summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/alternative.c133
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/apic/apic.c46
-rw-r--r--arch/x86/kernel/apic/msi.c5
-rw-r--r--arch/x86/kernel/apic/vector.c5
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c7
-rw-r--r--arch/x86/kernel/callthunks.c9
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c12
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c18
-rw-r--r--arch/x86/kernel/cpu/bugs.c30
-rw-r--r--arch/x86/kernel/cpu/common.c157
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c3
-rw-r--r--arch/x86/kernel/cpu/intel.c1
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c12
-rw-r--r--arch/x86/kernel/cpu/match.c5
-rw-r--r--arch/x86/kernel/cpu/mce/core.c24
-rw-r--r--arch/x86/kernel/cpu/mce/genpool.c40
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c21
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c27
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c5
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c5
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c65
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c40
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h5
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c11
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c24
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c12
-rw-r--r--arch/x86/kernel/cpu/resctrl/trace.h (renamed from arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h)24
-rw-r--r--arch/x86/kernel/cpu/sgx/driver.c2
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c1
-rw-r--r--arch/x86/kernel/cpu/topology_amd.c19
-rw-r--r--arch/x86/kernel/cpu/topology_ext.c15
-rw-r--r--arch/x86/kernel/crash.c32
-rw-r--r--arch/x86/kernel/devicetree.c26
-rw-r--r--arch/x86/kernel/dumpstack.c4
-rw-r--r--arch/x86/kernel/fpu/xstate.c5
-rw-r--r--arch/x86/kernel/fpu/xstate.h2
-rw-r--r--arch/x86/kernel/ftrace.c16
-rw-r--r--arch/x86/kernel/head_32.S13
-rw-r--r--arch/x86/kernel/head_64.S4
-rw-r--r--arch/x86/kernel/idt.c3
-rw-r--r--arch/x86/kernel/irq.c172
-rw-r--r--arch/x86/kernel/irq_64.c1
-rw-r--r--arch/x86/kernel/kprobes/core.c4
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kernel/module.c51
-rw-r--r--arch/x86/kernel/rtc.c1
-rw-r--r--arch/x86/kernel/setup.c42
-rw-r--r--arch/x86/kernel/sev.c14
-rw-r--r--arch/x86/kernel/shstk.c15
-rw-r--r--arch/x86/kernel/signal_32.c2
-rw-r--r--arch/x86/kernel/signal_64.c6
-rw-r--r--arch/x86/kernel/smpboot.c28
-rw-r--r--arch/x86/kernel/sys_x86_64.c42
-rw-r--r--arch/x86/kernel/topology.c43
-rw-r--r--arch/x86/kernel/tsc.c8
-rw-r--r--arch/x86/kernel/tsc_msr.c14
-rw-r--r--arch/x86/kernel/uprobes.c7
-rw-r--r--arch/x86/kernel/vmlinux.lds.S10
62 files changed, 740 insertions, 620 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 74077694da..20a0dd5170 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -40,7 +40,7 @@ KMSAN_SANITIZE_sev.o := n
KCOV_INSTRUMENT_head$(BITS).o := n
KCOV_INSTRUMENT_sev.o := n
-CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
+CFLAGS_irq.o := -I $(src)/../include/asm/trace
obj-y += head_$(BITS).o
obj-y += head$(BITS).o
@@ -62,7 +62,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
-obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
+obj-y += pci-dma.o quirks.o kdebugfs.o
obj-y += alternative.o i8253.o hw_breakpoint.o
obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += resource.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 45a280f216..89de612432 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -125,6 +125,20 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
};
/*
+ * Nomenclature for variable names to simplify and clarify this code and ease
+ * any potential staring at it:
+ *
+ * @instr: source address of the original instructions in the kernel text as
+ * generated by the compiler.
+ *
+ * @buf: temporary buffer on which the patching operates. This buffer is
+ * eventually text-poked into the kernel image.
+ *
+ * @replacement/@repl: pointer to the opcodes which are replacing @instr, located
+ * in the .altinstr_replacement section.
+ */
+
+/*
* Fill the buffer with a single effective instruction of size @len.
*
* In order not to issue an ORC stack depth tracking CFI entry (Call Frame Info)
@@ -133,28 +147,28 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
* each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and
* *jump* over instead of executing long and daft NOPs.
*/
-static void add_nop(u8 *instr, unsigned int len)
+static void add_nop(u8 *buf, unsigned int len)
{
- u8 *target = instr + len;
+ u8 *target = buf + len;
if (!len)
return;
if (len <= ASM_NOP_MAX) {
- memcpy(instr, x86_nops[len], len);
+ memcpy(buf, x86_nops[len], len);
return;
}
if (len < 128) {
- __text_gen_insn(instr, JMP8_INSN_OPCODE, instr, target, JMP8_INSN_SIZE);
- instr += JMP8_INSN_SIZE;
+ __text_gen_insn(buf, JMP8_INSN_OPCODE, buf, target, JMP8_INSN_SIZE);
+ buf += JMP8_INSN_SIZE;
} else {
- __text_gen_insn(instr, JMP32_INSN_OPCODE, instr, target, JMP32_INSN_SIZE);
- instr += JMP32_INSN_SIZE;
+ __text_gen_insn(buf, JMP32_INSN_OPCODE, buf, target, JMP32_INSN_SIZE);
+ buf += JMP32_INSN_SIZE;
}
- for (;instr < target; instr++)
- *instr = INT3_INSN_OPCODE;
+ for (;buf < target; buf++)
+ *buf = INT3_INSN_OPCODE;
}
extern s32 __retpoline_sites[], __retpoline_sites_end[];
@@ -187,12 +201,12 @@ static bool insn_is_nop(struct insn *insn)
* Find the offset of the first non-NOP instruction starting at @offset
* but no further than @len.
*/
-static int skip_nops(u8 *instr, int offset, int len)
+static int skip_nops(u8 *buf, int offset, int len)
{
struct insn insn;
for (; offset < len; offset += insn.length) {
- if (insn_decode_kernel(&insn, &instr[offset]))
+ if (insn_decode_kernel(&insn, &buf[offset]))
break;
if (!insn_is_nop(&insn))
@@ -203,66 +217,32 @@ static int skip_nops(u8 *instr, int offset, int len)
}
/*
- * Optimize a sequence of NOPs, possibly preceded by an unconditional jump
- * to the end of the NOP sequence into a single NOP.
- */
-static bool
-__optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target)
-{
- int i = *next - insn->length;
-
- switch (insn->opcode.bytes[0]) {
- case JMP8_INSN_OPCODE:
- case JMP32_INSN_OPCODE:
- *prev = i;
- *target = *next + insn->immediate.value;
- return false;
- }
-
- if (insn_is_nop(insn)) {
- int nop = i;
-
- *next = skip_nops(instr, *next, len);
- if (*target && *next == *target)
- nop = *prev;
-
- add_nop(instr + nop, *next - nop);
- DUMP_BYTES(ALT, instr, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, *next);
- return true;
- }
-
- *target = 0;
- return false;
-}
-
-/*
* "noinline" to cause control flow change and thus invalidate I$ and
* cause refetch after modification.
*/
-static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
+static void noinline optimize_nops(const u8 * const instr, u8 *buf, size_t len)
{
- int prev, target = 0;
-
for (int next, i = 0; i < len; i = next) {
struct insn insn;
- if (insn_decode_kernel(&insn, &instr[i]))
+ if (insn_decode_kernel(&insn, &buf[i]))
return;
next = i + insn.length;
- __optimize_nops(instr, len, &insn, &next, &prev, &target);
- }
-}
+ if (insn_is_nop(&insn)) {
+ int nop = i;
-static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len)
-{
- unsigned long flags;
+ /* Has the NOP already been optimized? */
+ if (i + insn.length == len)
+ return;
- local_irq_save(flags);
- optimize_nops(instr, len);
- sync_core();
- local_irq_restore(flags);
+ next = skip_nops(buf, next, len);
+
+ add_nop(buf + nop, next - nop);
+ DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, next);
+ }
+ }
}
/*
@@ -335,11 +315,9 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len)
return (target < src || target > src + src_len);
}
-void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
+static void __apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
{
- int prev, target = 0;
-
- for (int next, i = 0; i < len; i = next) {
+ for (int next, i = 0; i < instrlen; i = next) {
struct insn insn;
if (WARN_ON_ONCE(insn_decode_kernel(&insn, &buf[i])))
@@ -347,9 +325,6 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
next = i + insn.length;
- if (__optimize_nops(buf, len, &insn, &next, &prev, &target))
- continue;
-
switch (insn.opcode.bytes[0]) {
case 0x0f:
if (insn.opcode.bytes[1] < 0x80 ||
@@ -361,10 +336,10 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
case JMP8_INSN_OPCODE:
case JMP32_INSN_OPCODE:
case CALL_INSN_OPCODE:
- if (need_reloc(next + insn.immediate.value, src, src_len)) {
+ if (need_reloc(next + insn.immediate.value, repl, repl_len)) {
apply_reloc(insn.immediate.nbytes,
buf + i + insn_offset_immediate(&insn),
- src - dest);
+ repl - instr);
}
/*
@@ -372,7 +347,7 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
*/
if (insn.opcode.bytes[0] == JMP32_INSN_OPCODE) {
s32 imm = insn.immediate.value;
- imm += src - dest;
+ imm += repl - instr;
imm += JMP32_INSN_SIZE - JMP8_INSN_SIZE;
if ((imm >> 31) == (imm >> 7)) {
buf[i+0] = JMP8_INSN_OPCODE;
@@ -385,15 +360,21 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
}
if (insn_rip_relative(&insn)) {
- if (need_reloc(next + insn.displacement.value, src, src_len)) {
+ if (need_reloc(next + insn.displacement.value, repl, repl_len)) {
apply_reloc(insn.displacement.nbytes,
buf + i + insn_offset_displacement(&insn),
- src - dest);
+ repl - instr);
}
}
}
}
+void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
+{
+ __apply_relocation(buf, instr, instrlen, repl, repl_len);
+ optimize_nops(instr, buf, instrlen);
+}
+
/* Low-level backend functions usable from alternative code replacements. */
DEFINE_ASM_FUNC(nop_func, "", .entry.text);
EXPORT_SYMBOL_GPL(nop_func);
@@ -464,9 +445,9 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
void __init_or_module noinline apply_alternatives(struct alt_instr *start,
struct alt_instr *end)
{
- struct alt_instr *a;
- u8 *instr, *replacement;
u8 insn_buff[MAX_PATCH_LEN];
+ u8 *instr, *replacement;
+ struct alt_instr *a;
DPRINTK(ALT, "alt table %px, -> %px", start, end);
@@ -504,7 +485,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
* patch if feature is *NOT* present.
