdef CONFIG_RCU_BOOST */ +- +-/* +- * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST, +- * all uses are in dead code. Provide a definition to keep the compiler +- * happy, but add WARN_ON_ONCE() to complain if used in the wrong place. +- * This probably needs to be excluded from -rt builds. +- */ +-#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) +-#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1) +- +-#endif /* #else #ifdef CONFIG_RCU_BOOST */ +- + #ifdef CONFIG_RCU_NOCB_CPU + static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ + static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ +@@ -1028,18 +1002,21 @@ dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++/* ++ * If boosting, set rcuc kthreads to realtime priority. ++ */ ++static void rcu_cpu_kthread_setup(unsigned int cpu) ++{ + #ifdef CONFIG_RCU_BOOST ++ struct sched_param sp; + +-static void rcu_wake_cond(struct task_struct *t, int status) +-{ +- /* +- * If the thread is yielding, only wake it when this +- * is invoked from idle +- */ +- if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) +- wake_up_process(t); ++ sp.sched_priority = kthread_prio; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++#endif /* #ifdef CONFIG_RCU_BOOST */ + } + ++#ifdef CONFIG_RCU_BOOST ++ + /* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the +@@ -1177,23 +1154,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) + } + } + +-/* +- * Wake up the per-CPU kthread to invoke RCU callbacks. +- */ +-static void invoke_rcu_callbacks_kthread(void) +-{ +- unsigned long flags; +- +- local_irq_save(flags); +- __this_cpu_write(rcu_cpu_has_work, 1); +- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && +- current != __this_cpu_read(rcu_cpu_kthread_task)) { +- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), +- __this_cpu_read(rcu_cpu_kthread_status)); +- } +- local_irq_restore(flags); +-} +- + /* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. +@@ -1248,67 +1208,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + return 0; + } + +-static void rcu_kthread_do_work(void) +-{ +- rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); +- rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); +- rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); +-} +- +-static void rcu_cpu_kthread_setup(unsigned int cpu) +-{ +- struct sched_param sp; +- +- sp.sched_priority = kthread_prio; +- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +-} +- +-static void rcu_cpu_kthread_park(unsigned int cpu) +-{ +- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +-} +- +-static int rcu_cpu_kthread_should_run(unsigned int cpu) +-{ +- return __this_cpu_read(rcu_cpu_has_work); +-} +- +-/* +- * Per-CPU kernel thread that invokes RCU callbacks. This replaces the +- * RCU softirq used in flavors and configurations of RCU that do not +- * support RCU priority boosting. +- */ +-static void rcu_cpu_kthread(unsigned int cpu) +-{ +- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); +- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); +- int spincnt; +- +- for (spincnt = 0; spincnt < 10; spincnt++) { +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); +- local_bh_disable(); +- *statusp = RCU_KTHREAD_RUNNING; +- this_cpu_inc(rcu_cpu_kthread_loops); +- local_irq_disable(); +- work = *workp; +- *workp = 0; +- local_irq_enable(); +- if (work) +- rcu_kthread_do_work(); +- local_bh_enable(); +- if (*workp == 0) { +- trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); +- *statusp = RCU_KTHREAD_WAITING; +- return; +- } +- } +- *statusp = RCU_KTHREAD_YIELDING; +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); +- schedule_timeout_interruptible(2); +- trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); +- *statusp = RCU_KTHREAD_WAITING; +-} +- + /* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still +@@ -1339,26 +1238,12 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) + free_cpumask_var(cm); + } + +-static struct smp_hotplug_thread rcu_cpu_thread_spec = { +- .store = &rcu_cpu_kthread_task, +- .thread_should_run = rcu_cpu_kthread_should_run, +- .thread_fn = rcu_cpu_kthread, +- .thread_comm = "rcuc/%u", +- .setup = rcu_cpu_kthread_setup, +- .park = rcu_cpu_kthread_park, +-}; +- + /* + * Spawn boost kthreads -- called as soon as the scheduler is running. + */ + static void __init rcu_spawn_boost_kthreads(void) + { + struct rcu_node *rnp; +- int cpu; +- +- for_each_possible_cpu(cpu) +- per_cpu(rcu_cpu_has_work, cpu) = 0; +- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + } +@@ -1381,11 +1266,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + +-static void invoke_rcu_callbacks_kthread(void) +-{ +- WARN_ON_ONCE(1); +-} +- + static bool rcu_is_callbacks_kthread(void) + { + return false; +-- +2.36.1 + diff --git a/debian/patches-rt/0161-srcu-use-cpu_online-instead-custom-check.patch b/debian/patches-rt/0161-srcu-use-cpu_online-instead-custom-check.patch new file mode 100644 index 000000000..626188f7a --- /dev/null +++ b/debian/patches-rt/0161-srcu-use-cpu_online-instead-custom-check.patch @@ -0,0 +1,96 @@ +From 4ce509b22af5e28f62c90f342169dad726731a39 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 13 Sep 2017 14:43:41 +0200 +Subject: [PATCH 161/347] srcu: use cpu_online() instead custom check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The current check via srcu_online is slightly racy because after looking +at srcu_online there could be an interrupt that interrupted us long +enough until the CPU we checked against went offline. +An alternative would be to hold the hotplug rwsem (so the CPUs don't +change their state) and then check based on cpu_online() if we queue it +on a specific CPU or not. queue_work_on() itself can handle if something +is enqueued on an offline CPU but a timer which is enqueued on an offline +CPU won't fire until the CPU is back online. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/rcu/srcutree.c | 22 ++++------------------ + kernel/rcu/tree.c | 4 ---- + 2 files changed, 4 insertions(+), 22 deletions(-) + +diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c +index 1ff17e297f0c..df0375453ba1 100644 +--- a/kernel/rcu/srcutree.c ++++ b/kernel/rcu/srcutree.c +@@ -38,6 +38,7 @@ + #include <linux/delay.h> + #include <linux/module.h> + #include <linux/srcu.h> ++#include <linux/cpu.h> + + #include "rcu.h" + #include "rcu_segcblist.h" +@@ -460,21 +461,6 @@ static void srcu_gp_start(struct srcu_struct *sp) + WARN_ON_ONCE(state != SRCU_STATE_SCAN1); + } + +-/* +- * Track online CPUs to guide callback workqueue placement. +- */ +-DEFINE_PER_CPU(bool, srcu_online); +- +-void srcu_online_cpu(unsigned int cpu) +-{ +- WRITE_ONCE(per_cpu(srcu_online, cpu), true); +-} +- +-void srcu_offline_cpu(unsigned int cpu) +-{ +- WRITE_ONCE(per_cpu(srcu_online, cpu), false); +-} +- + /* + * Place the workqueue handler on the specified CPU if online, otherwise + * just run it whereever. This is useful for placing workqueue handlers +@@ -486,12 +472,12 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq, + { + bool ret; + +- preempt_disable(); +- if (READ_ONCE(per_cpu(srcu_online, cpu))) ++ cpus_read_lock(); ++ if (cpu_online(cpu)) + ret = queue_delayed_work_on(cpu, wq, dwork, delay); + else + ret = queue_delayed_work(wq, dwork, delay); +- preempt_enable(); ++ cpus_read_unlock(); + return ret; + } + +diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c +index ae716ca783bc..f162a4f54b05 100644 +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -3784,8 +3784,6 @@ int rcutree_online_cpu(unsigned int cpu) + rnp->ffmask |= rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } +- if (IS_ENABLED(CONFIG_TREE_SRCU)) +- srcu_online_cpu(cpu); + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) + return 0; /* Too early in boot for scheduler work. */ + sync_sched_exp_online_cleanup(cpu); +@@ -3813,8 +3811,6 @@ int rcutree_offline_cpu(unsigned int cpu) + } + + rcutree_affinity_setting(cpu, cpu); +- if (IS_ENABLED(CONFIG_TREE_SRCU)) +- srcu_offline_cpu(cpu); + return 0; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0162-srcu-replace-local_irqsave-with-a-locallock.patch b/debian/patches-rt/0162-srcu-replace-local_irqsave-with-a-locallock.patch new file mode 100644 index 000000000..5cdde2079 --- /dev/null +++ b/debian/patches-rt/0162-srcu-replace-local_irqsave-with-a-locallock.patch @@ -0,0 +1,77 @@ +From 62524e62d2f224889aee36c1c134f0efb2fba025 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 12 Oct 2017 18:37:12 +0200 +Subject: [PATCH 162/347] srcu: replace local_irqsave() with a locallock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There are two instances which disable interrupts in order to become a +stable this_cpu_ptr() pointer. The restore part is coupled with +spin_unlock_irqrestore() which does not work on RT. +Replace the local_irq_save() call with the appropriate local_lock() +version of it. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/rcu/srcutree.c | 14 +++++++++----- + 1 file changed, 9 insertions(+), 5 deletions(-) + +diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c +index df0375453ba1..0f09a1a9e17c 100644 +--- a/kernel/rcu/srcutree.c ++++ b/kernel/rcu/srcutree.c +@@ -39,6 +39,7 @@ + #include <linux/module.h> + #include <linux/srcu.h> + #include <linux/cpu.h> ++#include <linux/locallock.h> + + #include "rcu.h" + #include "rcu_segcblist.h" +@@ -760,6 +761,8 @@ static void srcu_flip(struct srcu_struct *sp) + * negligible when amoritized over that time period, and the extra latency + * of a needlessly non-expedited grace period is similarly negligible. + */ ++static DEFINE_LOCAL_IRQ_LOCK(sp_llock); ++ + static bool srcu_might_be_idle(struct srcu_struct *sp) + { + unsigned long curseq; +@@ -768,13 +771,13 @@ static bool srcu_might_be_idle(struct srcu_struct *sp) + unsigned long t; + + /* If the local srcu_data structure has callbacks, not idle. */ +- local_irq_save(flags); ++ local_lock_irqsave(sp_llock, flags); + sdp = this_cpu_ptr(sp->sda); + if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(sp_llock, flags); + return false; /* Callbacks already present, so not idle. */ + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(sp_llock, flags); + + /* + * No local callbacks, so probabalistically probe global state. +@@ -852,7 +855,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, + return; + } + rhp->func = func; +- local_irq_save(flags); ++ local_lock_irqsave(sp_llock, flags); + sdp = this_cpu_ptr(sp->sda); + spin_lock_rcu_node(sdp); + rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); +@@ -868,7 +871,8 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, + sdp->srcu_gp_seq_needed_exp = s; + needexp = true; + } +- spin_unlock_irqrestore_rcu_node(sdp, flags); ++ spin_unlock_rcu_node(sdp); ++ local_unlock_irqrestore(sp_llock, flags); + if (needgp) + srcu_funnel_gp_start(sp, sdp, s, do_norm); + else if (needexp) +-- +2.36.1 + diff --git a/debian/patches-rt/0163-rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch b/debian/patches-rt/0163-rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch new file mode 100644 index 000000000..495aa2d9d --- /dev/null +++ b/debian/patches-rt/0163-rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch @@ -0,0 +1,37 @@ +From 4da02c2768978a9206e437ab36a1d6e9ed2641af Mon Sep 17 00:00:00 2001 +From: Julia Cartwright <julia@ni.com> +Date: Wed, 12 Oct 2016 11:21:14 -0500 +Subject: [PATCH 163/347] rcu: enable rcu_normal_after_boot by default for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The forcing of an expedited grace period is an expensive and very +RT-application unfriendly operation, as it forcibly preempts all running +tasks on CPUs which are preventing the gp from expiring. + +By default, as a policy decision, disable the expediting of grace +periods (after boot) on configurations which enable PREEMPT_RT_FULL. + +Suggested-by: Luiz Capitulino <lcapitulino@redhat.com> +Acked-by: Paul E. McKenney <paulmck@linux.ibm.com> +Signed-off-by: Julia Cartwright <julia@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/rcu/update.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c +index 6ffafb1b1584..16d8dba23329 100644 +--- a/kernel/rcu/update.c ++++ b/kernel/rcu/update.c +@@ -68,7 +68,7 @@ extern int rcu_expedited; /* from sysctl */ + module_param(rcu_expedited, int, 0); + extern int rcu_normal; /* from sysctl */ + module_param(rcu_normal, int, 0); +-static int rcu_normal_after_boot; ++static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); + module_param(rcu_normal_after_boot, int, 0); + #endif /* #ifndef CONFIG_TINY_RCU */ + +-- +2.36.1 + diff --git a/debian/patches-rt/0164-tty-serial-omap-Make-the-locking-RT-aware.patch b/debian/patches-rt/0164-tty-serial-omap-Make-the-locking-RT-aware.patch new file mode 100644 index 000000000..842a20687 --- /dev/null +++ b/debian/patches-rt/0164-tty-serial-omap-Make-the-locking-RT-aware.patch @@ -0,0 +1,49 @@ +From ebe8e211893ebd446569ab83eeb7277a77db835f Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 28 Jul 2011 13:32:57 +0200 +Subject: [PATCH 164/347] tty/serial/omap: Make the locking RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the +optimsation we are looking for. Redo it to make it work on -RT and +non-RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/tty/serial/omap-serial.c | 12 ++++-------- + 1 file changed, 4 insertions(+), 8 deletions(-) + +diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c +index 6420ae581a80..0f4f41ed9ffa 100644 +--- a/drivers/tty/serial/omap-serial.c ++++ b/drivers/tty/serial/omap-serial.c +@@ -1307,13 +1307,10 @@ serial_omap_console_write(struct console *co, const char *s, + + pm_runtime_get_sync(up->dev); + +- local_irq_save(flags); +- if (up->port.sysrq) +- locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock(&up->port.lock); ++ if (up->port.sysrq || oops_in_progress) ++ locked = spin_trylock_irqsave(&up->port.lock, flags); + else +- spin_lock(&up->port.lock); ++ spin_lock_irqsave(&up->port.lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -1342,8 +1339,7 @@ serial_omap_console_write(struct console *co, const char *s, + pm_runtime_mark_last_busy(up->dev); + pm_runtime_put_autosuspend(up->dev); + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init +-- +2.36.1 + diff --git a/debian/patches-rt/0165-tty-serial-pl011-Make-the-locking-work-on-RT.patch b/debian/patches-rt/0165-tty-serial-pl011-Make-the-locking-work-on-RT.patch new file mode 100644 index 000000000..6309f7e50 --- /dev/null +++ b/debian/patches-rt/0165-tty-serial-pl011-Make-the-locking-work-on-RT.patch @@ -0,0 +1,54 @@ +From e699af6cca35d036a6876b5c9ec0b1355cc16842 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 8 Jan 2013 21:36:51 +0100 +Subject: [PATCH 165/347] tty/serial/pl011: Make the locking work on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the optimsation +we are looking for. Redo it to make it work on -RT and non-RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/tty/serial/amba-pl011.c | 15 ++++++++++----- + 1 file changed, 10 insertions(+), 5 deletions(-) + +diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c +index 5edc3813a9b9..7d4aee4c5091 100644 +--- a/drivers/tty/serial/amba-pl011.c ++++ b/drivers/tty/serial/amba-pl011.c +@@ -2196,13 +2196,19 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) + + clk_enable(uap->clk); + +- local_irq_save(flags); ++ /* ++ * local_irq_save(flags); ++ * ++ * This local_irq_save() is nonsense. If we come in via sysrq ++ * handling then interrupts are already disabled. Aside of ++ * that the port.sysrq check is racy on SMP regardless. ++ */ + if (uap->port.sysrq) + locked = 0; + else if (oops_in_progress) +- locked = spin_trylock(&uap->port.lock); ++ locked = spin_trylock_irqsave(&uap->port.lock, flags); + else +- spin_lock(&uap->port.lock); ++ spin_lock_irqsave(&uap->port.lock, flags); + + /* + * First save the CR then disable the interrupts +@@ -2228,8 +2234,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) + pl011_write(old_cr, uap, REG_CR); + + if (locked) +- spin_unlock(&uap->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&uap->port.lock, flags); + + clk_disable(uap->clk); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0166-tty-serial-pl011-explicitly-initialize-the-flags-var.patch b/debian/patches-rt/0166-tty-serial-pl011-explicitly-initialize-the-flags-var.patch new file mode 100644 index 000000000..abf490978 --- /dev/null +++ b/debian/patches-rt/0166-tty-serial-pl011-explicitly-initialize-the-flags-var.patch @@ -0,0 +1,45 @@ +From 59b39d4106f01f2ad2f1e7999490b5afc54f8b49 Mon Sep 17 00:00:00 2001 +From: Kurt Kanzenbach <kurt@linutronix.de> +Date: Mon, 24 Sep 2018 10:29:01 +0200 +Subject: [PATCH 166/347] tty: serial: pl011: explicitly initialize the flags + variable +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Silence the following gcc warning: + +drivers/tty/serial/amba-pl011.c: In function ‘pl011_console_write’: +./include/linux/spinlock.h:260:3: warning: ‘flags’ may be used uninitialized in this function [-Wmaybe-uninitialized] + _raw_spin_unlock_irqrestore(lock, flags); \ + ^~~~~~~~~~~~~~~~~~~~~~~~~~~ +drivers/tty/serial/amba-pl011.c:2214:16: note: ‘flags’ was declared here + unsigned long flags; + ^~~~~ + +The code is correct. Thus, initializing flags to zero doesn't change the +behavior and resolves the warning. + +Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/tty/serial/amba-pl011.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c +index 7d4aee4c5091..9666a20f23ec 100644 +--- a/drivers/tty/serial/amba-pl011.c ++++ b/drivers/tty/serial/amba-pl011.c +@@ -2191,7 +2191,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) + { + struct uart_amba_port *uap = amba_ports[co->index]; + unsigned int old_cr = 0, new_cr; +- unsigned long flags; ++ unsigned long flags = 0; + int locked = 1; + + clk_enable(uap->clk); +-- +2.36.1 + diff --git a/debian/patches-rt/0167-rt-Improve-the-serial-console-PASS_LIMIT.patch b/debian/patches-rt/0167-rt-Improve-the-serial-console-PASS_LIMIT.patch new file mode 100644 index 000000000..aa552dbab --- /dev/null +++ b/debian/patches-rt/0167-rt-Improve-the-serial-console-PASS_LIMIT.patch @@ -0,0 +1,47 @@ +From 2ca7e055b4220689e58ff53c7e64caf5e8eadb37 Mon Sep 17 00:00:00 2001 +From: Ingo Molnar <mingo@elte.hu> +Date: Wed, 14 Dec 2011 13:05:54 +0100 +Subject: [PATCH 167/347] rt: Improve the serial console PASS_LIMIT +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Beyond the warning: + + drivers/tty/serial/8250/8250.c:1613:6: warning: unused variable ‘pass_counter’ [-Wunused-variable] + +the solution of just looping infinitely was ugly - up it to 1 million to +give it a chance to continue in some really ugly situation. + +Signed-off-by: Ingo Molnar <mingo@elte.hu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/tty/serial/8250/8250_core.c | 11 ++++++++++- + 1 file changed, 10 insertions(+), 1 deletion(-) + +diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c +index d2df7d71d666..57fd29b2ddf5 100644 +--- a/drivers/tty/serial/8250/8250_core.c ++++ b/drivers/tty/serial/8250/8250_core.c +@@ -54,7 +54,16 @@ static struct uart_driver serial8250_reg; + + static unsigned int skip_txen_test; /* force skip of txen test at init time */ + +-#define PASS_LIMIT 512 ++/* ++ * On -rt we can have a more delays, and legitimately ++ * so - so don't drop work spuriously and spam the ++ * syslog: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define PASS_LIMIT 1000000 ++#else ++# define PASS_LIMIT 512 ++#endif + + #include <asm/serial.h> + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0168-tty-serial-8250-don-t-take-the-trylock-during-oops.patch b/debian/patches-rt/0168-tty-serial-8250-don-t-take-the-trylock-during-oops.patch new file mode 100644 index 000000000..8cb91d2aa --- /dev/null +++ b/debian/patches-rt/0168-tty-serial-8250-don-t-take-the-trylock-during-oops.patch @@ -0,0 +1,35 @@ +From bf2010a260b11e805d39d0d1a6d0302b1d3e7210 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 11 Apr 2016 16:55:02 +0200 +Subject: [PATCH 168/347] tty: serial: 8250: don't take the trylock during oops +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +An oops with irqs off (panic() from irqsafe hrtimer like the watchdog +timer) will lead to a lockdep warning on each invocation and as such +never completes. +Therefore we skip the trylock in the oops case. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/tty/serial/8250/8250_port.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c +index 34687c354f5e..ef8bccc0823c 100644 +--- a/drivers/tty/serial/8250/8250_port.c ++++ b/drivers/tty/serial/8250/8250_port.c +@@ -3294,10 +3294,8 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, + + serial8250_rpm_get(up); + +- if (port->sysrq) ++ if (port->sysrq || oops_in_progress) + locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); + +-- +2.36.1 + diff --git a/debian/patches-rt/0169-locking-percpu-rwsem-Remove-preempt_disable-variants.patch b/debian/patches-rt/0169-locking-percpu-rwsem-Remove-preempt_disable-variants.patch new file mode 100644 index 000000000..a6a0cd7c4 --- /dev/null +++ b/debian/patches-rt/0169-locking-percpu-rwsem-Remove-preempt_disable-variants.patch @@ -0,0 +1,226 @@ +From 80adc8fb1dabebcc9d41cb6c0f122860061c12a3 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Wed, 23 Nov 2016 16:29:32 +0100 +Subject: [PATCH 169/347] locking/percpu-rwsem: Remove preempt_disable variants +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Effective revert commit: + + 87709e28dc7c ("fs/locks: Use percpu_down_read_preempt_disable()") + +This is causing major pain for PREEMPT_RT and is only a very small +performance issue for PREEMPT=y. + +Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> +--- + fs/locks.c | 32 ++++++++++++++++---------------- + include/linux/percpu-rwsem.h | 24 ++++-------------------- + 2 files changed, 20 insertions(+), 36 deletions(-) + +diff --git a/fs/locks.c b/fs/locks.c +index 28270e74be34..552476d6f6bb 100644 +--- a/fs/locks.c ++++ b/fs/locks.c +@@ -936,7 +936,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) + return -ENOMEM; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + if (request->fl_flags & FL_ACCESS) + goto find_conflict; +@@ -977,7 +977,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) + + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + if (new_fl) + locks_free_lock(new_fl); + locks_dispose_list(&dispose); +@@ -1015,7 +1015,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, + new_fl2 = locks_alloc_lock(); + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + /* + * New lock request. Walk all POSIX locks and look for conflicts. If +@@ -1187,7 +1187,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, + } + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + /* + * Free any unused locks. + */ +@@ -1462,7 +1462,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) + return error; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + + time_out_leases(inode, &dispose); +@@ -1514,13 +1514,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) + locks_insert_block(fl, new_fl); + trace_break_lease_block(inode, new_fl); + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + + locks_dispose_list(&dispose); + error = wait_event_interruptible_timeout(new_fl->fl_wait, + !new_fl->fl_next, break_time); + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + trace_break_lease_unblock(inode, new_fl); + locks_delete_block(new_fl); +@@ -1537,7 +1537,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) + } + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + locks_dispose_list(&dispose); + locks_free_lock(new_fl); + return error; +@@ -1609,7 +1609,7 @@ int fcntl_getlease(struct file *filp) + + ctx = smp_load_acquire(&inode->i_flctx); + if (ctx && !list_empty_careful(&ctx->flc_lease)) { +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + time_out_leases(inode, &dispose); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { +@@ -1619,7 +1619,7 @@ int fcntl_getlease(struct file *filp) + break; + } + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + + locks_dispose_list(&dispose); + } +@@ -1693,7 +1693,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr + return -EINVAL; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + time_out_leases(inode, &dispose); + error = check_conflicting_open(dentry, arg, lease->fl_flags); +@@ -1764,7 +1764,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr + lease->fl_lmops->lm_setup(lease, priv); + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + locks_dispose_list(&dispose); + if (is_deleg) + inode_unlock(inode); +@@ -1787,7 +1787,7 @@ static int generic_delete_lease(struct file *filp, void *owner) + return error; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file == filp && +@@ -1800,7 +1800,7 @@ static int generic_delete_lease(struct file *filp, void *owner) + if (victim) + error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + locks_dispose_list(&dispose); + return error; + } +@@ -2531,13 +2531,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) + if (list_empty(&ctx->flc_lease)) + return; + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) + if (filp == fl->fl_file) + lease_modify(fl, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + + locks_dispose_list(&dispose); + } +diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h +index 79b99d653e03..fb44e237316d 100644 +--- a/include/linux/percpu-rwsem.h ++++ b/include/linux/percpu-rwsem.h +@@ -29,7 +29,7 @@ static struct percpu_rw_semaphore name = { \ + extern int __percpu_down_read(struct percpu_rw_semaphore *, int); + extern void __percpu_up_read(struct percpu_rw_semaphore *); + +-static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem) ++static inline void percpu_down_read(struct percpu_rw_semaphore *sem) + { + might_sleep(); + +@@ -47,16 +47,10 @@ static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore * + __this_cpu_inc(*sem->read_count); + if (unlikely(!rcu_sync_is_idle(&sem->rss))) + __percpu_down_read(sem, false); /* Unconditional memory barrier */ +- barrier(); + /* +- * The barrier() prevents the compiler from ++ * The preempt_enable() prevents the compiler from + * bleeding the critical section out. + */ +-} +- +-static inline void percpu_down_read(struct percpu_rw_semaphore *sem) +-{ +- percpu_down_read_preempt_disable(sem); + preempt_enable(); + } + +@@ -83,13 +77,9 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem) + return ret; + } + +-static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem) ++static inline void percpu_up_read(struct percpu_rw_semaphore *sem) + { +- /* +- * The barrier() prevents the compiler from +- * bleeding the critical section out. +- */ +- barrier(); ++ preempt_disable(); + /* + * Same as in percpu_down_read(). + */ +@@ -102,12 +92,6 @@ static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem + rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); + } + +-static inline void percpu_up_read(struct percpu_rw_semaphore *sem) +-{ +- preempt_disable(); +- percpu_up_read_preempt_enable(sem); +-} +- + extern void percpu_down_write(struct percpu_rw_semaphore *); + extern void percpu_up_write(struct percpu_rw_semaphore *); + +-- +2.36.1 + diff --git a/debian/patches-rt/0170-mm-Protect-activate_mm-by-preempt_-disable-enable-_r.patch b/debian/patches-rt/0170-mm-Protect-activate_mm-by-preempt_-disable-enable-_r.patch new file mode 100644 index 000000000..f39bdbeba --- /dev/null +++ b/debian/patches-rt/0170-mm-Protect-activate_mm-by-preempt_-disable-enable-_r.patch @@ -0,0 +1,82 @@ +From 67c3a14d6fbac8e692c9e7a999b7fe8d062529bc Mon Sep 17 00:00:00 2001 +From: Yong Zhang <yong.zhang0@gmail.com> +Date: Tue, 15 May 2012 13:53:56 +0800 +Subject: [PATCH 170/347] mm: Protect activate_mm() by + preempt_[disable&enable]_rt() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +User preempt_*_rt instead of local_irq_*_rt or otherwise there will be +warning on ARM like below: + +WARNING: at build/linux/kernel/smp.c:459 smp_call_function_many+0x98/0x264() +Modules linked in: +[<c0013bb4>] (unwind_backtrace+0x0/0xe4) from [<c001be94>] (warn_slowpath_common+0x4c/0x64) +[<c001be94>] (warn_slowpath_common+0x4c/0x64) from [<c001bec4>] (warn_slowpath_null+0x18/0x1c) +[<c001bec4>] (warn_slowpath_null+0x18/0x1c) from [<c0053ff8>](smp_call_function_many+0x98/0x264) +[<c0053ff8>] (smp_call_function_many+0x98/0x264) from [<c0054364>] (smp_call_function+0x44/0x6c) +[<c0054364>] (smp_call_function+0x44/0x6c) from [<c0017d50>] (__new_context+0xbc/0x124) +[<c0017d50>] (__new_context+0xbc/0x124) from [<c009e49c>] (flush_old_exec+0x460/0x5e4) +[<c009e49c>] (flush_old_exec+0x460/0x5e4) from [<c00d61ac>] (load_elf_binary+0x2e0/0x11ac) +[<c00d61ac>] (load_elf_binary+0x2e0/0x11ac) from [<c009d060>] (search_binary_handler+0x94/0x2a4) +[<c009d060>] (search_binary_handler+0x94/0x2a4) from [<c009e8fc>] (do_execve+0x254/0x364) +[<c009e8fc>] (do_execve+0x254/0x364) from [<c0010e84>] (sys_execve+0x34/0x54) +[<c0010e84>] (sys_execve+0x34/0x54) from [<c000da00>] (ret_fast_syscall+0x0/0x30) +---[ end trace 0000000000000002 ]--- + +The reason is that ARM need irq enabled when doing activate_mm(). +According to mm-protect-activate-switch-mm.patch, actually +preempt_[disable|enable]_rt() is sufficient. + +Inspired-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Yong Zhang <yong.zhang0@gmail.com> +Cc: Steven Rostedt <rostedt@goodmis.org> +Link: http://lkml.kernel.org/r/1337061236-1766-1-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + fs/exec.c | 2 ++ + mm/mmu_context.c | 2 ++ + 2 files changed, 4 insertions(+) + +diff --git a/fs/exec.c b/fs/exec.c +index 28e3b5eb2f4a..2c15772a1feb 100644 +--- a/fs/exec.c ++++ b/fs/exec.c +@@ -1028,6 +1028,7 @@ static int exec_mmap(struct mm_struct *mm) + } + } + task_lock(tsk); ++ preempt_disable_rt(); + + local_irq_disable(); + active_mm = tsk->active_mm; +@@ -1047,6 +1048,7 @@ static int exec_mmap(struct mm_struct *mm) + local_irq_enable(); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + if (old_mm) { + up_read(&old_mm->mmap_sem); +diff --git a/mm/mmu_context.c b/mm/mmu_context.c +index 3e612ae748e9..d0ccc070979f 100644 +--- a/mm/mmu_context.c ++++ b/mm/mmu_context.c +@@ -25,6 +25,7 @@ void use_mm(struct mm_struct *mm) + struct task_struct *tsk = current; + + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + if (active_mm != mm) { + mmgrab(mm); +@@ -32,6 +33,7 @@ void use_mm(struct mm_struct *mm) + } + tsk->mm = mm; + switch_mm(active_mm, mm, tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + #ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); +-- +2.36.1 + diff --git a/debian/patches-rt/0171-fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-ini.patch b/debian/patches-rt/0171-fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-ini.patch new file mode 100644 index 000000000..c6db9639d --- /dev/null +++ b/debian/patches-rt/0171-fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-ini.patch @@ -0,0 +1,61 @@ +From 54729c769ee68192a795377f27cc479b959ca152 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 13 Sep 2017 12:32:34 +0200 +Subject: [PATCH 171/347] fs/dcache: bring back explicit INIT_HLIST_BL_HEAD + init +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Commit 3d375d78593c ("mm: update callers to use HASH_ZERO flag") removed +INIT_HLIST_BL_HEAD and uses the ZERO flag instead for the init. However +on RT we have also a spinlock which needs an init call so we can't use +that. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/dcache.c | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +diff --git a/fs/dcache.c b/fs/dcache.c +index 1897833a4668..b5e53587d14b 100644 +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -3077,6 +3077,8 @@ __setup("dhash_entries=", set_dhash_entries); + + static void __init dcache_init_early(void) + { ++ unsigned int loop; ++ + /* If hashes are distributed across NUMA nodes, defer + * hash allocation until vmalloc space is available. + */ +@@ -3093,11 +3095,16 @@ static void __init dcache_init_early(void) + NULL, + 0, + 0); ++ ++ for (loop = 0; loop < (1U << d_hash_shift); loop++) ++ INIT_HLIST_BL_HEAD(dentry_hashtable + loop); ++ + d_hash_shift = 32 - d_hash_shift; + } + + static void __init dcache_init(void) + { ++ unsigned int loop; + /* + * A constructor could be added for stable state like the lists, + * but it is probably not worth it because of the cache nature +@@ -3121,6 +3128,10 @@ static void __init dcache_init(void) + NULL, + 0, + 0); ++ ++ for (loop = 0; loop < (1U << d_hash_shift); loop++) ++ INIT_HLIST_BL_HEAD(dentry_hashtable + loop); ++ + d_hash_shift = 32 - d_hash_shift; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0172-fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch b/debian/patches-rt/0172-fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch new file mode 100644 index 000000000..83ac5e6c0 --- /dev/null +++ b/debian/patches-rt/0172-fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch @@ -0,0 +1,99 @@ +From 44eeab3501a8354ba4c3fe6414168df6ccf60b74 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 20 Oct 2017 11:29:53 +0200 +Subject: [PATCH 172/347] fs/dcache: disable preemption on i_dir_seq's write + side +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +i_dir_seq is an opencoded seqcounter. Based on the code it looks like we +could have two writers in parallel despite the fact that the d_lock is +held. The problem is that during the write process on RT the preemption +is still enabled and if this process is interrupted by a reader with RT +priority then we lock up. +To avoid that lock up I am disabling the preemption during the update. +The rename of i_dir_seq is here to ensure to catch new write sides in +future. + +Cc: stable-rt@vger.kernel.org +Reported-by: Oleg.Karfich@wago.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/dcache.c | 12 +++++++----- + fs/inode.c | 2 +- + include/linux/fs.h | 2 +- + 3 files changed, 9 insertions(+), 7 deletions(-) + +diff --git a/fs/dcache.c b/fs/dcache.c +index b5e53587d14b..1ae163d54925 100644 +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -2406,9 +2406,10 @@ EXPORT_SYMBOL(d_rehash); + static inline unsigned start_dir_add(struct inode *dir) + { + ++ preempt_disable_rt(); + for (;;) { +- unsigned n = dir->i_dir_seq; +- if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) ++ unsigned n = dir->__i_dir_seq; ++ if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n) + return n; + cpu_relax(); + } +@@ -2416,7 +2417,8 @@ static inline unsigned start_dir_add(struct inode *dir) + + static inline void end_dir_add(struct inode *dir, unsigned n) + { +- smp_store_release(&dir->i_dir_seq, n + 2); ++ smp_store_release(&dir->__i_dir_seq, n + 2); ++ preempt_enable_rt(); + } + + static void d_wait_lookup(struct dentry *dentry) +@@ -2449,7 +2451,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, + + retry: + rcu_read_lock(); +- seq = smp_load_acquire(&parent->d_inode->i_dir_seq); ++ seq = smp_load_acquire(&parent->d_inode->__i_dir_seq); + r_seq = read_seqbegin(&rename_lock); + dentry = __d_lookup_rcu(parent, name, &d_seq); + if (unlikely(dentry)) { +@@ -2477,7 +2479,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, + } + + hlist_bl_lock(b); +- if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { ++ if (unlikely(READ_ONCE(parent->d_inode->__i_dir_seq) != seq)) { + hlist_bl_unlock(b); + rcu_read_unlock(); + goto retry; +diff --git a/fs/inode.c b/fs/inode.c +index c9eb5041ffae..e1fb0b743c96 100644 +--- a/fs/inode.c ++++ b/fs/inode.c +@@ -156,7 +156,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) + inode->i_bdev = NULL; + inode->i_cdev = NULL; + inode->i_link = NULL; +- inode->i_dir_seq = 0; ++ inode->__i_dir_seq = 0; + inode->i_rdev = 0; + inode->dirtied_when = 0; + +diff --git a/include/linux/fs.h b/include/linux/fs.h +index 86f884e78b6b..029870aca4ff 100644 +--- a/include/linux/fs.h ++++ b/include/linux/fs.h +@@ -679,7 +679,7 @@ struct inode { + struct block_device *i_bdev; + struct cdev *i_cdev; + char *i_link; +- unsigned i_dir_seq; ++ unsigned __i_dir_seq; + }; + + __u32 i_generation; +-- +2.36.1 + diff --git a/debian/patches-rt/0173-squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch b/debian/patches-rt/0173-squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch new file mode 100644 index 000000000..e885134f9 --- /dev/null +++ b/debian/patches-rt/0173-squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch @@ -0,0 +1,72 @@ +From 98873b747e4321516bb428c214fde307593e19f8 Mon Sep 17 00:00:00 2001 +From: Julia Cartwright <julia@ni.com> +Date: Mon, 7 May 2018 08:58:57 -0500 +Subject: [PATCH 173/347] squashfs: make use of local lock in multi_cpu + decompressor +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Currently, the squashfs multi_cpu decompressor makes use of +get_cpu_ptr()/put_cpu_ptr(), which unconditionally disable preemption +during decompression. + +Because the workload is distributed across CPUs, all CPUs can observe a +very high wakeup latency, which has been seen to be as much as 8000us. + +Convert this decompressor to make use of a local lock, which will allow +execution of the decompressor with preemption-enabled, but also ensure +concurrent accesses to the percpu compressor data on the local CPU will +be serialized. + +Cc: stable-rt@vger.kernel.org +Reported-by: Alexander Stein <alexander.stein@systec-electronic.com> +Tested-by: Alexander Stein <alexander.stein@systec-electronic.com> +Signed-off-by: Julia Cartwright <julia@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/squashfs/decompressor_multi_percpu.c | 16 ++++++++++++---- + 1 file changed, 12 insertions(+), 4 deletions(-) + +diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c +index 23a9c28ad8ea..6a73c4fa88e7 100644 +--- a/fs/squashfs/decompressor_multi_percpu.c ++++ b/fs/squashfs/decompressor_multi_percpu.c +@@ -10,6 +10,7 @@ + #include <linux/slab.h> + #include <linux/percpu.h> + #include <linux/buffer_head.h> ++#include <linux/locallock.h> + + #include "squashfs_fs.h" + #include "squashfs_fs_sb.h" +@@ -25,6 +26,8 @@ struct squashfs_stream { + void *stream; + }; + ++static DEFINE_LOCAL_IRQ_LOCK(stream_lock); ++ + void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) + { +@@ -79,10 +82,15 @@ int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + { + struct squashfs_stream __percpu *percpu = + (struct squashfs_stream __percpu *) msblk->stream; +- struct squashfs_stream *stream = get_cpu_ptr(percpu); +- int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, +- offset, length, output); +- put_cpu_ptr(stream); ++ struct squashfs_stream *stream; ++ int res; ++ ++ stream = get_locked_ptr(stream_lock, percpu); ++ ++ res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, ++ offset, length, output); ++ ++ put_locked_ptr(stream_lock, stream); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", +-- +2.36.1 + diff --git a/debian/patches-rt/0174-thermal-Defer-thermal-wakups-to-threads.patch b/debian/patches-rt/0174-thermal-Defer-thermal-wakups-to-threads.patch new file mode 100644 index 000000000..87e9fc777 --- /dev/null +++ b/debian/patches-rt/0174-thermal-Defer-thermal-wakups-to-threads.patch @@ -0,0 +1,137 @@ +From add227c3c4d74e71f3d02036aed9c6ceae6a6f6c Mon Sep 17 00:00:00 2001 +From: Daniel Wagner <wagi@monom.org> +Date: Tue, 17 Feb 2015 09:37:44 +0100 +Subject: [PATCH 174/347] thermal: Defer thermal wakups to threads +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On RT the spin lock in pkg_temp_thermal_platfrom_thermal_notify will +call schedule while we run in irq context. + +[<ffffffff816850ac>] dump_stack+0x4e/0x8f +[<ffffffff81680f7d>] __schedule_bug+0xa6/0xb4 +[<ffffffff816896b4>] __schedule+0x5b4/0x700 +[<ffffffff8168982a>] schedule+0x2a/0x90 +[<ffffffff8168a8b5>] rt_spin_lock_slowlock+0xe5/0x2d0 +[<ffffffff8168afd5>] rt_spin_lock+0x25/0x30 +[<ffffffffa03a7b75>] pkg_temp_thermal_platform_thermal_notify+0x45/0x134 [x86_pkg_temp_thermal] +[<ffffffff8103d4db>] ? therm_throt_process+0x1b/0x160 +[<ffffffff8103d831>] intel_thermal_interrupt+0x211/0x250 +[<ffffffff8103d8c1>] smp_thermal_interrupt+0x21/0x40 +[<ffffffff8169415d>] thermal_interrupt+0x6d/0x80 + +Let's defer the work to a kthread. + +Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> +[bigeasy: reoder init/denit position. TODO: flush swork on exit] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/thermal/x86_pkg_temp_thermal.c | 52 ++++++++++++++++++++++++-- + 1 file changed, 49 insertions(+), 3 deletions(-) + +diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c +index 1ef937d799e4..a5991cbb408f 100644 +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -29,6 +29,7 @@ + #include <linux/pm.h> + #include <linux/thermal.h> + #include <linux/debugfs.h> ++#include <linux/swork.h> + #include <asm/cpu_device_id.h> + #include <asm/mce.h> + +@@ -329,7 +330,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work) + schedule_delayed_work_on(cpu, work, ms); + } + +-static int pkg_thermal_notify(u64 msr_val) ++static void pkg_thermal_notify_work(struct swork_event *event) + { + int cpu = smp_processor_id(); + struct pkg_device *pkgdev; +@@ -348,9 +349,47 @@ static int pkg_thermal_notify(u64 msr_val) + } + + spin_unlock_irqrestore(&pkg_temp_lock, flags); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct swork_event notify_work; ++ ++static int pkg_thermal_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, pkg_thermal_notify_work); + return 0; + } + ++static void pkg_thermal_notify_work_cleanup(void) ++{ ++ swork_put(); ++} ++ ++static int pkg_thermal_notify(u64 msr_val) ++{ ++ swork_queue(¬ify_work); ++ return 0; ++} ++ ++#else /* !CONFIG_PREEMPT_RT_FULL */ ++ ++static int pkg_thermal_notify_work_init(void) { return 0; } ++ ++static void pkg_thermal_notify_work_cleanup(void) { } ++ ++static int pkg_thermal_notify(u64 msr_val) ++{ ++ pkg_thermal_notify_work(NULL); ++ return 0; ++} ++#endif /* CONFIG_PREEMPT_RT_FULL */ ++ + static int pkg_temp_thermal_device_add(unsigned int cpu) + { + int pkgid = topology_logical_package_id(cpu); +@@ -515,11 +554,16 @@ static int __init pkg_temp_thermal_init(void) + if (!x86_match_cpu(pkg_temp_thermal_ids)) + return -ENODEV; + ++ if (!pkg_thermal_notify_work_init()) ++ return -ENODEV; ++ + max_packages = topology_max_packages(); + packages = kcalloc(max_packages, sizeof(struct pkg_device *), + GFP_KERNEL); +- if (!packages) +- return -ENOMEM; ++ if (!packages) { ++ ret = -ENOMEM; ++ goto err; ++ } + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online", + pkg_thermal_cpu_online, pkg_thermal_cpu_offline); +@@ -537,6 +581,7 @@ static int __init pkg_temp_thermal_init(void) + return 0; + + err: ++ pkg_thermal_notify_work_cleanup(); + kfree(packages); + return ret; + } +@@ -550,6 +595,7 @@ static void __exit pkg_temp_thermal_exit(void) + cpuhp_remove_state(pkg_thermal_hp_state); + debugfs_remove_recursive(debugfs); + kfree(packages); ++ pkg_thermal_notify_work_cleanup(); + } + module_exit(pkg_temp_thermal_exit) + +-- +2.36.1 + diff --git a/debian/patches-rt/0175-x86-fpu-Disable-preemption-around-local_bh_disable.patch b/debian/patches-rt/0175-x86-fpu-Disable-preemption-around-local_bh_disable.patch new file mode 100644 index 000000000..1aaf1d6d1 --- /dev/null +++ b/debian/patches-rt/0175-x86-fpu-Disable-preemption-around-local_bh_disable.patch @@ -0,0 +1,38 @@ +From b666ce0515d1940495c2bbb0ca0f32c1fea9ef38 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 11 Dec 2018 15:10:33 +0100 +Subject: [PATCH 175/347] x86/fpu: Disable preemption around local_bh_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +__fpu__restore_sig() restores the content of the FPU state in the CPUs +and in order to avoid concurency it disbles BH. On !RT it also disables +preemption but on RT we can get preempted in BH. + +Add preempt_disable() while the FPU state is restored. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/kernel/fpu/signal.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c +index 86a231338bbf..e5c8d5245289 100644 +--- a/arch/x86/kernel/fpu/signal.c ++++ b/arch/x86/kernel/fpu/signal.c +@@ -351,10 +351,12 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) + sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); + } + ++ preempt_disable(); + local_bh_disable(); + fpu->initialized = 1; + fpu__restore(fpu); + local_bh_enable(); ++ preempt_enable(); + + /* Failure is already handled */ + return err; +-- +2.36.1 + diff --git a/debian/patches-rt/0176-fs-epoll-Do-not-disable-preemption-on-RT.patch b/debian/patches-rt/0176-fs-epoll-Do-not-disable-preemption-on-RT.patch new file mode 100644 index 000000000..bf911af26 --- /dev/null +++ b/debian/patches-rt/0176-fs-epoll-Do-not-disable-preemption-on-RT.patch @@ -0,0 +1,37 @@ +From 6507a3f1c5cfe4486efb5aada6114437dd6d099f Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 8 Jul 2011 16:35:35 +0200 +Subject: [PATCH 176/347] fs/epoll: Do not disable preemption on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +ep_call_nested() takes a sleeping lock so we can't disable preemption. +The light version is enough since ep_call_nested() doesn't mind beeing +invoked twice on the same CPU. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + fs/eventpoll.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/fs/eventpoll.c b/fs/eventpoll.c +index a4a32b79e832..8569db5eceb0 100644 +--- a/fs/eventpoll.c ++++ b/fs/eventpoll.c +@@ -569,12 +569,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests) + + static void ep_poll_safewake(wait_queue_head_t *wq) + { +- int this_cpu = get_cpu(); ++ int this_cpu = get_cpu_light(); + + ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, + ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); + +- put_cpu(); ++ put_cpu_light(); + } + + #else +-- +2.36.1 + diff --git a/debian/patches-rt/0177-mm-vmalloc-Another-preempt-disable-region-which-suck.patch b/debian/patches-rt/0177-mm-vmalloc-Another-preempt-disable-region-which-suck.patch new file mode 100644 index 000000000..54171e08f --- /dev/null +++ b/debian/patches-rt/0177-mm-vmalloc-Another-preempt-disable-region-which-suck.patch @@ -0,0 +1,73 @@ +From 1bb6422feb2c5d6c151b91f71dac97b33685af69 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 12 Jul 2011 11:39:36 +0200 +Subject: [PATCH 177/347] mm/vmalloc: Another preempt disable region which + sucks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Avoid the preempt disable version of get_cpu_var(). The inner-lock should +provide enough serialisation. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + mm/vmalloc.c | 13 ++++++++----- + 1 file changed, 8 insertions(+), 5 deletions(-) + +diff --git a/mm/vmalloc.c b/mm/vmalloc.c +index 1817871b0239..aa06badc76f4 100644 +--- a/mm/vmalloc.c ++++ b/mm/vmalloc.c +@@ -853,7 +853,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; +- int node, err; ++ int node, err, cpu; + void *vaddr; + + node = numa_node_id(); +@@ -896,11 +896,12 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) + BUG_ON(err); + radix_tree_preload_end(); + +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + spin_lock(&vbq->lock); + list_add_tail_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + + return vaddr; + } +@@ -969,6 +970,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) + struct vmap_block *vb; + void *vaddr = NULL; + unsigned int order; ++ int cpu; + + BUG_ON(offset_in_page(size)); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); +@@ -983,7 +985,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) + order = get_order(size); + + rcu_read_lock(); +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long pages_off; + +@@ -1006,7 +1009,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) + break; + } + +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + rcu_read_unlock(); + + /* Allocate new block if nothing was found */ +-- +2.36.1 + diff --git a/debian/patches-rt/0178-block-mq-use-cpu_light.patch b/debian/patches-rt/0178-block-mq-use-cpu_light.patch new file mode 100644 index 000000000..127e4aeb1 --- /dev/null +++ b/debian/patches-rt/0178-block-mq-use-cpu_light.patch @@ -0,0 +1,36 @@ +From 0d89852edf5dc2169659eb46bba1b5dc4f92444b Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 9 Apr 2014 10:37:23 +0200 +Subject: [PATCH 178/347] block: mq: use cpu_light() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +there is a might sleep splat because get_cpu() disables preemption and +later we grab a lock. As a workaround for this we use get_cpu_light(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + block/blk-mq.h | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/block/blk-mq.h b/block/blk-mq.h +index 5ad9251627f8..5a96c97991b6 100644 +--- a/block/blk-mq.h ++++ b/block/blk-mq.h +@@ -113,12 +113,12 @@ static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, + */ + static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) + { +- return __blk_mq_get_ctx(q, get_cpu()); ++ return __blk_mq_get_ctx(q, get_cpu_light()); + } + + static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) + { +- put_cpu(); ++ put_cpu_light(); + } + + struct blk_mq_alloc_data { +-- +2.36.1 + diff --git a/debian/patches-rt/0179-block-mq-do-not-invoke-preempt_disable.patch b/debian/patches-rt/0179-block-mq-do-not-invoke-preempt_disable.patch new file mode 100644 index 000000000..c6d47b2d4 --- /dev/null +++ b/debian/patches-rt/0179-block-mq-do-not-invoke-preempt_disable.patch @@ -0,0 +1,58 @@ +From 438290ebaac377f499a9c17e07ffa735ff6db1c2 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: [PATCH 179/347] block/mq: do not invoke preempt_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +preempt_disable() and get_cpu() don't play well together with the sleeping +locks it tries to allocate later. +It seems to be enough to replace it with get_cpu_light() and migrate_disable(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + block/blk-mq.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +diff --git a/block/blk-mq.c b/block/blk-mq.c +index ffa97d90bde9..ea41d67e4db5 100644 +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -570,7 +570,7 @@ static void __blk_mq_complete_request(struct request *rq) + return; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) + shared = cpus_share_cache(cpu, ctx->cpu); + +@@ -582,7 +582,7 @@ static void __blk_mq_complete_request(struct request *rq) + } else { + rq->q->softirq_done_fn(rq); + } +- put_cpu(); ++ put_cpu_light(); + } + + static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) +@@ -1387,14 +1387,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, + return; + + if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { +- int cpu = get_cpu(); ++ int cpu = get_cpu_light(); + if (cpumask_test_cpu(cpu, hctx->cpumask)) { + __blk_mq_run_hw_queue(hctx); +- put_cpu(); ++ put_cpu_light(); + return; + } + +- put_cpu(); ++ put_cpu_light(); + } + + kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, +-- +2.36.1 + diff --git a/debian/patches-rt/0180-block-mq-don-t-complete-requests-via-IPI.patch b/debian/patches-rt/0180-block-mq-don-t-complete-requests-via-IPI.patch new file mode 100644 index 000000000..b29ad2ead --- /dev/null +++ b/debian/patches-rt/0180-block-mq-don-t-complete-requests-via-IPI.patch @@ -0,0 +1,119 @@ +From 229760413c4138a40587def4f9420bdb432fa502 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 29 Jan 2015 15:10:08 +0100 +Subject: [PATCH 180/347] block/mq: don't complete requests via IPI +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The IPI runs in hardirq context and there are sleeping locks. This patch +moves the completion into a workqueue. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + block/blk-core.c | 3 +++ + block/blk-mq.c | 23 +++++++++++++++++++++++ + include/linux/blk-mq.h | 2 +- + include/linux/blkdev.h | 3 +++ + 4 files changed, 30 insertions(+), 1 deletion(-) + +diff --git a/block/blk-core.c b/block/blk-core.c +index 80f3e729fdd4..461a93c08c14 100644 +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -189,6 +189,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq) + + INIT_LIST_HEAD(&rq->queuelist); + INIT_LIST_HEAD(&rq->timeout_list); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + rq->cpu = -1; + rq->q = q; + rq->__sector = (sector_t) -1; +diff --git a/block/blk-mq.c b/block/blk-mq.c +index ea41d67e4db5..0f8dcb68b8a8 100644 +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -320,6 +320,9 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, + rq->extra_len = 0; + rq->__deadline = 0; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + INIT_LIST_HEAD(&rq->timeout_list); + rq->timeout = 0; + +@@ -547,12 +550,24 @@ void blk_mq_end_request(struct request *rq, blk_status_t error) + } + EXPORT_SYMBOL(blk_mq_end_request); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++void __blk_mq_complete_request_remote_work(struct work_struct *work) ++{ ++ struct request *rq = container_of(work, struct request, work); ++ ++ rq->q->softirq_done_fn(rq); ++} ++ ++#else ++ + static void __blk_mq_complete_request_remote(void *data) + { + struct request *rq = data; + + rq->q->softirq_done_fn(rq); + } ++#endif + + static void __blk_mq_complete_request(struct request *rq) + { +@@ -575,10 +590,18 @@ static void __blk_mq_complete_request(struct request *rq) + shared = cpus_share_cache(cpu, ctx->cpu); + + if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * We could force QUEUE_FLAG_SAME_FORCE then we would not get in ++ * here. But we could try to invoke it one the CPU like this. ++ */ ++ schedule_work_on(ctx->cpu, &rq->work); ++#else + rq->csd.func = __blk_mq_complete_request_remote; + rq->csd.info = rq; + rq->csd.flags = 0; + smp_call_function_single_async(ctx->cpu, &rq->csd); ++#endif + } else { + rq->q->softirq_done_fn(rq); + } +diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h +index 2885dce1ad49..8dbb9ecf9993 100644 +--- a/include/linux/blk-mq.h ++++ b/include/linux/blk-mq.h +@@ -256,7 +256,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) + return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; + } + +- ++void __blk_mq_complete_request_remote_work(struct work_struct *work); + int blk_mq_request_started(struct request *rq); + void blk_mq_start_request(struct request *rq); + void blk_mq_end_request(struct request *rq, blk_status_t error); +diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h +index 56fe682d9beb..39d90bf9b5fa 100644 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -157,6 +157,9 @@ enum mq_rq_state { + */ + struct request { + struct request_queue *q; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct work_struct work; ++#endif + struct blk_mq_ctx *mq_ctx; + + int cpu; +-- +2.36.1 + diff --git a/debian/patches-rt/0181-md-raid5-Make-raid5_percpu-handling-RT-aware.patch b/debian/patches-rt/0181-md-raid5-Make-raid5_percpu-handling-RT-aware.patch new file mode 100644 index 000000000..e1f7c3fce --- /dev/null +++ b/debian/patches-rt/0181-md-raid5-Make-raid5_percpu-handling-RT-aware.patch @@ -0,0 +1,77 @@ +From 17db75361d2ecbea4026acde76a744fdecc4c475 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 6 Apr 2010 16:51:31 +0200 +Subject: [PATCH 181/347] md: raid5: Make raid5_percpu handling RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +__raid_run_ops() disables preemption with get_cpu() around the access +to the raid5_percpu variables. That causes scheduling while atomic +spews on RT. + +Serialize the access to the percpu data with a lock and keep the code +preemptible. + +Reported-by: Udo van den Heuvel <udovdh@xs4all.nl> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Tested-by: Udo van den Heuvel <udovdh@xs4all.nl> +--- + drivers/md/raid5.c | 8 +++++--- + drivers/md/raid5.h | 1 + + 2 files changed, 6 insertions(+), 3 deletions(-) + +diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c +index c7bda4b0bced..8eb234732c9b 100644 +--- a/drivers/md/raid5.c ++++ b/drivers/md/raid5.c +@@ -2069,8 +2069,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) + struct raid5_percpu *percpu; + unsigned long cpu; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + percpu = per_cpu_ptr(conf->percpu, cpu); ++ spin_lock(&percpu->lock); + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; +@@ -2129,7 +2130,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } +- put_cpu(); ++ spin_unlock(&percpu->lock); ++ put_cpu_light(); + } + + static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh) +@@ -6816,6 +6818,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node) + __func__, cpu); + return -ENOMEM; + } ++ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); + return 0; + } + +@@ -6826,7 +6829,6 @@ static int raid5_alloc_percpu(struct r5conf *conf) + conf->percpu = alloc_percpu(struct raid5_percpu); + if (!conf->percpu) + return -ENOMEM; +- + err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node); + if (!err) { + conf->scribble_disks = max(conf->raid_disks, +diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h +index 8474c224127b..a3bf907ab2af 100644 +--- a/drivers/md/raid5.h ++++ b/drivers/md/raid5.h +@@ -637,6 +637,7 @@ struct r5conf { + int recovery_disabled; + /* per cpu variables */ + struct raid5_percpu { ++ spinlock_t lock; /* Protection for -RT */ + struct page *spare_page; /* Used when checking P/Q in raid6 */ + struct flex_array *scribble; /* space for constructing buffer + * lists and performing address +-- +2.36.1 + diff --git a/debian/patches-rt/0182-rt-Introduce-cpu_chill.patch b/debian/patches-rt/0182-rt-Introduce-cpu_chill.patch new file mode 100644 index 000000000..4980e8e7b --- /dev/null +++ b/debian/patches-rt/0182-rt-Introduce-cpu_chill.patch @@ -0,0 +1,113 @@ +From 7c3cf849b26619430967542431dbe55c30629824 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 7 Mar 2012 20:51:03 +0100 +Subject: [PATCH 182/347] rt: Introduce cpu_chill() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Add cpu_chill() to replace cpu_relax(). cpu_chill() +defaults to cpu_relax() for non RT. On RT it puts the looping task to +sleep for a tick so the preempted task can make progress. + +Steven Rostedt changed it to use a hrtimer instead of msleep(): +| +|Ulrich Obergfell pointed out that cpu_chill() calls msleep() which is woken +|up by the ksoftirqd running the TIMER softirq. But as the cpu_chill() is +|called from softirq context, it may block the ksoftirqd() from running, in +|which case, it may never wake up the msleep() causing the deadlock. + ++ bigeasy later changed to schedule_hrtimeout() +|If a task calls cpu_chill() and gets woken up by a regular or spurious +|wakeup and has a signal pending, then it exits the sleep loop in +|do_nanosleep() and sets up the restart block. If restart->nanosleep.type is +|not TI_NONE then this results in accessing a stale user pointer from a +|previously interrupted syscall and a copy to user based on the stale +|pointer or a BUG() when 'type' is not supported in nanosleep_copyout(). + ++ bigeasy: add PF_NOFREEZE: +| [....] Waiting for /dev to be fully populated... +| ===================================== +| [ BUG: udevd/229 still has locks held! ] +| 3.12.11-rt17 #23 Not tainted +| ------------------------------------- +| 1 lock held by udevd/229: +| #0: (&type->i_mutex_dir_key#2){+.+.+.}, at: lookup_slow+0x28/0x98 +| +| stack backtrace: +| CPU: 0 PID: 229 Comm: udevd Not tainted 3.12.11-rt17 #23 +| (unwind_backtrace+0x0/0xf8) from (show_stack+0x10/0x14) +| (show_stack+0x10/0x14) from (dump_stack+0x74/0xbc) +| (dump_stack+0x74/0xbc) from (do_nanosleep+0x120/0x160) +| (do_nanosleep+0x120/0x160) from (hrtimer_nanosleep+0x90/0x110) +| (hrtimer_nanosleep+0x90/0x110) from (cpu_chill+0x30/0x38) +| (cpu_chill+0x30/0x38) from (dentry_kill+0x158/0x1ec) +| (dentry_kill+0x158/0x1ec) from (dput+0x74/0x15c) +| (dput+0x74/0x15c) from (lookup_real+0x4c/0x50) +| (lookup_real+0x4c/0x50) from (__lookup_hash+0x34/0x44) +| (__lookup_hash+0x34/0x44) from (lookup_slow+0x38/0x98) +| (lookup_slow+0x38/0x98) from (path_lookupat+0x208/0x7fc) +| (path_lookupat+0x208/0x7fc) from (filename_lookup+0x20/0x60) +| (filename_lookup+0x20/0x60) from (user_path_at_empty+0x50/0x7c) +| (user_path_at_empty+0x50/0x7c) from (user_path_at+0x14/0x1c) +| (user_path_at+0x14/0x1c) from (vfs_fstatat+0x48/0x94) +| (vfs_fstatat+0x48/0x94) from (SyS_stat64+0x14/0x30) +| (SyS_stat64+0x14/0x30) from (ret_fast_syscall+0x0/0x48) + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/delay.h | 6 ++++++ + kernel/time/hrtimer.c | 21 +++++++++++++++++++++ + 2 files changed, 27 insertions(+) + +diff --git a/include/linux/delay.h b/include/linux/delay.h +index b78bab4395d8..7c4bc414a504 100644 +--- a/include/linux/delay.h ++++ b/include/linux/delay.h +@@ -64,4 +64,10 @@ static inline void ssleep(unsigned int seconds) + msleep(seconds * 1000); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void cpu_chill(void); ++#else ++# define cpu_chill() cpu_relax() ++#endif ++ + #endif /* defined(_LINUX_DELAY_H) */ +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 009001f06d33..0b94f54453ef 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1961,6 +1961,27 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, + } + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Sleep for 1 ms in hope whoever holds what we want will let it go. ++ */ ++void cpu_chill(void) ++{ ++ ktime_t chill_time; ++ unsigned int freeze_flag = current->flags & PF_NOFREEZE; ++ ++ chill_time = ktime_set(0, NSEC_PER_MSEC); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ current->flags |= PF_NOFREEZE; ++ sleeping_lock_inc(); ++ schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD); ++ sleeping_lock_dec(); ++ if (!freeze_flag) ++ current->flags &= ~PF_NOFREEZE; ++} ++EXPORT_SYMBOL(cpu_chill); ++#endif ++ + /* + * Functions related to boot-time initialization: + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0183-hrtimer-Don-t-lose-state-in-cpu_chill.patch b/debian/patches-rt/0183-hrtimer-Don-t-lose-state-in-cpu_chill.patch new file mode 100644 index 000000000..bb9264a1f --- /dev/null +++ b/debian/patches-rt/0183-hrtimer-Don-t-lose-state-in-cpu_chill.patch @@ -0,0 +1,48 @@ +From f5a443f1a8355f1e2aca72d20e931d136b979ac9 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 19 Feb 2019 16:59:15 +0100 +Subject: [PATCH 183/347] hrtimer: Don't lose state in cpu_chill() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In cpu_chill() the state is set to TASK_UNINTERRUPTIBLE and a timer is +programmed. On return the state is always TASK_RUNNING which means we +lose the state if it was something other than RUNNING. Also +set_current_state() sets ->task_state_change to within cpu_chill() which +is not expected. + +Save the task state on entry and restore it on return. Simply set the +state in order to avoid updating ->task_state_change. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 0b94f54453ef..96e505abf939 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1969,15 +1969,18 @@ void cpu_chill(void) + { + ktime_t chill_time; + unsigned int freeze_flag = current->flags & PF_NOFREEZE; ++ long saved_state; + ++ saved_state = current->state; + chill_time = ktime_set(0, NSEC_PER_MSEC); +- set_current_state(TASK_UNINTERRUPTIBLE); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + current->flags |= PF_NOFREEZE; + sleeping_lock_inc(); + schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD); + sleeping_lock_dec(); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; ++ __set_current_state_no_track(saved_state); + } + EXPORT_SYMBOL(cpu_chill); + #endif +-- +2.36.1 + diff --git a/debian/patches-rt/0184-hrtimer-cpu_chill-save-task-state-in-saved_state.patch b/debian/patches-rt/0184-hrtimer-cpu_chill-save-task-state-in-saved_state.patch new file mode 100644 index 000000000..6917a5783 --- /dev/null +++ b/debian/patches-rt/0184-hrtimer-cpu_chill-save-task-state-in-saved_state.patch @@ -0,0 +1,63 @@ +From 351c688963d6bfafec5cf05168e195effc77811c Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 26 Feb 2019 12:31:10 +0100 +Subject: [PATCH 184/347] hrtimer: cpu_chill(): save task state in + ->saved_state() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In the previous change I saved the current task state on stack. This was +bad because while the task is scheduled-out it might receive a wake-up. +The wake up changes the task state and we must not destroy it. + +Save the task-state in ->saved_state under a PI-lock to unsure that +state changes during are not missed while the task temporary scheduled +out. + +Reported-by: Mike Galbraith <efault@gmx.de> +Tested-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 18 +++++++++++++----- + 1 file changed, 13 insertions(+), 5 deletions(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 96e505abf939..aa8f3177580a 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1967,20 +1967,28 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, + */ + void cpu_chill(void) + { +- ktime_t chill_time; + unsigned int freeze_flag = current->flags & PF_NOFREEZE; +- long saved_state; ++ struct task_struct *self = current; ++ ktime_t chill_time; + +- saved_state = current->state; +- chill_time = ktime_set(0, NSEC_PER_MSEC); ++ raw_spin_lock_irq(&self->pi_lock); ++ self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock_irq(&self->pi_lock); ++ ++ chill_time = ktime_set(0, NSEC_PER_MSEC); ++ + current->flags |= PF_NOFREEZE; + sleeping_lock_inc(); + schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD); + sleeping_lock_dec(); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; +- __set_current_state_no_track(saved_state); ++ ++ raw_spin_lock_irq(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ raw_spin_unlock_irq(&self->pi_lock); + } + EXPORT_SYMBOL(cpu_chill); + #endif +-- +2.36.1 + diff --git a/debian/patches-rt/0185-block-blk-mq-move-blk_queue_usage_counter_release-in.patch b/debian/patches-rt/0185-block-blk-mq-move-blk_queue_usage_counter_release-in.patch new file mode 100644 index 000000000..802e53619 --- /dev/null +++ b/debian/patches-rt/0185-block-blk-mq-move-blk_queue_usage_counter_release-in.patch @@ -0,0 +1,120 @@ +From 3c180d9b5b9620bc5c18e0a7fb9f02059b333db3 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 13 Mar 2018 13:49:16 +0100 +Subject: [PATCH 185/347] block: blk-mq: move blk_queue_usage_counter_release() + into process context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +| BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +| in_atomic(): 1, irqs_disabled(): 0, pid: 255, name: kworker/u257:6 +| 5 locks held by kworker/u257:6/255: +| #0: ("events_unbound"){.+.+.+}, at: [<ffffffff8108edf1>] process_one_work+0x171/0x5e0 +| #1: ((&entry->work)){+.+.+.}, at: [<ffffffff8108edf1>] process_one_work+0x171/0x5e0 +| #2: (&shost->scan_mutex){+.+.+.}, at: [<ffffffffa000faa3>] __scsi_add_device+0xa3/0x130 [scsi_mod] +| #3: (&set->tag_list_lock){+.+...}, at: [<ffffffff812f09fa>] blk_mq_init_queue+0x96a/0xa50 +| #4: (rcu_read_lock_sched){......}, at: [<ffffffff8132887d>] percpu_ref_kill_and_confirm+0x1d/0x120 +| Preemption disabled at:[<ffffffff812eff76>] blk_mq_freeze_queue_start+0x56/0x70 +| +| CPU: 2 PID: 255 Comm: kworker/u257:6 Not tainted 3.18.7-rt0+ #1 +| Workqueue: events_unbound async_run_entry_fn +| 0000000000000003 ffff8800bc29f998 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff8800bc29f9b8 ffffffff8109aa16 ffff8800bc29fa28 +| ffff8800bc5d1bc8 ffff8800bc29f9e8 ffffffff815b8dd4 ffff880000000000 +| Call Trace: +| [<ffffffff815b3a12>] dump_stack+0x4f/0x7c +| [<ffffffff8109aa16>] __might_sleep+0x116/0x190 +| [<ffffffff815b8dd4>] rt_spin_lock+0x24/0x60 +| [<ffffffff810b6089>] __wake_up+0x29/0x60 +| [<ffffffff812ee06e>] blk_mq_usage_counter_release+0x1e/0x20 +| [<ffffffff81328966>] percpu_ref_kill_and_confirm+0x106/0x120 +| [<ffffffff812eff76>] blk_mq_freeze_queue_start+0x56/0x70 +| [<ffffffff812f0000>] blk_mq_update_tag_set_depth+0x40/0xd0 +| [<ffffffff812f0a1c>] blk_mq_init_queue+0x98c/0xa50 +| [<ffffffffa000dcf0>] scsi_mq_alloc_queue+0x20/0x60 [scsi_mod] +| [<ffffffffa000ea35>] scsi_alloc_sdev+0x2f5/0x370 [scsi_mod] +| [<ffffffffa000f494>] scsi_probe_and_add_lun+0x9e4/0xdd0 [scsi_mod] +| [<ffffffffa000fb26>] __scsi_add_device+0x126/0x130 [scsi_mod] +| [<ffffffffa013033f>] ata_scsi_scan_host+0xaf/0x200 [libata] +| [<ffffffffa012b5b6>] async_port_probe+0x46/0x60 [libata] +| [<ffffffff810978fb>] async_run_entry_fn+0x3b/0xf0 +| [<ffffffff8108ee81>] process_one_work+0x201/0x5e0 + +percpu_ref_kill_and_confirm() invokes blk_mq_usage_counter_release() in +a rcu-sched region. swait based wake queue can't be used due to +wake_up_all() usage and disabled interrupts in !RT configs (as reported +by Corey Minyard). +The wq_has_sleeper() check has been suggested by Peter Zijlstra. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + block/blk-core.c | 14 +++++++++++++- + include/linux/blkdev.h | 2 ++ + 2 files changed, 15 insertions(+), 1 deletion(-) + +diff --git a/block/blk-core.c b/block/blk-core.c +index 461a93c08c14..02835970ef1e 100644 +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -973,12 +973,21 @@ void blk_queue_exit(struct request_queue *q) + percpu_ref_put(&q->q_usage_counter); + } + ++static void blk_queue_usage_counter_release_swork(struct swork_event *sev) ++{ ++ struct request_queue *q = ++ container_of(sev, struct request_queue, mq_pcpu_wake); ++ ++ wake_up_all(&q->mq_freeze_wq); ++} ++ + static void blk_queue_usage_counter_release(struct percpu_ref *ref) + { + struct request_queue *q = + container_of(ref, struct request_queue, q_usage_counter); + +- wake_up_all(&q->mq_freeze_wq); ++ if (wq_has_sleeper(&q->mq_freeze_wq)) ++ swork_queue(&q->mq_pcpu_wake); + } + + static void blk_rq_timed_out_timer(struct timer_list *t) +@@ -1078,6 +1087,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, + queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); + + init_waitqueue_head(&q->mq_freeze_wq); ++ INIT_SWORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_swork); + + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. +@@ -3967,6 +3977,8 @@ int __init blk_dev_init(void) + if (!kblockd_workqueue) + panic("Failed to create kblockd\n"); + ++ BUG_ON(swork_get()); ++ + request_cachep = kmem_cache_create("blkdev_requests", + sizeof(struct request), 0, SLAB_PANIC, NULL); + +diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h +index 39d90bf9b5fa..0313098a428d 100644 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -27,6 +27,7 @@ + #include <linux/percpu-refcount.h> + #include <linux/scatterlist.h> + #include <linux/blkzoned.h> ++#include <linux/swork.h> + + struct module; + struct scsi_ioctl_command; +@@ -664,6 +665,7 @@ struct request_queue { + #endif + struct rcu_head rcu_head; + wait_queue_head_t mq_freeze_wq; ++ struct swork_event mq_pcpu_wake; + struct percpu_ref q_usage_counter; + struct list_head all_q_node; + +-- +2.36.1 + diff --git a/debian/patches-rt/0186-block-Use-cpu_chill-for-retry-loops.patch b/debian/patches-rt/0186-block-Use-cpu_chill-for-retry-loops.patch new file mode 100644 index 000000000..1e0c86edd --- /dev/null +++ b/debian/patches-rt/0186-block-Use-cpu_chill-for-retry-loops.patch @@ -0,0 +1,51 @@ +From f13997a9d1ad83528116e8daabc9b2247530ec63 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 20 Dec 2012 18:28:26 +0100 +Subject: [PATCH 186/347] block: Use cpu_chill() for retry loops +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Steven also observed a live lock when there was a +concurrent priority boosting going on. + +Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + block/blk-ioc.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/block/blk-ioc.c b/block/blk-ioc.c +index 4c810969c3e2..48089f5bcc11 100644 +--- a/block/blk-ioc.c ++++ b/block/blk-ioc.c +@@ -9,6 +9,7 @@ + #include <linux/blkdev.h> + #include <linux/slab.h> + #include <linux/sched/task.h> ++#include <linux/delay.h> + + #include "blk.h" + +@@ -119,7 +120,7 @@ static void ioc_release_fn(struct work_struct *work) + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + } + } +@@ -203,7 +204,7 @@ void put_io_context_active(struct io_context *ioc) + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + goto retry; + } + } +-- +2.36.1 + diff --git a/debian/patches-rt/0187-fs-dcache-Use-cpu_chill-in-trylock-loops.patch b/debian/patches-rt/0187-fs-dcache-Use-cpu_chill-in-trylock-loops.patch new file mode 100644 index 000000000..2df32b031 --- /dev/null +++ b/debian/patches-rt/0187-fs-dcache-Use-cpu_chill-in-trylock-loops.patch @@ -0,0 +1,66 @@ +From d12da2a9ddfd2e6803327ef9856a63caedb4c653 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 7 Mar 2012 21:00:34 +0100 +Subject: [PATCH 187/347] fs: dcache: Use cpu_chill() in trylock loops +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + fs/autofs/expire.c | 3 ++- + fs/namespace.c | 8 ++++++-- + 2 files changed, 8 insertions(+), 3 deletions(-) + +diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c +index 70e9afe589fb..1a6b88ad4fe0 100644 +--- a/fs/autofs/expire.c ++++ b/fs/autofs/expire.c +@@ -8,6 +8,7 @@ + * option, any later version, incorporated herein by reference. + */ + ++#include <linux/delay.h> + #include "autofs_i.h" + + /* Check if a dentry can be expired */ +@@ -153,7 +154,7 @@ static struct dentry *get_next_positive_dentry(struct dentry *prev, + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto relock; + } + spin_unlock(&p->d_lock); +diff --git a/fs/namespace.c b/fs/namespace.c +index 396ff1bcfdad..2c0ff275e978 100644 +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -14,6 +14,7 @@ + #include <linux/mnt_namespace.h> + #include <linux/user_namespace.h> + #include <linux/namei.h> ++#include <linux/delay.h> + #include <linux/security.h> + #include <linux/cred.h> + #include <linux/idr.h> +@@ -327,8 +328,11 @@ int __mnt_want_write(struct vfsmount *m) + * incremented count after it has set MNT_WRITE_HOLD. + */ + smp_mb(); +- while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) +- cpu_relax(); ++ while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { ++ preempt_enable(); ++ cpu_chill(); ++ preempt_disable(); ++ } + /* + * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will + * be set to match its requirements. So we must not load that until +-- +2.36.1 + diff --git a/debian/patches-rt/0188-net-Use-cpu_chill-instead-of-cpu_relax.patch b/debian/patches-rt/0188-net-Use-cpu_chill-instead-of-cpu_relax.patch new file mode 100644 index 000000000..eace39fdc --- /dev/null +++ b/debian/patches-rt/0188-net-Use-cpu_chill-instead-of-cpu_relax.patch @@ -0,0 +1,70 @@ +From 6113e8d5c66aab6927b9d8656e1c5b1e8d7e35fb Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 7 Mar 2012 21:10:04 +0100 +Subject: [PATCH 188/347] net: Use cpu_chill() instead of cpu_relax() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + net/packet/af_packet.c | 5 +++-- + net/rds/ib_rdma.c | 3 ++- + 2 files changed, 5 insertions(+), 3 deletions(-) + +diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c +index f654f79e3310..31ce7d1fbee1 100644 +--- a/net/packet/af_packet.c ++++ b/net/packet/af_packet.c +@@ -63,6 +63,7 @@ + #include <linux/if_packet.h> + #include <linux/wireless.h> + #include <linux/kernel.h> ++#include <linux/delay.h> + #include <linux/kmod.h> + #include <linux/slab.h> + #include <linux/vmalloc.h> +@@ -668,7 +669,7 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + +@@ -930,7 +931,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, + if (!(status & TP_STATUS_BLK_TMO)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + prb_close_block(pkc, pbd, po, status); +diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c +index 0b347f46b2f4..f395f06031bc 100644 +--- a/net/rds/ib_rdma.c ++++ b/net/rds/ib_rdma.c +@@ -34,6 +34,7 @@ + #include <linux/slab.h> + #include <linux/rculist.h> + #include <linux/llist.h> ++#include <linux/delay.h> + + #include "rds_single_path.h" + #include "ib_mr.h" +@@ -222,7 +223,7 @@ static inline void wait_clean_list_grace(void) + for_each_online_cpu(cpu) { + flag = &per_cpu(clean_list_grace, cpu); + while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) +- cpu_relax(); ++ cpu_chill(); + } + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0189-fs-dcache-use-swait_queue-instead-of-waitqueue.patch b/debian/patches-rt/0189-fs-dcache-use-swait_queue-instead-of-waitqueue.patch new file mode 100644 index 000000000..70a3b56d9 --- /dev/null +++ b/debian/patches-rt/0189-fs-dcache-use-swait_queue-instead-of-waitqueue.patch @@ -0,0 +1,241 @@ +From c6039e4946aa32ae6b790148a5a7357380e4a998 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 14 Sep 2016 14:35:49 +0200 +Subject: [PATCH 189/347] fs/dcache: use swait_queue instead of waitqueue +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +__d_lookup_done() invokes wake_up_all() while holding a hlist_bl_lock() +which disables preemption. As a workaround convert it to swait. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + fs/cifs/readdir.c | 2 +- + fs/dcache.c | 27 +++++++++++++++------------ + fs/fuse/dir.c | 2 +- + fs/namei.c | 4 ++-- + fs/nfs/dir.c | 4 ++-- + fs/nfs/unlink.c | 4 ++-- + fs/proc/base.c | 2 +- + fs/proc/proc_sysctl.c | 2 +- + include/linux/dcache.h | 4 ++-- + include/linux/nfs_xdr.h | 2 +- + kernel/sched/swait.c | 1 + + 11 files changed, 29 insertions(+), 25 deletions(-) + +diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c +index 3925a7bfc74d..33f7723fb83e 100644 +--- a/fs/cifs/readdir.c ++++ b/fs/cifs/readdir.c +@@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, + struct inode *inode; + struct super_block *sb = parent->d_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); + +diff --git a/fs/dcache.c b/fs/dcache.c +index 1ae163d54925..6e1c0b4c04f4 100644 +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -2423,21 +2423,24 @@ static inline void end_dir_add(struct inode *dir, unsigned n) + + static void d_wait_lookup(struct dentry *dentry) + { +- if (d_in_lookup(dentry)) { +- DECLARE_WAITQUEUE(wait, current); +- add_wait_queue(dentry->d_wait, &wait); +- do { +- set_current_state(TASK_UNINTERRUPTIBLE); +- spin_unlock(&dentry->d_lock); +- schedule(); +- spin_lock(&dentry->d_lock); +- } while (d_in_lookup(dentry)); +- } ++ struct swait_queue __wait; ++ ++ if (!d_in_lookup(dentry)) ++ return; ++ ++ INIT_LIST_HEAD(&__wait.task_list); ++ do { ++ prepare_to_swait_exclusive(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE); ++ spin_unlock(&dentry->d_lock); ++ schedule(); ++ spin_lock(&dentry->d_lock); ++ } while (d_in_lookup(dentry)); ++ finish_swait(dentry->d_wait, &__wait); + } + + struct dentry *d_alloc_parallel(struct dentry *parent, + const struct qstr *name, +- wait_queue_head_t *wq) ++ struct swait_queue_head *wq) + { + unsigned int hash = name->hash; + struct hlist_bl_head *b = in_lookup_hash(parent, hash); +@@ -2552,7 +2555,7 @@ void __d_lookup_done(struct dentry *dentry) + hlist_bl_lock(b); + dentry->d_flags &= ~DCACHE_PAR_LOOKUP; + __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); +- wake_up_all(dentry->d_wait); ++ swake_up_all(dentry->d_wait); + dentry->d_wait = NULL; + hlist_bl_unlock(b); + INIT_HLIST_NODE(&dentry->d_u.d_alias); +diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c +index 6098e0c7f87b..9ce28840684a 100644 +--- a/fs/fuse/dir.c ++++ b/fs/fuse/dir.c +@@ -1234,7 +1234,7 @@ static int fuse_direntplus_link(struct file *file, + struct inode *dir = d_inode(parent); + struct fuse_conn *fc; + struct inode *inode; +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + if (!o->nodeid) { + /* +diff --git a/fs/namei.c b/fs/namei.c +index 327844fedf3d..5114c8111807 100644 +--- a/fs/namei.c ++++ b/fs/namei.c +@@ -1646,7 +1646,7 @@ static struct dentry *__lookup_slow(const struct qstr *name, + { + struct dentry *dentry, *old; + struct inode *inode = dir->d_inode; +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + /* Don't go there if it's already dead */ + if (unlikely(IS_DEADDIR(inode))) +@@ -3136,7 +3136,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, + struct dentry *dentry; + int error, create_error = 0; + umode_t mode = op->mode; +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + if (unlikely(IS_DEADDIR(dir_inode))) + return -ENOENT; +diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c +index 4999bd148491..d8376dae3f7d 100644 +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -457,7 +457,7 @@ static + void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) + { + struct qstr filename = QSTR_INIT(entry->name, entry->len); +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + struct dentry *dentry; + struct dentry *alias; + struct inode *dir = d_inode(parent); +@@ -1519,7 +1519,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned open_flags, + umode_t mode) + { +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + struct nfs_open_context *ctx; + struct dentry *res; + struct iattr attr = { .ia_valid = ATTR_OPEN }; +diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c +index ce9100b5604d..839bfa76f41e 100644 +--- a/fs/nfs/unlink.c ++++ b/fs/nfs/unlink.c +@@ -13,7 +13,7 @@ + #include <linux/sunrpc/clnt.h> + #include <linux/nfs_fs.h> + #include <linux/sched.h> +-#include <linux/wait.h> ++#include <linux/swait.h> + #include <linux/namei.h> + #include <linux/fsnotify.h> + +@@ -206,7 +206,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name) + goto out_free_name; + } + data->res.dir_attr = &data->dir_attr; +- init_waitqueue_head(&data->wq); ++ init_swait_queue_head(&data->wq); + + status = -EBUSY; + spin_lock(&dentry->d_lock); +diff --git a/fs/proc/base.c b/fs/proc/base.c +index e3f10c110b74..accc230079bb 100644 +--- a/fs/proc/base.c ++++ b/fs/proc/base.c +@@ -1889,7 +1889,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, + + child = d_hash_and_lookup(dir, &qname); + if (!child) { +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) + goto end_instantiate; +diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c +index c95f32b83a94..75f500cb7e74 100644 +--- a/fs/proc/proc_sysctl.c ++++ b/fs/proc/proc_sysctl.c +@@ -681,7 +681,7 @@ static bool proc_sys_fill_cache(struct file *file, + + child = d_lookup(dir, &qname); + if (!child) { +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) + return false; +diff --git a/include/linux/dcache.h b/include/linux/dcache.h +index 02b1b40fea5b..50cbde278301 100644 +--- a/include/linux/dcache.h ++++ b/include/linux/dcache.h +@@ -105,7 +105,7 @@ struct dentry { + + union { + struct list_head d_lru; /* LRU list */ +- wait_queue_head_t *d_wait; /* in-lookup ones only */ ++ struct swait_queue_head *d_wait; /* in-lookup ones only */ + }; + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ +@@ -236,7 +236,7 @@ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); + extern struct dentry * d_alloc_anon(struct super_block *); + extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); + extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, +- wait_queue_head_t *); ++ struct swait_queue_head *); + extern struct dentry * d_splice_alias(struct inode *, struct dentry *); + extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); + extern struct dentry * d_exact_alias(struct dentry *, struct inode *); +diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h +index cab24a127feb..73b0d19ef0d9 100644 +--- a/include/linux/nfs_xdr.h ++++ b/include/linux/nfs_xdr.h +@@ -1549,7 +1549,7 @@ struct nfs_unlinkdata { + struct nfs_removeargs args; + struct nfs_removeres res; + struct dentry *dentry; +- wait_queue_head_t wq; ++ struct swait_queue_head wq; + struct rpc_cred *cred; + struct nfs_fattr dir_attr; + long timeout; +diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c +index c7cb30cdd1b7..119a56d7f739 100644 +--- a/kernel/sched/swait.c ++++ b/kernel/sched/swait.c +@@ -70,6 +70,7 @@ void swake_up_all(struct swait_queue_head *q) + struct swait_queue *curr; + LIST_HEAD(tmp); + ++ WARN_ON(irqs_disabled()); + raw_spin_lock_irq(&q->lock); + list_splice_init(&q->task_list, &tmp); + while (!list_empty(&tmp)) { +-- +2.36.1 + diff --git a/debian/patches-rt/0190-workqueue-Use-normal-rcu.patch b/debian/patches-rt/0190-workqueue-Use-normal-rcu.patch new file mode 100644 index 000000000..ca3010992 --- /dev/null +++ b/debian/patches-rt/0190-workqueue-Use-normal-rcu.patch @@ -0,0 +1,360 @@ +From 8a58c9e05c039f23a1192df034ad9f56961ba52d Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 24 Jul 2013 15:26:54 +0200 +Subject: [PATCH 190/347] workqueue: Use normal rcu +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There is no need for sched_rcu. The undocumented reason why sched_rcu +is used is to avoid a few explicit rcu_read_lock()/unlock() pairs by +abusing the fact that sched_rcu reader side critical sections are also +protected by preempt or irq disabled regions. