Merge tag 'ras_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:
 "A relatively big amount of movements in RAS-land this time around:

   - First part of a series to move the AMD address translation code
     from arch/x86/ to amd64_edac as that is its only user anyway

   - Some MCE error injection improvements to the AMD side

   - Reorganization of the #MC handler code and the facilities it calls
     to make it noinstr-safe

   - Add support for new AMD MCA bank types and non-uniform banks layout

   - The usual set of cleanups and fixes"

* tag 'ras_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/mce: Reduce number of machine checks taken during recovery
  x86/mce/inject: Avoid out-of-bounds write when setting flags
  x86/MCE/AMD, EDAC/mce_amd: Support non-uniform MCA bank type enumeration
  x86/MCE/AMD, EDAC/mce_amd: Add new SMCA bank types
  x86/mce: Check regs before accessing it
  x86/mce: Mark mce_start() noinstr
  x86/mce: Mark mce_timed_out() noinstr
  x86/mce: Move the tainting outside of the noinstr region
  x86/mce: Mark mce_read_aux() noinstr
  x86/mce: Mark mce_end() noinstr
  x86/mce: Mark mce_panic() noinstr
  x86/mce: Prevent severity computation from being instrumented
  x86/mce: Allow instrumentation during task work queueing
  x86/mce: Remove noinstr annotation from mce_setup()
  x86/mce: Use mce_rdmsrl() in severity checking code
  x86/mce: Remove function-local cpus variables
  x86/mce: Do not use memset to clear the banks bitmaps
  x86/mce/inject: Set the valid bit in MCA_STATUS before error injection
  x86/mce/inject: Check if a bank is populated before injecting
  x86/mce: Get rid of cpu_missing
  ...

arch/x86/include/asm/amd_nb.h

@@ -24,7 +24,6 @@ extern int amd_set_subcaches(int, unsigned long);
 
 extern int amd_smn_read(u16 node, u32 address, u32 *value);
 extern int amd_smn_write(u16 node, u32 address, u32 value);
-extern int amd_df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo);
 
 struct amd_l3_cache {
 	unsigned indices;

arch/x86/include/asm/mce.h

@@ -313,31 +313,22 @@ enum smca_bank_types {
 	SMCA_SMU,	/* System Management Unit */
 	SMCA_SMU_V2,
 	SMCA_MP5,	/* Microprocessor 5 Unit */
+	SMCA_MPDMA,	/* MPDMA Unit */
 	SMCA_NBIO,	/* Northbridge IO Unit */
 	SMCA_PCIE,	/* PCI Express Unit */
 	SMCA_PCIE_V2,
 	SMCA_XGMI_PCS,	/* xGMI PCS Unit */
+	SMCA_NBIF,	/* NBIF Unit */
+	SMCA_SHUB,	/* System HUB Unit */
+	SMCA_SATA,	/* SATA Unit */
+	SMCA_USB,	/* USB Unit */
+	SMCA_GMI_PCS,	/* GMI PCS Unit */
 	SMCA_XGMI_PHY,	/* xGMI PHY Unit */
 	SMCA_WAFL_PHY,	/* WAFL PHY Unit */
+	SMCA_GMI_PHY,	/* GMI PHY Unit */
 	N_SMCA_BANK_TYPES
 };
 
-#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype))
-
-struct smca_hwid {
-	unsigned int bank_type;	/* Use with smca_bank_types for easy indexing. */
-	u32 hwid_mcatype;	/* (hwid,mcatype) tuple */
-	u8 count;		/* Number of instances. */
-};
-
-struct smca_bank {
-	struct smca_hwid *hwid;
-	u32 id;			/* Value of MCA_IPID[InstanceId]. */
-	u8 sysfs_id;		/* Value used for sysfs name. */
-};
-
-extern struct smca_bank smca_banks[MAX_NR_BANKS];
-
 extern const char *smca_get_long_name(enum smca_bank_types t);
 extern bool amd_mce_is_memory_error(struct mce *m);
 