*/
if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
- optimize_nops_inplace(instr, a->instrlen);
+ memcpy(insn_buff, instr, a->instrlen);
+ optimize_nops(instr, insn_buff, a->instrlen);
+ text_poke_early(instr, insn_buff, a->instrlen);
continue;
}
@@ -526,7 +509,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
insn_buff[insn_buff_sz] = 0x90;
- apply_relocation(insn_buff, a->instrlen, instr, replacement, a->replacementlen);
+ apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr);
DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
@@ -761,7 +744,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
len = patch_retpoline(addr, &insn, bytes);
if (len == insn.length) {
- optimize_nops(bytes, len);
+ optimize_nops(addr, bytes, len);
DUMP_BYTES(RETPOLINE, ((u8*)addr), len, "%px: orig: ", addr);
DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
text_poke_early(addr, bytes, len);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 2ae98f754e..c884deca83 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -676,7 +676,7 @@ static const struct dma_map_ops gart_dma_ops = {
.get_sgtable = dma_common_get_sgtable,
.dma_supported = dma_direct_supported,
.get_required_mask = dma_direct_get_required_mask,
- .alloc_pages = dma_direct_alloc_pages,
+ .alloc_pages_op = dma_direct_alloc_pages,
.free_pages = dma_direct_free_pages,
};
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 803dcfb0e3..66fd4b2a37 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -497,32 +497,32 @@ static struct clock_event_device lapic_clockevent = {
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
static const struct x86_cpu_id deadline_match[] __initconst = {
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */
+ X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */
+ X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */
- X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, 0x0b000020),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0),
+ X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136),
+ X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014),
+ X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0),
- X86_MATCH_INTEL_FAM6_MODEL( HASWELL, 0x22),
- X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L, 0x20),
- X86_MATCH_INTEL_FAM6_MODEL( HASWELL_G, 0x17),
+ X86_MATCH_VFM(INTEL_HASWELL, 0x22),
+ X86_MATCH_VFM(INTEL_HASWELL_L, 0x20),
+ X86_MATCH_VFM(INTEL_HASWELL_G, 0x17),
- X86_MATCH_INTEL_FAM6_MODEL( BROADWELL, 0x25),
- X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_G, 0x17),
+ X86_MATCH_VFM(INTEL_BROADWELL, 0x25),
+ X86_MATCH_VFM(INTEL_BROADWELL_G, 0x17),
- X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_L, 0xb2),
- X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE, 0xb2),
+ X86_MATCH_VFM(INTEL_SKYLAKE_L, 0xb2),
+ X86_MATCH_VFM(INTEL_SKYLAKE, 0xb2),
- X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE_L, 0x52),
- X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE, 0x52),
+ X86_MATCH_VFM(INTEL_KABYLAKE_L, 0x52),
+ X86_MATCH_VFM(INTEL_KABYLAKE, 0x52),
{},
};
@@ -631,7 +631,7 @@ void lapic_update_tsc_freq(void)
static __initdata int lapic_cal_loops = -1;
static __initdata long lapic_cal_t1, lapic_cal_t2;
static __initdata unsigned long long lapic_cal_tsc1, lapic_cal_tsc2;
-static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
+static __initdata u32 lapic_cal_pm1, lapic_cal_pm2;
static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
/*
@@ -641,7 +641,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
{
unsigned long long tsc = 0;
long tapic = apic_read(APIC_TMCCT);
- unsigned long pm = acpi_pm_read_early();
+ u32 pm = acpi_pm_read_early();
if (boot_cpu_has(X86_FEATURE_TSC))
tsc = rdtsc();
@@ -666,7 +666,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
}
static int __init
-calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
+calibrate_by_pmtimer(u32 deltapm, long *delta, long *deltatsc)
{
const long pm_100ms = PMTMR_TICKS_PER_SEC / 10;
const long pm_thresh = pm_100ms / 100;
@@ -677,7 +677,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
return -1;
#endif
- apic_printk(APIC_VERBOSE, "... PM-Timer delta = %ld\n", deltapm);
+ apic_printk(APIC_VERBOSE, "... PM-Timer delta = %u\n", deltapm);
/* Check, if the PM timer is available */
if (!deltapm)
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index d9651f15ae..340769242d 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -184,7 +184,6 @@ static int x86_msi_prepare(struct irq_domain *domain, struct device *dev,
alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSI;
return 0;
case DOMAIN_BUS_PCI_DEVICE_MSIX:
- case DOMAIN_BUS_PCI_DEVICE_IMS:
alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX;
return 0;
default:
@@ -229,10 +228,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
case DOMAIN_BUS_PCI_DEVICE_MSI:
case DOMAIN_BUS_PCI_DEVICE_MSIX:
break;
- case DOMAIN_BUS_PCI_DEVICE_IMS:
- if (!(pops->supported_flags & MSI_FLAG_PCI_IMS))
- return false;
- break;
default:
WARN_ON_ONCE(1);
return false;
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 29cd0543fc..5573181450 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -965,7 +965,7 @@ static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
lockdep_assert_held(&vector_lock);
hlist_for_each_entry_safe(apicd, tmp, &cl->head, clist) {
- unsigned int irr, vector = apicd->prev_vector;
+ unsigned int vector = apicd->prev_vector;
/*
* Paranoia: Check if the vector that needs to be cleaned
@@ -979,8 +979,7 @@ static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
* fixup_irqs() was just called to scan IRR for set bits and
* forward them to new destination CPUs via IPIs.
*/
- irr = check_irr ? apic_read(APIC_IRR + (vector / 32 * 0x10)) : 0;
- if (irr & (1U << (vector % 32))) {
+ if (check_irr && is_vector_pending(vector)) {
pr_warn_once("Moved interrupt pending in old target APIC %u\n", apicd->irq);
rearm = true;
continue;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 567dbd2fe4..7db83212ef 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -178,13 +178,16 @@ static int x2apic_prepare_cpu(unsigned int cpu)
u32 phys_apicid = apic->cpu_present_to_apicid(cpu);
u32 cluster = apic_cluster(phys_apicid);
u32 logical_apicid = (cluster << 16) | (1 << (phys_apicid & 0xf));
+ int node = cpu_to_node(cpu);
x86_cpu_to_logical_apicid[cpu] = logical_apicid;
- if (alloc_clustermask(cpu, cluster, cpu_to_node(cpu)) < 0)
+ if (alloc_clustermask(cpu, cluster, node) < 0)
return -ENOMEM;
- if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL))
+
+ if (!zalloc_cpumask_var_node(&per_cpu(ipi_mask, cpu), GFP_KERNEL, node))
return -ENOMEM;
+
return 0;
}
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index e92ff0c11d..4656474567 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -185,8 +185,7 @@ static void *patch_dest(void *dest, bool direct)
u8 *pad = dest - tsize;
memcpy(insn_buff, skl_call_thunk_template, tsize);
- apply_relocation(insn_buff, tsize, pad,
- skl_call_thunk_template, tsize);
+ apply_relocation(insn_buff, pad, tsize, skl_call_thunk_template, tsize);
/* Already patched? */
if (!bcmp(pad, insn_buff, tsize))
@@ -308,8 +307,7 @@ static bool is_callthunk(void *addr)
pad = (void *)(dest - tmpl_size);
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, tmpl_size, pad,
- skl_call_thunk_template, tmpl_size);
+ apply_relocation(insn_buff, pad, tmpl_size, skl_call_thunk_template, tmpl_size);
return !bcmp(pad, insn_buff, tmpl_size);
}
@@ -327,8 +325,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
return 0;
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, tmpl_size, ip,
- skl_call_thunk_template, tmpl_size);
+ apply_relocation(insn_buff, ip, tmpl_size, skl_call_thunk_template, tmpl_size);
memcpy(*pprog, insn_buff, tmpl_size);
*pprog += tmpl_size;
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index eb4dbcdf41..a02bba0ed6 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -60,7 +60,7 @@ obj-$(CONFIG_ACRN_GUEST) += acrn.o
obj-$(CONFIG_DEBUG_FS) += debugfs.o
quiet_cmd_mkcapflags = MKCAP $@
- cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^
+ cmd_mkcapflags = $(CONFIG_SHELL) $(src)/mkcapflags.sh $@ $^
cpufeature = $(src)/../../include/asm/cpufeatures.h
vmxfeature = $(src)/../../include/asm/vmxfeatures.h
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 307302af0a..44df3f11e7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -13,6 +13,7 @@
#include <asm/apic.h>
#include <asm/cacheinfo.h>
#include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
#include <asm/spec-ctrl.h>
#include <asm/smp.h>
#include <asm/numa.h>
@@ -794,6 +795,11 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
clear_rdrand_cpuid_bit(c);
}
+static const struct x86_cpu_desc erratum_1386_microcode[] = {
+ AMD_CPU_DESC(0x17, 0x1, 0x2, 0x0800126e),
+ AMD_CPU_DESC(0x17, 0x31, 0x0, 0x08301052),
+};
+
static void fix_erratum_1386(struct cpuinfo_x86 *c)
{
/*
@@ -803,7 +809,13 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c)
*
* Affected parts all have no supervisor XSAVE states, meaning that
* the XSAVEC instruction (which works fine) is equivalent.
+ *
+ * Clear the feature flag only on microcode revisions which
+ * don't have the fix.