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/workqueue.c | 95 +++++++++++++++++++++++++--------------------- + 1 file changed, 52 insertions(+), 43 deletions(-) + +diff --git a/kernel/workqueue.c b/kernel/workqueue.c +index b1bb6cb5802e..3e2f67b77ab8 100644 +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -128,7 +128,7 @@ enum { + * + * PL: wq_pool_mutex protected. + * +- * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. ++ * PR: wq_pool_mutex protected for writes. RCU protected for reads. + * + * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. + * +@@ -137,7 +137,7 @@ enum { + * + * WQ: wq->mutex protected. + * +- * WR: wq->mutex protected for writes. Sched-RCU protected for reads. ++ * WR: wq->mutex protected for writes. RCU protected for reads. + * + * MD: wq_mayday_lock protected. + */ +@@ -184,7 +184,7 @@ struct worker_pool { + atomic_t nr_running ____cacheline_aligned_in_smp; + + /* +- * Destruction of pool is sched-RCU protected to allow dereferences ++ * Destruction of pool is RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; +@@ -213,7 +213,7 @@ struct pool_workqueue { + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue +- * itself is also sched-RCU protected so that the first pwq can be ++ * itself is also RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; +@@ -358,20 +358,20 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + #include <trace/events/workqueue.h> + + #define assert_rcu_or_pool_mutex() \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU or wq_pool_mutex should be held") ++ "RCU or wq_pool_mutex should be held") + + #define assert_rcu_or_wq_mutex(wq) \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq->mutex), \ +- "sched RCU or wq->mutex should be held") ++ "RCU or wq->mutex should be held") + + #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq->mutex) && \ + !lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU, wq->mutex or wq_pool_mutex should be held") ++ "RCU, wq->mutex or wq_pool_mutex should be held") + + #define for_each_cpu_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ +@@ -383,7 +383,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + * @pool: iteration cursor + * @pi: integer used for iteration + * +- * This must be called either with wq_pool_mutex held or sched RCU read ++ * This must be called either with wq_pool_mutex held or RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. + * +@@ -415,7 +415,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + * @pwq: iteration cursor + * @wq: the target workqueue + * +- * This must be called either with wq->mutex held or sched RCU read locked. ++ * This must be called either with wq->mutex held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -551,7 +551,7 @@ static int worker_pool_assign_id(struct worker_pool *pool) + * @wq: the target workqueue + * @node: the node ID + * +- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU ++ * This must be called with any of wq_pool_mutex, wq->mutex or RCU + * read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. +@@ -695,8 +695,8 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work) + * @work: the work item of interest + * + * Pools are created and destroyed under wq_pool_mutex, and allows read +- * access under sched-RCU read lock. As such, this function should be +- * called under wq_pool_mutex or with preemption disabled. ++ * access under RCU read lock. As such, this function should be ++ * called under wq_pool_mutex or inside of a rcu_read_lock() region. + * + * All fields of the returned pool are accessible as long as the above + * mentioned locking is in effect. If the returned pool needs to be used +@@ -1101,7 +1101,7 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) + { + if (pwq) { + /* +- * As both pwqs and pools are sched-RCU protected, the ++ * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ + spin_lock_irq(&pwq->pool->lock); +@@ -1229,6 +1229,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + ++ rcu_read_lock(); + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. +@@ -1267,10 +1268,12 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + set_work_pool_and_keep_pending(work, pool->id); + + spin_unlock(&pool->lock); ++ rcu_read_unlock(); + return 1; + } + spin_unlock(&pool->lock); + fail: ++ rcu_read_unlock(); + local_irq_restore(*flags); + if (work_is_canceling(work)) + return -ENOENT; +@@ -1383,6 +1386,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + if (unlikely(wq->flags & __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq))) + return; ++ rcu_read_lock(); + retry: + /* pwq which will be used unless @work is executing elsewhere */ + if (wq->flags & WQ_UNBOUND) { +@@ -1441,10 +1445,8 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); + +- if (WARN_ON(!list_empty(&work->entry))) { +- spin_unlock(&pwq->pool->lock); +- return; +- } ++ if (WARN_ON(!list_empty(&work->entry))) ++ goto out; + + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); +@@ -1463,7 +1465,9 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + debug_work_activate(work); + insert_work(pwq, work, worklist, work_flags); + ++out: + spin_unlock(&pwq->pool->lock); ++ rcu_read_unlock(); + } + + /** +@@ -2861,14 +2865,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, + + might_sleep(); + +- local_irq_disable(); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (!pool) { +- local_irq_enable(); ++ rcu_read_unlock(); + return false; + } + +- spin_lock(&pool->lock); ++ spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { +@@ -2900,10 +2904,11 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, + lock_map_acquire(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); + } +- ++ rcu_read_unlock(); + return true; + already_gone: + spin_unlock_irq(&pool->lock); ++ rcu_read_unlock(); + return false; + } + +@@ -3350,7 +3355,7 @@ static void rcu_free_pool(struct rcu_head *rcu) + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * +- * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU ++ * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). +@@ -3404,8 +3409,8 @@ static void put_unbound_pool(struct worker_pool *pool) + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + +- /* sched-RCU protected to allow dereferences from get_work_pool() */ +- call_rcu_sched(&pool->rcu, rcu_free_pool); ++ /* RCU protected to allow dereferences from get_work_pool() */ ++ call_rcu(&pool->rcu, rcu_free_pool); + } + + /** +@@ -3518,14 +3523,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work) + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + +- call_rcu_sched(&pwq->rcu, rcu_free_pwq); ++ call_rcu(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Schedule RCU free. + */ + if (is_last) +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } + + /** +@@ -4232,7 +4237,7 @@ void destroy_workqueue(struct workqueue_struct *wq) + * The base ref is never dropped on per-cpu pwqs. Directly + * schedule RCU free. + */ +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly +@@ -4342,7 +4347,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) + struct pool_workqueue *pwq; + bool ret; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); ++ preempt_disable(); + + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); +@@ -4353,7 +4359,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); +- rcu_read_unlock_sched(); ++ preempt_enable(); ++ rcu_read_unlock(); + + return ret; + } +@@ -4379,15 +4386,15 @@ unsigned int work_busy(struct work_struct *work) + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + +- local_irq_save(flags); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { +- spin_lock(&pool->lock); ++ spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; +- spin_unlock(&pool->lock); ++ spin_unlock_irqrestore(&pool->lock, flags); + } +- local_irq_restore(flags); ++ rcu_read_unlock(); + + return ret; + } +@@ -4572,7 +4579,7 @@ void show_workqueue_state(void) + unsigned long flags; + int pi; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + +@@ -4637,7 +4644,7 @@ void show_workqueue_state(void) + touch_nmi_watchdog(); + } + +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + + /* used to show worker information through /proc/PID/{comm,stat,status} */ +@@ -5024,16 +5031,16 @@ bool freeze_workqueues_busy(void) + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ +- rcu_read_lock_sched(); ++ rcu_read_lock(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { + busy = true; +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + goto out_unlock; + } + } +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + out_unlock: + mutex_unlock(&wq_pool_mutex); +@@ -5235,7 +5242,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, + const char *delim = ""; + int node, written = 0; + +- rcu_read_lock_sched(); ++ get_online_cpus(); ++ rcu_read_lock(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, +@@ -5243,7 +5251,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); ++ put_online_cpus(); + + return written; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0191-workqueue-Use-local-irq-lock-instead-of-irq-disable-.patch b/debian/patches-rt/0191-workqueue-Use-local-irq-lock-instead-of-irq-disable-.patch new file mode 100644 index 000000000..d77219e80 --- /dev/null +++ b/debian/patches-rt/0191-workqueue-Use-local-irq-lock-instead-of-irq-disable-.patch @@ -0,0 +1,186 @@ +From c05bd3f09ed30bc24aa6a2fe5cfc0abd2fe883b3 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 17 Jul 2011 21:42:26 +0200 +Subject: [PATCH 191/347] workqueue: Use local irq lock instead of irq disable + regions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Use a local_irq_lock as a replacement for irq off regions. We keep the +semantic of irq-off in regard to the pool->lock and remain preemptible. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/workqueue.c | 45 ++++++++++++++++++++++++++++++--------------- + 1 file changed, 30 insertions(+), 15 deletions(-) + +diff --git a/kernel/workqueue.c b/kernel/workqueue.c +index 3e2f67b77ab8..2b4c052c51b3 100644 +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -50,6 +50,7 @@ + #include <linux/sched/isolation.h> + #include <linux/nmi.h> + #include <linux/kvm_para.h> ++#include <linux/locallock.h> + + #include "workqueue_internal.h" + +@@ -351,6 +352,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient_wq); + struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; + EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + ++static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); ++ + static int worker_thread(void *__worker); + static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + +@@ -1104,9 +1107,11 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) + * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ +- spin_lock_irq(&pwq->pool->lock); ++ rcu_read_lock(); ++ local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); + put_pwq(pwq); +- spin_unlock_irq(&pwq->pool->lock); ++ local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); ++ rcu_read_unlock(); + } + } + +@@ -1210,7 +1215,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + struct worker_pool *pool; + struct pool_workqueue *pwq; + +- local_irq_save(*flags); ++ local_lock_irqsave(pendingb_lock, *flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { +@@ -1274,7 +1279,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + spin_unlock(&pool->lock); + fail: + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; + cpu_relax(); +@@ -1379,7 +1384,13 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ /* ++ * nort: On RT the "interrupts-disabled" rule has been replaced with ++ * pendingb_lock. ++ */ + lockdep_assert_irqs_disabled(); ++#endif + + + /* if draining, only works from the same workqueue are allowed */ +@@ -1487,14 +1498,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, + bool ret = false; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock,flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_work_on); +@@ -1503,8 +1514,11 @@ void delayed_work_timer_fn(struct timer_list *t) + { + struct delayed_work *dwork = from_timer(dwork, t, timer); + ++ /* XXX */ ++ /* local_lock(pendingb_lock); */ + /* should have been called from irqsafe timer with irq already off */ + __queue_work(dwork->cpu, dwork->wq, &dwork->work); ++ /* local_unlock(pendingb_lock); */ + } + EXPORT_SYMBOL(delayed_work_timer_fn); + +@@ -1559,14 +1573,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, + unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock, flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_delayed_work_on); +@@ -1601,7 +1615,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ +@@ -1612,11 +1626,12 @@ EXPORT_SYMBOL_GPL(mod_delayed_work_on); + static void rcu_work_rcufn(struct rcu_head *rcu) + { + struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); ++ unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_disable(); ++ local_lock_irqsave(pendingb_lock, flags); + __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); +- local_irq_enable(); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /** +@@ -3008,7 +3023,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + + /* + * This allows canceling during early boot. We know that @work +@@ -3069,10 +3084,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); + */ + bool flush_delayed_work(struct delayed_work *dwork) + { +- local_irq_disable(); ++ local_lock_irq(pendingb_lock); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- local_irq_enable(); ++ local_unlock_irq(pendingb_lock); + return flush_work(&dwork->work); + } + EXPORT_SYMBOL(flush_delayed_work); +@@ -3110,7 +3125,7 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) + return false; + + set_work_pool_and_clear_pending(work, get_work_pool_id(work)); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0192-workqueue-Prevent-workqueue-versus-ata-piix-livelock.patch b/debian/patches-rt/0192-workqueue-Prevent-workqueue-versus-ata-piix-livelock.patch new file mode 100644 index 000000000..28a95db99 --- /dev/null +++ b/debian/patches-rt/0192-workqueue-Prevent-workqueue-versus-ata-piix-livelock.patch @@ -0,0 +1,139 @@ +From c86179fe263e888b8dcffa0f1956e2b170b36b48 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Mon, 1 Jul 2013 11:02:42 +0200 +Subject: [PATCH 192/347] workqueue: Prevent workqueue versus ata-piix livelock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +An Intel i7 system regularly detected rcu_preempt stalls after the kernel +was upgraded from 3.6-rt to 3.8-rt. When the stall happened, disk I/O was no +longer possible, unless the system was restarted. + +The kernel message was: +INFO: rcu_preempt self-detected stall on CPU { 6} +[..] +NMI backtrace for cpu 6 +CPU 6 +Pid: 119, comm: irq/19-ata_piix Not tainted 3.8.13-rt13 #11 Shuttle Inc. SX58/SX58 +RIP: 0010:[<ffffffff8124ca60>] [<ffffffff8124ca60>] ip_compute_csum+0x30/0x30 +RSP: 0018:ffff880333303cb0 EFLAGS: 00000002 +RAX: 0000000000000006 RBX: 00000000000003e9 RCX: 0000000000000034 +RDX: 0000000000000000 RSI: ffffffff81aa16d0 RDI: 0000000000000001 +RBP: ffff880333303ce8 R08: ffffffff81aa16d0 R09: ffffffff81c1b8cc +R10: 0000000000000000 R11: 0000000000000000 R12: 000000000005161f +R13: 0000000000000006 R14: ffffffff81aa16d0 R15: 0000000000000002 +FS: 0000000000000000(0000) GS:ffff880333300000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b +CR2: 0000003c1b2bb420 CR3: 0000000001a0f000 CR4: 00000000000007e0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 +Process irq/19-ata_piix (pid: 119, threadinfo ffff88032d88a000, task ffff88032df80000) +Stack: +ffffffff8124cb32 000000000005161e 00000000000003e9 0000000000001000 +0000000000009022 ffffffff81aa16d0 0000000000000002 ffff880333303cf8 +ffffffff8124caa9 ffff880333303d08 ffffffff8124cad2 ffff880333303d28 +Call Trace: +<IRQ> +[<ffffffff8124cb32>] ? delay_tsc+0x33/0xe3 +[<ffffffff8124caa9>] __delay+0xf/0x11 +[<ffffffff8124cad2>] __const_udelay+0x27/0x29 +[<ffffffff8102d1fa>] native_safe_apic_wait_icr_idle+0x39/0x45 +[<ffffffff8102dc9b>] __default_send_IPI_dest_field.constprop.0+0x1e/0x58 +[<ffffffff8102dd1e>] default_send_IPI_mask_sequence_phys+0x49/0x7d +[<ffffffff81030326>] physflat_send_IPI_all+0x17/0x19 +[<ffffffff8102de53>] arch_trigger_all_cpu_backtrace+0x50/0x79 +[<ffffffff810b21d0>] rcu_check_callbacks+0x1cb/0x568 +[<ffffffff81048c9c>] ? raise_softirq+0x2e/0x35 +[<ffffffff81086be0>] ? tick_sched_do_timer+0x38/0x38 +[<ffffffff8104f653>] update_process_times+0x44/0x55 +[<ffffffff81086866>] tick_sched_handle+0x4a/0x59 +[<ffffffff81086c1c>] tick_sched_timer+0x3c/0x5b +[<ffffffff81062845>] __run_hrtimer+0x9b/0x158 +[<ffffffff810631d8>] hrtimer_interrupt+0x172/0x2aa +[<ffffffff8102d498>] smp_apic_timer_interrupt+0x76/0x89 +[<ffffffff814d881d>] apic_timer_interrupt+0x6d/0x80 +<EOI> +[<ffffffff81057cd2>] ? __local_lock_irqsave+0x17/0x4a +[<ffffffff81059336>] try_to_grab_pending+0x42/0x17e +[<ffffffff8105a699>] mod_delayed_work_on+0x32/0x88 +[<ffffffff8105a70b>] mod_delayed_work+0x1c/0x1e +[<ffffffff8122ae84>] blk_run_queue_async+0x37/0x39 +[<ffffffff81230985>] flush_end_io+0xf1/0x107 +[<ffffffff8122e0da>] blk_finish_request+0x21e/0x264 +[<ffffffff8122e162>] blk_end_bidi_request+0x42/0x60 +[<ffffffff8122e1ba>] blk_end_request+0x10/0x12 +[<ffffffff8132de46>] scsi_io_completion+0x1bf/0x492 +[<ffffffff81335cec>] ? sd_done+0x298/0x2ef +[<ffffffff81325a02>] scsi_finish_command+0xe9/0xf2 +[<ffffffff8132dbcb>] scsi_softirq_done+0x106/0x10f +[<ffffffff812333d3>] blk_done_softirq+0x77/0x87 +[<ffffffff8104826f>] do_current_softirqs+0x172/0x2e1 +[<ffffffff810aa820>] ? irq_thread_fn+0x3a/0x3a +[<ffffffff81048466>] local_bh_enable+0x43/0x72 +[<ffffffff810aa866>] irq_forced_thread_fn+0x46/0x52 +[<ffffffff810ab089>] irq_thread+0x8c/0x17c +[<ffffffff810ab179>] ? irq_thread+0x17c/0x17c +[<ffffffff810aaffd>] ? wake_threads_waitq+0x44/0x44 +[<ffffffff8105eb18>] kthread+0x8d/0x95 +[<ffffffff8105ea8b>] ? __kthread_parkme+0x65/0x65 +[<ffffffff814d7b7c>] ret_from_fork+0x7c/0xb0 +[<ffffffff8105ea8b>] ? __kthread_parkme+0x65/0x65 + +The state of softirqd of this CPU at the time of the crash was: +ksoftirqd/6 R running task 0 53 2 0x00000000 +ffff88032fc39d18 0000000000000046 ffff88033330c4c0 ffff8803303f4710 +ffff88032fc39fd8 ffff88032fc39fd8 0000000000000000 0000000000062500 +ffff88032df88000 ffff8803303f4710 0000000000000000 ffff88032fc38000 +Call Trace: +[<ffffffff8105a3ae>] ? __queue_work+0x27c/0x27c +[<ffffffff814d178c>] preempt_schedule+0x61/0x76 +[<ffffffff8106cccf>] migrate_enable+0xe5/0x1df +[<ffffffff8105a3ae>] ? __queue_work+0x27c/0x27c +[<ffffffff8104ef52>] run_timer_softirq+0x161/0x1d6 +[<ffffffff8104826f>] do_current_softirqs+0x172/0x2e1 +[<ffffffff8104840b>] run_ksoftirqd+0x2d/0x45 +[<ffffffff8106658a>] smpboot_thread_fn+0x2ea/0x308 +[<ffffffff810662a0>] ? test_ti_thread_flag+0xc/0xc +[<ffffffff810662a0>] ? test_ti_thread_flag+0xc/0xc +[<ffffffff8105eb18>] kthread+0x8d/0x95 +[<ffffffff8105ea8b>] ? __kthread_parkme+0x65/0x65 +[<ffffffff814d7afc>] ret_from_fork+0x7c/0xb0 +[<ffffffff8105ea8b>] ? __kthread_parkme+0x65/0x65 + +Apparently, the softirq demon and the ata_piix IRQ handler were waiting +for each other to finish ending up in a livelock. After the below patch +was applied, the system no longer crashes. + +Reported-by: Carsten Emde <C.Emde@osadl.org> +Proposed-by: Thomas Gleixner <tglx@linutronix.de> +Tested by: Carsten Emde <C.Emde@osadl.org> +Signed-off-by: Carsten Emde <C.Emde@osadl.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/workqueue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/kernel/workqueue.c b/kernel/workqueue.c +index 2b4c052c51b3..6e73e3eaca5e 100644 +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -51,6 +51,7 @@ + #include <linux/nmi.h> + #include <linux/kvm_para.h> + #include <linux/locallock.h> ++#include <linux/delay.h> + + #include "workqueue_internal.h" + +@@ -1282,7 +1283,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; +- cpu_relax(); ++ cpu_chill(); + return -EAGAIN; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0193-sched-Distangle-worker-accounting-from-rqlock.patch b/debian/patches-rt/0193-sched-Distangle-worker-accounting-from-rqlock.patch new file mode 100644 index 000000000..5347efe07 --- /dev/null +++ b/debian/patches-rt/0193-sched-Distangle-worker-accounting-from-rqlock.patch @@ -0,0 +1,291 @@ +From a446a9e4a93ca3245891dbdac928195f604ee473 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 22 Jun 2011 19:47:03 +0200 +Subject: [PATCH 193/347] sched: Distangle worker accounting from rqlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The worker accounting for cpu bound workers is plugged into the core +scheduler code and the wakeup code. This is not a hard requirement and +can be avoided by keeping track of the state in the workqueue code +itself. + +Keep track of the sleeping state in the worker itself and call the +notifier before entering the core scheduler. There might be false +positives when the task is woken between that call and actually +scheduling, but that's not really different from scheduling and being +woken immediately after switching away. There is also no harm from +updating nr_running when the task returns from scheduling instead of +accounting it in the wakeup code. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Cc: Peter Zijlstra <peterz@infradead.org> +Cc: Tejun Heo <tj@kernel.org> +Cc: Jens Axboe <axboe@kernel.dk> +Cc: Linus Torvalds <torvalds@linux-foundation.org> +Link: http://lkml.kernel.org/r/20110622174919.135236139@linutronix.de +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +[bigeasy: preempt_disable() around wq_worker_sleeping() by Daniel Bristot de + Oliveira] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/core.c | 90 +++++++++---------------------------- + kernel/workqueue.c | 52 ++++++++++----------- + kernel/workqueue_internal.h | 5 ++- + 3 files changed, 47 insertions(+), 100 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 0c44c16244a1..11afaa2c618a 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1704,10 +1704,6 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl + { + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; +- +- /* If a worker is waking up, notify the workqueue: */ +- if (p->flags & PF_WQ_WORKER) +- wq_worker_waking_up(p, cpu_of(rq)); + } + + /* +@@ -2146,56 +2142,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) + return success; + } + +-/** +- * try_to_wake_up_local - try to wake up a local task with rq lock held +- * @p: the thread to be awakened +- * @rf: request-queue flags for pinning +- * +- * Put @p on the run-queue if it's not already there. The caller must +- * ensure that this_rq() is locked, @p is bound to this_rq() and not +- * the current task. +- */ +-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) +-{ +- struct rq *rq = task_rq(p); +- +- if (WARN_ON_ONCE(rq != this_rq()) || +- WARN_ON_ONCE(p == current)) +- return; +- +- lockdep_assert_held(&rq->lock); +- +- if (!raw_spin_trylock(&p->pi_lock)) { +- /* +- * This is OK, because current is on_cpu, which avoids it being +- * picked for load-balance and preemption/IRQs are still +- * disabled avoiding further scheduler activity on it and we've +- * not yet picked a replacement task. +- */ +- rq_unlock(rq, rf); +- raw_spin_lock(&p->pi_lock); +- rq_relock(rq, rf); +- } +- +- if (!(p->state & TASK_NORMAL)) +- goto out; +- +- trace_sched_waking(p); +- +- if (!task_on_rq_queued(p)) { +- if (p->in_iowait) { +- delayacct_blkio_end(p); +- atomic_dec(&rq->nr_iowait); +- } +- ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); +- } +- +- ttwu_do_wakeup(rq, p, 0, rf); +- ttwu_stat(p, smp_processor_id(), 0); +-out: +- raw_spin_unlock(&p->pi_lock); +-} +- + /** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. +@@ -3566,21 +3512,6 @@ static void __sched notrace __schedule(bool preempt) + atomic_inc(&rq->nr_iowait); + delayacct_blkio_start(); + } +- +- /* +- * If a worker went to sleep, notify and ask workqueue +- * whether it wants to wake up a task to maintain +- * concurrency. +- * Only call wake up if prev isn't blocked on a sleeping +- * spin lock. +- */ +- if (prev->flags & PF_WQ_WORKER && !prev->saved_state) { +- struct task_struct *to_wakeup; +- +- to_wakeup = wq_worker_sleeping(prev); +- if (to_wakeup) +- try_to_wake_up_local(to_wakeup, &rf); +- } + } + switch_count = &prev->nvcsw; + } +@@ -3640,6 +3571,20 @@ static inline void sched_submit_work(struct task_struct *tsk) + { + if (!tsk->state || tsk_is_pi_blocked(tsk)) + return; ++ ++ /* ++ * If a worker went to sleep, notify and ask workqueue whether ++ * it wants to wake up a task to maintain concurrency. ++ * As this function is called inside the schedule() context, ++ * we disable preemption to avoid it calling schedule() again ++ * in the possible wakeup of a kworker. ++ */ ++ if (tsk->flags & PF_WQ_WORKER) { ++ preempt_disable(); ++ wq_worker_sleeping(tsk); ++ preempt_enable_no_resched(); ++ } ++ + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. +@@ -3648,6 +3593,12 @@ static inline void sched_submit_work(struct task_struct *tsk) + blk_schedule_flush_plug(tsk); + } + ++static void sched_update_worker(struct task_struct *tsk) ++{ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_running(tsk); ++} ++ + asmlinkage __visible void __sched schedule(void) + { + struct task_struct *tsk = current; +@@ -3658,6 +3609,7 @@ asmlinkage __visible void __sched schedule(void) + __schedule(false); + sched_preempt_enable_no_resched(); + } while (need_resched()); ++ sched_update_worker(tsk); + } + EXPORT_SYMBOL(schedule); + +diff --git a/kernel/workqueue.c b/kernel/workqueue.c +index 6e73e3eaca5e..0c529f920232 100644 +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -844,43 +844,32 @@ static void wake_up_worker(struct worker_pool *pool) + } + + /** +- * wq_worker_waking_up - a worker is waking up ++ * wq_worker_running - a worker is running again + * @task: task waking up +- * @cpu: CPU @task is waking up to + * +- * This function is called during try_to_wake_up() when a worker is +- * being awoken. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) ++ * This function is called when a worker returns from schedule() + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu) ++void wq_worker_running(struct task_struct *task) + { + struct worker *worker = kthread_data(task); + +- if (!(worker->flags & WORKER_NOT_RUNNING)) { +- WARN_ON_ONCE(worker->pool->cpu != cpu); ++ if (!worker->sleeping) ++ return; ++ if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&worker->pool->nr_running); +- } ++ worker->sleeping = 0; + } + + /** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep + * +- * This function is called during schedule() when a busy worker is +- * going to sleep. Worker on the same cpu can be woken up by +- * returning pointer to its task. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) +- * +- * Return: +- * Worker task on @cpu to wake up, %NULL if none. ++ * This function is called from schedule() when a busy worker is ++ * going to sleep. + */ +-struct task_struct *wq_worker_sleeping(struct task_struct *task) ++void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task), *to_wakeup = NULL; ++ struct worker *next, *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -889,13 +878,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) + * checking NOT_RUNNING. + */ + if (worker->flags & WORKER_NOT_RUNNING) +- return NULL; ++ return; + + pool = worker->pool; + +- /* this can only happen on the local cpu */ +- if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id())) +- return NULL; ++ if (WARN_ON_ONCE(worker->sleeping)) ++ return; ++ ++ worker->sleeping = 1; ++ spin_lock_irq(&pool->lock); + + /* + * The counterpart of the following dec_and_test, implied mb, +@@ -909,9 +900,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) + * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && +- !list_empty(&pool->worklist)) +- to_wakeup = first_idle_worker(pool); +- return to_wakeup ? to_wakeup->task : NULL; ++ !list_empty(&pool->worklist)) { ++ next = first_idle_worker(pool); ++ if (next) ++ wake_up_process(next->task); ++ } ++ spin_unlock_irq(&pool->lock); + } + + /** +diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h +index 66fbb5a9e633..30cfed226b39 100644 +--- a/kernel/workqueue_internal.h ++++ b/kernel/workqueue_internal.h +@@ -44,6 +44,7 @@ struct worker { + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ ++ int sleeping; /* None */ + + /* + * Opaque string set with work_set_desc(). Printed out with task +@@ -69,7 +70,7 @@ static inline struct worker *current_wq_worker(void) + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched/core.c and workqueue.c. + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu); +-struct task_struct *wq_worker_sleeping(struct task_struct *task); ++void wq_worker_running(struct task_struct *task); ++void wq_worker_sleeping(struct task_struct *task); + + #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ +-- +2.36.1 + diff --git a/debian/patches-rt/0194-debugobjects-Make-RT-aware.patch b/debian/patches-rt/0194-debugobjects-Make-RT-aware.patch new file mode 100644 index 000000000..3fd87b158 --- /dev/null +++ b/debian/patches-rt/0194-debugobjects-Make-RT-aware.patch @@ -0,0 +1,32 @@ +From eaad8379256de9e0327feb6fac10f692aaee4498 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 17 Jul 2011 21:41:35 +0200 +Subject: [PATCH 194/347] debugobjects: Make RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Avoid filling the pool / allocating memory with irqs off(). + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + lib/debugobjects.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/lib/debugobjects.c b/lib/debugobjects.c +index 14afeeb7d6ef..e28481c402ae 100644 +--- a/lib/debugobjects.c ++++ b/lib/debugobjects.c +@@ -376,7 +376,10 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) + struct debug_obj *obj; + unsigned long flags; + +- fill_pool(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (preempt_count() == 0 && !irqs_disabled()) ++#endif ++ fill_pool(); + + db = get_bucket((unsigned long) addr); + +-- +2.36.1 + diff --git a/debian/patches-rt/0195-seqlock-Prevent-rt-starvation.patch b/debian/patches-rt/0195-seqlock-Prevent-rt-starvation.patch new file mode 100644 index 000000000..6398461d7 --- /dev/null +++ b/debian/patches-rt/0195-seqlock-Prevent-rt-starvation.patch @@ -0,0 +1,195 @@ +From d2adc15afeaebd45ad21834295e100c5627a7fa2 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 22 Feb 2012 12:03:30 +0100 +Subject: [PATCH 195/347] seqlock: Prevent rt starvation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +If a low prio writer gets preempted while holding the seqlock write +locked, a high prio reader spins forever on RT. + +To prevent this let the reader grab the spinlock, so it blocks and +eventually boosts the writer. This way the writer can proceed and +endless spinning is prevented. + +For seqcount writers we disable preemption over the update code +path. Thanks to Al Viro for distangling some VFS code to make that +possible. + +Nicholas Mc Guire: +- spin_lock+unlock => spin_unlock_wait +- __write_seqcount_begin => __raw_write_seqcount_begin + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/seqlock.h | 57 ++++++++++++++++++++++++++++++++--------- + include/net/neighbour.h | 6 ++--- + 2 files changed, 48 insertions(+), 15 deletions(-) + +diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h +index a42a29952889..a3768cfce914 100644 +--- a/include/linux/seqlock.h ++++ b/include/linux/seqlock.h +@@ -221,20 +221,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) + return __read_seqcount_retry(s, start); + } + +- +- +-static inline void raw_write_seqcount_begin(seqcount_t *s) ++static inline void __raw_write_seqcount_begin(seqcount_t *s) + { + s->sequence++; + smp_wmb(); + } + +-static inline void raw_write_seqcount_end(seqcount_t *s) ++static inline void raw_write_seqcount_begin(seqcount_t *s) ++{ ++ preempt_disable_rt(); ++ __raw_write_seqcount_begin(s); ++} ++ ++static inline void __raw_write_seqcount_end(seqcount_t *s) + { + smp_wmb(); + s->sequence++; + } + ++static inline void raw_write_seqcount_end(seqcount_t *s) ++{ ++ __raw_write_seqcount_end(s); ++ preempt_enable_rt(); ++} ++ + /** + * raw_write_seqcount_barrier - do a seq write barrier + * @s: pointer to seqcount_t +@@ -435,10 +445,33 @@ typedef struct { + /* + * Read side functions for starting and finalizing a read side section. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + static inline unsigned read_seqbegin(const seqlock_t *sl) + { + return read_seqcount_begin(&sl->seqcount); + } ++#else ++/* ++ * Starvation safe read side for RT ++ */ ++static inline unsigned read_seqbegin(seqlock_t *sl) ++{ ++ unsigned ret; ++ ++repeat: ++ ret = READ_ONCE(sl->seqcount.sequence); ++ if (unlikely(ret & 1)) { ++ /* ++ * Take the lock and let the writer proceed (i.e. evtl ++ * boost it), otherwise we could loop here forever. ++ */ ++ spin_unlock_wait(&sl->lock); ++ goto repeat; ++ } ++ smp_rmb(); ++ return ret; ++} ++#endif + + static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) + { +@@ -453,36 +486,36 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) + static inline void write_seqlock(seqlock_t *sl) + { + spin_lock(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock(&sl->lock); + } + + static inline void write_seqlock_bh(seqlock_t *sl) + { + spin_lock_bh(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_bh(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_bh(&sl->lock); + } + + static inline void write_seqlock_irq(seqlock_t *sl) + { + spin_lock_irq(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_irq(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); + } + +@@ -491,7 +524,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + return flags; + } + +@@ -501,7 +534,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) + static inline void + write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); + } + +diff --git a/include/net/neighbour.h b/include/net/neighbour.h +index 5ce035984a4d..1166fc17b757 100644 +--- a/include/net/neighbour.h ++++ b/include/net/neighbour.h +@@ -451,7 +451,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) + } + #endif + +-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) ++static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) + { + unsigned int hh_alen = 0; + unsigned int seq; +@@ -493,7 +493,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb + + static inline int neigh_output(struct neighbour *n, struct sk_buff *skb) + { +- const struct hh_cache *hh = &n->hh; ++ struct hh_cache *hh = &n->hh; + + if ((n->nud_state & NUD_CONNECTED) && hh->hh_len) + return neigh_hh_output(hh, skb); +@@ -534,7 +534,7 @@ struct neighbour_cb { + + #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) + +-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, ++static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, + const struct net_device *dev) + { + unsigned int seq; +-- +2.36.1 + diff --git a/debian/patches-rt/0196-sunrpc-Make-svc_xprt_do_enqueue-use-get_cpu_light.patch b/debian/patches-rt/0196-sunrpc-Make-svc_xprt_do_enqueue-use-get_cpu_light.patch new file mode 100644 index 000000000..e55b80bd6 --- /dev/null +++ b/debian/patches-rt/0196-sunrpc-Make-svc_xprt_do_enqueue-use-get_cpu_light.patch @@ -0,0 +1,61 @@ +From f1452101ff124dd5a82d5345b6f92f98d891054f Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Wed, 18 Feb 2015 16:05:28 +0100 +Subject: [PATCH 196/347] sunrpc: Make svc_xprt_do_enqueue() use + get_cpu_light() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 1, irqs_disabled(): 0, pid: 3194, name: rpc.nfsd +|Preemption disabled at:[<ffffffffa06bf0bb>] svc_xprt_received+0x4b/0xc0 [sunrpc] +|CPU: 6 PID: 3194 Comm: rpc.nfsd Not tainted 3.18.7-rt1 #9 +|Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.404 11/06/2014 +| ffff880409630000 ffff8800d9a33c78 ffffffff815bdeb5 0000000000000002 +| 0000000000000000 ffff8800d9a33c98 ffffffff81073c86 ffff880408dd6008 +| ffff880408dd6000 ffff8800d9a33cb8 ffffffff815c3d84 ffff88040b3ac000 +|Call Trace: +| [<ffffffff815bdeb5>] dump_stack+0x4f/0x9e +| [<ffffffff81073c86>] __might_sleep+0xe6/0x150 +| [<ffffffff815c3d84>] rt_spin_lock+0x24/0x50 +| [<ffffffffa06beec0>] svc_xprt_do_enqueue+0x80/0x230 [sunrpc] +| [<ffffffffa06bf0bb>] svc_xprt_received+0x4b/0xc0 [sunrpc] +| [<ffffffffa06c03ed>] svc_add_new_perm_xprt+0x6d/0x80 [sunrpc] +| [<ffffffffa06b2693>] svc_addsock+0x143/0x200 [sunrpc] +| [<ffffffffa072e69c>] write_ports+0x28c/0x340 [nfsd] +| [<ffffffffa072d2ac>] nfsctl_transaction_write+0x4c/0x80 [nfsd] +| [<ffffffff8117ee83>] vfs_write+0xb3/0x1d0 +| [<ffffffff8117f889>] SyS_write+0x49/0xb0 +| [<ffffffff815c4556>] system_call_fastpath+0x16/0x1b + + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/sunrpc/svc_xprt.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c +index 4b56b949a463..83a4a0a13a1c 100644 +--- a/net/sunrpc/svc_xprt.c ++++ b/net/sunrpc/svc_xprt.c +@@ -402,7 +402,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) + if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) + return; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = svc_pool_for_cpu(xprt->xpt_server, cpu); + + atomic_long_inc(&pool->sp_stats.packets); +@@ -426,7 +426,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) + rqstp = NULL; + out_unlock: + rcu_read_unlock(); +- put_cpu(); ++ put_cpu_light(); + trace_svc_xprt_do_enqueue(xprt, rqstp); + } + EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); +-- +2.36.1 + diff --git a/debian/patches-rt/0197-net-Use-skbufhead-with-raw-lock.patch b/debian/patches-rt/0197-net-Use-skbufhead-with-raw-lock.patch new file mode 100644 index 000000000..f54ab15b6 --- /dev/null +++ b/debian/patches-rt/0197-net-Use-skbufhead-with-raw-lock.patch @@ -0,0 +1,148 @@ +From 8c4af88efcc296bc2daa2be90fbea82190799883 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 12 Jul 2011 15:38:34 +0200 +Subject: [PATCH 197/347] net: Use skbufhead with raw lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Use the rps lock as rawlock so we can keep irq-off regions. It looks low +latency. However we can't kfree() from this context therefore we defer this +to the softirq and use the tofree_queue list for it (similar to process_queue). + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/netdevice.h | 1 + + include/linux/skbuff.h | 7 +++++++ + net/core/dev.c | 26 ++++++++++++++++++++------ + 3 files changed, 28 insertions(+), 6 deletions(-) + +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index 8d48b352ee74..d893dc112afc 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -2990,6 +2990,7 @@ struct softnet_data { + unsigned int dropped; + struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; ++ struct sk_buff_head tofree_queue; + + }; + +diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h +index f97734f34746..3ede4f0eac10 100644 +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -287,6 +287,7 @@ struct sk_buff_head { + + __u32 qlen; + spinlock_t lock; ++ raw_spinlock_t raw_lock; + }; + + struct sk_buff; +@@ -1735,6 +1736,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list) + __skb_queue_head_init(list); + } + ++static inline void skb_queue_head_init_raw(struct sk_buff_head *list) ++{ ++ raw_spin_lock_init(&list->raw_lock); ++ __skb_queue_head_init(list); ++} ++ + static inline void skb_queue_head_init_class(struct sk_buff_head *list, + struct lock_class_key *class) + { +diff --git a/net/core/dev.c b/net/core/dev.c +index 315bdaf00ac8..c279375fa5b9 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -219,14 +219,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) + static inline void rps_lock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_lock(&sd->input_pkt_queue.lock); ++ raw_spin_lock(&sd->input_pkt_queue.raw_lock); + #endif + } + + static inline void rps_unlock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_unlock(&sd->input_pkt_queue.lock); ++ raw_spin_unlock(&sd->input_pkt_queue.raw_lock); + #endif + } + +@@ -5858,7 +5858,9 @@ static int process_backlog(struct napi_struct *napi, int quota) + while (again) { + struct sk_buff *skb; + ++ local_irq_disable(); + while ((skb = __skb_dequeue(&sd->process_queue))) { ++ local_irq_enable(); + rcu_read_lock(); + __netif_receive_skb(skb); + rcu_read_unlock(); +@@ -5866,9 +5868,9 @@ static int process_backlog(struct napi_struct *napi, int quota) + if (++work >= quota) + return work; + ++ local_irq_disable(); + } + +- local_irq_disable(); + rps_lock(sd); + if (skb_queue_empty(&sd->input_pkt_queue)) { + /* +@@ -6341,13 +6343,21 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) + unsigned long time_limit = jiffies + + usecs_to_jiffies(netdev_budget_usecs); + int budget = netdev_budget; ++ struct sk_buff_head tofree_q; ++ struct sk_buff *skb; + LIST_HEAD(list); + LIST_HEAD(repoll); + ++ __skb_queue_head_init(&tofree_q); ++ + local_irq_disable(); ++ skb_queue_splice_init(&sd->tofree_queue, &tofree_q); + list_splice_init(&sd->poll_list, &list); + local_irq_enable(); + ++ while ((skb = __skb_dequeue(&tofree_q))) ++ kfree_skb(skb); ++ + for (;;) { + struct napi_struct *n; + +@@ -9545,10 +9555,13 @@ static int dev_cpu_dead(unsigned int oldcpu) + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } +- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { ++ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } ++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { ++ kfree_skb(skb); ++ } + + return 0; + } +@@ -9859,8 +9872,9 @@ static int __init net_dev_init(void) + + INIT_WORK(flush, flush_backlog); + +- skb_queue_head_init(&sd->input_pkt_queue); +- skb_queue_head_init(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->input_pkt_queue); ++ skb_queue_head_init_raw(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->tofree_queue); + #ifdef CONFIG_XFRM_OFFLOAD + skb_queue_head_init(&sd->xfrm_backlog); + #endif +-- +2.36.1 + diff --git a/debian/patches-rt/0198-net-move-xmit_recursion-to-per-task-variable-on-RT.patch b/debian/patches-rt/0198-net-move-xmit_recursion-to-per-task-variable-on-RT.patch new file mode 100644 index 000000000..242d9fd91 --- /dev/null +++ b/debian/patches-rt/0198-net-move-xmit_recursion-to-per-task-variable-on-RT.patch @@ -0,0 +1,189 @@ +From 5b1c12f86da1a979d45cda068adc9b597bc37e53 Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Fri, 17 Dec 2021 14:31:31 -0600 +Subject: [PATCH 198/347] net: move xmit_recursion to per-task variable on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +A softirq on -RT can be preempted. That means one task is in +__dev_queue_xmit(), gets preempted and another task may enter +__dev_queue_xmit() aw well. netperf together with a bridge device +will then trigger the `recursion alert` because each task increments +the xmit_recursion variable which is per-CPU. +A virtual device like br0 is required to trigger this warning. + +This patch moves the lock owner and counter to be per task instead per-CPU so +it counts the recursion properly on -RT. The owner is also a task now and not a +CPU number. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Clark Williams <williams@redhat.com> +--- + include/linux/netdevice.h | 71 +++++++++++++++++++++++++++++++++++++-- + include/linux/sched.h | 3 ++ + net/core/dev.c | 6 +++- + 3 files changed, 77 insertions(+), 3 deletions(-) + +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index d893dc112afc..dfec34087039 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -588,7 +588,11 @@ struct netdev_queue { + * write-mostly part + */ + spinlock_t _xmit_lock ____cacheline_aligned_in_smp; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct task_struct *xmit_lock_owner; ++#else + int xmit_lock_owner; ++#endif + /* + * Time (in jiffies) of last Tx + */ +@@ -3009,14 +3013,38 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd, + #endif + } + ++#define XMIT_RECURSION_LIMIT 8 + DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int dev_recursion_level(void) ++{ ++ return current->xmit_recursion; ++} ++ ++static inline bool dev_xmit_recursion(void) ++{ ++ return unlikely(current->xmit_recursion > ++ XMIT_RECURSION_LIMIT); ++} ++ ++static inline void dev_xmit_recursion_inc(void) ++{ ++ current->xmit_recursion++; ++} ++ ++static inline void dev_xmit_recursion_dec(void) ++{ ++ current->xmit_recursion--; ++} ++ ++#else ++ + static inline int dev_recursion_level(void) + { + return this_cpu_read(softnet_data.xmit.recursion); + } + +-#define XMIT_RECURSION_LIMIT 8 + static inline bool dev_xmit_recursion(void) + { + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > +@@ -3032,6 +3060,7 @@ static inline void dev_xmit_recursion_dec(void) + { + __this_cpu_dec(softnet_data.xmit.recursion); + } ++#endif + + void __netif_schedule(struct Qdisc *q); + void netif_schedule_queue(struct netdev_queue *txq); +@@ -3841,6 +3870,44 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) + return (1U << debug_value) - 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) ++{ ++ txq->xmit_lock_owner = current; ++} ++ ++static inline void netdev_queue_clear_owner(struct netdev_queue *txq) ++{ ++ txq->xmit_lock_owner = NULL; ++} ++ ++static inline bool netdev_queue_has_owner(struct netdev_queue *txq) ++{ ++ if (txq->xmit_lock_owner != NULL) ++ return true; ++ return false; ++} ++ ++#else ++ ++static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) ++{ ++ txq->xmit_lock_owner = cpu; ++} ++ ++static inline void netdev_queue_clear_owner(struct netdev_queue *txq) ++{ ++ txq->xmit_lock_owner = -1; ++} ++ ++static inline bool netdev_queue_has_owner(struct netdev_queue *txq) ++{ ++ if (txq->xmit_lock_owner != -1) ++ return true; ++ return false; ++} ++#endif ++ + static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) + { + spin_lock(&txq->_xmit_lock); +@@ -3893,7 +3960,7 @@ static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) + + static inline void txq_trans_update(struct netdev_queue *txq) + { +- if (txq->xmit_lock_owner != -1) ++ if (netdev_queue_has_owner(txq)) + txq->trans_start = jiffies; + } + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index ceb3bdfb6bc4..b7a357635d60 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1218,6 +1218,9 @@ struct task_struct { + #endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; ++#endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int xmit_recursion; + #endif + int pagefault_disabled; + #ifdef CONFIG_MMU +diff --git a/net/core/dev.c b/net/core/dev.c +index c279375fa5b9..a59b1db02f8b 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3833,10 +3833,14 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) + if (dev->flags & IFF_UP) { + int cpu = smp_processor_id(); /* ok because BHs are off */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (READ_ONCE(txq->xmit_lock_owner) != current) { ++#else + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { ++#endif + if (dev_xmit_recursion()) + goto recursion_alert; + +@@ -8594,7 +8598,7 @@ static void netdev_init_one_queue(struct net_device *dev, + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); +- queue->xmit_lock_owner = -1; ++ netdev_queue_clear_owner(queue); + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); + queue->dev = dev; + #ifdef CONFIG_BQL +-- +2.36.1 + diff --git a/debian/patches-rt/0199-net-provide-a-way-to-delegate-processing-a-softirq-t.patch b/debian/patches-rt/0199-net-provide-a-way-to-delegate-processing-a-softirq-t.patch new file mode 100644 index 000000000..ad68c8b6d --- /dev/null +++ b/debian/patches-rt/0199-net-provide-a-way-to-delegate-processing-a-softirq-t.patch @@ -0,0 +1,89 @@ +From e035c89c203c5d80fa945338da5efe3ec563c7f7 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 20 Jan 2016 15:39:05 +0100 +Subject: [PATCH 199/347] net: provide a way to delegate processing a softirq + to ksoftirqd +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +If the NET_RX uses up all of his budget it moves the following NAPI +invocations into the `ksoftirqd`. On -RT it does not do so. Instead it +rises the NET_RX softirq in its current context again. + +In order to get closer to mainline's behaviour this patch provides +__raise_softirq_irqoff_ksoft() which raises the softirq in the ksoftird. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/interrupt.h | 8 ++++++++ + kernel/softirq.c | 21 +++++++++++++++++++++ + net/core/dev.c | 2 +- + 3 files changed, 30 insertions(+), 1 deletion(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index e1438fe66467..97d9ba26915e 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -518,6 +518,14 @@ extern void thread_do_softirq(void); + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); + extern void __raise_softirq_irqoff(unsigned int nr); ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void __raise_softirq_irqoff_ksoft(unsigned int nr); ++#else ++static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++} ++#endif + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 27a4bb2303d0..25bcf2f2714b 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -721,6 +721,27 @@ void __raise_softirq_irqoff(unsigned int nr) + wakeup_proper_softirq(nr); + } + ++/* ++ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd ++ */ ++void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ unsigned int mask; ++ ++ if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) || ++ !__this_cpu_read(ktimer_softirqd))) ++ return; ++ mask = 1UL << nr; ++ ++ trace_softirq_raise(nr); ++ or_softirq_pending(mask); ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++ wakeup_proper_softirq(nr); ++} ++ + /* + * This function must run with irqs disabled! + */ +diff --git a/net/core/dev.c b/net/core/dev.c +index a59b1db02f8b..2bf357d5602b 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -6391,7 +6391,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) + list_splice_tail(&repoll, &list); + list_splice(&list, &sd->poll_list); + if (!list_empty(&sd->poll_list)) +- __raise_softirq_irqoff(NET_RX_SOFTIRQ); ++ __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ); + + net_rps_action_and_irq_enable(sd); + out: +-- +2.36.1 + diff --git a/debian/patches-rt/0200-net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch b/debian/patches-rt/0200-net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch new file mode 100644 index 000000000..026e263e5 --- /dev/null +++ b/debian/patches-rt/0200-net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch @@ -0,0 +1,42 @@ +From e58c64de87f7c5ae3df17d3f8c9615e1655176eb Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 30 Mar 2016 13:36:29 +0200 +Subject: [PATCH 200/347] net: dev: always take qdisc's busylock in + __dev_xmit_skb() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The root-lock is dropped before dev_hard_start_xmit() is invoked and after +setting the __QDISC___STATE_RUNNING bit. If this task is now pushed away +by a task with a higher priority then the task with the higher priority +won't be able to submit packets to the NIC directly instead they will be +enqueued into the Qdisc. The NIC will remain idle until the task(s) with +higher priority leave the CPU and the task with lower priority gets back +and finishes the job. + +If we take always the busylock we ensure that the RT task can boost the +low-prio task and submit the packet. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/core/dev.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/net/core/dev.c b/net/core/dev.c +index 2bf357d5602b..7c59fa4d3ecf 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3472,7 +3472,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, + * This permits qdisc->running owner to get the lock more + * often and dequeue packets faster. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ contended = true; ++#else + contended = qdisc_is_running(q); ++#endif + if (unlikely(contended)) + spin_lock(&q->busylock); + +-- +2.36.1 + diff --git a/debian/patches-rt/0201-net-Qdisc-use-a-seqlock-instead-seqcount.patch b/debian/patches-rt/0201-net-Qdisc-use-a-seqlock-instead-seqcount.patch new file mode 100644 index 000000000..8d15d62a7 --- /dev/null +++ b/debian/patches-rt/0201-net-Qdisc-use-a-seqlock-instead-seqcount.patch @@ -0,0 +1,293 @@ +From 561eb0fa2d08a2b919983a6deaaef8022a6d0707 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 14 Sep 2016 17:36:35 +0200 +Subject: [PATCH 201/347] net/Qdisc: use a seqlock instead seqcount +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The seqcount disables preemption on -RT while it is held which can't +remove. Also we don't want the reader to spin for ages if the writer is +scheduled out. The seqlock on the other hand will serialize / sleep on +the lock while writer is active. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/seqlock.h | 9 +++++++++ + include/net/gen_stats.h | 9 +++++---- + include/net/net_seq_lock.h | 15 +++++++++++++++ + include/net/sch_generic.h | 19 +++++++++++++++++-- + net/core/gen_estimator.c | 6 +++--- + net/core/gen_stats.c | 8 ++++---- + net/sched/sch_api.c | 2 +- + net/sched/sch_generic.c | 12 ++++++++++++ + 8 files changed, 66 insertions(+), 14 deletions(-) + create mode 100644 include/net/net_seq_lock.h + +diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h +index a3768cfce914..31bc2cc99bf0 100644 +--- a/include/linux/seqlock.h ++++ b/include/linux/seqlock.h +@@ -489,6 +489,15 @@ static inline void write_seqlock(seqlock_t *sl) + __raw_write_seqcount_begin(&sl->seqcount); + } + ++static inline int try_write_seqlock(seqlock_t *sl) ++{ ++ if (spin_trylock(&sl->lock)) { ++ __raw_write_seqcount_begin(&sl->seqcount); ++ return 1; ++ } ++ return 0; ++} ++ + static inline void write_sequnlock(seqlock_t *sl) + { + __raw_write_seqcount_end(&sl->seqcount); +diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h +index 883bb9085f15..3b593cdeb9af 100644 +--- a/include/net/gen_stats.h ++++ b/include/net/gen_stats.h +@@ -6,6 +6,7 @@ + #include <linux/socket.h> + #include <linux/rtnetlink.h> + #include <linux/pkt_sched.h> ++#include <net/net_seq_lock.h> + + struct gnet_stats_basic_cpu { + struct gnet_stats_basic_packed bstats; +@@ -36,11 +37,11 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, + spinlock_t *lock, struct gnet_dump *d, + int padattr); + +-int gnet_stats_copy_basic(const seqcount_t *running, ++int gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b); +-void __gnet_stats_copy_basic(const seqcount_t *running, ++void __gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b); +@@ -60,13 +61,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **rate_est, + spinlock_t *lock, +- seqcount_t *running, struct nlattr *opt); ++ net_seqlock_t *running, struct nlattr *opt); + void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); + int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **ptr, + spinlock_t *lock, +- seqcount_t *running, struct nlattr *opt); ++ net_seqlock_t *running, struct nlattr *opt); + bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); + bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, + struct gnet_stats_rate_est64 *sample); +diff --git a/include/net/net_seq_lock.h b/include/net/net_seq_lock.h +new file mode 100644 +index 000000000000..a7034298a82a +--- /dev/null ++++ b/include/net/net_seq_lock.h +@@ -0,0 +1,15 @@ ++#ifndef __NET_NET_SEQ_LOCK_H__ ++#define __NET_NET_SEQ_LOCK_H__ ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define net_seqlock_t seqlock_t ++# define net_seq_begin(__r) read_seqbegin(__r) ++# define net_seq_retry(__r, __s) read_seqretry(__r, __s) ++ ++#else ++# define net_seqlock_t seqcount_t ++# define net_seq_begin(__r) read_seqcount_begin(__r) ++# define net_seq_retry(__r, __s) read_seqcount_retry(__r, __s) ++#endif ++ ++#endif +diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h +index 483303adf3df..038204c7b05e 100644 +--- a/include/net/sch_generic.h ++++ b/include/net/sch_generic.h +@@ -10,6 +10,7 @@ + #include <linux/percpu.h> + #include <linux/dynamic_queue_limits.h> + #include <linux/list.h> ++#include <net/net_seq_lock.h> + #include <linux/refcount.h> + #include <linux/workqueue.h> + #include <net/gen_stats.h> +@@ -100,7 +101,7 @@ struct Qdisc { + struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; + struct qdisc_skb_head q; + struct gnet_stats_basic_packed bstats; +- seqcount_t running; ++ net_seqlock_t running; + struct gnet_stats_queue qstats; + unsigned long state; + struct Qdisc *next_sched; +@@ -135,7 +136,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) + { + if (qdisc->flags & TCQ_F_NOLOCK) + return spin_is_locked(&qdisc->seqlock); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ return spin_is_locked(&qdisc->running.lock) ? true : false; ++#else + return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; ++#endif + } + + static inline bool qdisc_run_begin(struct Qdisc *qdisc) +@@ -146,17 +151,27 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) + } else if (qdisc_is_running(qdisc)) { + return false; + } ++#ifdef CONFIG_PREEMPT_RT_BASE ++ if (try_write_seqlock(&qdisc->running)) ++ return true; ++ return false; ++#else + /* Variant of write_seqcount_begin() telling lockdep a trylock + * was attempted. + */ + raw_write_seqcount_begin(&qdisc->running); + seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); + return true; ++#endif + } + + static inline void qdisc_run_end(struct Qdisc *qdisc) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ write_sequnlock(&qdisc->running); ++#else + write_seqcount_end(&qdisc->running); ++#endif + if (qdisc->flags & TCQ_F_NOLOCK) + spin_unlock(&qdisc->seqlock); + } +@@ -475,7 +490,7 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) + return qdisc_lock(root); + } + +-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) ++static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) + { + struct Qdisc *root = qdisc_root_sleeping(qdisc); + +diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c +index 752744db11ff..7112e28b4130 100644 +--- a/net/core/gen_estimator.c ++++ b/net/core/gen_estimator.c +@@ -46,7 +46,7 @@ + struct net_rate_estimator { + struct gnet_stats_basic_packed *bstats; + spinlock_t *stats_lock; +- seqcount_t *running; ++ net_seqlock_t *running; + struct gnet_stats_basic_cpu __percpu *cpu_bstats; + u8 ewma_log; + u8 intvl_log; /* period : (250ms << intvl_log) */ +@@ -129,7 +129,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **rate_est, + spinlock_t *lock, +- seqcount_t *running, ++ net_seqlock_t *running, + struct nlattr *opt) + { + struct gnet_estimator *parm = nla_data(opt); +@@ -230,7 +230,7 @@ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **rate_est, + spinlock_t *lock, +- seqcount_t *running, struct nlattr *opt) ++ net_seqlock_t *running, struct nlattr *opt) + { + return gen_new_estimator(bstats, cpu_bstats, rate_est, + lock, running, opt); +diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c +index e2fd8baec65f..8bab88738691 100644 +--- a/net/core/gen_stats.c ++++ b/net/core/gen_stats.c +@@ -142,7 +142,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, + } + + void +-__gnet_stats_copy_basic(const seqcount_t *running, ++__gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b) +@@ -155,10 +155,10 @@ __gnet_stats_copy_basic(const seqcount_t *running, + } + do { + if (running) +- seq = read_seqcount_begin(running); ++ seq = net_seq_begin(running); + bstats->bytes = b->bytes; + bstats->packets = b->packets; +- } while (running && read_seqcount_retry(running, seq)); ++ } while (running && net_seq_retry(running, seq)); + } + EXPORT_SYMBOL(__gnet_stats_copy_basic); + +@@ -176,7 +176,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); + * if the room in the socket buffer was not sufficient. + */ + int +-gnet_stats_copy_basic(const seqcount_t *running, ++gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b) +diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c +index 424e70907b96..6b4ee7c98d69 100644 +--- a/net/sched/sch_api.c ++++ b/net/sched/sch_api.c +@@ -1191,7 +1191,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, + rcu_assign_pointer(sch->stab, stab); + } + if (tca[TCA_RATE]) { +- seqcount_t *running; ++ net_seqlock_t *running; + + err = -EOPNOTSUPP; + if (sch->flags & TCQ_F_MQROOT) { +diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c +index 42a776abdf2f..cc4c4309a2b8 100644 +--- a/net/sched/sch_generic.c ++++ b/net/sched/sch_generic.c +@@ -576,7 +576,11 @@ struct Qdisc noop_qdisc = { + .ops = &noop_qdisc_ops, + .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), + .dev_queue = &noop_netdev_queue, ++#ifdef CONFIG_PREEMPT_RT_BASE ++ .running = __SEQLOCK_UNLOCKED(noop_qdisc.running), ++#else + .running = SEQCNT_ZERO(noop_qdisc.running), ++#endif + .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), + .gso_skb = { + .next = (struct sk_buff *)&noop_qdisc.gso_skb, +@@ -877,9 +881,17 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, + lockdep_set_class(&sch->busylock, + dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++ seqlock_init(&sch->running); ++ lockdep_set_class(&sch->running.seqcount, ++ dev->qdisc_running_key ?: &qdisc_running_key); ++ lockdep_set_class(&sch->running.lock, ++ dev->qdisc_running_key ?: &qdisc_running_key); ++#else + seqcount_init(&sch->running); + lockdep_set_class(&sch->running, + dev->qdisc_running_key ?: &qdisc_running_key); ++#endif + + sch->ops = ops; + sch->flags = ops->static_flags; +-- +2.36.1 + diff --git a/debian/patches-rt/0202-net-add-back-the-missing-serialization-in-ip_send_un.patch b/debian/patches-rt/0202-net-add-back-the-missing-serialization-in-ip_send_un.patch new file mode 100644 index 000000000..b6925c62f --- /dev/null +++ b/debian/patches-rt/0202-net-add-back-the-missing-serialization-in-ip_send_un.patch @@ -0,0 +1,99 @@ +From 3254a7bf68224051974bf79f76549e4592e45262 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 31 Aug 2016 17:21:56 +0200 +Subject: [PATCH 202/347] net: add back the missing serialization in + ip_send_unicast_reply() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Some time ago Sami Pietikäinen reported a crash on -RT in +ip_send_unicast_reply() which was later fixed by Nicholas Mc Guire +(v3.12.8-rt11). Later (v3.18.8) the code was reworked and I dropped the +patch. As it turns out it was mistake. +I have reports that the same crash is possible with a similar backtrace. +It seems that vanilla protects access to this_cpu_ptr() via +local_bh_disable(). This does not work the on -RT since we can have +NET_RX and NET_TX running in parallel on the same CPU. +This is brings back the old locks. + +|Unable to handle kernel NULL pointer dereference at virtual address 00000010 +|PC is at __ip_make_skb+0x198/0x3e8 +|[<c04e39d8>] (__ip_make_skb) from [<c04e3ca8>] (ip_push_pending_frames+0x20/0x40) +|[<c04e3ca8>] (ip_push_pending_frames) from [<c04e3ff0>] (ip_send_unicast_reply+0x210/0x22c) +|[<c04e3ff0>] (ip_send_unicast_reply) from [<c04fbb54>] (tcp_v4_send_reset+0x190/0x1c0) +|[<c04fbb54>] (tcp_v4_send_reset) from [<c04fcc1c>] (tcp_v4_do_rcv+0x22c/0x288) +|[<c04fcc1c>] (tcp_v4_do_rcv) from [<c0474364>] (release_sock+0xb4/0x150) +|[<c0474364>] (release_sock) from [<c04ed904>] (tcp_close+0x240/0x454) +|[<c04ed904>] (tcp_close) from [<c0511408>] (inet_release+0x74/0x7c) +|[<c0511408>] (inet_release) from [<c0470728>] (sock_release+0x30/0xb0) +|[<c0470728>] (sock_release) from [<c0470abc>] (sock_close+0x1c/0x24) +|[<c0470abc>] (sock_close) from [<c0115ec4>] (__fput+0xe8/0x20c) +|[<c0115ec4>] (__fput) from [<c0116050>] (____fput+0x18/0x1c) +|[<c0116050>] (____fput) from [<c0058138>] (task_work_run+0xa4/0xb8) +|[<c0058138>] (task_work_run) from [<c0011478>] (do_work_pending+0xd0/0xe4) +|[<c0011478>] (do_work_pending) from [<c000e740>] (work_pending+0xc/0x20) +|Code: e3530001 8a000001 e3a00040 ea000011 (e5973010) + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/ipv4/tcp_ipv4.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c +index 2719c60f285b..8e2db5007f59 100644 +--- a/net/ipv4/tcp_ipv4.c ++++ b/net/ipv4/tcp_ipv4.c +@@ -62,6 +62,7 @@ + #include <linux/init.h> + #include <linux/times.h> + #include <linux/slab.h> ++#include <linux/locallock.h> + + #include <net/net_namespace.h> + #include <net/icmp.h> +@@ -637,6 +638,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) + } + EXPORT_SYMBOL(tcp_v4_send_check); + ++static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); + /* + * This routine will send an RST to the other tcp. + * +@@ -771,6 +773,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) + arg.tos = ip_hdr(skb)->tos; + arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); + local_bh_disable(); ++ local_lock(tcp_sk_lock); + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? +@@ -783,6 +786,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) + ctl_sk->sk_mark = 0; + __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); ++ local_unlock(tcp_sk_lock); + local_bh_enable(); + + #ifdef CONFIG_TCP_MD5SIG +@@ -863,6 +867,7 @@ static void tcp_v4_send_ack(const struct sock *sk, + arg.tos = tos; + arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); + local_bh_disable(); ++ local_lock(tcp_sk_lock); + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? +@@ -874,6 +879,7 @@ static void tcp_v4_send_ack(const struct sock *sk, + + ctl_sk->sk_mark = 0; + __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); ++ local_unlock(tcp_sk_lock); + local_bh_enable(); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0203-net-add-a-lock-around-icmp_sk.patch b/debian/patches-rt/0203-net-add-a-lock-around-icmp_sk.patch new file mode 100644 index 000000000..fa2ad051e --- /dev/null +++ b/debian/patches-rt/0203-net-add-a-lock-around-icmp_sk.patch @@ -0,0 +1,65 @@ +From 95179968fe9e7b7b6484facb14b8ac985cc0d779 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 31 Aug 2016 17:54:09 +0200 +Subject: [PATCH 203/347] net: add a lock around icmp_sk() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +It looks like the this_cpu_ptr() access in icmp_sk() is protected with +local_bh_disable(). To avoid missing serialization in -RT I am adding +here a local lock. No crash has been observed, this is just precaution. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/ipv4/icmp.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c +index fe10a565b7d8..d35719e08aef 100644 +--- a/net/ipv4/icmp.c ++++ b/net/ipv4/icmp.c +@@ -77,6 +77,7 @@ + #include <linux/string.h> + #include <linux/netfilter_ipv4.h> + #include <linux/slab.h> ++#include <linux/locallock.h> + #include <net/snmp.h> + #include <net/ip.h> + #include <net/route.h> +@@ -204,6 +205,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; + * + * On SMP we have one ICMP socket per-cpu. + */ ++static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); ++ + static struct sock *icmp_sk(struct net *net) + { + return *this_cpu_ptr(net->ipv4.icmp_sk); +@@ -214,12 +217,16 @@ static inline struct sock *icmp_xmit_lock(struct net *net) + { + struct sock *sk; + ++ if (!local_trylock(icmp_sk_lock)) ++ return NULL; ++ + sk = icmp_sk(net); + + if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { + /* This can happen if the output path signals a + * dst_link_failure() for an outgoing ICMP packet. + */ ++ local_unlock(icmp_sk_lock); + return NULL; + } + return sk; +@@ -228,6 +235,7 @@ static inline struct sock *icmp_xmit_lock(struct net *net) + static inline void icmp_xmit_unlock(struct sock *sk) + { + spin_unlock(&sk->sk_lock.slock); ++ local_unlock(icmp_sk_lock); + } + + int sysctl_icmp_msgs_per_sec __read_mostly = 1000; +-- +2.36.1 + diff --git a/debian/patches-rt/0204-net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch b/debian/patches-rt/0204-net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch new file mode 100644 index 000000000..5a4aed73f --- /dev/null +++ b/debian/patches-rt/0204-net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch @@ -0,0 +1,77 @@ +From 2faaff72af2ce49a00236dbfe09246e3099229ec Mon Sep 17 00:00:00 2001 +From: Steven Rostedt <rostedt@goodmis.org> +Date: Tue, 6 Dec 2016 17:50:30 -0500 +Subject: [PATCH 204/347] net: Have __napi_schedule_irqoff() disable interrupts + on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +A customer hit a crash where the napi sd->poll_list became corrupted. +The customer had the bnx2x driver, which does a +__napi_schedule_irqoff() in its interrupt handler. Unfortunately, when +running with CONFIG_PREEMPT_RT_FULL, this interrupt handler is run as a +thread and is preemptable. The call to ____napi_schedule() must be done +with interrupts disabled to protect the per cpu softnet_data's +"poll_list, which is protected by disabling interrupts (disabling +preemption is enough when all interrupts are threaded and +local_bh_disable() can't preempt)." + +As bnx2x isn't the only driver that does this, the safest thing to do +is to make __napi_schedule_irqoff() call __napi_schedule() instead when +CONFIG_PREEMPT_RT_FULL is enabled, which will call local_irq_save() +before calling ____napi_schedule(). + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Steven Rostedt (Red Hat) <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/netdevice.h | 12 ++++++++++++ + net/core/dev.c | 2 ++ + 2 files changed, 14 insertions(+) + +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index dfec34087039..c4713217b20e 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -423,7 +423,19 @@ typedef enum rx_handler_result rx_handler_result_t; + typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); + + void __napi_schedule(struct napi_struct *n); ++ ++/* ++ * When PREEMPT_RT_FULL is defined, all device interrupt handlers ++ * run as threads, and they can also be preempted (without PREEMPT_RT ++ * interrupt threads can not be preempted). Which means that calling ++ * __napi_schedule_irqoff() from an interrupt handler can be preempted ++ * and can corrupt the napi->poll_list. ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define __napi_schedule_irqoff(n) __napi_schedule(n) ++#else + void __napi_schedule_irqoff(struct napi_struct *n); ++#endif + + static inline bool napi_disable_pending(struct napi_struct *n) + { +diff --git a/net/core/dev.c b/net/core/dev.c +index 7c59fa4d3ecf..e65dc7a7cc13 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -5953,6 +5953,7 @@ bool napi_schedule_prep(struct napi_struct *n) + } + EXPORT_SYMBOL(napi_schedule_prep); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * __napi_schedule_irqoff - schedule for receive + * @n: entry to schedule +@@ -5971,6 +5972,7 @@ void __napi_schedule_irqoff(struct napi_struct *n) + __napi_schedule(n); + } + EXPORT_SYMBOL(__napi_schedule_irqoff); ++#endif + + bool napi_complete_done(struct napi_struct *n, int work_done) + { +-- +2.36.1 + diff --git a/debian/patches-rt/0205-irqwork-push-most-work-into-softirq-context.patch b/debian/patches-rt/0205-irqwork-push-most-work-into-softirq-context.patch new file mode 100644 index 000000000..964c52d2e --- /dev/null +++ b/debian/patches-rt/0205-irqwork-push-most-work-into-softirq-context.patch @@ -0,0 +1,264 @@ +From c0405a2b67942dd7f8564a25fa5580c8f2774765 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 23 Jun 2015 15:32:51 +0200 +Subject: [PATCH 205/347] irqwork: push most work into softirq context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Initially we defered all irqwork into softirq because we didn't want the +latency spikes if perf or another user was busy and delayed the RT task. +The NOHZ trigger (nohz_full_kick_work) was the first user that did not work +as expected if it did not run in the original irqwork context so we had to +bring it back somehow for it. push_irq_work_func is the second one that +requires this. + +This patch adds the IRQ_WORK_HARD_IRQ which makes sure the callback runs +in raw-irq context. Everything else is defered into softirq context. Without +-RT we have the orignal behavior. + +This patch incorporates tglx orignal work which revoked a little bringing back +the arch_irq_work_raise() if possible and a few fixes from Steven Rostedt and +Mike Galbraith, + +[bigeasy: melt tglx's irq_work_tick_soft() which splits irq_work_tick() into a + hard and soft variant] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/irq_work.h | 8 +++++ + kernel/irq_work.c | 75 ++++++++++++++++++++++++++++++---------- + kernel/rcu/tree.c | 1 + + kernel/sched/topology.c | 1 + + kernel/time/tick-sched.c | 1 + + kernel/time/timer.c | 2 ++ + 6 files changed, 70 insertions(+), 18 deletions(-) + +diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h +index b11fcdfd0770..0c50559987c5 100644 +--- a/include/linux/irq_work.h ++++ b/include/linux/irq_work.h +@@ -18,6 +18,8 @@ + + /* Doesn't want IPI, wait for tick: */ + #define IRQ_WORK_LAZY BIT(2) ++/* Run hard IRQ context, even on RT */ ++#define IRQ_WORK_HARD_IRQ BIT(3) + + #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) + +@@ -52,4 +54,10 @@ static inline bool irq_work_needs_cpu(void) { return false; } + static inline void irq_work_run(void) { } + #endif + ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void); ++#else ++static inline void irq_work_tick_soft(void) { } ++#endif ++ + #endif /* _LINUX_IRQ_WORK_H */ +diff --git a/kernel/irq_work.c b/kernel/irq_work.c +index 73288914ed5e..2940622da5b3 100644 +--- a/kernel/irq_work.c ++++ b/kernel/irq_work.c +@@ -17,6 +17,7 @@ + #include <linux/cpu.h> + #include <linux/notifier.h> + #include <linux/smp.h> ++#include <linux/interrupt.h> + #include <asm/processor.h> + + +@@ -57,29 +58,35 @@ void __weak arch_irq_work_raise(void) + } + + /* Enqueue on current CPU, work must already be claimed and preempt disabled */ +-static void __irq_work_queue_local(struct irq_work *work) ++static void __irq_work_queue_local(struct irq_work *work, struct llist_head *list) + { +- /* If the work is "lazy", handle it from next tick if any */ +- if (work->flags & IRQ_WORK_LAZY) { +- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && +- tick_nohz_tick_stopped()) +- arch_irq_work_raise(); +- } else { +- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) +- arch_irq_work_raise(); +- } ++ bool empty; ++ ++ empty = llist_add(&work->llnode, list); ++ ++ if (empty && ++ (!(work->flags & IRQ_WORK_LAZY) || ++ tick_nohz_tick_stopped())) ++ arch_irq_work_raise(); + } + + /* Enqueue the irq work @work on the current CPU */ + bool irq_work_queue(struct irq_work *work) + { ++ struct llist_head *list; ++ + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; + + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); +- __irq_work_queue_local(work); ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ list = this_cpu_ptr(&lazy_list); ++ else ++ list = this_cpu_ptr(&raised_list); ++ ++ __irq_work_queue_local(work, list); + preempt_enable(); + + return true; +@@ -98,6 +105,9 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) + return irq_work_queue(work); + + #else /* CONFIG_SMP: */ ++ struct llist_head *list; ++ bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); ++ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + +@@ -106,13 +116,21 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) + return false; + + preempt_disable(); ++ ++ lazy_work = work->flags & IRQ_WORK_LAZY; ++ ++ if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) ++ list = &per_cpu(lazy_list, cpu); ++ else ++ list = &per_cpu(raised_list, cpu); ++ + if (cpu != smp_processor_id()) { + /* Arch remote IPI send/receive backend aren't NMI safe */ + WARN_ON_ONCE(in_nmi()); +- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) ++ if (llist_add(&work->llnode, list)) + arch_send_call_function_single_ipi(cpu); + } else { +- __irq_work_queue_local(work); ++ __irq_work_queue_local(work, list); + } + preempt_enable(); + +@@ -128,9 +146,8 @@ bool irq_work_needs_cpu(void) + raised = this_cpu_ptr(&raised_list); + lazy = this_cpu_ptr(&lazy_list); + +- if (llist_empty(raised) || arch_irq_work_has_interrupt()) +- if (llist_empty(lazy)) +- return false; ++ if (llist_empty(raised) && llist_empty(lazy)) ++ return false; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); +@@ -144,8 +161,12 @@ static void irq_work_run_list(struct llist_head *list) + struct llist_node *llnode; + unsigned long flags; + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ /* ++ * nort: On RT IRQ-work may run in SOFTIRQ context. ++ */ + BUG_ON(!irqs_disabled()); +- ++#endif + if (llist_empty(list)) + return; + +@@ -177,7 +198,16 @@ static void irq_work_run_list(struct llist_head *list) + void irq_work_run(void) + { + irq_work_run_list(this_cpu_ptr(&raised_list)); +- irq_work_run_list(this_cpu_ptr(&lazy_list)); ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { ++ /* ++ * NOTE: we raise softirq via IPI for safety, ++ * and execute in irq_work_tick() to move the ++ * overhead from hard to soft irq context. ++ */ ++ if (!llist_empty(this_cpu_ptr(&lazy_list))) ++ raise_softirq(TIMER_SOFTIRQ); ++ } else ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); + } + EXPORT_SYMBOL_GPL(irq_work_run); + +@@ -187,8 +217,17 @@ void irq_work_tick(void) + + if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) + irq_work_run_list(raised); ++ ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); ++} ++ ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void) ++{ + irq_work_run_list(this_cpu_ptr(&lazy_list)); + } ++#endif + + /* + * Synchronize against the irq_work @entry, ensures the entry is not +diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c +index f162a4f54b05..278fe66bfb70 100644 +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -1296,6 +1296,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) + !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && + (rnp->ffmask & rdp->grpmask)) { + init_irq_work(&rdp->rcu_iw, rcu_iw_handler); ++ rdp->rcu_iw.flags = IRQ_WORK_HARD_IRQ; + rdp->rcu_iw_pending = true; + rdp->rcu_iw_gp_seq = rnp->gp_seq; + irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); +diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c +index 02e85cd233d4..208af1181bf5 100644 +--- a/kernel/sched/topology.c ++++ b/kernel/sched/topology.c +@@ -279,6 +279,7 @@ static int init_rootdomain(struct root_domain *rd) + rd->rto_cpu = -1; + raw_spin_lock_init(&rd->rto_lock); + init_irq_work(&rd->rto_push_work, rto_push_irq_work_func); ++ rd->rto_push_work.flags |= IRQ_WORK_HARD_IRQ; + #endif + + init_dl_bw(&rd->dl_bw); +diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c +index 2b0ddd50e879..4d31ec98e968 100644 +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -236,6 +236,7 @@ static void nohz_full_kick_func(struct irq_work *work) + + static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_func, ++ .flags = IRQ_WORK_HARD_IRQ, + }; + + /* +diff --git a/kernel/time/timer.c b/kernel/time/timer.c +index 3cb79167852f..c7bd68db6f63 100644 +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -1747,6 +1747,8 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) + { + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + ++ irq_work_tick_soft(); ++ + __run_timers(base); + if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) + __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); +-- +2.36.1 + diff --git a/debian/patches-rt/0206-printk-Make-rt-aware.patch b/debian/patches-rt/0206-printk-Make-rt-aware.patch new file mode 100644 index 000000000..0ca16f202 --- /dev/null +++ b/debian/patches-rt/0206-printk-Make-rt-aware.patch @@ -0,0 +1,114 @@ +From fe512f6331aa2cda166c08988965010dd06d68e3 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 19 Sep 2012 14:50:37 +0200 +Subject: [PATCH 206/347] printk: Make rt aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Drop the lock before calling the console driver and do not disable +interrupts while printing to a serial console. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/printk/printk.c | 33 ++++++++++++++++++++++++++++++--- + 1 file changed, 30 insertions(+), 3 deletions(-) + +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index 7b774743e1ac..c06b1e00448d 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1654,6 +1654,7 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) + return do_syslog(type, buf, len, SYSLOG_FROM_READER); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Special console_lock variants that help to reduce the risk of soft-lockups. + * They allow to pass console_lock to another printk() call using a busy wait. +@@ -1794,6 +1795,15 @@ static int console_trylock_spinning(void) + return 1; + } + ++#else ++ ++static int console_trylock_spinning(void) ++{ ++ return console_trylock(); ++} ++ ++#endif ++ + /* + * Call the console drivers, asking them to write out + * log_buf[start] to log_buf[end - 1]. +@@ -1809,6 +1819,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, + if (!console_drivers) + return; + ++ migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; +@@ -1824,6 +1835,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, + else + con->write(con, text, len); + } ++ migrate_enable(); + } + + int printk_delay_msec __read_mostly; +@@ -2018,20 +2030,30 @@ asmlinkage int vprintk_emit(int facility, int level, + + /* If called from the scheduler, we can not call up(). */ + if (!in_sched && pending_output) { ++ int may_trylock = 1; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * we can't take a sleeping lock with IRQs or preeption disabled ++ * so we can't print in these contexts ++ */ ++ if (!(preempt_count() == 0 && !irqs_disabled())) ++ may_trylock = 0; ++#endif + /* + * Disable preemption to avoid being preempted while holding + * console_sem which would prevent anyone from printing to + * console + */ +- preempt_disable(); ++ migrate_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up + * /dev/kmsg and syslog() users. + */ +- if (console_trylock_spinning()) ++ if (may_trylock && console_trylock_spinning()) + console_unlock(); +- preempt_enable(); ++ migrate_enable(); + } + + if (pending_output) +@@ -2503,6 +2525,10 @@ void console_unlock(void) + console_seq++; + raw_spin_unlock(&logbuf_lock); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ printk_safe_exit_irqrestore(flags); ++ call_console_drivers(ext_text, ext_len, text, len); ++#else + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to +@@ -2521,6 +2547,7 @@ void console_unlock(void) + } + + printk_safe_exit_irqrestore(flags); ++#endif + + if (do_cond_resched) + cond_resched(); +-- +2.36.1 + diff --git a/debian/patches-rt/0207-kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch b/debian/patches-rt/0207-kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch new file mode 100644 index 000000000..75627e24f --- /dev/null +++ b/debian/patches-rt/0207-kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch @@ -0,0 +1,48 @@ +From 5ff42463701b87deff98424f5417e808d69fd327 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 19 May 2016 17:45:27 +0200 +Subject: [PATCH 207/347] kernel/printk: Don't try to print from IRQ/NMI region +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On -RT we try to acquire sleeping locks which might lead to warnings +from lockdep or a warn_on() from spin_try_lock() (which is a rtmutex on +RT). +We don't print in general from a IRQ off region so we should not try +this via console_unblank() / bust_spinlocks() as well. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/printk/printk.c | 10 ++++++++++ + 1 file changed, 10 insertions(+) + +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index c06b1e00448d..273f2c7864b5 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1819,6 +1819,11 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, + if (!console_drivers) + return; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ + migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) +@@ -2595,6 +2600,11 @@ void console_unblank(void) + { + struct console *c; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. +-- +2.36.1 + diff --git a/debian/patches-rt/0208-printk-Drop-the-logbuf_lock-more-often.patch b/debian/patches-rt/0208-printk-Drop-the-logbuf_lock-more-often.patch new file mode 100644 index 000000000..bc4f44f50 --- /dev/null +++ b/debian/patches-rt/0208-printk-Drop-the-logbuf_lock-more-often.patch @@ -0,0 +1,83 @@ +From b4bf7654e00cd7da0d18577698e25eb199de2d57 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 21 Mar 2013 19:01:05 +0100 +Subject: [PATCH 208/347] printk: Drop the logbuf_lock more often +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The lock is hold with irgs off. The latency drops 500us+ on my arm bugs +with a "full" buffer after executing "dmesg" on the shell. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/printk/printk.c | 28 ++++++++++++++++++++++++++++ + 1 file changed, 28 insertions(+) + +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index 273f2c7864b5..1e0988a0bb97 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1457,12 +1457,23 @@ static int syslog_print_all(char __user *buf, int size, bool clear) + u64 next_seq; + u64 seq; + u32 idx; ++ int attempts = 0; ++ int num_msg; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + logbuf_lock_irq(); ++ ++try_again: ++ attempts++; ++ if (attempts > 10) { ++ len = -EBUSY; ++ goto out; ++ } ++ num_msg = 0; ++ + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. +@@ -1475,6 +1486,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) + len += msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ logbuf_unlock_irq(); ++ logbuf_lock_irq(); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* move first record forward until length fits into the buffer */ +@@ -1486,6 +1505,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) + len -= msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ logbuf_unlock_irq(); ++ logbuf_lock_irq(); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* last message fitting into this dump */ +@@ -1523,6 +1550,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } ++out: + logbuf_unlock_irq(); + + kfree(text); +-- +2.36.1 + diff --git a/debian/patches-rt/0209-ARM-enable-irq-in-translation-section-permission-fau.patch b/debian/patches-rt/0209-ARM-enable-irq-in-translation-section-permission-fau.patch new file mode 100644 index 000000000..58d59fbae --- /dev/null +++ b/debian/patches-rt/0209-ARM-enable-irq-in-translation-section-permission-fau.patch @@ -0,0 +1,96 @@ +From c4bff0275d502012b7673069a3d2da755e67cdfb Mon Sep 17 00:00:00 2001 +From: "Yadi.hu" <yadi.hu@windriver.com> +Date: Wed, 10 Dec 2014 10:32:09 +0800 +Subject: [PATCH 209/347] ARM: enable irq in translation/section permission + fault handlers +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Probably happens on all ARM, with +CONFIG_PREEMPT_RT_FULL +CONFIG_DEBUG_ATOMIC_SLEEP + +This simple program.... + +int main() { + *((char*)0xc0001000) = 0; +}; + +[ 512.742724] BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +[ 512.743000] in_atomic(): 0, irqs_disabled(): 128, pid: 994, name: a +[ 512.743217] INFO: lockdep is turned off. +[ 512.743360] irq event stamp: 0 +[ 512.743482] hardirqs last enabled at (0): [< (null)>] (null) +[ 512.743714] hardirqs last disabled at (0): [<c0426370>] copy_process+0x3b0/0x11c0 +[ 512.744013] softirqs last enabled at (0): [<c0426370>] copy_process+0x3b0/0x11c0 +[ 512.744303] softirqs last disabled at (0): [< (null)>] (null) +[ 512.744631] [<c041872c>] (unwind_backtrace+0x0/0x104) +[ 512.745001] [<c09af0c4>] (dump_stack+0x20/0x24) +[ 512.745355] [<c0462490>] (__might_sleep+0x1dc/0x1e0) +[ 512.745717] [<c09b6770>] (rt_spin_lock+0x34/0x6c) +[ 512.746073] [<c0441bf0>] (do_force_sig_info+0x34/0xf0) +[ 512.746457] [<c0442668>] (force_sig_info+0x18/0x1c) +[ 512.746829] [<c041d880>] (__do_user_fault+0x9c/0xd8) +[ 512.747185] [<c041d938>] (do_bad_area+0x7c/0x94) +[ 512.747536] [<c041d990>] (do_sect_fault+0x40/0x48) +[ 512.747898] [<c040841c>] (do_DataAbort+0x40/0xa0) +[ 512.748181] Exception stack(0xecaa1fb0 to 0xecaa1ff8) + +Oxc0000000 belongs to kernel address space, user task can not be +allowed to access it. For above condition, correct result is that +test case should receive a “segment fault” and exits but not stacks. + +the root cause is commit 02fe2845d6a8 ("avoid enabling interrupts in +prefetch/data abort handlers"),it deletes irq enable block in Data +abort assemble code and move them into page/breakpiont/alignment fault +handlers instead. But author does not enable irq in translation/section +permission fault handlers. ARM disables irq when it enters exception/ +interrupt mode, if kernel doesn't enable irq, it would be still disabled +during translation/section permission fault. + +We see the above splat because do_force_sig_info is still called with +IRQs off, and that code eventually does a: + + spin_lock_irqsave(&t->sighand->siglock, flags); + +As this is architecture independent code, and we've not seen any other +need for other arch to have the siglock converted to raw lock, we can +conclude that we should enable irq for ARM translation/section +permission exception. + + +Signed-off-by: Yadi.hu <yadi.hu@windriver.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/mm/fault.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c +index a9ee0d9dc740..20b0e146de98 100644 +--- a/arch/arm/mm/fault.c ++++ b/arch/arm/mm/fault.c +@@ -439,6 +439,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, + if (addr < TASK_SIZE) + return do_page_fault(addr, fsr, regs); + ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + if (user_mode(regs)) + goto bad_area; + +@@ -506,6 +509,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, + static int + do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) + { ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + do_bad_area(addr, fsr, regs); + return 0; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0210-genirq-update-irq_set_irqchip_state-documentation.patch b/debian/patches-rt/0210-genirq-update-irq_set_irqchip_state-documentation.patch new file mode 100644 index 000000000..587d4cec5 --- /dev/null +++ b/debian/patches-rt/0210-genirq-update-irq_set_irqchip_state-documentation.patch @@ -0,0 +1,32 @@ +From ab960649ff425bcc7910011a0f591a4673e76df6 Mon Sep 17 00:00:00 2001 +From: Josh Cartwright <joshc@ni.com> +Date: Thu, 11 Feb 2016 11:54:00 -0600 +Subject: [PATCH 210/347] genirq: update irq_set_irqchip_state documentation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On -rt kernels, the use of migrate_disable()/migrate_enable() is +sufficient to guarantee a task isn't moved to another CPU. Update the +irq_set_irqchip_state() documentation to reflect this. + +Signed-off-by: Josh Cartwright <joshc@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/irq/manage.