Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Ingo Molnar:
 "Various RAS updates:

   - AMD MCE support updates for future CPUs, fixes and 'SMCA' (Scalable
     MCA) error decoding support (Aravind Gopalakrishnan)

   - x86 memcpy_mcsafe() support, to enable smart(er) hardware error
     recovery in NVDIMM drivers, based on an extension of the x86
     exception handling code.  (Tony Luck)"

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  EDAC/sb_edac: Fix computation of channel address
  x86/mm, x86/mce: Add memcpy_mcsafe()
  x86/mce/AMD: Document some functionality
  x86/mce: Clarify comments regarding deferred error
  x86/mce/AMD: Fix logic to obtain block address
  x86/mce/AMD, EDAC: Enable error decoding of Scalable MCA errors
  x86/mce: Move MCx_CONFIG MSR definitions
  x86/mce: Check for faults tagged in EXTABLE_CLASS_FAULT exception table entries
  x86/mm: Expand the exception table logic to allow new handling options
  x86/mce/AMD: Set MCAX Enable bit
  x86/mce/AMD: Carve out threshold block preparation
  x86/mce/AMD: Fix LVT offset configuration for thresholding
  x86/mce/AMD: Reduce number of blocks scanned per bank
  x86/mce/AMD: Do not perform shared bank check for future processors
  x86/mce: Fix order of AMD MCE init function call

6 files changed, 233 insertions, 102 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 9c682c222071..5119766d9889 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <asm/mce.h>
+#include <asm/uaccess.h>
 
 #include "mce-internal.h"
 
@@ -29,7 +30,7 @@
  * panic situations)
  */
 
-enum context { IN_KERNEL = 1, IN_USER = 2 };
+enum context { IN_KERNEL = 1, IN_USER = 2, IN_KERNEL_RECOV = 3 };
 enum ser { SER_REQUIRED = 1, NO_SER = 2 };
 enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 };
 
@@ -48,6 +49,7 @@ static struct severity {
 #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c }
 #define  KERNEL		.context = IN_KERNEL
 #define  USER		.context = IN_USER
+#define  KERNEL_RECOV	.context = IN_KERNEL_RECOV
 #define  SER		.ser = SER_REQUIRED
 #define  NOSER		.ser = NO_SER
 #define  EXCP		.excp = EXCP_CONTEXT
@@ -87,6 +89,10 @@ static struct severity {
 		EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
 		),
 	MCESEV(
+		PANIC, "In kernel and no restart IP",
+		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)
 		),
@@ -123,6 +129,11 @@ static struct severity {
 		MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV)
 		),
 	MCESEV(
+		AR, "Action required: data load in error recoverable area of kernel",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		KERNEL_RECOV
+		),
+	MCESEV(
 		AR, "Action required: data load error in a user process",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
 		USER
@@ -170,6 +181,9 @@ static struct severity {
 		)	/* always matches. keep at end */
 };
 
+#define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \
+				(MCG_STATUS_RIPV|MCG_STATUS_EIPV))
+
 /*
  * If mcgstatus indicated that ip/cs on the stack were
  * no good, then "m->cs" will be zero and we will have
@@ -183,7 +197,11 @@ static struct severity {
  */
 static int error_context(struct mce *m)
 {
-	return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
+	if ((m->cs & 3) == 3)
+		return IN_USER;
+	if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip))
+		return IN_KERNEL_RECOV;
+	return IN_KERNEL;
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a006f4cd792b..524f2a8492d7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -961,6 +961,20 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
+static int do_memory_failure(struct mce *m)
+{
+	int flags = MF_ACTION_REQUIRED;
+	int ret;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
+	if (!(m->mcgstatus & MCG_STATUS_RIPV))
+		flags |= MF_MUST_KILL;
+	ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
+	if (ret)
+		pr_err("Memory error not recovered");
+	return ret;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -998,8 +1012,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
-	u64 recover_paddr = ~0ull;
-	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
 	/* If this CPU is offline, just bail out. */
@@ -1136,22 +1148,13 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	}
 