*/
+ if (x86_cpu_has_min_microcode_rev(erratum_1386_microcode))
+ return;
+
clear_cpu_cap(c, X86_FEATURE_XSAVES);
}
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index fdbb5f0744..b3fa61d453 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -124,25 +124,24 @@ static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
return true;
}
-#define X86_MATCH(model) \
- X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \
- INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)
+#define X86_MATCH(vfm) \
+ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, NULL)
static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
- X86_MATCH(XEON_PHI_KNL),
- X86_MATCH(XEON_PHI_KNM),
+ X86_MATCH(INTEL_XEON_PHI_KNL),
+ X86_MATCH(INTEL_XEON_PHI_KNM),
{}
};
static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
- X86_MATCH(SKYLAKE_X),
+ X86_MATCH(INTEL_SKYLAKE_X),
{}
};
static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
- X86_MATCH(ATOM_GOLDMONT),
- X86_MATCH(ATOM_GOLDMONT_D),
- X86_MATCH(ATOM_GOLDMONT_PLUS),
+ X86_MATCH(INTEL_ATOM_GOLDMONT),
+ X86_MATCH(INTEL_ATOM_GOLDMONT_D),
+ X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS),
{}
};
@@ -346,6 +345,7 @@ static DECLARE_WORK(disable_freq_invariance_work,
disable_freq_invariance_workfn);
DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
static void scale_freq_tick(u64 acnt, u64 mcnt)
{
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ab18185894..b6f927f6c5 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -26,7 +26,7 @@
#include <asm/msr.h>
#include <asm/vmx.h>
#include <asm/paravirt.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/e820/api.h>
#include <asm/hypervisor.h>
#include <asm/tlbflush.h>
@@ -2391,20 +2391,20 @@ static void override_cache_bits(struct cpuinfo_x86 *c)
if (c->x86 != 6)
return;
- switch (c->x86_model) {
- case INTEL_FAM6_NEHALEM:
- case INTEL_FAM6_WESTMERE:
- case INTEL_FAM6_SANDYBRIDGE:
- case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_HASWELL:
- case INTEL_FAM6_HASWELL_L:
- case INTEL_FAM6_HASWELL_G:
- case INTEL_FAM6_BROADWELL:
- case INTEL_FAM6_BROADWELL_G:
- case INTEL_FAM6_SKYLAKE_L:
- case INTEL_FAM6_SKYLAKE:
- case INTEL_FAM6_KABYLAKE_L:
- case INTEL_FAM6_KABYLAKE:
+ switch (c->x86_vfm) {
+ case INTEL_NEHALEM:
+ case INTEL_WESTMERE:
+ case INTEL_SANDYBRIDGE:
+ case INTEL_IVYBRIDGE:
+ case INTEL_HASWELL:
+ case INTEL_HASWELL_L:
+ case INTEL_HASWELL_G:
+ case INTEL_BROADWELL:
+ case INTEL_BROADWELL_G:
+ case INTEL_SKYLAKE_L:
+ case INTEL_SKYLAKE:
+ case INTEL_KABYLAKE_L:
+ case INTEL_KABYLAKE:
if (c->x86_cache_bits < 44)
c->x86_cache_bits = 44;
break;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1982007828..d4e539d4e1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -68,6 +68,7 @@
#include <asm/traps.h>
#include <asm/sev.h>
#include <asm/tdx.h>
+#include <asm/posted_intr.h>
#include "cpu.h"
@@ -114,17 +115,17 @@ static const struct x86_cpu_id ppin_cpuids[] = {
X86_MATCH_FEATURE(X86_FEATURE_INTEL_PPIN, &ppin_info[X86_VENDOR_INTEL]),
/* Legacy models without CPUID enumeration */
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_HASWELL_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_BROADWELL_D, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_SKYLAKE_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &ppin_info[X86_VENDOR_INTEL]),
{}
};
@@ -1126,8 +1127,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define VULNWL(vendor, family, model, whitelist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
-#define VULNWL_INTEL(model, whitelist) \
- VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+#define VULNWL_INTEL(vfm, whitelist) \
+ X86_MATCH_VFM(vfm, whitelist)
#define VULNWL_AMD(family, whitelist) \
VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
@@ -1144,32 +1145,32 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL(VORTEX, 6, X86_MODEL_ANY, NO_SPECULATION),
/* Intel Family 6 */
- VULNWL_INTEL(TIGERLAKE, NO_MMIO),
- VULNWL_INTEL(TIGERLAKE_L, NO_MMIO),
- VULNWL_INTEL(ALDERLAKE, NO_MMIO),
- VULNWL_INTEL(ALDERLAKE_L, NO_MMIO),
+ VULNWL_INTEL(INTEL_TIGERLAKE, NO_MMIO),
+ VULNWL_INTEL(INTEL_TIGERLAKE_L, NO_MMIO),
+ VULNWL_INTEL(INTEL_ALDERLAKE, NO_MMIO),
+ VULNWL_INTEL(INTEL_ALDERLAKE_L, NO_MMIO),
- VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(CORE_YONAH, NO_SSB),
+ VULNWL_INTEL(INTEL_CORE_YONAH, NO_SSB),
- VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_INTEL(INTEL_ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_INTEL(INTEL_ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
/*
* Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1179,9 +1180,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
* good enough for our purposes.
*/
- VULNWL_INTEL(ATOM_TREMONT, NO_EIBRS_PBRSB),
- VULNWL_INTEL(ATOM_TREMONT_L, NO_EIBRS_PBRSB),
- VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_TREMONT, NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_TREMONT_L, NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
/* AMD Family 0xf - 0x12 */
VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
@@ -1202,10 +1203,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define VULNBL(vendor, family, model, blacklist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist)
-#define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \
- X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \
- INTEL_FAM6_##model, steppings, \
- X86_FEATURE_ANY, issues)
+#define VULNBL_INTEL_STEPPINGS(vfm, steppings, issues) \
+ X86_MATCH_VFM_STEPPINGS(vfm, steppings, issues)
#define VULNBL_AMD(family, blacklist) \
VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
@@ -1230,43 +1229,43 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define RFDS BIT(7)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
- VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
- VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
- VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS),
- VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS),
- VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS),
- VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_L, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_G, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_X, X86_STEPPING_ANY, MMIO),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPING_ANY, MMIO),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_G, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_X, X86_STEPPING_ANY, MMIO),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
+ VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE_L, X86_STEPPING_ANY, GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE, X86_STEPPING_ANY, GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(INTEL_ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE_L, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_P, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_S, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS),
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
@@ -2229,6 +2228,8 @@ void cpu_init(void)
barrier();
x2apic_setup();
+
+ intel_posted_msi_init();
}
mmgrab(&init_mm);
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 946813d816..b7d9f530ae 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -114,6 +114,9 @@ static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
if (WARN_ON(feature >= MAX_FEATURE_BITS))
return;
+ if (boot_cpu_has(feature))
+ WARN_ON(alternatives_patched);
+
clear_feature(c, feature);
/* Collect all features to disable, handling dependencies */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 93efd9edc7..fdf3489d92 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -228,6 +228,7 @@ static void detect_tme_early(struct cpuinfo_x86 *c)
if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
pr_info_once("x86/tme: not enabled by BIOS\n");
mktme_status = MKTME_DISABLED;
+ clear_cpu_cap(c, X86_FEATURE_TME);
return;
}
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index f18d35fe27..30b1d63b97 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -204,12 +204,12 @@ static int intel_epb_offline(unsigned int cpu)
}
static const struct x86_cpu_id intel_epb_normal[] = {
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,
- ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,
- ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,
- ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L,
+ ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT,
+ ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P,
+ ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
{}
};
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index ae71b8ef90..8e7de73332 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -17,8 +17,7 @@
*
* A typical table entry would be to match a specific CPU
*
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL,
- * X86_FEATURE_ANY, NULL);
+ * X86_MATCH_VFM_FEATURE(INTEL_BROADWELL, X86_FEATURE_ANY, NULL);
*
* Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY,
* %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor)
@@ -26,7 +25,7 @@
* asm/cpu_device_id.h contains a set of useful macros which are shortcuts
* for various common selections. The above can be shortened to:
*
- * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL);
+ * X86_MATCH_VFM(INTEL_BROADWELL, NULL);
*
* Arrays used to match for this should also be declared using
* MODULE_DEVICE_TABLE(x86cpu, ...)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 84d41be6d0..ad0623b659 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -47,7 +47,7 @@
#include <linux/kexec.h>
#include <asm/fred.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/traps.h>
#include <asm/tlbflush.h>
@@ -1593,6 +1593,24 @@ noinstr void do_machine_check(struct pt_regs *regs)
else
queue_task_work(&m, msg, kill_me_maybe);
+ } else if (m.mcgstatus & MCG_STATUS_SEAM_NR) {
+ /*
+ * Saved RIP on stack makes it look like the machine check
+ * was taken in the kernel on the instruction following
+ * the entry to SEAM mode. But MCG_STATUS_SEAM_NR indicates
+ * that the machine check was taken inside SEAM non-root
+ * mode. CPU core has already marked that guest as dead.
+ * It is OK for the kernel to resume execution at the
+ * apparent point of the machine check as the fault did
+ * not occur there. Mark the page as poisoned so it won't
+ * be added to free list when the guest is terminated.
+ */
+ if (mce_usable_address(&m)) {
+ struct page *p = pfn_to_online_page(m.addr >> PAGE_SHIFT);
+
+ if (p)
+ SetPageHWPoison(p);
+ }
} else {
/*
* Handle an MCE which has happened in kernel space but from
@@ -1930,14 +1948,14 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0)
cfg->bootlog = 0;
- if (c->x86 == 6 && c->x86_model == 45)
+ if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
mce_flags.snb_ifu_quirk = 1;
/*
* Skylake, Cascacde Lake and Cooper Lake require a quirk on
* rep movs.
*/
- if (c->x86 == 6 && c->x86_model == INTEL_FAM6_SKYLAKE_X)
+ if (c->x86_vfm == INTEL_SKYLAKE_X)
mce_flags.skx_repmov_quirk = 1;
}
diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index fbe8b61c34..4284749ec8 100644
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -16,14 +16,14 @@
* used to save error information organized in a lock-less list.
*
* This memory pool is only to be used to save MCE records in MCE context.
- * MCE events are rare, so a fixed size memory pool should be enough. Use
- * 2 pages to save MCE events for now (~80 MCE records at most).
+ * MCE events are rare, so a fixed size memory pool should be enough.
+ * Allocate on a sliding scale based on number of CPUs.