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c +index 2bb77b0ebac8..683debac6759 100644 +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -2335,7 +2335,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state); + * This call sets the internal irqchip state of an interrupt, + * depending on the value of @which. + * +- * This function should be called with preemption disabled if the ++ * This function should be called with migration disabled if the + * interrupt controller has per-cpu registers. + */ + int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, +-- +2.36.1 + diff --git a/debian/patches-rt/0211-KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch b/debian/patches-rt/0211-KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch new file mode 100644 index 000000000..a49a4c01e --- /dev/null +++ b/debian/patches-rt/0211-KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch @@ -0,0 +1,59 @@ +From e3788b349ef7d4161dc666a0aca9fc054c913c04 Mon Sep 17 00:00:00 2001 +From: Josh Cartwright <joshc@ni.com> +Date: Thu, 11 Feb 2016 11:54:01 -0600 +Subject: [PATCH 211/347] KVM: arm/arm64: downgrade preempt_disable()d region + to migrate_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +kvm_arch_vcpu_ioctl_run() disables the use of preemption when updating +the vgic and timer states to prevent the calling task from migrating to +another CPU. It does so to prevent the task from writing to the +incorrect per-CPU GIC distributor registers. + +On -rt kernels, it's possible to maintain the same guarantee with the +use of migrate_{disable,enable}(), with the added benefit that the +migrate-disabled region is preemptible. Update +kvm_arch_vcpu_ioctl_run() to do so. + +Cc: Christoffer Dall <christoffer.dall@linaro.org> +Reported-by: Manish Jaggi <Manish.Jaggi@caviumnetworks.com> +Signed-off-by: Josh Cartwright <joshc@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + virt/kvm/arm/arm.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c +index b943ec5345cb..ddc6db1e8cd2 100644 +--- a/virt/kvm/arm/arm.c ++++ b/virt/kvm/arm/arm.c +@@ -725,7 +725,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) + * involves poking the GIC, which must be done in a + * non-preemptible context. + */ +- preempt_disable(); ++ migrate_disable(); + + kvm_pmu_flush_hwstate(vcpu); + +@@ -774,7 +774,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); + local_irq_enable(); +- preempt_enable(); ++ migrate_enable(); + continue; + } + +@@ -852,7 +852,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) + /* Exit types that need handling before we can be preempted */ + handle_exit_early(vcpu, run, ret); + +- preempt_enable(); ++ migrate_enable(); + + ret = handle_exit(vcpu, run, ret); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0212-arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch b/debian/patches-rt/0212-arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch new file mode 100644 index 000000000..5ac88e5fe --- /dev/null +++ b/debian/patches-rt/0212-arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch @@ -0,0 +1,171 @@ +From e6eac38976a1eebb792eb6a02fd95ed0868576fc Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 25 Jul 2018 14:02:38 +0200 +Subject: [PATCH 212/347] arm64: fpsimd: use preemp_disable in addition to + local_bh_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In v4.16-RT I noticed a number of warnings from task_fpsimd_load(). The +code disables BH and expects that it is not preemptible. On -RT the +task remains preemptible but remains the same CPU. This may corrupt the +content of the SIMD registers if the task is preempted during +saving/restoring those registers. + +Add preempt_disable()/enable() to enfore the required semantic on -RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm64/kernel/fpsimd.c | 31 +++++++++++++++++++++++++++++-- + 1 file changed, 29 insertions(+), 2 deletions(-) + +diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c +index 89ab68cb35bb..481793a5adc1 100644 +--- a/arch/arm64/kernel/fpsimd.c ++++ b/arch/arm64/kernel/fpsimd.c +@@ -159,6 +159,16 @@ static void sve_free(struct task_struct *task) + __sve_free(task); + } + ++static void *sve_free_atomic(struct task_struct *task) ++{ ++ void *sve_state = task->thread.sve_state; ++ ++ WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); ++ ++ task->thread.sve_state = NULL; ++ return sve_state; ++} ++ + /* + * TIF_SVE controls whether a task can use SVE without trapping while + * in userspace, and also the way a task's FPSIMD/SVE state is stored +@@ -549,6 +559,7 @@ int sve_set_vector_length(struct task_struct *task, + * non-SVE thread. + */ + if (task == current) { ++ preempt_disable(); + local_bh_disable(); + + fpsimd_save(); +@@ -559,8 +570,10 @@ int sve_set_vector_length(struct task_struct *task, + if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + sve_to_fpsimd(task); + +- if (task == current) ++ if (task == current) { + local_bh_enable(); ++ preempt_enable(); ++ } + + /* + * Force reallocation of task SVE state to the correct size +@@ -815,6 +828,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) + + sve_alloc(current); + ++ preempt_disable(); + local_bh_disable(); + + fpsimd_save(); +@@ -828,6 +842,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) + WARN_ON(1); /* SVE access shouldn't have trapped */ + + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -894,10 +909,12 @@ void fpsimd_thread_switch(struct task_struct *next) + void fpsimd_flush_thread(void) + { + int vl, supported_vl; ++ void *mem = NULL; + + if (!system_supports_fpsimd()) + return; + ++ preempt_disable(); + local_bh_disable(); + + memset(¤t->thread.uw.fpsimd_state, 0, +@@ -906,7 +923,7 @@ void fpsimd_flush_thread(void) + + if (system_supports_sve()) { + clear_thread_flag(TIF_SVE); +- sve_free(current); ++ mem = sve_free_atomic(current); + + /* + * Reset the task vector length as required. +@@ -942,6 +959,8 @@ void fpsimd_flush_thread(void) + set_thread_flag(TIF_FOREIGN_FPSTATE); + + local_bh_enable(); ++ preempt_enable(); ++ kfree(mem); + } + + /* +@@ -953,9 +972,11 @@ void fpsimd_preserve_current_state(void) + if (!system_supports_fpsimd()) + return; + ++ preempt_disable(); + local_bh_disable(); + fpsimd_save(); + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -1026,6 +1047,7 @@ void fpsimd_restore_current_state(void) + return; + } + ++ preempt_disable(); + local_bh_disable(); + + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { +@@ -1034,6 +1056,7 @@ void fpsimd_restore_current_state(void) + } + + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -1046,6 +1069,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) + if (WARN_ON(!system_supports_fpsimd())) + return; + ++ preempt_disable(); + local_bh_disable(); + + current->thread.uw.fpsimd_state = *state; +@@ -1058,6 +1082,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) + clear_thread_flag(TIF_FOREIGN_FPSTATE); + + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -1104,6 +1129,7 @@ void kernel_neon_begin(void) + + BUG_ON(!may_use_simd()); + ++ preempt_disable(); + local_bh_disable(); + + __this_cpu_write(kernel_neon_busy, true); +@@ -1117,6 +1143,7 @@ void kernel_neon_begin(void) + preempt_disable(); + + local_bh_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(kernel_neon_begin); + +-- +2.36.1 + diff --git a/debian/patches-rt/0213-kgdb-serial-Short-term-workaround.patch b/debian/patches-rt/0213-kgdb-serial-Short-term-workaround.patch new file mode 100644 index 000000000..464f4b0d7 --- /dev/null +++ b/debian/patches-rt/0213-kgdb-serial-Short-term-workaround.patch @@ -0,0 +1,86 @@ +From 63a68f078dbbdde2ffc3a7cb2928cef6b17a38a3 Mon Sep 17 00:00:00 2001 +From: Jason Wessel <jason.wessel@windriver.com> +Date: Thu, 28 Jul 2011 12:42:23 -0500 +Subject: [PATCH 213/347] kgdb/serial: Short term workaround +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On 07/27/2011 04:37 PM, Thomas Gleixner wrote: +> - KGDB (not yet disabled) is reportedly unusable on -rt right now due +> to missing hacks in the console locking which I dropped on purpose. +> + +To work around this in the short term you can use this patch, in +addition to the clocksource watchdog patch that Thomas brewed up. + +Comments are welcome of course. Ultimately the right solution is to +change separation between the console and the HW to have a polled mode ++ work queue so as not to introduce any kind of latency. + +Thanks, +Jason. +--- + drivers/tty/serial/8250/8250_port.c | 3 +++ + include/linux/kdb.h | 2 ++ + kernel/debug/kdb/kdb_io.c | 2 ++ + 3 files changed, 7 insertions(+) + +diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c +index ef8bccc0823c..418b9c818b2e 100644 +--- a/drivers/tty/serial/8250/8250_port.c ++++ b/drivers/tty/serial/8250/8250_port.c +@@ -31,6 +31,7 @@ + #include <linux/nmi.h> + #include <linux/mutex.h> + #include <linux/slab.h> ++#include <linux/kdb.h> + #include <linux/uaccess.h> + #include <linux/pm_runtime.h> + #include <linux/ktime.h> +@@ -3296,6 +3297,8 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, + + if (port->sysrq || oops_in_progress) + locked = 0; ++ else if (in_kdb_printk()) ++ locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); + +diff --git a/include/linux/kdb.h b/include/linux/kdb.h +index 68bd88223417..e033b25b0b72 100644 +--- a/include/linux/kdb.h ++++ b/include/linux/kdb.h +@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt, + extern __printf(1, 2) int kdb_printf(const char *, ...); + typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); + ++#define in_kdb_printk() (kdb_trap_printk) + extern void kdb_init(int level); + + /* Access to kdb specific polling devices */ +@@ -201,6 +202,7 @@ extern int kdb_register_flags(char *, kdb_func_t, char *, char *, + extern int kdb_unregister(char *); + #else /* ! CONFIG_KGDB_KDB */ + static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } ++#define in_kdb_printk() (0) + static inline void kdb_init(int level) {} + static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, + char *help, short minlen) { return 0; } +diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c +index b45576ca3b0d..ad1a3bc7908f 100644 +--- a/kernel/debug/kdb/kdb_io.c ++++ b/kernel/debug/kdb/kdb_io.c +@@ -861,9 +861,11 @@ int kdb_printf(const char *fmt, ...) + va_list ap; + int r; + ++ kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); + va_end(ap); ++ kdb_trap_printk--; + + return r; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0214-sysfs-Add-sys-kernel-realtime-entry.patch b/debian/patches-rt/0214-sysfs-Add-sys-kernel-realtime-entry.patch new file mode 100644 index 000000000..b477086ae --- /dev/null +++ b/debian/patches-rt/0214-sysfs-Add-sys-kernel-realtime-entry.patch @@ -0,0 +1,54 @@ +From c48c3a32632d4b467e3609a87b4149f9136afff6 Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Sat, 30 Jul 2011 21:55:53 -0500 +Subject: [PATCH 214/347] sysfs: Add /sys/kernel/realtime entry +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Add a /sys/kernel entry to indicate that the kernel is a +realtime kernel. + +Clark says that he needs this for udev rules, udev needs to evaluate +if its a PREEMPT_RT kernel a few thousand times and parsing uname +output is too slow or so. + +Are there better solutions? Should it exist and return 0 on !-rt? + +Signed-off-by: Clark Williams <williams@redhat.com> +Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> +--- + kernel/ksysfs.c | 12 ++++++++++++ + 1 file changed, 12 insertions(+) + +diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c +index 46ba853656f6..9a23632b6294 100644 +--- a/kernel/ksysfs.c ++++ b/kernel/ksysfs.c +@@ -140,6 +140,15 @@ KERNEL_ATTR_RO(vmcoreinfo); + + #endif /* CONFIG_CRASH_CORE */ + ++#if defined(CONFIG_PREEMPT_RT_FULL) ++static ssize_t realtime_show(struct kobject *kobj, ++ struct kobj_attribute *attr, char *buf) ++{ ++ return sprintf(buf, "%d\n", 1); ++} ++KERNEL_ATTR_RO(realtime); ++#endif ++ + /* whether file capabilities are enabled */ + static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +@@ -230,6 +239,9 @@ static struct attribute * kernel_attrs[] = { + #ifndef CONFIG_TINY_RCU + &rcu_expedited_attr.attr, + &rcu_normal_attr.attr, ++#endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ &realtime_attr.attr, + #endif + NULL + }; +-- +2.36.1 + diff --git a/debian/patches-rt/0215-mm-rt-kmap_atomic-scheduling.patch b/debian/patches-rt/0215-mm-rt-kmap_atomic-scheduling.patch new file mode 100644 index 000000000..fe9e29581 --- /dev/null +++ b/debian/patches-rt/0215-mm-rt-kmap_atomic-scheduling.patch @@ -0,0 +1,325 @@ +From 6ffc40164236bf03b6c7c3c8dc826f5f96d8d797 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Thu, 28 Jul 2011 10:43:51 +0200 +Subject: [PATCH 215/347] mm, rt: kmap_atomic scheduling +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In fact, with migrate_disable() existing one could play games with +kmap_atomic. You could save/restore the kmap_atomic slots on context +switch (if there are any in use of course), this should be esp easy now +that we have a kmap_atomic stack. + +Something like the below.. it wants replacing all the preempt_disable() +stuff with pagefault_disable() && migrate_disable() of course, but then +you can flip kmaps around like below. + +Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> +[dvhart@linux.intel.com: build fix] +Link: http://lkml.kernel.org/r/1311842631.5890.208.camel@twins + +[tglx@linutronix.de: Get rid of the per cpu variable and store the idx + and the pte content right away in the task struct. + Shortens the context switch code. ] +--- + arch/x86/kernel/process_32.c | 32 ++++++++++++++++++++++++++++++++ + arch/x86/mm/highmem_32.c | 13 ++++++++++--- + arch/x86/mm/iomap_32.c | 9 ++++++++- + include/linux/highmem.h | 31 +++++++++++++++++++++++++------ + include/linux/sched.h | 7 +++++++ + include/linux/uaccess.h | 2 ++ + mm/highmem.c | 6 ++++-- + 7 files changed, 88 insertions(+), 12 deletions(-) + +diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c +index 020efe0f9614..5d0c975559ad 100644 +--- a/arch/x86/kernel/process_32.c ++++ b/arch/x86/kernel/process_32.c +@@ -38,6 +38,7 @@ + #include <linux/io.h> + #include <linux/kdebug.h> + #include <linux/syscalls.h> ++#include <linux/highmem.h> + + #include <asm/pgtable.h> + #include <asm/ldt.h> +@@ -205,6 +206,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) + } + EXPORT_SYMBOL_GPL(start_thread); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ pte_t *ptep = kmap_pte - idx; ++ ++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); ++ } ++} ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + + /* + * switch_to(x,y) should switch tasks from x to y. +@@ -274,6 +304,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) + + switch_to_extra(prev_p, next_p); + ++ switch_kmaps(prev_p, next_p); ++ + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so +diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c +index 6d18b70ed5a9..f752724c22e8 100644 +--- a/arch/x86/mm/highmem_32.c ++++ b/arch/x86/mm/highmem_32.c +@@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap); + */ + void *kmap_atomic_prot(struct page *page, pgprot_t prot) + { ++ pte_t pte = mk_pte(page, prot); + unsigned long vaddr; + int idx, type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + + if (!PageHighMem(page)) +@@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + BUG_ON(!pte_none(*(kmap_pte-idx))); +- set_pte(kmap_pte-idx, mk_pte(page, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte-idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -88,6 +92,9 @@ void __kunmap_atomic(void *kvaddr) + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + arch_flush_lazy_mmu_mode(); +@@ -100,7 +107,7 @@ void __kunmap_atomic(void *kvaddr) + #endif + + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c +index b3294d36769d..d5a48210d0f6 100644 +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -59,6 +59,7 @@ EXPORT_SYMBOL_GPL(iomap_free); + + void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + { ++ pte_t pte = pfn_pte(pfn, prot); + unsigned long vaddr; + int idx, type; + +@@ -68,7 +69,10 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +- set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte - idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -119,6 +123,9 @@ iounmap_atomic(void __iomem *kvaddr) + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + } +diff --git a/include/linux/highmem.h b/include/linux/highmem.h +index 0690679832d4..1ac89e4718bf 100644 +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -66,7 +66,7 @@ static inline void kunmap(struct page *page) + + static inline void *kmap_atomic(struct page *page) + { +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + return page_address(page); + } +@@ -75,7 +75,7 @@ static inline void *kmap_atomic(struct page *page) + static inline void __kunmap_atomic(void *addr) + { + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + + #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) +@@ -87,32 +87,51 @@ static inline void __kunmap_atomic(void *addr) + + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + ++#ifndef CONFIG_PREEMPT_RT_FULL + DECLARE_PER_CPU(int, __kmap_atomic_idx); ++#endif + + static inline int kmap_atomic_idx_push(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; + +-#ifdef CONFIG_DEBUG_HIGHMEM ++# ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(in_irq() && !irqs_disabled()); + BUG_ON(idx >= KM_TYPE_NR); +-#endif ++# endif + return idx; ++#else ++ current->kmap_idx++; ++ BUG_ON(current->kmap_idx > KM_TYPE_NR); ++ return current->kmap_idx - 1; ++#endif + } + + static inline int kmap_atomic_idx(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + return __this_cpu_read(__kmap_atomic_idx) - 1; ++#else ++ return current->kmap_idx - 1; ++#endif + } + + static inline void kmap_atomic_idx_pop(void) + { +-#ifdef CONFIG_DEBUG_HIGHMEM ++#ifndef CONFIG_PREEMPT_RT_FULL ++# ifdef CONFIG_DEBUG_HIGHMEM + int idx = __this_cpu_dec_return(__kmap_atomic_idx); + + BUG_ON(idx < 0); +-#else ++# else + __this_cpu_dec(__kmap_atomic_idx); ++# endif ++#else ++ current->kmap_idx--; ++# ifdef CONFIG_DEBUG_HIGHMEM ++ BUG_ON(current->kmap_idx < 0); ++# endif + #endif + } + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index b7a357635d60..577045ae8693 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -28,6 +28,7 @@ + #include <linux/mm_types_task.h> + #include <linux/task_io_accounting.h> + #include <linux/rseq.h> ++#include <asm/kmap_types.h> + + /* task_struct member predeclarations (sorted alphabetically): */ + struct audit_context; +@@ -1216,6 +1217,12 @@ struct task_struct { + int softirq_nestcnt; + unsigned int softirqs_raised; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 ++ int kmap_idx; ++ pte_t kmap_pte[KM_TYPE_NR]; ++# endif ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif +diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h +index db9b0dd0a7a3..e151bd0f6d49 100644 +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -185,6 +185,7 @@ static __always_inline void pagefault_disabled_dec(void) + */ + static inline void pagefault_disable(void) + { ++ migrate_disable(); + pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault +@@ -201,6 +202,7 @@ static inline void pagefault_enable(void) + */ + barrier(); + pagefault_disabled_dec(); ++ migrate_enable(); + } + + /* +diff --git a/mm/highmem.c b/mm/highmem.c +index 59db3223a5d6..22aa3ddbd87b 100644 +--- a/mm/highmem.c ++++ b/mm/highmem.c +@@ -30,10 +30,11 @@ + #include <linux/kgdb.h> + #include <asm/tlbflush.h> + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + DEFINE_PER_CPU(int, __kmap_atomic_idx); + #endif ++#endif + + /* + * Virtual_count is not a pure "count". +@@ -108,8 +109,9 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color) + unsigned long totalhigh_pages __read_mostly; + EXPORT_SYMBOL(totalhigh_pages); + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); ++#endif + + unsigned int nr_free_highpages (void) + { +-- +2.36.1 + diff --git a/debian/patches-rt/0216-x86-highmem-Add-a-already-used-pte-check.patch b/debian/patches-rt/0216-x86-highmem-Add-a-already-used-pte-check.patch new file mode 100644 index 000000000..1ed131e93 --- /dev/null +++ b/debian/patches-rt/0216-x86-highmem-Add-a-already-used-pte-check.patch @@ -0,0 +1,29 @@ +From 0aa2a1e54dccb65560925aedd34406b867f182ce Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 11 Mar 2013 17:09:55 +0100 +Subject: [PATCH 216/347] x86/highmem: Add a "already used pte" check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +This is a copy from kmap_atomic_prot(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/mm/iomap_32.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c +index d5a48210d0f6..c0ec8d430c02 100644 +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -69,6 +69,8 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); ++ WARN_ON(!pte_none(*(kmap_pte - idx))); ++ + #ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; + #endif +-- +2.36.1 + diff --git a/debian/patches-rt/0217-arm-highmem-Flush-tlb-on-unmap.patch b/debian/patches-rt/0217-arm-highmem-Flush-tlb-on-unmap.patch new file mode 100644 index 000000000..12a3a9b1e --- /dev/null +++ b/debian/patches-rt/0217-arm-highmem-Flush-tlb-on-unmap.patch @@ -0,0 +1,34 @@ +From 83b4c6d1975b6bbcc60751fc7150c6bda6b460a7 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 11 Mar 2013 21:37:27 +0100 +Subject: [PATCH 217/347] arm/highmem: Flush tlb on unmap +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The tlb should be flushed on unmap and thus make the mapping entry +invalid. This is only done in the non-debug case which does not look +right. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/arm/mm/highmem.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c +index d02f8187b1cc..eb4b225d28c9 100644 +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -112,10 +112,10 @@ void __kunmap_atomic(void *kvaddr) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); +- set_fixmap_pte(idx, __pte(0)); + #else + (void) idx; /* to kill a warning */ + #endif ++ set_fixmap_pte(idx, __pte(0)); + kmap_atomic_idx_pop(); + } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { + /* this address was obtained through kmap_high_get() */ +-- +2.36.1 + diff --git a/debian/patches-rt/0218-arm-Enable-highmem-for-rt.patch b/debian/patches-rt/0218-arm-Enable-highmem-for-rt.patch new file mode 100644 index 000000000..6d37c0670 --- /dev/null +++ b/debian/patches-rt/0218-arm-Enable-highmem-for-rt.patch @@ -0,0 +1,184 @@ +From d8647f71379a704607e15bb3a7fd5d84b3f10a6d Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 13 Feb 2013 11:03:11 +0100 +Subject: [PATCH 218/347] arm: Enable highmem for rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +fixup highmem for ARM. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm/include/asm/switch_to.h | 8 +++++ + arch/arm/mm/highmem.c | 56 +++++++++++++++++++++++++++----- + include/linux/highmem.h | 1 + + 3 files changed, 57 insertions(+), 8 deletions(-) + +diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h +index d3e937dcee4d..6ab96a2ce1f8 100644 +--- a/arch/arm/include/asm/switch_to.h ++++ b/arch/arm/include/asm/switch_to.h +@@ -4,6 +4,13 @@ + + #include <linux/thread_info.h> + ++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb +@@ -26,6 +33,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info + #define switch_to(prev,next,last) \ + do { \ + __complete_pending_tlbi(); \ ++ switch_kmaps(prev, next); \ + last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ + } while (0) + +diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c +index eb4b225d28c9..542692dbd40a 100644 +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr) + return *ptep; + } + ++static unsigned int fixmap_idx(int type) ++{ ++ return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++} ++ + void *kmap(struct page *page) + { + might_sleep(); +@@ -54,12 +59,13 @@ EXPORT_SYMBOL(kunmap); + + void *kmap_atomic(struct page *page) + { ++ pte_t pte = mk_pte(page, kmap_prot); + unsigned int idx; + unsigned long vaddr; + void *kmap; + int type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -79,7 +85,7 @@ void *kmap_atomic(struct page *page) + + type = kmap_atomic_idx_push(); + +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + vaddr = __fix_to_virt(idx); + #ifdef CONFIG_DEBUG_HIGHMEM + /* +@@ -93,7 +99,10 @@ void *kmap_atomic(struct page *page) + * in place, so the contained TLB flush ensures the TLB is updated + * with the new mapping. + */ +- set_fixmap_pte(idx, mk_pte(page, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -106,10 +115,13 @@ void __kunmap_atomic(void *kvaddr) + + if (kvaddr >= (void *)FIXADDR_START) { + type = kmap_atomic_idx(); +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + + if (cache_is_vivt()) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); + #else +@@ -122,28 +134,56 @@ void __kunmap_atomic(void *kvaddr) + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); + } + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + + void *kmap_atomic_pfn(unsigned long pfn) + { ++ pte_t pte = pfn_pte(pfn, kmap_prot); + unsigned long vaddr; + int idx, type; + struct page *page = pfn_to_page(pfn); + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + + type = kmap_atomic_idx_push(); +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + vaddr = __fix_to_virt(idx); + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); + #endif +- set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } ++#if defined CONFIG_PREEMPT_RT_FULL ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = fixmap_idx(i); ++ ++ set_fixmap_pte(idx, __pte(0)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = fixmap_idx(i); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_fixmap_pte(idx, next_p->kmap_pte[i]); ++ } ++} ++#endif +diff --git a/include/linux/highmem.h b/include/linux/highmem.h +index 1ac89e4718bf..eaa2ef9bc10e 100644 +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -8,6 +8,7 @@ + #include <linux/mm.h> + #include <linux/uaccess.h> + #include <linux/hardirq.h> ++#include <linux/sched.h> + + #include <asm/cacheflush.h> + +-- +2.36.1 + diff --git a/debian/patches-rt/0219-scsi-fcoe-Make-RT-aware.patch b/debian/patches-rt/0219-scsi-fcoe-Make-RT-aware.patch new file mode 100644 index 000000000..e64e58af6 --- /dev/null +++ b/debian/patches-rt/0219-scsi-fcoe-Make-RT-aware.patch @@ -0,0 +1,116 @@ +From de388c8a89d8d509914406a15bb839cc95b1eb06 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sat, 12 Nov 2011 14:00:48 +0100 +Subject: [PATCH 219/347] scsi/fcoe: Make RT aware. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Do not disable preemption while taking sleeping locks. All user look safe +for migrate_diable() only. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/scsi/fcoe/fcoe.c | 16 ++++++++-------- + drivers/scsi/fcoe/fcoe_ctlr.c | 4 ++-- + drivers/scsi/libfc/fc_exch.c | 4 ++-- + 3 files changed, 12 insertions(+), 12 deletions(-) + +diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c +index 6768b2e8148a..c20f51af6bdf 100644 +--- a/drivers/scsi/fcoe/fcoe.c ++++ b/drivers/scsi/fcoe/fcoe.c +@@ -1459,11 +1459,11 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev, + static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) + { + struct fcoe_percpu_s *fps; +- int rc; ++ int rc, cpu = get_cpu_light(); + +- fps = &get_cpu_var(fcoe_percpu); ++ fps = &per_cpu(fcoe_percpu, cpu); + rc = fcoe_get_paged_crc_eof(skb, tlen, fps); +- put_cpu_var(fcoe_percpu); ++ put_cpu_light(); + + return rc; + } +@@ -1650,11 +1650,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport, + return 0; + } + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + stats->InvalidCRCCount++; + if (stats->InvalidCRCCount < 5) + printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); +- put_cpu(); ++ put_cpu_light(); + return -EINVAL; + } + +@@ -1697,7 +1697,7 @@ static void fcoe_recv_frame(struct sk_buff *skb) + */ + hp = (struct fcoe_hdr *) skb_network_header(skb); + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { + if (stats->ErrorFrames < 5) + printk(KERN_WARNING "fcoe: FCoE version " +@@ -1729,13 +1729,13 @@ static void fcoe_recv_frame(struct sk_buff *skb) + goto drop; + + if (!fcoe_filter_frames(lport, fp)) { +- put_cpu(); ++ put_cpu_light(); + fc_exch_recv(lport, fp); + return; + } + drop: + stats->ErrorFrames++; +- put_cpu(); ++ put_cpu_light(); + kfree_skb(skb); + } + +diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c +index 658c0726581f..bceab74eecf7 100644 +--- a/drivers/scsi/fcoe/fcoe_ctlr.c ++++ b/drivers/scsi/fcoe/fcoe_ctlr.c +@@ -838,7 +838,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) + + INIT_LIST_HEAD(&del_list); + +- stats = per_cpu_ptr(fip->lp->stats, get_cpu()); ++ stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); + + list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { + deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; +@@ -874,7 +874,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) + sel_time = fcf->time; + } + } +- put_cpu(); ++ put_cpu_light(); + + list_for_each_entry_safe(fcf, next, &del_list, list) { + /* Removes fcf from current list */ +diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c +index 9fa0aa235cb4..ed538164320a 100644 +--- a/drivers/scsi/libfc/fc_exch.c ++++ b/drivers/scsi/libfc/fc_exch.c +@@ -833,10 +833,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport, + } + memset(ep, 0, sizeof(*ep)); + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = per_cpu_ptr(mp->pool, cpu); + spin_lock_bh(&pool->lock); +- put_cpu(); ++ put_cpu_light(); + + /* peek cache of free slot */ + if (pool->left != FC_XID_UNKNOWN) { +-- +2.36.1 + diff --git a/debian/patches-rt/0220-x86-crypto-Reduce-preempt-disabled-regions.patch b/debian/patches-rt/0220-x86-crypto-Reduce-preempt-disabled-regions.patch new file mode 100644 index 000000000..eeb0ae4e6 --- /dev/null +++ b/debian/patches-rt/0220-x86-crypto-Reduce-preempt-disabled-regions.patch @@ -0,0 +1,118 @@ +From 795856da132e0e41e6ba20d6020b7016f23159cf Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Mon, 14 Nov 2011 18:19:27 +0100 +Subject: [PATCH 220/347] x86: crypto: Reduce preempt disabled regions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Restrict the preempt disabled regions to the actual floating point +operations and enable preemption for the administrative actions. + +This is necessary on RT to avoid that kfree and other operations are +called with preemption disabled. + +Reported-and-tested-by: Carsten Emde <cbe@osadl.org> +Signed-off-by: Peter Zijlstra <peterz@infradead.org> + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/crypto/aesni-intel_glue.c | 22 ++++++++++++---------- + 1 file changed, 12 insertions(+), 10 deletions(-) + +diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c +index 917f25e4d0a8..58d8c03fc32d 100644 +--- a/arch/x86/crypto/aesni-intel_glue.c ++++ b/arch/x86/crypto/aesni-intel_glue.c +@@ -434,14 +434,14 @@ static int ecb_encrypt(struct skcipher_request *req) + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -456,14 +456,14 @@ static int ecb_decrypt(struct skcipher_request *req) + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -478,14 +478,14 @@ static int cbc_encrypt(struct skcipher_request *req) + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -500,14 +500,14 @@ static int cbc_decrypt(struct skcipher_request *req) + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -557,18 +557,20 @@ static int ctr_crypt(struct skcipher_request *req) + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { ++ kernel_fpu_begin(); + aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } + if (walk.nbytes) { ++ kernel_fpu_begin(); + ctr_crypt_final(ctx, &walk); ++ kernel_fpu_end(); + err = skcipher_walk_done(&walk, 0); + } +- kernel_fpu_end(); + + return err; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0221-crypto-Reduce-preempt-disabled-regions-more-algos.patch b/debian/patches-rt/0221-crypto-Reduce-preempt-disabled-regions-more-algos.patch new file mode 100644 index 000000000..ed1ebcb6d --- /dev/null +++ b/debian/patches-rt/0221-crypto-Reduce-preempt-disabled-regions-more-algos.patch @@ -0,0 +1,263 @@ +From ae835a4684737b3c2efebe8bcbb5e0348eefa1eb Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 21 Feb 2014 17:24:04 +0100 +Subject: [PATCH 221/347] crypto: Reduce preempt disabled regions, more algos +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Don Estabrook reported +| kernel: WARNING: CPU: 2 PID: 858 at kernel/sched/core.c:2428 migrate_disable+0xed/0x100() +| kernel: WARNING: CPU: 2 PID: 858 at kernel/sched/core.c:2462 migrate_enable+0x17b/0x200() +| kernel: WARNING: CPU: 3 PID: 865 at kernel/sched/core.c:2428 migrate_disable+0xed/0x100() + +and his backtrace showed some crypto functions which looked fine. + +The problem is the following sequence: + +glue_xts_crypt_128bit() +{ + blkcipher_walk_virt(); /* normal migrate_disable() */ + + glue_fpu_begin(); /* get atomic */ + + while (nbytes) { + __glue_xts_crypt_128bit(); + blkcipher_walk_done(); /* with nbytes = 0, migrate_enable() + * while we are atomic */ + }; + glue_fpu_end() /* no longer atomic */ +} + +and this is why the counter get out of sync and the warning is printed. +The other problem is that we are non-preemptible between +glue_fpu_begin() and glue_fpu_end() and the latency grows. To fix this, +I shorten the FPU off region and ensure blkcipher_walk_done() is called +with preemption enabled. This might hurt the performance because we now +enable/disable the FPU state more often but we gain lower latency and +the bug is gone. + + +Reported-by: Don Estabrook <don.estabrook@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/crypto/cast5_avx_glue.c | 21 +++++++++------------ + arch/x86/crypto/glue_helper.c | 31 ++++++++++++++++--------------- + 2 files changed, 25 insertions(+), 27 deletions(-) + +diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c +index 41034745d6a2..d4bf7fc02ee7 100644 +--- a/arch/x86/crypto/cast5_avx_glue.c ++++ b/arch/x86/crypto/cast5_avx_glue.c +@@ -61,7 +61,7 @@ static inline void cast5_fpu_end(bool fpu_enabled) + + static int ecb_crypt(struct skcipher_request *req, bool enc) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; +@@ -76,7 +76,7 @@ static int ecb_crypt(struct skcipher_request *req, bool enc) + u8 *wsrc = walk.src.virt.addr; + u8 *wdst = walk.dst.virt.addr; + +- fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); + + /* Process multi-block batch */ + if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { +@@ -105,10 +105,9 @@ static int ecb_crypt(struct skcipher_request *req, bool enc) + } while (nbytes >= bsize); + + done: ++ cast5_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -212,7 +211,7 @@ static int cbc_decrypt(struct skcipher_request *req) + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct skcipher_walk walk; + unsigned int nbytes; + int err; +@@ -220,12 +219,11 @@ static int cbc_decrypt(struct skcipher_request *req) + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes)) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); + nbytes = __cbc_decrypt(ctx, &walk); ++ cast5_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -292,7 +290,7 @@ static int ctr_crypt(struct skcipher_request *req) + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct skcipher_walk walk; + unsigned int nbytes; + int err; +@@ -300,13 +298,12 @@ static int ctr_crypt(struct skcipher_request *req) + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); + nbytes = __ctr_crypt(&walk, ctx); ++ cast5_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } + +- cast5_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + ctr_crypt_final(&walk, ctx); + err = skcipher_walk_done(&walk, 0); +diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c +index a78ef99a9981..dac489a1c4da 100644 +--- a/arch/x86/crypto/glue_helper.c ++++ b/arch/x86/crypto/glue_helper.c +@@ -38,7 +38,7 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -51,7 +51,7 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, + unsigned int i; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, nbytes); ++ &walk, false, nbytes); + for (i = 0; i < gctx->num_funcs; i++) { + func_bytes = bsize * gctx->funcs[i].num_blocks; + +@@ -69,10 +69,9 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, + if (nbytes < bsize) + break; + } ++ glue_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } +- +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_ecb_req_128bit); +@@ -115,7 +114,7 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -129,7 +128,7 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, + u128 last_iv; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, nbytes); ++ &walk, false, nbytes); + /* Start of the last block. */ + src += nbytes / bsize - 1; + dst += nbytes / bsize - 1; +@@ -161,10 +160,10 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, + done: + u128_xor(dst, dst, (u128 *)walk.iv); + *(u128 *)walk.iv = last_iv; ++ glue_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit); +@@ -175,7 +174,7 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -189,7 +188,7 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, + le128 ctrblk; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, nbytes); ++ &walk, false, nbytes); + + be128_to_le128(&ctrblk, (be128 *)walk.iv); + +@@ -213,11 +212,10 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, + } + + le128_to_be128((be128 *)walk.iv, &ctrblk); ++ glue_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); +- + if (nbytes) { + le128 ctrblk; + u128 tmp; +@@ -278,7 +276,7 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx, + { + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -289,21 +287,24 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx, + + /* set minimum length to bsize, for tweak_fn */ + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, ++ &walk, false, + nbytes < bsize ? bsize : nbytes); + + /* calculate first value of T */ + tweak_fn(tweak_ctx, walk.iv, walk.iv); + + while (nbytes) { ++ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, ++ &walk, fpu_enabled, ++ nbytes < bsize ? bsize : nbytes); + nbytes = __glue_xts_req_128bit(gctx, crypt_ctx, &walk); + ++ glue_fpu_end(fpu_enabled); ++ fpu_enabled = false; + err = skcipher_walk_done(&walk, nbytes); + nbytes = walk.nbytes; + } + +- glue_fpu_end(fpu_enabled); +- + return err; + } + EXPORT_SYMBOL_GPL(glue_xts_req_128bit); +-- +2.36.1 + diff --git a/debian/patches-rt/0222-crypto-limit-more-FPU-enabled-sections.patch b/debian/patches-rt/0222-crypto-limit-more-FPU-enabled-sections.patch new file mode 100644 index 000000000..e615a446d --- /dev/null +++ b/debian/patches-rt/0222-crypto-limit-more-FPU-enabled-sections.patch @@ -0,0 +1,108 @@ +From 8e09b2bca6f9a8364bba581fb391a85b500095bb Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 30 Nov 2017 13:40:10 +0100 +Subject: [PATCH 222/347] crypto: limit more FPU-enabled sections +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Those crypto drivers use SSE/AVX/… for their crypto work and in order to +do so in kernel they need to enable the "FPU" in kernel mode which +disables preemption. +There are two problems with the way they are used: +- the while loop which processes X bytes may create latency spikes and + should be avoided or limited. +- the cipher-walk-next part may allocate/free memory and may use + kmap_atomic(). + +The whole kernel_fpu_begin()/end() processing isn't probably that cheap. +It most likely makes sense to process as much of those as possible in one +go. The new *_fpu_sched_rt() schedules only if a RT task is pending. + +Probably we should measure the performance those ciphers in pure SW +mode and with this optimisations to see if it makes sense to keep them +for RT. + +This kernel_fpu_resched() makes the code more preemptible which might hurt +performance. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/crypto/chacha20_glue.c | 9 +++++---- + arch/x86/include/asm/fpu/api.h | 1 + + arch/x86/kernel/fpu/core.c | 12 ++++++++++++ + 3 files changed, 18 insertions(+), 4 deletions(-) + +diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c +index dce7c5d39c2f..6194160b7fbc 100644 +--- a/arch/x86/crypto/chacha20_glue.c ++++ b/arch/x86/crypto/chacha20_glue.c +@@ -81,23 +81,24 @@ static int chacha20_simd(struct skcipher_request *req) + + crypto_chacha20_init(state, ctx, walk.iv); + +- kernel_fpu_begin(); +- + while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { ++ kernel_fpu_begin(); ++ + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); ++ kernel_fpu_end(); + err = skcipher_walk_done(&walk, + walk.nbytes % CHACHA20_BLOCK_SIZE); + } + + if (walk.nbytes) { ++ kernel_fpu_begin(); + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes); ++ kernel_fpu_end(); + err = skcipher_walk_done(&walk, 0); + } + +- kernel_fpu_end(); +- + return err; + } + +diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h +index b56d504af654..e51c7094075d 100644 +--- a/arch/x86/include/asm/fpu/api.h ++++ b/arch/x86/include/asm/fpu/api.h +@@ -20,6 +20,7 @@ + */ + extern void kernel_fpu_begin(void); + extern void kernel_fpu_end(void); ++extern void kernel_fpu_resched(void); + extern bool irq_fpu_usable(void); + + /* +diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c +index 2e5003fef51a..768c53767bb2 100644 +--- a/arch/x86/kernel/fpu/core.c ++++ b/arch/x86/kernel/fpu/core.c +@@ -136,6 +136,18 @@ void kernel_fpu_end(void) + } + EXPORT_SYMBOL_GPL(kernel_fpu_end); + ++void kernel_fpu_resched(void) ++{ ++ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); ++ ++ if (should_resched(PREEMPT_OFFSET)) { ++ kernel_fpu_end(); ++ cond_resched(); ++ kernel_fpu_begin(); ++ } ++} ++EXPORT_SYMBOL_GPL(kernel_fpu_resched); ++ + /* + * Save the FPU state (mark it for reload if necessary): + * +-- +2.36.1 + diff --git a/debian/patches-rt/0223-crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch b/debian/patches-rt/0223-crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch new file mode 100644 index 000000000..e7be12f3f --- /dev/null +++ b/debian/patches-rt/0223-crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch @@ -0,0 +1,83 @@ +From fe05a8e53c2f5560f734ab76a4527bab302e88c0 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <efault@gmx.de> +Date: Wed, 11 Jul 2018 17:14:47 +0200 +Subject: [PATCH 223/347] crypto: scompress - serialize RT percpu scratch + buffer access with a local lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +| BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:974 +| in_atomic(): 1, irqs_disabled(): 0, pid: 1401, name: cryptomgr_test +| Preemption disabled at: +| [<ffff00000849941c>] scomp_acomp_comp_decomp+0x34/0x1a0 +| CPU: 21 PID: 1401 Comm: cryptomgr_test Tainted: G W 4.16.18-rt9-rt #1 +| Hardware name: www.cavium.com crb-1s/crb-1s, BIOS 0.3 Apr 25 2017 +| Call trace: +| dump_backtrace+0x0/0x1c8 +| show_stack+0x24/0x30 +| dump_stack+0xac/0xe8 +| ___might_sleep+0x124/0x188 +| rt_spin_lock+0x40/0x88 +| zip_load_instr+0x44/0x170 [thunderx_zip] +| zip_deflate+0x184/0x378 [thunderx_zip] +| zip_compress+0xb0/0x130 [thunderx_zip] +| zip_scomp_compress+0x48/0x60 [thunderx_zip] +| scomp_acomp_comp_decomp+0xd8/0x1a0 +| scomp_acomp_compress+0x24/0x30 +| test_acomp+0x15c/0x558 +| alg_test_comp+0xc0/0x128 +| alg_test.part.6+0x120/0x2c0 +| alg_test+0x6c/0xa0 +| cryptomgr_test+0x50/0x58 +| kthread+0x134/0x138 +| ret_from_fork+0x10/0x18 + +Mainline disables preemption to serialize percpu scratch buffer access, +causing the splat above. Serialize with a local lock for RT instead. + +Signed-off-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + crypto/scompress.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/crypto/scompress.c b/crypto/scompress.c +index 968bbcf65c94..c2f0077e0801 100644 +--- a/crypto/scompress.c ++++ b/crypto/scompress.c +@@ -24,6 +24,7 @@ + #include <linux/cryptouser.h> + #include <net/netlink.h> + #include <linux/scatterlist.h> ++#include <linux/locallock.h> + #include <crypto/scatterwalk.h> + #include <crypto/internal/acompress.h> + #include <crypto/internal/scompress.h> +@@ -34,6 +35,7 @@ static void * __percpu *scomp_src_scratches; + static void * __percpu *scomp_dst_scratches; + static int scomp_scratch_users; + static DEFINE_MUTEX(scomp_lock); ++static DEFINE_LOCAL_IRQ_LOCK(scomp_scratches_lock); + + #ifdef CONFIG_NET + static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg) +@@ -146,7 +148,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) + void **tfm_ctx = acomp_tfm_ctx(tfm); + struct crypto_scomp *scomp = *tfm_ctx; + void **ctx = acomp_request_ctx(req); +- const int cpu = get_cpu(); ++ const int cpu = local_lock_cpu(scomp_scratches_lock); + u8 *scratch_src = *per_cpu_ptr(scomp_src_scratches, cpu); + u8 *scratch_dst = *per_cpu_ptr(scomp_dst_scratches, cpu); + int ret; +@@ -181,7 +183,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) + 1); + } + out: +- put_cpu(); ++ local_unlock_cpu(scomp_scratches_lock); + return ret; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0224-crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch b/debian/patches-rt/0224-crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch new file mode 100644 index 000000000..85f584f79 --- /dev/null +++ b/debian/patches-rt/0224-crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch @@ -0,0 +1,85 @@ +From 7a1d28b6b70837f1554c28799195274823fc1e72 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 26 Jul 2018 18:52:00 +0200 +Subject: [PATCH 224/347] crypto: cryptd - add a lock instead + preempt_disable/local_bh_disable +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +cryptd has a per-CPU lock which protected with local_bh_disable() and +preempt_disable(). +Add an explicit spin_lock to make the locking context more obvious and +visible to lockdep. Since it is a per-CPU lock, there should be no lock +contention on the actual spinlock. +There is a small race-window where we could be migrated to another CPU +after the cpu_queue has been obtain. This is not a problem because the +actual ressource is protected by the spinlock. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + crypto/cryptd.c | 19 +++++++++---------- + 1 file changed, 9 insertions(+), 10 deletions(-) + +diff --git a/crypto/cryptd.c b/crypto/cryptd.c +index e0c8e907b086..e079f9a70201 100644 +--- a/crypto/cryptd.c ++++ b/crypto/cryptd.c +@@ -39,6 +39,7 @@ MODULE_PARM_DESC(cryptd_max_cpu_qlen, "Set cryptd Max queue depth"); + struct cryptd_cpu_queue { + struct crypto_queue queue; + struct work_struct work; ++ spinlock_t qlock; + }; + + struct cryptd_queue { +@@ -117,6 +118,7 @@ static int cryptd_init_queue(struct cryptd_queue *queue, + cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu); + crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); + INIT_WORK(&cpu_queue->work, cryptd_queue_worker); ++ spin_lock_init(&cpu_queue->qlock); + } + pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen); + return 0; +@@ -141,8 +143,10 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue, + struct cryptd_cpu_queue *cpu_queue; + atomic_t *refcnt; + +- cpu = get_cpu(); +- cpu_queue = this_cpu_ptr(queue->cpu_queue); ++ cpu_queue = raw_cpu_ptr(queue->cpu_queue); ++ spin_lock_bh(&cpu_queue->qlock); ++ cpu = smp_processor_id(); ++ + err = crypto_enqueue_request(&cpu_queue->queue, request); + + refcnt = crypto_tfm_ctx(request->tfm); +@@ -158,7 +162,7 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue, + atomic_inc(refcnt); + + out_put_cpu: +- put_cpu(); ++ spin_unlock_bh(&cpu_queue->qlock); + + return err; + } +@@ -174,16 +178,11 @@ static void cryptd_queue_worker(struct work_struct *work) + cpu_queue = container_of(work, struct cryptd_cpu_queue, work); + /* + * Only handle one request at a time to avoid hogging crypto workqueue. +- * preempt_disable/enable is used to prevent being preempted by +- * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent +- * cryptd_enqueue_request() being accessed from software interrupts. + */ +- local_bh_disable(); +- preempt_disable(); ++ spin_lock_bh(&cpu_queue->qlock); + backlog = crypto_get_backlog(&cpu_queue->queue); + req = crypto_dequeue_request(&cpu_queue->queue); +- preempt_enable(); +- local_bh_enable(); ++ spin_unlock_bh(&cpu_queue->qlock); + + if (!req) + return; +-- +2.36.1 + diff --git a/debian/patches-rt/0225-panic-skip-get_random_bytes-for-RT_FULL-in-init_oops.patch b/debian/patches-rt/0225-panic-skip-get_random_bytes-for-RT_FULL-in-init_oops.patch new file mode 100644 index 000000000..855ce6928 --- /dev/null +++ b/debian/patches-rt/0225-panic-skip-get_random_bytes-for-RT_FULL-in-init_oops.patch @@ -0,0 +1,34 @@ +From bc8c16173e79b830e1fb430fc0169dd04b8bbee8 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: [PATCH 225/347] panic: skip get_random_bytes for RT_FULL in + init_oops_id +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Disable on -RT. If this is invoked from irq-context we will have problems +to acquire the sleeping lock. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/panic.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/kernel/panic.c b/kernel/panic.c +index 8138a676fb7d..fa114be5c30f 100644 +--- a/kernel/panic.c ++++ b/kernel/panic.c +@@ -480,9 +480,11 @@ static u64 oops_id; + + static int init_oops_id(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + else ++#endif + oops_id++; + + return 0; +-- +2.36.1 + diff --git a/debian/patches-rt/0226-x86-stackprotector-Avoid-random-pool-on-rt.patch b/debian/patches-rt/0226-x86-stackprotector-Avoid-random-pool-on-rt.patch new file mode 100644 index 000000000..f9db1d99d --- /dev/null +++ b/debian/patches-rt/0226-x86-stackprotector-Avoid-random-pool-on-rt.patch @@ -0,0 +1,51 @@ +From b70b05c554fb10c5bccff5b27a1d5ed73d054313 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 16 Dec 2010 14:25:18 +0100 +Subject: [PATCH 226/347] x86: stackprotector: Avoid random pool on rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +CPU bringup calls into the random pool to initialize the stack +canary. During boot that works nicely even on RT as the might sleep +checks are disabled. During CPU hotplug the might sleep checks +trigger. Making the locks in random raw is a major PITA, so avoid the +call on RT is the only sensible solution. This is basically the same +randomness which we get during boot where the random pool has no +entropy and we rely on the TSC randomnness. + +Reported-by: Carsten Emde <carsten.emde@osadl.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/include/asm/stackprotector.h | 8 +++++++- + 1 file changed, 7 insertions(+), 1 deletion(-) + +diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h +index 9c556ea2eaa7..b136992beb1b 100644 +--- a/arch/x86/include/asm/stackprotector.h ++++ b/arch/x86/include/asm/stackprotector.h +@@ -65,7 +65,7 @@ + */ + static __always_inline void boot_init_stack_canary(void) + { +- u64 canary; ++ u64 uninitialized_var(canary); + u64 tsc; + + #ifdef CONFIG_X86_64 +@@ -76,8 +76,14 @@ static __always_inline void boot_init_stack_canary(void) + * of randomness. The TSC only matters for very early init, + * there it already has some randomness on most systems. Later + * on during the bootup the random pool has true entropy too. ++ * For preempt-rt we need to weaken the randomness a bit, as ++ * we can't call into the random generator from atomic context ++ * due to locking constraints. We just leave canary ++ * uninitialized and use the TSC based randomness on top of it. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + get_random_bytes(&canary, sizeof(canary)); ++#endif + tsc = rdtsc(); + canary += tsc + (tsc << 32UL); + canary &= CANARY_MASK; +-- +2.36.1 + diff --git a/debian/patches-rt/0228-cpu-hotplug-Implement-CPU-pinning.patch b/debian/patches-rt/0228-cpu-hotplug-Implement-CPU-pinning.patch new file mode 100644 index 000000000..9a3b2430f --- /dev/null +++ b/debian/patches-rt/0228-cpu-hotplug-Implement-CPU-pinning.patch @@ -0,0 +1,117 @@ +From 784e4a9806842dc64aa0902210fe4e11984d868a Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 19 Jul 2017 17:31:20 +0200 +Subject: [PATCH 228/347] cpu/hotplug: Implement CPU pinning +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/sched.h | 1 + + kernel/cpu.c | 38 ++++++++++++++++++++++++++++++++++++++ + 2 files changed, 39 insertions(+) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 577045ae8693..7523c0786a63 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -671,6 +671,7 @@ struct task_struct { + #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int migrate_disable; + int migrate_disable_update; ++ int pinned_on_cpu; + # ifdef CONFIG_SCHED_DEBUG + int migrate_disable_atomic; + # endif +diff --git a/kernel/cpu.c b/kernel/cpu.c +index 89a96cc14b39..797216a0b4c6 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -77,6 +77,11 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, + }; + ++#ifdef CONFIG_HOTPLUG_CPU ++static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \ ++ __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock); ++#endif ++ + #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) + static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +@@ -288,7 +293,28 @@ static int cpu_hotplug_disabled; + */ + void pin_current_cpu(void) + { ++ struct rt_rw_lock *cpuhp_pin; ++ unsigned int cpu; ++ int ret; ++ ++again: ++ cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); ++ ret = __read_rt_trylock(cpuhp_pin); ++ if (ret) { ++ current->pinned_on_cpu = smp_processor_id(); ++ return; ++ } ++ cpu = smp_processor_id(); ++ preempt_enable(); ++ ++ __read_rt_lock(cpuhp_pin); + ++ preempt_disable(); ++ if (cpu != smp_processor_id()) { ++ __read_rt_unlock(cpuhp_pin); ++ goto again; ++ } ++ current->pinned_on_cpu = cpu; + } + + /** +@@ -296,6 +322,13 @@ void pin_current_cpu(void) + */ + void unpin_current_cpu(void) + { ++ struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); ++ ++ if (WARN_ON(current->pinned_on_cpu != smp_processor_id())) ++ cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, current->pinned_on_cpu); ++ ++ current->pinned_on_cpu = -1; ++ __read_rt_unlock(cpuhp_pin); + } + + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); +@@ -920,6 +953,7 @@ static int take_cpu_down(void *_param) + + static int takedown_cpu(unsigned int cpu) + { ++ struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu); + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; + +@@ -932,11 +966,14 @@ static int takedown_cpu(unsigned int cpu) + */ + irq_lock_sparse(); + ++ __write_rt_lock(cpuhp_pin); ++ + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ + err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); + if (err) { ++ __write_rt_unlock(cpuhp_pin); + /* CPU refused to die */ + irq_unlock_sparse(); + /* Unpark the hotplug thread so we can rollback there */ +@@ -955,6 +992,7 @@ static int takedown_cpu(unsigned int cpu) + wait_for_ap_thread(st, false); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); + ++ __write_rt_unlock(cpuhp_pin); + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); + +-- +2.36.1 + diff --git a/debian/patches-rt/0229-sched-Allow-pinned-user-tasks-to-be-awakened-to-the-.patch b/debian/patches-rt/0229-sched-Allow-pinned-user-tasks-to-be-awakened-to-the-.patch new file mode 100644 index 000000000..2c10d0def --- /dev/null +++ b/debian/patches-rt/0229-sched-Allow-pinned-user-tasks-to-be-awakened-to-the-.patch @@ -0,0 +1,39 @@ +From 1e7afdc27ed9146e30dc69cdc8fcdc2ce334430e Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <efault@gmx.de> +Date: Sun, 19 Aug 2018 08:28:35 +0200 +Subject: [PATCH 229/347] sched: Allow pinned user tasks to be awakened to the + CPU they pinned +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Since commit 7af443ee16976 ("sched/core: Require cpu_active() in +select_task_rq(), for user tasks") select_fallback_rq() will BUG() if +the CPU to which a task has pinned itself and pinned becomes +!cpu_active() while it slept. +The task will continue running on the to-be-removed CPU and will remove +itself from the CPU during takedown_cpu() (while cpuhp_pin_lock will be +acquired) and move to another CPU based on its mask after the +migrate_disable() section has been left. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/core.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 11afaa2c618a..dba425296275 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -904,7 +904,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + +- if (is_per_cpu_kthread(p)) ++ if (is_per_cpu_kthread(p) || __migrate_disabled(p)) + return cpu_online(cpu); + + return cpu_active(cpu); +-- +2.36.1 + diff --git a/debian/patches-rt/0230-hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch b/debian/patches-rt/0230-hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch new file mode 100644 index 000000000..f60b81343 --- /dev/null +++ b/debian/patches-rt/0230-hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch @@ -0,0 +1,102 @@ +From 3ed5cb0e7f86a61b58b20f64a79148a2a80dac29 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 4 Aug 2017 18:31:00 +0200 +Subject: [PATCH 230/347] hotplug: duct-tape RT-rwlock usage for non-RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +This type is only available on -RT. We need to craft something for +non-RT. Since the only migrate_disable() user is -RT only, there is no +damage. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/cpu.c | 14 +++++++++++++- + 1 file changed, 13 insertions(+), 1 deletion(-) + +diff --git a/kernel/cpu.c b/kernel/cpu.c +index 797216a0b4c6..f6511c62c9a4 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -77,7 +77,7 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, + }; + +-#ifdef CONFIG_HOTPLUG_CPU ++#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PREEMPT_RT_FULL) + static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \ + __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock); + #endif +@@ -293,6 +293,7 @@ static int cpu_hotplug_disabled; + */ + void pin_current_cpu(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin; + unsigned int cpu; + int ret; +@@ -315,6 +316,7 @@ void pin_current_cpu(void) + goto again; + } + current->pinned_on_cpu = cpu; ++#endif + } + + /** +@@ -322,6 +324,7 @@ void pin_current_cpu(void) + */ + void unpin_current_cpu(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); + + if (WARN_ON(current->pinned_on_cpu != smp_processor_id())) +@@ -329,6 +332,7 @@ void unpin_current_cpu(void) + + current->pinned_on_cpu = -1; + __read_rt_unlock(cpuhp_pin); ++#endif + } + + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); +@@ -953,7 +957,9 @@ static int take_cpu_down(void *_param) + + static int takedown_cpu(unsigned int cpu) + { ++#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu); ++#endif + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; + +@@ -966,14 +972,18 @@ static int takedown_cpu(unsigned int cpu) + */ + irq_lock_sparse(); + ++#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_lock(cpuhp_pin); ++#endif + + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ + err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); + if (err) { ++#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_unlock(cpuhp_pin); ++#endif + /* CPU refused to die */ + irq_unlock_sparse(); + /* Unpark the hotplug thread so we can rollback there */ +@@ -992,7 +1002,9 @@ static int takedown_cpu(unsigned int cpu) + wait_for_ap_thread(st, false); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); + ++#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_unlock(cpuhp_pin); ++#endif + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); + +-- +2.36.1 + diff --git a/debian/patches-rt/0231-net-Remove-preemption-disabling-in-netif_rx.patch b/debian/patches-rt/0231-net-Remove-preemption-disabling-in-netif_rx.patch new file mode 100644 index 000000000..5575db994 --- /dev/null +++ b/debian/patches-rt/0231-net-Remove-preemption-disabling-in-netif_rx.patch @@ -0,0 +1,71 @@ +From 455243ba6a0787a8a8ed109e5af4e0cb42d90fbf Mon Sep 17 00:00:00 2001 +From: Priyanka Jain <Priyanka.Jain@freescale.com> +Date: Thu, 17 May 2012 09:35:11 +0530 +Subject: [PATCH 231/347] net: Remove preemption disabling in netif_rx() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +1)enqueue_to_backlog() (called from netif_rx) should be + bind to a particluar CPU. This can be achieved by + disabling migration. No need to disable preemption + +2)Fixes crash "BUG: scheduling while atomic: ksoftirqd" + in case of RT. + If preemption is disabled, enqueue_to_backog() is called + in atomic context. And if backlog exceeds its count, + kfree_skb() is called. But in RT, kfree_skb() might + gets scheduled out, so it expects non atomic context. + +3)When CONFIG_PREEMPT_RT_FULL is not defined, + migrate_enable(), migrate_disable() maps to + preempt_enable() and preempt_disable(), so no + change in functionality in case of non-RT. + +-Replace preempt_enable(), preempt_disable() with + migrate_enable(), migrate_disable() respectively +-Replace get_cpu(), put_cpu() with get_cpu_light(), + put_cpu_light() respectively + +Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com> +Acked-by: Rajan Srivastava <Rajan.Srivastava@freescale.com> +Cc: <rostedt@goodmis.orgn> +Link: http://lkml.kernel.org/r/1337227511-2271-1-git-send-email-Priyanka.Jain@freescale.com + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + net/core/dev.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/core/dev.c b/net/core/dev.c +index e65dc7a7cc13..3df1fe052863 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -4494,7 +4494,7 @@ static int netif_rx_internal(struct sk_buff *skb) + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + +- preempt_disable(); ++ migrate_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); +@@ -4504,14 +4504,14 @@ static int netif_rx_internal(struct sk_buff *skb) + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); +- preempt_enable(); ++ migrate_enable(); + } else + #endif + { + unsigned int qtail; + +- ret = enqueue_to_backlog(skb, get_cpu(), &qtail); +- put_cpu(); ++ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); ++ put_cpu_light(); + } + return ret; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0232-net-Another-local_irq_disable-kmalloc-headache.patch b/debian/patches-rt/0232-net-Another-local_irq_disable-kmalloc-headache.patch new file mode 100644 index 000000000..374593ebd --- /dev/null +++ b/debian/patches-rt/0232-net-Another-local_irq_disable-kmalloc-headache.patch @@ -0,0 +1,65 @@ +From b83d94e087c52b96575acd87c8ecaff00a418d02 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 26 Sep 2012 16:21:08 +0200 +Subject: [PATCH 232/347] net: Another local_irq_disable/kmalloc headache +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Replace it by a local lock. Though that's pretty inefficient :( + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + net/core/skbuff.c | 10 ++++++---- + 1 file changed, 6 insertions(+), 4 deletions(-) + +diff --git a/net/core/skbuff.c b/net/core/skbuff.c +index c623c129d0ab..0696d3cb809d 100644 +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -63,6 +63,7 @@ + #include <linux/errqueue.h> + #include <linux/prefetch.h> + #include <linux/if_vlan.h> ++#include <linux/locallock.h> + + #include <net/protocol.h> + #include <net/dst.h> +@@ -330,6 +331,7 @@ struct napi_alloc_cache { + + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); ++static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); + + static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +@@ -337,10 +339,10 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + unsigned long flags; + void *data; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc(nc, fragsz, gfp_mask); +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + return data; + } + +@@ -416,13 +418,13 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + + nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc(nc, len, gfp_mask); + pfmemalloc = nc->pfmemalloc; + +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + + if (unlikely(!data)) + return NULL; +-- +2.36.1 + diff --git a/debian/patches-rt/0233-net-core-protect-users-of-napi_alloc_cache-against-r.patch b/debian/patches-rt/0233-net-core-protect-users-of-napi_alloc_cache-against-r.patch new file mode 100644 index 000000000..58878036d --- /dev/null +++ b/debian/patches-rt/0233-net-core-protect-users-of-napi_alloc_cache-against-r.patch @@ -0,0 +1,115 @@ +From e8e3e8f9d02d605ac0820c51015b248d4c4a0873 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 15 Jan 2016 16:33:34 +0100 +Subject: [PATCH 233/347] net/core: protect users of napi_alloc_cache against + reentrance +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On -RT the code running in BH can not be moved to another CPU so CPU +local variable remain local. However the code can be preempted +and another task may enter BH accessing the same CPU using the same +napi_alloc_cache variable. +This patch ensures that each user of napi_alloc_cache uses a local lock. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + net/core/skbuff.c | 23 ++++++++++++++++++----- + 1 file changed, 18 insertions(+), 5 deletions(-) + +diff --git a/net/core/skbuff.c b/net/core/skbuff.c +index 0696d3cb809d..58f78205585c 100644 +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -332,6 +332,7 @@ struct napi_alloc_cache { + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); + static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); ++static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock); + + static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +@@ -363,9 +364,13 @@ EXPORT_SYMBOL(netdev_alloc_frag); + + static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; ++ void *data; + +- return page_frag_alloc(&nc->page, fragsz, gfp_mask); ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ data = page_frag_alloc(&nc->page, fragsz, gfp_mask); ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ return data; + } + + void *napi_alloc_frag(unsigned int fragsz) +@@ -468,6 +473,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + struct napi_alloc_cache *nc; + struct sk_buff *skb; + void *data; ++ bool pfmemalloc; + + len += NET_SKB_PAD + NET_IP_ALIGN; + +@@ -490,7 +496,10 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + data = page_frag_alloc(&nc->page, len, gfp_mask); ++ pfmemalloc = nc->page.pfmemalloc; ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + if (unlikely(!data)) + return NULL; + +@@ -501,7 +510,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + } + + /* use OR instead of assignment to avoid clearing of bits in mask */ +- if (nc->page.pfmemalloc) ++ if (pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +@@ -733,23 +742,26 @@ void __consume_stateless_skb(struct sk_buff *skb) + + void __kfree_skb_flush(void) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + /* flush skb_cache if containing objects */ + if (nc->skb_count) { + kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, + nc->skb_cache); + nc->skb_count = 0; + } ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + } + + static inline void _kfree_skb_defer(struct sk_buff *skb) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; + + /* drop skb->head and call any destructors for packet */ + skb_release_all(skb); + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + /* record skb to CPU local list */ + nc->skb_cache[nc->skb_count++] = skb; + +@@ -764,6 +776,7 @@ static inline void _kfree_skb_defer(struct sk_buff *skb) + nc->skb_cache); + nc->skb_count = 0; + } ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + } + void __kfree_skb_defer(struct sk_buff *skb) + { +-- +2.36.1 + diff --git a/debian/patches-rt/0234-net-netfilter-Serialize-xt_write_recseq-sections-on-.patch b/debian/patches-rt/0234-net-netfilter-Serialize-xt_write_recseq-sections-on-.patch new file mode 100644 index 000000000..615fae013 --- /dev/null +++ b/debian/patches-rt/0234-net-netfilter-Serialize-xt_write_recseq-sections-on-.patch @@ -0,0 +1,84 @@ +From 1eb35887a41aa67c6e796dc4f7097e1b08c82a38 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Sun, 28 Oct 2012 11:18:08 +0100 +Subject: [PATCH 234/347] net: netfilter: Serialize xt_write_recseq sections on + RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The netfilter code relies only on the implicit semantics of +local_bh_disable() for serializing wt_write_recseq sections. RT breaks +that and needs explicit serialization here. + +Reported-by: Peter LaDow <petela@gocougs.wsu.edu> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/netfilter/x_tables.h | 7 +++++++ + net/netfilter/core.c | 6 ++++++ + 2 files changed, 13 insertions(+) + +diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h +index 0ade4d1e4dd9..3e21ce64ce54 100644 +--- a/include/linux/netfilter/x_tables.h ++++ b/include/linux/netfilter/x_tables.h +@@ -6,6 +6,7 @@ + #include <linux/netdevice.h> + #include <linux/static_key.h> + #include <linux/netfilter.h> ++#include <linux/locallock.h> + #include <uapi/linux/netfilter/x_tables.h> + + /* Test a struct->invflags and a boolean for inequality */ +@@ -345,6 +346,8 @@ void xt_free_table_info(struct xt_table_info *info); + */ + DECLARE_PER_CPU(seqcount_t, xt_recseq); + ++DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); ++ + /* xt_tee_enabled - true if x_tables needs to handle reentrancy + * + * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. +@@ -365,6 +368,9 @@ static inline unsigned int xt_write_recseq_begin(void) + { + unsigned int addend; + ++ /* RT protection */ ++ local_lock(xt_write_lock); ++ + /* + * Low order bit of sequence is set if we already + * called xt_write_recseq_begin(). +@@ -395,6 +401,7 @@ static inline void xt_write_recseq_end(unsigned int addend) + /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ + smp_wmb(); + __this_cpu_add(xt_recseq.sequence, addend); ++ local_unlock(xt_write_lock); + } + + /* +diff --git a/net/netfilter/core.c b/net/netfilter/core.c +index 722d1b057f61..5b8ebd8abcb0 100644 +--- a/net/netfilter/core.c ++++ b/net/netfilter/core.c +@@ -20,6 +20,7 @@ + #include <linux/inetdevice.h> + #include <linux/proc_fs.h> + #include <linux/mutex.h> ++#include <linux/locallock.h> + #include <linux/mm.h> + #include <linux/rcupdate.h> + #include <net/net_namespace.h> +@@ -27,6 +28,11 @@ + + #include "nf_internals.h" + ++#ifdef CONFIG_PREEMPT_RT_BASE ++DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); ++EXPORT_PER_CPU_SYMBOL(xt_write_lock); ++#endif ++ + const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; + EXPORT_SYMBOL_GPL(nf_ipv6_ops); + +-- +2.36.1 + diff --git a/debian/patches-rt/0235-lockdep-selftest-Only-do-hardirq-context-test-for-ra.patch b/debian/patches-rt/0235-lockdep-selftest-Only-do-hardirq-context-test-for-ra.patch new file mode 100644 index 000000000..4b7bc1086 --- /dev/null +++ b/debian/patches-rt/0235-lockdep-selftest-Only-do-hardirq-context-test-for-ra.patch @@ -0,0 +1,62 @@ +From 8e7150c0542da06cffef7097a59911e86fbfe15e Mon Sep 17 00:00:00 2001 +From: Yong Zhang <yong.zhang@windriver.com> +Date: Mon, 16 Apr 2012 15:01:56 +0800 +Subject: [PATCH 235/347] lockdep: selftest: Only do hardirq context test for + raw spinlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +On -rt there is no softirq context any more and rwlock is sleepable, +disable softirq context test and rwlock+irq test. + +Signed-off-by: Yong Zhang <yong.zhang0@gmail.com> +Cc: Yong Zhang <yong.zhang@windriver.com> +Link: http://lkml.kernel.org/r/1334559716-18447-3-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + lib/locking-selftest.c | 23 +++++++++++++++++++++++ + 1 file changed, 23 insertions(+) + +diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c +index 1e1bbf171eca..5cdf3809905e 100644 +--- a/lib/locking-selftest.c ++++ b/lib/locking-selftest.c +@@ -2057,6 +2057,7 @@ void locking_selftest(void) + + printk(" --------------------------------------------------------------------------\n"); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * irq-context testcases: + */ +@@ -2069,6 +2070,28 @@ void locking_selftest(void) + + DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); + // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); ++#else ++ /* On -rt, we only do hardirq context test for raw spinlock */ ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); ++#endif + + ww_tests(); + +-- +2.36.1 + diff --git a/debian/patches-rt/0236-lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch b/debian/patches-rt/0236-lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch new file mode 100644 index 000000000..35eb70ae6 --- /dev/null +++ b/debian/patches-rt/0236-lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch @@ -0,0 +1,149 @@ +From 8ad69a9f55b91025e0c0db41575ffe79d52fdb7b Mon Sep 17 00:00:00 2001 +From: Josh Cartwright <josh.cartwright@ni.com> +Date: Wed, 28 Jan 2015 13:08:45 -0600 +Subject: [PATCH 236/347] lockdep: selftest: fix warnings due to missing + PREEMPT_RT conditionals +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +"lockdep: Selftest: Only do hardirq context test for raw spinlock" +disabled the execution of certain tests with PREEMPT_RT_FULL, but did +not prevent the tests from still being defined. This leads to warnings +like: + + ./linux/lib/locking-selftest.c:574:1: warning: 'irqsafe1_hard_rlock_12' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:574:1: warning: 'irqsafe1_hard_rlock_21' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:577:1: warning: 'irqsafe1_hard_wlock_12' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:577:1: warning: 'irqsafe1_hard_wlock_21' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:580:1: warning: 'irqsafe1_soft_spin_12' defined but not used [-Wunused-function] + ... + +Fixed by wrapping the test definitions in #ifndef CONFIG_PREEMPT_RT_FULL +conditionals. + + +Signed-off-by: Josh Cartwright <josh.cartwright@ni.com> +Signed-off-by: Xander Huff <xander.huff@ni.com> +Acked-by: Gratian Crisan <gratian.crisan@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + lib/locking-selftest.c | 27 +++++++++++++++++++++++++++ + 1 file changed, 27 insertions(+) + +diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c +index 5cdf3809905e..32db9532ddd4 100644 +--- a/lib/locking-selftest.c ++++ b/lib/locking-selftest.c +@@ -742,6 +742,8 @@ GENERATE_TESTCASE(init_held_rtmutex); + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) + +@@ -757,9 +759,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock) + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Enabling hardirqs with a softirq-safe lock held: + */ +@@ -792,6 +797,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) + #undef E1 + #undef E2 + ++#endif ++ + /* + * Enabling irqs with an irq-safe lock held: + */ +@@ -815,6 +822,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) + +@@ -830,6 +839,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock) + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + +@@ -861,6 +872,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) + +@@ -876,6 +889,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock) + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 +@@ -909,6 +924,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) + +@@ -924,10 +941,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock) + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock irq inversion. + * +@@ -990,6 +1011,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_wlock) + #undef E2 + #undef E3 + ++#endif ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock recursion that is actually safe. + */ +@@ -1028,6 +1053,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) + #undef E2 + #undef E3 + ++#endif ++ + /* + * read-lock / write-lock recursion that is unsafe. + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0237-sched-Add-support-for-lazy-preemption.patch b/debian/patches-rt/0237-sched-Add-support-for-lazy-preemption.patch new file mode 100644 index 000000000..cc0305fdc --- /dev/null +++ b/debian/patches-rt/0237-sched-Add-support-for-lazy-preemption.patch @@ -0,0 +1,671 @@ +From a8be86e68c8a8706268f9765c7e4eba79d265e70 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 26 Oct 2012 18:50:54 +0100 +Subject: [PATCH 237/347] sched: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +It has become an obsession to mitigate the determinism vs. throughput +loss of RT. Looking at the mainline semantics of preemption points +gives a hint why RT sucks throughput wise for ordinary SCHED_OTHER +tasks. One major issue is the wakeup of tasks which are right away +preempting the waking task while the waking task holds a lock on which +the woken task will block right after having preempted the wakee. In +mainline this is prevented due to the implicit preemption disable of +spin/rw_lock held regions. On RT this is not possible due to the fully +preemptible nature of sleeping spinlocks. + +Though for a SCHED_OTHER task preempting another SCHED_OTHER task this +is really not a correctness issue. RT folks are concerned about +SCHED_FIFO/RR tasks preemption and not about the purely fairness +driven SCHED_OTHER preemption latencies. + +So I introduced a lazy preemption mechanism which only applies to +SCHED_OTHER tasks preempting another SCHED_OTHER task. Aside of the +existing preempt_count each tasks sports now a preempt_lazy_count +which is manipulated on lock acquiry and release. This is slightly +incorrect as for lazyness reasons I coupled this on +migrate_disable/enable so some other mechanisms get the same treatment +(e.g. get_cpu_light). + +Now on the scheduler side instead of setting NEED_RESCHED this sets +NEED_RESCHED_LAZY in case of a SCHED_OTHER/SCHED_OTHER preemption and +therefor allows to exit the waking task the lock held region before +the woken task preempts. That also works better for cross CPU wakeups +as the other side can stay in the adaptive spinning loop. + +For RT class preemption there is no change. This simply sets +NEED_RESCHED and forgoes the lazy preemption counter. + + Initial test do not expose any observable latency increasement, but +history shows that I've been proven wrong before :) + +The lazy preemption mode is per default on, but with +CONFIG_SCHED_DEBUG enabled it can be disabled via: + + # echo NO_PREEMPT_LAZY >/sys/kernel/debug/sched_features + +and reenabled via + + # echo PREEMPT_LAZY >/sys/kernel/debug/sched_features + +The test results so far are very machine and workload dependent, but +there is a clear trend that it enhances the non RT workload +performance. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/preempt.h | 35 ++++++++++++++- + include/linux/sched.h | 38 +++++++++++++++++ + include/linux/thread_info.h | 12 +++++- + include/linux/trace_events.h | 1 + + kernel/Kconfig.preempt | 6 +++ + kernel/cpu.c | 2 + + kernel/sched/core.c | 83 +++++++++++++++++++++++++++++++++++- + kernel/sched/fair.c | 16 +++---- + kernel/sched/features.h | 3 ++ + kernel/sched/sched.h | 9 ++++ + kernel/trace/trace.c | 36 +++++++++------- + kernel/trace/trace.h | 2 + + kernel/trace/trace_output.c | 14 +++++- + 13 files changed, 228 insertions(+), 29 deletions(-) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index ed8413e7140f..9c74a019bf57 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -180,6 +180,20 @@ extern void preempt_count_sub(int val); + #define preempt_count_inc() preempt_count_add(1) + #define preempt_count_dec() preempt_count_sub(1) + ++#ifdef CONFIG_PREEMPT_LAZY ++#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) ++#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) ++#define inc_preempt_lazy_count() add_preempt_lazy_count(1) ++#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) ++#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) ++#else ++#define add_preempt_lazy_count(val) do { } while (0) ++#define sub_preempt_lazy_count(val) do { } while (0) ++#define inc_preempt_lazy_count() do { } while (0) ++#define dec_preempt_lazy_count() do { } while (0) ++#define preempt_lazy_count() (0) ++#endif ++ + #ifdef CONFIG_PREEMPT_COUNT + + #define preempt_disable() \ +@@ -188,6 +202,12 @@ do { \ + barrier(); \ + } while (0) + ++#define preempt_lazy_disable() \ ++do { \ ++ inc_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define sched_preempt_enable_no_resched() \ + do { \ + barrier(); \ +@@ -250,6 +270,13 @@ do { \ + __preempt_schedule(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++ preempt_check_resched(); \ ++} while (0) ++ + #else /* !CONFIG_PREEMPT */ + #define preempt_enable() \ + do { \ +@@ -257,6 +284,12 @@ do { \ + preempt_count_dec(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define preempt_enable_notrace() \ + do { \ + barrier(); \ +@@ -323,7 +356,7 @@ do { \ + } while (0) + #define preempt_fold_need_resched() \ + do { \ +- if (tif_need_resched()) \ ++ if (tif_need_resched_now()) \ + set_preempt_need_resched(); \ + } while (0) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 7523c0786a63..044bebd3d16f 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1733,6 +1733,44 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); ++} ++ ++static inline int need_resched_lazy(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#else ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } ++static inline int need_resched_lazy(void) { return 0; } ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#endif ++ ++ + static inline bool __task_is_stopped_or_traced(struct task_struct *task) + { + if (task->state & (__TASK_STOPPED | __TASK_TRACED)) +diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h +index 62dbecfe9132..57a3d99dc067 100644 +--- a/include/linux/thread_info.h ++++ b/include/linux/thread_info.h +@@ -110,7 +110,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) + #define test_thread_flag(flag) \ + test_ti_thread_flag(current_thread_info(), flag) + +-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#ifdef CONFIG_PREEMPT_LAZY ++#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) ++#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++ ++#else ++#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_lazy() 0 ++#endif + + #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES + static inline int arch_within_stack_frames(const void * const stack, +diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h +index 1cc4d2da954c..72864a11cec0 100644 +--- a/include/linux/trace_events.h ++++ b/include/linux/trace_events.h +@@ -64,6 +64,7 @@ struct trace_entry { + int pid; + unsigned short migrate_disable; + unsigned short padding; ++ unsigned char preempt_lazy_count; + }; + + #define TRACE_EVENT_TYPE_MAX \ +diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt +index 907d72b3ba95..306567f72a3e 100644 +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -6,6 +6,12 @@ config PREEMPT_RT_BASE + bool + select PREEMPT + ++config HAVE_PREEMPT_LAZY ++ bool ++ ++config PREEMPT_LAZY ++ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL ++ + choice + prompt "Preemption Model" + default PREEMPT_NONE +diff --git a/kernel/cpu.c b/kernel/cpu.c +index f6511c62c9a4..11f48774b129 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -306,11 +306,13 @@ void pin_current_cpu(void) + return; + } + cpu = smp_processor_id(); ++ preempt_lazy_enable(); + preempt_enable(); + + __read_rt_lock(cpuhp_pin); + + preempt_disable(); ++ preempt_lazy_disable(); + if (cpu != smp_processor_id()) { + __read_rt_unlock(cpuhp_pin); + goto again; +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index dba425296275..0995748a3a1d 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -493,6 +493,48 @@ void resched_curr(struct rq *rq) + trace_sched_wake_idle_without_ipi(cpu); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++ ++static int tsk_is_polling(struct task_struct *p) ++{ ++#ifdef TIF_POLLING_NRFLAG ++ return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); ++#else ++ return 0; ++#endif ++} ++ ++void resched_curr_lazy(struct rq *rq) ++{ ++ struct task_struct *curr = rq->curr; ++ int cpu; ++ ++ if (!sched_feat(PREEMPT_LAZY)) { ++ resched_curr(rq); ++ return; ++ } ++ ++ lockdep_assert_held(&rq->lock); ++ ++ if (test_tsk_need_resched(curr)) ++ return; ++ ++ if (test_tsk_need_resched_lazy(curr)) ++ return; ++ ++ set_tsk_need_resched_lazy(curr); ++ ++ cpu = cpu_of(rq); ++ if (cpu == smp_processor_id()) ++ return; ++ ++ /* NEED_RESCHED_LAZY must be visible before we test polling */ ++ smp_mb(); ++ if (!tsk_is_polling(curr)) ++ smp_send_reschedule(cpu); ++} ++#endif ++ + void resched_cpu(int cpu) + { + struct rq *rq = cpu_rq(cpu); +@@ -2409,6 +2451,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) + p->on_cpu = 0; + #endif + init_task_preempt_count(p); ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(p)->preempt_lazy_count = 0; ++#endif + #ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +@@ -3518,6 +3563,7 @@ static void __sched notrace __schedule(bool preempt) + + next = pick_next_task(rq, prev, &rf); + clear_tsk_need_resched(prev); ++ clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + + if (likely(prev != next)) { +@@ -3698,6 +3744,30 @@ static void __sched notrace preempt_schedule_common(void) + } while (need_resched()); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++/* ++ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is ++ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as ++ * preempt_lazy_count counter >0. ++ */ ++static __always_inline int preemptible_lazy(void) ++{ ++ if (test_thread_flag(TIF_NEED_RESCHED)) ++ return 1; ++ if (current_thread_info()->preempt_lazy_count) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline int preemptible_lazy(void) ++{ ++ return 1; ++} ++ ++#endif ++ + #ifdef CONFIG_PREEMPT + /* + * this is the entry point to schedule() from in-kernel preemption +@@ -3712,7 +3782,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) + */ + if (likely(!preemptible())) + return; +- ++ if (!preemptible_lazy()) ++ return; + preempt_schedule_common(); + } + NOKPROBE_SYMBOL(preempt_schedule); +@@ -3739,6 +3810,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) + if (likely(!preemptible())) + return; + ++ if (!preemptible_lazy()) ++ return; ++ + do { + /* + * Because the function tracer can trace preempt_count_sub() +@@ -5505,7 +5579,9 @@ void init_idle(struct task_struct *idle, int cpu) + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +- ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(idle)->preempt_lazy_count = 0; ++#endif + /* + * The idle tasks have their own, simple scheduling class: + */ +@@ -7222,6 +7298,7 @@ void migrate_disable(void) + } + + preempt_disable(); ++ preempt_lazy_disable(); + pin_current_cpu(); + + migrate_disable_update_cpus_allowed(p); +@@ -7289,6 +7366,7 @@ void migrate_enable(void) + arg.dest_cpu = dest_cpu; + + unpin_current_cpu(); ++ preempt_lazy_enable(); + preempt_enable(); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); +@@ -7297,6 +7375,7 @@ void migrate_enable(void) + } + } + unpin_current_cpu(); ++ preempt_lazy_enable(); + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 16940416d526..d006dfc54a45 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -4104,7 +4104,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. +@@ -4128,7 +4128,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) + return; + + if (delta > ideal_runtime) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static void +@@ -4270,7 +4270,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) + * validating it and just reschedule. + */ + if (queued) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* +@@ -4404,7 +4404,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static __always_inline +@@ -5112,7 +5112,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) + + if (delta < 0) { + if (rq->curr == p) +- resched_curr(rq); ++ resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); +@@ -6706,7 +6706,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ + return; + + preempt: +- resched_curr(rq); ++ resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved +@@ -9840,7 +9840,7 @@ static void task_fork_fair(struct task_struct *p) + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); +- resched_curr(rq); ++ resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; +@@ -9864,7 +9864,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) + */ + if (rq->curr == p) { + if (p->prio > oldprio) +- resched_curr(rq); ++ resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); + } +diff --git a/kernel/sched/features.h b/kernel/sched/features.h +index 68de18405857..12a12be6770b 100644 +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -48,6 +48,9 @@ SCHED_FEAT(NONTASK_CAPACITY, true) + + #ifdef CONFIG_PREEMPT_RT_FULL + SCHED_FEAT(TTWU_QUEUE, false) ++# ifdef CONFIG_PREEMPT_LAZY ++SCHED_FEAT(PREEMPT_LAZY, true) ++# endif + #else + + /* +diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h +index 637c408fb2dc..87a05bb90124 100644 +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -1643,6 +1643,15 @@ extern void reweight_task(struct task_struct *p, int prio); + extern void resched_curr(struct rq *rq); + extern void resched_cpu(int cpu); + ++#ifdef CONFIG_PREEMPT_LAZY ++extern void resched_curr_lazy(struct rq *rq); ++#else ++static inline void resched_curr_lazy(struct rq *rq) ++{ ++ resched_curr(rq); ++} ++#endif ++ + extern struct rt_bandwidth def_rt_bandwidth; + extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c +index 2a8b830d42f1..f36b954d2e30 100644 +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -2153,6 +2153,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, + struct task_struct *tsk = current; + + entry->preempt_count = pc & 0xff; ++ entry->preempt_lazy_count = preempt_lazy_count(); + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +@@ -2163,7 +2164,8 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, + ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | +- (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; +@@ -3364,15 +3366,17 @@ get_total_entries(struct trace_buffer *buf, + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _------=> CPU# \n" +- "# / _-----=> irqs-off \n" +- "# | / _----=> need-resched \n" +- "# || / _---=> hardirq/softirq \n" +- "# ||| / _--=> preempt-depth \n" +- "# |||| / _--=> migrate-disable\n" +- "# ||||| / delay \n" +- "# cmd pid |||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +@@ -3410,15 +3414,17 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file + tgid ? tgid_space : space); + seq_printf(m, "# %s / _----=> need-resched\n", + tgid ? tgid_space : space); +- seq_printf(m, "# %s| / _---=> hardirq/softirq\n", ++ seq_printf(m, "# %s| / _---=> need-resched_lazy\n", + tgid ? tgid_space : space); +- seq_printf(m, "# %s|| / _--=> preempt-depth\n", ++ seq_printf(m, "# %s|| / _--=> hardirq/softirq\n", + tgid ? tgid_space : space); +- seq_printf(m, "# %s||| / delay\n", ++ seq_printf(m, "# %s||| / preempt-depth\n", + tgid ? tgid_space : space); +- seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n", ++ seq_printf(m, "# %s|||| / delay\n", ++ tgid ? tgid_space : space); ++ seq_printf(m, "# TASK-PID %sCPU# ||||| TIMESTAMP FUNCTION\n", + tgid ? " TGID " : space); +- seq_printf(m, "# | | %s | |||| | |\n", ++ seq_printf(m, "# | | %s | ||||| | |\n", + tgid ? " | " : space); + } + +diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h +index 74185fb040f3..7740bcdad355 100644 +--- a/kernel/trace/trace.h ++++ b/kernel/trace/trace.h +@@ -127,6 +127,7 @@ struct kretprobe_trace_entry_head { + * NEED_RESCHED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler ++ * NEED_RESCHED_LAZY - lazy reschedule is requested + */ + enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, +@@ -136,6 +137,7 @@ enum trace_flag_type { + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x80, + }; + + #define TRACE_BUF_SIZE 1024 +diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c +index 46c96744f09d..3f78b0afb729 100644 +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -448,6 +448,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + { + char hardsoft_irq; + char need_resched; ++ char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; +@@ -478,6 +479,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + break; + } + ++ need_resched_lazy = ++ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; ++ + hardsoft_irq = + (nmi && hardirq) ? 