Merge tag 'ras_updates_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:

 - Extend the recovery from MCE in kernel space also to processes which
   encounter an MCE in kernel space but while copying from user memory
   by sending them a SIGBUS on return to user space and umapping the
   faulty memory, by Tony Luck and Youquan Song.

 - memcpy_mcsafe() rework by splitting the functionality into
   copy_mc_to_user() and copy_mc_to_kernel(). This, as a result, enables
   support for new hardware which can recover from a machine check
   encountered during a fast string copy and makes that the default and
   lets the older hardware which does not support that advance recovery,
   opt in to use the old, fragile, slow variant, by Dan Williams.

 - New AMD hw enablement, by Yazen Ghannam and Akshay Gupta.

 - Do not use MSR-tracing accessors in #MC context and flag any fault
   while accessing MCA architectural MSRs as an architectural violation
   with the hope that such hw/fw misdesigns are caught early during the
   hw eval phase and they don't make it into production.

 - Misc fixes, improvements and cleanups, as always.

* tag 'ras_updates_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Allow for copy_mc_fragile symbol checksum to be generated
  x86/mce: Decode a kernel instruction to determine if it is copying from user
  x86/mce: Recover from poison found while copying from user space
  x86/mce: Avoid tail copy when machine check terminated a copy from user
  x86/mce: Add _ASM_EXTABLE_CPY for copy user access
  x86/mce: Provide method to find out the type of an exception handler
  x86/mce: Pass pointer to saved pt_regs to severity calculation routines
  x86/copy_mc: Introduce copy_mc_enhanced_fast_string()
  x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}()
  x86/mce: Drop AMD-specific "DEFERRED" case from Intel severity rule list
  x86/mce: Add Skylake quirk for patrol scrub reported errors
  RAS/CEC: Convert to DEFINE_SHOW_ATTRIBUTE()
  x86/mce: Annotate mce_rd/wrmsrl() with noinstr
  x86/mce/dev-mcelog: Do not update kflags on AMD systems
  x86/mce: Stop mce_reign() from re-computing severity for every CPU
  x86/mce: Make mce_rdmsrl() panic on an inaccessible MSR
  x86/mce: Increase maximum number of banks to 64
  x86/mce: Delay clearing IA32_MCG_STATUS to the end of do_machine_check()
  x86/MCE/AMD, EDAC/mce_amd: Remove struct smca_hwid.xec_bitmap
  RAS/CEC: Fix cec_init() prototype

1 files changed, 89 insertions, 13 deletions

diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index e1da619add19..83df991314c5 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -9,9 +9,14 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/debugfs.h>
-#include <asm/mce.h>
 #include <linux/uaccess.h>
 
+#include <asm/mce.h>
+#include <asm/intel-family.h>
+#include <asm/traps.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+
 #include "internal.h"
 
 /*
@@ -40,9 +45,14 @@ static struct severity {
 	unsigned char context;
 	unsigned char excp;
 	unsigned char covered;
+	unsigned char cpu_model;
+	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  KERNEL		.context = IN_KERNEL
 #define  USER		.context = IN_USER
 #define  KERNEL_RECOV	.context = IN_KERNEL_RECOV
@@ -90,14 +100,9 @@ static struct severity {
 		EXCP, KERNEL_RECOV, MCGMASK(MCG_STATUS_RIPV, 0)
 		),
 	MCESEV(
-		DEFERRED, "Deferred error",
-		NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED)
-		),
-	MCESEV(
 		KEEP, "Corrected error",
 		NOSER, BITCLR(MCI_STATUS_UC)
 		),
-
 	/*
 	 * known AO MCACODs reported via MCE or CMC:
 	 *
@@ -113,6 +118,18 @@ static struct severity {
 		AO, "Action optional: last level cache writeback error",
 		SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
 		),
+	/*
+	 * Quirk for Skylake/Cascade Lake. Patrol scrubber may be configured
+	 * to report uncorrected errors using CMCI with a special signature.
+	 * UC=0, MSCOD=0x0010, MCACOD=binary(000X 0000 1100 XXXX) reported
+	 * in one of the memory controller banks.
+	 * Set severity to "AO" for same action as normal patrol scrub error.
+	 */
+	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)
+	),
 