*/
-#define MCE_POOLSZ (2 * PAGE_SIZE)
+#define MCE_MIN_ENTRIES 80
+#define MCE_PER_CPU 2
static struct gen_pool *mce_evt_pool;
static LLIST_HEAD(mce_event_llist);
-static char gen_pool_buf[MCE_POOLSZ];
/*
* Compare the record "t" with each of the records on list "l" to see if
@@ -118,22 +118,32 @@ int mce_gen_pool_add(struct mce *mce)
static int mce_gen_pool_create(void)
{
- struct gen_pool *tmpp;
+ int mce_numrecords, mce_poolsz, order;
+ struct gen_pool *gpool;
int ret = -ENOMEM;
-
- tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
- if (!tmpp)
- goto out;
-
- ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+ void *mce_pool;
+
+ order = order_base_2(sizeof(struct mce_evt_llist));
+ gpool = gen_pool_create(order, -1);
+ if (!gpool)
+ return ret;
+
+ mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU);
+ mce_poolsz = mce_numrecords * (1 << order);
+ mce_pool = kmalloc(mce_poolsz, GFP_KERNEL);
+ if (!mce_pool) {
+ gen_pool_destroy(gpool);
+ return ret;
+ }
+ ret = gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1);
if (ret) {
- gen_pool_destroy(tmpp);
- goto out;
+ gen_pool_destroy(gpool);
+ kfree(mce_pool);
+ return ret;
}
- mce_evt_pool = tmpp;
+ mce_evt_pool = gpool;
-out:
return ret;
}
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 399b62e223..f6103e6bf6 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -13,7 +13,7 @@
#include <linux/cpumask.h>
#include <asm/apic.h>
#include <asm/cpufeature.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/mce.h>
@@ -455,10 +455,10 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
{
u64 error_control;
- switch (c->x86_model) {
- case INTEL_FAM6_SANDYBRIDGE_X:
- case INTEL_FAM6_IVYBRIDGE_X:
- case INTEL_FAM6_HASWELL_X:
+ switch (c->x86_vfm) {
+ case INTEL_SANDYBRIDGE_X:
+ case INTEL_IVYBRIDGE_X:
+ case INTEL_HASWELL_X:
if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control))
return;
error_control |= 2;
@@ -484,12 +484,11 @@ bool intel_filter_mce(struct mce *m)
struct cpuinfo_x86 *c = &boot_cpu_data;
/* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */
- if ((c->x86 == 6) &&
- ((c->x86_model == INTEL_FAM6_HASWELL) ||
- (c->x86_model == INTEL_FAM6_HASWELL_L) ||
- (c->x86_model == INTEL_FAM6_BROADWELL) ||
- (c->x86_model == INTEL_FAM6_HASWELL_G) ||
- (c->x86_model == INTEL_FAM6_SKYLAKE_X)) &&
+ if ((c->x86_vfm == INTEL_HASWELL ||
+ c->x86_vfm == INTEL_HASWELL_L ||
+ c->x86_vfm == INTEL_BROADWELL ||
+ c->x86_vfm == INTEL_HASWELL_G ||
+ c->x86_vfm == INTEL_SKYLAKE_X) &&
(m->bank == 0) &&
((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
return true;
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index c4477162c0..dac4d64dfb 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -12,7 +12,7 @@
#include <linux/uaccess.h>
#include <asm/mce.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/traps.h>
#include <asm/insn.h>
#include <asm/insn-eval.h>
@@ -39,20 +39,20 @@ static struct severity {
u64 mask;
u64 result;
unsigned char sev;
- unsigned char mcgmask;
- unsigned char mcgres;
+ unsigned short mcgmask;
+ unsigned short mcgres;
unsigned char ser;
unsigned char context;
unsigned char excp;
unsigned char covered;
- unsigned char cpu_model;
+ unsigned int cpu_vfm;
unsigned char cpu_minstepping;
unsigned char bank_lo, bank_hi;
char *msg;
} severities[] = {
#define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c }
#define BANK_RANGE(l, h) .bank_lo = l, .bank_hi = h
-#define MODEL_STEPPING(m, s) .cpu_model = m, .cpu_minstepping = s
+#define VFM_STEPPING(m, s) .cpu_vfm = m, .cpu_minstepping = s
#define KERNEL .context = IN_KERNEL
#define USER .context = IN_USER
#define KERNEL_RECOV .context = IN_KERNEL_RECOV
@@ -128,7 +128,7 @@ static struct severity {
MCESEV(
AO, "Uncorrected Patrol Scrub Error",
SER, MASK(MCI_STATUS_UC|MCI_ADDR|0xffffeff0, MCI_ADDR|0x001000c0),
- MODEL_STEPPING(INTEL_FAM6_SKYLAKE_X, 4), BANK_RANGE(13, 18)
+ VFM_STEPPING(INTEL_SKYLAKE_X, 4), BANK_RANGE(13, 18)
),
/* ignore OVER for UCNA */
@@ -174,6 +174,18 @@ static struct severity {
USER
),
MCESEV(
+ AR, "Data load error in SEAM non-root mode",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+ MCGMASK(MCG_STATUS_SEAM_NR, MCG_STATUS_SEAM_NR),
+ KERNEL
+ ),
+ MCESEV(
+ AR, "Instruction fetch error in SEAM non-root mode",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+ MCGMASK(MCG_STATUS_SEAM_NR, MCG_STATUS_SEAM_NR),
+ KERNEL
+ ),
+ MCESEV(
PANIC, "Data load in unrecoverable area of kernel",
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
KERNEL
@@ -290,7 +302,6 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs)
switch (fixup_type) {
case EX_TYPE_UACCESS:
- case EX_TYPE_COPY:
if (!copy_user)
return IN_KERNEL;
m->kflags |= MCE_IN_KERNEL_COPYIN;
@@ -386,7 +397,7 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char
continue;
if (s->excp && excp != s->excp)
continue;
- if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model)
+ if (s->cpu_vfm && boot_cpu_data.x86_vfm != s->cpu_vfm)
continue;
if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping)
continue;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 620f0af713..c0d56c02b8 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -84,8 +84,6 @@ struct microcode_amd {
unsigned int mpb[];
};
-#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
-
static struct equiv_cpu_table {
unsigned int num_entries;
struct equiv_cpu_entry *entry;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 232026a239..b3658d11e7 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -60,11 +60,6 @@ module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
*/
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
-struct cpu_info_ctx {
- struct cpu_signature *cpu_sig;
- int err;
-};
-
/*
* Those patch levels cannot be updated to newer ones and thus should be final.
*/
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 5f0414452b..815fa67356 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -21,7 +21,7 @@
#include <linux/uio.h>
#include <linux/mm.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/setup.h>
@@ -577,8 +577,7 @@ static bool is_blacklisted(unsigned int cpu)
* This behavior is documented in item BDF90, #334165 (Intel Xeon
* Processor E7-8800/4800 v4 Product Family).
*/
- if (c->x86 == 6 &&
- c->x86_model == INTEL_FAM6_BROADWELL_X &&
+ if (c->x86_vfm == INTEL_BROADWELL_X &&
c->x86_stepping == 0x01 &&
llc_size_per_core > 2621440 &&
c->microcode < 0x0b000021) {
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 83e4034158..a113d9aba5 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
#include <linux/cacheinfo.h>
#include <linux/cpuhotplug.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/resctrl.h>
#include "internal.h"
@@ -56,14 +56,9 @@ int max_name_width, max_data_width;
*/
bool rdt_alloc_capable;
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r);
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r);
+static void mba_wrmsr_intel(struct msr_param *m);
+static void cat_wrmsr(struct msr_param *m);
+static void mba_wrmsr_amd(struct msr_param *m);
#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
@@ -309,12 +304,11 @@ static void rdt_get_cdp_l2_config(void)
rdt_get_cdp_config(RDT_RESOURCE_L2);
}
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void mba_wrmsr_amd(struct msr_param *m)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
for (i = m->low; i < m->high; i++)
wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -334,25 +328,22 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
return r->default_ctrl;
}
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r)
+static void mba_wrmsr_intel(struct msr_param *m)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
/* Write the delay values for mba. */
for (i = m->low; i < m->high; i++)
- wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r));
+ wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
}
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void cat_wrmsr(struct msr_param *m)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
for (i = m->low; i < m->high; i++)
wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -362,6 +353,8 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
{
struct rdt_domain *d;
+ lockdep_assert_cpus_held();
+
list_for_each_entry(d, &r->domains, list) {
/* Find the domain that contains this CPU */
if (cpumask_test_cpu(cpu, &d->cpu_mask))
@@ -378,19 +371,11 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
void rdt_ctrl_update(void *arg)
{
+ struct rdt_hw_resource *hw_res;
struct msr_param *m = arg;
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
- struct rdt_resource *r = m->res;
- int cpu = smp_processor_id();
- struct rdt_domain *d;
- d = get_domain_from_cpu(cpu, r);
- if (d) {
- hw_res->msr_update(d, m, r);
- return;
- }
- pr_warn_once("cpu %d not found in any domain for resource %s\n",
- cpu, r->name);
+ hw_res = resctrl_to_arch_res(m->res);
+ hw_res->msr_update(m);
}
/*
@@ -463,9 +448,11 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
hw_dom->ctrl_val = dc;
setup_default_ctrlval(r, dc);
+ m.res = r;
+ m.dom = d;
m.low = 0;
m.high = hw_res->num_closid;
- hw_res->msr_update(d, &m, r);
+ hw_res->msr_update(&m);
return 0;
}
@@ -821,18 +808,18 @@ static __init bool get_rdt_mon_resources(void)
static __init void __check_quirks_intel(void)
{
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_HASWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_HASWELL_X:
if (!rdt_options[RDT_FLAG_L3_CAT].force_off)
cache_alloc_hsw_probe();
break;
- case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_SKYLAKE_X:
if (boot_cpu_data.x86_stepping <= 4)
set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
else
set_rdt_options("!l3cat");
fallthrough;
- case INTEL_FAM6_BROADWELL_X:
+ case INTEL_BROADWELL_X:
intel_rdt_mbm_apply_quirk();
break;
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 7997b47743..b7291f6039 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -272,22 +272,6 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
}
}
-static bool apply_config(struct rdt_hw_domain *hw_dom,
- struct resctrl_staged_config *cfg, u32 idx,
- cpumask_var_t cpu_mask)
-{
- struct rdt_domain *dom = &hw_dom->d_resctrl;
-
- if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
- cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
- hw_dom->ctrl_val[idx] = cfg->new_ctrl;
-
- return true;
- }
-
- return false;
-}
-
int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
u32 closid, enum resctrl_conf_type t, u32 cfg_val)
{
@@ -302,9 +286,10 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
hw_dom->ctrl_val[idx] = cfg_val;
msr_param.res = r;
+ msr_param.dom = d;
msr_param.low = idx;
msr_param.high = idx + 1;
- hw_res->msr_update(d, &msr_param, r);
+ hw_res->msr_update(&msr_param);
return 0;
}
@@ -315,48 +300,39 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
struct rdt_hw_domain *hw_dom;
struct msr_param msr_param;
enum resctrl_conf_type t;
- cpumask_var_t cpu_mask;
struct rdt_domain *d;
u32 idx;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
- if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
- return -ENOMEM;
-
- msr_param.res = NULL;
list_for_each_entry(d, &r->domains, list) {
hw_dom = resctrl_to_arch_dom(d);
+ msr_param.res = NULL;
for (t = 0; t < CDP_NUM_TYPES; t++) {
cfg = &hw_dom->d_resctrl.staged_config[t];
if (!cfg->have_new_ctrl)
continue;
idx = get_config_index(closid, t);
- if (!apply_config(hw_dom, cfg, idx, cpu_mask))
+ if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
continue;
+ hw_dom->ctrl_val[idx] = cfg->new_ctrl;
if (!msr_param.res) {
msr_param.low = idx;
msr_param.high = msr_param.low + 1;
msr_param.res = r;
+ msr_param.dom = d;
} else {
msr_param.low = min(msr_param.low, idx);
msr_param.high = max(msr_param.high, idx + 1);
}
}
+ if (msr_param.res)
+ smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
}
- if (cpumask_empty(cpu_mask))
- goto done;
-
- /* Update resource control msr on all the CPUs. */
- on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-done:
- free_cpumask_var(cpu_mask);
-
return 0;
}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 1a8687f807..f1d926832e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -379,11 +379,13 @@ static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
/**
* struct msr_param - set a range of MSRs from a domain
* @res: The resource to use
+ * @dom: The domain to update
* @low: Beginning index from base MSR
* @high: End index
*/
struct msr_param {
struct rdt_resource *res;
+ struct rdt_domain *dom;
u32 low;
u32 high;
};
@@ -443,8 +445,7 @@ struct rdt_hw_resource {
struct rdt_resource r_resctrl;
u32 num_closid;
unsigned int msr_base;
- void (*msr_update) (struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r);
+ void (*msr_update)(struct msr_param *m);
unsigned int mon_scale;
unsigned int mbm_width;
unsigned int mbm_cfg_mask;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 2ce5f4913c..366f496ca3 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -24,6 +24,7 @@
#include <asm/resctrl.h>
#include "internal.h"
+#include "trace.h"
/**
* struct rmid_entry - dirty tracking for all RMID.