 	/*
-	 * At insane "tolerant" levels we take no action. Otherwise
-	 * we only die if we have no other choice. For less serious
-	 * issues we try to recover, or limit damage to the current
-	 * process.
+	 * If tolerant is at an insane level we drop requests to kill
+	 * processes and continue even when there is no way out.
 	 */
-	if (cfg->tolerant < 3) {
-		if (no_way_out)
-			mce_panic("Fatal machine check on current CPU", &m, msg);
-		if (worst == MCE_AR_SEVERITY) {
-			recover_paddr = m.addr;
-			if (!(m.mcgstatus & MCG_STATUS_RIPV))
-				flags |= MF_MUST_KILL;
-		} else if (kill_it) {
-			force_sig(SIGBUS, current);
-		}
-	}
+	if (cfg->tolerant == 3)
+		kill_it = 0;
+	else if (no_way_out)
+		mce_panic("Fatal machine check on current CPU", &m, msg);
 
 	if (worst > 0)
 		mce_report_event(regs);
@@ -1159,25 +1162,24 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 out:
 	sync_core();
 
-	if (recover_paddr == ~0ull)
-		goto done;
+	if (worst != MCE_AR_SEVERITY && !kill_it)
+		goto out_ist;
 
-	pr_err("Uncorrected hardware memory error in user-access at %llx",
-		 recover_paddr);
-	/*
-	 * We must call memory_failure() here even if the current process is
-	 * doomed. We still need to mark the page as poisoned and alert any
-	 * other users of the page.
-	 */
-	ist_begin_non_atomic(regs);
-	local_irq_enable();
-	if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) {
-		pr_err("Memory error not recovered");
-		force_sig(SIGBUS, current);
+	/* Fault was in user mode and we need to take some action */
+	if ((m.cs & 3) == 3) {
+		ist_begin_non_atomic(regs);
+		local_irq_enable();
+
+		if (kill_it || do_memory_failure(&m))
+			force_sig(SIGBUS, current);
+		local_irq_disable();
+		ist_end_non_atomic();
+	} else {
+		if (!fixup_exception(regs, X86_TRAP_MC))
+			mce_panic("Failed kernel mode recovery", &m, NULL);
 	}
-	local_irq_disable();
-	ist_end_non_atomic();
-done:
+
+out_ist:
 	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1617,10 +1619,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_AMD: {
 		u32 ebx = cpuid_ebx(0x80000007);
 
-		mce_amd_feature_init(c);
 		mce_flags.overflow_recov = !!(ebx & BIT(0));
 		mce_flags.succor	 = !!(ebx & BIT(1));
 		mce_flags.smca		 = !!(ebx & BIT(3));
+		mce_amd_feature_init(c);
 
 		break;
 		}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index e99b15077e94..9d656fd436ef 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,5 +1,5 @@
 /*
- *  (c) 2005-2015 Advanced Micro Devices, Inc.
+ *  (c) 2005-2016 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
@@ -28,7 +28,7 @@
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
-#define NR_BLOCKS         9
+#define NR_BLOCKS         5
 #define THRESHOLD_MAX     0xFFF
 #define INT_TYPE_APIC     0x00020000
 #define MASK_VALID_HI     0x80000000
@@ -49,6 +49,19 @@
 #define DEF_LVT_OFF		0x2
 #define DEF_INT_TYPE_APIC	0x2
 
+/* Scalable MCA: */
+
+/* Threshold LVT offset is at MSR0xC0000410[15:12] */
+#define SMCA_THR_LVT_OFF	0xF000
+
+/*
+ * OS is required to set the MCAX bit to acknowledge that it is now using the
+ * new MSR ranges and new registers under each bank. It also means that the OS
+ * will configure deferred errors in the new MCx_CONFIG register. If the bit is
+ * not set, uncorrectable errors will cause a system panic.
+ */
+#define SMCA_MCAX_EN_OFF	0x1
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -58,6 +71,35 @@ static const char * const th_names[] = {
 	"execution_unit",
 };
 