 	/* ignore OVER for UCNA */
 	MCESEV(
@@ -198,6 +215,47 @@ static struct severity {
 #define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \
 				(MCG_STATUS_RIPV|MCG_STATUS_EIPV))
 
+static bool is_copy_from_user(struct pt_regs *regs)
+{
+	u8 insn_buf[MAX_INSN_SIZE];
+	struct insn insn;
+	unsigned long addr;
+
+	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
+		return false;
+
+	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
+	insn_get_opcode(&insn);
+	if (!insn.opcode.got)
+		return false;
+
+	switch (insn.opcode.value) {
+	/* MOV mem,reg */
+	case 0x8A: case 0x8B:
+	/* MOVZ mem,reg */
+	case 0xB60F: case 0xB70F:
+		insn_get_modrm(&insn);
+		insn_get_sib(&insn);
+		if (!insn.modrm.got || !insn.sib.got)
+			return false;
+		addr = (unsigned long)insn_get_addr_ref(&insn, regs);
+		break;
+	/* REP MOVS */
+	case 0xA4: case 0xA5:
+		addr = regs->si;
+		break;
+	default:
+		return false;
+	}
+
+	if (fault_in_kernel_space(addr))
+		return false;
+
+	current->mce_vaddr = (void __user *)addr;
+
+	return true;
+}
+
 /*
  * If mcgstatus indicated that ip/cs on the stack were
  * no good, then "m->cs" will be zero and we will have
@@ -209,15 +267,25 @@ static struct severity {
  * distinguish an exception taken in user from from one
  * taken in the kernel.
  */
-static int error_context(struct mce *m)
+static int error_context(struct mce *m, struct pt_regs *regs)
 {
+	enum handler_type t;
+
 	if ((m->cs & 3) == 3)
 		return IN_USER;
+	if (!mc_recoverable(m->mcgstatus))
+		return IN_KERNEL;
 
-	if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) {
+	t = ex_get_fault_handler_type(m->ip);
+	if (t == EX_HANDLER_FAULT) {
 		m->kflags |= MCE_IN_KERNEL_RECOV;
 		return IN_KERNEL_RECOV;
 	}
+	if (t == EX_HANDLER_UACCESS && regs && is_copy_from_user(regs)) {
+		m->kflags |= MCE_IN_KERNEL_RECOV;
+		m->kflags |= MCE_IN_KERNEL_COPYIN;
+		return IN_KERNEL_RECOV;
+	}
 
 	return IN_KERNEL;
 }
@@ -253,9 +321,10 @@ static int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
  * See AMD Error Scope Hierarchy table in a newer BKDG. For example
  * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features"
  */
-static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_excp)
+static int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant,
+			    char **msg, bool is_excp)
 {
-	enum context ctx = error_context(m);
+	enum context ctx = error_context(m, regs);
 
 	/* Processor Context Corrupt, no need to fumble too much, die! */
 	if (m->status & MCI_STATUS_PCC)
@@ -305,10 +374,11 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc
 	return MCE_KEEP_SEVERITY;
 }
 
-static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_excp)
+static int mce_severity_intel(struct mce *m, struct pt_regs *regs,
+			      int tolerant, char **msg, bool is_excp)
 {
 	enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP);
-	enum context ctx = error_context(m);
+	enum context ctx = error_context(m, regs);
 	struct severity *s;
 
 	for (s = severities;; s++) {
@@ -324,6 +394,12 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e
 			continue;
 		if (s->excp && excp != s->excp)
 			continue;
+		if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model)
+			continue;
+		if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping)
+			continue;
+		if (s->bank_lo && (m->bank < s->bank_lo || m->bank > s->bank_hi))
+			continue;
 		if (msg)
 			*msg = s->msg;
 		s->covered = 1;
@@ -336,7 +412,7 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e
 }
 
 /* Default to mce_severity_intel */
-int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) =
+int (*mce_severity)(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, bool is_excp) =
 		    mce_severity_intel;
 
 void __init mcheck_vendor_init_severity(void)