@@ -354,6 +355,16 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
rmid_dirty = true;
} else {
rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+
+ /*
+ * x86's CLOSID and RMID are independent numbers, so the entry's
+ * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
+ * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
+ * used to select the configuration. It is thus necessary to track both
+ * CLOSID and RMID because there may be dependencies between them
+ * on some architectures.
+ */
+ trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->id, val);
}
if (force_free || !rmid_dirty) {
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 884b88e251..aacf236dfe 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -23,7 +23,7 @@
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/resctrl.h>
#include <asm/perf_event.h>
@@ -31,7 +31,7 @@
#include "internal.h"
#define CREATE_TRACE_POINTS
-#include "pseudo_lock_event.h"
+#include "trace.h"
/*
* The bits needed to disable hardware prefetching varies based on the
@@ -88,8 +88,8 @@ static u64 get_prefetch_disable_bits(void)
boot_cpu_data.x86 != 6)
return 0;
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_BROADWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_BROADWELL_X:
/*
* SDM defines bits of MSR_MISC_FEATURE_CONTROL register
* as:
@@ -100,8 +100,8 @@ static u64 get_prefetch_disable_bits(void)
* 63:4 Reserved
*/
return 0xF;
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_PLUS:
/*
* SDM defines bits of MSR_MISC_FEATURE_CONTROL register
* as:
@@ -1084,9 +1084,9 @@ static int measure_l2_residency(void *_plr)
* L2_HIT 02H
* L2_MISS 10H
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_PLUS:
perf_miss_attr.config = X86_CONFIG(.event = 0xd1,
.umask = 0x10);
perf_hit_attr.config = X86_CONFIG(.event = 0xd1,
@@ -1123,8 +1123,8 @@ static int measure_l3_residency(void *_plr)
* MISS 41H
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_BROADWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_BROADWELL_X:
/* On BDW the hit event counts references, not hits */
perf_hit_attr.config = X86_CONFIG(.event = 0x2e,
.umask = 0x4f);
@@ -1142,7 +1142,7 @@ static int measure_l3_residency(void *_plr)
*/
counts.miss_after -= counts.miss_before;
- if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) {
+ if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_X) {
/*
* On BDW references and misses are counted, need to adjust.
* Sometimes the "hits" counter is a bit more than the
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 011e17efb1..02f213f1c5 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2813,16 +2813,12 @@ static int reset_all_ctrls(struct rdt_resource *r)
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
struct rdt_hw_domain *hw_dom;
struct msr_param msr_param;
- cpumask_var_t cpu_mask;
struct rdt_domain *d;
int i;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
- if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
- return -ENOMEM;
-
msr_param.res = r;
msr_param.low = 0;
msr_param.high = hw_res->num_closid;
@@ -2834,17 +2830,13 @@ static int reset_all_ctrls(struct rdt_resource *r)
*/
list_for_each_entry(d, &r->domains, list) {
hw_dom = resctrl_to_arch_dom(d);
- cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
for (i = 0; i < hw_res->num_closid; i++)
hw_dom->ctrl_val[i] = r->default_ctrl;
+ msr_param.dom = d;
+ smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
}
- /* Update CBM on all the CPUs in cpu_mask */
- on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
- free_cpumask_var(cpu_mask);
-
return 0;
}
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h b/arch/x86/kernel/cpu/resctrl/trace.h
index 428ebbd427..2a506316b3 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/resctrl/trace.h
@@ -2,8 +2,8 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM resctrl
-#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_PSEUDO_LOCK_H
+#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RESCTRL_H
#include <linux/tracepoint.h>
@@ -35,9 +35,25 @@ TRACE_EVENT(pseudo_lock_l3,
TP_printk("hits=%llu miss=%llu",
__entry->l3_hits, __entry->l3_miss));
-#endif /* _TRACE_PSEUDO_LOCK_H */
+TRACE_EVENT(mon_llc_occupancy_limbo,
+ TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
+ TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
+ TP_STRUCT__entry(__field(u32, ctrl_hw_id)
+ __field(u32, mon_hw_id)
+ __field(int, domain_id)
+ __field(u64, llc_occupancy_bytes)),
+ TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
+ __entry->mon_hw_id = mon_hw_id;
+ __entry->domain_id = domain_id;
+ __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
+ TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
+ __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
+ __entry->llc_occupancy_bytes)
+ );
+
+#endif /* _TRACE_RESCTRL_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE pseudo_lock_event
+#define TRACE_INCLUDE_FILE trace
#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 262f5fb18d..22b65a5f5e 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file,
if (flags & MAP_FIXED)
return addr;
- return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+ return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 166692f2d5..27892e57c4 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -13,6 +13,7 @@
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
#include <asm/sgx.h>
#include "driver.h"
#include "encl.h"
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 5ee6373d4d..7d476fa697 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -58,7 +58,7 @@ static void store_node(struct topo_scan *tscan, u16 nr_nodes, u16 node_id)
tscan->amd_node_id = node_id;
}
-static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb)
+static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext)
{
struct {
// eax
@@ -86,7 +86,7 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb)
* If leaf 0xb is available, then the domain shifts are set
* already and nothing to do here. Only valid for family >= 0x17.
*/
- if (!has_0xb && tscan->c->x86 >= 0x17) {
+ if (!has_topoext && tscan->c->x86 >= 0x17) {
/*
* Leaf 0x80000008 set the CORE domain shift already.
* Update the SMT domain, but do not propagate it.
@@ -169,21 +169,24 @@ static void topoext_fixup(struct topo_scan *tscan)
static void parse_topology_amd(struct topo_scan *tscan)
{
- bool has_0xb = false;
+ bool has_topoext = false;
/*
* If the extended topology leaf 0x8000_001e is available
- * try to get SMT and CORE shift from leaf 0xb first, then
- * try to get the CORE shift from leaf 0x8000_0008.
+ * try to get SMT, CORE, TILE, and DIE shifts from extended
+ * CPUID leaf 0x8000_0026 on supported processors first. If
+ * extended CPUID leaf 0x8000_0026 is not supported, try to
+ * get SMT and CORE shift from leaf 0xb first, then try to
+ * get the CORE shift from leaf 0x8000_0008.