+/* Define HWID to IP type mappings for Scalable MCA */
+struct amd_hwid amd_hwids[] = {
+	[SMCA_F17H_CORE]	= { "f17h_core",	0xB0 },
+	[SMCA_DF]		= { "data_fabric",	0x2E },
+	[SMCA_UMC]		= { "umc",		0x96 },
+	[SMCA_PB]		= { "param_block",	0x5 },
+	[SMCA_PSP]		= { "psp",		0xFF },
+	[SMCA_SMU]		= { "smu",		0x1 },
+};
+EXPORT_SYMBOL_GPL(amd_hwids);
+
+const char * const amd_core_mcablock_names[] = {
+	[SMCA_LS]		= "load_store",
+	[SMCA_IF]		= "insn_fetch",
+	[SMCA_L2_CACHE]		= "l2_cache",
+	[SMCA_DE]		= "decode_unit",
+	[RES]			= "",
+	[SMCA_EX]		= "execution_unit",
+	[SMCA_FP]		= "floating_point",
+	[SMCA_L3_CACHE]		= "l3_cache",
+};
+EXPORT_SYMBOL_GPL(amd_core_mcablock_names);
+
+const char * const amd_df_mcablock_names[] = {
+	[SMCA_CS]		= "coherent_slave",
+	[SMCA_PIE]		= "pie",
+};
+EXPORT_SYMBOL_GPL(amd_df_mcablock_names);
+
 static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
@@ -84,6 +126,13 @@ struct thresh_restart {
 
 static inline bool is_shared_bank(int bank)
 {
+	/*
+	 * Scalable MCA provides for only one core to have access to the MSRs of
+	 * a shared bank.
+	 */
+	if (mce_flags.smca)
+		return false;
+
 	/* Bank 4 is for northbridge reporting and is thus shared */
 	return (bank == 4);
 }
@@ -135,6 +184,14 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
 	}
 
 	if (apic != msr) {
+		/*
+		 * On SMCA CPUs, LVT offset is programmed at a different MSR, and
+		 * the BIOS provides the value. The original field where LVT offset
+		 * was set is reserved. Return early here:
+		 */
+		if (mce_flags.smca)
+			return 0;
+
 		pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
 		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
 		       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
@@ -144,10 +201,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
 	return 1;
 };
 
-/*
- * Called via smp_call_function_single(), must be called with correct
- * cpu affinity.
- */
+/* Reprogram MCx_MISC MSR behind this threshold bank. */
 static void threshold_restart_bank(void *_tr)
 {
 	struct thresh_restart *tr = _tr;
@@ -247,27 +301,116 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
+static u32 get_block_address(u32 current_addr, u32 low, u32 high,
+			     unsigned int bank, unsigned int block)
+{
+	u32 addr = 0, offset = 0;
+
+	if (mce_flags.smca) {
+		if (!block) {
+			addr = MSR_AMD64_SMCA_MCx_MISC(bank);
+		} else {
+			/*
+			 * For SMCA enabled processors, BLKPTR field of the
+			 * first MISC register (MCx_MISC0) indicates presence of
+			 * additional MISC register set (MISC1-4).
+			 */
+			u32 low, high;
+
+			if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+				return addr;
+
+			if (!(low & MCI_CONFIG_MCAX))
+				return addr;
+
+			if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+			    (low & MASK_BLKPTR_LO))
+				addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+		}
+		return addr;
+	}
+
+	/* Fall back to method we used for older processors: */
+	switch (block) {
+	case 0:
+		addr = MSR_IA32_MCx_MISC(bank);
+		break;
+	case 1:
+		offset = ((low & MASK_BLKPTR_LO) >> 21);
+		if (offset)
+			addr = MCG_XBLK_ADDR + offset;
+		break;
+	default:
+		addr = ++current_addr;
+	}
+	return addr;
+}
+
+static int
+prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
+			int offset, u32 misc_high)
+{
+	unsigned int cpu = smp_processor_id();
+	struct threshold_block b;
+	int new;
+
+	if (!block)
+		per_cpu(bank_map, cpu) |= (1 << bank);
+
+	memset(&b, 0, sizeof(b));
+	b.cpu			= cpu;
+	b.bank			= bank;
+	b.block			= block;
+	b.address		= addr;
+	b.interrupt_capable	= lvt_interrupt_supported(bank, misc_high);
+
+	if (!b.interrupt_capable)
+		goto done;
+
+	b.interrupt_enable = 1;
+
+	if (mce_flags.smca) {
+		u32 smca_low, smca_high;
+		u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
+
+		if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
+			smca_high |= SMCA_MCAX_EN_OFF;
+			wrmsr(smca_addr, smca_low, smca_high);
+		}
+
+		/* Gather LVT offset for thresholding: */
+		if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
+			goto out;
+
+		new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
+	} else {
+		new = (misc_high & MASK_LVTOFF_HI) >> 20;
+	}
+
+	offset = setup_APIC_mce_threshold(offset, new);
+
+	if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt))
+		mce_threshold_vector = amd_threshold_interrupt;
+
+done:
+	mce_threshold_block_init(&b, offset);
+
+out:
+	return offset;
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
-	struct threshold_block b;
-	unsigned int cpu = smp_processor_id();
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
-	int offset = -1, new;
+	int offset = -1;
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			if (block == 0)
-				address = MSR_IA32_MCx_MISC(bank);
-			else if (block == 1) {
-				address = (low & MASK_BLKPTR_LO) >> 21;
-				if (!address)
-					break;
-
-				address += MCG_XBLK_ADDR;
-			} else
-				++address;
+			address = get_block_address(address, low, high, bank, block);
+			if (!address)
+				break;
 