'Z' : + nmi ? 'z' : +@@ -486,14 +490,20 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + softirq ? 's' : + '.' ; + +- trace_seq_printf(s, "%c%c%c", +- irqs_off, need_resched, hardsoft_irq); ++ trace_seq_printf(s, "%c%c%c%c", ++ irqs_off, need_resched, need_resched_lazy, ++ hardsoft_irq); + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_putc(s, '.'); + ++ if (entry->preempt_lazy_count) ++ trace_seq_printf(s, "%x", entry->preempt_lazy_count); ++ else ++ trace_seq_putc(s, '.'); ++ + if (entry->migrate_disable) + trace_seq_printf(s, "%x", entry->migrate_disable); + else +-- +2.36.1 + diff --git a/debian/patches-rt/0238-ftrace-Fix-trace-header-alignment.patch b/debian/patches-rt/0238-ftrace-Fix-trace-header-alignment.patch new file mode 100644 index 000000000..37c7a1fee --- /dev/null +++ b/debian/patches-rt/0238-ftrace-Fix-trace-header-alignment.patch @@ -0,0 +1,52 @@ +From 4462a16fd2c2a84dcf4ff6f574044ed4cafd7860 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Sun, 16 Oct 2016 05:08:30 +0200 +Subject: [PATCH 238/347] ftrace: Fix trace header alignment +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Line up helper arrows to the right column. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +[bigeasy: fixup function tracer header] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/trace/trace.c | 22 +++++++++++----------- + 1 file changed, 11 insertions(+), 11 deletions(-) + +diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c +index f36b954d2e30..87bce59fa340 100644 +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -3366,17 +3366,17 @@ get_total_entries(struct trace_buffer *buf, + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _--------=> CPU# \n" +- "# / _-------=> irqs-off \n" +- "# | / _------=> need-resched \n" +- "# || / _-----=> need-resched_lazy \n" +- "# ||| / _----=> hardirq/softirq \n" +- "# |||| / _---=> preempt-depth \n" +- "# ||||| / _--=> preempt-lazy-depth\n" +- "# |||||| / _-=> migrate-disable \n" +- "# ||||||| / delay \n" +- "# cmd pid |||||||| time | caller \n" +- "# \\ / |||||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +-- +2.36.1 + diff --git a/debian/patches-rt/0239-x86-Support-for-lazy-preemption.patch b/debian/patches-rt/0239-x86-Support-for-lazy-preemption.patch new file mode 100644 index 000000000..a1c901aff --- /dev/null +++ b/debian/patches-rt/0239-x86-Support-for-lazy-preemption.patch @@ -0,0 +1,240 @@ +From 0a855342d92f9b1b29ba2616d4d50637087cd955 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 1 Nov 2012 11:03:47 +0100 +Subject: [PATCH 239/347] x86: Support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Implement the x86 pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/Kconfig | 1 + + arch/x86/entry/common.c | 4 ++-- + arch/x86/entry/entry_32.S | 17 ++++++++++++++++ + arch/x86/entry/entry_64.S | 16 +++++++++++++++ + arch/x86/include/asm/preempt.h | 31 +++++++++++++++++++++++++++++- + arch/x86/include/asm/thread_info.h | 11 +++++++++++ + arch/x86/kernel/asm-offsets.c | 2 ++ + 7 files changed, 79 insertions(+), 3 deletions(-) + +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index 6ee7220e7f47..7299aeaa7cbb 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -180,6 +180,7 @@ config X86 + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if PARAVIRT + select HAVE_RCU_TABLE_INVALIDATE if HAVE_RCU_TABLE_FREE + select HAVE_REGS_AND_STACK_ACCESS_API +diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c +index 91676b0d2d4c..3b5e41d9b29d 100644 +--- a/arch/x86/entry/common.c ++++ b/arch/x86/entry/common.c +@@ -134,7 +134,7 @@ static long syscall_trace_enter(struct pt_regs *regs) + + #define EXIT_TO_USERMODE_LOOP_FLAGS \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ +- _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) ++ _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) + + static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) + { +@@ -149,7 +149,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) + /* We have work to do. */ + local_irq_enable(); + +- if (cached_flags & _TIF_NEED_RESCHED) ++ if (cached_flags & _TIF_NEED_RESCHED_MASK) + schedule(); + + #ifdef ARCH_RT_DELAYS_SIGNAL_SEND +diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S +index 37d9016d4768..324b7539eaab 100644 +--- a/arch/x86/entry/entry_32.S ++++ b/arch/x86/entry/entry_32.S +@@ -750,8 +750,25 @@ END(ret_from_exception) + ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) + .Lneed_resched: ++ # preempt count == 0 + NEED_RS set? + cmpl $0, PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz restore_all_kernel ++#else ++ jz test_int_off ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jne restore_all ++ ++ movl PER_CPU_VAR(current_task), %ebp ++ cmpl $0,TASK_TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? ++ jnz restore_all ++ ++ testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp) ++ jz restore_all ++ test_int_off: ++#endif + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all_kernel + call preempt_schedule_irq +diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S +index f53d995b1370..94fccaa04bfa 100644 +--- a/arch/x86/entry/entry_64.S ++++ b/arch/x86/entry/entry_64.S +@@ -733,7 +733,23 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) + btl $9, EFLAGS(%rsp) /* were interrupts off? */ + jnc 1f + 0: cmpl $0, PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz 1f ++#else ++ jz do_preempt_schedule_irq ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jnz 1f ++ ++ movq PER_CPU_VAR(current_task), %rcx ++ cmpl $0, TASK_TI_preempt_lazy_count(%rcx) ++ jnz 1f ++ ++ btl $TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx) ++ jnc 1f ++do_preempt_schedule_irq: ++#endif + call preempt_schedule_irq + jmp 0b + 1: +diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h +index 7f2dbd91fc74..22992c837795 100644 +--- a/arch/x86/include/asm/preempt.h ++++ b/arch/x86/include/asm/preempt.h +@@ -86,17 +86,46 @@ static __always_inline void __preempt_count_sub(int val) + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +-static __always_inline bool __preempt_count_dec_and_test(void) ++static __always_inline bool ____preempt_count_dec_and_test(void) + { + GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e); + } + ++static __always_inline bool __preempt_count_dec_and_test(void) ++{ ++ if (____preempt_count_dec_and_test()) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif ++} ++ + /* + * Returns true when we need to resched and can (barring IRQ state). + */ + static __always_inline bool should_resched(int preempt_offset) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ u32 tmp; ++ ++ tmp = raw_cpu_read_4(__preempt_count); ++ if (tmp == preempt_offset) ++ return true; ++ ++ /* preempt count == 0 ? */ ++ tmp &= ~PREEMPT_NEED_RESCHED; ++ if (tmp) ++ return false; ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); ++#endif + } + + #ifdef CONFIG_PREEMPT +diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h +index b5e4c357523e..d311dc042ddd 100644 +--- a/arch/x86/include/asm/thread_info.h ++++ b/arch/x86/include/asm/thread_info.h +@@ -56,17 +56,24 @@ struct task_struct; + struct thread_info { + unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ ++ int preempt_lazy_count; /* 0 => lazy preemptable ++ <0 => BUG */ + }; + + #define INIT_THREAD_INFO(tsk) \ + { \ + .flags = 0, \ ++ .preempt_lazy_count = 0, \ + } + + #else /* !__ASSEMBLY__ */ + + #include <asm/asm-offsets.h> + ++#define GET_THREAD_INFO(reg) \ ++ _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ ++ _ASM_SUB $(THREAD_SIZE),reg ; ++ + #endif + + /* +@@ -91,6 +98,7 @@ struct thread_info { + #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ + #define TIF_NOTSC 16 /* TSC is not accessible in userland */ + #define TIF_IA32 17 /* IA32 compatibility process */ ++#define TIF_NEED_RESCHED_LAZY 18 /* lazy rescheduling necessary */ + #define TIF_NOHZ 19 /* in adaptive nohz mode */ + #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ + #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ +@@ -120,6 +128,7 @@ struct thread_info { + #define _TIF_NOCPUID (1 << TIF_NOCPUID) + #define _TIF_NOTSC (1 << TIF_NOTSC) + #define _TIF_IA32 (1 << TIF_IA32) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_NOHZ (1 << TIF_NOHZ) + #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) + #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) +@@ -165,6 +174,8 @@ struct thread_info { + #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #define STACK_WARN (THREAD_SIZE/8) + + /* +diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c +index 01de31db300d..ce1c5b9fbd8c 100644 +--- a/arch/x86/kernel/asm-offsets.c ++++ b/arch/x86/kernel/asm-offsets.c +@@ -38,6 +38,7 @@ void common(void) { + + BLANK(); + OFFSET(TASK_TI_flags, task_struct, thread_info.flags); ++ OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count); + OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); + + BLANK(); +@@ -94,6 +95,7 @@ void common(void) { + + BLANK(); + DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); ++ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); + + /* TLB state for the entry code */ + OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); +-- +2.36.1 + diff --git a/debian/patches-rt/0240-x86-lazy-preempt-properly-check-against-preempt-mask.patch b/debian/patches-rt/0240-x86-lazy-preempt-properly-check-against-preempt-mask.patch new file mode 100644 index 000000000..df8346c2d --- /dev/null +++ b/debian/patches-rt/0240-x86-lazy-preempt-properly-check-against-preempt-mask.patch @@ -0,0 +1,33 @@ +From 87b957ebbe16c81c7a72161e8d1ab55d0746bd83 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 18 Feb 2019 16:57:09 +0100 +Subject: [PATCH 240/347] x86: lazy-preempt: properly check against + preempt-mask +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +should_resched() should check against preempt_offset after unmasking the +need-resched-bit. Otherwise should_resched() won't work for +preempt_offset != 0 and lazy-preempt set. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/include/asm/preempt.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h +index 22992c837795..f66708779274 100644 +--- a/arch/x86/include/asm/preempt.h ++++ b/arch/x86/include/asm/preempt.h +@@ -118,7 +118,7 @@ static __always_inline bool should_resched(int preempt_offset) + + /* preempt count == 0 ? */ + tmp &= ~PREEMPT_NEED_RESCHED; +- if (tmp) ++ if (tmp != preempt_offset) + return false; + if (current_thread_info()->preempt_lazy_count) + return false; +-- +2.36.1 + diff --git a/debian/patches-rt/0241-x86-lazy-preempt-use-proper-return-label-on-32bit-x8.patch b/debian/patches-rt/0241-x86-lazy-preempt-use-proper-return-label-on-32bit-x8.patch new file mode 100644 index 000000000..430b7295c --- /dev/null +++ b/debian/patches-rt/0241-x86-lazy-preempt-use-proper-return-label-on-32bit-x8.patch @@ -0,0 +1,45 @@ +From 6f0e27cbe8c66801cdad07e48be779eff3301cc1 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 26 Feb 2019 14:53:49 +0100 +Subject: [PATCH 241/347] x86: lazy-preempt: use proper return label on + 32bit-x86 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The lazy-preempt uses the wrong return label in case preemption isn't +possible. This results crash while returning to the kernel. + +Use the correct return label if preemption isn' possible. + +Reported-by: Andri Yngvason <andri@yngvason.is> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/entry/entry_32.S | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S +index 324b7539eaab..d8b40085c2b8 100644 +--- a/arch/x86/entry/entry_32.S ++++ b/arch/x86/entry/entry_32.S +@@ -759,15 +759,15 @@ ENTRY(resume_kernel) + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) +- jne restore_all ++ jne restore_all_kernel + + movl PER_CPU_VAR(current_task), %ebp + cmpl $0,TASK_TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? +- jnz restore_all ++ jnz restore_all_kernel + + testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp) +- jz restore_all +- test_int_off: ++ jz restore_all_kernel ++test_int_off: + #endif + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all_kernel +-- +2.36.1 + diff --git a/debian/patches-rt/0242-arm-Add-support-for-lazy-preemption.patch b/debian/patches-rt/0242-arm-Add-support-for-lazy-preemption.patch new file mode 100644 index 000000000..af7fd9bc3 --- /dev/null +++ b/debian/patches-rt/0242-arm-Add-support-for-lazy-preemption.patch @@ -0,0 +1,168 @@ +From 3845cb2e5f05561da9e363932c9373f45b5fa6a4 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 31 Oct 2012 12:04:11 +0100 +Subject: [PATCH 242/347] arm: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Implement the arm pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm/Kconfig | 1 + + arch/arm/include/asm/thread_info.h | 8 ++++++-- + arch/arm/kernel/asm-offsets.c | 1 + + arch/arm/kernel/entry-armv.S | 19 ++++++++++++++++--- + arch/arm/kernel/entry-common.S | 9 +++++++-- + arch/arm/kernel/signal.c | 3 ++- + 6 files changed, 33 insertions(+), 8 deletions(-) + +diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index ec99422059e3..2607cae04885 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -91,6 +91,7 @@ config ARM + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ +diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h +index 8f55dc520a3e..4f834bfca470 100644 +--- a/arch/arm/include/asm/thread_info.h ++++ b/arch/arm/include/asm/thread_info.h +@@ -49,6 +49,7 @@ struct cpu_context_save { + struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + __u32 cpu; /* cpu */ +@@ -139,7 +140,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, + #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ + #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ + #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ +-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ ++#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ ++#define TIF_NEED_RESCHED_LAZY 7 + + #define TIF_NOHZ 12 /* in adaptive nohz mode */ + #define TIF_USING_IWMMXT 17 +@@ -149,6 +151,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +@@ -164,7 +167,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, + * Change these and you break ASM code in entry-common.S + */ + #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +- _TIF_NOTIFY_RESUME | _TIF_UPROBE) ++ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ ++ _TIF_NEED_RESCHED_LAZY) + + #endif /* __KERNEL__ */ + #endif /* __ASM_ARM_THREAD_INFO_H */ +diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c +index 40afe953a0e2..d634d6f36140 100644 +--- a/arch/arm/kernel/asm-offsets.c ++++ b/arch/arm/kernel/asm-offsets.c +@@ -58,6 +58,7 @@ int main(void) + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S +index d779cd1a3b0c..dc7ae3d8e62f 100644 +--- a/arch/arm/kernel/entry-armv.S ++++ b/arch/arm/kernel/entry-armv.S +@@ -209,11 +209,18 @@ ENDPROC(__dabt_svc) + + #ifdef CONFIG_PREEMPT + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count +- ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 ++ bne 1f @ return from exeption ++ ldr r0, [tsk, #TI_FLAGS] @ get flags ++ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set ++ blne svc_preempt @ preempt! ++ ++ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r8, #0 @ if preempt lazy count != 0 + movne r0, #0 @ force flags to 0 +- tst r0, #_TIF_NEED_RESCHED ++ tst r0, #_TIF_NEED_RESCHED_LAZY + blne svc_preempt ++1: + #endif + + svc_exit r5, irq = 1 @ return from exception +@@ -228,8 +235,14 @@ ENDPROC(__irq_svc) + 1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED ++ bne 1b ++ tst r0, #_TIF_NEED_RESCHED_LAZY + reteq r8 @ go again +- b 1b ++ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r0, #0 @ if preempt lazy count != 0 ++ beq 1b ++ ret r8 @ go again ++ + #endif + + __und_fault: +diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S +index e27fc2df5231..bc326519f648 100644 +--- a/arch/arm/kernel/entry-common.S ++++ b/arch/arm/kernel/entry-common.S +@@ -56,7 +56,9 @@ saved_pc .req lr + cmp r2, #TASK_SIZE + blne addr_limit_check_failed + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing +- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK ++ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) ++ bne fast_work_pending ++ tst r1, #_TIF_SECCOMP + bne fast_work_pending + + +@@ -93,8 +95,11 @@ ENDPROC(ret_fast_syscall) + cmp r2, #TASK_SIZE + blne addr_limit_check_failed + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing +- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK ++ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) ++ bne do_slower_path ++ tst r1, #_TIF_SECCOMP + beq no_work_pending ++do_slower_path: + UNWIND(.fnend ) + ENDPROC(ret_fast_syscall) + +diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c +index 1c01358b9b6d..263b0321dc50 100644 +--- a/arch/arm/kernel/signal.c ++++ b/arch/arm/kernel/signal.c +@@ -652,7 +652,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) + */ + trace_hardirqs_off(); + do { +- if (likely(thread_flags & _TIF_NEED_RESCHED)) { ++ if (likely(thread_flags & (_TIF_NEED_RESCHED | ++ _TIF_NEED_RESCHED_LAZY))) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) +-- +2.36.1 + diff --git a/debian/patches-rt/0243-powerpc-Add-support-for-lazy-preemption.patch b/debian/patches-rt/0243-powerpc-Add-support-for-lazy-preemption.patch new file mode 100644 index 000000000..7c07610a1 --- /dev/null +++ b/debian/patches-rt/0243-powerpc-Add-support-for-lazy-preemption.patch @@ -0,0 +1,196 @@ +From 0fe19697678375c08da0c1d53231706a9df830d4 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 1 Nov 2012 10:14:11 +0100 +Subject: [PATCH 243/347] powerpc: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Implement the powerpc pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/Kconfig | 1 + + arch/powerpc/include/asm/thread_info.h | 9 +++++++-- + arch/powerpc/kernel/asm-offsets.c | 1 + + arch/powerpc/kernel/entry_32.S | 17 ++++++++++++----- + arch/powerpc/kernel/entry_64.S | 16 ++++++++++++---- + 5 files changed, 33 insertions(+), 11 deletions(-) + +diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig +index f4517f4be192..4536d047cdff 100644 +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -217,6 +217,7 @@ config PPC + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if SMP + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE if PPC64 && CPU_LITTLE_ENDIAN +diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h +index 3c0002044bc9..ce316076bc52 100644 +--- a/arch/powerpc/include/asm/thread_info.h ++++ b/arch/powerpc/include/asm/thread_info.h +@@ -37,6 +37,8 @@ struct thread_info { + int cpu; /* cpu we're on */ + int preempt_count; /* 0 => preemptable, + <0 => BUG */ ++ int preempt_lazy_count; /* 0 => preemptable, ++ <0 => BUG */ + unsigned long local_flags; /* private flags for thread */ + #ifdef CONFIG_LIVEPATCH + unsigned long *livepatch_sp; +@@ -81,7 +83,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src + #define TIF_SIGPENDING 1 /* signal pending */ + #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ + #define TIF_FSCHECK 3 /* Check FS is USER_DS on return */ +-#define TIF_32BIT 4 /* 32 bit binary */ ++#define TIF_NEED_RESCHED_LAZY 4 /* lazy rescheduling necessary */ + #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ + #define TIF_PATCH_PENDING 6 /* pending live patching update */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ +@@ -100,6 +102,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src + #define TIF_ELF2ABI 18 /* function descriptors must die! */ + #endif + #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ ++#define TIF_32BIT 20 /* 32 bit binary */ + + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) +@@ -119,6 +122,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src + #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) + #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) + #define _TIF_NOHZ (1<<TIF_NOHZ) ++#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) + #define _TIF_FSCHECK (1<<TIF_FSCHECK) + #define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ +@@ -127,8 +131,9 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src + #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \ +- _TIF_FSCHECK) ++ _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY) + #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + + /* Bits in local_flags */ + /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */ +diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c +index 50400f213bbf..1bb82c5dc1d9 100644 +--- a/arch/powerpc/kernel/asm-offsets.c ++++ b/arch/powerpc/kernel/asm-offsets.c +@@ -156,6 +156,7 @@ int main(void) + OFFSET(TI_FLAGS, thread_info, flags); + OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags); + OFFSET(TI_PREEMPT, thread_info, preempt_count); ++ OFFSET(TI_PREEMPT_LAZY, thread_info, preempt_lazy_count); + OFFSET(TI_TASK, thread_info, task); + OFFSET(TI_CPU, thread_info, cpu); + +diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S +index 26b3f853cbf6..3783f3ef17a4 100644 +--- a/arch/powerpc/kernel/entry_32.S ++++ b/arch/powerpc/kernel/entry_32.S +@@ -888,7 +888,14 @@ user_exc_return: /* r10 contains MSR_KERNEL here */ + cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ + bne restore + andi. r8,r8,_TIF_NEED_RESCHED ++ bne+ 1f ++ lwz r0,TI_PREEMPT_LAZY(r9) ++ cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ ++ bne restore ++ lwz r0,TI_FLAGS(r9) ++ andi. r0,r0,_TIF_NEED_RESCHED_LAZY + beq+ restore ++1: + lwz r3,_MSR(r1) + andi. r0,r3,MSR_EE /* interrupts off? */ + beq restore /* don't schedule if so */ +@@ -899,11 +906,11 @@ user_exc_return: /* r10 contains MSR_KERNEL here */ + */ + bl trace_hardirqs_off + #endif +-1: bl preempt_schedule_irq ++2: bl preempt_schedule_irq + CURRENT_THREAD_INFO(r9, r1) + lwz r3,TI_FLAGS(r9) +- andi. r0,r3,_TIF_NEED_RESCHED +- bne- 1b ++ andi. r0,r3,_TIF_NEED_RESCHED_MASK ++ bne- 2b + #ifdef CONFIG_TRACE_IRQFLAGS + /* And now, to properly rebalance the above, we tell lockdep they + * are being turned back on, which will happen when we return +@@ -1232,7 +1239,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) + #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */ + + do_work: /* r10 contains MSR_KERNEL here */ +- andi. r0,r9,_TIF_NEED_RESCHED ++ andi. r0,r9,_TIF_NEED_RESCHED_MASK + beq do_user_signal + + do_resched: /* r10 contains MSR_KERNEL here */ +@@ -1253,7 +1260,7 @@ do_resched: /* r10 contains MSR_KERNEL here */ + MTMSRD(r10) /* disable interrupts */ + CURRENT_THREAD_INFO(r9, r1) + lwz r9,TI_FLAGS(r9) +- andi. r0,r9,_TIF_NEED_RESCHED ++ andi. r0,r9,_TIF_NEED_RESCHED_MASK + bne- do_resched + andi. r0,r9,_TIF_USER_WORK_MASK + beq restore_user +diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S +index 58b50967b3e5..ef02e41d5d96 100644 +--- a/arch/powerpc/kernel/entry_64.S ++++ b/arch/powerpc/kernel/entry_64.S +@@ -176,7 +176,7 @@ system_call: /* label this so stack traces look sane */ + * based on caller's run-mode / personality. + */ + ld r11,SYS_CALL_TABLE@toc(2) +- andi. r10,r10,_TIF_32BIT ++ andis. r10,r10,_TIF_32BIT@h + beq 15f + addi r11,r11,8 /* use 32-bit syscall entries */ + clrldi r3,r3,32 +@@ -774,7 +774,7 @@ _GLOBAL(ret_from_except_lite) + bl restore_math + b restore + #endif +-1: andi. r0,r4,_TIF_NEED_RESCHED ++1: andi. r0,r4,_TIF_NEED_RESCHED_MASK + beq 2f + bl restore_interrupts + SCHEDULE_USER +@@ -836,10 +836,18 @@ _GLOBAL(ret_from_except_lite) + + #ifdef CONFIG_PREEMPT + /* Check if we need to preempt */ ++ lwz r8,TI_PREEMPT(r9) ++ cmpwi 0,r8,0 /* if non-zero, just restore regs and return */ ++ bne restore + andi. r0,r4,_TIF_NEED_RESCHED ++ bne+ check_count ++ ++ andi. r0,r4,_TIF_NEED_RESCHED_LAZY + beq+ restore ++ lwz r8,TI_PREEMPT_LAZY(r9) ++ + /* Check that preempt_count() == 0 and interrupts are enabled */ +- lwz r8,TI_PREEMPT(r9) ++check_count: + cmpwi cr0,r8,0 + bne restore + ld r0,SOFTE(r1) +@@ -856,7 +864,7 @@ _GLOBAL(ret_from_except_lite) + /* Re-test flags and eventually loop */ + CURRENT_THREAD_INFO(r9, r1) + ld r4,TI_FLAGS(r9) +- andi. r0,r4,_TIF_NEED_RESCHED ++ andi. r0,r4,_TIF_NEED_RESCHED_MASK + bne 1b + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0244-arch-arm64-Add-lazy-preempt-support.patch b/debian/patches-rt/0244-arch-arm64-Add-lazy-preempt-support.patch new file mode 100644 index 000000000..204ee7168 --- /dev/null +++ b/debian/patches-rt/0244-arch-arm64-Add-lazy-preempt-support.patch @@ -0,0 +1,133 @@ +From a8bd2b75bb41fc1acdebf6aa547a3e7cfa524445 Mon Sep 17 00:00:00 2001 +From: Anders Roxell <anders.roxell@linaro.org> +Date: Thu, 14 May 2015 17:52:17 +0200 +Subject: [PATCH 244/347] arch/arm64: Add lazy preempt support +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +arm64 is missing support for PREEMPT_RT. The main feature which is +lacking is support for lazy preemption. The arch-specific entry code, +thread information structure definitions, and associated data tables +have to be extended to provide this support. Then the Kconfig file has +to be extended to indicate the support is available, and also to +indicate that support for full RT preemption is now available. + +Signed-off-by: Anders Roxell <anders.roxell@linaro.org> +--- + arch/arm64/Kconfig | 1 + + arch/arm64/include/asm/thread_info.h | 6 +++++- + arch/arm64/kernel/asm-offsets.c | 1 + + arch/arm64/kernel/entry.S | 12 +++++++++--- + arch/arm64/kernel/signal.c | 2 +- + 5 files changed, 17 insertions(+), 5 deletions(-) + +diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig +index a101f5d2fbed..84f53dc1a75b 100644 +--- a/arch/arm64/Kconfig ++++ b/arch/arm64/Kconfig +@@ -141,6 +141,7 @@ config ARM64 + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RCU_TABLE_FREE + select HAVE_RSEQ +diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h +index 69ac5262cccd..39e921817f28 100644 +--- a/arch/arm64/include/asm/thread_info.h ++++ b/arch/arm64/include/asm/thread_info.h +@@ -43,6 +43,7 @@ struct thread_info { + u64 ttbr0; /* saved TTBR0_EL1 */ + #endif + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + }; + + #define thread_saved_pc(tsk) \ +@@ -76,6 +77,7 @@ void arch_release_task_struct(struct task_struct *tsk); + #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ + #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ + #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ ++#define TIF_NEED_RESCHED_LAZY 6 + #define TIF_NOHZ 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -94,6 +96,7 @@ void arch_release_task_struct(struct task_struct *tsk); + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) + #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_NOHZ (1 << TIF_NOHZ) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +@@ -107,8 +110,9 @@ void arch_release_task_struct(struct task_struct *tsk); + + #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ +- _TIF_UPROBE | _TIF_FSCHECK) ++ _TIF_UPROBE | _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ + _TIF_NOHZ) +diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c +index 92fba851ce53..844c71bc865b 100644 +--- a/arch/arm64/kernel/asm-offsets.c ++++ b/arch/arm64/kernel/asm-offsets.c +@@ -41,6 +41,7 @@ int main(void) + BLANK(); + DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); + DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); ++ DEFINE(TSK_TI_PREEMPT_LAZY, offsetof(struct task_struct, thread_info.preempt_lazy_count)); + DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit)); + #ifdef CONFIG_ARM64_SW_TTBR0_PAN + DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); +diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S +index 85433a84783b..201f412b556e 100644 +--- a/arch/arm64/kernel/entry.S ++++ b/arch/arm64/kernel/entry.S +@@ -634,11 +634,16 @@ ENDPROC(el1_sync) + + #ifdef CONFIG_PREEMPT + ldr w24, [tsk, #TSK_TI_PREEMPT] // get preempt count +- cbnz w24, 1f // preempt count != 0 ++ cbnz w24, 2f // preempt count != 0 + ldr x0, [tsk, #TSK_TI_FLAGS] // get flags +- tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? +- bl el1_preempt ++ tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? ++ ++ ldr w24, [tsk, #TSK_TI_PREEMPT_LAZY] // get preempt lazy count ++ cbnz w24, 2f // preempt lazy count != 0 ++ tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? + 1: ++ bl el1_preempt ++2: + #endif + #ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_on +@@ -652,6 +657,7 @@ ENDPROC(el1_irq) + 1: bl preempt_schedule_irq // irq en/disable is done inside + ldr x0, [tsk, #TSK_TI_FLAGS] // get new tasks TI_FLAGS + tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ++ tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? + ret x24 + #endif + +diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c +index ca565853dea6..3f321daa7702 100644 +--- a/arch/arm64/kernel/signal.c ++++ b/arch/arm64/kernel/signal.c +@@ -919,7 +919,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, + /* Check valid user FS if needed */ + addr_limit_user_check(); + +- if (thread_flags & _TIF_NEED_RESCHED) { ++ if (thread_flags & _TIF_NEED_RESCHED_MASK) { + /* Unmask Debug and SError for the next task */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + +-- +2.36.1 + diff --git a/debian/patches-rt/0245-connector-cn_proc-Protect-send_msg-with-a-local-lock.patch b/debian/patches-rt/0245-connector-cn_proc-Protect-send_msg-with-a-local-lock.patch new file mode 100644 index 000000000..8ce25e4b2 --- /dev/null +++ b/debian/patches-rt/0245-connector-cn_proc-Protect-send_msg-with-a-local-lock.patch @@ -0,0 +1,74 @@ +From 2d5d86f2a24500c2b02576c9d5de36bb90e86f10 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Sun, 16 Oct 2016 05:11:54 +0200 +Subject: [PATCH 245/347] connector/cn_proc: Protect send_msg() with a local + lock on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:931 +|in_atomic(): 1, irqs_disabled(): 0, pid: 31807, name: sleep +|Preemption disabled at:[<ffffffff8148019b>] proc_exit_connector+0xbb/0x140 +| +|CPU: 4 PID: 31807 Comm: sleep Tainted: G W E 4.8.0-rt11-rt #106 +|Call Trace: +| [<ffffffff813436cd>] dump_stack+0x65/0x88 +| [<ffffffff8109c425>] ___might_sleep+0xf5/0x180 +| [<ffffffff816406b0>] __rt_spin_lock+0x20/0x50 +| [<ffffffff81640978>] rt_read_lock+0x28/0x30 +| [<ffffffff8156e209>] netlink_broadcast_filtered+0x49/0x3f0 +| [<ffffffff81522621>] ? __kmalloc_reserve.isra.33+0x31/0x90 +| [<ffffffff8156e5cd>] netlink_broadcast+0x1d/0x20 +| [<ffffffff8147f57a>] cn_netlink_send_mult+0x19a/0x1f0 +| [<ffffffff8147f5eb>] cn_netlink_send+0x1b/0x20 +| [<ffffffff814801d8>] proc_exit_connector+0xf8/0x140 +| [<ffffffff81077f71>] do_exit+0x5d1/0xba0 +| [<ffffffff810785cc>] do_group_exit+0x4c/0xc0 +| [<ffffffff81078654>] SyS_exit_group+0x14/0x20 +| [<ffffffff81640a72>] entry_SYSCALL_64_fastpath+0x1a/0xa4 + +Since ab8ed951080e ("connector: fix out-of-order cn_proc netlink message +delivery") which is v4.7-rc6. + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/connector/cn_proc.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c +index ad48fd52cb53..c5264b3ee0b0 100644 +--- a/drivers/connector/cn_proc.c ++++ b/drivers/connector/cn_proc.c +@@ -32,6 +32,7 @@ + #include <linux/pid_namespace.h> + + #include <linux/cn_proc.h> ++#include <linux/locallock.h> + + /* + * Size of a cn_msg followed by a proc_event structure. Since the +@@ -54,10 +55,11 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; + + /* proc_event_counts is used as the sequence number of the netlink message */ + static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 }; ++static DEFINE_LOCAL_IRQ_LOCK(send_msg_lock); + + static inline void send_msg(struct cn_msg *msg) + { +- preempt_disable(); ++ local_lock(send_msg_lock); + + msg->seq = __this_cpu_inc_return(proc_event_counts) - 1; + ((struct proc_event *)msg->data)->cpu = smp_processor_id(); +@@ -70,7 +72,7 @@ static inline void send_msg(struct cn_msg *msg) + */ + cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); + +- preempt_enable(); ++ local_unlock(send_msg_lock); + } + + void proc_fork_connector(struct task_struct *task) +-- +2.36.1 + diff --git a/debian/patches-rt/0246-drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch b/debian/patches-rt/0246-drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch new file mode 100644 index 000000000..04dcb13d9 --- /dev/null +++ b/debian/patches-rt/0246-drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch @@ -0,0 +1,104 @@ +From cdff10ec863d6d0e7d18beb8cb66adc86674bb2b Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Thu, 31 Mar 2016 04:08:28 +0200 +Subject: [PATCH 246/347] drivers/block/zram: Replace bit spinlocks with + rtmutex for -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +They're nondeterministic, and lead to ___might_sleep() splats in -rt. +OTOH, they're a lot less wasteful than an rtmutex per page. + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/block/zram/zram_drv.c | 38 +++++++++++++++++++++++++++++++++++ + drivers/block/zram/zram_drv.h | 3 +++ + 2 files changed, 41 insertions(+) + +diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c +index 5e05bfcecd7b..04e4297f8318 100644 +--- a/drivers/block/zram/zram_drv.c ++++ b/drivers/block/zram/zram_drv.c +@@ -53,6 +53,40 @@ static size_t huge_class_size; + + static void zram_free_page(struct zram *zram, size_t index); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) ++{ ++ size_t index; ++ ++ for (index = 0; index < num_pages; index++) ++ spin_lock_init(&zram->table[index].lock); ++} ++ ++static int zram_slot_trylock(struct zram *zram, u32 index) ++{ ++ int ret; ++ ++ ret = spin_trylock(&zram->table[index].lock); ++ if (ret) ++ __set_bit(ZRAM_LOCK, &zram->table[index].value); ++ return ret; ++} ++ ++static void zram_slot_lock(struct zram *zram, u32 index) ++{ ++ spin_lock(&zram->table[index].lock); ++ __set_bit(ZRAM_LOCK, &zram->table[index].value); ++} ++ ++static void zram_slot_unlock(struct zram *zram, u32 index) ++{ ++ __clear_bit(ZRAM_LOCK, &zram->table[index].value); ++ spin_unlock(&zram->table[index].lock); ++} ++ ++#else ++static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { } ++ + static int zram_slot_trylock(struct zram *zram, u32 index) + { + return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value); +@@ -67,6 +101,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index) + { + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].value); + } ++#endif + + static inline bool init_done(struct zram *zram) + { +@@ -902,6 +937,8 @@ static DEVICE_ATTR_RO(io_stat); + static DEVICE_ATTR_RO(mm_stat); + static DEVICE_ATTR_RO(debug_stat); + ++ ++ + static void zram_meta_free(struct zram *zram, u64 disksize) + { + size_t num_pages = disksize >> PAGE_SHIFT; +@@ -932,6 +969,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) + + if (!huge_class_size) + huge_class_size = zs_huge_class_size(zram->mem_pool); ++ zram_meta_init_table_locks(zram, num_pages); + return true; + } + +diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h +index d1095dfdffa8..144e91061df8 100644 +--- a/drivers/block/zram/zram_drv.h ++++ b/drivers/block/zram/zram_drv.h +@@ -61,6 +61,9 @@ struct zram_table_entry { + unsigned long element; + }; + unsigned long value; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t lock; ++#endif + #ifdef CONFIG_ZRAM_MEMORY_TRACKING + ktime_t ac_time; + #endif +-- +2.36.1 + diff --git a/debian/patches-rt/0247-drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch b/debian/patches-rt/0247-drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch new file mode 100644 index 000000000..e12dd3c3c --- /dev/null +++ b/debian/patches-rt/0247-drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch @@ -0,0 +1,107 @@ +From fcbeb7ab5dc2a2e2f1243df805e9a4f0103b212b Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Thu, 20 Oct 2016 11:15:22 +0200 +Subject: [PATCH 247/347] drivers/zram: Don't disable preemption in + zcomp_stream_get/put() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +In v4.7, the driver switched to percpu compression streams, disabling +preemption via get/put_cpu_ptr(). Use a per-zcomp_strm lock here. We +also have to fix an lock order issue in zram_decompress_page() such +that zs_map_object() nests inside of zcomp_stream_put() as it does in +zram_bvec_write(). + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +[bigeasy: get_locked_var() -> per zcomp_strm lock] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/block/zram/zcomp.c | 12 ++++++++++-- + drivers/block/zram/zcomp.h | 1 + + drivers/block/zram/zram_drv.c | 5 +++-- + 3 files changed, 14 insertions(+), 4 deletions(-) + +diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c +index 4ed0a78fdc09..dd65a27ae2cc 100644 +--- a/drivers/block/zram/zcomp.c ++++ b/drivers/block/zram/zcomp.c +@@ -116,12 +116,19 @@ ssize_t zcomp_available_show(const char *comp, char *buf) + + struct zcomp_strm *zcomp_stream_get(struct zcomp *comp) + { +- return *get_cpu_ptr(comp->stream); ++ struct zcomp_strm *zstrm; ++ ++ zstrm = *this_cpu_ptr(comp->stream); ++ spin_lock(&zstrm->zcomp_lock); ++ return zstrm; + } + + void zcomp_stream_put(struct zcomp *comp) + { +- put_cpu_ptr(comp->stream); ++ struct zcomp_strm *zstrm; ++ ++ zstrm = *this_cpu_ptr(comp->stream); ++ spin_unlock(&zstrm->zcomp_lock); + } + + int zcomp_compress(struct zcomp_strm *zstrm, +@@ -171,6 +178,7 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node) + pr_err("Can't allocate a compression stream\n"); + return -ENOMEM; + } ++ spin_lock_init(&zstrm->zcomp_lock); + *per_cpu_ptr(comp->stream, cpu) = zstrm; + return 0; + } +diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h +index 41c1002a7d7d..d424eafcbf8e 100644 +--- a/drivers/block/zram/zcomp.h ++++ b/drivers/block/zram/zcomp.h +@@ -14,6 +14,7 @@ struct zcomp_strm { + /* compression/decompression buffer */ + void *buffer; + struct crypto_comp *tfm; ++ spinlock_t zcomp_lock; + }; + + /* dynamic per-device compression frontend */ +diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c +index 04e4297f8318..2919ad13bce9 100644 +--- a/drivers/block/zram/zram_drv.c ++++ b/drivers/block/zram/zram_drv.c +@@ -1028,6 +1028,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, + unsigned long handle; + unsigned int size; + void *src, *dst; ++ struct zcomp_strm *zstrm; + + if (zram_wb_enabled(zram)) { + zram_slot_lock(zram, index); +@@ -1062,6 +1063,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, + + size = zram_get_obj_size(zram, index); + ++ zstrm = zcomp_stream_get(zram->comp); + src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); + if (size == PAGE_SIZE) { + dst = kmap_atomic(page); +@@ -1069,14 +1071,13 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, + kunmap_atomic(dst); + ret = 0; + } else { +- struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp); + + dst = kmap_atomic(page); + ret = zcomp_decompress(zstrm, src, size, dst); + kunmap_atomic(dst); +- zcomp_stream_put(zram->comp); + } + zs_unmap_object(zram->mem_pool, handle); ++ zcomp_stream_put(zram->comp); + zram_slot_unlock(zram, index); + + /* Should NEVER happen. Return bio error if it does. */ +-- +2.36.1 + diff --git a/debian/patches-rt/0248-drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch b/debian/patches-rt/0248-drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch new file mode 100644 index 000000000..0ff366338 --- /dev/null +++ b/debian/patches-rt/0248-drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch @@ -0,0 +1,44 @@ +From 6b94039830863cbed6f161843e96e0cd79637353 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <efault@gmx.de> +Date: Wed, 23 Aug 2017 11:57:29 +0200 +Subject: [PATCH 248/347] drivers/zram: fix zcomp_stream_get() + smp_processor_id() use in preemptible code +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Use get_local_ptr() instead this_cpu_ptr() to avoid a warning regarding +smp_processor_id() in preemptible code. +raw_cpu_ptr() would be fine, too because the per-CPU data structure is +protected with a spin lock so it does not matter much if we take the +other one. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/block/zram/zcomp.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c +index dd65a27ae2cc..eece02262000 100644 +--- a/drivers/block/zram/zcomp.c ++++ b/drivers/block/zram/zcomp.c +@@ -118,7 +118,7 @@ struct zcomp_strm *zcomp_stream_get(struct zcomp *comp) + { + struct zcomp_strm *zstrm; + +- zstrm = *this_cpu_ptr(comp->stream); ++ zstrm = *get_local_ptr(comp->stream); + spin_lock(&zstrm->zcomp_lock); + return zstrm; + } +@@ -129,6 +129,7 @@ void zcomp_stream_put(struct zcomp *comp) + + zstrm = *this_cpu_ptr(comp->stream); + spin_unlock(&zstrm->zcomp_lock); ++ put_local_ptr(zstrm); + } + + int zcomp_compress(struct zcomp_strm *zstrm, +-- +2.36.1 + diff --git a/debian/patches-rt/0249-tpm_tis-fix-stall-after-iowrite-s.patch b/debian/patches-rt/0249-tpm_tis-fix-stall-after-iowrite-s.patch new file mode 100644 index 000000000..0da4b19d0 --- /dev/null +++ b/debian/patches-rt/0249-tpm_tis-fix-stall-after-iowrite-s.patch @@ -0,0 +1,84 @@ +From 4ef974ed9fe88d78a6e03689fab80c553fcf70df Mon Sep 17 00:00:00 2001 +From: Haris Okanovic <haris.okanovic@ni.com> +Date: Tue, 15 Aug 2017 15:13:08 -0500 +Subject: [PATCH 249/347] tpm_tis: fix stall after iowrite*()s +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +ioread8() operations to TPM MMIO addresses can stall the cpu when +immediately following a sequence of iowrite*()'s to the same region. + +For example, cyclitest measures ~400us latency spikes when a non-RT +usermode application communicates with an SPI-based TPM chip (Intel Atom +E3940 system, PREEMPT_RT_FULL kernel). The spikes are caused by a +stalling ioread8() operation following a sequence of 30+ iowrite8()s to +the same address. I believe this happens because the write sequence is +buffered (in cpu or somewhere along the bus), and gets flushed on the +first LOAD instruction (ioread*()) that follows. + +The enclosed change appears to fix this issue: read the TPM chip's +access register (status code) after every iowrite*() operation to +amortize the cost of flushing data to chip across multiple instructions. + +Signed-off-by: Haris Okanovic <haris.okanovic@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/char/tpm/tpm_tis.c | 29 +++++++++++++++++++++++++++-- + 1 file changed, 27 insertions(+), 2 deletions(-) + +diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c +index 5a3a4f095391..5ecca6585049 100644 +--- a/drivers/char/tpm/tpm_tis.c ++++ b/drivers/char/tpm/tpm_tis.c +@@ -54,6 +54,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da + return container_of(data, struct tpm_tis_tcg_phy, priv); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Flushes previous write operations to chip so that a subsequent ++ * ioread*()s won't stall a cpu. ++ */ ++static inline void tpm_tis_flush(void __iomem *iobase) ++{ ++ ioread8(iobase + TPM_ACCESS(0)); ++} ++#else ++#define tpm_tis_flush(iobase) do { } while (0) ++#endif ++ ++static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr) ++{ ++ iowrite8(b, iobase + addr); ++ tpm_tis_flush(iobase); ++} ++ ++static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr) ++{ ++ iowrite32(b, iobase + addr); ++ tpm_tis_flush(iobase); ++} ++ + static int interrupts = -1; + module_param(interrupts, int, 0444); + MODULE_PARM_DESC(interrupts, "Enable interrupts"); +@@ -173,7 +198,7 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, + struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); + + while (len--) +- iowrite8(*value++, phy->iobase + addr); ++ tpm_tis_iowrite8(*value++, phy->iobase, addr); + + return 0; + } +@@ -200,7 +225,7 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value) + { + struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); + +- iowrite32(value, phy->iobase + addr); ++ tpm_tis_iowrite32(value, phy->iobase, addr); + + return 0; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0250-watchdog-prevent-deferral-of-watchdogd-wakeup-on-RT.patch b/debian/patches-rt/0250-watchdog-prevent-deferral-of-watchdogd-wakeup-on-RT.patch new file mode 100644 index 000000000..c9d461226 --- /dev/null +++ b/debian/patches-rt/0250-watchdog-prevent-deferral-of-watchdogd-wakeup-on-RT.patch @@ -0,0 +1,81 @@ +From 2536bb24992f08158455b5ad1434f439f6543db5 Mon Sep 17 00:00:00 2001 +From: Julia Cartwright <julia@ni.com> +Date: Fri, 28 Sep 2018 21:03:51 +0000 +Subject: [PATCH 250/347] watchdog: prevent deferral of watchdogd wakeup on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When PREEMPT_RT_FULL is enabled, all hrtimer expiry functions are +deferred for execution into the context of ktimersoftd unless otherwise +annotated. + +Deferring the expiry of the hrtimer used by the watchdog core, however, +is a waste, as the callback does nothing but queue a kthread work item +and wakeup watchdogd. + +It's worst then that, too: the deferral through ktimersoftd also means +that for correct behavior a user must adjust the scheduling parameters +of both watchdogd _and_ ktimersoftd, which is unnecessary and has other +side effects (like causing unrelated expiry functions to execute at +potentially elevated priority). + +Instead, mark the hrtimer used by the watchdog core as being _HARD to +allow it's execution directly from hardirq context. The work done in +this expiry function is well-bounded and minimal. + +A user still must adjust the scheduling parameters of the watchdogd +to be correct w.r.t. their application needs. + +Cc: Guenter Roeck <linux@roeck-us.net> +Reported-and-tested-by: Steffen Trumtrar <s.trumtrar@pengutronix.de> +Reported-by: Tim Sander <tim@krieglstein.org> +Signed-off-by: Julia Cartwright <julia@ni.com> +Acked-by: Guenter Roeck <linux@roeck-us.net> +[bigeasy: use only HRTIMER_MODE_REL_HARD] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/watchdog/watchdog_dev.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c +index 8fe59b7d8eec..516782cff8d2 100644 +--- a/drivers/watchdog/watchdog_dev.c ++++ b/drivers/watchdog/watchdog_dev.c +@@ -145,7 +145,7 @@ static inline void watchdog_update_worker(struct watchdog_device *wdd) + ktime_t t = watchdog_next_keepalive(wdd); + + if (t > 0) +- hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL); ++ hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL_HARD); + } else { + hrtimer_cancel(&wd_data->timer); + } +@@ -164,7 +164,7 @@ static int __watchdog_ping(struct watchdog_device *wdd) + if (ktime_after(earliest_keepalive, now)) { + hrtimer_start(&wd_data->timer, + ktime_sub(earliest_keepalive, now), +- HRTIMER_MODE_REL); ++ HRTIMER_MODE_REL_HARD); + return 0; + } + +@@ -959,7 +959,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) + dev_set_name(&wd_data->dev, "watchdog%d", wdd->id); + + kthread_init_work(&wd_data->work, watchdog_ping_work); +- hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + wd_data->timer.function = watchdog_timer_expired; + + if (wdd->id == 0) { +@@ -1007,7 +1007,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) + __module_get(wdd->ops->owner); + get_device(&wd_data->dev); + if (handle_boot_enabled) +- hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL); ++ hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL_HARD); + else + pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n", + wdd->id); +-- +2.36.1 + diff --git a/debian/patches-rt/0251-drm-radeon-i915-Use-preempt_disable-enable_rt-where-.patch b/debian/patches-rt/0251-drm-radeon-i915-Use-preempt_disable-enable_rt-where-.patch new file mode 100644 index 000000000..898eacd8a --- /dev/null +++ b/debian/patches-rt/0251-drm-radeon-i915-Use-preempt_disable-enable_rt-where-.patch @@ -0,0 +1,61 @@ +From f85948d1377d8e7d97d94d7d90250791825fc355 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Sat, 27 Feb 2016 08:09:11 +0100 +Subject: [PATCH 251/347] drm,radeon,i915: Use preempt_disable/enable_rt() + where recommended +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +DRM folks identified the spots, so use them. + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: linux-rt-users <linux-rt-users@vger.kernel.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/gpu/drm/i915/i915_irq.c | 2 ++ + drivers/gpu/drm/radeon/radeon_display.c | 2 ++ + 2 files changed, 4 insertions(+) + +diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c +index b7c398232136..eed1ba3009c6 100644 +--- a/drivers/gpu/drm/i915/i915_irq.c ++++ b/drivers/gpu/drm/i915/i915_irq.c +@@ -1025,6 +1025,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -1076,6 +1077,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + +diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c +index 5985efc5a1f3..de2552a40d36 100644 +--- a/drivers/gpu/drm/radeon/radeon_display.c ++++ b/drivers/gpu/drm/radeon/radeon_display.c +@@ -1818,6 +1818,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, + struct radeon_device *rdev = dev->dev_private; + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -1910,6 +1911,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + /* Decode into vertical and horizontal scanout position. */ + *vpos = position & 0x1fff; +-- +2.36.1 + diff --git a/debian/patches-rt/0252-drm-i915-Use-local_lock-unlock_irq-in-intel_pipe_upd.patch b/debian/patches-rt/0252-drm-i915-Use-local_lock-unlock_irq-in-intel_pipe_upd.patch new file mode 100644 index 000000000..dde8a6cd7 --- /dev/null +++ b/debian/patches-rt/0252-drm-i915-Use-local_lock-unlock_irq-in-intel_pipe_upd.patch @@ -0,0 +1,128 @@ +From d4f3a1228c468da8962aa6b9742e67924796defd Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Sat, 27 Feb 2016 09:01:42 +0100 +Subject: [PATCH 252/347] drm,i915: Use local_lock/unlock_irq() in + intel_pipe_update_start/end() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ 8.014039] BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:918 +[ 8.014041] in_atomic(): 0, irqs_disabled(): 1, pid: 78, name: kworker/u4:4 +[ 8.014045] CPU: 1 PID: 78 Comm: kworker/u4:4 Not tainted 4.1.7-rt7 #5 +[ 8.014055] Workqueue: events_unbound async_run_entry_fn +[ 8.014059] 0000000000000000 ffff880037153748 ffffffff815f32c9 0000000000000002 +[ 8.014063] ffff88013a50e380 ffff880037153768 ffffffff815ef075 ffff8800372c06c8 +[ 8.014066] ffff8800372c06c8 ffff880037153778 ffffffff8107c0b3 ffff880037153798 +[ 8.014067] Call Trace: +[ 8.014074] [<ffffffff815f32c9>] dump_stack+0x4a/0x61 +[ 8.014078] [<ffffffff815ef075>] ___might_sleep.part.93+0xe9/0xee +[ 8.014082] [<ffffffff8107c0b3>] ___might_sleep+0x53/0x80 +[ 8.014086] [<ffffffff815f9064>] rt_spin_lock+0x24/0x50 +[ 8.014090] [<ffffffff8109368b>] prepare_to_wait+0x2b/0xa0 +[ 8.014152] [<ffffffffa016c04c>] intel_pipe_update_start+0x17c/0x300 [i915] +[ 8.014156] [<ffffffff81093b40>] ? prepare_to_wait_event+0x120/0x120 +[ 8.014201] [<ffffffffa0158f36>] intel_begin_crtc_commit+0x166/0x1e0 [i915] +[ 8.014215] [<ffffffffa00c806d>] drm_atomic_helper_commit_planes+0x5d/0x1a0 [drm_kms_helper] +[ 8.014260] [<ffffffffa0171e9b>] intel_atomic_commit+0xab/0xf0 [i915] +[ 8.014288] [<ffffffffa00654c7>] drm_atomic_commit+0x37/0x60 [drm] +[ 8.014298] [<ffffffffa00c6fcd>] drm_atomic_helper_plane_set_property+0x8d/0xd0 [drm_kms_helper] +[ 8.014301] [<ffffffff815f77d9>] ? __ww_mutex_lock+0x39/0x40 +[ 8.014319] [<ffffffffa0053b3d>] drm_mode_plane_set_obj_prop+0x2d/0x90 [drm] +[ 8.014328] [<ffffffffa00c8edb>] restore_fbdev_mode+0x6b/0xf0 [drm_kms_helper] +[ 8.014337] [<ffffffffa00cae49>] drm_fb_helper_restore_fbdev_mode_unlocked+0x29/0x80 [drm_kms_helper] +[ 8.014346] [<ffffffffa00caec2>] drm_fb_helper_set_par+0x22/0x50 [drm_kms_helper] +[ 8.014390] [<ffffffffa016dfba>] intel_fbdev_set_par+0x1a/0x60 [i915] +[ 8.014394] [<ffffffff81327dc4>] fbcon_init+0x4f4/0x580 +[ 8.014398] [<ffffffff8139ef4c>] visual_init+0xbc/0x120 +[ 8.014401] [<ffffffff813a1623>] do_bind_con_driver+0x163/0x330 +[ 8.014405] [<ffffffff813a1b2c>] do_take_over_console+0x11c/0x1c0 +[ 8.014408] [<ffffffff813236e3>] do_fbcon_takeover+0x63/0xd0 +[ 8.014410] [<ffffffff81328965>] fbcon_event_notify+0x785/0x8d0 +[ 8.014413] [<ffffffff8107c12d>] ? __might_sleep+0x4d/0x90 +[ 8.014416] [<ffffffff810775fe>] notifier_call_chain+0x4e/0x80 +[ 8.014419] [<ffffffff810779cd>] __blocking_notifier_call_chain+0x4d/0x70 +[ 8.014422] [<ffffffff81077a06>] blocking_notifier_call_chain+0x16/0x20 +[ 8.014425] [<ffffffff8132b48b>] fb_notifier_call_chain+0x1b/0x20 +[ 8.014428] [<ffffffff8132d8fa>] register_framebuffer+0x21a/0x350 +[ 8.014439] [<ffffffffa00cb164>] drm_fb_helper_initial_config+0x274/0x3e0 [drm_kms_helper] +[ 8.014483] [<ffffffffa016f1cb>] intel_fbdev_initial_config+0x1b/0x20 [i915] +[ 8.014486] [<ffffffff8107912c>] async_run_entry_fn+0x4c/0x160 +[ 8.014490] [<ffffffff81070ffa>] process_one_work+0x14a/0x470 +[ 8.014493] [<ffffffff81071489>] worker_thread+0x169/0x4c0 +[ 8.014496] [<ffffffff81071320>] ? process_one_work+0x470/0x470 +[ 8.014499] [<ffffffff81076606>] kthread+0xc6/0xe0 +[ 8.014502] [<ffffffff81070000>] ? queue_work_on+0x80/0x110 +[ 8.014506] [<ffffffff81076540>] ? kthread_worker_fn+0x1c0/0x1c0 + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: linux-rt-users <linux-rt-users@vger.kernel.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/gpu/drm/i915/intel_sprite.c | 13 ++++++++----- + 1 file changed, 8 insertions(+), 5 deletions(-) + +diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c +index f7026e887fa9..07e4ddebdd80 100644 +--- a/drivers/gpu/drm/i915/intel_sprite.c ++++ b/drivers/gpu/drm/i915/intel_sprite.c +@@ -36,6 +36,7 @@ + #include <drm/drm_rect.h> + #include <drm/drm_atomic.h> + #include <drm/drm_plane_helper.h> ++#include <linux/locallock.h> + #include "intel_drv.h" + #include "intel_frontbuffer.h" + #include <drm/i915_drm.h> +@@ -60,6 +61,8 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode, + #define VBLANK_EVASION_TIME_US 100 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock); ++ + /** + * intel_pipe_update_start() - start update of a set of display registers + * @new_crtc_state: the new crtc state +@@ -107,7 +110,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) + if (intel_psr_wait_for_idle(new_crtc_state)) + DRM_ERROR("PSR idle timed out, atomic update may fail\n"); + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + + crtc->debug.min_vbl = min; + crtc->debug.max_vbl = max; +@@ -131,11 +134,11 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) + break; + } + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + timeout = schedule_timeout(timeout); + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + } + + finish_wait(wq, &wait); +@@ -168,7 +171,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) + return; + + irq_disable: +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + } + + /** +@@ -204,7 +207,7 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) + new_crtc_state->base.event = NULL; + } + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + if (intel_vgpu_active(dev_priv)) + return; +-- +2.36.1 + diff --git a/debian/patches-rt/0253-drm-i915-disable-tracing-on-RT.patch b/debian/patches-rt/0253-drm-i915-disable-tracing-on-RT.patch new file mode 100644 index 000000000..78662975e --- /dev/null +++ b/debian/patches-rt/0253-drm-i915-disable-tracing-on-RT.patch @@ -0,0 +1,47 @@ +From 5e32c1ba695c3d32da799c26e267183a4516ffb8 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 6 Dec 2018 09:52:20 +0100 +Subject: [PATCH 253/347] drm/i915: disable tracing on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Luca Abeni reported this: +| BUG: scheduling while atomic: kworker/u8:2/15203/0x00000003 +| CPU: 1 PID: 15203 Comm: kworker/u8:2 Not tainted 4.19.1-rt3 #10 +| Call Trace: +| rt_spin_lock+0x3f/0x50 +| gen6_read32+0x45/0x1d0 [i915] +| g4x_get_vblank_counter+0x36/0x40 [i915] +| trace_event_raw_event_i915_pipe_update_start+0x7d/0xf0 [i915] + +The tracing events use trace_i915_pipe_update_start() among other events +use functions acquire spin locks. A few trace points use +intel_get_crtc_scanline(), others use ->get_vblank_counter() wich also +might acquire a sleeping lock. + +Based on this I don't see any other way than disable trace points on RT. + +Cc: stable-rt@vger.kernel.org +Reported-by: Luca Abeni <lucabe72@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/i915_trace.h | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h +index b50c6b829715..cc54ec0ef75c 100644 +--- a/drivers/gpu/drm/i915/i915_trace.h ++++ b/drivers/gpu/drm/i915/i915_trace.h +@@ -2,6 +2,10 @@ + #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) + #define _I915_TRACE_H_ + ++#ifdef CONFIG_PREEMPT_RT_BASE ++#define NOTRACE ++#endif ++ + #include <linux/stringify.h> + #include <linux/types.h> + #include <linux/tracepoint.h> +-- +2.36.1 + diff --git a/debian/patches-rt/0254-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch b/debian/patches-rt/0254-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch new file mode 100644 index 000000000..773a63282 --- /dev/null +++ b/debian/patches-rt/0254-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch @@ -0,0 +1,33 @@ +From ce732f94a77dce31d3b008046d756121676cc0f4 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 19 Dec 2018 10:47:02 +0100 +Subject: [PATCH 254/347] drm/i915: skip DRM_I915_LOW_LEVEL_TRACEPOINTS with + NOTRACE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The order of the header files is important. If this header file is +included after tracepoint.h was included then the NOTRACE here becomes a +nop. Currently this happens for two .c files which use the tracepoitns +behind DRM_I915_LOW_LEVEL_TRACEPOINTS. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/i915_trace.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h +index cc54ec0ef75c..33028d8f470e 100644 +--- a/drivers/gpu/drm/i915/i915_trace.h ++++ b/drivers/gpu/drm/i915/i915_trace.h +@@ -683,7 +683,7 @@ DEFINE_EVENT(i915_request, i915_request_add, + TP_ARGS(rq) + ); + +-#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) ++#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) && !defined(NOTRACE) + DEFINE_EVENT(i915_request, i915_request_submit, + TP_PROTO(struct i915_request *rq), + TP_ARGS(rq) +-- +2.36.1 + diff --git a/debian/patches-rt/0255-cgroups-use-simple-wait-in-css_release.patch b/debian/patches-rt/0255-cgroups-use-simple-wait-in-css_release.patch new file mode 100644 index 000000000..684e7bd06 --- /dev/null +++ b/debian/patches-rt/0255-cgroups-use-simple-wait-in-css_release.patch @@ -0,0 +1,95 @@ +From 8aa689c199e634af88b029260b92afed2a93b215 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 13 Feb 2015 15:52:24 +0100 +Subject: [PATCH 255/347] cgroups: use simple wait in css_release() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +To avoid: +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +|in_atomic(): 1, irqs_disabled(): 0, pid: 92, name: rcuc/11 +|2 locks held by rcuc/11/92: +| #0: (rcu_callback){......}, at: [<ffffffff810e037e>] rcu_cpu_kthread+0x3de/0x940 +| #1: (rcu_read_lock_sched){......}, at: [<ffffffff81328390>] percpu_ref_call_confirm_rcu+0x0/0xd0 +|Preemption disabled at:[<ffffffff813284e2>] percpu_ref_switch_to_atomic_rcu+0x82/0xc0 +|CPU: 11 PID: 92 Comm: rcuc/11 Not tainted 3.18.7-rt0+ #1 +| ffff8802398cdf80 ffff880235f0bc28 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff880235f0bc48 ffffffff8109aa16 0000000000000000 +| ffff8802398cdf80 ffff880235f0bc78 ffffffff815b8dd4 000000000000df80 +|Call Trace: +| [<ffffffff815b3a12>] dump_stack+0x4f/0x7c +| [<ffffffff8109aa16>] __might_sleep+0x116/0x190 +| [<ffffffff815b8dd4>] rt_spin_lock+0x24/0x60 +| [<ffffffff8108d2cd>] queue_work_on+0x6d/0x1d0 +| [<ffffffff8110c881>] css_release+0x81/0x90 +| [<ffffffff8132844e>] percpu_ref_call_confirm_rcu+0xbe/0xd0 +| [<ffffffff813284e2>] percpu_ref_switch_to_atomic_rcu+0x82/0xc0 +| [<ffffffff810e03e5>] rcu_cpu_kthread+0x445/0x940 +| [<ffffffff81098a2d>] smpboot_thread_fn+0x18d/0x2d0 +| [<ffffffff810948d8>] kthread+0xe8/0x100 +| [<ffffffff815b9c3c>] ret_from_fork+0x7c/0xb0 + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/cgroup-defs.h | 2 ++ + kernel/cgroup/cgroup.c | 9 +++++---- + 2 files changed, 7 insertions(+), 4 deletions(-) + +diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h +index f92264d1ed4f..cc912f3dc203 100644 +--- a/include/linux/cgroup-defs.h ++++ b/include/linux/cgroup-defs.h +@@ -20,6 +20,7 @@ + #include <linux/u64_stats_sync.h> + #include <linux/workqueue.h> + #include <linux/bpf-cgroup.h> ++#include <linux/swork.h> + + #ifdef CONFIG_CGROUPS + +@@ -157,6 +158,7 @@ struct cgroup_subsys_state { + + /* percpu_ref killing and RCU release */ + struct work_struct destroy_work; ++ struct swork_event destroy_swork; + struct rcu_work destroy_rwork; + + /* +diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c +index 4e8284d8cacc..86b10cb1d68a 100644 +--- a/kernel/cgroup/cgroup.c ++++ b/kernel/cgroup/cgroup.c +@@ -4738,10 +4738,10 @@ static void css_free_rwork_fn(struct work_struct *work) + } + } + +-static void css_release_work_fn(struct work_struct *work) ++static void css_release_work_fn(struct swork_event *sev) + { + struct cgroup_subsys_state *css = +- container_of(work, struct cgroup_subsys_state, destroy_work); ++ container_of(sev, struct cgroup_subsys_state, destroy_swork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + +@@ -4803,8 +4803,8 @@ static void css_release(struct percpu_ref *ref) + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + +- INIT_WORK(&css->destroy_work, css_release_work_fn); +- queue_work(cgroup_destroy_wq, &css->destroy_work); ++ INIT_SWORK(&css->destroy_swork, css_release_work_fn); ++ swork_queue(&css->destroy_swork); + } + + static void init_and_link_css(struct cgroup_subsys_state *css, +@@ -5524,6 +5524,7 @@ static int __init cgroup_wq_init(void) + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); ++ BUG_ON(swork_get()); + return 0; + } + core_initcall(cgroup_wq_init); +-- +2.36.1 + diff --git a/debian/patches-rt/0256-cpuset-Convert-callback_lock-to-raw_spinlock_t.patch b/debian/patches-rt/0256-cpuset-Convert-callback_lock-to-raw_spinlock_t.patch new file mode 100644 index 000000000..68ac442a9 --- /dev/null +++ b/debian/patches-rt/0256-cpuset-Convert-callback_lock-to-raw_spinlock_t.patch @@ -0,0 +1,293 @@ +From fd27c495e357db5ecab593fc59617b9c3f39c770 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <efault@gmx.de> +Date: Sun, 8 Jan 2017 09:32:25 +0100 +Subject: [PATCH 256/347] cpuset: Convert callback_lock to raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The two commits below add up to a cpuset might_sleep() splat for RT: + +8447a0fee974 cpuset: convert callback_mutex to a spinlock +344736f29b35 cpuset: simplify cpuset_node_allowed API + +BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:995 +in_atomic(): 0, irqs_disabled(): 1, pid: 11718, name: cset +CPU: 135 PID: 11718 Comm: cset Tainted: G E 4.10.0-rt1-rt #4 +Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0056.R01.1409242327 09/24/2014 +Call Trace: + ? dump_stack+0x5c/0x81 + ? ___might_sleep+0xf4/0x170 + ? rt_spin_lock+0x1c/0x50 + ? __cpuset_node_allowed+0x66/0xc0 + ? ___slab_alloc+0x390/0x570 <disables IRQs> + ? anon_vma_fork+0x8f/0x140 + ? copy_page_range+0x6cf/0xb00 + ? anon_vma_fork+0x8f/0x140 + ? __slab_alloc.isra.74+0x5a/0x81 + ? anon_vma_fork+0x8f/0x140 + ? kmem_cache_alloc+0x1b5/0x1f0 + ? anon_vma_fork+0x8f/0x140 + ? copy_process.part.35+0x1670/0x1ee0 + ? _do_fork+0xdd/0x3f0 + ? _do_fork+0xdd/0x3f0 + ? do_syscall_64+0x61/0x170 + ? entry_SYSCALL64_slow_path+0x25/0x25 + +The later ensured that a NUMA box WILL take callback_lock in atomic +context by removing the allocator and reclaim path __GFP_HARDWALL +usage which prevented such contexts from taking callback_mutex. + +One option would be to reinstate __GFP_HARDWALL protections for +RT, however, as the 8447a0fee974 changelog states: + +The callback_mutex is only used to synchronize reads/updates of cpusets' +flags and cpu/node masks. These operations should always proceed fast so +there's no reason why we can't use a spinlock instead of the mutex. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith <efault@gmx.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/cgroup/cpuset.c | 66 +++++++++++++++++++++--------------------- + 1 file changed, 33 insertions(+), 33 deletions(-) + +diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c +index 35541e1dfad9..42ed4e497336 100644 +--- a/kernel/cgroup/cpuset.c ++++ b/kernel/cgroup/cpuset.c +@@ -288,7 +288,7 @@ static struct cpuset top_cpuset = { + */ + + static DEFINE_MUTEX(cpuset_mutex); +-static DEFINE_SPINLOCK(callback_lock); ++static DEFINE_RAW_SPINLOCK(callback_lock); + + static struct workqueue_struct *cpuset_migrate_mm_wq; + +@@ -922,9 +922,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) + continue; + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cp->effective_cpus, new_cpus); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + WARN_ON(!is_in_v2_mode() && + !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); +@@ -989,9 +989,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, + if (retval < 0) + return retval; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* use trialcs->cpus_allowed as a temp variable */ + update_cpumasks_hier(cs, trialcs->cpus_allowed); +@@ -1175,9 +1175,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) + continue; + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cp->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + WARN_ON(!is_in_v2_mode() && + !nodes_equal(cp->mems_allowed, cp->effective_mems)); +@@ -1245,9 +1245,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, + if (retval < 0) + goto done; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->mems_allowed = trialcs->mems_allowed; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* use trialcs->mems_allowed as a temp variable */ + update_nodemasks_hier(cs, &trialcs->mems_allowed); +@@ -1338,9 +1338,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->flags = trialcs->flags; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) + rebuild_sched_domains_locked(); +@@ -1761,7 +1761,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) + cpuset_filetype_t type = seq_cft(sf)->private; + int ret = 0; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + + switch (type) { + case FILE_CPULIST: +@@ -1780,7 +1780,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) + ret = -EINVAL; + } + +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + return ret; + } + +@@ -1995,12 +1995,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) + + cpuset_inc(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (is_in_v2_mode()) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + } +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) + goto out_unlock; +@@ -2027,12 +2027,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) + } + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->mems_allowed = parent->mems_allowed; + cs->effective_mems = parent->mems_allowed; + cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); + cpumask_copy(cs->effective_cpus, parent->cpus_allowed); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + out_unlock: + mutex_unlock(&cpuset_mutex); + return 0; +@@ -2071,7 +2071,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) + static void cpuset_bind(struct cgroup_subsys_state *root_css) + { + mutex_lock(&cpuset_mutex); +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + + if (is_in_v2_mode()) { + cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); +@@ -2082,7 +2082,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) + top_cpuset.mems_allowed = top_cpuset.effective_mems; + } + +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + mutex_unlock(&cpuset_mutex); + } + +@@ -2180,12 +2180,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs, + { + bool is_empty; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, new_cpus); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->mems_allowed = *new_mems; + cs->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* + * Don't call update_tasks_cpumask() if the cpuset becomes empty, +@@ -2222,10 +2222,10 @@ hotplug_update_tasks(struct cpuset *cs, + if (nodes_empty(*new_mems)) + *new_mems = parent_cs(cs)->effective_mems; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (cpus_updated) + update_tasks_cpumask(cs); +@@ -2318,21 +2318,21 @@ static void cpuset_hotplug_workfn(struct work_struct *work) + + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (!on_dfl) + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + cpumask_copy(top_cpuset.effective_cpus, &new_cpus); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } + + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (!on_dfl) + top_cpuset.mems_allowed = new_mems; + top_cpuset.effective_mems = new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + update_tasks_nodemask(&top_cpuset); + } + +@@ -2434,11 +2434,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) + { + unsigned long flags; + +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_cpus(task_cs(tsk), pmask); + rcu_read_unlock(); +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + } + + /** +@@ -2499,11 +2499,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) + nodemask_t mask; + unsigned long flags; + +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &mask); + rcu_read_unlock(); +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + + return mask; + } +@@ -2595,14 +2595,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) + return true; + + /* Not hardwall and node outside mems_allowed: scan up cpusets */ +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + + rcu_read_lock(); + cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); + rcu_read_unlock(); + +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + return allowed; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0257-apparmor-use-a-locallock-instead-preempt_disable.patch b/debian/patches-rt/0257-apparmor-use-a-locallock-instead-preempt_disable.patch new file mode 100644 index 000000000..c00ea5391 --- /dev/null +++ b/debian/patches-rt/0257-apparmor-use-a-locallock-instead-preempt_disable.patch @@ -0,0 +1,85 @@ +From bc99d234e02c1f42a9a71a2aca38406d1902582b Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 11 Oct 2017 17:43:49 +0200 +Subject: [PATCH 257/347] apparmor: use a locallock instead preempt_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +get_buffers() disables preemption which acts as a lock for the per-CPU +variable. Since we can't disable preemption here on RT, a local_lock is +lock is used in order to remain on the same CPU and not to have more +than one user within the critical section. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + security/apparmor/include/path.h | 19 ++++++++++++++++--- + security/apparmor/lsm.c | 2 +- + 2 files changed, 17 insertions(+), 4 deletions(-) + +diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h +index b6380c5f0097..12abfddb19c9 100644 +--- a/security/apparmor/include/path.h ++++ b/security/apparmor/include/path.h +@@ -40,8 +40,10 @@ struct aa_buffers { + + #include <linux/percpu.h> + #include <linux/preempt.h> ++#include <linux/locallock.h> + + DECLARE_PER_CPU(struct aa_buffers, aa_buffers); ++DECLARE_LOCAL_IRQ_LOCK(aa_buffers_lock); + + #define ASSIGN(FN, A, X, N) ((X) = FN(A, N)) + #define EVAL1(FN, A, X) ASSIGN(FN, A, X, 0) /*X = FN(0)*/ +@@ -51,7 +53,17 @@ DECLARE_PER_CPU(struct aa_buffers, aa_buffers); + + #define for_each_cpu_buffer(I) for ((I) = 0; (I) < MAX_PATH_BUFFERS; (I)++) + +-#ifdef CONFIG_DEBUG_PREEMPT ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void AA_BUG_PREEMPT_ENABLED(const char *s) ++{ ++ struct local_irq_lock *lv; ++ ++ lv = this_cpu_ptr(&aa_buffers_lock); ++ WARN_ONCE(lv->owner != current, ++ "__get_buffer without aa_buffers_lock\n"); ++} ++ ++#elif defined(CONFIG_DEBUG_PREEMPT) + #define AA_BUG_PREEMPT_ENABLED(X) AA_BUG(preempt_count() <= 0, X) + #else + #define AA_BUG_PREEMPT_ENABLED(X) /* nop */ +@@ -67,14 +79,15 @@ DECLARE_PER_CPU(struct aa_buffers, aa_buffers); + + #define get_buffers(X...) \ + do { \ +- struct aa_buffers *__cpu_var = get_cpu_ptr(&aa_buffers); \ ++ struct aa_buffers *__cpu_var; \ ++ __cpu_var = get_locked_ptr(aa_buffers_lock, &aa_buffers); \ + __get_buffers(__cpu_var, X); \ + } while (0) + + #define put_buffers(X, Y...) \ + do { \ + __put_buffers(X, Y); \ +- put_cpu_ptr(&aa_buffers); \ ++ put_locked_ptr(aa_buffers_lock, &aa_buffers); \ + } while (0) + + #endif /* __AA_PATH_H */ +diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c +index 898752b818dc..690c8fccd0a0 100644 +--- a/security/apparmor/lsm.c ++++ b/security/apparmor/lsm.c +@@ -45,7 +45,7 @@ + int apparmor_initialized; + + DEFINE_PER_CPU(struct aa_buffers, aa_buffers); +- ++DEFINE_LOCAL_IRQ_LOCK(aa_buffers_lock); + + /* + * LSM hook functions +-- +2.36.1 + diff --git a/debian/patches-rt/0258-workqueue-Prevent-deadlock-stall-on-RT.patch b/debian/patches-rt/0258-workqueue-Prevent-deadlock-stall-on-RT.patch new file mode 100644 index 000000000..10fe17fc0 --- /dev/null +++ b/debian/patches-rt/0258-workqueue-Prevent-deadlock-stall-on-RT.patch @@ -0,0 +1,207 @@ +From 95516b448b8dcc30ac9e5fc0e38c1c3d3f8ef930 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 27 Jun 2014 16:24:52 +0200 +Subject: [PATCH 258/347] workqueue: Prevent deadlock/stall on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Austin reported a XFS deadlock/stall on RT where scheduled work gets +never exececuted and tasks are waiting for each other for ever. + +The underlying problem is the modification of the RT code to the +handling of workers which are about to go to sleep. In mainline a +worker thread which goes to sleep wakes an idle worker if there is +more work to do. This happens from the guts of the schedule() +function. On RT this must be outside and the accessed data structures +are not protected against scheduling due to the spinlock to rtmutex +conversion. So the naive solution to this was to move the code outside +of the scheduler and protect the data structures by the pool +lock. That approach turned out to be a little naive as we cannot call +into that code when the thread blocks on a lock, as it is not allowed +to block on two locks in parallel. So we dont call into the worker +wakeup magic when the worker is blocked on a lock, which causes the +deadlock/stall observed by Austin and Mike. + +Looking deeper into that worker code it turns out that the only +relevant data structure which needs to be protected is the list of +idle workers which can be woken up. + +So the solution is to protect the list manipulation operations with +preempt_enable/disable pairs on RT and call unconditionally into the +worker code even when the worker is blocked on a lock. The preemption +protection is safe as there is nothing which can fiddle with the list +outside of thread context. + +Reported-and_tested-by: Austin Schuh <austin@peloton-tech.com> +Reported-and_tested-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Link: http://vger.kernel.org/r/alpine.DEB.2.10.1406271249510.5170@nanos +Cc: Richard Weinberger <richard.weinberger@gmail.com> +Cc: Steven Rostedt <rostedt@goodmis.org> +--- + kernel/sched/core.c | 6 +++-- + kernel/workqueue.c | 60 +++++++++++++++++++++++++++++++++++---------- + 2 files changed, 51 insertions(+), 15 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 0995748a3a1d..feaf4d5683af 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3615,9 +3615,8 @@ void __noreturn do_task_dead(void) + + static inline void sched_submit_work(struct task_struct *tsk) + { +- if (!tsk->state || tsk_is_pi_blocked(tsk)) ++ if (!tsk->state) + return; +- + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. +@@ -3631,6 +3630,9 @@ static inline void sched_submit_work(struct task_struct *tsk) + preempt_enable_no_resched(); + } + ++ if (tsk_is_pi_blocked(tsk)) ++ return; ++ + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. +diff --git a/kernel/workqueue.c b/kernel/workqueue.c +index 0c529f920232..91f5696cf335 100644 +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -126,6 +126,11 @@ enum { + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * ++ * On RT we need the extra protection via rt_lock_idle_list() for ++ * the list manipulations against read access from ++ * wq_worker_sleeping(). All other places are nicely serialized via ++ * pool->lock. ++ * + * A: wq_pool_attach_mutex protected. + * + * PL: wq_pool_mutex protected. +@@ -431,6 +436,31 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void rt_lock_idle_list(struct worker_pool *pool) ++{ ++ preempt_disable(); ++} ++static inline void rt_unlock_idle_list(struct worker_pool *pool) ++{ ++ preempt_enable(); ++} ++static inline void sched_lock_idle_list(struct worker_pool *pool) { } ++static inline void sched_unlock_idle_list(struct worker_pool *pool) { } ++#else ++static inline void rt_lock_idle_list(struct worker_pool *pool) { } ++static inline void rt_unlock_idle_list(struct worker_pool *pool) { } ++static inline void sched_lock_idle_list(struct worker_pool *pool) ++{ ++ spin_lock_irq(&pool->lock); ++} ++static inline void sched_unlock_idle_list(struct worker_pool *pool) ++{ ++ spin_unlock_irq(&pool->lock); ++} ++#endif ++ ++ + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -837,10 +867,16 @@ static struct worker *first_idle_worker(struct worker_pool *pool) + */ + static void wake_up_worker(struct worker_pool *pool) + { +- struct worker *worker = first_idle_worker(pool); ++ struct worker *worker; ++ ++ rt_lock_idle_list(pool); ++ ++ worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); ++ ++ rt_unlock_idle_list(pool); + } + + /** +@@ -869,7 +905,7 @@ void wq_worker_running(struct task_struct *task) + */ + void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *next, *worker = kthread_data(task); ++ struct worker *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -886,26 +922,18 @@ void wq_worker_sleeping(struct task_struct *task) + return; + + worker->sleeping = 1; +- spin_lock_irq(&pool->lock); + + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. +- * +- * NOT_RUNNING is clear. This means that we're bound to and +- * running on the local cpu w/ rq lock held and preemption +- * disabled, which in turn means that none else could be +- * manipulating idle_list, so dereferencing idle_list without pool +- * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) { +- next = first_idle_worker(pool); +- if (next) +- wake_up_process(next->task); ++ sched_lock_idle_list(pool); ++ wake_up_worker(pool); ++ sched_unlock_idle_list(pool); + } +- spin_unlock_irq(&pool->lock); + } + + /** +@@ -1678,7 +1706,9 @@ static void worker_enter_idle(struct worker *worker) + worker->last_active = jiffies; + + /* idle_list is LIFO */ ++ rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); ++ rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); +@@ -1711,7 +1741,9 @@ static void worker_leave_idle(struct worker *worker) + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + } + + static struct worker *alloc_worker(int node) +@@ -1876,7 +1908,9 @@ static void destroy_worker(struct worker *worker) + pool->nr_workers--; + pool->nr_idle--; + ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0259-signals-Allow-rt-tasks-to-cache-one-sigqueue-struct.patch b/debian/patches-rt/0259-signals-Allow-rt-tasks-to-cache-one-sigqueue-struct.patch new file mode 100644 index 000000000..271df4103 --- /dev/null +++ b/debian/patches-rt/0259-signals-Allow-rt-tasks-to-cache-one-sigqueue-struct.patch @@ -0,0 +1,213 @@ +From 257506013947ed8b9b81885786294572a53a0a59 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 3 Jul 2009 08:44:56 -0500 +Subject: [PATCH 259/347] signals: Allow rt tasks to cache one sigqueue struct +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +To avoid allocation allow rt tasks to cache one sigqueue struct in +task struct. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/sched.h | 2 ++ + include/linux/signal.h | 1 + + kernel/exit.c | 2 +- + kernel/fork.c | 1 + + kernel/signal.c | 69 +++++++++++++++++++++++++++++++++++++++--- + 5 files changed, 70 insertions(+), 5 deletions(-) + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 044bebd3d16f..e567fe2d7058 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -895,6 +895,8 @@ struct task_struct { + /* Signal handlers: */ + struct signal_struct *signal; + struct sighand_struct *sighand; ++ struct sigqueue *sigqueue_cache; ++ + sigset_t blocked; + sigset_t real_blocked; + /* Restored if set_restore_sigmask() was used: */ +diff --git a/include/linux/signal.h b/include/linux/signal.h +index 0be5ce2375cb..6495fda18c2c 100644 +--- a/include/linux/signal.h ++++ b/include/linux/signal.h +@@ -245,6 +245,7 @@ static inline void init_sigpending(struct sigpending *sig) + } + + extern void flush_sigqueue(struct sigpending *queue); ++extern void flush_task_sigqueue(struct task_struct *tsk); + + /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ + static inline int valid_signal(unsigned long sig) +diff --git a/kernel/exit.c b/kernel/exit.c +index 908e7a33e1fc..2a414fc71b87 100644 +--- a/kernel/exit.c ++++ b/kernel/exit.c +@@ -160,7 +160,7 @@ static void __exit_signal(struct task_struct *tsk) + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ +- flush_sigqueue(&tsk->pending); ++ flush_task_sigqueue(tsk); + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + +diff --git a/kernel/fork.c b/kernel/fork.c +index 51ec12803c0b..fdc61ac6a748 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1848,6 +1848,7 @@ static __latent_entropy struct task_struct *copy_process( + spin_lock_init(&p->alloc_lock); + + init_sigpending(&p->pending); ++ p->sigqueue_cache = NULL; + + p->utime = p->stime = p->gtime = 0; + #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME +diff --git a/kernel/signal.c b/kernel/signal.c +index 58bd3b3dd499..74f807bba0b8 100644 +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -19,6 +19,7 @@ + #include <linux/sched/task.h> + #include <linux/sched/task_stack.h> + #include <linux/sched/cputime.h> ++#include <linux/sched/rt.h> + #include <linux/fs.h> + #include <linux/tty.h> + #include <linux/binfmts.h> +@@ -398,13 +399,30 @@ void task_join_group_stop(struct task_struct *task) + task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); + } + ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ struct sigqueue *q = t->sigqueue_cache; ++ ++ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) ++ return NULL; ++ return q; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) ++ return 0; ++ return 1; ++} ++ + /* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ + static struct sigqueue * +-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) ++__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit, int fromslab) + { + struct sigqueue *q = NULL; + struct user_struct *user; +@@ -426,7 +444,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi + rcu_read_unlock(); + + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { +- q = kmem_cache_alloc(sigqueue_cachep, flags); ++ if (!fromslab) ++ q = get_task_cache(t); ++ if (!q) ++ q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } +@@ -443,6 +464,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi + return q; + } + ++static struct sigqueue * ++__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit) ++{ ++ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); ++} ++ + static void __sigqueue_free(struct sigqueue *q) + { + if (q->flags & SIGQUEUE_PREALLOC) +@@ -452,6 +480,21 @@ static void __sigqueue_free(struct sigqueue *q) + kmem_cache_free(sigqueue_cachep, q); + } + ++static void sigqueue_free_current(struct sigqueue *q) ++{ ++ struct user_struct *up; ++ ++ if (q->flags & SIGQUEUE_PREALLOC) ++ return; ++ ++ up = q->user; ++ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { ++ atomic_dec(&up->sigpending); ++ free_uid(up); ++ } else ++ __sigqueue_free(q); ++} ++ + void flush_sigqueue(struct sigpending *queue) + { + struct sigqueue *q; +@@ -464,6 +507,21 @@ void flush_sigqueue(struct sigpending *queue) + } + } + ++/* ++ * Called from __exit_signal. Flush tsk->pending and ++ * tsk->sigqueue_cache ++ */ ++void flush_task_sigqueue(struct task_struct *tsk) ++{ ++ struct sigqueue *q; ++ ++ flush_sigqueue(&tsk->pending); ++ ++ q = get_task_cache(tsk); ++ if (q) ++ kmem_cache_free(sigqueue_cachep, q); ++} ++ + /* + * Flush all pending signals for this kthread. + */ +@@ -587,7 +645,7 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, + (info->si_code == SI_TIMER) && + (info->si_sys_private); + +- __sigqueue_free(first); ++ sigqueue_free_current(first); + } else { + /* + * Ok, it wasn't in the queue. This must be +@@ -624,6 +682,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) + bool resched_timer = false; + int signr; + ++ WARN_ON_ONCE(tsk != current); ++ + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ +@@ -1762,7 +1822,8 @@ EXPORT_SYMBOL(kill_pid); + */ + struct sigqueue *sigqueue_alloc(void) + { +- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); ++ /* Preallocated sigqueue objects always from the slabcache ! */ ++ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); + + if (q) + q->flags |= SIGQUEUE_PREALLOC; +-- +2.36.1 + diff --git a/debian/patches-rt/0260-Add-localversion-for-RT-release.patch b/debian/patches-rt/0260-Add-localversion-for-RT-release.patch new file mode 100644 index 000000000..b4212f0a6 --- /dev/null +++ b/debian/patches-rt/0260-Add-localversion-for-RT-release.patch @@ -0,0 +1,22 @@ +From 0146607e465af932fed9f14bc6c3bd83e1723699 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 8 Jul 2011 20:25:16 +0200 +Subject: [PATCH 260/347] Add localversion for -RT release +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + localversion-rt | 1 + + 1 file changed, 1 insertion(+) + create mode 100644 localversion-rt + +diff --git a/localversion-rt b/localversion-rt +new file mode 100644 +index 000000000000..1199ebade17b +--- /dev/null ++++ b/localversion-rt +@@ -0,0 +1 @@ ++-rt16 +-- +2.36.1 + diff --git a/debian/patches-rt/0261-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch b/debian/patches-rt/0261-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch new file mode 100644 index 000000000..f86ebc321 --- /dev/null +++ b/debian/patches-rt/0261-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch @@ -0,0 +1,97 @@ +From 0e0334043fc179c95449e93c201474b96f1f8656 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 26 Mar 2019 18:31:54 +0100 +Subject: [PATCH 261/347] powerpc/pseries/iommu: Use a locallock instead + local_irq_save() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The locallock protects the per-CPU variable tce_page. The function +attempts to allocate memory while tce_page is protected (by disabling +interrupts). + +Use local_irq_save() instead of local_irq_disable(). + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + arch/powerpc/platforms/pseries/iommu.c | 16 ++++++++++------ + 1 file changed, 10 insertions(+), 6 deletions(-) + +diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c +index b1a08cb760e0..8ef818ad83ec 100644 +--- a/arch/powerpc/platforms/pseries/iommu.c ++++ b/arch/powerpc/platforms/pseries/iommu.c +@@ -38,6 +38,7 @@ + #include <linux/of.h> + #include <linux/iommu.h> + #include <linux/rculist.h> ++#include <linux/locallock.h> + #include <asm/io.h> + #include <asm/prom.h> + #include <asm/rtas.h> +@@ -212,6 +213,7 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, + } + + static DEFINE_PER_CPU(__be64 *, tce_page); ++static DEFINE_LOCAL_IRQ_LOCK(tcp_page_lock); + + static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + long npages, unsigned long uaddr, +@@ -233,7 +235,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + direction, attrs); + } + +- local_irq_save(flags); /* to protect tcep and the page behind it */ ++ /* to protect tcep and the page behind it */ ++ local_lock_irqsave(tcp_page_lock, flags); + + tcep = __this_cpu_read(tce_page); + +@@ -244,7 +247,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); + /* If allocation fails, fall back to the loop implementation */ + if (!tcep) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(tcp_page_lock, flags); + return tce_build_pSeriesLP(tbl->it_index, tcenum, + tbl->it_page_shift, + npages, uaddr, direction, attrs); +@@ -279,7 +282,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + tcenum += limit; + } while (npages > 0 && !rc); + +- local_irq_restore(flags); ++ local_unlock_irqrestore(tcp_page_lock, flags); + + if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { + ret = (int)rc; +@@ -450,13 +453,14 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, + DMA_BIDIRECTIONAL, 0); + } + +- local_irq_disable(); /* to protect tcep and the page behind it */ ++ /* to protect tcep and the page behind it */ ++ local_lock_irq(tcp_page_lock); + tcep = __this_cpu_read(tce_page); + + if (!tcep) { + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); + if (!tcep) { +- local_irq_enable(); ++ local_unlock_irq(tcp_page_lock); + return -ENOMEM; + } + __this_cpu_write(tce_page, tcep); +@@ -502,7 +506,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, + + /* error cleanup: caller will clear whole range */ + +- local_irq_enable(); ++ local_unlock_irq(tcp_page_lock); + return rc; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0262-powerpc-reshuffle-TIF-bits.patch b/debian/patches-rt/0262-powerpc-reshuffle-TIF-bits.patch new file mode 100644 index 000000000..423525f91 --- /dev/null +++ b/debian/patches-rt/0262-powerpc-reshuffle-TIF-bits.patch @@ -0,0 +1,152 @@ +From a32952376eefc4ff8ec9467ec77f2402c56491f5 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 22 Mar 2019 17:15:58 +0100 +Subject: [PATCH 262/347] powerpc: reshuffle TIF bits +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Powerpc32/64 does not compile because TIF_SYSCALL_TRACE's bit is higher +than 15 and the assembly instructions don't expect that. + +Move TIF_RESTOREALL, TIF_NOERROR to the higher bits and keep +TIF_NEED_RESCHED_LAZY in the lower range. As a result one split load is +needed and otherwise we can use immediates. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + arch/powerpc/include/asm/thread_info.h | 11 +++++++---- + arch/powerpc/kernel/entry_32.S | 12 +++++++----- + arch/powerpc/kernel/entry_64.S | 12 +++++++----- + 3 files changed, 21 insertions(+), 14 deletions(-) + +diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h +index ce316076bc52..64c3d1a720e2 100644 +--- a/arch/powerpc/include/asm/thread_info.h ++++ b/arch/powerpc/include/asm/thread_info.h +@@ -83,18 +83,18 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src + #define TIF_SIGPENDING 1 /* signal pending */ + #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ + #define TIF_FSCHECK 3 /* Check FS is USER_DS on return */ +-#define TIF_NEED_RESCHED_LAZY 4 /* lazy rescheduling necessary */ + #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ + #define TIF_PATCH_PENDING 6 /* pending live patching update */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ + #define TIF_SINGLESTEP 8 /* singlestepping active */ + #define TIF_NOHZ 9 /* in adaptive nohz mode */ + #define TIF_SECCOMP 10 /* secure computing */ +-#define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ +-#define TIF_NOERROR 12 /* Force successful syscall return */ ++ ++#define TIF_NEED_RESCHED_LAZY 11 /* lazy rescheduling necessary */ ++#define TIF_SYSCALL_TRACEPOINT 12 /* syscall tracepoint instrumentation */ ++ + #define TIF_NOTIFY_RESUME 13 /* callback before returning to user */ + #define TIF_UPROBE 14 /* breakpointed or single-stepping */ +-#define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ + #define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation + for stack store? */ + #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ +@@ -103,6 +103,9 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src + #endif + #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ + #define TIF_32BIT 20 /* 32 bit binary */ ++#define TIF_RESTOREALL 21 /* Restore all regs (implies NOERROR) */ ++#define TIF_NOERROR 22 /* Force successful syscall return */ ++ + + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) +diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S +index 3783f3ef17a4..44bcf1585bd1 100644 +--- a/arch/powerpc/kernel/entry_32.S ++++ b/arch/powerpc/kernel/entry_32.S +@@ -393,7 +393,9 @@ _GLOBAL(DoSyscall) + MTMSRD(r10) + lwz r9,TI_FLAGS(r12) + li r8,-MAX_ERRNO +- andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) ++ lis r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@h ++ ori r0,r0, (_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@l ++ and. r0,r9,r0 + bne- syscall_exit_work + cmplw 0,r3,r8 + blt+ syscall_exit_cont +@@ -511,13 +513,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) + b syscall_dotrace_cont + + syscall_exit_work: +- andi. r0,r9,_TIF_RESTOREALL ++ andis. r0,r9,_TIF_RESTOREALL@h + beq+ 0f + REST_NVGPRS(r1) + b 2f + 0: cmplw 0,r3,r8 + blt+ 1f +- andi. r0,r9,_TIF_NOERROR ++ andis. r0,r9,_TIF_NOERROR@h + bne- 1f + lwz r11,_CCR(r1) /* Load CR */ + neg r3,r3 +@@ -526,12 +528,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) + + 1: stw r6,RESULT(r1) /* Save result */ + stw r3,GPR3(r1) /* Update return value */ +-2: andi. r0,r9,(_TIF_PERSYSCALL_MASK) ++2: andis. r0,r9,(_TIF_PERSYSCALL_MASK)@h + beq 4f + + /* Clear per-syscall TIF flags if any are set. */ + +- li r11,_TIF_PERSYSCALL_MASK ++ lis r11,_TIF_PERSYSCALL_MASK@h + addi r12,r12,TI_FLAGS + 3: lwarx r8,0,r12 + andc r8,r8,r11 +diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S +index ef02e41d5d96..229cdb04e9b0 100644 +--- a/arch/powerpc/kernel/entry_64.S ++++ b/arch/powerpc/kernel/entry_64.S +@@ -250,7 +250,9 @@ system_call: /* label this so stack traces look sane */ + + ld r9,TI_FLAGS(r12) + li r11,-MAX_ERRNO +- andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) ++ lis r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@h ++ ori r0,r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@l ++ and. r0,r9,r0 + bne- .Lsyscall_exit_work + + andi. r0,r8,MSR_FP +@@ -363,25 +365,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + /* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr. + If TIF_NOERROR is set, just save r3 as it is. */ + +- andi. r0,r9,_TIF_RESTOREALL ++ andis. r0,r9,_TIF_RESTOREALL@h + beq+ 0f + REST_NVGPRS(r1) + b 2f + 0: cmpld r3,r11 /* r11 is -MAX_ERRNO */ + blt+ 1f +- andi. r0,r9,_TIF_NOERROR ++ andis. r0,r9,_TIF_NOERROR@h + bne- 1f + ld r5,_CCR(r1) + neg r3,r3 + oris r5,r5,0x1000 /* Set SO bit in CR */ + std r5,_CCR(r1) + 1: std r3,GPR3(r1) +-2: andi. r0,r9,(_TIF_PERSYSCALL_MASK) ++2: andis. r0,r9,(_TIF_PERSYSCALL_MASK)@h + beq 4f + + /* Clear per-syscall TIF flags if any are set. */ + +- li r11,_TIF_PERSYSCALL_MASK ++ lis r11,(_TIF_PERSYSCALL_MASK)@h + addi r12,r12,TI_FLAGS + 3: ldarx r10,0,r12 + andc r10,r10,r11 +-- +2.36.1 + diff --git a/debian/patches-rt/0263-tty-sysrq-Convert-show_lock-to-raw_spinlock_t.patch b/debian/patches-rt/0263-tty-sysrq-Convert-show_lock-to-raw_spinlock_t.patch new file mode 100644 index 000000000..25b626e50 --- /dev/null +++ b/debian/patches-rt/0263-tty-sysrq-Convert-show_lock-to-raw_spinlock_t.patch @@ -0,0 +1,63 @@ +From 80d2475bc6d0eacb1cf634c16818c86554fcee0c Mon Sep 17 00:00:00 2001 +From: Julien Grall <julien.grall@arm.com> +Date: Wed, 13 Mar 2019 11:40:34 +0000 +Subject: [PATCH 263/347] tty/sysrq: Convert show_lock to raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Systems which don't provide arch_trigger_cpumask_backtrace() will +invoke showacpu() from a smp_call_function() function which is invoked +with disabled interrupts even on -RT systems. + +The function acquires the show_lock lock which only purpose is to +ensure that the CPUs don't print simultaneously. Otherwise the +output would clash and it would be hard to tell the output from CPUx +apart from CPUy. + +On -RT the spin_lock() can not be acquired from this context. A +raw_spin_lock() is required. It will introduce the system's latency +by performing the sysrq request and other CPUs will block on the lock +until the request is done. This is okay because the user asked for a +backtrace of all active CPUs and under "normal circumstances in +production" this path should not be triggered. + +Signed-off-by: Julien Grall <julien.grall@arm.com> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy@linuxtronix.de: commit description] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/tty/sysrq.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c +index cee0274806c5..f785ca55fb85 100644 +--- a/drivers/tty/sysrq.c ++++ b/drivers/tty/sysrq.c +@@ -215,7 +215,7 @@ static struct sysrq_key_op sysrq_showlocks_op = { + #endif + + #ifdef CONFIG_SMP +-static DEFINE_SPINLOCK(show_lock); ++static DEFINE_RAW_SPINLOCK(show_lock); + + static void showacpu(void *dummy) + { +@@ -225,10 +225,10 @@ static void showacpu(void *dummy) + if (idle_cpu(smp_processor_id())) + return; + +- spin_lock_irqsave(&show_lock, flags); ++ raw_spin_lock_irqsave(&show_lock, flags); + pr_info("CPU%d:\n", smp_processor_id()); + show_stack(NULL, NULL); +- spin_unlock_irqrestore(&show_lock, flags); ++ raw_spin_unlock_irqrestore(&show_lock, flags); + } + + static void sysrq_showregs_othercpus(struct work_struct *dummy) +-- +2.36.1 + diff --git a/debian/patches-rt/0264-drm-i915-Don-t-disable-interrupts-independently-of-t.patch b/debian/patches-rt/0264-drm-i915-Don-t-disable-interrupts-independently-of-t.patch new file mode 100644 index 000000000..e95fb336e --- /dev/null +++ b/debian/patches-rt/0264-drm-i915-Don-t-disable-interrupts-independently-of-t.patch @@ -0,0 +1,51 @@ +From 31ae53586975d39dd03dabf5c944b498dcc73289 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 10 Apr 2019 11:01:37 +0200 +Subject: [PATCH 264/347] drm/i915: Don't disable interrupts independently of + the lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The locks (timeline->lock and rq->lock) need to be taken with disabled +interrupts. This is done in __retire_engine_request() by disabling the +interrupts independently of the locks itself. +While local_irq_disable()+spin_lock() equals spin_lock_irq() on vanilla +it does not on RT. Also, it is not obvious if there is a special reason +to why the interrupts are disabled independently of the lock. + +Enable/disable interrupts as part of the locking instruction. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/gpu/drm/i915/i915_request.c | 8 ++------ + 1 file changed, 2 insertions(+), 6 deletions(-) + +diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c +index 5c2c93cbab12..7124510b9131 100644 +--- a/drivers/gpu/drm/i915/i915_request.c ++++ b/drivers/gpu/drm/i915/i915_request.c +@@ -356,9 +356,7 @@ static void __retire_engine_request(struct intel_engine_cs *engine, + + GEM_BUG_ON(!i915_request_completed(rq)); + +- local_irq_disable(); +- +- spin_lock(&engine->timeline.lock); ++ spin_lock_irq(&engine->timeline.lock); + GEM_BUG_ON(!list_is_first(&rq->link, &engine->timeline.requests)); + list_del_init(&rq->link); + spin_unlock(&engine->timeline.lock); +@@ -372,9 +370,7 @@ static void __retire_engine_request(struct intel_engine_cs *engine, + GEM_BUG_ON(!atomic_read(&rq->i915->gt_pm.rps.num_waiters)); + atomic_dec(&rq->i915->gt_pm.rps.num_waiters); + } +- spin_unlock(&rq->lock); +- +- local_irq_enable(); ++ spin_unlock_irq(&rq->lock); + + /* + * The backing object for the context is done after switching to the +-- +2.36.1 + diff --git a/debian/patches-rt/0265-sched-completion-Fix-a-lockup-in-wait_for_completion.patch b/debian/patches-rt/0265-sched-completion-Fix-a-lockup-in-wait_for_completion.patch new file mode 100644 index 000000000..bf5c14343 --- /dev/null +++ b/debian/patches-rt/0265-sched-completion-Fix-a-lockup-in-wait_for_completion.patch @@ -0,0 +1,69 @@ +From 055b27065070862af1438159975c51c824ed6db1 Mon Sep 17 00:00:00 2001 +From: Corey Minyard <cminyard@mvista.com> +Date: Thu, 9 May 2019 14:33:20 -0500 +Subject: [PATCH 265/347] sched/completion: Fix a lockup in + wait_for_completion() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Consider following race: + + T0 T1 T2 + wait_for_completion() + do_wait_for_common() + __prepare_to_swait() + schedule() + complete() + x->done++ (0 -> 1) + raw_spin_lock_irqsave() + swake_up_locked() wait_for_completion() + wake_up_process(T0) + list_del_init() + raw_spin_unlock_irqrestore() + raw_spin_lock_irq(&x->wait.lock) + raw_spin_lock_irq(&x->wait.lock) x->done != UINT_MAX, 1 -> 0 + raw_spin_unlock_irq(&x->wait.lock) + return 1 + while (!x->done && timeout), + continue loop, not enqueued + on &x->wait + +Basically, the problem is that the original wait queues used in +completions did not remove the item from the queue in the wakeup +function, but swake_up_locked() does. + +Fix it by adding the thread to the wait queue inside the do loop. +The design of swait detects if it is already in the list and doesn't +do the list add again. + +Cc: stable-rt@vger.kernel.org +Fixes: a04ff6b4ec4ee7e ("completion: Use simple wait queues") +Signed-off-by: Corey Minyard <cminyard@mvista.com> +Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: shorten commit message ] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/sched/completion.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c +index 755a58084978..49c14137988e 100644 +--- a/kernel/sched/completion.c ++++ b/kernel/sched/completion.c +@@ -72,12 +72,12 @@ do_wait_for_common(struct completion *x, + if (!x->done) { + DECLARE_SWAITQUEUE(wait); + +- __prepare_to_swait(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } ++ __prepare_to_swait(&x->wait, &wait); + __set_current_state(state); + raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); +-- +2.36.1 + diff --git a/debian/patches-rt/0266-kthread-add-a-global-worker-thread.patch b/debian/patches-rt/0266-kthread-add-a-global-worker-thread.patch new file mode 100644 index 000000000..467bba0ef --- /dev/null +++ b/debian/patches-rt/0266-kthread-add-a-global-worker-thread.patch @@ -0,0 +1,180 @@ +From 840c9b4ba91e8486a177aafa9089c694248955c7 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 12 Feb 2019 15:09:38 +0100 +Subject: [PATCH 266/347] kthread: add a global worker thread. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 0532e87d9d44795221aa921ba7024bde689cc894 ] + +Add kthread_schedule_work() which uses a global kthread for all its +jobs. +Split the cgroup include to avoid recussive includes from interrupt.h. +Fixup everything that fails to build (and did not include all header). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +[ + Fixed up include in blk-cgroup.h reported by Juri Lelli + http://lkml.kernel.org/r/20190722083009.GE25636@localhost.localdomain +] +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/block/loop.c | 2 +- + drivers/spi/spi-rockchip.c | 1 + + include/linux/blk-cgroup.h | 2 +- + include/linux/kthread-cgroup.h | 17 +++++++++++++++++ + include/linux/kthread.h | 17 +++++++---------- + init/main.c | 1 + + kernel/kthread.c | 14 ++++++++++++++ + 7 files changed, 42 insertions(+), 12 deletions(-) + create mode 100644 include/linux/kthread-cgroup.h + +diff --git a/drivers/block/loop.c b/drivers/block/loop.c +index c31a76485c9c..d24660961343 100644 +--- a/drivers/block/loop.c ++++ b/drivers/block/loop.c +@@ -70,7 +70,7 @@ + #include <linux/writeback.h> + #include <linux/completion.h> + #include <linux/highmem.h> +-#include <linux/kthread.h> ++#include <linux/kthread-cgroup.h> + #include <linux/splice.h> + #include <linux/sysfs.h> + #include <linux/miscdevice.h> +diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c +index 185bbdce62b1..63b10236eb05 100644 +--- a/drivers/spi/spi-rockchip.c ++++ b/drivers/spi/spi-rockchip.c +@@ -22,6 +22,7 @@ + #include <linux/spi/spi.h> + #include <linux/pm_runtime.h> + #include <linux/scatterlist.h> ++#include <linux/interrupt.h> + + #define DRIVER_NAME "rockchip-spi" + +diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h +index 8f1be8b49391..dc26ce6d840d 100644 +--- a/include/linux/blk-cgroup.h ++++ b/include/linux/blk-cgroup.h +@@ -14,7 +14,7 @@ + * Nauman Rafique <nauman@google.com> + */ + +-#include <linux/cgroup.h> ++#include <linux/kthread-cgroup.h> + #include <linux/percpu_counter.h> + #include <linux/seq_file.h> + #include <linux/radix-tree.h> +diff --git a/include/linux/kthread-cgroup.h b/include/linux/kthread-cgroup.h +new file mode 100644 +index 000000000000..53d34bca9d72 +--- /dev/null ++++ b/include/linux/kthread-cgroup.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++#ifndef _LINUX_KTHREAD_CGROUP_H ++#define _LINUX_KTHREAD_CGROUP_H ++#include <linux/kthread.h> ++#include <linux/cgroup.h> ++ ++#ifdef CONFIG_BLK_CGROUP ++void kthread_associate_blkcg(struct cgroup_subsys_state *css); ++struct cgroup_subsys_state *kthread_blkcg(void); ++#else ++static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } ++static inline struct cgroup_subsys_state *kthread_blkcg(void) ++{ ++ return NULL; ++} ++#endif ++#endif +diff --git a/include/linux/kthread.h b/include/linux/kthread.h +index e0498e46d642..31140f0a6c2c 100644 +--- a/include/linux/kthread.h ++++ b/include/linux/kthread.h +@@ -4,7 +4,6 @@ + /* Simple interface for creating and stopping kernel threads without mess. */ + #include <linux/err.h> + #include <linux/sched.h> +-#include <linux/cgroup.h> + + __printf(4, 5) + struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), +@@ -109,7 +108,7 @@ struct kthread_delayed_work { + }; + + #define KTHREAD_WORKER_INIT(worker) { \ +- .lock = __SPIN_LOCK_UNLOCKED((worker).lock), \ ++ .lock = __RAW_SPIN_LOCK_UNLOCKED((worker).lock), \ + .work_list = LIST_HEAD_INIT((worker).work_list), \ + .delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\ + } +@@ -201,14 +200,12 @@ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); + + void kthread_destroy_worker(struct kthread_worker *worker); + +-#ifdef CONFIG_BLK_CGROUP +-void kthread_associate_blkcg(struct cgroup_subsys_state *css); +-struct cgroup_subsys_state *kthread_blkcg(void); +-#else +-static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } +-static inline struct cgroup_subsys_state *kthread_blkcg(void) ++extern struct kthread_worker kthread_global_worker; ++void kthread_init_global_worker(void); ++ ++static inline bool kthread_schedule_work(struct kthread_work *work) + { +- return NULL; ++ return kthread_queue_work(&kthread_global_worker, work); + } +-#endif ++ + #endif /* _LINUX_KTHREAD_H */ +diff --git a/init/main.c b/init/main.c +index 0d5763c5da28..f5d0917a4d4b 100644 +--- a/init/main.c ++++ b/init/main.c +@@ -1132,6 +1132,7 @@ static noinline void __init kernel_init_freeable(void) + smp_prepare_cpus(setup_max_cpus); + + workqueue_init(); ++ kthread_init_global_worker(); + + init_mm_internals(); + +diff --git a/kernel/kthread.c b/kernel/kthread.c +index c8cf4731ced8..6bbd391f0d9c 100644 +--- a/kernel/kthread.c ++++ b/kernel/kthread.c +@@ -20,6 +20,7 @@ + #include <linux/freezer.h> + #include <linux/ptrace.h> + #include <linux/uaccess.h> ++#include <linux/cgroup.h> + #include <trace/events/sched.h> + + static DEFINE_SPINLOCK(kthread_create_lock); +@@ -1244,6 +1245,19 @@ void kthread_destroy_worker(struct kthread_worker *worker) + } + EXPORT_SYMBOL(kthread_destroy_worker); + ++DEFINE_KTHREAD_WORKER(kthread_global_worker); ++EXPORT_SYMBOL(kthread_global_worker); ++ ++__init void kthread_init_global_worker(void) ++{ ++ kthread_global_worker.task = kthread_create(kthread_worker_fn, ++ &kthread_global_worker, ++ "kswork"); ++ if (WARN_ON(IS_ERR(kthread_global_worker.task))) ++ return; ++ wake_up_process(kthread_global_worker.task); ++} ++ + #ifdef CONFIG_BLK_CGROUP + /** + * kthread_associate_blkcg - associate blkcg to current kthread +-- +2.36.1 + diff --git a/debian/patches-rt/0267-arm-imx6-cpuidle-Use-raw_spinlock_t.patch b/debian/patches-rt/0267-arm-imx6-cpuidle-Use-raw_spinlock_t.patch new file mode 100644 index 000000000..469d00fed --- /dev/null +++ b/debian/patches-rt/0267-arm-imx6-cpuidle-Use-raw_spinlock_t.patch @@ -0,0 +1,52 @@ +From 2fba570810dc44f1b4e171167882ff311417e129 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 14 May 2019 17:07:44 +0200 +Subject: [PATCH 267/347] arm: imx6: cpuidle: Use raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 40d0332ec8312e9c090f0a5414d9c90e12b13611 ] + +The idle call back is invoked with disabled interrupts and requires +raw_spinlock_t locks to work. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + arch/arm/mach-imx/cpuidle-imx6q.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c +index 326e870d7123..d9ac80aa1eb0 100644 +--- a/arch/arm/mach-imx/cpuidle-imx6q.c ++++ b/arch/arm/mach-imx/cpuidle-imx6q.c +@@ -17,22 +17,22 @@ + #include "hardware.h" + + static int num_idle_cpus = 0; +-static DEFINE_SPINLOCK(cpuidle_lock); ++static DEFINE_RAW_SPINLOCK(cpuidle_lock); + + static int imx6q_enter_wait(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) + { +- spin_lock(&cpuidle_lock); ++ raw_spin_lock(&cpuidle_lock); + if (++num_idle_cpus == num_online_cpus()) + imx6_set_lpm(WAIT_UNCLOCKED); +- spin_unlock(&cpuidle_lock); ++ raw_spin_unlock(&cpuidle_lock); + + cpu_do_idle(); + +- spin_lock(&cpuidle_lock); ++ raw_spin_lock(&cpuidle_lock); + if (num_idle_cpus-- == num_online_cpus()) + imx6_set_lpm(WAIT_CLOCKED); +- spin_unlock(&cpuidle_lock); ++ raw_spin_unlock(&cpuidle_lock); + + return index; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0268-rcu-Don-t-allow-to-change-rcu_normal_after_boot-on-R.patch b/debian/patches-rt/0268-rcu-Don-t-allow-to-change-rcu_normal_after_boot-on-R.patch new file mode 100644 index 000000000..3e9b760d5 --- /dev/null +++ b/debian/patches-rt/0268-rcu-Don-t-allow-to-change-rcu_normal_after_boot-on-R.patch @@ -0,0 +1,36 @@ +From c06c2524bbfc1d9e9531a571fb86a03cd7965bd3 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 24 Jun 2019 18:29:13 +0200 +Subject: [PATCH 268/347] rcu: Don't allow to change rcu_normal_after_boot on + RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit c6c058c10577815a2491ce661876cff00a4c3b15 ] + +On RT rcu_normal_after_boot is enabled by default. +Don't allow to disable it on RT because the "expedited rcu" would +introduce latency spikes. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/rcu/update.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c +index 16d8dba23329..ed75addd3ccd 100644 +--- a/kernel/rcu/update.c ++++ b/kernel/rcu/update.c +@@ -69,7 +69,9 @@ module_param(rcu_expedited, int, 0); + extern int rcu_normal; /* from sysctl */ + module_param(rcu_normal, int, 0); + static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); ++#ifndef CONFIG_PREEMPT_RT_FULL + module_param(rcu_normal_after_boot, int, 0); ++#endif + #endif /* #ifndef CONFIG_TINY_RCU */ + + #ifdef CONFIG_DEBUG_LOCK_ALLOC +-- +2.36.1 + diff --git a/debian/patches-rt/0269-pci-switchtec-fix-stream_open.cocci-warnings.patch b/debian/patches-rt/0269-pci-switchtec-fix-stream_open.cocci-warnings.patch new file mode 100644 index 000000000..b754add55 --- /dev/null +++ b/debian/patches-rt/0269-pci-switchtec-fix-stream_open.cocci-warnings.patch @@ -0,0 +1,40 @@ +From 088093ff4b48997a7b7ee99d8dcdfd02b47bf472 Mon Sep 17 00:00:00 2001 +From: kbuild test robot <lkp@intel.com> +Date: Sat, 13 Apr 2019 11:22:51 +0800 +Subject: [PATCH 269/347] pci/switchtec: fix stream_open.cocci warnings +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 9462c69e29307adc95c289f50839d5d683973891 ] + +drivers/pci/switch/switchtec.c:395:1-17: ERROR: switchtec_fops: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix. + +Generated by: scripts/coccinelle/api/stream_open.cocci + +Cc: Kirill Smelkov <kirr@nexedi.com> +Cc: Julia Lawall <julia.lawall@lip6.fr> +Fixes: 8a29a3bae2a2 ("pci/switchtec: Don't use completion's wait queue") +Cc: stable-rt@vger.kernel.org # where it applies to +Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1904131849350.2536@hadrien +Signed-off-by: kbuild test robot <lkp@intel.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/pci/switch/switchtec.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c +index a8df847bedee..25d1f96cddc1 100644 +--- a/drivers/pci/switch/switchtec.c ++++ b/drivers/pci/switch/switchtec.c +@@ -356,7 +356,7 @@ static int switchtec_dev_open(struct inode *inode, struct file *filp) + return PTR_ERR(stuser); + + filp->private_data = stuser; +- nonseekable_open(inode, filp); ++ stream_open(inode, filp); + + dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser); + +-- +2.36.1 + diff --git a/debian/patches-rt/0270-sched-core-Drop-a-preempt_disable_rt-statement.patch b/debian/patches-rt/0270-sched-core-Drop-a-preempt_disable_rt-statement.patch new file mode 100644 index 000000000..c1c54692c --- /dev/null +++ b/debian/patches-rt/0270-sched-core-Drop-a-preempt_disable_rt-statement.patch @@ -0,0 +1,50 @@ +From 3b0ab176baa325b6e2d909c3d2ce7860873c1726 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 24 Jun 2019 19:33:16 +0200 +Subject: [PATCH 270/347] sched/core: Drop a preempt_disable_rt() statement +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 761126efdcbe3fa3e99c9079fa0ad6eca2f251f2 ] + +The caller holds a lock which already disables preemption. +Drop the preempt_disable_rt() statement in get_nohz_timer_target(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 9 ++------- + 1 file changed, 2 insertions(+), 7 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index feaf4d5683af..3b0f62be3ece 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -558,14 +558,11 @@ void resched_cpu(int cpu) + */ + int get_nohz_timer_target(void) + { +- int i, cpu; ++ int i, cpu = smp_processor_id(); + struct sched_domain *sd; + +- preempt_disable_rt(); +- cpu = smp_processor_id(); +- + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) +- goto preempt_en_rt; ++ return cpu; + + rcu_read_lock(); + for_each_domain(cpu, sd) { +@@ -584,8 +581,6 @@ int get_nohz_timer_target(void) + cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + unlock: + rcu_read_unlock(); +-preempt_en_rt: +- preempt_enable_rt(); + return cpu; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0271-timers-Redo-the-notification-of-canceling-timers-on-.patch b/debian/patches-rt/0271-timers-Redo-the-notification-of-canceling-timers-on-.patch new file mode 100644 index 000000000..46b7ac22c --- /dev/null +++ b/debian/patches-rt/0271-timers-Redo-the-notification-of-canceling-timers-on-.patch @@ -0,0 +1,650 @@ +From abca2e3959b31be6e2cbc9d1e8d6ddebf31df3ea Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 24 Jun 2019 19:39:06 +0200 +Subject: [PATCH 271/347] timers: Redo the notification of canceling timers on + -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit c71273154c2ad12e13333aada340ff30e826a11b ] + +Rework of the hrtimer, timer and posix-timer cancelation interface +on -RT. Instead of the swait/schedule interface we now have locks +which are taken while timer is active. During the cancellation of an +active timer the lock is acquired. The lock will then either +PI-boost the timer or block and wait until the timer completed. +The new code looks simpler and does not trigger a warning from +rcu_note_context_switch() anymore like reported by Grygorii Strashko +and Daniel Wagner. +The patches were contributed by Anna-Maria Gleixner. + +This is an all in one commit of the following patches: +| [PATCH] timers: Introduce expiry spin lock +| [PATCH] timers: Drop expiry lock after each timer invocation +| [PATCH] hrtimer: Introduce expiry spin lock +| [PATCH] posix-timers: move rcu out of union +| [PATCH] posix-timers: Add expiry lock + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + fs/timerfd.c | 5 +- + include/linux/hrtimer.h | 17 ++---- + include/linux/posix-timers.h | 1 + + kernel/time/alarmtimer.c | 2 +- + kernel/time/hrtimer.c | 36 ++++--------- + kernel/time/itimer.c | 2 +- + kernel/time/posix-cpu-timers.c | 23 ++++++++ + kernel/time/posix-timers.c | 69 ++++++++++-------------- + kernel/time/posix-timers.h | 2 + + kernel/time/timer.c | 96 ++++++++++++++++------------------ + 10 files changed, 118 insertions(+), 135 deletions(-) + +diff --git a/fs/timerfd.c b/fs/timerfd.c +index 82d0f52414a6..f845093466be 100644 +--- a/fs/timerfd.c ++++ b/fs/timerfd.c +@@ -471,10 +471,11 @@ static int do_timerfd_settime(int ufd, int flags, + break; + } + spin_unlock_irq(&ctx->wqh.lock); ++ + if (isalarm(ctx)) +- hrtimer_wait_for_timer(&ctx->t.alarm.timer); ++ hrtimer_grab_expiry_lock(&ctx->t.alarm.timer); + else +- hrtimer_wait_for_timer(&ctx->t.tmr); ++ hrtimer_grab_expiry_lock(&ctx->t.tmr); + } + + /* +diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h +index 082147c07831..aee31b1f0cc3 100644 +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -22,7 +22,6 @@ + #include <linux/percpu.h> + #include <linux/timer.h> + #include <linux/timerqueue.h> +-#include <linux/wait.h> + + struct hrtimer_clock_base; + struct hrtimer_cpu_base; +@@ -193,6 +192,8 @@ enum hrtimer_base_type { + * @nr_retries: Total number of hrtimer interrupt retries + * @nr_hangs: Total number of hrtimer interrupt hangs + * @max_hang_time: Maximum time spent in hrtimer_interrupt ++ * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are ++ * expired + * @expires_next: absolute time of the next event, is required for remote + * hrtimer enqueue; it is the total first expiry time (hard + * and soft hrtimer are taken into account) +@@ -220,12 +221,10 @@ struct hrtimer_cpu_base { + unsigned short nr_hangs; + unsigned int max_hang_time; + #endif ++ spinlock_t softirq_expiry_lock; + ktime_t expires_next; + struct hrtimer *next_timer; + ktime_t softirq_expires_next; +-#ifdef CONFIG_PREEMPT_RT_BASE +- wait_queue_head_t wait; +-#endif + struct hrtimer *softirq_next_timer; + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + } ____cacheline_aligned; +@@ -426,6 +425,7 @@ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, + + extern int hrtimer_cancel(struct hrtimer *timer); + extern int hrtimer_try_to_cancel(struct hrtimer *timer); ++extern void hrtimer_grab_expiry_lock(const struct hrtimer *timer); + + static inline void hrtimer_start_expires(struct hrtimer *timer, + enum hrtimer_mode mode) +@@ -443,13 +443,6 @@ static inline void hrtimer_restart(struct hrtimer *timer) + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + +-/* Softirq preemption could deadlock timer removal */ +-#ifdef CONFIG_PREEMPT_RT_BASE +- extern void hrtimer_wait_for_timer(const struct hrtimer *timer); +-#else +-# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) +-#endif +- + /* Query timers: */ + extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +@@ -481,7 +474,7 @@ static inline bool hrtimer_is_queued(struct hrtimer *timer) + * Helper function to check, whether the timer is running the callback + * function + */ +-static inline int hrtimer_callback_running(const struct hrtimer *timer) ++static inline int hrtimer_callback_running(struct hrtimer *timer) + { + return timer->base->running == timer; + } +diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h +index 0571b498db73..3e6c91bdf2ef 100644 +--- a/include/linux/posix-timers.h ++++ b/include/linux/posix-timers.h +@@ -15,6 +15,7 @@ struct cpu_timer_list { + u64 expires, incr; + struct task_struct *task; + int firing; ++ int firing_cpu; + }; + + /* +diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c +index f4c8cfde00b0..e7b983df6996 100644 +--- a/kernel/time/alarmtimer.c ++++ b/kernel/time/alarmtimer.c +@@ -438,7 +438,7 @@ int alarm_cancel(struct alarm *alarm) + int ret = alarm_try_to_cancel(alarm); + if (ret >= 0) + return ret; +- hrtimer_wait_for_timer(&alarm->timer); ++ hrtimer_grab_expiry_lock(&alarm->timer); + } + } + EXPORT_SYMBOL_GPL(alarm_cancel); +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index aa8f3177580a..bbc408f24f5d 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -981,33 +981,16 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) + } + EXPORT_SYMBOL_GPL(hrtimer_forward); + +-#ifdef CONFIG_PREEMPT_RT_BASE +-# define wake_up_timer_waiters(b) wake_up(&(b)->wait) +- +-/** +- * hrtimer_wait_for_timer - Wait for a running timer +- * +- * @timer: timer to wait for +- * +- * The function waits in case the timers callback function is +- * currently executed on the waitqueue of the timer base. The +- * waitqueue is woken up after the timer callback function has +- * finished execution. +- */ +-void hrtimer_wait_for_timer(const struct hrtimer *timer) ++void hrtimer_grab_expiry_lock(const struct hrtimer *timer) + { + struct hrtimer_clock_base *base = timer->base; + +- if (base && base->cpu_base && +- base->index >= HRTIMER_BASE_MONOTONIC_SOFT) +- wait_event(base->cpu_base->wait, +- !(hrtimer_callback_running(timer))); ++ if (base && base->cpu_base) { ++ spin_lock(&base->cpu_base->softirq_expiry_lock); ++ spin_unlock(&base->cpu_base->softirq_expiry_lock); ++ } + } + +-#else +-# define wake_up_timer_waiters(b) do { } while (0) +-#endif +- + /* + * enqueue_hrtimer - internal function to (re)start a timer + * +@@ -1291,7 +1274,7 @@ int hrtimer_cancel(struct hrtimer *timer) + + if (ret >= 0) + return ret; +- hrtimer_wait_for_timer(timer); ++ hrtimer_grab_expiry_lock(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1595,6 +1578,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) + unsigned long flags; + ktime_t now; + ++ spin_lock(&cpu_base->softirq_expiry_lock); + raw_spin_lock_irqsave(&cpu_base->lock, flags); + + now = hrtimer_update_base(cpu_base); +@@ -1604,7 +1588,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) + hrtimer_update_softirq_timer(cpu_base, true); + + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); +- wake_up_timer_waiters(cpu_base); ++ spin_unlock(&cpu_base->softirq_expiry_lock); + } + + #ifdef CONFIG_HIGH_RES_TIMERS +@@ -2014,9 +1998,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) + cpu_base->softirq_next_timer = NULL; + cpu_base->expires_next = KTIME_MAX; + cpu_base->softirq_expires_next = KTIME_MAX; +-#ifdef CONFIG_PREEMPT_RT_BASE +- init_waitqueue_head(&cpu_base->wait); +-#endif ++ spin_lock_init(&cpu_base->softirq_expiry_lock); + return 0; + } + +diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c +index 7650ee736964..48d977f947d9 100644 +--- a/kernel/time/itimer.c ++++ b/kernel/time/itimer.c +@@ -211,7 +211,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); +- hrtimer_wait_for_timer(&tsk->signal->real_timer); ++ hrtimer_grab_expiry_lock(timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); +diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c +index 2d29b269dc83..54632ed51c65 100644 +--- a/kernel/time/posix-cpu-timers.c ++++ b/kernel/time/posix-cpu-timers.c +@@ -792,6 +792,7 @@ check_timers_list(struct list_head *timers, + return t->expires; + + t->firing = 1; ++ t->firing_cpu = smp_processor_id(); + list_move_tail(&t->entry, firing); + } + +@@ -1138,6 +1139,20 @@ static inline int fastpath_timer_check(struct task_struct *tsk) + return 0; + } + ++static DEFINE_PER_CPU(spinlock_t, cpu_timer_expiry_lock) = __SPIN_LOCK_UNLOCKED(cpu_timer_expiry_lock); ++ ++void cpu_timers_grab_expiry_lock(struct k_itimer *timer) ++{ ++ int cpu = timer->it.cpu.firing_cpu; ++ ++ if (cpu >= 0) { ++ spinlock_t *expiry_lock = per_cpu_ptr(&cpu_timer_expiry_lock, cpu); ++ ++ spin_lock_irq(expiry_lock); ++ spin_unlock_irq(expiry_lock); ++ } ++} ++ + /* + * This is called from the timer interrupt handler. The irq handler has + * already updated our counts. We need to check if any timers fire now. +@@ -1148,6 +1163,7 @@ static void __run_posix_cpu_timers(struct task_struct *tsk) + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; ++ spinlock_t *expiry_lock; + + /* + * The fast path checks that there are no expired thread or thread +@@ -1156,6 +1172,9 @@ static void __run_posix_cpu_timers(struct task_struct *tsk) + if (!fastpath_timer_check(tsk)) + return; + ++ expiry_lock = this_cpu_ptr(&cpu_timer_expiry_lock); ++ spin_lock(expiry_lock); ++ + if (!lock_task_sighand(tsk, &flags)) + return; + /* +@@ -1190,6 +1209,7 @@ static void __run_posix_cpu_timers(struct task_struct *tsk) + list_del_init(&timer->it.cpu.entry); + cpu_firing = timer->it.cpu.firing; + timer->it.cpu.firing = 0; ++ timer->it.cpu.firing_cpu = -1; + /* + * The firing flag is -1 if we collided with a reset + * of the timer, which already reported this +@@ -1199,6 +1219,7 @@ static void __run_posix_cpu_timers(struct task_struct *tsk) + cpu_timer_fire(timer); + spin_unlock(&timer->it_lock); + } ++ spin_unlock(expiry_lock); + } + + #ifdef CONFIG_PREEMPT_RT_BASE +@@ -1466,6 +1487,8 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, + spin_unlock_irq(&timer.it_lock); + + while (error == TIMER_RETRY) { ++ ++ cpu_timers_grab_expiry_lock(&timer); + /* + * We need to handle case when timer was or is in the + * middle of firing. In other cases we already freed +diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c +index 2cf5aa704106..3fd433d2a767 100644 +--- a/kernel/time/posix-timers.c ++++ b/kernel/time/posix-timers.c +@@ -821,25 +821,20 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + +-/* +- * Protected by RCU! +- */ +-static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timr) ++static int common_hrtimer_try_to_cancel(struct k_itimer *timr) + { +-#ifdef CONFIG_PREEMPT_RT_FULL +- if (kc->timer_arm == common_hrtimer_arm) +- hrtimer_wait_for_timer(&timr->it.real.timer); +- else if (kc == &alarm_clock) +- hrtimer_wait_for_timer(&timr->it.alarm.alarmtimer.timer); +- else +- /* FIXME: Whacky hack for posix-cpu-timers */ +- schedule_timeout(1); +-#endif ++ return hrtimer_try_to_cancel(&timr->it.real.timer); + } + +-static int common_hrtimer_try_to_cancel(struct k_itimer *timr) ++static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timer) + { +- return hrtimer_try_to_cancel(&timr->it.real.timer); ++ if (kc->timer_arm == common_hrtimer_arm) ++ hrtimer_grab_expiry_lock(&timer->it.real.timer); ++ else if (kc == &alarm_clock) ++ hrtimer_grab_expiry_lock(&timer->it.alarm.alarmtimer.timer); ++ else ++ /* posix-cpu-timers */ ++ cpu_timers_grab_expiry_lock(timer); + } + + /* Set a POSIX.1b interval timer. */ +@@ -901,21 +896,21 @@ static int do_timer_settime(timer_t timer_id, int flags, + if (!timr) + return -EINVAL; + +- rcu_read_lock(); + kc = timr->kclock; + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; + else + error = kc->timer_set(timr, flags, new_spec64, old_spec64); + +- unlock_timer(timr, flag); + if (error == TIMER_RETRY) { ++ rcu_read_lock(); ++ unlock_timer(timr, flag); + timer_wait_for_callback(kc, timr); +- old_spec64 = NULL; // We already got the old time... + rcu_read_unlock(); ++ old_spec64 = NULL; // We already got the old time... + goto retry; + } +- rcu_read_unlock(); ++ unlock_timer(timr, flag); + + return error; + } +@@ -977,13 +972,21 @@ int common_timer_del(struct k_itimer *timer) + return 0; + } + +-static inline int timer_delete_hook(struct k_itimer *timer) ++static int timer_delete_hook(struct k_itimer *timer) + { + const struct k_clock *kc = timer->kclock; ++ int ret; + + if (WARN_ON_ONCE(!kc || !kc->timer_del)) + return -EINVAL; +- return kc->timer_del(timer); ++ ret = kc->timer_del(timer); ++ if (ret == TIMER_RETRY) { ++ rcu_read_lock(); ++ spin_unlock_irq(&timer->it_lock); ++ timer_wait_for_callback(kc, timer); ++ rcu_read_unlock(); ++ } ++ return ret; + } + + /* Delete a POSIX.1b interval timer. */ +@@ -997,15 +1000,8 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) + if (!timer) + return -EINVAL; + +- rcu_read_lock(); +- if (timer_delete_hook(timer) == TIMER_RETRY) { +- unlock_timer(timer, flags); +- timer_wait_for_callback(clockid_to_kclock(timer->it_clock), +- timer); +- rcu_read_unlock(); ++ if (timer_delete_hook(timer) == TIMER_RETRY) + goto retry_delete; +- } +- rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); +@@ -1031,20 +1027,9 @@ static void itimer_delete(struct k_itimer *timer) + retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + +- /* On RT we can race with a deletion */ +- if (!timer->it_signal) { +- unlock_timer(timer, flags); +- return; +- } +- +- if (timer_delete_hook(timer) == TIMER_RETRY) { +- rcu_read_lock(); +- unlock_timer(timer, flags); +- timer_wait_for_callback(clockid_to_kclock(timer->it_clock), +- timer); +- rcu_read_unlock(); ++ if (timer_delete_hook(timer) == TIMER_RETRY) + goto retry_delete; +- } ++ + list_del(&timer->list); + /* + * This keeps any tasks waiting on the spin lock from thinking +diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h +index ddb21145211a..725bd230a8db 100644 +--- a/kernel/time/posix-timers.h ++++ b/kernel/time/posix-timers.h +@@ -32,6 +32,8 @@ extern const struct k_clock clock_process; + extern const struct k_clock clock_thread; + extern const struct k_clock alarm_clock; + ++extern void cpu_timers_grab_expiry_lock(struct k_itimer *timer); ++ + int posix_timer_event(struct k_itimer *timr, int si_private); + + void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting); +diff --git a/kernel/time/timer.c b/kernel/time/timer.c +index c7bd68db6f63..a2be2277506d 100644 +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -45,7 +45,6 @@ + #include <linux/slab.h> + #include <linux/compat.h> + #include <linux/random.h> +-#include <linux/swait.h> + + #include <linux/uaccess.h> + #include <asm/unistd.h> +@@ -199,9 +198,7 @@ EXPORT_SYMBOL(jiffies_64); + struct timer_base { + raw_spinlock_t lock; + struct timer_list *running_timer; +-#ifdef CONFIG_PREEMPT_RT_FULL +- struct swait_queue_head wait_for_running_timer; +-#endif ++ spinlock_t expiry_lock; + unsigned long clk; + unsigned long next_expiry; + unsigned int cpu; +@@ -1201,33 +1198,6 @@ void add_timer_on(struct timer_list *timer, int cpu) + } + EXPORT_SYMBOL_GPL(add_timer_on); + +-#ifdef CONFIG_PREEMPT_RT_FULL +-/* +- * Wait for a running timer +- */ +-static void wait_for_running_timer(struct timer_list *timer) +-{ +- struct timer_base *base; +- u32 tf = timer->flags; +- +- if (tf & TIMER_MIGRATING) +- return; +- +- base = get_timer_base(tf); +- swait_event_exclusive(base->wait_for_running_timer, +- base->running_timer != timer); +-} +- +-# define wakeup_timer_waiters(b) swake_up_all(&(b)->wait_for_running_timer) +-#else +-static inline void wait_for_running_timer(struct timer_list *timer) +-{ +- cpu_relax(); +-} +- +-# define wakeup_timer_waiters(b) do { } while (0) +-#endif +- + /** + * del_timer - deactivate a timer. + * @timer: the timer to be deactivated +@@ -1257,14 +1227,8 @@ int del_timer(struct timer_list *timer) + } + EXPORT_SYMBOL(del_timer); + +-/** +- * try_to_del_timer_sync - Try to deactivate a timer +- * @timer: timer to delete +- * +- * This function tries to deactivate a timer. Upon successful (ret >= 0) +- * exit the timer is not queued and the handler is not running on any CPU. +- */ +-int try_to_del_timer_sync(struct timer_list *timer) ++static int __try_to_del_timer_sync(struct timer_list *timer, ++ struct timer_base **basep) + { + struct timer_base *base; + unsigned long flags; +@@ -1272,7 +1236,7 @@ int try_to_del_timer_sync(struct timer_list *timer) + + debug_assert_init(timer); + +- base = lock_timer_base(timer, &flags); ++ *basep = base = lock_timer_base(timer, &flags); + + if (base->running_timer != timer) + ret = detach_if_pending(timer, base, true); +@@ -1281,9 +1245,42 @@ int try_to_del_timer_sync(struct timer_list *timer) + + return ret; + } ++ ++/** ++ * try_to_del_timer_sync - Try to deactivate a timer ++ * @timer: timer to delete ++ * ++ * This function tries to deactivate a timer. Upon successful (ret >= 0) ++ * exit the timer is not queued and the handler is not running on any CPU. ++ */ ++int try_to_del_timer_sync(struct timer_list *timer) ++{ ++ struct timer_base *base; ++ ++ return __try_to_del_timer_sync(timer, &base); ++} + EXPORT_SYMBOL(try_to_del_timer_sync); + + #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++static int __del_timer_sync(struct timer_list *timer) ++{ ++ struct timer_base *base; ++ int ret; ++ ++ for (;;) { ++ ret = __try_to_del_timer_sync(timer, &base); ++ if (ret >= 0) ++ return ret; ++ ++ /* ++ * When accessing the lock, timers of base are no longer expired ++ * and so timer is no longer running. ++ */ ++ spin_lock(&base->expiry_lock); ++ spin_unlock(&base->expiry_lock); ++ } ++} ++ + /** + * del_timer_sync - deactivate a timer and wait for the handler to finish. + * @timer: the timer to be deactivated +@@ -1339,12 +1336,8 @@ int del_timer_sync(struct timer_list *timer) + * could lead to deadlock. + */ + WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); +- for (;;) { +- int ret = try_to_del_timer_sync(timer); +- if (ret >= 0) +- return ret; +- wait_for_running_timer(timer); +- } ++ ++ return __del_timer_sync(timer); + } + EXPORT_SYMBOL(del_timer_sync); + #endif +@@ -1409,11 +1402,15 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) + raw_spin_unlock(&base->lock); + call_timer_fn(timer, fn); + base->running_timer = NULL; ++ spin_unlock(&base->expiry_lock); ++ spin_lock(&base->expiry_lock); + raw_spin_lock(&base->lock); + } else { + raw_spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn); + base->running_timer = NULL; ++ spin_unlock(&base->expiry_lock); ++ spin_lock(&base->expiry_lock); + raw_spin_lock_irq(&base->lock); + } + } +@@ -1710,6 +1707,7 @@ static inline void __run_timers(struct timer_base *base) + if (!time_after_eq(jiffies, base->clk)) + return; + ++ spin_lock(&base->expiry_lock); + raw_spin_lock_irq(&base->lock); + + /* +@@ -1737,7 +1735,7 @@ static inline void __run_timers(struct timer_base *base) + expire_timers(base, heads + levels); + } + raw_spin_unlock_irq(&base->lock); +- wakeup_timer_waiters(base); ++ spin_unlock(&base->expiry_lock); + } + + /* +@@ -1984,9 +1982,7 @@ static void __init init_timer_cpu(int cpu) + base->cpu = cpu; + raw_spin_lock_init(&base->lock); + base->clk = jiffies; +-#ifdef CONFIG_PREEMPT_RT_FULL +- init_swait_queue_head(&base->wait_for_running_timer); +-#endif ++ spin_lock_init(&base->expiry_lock); + } + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0272-Revert-futex-Ensure-lock-unlock-symetry-versus-pi_lo.patch b/debian/patches-rt/0272-Revert-futex-Ensure-lock-unlock-symetry-versus-pi_lo.patch new file mode 100644 index 000000000..82f8bb5db --- /dev/null +++ b/debian/patches-rt/0272-Revert-futex-Ensure-lock-unlock-symetry-versus-pi_lo.patch @@ -0,0 +1,35 @@ +From 32f4aadb8254fd22b687cf1631c4859a2bf1b6bc Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 26 Jun 2019 17:44:13 +0200 +Subject: [PATCH 272/347] Revert "futex: Ensure lock/unlock symetry versus + pi_lock and hash bucket lock" +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 6a773b70cf105b46298ed3b44e77c102ce31d9ec ] + +Drop the RT fixup, the futex code will be changed to avoid the need for +the workaround. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/futex.c | 2 -- + 1 file changed, 2 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index a5a263a3efbf..3449a716a378 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -962,9 +962,7 @@ static void exit_pi_state_list(struct task_struct *curr) + if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); +- raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); +- raw_spin_lock_irq(&curr->pi_lock); + put_pi_state(pi_state); + continue; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0273-Revert-futex-Fix-bug-on-when-a-requeued-RT-task-time.patch b/debian/patches-rt/0273-Revert-futex-Fix-bug-on-when-a-requeued-RT-task-time.patch new file mode 100644 index 000000000..8b7b98e81 --- /dev/null +++ b/debian/patches-rt/0273-Revert-futex-Fix-bug-on-when-a-requeued-RT-task-time.patch @@ -0,0 +1,83 @@ +From 808788c03b3c849951c646819ad23ff2efaf78a9 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 26 Jun 2019 17:44:18 +0200 +Subject: [PATCH 273/347] Revert "futex: Fix bug on when a requeued RT task + times out" +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit f1a170cb3289a48df26cae3c60d77608f7a988bb ] + +Drop the RT fixup, the futex code will be changed to avoid the need for +the workaround. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/locking/rtmutex.c | 31 +------------------------------ + kernel/locking/rtmutex_common.h | 1 - + 2 files changed, 1 insertion(+), 31 deletions(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index ded2296f848a..a87b65447991 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -144,8 +144,7 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) + + static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) + { +- return waiter && waiter != PI_WAKEUP_INPROGRESS && +- waiter != PI_REQUEUE_INPROGRESS; ++ return waiter && waiter != PI_WAKEUP_INPROGRESS; + } + + /* +@@ -2349,34 +2348,6 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + if (try_to_take_rt_mutex(lock, task, NULL)) + return 1; + +-#ifdef CONFIG_PREEMPT_RT_FULL +- /* +- * In PREEMPT_RT there's an added race. +- * If the task, that we are about to requeue, times out, +- * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue +- * to skip this task. But right after the task sets +- * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then +- * block on the spin_lock(&hb->lock), which in RT is an rtmutex. +- * This will replace the PI_WAKEUP_INPROGRESS with the actual +- * lock that it blocks on. We *must not* place this task +- * on this proxy lock in that case. +- * +- * To prevent this race, we first take the task's pi_lock +- * and check if it has updated its pi_blocked_on. If it has, +- * we assume that it woke up and we return -EAGAIN. +- * Otherwise, we set the task's pi_blocked_on to +- * PI_REQUEUE_INPROGRESS, so that if the task is waking up +- * it will know that we are in the process of requeuing it. +- */ +- raw_spin_lock(&task->pi_lock); +- if (task->pi_blocked_on) { +- raw_spin_unlock(&task->pi_lock); +- return -EAGAIN; +- } +- task->pi_blocked_on = PI_REQUEUE_INPROGRESS; +- raw_spin_unlock(&task->pi_lock); +-#endif +- + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 8e0c592273e6..627340e7427e 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -133,7 +133,6 @@ enum rtmutex_chainwalk { + * PI-futex support (proxy locking functions, etc.): + */ + #define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +-#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, +-- +2.36.1 + diff --git a/debian/patches-rt/0274-Revert-rtmutex-Handle-the-various-new-futex-race-con.patch b/debian/patches-rt/0274-Revert-rtmutex-Handle-the-various-new-futex-race-con.patch new file mode 100644 index 000000000..f8fd52438 --- /dev/null +++ b/debian/patches-rt/0274-Revert-rtmutex-Handle-the-various-new-futex-race-con.patch @@ -0,0 +1,249 @@ +From 206aee0eb3ade56ba7f62d90334791f6808738dc Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 26 Jun 2019 17:44:21 +0200 +Subject: [PATCH 274/347] Revert "rtmutex: Handle the various new futex race + conditions" +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 9e0265c21af4d6388d47dcd5ce20f76ec3a2e468 ] + +Drop the RT fixup, the futex code will be changed to avoid the need for +the workaround. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/futex.c | 75 ++++++--------------------------- + kernel/locking/rtmutex.c | 36 +++------------- + kernel/locking/rtmutex_common.h | 2 - + 3 files changed, 20 insertions(+), 93 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index 3449a716a378..bcd01b5a47df 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2255,16 +2255,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; +- } else if (ret == -EAGAIN) { +- /* +- * Waiter was woken by timeout or +- * signal and has set pi_blocked_on to +- * PI_WAKEUP_INPROGRESS before we +- * tried to enqueue it on the rtmutex. +- */ +- this->pi_state = NULL; +- put_pi_state(pi_state); +- continue; + } else if (ret) { + /* + * rt_mutex_start_proxy_lock() detected a +@@ -3343,7 +3333,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + { + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; +- struct futex_hash_bucket *hb, *hb2; ++ struct futex_hash_bucket *hb; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -3401,55 +3391,20 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- /* +- * On RT we must avoid races with requeue and trying to block +- * on two mutexes (hb->lock and uaddr2's rtmutex) by +- * serializing access to pi_blocked_on with pi_lock. +- */ +- raw_spin_lock_irq(¤t->pi_lock); +- if (current->pi_blocked_on) { +- /* +- * We have been requeued or are in the process of +- * being requeued. +- */ +- raw_spin_unlock_irq(¤t->pi_lock); +- } else { +- /* +- * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS +- * prevents a concurrent requeue from moving us to the +- * uaddr2 rtmutex. After that we can safely acquire +- * (and possibly block on) hb->lock. +- */ +- current->pi_blocked_on = PI_WAKEUP_INPROGRESS; +- raw_spin_unlock_irq(¤t->pi_lock); +- +- spin_lock(&hb->lock); +- +- /* +- * Clean up pi_blocked_on. We might leak it otherwise +- * when we succeeded with the hb->lock in the fast +- * path. +- */ +- raw_spin_lock_irq(¤t->pi_lock); +- current->pi_blocked_on = NULL; +- raw_spin_unlock_irq(¤t->pi_lock); +- +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; +- } ++ spin_lock(&hb->lock); ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; + + /* +- * In order to be here, we have either been requeued, are in +- * the process of being requeued, or requeue successfully +- * acquired uaddr2 on our behalf. If pi_blocked_on was +- * non-null above, we may be racing with a requeue. Do not +- * rely on q->lock_ptr to be hb2->lock until after blocking on +- * hb->lock or hb2->lock. The futex_requeue dropped our key1 +- * reference and incremented our key2 reference count. ++ * In order for us to be here, we know our q.key == key2, and since ++ * we took the hb->lock above, we also know that futex_requeue() has ++ * completed and we no longer have to concern ourselves with a wakeup ++ * race with the atomic proxy lock acquisition by the requeue code. The ++ * futex_requeue dropped our key1 reference and incremented our key2 ++ * reference count. + */ +- hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -3458,8 +3413,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(&hb2->lock); +- BUG_ON(&hb2->lock != q.lock_ptr); ++ spin_lock(q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which +@@ -3485,8 +3439,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + pi_mutex = &q.pi_state->pi_mutex; + ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); + +- spin_lock(&hb2->lock); +- BUG_ON(&hb2->lock != q.lock_ptr); ++ spin_lock(q.lock_ptr); + if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) + ret = 0; + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index a87b65447991..05fcf8a75a51 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -142,11 +142,6 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } + +-static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) +-{ +- return waiter && waiter != PI_WAKEUP_INPROGRESS; +-} +- + /* + * We can speed up the acquire/release, if there's no debugging state to be + * set up. +@@ -420,8 +415,7 @@ int max_lock_depth = 1024; + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return rt_mutex_real_waiter(p->pi_blocked_on) ? +- p->pi_blocked_on->lock : NULL; ++ return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; + } + + /* +@@ -557,7 +551,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!rt_mutex_real_waiter(waiter)) ++ if (!waiter) + goto out_unlock_pi; + + /* +@@ -1327,22 +1321,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + return -EDEADLK; + + raw_spin_lock(&task->pi_lock); +- /* +- * In the case of futex requeue PI, this will be a proxy +- * lock. The task will wake unaware that it is enqueueed on +- * this lock. Avoid blocking on two locks and corrupting +- * pi_blocked_on via the PI_WAKEUP_INPROGRESS +- * flag. futex_wait_requeue_pi() sets this when it wakes up +- * before requeue (due to a signal or timeout). Do not enqueue +- * the task if PI_WAKEUP_INPROGRESS is set. +- */ +- if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { +- raw_spin_unlock(&task->pi_lock); +- return -EAGAIN; +- } +- +- BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); +- + waiter->task = task; + waiter->lock = lock; + waiter->prio = task->prio; +@@ -1366,7 +1344,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + rt_mutex_enqueue_pi(owner, waiter); + + rt_mutex_adjust_prio(owner); +- if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ if (owner->pi_blocked_on) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -1466,7 +1444,7 @@ static void remove_waiter(struct rt_mutex *lock, + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock = NULL; ++ struct rt_mutex *next_lock; + + lockdep_assert_held(&lock->wait_lock); + +@@ -1492,8 +1470,7 @@ static void remove_waiter(struct rt_mutex *lock, + rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- if (rt_mutex_real_waiter(owner->pi_blocked_on)) +- next_lock = task_blocked_on_lock(owner); ++ next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock(&owner->pi_lock); + +@@ -1529,8 +1506,7 @@ void rt_mutex_adjust_pi(struct task_struct *task) + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!rt_mutex_real_waiter(waiter) || +- rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { ++ if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index 627340e7427e..f587e0422d23 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -132,8 +132,6 @@ enum rtmutex_chainwalk { + /* + * PI-futex support (proxy locking functions, etc.): + */ +-#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +- + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); +-- +2.36.1 + diff --git a/debian/patches-rt/0275-Revert-futex-workaround-migrate_disable-enable-in-di.patch b/debian/patches-rt/0275-Revert-futex-workaround-migrate_disable-enable-in-di.patch new file mode 100644 index 000000000..6d5ad8916 --- /dev/null +++ b/debian/patches-rt/0275-Revert-futex-workaround-migrate_disable-enable-in-di.patch @@ -0,0 +1,70 @@ +From 42f821c624f6605415eed76cbf5ece8a41b47ddf Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 26 Jun 2019 17:44:27 +0200 +Subject: [PATCH 275/347] Revert "futex: workaround migrate_disable/enable in + different context" +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit a71221d81cc4873891ae44f3aa02df596079b786 ] + +Drop the RT fixup, the futex code will be changed to avoid the need for +the workaround. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/futex.c | 19 ------------------- + 1 file changed, 19 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index bcd01b5a47df..9bcfdcffb2dd 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2998,14 +2998,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + * before __rt_mutex_start_proxy_lock() is done. + */ + raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); +- /* +- * the migrate_disable() here disables migration in the in_atomic() fast +- * path which is enabled again in the following spin_unlock(). We have +- * one migrate_disable() pending in the slow-path which is reversed +- * after the raw_spin_unlock_irq() where we leave the atomic context. +- */ +- migrate_disable(); +- + spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter +@@ -3014,7 +3006,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + */ + ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); + raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); +- migrate_enable(); + + if (ret) { + if (ret == 1) +@@ -3149,21 +3140,11 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + * rt_waiter. Also see the WARN in wake_futex_pi(). + */ + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); +- /* +- * Magic trickery for now to make the RT migrate disable +- * logic happy. The following spin_unlock() happens with +- * interrupts disabled so the internal migrate_enable() +- * won't undo the migrate_disable() which was issued when +- * locking hb->lock. +- */ +- migrate_disable(); + spin_unlock(&hb->lock); + + /* drops pi_state->pi_mutex.wait_lock */ + ret = wake_futex_pi(uaddr, uval, pi_state); + +- migrate_enable(); +- + put_pi_state(pi_state); + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0276-futex-Make-the-futex_hash_bucket-lock-raw.patch b/debian/patches-rt/0276-futex-Make-the-futex_hash_bucket-lock-raw.patch new file mode 100644 index 000000000..da5c08609 --- /dev/null +++ b/debian/patches-rt/0276-futex-Make-the-futex_hash_bucket-lock-raw.patch @@ -0,0 +1,340 @@ +From 07c4f7b101fb3ad4704efeda1f43246b289b62ad Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 26 Jun 2019 11:59:44 +0200 +Subject: [PATCH 276/347] futex: Make the futex_hash_bucket lock raw +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit f646521aadedab78801c9befe193e2e8a0c99298 ] + +Since commit 1a1fb985f2e2b ("futex: Handle early deadlock return +correctly") we can deadlock while we attempt to acquire the HB lock if +we fail to acquire the lock. +The RT waiter (for the futex lock) is still enqueued and acquiring the +HB lock may build up a lock chain which leads to a deadlock if the owner +of the lock futex-lock holds the HB lock. + +Make the hash bucket lock raw so it does not participate in the +lockchain. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/futex.c | 86 +++++++++++++++++++++++++------------------------- + 1 file changed, 43 insertions(+), 43 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index 9bcfdcffb2dd..8a49dd71b233 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -243,7 +243,7 @@ struct futex_q { + struct plist_node list; + + struct task_struct *task; +- spinlock_t *lock_ptr; ++ raw_spinlock_t *lock_ptr; + union futex_key key; + struct futex_pi_state *pi_state; + struct rt_mutex_waiter *rt_waiter; +@@ -264,7 +264,7 @@ static const struct futex_q futex_q_init = { + */ + struct futex_hash_bucket { + atomic_t waiters; +- spinlock_t lock; ++ raw_spinlock_t lock; + struct plist_head chain; + } ____cacheline_aligned_in_smp; + +@@ -952,7 +952,7 @@ static void exit_pi_state_list(struct task_struct *curr) + } + raw_spin_unlock_irq(&curr->pi_lock); + +- spin_lock(&hb->lock); ++ raw_spin_lock(&hb->lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); + /* +@@ -962,7 +962,7 @@ static void exit_pi_state_list(struct task_struct *curr) + if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + put_pi_state(pi_state); + continue; + } +@@ -974,7 +974,7 @@ static void exit_pi_state_list(struct task_struct *curr) + + raw_spin_unlock(&curr->pi_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + + rt_mutex_futex_unlock(&pi_state->pi_mutex); + put_pi_state(pi_state); +@@ -1523,7 +1523,7 @@ static void __unqueue_futex(struct futex_q *q) + { + struct futex_hash_bucket *hb; + +- if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr)) ++ if (WARN_ON_SMP(!q->lock_ptr || !raw_spin_is_locked(q->lock_ptr)) + || WARN_ON(plist_node_empty(&q->list))) + return; + +@@ -1643,21 +1643,21 @@ static inline void + double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) + { + if (hb1 <= hb2) { +- spin_lock(&hb1->lock); ++ raw_spin_lock(&hb1->lock); + if (hb1 < hb2) +- spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); ++ raw_spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); + } else { /* hb1 > hb2 */ +- spin_lock(&hb2->lock); +- spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING); ++ raw_spin_lock(&hb2->lock); ++ raw_spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING); + } + } + + static inline void + double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) + { +- spin_unlock(&hb1->lock); ++ raw_spin_unlock(&hb1->lock); + if (hb1 != hb2) +- spin_unlock(&hb2->lock); ++ raw_spin_unlock(&hb2->lock); + } + + /* +@@ -1685,7 +1685,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) + if (!hb_waiters_pending(hb)) + goto out_put_key; + +- spin_lock(&hb->lock); ++ raw_spin_lock(&hb->lock); + + plist_for_each_entry_safe(this, next, &hb->chain, list) { + if (match_futex (&this->key, &key)) { +@@ -1704,7 +1704,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) + } + } + +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + wake_up_q(&wake_q); + out_put_key: + put_futex_key(&key); +@@ -2326,7 +2326,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) + + q->lock_ptr = &hb->lock; + +- spin_lock(&hb->lock); /* implies smp_mb(); (A) */ ++ raw_spin_lock(&hb->lock); /* implies smp_mb(); (A) */ + return hb; + } + +@@ -2334,7 +2334,7 @@ static inline void + queue_unlock(struct futex_hash_bucket *hb) + __releases(&hb->lock) + { +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + hb_waiters_dec(hb); + } + +@@ -2373,7 +2373,7 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) + __releases(&hb->lock) + { + __queue_me(q, hb); +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + } + + /** +@@ -2389,41 +2389,41 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) + */ + static int unqueue_me(struct futex_q *q) + { +- spinlock_t *lock_ptr; ++ raw_spinlock_t *lock_ptr; + int ret = 0; + + /* In the common case we don't take the spinlock, which is nice. */ + retry: + /* +- * q->lock_ptr can change between this read and the following spin_lock. +- * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and +- * optimizing lock_ptr out of the logic below. ++ * q->lock_ptr can change between this read and the following ++ * raw_spin_lock. Use READ_ONCE to forbid the compiler from reloading ++ * q->lock_ptr and optimizing lock_ptr out of the logic below. + */ + lock_ptr = READ_ONCE(q->lock_ptr); + if (lock_ptr != NULL) { +- spin_lock(lock_ptr); ++ raw_spin_lock(lock_ptr); + /* + * q->lock_ptr can change between reading it and +- * spin_lock(), causing us to take the wrong lock. This ++ * raw_spin_lock(), causing us to take the wrong lock. This + * corrects the race condition. + * + * Reasoning goes like this: if we have the wrong lock, + * q->lock_ptr must have changed (maybe several times) +- * between reading it and the spin_lock(). It can +- * change again after the spin_lock() but only if it was +- * already changed before the spin_lock(). It cannot, ++ * between reading it and the raw_spin_lock(). It can ++ * change again after the raw_spin_lock() but only if it was ++ * already changed before the raw_spin_lock(). It cannot, + * however, change back to the original value. Therefore + * we can detect whether we acquired the correct lock. + */ + if (unlikely(lock_ptr != q->lock_ptr)) { +- spin_unlock(lock_ptr); ++ raw_spin_unlock(lock_ptr); + goto retry; + } + __unqueue_futex(q); + + BUG_ON(q->pi_state); + +- spin_unlock(lock_ptr); ++ raw_spin_unlock(lock_ptr); + ret = 1; + } + +@@ -2445,7 +2445,7 @@ static void unqueue_me_pi(struct futex_q *q) + put_pi_state(q->pi_state); + q->pi_state = NULL; + +- spin_unlock(q->lock_ptr); ++ raw_spin_unlock(q->lock_ptr); + } + + static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, +@@ -2569,7 +2569,7 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + */ + handle_err: + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); +- spin_unlock(q->lock_ptr); ++ raw_spin_unlock(q->lock_ptr); + + switch (err) { + case -EFAULT: +@@ -2586,7 +2586,7 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + break; + } + +- spin_lock(q->lock_ptr); ++ raw_spin_lock(q->lock_ptr); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + + /* +@@ -2700,7 +2700,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, + /* + * The task state is guaranteed to be set before another task can + * wake it. set_current_state() is implemented using smp_store_mb() and +- * queue_me() calls spin_unlock() upon completion, both serializing ++ * queue_me() calls raw_spin_unlock() upon completion, both serializing + * access to the hash list and forcing another memory barrier. + */ + set_current_state(TASK_INTERRUPTIBLE); +@@ -2998,7 +2998,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + * before __rt_mutex_start_proxy_lock() is done. + */ + raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); +- spin_unlock(q.lock_ptr); ++ raw_spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when +@@ -3019,7 +3019,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); + + cleanup: +- spin_lock(q.lock_ptr); ++ raw_spin_lock(q.lock_ptr); + /* + * If we failed to acquire the lock (deadlock/signal/timeout), we must + * first acquire the hb->lock before removing the lock from the +@@ -3106,7 +3106,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + return ret; + + hb = hash_futex(&key); +- spin_lock(&hb->lock); ++ raw_spin_lock(&hb->lock); + + /* + * Check waiters first. We do not trust user space values at +@@ -3140,7 +3140,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + * rt_waiter. Also see the WARN in wake_futex_pi(). + */ + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + + /* drops pi_state->pi_mutex.wait_lock */ + ret = wake_futex_pi(uaddr, uval, pi_state); +@@ -3179,7 +3179,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + * owner. + */ + if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) { +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + switch (ret) { + case -EFAULT: + goto pi_faulted; +@@ -3199,7 +3199,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + ret = (curval == uval) ? 0 : -EAGAIN; + + out_unlock: +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + out_putkey: + put_futex_key(&key); + return ret; +@@ -3372,9 +3372,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- spin_lock(&hb->lock); ++ raw_spin_lock(&hb->lock); + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); ++ raw_spin_unlock(&hb->lock); + if (ret) + goto out_put_keys; + +@@ -3394,7 +3394,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(q.lock_ptr); ++ raw_spin_lock(q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which +@@ -3420,7 +3420,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + pi_mutex = &q.pi_state->pi_mutex; + ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); + +- spin_lock(q.lock_ptr); ++ raw_spin_lock(q.lock_ptr); + if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) + ret = 0; + +@@ -4179,7 +4179,7 @@ static int __init futex_init(void) + for (i = 0; i < futex_hashsize; i++) { + atomic_set(&futex_queues[i].waiters, 0); + plist_head_init(&futex_queues[i].chain); +- spin_lock_init(&futex_queues[i].lock); ++ raw_spin_lock_init(&futex_queues[i].lock); + } + + return 0; +-- +2.36.1 + diff --git a/debian/patches-rt/0277-futex-Delay-deallocation-of-pi_state.patch b/debian/patches-rt/0277-futex-Delay-deallocation-of-pi_state.patch new file mode 100644 index 000000000..d75a415e1 --- /dev/null +++ b/debian/patches-rt/0277-futex-Delay-deallocation-of-pi_state.patch @@ -0,0 +1,182 @@ +From 83bf13ff04d052ee07805956bae67c712bbb761b Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 26 Jun 2019 13:35:36 +0200 +Subject: [PATCH 277/347] futex: Delay deallocation of pi_state +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit d7c7cf8cb68b7df17e6e50be1f25f35d83e686c7 ] + +On -RT we can't invoke kfree() in a non-preemptible context. + +Defer the deallocation of pi_state to preemptible context. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/futex.c | 55 ++++++++++++++++++++++++++++++++++++++++---------- + 1 file changed, 44 insertions(+), 11 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index 8a49dd71b233..2fc6bedb460e 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -871,13 +871,13 @@ static void get_pi_state(struct futex_pi_state *pi_state) + * Drops a reference to the pi_state object and frees or caches it + * when the last reference is gone. + */ +-static void put_pi_state(struct futex_pi_state *pi_state) ++static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state) + { + if (!pi_state) +- return; ++ return NULL; + + if (!atomic_dec_and_test(&pi_state->refcount)) +- return; ++ return NULL; + + /* + * If pi_state->owner is NULL, the owner is most probably dying +@@ -892,9 +892,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) + raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); + } + +- if (current->pi_state_cache) { +- kfree(pi_state); +- } else { ++ if (!current->pi_state_cache) { + /* + * pi_state->list is already empty. + * clear pi_state->owner. +@@ -903,6 +901,30 @@ static void put_pi_state(struct futex_pi_state *pi_state) + pi_state->owner = NULL; + atomic_set(&pi_state->refcount, 1); + current->pi_state_cache = pi_state; ++ pi_state = NULL; ++ } ++ return pi_state; ++} ++ ++static void put_pi_state(struct futex_pi_state *pi_state) ++{ ++ kfree(__put_pi_state(pi_state)); ++} ++ ++static void put_pi_state_atomic(struct futex_pi_state *pi_state, ++ struct list_head *to_free) ++{ ++ if (__put_pi_state(pi_state)) ++ list_add(&pi_state->list, to_free); ++} ++ ++static void free_pi_state_list(struct list_head *to_free) ++{ ++ struct futex_pi_state *p, *next; ++ ++ list_for_each_entry_safe(p, next, to_free, list) { ++ list_del(&p->list); ++ kfree(p); + } + } + +@@ -919,6 +941,7 @@ static void exit_pi_state_list(struct task_struct *curr) + struct futex_pi_state *pi_state; + struct futex_hash_bucket *hb; + union futex_key key = FUTEX_KEY_INIT; ++ LIST_HEAD(to_free); + + if (!futex_cmpxchg_enabled) + return; +@@ -963,7 +986,7 @@ static void exit_pi_state_list(struct task_struct *curr) + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock(&hb->lock); +- put_pi_state(pi_state); ++ put_pi_state_atomic(pi_state, &to_free); + continue; + } + +@@ -982,6 +1005,8 @@ static void exit_pi_state_list(struct task_struct *curr) + raw_spin_lock_irq(&curr->pi_lock); + } + raw_spin_unlock_irq(&curr->pi_lock); ++ ++ free_pi_state_list(&to_free); + } + #else + static inline void exit_pi_state_list(struct task_struct *curr) { } +@@ -2017,6 +2042,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; + DEFINE_WAKE_Q(wake_q); ++ LIST_HEAD(to_free); + + if (nr_wake < 0 || nr_requeue < 0) + return -EINVAL; +@@ -2265,7 +2291,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + * object. + */ + this->pi_state = NULL; +- put_pi_state(pi_state); ++ put_pi_state_atomic(pi_state, &to_free); + /* + * We stop queueing more waiters and let user + * space deal with the mess. +@@ -2282,7 +2308,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We + * need to drop it here again. + */ +- put_pi_state(pi_state); ++ put_pi_state_atomic(pi_state, &to_free); + + out_unlock: + double_unlock_hb(hb1, hb2); +@@ -2303,6 +2329,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + out_put_key1: + put_futex_key(&key1); + out: ++ free_pi_state_list(&to_free); + return ret ? ret : task_count; + } + +@@ -2439,13 +2466,16 @@ static int unqueue_me(struct futex_q *q) + static void unqueue_me_pi(struct futex_q *q) + __releases(q->lock_ptr) + { ++ struct futex_pi_state *ps; ++ + __unqueue_futex(q); + + BUG_ON(!q->pi_state); +- put_pi_state(q->pi_state); ++ ps = __put_pi_state(q->pi_state); + q->pi_state = NULL; + + raw_spin_unlock(q->lock_ptr); ++ kfree(ps); + } + + static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, +@@ -3394,14 +3424,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { ++ struct futex_pi_state *ps_free; ++ + raw_spin_lock(q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ +- put_pi_state(q.pi_state); ++ ps_free = __put_pi_state(q.pi_state); + spin_unlock(&hb2->lock); ++ kfree(ps_free); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. +-- +2.36.1 + diff --git a/debian/patches-rt/0278-mm-zswap-Do-not-disable-preemption-in-zswap_frontswa.patch b/debian/patches-rt/0278-mm-zswap-Do-not-disable-preemption-in-zswap_frontswa.patch new file mode 100644 index 000000000..b44e7ef6e --- /dev/null +++ b/debian/patches-rt/0278-mm-zswap-Do-not-disable-preemption-in-zswap_frontswa.patch @@ -0,0 +1,127 @@ +From f41d5cdc361ba012b59e23b78fe3501b16cfda3d Mon Sep 17 00:00:00 2001 +From: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> +Date: Tue, 25 Jun 2019 11:28:04 -0300 +Subject: [PATCH 278/347] mm/zswap: Do not disable preemption in + zswap_frontswap_store() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 4e4cf4be79635e67144632d9135286381acbc95a ] + +Zswap causes "BUG: scheduling while atomic" by blocking on a rt_spin_lock() with +preemption disabled. The preemption is disabled by get_cpu_var() in +zswap_frontswap_store() to protect the access of the zswap_dstmem percpu variable. + +Use get_locked_var() to protect the percpu zswap_dstmem variable, making the +code preemptive. + +As get_cpu_ptr() also disables preemption, replace it by this_cpu_ptr() and +remove the counterpart put_cpu_ptr(). + +Steps to Reproduce: + + 1. # grubby --args "zswap.enabled=1" --update-kernel DEFAULT + 2. # reboot + 3. Calculate the amount o memory to be used by the test: + ---> grep MemAvailable /proc/meminfo + ---> Add 25% ~ 50% to that value + 4. # stress --vm 1 --vm-bytes ${MemAvailable+25%} --timeout 240s + +Usually, in less than 5 minutes the backtrace listed below appears, followed +by a kernel panic: + +| BUG: scheduling while atomic: kswapd1/181/0x00000002 +| +| Preemption disabled at: +| [<ffffffff8b2a6cda>] zswap_frontswap_store+0x21a/0x6e1 +| +| Kernel panic - not syncing: scheduling while atomic +| CPU: 14 PID: 181 Comm: kswapd1 Kdump: loaded Not tainted 5.0.14-rt9 #1 +| Hardware name: AMD Pence/Pence, BIOS WPN2321X_Weekly_12_03_21 03/19/2012 +| Call Trace: +| panic+0x106/0x2a7 +| __schedule_bug.cold+0x3f/0x51 +| __schedule+0x5cb/0x6f0 +| schedule+0x43/0xd0 +| rt_spin_lock_slowlock_locked+0x114/0x2b0 +| rt_spin_lock_slowlock+0x51/0x80 +| zbud_alloc+0x1da/0x2d0 +| zswap_frontswap_store+0x31a/0x6e1 +| __frontswap_store+0xab/0x130 +| swap_writepage+0x39/0x70 +| pageout.isra.0+0xe3/0x320 +| shrink_page_list+0xa8e/0xd10 +| shrink_inactive_list+0x251/0x840 +| shrink_node_memcg+0x213/0x770 +| shrink_node+0xd9/0x450 +| balance_pgdat+0x2d5/0x510 +| kswapd+0x218/0x470 +| kthread+0xfb/0x130 +| ret_from_fork+0x27/0x50 + +Cc: stable-rt@vger.kernel.org +Reported-by: Ping Fang <pifang@redhat.com> +Signed-off-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com> +Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + mm/zswap.c | 12 +++++++----- + 1 file changed, 7 insertions(+), 5 deletions(-) + +diff --git a/mm/zswap.c b/mm/zswap.c +index cd91fd9d96b8..420225d3ff0b 100644 +--- a/mm/zswap.c ++++ b/mm/zswap.c +@@ -27,6 +27,7 @@ + #include <linux/highmem.h> + #include <linux/slab.h> + #include <linux/spinlock.h> ++#include <linux/locallock.h> + #include <linux/types.h> + #include <linux/atomic.h> + #include <linux/frontswap.h> +@@ -990,6 +991,8 @@ static void zswap_fill_page(void *ptr, unsigned long value) + memset_l(page, value, PAGE_SIZE / sizeof(unsigned long)); + } + ++/* protect zswap_dstmem from concurrency */ ++static DEFINE_LOCAL_IRQ_LOCK(zswap_dstmem_lock); + /********************************* + * frontswap hooks + **********************************/ +@@ -1066,12 +1069,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, + } + + /* compress */ +- dst = get_cpu_var(zswap_dstmem); +- tfm = *get_cpu_ptr(entry->pool->tfm); ++ dst = get_locked_var(zswap_dstmem_lock, zswap_dstmem); ++ tfm = *this_cpu_ptr(entry->pool->tfm); + src = kmap_atomic(page); + ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen); + kunmap_atomic(src); +- put_cpu_ptr(entry->pool->tfm); + if (ret) { + ret = -EINVAL; + goto put_dstmem; +@@ -1094,7 +1096,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, + memcpy(buf, &zhdr, hlen); + memcpy(buf + hlen, dst, dlen); + zpool_unmap_handle(entry->pool->zpool, handle); +- put_cpu_var(zswap_dstmem); ++ put_locked_var(zswap_dstmem_lock, zswap_dstmem); + + /* populate entry */ + entry->offset = offset; +@@ -1122,7 +1124,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, + return 0; + + put_dstmem: +- put_cpu_var(zswap_dstmem); ++ put_locked_var(zswap_dstmem_lock, zswap_dstmem); + zswap_pool_put(entry->pool); + freepage: + zswap_entry_cache_free(entry); +-- +2.36.1 + diff --git a/debian/patches-rt/0279-revert-aio.patch b/debian/patches-rt/0279-revert-aio.patch new file mode 100644 index 000000000..2473add45 --- /dev/null +++ b/debian/patches-rt/0279-revert-aio.patch @@ -0,0 +1,71 @@ +From f543c9a26aefcba7e267ea5d79ee00bcf6679b50 Mon Sep 17 00:00:00 2001 +From: "Steven Rostedt (VMware)" <rostedt@goodmis.org> +Date: Fri, 20 Sep 2019 17:50:53 -0400 +Subject: [PATCH 279/347] revert-aio +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +revert: fs/aio: simple simple work + +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + fs/aio.c | 15 ++------------- + 1 file changed, 2 insertions(+), 13 deletions(-) + +diff --git a/fs/aio.c b/fs/aio.c +index 21eacb0f3f56..9635c29b83da 100644 +--- a/fs/aio.c ++++ b/fs/aio.c +@@ -42,7 +42,6 @@ + #include <linux/ramfs.h> + #include <linux/percpu-refcount.h> + #include <linux/mount.h> +-#include <linux/swork.h> + + #include <asm/kmap_types.h> + #include <linux/uaccess.h> +@@ -122,7 +121,6 @@ struct kioctx { + long nr_pages; + + struct rcu_work free_rwork; /* see free_ioctx() */ +- struct swork_event free_swork; /* see free_ioctx() */ + + /* + * signals when all in-flight requests are done +@@ -269,7 +267,6 @@ static int __init aio_setup(void) + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; +- BUG_ON(swork_get()); + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); +@@ -611,9 +608,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref) + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users_work(struct swork_event *sev) ++static void free_ioctx_users(struct percpu_ref *ref) + { +- struct kioctx *ctx = container_of(sev, struct kioctx, free_swork); ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -631,14 +628,6 @@ static void free_ioctx_users_work(struct swork_event *sev) + percpu_ref_put(&ctx->reqs); + } + +-static void free_ioctx_users(struct percpu_ref *ref) +-{ +- struct kioctx *ctx = container_of(ref, struct kioctx, users); +- +- INIT_SWORK(&ctx->free_swork, free_ioctx_users_work); +- swork_queue(&ctx->free_swork); +-} +- + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; +-- +2.36.1 + diff --git a/debian/patches-rt/0280-fs-aio-simple-simple-work.patch b/debian/patches-rt/0280-fs-aio-simple-simple-work.patch new file mode 100644 index 000000000..8bbb8340f --- /dev/null +++ b/debian/patches-rt/0280-fs-aio-simple-simple-work.patch @@ -0,0 +1,76 @@ +From 238624153731bac8138142a9d688f5b51a5f70fe Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 16 Feb 2015 18:49:10 +0100 +Subject: [PATCH 280/347] fs/aio: simple simple work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 1a142116f6435ef070ecebb66d2d599507c10601 ] + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:768 +|in_atomic(): 1, irqs_disabled(): 0, pid: 26, name: rcuos/2 +|2 locks held by rcuos/2/26: +| #0: (rcu_callback){.+.+..}, at: [<ffffffff810b1a12>] rcu_nocb_kthread+0x1e2/0x380 +| #1: (rcu_read_lock_sched){.