*/
if (cpu_feature_enabled(X86_FEATURE_TOPOEXT))
- has_0xb = cpu_parse_topology_ext(tscan);
+ has_topoext = cpu_parse_topology_ext(tscan);
- if (!has_0xb && !parse_8000_0008(tscan))
+ if (!has_topoext && !parse_8000_0008(tscan))
return;
/* Prefer leaf 0x8000001e if available */
- if (parse_8000_001e(tscan, has_0xb))
+ if (parse_8000_001e(tscan, has_topoext))
return;
/* Try the NODEID MSR */
diff --git a/arch/x86/kernel/cpu/topology_ext.c b/arch/x86/kernel/cpu/topology_ext.c
index e477228cd5..467b0326bf 100644
--- a/arch/x86/kernel/cpu/topology_ext.c
+++ b/arch/x86/kernel/cpu/topology_ext.c
@@ -13,7 +13,10 @@ enum topo_types {
CORE_TYPE = 2,
MAX_TYPE_0B = 3,
MODULE_TYPE = 3,
+ AMD_CCD_TYPE = 3,
TILE_TYPE = 4,
+ AMD_SOCKET_TYPE = 4,
+ MAX_TYPE_80000026 = 5,
DIE_TYPE = 5,
DIEGRP_TYPE = 6,
MAX_TYPE_1F = 7,
@@ -32,6 +35,13 @@ static const unsigned int topo_domain_map_0b_1f[MAX_TYPE_1F] = {
[DIEGRP_TYPE] = TOPO_DIEGRP_DOMAIN,
};
+static const unsigned int topo_domain_map_80000026[MAX_TYPE_80000026] = {
+ [SMT_TYPE] = TOPO_SMT_DOMAIN,
+ [CORE_TYPE] = TOPO_CORE_DOMAIN,
+ [AMD_CCD_TYPE] = TOPO_TILE_DOMAIN,
+ [AMD_SOCKET_TYPE] = TOPO_DIE_DOMAIN,
+};
+
static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf,
unsigned int *last_dom)
{
@@ -56,6 +66,7 @@ static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf,
switch (leaf) {
case 0x0b: maxtype = MAX_TYPE_0B; map = topo_domain_map_0b_1f; break;
case 0x1f: maxtype = MAX_TYPE_1F; map = topo_domain_map_0b_1f; break;
+ case 0x80000026: maxtype = MAX_TYPE_80000026; map = topo_domain_map_80000026; break;
default: return false;
}
@@ -125,6 +136,10 @@ bool cpu_parse_topology_ext(struct topo_scan *tscan)
if (tscan->c->cpuid_level >= 0x1f && parse_topology_leaf(tscan, 0x1f))
return true;
+ /* AMD: Try leaf 0x80000026 first. */
+ if (tscan->c->extended_cpuid_level >= 0x80000026 && parse_topology_leaf(tscan, 0x80000026))
+ return true;
+
/* Intel/AMD: Fall back to leaf 0xB if available */
return tscan->c->cpuid_level >= 0x0b && parse_topology_leaf(tscan, 0x0b);
}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e74d0c4286..f06501445c 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -402,20 +402,26 @@ int crash_load_segments(struct kimage *image)
#undef pr_fmt
#define pr_fmt(fmt) "crash hp: " fmt
-/* These functions provide the value for the sysfs crash_hotplug nodes */
-#ifdef CONFIG_HOTPLUG_CPU
-int arch_crash_hotplug_cpu_support(void)
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
{
- return crash_check_update_elfcorehdr();
-}
-#endif
-#ifdef CONFIG_MEMORY_HOTPLUG
-int arch_crash_hotplug_memory_support(void)
-{
- return crash_check_update_elfcorehdr();
-}
+#ifdef CONFIG_KEXEC_FILE
+ if (image->file_mode)
+ return 1;
#endif
+ /*
+ * Initially, crash hotplug support for kexec_load was added
+ * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this
+ * functionality was expanded to accommodate multiple kexec
+ * segment updates, leading to the introduction of the
+ * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently,
+ * when the kexec tool sends either of these flags, it indicates
+ * that the required kexec segment (elfcorehdr) is excluded from
+ * the SHA calculation.
+ */
+ return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR ||
+ kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT);
+}
unsigned int arch_crash_get_elfcorehdr_size(void)
{
@@ -432,10 +438,12 @@ unsigned int arch_crash_get_elfcorehdr_size(void)
/**
* arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
* @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and
+ * NULL for CPU hotplug case.
*
* Prepare the new elfcorehdr and replace the existing elfcorehdr.
*/
-void arch_crash_handle_hotplug_event(struct kimage *image)
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
{
void *elfbuf = NULL, *old_elfcorehdr;
unsigned long nr_mem_ranges;
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 003e0298f4..64280879c6 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -24,6 +24,7 @@
#include <asm/pci_x86.h>
#include <asm/setup.h>
#include <asm/i8259.h>
+#include <asm/numa.h>
#include <asm/prom.h>
__initdata u64 initial_dtb;
@@ -82,7 +83,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
if (ret)
- return ret;
+ return pcibios_err_to_errno(ret);
if (!pin)
return 0;
@@ -137,6 +138,7 @@ static void __init dtb_cpu_setup(void)
continue;
}
topology_register_apic(apic_id, CPU_ACPIID_INVALID, true);
+ set_apicid_to_node(apic_id, of_node_to_nid(dn));
}
}
@@ -277,9 +279,18 @@ static void __init dtb_apic_setup(void)
dtb_ioapic_setup();
}
-#ifdef CONFIG_OF_EARLY_FLATTREE
+static void __init x86_dtb_parse_smp_config(void)
+{
+ if (!of_have_populated_dt())
+ return;
+
+ dtb_setup_hpet();
+ dtb_apic_setup();
+}
+
void __init x86_flattree_get_config(void)
{
+#ifdef CONFIG_OF_EARLY_FLATTREE
u32 size, map_len;
void *dt;
@@ -301,14 +312,7 @@ void __init x86_flattree_get_config(void)
if (initial_dtb)
early_memunmap(dt, map_len);
-}
#endif
-
-void __init x86_dtb_parse_smp_config(void)
-{
- if (!of_have_populated_dt())
- return;
-
- dtb_setup_hpet();
- dtb_apic_setup();
+ if (of_have_populated_dt())
+ x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 44a91ef5a2..a7d562697e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -405,8 +405,8 @@ static void __die_header(const char *str, struct pt_regs *regs, long err)
pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
printk(KERN_DEFAULT
- "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
- pr,
+ "Oops: %s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff,
+ ++die_counter, pr,
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 33a214b1a4..c5a026fee5 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -991,6 +991,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
return __raw_xsave_addr(xsave, xfeature_nr);
}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
#ifdef CONFIG_ARCH_HAS_PKEYS
@@ -1434,8 +1435,8 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
return rstor;
/*
- * XSAVE(S): clone(), fpu_swap_kvm_fpu()
- * XRSTORS(S): fpu_swap_kvm_fpu()
+ * XSAVE(S): clone(), fpu_swap_kvm_fpstate()
+ * XRSTORS(S): fpu_swap_kvm_fpstate()
*/
/*
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 19ca623ffa..05df04f396 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -54,8 +54,6 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void
extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system_xstate(unsigned int legacy_size);
-extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
-
static inline u64 xfeatures_mask_supervisor(void)
{
return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 70139d9d2e..8da0e66ca2 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -25,6 +25,7 @@
#include <linux/memory.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
+#include <linux/execmem.h>
#include <trace/syscall.h>
@@ -260,25 +261,14 @@ void arch_ftrace_update_code(int command)
/* Currently only x86_64 supports dynamic trampolines */
#ifdef CONFIG_X86_64
-#ifdef CONFIG_MODULES
-#include <linux/moduleloader.h>
-/* Module allocation simplifies allocating memory for code */
static inline void *alloc_tramp(unsigned long size)
{
- return module_alloc(size);
+ return execmem_alloc(EXECMEM_FTRACE, size);
}
static inline void tramp_free(void *tramp)
{
- module_memfree(tramp);
+ execmem_free(tramp);
}
-#else
-/* Trampolines can only be created if modules are supported */
-static inline void *alloc_tramp(unsigned long size)
-{
- return NULL;
-}
-static inline void tramp_free(void *tramp) { }
-#endif
/* Defined as markers to the end of the ftrace default trampolines */
extern void ftrace_regs_caller_end(void);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b50f3641c4..2e42056d23 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -44,9 +44,6 @@
#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability
#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id
-
-#define SIZEOF_PTREGS 17*4
-
/*
* Worst-case size of the kernel mapping we need to make:
* a relocatable kernel can live anywhere in lowmem, so we need to be able
@@ -488,19 +485,13 @@ SYM_DATA_END(initial_page_table)
.data
.balign 4
-/*
- * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder
- * reliably detect the end of the stack.
- */
-SYM_DATA(initial_stack,
- .long init_thread_union + THREAD_SIZE -
- SIZEOF_PTREGS - TOP_OF_KERNEL_STACK_PADDING)
+SYM_DATA(initial_stack, .long __top_init_kernel_stack)
__INITRODATA
int_msg:
.asciz "Unknown interrupt or fault at: %p %p %p\n"
-#include "../../x86/xen/xen-head.S"
+#include "../xen/xen-head.S"
/*
* The IDT and GDT 'descriptors' are a strange 48-bit object
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d8198fbd70..330922b328 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -66,7 +66,7 @@ SYM_CODE_START_NOALIGN(startup_64)
mov %rsi, %r15
/* Set up the stack for verify_cpu() */
- leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
+ leaq __top_init_kernel_stack(%rip), %rsp
/* Setup GSBASE to allow stack canary access for C code */
movl $MSR_GS_BASE, %ecx
@@ -720,7 +720,7 @@ SYM_DATA(smpboot_control, .long 0)
SYM_DATA(phys_base, .quad 0x0)
EXPORT_SYMBOL(phys_base)
-#include "../../x86/xen/xen-head.S"
+#include "../xen/xen-head.S"
__PAGE_ALIGNED_BSS
SYM_DATA_START_PAGE_ALIGNED(empty_zero_page)
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index fc37c8d83d..f445bec516 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -163,6 +163,9 @@ static const __initconst struct idt_data apic_idts[] = {
# endif
INTG(SPURIOUS_APIC_VECTOR, asm_sysvec_spurious_apic_interrupt),
INTG(ERROR_APIC_VECTOR, asm_sysvec_error_interrupt),
+# ifdef CONFIG_X86_POSTED_MSI
+ INTG(POSTED_MSI_NOTIFICATION_VECTOR, asm_sysvec_posted_msi_notification),
+# endif
#endif
};
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 35fde01079..385e3a5fc3 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,8 @@
#include <asm/desc.h>
#include <asm/traps.h>
#include <asm/thermal.h>
+#include <asm/posted_intr.h>
+#include <asm/irq_remapping.h>
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
@@ -182,6 +184,13 @@ int arch_show_interrupts(struct seq_file *p, int prec)
irq_stats(j)->kvm_posted_intr_wakeup_ipis);
seq_puts(p, " Posted-interrupt wakeup event\n");
#endif
+#ifdef CONFIG_X86_POSTED_MSI
+ seq_printf(p, "%*s: ", prec, "PMN");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->posted_msi_notification_count);
+ seq_puts(p, " Posted MSI notification event\n");
+#endif
return 0;
}
@@ -240,24 +249,16 @@ static __always_inline void handle_irq(struct irq_desc *desc,
__handle_irq(desc, regs);
}
-/*
- * common_interrupt() handles all normal device IRQ's (the special SMP
- * cross-CPU interrupts have their own entry points).