 			if (rdmsr_safe(address, &low, &high))
 				break;
@@ -279,29 +422,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			     (high & MASK_LOCKED_HI))
 				continue;
 
-			if (!block)
-				per_cpu(bank_map, cpu) |= (1 << bank);
-
-			memset(&b, 0, sizeof(b));
-			b.cpu			= cpu;
-			b.bank			= bank;
-			b.block			= block;
-			b.address		= address;
-			b.interrupt_capable	= lvt_interrupt_supported(bank, high);
-
-			if (!b.interrupt_capable)
-				goto init;
-
-			b.interrupt_enable = 1;
-			new	= (high & MASK_LVTOFF_HI) >> 20;
-			offset  = setup_APIC_mce_threshold(offset, new);
-
-			if ((offset == new) &&
-			    (mce_threshold_vector != amd_threshold_interrupt))
-				mce_threshold_vector = amd_threshold_interrupt;
-
-init:
-			mce_threshold_block_init(&b, offset);
+			offset = prepare_threshold_block(bank, block, address, offset, high);
 		}
 	}
 
@@ -394,16 +515,9 @@ static void amd_threshold_interrupt(void)
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			if (block == 0) {
-				address = MSR_IA32_MCx_MISC(bank);
-			} else if (block == 1) {
-				address = (low & MASK_BLKPTR_LO) >> 21;
-				if (!address)
-					break;
-				address += MCG_XBLK_ADDR;
-			} else {
-				++address;
-			}
+			address = get_block_address(address, low, high, bank, block);
+			if (!address)
+				break;
 
 			if (rdmsr_safe(address, &low, &high))
 				break;
@@ -623,16 +737,11 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	if (err)
 		goto out_free;
 recurse:
-	if (!block) {
-		address = (low & MASK_BLKPTR_LO) >> 21;
-		if (!address)
-			return 0;
-		address += MCG_XBLK_ADDR;
-	} else {
-		++address;
-	}
+	address = get_block_address(address, low, high, bank, ++block);
+	if (!address)
+		return 0;
 
-	err = allocate_threshold_blocks(cpu, bank, ++block, address);
+	err = allocate_threshold_blocks(cpu, bank, block, address);
 	if (err)
 		goto out_free;
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1deffe6cc873..0f05deeff5ce 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -988,7 +988,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		if (fixup_exception(regs))
+		if (fixup_exception(regs, trapnr))
 			return 1;
 
 		/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ade185a46b1d..211c11c7bba4 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -199,7 +199,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	}
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs)) {
+		if (!fixup_exception(regs, trapnr)) {
 			tsk->thread.error_code = error_code;
 			tsk->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
@@ -453,7 +453,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
 	tsk = current;
 	if (!user_mode(regs)) {
-		if (fixup_exception(regs))
+		if (fixup_exception(regs, X86_TRAP_GP))
 			return;
 
 		tsk->thread.error_code = error_code;
@@ -699,7 +699,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	conditional_sti(regs);
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs)) {
+		if (!fixup_exception(regs, trapnr)) {
 			task->thread.error_code = error_code;
 			task->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index a0695be19864..cd05942bc918 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -37,6 +37,8 @@ EXPORT_SYMBOL(__copy_user_nocache);
 EXPORT_SYMBOL(_copy_from_user);
 EXPORT_SYMBOL(_copy_to_user);
 
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
+
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);