@@ -345,16 +336,13 @@ extern int mce_threshold_create_device(unsigned int cpu);
 extern int mce_threshold_remove_device(unsigned int cpu);
 
 void mce_amd_feature_init(struct cpuinfo_x86 *c);
-int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
-enum smca_bank_types smca_get_bank_type(unsigned int bank);
+enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank);
 #else
 
 static inline int mce_threshold_create_device(unsigned int cpu)		{ return 0; };
 static inline int mce_threshold_remove_device(unsigned int cpu)		{ return 0; };
 static inline bool amd_mce_is_memory_error(struct mce *m)		{ return false; };
 static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)		{ }
-static inline int
-umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)	{ return -EINVAL; };
 #endif
 
 static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c)	{ return mce_amd_feature_init(c); }

arch/x86/kernel/amd_nb.c

@@ -29,7 +29,7 @@
 #define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d
 #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e
 
-/* Protect the PCI config register pairs used for SMN and DF indirect access. */
+/* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
 
 static u32 *flush_words;
@@ -182,53 +182,6 @@ int amd_smn_write(u16 node, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(amd_smn_write);
 
-/*
- * Data Fabric Indirect Access uses FICAA/FICAD.
- *
- * Fabric Indirect Configuration Access Address (FICAA): Constructed based
- * on the device's Instance Id and the PCI function and register offset of
- * the desired register.
- *
- * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO
- * and FICAD HI registers but so far we only need the LO register.
- */
-int amd_df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
-{
-	struct pci_dev *F4;
-	u32 ficaa;
-	int err = -ENODEV;
-
-	if (node >= amd_northbridges.num)
-		goto out;
-
-	F4 = node_to_amd_nb(node)->link;
-	if (!F4)
-		goto out;
-
-	ficaa  = 1;
-	ficaa |= reg & 0x3FC;
-	ficaa |= (func & 0x7) << 11;
-	ficaa |= instance_id << 16;
-
-	mutex_lock(&smn_mutex);
-
-	err = pci_write_config_dword(F4, 0x5C, ficaa);
-	if (err) {
-		pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
-		goto out_unlock;
-	}
-
-	err = pci_read_config_dword(F4, 0x98, lo);
-	if (err)
-		pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
-
-out_unlock:
-	mutex_unlock(&smn_mutex);
-
-out:
-	return err;
-}
-EXPORT_SYMBOL_GPL(amd_df_indirect_read);
 
 int amd_cache_northbridges(void)
 {

arch/x86/kernel/cpu/mce/amd.c

@@ -71,6 +71,22 @@ static const char * const smca_umc_block_names[] = {
 	"misc_umc"
 };
 
+#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype))
+
+struct smca_hwid {
+	unsigned int bank_type;	/* Use with smca_bank_types for easy indexing. */
+	u32 hwid_mcatype;	/* (hwid,mcatype) tuple */
+};
+
+struct smca_bank {
+	const struct smca_hwid *hwid;
+	u32 id;			/* Value of MCA_IPID[InstanceId]. */
+	u8 sysfs_id;		/* Value used for sysfs name. */
+};
+
+static DEFINE_PER_CPU_READ_MOSTLY(struct smca_bank[MAX_NR_BANKS], smca_banks);
+static DEFINE_PER_CPU_READ_MOSTLY(u8[N_SMCA_BANK_TYPES], smca_bank_counts);
+
 struct smca_bank_name {
 	const char *name;	/* Short name for sysfs */
 	const char *long_name;	/* Long name for pretty-printing */
@@ -95,11 +111,18 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_PSP ... SMCA_PSP_V2]	= { "psp",		"Platform Security Processor" },
 	[SMCA_SMU ... SMCA_SMU_V2]	= { "smu",		"System Management Unit" },
 	[SMCA_MP5]			= { "mp5",		"Microprocessor 5 Unit" },
+	[SMCA_MPDMA]			= { "mpdma",		"MPDMA Unit" },
 	[SMCA_NBIO]			= { "nbio",		"Northbridge IO Unit" },
 	[SMCA_PCIE ... SMCA_PCIE_V2]	= { "pcie",		"PCI Express Unit" },
 	[SMCA_XGMI_PCS]			= { "xgmi_pcs",		"Ext Global Memory Interconnect PCS Unit" },
+	[SMCA_NBIF]			= { "nbif",		"NBIF Unit" },
+	[SMCA_SHUB]			= { "shub",		"System Hub Unit" },
+	[SMCA_SATA]			= { "sata",		"SATA Unit" },
+	[SMCA_USB]			= { "usb",		"USB Unit" },
+	[SMCA_GMI_PCS]			= { "gmi_pcs",		"Global Memory Interconnect PCS Unit" },
 	[SMCA_XGMI_PHY]			= { "xgmi_phy",		"Ext Global Memory Interconnect PHY Unit" },
 	[SMCA_WAFL_PHY]			= { "wafl_phy",		"WAFL PHY Unit" },
+	[SMCA_GMI_PHY]			= { "gmi_phy",		"Global Memory Interconnect PHY Unit" },
 };
 