- */
-DEFINE_IDTENTRY_IRQ(common_interrupt)
+static __always_inline int call_irq_handler(int vector, struct pt_regs *regs)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
struct irq_desc *desc;
-
- /* entry code tells RCU that we're not quiescent. Check it. */
- RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
+ int ret = 0;
desc = __this_cpu_read(vector_irq[vector]);
if (likely(!IS_ERR_OR_NULL(desc))) {
handle_irq(desc, regs);
} else {
- apic_eoi();
-
+ ret = -EINVAL;
if (desc == VECTOR_UNUSED) {
pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n",
__func__, smp_processor_id(),
@@ -267,6 +268,23 @@ DEFINE_IDTENTRY_IRQ(common_interrupt)
}
}
+ return ret;
+}
+
+/*
+ * common_interrupt() handles all normal device IRQ's (the special SMP
+ * cross-CPU interrupts have their own entry points).
+ */
+DEFINE_IDTENTRY_IRQ(common_interrupt)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ /* entry code tells RCU that we're not quiescent. Check it. */
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
+
+ if (unlikely(call_irq_handler(vector, regs)))
+ apic_eoi();
+
set_irq_regs(old_regs);
}
@@ -334,12 +352,139 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi)
}
#endif
+#ifdef CONFIG_X86_POSTED_MSI
+
+/* Posted Interrupt Descriptors for coalesced MSIs to be posted */
+DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc);
+
+void intel_posted_msi_init(void)
+{
+ u32 destination;
+ u32 apic_id;
+
+ this_cpu_write(posted_msi_pi_desc.nv, POSTED_MSI_NOTIFICATION_VECTOR);
+
+ /*
+ * APIC destination ID is stored in bit 8:15 while in XAPIC mode.
+ * VT-d spec. CH 9.11
+ */
+ apic_id = this_cpu_read(x86_cpu_to_apicid);
+ destination = x2apic_enabled() ? apic_id : apic_id << 8;
+ this_cpu_write(posted_msi_pi_desc.ndst, destination);
+}
+
+/*
+ * De-multiplexing posted interrupts is on the performance path, the code
+ * below is written to optimize the cache performance based on the following
+ * considerations:
+ * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently
+ * accessed by both CPU and IOMMU.
+ * 2.During posted MSI processing, the CPU needs to do 64-bit read and xchg
+ * for checking and clearing posted interrupt request (PIR), a 256 bit field
+ * within the PID.
+ * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache
+ * line when posting interrupts and setting control bits.
+ * 4.The CPU can access the cache line a magnitude faster than the IOMMU.
+ * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID
+ * cache line. The cache line states after each operation are as follows:
+ * CPU IOMMU PID Cache line state
+ * ---------------------------------------------------------------
+ *...read64 exclusive
+ *...lock xchg64 modified
+ *... post/atomic swap invalid
+ *...-------------------------------------------------------------
+ *
+ * To reduce L1 data cache miss, it is important to avoid contention with
+ * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used
+ * to dispatch interrupt handlers.
+ *
+ * In addition, the code is trying to keep the cache line state consistent
+ * as much as possible. e.g. when making a copy and clearing the PIR
+ * (assuming non-zero PIR bits are present in the entire PIR), it does:
+ * read, read, read, read, xchg, xchg, xchg, xchg
+ * instead of:
+ * read, xchg, read, xchg, read, xchg, read, xchg
+ */
+static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs)
+{
+ int i, vec = FIRST_EXTERNAL_VECTOR;
+ unsigned long pir_copy[4];
+ bool handled = false;
+
+ for (i = 0; i < 4; i++)
+ pir_copy[i] = pir[i];
+
+ for (i = 0; i < 4; i++) {
+ if (!pir_copy[i])
+ continue;
+
+ pir_copy[i] = arch_xchg(&pir[i], 0);
+ handled = true;
+ }
+
+ if (handled) {
+ for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
+ call_irq_handler(vec, regs);
+ }
+
+ return handled;
+}
+
+/*
+ * Performance data shows that 3 is good enough to harvest 90+% of the benefit
+ * on high IRQ rate workload.
+ */
+#define MAX_POSTED_MSI_COALESCING_LOOP 3
+
+/*
+ * For MSIs that are delivered as posted interrupts, the CPU notifications
+ * can be coalesced if the MSIs arrive in high frequency bursts.
+ */
+DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ struct pi_desc *pid;
+ int i = 0;
+
+ pid = this_cpu_ptr(&posted_msi_pi_desc);
+
+ inc_irq_stat(posted_msi_notification_count);
+ irq_enter();
+
+ /*
+ * Max coalescing count includes the extra round of handle_pending_pir
+ * after clearing the outstanding notification bit. Hence, at most
+ * MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here.
+ */
+ while (++i < MAX_POSTED_MSI_COALESCING_LOOP) {
+ if (!handle_pending_pir(pid->pir64, regs))
+ break;
+ }
+
+ /*
+ * Clear outstanding notification bit to allow new IRQ notifications,
+ * do this last to maximize the window of interrupt coalescing.
+ */
+ pi_clear_on(pid);
+
+ /*
+ * There could be a race of PI notification and the clearing of ON bit,
+ * process PIR bits one last time such that handling the new interrupts
+ * are not delayed until the next IRQ.
+ */
+ handle_pending_pir(pid->pir64, regs);
+
+ apic_eoi();
+ irq_exit();
+ set_irq_regs(old_regs);
+}
+#endif /* X86_POSTED_MSI */
#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
- unsigned int irr, vector;
+ unsigned int vector;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
@@ -366,8 +511,7 @@ void fixup_irqs(void)
if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
continue;
- irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
- if (irr & (1 << (vector % 32))) {
+ if (is_vector_pending(vector)) {
desc = __this_cpu_read(vector_irq[vector]);
raw_spin_lock(&desc->lock);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index fe0c859873..ade0043ce5 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,6 +18,7 @@
#include <linux/uaccess.h>
#include <linux/smp.h>
#include <linux/sched/task_stack.h>
+#include <linux/vmalloc.h>
#include <asm/cpu_entry_area.h>
#include <asm/softirq_stack.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index d0e49bd7c6..72e6a45e7e 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -40,12 +40,12 @@
#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/kasan.h>
-#include <linux/moduleloader.h>
#include <linux/objtool.h>
#include <linux/vmalloc.h>
#include <linux/pgtable.h>
#include <linux/set_memory.h>
#include <linux/cfi.h>
+#include <linux/execmem.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
@@ -495,7 +495,7 @@ void *alloc_insn_page(void)
{
void *page;
- page = module_alloc(PAGE_SIZE);
+ page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
if (!page)
return NULL;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7f0732bc0c..263f8aed4e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -44,7 +44,7 @@
#include <asm/svm.h>
#include <asm/e820/api.h>
-DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
+DEFINE_STATIC_KEY_FALSE_RO(kvm_async_pf_enabled);
static int kvmapf = 1;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index e18914c0e3..837450b6e8 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -36,57 +36,6 @@ do { \
} while (0)
#endif
-#ifdef CONFIG_RANDOMIZE_BASE
-static unsigned long module_load_offset;
-
-/* Mutex protects the module_load_offset. */
-static DEFINE_MUTEX(module_kaslr_mutex);
-
-static unsigned long int get_module_load_offset(void)
-{
- if (kaslr_enabled()) {
- mutex_lock(&module_kaslr_mutex);
- /*
- * Calculate the module_load_offset the first time this
- * code is called. Once calculated it stays the same until
- * reboot.
- */
- if (module_load_offset == 0)
- module_load_offset =
- get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
- mutex_unlock(&module_kaslr_mutex);
- }
- return module_load_offset;
-}
-#else
-static unsigned long int get_module_load_offset(void)
-{
- return 0;
-}
-#endif
-
-void *module_alloc(unsigned long size)
-{
- gfp_t gfp_mask = GFP_KERNEL;
- void *p;
-
- if (PAGE_ALIGN(size) > MODULES_LEN)
- return NULL;
-
- p = __vmalloc_node_range(size, MODULE_ALIGN,
- MODULES_VADDR + get_module_load_offset(),
- MODULES_END, gfp_mask, PAGE_KERNEL,
- VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
- NUMA_NO_NODE, __builtin_return_address(0));
-
- if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
- vfree(p);
- return NULL;
- }
-
- return p;
-}
-
#ifdef CONFIG_X86_32
int apply_relocate(Elf32_Shdr *sechdrs,
const char *strtab,
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 2e7066980f..51a849a79c 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -10,7 +10,6 @@
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
#include <asm/time.h>
-#include <asm/intel-mid.h>
#include <asm/setup.h>
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e125e059e2..05c5aa951d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,6 +7,7 @@
*/
#include <linux/acpi.h>
#include <linux/console.h>
+#include <linux/cpu.h>
#include <linux/crash_dump.h>
#include <linux/dma-map-ops.h>
#include <linux/efi.h>
@@ -753,6 +754,22 @@ void __init setup_arch(char **cmdline_p)
boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS;
#endif
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0]) {
+ /* append boot loader cmdline to builtin */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif
+#endif
+
+ strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+ *cmdline_p = command_line;
+
/*
* If we have OLPC OFW, we might end up relocating the fixmap due to
* reserve_top(), so do this before touching the ioremap area.