+.+..}, at: [<ffffffff812acd26>] percpu_ref_kill_rcu+0xa6/0x1c0 +|Preemption disabled at:[<ffffffff810b1a93>] rcu_nocb_kthread+0x263/0x380 +|Call Trace: +| [<ffffffff81582e9e>] dump_stack+0x4e/0x9c +| [<ffffffff81077aeb>] __might_sleep+0xfb/0x170 +| [<ffffffff81589304>] rt_spin_lock+0x24/0x70 +| [<ffffffff811c5790>] free_ioctx_users+0x30/0x130 +| [<ffffffff812ace34>] percpu_ref_kill_rcu+0x1b4/0x1c0 +| [<ffffffff810b1a93>] rcu_nocb_kthread+0x263/0x380 +| [<ffffffff8106e046>] kthread+0xd6/0xf0 +| [<ffffffff81591eec>] ret_from_fork+0x7c/0xb0 + +replace this preempt_disable() friendly swork. + +Reported-By: Mike Galbraith <umgwanakikbuti@gmail.com> +Suggested-by: Benjamin LaHaise <bcrl@kvack.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + fs/aio.c | 13 +++++++++++-- + 1 file changed, 11 insertions(+), 2 deletions(-) + +diff --git a/fs/aio.c b/fs/aio.c +index 9635c29b83da..303e85033965 100644 +--- a/fs/aio.c ++++ b/fs/aio.c +@@ -121,6 +121,7 @@ struct kioctx { + long nr_pages; + + struct rcu_work free_rwork; /* see free_ioctx() */ ++ struct kthread_work free_kwork; /* see free_ioctx() */ + + /* + * signals when all in-flight requests are done +@@ -608,9 +609,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref) + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users(struct percpu_ref *ref) ++static void free_ioctx_users_work(struct kthread_work *work) + { +- struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ struct kioctx *ctx = container_of(work, struct kioctx, free_kwork); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -628,6 +629,14 @@ static void free_ioctx_users(struct percpu_ref *ref) + percpu_ref_put(&ctx->reqs); + } + ++static void free_ioctx_users(struct percpu_ref *ref) ++{ ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ ++ kthread_init_work(&ctx->free_kwork, free_ioctx_users_work); ++ kthread_schedule_work(&ctx->free_kwork); ++} ++ + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; +-- +2.36.1 + diff --git a/debian/patches-rt/0281-revert-thermal.patch b/debian/patches-rt/0281-revert-thermal.patch new file mode 100644 index 000000000..eb35b59a3 --- /dev/null +++ b/debian/patches-rt/0281-revert-thermal.patch @@ -0,0 +1,120 @@ +From 0e238fd1114bbb3f58ef4d2c32558d13f7ba6b75 Mon Sep 17 00:00:00 2001 +From: "Steven Rostedt (VMware)" <rostedt@goodmis.org> +Date: Fri, 20 Sep 2019 17:50:53 -0400 +Subject: [PATCH 281/347] revert-thermal +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Revert: thermal: Defer thermal wakups to threads + +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/thermal/x86_pkg_temp_thermal.c | 52 ++------------------------ + 1 file changed, 3 insertions(+), 49 deletions(-) + +diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c +index a5991cbb408f..1ef937d799e4 100644 +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -29,7 +29,6 @@ + #include <linux/pm.h> + #include <linux/thermal.h> + #include <linux/debugfs.h> +-#include <linux/swork.h> + #include <asm/cpu_device_id.h> + #include <asm/mce.h> + +@@ -330,7 +329,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work) + schedule_delayed_work_on(cpu, work, ms); + } + +-static void pkg_thermal_notify_work(struct swork_event *event) ++static int pkg_thermal_notify(u64 msr_val) + { + int cpu = smp_processor_id(); + struct pkg_device *pkgdev; +@@ -349,47 +348,9 @@ static void pkg_thermal_notify_work(struct swork_event *event) + } + + spin_unlock_irqrestore(&pkg_temp_lock, flags); +-} +- +-#ifdef CONFIG_PREEMPT_RT_FULL +-static struct swork_event notify_work; +- +-static int pkg_thermal_notify_work_init(void) +-{ +- int err; +- +- err = swork_get(); +- if (err) +- return err; +- +- INIT_SWORK(¬ify_work, pkg_thermal_notify_work); + return 0; + } + +-static void pkg_thermal_notify_work_cleanup(void) +-{ +- swork_put(); +-} +- +-static int pkg_thermal_notify(u64 msr_val) +-{ +- swork_queue(¬ify_work); +- return 0; +-} +- +-#else /* !CONFIG_PREEMPT_RT_FULL */ +- +-static int pkg_thermal_notify_work_init(void) { return 0; } +- +-static void pkg_thermal_notify_work_cleanup(void) { } +- +-static int pkg_thermal_notify(u64 msr_val) +-{ +- pkg_thermal_notify_work(NULL); +- return 0; +-} +-#endif /* CONFIG_PREEMPT_RT_FULL */ +- + static int pkg_temp_thermal_device_add(unsigned int cpu) + { + int pkgid = topology_logical_package_id(cpu); +@@ -554,16 +515,11 @@ static int __init pkg_temp_thermal_init(void) + if (!x86_match_cpu(pkg_temp_thermal_ids)) + return -ENODEV; + +- if (!pkg_thermal_notify_work_init()) +- return -ENODEV; +- + max_packages = topology_max_packages(); + packages = kcalloc(max_packages, sizeof(struct pkg_device *), + GFP_KERNEL); +- if (!packages) { +- ret = -ENOMEM; +- goto err; +- } ++ if (!packages) ++ return -ENOMEM; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online", + pkg_thermal_cpu_online, pkg_thermal_cpu_offline); +@@ -581,7 +537,6 @@ static int __init pkg_temp_thermal_init(void) + return 0; + + err: +- pkg_thermal_notify_work_cleanup(); + kfree(packages); + return ret; + } +@@ -595,7 +550,6 @@ static void __exit pkg_temp_thermal_exit(void) + cpuhp_remove_state(pkg_thermal_hp_state); + debugfs_remove_recursive(debugfs); + kfree(packages); +- pkg_thermal_notify_work_cleanup(); + } + module_exit(pkg_temp_thermal_exit) + +-- +2.36.1 + diff --git a/debian/patches-rt/0282-thermal-Defer-thermal-wakups-to-threads.patch b/debian/patches-rt/0282-thermal-Defer-thermal-wakups-to-threads.patch new file mode 100644 index 000000000..c87c2c1ee --- /dev/null +++ b/debian/patches-rt/0282-thermal-Defer-thermal-wakups-to-threads.patch @@ -0,0 +1,98 @@ +From 260167472319caeab60ece36de5dcd04ef245df5 Mon Sep 17 00:00:00 2001 +From: Daniel Wagner <wagi@monom.org> +Date: Tue, 17 Feb 2015 09:37:44 +0100 +Subject: [PATCH 282/347] thermal: Defer thermal wakups to threads +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit ad2408dc248fe58536eef5b2b5734d8f9d3a280b ] + +On RT the spin lock in pkg_temp_thermal_platfrom_thermal_notify will +call schedule while we run in irq context. + +[<ffffffff816850ac>] dump_stack+0x4e/0x8f +[<ffffffff81680f7d>] __schedule_bug+0xa6/0xb4 +[<ffffffff816896b4>] __schedule+0x5b4/0x700 +[<ffffffff8168982a>] schedule+0x2a/0x90 +[<ffffffff8168a8b5>] rt_spin_lock_slowlock+0xe5/0x2d0 +[<ffffffff8168afd5>] rt_spin_lock+0x25/0x30 +[<ffffffffa03a7b75>] pkg_temp_thermal_platform_thermal_notify+0x45/0x134 [x86_pkg_temp_thermal] +[<ffffffff8103d4db>] ? therm_throt_process+0x1b/0x160 +[<ffffffff8103d831>] intel_thermal_interrupt+0x211/0x250 +[<ffffffff8103d8c1>] smp_thermal_interrupt+0x21/0x40 +[<ffffffff8169415d>] thermal_interrupt+0x6d/0x80 + +Let's defer the work to a kthread. + +Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: reoder init/denit position. TODO: flush swork on exit] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/thermal/x86_pkg_temp_thermal.c | 28 +++++++++++++++++++++++++- + 1 file changed, 27 insertions(+), 1 deletion(-) + +diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c +index 1ef937d799e4..82f21fd4afb0 100644 +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -29,6 +29,7 @@ + #include <linux/pm.h> + #include <linux/thermal.h> + #include <linux/debugfs.h> ++#include <linux/kthread.h> + #include <asm/cpu_device_id.h> + #include <asm/mce.h> + +@@ -329,7 +330,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work) + schedule_delayed_work_on(cpu, work, ms); + } + +-static int pkg_thermal_notify(u64 msr_val) ++static void pkg_thermal_notify_work(struct kthread_work *work) + { + int cpu = smp_processor_id(); + struct pkg_device *pkgdev; +@@ -348,8 +349,32 @@ static int pkg_thermal_notify(u64 msr_val) + } + + spin_unlock_irqrestore(&pkg_temp_lock, flags); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static DEFINE_KTHREAD_WORK(notify_work, pkg_thermal_notify_work); ++ ++static int pkg_thermal_notify(u64 msr_val) ++{ ++ kthread_schedule_work(¬ify_work); ++ return 0; ++} ++ ++static void pkg_thermal_notify_flush(void) ++{ ++ kthread_flush_work(¬ify_work); ++} ++ ++#else /* !CONFIG_PREEMPT_RT_FULL */ ++ ++static void pkg_thermal_notify_flush(void) { } ++ ++static int pkg_thermal_notify(u64 msr_val) ++{ ++ pkg_thermal_notify_work(NULL); + return 0; + } ++#endif /* CONFIG_PREEMPT_RT_FULL */ + + static int pkg_temp_thermal_device_add(unsigned int cpu) + { +@@ -548,6 +573,7 @@ static void __exit pkg_temp_thermal_exit(void) + platform_thermal_package_rate_control = NULL; + + cpuhp_remove_state(pkg_thermal_hp_state); ++ pkg_thermal_notify_flush(); + debugfs_remove_recursive(debugfs); + kfree(packages); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0283-revert-block.patch b/debian/patches-rt/0283-revert-block.patch new file mode 100644 index 000000000..71ddf1806 --- /dev/null +++ b/debian/patches-rt/0283-revert-block.patch @@ -0,0 +1,83 @@ +From aceaba22f9a9db0bf15d1a63ca7d08080314f7b0 Mon Sep 17 00:00:00 2001 +From: "Steven Rostedt (VMware)" <rostedt@goodmis.org> +Date: Fri, 20 Sep 2019 17:50:54 -0400 +Subject: [PATCH 283/347] revert-block +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Revert swork version of: block: blk-mq: move blk_queue_usage_counter_release() into process context + +In order to switch to upstream, we need to revert the swork code. + +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + block/blk-core.c | 14 +------------- + include/linux/blkdev.h | 2 -- + 2 files changed, 1 insertion(+), 15 deletions(-) + +diff --git a/block/blk-core.c b/block/blk-core.c +index 02835970ef1e..461a93c08c14 100644 +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -973,21 +973,12 @@ void blk_queue_exit(struct request_queue *q) + percpu_ref_put(&q->q_usage_counter); + } + +-static void blk_queue_usage_counter_release_swork(struct swork_event *sev) +-{ +- struct request_queue *q = +- container_of(sev, struct request_queue, mq_pcpu_wake); +- +- wake_up_all(&q->mq_freeze_wq); +-} +- + static void blk_queue_usage_counter_release(struct percpu_ref *ref) + { + struct request_queue *q = + container_of(ref, struct request_queue, q_usage_counter); + +- if (wq_has_sleeper(&q->mq_freeze_wq)) +- swork_queue(&q->mq_pcpu_wake); ++ wake_up_all(&q->mq_freeze_wq); + } + + static void blk_rq_timed_out_timer(struct timer_list *t) +@@ -1087,7 +1078,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, + queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); + + init_waitqueue_head(&q->mq_freeze_wq); +- INIT_SWORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_swork); + + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. +@@ -3977,8 +3967,6 @@ int __init blk_dev_init(void) + if (!kblockd_workqueue) + panic("Failed to create kblockd\n"); + +- BUG_ON(swork_get()); +- + request_cachep = kmem_cache_create("blkdev_requests", + sizeof(struct request), 0, SLAB_PANIC, NULL); + +diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h +index 0313098a428d..39d90bf9b5fa 100644 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -27,7 +27,6 @@ + #include <linux/percpu-refcount.h> + #include <linux/scatterlist.h> + #include <linux/blkzoned.h> +-#include <linux/swork.h> + + struct module; + struct scsi_ioctl_command; +@@ -665,7 +664,6 @@ struct request_queue { + #endif + struct rcu_head rcu_head; + wait_queue_head_t mq_freeze_wq; +- struct swork_event mq_pcpu_wake; + struct percpu_ref q_usage_counter; + struct list_head all_q_node; + +-- +2.36.1 + diff --git a/debian/patches-rt/0284-block-blk-mq-move-blk_queue_usage_counter_release-in.patch b/debian/patches-rt/0284-block-blk-mq-move-blk_queue_usage_counter_release-in.patch new file mode 100644 index 000000000..97f2bf9b8 --- /dev/null +++ b/debian/patches-rt/0284-block-blk-mq-move-blk_queue_usage_counter_release-in.patch @@ -0,0 +1,114 @@ +From 8ba3db6f9244e6911ac88380cd133f39aaba95ab Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 13 Mar 2018 13:49:16 +0100 +Subject: [PATCH 284/347] block: blk-mq: move blk_queue_usage_counter_release() + into process context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 61c928ecf4fe200bda9b49a0813b5ba0f43995b5 ] + +| BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +| in_atomic(): 1, irqs_disabled(): 0, pid: 255, name: kworker/u257:6 +| 5 locks held by kworker/u257:6/255: +| #0: ("events_unbound"){.+.+.+}, at: [<ffffffff8108edf1>] process_one_work+0x171/0x5e0 +| #1: ((&entry->work)){+.+.+.}, at: [<ffffffff8108edf1>] process_one_work+0x171/0x5e0 +| #2: (&shost->scan_mutex){+.+.+.}, at: [<ffffffffa000faa3>] __scsi_add_device+0xa3/0x130 [scsi_mod] +| #3: (&set->tag_list_lock){+.+...}, at: [<ffffffff812f09fa>] blk_mq_init_queue+0x96a/0xa50 +| #4: (rcu_read_lock_sched){......}, at: [<ffffffff8132887d>] percpu_ref_kill_and_confirm+0x1d/0x120 +| Preemption disabled at:[<ffffffff812eff76>] blk_mq_freeze_queue_start+0x56/0x70 +| +| CPU: 2 PID: 255 Comm: kworker/u257:6 Not tainted 3.18.7-rt0+ #1 +| Workqueue: events_unbound async_run_entry_fn +| 0000000000000003 ffff8800bc29f998 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff8800bc29f9b8 ffffffff8109aa16 ffff8800bc29fa28 +| ffff8800bc5d1bc8 ffff8800bc29f9e8 ffffffff815b8dd4 ffff880000000000 +| Call Trace: +| [<ffffffff815b3a12>] dump_stack+0x4f/0x7c +| [<ffffffff8109aa16>] __might_sleep+0x116/0x190 +| [<ffffffff815b8dd4>] rt_spin_lock+0x24/0x60 +| [<ffffffff810b6089>] __wake_up+0x29/0x60 +| [<ffffffff812ee06e>] blk_mq_usage_counter_release+0x1e/0x20 +| [<ffffffff81328966>] percpu_ref_kill_and_confirm+0x106/0x120 +| [<ffffffff812eff76>] blk_mq_freeze_queue_start+0x56/0x70 +| [<ffffffff812f0000>] blk_mq_update_tag_set_depth+0x40/0xd0 +| [<ffffffff812f0a1c>] blk_mq_init_queue+0x98c/0xa50 +| [<ffffffffa000dcf0>] scsi_mq_alloc_queue+0x20/0x60 [scsi_mod] +| [<ffffffffa000ea35>] scsi_alloc_sdev+0x2f5/0x370 [scsi_mod] +| [<ffffffffa000f494>] scsi_probe_and_add_lun+0x9e4/0xdd0 [scsi_mod] +| [<ffffffffa000fb26>] __scsi_add_device+0x126/0x130 [scsi_mod] +| [<ffffffffa013033f>] ata_scsi_scan_host+0xaf/0x200 [libata] +| [<ffffffffa012b5b6>] async_port_probe+0x46/0x60 [libata] +| [<ffffffff810978fb>] async_run_entry_fn+0x3b/0xf0 +| [<ffffffff8108ee81>] process_one_work+0x201/0x5e0 + +percpu_ref_kill_and_confirm() invokes blk_mq_usage_counter_release() in +a rcu-sched region. swait based wake queue can't be used due to +wake_up_all() usage and disabled interrupts in !RT configs (as reported +by Corey Minyard). +The wq_has_sleeper() check has been suggested by Peter Zijlstra. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + block/blk-core.c | 12 +++++++++++- + include/linux/blkdev.h | 2 ++ + 2 files changed, 13 insertions(+), 1 deletion(-) + +diff --git a/block/blk-core.c b/block/blk-core.c +index 461a93c08c14..a67a50dd714a 100644 +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -973,12 +973,21 @@ void blk_queue_exit(struct request_queue *q) + percpu_ref_put(&q->q_usage_counter); + } + ++static void blk_queue_usage_counter_release_wrk(struct kthread_work *work) ++{ ++ struct request_queue *q = ++ container_of(work, struct request_queue, mq_pcpu_wake); ++ ++ wake_up_all(&q->mq_freeze_wq); ++} ++ + static void blk_queue_usage_counter_release(struct percpu_ref *ref) + { + struct request_queue *q = + container_of(ref, struct request_queue, q_usage_counter); + +- wake_up_all(&q->mq_freeze_wq); ++ if (wq_has_sleeper(&q->mq_freeze_wq)) ++ kthread_schedule_work(&q->mq_pcpu_wake); + } + + static void blk_rq_timed_out_timer(struct timer_list *t) +@@ -1078,6 +1087,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, + queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); + + init_waitqueue_head(&q->mq_freeze_wq); ++ kthread_init_work(&q->mq_pcpu_wake, blk_queue_usage_counter_release_wrk); + + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. +diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h +index 39d90bf9b5fa..5566d0049c22 100644 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -13,6 +13,7 @@ + #include <linux/llist.h> + #include <linux/timer.h> + #include <linux/workqueue.h> ++#include <linux/kthread.h> + #include <linux/pagemap.h> + #include <linux/backing-dev-defs.h> + #include <linux/wait.h> +@@ -664,6 +665,7 @@ struct request_queue { + #endif + struct rcu_head rcu_head; + wait_queue_head_t mq_freeze_wq; ++ struct kthread_work mq_pcpu_wake; + struct percpu_ref q_usage_counter; + struct list_head all_q_node; + +-- +2.36.1 + diff --git a/debian/patches-rt/0285-workqueue-rework.patch b/debian/patches-rt/0285-workqueue-rework.patch new file mode 100644 index 000000000..056eb3a62 --- /dev/null +++ b/debian/patches-rt/0285-workqueue-rework.patch @@ -0,0 +1,1464 @@ +From 6fb18a4e40f7937eb1d0ab9dd2929a50d30d91f7 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 29 May 2019 18:52:27 +0200 +Subject: [PATCH 285/347] workqueue: rework +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit d15a862f24df983458533aebd6fa207ecdd1095a ] + +This is an all-in change of the workqueue rework. +The worker_pool.lock is made to raw_spinlock_t. With this change we can +schedule workitems from preempt-disable sections and sections with disabled +interrupts. This change allows to remove all kthread_.* workarounds we used to +have. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + block/blk-core.c | 6 +- + drivers/block/loop.c | 2 +- + drivers/spi/spi-rockchip.c | 1 - + drivers/thermal/x86_pkg_temp_thermal.c | 28 +-- + fs/aio.c | 10 +- + include/linux/blk-cgroup.h | 2 +- + include/linux/blkdev.h | 2 +- + include/linux/kthread-cgroup.h | 17 -- + include/linux/kthread.h | 15 +- + include/linux/swait.h | 14 ++ + include/linux/workqueue.h | 4 - + init/main.c | 1 - + kernel/kthread.c | 14 -- + kernel/sched/core.c | 1 + + kernel/time/hrtimer.c | 24 -- + kernel/workqueue.c | 304 +++++++++++-------------- + 16 files changed, 163 insertions(+), 282 deletions(-) + delete mode 100644 include/linux/kthread-cgroup.h + +diff --git a/block/blk-core.c b/block/blk-core.c +index a67a50dd714a..ed6ae335756d 100644 +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -973,7 +973,7 @@ void blk_queue_exit(struct request_queue *q) + percpu_ref_put(&q->q_usage_counter); + } + +-static void blk_queue_usage_counter_release_wrk(struct kthread_work *work) ++static void blk_queue_usage_counter_release_wrk(struct work_struct *work) + { + struct request_queue *q = + container_of(work, struct request_queue, mq_pcpu_wake); +@@ -987,7 +987,7 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref) + container_of(ref, struct request_queue, q_usage_counter); + + if (wq_has_sleeper(&q->mq_freeze_wq)) +- kthread_schedule_work(&q->mq_pcpu_wake); ++ schedule_work(&q->mq_pcpu_wake); + } + + static void blk_rq_timed_out_timer(struct timer_list *t) +@@ -1087,7 +1087,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, + queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); + + init_waitqueue_head(&q->mq_freeze_wq); +- kthread_init_work(&q->mq_pcpu_wake, blk_queue_usage_counter_release_wrk); ++ INIT_WORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_wrk); + + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. +diff --git a/drivers/block/loop.c b/drivers/block/loop.c +index d24660961343..c31a76485c9c 100644 +--- a/drivers/block/loop.c ++++ b/drivers/block/loop.c +@@ -70,7 +70,7 @@ + #include <linux/writeback.h> + #include <linux/completion.h> + #include <linux/highmem.h> +-#include <linux/kthread-cgroup.h> ++#include <linux/kthread.h> + #include <linux/splice.h> + #include <linux/sysfs.h> + #include <linux/miscdevice.h> +diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c +index 63b10236eb05..185bbdce62b1 100644 +--- a/drivers/spi/spi-rockchip.c ++++ b/drivers/spi/spi-rockchip.c +@@ -22,7 +22,6 @@ + #include <linux/spi/spi.h> + #include <linux/pm_runtime.h> + #include <linux/scatterlist.h> +-#include <linux/interrupt.h> + + #define DRIVER_NAME "rockchip-spi" + +diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c +index 82f21fd4afb0..1ef937d799e4 100644 +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -29,7 +29,6 @@ + #include <linux/pm.h> + #include <linux/thermal.h> + #include <linux/debugfs.h> +-#include <linux/kthread.h> + #include <asm/cpu_device_id.h> + #include <asm/mce.h> + +@@ -330,7 +329,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work) + schedule_delayed_work_on(cpu, work, ms); + } + +-static void pkg_thermal_notify_work(struct kthread_work *work) ++static int pkg_thermal_notify(u64 msr_val) + { + int cpu = smp_processor_id(); + struct pkg_device *pkgdev; +@@ -349,32 +348,8 @@ static void pkg_thermal_notify_work(struct kthread_work *work) + } + + spin_unlock_irqrestore(&pkg_temp_lock, flags); +-} +- +-#ifdef CONFIG_PREEMPT_RT_FULL +-static DEFINE_KTHREAD_WORK(notify_work, pkg_thermal_notify_work); +- +-static int pkg_thermal_notify(u64 msr_val) +-{ +- kthread_schedule_work(¬ify_work); +- return 0; +-} +- +-static void pkg_thermal_notify_flush(void) +-{ +- kthread_flush_work(¬ify_work); +-} +- +-#else /* !CONFIG_PREEMPT_RT_FULL */ +- +-static void pkg_thermal_notify_flush(void) { } +- +-static int pkg_thermal_notify(u64 msr_val) +-{ +- pkg_thermal_notify_work(NULL); + return 0; + } +-#endif /* CONFIG_PREEMPT_RT_FULL */ + + static int pkg_temp_thermal_device_add(unsigned int cpu) + { +@@ -573,7 +548,6 @@ static void __exit pkg_temp_thermal_exit(void) + platform_thermal_package_rate_control = NULL; + + cpuhp_remove_state(pkg_thermal_hp_state); +- pkg_thermal_notify_flush(); + debugfs_remove_recursive(debugfs); + kfree(packages); + } +diff --git a/fs/aio.c b/fs/aio.c +index 303e85033965..6deff68b92c7 100644 +--- a/fs/aio.c ++++ b/fs/aio.c +@@ -121,7 +121,7 @@ struct kioctx { + long nr_pages; + + struct rcu_work free_rwork; /* see free_ioctx() */ +- struct kthread_work free_kwork; /* see free_ioctx() */ ++ struct work_struct free_work; /* see free_ioctx() */ + + /* + * signals when all in-flight requests are done +@@ -609,9 +609,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref) + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users_work(struct kthread_work *work) ++static void free_ioctx_users_work(struct work_struct *work) + { +- struct kioctx *ctx = container_of(work, struct kioctx, free_kwork); ++ struct kioctx *ctx = container_of(work, struct kioctx, free_work); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -633,8 +633,8 @@ static void free_ioctx_users(struct percpu_ref *ref) + { + struct kioctx *ctx = container_of(ref, struct kioctx, users); + +- kthread_init_work(&ctx->free_kwork, free_ioctx_users_work); +- kthread_schedule_work(&ctx->free_kwork); ++ INIT_WORK(&ctx->free_work, free_ioctx_users_work); ++ schedule_work(&ctx->free_work); + } + + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) +diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h +index dc26ce6d840d..53f63f18ecdf 100644 +--- a/include/linux/blk-cgroup.h ++++ b/include/linux/blk-cgroup.h +@@ -14,7 +14,7 @@ + * Nauman Rafique <nauman@google.com> + */ + +-#include <linux/kthread-cgroup.h> ++#include <linux/kthread.h> + #include <linux/percpu_counter.h> + #include <linux/seq_file.h> + #include <linux/radix-tree.h> +diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h +index 5566d0049c22..c01e5d9597f9 100644 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -665,7 +665,7 @@ struct request_queue { + #endif + struct rcu_head rcu_head; + wait_queue_head_t mq_freeze_wq; +- struct kthread_work mq_pcpu_wake; ++ struct work_struct mq_pcpu_wake; + struct percpu_ref q_usage_counter; + struct list_head all_q_node; + +diff --git a/include/linux/kthread-cgroup.h b/include/linux/kthread-cgroup.h +deleted file mode 100644 +index 53d34bca9d72..000000000000 +--- a/include/linux/kthread-cgroup.h ++++ /dev/null +@@ -1,17 +0,0 @@ +-/* SPDX-License-Identifier: GPL-2.0 */ +-#ifndef _LINUX_KTHREAD_CGROUP_H +-#define _LINUX_KTHREAD_CGROUP_H +-#include <linux/kthread.h> +-#include <linux/cgroup.h> +- +-#ifdef CONFIG_BLK_CGROUP +-void kthread_associate_blkcg(struct cgroup_subsys_state *css); +-struct cgroup_subsys_state *kthread_blkcg(void); +-#else +-static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } +-static inline struct cgroup_subsys_state *kthread_blkcg(void) +-{ +- return NULL; +-} +-#endif +-#endif +diff --git a/include/linux/kthread.h b/include/linux/kthread.h +index 31140f0a6c2c..0e3b9b528c9e 100644 +--- a/include/linux/kthread.h ++++ b/include/linux/kthread.h +@@ -4,6 +4,7 @@ + /* Simple interface for creating and stopping kernel threads without mess. */ + #include <linux/err.h> + #include <linux/sched.h> ++#include <linux/cgroup.h> + + __printf(4, 5) + struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), +@@ -200,12 +201,14 @@ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); + + void kthread_destroy_worker(struct kthread_worker *worker); + +-extern struct kthread_worker kthread_global_worker; +-void kthread_init_global_worker(void); +- +-static inline bool kthread_schedule_work(struct kthread_work *work) ++#ifdef CONFIG_BLK_CGROUP ++void kthread_associate_blkcg(struct cgroup_subsys_state *css); ++struct cgroup_subsys_state *kthread_blkcg(void); ++#else ++static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } ++static inline struct cgroup_subsys_state *kthread_blkcg(void) + { +- return kthread_queue_work(&kthread_global_worker, work); ++ return NULL; + } +- ++#endif + #endif /* _LINUX_KTHREAD_H */ +diff --git a/include/linux/swait.h b/include/linux/swait.h +index f426a0661aa0..21ae66cd41d3 100644 +--- a/include/linux/swait.h ++++ b/include/linux/swait.h +@@ -299,4 +299,18 @@ do { \ + __ret; \ + }) + ++#define __swait_event_lock_irq(wq, condition, lock, cmd) \ ++ ___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ ++ raw_spin_unlock_irq(&lock); \ ++ cmd; \ ++ schedule(); \ ++ raw_spin_lock_irq(&lock)) ++ ++#define swait_event_lock_irq(wq_head, condition, lock) \ ++ do { \ ++ if (condition) \ ++ break; \ ++ __swait_event_lock_irq(wq_head, condition, lock, ); \ ++ } while (0) ++ + #endif /* _LINUX_SWAIT_H */ +diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h +index 60d673e15632..546aa73fba6a 100644 +--- a/include/linux/workqueue.h ++++ b/include/linux/workqueue.h +@@ -455,10 +455,6 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, + + extern void destroy_workqueue(struct workqueue_struct *wq); + +-struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); +-void free_workqueue_attrs(struct workqueue_attrs *attrs); +-int apply_workqueue_attrs(struct workqueue_struct *wq, +- const struct workqueue_attrs *attrs); + int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); + + extern bool queue_work_on(int cpu, struct workqueue_struct *wq, +diff --git a/init/main.c b/init/main.c +index f5d0917a4d4b..0d5763c5da28 100644 +--- a/init/main.c ++++ b/init/main.c +@@ -1132,7 +1132,6 @@ static noinline void __init kernel_init_freeable(void) + smp_prepare_cpus(setup_max_cpus); + + workqueue_init(); +- kthread_init_global_worker(); + + init_mm_internals(); + +diff --git a/kernel/kthread.c b/kernel/kthread.c +index 6bbd391f0d9c..c8cf4731ced8 100644 +--- a/kernel/kthread.c ++++ b/kernel/kthread.c +@@ -20,7 +20,6 @@ + #include <linux/freezer.h> + #include <linux/ptrace.h> + #include <linux/uaccess.h> +-#include <linux/cgroup.h> + #include <trace/events/sched.h> + + static DEFINE_SPINLOCK(kthread_create_lock); +@@ -1245,19 +1244,6 @@ void kthread_destroy_worker(struct kthread_worker *worker) + } + EXPORT_SYMBOL(kthread_destroy_worker); + +-DEFINE_KTHREAD_WORKER(kthread_global_worker); +-EXPORT_SYMBOL(kthread_global_worker); +- +-__init void kthread_init_global_worker(void) +-{ +- kthread_global_worker.task = kthread_create(kthread_worker_fn, +- &kthread_global_worker, +- "kswork"); +- if (WARN_ON(IS_ERR(kthread_global_worker.task))) +- return; +- wake_up_process(kthread_global_worker.task); +-} +- + #ifdef CONFIG_BLK_CGROUP + /** + * kthread_associate_blkcg - associate blkcg to current kthread +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 3b0f62be3ece..1d4d4780dd79 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3612,6 +3612,7 @@ static inline void sched_submit_work(struct task_struct *tsk) + { + if (!tsk->state) + return; ++ + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index bbc408f24f5d..eb2db7e6a241 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -748,29 +748,6 @@ static void hrtimer_switch_to_hres(void) + retrigger_next_event(NULL); + } + +-#ifdef CONFIG_PREEMPT_RT_FULL +- +-static struct swork_event clock_set_delay_work; +- +-static void run_clock_set_delay(struct swork_event *event) +-{ +- clock_was_set(); +-} +- +-void clock_was_set_delayed(void) +-{ +- swork_queue(&clock_set_delay_work); +-} +- +-static __init int create_clock_set_delay_thread(void) +-{ +- WARN_ON(swork_get()); +- INIT_SWORK(&clock_set_delay_work, run_clock_set_delay); +- return 0; +-} +-early_initcall(create_clock_set_delay_thread); +-#else /* PREEMPT_RT_FULL */ +- + static void clock_was_set_work(struct work_struct *work) + { + clock_was_set(); +@@ -786,7 +763,6 @@ void clock_was_set_delayed(void) + { + schedule_work(&hrtimer_work); + } +-#endif + + #else + +diff --git a/kernel/workqueue.c b/kernel/workqueue.c +index 91f5696cf335..4ed22776b2ee 100644 +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -50,8 +50,6 @@ + #include <linux/sched/isolation.h> + #include <linux/nmi.h> + #include <linux/kvm_para.h> +-#include <linux/locallock.h> +-#include <linux/delay.h> + + #include "workqueue_internal.h" + +@@ -126,11 +124,6 @@ enum { + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * +- * On RT we need the extra protection via rt_lock_idle_list() for +- * the list manipulations against read access from +- * wq_worker_sleeping(). All other places are nicely serialized via +- * pool->lock. +- * + * A: wq_pool_attach_mutex protected. + * + * PL: wq_pool_mutex protected. +@@ -152,7 +145,7 @@ enum { + /* struct worker is defined in workqueue_internal.h */ + + struct worker_pool { +- spinlock_t lock; /* the pool lock */ ++ raw_spinlock_t lock; /* the pool lock */ + int cpu; /* I: the associated cpu */ + int node; /* I: the associated node ID */ + int id; /* I: pool ID */ +@@ -305,8 +298,8 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; + + static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ + static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ +-static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ +-static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ ++static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ ++static DECLARE_SWAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ + + static LIST_HEAD(workqueues); /* PR: list of all workqueues */ + static bool workqueue_freezing; /* PL: have wqs started freezing? */ +@@ -358,8 +351,6 @@ EXPORT_SYMBOL_GPL(system_power_efficient_wq); + struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; + EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + +-static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); +- + static int worker_thread(void *__worker); + static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + +@@ -436,31 +427,6 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + +-#ifdef CONFIG_PREEMPT_RT_BASE +-static inline void rt_lock_idle_list(struct worker_pool *pool) +-{ +- preempt_disable(); +-} +-static inline void rt_unlock_idle_list(struct worker_pool *pool) +-{ +- preempt_enable(); +-} +-static inline void sched_lock_idle_list(struct worker_pool *pool) { } +-static inline void sched_unlock_idle_list(struct worker_pool *pool) { } +-#else +-static inline void rt_lock_idle_list(struct worker_pool *pool) { } +-static inline void rt_unlock_idle_list(struct worker_pool *pool) { } +-static inline void sched_lock_idle_list(struct worker_pool *pool) +-{ +- spin_lock_irq(&pool->lock); +-} +-static inline void sched_unlock_idle_list(struct worker_pool *pool) +-{ +- spin_unlock_irq(&pool->lock); +-} +-#endif +- +- + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -863,20 +829,14 @@ static struct worker *first_idle_worker(struct worker_pool *pool) + * Wake up the first idle worker of @pool. + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void wake_up_worker(struct worker_pool *pool) + { +- struct worker *worker; +- +- rt_lock_idle_list(pool); +- +- worker = first_idle_worker(pool); ++ struct worker *worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); +- +- rt_unlock_idle_list(pool); + } + + /** +@@ -905,7 +865,7 @@ void wq_worker_running(struct task_struct *task) + */ + void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task); ++ struct worker *next, *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -922,18 +882,26 @@ void wq_worker_sleeping(struct task_struct *task) + return; + + worker->sleeping = 1; ++ raw_spin_lock_irq(&pool->lock); + + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. ++ * ++ * NOT_RUNNING is clear. This means that we're bound to and ++ * running on the local cpu w/ rq lock held and preemption ++ * disabled, which in turn means that none else could be ++ * manipulating idle_list, so dereferencing idle_list without pool ++ * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) { +- sched_lock_idle_list(pool); +- wake_up_worker(pool); +- sched_unlock_idle_list(pool); ++ next = first_idle_worker(pool); ++ if (next) ++ wake_up_process(next->task); + } ++ raw_spin_unlock_irq(&pool->lock); + } + + /** +@@ -944,7 +912,7 @@ void wq_worker_sleeping(struct task_struct *task) + * Set @flags in @worker->flags and adjust nr_running accordingly. + * + * CONTEXT: +- * spin_lock_irq(pool->lock) ++ * raw_spin_lock_irq(pool->lock) + */ + static inline void worker_set_flags(struct worker *worker, unsigned int flags) + { +@@ -969,7 +937,7 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags) + * Clear @flags in @worker->flags and adjust nr_running accordingly. + * + * CONTEXT: +- * spin_lock_irq(pool->lock) ++ * raw_spin_lock_irq(pool->lock) + */ + static inline void worker_clr_flags(struct worker *worker, unsigned int flags) + { +@@ -1017,7 +985,7 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) + * actually occurs, it should be easy to locate the culprit work function. + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + * + * Return: + * Pointer to worker which is executing @work if found, %NULL +@@ -1052,7 +1020,7 @@ static struct worker *find_worker_executing_work(struct worker_pool *pool, + * nested inside outer list_for_each_entry_safe(). + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void move_linked_works(struct work_struct *work, struct list_head *head, + struct work_struct **nextp) +@@ -1130,11 +1098,9 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) + * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ +- rcu_read_lock(); +- local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); ++ raw_spin_lock_irq(&pwq->pool->lock); + put_pwq(pwq); +- local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); +- rcu_read_unlock(); ++ raw_spin_unlock_irq(&pwq->pool->lock); + } + } + +@@ -1167,7 +1133,7 @@ static void pwq_activate_first_delayed(struct pool_workqueue *pwq) + * decrement nr_in_flight of its pwq and handle workqueue flushing. + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) + { +@@ -1238,7 +1204,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + struct worker_pool *pool; + struct pool_workqueue *pwq; + +- local_lock_irqsave(pendingb_lock, *flags); ++ local_irq_save(*flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { +@@ -1266,7 +1232,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + if (!pool) + goto fail; + +- spin_lock(&pool->lock); ++ raw_spin_lock(&pool->lock); + /* + * work->data is guaranteed to point to pwq only while the work + * item is queued on pwq->wq, and both updating work->data to point +@@ -1295,17 +1261,17 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + /* work->data points to pwq iff queued, point to pool */ + set_work_pool_and_keep_pending(work, pool->id); + +- spin_unlock(&pool->lock); ++ raw_spin_unlock(&pool->lock); + rcu_read_unlock(); + return 1; + } +- spin_unlock(&pool->lock); ++ raw_spin_unlock(&pool->lock); + fail: + rcu_read_unlock(); +- local_unlock_irqrestore(pendingb_lock, *flags); ++ local_irq_restore(*flags); + if (work_is_canceling(work)) + return -ENOENT; +- cpu_chill(); ++ cpu_relax(); + return -EAGAIN; + } + +@@ -1320,7 +1286,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + * work_struct flags. + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, + struct list_head *head, unsigned int extra_flags) +@@ -1407,13 +1373,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ +-#ifndef CONFIG_PREEMPT_RT_FULL +- /* +- * nort: On RT the "interrupts-disabled" rule has been replaced with +- * pendingb_lock. +- */ + lockdep_assert_irqs_disabled(); +-#endif + + + /* if draining, only works from the same workqueue are allowed */ +@@ -1442,7 +1402,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + if (last_pool && last_pool != pwq->pool) { + struct worker *worker; + +- spin_lock(&last_pool->lock); ++ raw_spin_lock(&last_pool->lock); + + worker = find_worker_executing_work(last_pool, work); + +@@ -1450,11 +1410,11 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + pwq = worker->current_pwq; + } else { + /* meh... not running there, queue here */ +- spin_unlock(&last_pool->lock); +- spin_lock(&pwq->pool->lock); ++ raw_spin_unlock(&last_pool->lock); ++ raw_spin_lock(&pwq->pool->lock); + } + } else { +- spin_lock(&pwq->pool->lock); ++ raw_spin_lock(&pwq->pool->lock); + } + + /* +@@ -1467,7 +1427,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + */ + if (unlikely(!pwq->refcnt)) { + if (wq->flags & WQ_UNBOUND) { +- spin_unlock(&pwq->pool->lock); ++ raw_spin_unlock(&pwq->pool->lock); + cpu_relax(); + goto retry; + } +@@ -1500,7 +1460,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, + insert_work(pwq, work, worklist, work_flags); + + out: +- spin_unlock(&pwq->pool->lock); ++ raw_spin_unlock(&pwq->pool->lock); + rcu_read_unlock(); + } + +@@ -1521,14 +1481,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, + bool ret = false; + unsigned long flags; + +- local_lock_irqsave(pendingb_lock,flags); ++ local_irq_save(flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + +- local_unlock_irqrestore(pendingb_lock, flags); ++ local_irq_restore(flags); + return ret; + } + EXPORT_SYMBOL(queue_work_on); +@@ -1536,12 +1496,11 @@ EXPORT_SYMBOL(queue_work_on); + void delayed_work_timer_fn(struct timer_list *t) + { + struct delayed_work *dwork = from_timer(dwork, t, timer); ++ unsigned long flags; + +- /* XXX */ +- /* local_lock(pendingb_lock); */ +- /* should have been called from irqsafe timer with irq already off */ ++ local_irq_save(flags); + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- /* local_unlock(pendingb_lock); */ ++ local_irq_restore(flags); + } + EXPORT_SYMBOL(delayed_work_timer_fn); + +@@ -1596,14 +1555,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, + unsigned long flags; + + /* read the comment in __queue_work() */ +- local_lock_irqsave(pendingb_lock, flags); ++ local_irq_save(flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + +- local_unlock_irqrestore(pendingb_lock, flags); ++ local_irq_restore(flags); + return ret; + } + EXPORT_SYMBOL(queue_delayed_work_on); +@@ -1638,7 +1597,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); +- local_unlock_irqrestore(pendingb_lock, flags); ++ local_irq_restore(flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ +@@ -1649,12 +1608,11 @@ EXPORT_SYMBOL_GPL(mod_delayed_work_on); + static void rcu_work_rcufn(struct rcu_head *rcu) + { + struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); +- unsigned long flags; + + /* read the comment in __queue_work() */ +- local_lock_irqsave(pendingb_lock, flags); ++ local_irq_disable(); + __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); +- local_unlock_irqrestore(pendingb_lock, flags); ++ local_irq_enable(); + } + + /** +@@ -1689,7 +1647,7 @@ EXPORT_SYMBOL(queue_rcu_work); + * necessary. + * + * LOCKING: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void worker_enter_idle(struct worker *worker) + { +@@ -1706,9 +1664,7 @@ static void worker_enter_idle(struct worker *worker) + worker->last_active = jiffies; + + /* idle_list is LIFO */ +- rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); +- rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); +@@ -1731,7 +1687,7 @@ static void worker_enter_idle(struct worker *worker) + * @worker is leaving idle state. Update stats. + * + * LOCKING: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void worker_leave_idle(struct worker *worker) + { +@@ -1741,9 +1697,7 @@ static void worker_leave_idle(struct worker *worker) + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; +- rt_lock_idle_list(pool); + list_del_init(&worker->entry); +- rt_unlock_idle_list(pool); + } + + static struct worker *alloc_worker(int node) +@@ -1868,11 +1822,11 @@ static struct worker *create_worker(struct worker_pool *pool) + worker_attach_to_pool(worker, pool); + + /* start the newly created worker */ +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + worker->pool->nr_workers++; + worker_enter_idle(worker); + wake_up_process(worker->task); +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + + return worker; + +@@ -1891,7 +1845,7 @@ static struct worker *create_worker(struct worker_pool *pool) + * be idle. + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void destroy_worker(struct worker *worker) + { +@@ -1908,9 +1862,7 @@ static void destroy_worker(struct worker *worker) + pool->nr_workers--; + pool->nr_idle--; + +- rt_lock_idle_list(pool); + list_del_init(&worker->entry); +- rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); + } +@@ -1919,7 +1871,7 @@ static void idle_worker_timeout(struct timer_list *t) + { + struct worker_pool *pool = from_timer(pool, t, idle_timer); + +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + while (too_many_workers(pool)) { + struct worker *worker; +@@ -1937,7 +1889,7 @@ static void idle_worker_timeout(struct timer_list *t) + destroy_worker(worker); + } + +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + } + + static void send_mayday(struct work_struct *work) +@@ -1968,8 +1920,8 @@ static void pool_mayday_timeout(struct timer_list *t) + struct worker_pool *pool = from_timer(pool, t, mayday_timer); + struct work_struct *work; + +- spin_lock_irq(&pool->lock); +- spin_lock(&wq_mayday_lock); /* for wq->maydays */ ++ raw_spin_lock_irq(&pool->lock); ++ raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ + + if (need_to_create_worker(pool)) { + /* +@@ -1982,8 +1934,8 @@ static void pool_mayday_timeout(struct timer_list *t) + send_mayday(work); + } + +- spin_unlock(&wq_mayday_lock); +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock(&wq_mayday_lock); ++ raw_spin_unlock_irq(&pool->lock); + + mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); + } +@@ -2002,7 +1954,7 @@ static void pool_mayday_timeout(struct timer_list *t) + * may_start_working() %true. + * + * LOCKING: +- * spin_lock_irq(pool->lock) which may be released and regrabbed ++ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. Called only from + * manager. + */ +@@ -2011,7 +1963,7 @@ __releases(&pool->lock) + __acquires(&pool->lock) + { + restart: +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + + /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ + mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); +@@ -2027,7 +1979,7 @@ __acquires(&pool->lock) + } + + del_timer_sync(&pool->mayday_timer); +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + /* + * This is necessary even after a new worker was just successfully + * created as @pool->lock was dropped and the new worker might have +@@ -2050,7 +2002,7 @@ __acquires(&pool->lock) + * and may_start_working() is true. + * + * CONTEXT: +- * spin_lock_irq(pool->lock) which may be released and regrabbed ++ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. + * + * Return: +@@ -2073,7 +2025,7 @@ static bool manage_workers(struct worker *worker) + + pool->manager = NULL; + pool->flags &= ~POOL_MANAGER_ACTIVE; +- wake_up(&wq_manager_wait); ++ swake_up_one(&wq_manager_wait); + return true; + } + +@@ -2089,7 +2041,7 @@ static bool manage_workers(struct worker *worker) + * call this function to process a work. + * + * CONTEXT: +- * spin_lock_irq(pool->lock) which is released and regrabbed. ++ * raw_spin_lock_irq(pool->lock) which is released and regrabbed. + */ + static void process_one_work(struct worker *worker, struct work_struct *work) + __releases(&pool->lock) +@@ -2171,7 +2123,7 @@ __acquires(&pool->lock) + */ + set_work_pool_and_clear_pending(work, pool->id); + +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + + lock_map_acquire(&pwq->wq->lockdep_map); + lock_map_acquire(&lockdep_map); +@@ -2226,7 +2178,7 @@ __acquires(&pool->lock) + */ + cond_resched(); + +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + /* clear cpu intensive status */ + if (unlikely(cpu_intensive)) +@@ -2249,7 +2201,7 @@ __acquires(&pool->lock) + * fetches a work from the top and executes it. + * + * CONTEXT: +- * spin_lock_irq(pool->lock) which may be released and regrabbed ++ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. + */ + static void process_scheduled_works(struct worker *worker) +@@ -2291,11 +2243,11 @@ static int worker_thread(void *__worker) + /* tell the scheduler that this is a workqueue worker */ + set_pf_worker(true); + woke_up: +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + /* am I supposed to die? */ + if (unlikely(worker->flags & WORKER_DIE)) { +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + WARN_ON_ONCE(!list_empty(&worker->entry)); + set_pf_worker(false); + +@@ -2361,7 +2313,7 @@ static int worker_thread(void *__worker) + */ + worker_enter_idle(worker); + __set_current_state(TASK_IDLE); +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + schedule(); + goto woke_up; + } +@@ -2415,7 +2367,7 @@ static int rescuer_thread(void *__rescuer) + should_stop = kthread_should_stop(); + + /* see whether any pwq is asking for help */ +- spin_lock_irq(&wq_mayday_lock); ++ raw_spin_lock_irq(&wq_mayday_lock); + + while (!list_empty(&wq->maydays)) { + struct pool_workqueue *pwq = list_first_entry(&wq->maydays, +@@ -2427,11 +2379,11 @@ static int rescuer_thread(void *__rescuer) + __set_current_state(TASK_RUNNING); + list_del_init(&pwq->mayday_node); + +- spin_unlock_irq(&wq_mayday_lock); ++ raw_spin_unlock_irq(&wq_mayday_lock); + + worker_attach_to_pool(rescuer, pool); + +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + /* + * Slurp in all works issued via this workqueue and +@@ -2460,7 +2412,7 @@ static int rescuer_thread(void *__rescuer) + * incur MAYDAY_INTERVAL delay inbetween. + */ + if (need_to_create_worker(pool)) { +- spin_lock(&wq_mayday_lock); ++ raw_spin_lock(&wq_mayday_lock); + /* + * Queue iff we aren't racing destruction + * and somebody else hasn't queued it already. +@@ -2469,7 +2421,7 @@ static int rescuer_thread(void *__rescuer) + get_pwq(pwq); + list_add_tail(&pwq->mayday_node, &wq->maydays); + } +- spin_unlock(&wq_mayday_lock); ++ raw_spin_unlock(&wq_mayday_lock); + } + } + +@@ -2487,14 +2439,14 @@ static int rescuer_thread(void *__rescuer) + if (need_more_worker(pool)) + wake_up_worker(pool); + +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + + worker_detach_from_pool(rescuer); + +- spin_lock_irq(&wq_mayday_lock); ++ raw_spin_lock_irq(&wq_mayday_lock); + } + +- spin_unlock_irq(&wq_mayday_lock); ++ raw_spin_unlock_irq(&wq_mayday_lock); + + if (should_stop) { + __set_current_state(TASK_RUNNING); +@@ -2574,7 +2526,7 @@ static void wq_barrier_func(struct work_struct *work) + * underneath us, so we can't reliably determine pwq from @target. + * + * CONTEXT: +- * spin_lock_irq(pool->lock). ++ * raw_spin_lock_irq(pool->lock). + */ + static void insert_wq_barrier(struct pool_workqueue *pwq, + struct wq_barrier *barr, +@@ -2661,7 +2613,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, + for_each_pwq(pwq, wq) { + struct worker_pool *pool = pwq->pool; + +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + if (flush_color >= 0) { + WARN_ON_ONCE(pwq->flush_color != -1); +@@ -2678,7 +2630,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, + pwq->work_color = work_color; + } + +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + } + + if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) +@@ -2878,9 +2830,9 @@ void drain_workqueue(struct workqueue_struct *wq) + for_each_pwq(pwq, wq) { + bool drained; + +- spin_lock_irq(&pwq->pool->lock); ++ raw_spin_lock_irq(&pwq->pool->lock); + drained = !pwq->nr_active && list_empty(&pwq->delayed_works); +- spin_unlock_irq(&pwq->pool->lock); ++ raw_spin_unlock_irq(&pwq->pool->lock); + + if (drained) + continue; +@@ -2916,7 +2868,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, + return false; + } + +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { +@@ -2932,7 +2884,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, + check_flush_dependency(pwq->wq, work); + + insert_wq_barrier(pwq, barr, work, worker); +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + + /* + * Force a lock recursion deadlock when using flush_work() inside a +@@ -2951,7 +2903,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, + rcu_read_unlock(); + return true; + already_gone: +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + rcu_read_unlock(); + return false; + } +@@ -3052,7 +3004,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); +- local_unlock_irqrestore(pendingb_lock, flags); ++ local_irq_restore(flags); + + /* + * This allows canceling during early boot. We know that @work +@@ -3113,10 +3065,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); + */ + bool flush_delayed_work(struct delayed_work *dwork) + { +- local_lock_irq(pendingb_lock); ++ local_irq_disable(); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- local_unlock_irq(pendingb_lock); ++ local_irq_enable(); + return flush_work(&dwork->work); + } + EXPORT_SYMBOL(flush_delayed_work); +@@ -3154,7 +3106,7 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) + return false; + + set_work_pool_and_clear_pending(work, get_work_pool_id(work)); +- local_unlock_irqrestore(pendingb_lock, flags); ++ local_irq_restore(flags); + return ret; + } + +@@ -3264,7 +3216,7 @@ EXPORT_SYMBOL_GPL(execute_in_process_context); + * + * Undo alloc_workqueue_attrs(). + */ +-void free_workqueue_attrs(struct workqueue_attrs *attrs) ++static void free_workqueue_attrs(struct workqueue_attrs *attrs) + { + if (attrs) { + free_cpumask_var(attrs->cpumask); +@@ -3274,21 +3226,20 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs) + + /** + * alloc_workqueue_attrs - allocate a workqueue_attrs +- * @gfp_mask: allocation mask to use + * + * Allocate a new workqueue_attrs, initialize with default settings and + * return it. + * + * Return: The allocated new workqueue_attr on success. %NULL on failure. + */ +-struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask) ++static struct workqueue_attrs *alloc_workqueue_attrs(void) + { + struct workqueue_attrs *attrs; + +- attrs = kzalloc(sizeof(*attrs), gfp_mask); ++ attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); + if (!attrs) + goto fail; +- if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask)) ++ if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) + goto fail; + + cpumask_copy(attrs->cpumask, cpu_possible_mask); +@@ -3345,7 +3296,7 @@ static bool wqattrs_equal(const struct workqueue_attrs *a, + */ + static int init_worker_pool(struct worker_pool *pool) + { +- spin_lock_init(&pool->lock); ++ raw_spin_lock_init(&pool->lock); + pool->id = -1; + pool->cpu = -1; + pool->node = NUMA_NO_NODE; +@@ -3366,7 +3317,7 @@ static int init_worker_pool(struct worker_pool *pool) + pool->refcnt = 1; + + /* shouldn't fail above this point */ +- pool->attrs = alloc_workqueue_attrs(GFP_KERNEL); ++ pool->attrs = alloc_workqueue_attrs(); + if (!pool->attrs) + return -ENOMEM; + return 0; +@@ -3431,15 +3382,15 @@ static void put_unbound_pool(struct worker_pool *pool) + * @pool's workers from blocking on attach_mutex. We're the last + * manager and @pool gets freed with the flag set. + */ +- spin_lock_irq(&pool->lock); +- wait_event_lock_irq(wq_manager_wait, ++ raw_spin_lock_irq(&pool->lock); ++ swait_event_lock_irq(wq_manager_wait, + !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock); + pool->flags |= POOL_MANAGER_ACTIVE; + + while ((worker = first_idle_worker(pool))) + destroy_worker(worker); + WARN_ON(pool->nr_workers || pool->nr_idle); +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + + mutex_lock(&wq_pool_attach_mutex); + if (!list_empty(&pool->workers)) +@@ -3599,7 +3550,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) + return; + + /* this function can be called during early boot w/ irq disabled */ +- spin_lock_irqsave(&pwq->pool->lock, flags); ++ raw_spin_lock_irqsave(&pwq->pool->lock, flags); + + /* + * During [un]freezing, the caller is responsible for ensuring that +@@ -3629,7 +3580,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) + pwq->max_active = 0; + } + +- spin_unlock_irqrestore(&pwq->pool->lock, flags); ++ raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); + } + + /* initialize newly alloced @pwq which is associated with @wq and @pool */ +@@ -3802,8 +3753,8 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, + + ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); + +- new_attrs = alloc_workqueue_attrs(GFP_KERNEL); +- tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL); ++ new_attrs = alloc_workqueue_attrs(); ++ tmp_attrs = alloc_workqueue_attrs(); + if (!ctx || !new_attrs || !tmp_attrs) + goto out_free; + +@@ -3939,7 +3890,7 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, + * + * Return: 0 on success and -errno on failure. + */ +-int apply_workqueue_attrs(struct workqueue_struct *wq, ++static int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) + { + int ret; +@@ -3950,7 +3901,6 @@ int apply_workqueue_attrs(struct workqueue_struct *wq, + + return ret; + } +-EXPORT_SYMBOL_GPL(apply_workqueue_attrs); + + /** + * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug +@@ -4028,9 +3978,9 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, + + use_dfl_pwq: + mutex_lock(&wq->mutex); +- spin_lock_irq(&wq->dfl_pwq->pool->lock); ++ raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); + get_pwq(wq->dfl_pwq); +- spin_unlock_irq(&wq->dfl_pwq->pool->lock); ++ raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); + old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); + out_unlock: + mutex_unlock(&wq->mutex); +@@ -4149,7 +4099,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, + return NULL; + + if (flags & WQ_UNBOUND) { +- wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL); ++ wq->unbound_attrs = alloc_workqueue_attrs(); + if (!wq->unbound_attrs) + goto err_free_wq; + } +@@ -4236,9 +4186,9 @@ void destroy_workqueue(struct workqueue_struct *wq) + struct worker *rescuer = wq->rescuer; + + /* this prevents new queueing */ +- spin_lock_irq(&wq_mayday_lock); ++ raw_spin_lock_irq(&wq_mayday_lock); + wq->rescuer = NULL; +- spin_unlock_irq(&wq_mayday_lock); ++ raw_spin_unlock_irq(&wq_mayday_lock); + + /* rescuer will empty maydays list before exiting */ + kthread_stop(rescuer->task); +@@ -4433,10 +4383,10 @@ unsigned int work_busy(struct work_struct *work) + rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { +- spin_lock_irqsave(&pool->lock, flags); ++ raw_spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; +- spin_unlock_irqrestore(&pool->lock, flags); ++ raw_spin_unlock_irqrestore(&pool->lock, flags); + } + rcu_read_unlock(); + +@@ -4643,10 +4593,10 @@ void show_workqueue_state(void) + pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); + + for_each_pwq(pwq, wq) { +- spin_lock_irqsave(&pwq->pool->lock, flags); ++ raw_spin_lock_irqsave(&pwq->pool->lock, flags); + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + show_pwq(pwq); +- spin_unlock_irqrestore(&pwq->pool->lock, flags); ++ raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_workqueue_state(). Avoid triggering +@@ -4660,7 +4610,7 @@ void show_workqueue_state(void) + struct worker *worker; + bool first = true; + +- spin_lock_irqsave(&pool->lock, flags); ++ raw_spin_lock_irqsave(&pool->lock, flags); + if (pool->nr_workers == pool->nr_idle) + goto next_pool; + +@@ -4679,7 +4629,7 @@ void show_workqueue_state(void) + } + pr_cont("\n"); + next_pool: +- spin_unlock_irqrestore(&pool->lock, flags); ++ raw_spin_unlock_irqrestore(&pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_workqueue_state(). Avoid triggering +@@ -4709,7 +4659,7 @@ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) + struct worker_pool *pool = worker->pool; + + if (pool) { +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + /* + * ->desc tracks information (wq name or + * set_worker_desc()) for the latest execution. If +@@ -4723,7 +4673,7 @@ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) + scnprintf(buf + off, size - off, "-%s", + worker->desc); + } +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + } + } + +@@ -4754,7 +4704,7 @@ static void unbind_workers(int cpu) + + for_each_cpu_worker_pool(pool, cpu) { + mutex_lock(&wq_pool_attach_mutex); +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + /* + * We've blocked all attach/detach operations. Make all workers +@@ -4768,7 +4718,7 @@ static void unbind_workers(int cpu) + + pool->flags |= POOL_DISASSOCIATED; + +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + mutex_unlock(&wq_pool_attach_mutex); + + /* +@@ -4794,9 +4744,9 @@ static void unbind_workers(int cpu) + * worker blocking could lead to lengthy stalls. Kick off + * unbound chain execution of currently pending work items. + */ +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + wake_up_worker(pool); +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + } + } + +@@ -4823,7 +4773,7 @@ static void rebind_workers(struct worker_pool *pool) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, + pool->attrs->cpumask) < 0); + +- spin_lock_irq(&pool->lock); ++ raw_spin_lock_irq(&pool->lock); + + pool->flags &= ~POOL_DISASSOCIATED; + +@@ -4862,7 +4812,7 @@ static void rebind_workers(struct worker_pool *pool) + WRITE_ONCE(worker->flags, worker_flags); + } + +- spin_unlock_irq(&pool->lock); ++ raw_spin_unlock_irq(&pool->lock); + } + + /** +@@ -5321,7 +5271,7 @@ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) + + lockdep_assert_held(&wq_pool_mutex); + +- attrs = alloc_workqueue_attrs(GFP_KERNEL); ++ attrs = alloc_workqueue_attrs(); + if (!attrs) + return NULL; + +@@ -5750,7 +5700,7 @@ static void __init wq_numa_init(void) + return; + } + +- wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL); ++ wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(); + BUG_ON(!wq_update_unbound_numa_attrs_buf); + + /* +@@ -5825,7 +5775,7 @@ int __init workqueue_init_early(void) + for (i = 0; i < NR_STD_WORKER_POOLS; i++) { + struct workqueue_attrs *attrs; + +- BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); ++ BUG_ON(!(attrs = alloc_workqueue_attrs())); + attrs->nice = std_nice[i]; + unbound_std_wq_attrs[i] = attrs; + +@@ -5834,7 +5784,7 @@ int __init workqueue_init_early(void) + * guaranteed by max_active which is enforced by pwqs. + * Turn off NUMA so that dfl_pwq is used for all nodes. + */ +- BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); ++ BUG_ON(!(attrs = alloc_workqueue_attrs())); + attrs->nice = std_nice[i]; + attrs->no_numa = true; + ordered_wq_attrs[i] = attrs; +-- +2.36.1 + diff --git a/debian/patches-rt/0286-i2c-exynos5-Remove-IRQF_ONESHOT.patch b/debian/patches-rt/0286-i2c-exynos5-Remove-IRQF_ONESHOT.patch new file mode 100644 index 000000000..077cdff08 --- /dev/null +++ b/debian/patches-rt/0286-i2c-exynos5-Remove-IRQF_ONESHOT.patch @@ -0,0 +1,48 @@ +From 6a0747038b36d84b3cb51152e09dda7db35fd222 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 13 Aug 2019 12:30:12 +0200 +Subject: [PATCH 286/347] i2c: exynos5: Remove IRQF_ONESHOT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 4b217df0ab3f7910c96e42091cc7d9f221d05f01 ] + +The drivers sets IRQF_ONESHOT and passes only a primary handler. The IRQ +is masked while the primary is handler is invoked independently of +IRQF_ONESHOT. +With IRQF_ONESHOT the core code will not force-thread the interrupt and +this is probably not intended. I *assume* that the original author copied +the IRQ registration from another driver which passed a primary and +secondary handler and removed the secondary handler but keeping the +ONESHOT flag. + +Remove IRQF_ONESHOT. + +Reported-by: Benjamin Rouxel <benjamin.rouxel@uva.nl> +Tested-by: Benjamin Rouxel <benjamin.rouxel@uva.nl> +Cc: Kukjin Kim <kgene@kernel.org> +Cc: Krzysztof Kozlowski <krzk@kernel.org> +Cc: linux-samsung-soc@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/i2c/busses/i2c-exynos5.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c +index c1ce2299a76e..5c57ecf4b79e 100644 +--- a/drivers/i2c/busses/i2c-exynos5.c ++++ b/drivers/i2c/busses/i2c-exynos5.c +@@ -800,9 +800,7 @@ static int exynos5_i2c_probe(struct platform_device *pdev) + } + + ret = devm_request_irq(&pdev->dev, i2c->irq, exynos5_i2c_irq, +- IRQF_NO_SUSPEND | IRQF_ONESHOT, +- dev_name(&pdev->dev), i2c); +- ++ IRQF_NO_SUSPEND, dev_name(&pdev->dev), i2c); + if (ret != 0) { + dev_err(&pdev->dev, "cannot request HS-I2C IRQ %d\n", i2c->irq); + goto err_clk; +-- +2.36.1 + diff --git a/debian/patches-rt/0287-i2c-hix5hd2-Remove-IRQF_ONESHOT.patch b/debian/patches-rt/0287-i2c-hix5hd2-Remove-IRQF_ONESHOT.patch new file mode 100644 index 000000000..72f7695b6 --- /dev/null +++ b/debian/patches-rt/0287-i2c-hix5hd2-Remove-IRQF_ONESHOT.patch @@ -0,0 +1,42 @@ +From d269babaefa33b4ea277b2a6033637b320c77f6f Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 13 Aug 2019 12:30:37 +0200 +Subject: [PATCH 287/347] i2c: hix5hd2: Remove IRQF_ONESHOT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit e88b481f3f86f11e3243e0808a830e5ca5782a9d ] + +The drivers sets IRQF_ONESHOT and passes only a primary handler. The IRQ +is masked while the primary is handler is invoked independently of +IRQF_ONESHOT. +With IRQF_ONESHOT the core code will not force-thread the interrupt and +this is probably not intended. I *assume* that the original author copied +the IRQ registration from another driver which passed a primary and +secondary handler and removed the secondary handler but keeping the +ONESHOT flag. + +Remove IRQF_ONESHOT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/i2c/busses/i2c-hix5hd2.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c +index b5ad7696adf9..0f08ef1f7f41 100644 +--- a/drivers/i2c/busses/i2c-hix5hd2.c ++++ b/drivers/i2c/busses/i2c-hix5hd2.c +@@ -449,8 +449,7 @@ static int hix5hd2_i2c_probe(struct platform_device *pdev) + hix5hd2_i2c_init(priv); + + ret = devm_request_irq(&pdev->dev, irq, hix5hd2_i2c_irq, +- IRQF_NO_SUSPEND | IRQF_ONESHOT, +- dev_name(&pdev->dev), priv); ++ IRQF_NO_SUSPEND, dev_name(&pdev->dev), priv); + if (ret != 0) { + dev_err(&pdev->dev, "cannot request HS-I2C IRQ %d\n", irq); + goto err_clk; +-- +2.36.1 + diff --git a/debian/patches-rt/0288-sched-deadline-Ensure-inactive_timer-runs-in-hardirq.patch b/debian/patches-rt/0288-sched-deadline-Ensure-inactive_timer-runs-in-hardirq.patch new file mode 100644 index 000000000..8e5e4c8de --- /dev/null +++ b/debian/patches-rt/0288-sched-deadline-Ensure-inactive_timer-runs-in-hardirq.patch @@ -0,0 +1,50 @@ +From 8161b3a85bed84a4cc75f68d048b35c2e09442ed Mon Sep 17 00:00:00 2001 +From: Juri Lelli <juri.lelli@redhat.com> +Date: Wed, 31 Jul 2019 12:37:15 +0200 +Subject: [PATCH 288/347] sched/deadline: Ensure inactive_timer runs in hardirq + context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit ba94e7aed7405c58251b1380e6e7d73aa8284b41 ] + +SCHED_DEADLINE inactive timer needs to run in hardirq context (as +dl_task_timer already does) on PREEMPT_RT + +Change the mode to HRTIMER_MODE_REL_HARD. + +[ tglx: Fixed up the start site, so mode debugging works ] + +Signed-off-by: Juri Lelli <juri.lelli@redhat.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Link: https://lkml.kernel.org/r/20190731103715.4047-1-juri.lelli@redhat.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/deadline.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c +index 1a285367081c..0bc1bad199c1 100644 +--- a/kernel/sched/deadline.c ++++ b/kernel/sched/deadline.c +@@ -287,7 +287,7 @@ static void task_non_contending(struct task_struct *p) + + dl_se->dl_non_contending = 1; + get_task_struct(p); +- hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL); ++ hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD); + } + + static void task_contending(struct sched_dl_entity *dl_se, int flags) +@@ -1325,7 +1325,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) + { + struct hrtimer *timer = &dl_se->inactive_timer; + +- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + timer->function = inactive_task_timer; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0289-thermal-x86_pkg_temp-make-pkg_temp_lock-a-raw-spinlo.patch b/debian/patches-rt/0289-thermal-x86_pkg_temp-make-pkg_temp_lock-a-raw-spinlo.patch new file mode 100644 index 000000000..3fe37ca3c --- /dev/null +++ b/debian/patches-rt/0289-thermal-x86_pkg_temp-make-pkg_temp_lock-a-raw-spinlo.patch @@ -0,0 +1,120 @@ +From 402252a8f4f986a5eb23639e3b9a1d9df4902d27 Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Mon, 15 Jul 2019 15:25:00 -0500 +Subject: [PATCH 289/347] thermal/x86_pkg_temp: make pkg_temp_lock a raw + spinlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 8b03bb3ea7861b70b506199a69b1c8f81fe2d4d0 ] + +The spinlock pkg_temp_lock has the potential of being taken in atomic +context on v5.2-rt PREEMPT_RT. It's static and limited scope so +go ahead and make it a raw spinlock. + +Signed-off-by: Clark Williams <williams@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/thermal/x86_pkg_temp_thermal.c | 24 ++++++++++++------------ + 1 file changed, 12 insertions(+), 12 deletions(-) + +diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c +index 1ef937d799e4..540becb78a0f 100644 +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -75,7 +75,7 @@ static int max_packages __read_mostly; + /* Array of package pointers */ + static struct pkg_device **packages; + /* Serializes interrupt notification, work and hotplug */ +-static DEFINE_SPINLOCK(pkg_temp_lock); ++static DEFINE_RAW_SPINLOCK(pkg_temp_lock); + /* Protects zone operation in the work function against hotplug removal */ + static DEFINE_MUTEX(thermal_zone_mutex); + +@@ -291,12 +291,12 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work) + u64 msr_val, wr_val; + + mutex_lock(&thermal_zone_mutex); +- spin_lock_irq(&pkg_temp_lock); ++ raw_spin_lock_irq(&pkg_temp_lock); + ++pkg_work_cnt; + + pkgdev = pkg_temp_thermal_get_dev(cpu); + if (!pkgdev) { +- spin_unlock_irq(&pkg_temp_lock); ++ raw_spin_unlock_irq(&pkg_temp_lock); + mutex_unlock(&thermal_zone_mutex); + return; + } +@@ -310,7 +310,7 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work) + } + + enable_pkg_thres_interrupt(); +- spin_unlock_irq(&pkg_temp_lock); ++ raw_spin_unlock_irq(&pkg_temp_lock); + + /* + * If tzone is not NULL, then thermal_zone_mutex will prevent the +@@ -335,7 +335,7 @@ static int pkg_thermal_notify(u64 msr_val) + struct pkg_device *pkgdev; + unsigned long flags; + +- spin_lock_irqsave(&pkg_temp_lock, flags); ++ raw_spin_lock_irqsave(&pkg_temp_lock, flags); + ++pkg_interrupt_cnt; + + disable_pkg_thres_interrupt(); +@@ -347,7 +347,7 @@ static int pkg_thermal_notify(u64 msr_val) + pkg_thermal_schedule_work(pkgdev->cpu, &pkgdev->work); + } + +- spin_unlock_irqrestore(&pkg_temp_lock, flags); ++ raw_spin_unlock_irqrestore(&pkg_temp_lock, flags); + return 0; + } + +@@ -393,9 +393,9 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) + pkgdev->msr_pkg_therm_high); + + cpumask_set_cpu(cpu, &pkgdev->cpumask); +- spin_lock_irq(&pkg_temp_lock); ++ raw_spin_lock_irq(&pkg_temp_lock); + packages[pkgid] = pkgdev; +- spin_unlock_irq(&pkg_temp_lock); ++ raw_spin_unlock_irq(&pkg_temp_lock); + return 0; + } + +@@ -432,7 +432,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu) + } + + /* Protect against work and interrupts */ +- spin_lock_irq(&pkg_temp_lock); ++ raw_spin_lock_irq(&pkg_temp_lock); + + /* + * Check whether this cpu was the current target and store the new +@@ -464,9 +464,9 @@ static int pkg_thermal_cpu_offline(unsigned int cpu) + * To cancel the work we need to drop the lock, otherwise + * we might deadlock if the work needs to be flushed. + */ +- spin_unlock_irq(&pkg_temp_lock); ++ raw_spin_unlock_irq(&pkg_temp_lock); + cancel_delayed_work_sync(&pkgdev->work); +- spin_lock_irq(&pkg_temp_lock); ++ raw_spin_lock_irq(&pkg_temp_lock); + /* + * If this is not the last cpu in the package and the work + * did not run after we dropped the lock above, then we +@@ -477,7 +477,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu) + pkg_thermal_schedule_work(target, &pkgdev->work); + } + +- spin_unlock_irq(&pkg_temp_lock); ++ raw_spin_unlock_irq(&pkg_temp_lock); + + /* Final cleanup if this is the last cpu */ + if (lastcpu) +-- +2.36.1 + diff --git a/debian/patches-rt/0290-dma-buf-Use-seqlock_t-instread-disabling-preemption.patch b/debian/patches-rt/0290-dma-buf-Use-seqlock_t-instread-disabling-preemption.patch new file mode 100644 index 000000000..5376a0901 --- /dev/null +++ b/debian/patches-rt/0290-dma-buf-Use-seqlock_t-instread-disabling-preemption.patch @@ -0,0 +1,296 @@ +From f2b7bfd175503ed854870b368aaa9e1be2159cab Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 14 Aug 2019 16:38:43 +0200 +Subject: [PATCH 290/347] dma-buf: Use seqlock_t instread disabling preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 240610aa31094f51f299f06eb8dae8d4cd8d4500 ] + +"dma reservation" disables preemption while acquiring the write access +for "seqcount" and then may acquire a spinlock_t. + +Replace the seqcount with a seqlock_t which provides seqcount like +semantic and lock for writer. + +Link: https://lkml.kernel.org/r/f410b429-db86-f81c-7c67-f563fa808b62@free.fr +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/dma-buf/dma-buf.c | 8 ++-- + drivers/dma-buf/reservation.c | 43 +++++++------------ + .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6 +-- + drivers/gpu/drm/i915/i915_gem.c | 10 ++--- + include/linux/reservation.h | 4 +- + 5 files changed, 29 insertions(+), 42 deletions(-) + +diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c +index 69842145c223..4c3ef46e7149 100644 +--- a/drivers/dma-buf/dma-buf.c ++++ b/drivers/dma-buf/dma-buf.c +@@ -179,7 +179,7 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) + return 0; + + retry: +- seq = read_seqcount_begin(&resv->seq); ++ seq = read_seqbegin(&resv->seq); + rcu_read_lock(); + + fobj = rcu_dereference(resv->fence); +@@ -188,7 +188,7 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) + else + shared_count = 0; + fence_excl = rcu_dereference(resv->fence_excl); +- if (read_seqcount_retry(&resv->seq, seq)) { ++ if (read_seqretry(&resv->seq, seq)) { + rcu_read_unlock(); + goto retry; + } +@@ -1046,12 +1046,12 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) + + robj = buf_obj->resv; + while (true) { +- seq = read_seqcount_begin(&robj->seq); ++ seq = read_seqbegin(&robj->seq); + rcu_read_lock(); + fobj = rcu_dereference(robj->fence); + shared_count = fobj ? fobj->shared_count : 0; + fence = rcu_dereference(robj->fence_excl); +- if (!read_seqcount_retry(&robj->seq, seq)) ++ if (!read_seqretry(&robj->seq, seq)) + break; + rcu_read_unlock(); + } +diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c +index 49ab09468ba1..f11d58492216 100644 +--- a/drivers/dma-buf/reservation.c ++++ b/drivers/dma-buf/reservation.c +@@ -109,8 +109,7 @@ reservation_object_add_shared_inplace(struct reservation_object *obj, + + dma_fence_get(fence); + +- preempt_disable(); +- write_seqcount_begin(&obj->seq); ++ write_seqlock(&obj->seq); + + for (i = 0; i < fobj->shared_count; ++i) { + struct dma_fence *old_fence; +@@ -121,8 +120,7 @@ reservation_object_add_shared_inplace(struct reservation_object *obj, + if (old_fence->context == fence->context) { + /* memory barrier is added by write_seqcount_begin */ + RCU_INIT_POINTER(fobj->shared[i], fence); +- write_seqcount_end(&obj->seq); +- preempt_enable(); ++ write_sequnlock(&obj->seq); + + dma_fence_put(old_fence); + return; +@@ -146,8 +144,7 @@ reservation_object_add_shared_inplace(struct reservation_object *obj, + fobj->shared_count++; + } + +- write_seqcount_end(&obj->seq); +- preempt_enable(); ++ write_sequnlock(&obj->seq); + + dma_fence_put(signaled); + } +@@ -191,15 +188,13 @@ reservation_object_add_shared_replace(struct reservation_object *obj, + fobj->shared_count++; + + done: +- preempt_disable(); +- write_seqcount_begin(&obj->seq); ++ write_seqlock(&obj->seq); + /* + * RCU_INIT_POINTER can be used here, + * seqcount provides the necessary barriers + */ + RCU_INIT_POINTER(obj->fence, fobj); +- write_seqcount_end(&obj->seq); +- preempt_enable(); ++ write_sequnlock(&obj->seq); + + if (!old) + return; +@@ -259,14 +254,11 @@ void reservation_object_add_excl_fence(struct reservation_object *obj, + if (fence) + dma_fence_get(fence); + +- preempt_disable(); +- write_seqcount_begin(&obj->seq); +- /* write_seqcount_begin provides the necessary memory barrier */ ++ write_seqlock(&obj->seq); + RCU_INIT_POINTER(obj->fence_excl, fence); + if (old) + old->shared_count = 0; +- write_seqcount_end(&obj->seq); +- preempt_enable(); ++ write_sequnlock(&obj->seq); + + /* inplace update, no shared fences */ + while (i--) +@@ -349,13 +341,10 @@ int reservation_object_copy_fences(struct reservation_object *dst, + src_list = reservation_object_get_list(dst); + old = reservation_object_get_excl(dst); + +- preempt_disable(); +- write_seqcount_begin(&dst->seq); +- /* write_seqcount_begin provides the necessary memory barrier */ ++ write_seqlock(&dst->seq); + RCU_INIT_POINTER(dst->fence_excl, new); + RCU_INIT_POINTER(dst->fence, dst_list); +- write_seqcount_end(&dst->seq); +- preempt_enable(); ++ write_sequnlock(&dst->seq); + + if (src_list) + kfree_rcu(src_list, rcu); +@@ -396,7 +385,7 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, + shared_count = i = 0; + + rcu_read_lock(); +- seq = read_seqcount_begin(&obj->seq); ++ seq = read_seqbegin(&obj->seq); + + fence_excl = rcu_dereference(obj->fence_excl); + if (fence_excl && !dma_fence_get_rcu(fence_excl)) +@@ -445,7 +434,7 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, + } + } + +- if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) { ++ if (i != shared_count || read_seqretry(&obj->seq, seq)) { + while (i--) + dma_fence_put(shared[i]); + dma_fence_put(fence_excl); +@@ -494,7 +483,7 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, + + retry: + shared_count = 0; +- seq = read_seqcount_begin(&obj->seq); ++ seq = read_seqbegin(&obj->seq); + rcu_read_lock(); + i = -1; + +@@ -541,7 +530,7 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, + + rcu_read_unlock(); + if (fence) { +- if (read_seqcount_retry(&obj->seq, seq)) { ++ if (read_seqretry(&obj->seq, seq)) { + dma_fence_put(fence); + goto retry; + } +@@ -597,7 +586,7 @@ bool reservation_object_test_signaled_rcu(struct reservation_object *obj, + retry: + ret = true; + shared_count = 0; +- seq = read_seqcount_begin(&obj->seq); ++ seq = read_seqbegin(&obj->seq); + + if (test_all) { + unsigned i; +@@ -618,7 +607,7 @@ bool reservation_object_test_signaled_rcu(struct reservation_object *obj, + break; + } + +- if (read_seqcount_retry(&obj->seq, seq)) ++ if (read_seqretry(&obj->seq, seq)) + goto retry; + } + +@@ -631,7 +620,7 @@ bool reservation_object_test_signaled_rcu(struct reservation_object *obj, + if (ret < 0) + goto retry; + +- if (read_seqcount_retry(&obj->seq, seq)) ++ if (read_seqretry(&obj->seq, seq)) + goto retry; + } + } +diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +index 4488aad64643..f22feb25eba9 100644 +--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c ++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +@@ -261,11 +261,9 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, + } + + /* Install the new fence list, seqcount provides the barriers */ +- preempt_disable(); +- write_seqcount_begin(&resv->seq); ++ write_seqlock(&resv->seq); + RCU_INIT_POINTER(resv->fence, new); +- write_seqcount_end(&resv->seq); +- preempt_enable(); ++ write_sequnlock(&resv->seq); + + /* Drop the references to the removed fences or move them to ef_list */ + for (i = j, k = 0; i < old->shared_count; ++i) { +diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c +index 5b0d6d8b3ab8..3fe4a1e93a1a 100644 +--- a/drivers/gpu/drm/i915/i915_gem.c ++++ b/drivers/gpu/drm/i915/i915_gem.c +@@ -516,7 +516,7 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, + long timeout, + struct intel_rps_client *rps_client) + { +- unsigned int seq = __read_seqcount_begin(&resv->seq); ++ unsigned int seq = read_seqbegin(&resv->seq); + struct dma_fence *excl; + bool prune_fences = false; + +@@ -569,9 +569,9 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, + * signaled and that the reservation object has not been changed (i.e. + * no new fences have been added). + */ +- if (prune_fences && !__read_seqcount_retry(&resv->seq, seq)) { ++ if (prune_fences && !read_seqretry(&resv->seq, seq)) { + if (reservation_object_trylock(resv)) { +- if (!__read_seqcount_retry(&resv->seq, seq)) ++ if (!read_seqretry(&resv->seq, seq)) + reservation_object_add_excl_fence(resv, NULL); + reservation_object_unlock(resv); + } +@@ -4696,7 +4696,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, + * + */ + retry: +- seq = raw_read_seqcount(&obj->resv->seq); ++ seq = read_seqbegin(&obj->resv->seq); + + /* Translate the exclusive fence to the READ *and* WRITE engine */ + args->busy = busy_check_writer(rcu_dereference(obj->resv->fence_excl)); +@@ -4714,7 +4714,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, + } + } + +- if (args->busy && read_seqcount_retry(&obj->resv->seq, seq)) ++ if (args->busy && read_seqretry(&obj->resv->seq, seq)) + goto retry; + + err = 0; +diff --git a/include/linux/reservation.h b/include/linux/reservation.h +index 02166e815afb..0b31df1af698 100644 +--- a/include/linux/reservation.h ++++ b/include/linux/reservation.h +@@ -72,7 +72,7 @@ struct reservation_object_list { + */ + struct reservation_object { + struct ww_mutex lock; +- seqcount_t seq; ++ seqlock_t seq; + + struct dma_fence __rcu *fence_excl; + struct reservation_object_list __rcu *fence; +@@ -92,7 +92,7 @@ reservation_object_init(struct reservation_object *obj) + { + ww_mutex_init(&obj->lock, &reservation_ww_class); + +- __seqcount_init(&obj->seq, reservation_seqcount_string, &reservation_seqcount_class); ++ seqlock_init(&obj->seq); + RCU_INIT_POINTER(obj->fence, NULL); + RCU_INIT_POINTER(obj->fence_excl, NULL); + obj->staged = NULL; +-- +2.36.1 + diff --git a/debian/patches-rt/0291-KVM-arm-arm64-Let-the-timer-expire-in-hardirq-contex.patch b/debian/patches-rt/0291-KVM-arm-arm64-Let-the-timer-expire-in-hardirq-contex.patch new file mode 100644 index 000000000..d290086bf --- /dev/null +++ b/debian/patches-rt/0291-KVM-arm-arm64-Let-the-timer-expire-in-hardirq-contex.patch @@ -0,0 +1,54 @@ +From 1e93492b5c8f5b655d5c6e7c3867eef80ef38223 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 13 Aug 2019 14:29:41 +0200 +Subject: [PATCH 291/347] KVM: arm/arm64: Let the timer expire in hardirq + context on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 719cc080c914045a6e35787bf4dc3ba91cfd3efb ] + +The timers are canceled from an preempt-notifier which is invoked with +disabled preemption which is not allowed on PREEMPT_RT. +The timer callback is short so in could be invoked in hard-IRQ context +on -RT. + +Let the timer expire on hard-IRQ context even on -RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Acked-by: Marc Zyngier <maz@kernel.org> +Tested-by: Julien Grall <julien.grall@arm.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + virt/kvm/arm/arch_timer.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c +index 17cecc96f735..217d39f40393 100644 +--- a/virt/kvm/arm/arch_timer.c ++++ b/virt/kvm/arm/arch_timer.c +@@ -67,7 +67,7 @@ static inline bool userspace_irqchip(struct kvm *kvm) + static void soft_timer_start(struct hrtimer *hrt, u64 ns) + { + hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), +- HRTIMER_MODE_ABS); ++ HRTIMER_MODE_ABS_HARD); + } + + static void soft_timer_cancel(struct hrtimer *hrt, struct work_struct *work) +@@ -638,10 +638,10 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) + vcpu_ptimer(vcpu)->cntvoff = 0; + + INIT_WORK(&timer->expired, kvm_timer_inject_irq_work); +- hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + timer->bg_timer.function = kvm_bg_timer_expire; + +- hrtimer_init(&timer->phys_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init(&timer->phys_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + timer->phys_timer.function = kvm_phys_timer_expire; + + vtimer->irq.irq = default_vtimer_irq.irq; +-- +2.36.1 + diff --git a/debian/patches-rt/0292-x86-preempt-Check-preemption-level-before-looking-at.patch b/debian/patches-rt/0292-x86-preempt-Check-preemption-level-before-looking-at.patch new file mode 100644 index 000000000..df53f3dd7 --- /dev/null +++ b/debian/patches-rt/0292-x86-preempt-Check-preemption-level-before-looking-at.patch @@ -0,0 +1,34 @@ +From 3a7e827c42b01480e35997bdc722eaaa457840d1 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 14 Aug 2019 17:08:58 +0200 +Subject: [PATCH 292/347] x86: preempt: Check preemption level before looking + at lazy-preempt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 19fc8557f2323c52b26561651ed4d51fc688a740 ] + +Before evaluating the lazy-preempt state it must be ensure that the +preempt-count is zero. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + arch/x86/include/asm/preempt.h | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h +index f66708779274..afa0e42ccdd1 100644 +--- a/arch/x86/include/asm/preempt.h ++++ b/arch/x86/include/asm/preempt.h +@@ -96,6 +96,8 @@ static __always_inline bool __preempt_count_dec_and_test(void) + if (____preempt_count_dec_and_test()) + return true; + #ifdef CONFIG_PREEMPT_LAZY ++ if (preempt_count()) ++ return false; + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +-- +2.36.1 + diff --git a/debian/patches-rt/0293-hrtimer-Use-READ_ONCE-to-access-timer-base-in-hrimer.patch b/debian/patches-rt/0293-hrtimer-Use-READ_ONCE-to-access-timer-base-in-hrimer.patch new file mode 100644 index 000000000..2f06144ba --- /dev/null +++ b/debian/patches-rt/0293-hrtimer-Use-READ_ONCE-to-access-timer-base-in-hrimer.patch @@ -0,0 +1,42 @@ +From 656b33d3842f931f31f5149e458db52b85c4af3e Mon Sep 17 00:00:00 2001 +From: Julien Grall <julien.grall@arm.com> +Date: Wed, 21 Aug 2019 10:24:07 +0100 +Subject: [PATCH 293/347] hrtimer: Use READ_ONCE to access timer->base in + hrimer_grab_expiry_lock() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 2c8fdbe7ef0ad06c1a326886c5954e117b5657d6 ] + +The update to timer->base is protected by the base->cpu_base->lock(). +However, hrtimer_grab_expirty_lock() does not access it with the lock. + +So it would theorically be possible to have timer->base changed under +our feet. We need to prevent the compiler to refetch timer->base so the +check and the access is performed on the same base. + +Other access of timer->base are either done with a lock or protected +with READ_ONCE(). So use READ_ONCE() in hrtimer_grab_expirty_lock(). + +Signed-off-by: Julien Grall <julien.grall@arm.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/time/hrtimer.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index eb2db7e6a241..dff440fd968b 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -959,7 +959,7 @@ EXPORT_SYMBOL_GPL(hrtimer_forward); + + void hrtimer_grab_expiry_lock(const struct hrtimer *timer) + { +- struct hrtimer_clock_base *base = timer->base; ++ struct hrtimer_clock_base *base = READ_ONCE(timer->base); + + if (base && base->cpu_base) { + spin_lock(&base->cpu_base->softirq_expiry_lock); +-- +2.36.1 + diff --git a/debian/patches-rt/0294-hrtimer-Don-t-grab-the-expiry-lock-for-non-soft-hrti.patch b/debian/patches-rt/0294-hrtimer-Don-t-grab-the-expiry-lock-for-non-soft-hrti.patch new file mode 100644 index 000000000..2d81ae91d --- /dev/null +++ b/debian/patches-rt/0294-hrtimer-Don-t-grab-the-expiry-lock-for-non-soft-hrti.patch @@ -0,0 +1,41 @@ +From cec8a994798fd0bebd900d555590ab684d4c7edc Mon Sep 17 00:00:00 2001 +From: Julien Grall <julien.grall@arm.com> +Date: Wed, 21 Aug 2019 10:24:08 +0100 +Subject: [PATCH 294/347] hrtimer: Don't grab the expiry lock for non-soft + hrtimer +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit fd420354bea2f57c11f3de191dffdeea76531e76 ] + +Acquiring the lock in hrtimer_grab_expiry_lock() is designed for +sleeping-locks and should not be used with disabled interrupts. +hrtimer_cancel() may invoke hrtimer_grab_expiry_lock() also for locks +which expire in hard-IRQ context. + +Let hrtimer_cancel() invoke hrtimer_grab_expiry_lock() only for locks +which expire in softirq context. + +Signed-off-by: Julien Grall <julien.grall@arm.com> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: rewrite changelog] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index dff440fd968b..24bfae0e92e2 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -961,7 +961,7 @@ void hrtimer_grab_expiry_lock(const struct hrtimer *timer) + { + struct hrtimer_clock_base *base = READ_ONCE(timer->base); + +- if (base && base->cpu_base) { ++ if (timer->is_soft && base && base->cpu_base) { + spin_lock(&base->cpu_base->softirq_expiry_lock); + spin_unlock(&base->cpu_base->softirq_expiry_lock); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0295-hrtimer-Prevent-using-hrtimer_grab_expiry_lock-on-mi.patch b/debian/patches-rt/0295-hrtimer-Prevent-using-hrtimer_grab_expiry_lock-on-mi.patch new file mode 100644 index 000000000..66133c2af --- /dev/null +++ b/debian/patches-rt/0295-hrtimer-Prevent-using-hrtimer_grab_expiry_lock-on-mi.patch @@ -0,0 +1,43 @@ +From 7e9203de23a787ac491b8114acaf5a8c37f60d36 Mon Sep 17 00:00:00 2001 +From: Julien Grall <julien.grall@arm.com> +Date: Wed, 21 Aug 2019 10:24:09 +0100 +Subject: [PATCH 295/347] hrtimer: Prevent using hrtimer_grab_expiry_lock() on + migration_base +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit cef1b87f98823af923a386f3f69149acb212d4a1 ] + +As tglx puts it: +|If base == migration_base then there is no point to lock soft_expiry_lock +|simply because the timer is not executing the callback in soft irq context +|and the whole lock/unlock dance can be avoided. + +Furthermore, all the path leading to hrtimer_grab_expiry_lock() assumes +timer->base and timer->base->cpu_base are always non-NULL. So it is safe +to remove the NULL checks here. + +Signed-off-by: Julien Grall <julien.grall@arm.com> +Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1908211557420.2223@nanos.tec.linutronix.de +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: rewrite changelog] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 24bfae0e92e2..3f9d156c36f1 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -961,7 +961,7 @@ void hrtimer_grab_expiry_lock(const struct hrtimer *timer) + { + struct hrtimer_clock_base *base = READ_ONCE(timer->base); + +- if (timer->is_soft && base && base->cpu_base) { ++ if (timer->is_soft && base != &migration_base) { + spin_lock(&base->cpu_base->softirq_expiry_lock); + spin_unlock(&base->cpu_base->softirq_expiry_lock); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0296-hrtimer-Add-a-missing-bracket-and-hide-migration_bas.patch b/debian/patches-rt/0296-hrtimer-Add-a-missing-bracket-and-hide-migration_bas.patch new file mode 100644 index 000000000..54806bcb2 --- /dev/null +++ b/debian/patches-rt/0296-hrtimer-Add-a-missing-bracket-and-hide-migration_bas.patch @@ -0,0 +1,75 @@ +From 1f69d8dae481d24ebdbd40717196cc8e36553976 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 4 Sep 2019 16:55:27 +0200 +Subject: [PATCH 296/347] hrtimer: Add a missing bracket and hide + `migration_base' on !SMP +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 47b6de0b7f22c28b40275aeede3993d807668c3b ] + +[ Upstream commit 5d2295f3a93b04986d069ebeaf5b07725f9096c1 ] + +The recent change to avoid taking the expiry lock when a timer is currently +migrated missed to add a bracket at the end of the if statement leading to +compile errors. Since that commit the variable `migration_base' is always +used but it is only available on SMP configuration thus leading to another +compile error. The changelog says "The timer base and base->cpu_base +cannot be NULL in the code path", so it is safe to limit this check to SMP +configurations only. + +Add the missing bracket to the if statement and hide `migration_base' +behind CONFIG_SMP bars. + +[ tglx: Mark the functions inline ... ] + +Fixes: 68b2c8c1e4210 ("hrtimer: Don't take expiry_lock when timer is currently migrated") +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Link: https://lkml.kernel.org/r/20190904145527.eah7z56ntwobqm6j@linutronix.de +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: port back to RT] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/time/hrtimer.c | 12 +++++++++++- + 1 file changed, 11 insertions(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 3f9d156c36f1..0f841f18c363 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -150,6 +150,11 @@ static struct hrtimer_cpu_base migration_cpu_base = { + + #define migration_base migration_cpu_base.clock_base[0] + ++static inline bool is_migration_base(struct hrtimer_clock_base *base) ++{ ++ return base == &migration_base; ++} ++ + /* + * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock + * means that all timers which are tied to this base via timer->base are +@@ -274,6 +279,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, + + #else /* CONFIG_SMP */ + ++static inline bool is_migration_base(struct hrtimer_clock_base *base) ++{ ++ return false; ++} ++ + static inline struct hrtimer_clock_base * + lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) + { +@@ -961,7 +971,7 @@ void hrtimer_grab_expiry_lock(const struct hrtimer *timer) + { + struct hrtimer_clock_base *base = READ_ONCE(timer->base); + +- if (timer->is_soft && base != &migration_base) { ++ if (timer->is_soft && is_migration_base(base)) { + spin_lock(&base->cpu_base->softirq_expiry_lock); + spin_unlock(&base->cpu_base->softirq_expiry_lock); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0297-posix-timers-Unlock-expiry-lock-in-the-early-return.patch b/debian/patches-rt/0297-posix-timers-Unlock-expiry-lock-in-the-early-return.patch new file mode 100644 index 000000000..001c07c9c --- /dev/null +++ b/debian/patches-rt/0297-posix-timers-Unlock-expiry-lock-in-the-early-return.patch @@ -0,0 +1,41 @@ +From 89d528d5fab49f30a5cbd2ef13e19d488a6e21ae Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 16 Sep 2019 12:33:59 +0200 +Subject: [PATCH 297/347] posix-timers: Unlock expiry lock in the early return +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 356a2781375ec58521a9bc3f500488745990c242 ] + +Patch ("posix-timers: Add expiry lock") acquired a lock in +run_posix_cpu_timers() but didn't drop the lock in the early return. + +Unlock the lock in the early return path. + +Reported-by: kbuild test robot <lkp@intel.com> +Reported-by: Dan Carpenter <dan.carpenter@oracle.com> +Reviewed-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/time/posix-cpu-timers.