 static const char *smca_get_name(enum smca_bank_types t)
@@ -119,14 +142,14 @@ const char *smca_get_long_name(enum smca_bank_types t)
 }
 EXPORT_SYMBOL_GPL(smca_get_long_name);
 
-enum smca_bank_types smca_get_bank_type(unsigned int bank)
+enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank)
 {
 	struct smca_bank *b;
 
 	if (bank >= MAX_NR_BANKS)
 		return N_SMCA_BANK_TYPES;
 
-	b = &smca_banks[bank];
+	b = &per_cpu(smca_banks, cpu)[bank];
 	if (!b->hwid)
 		return N_SMCA_BANK_TYPES;
 
@@ -134,7 +157,7 @@ enum smca_bank_types smca_get_bank_type(unsigned int bank)
 }
 EXPORT_SYMBOL_GPL(smca_get_bank_type);
 
-static struct smca_hwid smca_hwid_mcatypes[] = {
+static const struct smca_hwid smca_hwid_mcatypes[] = {
 	/* { bank_type, hwid_mcatype } */
 
 	/* Reserved type */
@@ -174,6 +197,9 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 	/* Microprocessor 5 Unit MCA type */
 	{ SMCA_MP5,	 HWID_MCATYPE(0x01, 0x2)	},
 
+	/* MPDMA MCA type */
+	{ SMCA_MPDMA,	 HWID_MCATYPE(0x01, 0x3)	},
+
 	/* Northbridge IO Unit MCA type */
 	{ SMCA_NBIO,	 HWID_MCATYPE(0x18, 0x0)	},
 
@@ -181,19 +207,17 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 	{ SMCA_PCIE,	 HWID_MCATYPE(0x46, 0x0)	},
 	{ SMCA_PCIE_V2,	 HWID_MCATYPE(0x46, 0x1)	},
 
-	/* xGMI PCS MCA type */
 	{ SMCA_XGMI_PCS, HWID_MCATYPE(0x50, 0x0)	},
-
-	/* xGMI PHY MCA type */
+	{ SMCA_NBIF,	 HWID_MCATYPE(0x6C, 0x0)	},
+	{ SMCA_SHUB,	 HWID_MCATYPE(0x80, 0x0)	},
+	{ SMCA_SATA,	 HWID_MCATYPE(0xA8, 0x0)	},
+	{ SMCA_USB,	 HWID_MCATYPE(0xAA, 0x0)	},
+	{ SMCA_GMI_PCS,  HWID_MCATYPE(0x241, 0x0)	},
 	{ SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0)	},
-
-	/* WAFL PHY MCA type */
 	{ SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0)	},
+	{ SMCA_GMI_PHY,	 HWID_MCATYPE(0x269, 0x0)	},
 };
 
-struct smca_bank smca_banks[MAX_NR_BANKS];
-EXPORT_SYMBOL_GPL(smca_banks);
-
 /*
  * In SMCA enabled processors, we can have multiple banks for a given IP type.
  * So to define a unique name for each bank, we use a temp c-string to append
@@ -249,8 +273,9 @@ static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu)
 
 static void smca_configure(unsigned int bank, unsigned int cpu)
 {
+	u8 *bank_counts = this_cpu_ptr(smca_bank_counts);
+	const struct smca_hwid *s_hwid;
 	unsigned int i, hwid_mcatype;
-	struct smca_hwid *s_hwid;
 	u32 high, low;
 	u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank);
 