@@ -832,22 +849,6 @@ void __init setup_arch(char **cmdline_p)
bss_resource.start = __pa_symbol(__bss_start);
bss_resource.end = __pa_symbol(__bss_stop)-1;
-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
- strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
- if (builtin_cmdline[0]) {
- /* append boot loader cmdline to builtin */
- strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
- strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
- strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
- }
-#endif
-#endif
-
- strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
- *cmdline_p = command_line;
-
/*
* x86_configure_nx() is called before parse_early_param() to detect
* whether hardware doesn't support NX (so that the early EHCI debug
@@ -1107,8 +1108,6 @@ void __init setup_arch(char **cmdline_p)
*/
arch_reserve_crashkernel();
- memblock_find_dma_reserve();
-
if (!early_xdbc_setup_hardware())
early_xdbc_register_console();
@@ -1218,3 +1217,10 @@ static int __init register_kernel_offset_dumper(void)
return 0;
}
__initcall(register_kernel_offset_dumper);
+
+#ifdef CONFIG_HOTPLUG_CPU
+bool arch_cpu_is_hotpluggable(int cpu)
+{
+ return cpu > 0;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 38ad066179..3342ed58e1 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -648,7 +648,7 @@ static u64 __init get_secrets_page(void)
static u64 __init get_snp_jump_table_addr(void)
{
- struct snp_secrets_page_layout *layout;
+ struct snp_secrets_page *secrets;
void __iomem *mem;
u64 pa, addr;
@@ -662,9 +662,9 @@ static u64 __init get_snp_jump_table_addr(void)
return 0;
}
- layout = (__force struct snp_secrets_page_layout *)mem;
+ secrets = (__force struct snp_secrets_page *)mem;
- addr = layout->os_area.ap_jump_table_pa;
+ addr = secrets->os_area.ap_jump_table_pa;
iounmap(mem);
return addr;
@@ -938,7 +938,7 @@ static int snp_set_vmsa(void *va, bool vmsa)
#define INIT_LDTR_ATTRIBS (SVM_SELECTOR_P_MASK | 2)
#define INIT_TR_ATTRIBS (SVM_SELECTOR_P_MASK | 3)
-static void *snp_alloc_vmsa_page(void)
+static void *snp_alloc_vmsa_page(int cpu)
{
struct page *p;
@@ -950,7 +950,7 @@ static void *snp_alloc_vmsa_page(void)
*
* Allocate an 8k page which is also 8k-aligned.
*/
- p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+ p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
if (!p)
return NULL;
@@ -1019,7 +1019,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
* #VMEXIT of that vCPU would wipe out all of the settings being done
* here.
*/
- vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page();
+ vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(cpu);
if (!vmsa)
return -ENOMEM;
@@ -1341,7 +1341,7 @@ static void __init alloc_runtime_data(int cpu)
{
struct sev_es_runtime_data *data;
- data = memblock_alloc(sizeof(*data), PAGE_SIZE);
+ data = memblock_alloc_node(sizeof(*data), PAGE_SIZE, cpu_to_node(cpu));
if (!data)
panic("Can't allocate SEV-ES runtime data");
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 59e15dd8d0..9797d4cdb7 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -163,8 +163,8 @@ static int shstk_setup(void)
if (features_enabled(ARCH_SHSTK_SHSTK))
return 0;
- /* Also not supported for 32 bit and x32 */
- if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_32bit_syscall())
+ /* Also not supported for 32 bit */
+ if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_ia32_syscall())
return -EOPNOTSUPP;
size = adjust_shstk_size(0);
@@ -577,3 +577,14 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2)
return wrss_control(true);
return -EINVAL;
}
+
+int shstk_update_last_frame(unsigned long val)
+{
+ unsigned long ssp;
+
+ if (!features_enabled(ARCH_SHSTK_SHSTK))
+ return 0;
+
+ ssp = get_user_shstk_addr();
+ return write_user_shstk_64((u64 __user *)ssp, (u64)val);
+}
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index c12624bc82..ef654530bf 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -34,7 +34,7 @@
#include <asm/gsseg.h>
#ifdef CONFIG_IA32_EMULATION
-#include <asm/ia32_unistd.h>
+#include <asm/unistd_32_ia32.h>
static inline void reload_segments(struct sigcontext_32 *sc)
{
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 23d8aaf8d9..8a94053c54 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -315,6 +315,9 @@ int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
uc_flags = frame_uc_flags(regs);
+ if (setup_signal_shadow_stack(ksig))
+ return -EFAULT;
+
if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
@@ -377,6 +380,9 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
goto badframe;
+ if (restore_signal_shadow_stack())
+ goto badframe;
+
if (compat_restore_altstack(&frame->uc.uc_stack))
goto badframe;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 76bb65045c..0c35207320 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -438,9 +438,9 @@ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
*/
static const struct x86_cpu_id intel_cod_cpu[] = {
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0), /* COD */
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0), /* COD */
- X86_MATCH_INTEL_FAM6_MODEL(ANY, 1), /* SNC */
+ X86_MATCH_VFM(INTEL_HASWELL_X, 0), /* COD */
+ X86_MATCH_VFM(INTEL_BROADWELL_X, 0), /* COD */
+ X86_MATCH_VFM(INTEL_ANY, 1), /* SNC */
{}
};
@@ -1033,20 +1033,22 @@ static __init void disable_smp(void)
void __init smp_prepare_cpus_common(void)
{
- unsigned int i;
+ unsigned int cpu, node;
/* Mark all except the boot CPU as hotpluggable */
- for_each_possible_cpu(i) {
- if (i)
- per_cpu(cpu_info.cpu_index, i) = nr_cpu_ids;
+ for_each_possible_cpu(cpu) {
+ if (cpu)
+ per_cpu(cpu_info.cpu_index, cpu) = nr_cpu_ids;
}
- for_each_possible_cpu(i) {
- zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
+ for_each_possible_cpu(cpu) {
+ node = cpu_to_node(cpu);
+
+ zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_die_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_llc_shared_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_l2c_shared_map, cpu), GFP_KERNEL, node);
}
set_cpu_sibling_map(0);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index cb9fa1d5c6..01d7cd85ef 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -112,13 +112,21 @@ static void find_start_end(unsigned long addr, unsigned long flags,
*end = task_size_64bit(addr > DEFAULT_MAP_WINDOW);
}
+static inline unsigned long stack_guard_placement(vm_flags_t vm_flags)
+{
+ if (vm_flags & VM_SHADOW_STACK)
+ return PAGE_SIZE;
+
+ return 0;
+}
+
unsigned long
-arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags)
+arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
unsigned long begin, end;
if (flags & MAP_FIXED)
@@ -137,12 +145,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
return addr;
}
- info.flags = 0;
info.length = len;
info.low_limit = begin;
info.high_limit = end;
- info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
+ info.start_gap = stack_guard_placement(vm_flags);
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
@@ -151,14 +158,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
}
unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
+arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags, vm_flags_t vm_flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
/* requested length too big for entire address space */
if (len > TASK_SIZE)
@@ -192,6 +199,7 @@ get_unmapped_area:
info.low_limit = PAGE_SIZE;
info.high_limit = get_mmap_base(0);
+ info.start_gap = stack_guard_placement(vm_flags);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
@@ -203,7 +211,6 @@ get_unmapped_area:
if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
- info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
@@ -223,3 +230,18 @@ bottomup:
*/
return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}
+
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0);
+}
+
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
+{
+ return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0);
+}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
deleted file mode 100644
index d42c28b8bf..0000000000
--- a/arch/x86/kernel/topology.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Populate sysfs with topology information
- *
- * Written by: Matthew Dobson, IBM Corporation
- * Original Code: Paul Dorwin, IBM Corporation, Patrick Mochel, OSDL
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to <colpatch@us.ibm.com>
- */
-#include <linux/interrupt.h>
-#include <linux/nodemask.h>
-#include <linux/export.h>
-#include <linux/mmzone.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/irq.h>
-#include <asm/io_apic.h>
-#include <asm/cpu.h>
-
-#ifdef CONFIG_HOTPLUG_CPU
-bool arch_cpu_is_hotpluggable(int cpu)
-{
- return cpu > 0;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 5a69a49acc..06b170759e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -26,7 +26,7 @@
#include <asm/x86_init.h>
#include <asm/geode.h>
#include <asm/apic.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/i8259.h>
#include <asm/uv/uv.h>
@@ -44,7 +44,7 @@ EXPORT_SYMBOL(tsc_khz);
static int __read_mostly tsc_unstable;
static unsigned int __initdata tsc_early_khz;
-static DEFINE_STATIC_KEY_FALSE(__use_tsc);
+static DEFINE_STATIC_KEY_FALSE_RO(__use_tsc);
int tsc_clocksource_reliable;
@@ -682,7 +682,7 @@ unsigned long native_calibrate_tsc(void)
* clock.
*/
if (crystal_khz == 0 &&
- boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_D)
+ boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D)
crystal_khz = 25000;
/*
@@ -713,7 +713,7 @@ unsigned long native_calibrate_tsc(void)
* For Atom SoCs TSC is the only reliable clocksource.
* Mark TSC reliable so no watchdog on it.
*/
- if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT)
+ if (boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT)
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 6555a857a1..deeb028256 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -147,13 +147,13 @@ static const struct freq_desc freq_desc_lgm = {
};
static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID, &freq_desc_pnw),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_TABLET,&freq_desc_clv),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &freq_desc_byt),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &freq_desc_tng),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &freq_desc_cht),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_MID, &freq_desc_ann),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_NP, &freq_desc_lgm),
+ X86_MATCH_VFM(INTEL_ATOM_SALTWELL_MID, &freq_desc_pnw),
+ X86_MATCH_VFM(INTEL_ATOM_SALTWELL_TABLET, &freq_desc_clv),
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT, &freq_desc_byt),
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID, &freq_desc_tng),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT, &freq_desc_cht),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID, &freq_desc_ann),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP, &freq_desc_lgm),
{}
};
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c07f6daaa..6402fb3089 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1076,8 +1076,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
return orig_ret_vaddr;
nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
- if (likely(!nleft))
+ if (likely(!nleft)) {
+ if (shstk_update_last_frame(trampoline_vaddr)) {
+ force_sig(SIGSEGV);
+ return -1;
+ }
return orig_ret_vaddr;
+ }
if (nleft != rasize) {
pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 56451fd209..3509afc6a6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -15,11 +15,7 @@
* put it inside the section definition.
*/
-#ifdef CONFIG_X86_32
-#define LOAD_OFFSET __PAGE_OFFSET
-#else
#define LOAD_OFFSET __START_KERNEL_map
-#endif
#define RUNTIME_DISCARD_EXIT
#define EMITS_PT_NOTE
@@ -114,11 +110,10 @@ PHDRS {
SECTIONS
{
+ . = __START_KERNEL;
#ifdef CONFIG_X86_32
- . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
phys_startup_32 = ABSOLUTE(startup_32 - LOAD_OFFSET);
#else
- . = __START_KERNEL;
phys_startup_64 = ABSOLUTE(startup_64 - LOAD_OFFSET);
#endif
@@ -172,6 +167,9 @@ SECTIONS
/* init_task */
INIT_TASK_DATA(THREAD_SIZE)
+ /* equivalent to task_pt_regs(&init_task) */
+ __top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE;
+
#ifdef CONFIG_X86_32
/* 32 bit has nosave before _edata */
NOSAVE_DATA