Merging upstream version 6.7.12.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 158 insertions, 62 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 2055fb308f..77a1ceb717 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1002,11 +1002,11 @@ static bool cpu_has_zenbleed_microcode(void)
 	u32 good_rev = 0;
 
 	switch (boot_cpu_data.x86_model) {
-	case 0x30 ... 0x3f: good_rev = 0x0830107a; break;
-	case 0x60 ... 0x67: good_rev = 0x0860010b; break;
-	case 0x68 ... 0x6f: good_rev = 0x08608105; break;
-	case 0x70 ... 0x7f: good_rev = 0x08701032; break;
-	case 0xa0 ... 0xaf: good_rev = 0x08a00008; break;
+	case 0x30 ... 0x3f: good_rev = 0x0830107b; break;
+	case 0x60 ... 0x67: good_rev = 0x0860010c; break;
+	case 0x68 ... 0x6f: good_rev = 0x08608107; break;
+	case 0x70 ... 0x7f: good_rev = 0x08701033; break;
+	case 0xa0 ... 0xaf: good_rev = 0x08a00009; break;
 
 	default:
 		return false;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 48d049cd74..01ac18f561 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -422,6 +422,13 @@ static void __init mmio_select_mitigation(void)
 	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
 					      boot_cpu_has(X86_FEATURE_RTM)))
 		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+
+	/*
+	 * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based
+	 * mitigations, disable KVM-only mitigation in that case.
+	 */
+	if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
+		static_branch_disable(&mmio_stale_data_clear);
 	else
 		static_branch_enable(&mmio_stale_data_clear);
 
@@ -474,6 +481,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str)
 early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"Register File Data Sampling: " fmt
+
+enum rfds_mitigations {
+	RFDS_MITIGATION_OFF,
+	RFDS_MITIGATION_VERW,
+	RFDS_MITIGATION_UCODE_NEEDED,
+};
+
+/* Default mitigation for Register File Data Sampling */
+static enum rfds_mitigations rfds_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF;
+
+static const char * const rfds_strings[] = {
+	[RFDS_MITIGATION_OFF]			= "Vulnerable",
+	[RFDS_MITIGATION_VERW]			= "Mitigation: Clear Register File",
+	[RFDS_MITIGATION_UCODE_NEEDED]		= "Vulnerable: No microcode",
+};
+
+static void __init rfds_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) {
+		rfds_mitigation = RFDS_MITIGATION_OFF;
+		return;
+	}
+	if (rfds_mitigation == RFDS_MITIGATION_OFF)
+		return;
+
+	if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR)
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+	else
+		rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
+}
+
+static __init int rfds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_RFDS))
+		return 0;
+
+	if (!strcmp(str, "off"))
+		rfds_mitigation = RFDS_MITIGATION_OFF;
+	else if (!strcmp(str, "on"))
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+
+	return 0;
+}
+early_param("reg_file_data_sampling", rfds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "" fmt
 
 static void __init md_clear_update_mitigation(void)
@@ -498,11 +556,19 @@ static void __init md_clear_update_mitigation(void)
 		taa_mitigation = TAA_MITIGATION_VERW;
 		taa_select_mitigation();
 	}
-	if (mmio_mitigation == MMIO_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
+	/*
+	 * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear
+	 * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
 		mmio_mitigation = MMIO_MITIGATION_VERW;
 		mmio_select_mitigation();
 	}
+	if (rfds_mitigation == RFDS_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_RFDS)) {
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+		rfds_select_mitigation();
+	}
 out:
 	if (boot_cpu_has_bug(X86_BUG_MDS))
 		pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
@@ -512,6 +578,8 @@ out:
 		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
 	else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
 		pr_info("MMIO Stale Data: Unknown: No mitigations\n");
+	if (boot_cpu_has_bug(X86_BUG_RFDS))
+		pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]);
 }
 
 static void __init md_clear_select_mitigation(void)
@@ -519,11 +587,12 @@ static void __init md_clear_select_mitigation(void)
 	mds_select_mitigation();
 	taa_select_mitigation();
 	mmio_select_mitigation();
+	rfds_select_mitigation();
 
