Merging upstream version 6.10.3.

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

4 files changed, 75 insertions, 37 deletions

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;