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c +index 54632ed51c65..b9e4ccbb60f3 100644 +--- a/kernel/time/posix-cpu-timers.c ++++ b/kernel/time/posix-cpu-timers.c +@@ -1175,8 +1175,10 @@ static void __run_posix_cpu_timers(struct task_struct *tsk) + expiry_lock = this_cpu_ptr(&cpu_timer_expiry_lock); + spin_lock(expiry_lock); + +- if (!lock_task_sighand(tsk, &flags)) ++ if (!lock_task_sighand(tsk, &flags)) { ++ spin_unlock(expiry_lock); + return; ++ } + /* + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and +-- +2.36.1 + diff --git a/debian/patches-rt/0298-sched-migrate_dis-enable-Use-sleeping_lock-to-annota.patch b/debian/patches-rt/0298-sched-migrate_dis-enable-Use-sleeping_lock-to-annota.patch new file mode 100644 index 000000000..6c1157424 --- /dev/null +++ b/debian/patches-rt/0298-sched-migrate_dis-enable-Use-sleeping_lock-to-annota.patch @@ -0,0 +1,58 @@ +From 813c54ab7d391f197cafdfef09b14958da328122 Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Tue, 24 Sep 2019 14:36:41 +0200 +Subject: [PATCH 298/347] =?UTF-8?q?sched:=20migrate=5Fdis/enable:=20Use=20?= + =?UTF-8?q?sleeping=5Flock=E2=80=A6()=20to=20annotate=20sleeping=20points?= +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 4230dd3824c3e1785504e6f757ce79a4b55651fa ] + +Without this, rcu_note_context_switch() will complain if an RCU read lock +is held when migrate_enable() calls stop_one_cpu(). Likewise when +migrate_disable() calls pin_current_cpu() which calls __read_rt_lock() -- +which bypasses the part of the mutex code that calls sleeping_lock_inc(). + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: use sleeping_lock_…() ] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/cpu.c | 2 ++ + kernel/sched/core.c | 3 +++ + 2 files changed, 5 insertions(+) + +diff --git a/kernel/cpu.c b/kernel/cpu.c +index 11f48774b129..c84a93f84164 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -309,7 +309,9 @@ void pin_current_cpu(void) + preempt_lazy_enable(); + preempt_enable(); + ++ sleeping_lock_inc(); + __read_rt_lock(cpuhp_pin); ++ sleeping_lock_dec(); + + preempt_disable(); + preempt_lazy_disable(); +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 1d4d4780dd79..33c1ae19410e 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7366,7 +7366,10 @@ void migrate_enable(void) + unpin_current_cpu(); + preempt_lazy_enable(); + preempt_enable(); ++ ++ sleeping_lock_inc(); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); ++ sleeping_lock_dec(); + tlb_migrate_finish(p->mm); + + return; +-- +2.36.1 + diff --git a/debian/patches-rt/0299-sched-__set_cpus_allowed_ptr-Check-cpus_mask-not-cpu.patch b/debian/patches-rt/0299-sched-__set_cpus_allowed_ptr-Check-cpus_mask-not-cpu.patch new file mode 100644 index 000000000..693556876 --- /dev/null +++ b/debian/patches-rt/0299-sched-__set_cpus_allowed_ptr-Check-cpus_mask-not-cpu.patch @@ -0,0 +1,39 @@ +From a1f857c1918e1e9cf21358347d4f0bbd0c6da587 Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Sat, 27 Jul 2019 00:56:32 -0500 +Subject: [PATCH 299/347] sched: __set_cpus_allowed_ptr: Check cpus_mask, not + cpus_ptr +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit e5606fb7b042db634ed62b4dd733d62e050e468f ] + +This function is concerned with the long-term cpu mask, not the +transitory mask the task might have while migrate disabled. Before +this patch, if a task was migrate disabled at the time +__set_cpus_allowed_ptr() was called, and the new mask happened to be +equal to the cpu that the task was running on, then the mask update +would be lost. + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 33c1ae19410e..4f5242c9ca78 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1157,7 +1157,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, + goto out; + } + +- if (cpumask_equal(p->cpus_ptr, new_mask)) ++ if (cpumask_equal(&p->cpus_mask, new_mask)) + goto out; + + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); +-- +2.36.1 + diff --git a/debian/patches-rt/0300-sched-Remove-dead-__migrate_disabled-check.patch b/debian/patches-rt/0300-sched-Remove-dead-__migrate_disabled-check.patch new file mode 100644 index 000000000..156d1ac5b --- /dev/null +++ b/debian/patches-rt/0300-sched-Remove-dead-__migrate_disabled-check.patch @@ -0,0 +1,39 @@ +From 5090ad8fa345caac33cc1dbdc60002b7264b8b59 Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Sat, 27 Jul 2019 00:56:33 -0500 +Subject: [PATCH 300/347] sched: Remove dead __migrate_disabled() check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 14d9272d534ea91262e15db99443fc5995c7c016 ] + +This code was unreachable given the __migrate_disabled() branch +to "out" immediately beforehand. + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 7 ------- + 1 file changed, 7 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 4f5242c9ca78..e64d2b2b3a69 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1182,13 +1182,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + +-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +- if (__migrate_disabled(p)) { +- p->migrate_disable_update = 1; +- goto out; +- } +-#endif +- + if (task_running(rq, p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; + /* Need help from migration thread: drop lock and wait. */ +-- +2.36.1 + diff --git a/debian/patches-rt/0301-sched-migrate-disable-Protect-cpus_ptr-with-lock.patch b/debian/patches-rt/0301-sched-migrate-disable-Protect-cpus_ptr-with-lock.patch new file mode 100644 index 000000000..1f1822daf --- /dev/null +++ b/debian/patches-rt/0301-sched-migrate-disable-Protect-cpus_ptr-with-lock.patch @@ -0,0 +1,47 @@ +From c4c6908e112c8368299d23485a921dcc83876ec2 Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Sat, 27 Jul 2019 00:56:34 -0500 +Subject: [PATCH 301/347] sched: migrate disable: Protect cpus_ptr with lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 27ee52a891ed2c7e2e2c8332ccae0de7c2674b09 ] + +Various places assume that cpus_ptr is protected by rq/pi locks, +so don't change it before grabbing those locks. + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index e64d2b2b3a69..6f91ee2b7e91 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7244,9 +7244,8 @@ migrate_disable_update_cpus_allowed(struct task_struct *p) + struct rq *rq; + struct rq_flags rf; + +- p->cpus_ptr = cpumask_of(smp_processor_id()); +- + rq = task_rq_lock(p, &rf); ++ p->cpus_ptr = cpumask_of(smp_processor_id()); + update_nr_migratory(p, -1); + p->nr_cpus_allowed = 1; + task_rq_unlock(rq, p, &rf); +@@ -7258,9 +7257,8 @@ migrate_enable_update_cpus_allowed(struct task_struct *p) + struct rq *rq; + struct rq_flags rf; + +- p->cpus_ptr = &p->cpus_mask; +- + rq = task_rq_lock(p, &rf); ++ p->cpus_ptr = &p->cpus_mask; + p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); + update_nr_migratory(p, 1); + task_rq_unlock(rq, p, &rf); +-- +2.36.1 + diff --git a/debian/patches-rt/0302-lib-smp_processor_id-Don-t-use-cpumask_equal.patch b/debian/patches-rt/0302-lib-smp_processor_id-Don-t-use-cpumask_equal.patch new file mode 100644 index 000000000..ce14d4f68 --- /dev/null +++ b/debian/patches-rt/0302-lib-smp_processor_id-Don-t-use-cpumask_equal.patch @@ -0,0 +1,45 @@ +From 9f39347ad1257ec5ba912513bc7fda854af0bcd0 Mon Sep 17 00:00:00 2001 +From: Waiman Long <longman@redhat.com> +Date: Thu, 3 Oct 2019 16:36:08 -0400 +Subject: [PATCH 302/347] lib/smp_processor_id: Don't use cpumask_equal() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 659252061477862f45b79e1de169e6030f5c8918 ] + +The check_preemption_disabled() function uses cpumask_equal() to see +if the task is bounded to the current CPU only. cpumask_equal() calls +memcmp() to do the comparison. As x86 doesn't have __HAVE_ARCH_MEMCMP, +the slow memcmp() function in lib/string.c is used. + +On a RT kernel that call check_preemption_disabled() very frequently, +below is the perf-record output of a certain microbenchmark: + + 42.75% 2.45% testpmd [kernel.kallsyms] [k] check_preemption_disabled + 40.01% 39.97% testpmd [kernel.kallsyms] [k] memcmp + +We should avoid calling memcmp() in performance critical path. So the +cpumask_equal() call is now replaced with an equivalent simpler check. + +Signed-off-by: Waiman Long <longman@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + lib/smp_processor_id.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c +index fb35c45b9421..b8a8a8db2d75 100644 +--- a/lib/smp_processor_id.c ++++ b/lib/smp_processor_id.c +@@ -22,7 +22,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1, + * Kernel threads bound to a single CPU can safely use + * smp_processor_id(): + */ +- if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu))) ++ if (current->nr_cpus_allowed == 1) + goto out; + + /* +-- +2.36.1 + diff --git a/debian/patches-rt/0303-futex-Make-the-futex_hash_bucket-spinlock_t-again-an.patch b/debian/patches-rt/0303-futex-Make-the-futex_hash_bucket-spinlock_t-again-an.patch new file mode 100644 index 000000000..480218133 --- /dev/null +++ b/debian/patches-rt/0303-futex-Make-the-futex_hash_bucket-spinlock_t-again-an.patch @@ -0,0 +1,735 @@ +From f7a1b76e65c0d79612a6f81b5afc8558b6256242 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 7 Oct 2019 16:45:18 +0200 +Subject: [PATCH 303/347] futex: Make the futex_hash_bucket spinlock_t again + and bring back its old state +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 954ad80c23edfe71f4e8ce70b961eac884320c3a ] + +This is an all-in-one patch that reverts the patches: + futex: Make the futex_hash_bucket lock raw + futex: Delay deallocation of pi_state + +and adds back the old patches we had: + futex: workaround migrate_disable/enable in different context + rtmutex: Handle the various new futex race conditions + futex: Fix bug on when a requeued RT task times out + futex: Ensure lock/unlock symetry versus pi_lock and hash bucket lock + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/futex.c | 228 ++++++++++++++++++-------------- + kernel/locking/rtmutex.c | 65 ++++++++- + kernel/locking/rtmutex_common.h | 3 + + 3 files changed, 193 insertions(+), 103 deletions(-) + +diff --git a/kernel/futex.c b/kernel/futex.c +index 2fc6bedb460e..81090f7a3ed9 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -243,7 +243,7 @@ struct futex_q { + struct plist_node list; + + struct task_struct *task; +- raw_spinlock_t *lock_ptr; ++ spinlock_t *lock_ptr; + union futex_key key; + struct futex_pi_state *pi_state; + struct rt_mutex_waiter *rt_waiter; +@@ -264,7 +264,7 @@ static const struct futex_q futex_q_init = { + */ + struct futex_hash_bucket { + atomic_t waiters; +- raw_spinlock_t lock; ++ spinlock_t lock; + struct plist_head chain; + } ____cacheline_aligned_in_smp; + +@@ -871,13 +871,13 @@ static void get_pi_state(struct futex_pi_state *pi_state) + * Drops a reference to the pi_state object and frees or caches it + * when the last reference is gone. + */ +-static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state) ++static void put_pi_state(struct futex_pi_state *pi_state) + { + if (!pi_state) +- return NULL; ++ return; + + if (!atomic_dec_and_test(&pi_state->refcount)) +- return NULL; ++ return; + + /* + * If pi_state->owner is NULL, the owner is most probably dying +@@ -892,7 +892,9 @@ static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state) + raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); + } + +- if (!current->pi_state_cache) { ++ if (current->pi_state_cache) { ++ kfree(pi_state); ++ } else { + /* + * pi_state->list is already empty. + * clear pi_state->owner. +@@ -901,30 +903,6 @@ static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state) + pi_state->owner = NULL; + atomic_set(&pi_state->refcount, 1); + current->pi_state_cache = pi_state; +- pi_state = NULL; +- } +- return pi_state; +-} +- +-static void put_pi_state(struct futex_pi_state *pi_state) +-{ +- kfree(__put_pi_state(pi_state)); +-} +- +-static void put_pi_state_atomic(struct futex_pi_state *pi_state, +- struct list_head *to_free) +-{ +- if (__put_pi_state(pi_state)) +- list_add(&pi_state->list, to_free); +-} +- +-static void free_pi_state_list(struct list_head *to_free) +-{ +- struct futex_pi_state *p, *next; +- +- list_for_each_entry_safe(p, next, to_free, list) { +- list_del(&p->list); +- kfree(p); + } + } + +@@ -941,7 +919,6 @@ static void exit_pi_state_list(struct task_struct *curr) + struct futex_pi_state *pi_state; + struct futex_hash_bucket *hb; + union futex_key key = FUTEX_KEY_INIT; +- LIST_HEAD(to_free); + + if (!futex_cmpxchg_enabled) + return; +@@ -975,7 +952,7 @@ static void exit_pi_state_list(struct task_struct *curr) + } + raw_spin_unlock_irq(&curr->pi_lock); + +- raw_spin_lock(&hb->lock); ++ spin_lock(&hb->lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); + /* +@@ -985,8 +962,10 @@ static void exit_pi_state_list(struct task_struct *curr) + if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); +- raw_spin_unlock(&hb->lock); +- put_pi_state_atomic(pi_state, &to_free); ++ raw_spin_unlock_irq(&curr->pi_lock); ++ spin_unlock(&hb->lock); ++ raw_spin_lock_irq(&curr->pi_lock); ++ put_pi_state(pi_state); + continue; + } + +@@ -997,7 +976,7 @@ static void exit_pi_state_list(struct task_struct *curr) + + raw_spin_unlock(&curr->pi_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); +- raw_spin_unlock(&hb->lock); ++ spin_unlock(&hb->lock); + + rt_mutex_futex_unlock(&pi_state->pi_mutex); + put_pi_state(pi_state); +@@ -1005,8 +984,6 @@ static void exit_pi_state_list(struct task_struct *curr) + raw_spin_lock_irq(&curr->pi_lock); + } + raw_spin_unlock_irq(&curr->pi_lock); +- +- free_pi_state_list(&to_free); + } + #else + static inline void exit_pi_state_list(struct task_struct *curr) { } +@@ -1548,7 +1525,7 @@ static void __unqueue_futex(struct futex_q *q) + { + struct futex_hash_bucket *hb; + +- if (WARN_ON_SMP(!q->lock_ptr || !raw_spin_is_locked(q->lock_ptr)) ++ if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr)) + || WARN_ON(plist_node_empty(&q->list))) + return; + +@@ -1668,21 +1645,21 @@ static inline void + double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) + { + if (hb1 <= hb2) { +- raw_spin_lock(&hb1->lock); ++ spin_lock(&hb1->lock); + if (hb1 < hb2) +- raw_spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); ++ spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); + } else { /* hb1 > hb2 */ +- raw_spin_lock(&hb2->lock); +- raw_spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING); ++ spin_lock(&hb2->lock); ++ spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING); + } + } + + static inline void + double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) + { +- raw_spin_unlock(&hb1->lock); ++ spin_unlock(&hb1->lock); + if (hb1 != hb2) +- raw_spin_unlock(&hb2->lock); ++ spin_unlock(&hb2->lock); + } + + /* +@@ -1710,7 +1687,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) + if (!hb_waiters_pending(hb)) + goto out_put_key; + +- raw_spin_lock(&hb->lock); ++ spin_lock(&hb->lock); + + plist_for_each_entry_safe(this, next, &hb->chain, list) { + if (match_futex (&this->key, &key)) { +@@ -1729,7 +1706,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) + } + } + +- raw_spin_unlock(&hb->lock); ++ spin_unlock(&hb->lock); + wake_up_q(&wake_q); + out_put_key: + put_futex_key(&key); +@@ -2042,7 +2019,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; + DEFINE_WAKE_Q(wake_q); +- LIST_HEAD(to_free); + + if (nr_wake < 0 || nr_requeue < 0) + return -EINVAL; +@@ -2281,6 +2257,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; ++ } else if (ret == -EAGAIN) { ++ /* ++ * Waiter was woken by timeout or ++ * signal and has set pi_blocked_on to ++ * PI_WAKEUP_INPROGRESS before we ++ * tried to enqueue it on the rtmutex. ++ */ ++ this->pi_state = NULL; ++ put_pi_state(pi_state); ++ continue; + } else if (ret) { + /* + * rt_mutex_start_proxy_lock() detected a +@@ -2291,7 +2277,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + * object. + */ + this->pi_state = NULL; +- put_pi_state_atomic(pi_state, &to_free); ++ put_pi_state(pi_state); + /* + * We stop queueing more waiters and let user + * space deal with the mess. +@@ -2308,7 +2294,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We + * need to drop it here again. + */ +- put_pi_state_atomic(pi_state, &to_free); ++ put_pi_state(pi_state); + + out_unlock: + double_unlock_hb(hb1, hb2); +@@ -2329,7 +2315,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, + out_put_key1: + put_futex_key(&key1); + out: +- free_pi_state_list(&to_free); + return ret ? ret : task_count; + } + +@@ -2353,7 +2338,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) + + q->lock_ptr = &hb->lock; + +- raw_spin_lock(&hb->lock); /* implies smp_mb(); (A) */ ++ spin_lock(&hb->lock); /* implies smp_mb(); (A) */ + return hb; + } + +@@ -2361,7 +2346,7 @@ static inline void + queue_unlock(struct futex_hash_bucket *hb) + __releases(&hb->lock) + { +- raw_spin_unlock(&hb->lock); ++ spin_unlock(&hb->lock); + hb_waiters_dec(hb); + } + +@@ -2400,7 +2385,7 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) + __releases(&hb->lock) + { + __queue_me(q, hb); +- raw_spin_unlock(&hb->lock); ++ spin_unlock(&hb->lock); + } + + /** +@@ -2416,41 +2401,41 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) + */ + static int unqueue_me(struct futex_q *q) + { +- raw_spinlock_t *lock_ptr; ++ spinlock_t *lock_ptr; + int ret = 0; + + /* In the common case we don't take the spinlock, which is nice. */ + retry: + /* +- * q->lock_ptr can change between this read and the following +- * raw_spin_lock. Use READ_ONCE to forbid the compiler from reloading +- * q->lock_ptr and optimizing lock_ptr out of the logic below. ++ * q->lock_ptr can change between this read and the following spin_lock. ++ * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and ++ * optimizing lock_ptr out of the logic below. + */ + lock_ptr = READ_ONCE(q->lock_ptr); + if (lock_ptr != NULL) { +- raw_spin_lock(lock_ptr); ++ spin_lock(lock_ptr); + /* + * q->lock_ptr can change between reading it and +- * raw_spin_lock(), causing us to take the wrong lock. This ++ * spin_lock(), causing us to take the wrong lock. This + * corrects the race condition. + * + * Reasoning goes like this: if we have the wrong lock, + * q->lock_ptr must have changed (maybe several times) +- * between reading it and the raw_spin_lock(). It can +- * change again after the raw_spin_lock() but only if it was +- * already changed before the raw_spin_lock(). It cannot, ++ * between reading it and the spin_lock(). It can ++ * change again after the spin_lock() but only if it was ++ * already changed before the spin_lock(). It cannot, + * however, change back to the original value. Therefore + * we can detect whether we acquired the correct lock. + */ + if (unlikely(lock_ptr != q->lock_ptr)) { +- raw_spin_unlock(lock_ptr); ++ spin_unlock(lock_ptr); + goto retry; + } + __unqueue_futex(q); + + BUG_ON(q->pi_state); + +- raw_spin_unlock(lock_ptr); ++ spin_unlock(lock_ptr); + ret = 1; + } + +@@ -2466,16 +2451,13 @@ static int unqueue_me(struct futex_q *q) + static void unqueue_me_pi(struct futex_q *q) + __releases(q->lock_ptr) + { +- struct futex_pi_state *ps; +- + __unqueue_futex(q); + + BUG_ON(!q->pi_state); +- ps = __put_pi_state(q->pi_state); ++ put_pi_state(q->pi_state); + q->pi_state = NULL; + +- raw_spin_unlock(q->lock_ptr); +- kfree(ps); ++ spin_unlock(q->lock_ptr); + } + + static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, +@@ -2599,7 +2581,7 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + */ + handle_err: + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); +- raw_spin_unlock(q->lock_ptr); ++ spin_unlock(q->lock_ptr); + + switch (err) { + case -EFAULT: +@@ -2616,7 +2598,7 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + break; + } + +- raw_spin_lock(q->lock_ptr); ++ spin_lock(q->lock_ptr); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + + /* +@@ -2730,7 +2712,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, + /* + * The task state is guaranteed to be set before another task can + * wake it. set_current_state() is implemented using smp_store_mb() and +- * queue_me() calls raw_spin_unlock() upon completion, both serializing ++ * queue_me() calls spin_unlock() upon completion, both serializing + * access to the hash list and forcing another memory barrier. + */ + set_current_state(TASK_INTERRUPTIBLE); +@@ -3028,7 +3010,15 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + * before __rt_mutex_start_proxy_lock() is done. + */ + raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); +- raw_spin_unlock(q.lock_ptr); ++ /* ++ * the migrate_disable() here disables migration in the in_atomic() fast ++ * path which is enabled again in the following spin_unlock(). We have ++ * one migrate_disable() pending in the slow-path which is reversed ++ * after the raw_spin_unlock_irq() where we leave the atomic context. ++ */ ++ migrate_disable(); ++ ++ spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when +@@ -3036,6 +3026,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + */ + ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); + raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); ++ migrate_enable(); + + if (ret) { + if (ret == 1) +@@ -3049,7 +3040,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, + ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); + + cleanup: +- raw_spin_lock(q.lock_ptr); ++ spin_lock(q.lock_ptr); + /* + * If we failed to acquire the lock (deadlock/signal/timeout), we must + * first acquire the hb->lock before removing the lock from the +@@ -3136,7 +3127,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + return ret; + + hb = hash_futex(&key); +- raw_spin_lock(&hb->lock); ++ spin_lock(&hb->lock); + + /* + * Check waiters first. We do not trust user space values at +@@ -3170,10 +3161,19 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + * rt_waiter. Also see the WARN in wake_futex_pi(). + */ + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); +- raw_spin_unlock(&hb->lock); ++ /* ++ * Magic trickery for now to make the RT migrate disable ++ * logic happy. The following spin_unlock() happens with ++ * interrupts disabled so the internal migrate_enable() ++ * won't undo the migrate_disable() which was issued when ++ * locking hb->lock. ++ */ ++ migrate_disable(); ++ spin_unlock(&hb->lock); + + /* drops pi_state->pi_mutex.wait_lock */ + ret = wake_futex_pi(uaddr, uval, pi_state); ++ migrate_enable(); + + put_pi_state(pi_state); + +@@ -3209,7 +3209,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + * owner. + */ + if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) { +- raw_spin_unlock(&hb->lock); ++ spin_unlock(&hb->lock); + switch (ret) { + case -EFAULT: + goto pi_faulted; +@@ -3229,7 +3229,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) + ret = (curval == uval) ? 0 : -EAGAIN; + + out_unlock: +- raw_spin_unlock(&hb->lock); ++ spin_unlock(&hb->lock); + out_putkey: + put_futex_key(&key); + return ret; +@@ -3344,7 +3344,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + { + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; +- struct futex_hash_bucket *hb; ++ struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -3402,20 +3402,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- raw_spin_lock(&hb->lock); +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- raw_spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; ++ /* ++ * On RT we must avoid races with requeue and trying to block ++ * on two mutexes (hb->lock and uaddr2's rtmutex) by ++ * serializing access to pi_blocked_on with pi_lock. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ if (current->pi_blocked_on) { ++ /* ++ * We have been requeued or are in the process of ++ * being requeued. ++ */ ++ raw_spin_unlock_irq(¤t->pi_lock); ++ } else { ++ /* ++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS ++ * prevents a concurrent requeue from moving us to the ++ * uaddr2 rtmutex. After that we can safely acquire ++ * (and possibly block on) hb->lock. ++ */ ++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ spin_lock(&hb->lock); ++ ++ /* ++ * Clean up pi_blocked_on. We might leak it otherwise ++ * when we succeeded with the hb->lock in the fast ++ * path. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ current->pi_blocked_on = NULL; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; ++ } + + /* +- * In order for us to be here, we know our q.key == key2, and since +- * we took the hb->lock above, we also know that futex_requeue() has +- * completed and we no longer have to concern ourselves with a wakeup +- * race with the atomic proxy lock acquisition by the requeue code. The +- * futex_requeue dropped our key1 reference and incremented our key2 +- * reference count. ++ * In order to be here, we have either been requeued, are in ++ * the process of being requeued, or requeue successfully ++ * acquired uaddr2 on our behalf. If pi_blocked_on was ++ * non-null above, we may be racing with a requeue. Do not ++ * rely on q->lock_ptr to be hb2->lock until after blocking on ++ * hb->lock or hb2->lock. The futex_requeue dropped our key1 ++ * reference and incremented our key2 reference count. + */ ++ hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -3424,17 +3459,15 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- struct futex_pi_state *ps_free; +- +- raw_spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ +- ps_free = __put_pi_state(q.pi_state); ++ put_pi_state(q.pi_state); + spin_unlock(&hb2->lock); +- kfree(ps_free); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. +@@ -3453,7 +3486,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + pi_mutex = &q.pi_state->pi_mutex; + ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); + +- raw_spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) + ret = 0; + +@@ -4212,7 +4246,7 @@ static int __init futex_init(void) + for (i = 0; i < futex_hashsize; i++) { + atomic_set(&futex_queues[i].waiters, 0); + plist_head_init(&futex_queues[i].chain); +- raw_spin_lock_init(&futex_queues[i].lock); ++ spin_lock_init(&futex_queues[i].lock); + } + + return 0; +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 05fcf8a75a51..ded2296f848a 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -142,6 +142,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } + ++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) ++{ ++ return waiter && waiter != PI_WAKEUP_INPROGRESS && ++ waiter != PI_REQUEUE_INPROGRESS; ++} ++ + /* + * We can speed up the acquire/release, if there's no debugging state to be + * set up. +@@ -415,7 +421,8 @@ int max_lock_depth = 1024; + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; ++ return rt_mutex_real_waiter(p->pi_blocked_on) ? ++ p->pi_blocked_on->lock : NULL; + } + + /* +@@ -551,7 +558,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!waiter) ++ if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* +@@ -1321,6 +1328,22 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + return -EDEADLK; + + raw_spin_lock(&task->pi_lock); ++ /* ++ * In the case of futex requeue PI, this will be a proxy ++ * lock. The task will wake unaware that it is enqueueed on ++ * this lock. Avoid blocking on two locks and corrupting ++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS ++ * flag. futex_wait_requeue_pi() sets this when it wakes up ++ * before requeue (due to a signal or timeout). Do not enqueue ++ * the task if PI_WAKEUP_INPROGRESS is set. ++ */ ++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ ++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); ++ + waiter->task = task; + waiter->lock = lock; + waiter->prio = task->prio; +@@ -1344,7 +1367,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + rt_mutex_enqueue_pi(owner, waiter); + + rt_mutex_adjust_prio(owner); +- if (owner->pi_blocked_on) ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -1444,7 +1467,7 @@ static void remove_waiter(struct rt_mutex *lock, + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock; ++ struct rt_mutex *next_lock = NULL; + + lockdep_assert_held(&lock->wait_lock); + +@@ -1470,7 +1493,8 @@ static void remove_waiter(struct rt_mutex *lock, + rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- next_lock = task_blocked_on_lock(owner); ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock(&owner->pi_lock); + +@@ -1506,7 +1530,8 @@ void rt_mutex_adjust_pi(struct task_struct *task) + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { ++ if (!rt_mutex_real_waiter(waiter) || ++ rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } +@@ -2324,6 +2349,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + if (try_to_take_rt_mutex(lock, task, NULL)) + return 1; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * In PREEMPT_RT there's an added race. ++ * If the task, that we are about to requeue, times out, ++ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue ++ * to skip this task. But right after the task sets ++ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then ++ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. ++ * This will replace the PI_WAKEUP_INPROGRESS with the actual ++ * lock that it blocks on. We *must not* place this task ++ * on this proxy lock in that case. ++ * ++ * To prevent this race, we first take the task's pi_lock ++ * and check if it has updated its pi_blocked_on. If it has, ++ * we assume that it woke up and we return -EAGAIN. ++ * Otherwise, we set the task's pi_blocked_on to ++ * PI_REQUEUE_INPROGRESS, so that if the task is waking up ++ * it will know that we are in the process of requeuing it. ++ */ ++ raw_spin_lock(&task->pi_lock); ++ if (task->pi_blocked_on) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; ++ raw_spin_unlock(&task->pi_lock); ++#endif ++ + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); +diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h +index f587e0422d23..8e0c592273e6 100644 +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -132,6 +132,9 @@ enum rtmutex_chainwalk { + /* + * PI-futex support (proxy locking functions, etc.): + */ ++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) ++ + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); +-- +2.36.1 + diff --git a/debian/patches-rt/0304-locking-rtmutex-Clean-pi_blocked_on-in-the-error-cas.patch b/debian/patches-rt/0304-locking-rtmutex-Clean-pi_blocked_on-in-the-error-cas.patch new file mode 100644 index 000000000..86fb4bb50 --- /dev/null +++ b/debian/patches-rt/0304-locking-rtmutex-Clean-pi_blocked_on-in-the-error-cas.patch @@ -0,0 +1,102 @@ +From 91bba7aa7f53d991fab4b00ba2bb333dc25dd2ee Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Mon, 30 Sep 2019 18:15:44 +0200 +Subject: [PATCH 304/347] locking/rtmutex: Clean ->pi_blocked_on in the error + case +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 0be4ea6e3ce693101be0fbd55a0cc7ce238ab2eb ] + +The function rt_mutex_wait_proxy_lock() cleans ->pi_blocked_on in case +of failure (timeout, signal). The same cleanup is required in +__rt_mutex_start_proxy_lock(). +In both the cases the tasks was interrupted by a signal or timeout while +acquiring the lock and after the interruption it longer blocks on the +lock. + +Fixes: 1a1fb985f2e2b ("futex: Handle early deadlock return correctly") +Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/locking/rtmutex.c | 43 +++++++++++++++++++++++----------------- + 1 file changed, 25 insertions(+), 18 deletions(-) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index ded2296f848a..dc95a81ae3a6 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -2319,6 +2319,26 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock) + rt_mutex_set_owner(lock, NULL); + } + ++static void fixup_rt_mutex_blocked(struct rt_mutex *lock) ++{ ++ struct task_struct *tsk = current; ++ /* ++ * RT has a problem here when the wait got interrupted by a timeout ++ * or a signal. task->pi_blocked_on is still set. The task must ++ * acquire the hash bucket lock when returning from this function. ++ * ++ * If the hash bucket lock is contended then the ++ * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in ++ * task_blocks_on_rt_mutex() will trigger. This can be avoided by ++ * clearing task->pi_blocked_on which removes the task from the ++ * boosting chain of the rtmutex. That's correct because the task ++ * is not longer blocked on it. ++ */ ++ raw_spin_lock(&tsk->pi_lock); ++ tsk->pi_blocked_on = NULL; ++ raw_spin_unlock(&tsk->pi_lock); ++} ++ + /** + * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take +@@ -2391,6 +2411,9 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + ret = 0; + } + ++ if (ret) ++ fixup_rt_mutex_blocked(lock); ++ + debug_rt_mutex_print_deadlock(waiter); + + return ret; +@@ -2471,7 +2494,6 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter) + { +- struct task_struct *tsk = current; + int ret; + + raw_spin_lock_irq(&lock->wait_lock); +@@ -2483,23 +2505,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); +- /* +- * RT has a problem here when the wait got interrupted by a timeout +- * or a signal. task->pi_blocked_on is still set. The task must +- * acquire the hash bucket lock when returning from this function. +- * +- * If the hash bucket lock is contended then the +- * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in +- * task_blocks_on_rt_mutex() will trigger. This can be avoided by +- * clearing task->pi_blocked_on which removes the task from the +- * boosting chain of the rtmutex. That's correct because the task +- * is not longer blocked on it. +- */ +- if (ret) { +- raw_spin_lock(&tsk->pi_lock); +- tsk->pi_blocked_on = NULL; +- raw_spin_unlock(&tsk->pi_lock); +- } ++ if (ret) ++ fixup_rt_mutex_blocked(lock); + + raw_spin_unlock_irq(&lock->wait_lock); + +-- +2.36.1 + diff --git a/debian/patches-rt/0305-lib-ubsan-Don-t-seralize-UBSAN-report.patch b/debian/patches-rt/0305-lib-ubsan-Don-t-seralize-UBSAN-report.patch new file mode 100644 index 000000000..0d8dba5e3 --- /dev/null +++ b/debian/patches-rt/0305-lib-ubsan-Don-t-seralize-UBSAN-report.patch @@ -0,0 +1,308 @@ +From 7310d776df7bc46b442c51d6b723b77ef6614830 Mon Sep 17 00:00:00 2001 +From: Julien Grall <julien.grall@arm.com> +Date: Fri, 20 Sep 2019 11:08:35 +0100 +Subject: [PATCH 305/347] lib/ubsan: Don't seralize UBSAN report +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 4702c28ac777b27acb499cbd5e8e787ce1a7d82d ] + +At the moment, UBSAN report will be serialized using a spin_lock(). On +RT-systems, spinlocks are turned to rt_spin_lock and may sleep. This will +result to the following splat if the undefined behavior is in a context +that can sleep: + +| BUG: sleeping function called from invalid context at /src/linux/kernel/locking/rtmutex.c:968 +| in_atomic(): 1, irqs_disabled(): 128, pid: 3447, name: make +| 1 lock held by make/3447: +| #0: 000000009a966332 (&mm->mmap_sem){++++}, at: do_page_fault+0x140/0x4f8 +| Preemption disabled at: +| [<ffff000011324a4c>] rt_mutex_futex_unlock+0x4c/0xb0 +| CPU: 3 PID: 3447 Comm: make Tainted: G W 5.2.14-rt7-01890-ge6e057589653 #911 +| Call trace: +| dump_backtrace+0x0/0x148 +| show_stack+0x14/0x20 +| dump_stack+0xbc/0x104 +| ___might_sleep+0x154/0x210 +| rt_spin_lock+0x68/0xa0 +| ubsan_prologue+0x30/0x68 +| handle_overflow+0x64/0xe0 +| __ubsan_handle_add_overflow+0x10/0x18 +| __lock_acquire+0x1c28/0x2a28 +| lock_acquire+0xf0/0x370 +| _raw_spin_lock_irqsave+0x58/0x78 +| rt_mutex_futex_unlock+0x4c/0xb0 +| rt_spin_unlock+0x28/0x70 +| get_page_from_freelist+0x428/0x2b60 +| __alloc_pages_nodemask+0x174/0x1708 +| alloc_pages_vma+0x1ac/0x238 +| __handle_mm_fault+0x4ac/0x10b0 +| handle_mm_fault+0x1d8/0x3b0 +| do_page_fault+0x1c8/0x4f8 +| do_translation_fault+0xb8/0xe0 +| do_mem_abort+0x3c/0x98 +| el0_da+0x20/0x24 + +The spin_lock() will protect against multiple CPUs to output a report +together, I guess to prevent them to be interleaved. However, they can +still interleave with other messages (and even splat from __migth_sleep). + +So the lock usefulness seems pretty limited. Rather than trying to +accomodate RT-system by switching to a raw_spin_lock(), the lock is now +completely dropped. + +Link: https://lkml.kernel.org/r/20190920100835.14999-1-julien.grall@arm.com +Reported-by: Andre Przywara <andre.przywara@arm.com> +Signed-off-by: Julien Grall <julien.grall@arm.com> +Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + lib/ubsan.c | 64 +++++++++++++++++++---------------------------------- + 1 file changed, 23 insertions(+), 41 deletions(-) + +diff --git a/lib/ubsan.c b/lib/ubsan.c +index 1e9e2ab25539..5830cc9a2164 100644 +--- a/lib/ubsan.c ++++ b/lib/ubsan.c +@@ -143,25 +143,21 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type, + } + } + +-static DEFINE_SPINLOCK(report_lock); +- +-static void ubsan_prologue(struct source_location *location, +- unsigned long *flags) ++static void ubsan_prologue(struct source_location *location) + { + current->in_ubsan++; +- spin_lock_irqsave(&report_lock, *flags); + + pr_err("========================================" + "========================================\n"); + print_source_location("UBSAN: Undefined behaviour in", location); + } + +-static void ubsan_epilogue(unsigned long *flags) ++static void ubsan_epilogue(void) + { + dump_stack(); + pr_err("========================================" + "========================================\n"); +- spin_unlock_irqrestore(&report_lock, *flags); ++ + current->in_ubsan--; + } + +@@ -170,14 +166,13 @@ static void handle_overflow(struct overflow_data *data, void *lhs, + { + + struct type_descriptor *type = data->type; +- unsigned long flags; + char lhs_val_str[VALUE_LENGTH]; + char rhs_val_str[VALUE_LENGTH]; + + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs); + val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs); +@@ -189,7 +184,7 @@ static void handle_overflow(struct overflow_data *data, void *lhs, + rhs_val_str, + type->type_name); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + + void __ubsan_handle_add_overflow(struct overflow_data *data, +@@ -217,20 +212,19 @@ EXPORT_SYMBOL(__ubsan_handle_mul_overflow); + void __ubsan_handle_negate_overflow(struct overflow_data *data, + void *old_val) + { +- unsigned long flags; + char old_val_str[VALUE_LENGTH]; + + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val); + + pr_err("negation of %s cannot be represented in type %s:\n", + old_val_str, data->type->type_name); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + EXPORT_SYMBOL(__ubsan_handle_negate_overflow); + +@@ -238,13 +232,12 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow); + void __ubsan_handle_divrem_overflow(struct overflow_data *data, + void *lhs, void *rhs) + { +- unsigned long flags; + char rhs_val_str[VALUE_LENGTH]; + + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs); + +@@ -254,58 +247,52 @@ void __ubsan_handle_divrem_overflow(struct overflow_data *data, + else + pr_err("division by zero\n"); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + EXPORT_SYMBOL(__ubsan_handle_divrem_overflow); + + static void handle_null_ptr_deref(struct type_mismatch_data_common *data) + { +- unsigned long flags; +- + if (suppress_report(data->location)) + return; + +- ubsan_prologue(data->location, &flags); ++ ubsan_prologue(data->location); + + pr_err("%s null pointer of type %s\n", + type_check_kinds[data->type_check_kind], + data->type->type_name); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + + static void handle_misaligned_access(struct type_mismatch_data_common *data, + unsigned long ptr) + { +- unsigned long flags; +- + if (suppress_report(data->location)) + return; + +- ubsan_prologue(data->location, &flags); ++ ubsan_prologue(data->location); + + pr_err("%s misaligned address %p for type %s\n", + type_check_kinds[data->type_check_kind], + (void *)ptr, data->type->type_name); + pr_err("which requires %ld byte alignment\n", data->alignment); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + + static void handle_object_size_mismatch(struct type_mismatch_data_common *data, + unsigned long ptr) + { +- unsigned long flags; +- + if (suppress_report(data->location)) + return; + +- ubsan_prologue(data->location, &flags); ++ ubsan_prologue(data->location); + pr_err("%s address %p with insufficient space\n", + type_check_kinds[data->type_check_kind], + (void *) ptr); + pr_err("for an object of type %s\n", data->type->type_name); +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + + static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data, +@@ -369,25 +356,23 @@ EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive); + + void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index) + { +- unsigned long flags; + char index_str[VALUE_LENGTH]; + + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(index_str, sizeof(index_str), data->index_type, index); + pr_err("index %s is out of range for type %s\n", index_str, + data->array_type->type_name); +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + EXPORT_SYMBOL(__ubsan_handle_out_of_bounds); + + void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, + void *lhs, void *rhs) + { +- unsigned long flags; + struct type_descriptor *rhs_type = data->rhs_type; + struct type_descriptor *lhs_type = data->lhs_type; + char rhs_str[VALUE_LENGTH]; +@@ -396,7 +381,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(rhs_str, sizeof(rhs_str), rhs_type, rhs); + val_to_string(lhs_str, sizeof(lhs_str), lhs_type, lhs); +@@ -419,18 +404,16 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, + lhs_str, rhs_str, + lhs_type->type_name); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds); + + + void __ubsan_handle_builtin_unreachable(struct unreachable_data *data) + { +- unsigned long flags; +- +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + pr_err("calling __builtin_unreachable()\n"); +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + panic("can't return from __builtin_unreachable()"); + } + EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable); +@@ -438,19 +421,18 @@ EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable); + void __ubsan_handle_load_invalid_value(struct invalid_value_data *data, + void *val) + { +- unsigned long flags; + char val_str[VALUE_LENGTH]; + + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(val_str, sizeof(val_str), data->type, val); + + pr_err("load of value %s is not a valid value for type %s\n", + val_str, data->type->type_name); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + EXPORT_SYMBOL(__ubsan_handle_load_invalid_value); +-- +2.36.1 + diff --git a/debian/patches-rt/0306-kmemleak-Change-the-lock-of-kmemleak_object-to-raw_s.patch b/debian/patches-rt/0306-kmemleak-Change-the-lock-of-kmemleak_object-to-raw_s.patch new file mode 100644 index 000000000..ca08e2aca --- /dev/null +++ b/debian/patches-rt/0306-kmemleak-Change-the-lock-of-kmemleak_object-to-raw_s.patch @@ -0,0 +1,293 @@ +From 3d72712c05917c06303670565d51a308334595d6 Mon Sep 17 00:00:00 2001 +From: Liu Haitao <haitao.liu@windriver.com> +Date: Fri, 27 Sep 2019 16:22:30 +0800 +Subject: [PATCH 306/347] kmemleak: Change the lock of kmemleak_object to + raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 217847f57119b5fdd377bfa3d344613ddb98d9fc ] + +The commit ("kmemleak: Turn kmemleak_lock to raw spinlock on RT") +changed the kmemleak_lock to raw spinlock. However the +kmemleak_object->lock is held after the kmemleak_lock is held in +scan_block(). + +Make the object->lock a raw_spinlock_t. + +Cc: stable-rt@vger.kernel.org +Link: https://lkml.kernel.org/r/20190927082230.34152-1-yongxin.liu@windriver.com +Signed-off-by: Liu Haitao <haitao.liu@windriver.com> +Signed-off-by: Yongxin Liu <yongxin.liu@windriver.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + mm/kmemleak.c | 72 +++++++++++++++++++++++++-------------------------- + 1 file changed, 36 insertions(+), 36 deletions(-) + +diff --git a/mm/kmemleak.c b/mm/kmemleak.c +index 5b6718dd3a64..23e2837501d6 100644 +--- a/mm/kmemleak.c ++++ b/mm/kmemleak.c +@@ -147,7 +147,7 @@ struct kmemleak_scan_area { + * (use_count) and freed using the RCU mechanism. + */ + struct kmemleak_object { +- spinlock_t lock; ++ raw_spinlock_t lock; + unsigned int flags; /* object status flags */ + struct list_head object_list; + struct list_head gray_list; +@@ -561,7 +561,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, + INIT_LIST_HEAD(&object->object_list); + INIT_LIST_HEAD(&object->gray_list); + INIT_HLIST_HEAD(&object->area_list); +- spin_lock_init(&object->lock); ++ raw_spin_lock_init(&object->lock); + atomic_set(&object->use_count, 1); + object->flags = OBJECT_ALLOCATED; + object->pointer = ptr; +@@ -642,9 +642,9 @@ static void __delete_object(struct kmemleak_object *object) + * Locking here also ensures that the corresponding memory block + * cannot be freed when it is being scanned. + */ +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + object->flags &= ~OBJECT_ALLOCATED; +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); + } + +@@ -716,9 +716,9 @@ static void paint_it(struct kmemleak_object *object, int color) + { + unsigned long flags; + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + __paint_it(object, color); +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + } + + static void paint_ptr(unsigned long ptr, int color) +@@ -778,7 +778,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) + goto out; + } + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + if (size == SIZE_MAX) { + size = object->pointer + object->size - ptr; + } else if (ptr + size > object->pointer + object->size) { +@@ -794,7 +794,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) + + hlist_add_head(&area->node, &object->area_list); + out_unlock: +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + out: + put_object(object); + } +@@ -817,9 +817,9 @@ static void object_set_excess_ref(unsigned long ptr, unsigned long excess_ref) + return; + } + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + object->excess_ref = excess_ref; +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); + } + +@@ -839,9 +839,9 @@ static void object_no_scan(unsigned long ptr) + return; + } + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + object->flags |= OBJECT_NO_SCAN; +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); + } + +@@ -902,11 +902,11 @@ static void early_alloc(struct early_log *log) + log->min_count, GFP_ATOMIC); + if (!object) + goto out; +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + for (i = 0; i < log->trace_len; i++) + object->trace[i] = log->trace[i]; + object->trace_len = log->trace_len; +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + out: + rcu_read_unlock(); + } +@@ -1096,9 +1096,9 @@ void __ref kmemleak_update_trace(const void *ptr) + return; + } + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + object->trace_len = __save_stack_trace(object->trace); +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); + } +@@ -1344,7 +1344,7 @@ static void scan_block(void *_start, void *_end, + * previously acquired in scan_object(). These locks are + * enclosed by scan_mutex. + */ +- spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); ++ raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); + /* only pass surplus references (object already gray) */ + if (color_gray(object)) { + excess_ref = object->excess_ref; +@@ -1353,7 +1353,7 @@ static void scan_block(void *_start, void *_end, + excess_ref = 0; + update_refs(object); + } +- spin_unlock(&object->lock); ++ raw_spin_unlock(&object->lock); + + if (excess_ref) { + object = lookup_object(excess_ref, 0); +@@ -1362,9 +1362,9 @@ static void scan_block(void *_start, void *_end, + if (object == scanned) + /* circular reference, ignore */ + continue; +- spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); ++ raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING); + update_refs(object); +- spin_unlock(&object->lock); ++ raw_spin_unlock(&object->lock); + } + } + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); +@@ -1400,7 +1400,7 @@ static void scan_object(struct kmemleak_object *object) + * Once the object->lock is acquired, the corresponding memory block + * cannot be freed (the same lock is acquired in delete_object). + */ +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + if (object->flags & OBJECT_NO_SCAN) + goto out; + if (!(object->flags & OBJECT_ALLOCATED)) +@@ -1419,9 +1419,9 @@ static void scan_object(struct kmemleak_object *object) + if (start >= end) + break; + +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + cond_resched(); +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + } while (object->flags & OBJECT_ALLOCATED); + } else + hlist_for_each_entry(area, &object->area_list, node) +@@ -1429,7 +1429,7 @@ static void scan_object(struct kmemleak_object *object) + (void *)(area->start + area->size), + object); + out: +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + } + + /* +@@ -1482,7 +1482,7 @@ static void kmemleak_scan(void) + /* prepare the kmemleak_object's */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + #ifdef DEBUG + /* + * With a few exceptions there should be a maximum of +@@ -1499,7 +1499,7 @@ static void kmemleak_scan(void) + if (color_gray(object) && get_object(object)) + list_add_tail(&object->gray_list, &gray_list); + +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + +@@ -1564,14 +1564,14 @@ static void kmemleak_scan(void) + */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + if (color_white(object) && (object->flags & OBJECT_ALLOCATED) + && update_checksum(object) && get_object(object)) { + /* color it gray temporarily */ + object->count = object->min_count; + list_add_tail(&object->gray_list, &gray_list); + } +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + +@@ -1591,13 +1591,13 @@ static void kmemleak_scan(void) + */ + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + if (unreferenced_object(object) && + !(object->flags & OBJECT_REPORTED)) { + object->flags |= OBJECT_REPORTED; + new_leaks++; + } +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + +@@ -1749,10 +1749,10 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v) + struct kmemleak_object *object = v; + unsigned long flags; + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object)) + print_unreferenced(seq, object); +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + return 0; + } + +@@ -1782,9 +1782,9 @@ static int dump_str_object_info(const char *str) + return -EINVAL; + } + +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + dump_object_info(object); +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); + return 0; +@@ -1803,11 +1803,11 @@ static void kmemleak_clear(void) + + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { +- spin_lock_irqsave(&object->lock, flags); ++ raw_spin_lock_irqsave(&object->lock, flags); + if ((object->flags & OBJECT_REPORTED) && + unreferenced_object(object)) + __paint_it(object, KMEMLEAK_GREY); +- spin_unlock_irqrestore(&object->lock, flags); ++ raw_spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); + +-- +2.36.1 + diff --git a/debian/patches-rt/0307-sched-migrate_enable-Use-select_fallback_rq.patch b/debian/patches-rt/0307-sched-migrate_enable-Use-select_fallback_rq.patch new file mode 100644 index 000000000..6de7f0383 --- /dev/null +++ b/debian/patches-rt/0307-sched-migrate_enable-Use-select_fallback_rq.patch @@ -0,0 +1,66 @@ +From 86ff244b7222b5d5734b2c195ba28c7bbb5b6b0a Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Sat, 12 Oct 2019 01:52:12 -0500 +Subject: [PATCH 307/347] sched: migrate_enable: Use select_fallback_rq() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit adfa969d4cfcc995a9d866020124e50f1827d2d1 ] + +migrate_enable() currently open-codes a variant of select_fallback_rq(). +However, it does not have the "No more Mr. Nice Guy" fallback and thus +it will pass an invalid CPU to the migration thread if cpus_mask only +contains a CPU that is !active. + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 25 ++++++++++--------------- + 1 file changed, 10 insertions(+), 15 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 6f91ee2b7e91..7eb3037c0b35 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7329,6 +7329,7 @@ void migrate_enable(void) + if (p->migrate_disable_update) { + struct rq *rq; + struct rq_flags rf; ++ int cpu = task_cpu(p); + + rq = task_rq_lock(p, &rf); + update_rq_clock(rq); +@@ -7338,21 +7339,15 @@ void migrate_enable(void) + + p->migrate_disable_update = 0; + +- WARN_ON(smp_processor_id() != task_cpu(p)); +- if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { +- const struct cpumask *cpu_valid_mask = cpu_active_mask; +- struct migration_arg arg; +- unsigned int dest_cpu; +- +- if (p->flags & PF_KTHREAD) { +- /* +- * Kernel threads are allowed on online && !active CPUs +- */ +- cpu_valid_mask = cpu_online_mask; +- } +- dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask); +- arg.task = p; +- arg.dest_cpu = dest_cpu; ++ WARN_ON(smp_processor_id() != cpu); ++ if (!cpumask_test_cpu(cpu, &p->cpus_mask)) { ++ struct migration_arg arg = { p }; ++ struct rq_flags rf; ++ ++ rq = task_rq_lock(p, &rf); ++ update_rq_clock(rq); ++ arg.dest_cpu = select_fallback_rq(cpu, p); ++ task_rq_unlock(rq, p, &rf); + + unpin_current_cpu(); + preempt_lazy_enable(); +-- +2.36.1 + diff --git a/debian/patches-rt/0308-sched-Lazy-migrate_disable-processing.patch b/debian/patches-rt/0308-sched-Lazy-migrate_disable-processing.patch new file mode 100644 index 000000000..973b6e870 --- /dev/null +++ b/debian/patches-rt/0308-sched-Lazy-migrate_disable-processing.patch @@ -0,0 +1,616 @@ +From 34b182c6f6606c5a02a3ddea15356251ca28093b Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Sat, 12 Oct 2019 01:52:13 -0500 +Subject: [PATCH 308/347] sched: Lazy migrate_disable processing +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 425c5b38779a860062aa62219dc920d374b13c17 ] + +Avoid overhead on the majority of migrate disable/enable sequences by +only manipulating scheduler data (and grabbing the relevant locks) when +the task actually schedules while migrate-disabled. A kernel build +showed around a 10% reduction in system time (with CONFIG_NR_CPUS=512). + +Instead of cpuhp_pin_lock, CPU hotplug is handled by keeping a per-CPU +count of the number of pinned tasks (including tasks which have not +scheduled in the migrate-disabled section); takedown_cpu() will +wait until that reaches zero (confirmed by take_cpu_down() in stop +machine context to deal with races) before migrating tasks off of the +cpu. + +To simplify synchronization, updating cpus_mask is no longer deferred +until migrate_enable(). This lets us not have to worry about +migrate_enable() missing the update if it's on the fast path (didn't +schedule during the migrate disabled section). It also makes the code +a bit simpler and reduces deviation from mainline. + +While the main motivation for this is the performance benefit, lazy +migrate disable also eliminates the restriction on calling +migrate_disable() while atomic but leaving the atomic region prior to +calling migrate_enable() -- though this won't help with local_bh_disable() +(and thus rcutorture) unless something similar is done with the recently +added local_lock. + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + include/linux/cpu.h | 4 - + include/linux/sched.h | 11 +-- + init/init_task.c | 4 + + kernel/cpu.c | 103 +++++++++-------------- + kernel/sched/core.c | 182 +++++++++++++++++------------------------ + kernel/sched/sched.h | 4 + + lib/smp_processor_id.c | 3 + + 7 files changed, 129 insertions(+), 182 deletions(-) + +diff --git a/include/linux/cpu.h b/include/linux/cpu.h +index e67645924404..87347ccbba0c 100644 +--- a/include/linux/cpu.h ++++ b/include/linux/cpu.h +@@ -118,8 +118,6 @@ extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); + void clear_tasks_mm_cpumask(int cpu); + int cpu_down(unsigned int cpu); +-extern void pin_current_cpu(void); +-extern void unpin_current_cpu(void); + + #else /* CONFIG_HOTPLUG_CPU */ + +@@ -131,8 +129,6 @@ static inline int cpus_read_trylock(void) { return true; } + static inline void lockdep_assert_cpus_held(void) { } + static inline void cpu_hotplug_disable(void) { } + static inline void cpu_hotplug_enable(void) { } +-static inline void pin_current_cpu(void) { } +-static inline void unpin_current_cpu(void) { } + + #endif /* !CONFIG_HOTPLUG_CPU */ + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index e567fe2d7058..65069db8923c 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -227,6 +227,8 @@ extern void io_schedule_finish(int token); + extern long io_schedule_timeout(long timeout); + extern void io_schedule(void); + ++int cpu_nr_pinned(int cpu); ++ + /** + * struct prev_cputime - snapshot of system and user cputime + * @utime: time spent in user mode +@@ -670,16 +672,13 @@ struct task_struct { + cpumask_t cpus_mask; + #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int migrate_disable; +- int migrate_disable_update; +- int pinned_on_cpu; ++ bool migrate_disable_scheduled; + # ifdef CONFIG_SCHED_DEBUG +- int migrate_disable_atomic; ++ int pinned_on_cpu; + # endif +- + #elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + # ifdef CONFIG_SCHED_DEBUG + int migrate_disable; +- int migrate_disable_atomic; + # endif + #endif + #ifdef CONFIG_PREEMPT_RT_FULL +@@ -2058,4 +2057,6 @@ static inline void rseq_syscall(struct pt_regs *regs) + + #endif + ++extern struct task_struct *takedown_cpu_task; ++ + #endif +diff --git a/init/init_task.c b/init/init_task.c +index 634becebd713..45b84137c4b3 100644 +--- a/init/init_task.c ++++ b/init/init_task.c +@@ -80,6 +80,10 @@ struct task_struct init_task + .cpus_ptr = &init_task.cpus_mask, + .cpus_mask = CPU_MASK_ALL, + .nr_cpus_allowed= NR_CPUS, ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) && \ ++ defined(CONFIG_SCHED_DEBUG) ++ .pinned_on_cpu = -1, ++#endif + .mm = NULL, + .active_mm = &init_mm, + .restart_block = { +diff --git a/kernel/cpu.c b/kernel/cpu.c +index c84a93f84164..edd4fd8da726 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -77,11 +77,6 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, + }; + +-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PREEMPT_RT_FULL) +-static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \ +- __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock); +-#endif +- + #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) + static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +@@ -288,57 +283,6 @@ static int cpu_hotplug_disabled; + + #ifdef CONFIG_HOTPLUG_CPU + +-/** +- * pin_current_cpu - Prevent the current cpu from being unplugged +- */ +-void pin_current_cpu(void) +-{ +-#ifdef CONFIG_PREEMPT_RT_FULL +- struct rt_rw_lock *cpuhp_pin; +- unsigned int cpu; +- int ret; +- +-again: +- cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); +- ret = __read_rt_trylock(cpuhp_pin); +- if (ret) { +- current->pinned_on_cpu = smp_processor_id(); +- return; +- } +- cpu = smp_processor_id(); +- preempt_lazy_enable(); +- preempt_enable(); +- +- sleeping_lock_inc(); +- __read_rt_lock(cpuhp_pin); +- sleeping_lock_dec(); +- +- preempt_disable(); +- preempt_lazy_disable(); +- if (cpu != smp_processor_id()) { +- __read_rt_unlock(cpuhp_pin); +- goto again; +- } +- current->pinned_on_cpu = cpu; +-#endif +-} +- +-/** +- * unpin_current_cpu - Allow unplug of current cpu +- */ +-void unpin_current_cpu(void) +-{ +-#ifdef CONFIG_PREEMPT_RT_FULL +- struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); +- +- if (WARN_ON(current->pinned_on_cpu != smp_processor_id())) +- cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, current->pinned_on_cpu); +- +- current->pinned_on_cpu = -1; +- __read_rt_unlock(cpuhp_pin); +-#endif +-} +- + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); + + void cpus_read_lock(void) +@@ -932,6 +876,15 @@ static int take_cpu_down(void *_param) + int err, cpu = smp_processor_id(); + int ret; + ++#ifdef CONFIG_PREEMPT_RT_BASE ++ /* ++ * If any tasks disabled migration before we got here, ++ * go back and sleep again. ++ */ ++ if (cpu_nr_pinned(cpu)) ++ return -EAGAIN; ++#endif ++ + /* Ensure this CPU doesn't handle any more interrupts. */ + err = __cpu_disable(); + if (err < 0) +@@ -959,11 +912,10 @@ static int take_cpu_down(void *_param) + return 0; + } + ++struct task_struct *takedown_cpu_task; ++ + static int takedown_cpu(unsigned int cpu) + { +-#ifdef CONFIG_PREEMPT_RT_FULL +- struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu); +-#endif + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; + +@@ -976,17 +928,38 @@ static int takedown_cpu(unsigned int cpu) + */ + irq_lock_sparse(); + +-#ifdef CONFIG_PREEMPT_RT_FULL +- __write_rt_lock(cpuhp_pin); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ WARN_ON_ONCE(takedown_cpu_task); ++ takedown_cpu_task = current; ++ ++again: ++ /* ++ * If a task pins this CPU after we pass this check, take_cpu_down ++ * will return -EAGAIN. ++ */ ++ for (;;) { ++ int nr_pinned; ++ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ nr_pinned = cpu_nr_pinned(cpu); ++ if (nr_pinned == 0) ++ break; ++ schedule(); ++ } ++ set_current_state(TASK_RUNNING); + #endif + + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ + err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ if (err == -EAGAIN) ++ goto again; ++#endif + if (err) { +-#ifdef CONFIG_PREEMPT_RT_FULL +- __write_rt_unlock(cpuhp_pin); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ takedown_cpu_task = NULL; + #endif + /* CPU refused to die */ + irq_unlock_sparse(); +@@ -1006,8 +979,8 @@ static int takedown_cpu(unsigned int cpu) + wait_for_ap_thread(st, false); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); + +-#ifdef CONFIG_PREEMPT_RT_FULL +- __write_rt_unlock(cpuhp_pin); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ takedown_cpu_task = NULL; + #endif + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 7eb3037c0b35..de6514e13e0c 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1065,7 +1065,8 @@ static int migration_cpu_stop(void *data) + void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) + { + cpumask_copy(&p->cpus_mask, new_mask); +- p->nr_cpus_allowed = cpumask_weight(new_mask); ++ if (p->cpus_ptr == &p->cpus_mask) ++ p->nr_cpus_allowed = cpumask_weight(new_mask); + } + + #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +@@ -1076,8 +1077,7 @@ int __migrate_disabled(struct task_struct *p) + EXPORT_SYMBOL_GPL(__migrate_disabled); + #endif + +-static void __do_set_cpus_allowed_tail(struct task_struct *p, +- const struct cpumask *new_mask) ++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + { + struct rq *rq = task_rq(p); + bool queued, running; +@@ -1106,20 +1106,6 @@ static void __do_set_cpus_allowed_tail(struct task_struct *p, + set_curr_task(rq, p); + } + +-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +-{ +-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +- if (__migrate_disabled(p)) { +- lockdep_assert_held(&p->pi_lock); +- +- cpumask_copy(&p->cpus_mask, new_mask); +- p->migrate_disable_update = 1; +- return; +- } +-#endif +- __do_set_cpus_allowed_tail(p, new_mask); +-} +- + /* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on +@@ -1179,7 +1165,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, + } + + /* Can the task run on the task's current CPU? If so, we're done */ +- if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) ++ if (cpumask_test_cpu(task_cpu(p), new_mask) || ++ p->cpus_ptr != &p->cpus_mask) + goto out; + + if (task_running(rq, p) || p->state == TASK_WAKING) { +@@ -3459,6 +3446,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) + BUG(); + } + ++static void migrate_disabled_sched(struct task_struct *p); ++ + /* + * __schedule() is the main scheduler function. + * +@@ -3529,6 +3518,9 @@ static void __sched notrace __schedule(bool preempt) + rq_lock(rq, &rf); + smp_mb__after_spinlock(); + ++ if (__migrate_disabled(prev)) ++ migrate_disabled_sched(prev); ++ + /* Promote REQ to ACT */ + rq->clock_update_flags <<= 1; + update_rq_clock(rq); +@@ -5777,6 +5769,8 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) + BUG_ON(!next); + put_prev_task(rq, next); + ++ WARN_ON_ONCE(__migrate_disabled(next)); ++ + /* + * Rules for changing task_struct::cpus_mask are holding + * both pi_lock and rq->lock, such that holding either +@@ -7241,14 +7235,9 @@ update_nr_migratory(struct task_struct *p, long delta) + static inline void + migrate_disable_update_cpus_allowed(struct task_struct *p) + { +- struct rq *rq; +- struct rq_flags rf; +- +- rq = task_rq_lock(p, &rf); + p->cpus_ptr = cpumask_of(smp_processor_id()); + update_nr_migratory(p, -1); + p->nr_cpus_allowed = 1; +- task_rq_unlock(rq, p, &rf); + } + + static inline void +@@ -7266,54 +7255,35 @@ migrate_enable_update_cpus_allowed(struct task_struct *p) + + void migrate_disable(void) + { +- struct task_struct *p = current; ++ preempt_disable(); + +- if (in_atomic() || irqs_disabled()) { ++ if (++current->migrate_disable == 1) { ++ this_rq()->nr_pinned++; ++ preempt_lazy_disable(); + #ifdef CONFIG_SCHED_DEBUG +- p->migrate_disable_atomic++; ++ WARN_ON_ONCE(current->pinned_on_cpu >= 0); ++ current->pinned_on_cpu = smp_processor_id(); + #endif +- return; +- } +-#ifdef CONFIG_SCHED_DEBUG +- if (unlikely(p->migrate_disable_atomic)) { +- tracing_off(); +- WARN_ON_ONCE(1); + } +-#endif + +- if (p->migrate_disable) { +- p->migrate_disable++; +- return; +- } ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_disable); + +- preempt_disable(); +- preempt_lazy_disable(); +- pin_current_cpu(); ++static void migrate_disabled_sched(struct task_struct *p) ++{ ++ if (p->migrate_disable_scheduled) ++ return; + + migrate_disable_update_cpus_allowed(p); +- p->migrate_disable = 1; +- +- preempt_enable(); ++ p->migrate_disable_scheduled = 1; + } +-EXPORT_SYMBOL(migrate_disable); + + void migrate_enable(void) + { + struct task_struct *p = current; +- +- if (in_atomic() || irqs_disabled()) { +-#ifdef CONFIG_SCHED_DEBUG +- p->migrate_disable_atomic--; +-#endif +- return; +- } +- +-#ifdef CONFIG_SCHED_DEBUG +- if (unlikely(p->migrate_disable_atomic)) { +- tracing_off(); +- WARN_ON_ONCE(1); +- } +-#endif ++ struct rq *rq = this_rq(); ++ int cpu = task_cpu(p); + + WARN_ON_ONCE(p->migrate_disable <= 0); + if (p->migrate_disable > 1) { +@@ -7323,67 +7293,69 @@ void migrate_enable(void) + + preempt_disable(); + ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(current->pinned_on_cpu != cpu); ++ current->pinned_on_cpu = -1; ++#endif ++ ++ WARN_ON_ONCE(rq->nr_pinned < 1); ++ + p->migrate_disable = 0; ++ rq->nr_pinned--; ++ if (rq->nr_pinned == 0 && unlikely(!cpu_active(cpu)) && ++ takedown_cpu_task) ++ wake_up_process(takedown_cpu_task); ++ ++ if (!p->migrate_disable_scheduled) ++ goto out; ++ ++ p->migrate_disable_scheduled = 0; ++ + migrate_enable_update_cpus_allowed(p); + +- if (p->migrate_disable_update) { +- struct rq *rq; ++ WARN_ON(smp_processor_id() != cpu); ++ if (!is_cpu_allowed(p, cpu)) { ++ struct migration_arg arg = { p }; + struct rq_flags rf; +- int cpu = task_cpu(p); + + rq = task_rq_lock(p, &rf); + update_rq_clock(rq); +- +- __do_set_cpus_allowed_tail(p, &p->cpus_mask); ++ arg.dest_cpu = select_fallback_rq(cpu, p); + task_rq_unlock(rq, p, &rf); + +- p->migrate_disable_update = 0; +- +- WARN_ON(smp_processor_id() != cpu); +- if (!cpumask_test_cpu(cpu, &p->cpus_mask)) { +- struct migration_arg arg = { p }; +- struct rq_flags rf; ++ preempt_lazy_enable(); ++ preempt_enable(); + +- rq = task_rq_lock(p, &rf); +- update_rq_clock(rq); +- arg.dest_cpu = select_fallback_rq(cpu, p); +- task_rq_unlock(rq, p, &rf); +- +- unpin_current_cpu(); +- preempt_lazy_enable(); +- preempt_enable(); +- +- sleeping_lock_inc(); +- stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); +- sleeping_lock_dec(); +- tlb_migrate_finish(p->mm); ++ sleeping_lock_inc(); ++ stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); ++ sleeping_lock_dec(); ++ tlb_migrate_finish(p->mm); + +- return; +- } ++ return; + } +- unpin_current_cpu(); ++ ++out: + preempt_lazy_enable(); + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); + +-#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +-void migrate_disable(void) ++int cpu_nr_pinned(int cpu) + { +-#ifdef CONFIG_SCHED_DEBUG +- struct task_struct *p = current; ++ struct rq *rq = cpu_rq(cpu); + +- if (in_atomic() || irqs_disabled()) { +- p->migrate_disable_atomic++; +- return; +- } ++ return rq->nr_pinned; ++} + +- if (unlikely(p->migrate_disable_atomic)) { +- tracing_off(); +- WARN_ON_ONCE(1); +- } ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++static void migrate_disabled_sched(struct task_struct *p) ++{ ++} + +- p->migrate_disable++; ++void migrate_disable(void) ++{ ++#ifdef CONFIG_SCHED_DEBUG ++ current->migrate_disable++; + #endif + barrier(); + } +@@ -7394,20 +7366,14 @@ void migrate_enable(void) + #ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + +- if (in_atomic() || irqs_disabled()) { +- p->migrate_disable_atomic--; +- return; +- } +- +- if (unlikely(p->migrate_disable_atomic)) { +- tracing_off(); +- WARN_ON_ONCE(1); +- } +- + WARN_ON_ONCE(p->migrate_disable <= 0); + p->migrate_disable--; + #endif + barrier(); + } + EXPORT_SYMBOL(migrate_enable); ++#else ++static void migrate_disabled_sched(struct task_struct *p) ++{ ++} + #endif +diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h +index 87a05bb90124..45b3f135d205 100644 +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -915,6 +915,10 @@ struct rq { + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; + #endif ++ ++#if defined(CONFIG_PREEMPT_RT_BASE) && defined(CONFIG_SMP) ++ int nr_pinned; ++#endif + }; + + static inline int cpu_of(struct rq *rq) +diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c +index b8a8a8db2d75..0c80992aa337 100644 +--- a/lib/smp_processor_id.c ++++ b/lib/smp_processor_id.c +@@ -22,6 +22,9 @@ notrace static unsigned int check_preemption_disabled(const char *what1, + * Kernel threads bound to a single CPU can safely use + * smp_processor_id(): + */ ++ if (current->migrate_disable) ++ goto out; ++ + if (current->nr_cpus_allowed == 1) + goto out; + +-- +2.36.1 + diff --git a/debian/patches-rt/0309-sched-migrate_enable-Use-stop_one_cpu_nowait.patch b/debian/patches-rt/0309-sched-migrate_enable-Use-stop_one_cpu_nowait.patch new file mode 100644 index 000000000..21108241b --- /dev/null +++ b/debian/patches-rt/0309-sched-migrate_enable-Use-stop_one_cpu_nowait.patch @@ -0,0 +1,121 @@ +From 778702cffc4e8e3f002716b84944ddf23692639f Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Sat, 12 Oct 2019 01:52:14 -0500 +Subject: [PATCH 309/347] sched: migrate_enable: Use stop_one_cpu_nowait() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 6b39a1fa8c53cae08dc03afdae193b7d3a78a173 ] + +migrate_enable() can be called with current->state != TASK_RUNNING. +Avoid clobbering the existing state by using stop_one_cpu_nowait(). +Since we're stopping the current cpu, we know that we won't get +past __schedule() until migration_cpu_stop() has run (at least up to +the point of migrating us to another cpu). + +Signed-off-by: Scott Wood <swood@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + include/linux/stop_machine.h | 2 ++ + kernel/sched/core.c | 23 +++++++++++++---------- + kernel/stop_machine.c | 7 +++++-- + 3 files changed, 20 insertions(+), 12 deletions(-) + +diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h +index ccdaa8fd5657..150e886ed83d 100644 +--- a/include/linux/stop_machine.h ++++ b/include/linux/stop_machine.h +@@ -26,6 +26,8 @@ struct cpu_stop_work { + cpu_stop_fn_t fn; + void *arg; + struct cpu_stop_done *done; ++ /* Did not run due to disabled stopper; for nowait debug checks */ ++ bool disabled; + }; + + int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index de6514e13e0c..dff9d26a8625 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -990,6 +990,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, + struct migration_arg { + struct task_struct *task; + int dest_cpu; ++ bool done; + }; + + /* +@@ -1025,6 +1026,11 @@ static int migration_cpu_stop(void *data) + struct task_struct *p = arg->task; + struct rq *rq = this_rq(); + struct rq_flags rf; ++ int dest_cpu = arg->dest_cpu; ++ ++ /* We don't look at arg after this point. */ ++ smp_mb(); ++ arg->done = true; + + /* + * The original target CPU might have gone down and we might +@@ -1047,9 +1053,9 @@ static int migration_cpu_stop(void *data) + */ + if (task_rq(p) == rq) { + if (task_on_rq_queued(p)) +- rq = __migrate_task(rq, &rf, p, arg->dest_cpu); ++ rq = __migrate_task(rq, &rf, p, dest_cpu); + else +- p->wake_cpu = arg->dest_cpu; ++ p->wake_cpu = dest_cpu; + } + rq_unlock(rq, &rf); + raw_spin_unlock(&p->pi_lock); +@@ -7316,6 +7322,7 @@ void migrate_enable(void) + WARN_ON(smp_processor_id() != cpu); + if (!is_cpu_allowed(p, cpu)) { + struct migration_arg arg = { p }; ++ struct cpu_stop_work work; + struct rq_flags rf; + + rq = task_rq_lock(p, &rf); +@@ -7323,15 +7330,11 @@ void migrate_enable(void) + arg.dest_cpu = select_fallback_rq(cpu, p); + task_rq_unlock(rq, p, &rf); + +- preempt_lazy_enable(); +- preempt_enable(); +- +- sleeping_lock_inc(); +- stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); +- sleeping_lock_dec(); ++ stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop, ++ &arg, &work); + tlb_migrate_finish(p->mm); +- +- return; ++ __schedule(true); ++ WARN_ON_ONCE(!arg.done && !work.disabled); + } + + out: +diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c +index 067cb83f37ea..2d15c0d50625 100644 +--- a/kernel/stop_machine.c ++++ b/kernel/stop_machine.c +@@ -86,8 +86,11 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) + enabled = stopper->enabled; + if (enabled) + __cpu_stop_queue_work(stopper, work, &wakeq); +- else if (work->done) +- cpu_stop_signal_done(work->done); ++ else { ++ work->disabled = true; ++ if (work->done) ++ cpu_stop_signal_done(work->done); ++ } + raw_spin_unlock_irqrestore(&stopper->lock, flags); + + wake_up_q(&wakeq); +-- +2.36.1 + diff --git a/debian/patches-rt/0310-Revert-ARM-Initialize-split-page-table-locks-for-vec.patch b/debian/patches-rt/0310-Revert-ARM-Initialize-split-page-table-locks-for-vec.patch new file mode 100644 index 000000000..92464be91 --- /dev/null +++ b/debian/patches-rt/0310-Revert-ARM-Initialize-split-page-table-locks-for-vec.patch @@ -0,0 +1,87 @@ +From 24329bb57c5b6fae2c3360adcb2c69bbcd4314f4 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 18 Oct 2019 13:04:15 +0200 +Subject: [PATCH 310/347] Revert "ARM: Initialize split page table locks for + vector page" +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 247074c44d8c3e619dfde6404a52295d8d671d38 ] + +I'm dropping this patch, with its original description: + +|ARM: Initialize split page table locks for vector page +| +|Without this patch, ARM can not use SPLIT_PTLOCK_CPUS if +|PREEMPT_RT_FULL=y because vectors_user_mapping() creates a +|VM_ALWAYSDUMP mapping of the vector page (address 0xffff0000), but no +|ptl->lock has been allocated for the page. An attempt to coredump +|that page will result in a kernel NULL pointer dereference when +|follow_page() attempts to lock the page. +| +|The call tree to the NULL pointer dereference is: +| +| do_notify_resume() +| get_signal_to_deliver() +| do_coredump() +| elf_core_dump() +| get_dump_page() +| __get_user_pages() +| follow_page() +| pte_offset_map_lock() <----- a #define +| ... +| rt_spin_lock() +| +|The underlying problem is exposed by mm-shrink-the-page-frame-to-rt-size.patch. + +The patch named mm-shrink-the-page-frame-to-rt-size.patch was dropped +from the RT queue once the SPLIT_PTLOCK_CPUS feature (in a slightly +different shape) went upstream (somewhere between v3.12 and v3.14). + +I can see that the patch still allocates a lock which wasn't there +before. However I can't trigger a kernel oops like described in the +patch by triggering a coredump. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + arch/arm/kernel/process.c | 24 ------------------------ + 1 file changed, 24 deletions(-) + +diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c +index 8d3c7ce34c24..82ab015bf42b 100644 +--- a/arch/arm/kernel/process.c ++++ b/arch/arm/kernel/process.c +@@ -324,30 +324,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) + } + + #ifdef CONFIG_MMU +-/* +- * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not +- * initialized by pgtable_page_ctor() then a coredump of the vector page will +- * fail. +- */ +-static int __init vectors_user_mapping_init_page(void) +-{ +- struct page *page; +- unsigned long addr = 0xffff0000; +- pgd_t *pgd; +- pud_t *pud; +- pmd_t *pmd; +- +- pgd = pgd_offset_k(addr); +- pud = pud_offset(pgd, addr); +- pmd = pmd_offset(pud, addr); +- page = pmd_page(*(pmd)); +- +- pgtable_page_ctor(page); +- +- return 0; +-} +-late_initcall(vectors_user_mapping_init_page); +- + #ifdef CONFIG_KUSER_HELPERS + /* + * The vectors page is always readable from user space for the +-- +2.36.1 + diff --git a/debian/patches-rt/0311-locking-Make-spinlock_t-and-rwlock_t-a-RCU-section-o.patch b/debian/patches-rt/0311-locking-Make-spinlock_t-and-rwlock_t-a-RCU-section-o.patch new file mode 100644 index 000000000..b6096f1c2 --- /dev/null +++ b/debian/patches-rt/0311-locking-Make-spinlock_t-and-rwlock_t-a-RCU-section-o.patch @@ -0,0 +1,129 @@ +From c0b7b36cdce411ac0992029c343d9fb8eb65c305 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 19 Nov 2019 09:25:04 +0100 +Subject: [PATCH 311/347] locking: Make spinlock_t and rwlock_t a RCU section + on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 84440022a0e1c8c936d61f8f97593674a295d409 ] + +On !RT a locked spinlock_t and rwlock_t disables preemption which +implies a RCU read section. There is code that relies on that behaviour. + +Add an explicit RCU read section on RT while a sleeping lock (a lock +which would disables preemption on !RT) acquired. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/locking/rtmutex.c | 6 ++++++ + kernel/locking/rwlock-rt.c | 6 ++++++ + 2 files changed, 12 insertions(+) + +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index dc95a81ae3a6..fe5153fc7665 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1142,6 +1142,7 @@ void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) + void __lockfunc rt_spin_lock(spinlock_t *lock) + { + sleeping_lock_inc(); ++ rcu_read_lock(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +@@ -1157,6 +1158,7 @@ void __lockfunc __rt_spin_lock(struct rt_mutex *lock) + void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) + { + sleeping_lock_inc(); ++ rcu_read_lock(); + migrate_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +@@ -1170,6 +1172,7 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock) + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); + migrate_enable(); ++ rcu_read_unlock(); + sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_spin_unlock); +@@ -1201,6 +1204,7 @@ int __lockfunc rt_spin_trylock(spinlock_t *lock) + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ rcu_read_lock(); + } else { + migrate_enable(); + sleeping_lock_dec(); +@@ -1217,6 +1221,7 @@ int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + sleeping_lock_inc(); ++ rcu_read_lock(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else +@@ -1233,6 +1238,7 @@ int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + sleeping_lock_inc(); ++ rcu_read_lock(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } +diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c +index c3b91205161c..0ae8c62ea832 100644 +--- a/kernel/locking/rwlock-rt.c ++++ b/kernel/locking/rwlock-rt.c +@@ -310,6 +310,7 @@ int __lockfunc rt_read_trylock(rwlock_t *rwlock) + ret = do_read_rt_trylock(rwlock); + if (ret) { + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); ++ rcu_read_lock(); + } else { + migrate_enable(); + sleeping_lock_dec(); +@@ -327,6 +328,7 @@ int __lockfunc rt_write_trylock(rwlock_t *rwlock) + ret = do_write_rt_trylock(rwlock); + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ rcu_read_lock(); + } else { + migrate_enable(); + sleeping_lock_dec(); +@@ -338,6 +340,7 @@ EXPORT_SYMBOL(rt_write_trylock); + void __lockfunc rt_read_lock(rwlock_t *rwlock) + { + sleeping_lock_inc(); ++ rcu_read_lock(); + migrate_disable(); + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + do_read_rt_lock(rwlock); +@@ -347,6 +350,7 @@ EXPORT_SYMBOL(rt_read_lock); + void __lockfunc rt_write_lock(rwlock_t *rwlock) + { + sleeping_lock_inc(); ++ rcu_read_lock(); + migrate_disable(); + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + do_write_rt_lock(rwlock); +@@ -358,6 +362,7 @@ void __lockfunc rt_read_unlock(rwlock_t *rwlock) + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_read_rt_unlock(rwlock); + migrate_enable(); ++ rcu_read_unlock(); + sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_read_unlock); +@@ -367,6 +372,7 @@ void __lockfunc rt_write_unlock(rwlock_t *rwlock) + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_write_rt_unlock(rwlock); + migrate_enable(); ++ rcu_read_unlock(); + sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_write_unlock); +-- +2.36.1 + diff --git a/debian/patches-rt/0312-sched-core-migrate_enable-must-access-takedown_cpu_t.patch b/debian/patches-rt/0312-sched-core-migrate_enable-must-access-takedown_cpu_t.patch new file mode 100644 index 000000000..2132d259a --- /dev/null +++ b/debian/patches-rt/0312-sched-core-migrate_enable-must-access-takedown_cpu_t.patch @@ -0,0 +1,55 @@ +From 01f24622e993de73c028f4eaa067c421e4e0d851 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 29 Nov 2019 17:24:55 +0100 +Subject: [PATCH 312/347] sched/core: migrate_enable() must access + takedown_cpu_task on !HOTPLUG_CPU +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit a61d1977f692e46bad99a100f264981ba08cb4bd ] + +The variable takedown_cpu_task is never declared/used on !HOTPLUG_CPU +except for migrate_enable(). This leads to a link error. + +Don't use takedown_cpu_task in !HOTPLUG_CPU. + +Reported-by: Dick Hollenbeck <dick@softplc.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/cpu.c | 2 ++ + kernel/sched/core.c | 2 ++ + 2 files changed, 4 insertions(+) + +diff --git a/kernel/cpu.c b/kernel/cpu.c +index edd4fd8da726..44245b35c09c 100644 +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -912,7 +912,9 @@ static int take_cpu_down(void *_param) + return 0; + } + ++#ifdef CONFIG_PREEMPT_RT_BASE + struct task_struct *takedown_cpu_task; ++#endif + + static int takedown_cpu(unsigned int cpu) + { +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index dff9d26a8625..270adb525d93 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7308,9 +7308,11 @@ void migrate_enable(void) + + p->migrate_disable = 0; + rq->nr_pinned--; ++#ifdef CONFIG_HOTPLUG_CPU + if (rq->nr_pinned == 0 && unlikely(!cpu_active(cpu)) && + takedown_cpu_task) + wake_up_process(takedown_cpu_task); ++#endif + + if (!p->migrate_disable_scheduled) + goto out; +-- +2.36.1 + diff --git a/debian/patches-rt/0313-lib-smp_processor_id-Adjust-check_preemption_disable.patch b/debian/patches-rt/0313-lib-smp_processor_id-Adjust-check_preemption_disable.patch new file mode 100644 index 000000000..54602a05d --- /dev/null +++ b/debian/patches-rt/0313-lib-smp_processor_id-Adjust-check_preemption_disable.patch @@ -0,0 +1,41 @@ +From d66acdc1d09f10c3141286072a6c07ec47245926 Mon Sep 17 00:00:00 2001 +From: Daniel Wagner <dwagner@suse.de> +Date: Mon, 16 Dec 2019 16:15:57 +0100 +Subject: [PATCH 313/347] lib/smp_processor_id: Adjust + check_preemption_disabled() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit af3c1c5fdf177870fb5e6e16b24e374696ab28f5 ] + +The current->migrate_disable counter is not always defined leading to +build failures with DEBUG_PREEMPT && !PREEMPT_RT_BASE. + +Restrict the access to ->migrate_disable to same set where +->migrate_disable is modified. + +Signed-off-by: Daniel Wagner <dwagner@suse.