 	/*
-	 * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update
-	 * and print their mitigation after MDS, TAA and MMIO Stale Data
-	 * mitigation selection is done.
+	 * As these mitigations are inter-related and rely on VERW instruction
+	 * to clear the microarchitural buffers, update and print their status
+	 * after mitigation selection is done for each of these vulnerabilities.
 	 */
 	md_clear_update_mitigation();
 }
@@ -2612,6 +2681,11 @@ static ssize_t mmio_stale_data_show_state(char *buf)
 			  sched_smt_active() ? "vulnerable" : "disabled");
 }
 
+static ssize_t rfds_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
@@ -2771,6 +2845,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_GDS:
 		return gds_show_state(buf);
 
+	case X86_BUG_RFDS:
+		return rfds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -2845,4 +2922,9 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_GDS);
 }
+
+ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 34cac9ea19..97ea52a4e8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1274,6 +1274,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define SRSO		BIT(5)
 /* CPU is affected by GDS */
 #define GDS		BIT(6)
+/* CPU is affected by Register File Data Sampling */
+#define RFDS		BIT(7)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
@@ -1301,9 +1303,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	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(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
+	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_AMD(0x15, RETBLEED),
 	VULNBL_AMD(0x16, RETBLEED),
@@ -1337,6 +1348,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap)
 		ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
 }
 
+static bool __init vulnerable_to_rfds(u64 ia32_cap)
+{
+	/* The "immunity" bit trumps everything else: */
+	if (ia32_cap & ARCH_CAP_RFDS_NO)
+		return false;
+
+	/*
+	 * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to
+	 * indicate that mitigation is needed because guest is running on a
+	 * vulnerable hardware or may migrate to such hardware:
+	 */
+	if (ia32_cap & ARCH_CAP_RFDS_CLEAR)
+		return true;
+
+	/* Only consult the blacklist when there is no enumeration: */
+	return cpu_matches(cpu_vuln_blacklist, RFDS);
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = x86_read_arch_cap_msr();
@@ -1448,6 +1477,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	    boot_cpu_has(X86_FEATURE_AVX))
 		setup_force_cpu_bug(X86_BUG_GDS);
 
+	if (vulnerable_to_rfds(ia32_cap))
+		setup_force_cpu_bug(X86_BUG_RFDS);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 19e0681f04..d04371e851 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -231,9 +231,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	union cpuid_0x10_3_eax eax;
-	union cpuid_0x10_x_edx edx;
-	u32 ebx, ecx, subleaf;
+	u32 eax, ebx, ecx, edx, subleaf;
 
 	/*
 	 * Query CPUID_Fn80000020_EDX_x01 for MBA and
@@ -241,9 +239,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	 */
 	subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 :  1;
 
-	cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full);
-	hw_res->num_closid = edx.split.cos_max + 1;
-	r->default_ctrl = MAX_MBA_BW_AMD;
+	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);
+	hw_res->num_closid = edx + 1;
+	r->default_ctrl = 1 << eax;
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index a4f1aa15f0..52e7e7deee 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -18,7 +18,6 @@
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
-#define MAX_MBA_BW_AMD			0x800
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
@@ -296,14 +295,10 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
- * @delta_bw:	Difference between the current and previous bandwidth
- * @delta_comp:	Indicates whether to compute the delta_bw
  */
 struct mbm_state {
 	u64	prev_bw_bytes;
 	u32	prev_bw;
-	u32	delta_bw;
-	bool	delta_comp;
 };
 
 /**
@@ -395,6 +390,8 @@ struct rdt_parse_data {
  * @msr_update:		Function pointer to update QOS MSRs
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
+ * @mbm_cfg_mask:	Bandwidth sources that can be tracked when Bandwidth
+ *			Monitoring Event Configuration (BMEC) is supported.
  * @cdp_enabled:	CDP state of this resource
  *
  * Members of this structure are either private to the architecture
@@ -409,6 +406,7 @@ struct rdt_hw_resource {
 				 struct rdt_resource *r);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
+	unsigned int		mbm_cfg_mask;
 	bool			cdp_enabled;
 };
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f136ac0468..3a6c069614 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -440,9 +440,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 
 	cur_bw = bytes / SZ_1M;
 
-	if (m->delta_comp)
-		m->delta_bw = abs(cur_bw - m->prev_bw);
-	m->delta_comp = false;
 	m->prev_bw = cur_bw;
 }
 
@@ -520,11 +517,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 {
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
-	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
 	struct rdt_domain *dom_mba;
 	struct list_head *head;
 	struct rdtgroup *entry;
+	u32 cur_bw, user_bw;
 
 	if (!is_mbm_local_enabled())
 		return;
@@ -543,7 +540,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 
 	cur_bw = pmbm_data->prev_bw;
 	user_bw = dom_mba->mbps_val[closid];
-	delta_bw = pmbm_data->delta_bw;
 
 	/* MBA resource doesn't support CDP */
 	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
@@ -555,49 +551,31 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
 		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
 		cur_bw += cmbm_data->prev_bw;
-		delta_bw += cmbm_data->delta_bw;
 	}
 
 	/*
 	 * Scale up/down the bandwidth linearly for the ctrl group.  The
 	 * bandwidth step is the bandwidth granularity specified by the
 	 * hardware.
-	 *
-	 * The delta_bw is used when increasing the bandwidth so that we
-	 * dont alternately increase and decrease the control values
-	 * continuously.
-	 *
-	 * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if
-	 * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep
-	 * switching between 90 and 110 continuously if we only check
-	 * cur_bw < user_bw.
+	 * Always increase throttling if current bandwidth is above the
+	 * target set by user.
+	 * But avoid thrashing up and down on every poll by checking
+	 * whether a decrease in throttling is likely to push the group
+	 * back over target. E.g. if currently throttling to 30% of bandwidth
+	 * on a system with 10% granularity steps, check whether moving to
+	 * 40% would go past the limit by multiplying current bandwidth by
+	 * "(30 + 10) / 30".
 	 */
 	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
 		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
 	} else if (cur_msr_val < MAX_MBA_BW &&
-		   (user_bw > (cur_bw + delta_bw))) {
+		   (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
 		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
 	} else {
 		return;
 	}
 
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
-
-	/*
-	 * Delta values are updated dynamically package wise for each
-	 * rdtgrp every time the throttle MSR changes value.
-	 *
-	 * This is because (1)the increase in bandwidth is not perfectly
-	 * linear and only "approximately" linear even when the hardware
-	 * says it is linear.(2)Also since MBA is a core specific
-	 * mechanism, the delta values vary based on number of cores used
-	 * by the rdtgrp.
-	 */
-	pmbm_data->delta_comp = true;
-	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
-		cmbm_data->delta_comp = true;
-	}
 }
 
 static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
@@ -813,6 +791,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		return ret;
 
 	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* Detect list of bandwidth sources that can be tracked */
+		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
+		hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
+
 		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
 			mbm_total_event.configurable = true;
 			mbm_config_rftype_init("mbm_total_bytes_config");
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 69a1de9238..2b69e560b0 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1620,12 +1620,6 @@ static int mbm_config_write_domain(struct rdt_resource *r,
 	struct mon_config_info mon_info = {0};
 	int ret = 0;
 
-	/* mon_config cannot be more than the supported set of events */
-	if (val > MAX_EVT_CONFIG_BITS) {
-		rdt_last_cmd_puts("Invalid event configuration\n");
-		return -EINVAL;
-	}
-
 	/*
 	 * Read the current config value first. If both are the same then
 	 * no need to write it again.
@@ -1663,6 +1657,7 @@ out:
 
 static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	char *dom_str = NULL, *id_str;
 	unsigned long dom_id, val;
 	struct rdt_domain *d;
@@ -1686,6 +1681,13 @@ next:
 		return -EINVAL;
 	}
 
+	/* Value from user cannot be more than the supported set of events */
+	if ((val & hw_res->mbm_cfg_mask) != val) {
+		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
+				    hw_res->mbm_cfg_mask);
+		return -EINVAL;
+	}
+
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
 			ret = mbm_config_write_domain(r, d, evtid, val);