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: adjust condition + description] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + lib/smp_processor_id.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c +index 0c80992aa337..2e7398534b66 100644 +--- a/lib/smp_processor_id.c ++++ b/lib/smp_processor_id.c +@@ -22,8 +22,10 @@ notrace static unsigned int check_preemption_disabled(const char *what1, + * Kernel threads bound to a single CPU can safely use + * smp_processor_id(): + */ ++#if defined(CONFIG_PREEMPT_RT_BASE) && (defined(CONFIG_SMP) || defined(CONFIG_SCHED_DEBUG)) + if (current->migrate_disable) + goto out; ++#endif + + if (current->nr_cpus_allowed == 1) + goto out; +-- +2.36.1 + diff --git a/debian/patches-rt/0314-sched-migrate_enable-Busy-loop-until-the-migration-r.patch b/debian/patches-rt/0314-sched-migrate_enable-Busy-loop-until-the-migration-r.patch new file mode 100644 index 000000000..d51c9b637 --- /dev/null +++ b/debian/patches-rt/0314-sched-migrate_enable-Busy-loop-until-the-migration-r.patch @@ -0,0 +1,57 @@ +From 090c26864ec17b496dea3397656b006550e31852 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 12 Dec 2019 10:53:59 +0100 +Subject: [PATCH 314/347] sched: migrate_enable: Busy loop until the migration + request is completed +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 140d7f54a5fff02898d2ca9802b39548bf7455f1 ] + +If user task changes the CPU affinity mask of a running task it will +dispatch migration request if the current CPU is no longer allowed. This +might happen shortly before a task enters a migrate_disable() section. +Upon leaving the migrate_disable() section, the task will notice that +the current CPU is no longer allowed and will will dispatch its own +migration request to move it off the current CPU. +While invoking __schedule() the first migration request will be +processed and the task returns on the "new" CPU with "arg.done = 0". Its +own migration request will be processed shortly after and will result in +memory corruption if the stack memory, designed for request, was used +otherwise in the meantime. + +Spin until the migration request has been processed if it was accepted. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 270adb525d93..d190d9e6b10f 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7323,7 +7323,7 @@ void migrate_enable(void) + + WARN_ON(smp_processor_id() != cpu); + if (!is_cpu_allowed(p, cpu)) { +- struct migration_arg arg = { p }; ++ struct migration_arg arg = { .task = p }; + struct cpu_stop_work work; + struct rq_flags rf; + +@@ -7336,7 +7336,10 @@ void migrate_enable(void) + &arg, &work); + tlb_migrate_finish(p->mm); + __schedule(true); +- WARN_ON_ONCE(!arg.done && !work.disabled); ++ if (!work.disabled) { ++ while (!arg.done) ++ cpu_relax(); ++ } + } + + out: +-- +2.36.1 + diff --git a/debian/patches-rt/0315-userfaultfd-Use-a-seqlock-instead-of-seqcount.patch b/debian/patches-rt/0315-userfaultfd-Use-a-seqlock-instead-of-seqcount.patch new file mode 100644 index 000000000..227e20afd --- /dev/null +++ b/debian/patches-rt/0315-userfaultfd-Use-a-seqlock-instead-of-seqcount.patch @@ -0,0 +1,80 @@ +From 4639984350d5520c7268c26b6454c2f47cf139e4 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 18 Dec 2019 12:25:09 +0100 +Subject: [PATCH 315/347] userfaultfd: Use a seqlock instead of seqcount +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit dc952a564d02997330654be9628bbe97ba2a05d3 ] + +On RT write_seqcount_begin() disables preemption which leads to warning +in add_wait_queue() while the spinlock_t is acquired. +The waitqueue can't be converted to swait_queue because +userfaultfd_wake_function() is used as a custom wake function. + +Use seqlock instead seqcount to avoid the preempt_disable() section +during add_wait_queue(). + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + fs/userfaultfd.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c +index 23c8efc967af..3f79609511da 100644 +--- a/fs/userfaultfd.c ++++ b/fs/userfaultfd.c +@@ -56,7 +56,7 @@ struct userfaultfd_ctx { + /* waitqueue head for events */ + wait_queue_head_t event_wqh; + /* a refile sequence protected by fault_pending_wqh lock */ +- struct seqcount refile_seq; ++ seqlock_t refile_seq; + /* pseudo fd refcounting */ + atomic_t refcount; + /* userfaultfd syscall flags */ +@@ -1059,7 +1059,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, + * waitqueue could become empty if this is the + * only userfault. + */ +- write_seqcount_begin(&ctx->refile_seq); ++ write_seqlock(&ctx->refile_seq); + + /* + * The fault_pending_wqh.lock prevents the uwq +@@ -1085,7 +1085,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, + list_del(&uwq->wq.entry); + add_wait_queue(&ctx->fault_wqh, &uwq->wq); + +- write_seqcount_end(&ctx->refile_seq); ++ write_sequnlock(&ctx->refile_seq); + + /* careful to always initialize msg if ret == 0 */ + *msg = uwq->msg; +@@ -1258,11 +1258,11 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, + * sure we've userfaults to wake. + */ + do { +- seq = read_seqcount_begin(&ctx->refile_seq); ++ seq = read_seqbegin(&ctx->refile_seq); + need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || + waitqueue_active(&ctx->fault_wqh); + cond_resched(); +- } while (read_seqcount_retry(&ctx->refile_seq, seq)); ++ } while (read_seqretry(&ctx->refile_seq, seq)); + if (need_wakeup) + __wake_userfault(ctx, range); + } +@@ -1936,7 +1936,7 @@ static void init_once_userfaultfd_ctx(void *mem) + init_waitqueue_head(&ctx->fault_wqh); + init_waitqueue_head(&ctx->event_wqh); + init_waitqueue_head(&ctx->fd_wqh); +- seqcount_init(&ctx->refile_seq); ++ seqlock_init(&ctx->refile_seq); + } + + SYSCALL_DEFINE1(userfaultfd, int, flags) +-- +2.36.1 + diff --git a/debian/patches-rt/0316-sched-migrate_enable-Use-per-cpu-cpu_stop_work.patch b/debian/patches-rt/0316-sched-migrate_enable-Use-per-cpu-cpu_stop_work.patch new file mode 100644 index 000000000..fcff1b8a4 --- /dev/null +++ b/debian/patches-rt/0316-sched-migrate_enable-Use-per-cpu-cpu_stop_work.patch @@ -0,0 +1,83 @@ +From 5595f7a45953987f56b3e64c3a20f6f90735d4a1 Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Fri, 24 Jan 2020 06:11:46 -0500 +Subject: [PATCH 316/347] sched: migrate_enable: Use per-cpu cpu_stop_work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 2dcd94b443c5dcbc20281666321b7f025f9cc85c ] + +Commit e6c287b1512d ("sched: migrate_enable: Use stop_one_cpu_nowait()") +adds a busy wait to deal with an edge case where the migrated thread +can resume running on another CPU before the stopper has consumed +cpu_stop_work. However, this is done with preemption disabled and can +potentially lead to deadlock. + +While it is not guaranteed that the cpu_stop_work will be consumed before +the migrating thread resumes and exits the stack frame, it is guaranteed +that nothing other than the stopper can run on the old cpu between the +migrating thread scheduling out and the cpu_stop_work being consumed. +Thus, we can store cpu_stop_work in per-cpu data without it being +reused too early. + +Fixes: e6c287b1512d ("sched: migrate_enable: Use stop_one_cpu_nowait()") +Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Scott Wood <swood@redhat.com> +Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 22 ++++++++++++++-------- + 1 file changed, 14 insertions(+), 8 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index d190d9e6b10f..8b946353b1d7 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7285,6 +7285,9 @@ static void migrate_disabled_sched(struct task_struct *p) + p->migrate_disable_scheduled = 1; + } + ++static DEFINE_PER_CPU(struct cpu_stop_work, migrate_work); ++static DEFINE_PER_CPU(struct migration_arg, migrate_arg); ++ + void migrate_enable(void) + { + struct task_struct *p = current; +@@ -7323,23 +7326,26 @@ void migrate_enable(void) + + WARN_ON(smp_processor_id() != cpu); + if (!is_cpu_allowed(p, cpu)) { +- struct migration_arg arg = { .task = p }; +- struct cpu_stop_work work; ++ struct migration_arg __percpu *arg; ++ struct cpu_stop_work __percpu *work; + struct rq_flags rf; + ++ work = this_cpu_ptr(&migrate_work); ++ arg = this_cpu_ptr(&migrate_arg); ++ WARN_ON_ONCE(!arg->done && !work->disabled && work->arg); ++ ++ arg->task = p; ++ arg->done = false; ++ + rq = task_rq_lock(p, &rf); + update_rq_clock(rq); +- arg.dest_cpu = select_fallback_rq(cpu, p); ++ arg->dest_cpu = select_fallback_rq(cpu, p); + task_rq_unlock(rq, p, &rf); + + stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop, +- &arg, &work); ++ arg, work); + tlb_migrate_finish(p->mm); + __schedule(true); +- if (!work.disabled) { +- while (!arg.done) +- cpu_relax(); +- } + } + + out: +-- +2.36.1 + diff --git a/debian/patches-rt/0317-sched-migrate_enable-Remove-__schedule-call.patch b/debian/patches-rt/0317-sched-migrate_enable-Remove-__schedule-call.patch new file mode 100644 index 000000000..2078fa5bb --- /dev/null +++ b/debian/patches-rt/0317-sched-migrate_enable-Remove-__schedule-call.patch @@ -0,0 +1,41 @@ +From 1742897c78e053379ae6bb15024026f01e0bac2d Mon Sep 17 00:00:00 2001 +From: Scott Wood <swood@redhat.com> +Date: Fri, 24 Jan 2020 06:11:47 -0500 +Subject: [PATCH 317/347] sched: migrate_enable: Remove __schedule() call +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit b8162e61e9a33bd1de6452eb838fbf50a93ddd9a ] + +We can rely on preempt_enable() to schedule. Besides simplifying the +code, this potentially allows sequences such as the following to be +permitted: + +migrate_disable(); +preempt_disable(); +migrate_enable(); +preempt_enable(); + +Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Scott Wood <swood@redhat.com> +Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/sched/core.c | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 8b946353b1d7..410882ff2007 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7345,7 +7345,6 @@ void migrate_enable(void) + stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop, + arg, work); + tlb_migrate_finish(p->mm); +- __schedule(true); + } + + out: +-- +2.36.1 + diff --git a/debian/patches-rt/0318-mm-memcontrol-Move-misplaced-local_unlock_irqrestore.patch b/debian/patches-rt/0318-mm-memcontrol-Move-misplaced-local_unlock_irqrestore.patch new file mode 100644 index 000000000..87fb2dcd0 --- /dev/null +++ b/debian/patches-rt/0318-mm-memcontrol-Move-misplaced-local_unlock_irqrestore.patch @@ -0,0 +1,42 @@ +From 402c737918994231fbd205f2a7dcf06c5046a849 Mon Sep 17 00:00:00 2001 +From: Matt Fleming <matt@codeblueprint.co.uk> +Date: Sun, 26 Jan 2020 21:19:45 +0000 +Subject: [PATCH 318/347] mm/memcontrol: Move misplaced + local_unlock_irqrestore() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 071a1d6a6e14d0dec240a8c67b425140d7f92f6a ] + +The comment about local_lock_irqsave() mentions just the counters and +css_put_many()'s callback just invokes a worker so it is safe to move the +unlock function after memcg_check_events() so css_put_many() can be invoked +without the lock acquired. + +Cc: Daniel Wagner <wagi@monom.org> +Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +[bigeasy: rewrote the patch description] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + mm/memcontrol.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/mm/memcontrol.c b/mm/memcontrol.c +index 239fec6eac9f..d5bda1449fe3 100644 +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -6541,10 +6541,10 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) + mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), + -nr_entries); + memcg_check_events(memcg, page); ++ local_unlock_irqrestore(event_lock, flags); + + if (!mem_cgroup_is_root(memcg)) + css_put_many(&memcg->css, nr_entries); +- local_unlock_irqrestore(event_lock, flags); + } + + /** +-- +2.36.1 + diff --git a/debian/patches-rt/0319-locallock-Include-header-for-the-current-macro.patch b/debian/patches-rt/0319-locallock-Include-header-for-the-current-macro.patch new file mode 100644 index 000000000..ca93285f9 --- /dev/null +++ b/debian/patches-rt/0319-locallock-Include-header-for-the-current-macro.patch @@ -0,0 +1,32 @@ +From b075c120b3110dd2e9ef474ece2f4aade2d0a10c Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 4 Feb 2020 13:29:50 +0100 +Subject: [PATCH 319/347] locallock: Include header for the `current' macro +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit e693075a5fd852043fa8d2b0467e078d9e5cb782 ] + +Include the header for `current' macro so that +CONFIG_KERNEL_HEADER_TEST=y passes. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + include/linux/locallock.h | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/include/linux/locallock.h b/include/linux/locallock.h +index 921eab83cd34..81c89d87723b 100644 +--- a/include/linux/locallock.h ++++ b/include/linux/locallock.h +@@ -3,6 +3,7 @@ + + #include <linux/percpu.h> + #include <linux/spinlock.h> ++#include <asm/current.h> + + #ifdef CONFIG_PREEMPT_RT_BASE + +-- +2.36.1 + diff --git a/debian/patches-rt/0320-drm-vmwgfx-Drop-preempt_disable-in-vmw_fifo_ping_hos.patch b/debian/patches-rt/0320-drm-vmwgfx-Drop-preempt_disable-in-vmw_fifo_ping_hos.patch new file mode 100644 index 000000000..2dc30fc19 --- /dev/null +++ b/debian/patches-rt/0320-drm-vmwgfx-Drop-preempt_disable-in-vmw_fifo_ping_hos.patch @@ -0,0 +1,45 @@ +From fc0f8480da7d2d5927404e67031daba0ca53a1a2 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 21 Feb 2020 18:57:11 +0100 +Subject: [PATCH 320/347] drm/vmwgfx: Drop preempt_disable() in + vmw_fifo_ping_host() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit b901491e7b9b7a676818d84e482b69be72fc142f ] + +vmw_fifo_ping_host() disables preemption around a test and a register +write via vmw_write(). The write function acquires a spinlock_t typed +lock which is not allowed in a preempt_disable()ed section on +PREEMPT_RT. This has been reported in the bugzilla. + +It has been explained by Thomas Hellstrom that this preempt_disable()ed +section is not required for correctness. + +Remove the preempt_disable() section. + +Link: https://bugzilla.kernel.org/show_bug.cgi?id=206591 +Link: https://lkml.kernel.org/r/0b5e1c65d89951de993deab06d1d197b40fd67aa.camel@vmware.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c | 2 -- + 1 file changed, 2 deletions(-) + +diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +index d0fd147ef75f..fb5a3461bb8c 100644 +--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c ++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +@@ -167,10 +167,8 @@ void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason) + { + u32 *fifo_mem = dev_priv->mmio_virt; + +- preempt_disable(); + if (cmpxchg(fifo_mem + SVGA_FIFO_BUSY, 0, 1) == 0) + vmw_write(dev_priv, SVGA_REG_SYNC, reason); +- preempt_enable(); + } + + void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) +-- +2.36.1 + diff --git a/debian/patches-rt/0321-tracing-make-preempt_lazy-and-migrate_disable-counte.patch b/debian/patches-rt/0321-tracing-make-preempt_lazy-and-migrate_disable-counte.patch new file mode 100644 index 000000000..937b26b3c --- /dev/null +++ b/debian/patches-rt/0321-tracing-make-preempt_lazy-and-migrate_disable-counte.patch @@ -0,0 +1,56 @@ +From 8f58969bec3bc125c8257b4aea667ebb352cc73a Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 21 Feb 2020 18:15:15 +0100 +Subject: [PATCH 321/347] tracing: make preempt_lazy and migrate_disable + counter smaller +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit dd430bf5ecb40f9a89679c85868826475d71de54 ] + +The migrate_disable counter should not exceed 255 so it is enough to +store it in an 8bit field. +With this change we can move the `preempt_lazy_count' member into the +gap so the whole struct shrinks by 4 bytes to 12 bytes in total. +Remove the `padding' field, it is not needed. +Update the tracing fields in trace_define_common_fields() (it was +missing the preempt_lazy_count field). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + include/linux/trace_events.h | 3 +-- + kernel/trace/trace_events.c | 4 ++-- + 2 files changed, 3 insertions(+), 4 deletions(-) + +diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h +index 72864a11cec0..e26a85c1b7ba 100644 +--- a/include/linux/trace_events.h ++++ b/include/linux/trace_events.h +@@ -62,8 +62,7 @@ struct trace_entry { + unsigned char flags; + unsigned char preempt_count; + int pid; +- unsigned short migrate_disable; +- unsigned short padding; ++ unsigned char migrate_disable; + unsigned char preempt_lazy_count; + }; + +diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c +index fbb04cf1d5bc..9b1b1c6de2bd 100644 +--- a/kernel/trace/trace_events.c ++++ b/kernel/trace/trace_events.c +@@ -188,8 +188,8 @@ static int trace_define_common_fields(void) + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); +- __common_field(unsigned short, migrate_disable); +- __common_field(unsigned short, padding); ++ __common_field(unsigned char, migrate_disable); ++ __common_field(unsigned char, preempt_lazy_count); + + return ret; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0322-lib-ubsan-Remove-flags-parameter-from-calls-to-ubsan.patch b/debian/patches-rt/0322-lib-ubsan-Remove-flags-parameter-from-calls-to-ubsan.patch new file mode 100644 index 000000000..709e7d601 --- /dev/null +++ b/debian/patches-rt/0322-lib-ubsan-Remove-flags-parameter-from-calls-to-ubsan.patch @@ -0,0 +1,57 @@ +From d107484fb77558e58c28e33e5642d7a11f05dfea Mon Sep 17 00:00:00 2001 +From: Tiejun Chen <tiejunc@vmware.com> +Date: Mon, 30 Mar 2020 18:45:23 -0400 +Subject: [PATCH 322/347] lib/ubsan: Remove flags parameter from calls to + ubsan_prologue() and ubsan_epilogue() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Fails to build with CONFIG_UBSAN=y + +lib/ubsan.c: In function '__ubsan_handle_vla_bound_not_positive': +lib/ubsan.c:348:2: error: too many arguments to function 'ubsan_prologue' + ubsan_prologue(&data->location, &flags); + ^~~~~~~~~~~~~~ +lib/ubsan.c:146:13: note: declared here + static void ubsan_prologue(struct source_location *location) + ^~~~~~~~~~~~~~ +lib/ubsan.c:353:2: error: too many arguments to function 'ubsan_epilogue' + ubsan_epilogue(&flags); + ^~~~~~~~~~~~~~ +lib/ubsan.c:155:13: note: declared here + static void ubsan_epilogue(void) + ^~~~~~~~~~~~~~ + +Signed-off-by: Tiejun Chen <tiejunc@vmware.com> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + lib/ubsan.c | 5 ++--- + 1 file changed, 2 insertions(+), 3 deletions(-) + +diff --git a/lib/ubsan.c b/lib/ubsan.c +index 5830cc9a2164..199c75e03469 100644 +--- a/lib/ubsan.c ++++ b/lib/ubsan.c +@@ -339,18 +339,17 @@ EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1); + void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data, + void *bound) + { +- unsigned long flags; + char bound_str[VALUE_LENGTH]; + + if (suppress_report(&data->location)) + return; + +- ubsan_prologue(&data->location, &flags); ++ ubsan_prologue(&data->location); + + val_to_string(bound_str, sizeof(bound_str), data->type, bound); + pr_err("variable length array bound value %s <= 0\n", bound_str); + +- ubsan_epilogue(&flags); ++ ubsan_epilogue(); + } + EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive); + +-- +2.36.1 + diff --git a/debian/patches-rt/0323-irq_work-Fix-checking-of-IRQ_WORK_LAZY-flag-set-on-n.patch b/debian/patches-rt/0323-irq_work-Fix-checking-of-IRQ_WORK_LAZY-flag-set-on-n.patch new file mode 100644 index 000000000..972bc210f --- /dev/null +++ b/debian/patches-rt/0323-irq_work-Fix-checking-of-IRQ_WORK_LAZY-flag-set-on-n.patch @@ -0,0 +1,72 @@ +From 5b50540220e8d385682175fbc0b355e38289bbac Mon Sep 17 00:00:00 2001 +From: "Steven Rostedt (VMware)" <rostedt@goodmis.org> +Date: Sun, 22 Mar 2020 00:00:28 +0100 +Subject: [PATCH 323/347] irq_work: Fix checking of IRQ_WORK_LAZY flag set on + non PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +When CONFIG_PREEMPT_RT_FULL is not set, some of the checks for using +lazy_list are not properly made as the IRQ_WORK_LAZY is not checked. There's +two locations that need this update, so a use_lazy_list() helper function is +added and used in both locations. + +Link: https://lore.kernel.org/r/20200321230028.GA22058@duo.ucw.cz +Reported-by: Pavel Machek <pavel@denx.de> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +--- + kernel/irq_work.c | 15 ++++++++------- + 1 file changed, 8 insertions(+), 7 deletions(-) + +diff --git a/kernel/irq_work.c b/kernel/irq_work.c +index 2940622da5b3..b6d9d35941ac 100644 +--- a/kernel/irq_work.c ++++ b/kernel/irq_work.c +@@ -70,6 +70,12 @@ static void __irq_work_queue_local(struct irq_work *work, struct llist_head *lis + arch_irq_work_raise(); + } + ++static inline bool use_lazy_list(struct irq_work *work) ++{ ++ return (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ || (work->flags & IRQ_WORK_LAZY); ++} ++ + /* Enqueue the irq work @work on the current CPU */ + bool irq_work_queue(struct irq_work *work) + { +@@ -81,11 +87,10 @@ bool irq_work_queue(struct irq_work *work) + + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); +- if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ if (use_lazy_list(work)) + list = this_cpu_ptr(&lazy_list); + else + list = this_cpu_ptr(&raised_list); +- + __irq_work_queue_local(work, list); + preempt_enable(); + +@@ -106,7 +111,6 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) + + #else /* CONFIG_SMP: */ + struct llist_head *list; +- bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); +@@ -116,10 +120,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) + return false; + + preempt_disable(); +- +- lazy_work = work->flags & IRQ_WORK_LAZY; +- +- if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) ++ if (use_lazy_list(work)) + list = &per_cpu(lazy_list, cpu); + else + list = &per_cpu(raised_list, cpu); +-- +2.36.1 + diff --git a/debian/patches-rt/0324-tasklet-Address-a-race-resulting-in-double-enqueue.patch b/debian/patches-rt/0324-tasklet-Address-a-race-resulting-in-double-enqueue.patch new file mode 100644 index 000000000..70a6d70cb --- /dev/null +++ b/debian/patches-rt/0324-tasklet-Address-a-race-resulting-in-double-enqueue.patch @@ -0,0 +1,120 @@ +From f9bcdc9de0ced2b99b351e226344eb1c0246dd5c Mon Sep 17 00:00:00 2001 +From: Zhang Xiao <xiao.zhang@windriver.com> +Date: Tue, 17 Mar 2020 12:47:43 +0100 +Subject: [PATCH 324/347] tasklet: Address a race resulting in double-enqueue +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The kernel bugzilla has the following race condition reported: + +CPU0 CPU1 CPU2 +------------------------------------------------ +test_set SCHED + test_set RUN + if SCHED + add_list + raise + clear RUN +<softirq> +test_set RUN +test_clear SCHED + ->func + test_set SCHED +tasklet_try_unlock ->0 +test_clear SCHED + test_set SCHED + ->func +tasklet_try_unlock ->1 + test_set RUN + if SCHED + add list + raise + clear RUN + test_set RUN + if SCHED + add list + raise + clear RUN + +As a result the tasklet is enqueued on both CPUs and run on both CPUs. Due +to the nature of the list used here, it is possible that further +(different) tasklets, which are enqueued after this double-enqueued +tasklet, are scheduled on CPU2 but invoked on CPU1. It is also possible +that these tasklets won't be invoked at all, because during the second +enqueue process the t->next pointer is set to NULL - dropping everything +from the list. + +This race will trigger one or two of the WARN_ON() in +tasklet_action_common(). +The problem is that the tasklet may be invoked multiple times and clear +SCHED bit on each invocation. This makes it possible to enqueue the +very same tasklet on different CPUs. + +Current RT-devel is using the upstream implementation which does not +re-run tasklets if they have SCHED set again and so it does not clear +the SCHED bit multiple times on a single invocation. + +Introduce the CHAINED flag. The tasklet will only be enqueued if the +CHAINED flag has been set successfully. +If it is possible to exchange the flags (CHAINED | RUN) -> 0 then the +tasklet won't be re-run. Otherwise the possible SCHED flag is removed +and the tasklet is re-run again. + +Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=61451 +Not-signed-off-by: Zhang Xiao <xiao.zhang@windriver.com> +[bigeasy: patch description] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> + +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + include/linux/interrupt.h | 5 ++++- + kernel/softirq.c | 6 +++++- + 2 files changed, 9 insertions(+), 2 deletions(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index 97d9ba26915e..a3b5edb26bc5 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -579,12 +579,15 @@ enum + { + TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ + TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ +- TASKLET_STATE_PENDING /* Tasklet is pending */ ++ TASKLET_STATE_PENDING, /* Tasklet is pending */ ++ TASKLET_STATE_CHAINED /* Tasklet is chained */ + }; + + #define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) + #define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) + #define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) ++#define TASKLET_STATEF_CHAINED (1 << TASKLET_STATE_CHAINED) ++#define TASKLET_STATEF_RC (TASKLET_STATEF_RUN | TASKLET_STATEF_CHAINED) + + #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static inline int tasklet_trylock(struct tasklet_struct *t) +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 25bcf2f2714b..73dae64bfc9c 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -947,6 +947,10 @@ static void __tasklet_schedule_common(struct tasklet_struct *t, + * is locked before adding it to the list. + */ + if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++ if (test_and_set_bit(TASKLET_STATE_CHAINED, &t->state)) { ++ tasklet_unlock(t); ++ return; ++ } + t->next = NULL; + *head->tail = t; + head->tail = &(t->next); +@@ -1040,7 +1044,7 @@ static void tasklet_action_common(struct softirq_action *a, + again: + t->func(t->data); + +- while (!tasklet_tryunlock(t)) { ++ while (cmpxchg(&t->state, TASKLET_STATEF_RC, 0) != TASKLET_STATEF_RC) { + /* + * If it got disabled meanwhile, bail out: + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0325-hrtimer-fix-logic-for-when-grabbing-softirq_expiry_l.patch b/debian/patches-rt/0325-hrtimer-fix-logic-for-when-grabbing-softirq_expiry_l.patch new file mode 100644 index 000000000..f84843891 --- /dev/null +++ b/debian/patches-rt/0325-hrtimer-fix-logic-for-when-grabbing-softirq_expiry_l.patch @@ -0,0 +1,50 @@ +From f3c5f444176119ec51e092dc9b9edea7a679c55e Mon Sep 17 00:00:00 2001 +From: Rasmus Villemoes <rasmus.villemoes@prevas.dk> +Date: Tue, 28 Apr 2020 16:40:26 +0200 +Subject: [PATCH 325/347] hrtimer: fix logic for when grabbing + softirq_expiry_lock can be elided +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Commit + + hrtimer: Add a missing bracket and hide `migration_base' on !SMP + +which is 47b6de0b7f22 in 5.2-rt and 40aae5708e7a in 4.19-rt, +inadvertently changed the logic from base != &migration_base to base +== &migration_base. + +On !CONFIG_SMP, the effect was to effectively always elide this +lock/unlock pair (since is_migration_base() is unconditionally false), +which for me consistently causes lockups during reboot, and reportedly +also often causes a hang during boot. + +Adding this logical negation (or, what is effectively the same thing +on !CONFIG_SMP, reverting the above commit as well as "hrtimer: +Prevent using hrtimer_grab_expiry_lock() on migration_base") fixes +that lockup. + +Fixes: 40aae5708e7a (hrtimer: Add a missing bracket and hide `migration_base' on !SMP) # 4.19-rt +Fixes: 47b6de0b7f22 (hrtimer: Add a missing bracket and hide `migration_base' on !SMP) # 5.2-rt +Signed-off-by: Rasmus Villemoes <rasmus.villemoes@prevas.dk> +Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + kernel/time/hrtimer.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 0f841f18c363..a84673149881 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -971,7 +971,7 @@ void hrtimer_grab_expiry_lock(const struct hrtimer *timer) + { + struct hrtimer_clock_base *base = READ_ONCE(timer->base); + +- if (timer->is_soft && is_migration_base(base)) { ++ if (timer->is_soft && !is_migration_base(base)) { + spin_lock(&base->cpu_base->softirq_expiry_lock); + spin_unlock(&base->cpu_base->softirq_expiry_lock); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0326-fs-dcache-Include-swait.h-header.patch b/debian/patches-rt/0326-fs-dcache-Include-swait.h-header.patch new file mode 100644 index 000000000..b1408b268 --- /dev/null +++ b/debian/patches-rt/0326-fs-dcache-Include-swait.h-header.patch @@ -0,0 +1,36 @@ +From ff692653d0de39bf90f5a339c17c880b5afa0777 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 16 Apr 2020 12:42:15 +0200 +Subject: [PATCH 326/347] fs/dcache: Include swait.h header +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 279f90ddf53cd6bd3c203fbbf488d642ea2603de ] + +Include the swait.h header so it compiles even if not all patches are +applied. + +Reported-by: kbuild test robot <lkp@intel.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> + + Conflicts: + fs/proc/base.c +--- + fs/proc/base.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/fs/proc/base.c b/fs/proc/base.c +index accc230079bb..8806344af241 100644 +--- a/fs/proc/base.c ++++ b/fs/proc/base.c +@@ -95,6 +95,7 @@ + #include <linux/flex_array.h> + #include <linux/posix-timers.h> + #include <trace/events/oom.h> ++#include <linux/swait.h> + #include "internal.h" + #include "fd.h" + +-- +2.36.1 + diff --git a/debian/patches-rt/0327-mm-slub-Always-flush-the-delayed-empty-slubs-in-flus.patch b/debian/patches-rt/0327-mm-slub-Always-flush-the-delayed-empty-slubs-in-flus.patch new file mode 100644 index 000000000..870ba009b --- /dev/null +++ b/debian/patches-rt/0327-mm-slub-Always-flush-the-delayed-empty-slubs-in-flus.patch @@ -0,0 +1,64 @@ +From b997a51c5b5970f8defda681658e94bb5612dd2f Mon Sep 17 00:00:00 2001 +From: Kevin Hao <haokexin@gmail.com> +Date: Mon, 4 May 2020 11:34:07 +0800 +Subject: [PATCH 327/347] mm: slub: Always flush the delayed empty slubs in + flush_all() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 23a2c31b19e99beaf5107071b0f32a596202cdae ] + +After commit f0b231101c94 ("mm/SLUB: delay giving back empty slubs to +IRQ enabled regions"), when the free_slab() is invoked with the IRQ +disabled, the empty slubs are moved to a per-CPU list and will be +freed after IRQ enabled later. But in the current codes, there is +a check to see if there really has the cpu slub on a specific cpu +before flushing the delayed empty slubs, this may cause a reference +of already released kmem_cache in a scenario like below: + cpu 0 cpu 1 + kmem_cache_destroy() + flush_all() + --->IPI flush_cpu_slab() + flush_slab() + deactivate_slab() + discard_slab() + free_slab() + c->page = NULL; + for_each_online_cpu(cpu) + if (!has_cpu_slab(1, s)) + continue + this skip to flush the delayed + empty slub released by cpu1 + kmem_cache_free(kmem_cache, s) + + kmalloc() + __slab_alloc() + free_delayed() + __free_slab() + reference to released kmem_cache + +Fixes: f0b231101c94 ("mm/SLUB: delay giving back empty slubs to IRQ enabled regions") +Signed-off-by: Kevin Hao <haokexin@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: stable-rt@vger.kernel.org +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + mm/slub.c | 3 --- + 1 file changed, 3 deletions(-) + +diff --git a/mm/slub.c b/mm/slub.c +index 3b1edb545215..497096152c39 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -2376,9 +2376,6 @@ static void flush_all(struct kmem_cache *s) + for_each_online_cpu(cpu) { + struct slub_free_list *f; + +- if (!has_cpu_slab(cpu, s)) +- continue; +- + f = &per_cpu(slub_free_list, cpu); + raw_spin_lock_irq(&f->lock); + list_splice_init(&f->list, &tofree); +-- +2.36.1 + diff --git a/debian/patches-rt/0328-tasklet-Fix-UP-case-for-tasklet-CHAINED-state.patch b/debian/patches-rt/0328-tasklet-Fix-UP-case-for-tasklet-CHAINED-state.patch new file mode 100644 index 000000000..704118247 --- /dev/null +++ b/debian/patches-rt/0328-tasklet-Fix-UP-case-for-tasklet-CHAINED-state.patch @@ -0,0 +1,56 @@ +From 562e557f31503bcd1d37d5979221e28bd0328786 Mon Sep 17 00:00:00 2001 +From: Tom Zanussi <zanussi@kernel.org> +Date: Tue, 9 Jun 2020 11:04:08 -0500 +Subject: [PATCH 328/347] tasklet: Fix UP case for tasklet CHAINED state +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +commit 62d0a2a30cd0 (tasklet: Address a race resulting in +double-enqueue) addresses a problem that can result in a tasklet being +enqueued on two cpus at the same time by combining the RUN flag with a +new CHAINED flag, and relies on the combination to be present in order +to zero it out, which can never happen on (!SMP and !PREEMPT_RT_FULL) +because the RUN flag is SMP/PREEMPT_RT_FULL-only. + +So make sure the above commit is only applied for the SMP || +PREEMPT_RT_FULL case. + +Fixes: 62d0a2a30cd0 ("tasklet: Address a race resulting in double-enqueue") +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +Reported-by: Ramon Fried <rfried.dev@gmail.com> +Tested-By: Ramon Fried <rfried.dev@gmail.com> +--- + kernel/softirq.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 73dae64bfc9c..9bad7a16dc61 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -947,10 +947,12 @@ static void __tasklet_schedule_common(struct tasklet_struct *t, + * is locked before adding it to the list. + */ + if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + if (test_and_set_bit(TASKLET_STATE_CHAINED, &t->state)) { + tasklet_unlock(t); + return; + } ++#endif + t->next = NULL; + *head->tail = t; + head->tail = &(t->next); +@@ -1044,7 +1046,11 @@ static void tasklet_action_common(struct softirq_action *a, + again: + t->func(t->data); + ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + while (cmpxchg(&t->state, TASKLET_STATEF_RC, 0) != TASKLET_STATEF_RC) { ++#else ++ while (!tasklet_tryunlock(t)) { ++#endif + /* + * If it got disabled meanwhile, bail out: + */ +-- +2.36.1 + diff --git a/debian/patches-rt/0329-signal-Prevent-double-free-of-user-struct.patch b/debian/patches-rt/0329-signal-Prevent-double-free-of-user-struct.patch new file mode 100644 index 000000000..253dc5c91 --- /dev/null +++ b/debian/patches-rt/0329-signal-Prevent-double-free-of-user-struct.patch @@ -0,0 +1,55 @@ +From a99e09659e6cd4b633c3689f2c3aa5f8a816fe5b Mon Sep 17 00:00:00 2001 +From: Matt Fleming <matt@codeblueprint.co.uk> +Date: Tue, 7 Apr 2020 10:54:13 +0100 +Subject: [PATCH 329/347] signal: Prevent double-free of user struct +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upsteam commit 9567db2ebe566a93485e1a27d8759969d0002d7a ] + +The way user struct reference counting works changed significantly with, + + fda31c50292a ("signal: avoid double atomic counter increments for user accounting") + +Now user structs are only freed once the last pending signal is +dequeued. Make sigqueue_free_current() follow this new convention to +avoid freeing the user struct multiple times and triggering this +warning: + + refcount_t: underflow; use-after-free. + WARNING: CPU: 0 PID: 6794 at lib/refcount.c:288 refcount_dec_not_one+0x45/0x50 + Call Trace: + refcount_dec_and_lock_irqsave+0x16/0x60 + free_uid+0x31/0xa0 + __dequeue_signal+0x17c/0x190 + dequeue_signal+0x5a/0x1b0 + do_sigtimedwait+0x208/0x250 + __x64_sys_rt_sigtimedwait+0x6f/0xd0 + do_syscall_64+0x72/0x200 + entry_SYSCALL_64_after_hwframe+0x49/0xbe + +Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> +Reported-by: Daniel Wagner <wagi@monom.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + kernel/signal.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/kernel/signal.c b/kernel/signal.c +index 74f807bba0b8..59294dfaa744 100644 +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -489,8 +489,8 @@ static void sigqueue_free_current(struct sigqueue *q) + + up = q->user; + if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { +- atomic_dec(&up->sigpending); +- free_uid(up); ++ if (atomic_dec_and_test(&up->sigpending)) ++ free_uid(up); + } else + __sigqueue_free(q); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0330-Bluetooth-Acquire-sk_lock.slock-without-disabling-in.patch b/debian/patches-rt/0330-Bluetooth-Acquire-sk_lock.slock-without-disabling-in.patch new file mode 100644 index 000000000..ff8d39cfc --- /dev/null +++ b/debian/patches-rt/0330-Bluetooth-Acquire-sk_lock.slock-without-disabling-in.patch @@ -0,0 +1,65 @@ +From ba289a24015e6e110bcc57dad832a8094be6b955 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 28 May 2020 14:35:12 +0200 +Subject: [PATCH 330/347] Bluetooth: Acquire sk_lock.slock without disabling + interrupts +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit e6da0edc24eecef2f6964d92fa9044e1821deace ] + +There was a lockdep which led to commit + fad003b6c8e3d ("Bluetooth: Fix inconsistent lock state with RFCOMM") + +Lockdep noticed that `sk->sk_lock.slock' was acquired without disabling +the softirq while the lock was also used in softirq context. +Unfortunately the solution back then was to disable interrupts before +acquiring the lock which however made lockdep happy. +It would have been enough to simply disable the softirq. Disabling +interrupts before acquiring a spinlock_t is not allowed on PREEMPT_RT +because these locks are converted to 'sleeping' spinlocks. + +Use spin_lock_bh() in order to acquire the `sk_lock.slock'. + +Reported-by: Luis Claudio R. Goncalves <lclaudio@uudg.org> +Reported-by: kbuild test robot <lkp@intel.com> [missing unlock] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Marcel Holtmann <marcel@holtmann.org> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + net/bluetooth/rfcomm/sock.c | 7 ++----- + 1 file changed, 2 insertions(+), 5 deletions(-) + +diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c +index c044ff2f73e6..75bc8102cdd7 100644 +--- a/net/bluetooth/rfcomm/sock.c ++++ b/net/bluetooth/rfcomm/sock.c +@@ -64,15 +64,13 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb) + static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) + { + struct sock *sk = d->owner, *parent; +- unsigned long flags; + + if (!sk) + return; + + BT_DBG("dlc %p state %ld err %d", d, d->state, err); + +- local_irq_save(flags); +- bh_lock_sock(sk); ++ spin_lock_bh(&sk->sk_lock.slock); + + if (err) + sk->sk_err = err; +@@ -93,8 +91,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) + sk->sk_state_change(sk); + } + +- bh_unlock_sock(sk); +- local_irq_restore(flags); ++ spin_unlock_bh(&sk->sk_lock.slock); + + if (parent && sock_flag(sk, SOCK_ZAPPED)) { + /* We have to drop DLC lock here, otherwise +-- +2.36.1 + diff --git a/debian/patches-rt/0331-net-phy-fixed_phy-Remove-unused-seqcount.patch b/debian/patches-rt/0331-net-phy-fixed_phy-Remove-unused-seqcount.patch new file mode 100644 index 000000000..ceacf6b1e --- /dev/null +++ b/debian/patches-rt/0331-net-phy-fixed_phy-Remove-unused-seqcount.patch @@ -0,0 +1,89 @@ +From 1d956b22e273e7a1ce90b54cd84598e1a427f3f2 Mon Sep 17 00:00:00 2001 +From: "Ahmed S. Darwish" <a.darwish@linutronix.de> +Date: Wed, 10 Jun 2020 12:53:00 +0200 +Subject: [PATCH 331/347] net: phy: fixed_phy: Remove unused seqcount +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 6554eac9ef2bd1c968886b31cc7266b49258a463 ] + +Commit bf7afb29d545 ("phy: improve safety of fixed-phy MII register +reading") protected the fixed PHY status with a sequence counter. + +Two years later, commit d2b977939b18 ("net: phy: fixed-phy: remove +fixed_phy_update_state()") removed the sequence counter's write side +critical section -- neutralizing its read side retry loop. + +Remove the unused seqcount. + +Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de> +Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reviewed-by: Andrew Lunn <andrew@lunn.ch> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from v5.8-rc1 commit 79cbb6bc3332da7162c2581e151659ab8ebaa528) +Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + drivers/net/phy/fixed_phy.c | 25 +++++++++---------------- + 1 file changed, 9 insertions(+), 16 deletions(-) + +diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c +index 59820164502e..953ff54dd5df 100644 +--- a/drivers/net/phy/fixed_phy.c ++++ b/drivers/net/phy/fixed_phy.c +@@ -23,7 +23,6 @@ + #include <linux/slab.h> + #include <linux/of.h> + #include <linux/gpio.h> +-#include <linux/seqlock.h> + #include <linux/idr.h> + + #include "swphy.h" +@@ -36,7 +35,6 @@ struct fixed_mdio_bus { + struct fixed_phy { + int addr; + struct phy_device *phydev; +- seqcount_t seqcount; + struct fixed_phy_status status; + int (*link_update)(struct net_device *, struct fixed_phy_status *); + struct list_head node; +@@ -62,18 +60,15 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num) + list_for_each_entry(fp, &fmb->phys, node) { + if (fp->addr == phy_addr) { + struct fixed_phy_status state; +- int s; +- +- do { +- s = read_seqcount_begin(&fp->seqcount); +- /* Issue callback if user registered it. */ +- if (fp->link_update) +- fp->link_update(fp->phydev->attached_dev, +- &fp->status); +- /* Check the GPIO for change in status */ +- fixed_phy_update(fp); +- state = fp->status; +- } while (read_seqcount_retry(&fp->seqcount, s)); ++ ++ /* Issue callback if user registered it. */ ++ if (fp->link_update) ++ fp->link_update(fp->phydev->attached_dev, ++ &fp->status); ++ ++ /* Check the GPIO for change in status */ ++ fixed_phy_update(fp); ++ state = fp->status; + + return swphy_read_reg(reg_num, &state); + } +@@ -131,8 +126,6 @@ int fixed_phy_add(unsigned int irq, int phy_addr, + if (!fp) + return -ENOMEM; + +- seqcount_init(&fp->seqcount); +- + if (irq != PHY_POLL) + fmb->mii_bus->irq[phy_addr] = irq; + +-- +2.36.1 + diff --git a/debian/patches-rt/0332-net-xfrm-fix-compress-vs-decompress-serialization.patch b/debian/patches-rt/0332-net-xfrm-fix-compress-vs-decompress-serialization.patch new file mode 100644 index 000000000..23117039c --- /dev/null +++ b/debian/patches-rt/0332-net-xfrm-fix-compress-vs-decompress-serialization.patch @@ -0,0 +1,102 @@ +From 502a0ae30b2c2d53fde16d55fe8ae20312d4b520 Mon Sep 17 00:00:00 2001 +From: Davidlohr Bueso <dave@stgolabs.net> +Date: Tue, 18 Aug 2020 09:20:53 -0700 +Subject: [PATCH 332/347] net: xfrm: fix compress vs decompress serialization +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +A crash was seen in xfrm when running ltp's 'tcp4_ipsec06' stresser on v4.x +based RT kernels. + +ipcomp_compress() will serialize access to the ipcomp_scratches percpu buffer by +disabling BH and preventing a softirq from coming in and running ipcom_decompress(), +which is never called from process context. This of course won't work on RT and +the buffer can get corrupted; there have been similar issues with in the past with +such assumptions, ie: ebf255ed6c44 (net: add back the missing serialization in +ip_send_unicast_reply()). + +Similarly, this patch addresses the issue with locallocks allowing RT to have a +percpu spinlock and do the correct serialization. + +Signed-off-by: Davidlohr Bueso <dbueso@suse.de> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + net/xfrm/xfrm_ipcomp.c | 21 +++++++++++++++------ + 1 file changed, 15 insertions(+), 6 deletions(-) + +diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c +index a00ec715aa46..a97997385423 100644 +--- a/net/xfrm/xfrm_ipcomp.c ++++ b/net/xfrm/xfrm_ipcomp.c +@@ -20,6 +20,7 @@ + #include <linux/list.h> + #include <linux/module.h> + #include <linux/mutex.h> ++#include <linux/locallock.h> + #include <linux/percpu.h> + #include <linux/slab.h> + #include <linux/smp.h> +@@ -36,6 +37,7 @@ struct ipcomp_tfms { + + static DEFINE_MUTEX(ipcomp_resource_mutex); + static void * __percpu *ipcomp_scratches; ++static DEFINE_LOCAL_IRQ_LOCK(ipcomp_scratches_lock); + static int ipcomp_scratch_users; + static LIST_HEAD(ipcomp_tfms_list); + +@@ -45,12 +47,15 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) + const int plen = skb->len; + int dlen = IPCOMP_SCRATCH_SIZE; + const u8 *start = skb->data; +- const int cpu = get_cpu(); +- u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); +- struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); +- int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); +- int len; ++ u8 *scratch; ++ struct crypto_comp *tfm; ++ int err, len; ++ ++ local_lock(ipcomp_scratches_lock); + ++ scratch = *this_cpu_ptr(ipcomp_scratches); ++ tfm = *this_cpu_ptr(ipcd->tfms); ++ err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); + if (err) + goto out; + +@@ -103,7 +108,7 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) + err = 0; + + out: +- put_cpu(); ++ local_unlock(ipcomp_scratches_lock); + return err; + } + +@@ -146,6 +151,8 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) + int err; + + local_bh_disable(); ++ local_lock(ipcomp_scratches_lock); ++ + scratch = *this_cpu_ptr(ipcomp_scratches); + tfm = *this_cpu_ptr(ipcd->tfms); + err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); +@@ -158,12 +165,14 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) + } + + memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); ++ local_unlock(ipcomp_scratches_lock); + local_bh_enable(); + + pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); + return 0; + + out: ++ local_unlock(ipcomp_scratches_lock); + local_bh_enable(); + return err; + } +-- +2.36.1 + diff --git a/debian/patches-rt/0333-mm-memcontrol-Disable-preemption-in-__mod_memcg_lruv.patch b/debian/patches-rt/0333-mm-memcontrol-Disable-preemption-in-__mod_memcg_lruv.patch new file mode 100644 index 000000000..8c05dc952 --- /dev/null +++ b/debian/patches-rt/0333-mm-memcontrol-Disable-preemption-in-__mod_memcg_lruv.patch @@ -0,0 +1,50 @@ +From 5e6613efc5bd79951fdfab9ce61217ba8480a0bc Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 28 Oct 2020 18:15:32 +0100 +Subject: [PATCH 333/347] mm/memcontrol: Disable preemption in + __mod_memcg_lruvec_state() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 74858f0d38a8d3c069a0745ff53ae084c8e7cabb ] + +The callers expect disabled preemption/interrupts while invoking +__mod_memcg_lruvec_state(). This works mainline because a lock of +somekind is acquired. + +Use preempt_disable_rt() where per-CPU variables are accessed and a +stable pointer is expected. This is also done in __mod_zone_page_state() +for the same reason. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Tom Zanussi <zanussi@kernel.org> + + Conflicts: + mm/memcontrol.c +--- + include/linux/memcontrol.h | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h +index cc6b6532eb56..dbb2c4e27277 100644 +--- a/include/linux/memcontrol.h ++++ b/include/linux/memcontrol.h +@@ -665,6 +665,7 @@ static inline void __mod_lruvec_state(struct lruvec *lruvec, + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + ++ preempt_disable_rt(); + /* Update memcg */ + __mod_memcg_state(pn->memcg, idx, val); + +@@ -675,6 +676,7 @@ static inline void __mod_lruvec_state(struct lruvec *lruvec, + x = 0; + } + __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x); ++ preempt_enable_rt(); + } + + static inline void mod_lruvec_state(struct lruvec *lruvec, +-- +2.36.1 + diff --git a/debian/patches-rt/0334-ptrace-fix-ptrace_unfreeze_traced-race-with-rt-lock.patch b/debian/patches-rt/0334-ptrace-fix-ptrace_unfreeze_traced-race-with-rt-lock.patch new file mode 100644 index 000000000..ab3bf14d5 --- /dev/null +++ b/debian/patches-rt/0334-ptrace-fix-ptrace_unfreeze_traced-race-with-rt-lock.patch @@ -0,0 +1,68 @@ +From a888cf3e5934c79d8edfca69dfe7fbe8f52c7476 Mon Sep 17 00:00:00 2001 +From: Oleg Nesterov <oleg@redhat.com> +Date: Tue, 3 Nov 2020 12:39:01 +0100 +Subject: [PATCH 334/347] ptrace: fix ptrace_unfreeze_traced() race with + rt-lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +[ Upstream commit 0fdc91971b34cf6857b4cfd8c322ae936cfc189b ] + +The patch "ptrace: fix ptrace vs tasklist_lock race" changed +ptrace_freeze_traced() to take task->saved_state into account, but +ptrace_unfreeze_traced() has the same problem and needs a similar fix: +it should check/update both ->state and ->saved_state. + +Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com> +Fixes: "ptrace: fix ptrace vs tasklist_lock race" +Signed-off-by: Oleg Nesterov <oleg@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: stable-rt@vger.kernel.org +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +--- + kernel/ptrace.c | 23 +++++++++++++++-------- + 1 file changed, 15 insertions(+), 8 deletions(-) + +diff --git a/kernel/ptrace.c b/kernel/ptrace.c +index 9c59e523f3cd..b7d2a22534da 100644 +--- a/kernel/ptrace.c ++++ b/kernel/ptrace.c +@@ -207,8 +207,8 @@ static bool ptrace_freeze_traced(struct task_struct *task) + + static void ptrace_unfreeze_traced(struct task_struct *task) + { +- if (task->state != __TASK_TRACED) +- return; ++ unsigned long flags; ++ bool frozen = true; + + WARN_ON(!task->ptrace || task->parent != current); + +@@ -217,12 +217,19 @@ static void ptrace_unfreeze_traced(struct task_struct *task) + * Recheck state under the lock to close this race. + */ + spin_lock_irq(&task->sighand->siglock); +- if (task->state == __TASK_TRACED) { +- if (__fatal_signal_pending(task)) +- wake_up_state(task, __TASK_TRACED); +- else +- task->state = TASK_TRACED; +- } ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ if (task->state == __TASK_TRACED) ++ task->state = TASK_TRACED; ++ else if (task->saved_state == __TASK_TRACED) ++ task->saved_state = TASK_TRACED; ++ else ++ frozen = false; ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ ++ if (frozen && __fatal_signal_pending(task)) ++ wake_up_state(task, __TASK_TRACED); ++ + spin_unlock_irq(&task->sighand->siglock); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0335-Linux-4.19.185-rt76-REBASE.patch b/debian/patches-rt/0335-Linux-4.19.185-rt76-REBASE.patch new file mode 100644 index 000000000..d38a3565e --- /dev/null +++ b/debian/patches-rt/0335-Linux-4.19.185-rt76-REBASE.patch @@ -0,0 +1,21 @@ +From 6142a4642e9bcfd6fbbaf6cddd32841755deff8b Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Mon, 12 Apr 2021 15:03:55 -0500 +Subject: [PATCH 335/347] Linux 4.19.185-rt76 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Clark Williams <williams@redhat.com> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index 1199ebade17b..c1f2720eaf25 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt16 ++-rt76 +-- +2.36.1 + diff --git a/debian/patches-rt/0336-mm-slub-Don-t-resize-the-location-tracking-cache-on-.patch b/debian/patches-rt/0336-mm-slub-Don-t-resize-the-location-tracking-cache-on-.patch new file mode 100644 index 000000000..eaf171957 --- /dev/null +++ b/debian/patches-rt/0336-mm-slub-Don-t-resize-the-location-tracking-cache-on-.patch @@ -0,0 +1,38 @@ +From 4da7dd5c5195e9f48a911e768ca8bd317f5c6b7f Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 26 Feb 2021 17:26:04 +0100 +Subject: [PATCH 336/347] mm: slub: Don't resize the location tracking cache on + PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The location tracking cache has a size of a page and is resized if its +current size is too small. +This allocation happens with disabled interrupts and can't happen on +PREEMPT_RT. +Should one page be too small, then we have to allocate more at the +beginning. The only downside is that less callers will be visible. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +(cherry picked from commit 87bd0bf324f4c5468ea3d1de0482589f491f3145) +Signed-off-by: Clark Williams <williams@redhat.com> +--- + mm/slub.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/mm/slub.c b/mm/slub.c +index 497096152c39..6b9b894ba5bc 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -4591,6 +4591,9 @@ static int alloc_loc_track(struct loc_track *t, unsigned long max, gfp_t flags) + struct location *l; + int order; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT) && flags == GFP_ATOMIC) ++ return 0; ++ + order = get_order(sizeof(struct location) * max); + + l = (void *)__get_free_pages(flags, order); +-- +2.36.1 + diff --git a/debian/patches-rt/0337-locking-rwsem_rt-Add-__down_read_interruptible.patch b/debian/patches-rt/0337-locking-rwsem_rt-Add-__down_read_interruptible.patch new file mode 100644 index 000000000..32dbf855c --- /dev/null +++ b/debian/patches-rt/0337-locking-rwsem_rt-Add-__down_read_interruptible.patch @@ -0,0 +1,54 @@ +From 22e1c0d3e27bd960ae3561172ca15089721253c6 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 19 Jan 2021 18:54:33 +0100 +Subject: [PATCH 337/347] locking/rwsem_rt: Add __down_read_interruptible() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The stable backported a patch which adds __down_read_interruptible() for +the generic rwsem implementation. + +Add RT's version __down_read_interruptible(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/rwsem_rt.h | 1 + + kernel/locking/rwsem-rt.c | 11 +++++++++++ + 2 files changed, 12 insertions(+) + +diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h +index 2018ff77904a..3fb092b7bcc0 100644 +--- a/include/linux/rwsem_rt.h ++++ b/include/linux/rwsem_rt.h +@@ -56,6 +56,7 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) + } + + extern void __down_read(struct rw_semaphore *sem); ++extern int __down_read_interruptible(struct rw_semaphore *sem); + extern int __down_read_killable(struct rw_semaphore *sem); + extern int __down_read_trylock(struct rw_semaphore *sem); + extern void __down_write(struct rw_semaphore *sem); +diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c +index f518495bd6cc..19ea20be3fd7 100644 +--- a/kernel/locking/rwsem-rt.c ++++ b/kernel/locking/rwsem-rt.c +@@ -166,6 +166,17 @@ void __down_read(struct rw_semaphore *sem) + WARN_ON_ONCE(ret); + } + ++int __down_read_interruptible(struct rw_semaphore *sem) ++{ ++ int ret; ++ ++ ret = __down_read_common(sem, TASK_INTERRUPTIBLE); ++ if (likely(!ret)) ++ return ret; ++ WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret); ++ return -EINTR; ++} ++ + int __down_read_killable(struct rw_semaphore *sem) + { + int ret; +-- +2.36.1 + diff --git a/debian/patches-rt/0338-Linux-4.19.206-rt87-REBASE.patch b/debian/patches-rt/0338-Linux-4.19.206-rt87-REBASE.patch new file mode 100644 index 000000000..eb89fd8dd --- /dev/null +++ b/debian/patches-rt/0338-Linux-4.19.206-rt87-REBASE.patch @@ -0,0 +1,21 @@ +From de4f10a80cbe40566ab9124766a9dce2d30fc651 Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Fri, 3 Sep 2021 10:24:35 -0500 +Subject: [PATCH 338/347] Linux 4.19.206-rt87 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Clark Williams <williams@redhat.com> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index c1f2720eaf25..bd5aee366a48 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt76 ++-rt87 +-- +2.36.1 + diff --git a/debian/patches-rt/0339-locking-rwsem-rt-Remove-might_sleep-in-__up_read.patch b/debian/patches-rt/0339-locking-rwsem-rt-Remove-might_sleep-in-__up_read.patch new file mode 100644 index 000000000..3edc4a486 --- /dev/null +++ b/debian/patches-rt/0339-locking-rwsem-rt-Remove-might_sleep-in-__up_read.patch @@ -0,0 +1,33 @@ +From 339b3a147a8e17bd3c87f9c9b16ad2c3d8e517c9 Mon Sep 17 00:00:00 2001 +From: Andrew Halaney <ahalaney@redhat.com> +Date: Tue, 6 Apr 2021 17:19:52 -0500 +Subject: [PATCH 339/347] locking/rwsem-rt: Remove might_sleep() in __up_read() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +There's no chance of sleeping here, the reader is giving up the +lock and possibly waking up the writer who is waiting on it. + +Reported-by: Chunyu Hu <chuhu@redhat.com> +Signed-off-by: Andrew Halaney <ahalaney@redhat.com> +Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> +(cherry picked from commit b2ed0a4302faf2bb09e97529dd274233c082689b) +Signed-off-by: Clark Williams <williams@redhat.com> +--- + kernel/locking/rwsem-rt.c | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c +index 19ea20be3fd7..966946454ced 100644 +--- a/kernel/locking/rwsem-rt.c ++++ b/kernel/locking/rwsem-rt.c +@@ -200,7 +200,6 @@ void __up_read(struct rw_semaphore *sem) + if (!atomic_dec_and_test(&sem->readers)) + return; + +- might_sleep(); + raw_spin_lock_irq(&m->wait_lock); + /* + * Wake the writer, i.e. the rtmutex owner. It might release the +-- +2.36.1 + diff --git a/debian/patches-rt/0340-Linux-4.19.214-rt93-REBASE.patch b/debian/patches-rt/0340-Linux-4.19.214-rt93-REBASE.patch new file mode 100644 index 000000000..2529b908a --- /dev/null +++ b/debian/patches-rt/0340-Linux-4.19.214-rt93-REBASE.patch @@ -0,0 +1,21 @@ +From 10fb3965169bb32da6eddef5672ba845f4dd3a67 Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Fri, 29 Oct 2021 09:49:56 -0500 +Subject: [PATCH 340/347] Linux 4.19.214-rt93 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Clark Williams <williams@redhat.com> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index bd5aee366a48..e98a1fe050bd 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt87 ++-rt93 +-- +2.36.1 + diff --git a/debian/patches-rt/0341-fscache-fix-initialisation-of-cookie-hash-table-raw-.patch b/debian/patches-rt/0341-fscache-fix-initialisation-of-cookie-hash-table-raw-.patch new file mode 100644 index 000000000..3be61a807 --- /dev/null +++ b/debian/patches-rt/0341-fscache-fix-initialisation-of-cookie-hash-table-raw-.patch @@ -0,0 +1,37 @@ +From dc029afd264318942ce9a174edffa950f762e7f9 Mon Sep 17 00:00:00 2001 +From: Gregor Beck <gbeck@esigma-technology.com> +Date: Fri, 3 Sep 2021 14:19:11 +0200 +Subject: [PATCH 341/347] fscache: fix initialisation of cookie hash table raw + spinlocks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The original patch, 602660600bcd ("fscache: initialize cookie hash +table raw spinlocks"), subtracted 1 from the shift and so still left +some spinlocks uninitialized. This fixes that. + +[zanussi: Added changelog text] + +Signed-off-by: Gregor Beck <gregor.beck@gmail.com> +Fixes: 602660600bcd ("fscache: initialize cookie hash table raw spinlocks") +Signed-off-by: Tom Zanussi <zanussi@kernel.org> +(cherry picked from commit 2cdede918a7b5f2b367e4839ad021e1d3b2479b1) +Signed-off-by: Clark Williams <williams@redhat.com> +--- + fs/fscache/cookie.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c +index b2b9a85a4ba5..84e57196a293 100644 +--- a/fs/fscache/cookie.c ++++ b/fs/fscache/cookie.c +@@ -955,6 +955,6 @@ void __init fscache_cookie_init(void) + { + int i; + +- for (i = 0; i < (1 << fscache_cookie_hash_shift) - 1; i++) ++ for (i = 0; i < ARRAY_SIZE(fscache_cookie_hash); i++) + INIT_HLIST_BL_HEAD(&fscache_cookie_hash[i]); + } +-- +2.36.1 + diff --git a/debian/patches-rt/0342-Linux-4.19.225-rt101-REBASE.patch b/debian/patches-rt/0342-Linux-4.19.225-rt101-REBASE.patch new file mode 100644 index 000000000..c8fb23eed --- /dev/null +++ b/debian/patches-rt/0342-Linux-4.19.225-rt101-REBASE.patch @@ -0,0 +1,21 @@ +From cc57b2b4fdc4b90708433ff46b962f99cbec2e6c Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Wed, 12 Jan 2022 21:43:37 -0600 +Subject: [PATCH 342/347] Linux 4.19.225-rt101 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Clark Williams <williams@redhat.com> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index e98a1fe050bd..9ea5981fa956 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt93 ++-rt101 +-- +2.36.1 + diff --git a/debian/patches-rt/0343-rt-PREEMPT_RT-safety-net-for-backported-patches.patch b/debian/patches-rt/0343-rt-PREEMPT_RT-safety-net-for-backported-patches.patch new file mode 100644 index 000000000..b4d67b156 --- /dev/null +++ b/debian/patches-rt/0343-rt-PREEMPT_RT-safety-net-for-backported-patches.patch @@ -0,0 +1,52 @@ +From 8961a29e7aa52c929475c767559b23e018fe8b01 Mon Sep 17 00:00:00 2001 +From: Clark Williams <clark.williams@gmail.com> +Date: Sun, 30 Jan 2022 15:46:27 -0600 +Subject: [PATCH 343/347] rt: PREEMPT_RT safety net for backported patches +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +While doing some 4.19-rt cleanup work, I stumbled across the fact that parts of +two backported patches were dependent on CONFIG_PREEMPT_RT, rather than +the CONFIG_PREEMPT_RT_FULL used in 4.19 and earlier RT series. The commits +in the linux-stable-rt v4.19-rt branch are: + +dad4c6a33bf4e mm: slub: Don't resize the location tracking cache on PREEMPT_RT +e626b6f873f2c net: Treat __napi_schedule_irqoff() as __napi_schedule() on PREEMPT_RT + +Discussing this at the Stable RT maintainers meeting, Steven Rostedt suggested that +we automagically select CONFIG_PREEMPT_RT if CONFIG_PREEMPT_RT_FULL is on, giving +us a safety net for any subsequently backported patches. Here's my first cut at +that patch. + +I suspect we'll need a similar patch for stable RT kernels < 4.19. + +Suggested-by: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Clark Williams <williams@redhat.com> +--- + kernel/Kconfig.preempt | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt +index 306567f72a3e..fd924c0bcea7 100644 +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -6,6 +6,9 @@ config PREEMPT_RT_BASE + bool + select PREEMPT + ++config PREEMPT_RT ++ bool ++ + config HAVE_PREEMPT_LAZY + bool + +@@ -80,6 +83,7 @@ config PREEMPT_RT_FULL + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + select PREEMPT_RCU ++ select PREEMPT_RT + help + All and everything + +-- +2.36.1 + diff --git a/debian/patches-rt/0344-net-Add-missing-xmit_lock_owner-hunks.patch b/debian/patches-rt/0344-net-Add-missing-xmit_lock_owner-hunks.patch new file mode 100644 index 000000000..467bb1739 --- /dev/null +++ b/debian/patches-rt/0344-net-Add-missing-xmit_lock_owner-hunks.patch @@ -0,0 +1,117 @@ +From 1a0157a8d087c0c5bdf88ad97e2d4db77bee63aa Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 22 Dec 2021 20:35:22 +0100 +Subject: [PATCH 344/347] net: Add missing xmit_lock_owner hunks. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The patch + net: move xmit_recursion to per-task variable on -RT + +lost a few hunks during its rebase. + +Add the `xmit_lock_owner' accessor/wrapper. + +Reported-by: Salvatore Bonaccorso <carnil@debian.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/netdevice.h | 29 +++++++++++++---------------- + 1 file changed, 13 insertions(+), 16 deletions(-) + +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index c4713217b20e..bd73117e2636 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -3885,17 +3885,17 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) + #ifdef CONFIG_PREEMPT_RT_FULL + static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) + { +- txq->xmit_lock_owner = current; ++ WRITE_ONCE(txq->xmit_lock_owner, current); + } + + static inline void netdev_queue_clear_owner(struct netdev_queue *txq) + { +- txq->xmit_lock_owner = NULL; ++ WRITE_ONCE(txq->xmit_lock_owner, NULL); + } + + static inline bool netdev_queue_has_owner(struct netdev_queue *txq) + { +- if (txq->xmit_lock_owner != NULL) ++ if (READ_ONCE(txq->xmit_lock_owner) != NULL) + return true; + return false; + } +@@ -3904,17 +3904,19 @@ static inline bool netdev_queue_has_owner(struct netdev_queue *txq) + + static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) + { +- txq->xmit_lock_owner = cpu; ++ /* Pairs with READ_ONCE() in __dev_queue_xmit() */ ++ WRITE_ONCE(txq->xmit_lock_owner, cpu); + } + + static inline void netdev_queue_clear_owner(struct netdev_queue *txq) + { +- txq->xmit_lock_owner = -1; ++ /* Pairs with READ_ONCE() in __dev_queue_xmit() */ ++ WRITE_ONCE(txq->xmit_lock_owner, -1); + } + + static inline bool netdev_queue_has_owner(struct netdev_queue *txq) + { +- if (txq->xmit_lock_owner != -1) ++ if (READ_ONCE(txq->xmit_lock_owner) != -1) + return true; + return false; + } +@@ -3923,8 +3925,7 @@ static inline bool netdev_queue_has_owner(struct netdev_queue *txq) + static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) + { + spin_lock(&txq->_xmit_lock); +- /* Pairs with READ_ONCE() in __dev_queue_xmit() */ +- WRITE_ONCE(txq->xmit_lock_owner, cpu); ++ netdev_queue_set_owner(txq, cpu); + } + + static inline bool __netif_tx_acquire(struct netdev_queue *txq) +@@ -3941,8 +3942,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq) + static inline void __netif_tx_lock_bh(struct netdev_queue *txq) + { + spin_lock_bh(&txq->_xmit_lock); +- /* Pairs with READ_ONCE() in __dev_queue_xmit() */ +- WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); ++ netdev_queue_set_owner(txq, smp_processor_id()); + } + + static inline bool __netif_tx_trylock(struct netdev_queue *txq) +@@ -3950,23 +3950,20 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) + bool ok = spin_trylock(&txq->_xmit_lock); + + if (likely(ok)) { +- /* Pairs with READ_ONCE() in __dev_queue_xmit() */ +- WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); ++ netdev_queue_set_owner(txq, smp_processor_id()); + } + return ok; + } + + static inline void __netif_tx_unlock(struct netdev_queue *txq) + { +- /* Pairs with READ_ONCE() in __dev_queue_xmit() */ +- WRITE_ONCE(txq->xmit_lock_owner, -1); ++ netdev_queue_clear_owner(txq); + spin_unlock(&txq->_xmit_lock); + } + + static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) + { +- /* Pairs with READ_ONCE() in __dev_queue_xmit() */ +- WRITE_ONCE(txq->xmit_lock_owner, -1); ++ netdev_queue_clear_owner(txq); + spin_unlock_bh(&txq->_xmit_lock); + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0345-Linux-4.19.237-rt107-REBASE.patch b/debian/patches-rt/0345-Linux-4.19.237-rt107-REBASE.patch new file mode 100644 index 000000000..e38739169 --- /dev/null +++ b/debian/patches-rt/0345-Linux-4.19.237-rt107-REBASE.patch @@ -0,0 +1,21 @@ +From da237074d357316e91a363c91e29aeaaace6ce6c Mon Sep 17 00:00:00 2001 +From: Daniel Wagner <wagi@monom.org> +Date: Thu, 31 Mar 2022 20:37:13 +0200 +Subject: [PATCH 345/347] Linux 4.19.237-rt107 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Daniel Wagner <wagi@monom.org> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index 9ea5981fa956..2e0a3c960575 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt101 ++-rt107 +-- +2.36.1 + diff --git a/debian/patches-rt/0346-genirq-Add-lost-hunk-to-irq_forced_thread_fn.patch b/debian/patches-rt/0346-genirq-Add-lost-hunk-to-irq_forced_thread_fn.patch new file mode 100644 index 000000000..0c8b0e14e --- /dev/null +++ b/debian/patches-rt/0346-genirq-Add-lost-hunk-to-irq_forced_thread_fn.patch @@ -0,0 +1,41 @@ +From d379a82e852964afe457dcf44bf4a00fc59de389 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 29 Apr 2022 11:02:18 -0500 +Subject: [PATCH 346/347] genirq: Add lost hunk to irq_forced_thread_fn(). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +The irq_settings_no_softirq_call() related handling got lost in process, +here are the missing bits. + +Reported-by: Martin Kaistra <martin.kaistra@linutronix.de> +Fixes: b0cf5c230e2a0 ("Merge tag 'v4.19.183' into linux-4.19.y-rt") +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Clark Williams <williams@redhat.com> +--- + kernel/irq/manage.c | 10 +++++++++- + 1 file changed, 9 insertions(+), 1 deletion(-) + +diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c +index 6c88d81399dd..8f710f1755d8 100644 +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -998,7 +998,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) + irq_finalize_oneshot(desc, action); + if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) + local_irq_enable(); +- local_bh_enable(); ++ /* ++ * Interrupts which have real time requirements can be set up ++ * to avoid softirq processing in the thread handler. This is ++ * safe as these interrupts do not raise soft interrupts. ++ */ ++ if (irq_settings_no_softirq_call(desc)) ++ _local_bh_enable(); ++ else ++ local_bh_enable(); + return ret; + } + +-- +2.36.1 + diff --git a/debian/patches-rt/0347-Linux-4.19.246-rt110-REBASE.patch b/debian/patches-rt/0347-Linux-4.19.246-rt110-REBASE.patch new file mode 100644 index 000000000..746979875 --- /dev/null +++ b/debian/patches-rt/0347-Linux-4.19.246-rt110-REBASE.patch @@ -0,0 +1,21 @@ +From b7cf2f6b538ab97b989cbb2d10bf804994874ba5 Mon Sep 17 00:00:00 2001 +From: Daniel Wagner <wagi@monom.org> +Date: Tue, 14 Jun 2022 07:47:54 +0200 +Subject: [PATCH 347/347] Linux 4.19.246-rt110 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz + +Signed-off-by: Daniel Wagner <wagi@monom.org> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index 2e0a3c960575..b3e668a8fb94 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt107 ++-rt110 +-- +2.36.1 + diff --git a/debian/patches-rt/series b/debian/patches-rt/series new file mode 100644 index 000000000..8d7c2429b --- /dev/null +++ b/debian/patches-rt/series @@ -0,0 +1,346 @@ +0001-ARM-at91-add-TCB-registers-definitions.patch +0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch +0003-clocksource-drivers-timer-atmel-tcb-add-clockevent-d.patch +0004-clocksource-drivers-atmel-pit-make-option-silent.patch +0005-ARM-at91-Implement-clocksource-selection.patch +0006-ARM-configs-at91-use-new-TCB-timer-driver.patch +0007-ARM-configs-at91-unselect-PIT.patch +0008-irqchip-gic-v3-its-Move-pending-table-allocation-to-.patch +0009-kthread-convert-worker-lock-to-raw-spinlock.patch +0010-crypto-caam-qi-simplify-CGR-allocation-freeing.patch +0011-sched-fair-Robustify-CFS-bandwidth-timer-locking.patch +0012-arm-Convert-arm-boot_lock-to-raw.patch +0013-x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch +0014-cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch +0015-fscache-initialize-cookie-hash-table-raw-spinlocks.patch +0016-Drivers-hv-vmbus-include-header-for-get_irq_regs.patch +0017-percpu-include-irqflags.h-for-raw_local_irq_save.patch +0018-efi-Allow-efi-runtime.patch +0019-x86-efi-drop-task_lock-from-efi_switch_mm.patch +0020-arm64-KVM-compute_layout-before-altenates-are-applie.patch +0021-of-allocate-free-phandle-cache-outside-of-the-devtre.patch +0022-mm-kasan-make-quarantine_lock-a-raw_spinlock_t.patch +0023-EXP-rcu-Revert-expedited-GP-parallelization-cleverne.patch +0024-kmemleak-Turn-kmemleak_lock-to-raw-spinlock-on-RT.patch +0025-NFSv4-replace-seqcount_t-with-a-seqlock_t.patch +0026-kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch +0027-kernel-sched-core-add-migrate_disable.patch +0028-sched-migrate_disable-Add-export_symbol_gpl-for-__mi.patch +0029-arm-at91-do-not-disable-enable-clocks-in-a-row.patch +0030-clocksource-TCLIB-Allow-higher-clock-rates-for-clock.patch +0031-timekeeping-Split-jiffies-seqlock.patch +0032-signal-Revert-ptrace-preempt-magic.patch +0033-net-sched-Use-msleep-instead-of-yield.patch +0034-dm-rq-remove-BUG_ON-irqs_disabled-check.patch +0035-usb-do-no-disable-interrupts-in-giveback.patch +0036-rt-Provide-PREEMPT_RT_BASE-config-switch.patch +0037-cpumask-Disable-CONFIG_CPUMASK_OFFSTACK-for-RT.patch +0038-jump-label-disable-if-stop_machine-is-used.patch +0039-kconfig-Disable-config-options-which-are-not-RT-comp.patch +0040-lockdep-disable-self-test.patch +0041-mm-Allow-only-slub-on-RT.patch +0042-locking-Disable-spin-on-owner-for-RT.patch +0043-rcu-Disable-RCU_FAST_NO_HZ-on-RT.patch +0044-rcu-make-RCU_BOOST-default-on-RT.patch +0045-sched-Disable-CONFIG_RT_GROUP_SCHED-on-RT.patch +0046-net-core-disable-NET_RX_BUSY_POLL.patch +0047-arm-disable-NEON-in-kernel-mode.patch +0048-powerpc-Use-generic-rwsem-on-RT.patch +0049-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch +0050-powerpc-Disable-highmem-on-RT.patch +0051-mips-Disable-highmem-on-RT.patch +0052-x86-Use-generic-rwsem_spinlocks-on-rt.patch +0053-leds-trigger-disable-CPU-trigger-on-RT.patch +0054-cpufreq-drop-K8-s-driver-from-beeing-selected.patch +0055-md-disable-bcache.patch +0056-efi-Disable-runtime-services-on-RT.patch +0057-printk-Add-a-printk-kill-switch.patch +0058-printk-Add-force_early_printk-boot-param-to-help-wit.patch +0059-preempt-Provide-preempt_-_-no-rt-variants.patch +0060-futex-workaround-migrate_disable-enable-in-different.patch +0061-rt-Add-local-irq-locks.patch +0062-locallock-provide-get-put-_locked_ptr-variants.patch +0063-mm-scatterlist-Do-not-disable-irqs-on-RT.patch +0064-signal-x86-Delay-calling-signals-in-atomic.patch +0065-x86-signal-delay-calling-signals-on-32bit.patch +0066-buffer_head-Replace-bh_uptodate_lock-for-rt.patch +0067-fs-jbd-jbd2-Make-state-lock-and-journal-head-lock-rt.patch +0068-list_bl-Make-list-head-locking-RT-safe.patch +0069-list_bl-fixup-bogus-lockdep-warning.patch +0070-genirq-Disable-irqpoll-on-rt.patch +0071-genirq-Force-interrupt-thread-on-RT.patch +0072-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch +0073-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch +0074-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch +0075-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch +0076-mm-page_alloc-rt-friendly-per-cpu-pages.patch +0077-mm-swap-Convert-to-percpu-locked.patch +0078-mm-perform-lru_add_drain_all-remotely.patch +0079-mm-vmstat-Protect-per-cpu-variables-with-preempt-dis.patch +0080-ARM-Initialize-split-page-table-locks-for-vector-pag.patch +0081-mm-Enable-SLUB-for-RT.patch +0082-slub-Enable-irqs-for-__GFP_WAIT.patch +0083-slub-Disable-SLUB_CPU_PARTIAL.patch +0084-mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch +0085-mm-memcontrol-Replace-local_irq_disable-with-local-l.patch +0086-mm-zsmalloc-copy-with-get_cpu_var-and-locking.patch +0087-x86-mm-pat-disable-preemption-__split_large_page-aft.patch +0088-radix-tree-use-local-locks.patch +0089-timers-Prepare-for-full-preemption.patch +0090-x86-kvm-Require-const-tsc-for-RT.patch +0091-pci-switchtec-Don-t-use-completion-s-wait-queue.patch +0092-wait.h-include-atomic.h.patch +0093-work-simple-Simple-work-queue-implemenation.patch +0094-work-simple-drop-a-shit-statement-in-SWORK_EVENT_PEN.patch +0095-completion-Use-simple-wait-queues.patch +0096-fs-aio-simple-simple-work.patch +0097-time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch +0098-hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch +0099-hrtimers-Prepare-full-preemption.patch +0100-hrtimer-by-timers-by-default-into-the-softirq-contex.patch +0101-sched-fair-Make-the-hrtimers-non-hard-again.patch +0102-hrtimer-Move-schedule_work-call-to-helper-thread.patch +0103-hrtimer-move-state-change-before-hrtimer_cancel-in-d.patch +0104-posix-timers-Thread-posix-cpu-timers-on-rt.patch +0105-sched-Move-task_struct-cleanup-to-RCU.patch +0106-sched-Limit-the-number-of-task-migrations-per-batch.patch +0107-sched-Move-mmdrop-to-RCU-on-RT.patch +0108-kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch +0109-sched-Add-saved_state-for-tasks-blocked-on-sleeping-.patch +0110-sched-Do-not-account-rcu_preempt_depth-on-RT-in-migh.patch +0111-sched-Use-the-proper-LOCK_OFFSET-for-cond_resched.patch +0112-sched-Disable-TTWU_QUEUE-on-RT.patch +0113-sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch +0114-rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch +0115-hotplug-Lightweight-get-online-cpus.patch +0116-trace-Add-migrate-disabled-counter-to-tracing-output.patch +0117-lockdep-Make-it-RT-aware.patch +0118-tasklet-Prevent-tasklets-from-going-into-infinite-sp.patch +0119-softirq-Check-preemption-after-reenabling-interrupts.patch +0120-softirq-Disable-softirq-stacks-for-RT.patch +0121-softirq-Split-softirq-locks.patch +0122-net-core-use-local_bh_disable-in-netif_rx_ni.patch +0123-genirq-Allow-disabling-of-softirq-processing-in-irq-.patch +0124-softirq-split-timer-softirqs-out-of-ksoftirqd.patch +0125-softirq-Avoid-local_softirq_pending-messages-if-ksof.patch +0126-softirq-Avoid-local_softirq_pending-messages-if-task.patch +0127-rtmutex-trylock-is-okay-on-RT.patch +0128-fs-nfs-turn-rmdir_sem-into-a-semaphore.patch +0129-rtmutex-Handle-the-various-new-futex-race-conditions.patch +0130-futex-Fix-bug-on-when-a-requeued-RT-task-times-out.patch +0131-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch +0132-pid.h-include-atomic.h.patch +0133-arm-include-definition-for-cpumask_t.patch +0134-locking-locktorture-Do-NOT-include-rwlock.h-directly.patch +0135-rtmutex-Add-rtmutex_lock_killable.patch +0136-rtmutex-Make-lock_killable-work.patch +0137-spinlock-Split-the-lock-types-header.patch +0138-rtmutex-Avoid-include-hell.patch +0139-rbtree-don-t-include-the-rcu-header.patch +0140-rtmutex-Provide-rt_mutex_slowlock_locked.patch +0141-rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch +0142-rtmutex-add-sleeping-lock-implementation.patch +0143-rtmutex-add-mutex-implementation-based-on-rtmutex.patch +0144-rtmutex-add-rwsem-implementation-based-on-rtmutex.patch +0145-rtmutex-add-rwlock-implementation-based-on-rtmutex.patch +0146-rtmutex-rwlock-preserve-state-like-a-sleeping-lock.patch +0147-rtmutex-wire-up-RT-s-locking.patch +0148-rtmutex-add-ww_mutex-addon-for-mutex-rt.patch +0149-kconfig-Add-PREEMPT_RT_FULL.patch +0150-locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch +0151-locking-rt-mutex-Flush-block-plug-on-__down_read.patch +0152-locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch +0153-ptrace-fix-ptrace-vs-tasklist_lock-race.patch +0154-rtmutex-annotate-sleeping-lock-context.patch +0155-sched-migrate_disable-fallback-to-preempt_disable-in.patch +0156-locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch +0157-rcu-Frob-softirq-test.patch +0158-rcu-Merge-RCU-bh-into-RCU-preempt.patch +0159-rcu-Make-ksoftirqd-do-RCU-quiescent-states.patch +0160-rcu-Eliminate-softirq-processing-from-rcutree.patch +0161-srcu-use-cpu_online-instead-custom-check.patch +0162-srcu-replace-local_irqsave-with-a-locallock.patch +0163-rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch +0164-tty-serial-omap-Make-the-locking-RT-aware.patch +0165-tty-serial-pl011-Make-the-locking-work-on-RT.patch +0166-tty-serial-pl011-explicitly-initialize-the-flags-var.patch +0167-rt-Improve-the-serial-console-PASS_LIMIT.patch +0168-tty-serial-8250-don-t-take-the-trylock-during-oops.patch +0169-locking-percpu-rwsem-Remove-preempt_disable-variants.patch +0170-mm-Protect-activate_mm-by-preempt_-disable-enable-_r.patch +0171-fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-ini.patch +0172-fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch +0173-squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch +0174-thermal-Defer-thermal-wakups-to-threads.patch +0175-x86-fpu-Disable-preemption-around-local_bh_disable.patch +0176-fs-epoll-Do-not-disable-preemption-on-RT.patch +0177-mm-vmalloc-Another-preempt-disable-region-which-suck.patch +0178-block-mq-use-cpu_light.patch +0179-block-mq-do-not-invoke-preempt_disable.patch +0180-block-mq-don-t-complete-requests-via-IPI.patch +0181-md-raid5-Make-raid5_percpu-handling-RT-aware.patch +0182-rt-Introduce-cpu_chill.patch +0183-hrtimer-Don-t-lose-state-in-cpu_chill.patch +0184-hrtimer-cpu_chill-save-task-state-in-saved_state.patch +0185-block-blk-mq-move-blk_queue_usage_counter_release-in.patch +0186-block-Use-cpu_chill-for-retry-loops.patch +0187-fs-dcache-Use-cpu_chill-in-trylock-loops.patch +0188-net-Use-cpu_chill-instead-of-cpu_relax.patch +0189-fs-dcache-use-swait_queue-instead-of-waitqueue.patch +0190-workqueue-Use-normal-rcu.patch +0191-workqueue-Use-local-irq-lock-instead-of-irq-disable-.patch +0192-workqueue-Prevent-workqueue-versus-ata-piix-livelock.patch +0193-sched-Distangle-worker-accounting-from-rqlock.patch +0194-debugobjects-Make-RT-aware.patch +0195-seqlock-Prevent-rt-starvation.patch +0196-sunrpc-Make-svc_xprt_do_enqueue-use-get_cpu_light.patch +0197-net-Use-skbufhead-with-raw-lock.patch +0198-net-move-xmit_recursion-to-per-task-variable-on-RT.patch +0199-net-provide-a-way-to-delegate-processing-a-softirq-t.patch +0200-net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch +0201-net-Qdisc-use-a-seqlock-instead-seqcount.patch +0202-net-add-back-the-missing-serialization-in-ip_send_un.patch +0203-net-add-a-lock-around-icmp_sk.patch +0204-net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch +0205-irqwork-push-most-work-into-softirq-context.patch +0206-printk-Make-rt-aware.patch +0207-kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch +0208-printk-Drop-the-logbuf_lock-more-often.patch +0209-ARM-enable-irq-in-translation-section-permission-fau.patch +0210-genirq-update-irq_set_irqchip_state-documentation.patch +0211-KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch +0212-arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch +0213-kgdb-serial-Short-term-workaround.patch +0214-sysfs-Add-sys-kernel-realtime-entry.patch +0215-mm-rt-kmap_atomic-scheduling.patch +0216-x86-highmem-Add-a-already-used-pte-check.patch +0217-arm-highmem-Flush-tlb-on-unmap.patch +0218-arm-Enable-highmem-for-rt.patch +0219-scsi-fcoe-Make-RT-aware.patch +0220-x86-crypto-Reduce-preempt-disabled-regions.patch +0221-crypto-Reduce-preempt-disabled-regions-more-algos.patch +0222-crypto-limit-more-FPU-enabled-sections.patch +0223-crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch +0224-crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch +0225-panic-skip-get_random_bytes-for-RT_FULL-in-init_oops.patch +0226-x86-stackprotector-Avoid-random-pool-on-rt.patch +0228-cpu-hotplug-Implement-CPU-pinning.patch +0229-sched-Allow-pinned-user-tasks-to-be-awakened-to-the-.patch +0230-hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch +0231-net-Remove-preemption-disabling-in-netif_rx.patch +0232-net-Another-local_irq_disable-kmalloc-headache.patch +0233-net-core-protect-users-of-napi_alloc_cache-against-r.patch +0234-net-netfilter-Serialize-xt_write_recseq-sections-on-.patch +0235-lockdep-selftest-Only-do-hardirq-context-test-for-ra.patch +0236-lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch +0237-sched-Add-support-for-lazy-preemption.patch +0238-ftrace-Fix-trace-header-alignment.patch +0239-x86-Support-for-lazy-preemption.patch +0240-x86-lazy-preempt-properly-check-against-preempt-mask.patch +0241-x86-lazy-preempt-use-proper-return-label-on-32bit-x8.patch +0242-arm-Add-support-for-lazy-preemption.patch +0243-powerpc-Add-support-for-lazy-preemption.patch +0244-arch-arm64-Add-lazy-preempt-support.patch +0245-connector-cn_proc-Protect-send_msg-with-a-local-lock.patch +0246-drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch +0247-drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch +0248-drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch +0249-tpm_tis-fix-stall-after-iowrite-s.patch +0250-watchdog-prevent-deferral-of-watchdogd-wakeup-on-RT.patch +0251-drm-radeon-i915-Use-preempt_disable-enable_rt-where-.patch +0252-drm-i915-Use-local_lock-unlock_irq-in-intel_pipe_upd.patch +0253-drm-i915-disable-tracing-on-RT.patch +0254-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch +0255-cgroups-use-simple-wait-in-css_release.patch +0256-cpuset-Convert-callback_lock-to-raw_spinlock_t.patch +0257-apparmor-use-a-locallock-instead-preempt_disable.patch +0258-workqueue-Prevent-deadlock-stall-on-RT.patch +0259-signals-Allow-rt-tasks-to-cache-one-sigqueue-struct.patch +0260-Add-localversion-for-RT-release.patch +0261-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch +0262-powerpc-reshuffle-TIF-bits.patch +0263-tty-sysrq-Convert-show_lock-to-raw_spinlock_t.patch +0264-drm-i915-Don-t-disable-interrupts-independently-of-t.patch +0265-sched-completion-Fix-a-lockup-in-wait_for_completion.patch +0266-kthread-add-a-global-worker-thread.patch +0267-arm-imx6-cpuidle-Use-raw_spinlock_t.patch +0268-rcu-Don-t-allow-to-change-rcu_normal_after_boot-on-R.patch +0269-pci-switchtec-fix-stream_open.cocci-warnings.patch +0270-sched-core-Drop-a-preempt_disable_rt-statement.patch +0271-timers-Redo-the-notification-of-canceling-timers-on-.patch +0272-Revert-futex-Ensure-lock-unlock-symetry-versus-pi_lo.patch +0273-Revert-futex-Fix-bug-on-when-a-requeued-RT-task-time.patch +0274-Revert-rtmutex-Handle-the-various-new-futex-race-con.patch +0275-Revert-futex-workaround-migrate_disable-enable-in-di.patch +0276-futex-Make-the-futex_hash_bucket-lock-raw.patch +0277-futex-Delay-deallocation-of-pi_state.patch +0278-mm-zswap-Do-not-disable-preemption-in-zswap_frontswa.patch +0279-revert-aio.patch +0280-fs-aio-simple-simple-work.patch +0281-revert-thermal.patch +0282-thermal-Defer-thermal-wakups-to-threads.patch +0283-revert-block.patch +0284-block-blk-mq-move-blk_queue_usage_counter_release-in.patch +0285-workqueue-rework.patch +0286-i2c-exynos5-Remove-IRQF_ONESHOT.patch +0287-i2c-hix5hd2-Remove-IRQF_ONESHOT.patch +0288-sched-deadline-Ensure-inactive_timer-runs-in-hardirq.patch +0289-thermal-x86_pkg_temp-make-pkg_temp_lock-a-raw-spinlo.patch +0290-dma-buf-Use-seqlock_t-instread-disabling-preemption.patch +0291-KVM-arm-arm64-Let-the-timer-expire-in-hardirq-contex.patch +0292-x86-preempt-Check-preemption-level-before-looking-at.patch +0293-hrtimer-Use-READ_ONCE-to-access-timer-base-in-hrimer.patch +0294-hrtimer-Don-t-grab-the-expiry-lock-for-non-soft-hrti.patch +0295-hrtimer-Prevent-using-hrtimer_grab_expiry_lock-on-mi.patch +0296-hrtimer-Add-a-missing-bracket-and-hide-migration_bas.patch +0297-posix-timers-Unlock-expiry-lock-in-the-early-return.patch +0298-sched-migrate_dis-enable-Use-sleeping_lock-to-annota.patch +0299-sched-__set_cpus_allowed_ptr-Check-cpus_mask-not-cpu.patch +0300-sched-Remove-dead-__migrate_disabled-check.patch +0301-sched-migrate-disable-Protect-cpus_ptr-with-lock.patch +0302-lib-smp_processor_id-Don-t-use-cpumask_equal.patch +0303-futex-Make-the-futex_hash_bucket-spinlock_t-again-an.patch +0304-locking-rtmutex-Clean-pi_blocked_on-in-the-error-cas.patch +0305-lib-ubsan-Don-t-seralize-UBSAN-report.patch +0306-kmemleak-Change-the-lock-of-kmemleak_object-to-raw_s.patch +0307-sched-migrate_enable-Use-select_fallback_rq.patch +0308-sched-Lazy-migrate_disable-processing.patch +0309-sched-migrate_enable-Use-stop_one_cpu_nowait.patch +0310-Revert-ARM-Initialize-split-page-table-locks-for-vec.patch +0311-locking-Make-spinlock_t-and-rwlock_t-a-RCU-section-o.patch +0312-sched-core-migrate_enable-must-access-takedown_cpu_t.patch +0313-lib-smp_processor_id-Adjust-check_preemption_disable.patch +0314-sched-migrate_enable-Busy-loop-until-the-migration-r.patch +0315-userfaultfd-Use-a-seqlock-instead-of-seqcount.patch +0316-sched-migrate_enable-Use-per-cpu-cpu_stop_work.patch +0317-sched-migrate_enable-Remove-__schedule-call.patch +0318-mm-memcontrol-Move-misplaced-local_unlock_irqrestore.patch +0319-locallock-Include-header-for-the-current-macro.patch +0320-drm-vmwgfx-Drop-preempt_disable-in-vmw_fifo_ping_hos.patch +0321-tracing-make-preempt_lazy-and-migrate_disable-counte.patch +0322-lib-ubsan-Remove-flags-parameter-from-calls-to-ubsan.patch +0323-irq_work-Fix-checking-of-IRQ_WORK_LAZY-flag-set-on-n.patch +0324-tasklet-Address-a-race-resulting-in-double-enqueue.patch +0325-hrtimer-fix-logic-for-when-grabbing-softirq_expiry_l.patch +0326-fs-dcache-Include-swait.h-header.patch +0327-mm-slub-Always-flush-the-delayed-empty-slubs-in-flus.patch +0328-tasklet-Fix-UP-case-for-tasklet-CHAINED-state.patch +0329-signal-Prevent-double-free-of-user-struct.patch +0330-Bluetooth-Acquire-sk_lock.slock-without-disabling-in.patch +0331-net-phy-fixed_phy-Remove-unused-seqcount.patch +0332-net-xfrm-fix-compress-vs-decompress-serialization.patch +0333-mm-memcontrol-Disable-preemption-in-__mod_memcg_lruv.patch +0334-ptrace-fix-ptrace_unfreeze_traced-race-with-rt-lock.patch +0335-Linux-4.19.185-rt76-REBASE.patch +0336-mm-slub-Don-t-resize-the-location-tracking-cache-on-.patch +0337-locking-rwsem_rt-Add-__down_read_interruptible.patch +0338-Linux-4.19.206-rt87-REBASE.patch +0339-locking-rwsem-rt-Remove-might_sleep-in-__up_read.patch +0340-Linux-4.19.214-rt93-REBASE.patch +0341-fscache-fix-initialisation-of-cookie-hash-table-raw-.patch +0342-Linux-4.19.225-rt101-REBASE.patch +0343-rt-PREEMPT_RT-safety-net-for-backported-patches.patch +0344-net-Add-missing-xmit_lock_owner-hunks.patch +0345-Linux-4.19.237-rt107-REBASE.patch +0346-genirq-Add-lost-hunk-to-irq_forced_thread_fn.patch +0347-Linux-4.19.246-rt110-REBASE.patch |