@@ -286,10 +311,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 
 	smca_set_misc_banks_map(bank, cpu);
 
-	/* Return early if this bank was already initialized. */
-	if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0)
-		return;
-
 	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) {
 		pr_warn("Failed to read MCA_IPID for bank %d\n", bank);
 		return;
@@ -300,10 +321,11 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 
 	for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) {
 		s_hwid = &smca_hwid_mcatypes[i];
+
 		if (hwid_mcatype == s_hwid->hwid_mcatype) {
-			smca_banks[bank].hwid = s_hwid;
-			smca_banks[bank].id = low;
-			smca_banks[bank].sysfs_id = s_hwid->count++;
+			this_cpu_ptr(smca_banks)[bank].hwid = s_hwid;
+			this_cpu_ptr(smca_banks)[bank].id = low;
+			this_cpu_ptr(smca_banks)[bank].sysfs_id = bank_counts[s_hwid->bank_type]++;
 			break;
 		}
 	}
@@ -589,7 +611,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 
 bool amd_filter_mce(struct mce *m)
 {
-	enum smca_bank_types bank_type = smca_get_bank_type(m->bank);
+	enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank);
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	/* See Family 17h Models 10h-2Fh Erratum #1114. */
@@ -627,7 +649,7 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 	} else if (c->x86 == 0x17 &&
 		   (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) {
 
-		if (smca_get_bank_type(bank) != SMCA_IF)
+		if (smca_get_bank_type(smp_processor_id(), bank) != SMCA_IF)
 			return;
 
 		msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank);
@@ -689,213 +711,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		deferred_error_interrupt_enable(c);
 }
 
-int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
-{
-	u64 dram_base_addr, dram_limit_addr, dram_hole_base;
-	/* We start from the normalized address */
-	u64 ret_addr = norm_addr;
-
-	u32 tmp;
-
-	u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
-	u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
-	u8 intlv_addr_sel, intlv_addr_bit;
-	u8 num_intlv_bits, hashed_bit;
-	u8 lgcy_mmio_hole_en, base = 0;
-	u8 cs_mask, cs_id = 0;
-	bool hash_enabled = false;
-
-	/* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
-	if (amd_df_indirect_read(nid, 0, 0x1B4, umc, &tmp))
-		goto out_err;
-
-	/* Remove HiAddrOffset from normalized address, if enabled: */
-	if (tmp & BIT(0)) {
-		u64 hi_addr_offset = (tmp & GENMASK_ULL(31, 20)) << 8;
-
-		if (norm_addr >= hi_addr_offset) {
-			ret_addr -= hi_addr_offset;
-			base = 1;
-		}
-	}
-
-	/* Read D18F0x110 (DramBaseAddress). */
-	if (amd_df_indirect_read(nid, 0, 0x110 + (8 * base), umc, &tmp))
-		goto out_err;
-
-	/* Check if address range is valid. */
-	if (!(tmp & BIT(0))) {
-		pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
-			__func__, tmp);
-		goto out_err;
-	}
-
-	lgcy_mmio_hole_en = tmp & BIT(1);
-	intlv_num_chan	  = (tmp >> 4) & 0xF;
-	intlv_addr_sel	  = (tmp >> 8) & 0x7;
-	dram_base_addr	  = (tmp & GENMASK_ULL(31, 12)) << 16;
-
-	/* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
-	if (intlv_addr_sel > 3) {
-		pr_err("%s: Invalid interleave address select %d.\n",
-			__func__, intlv_addr_sel);
-		goto out_err;
-	}
-
-	/* Read D18F0x114 (DramLimitAddress). */
-	if (amd_df_indirect_read(nid, 0, 0x114 + (8 * base), umc, &tmp))
-		goto out_err;
-
-	intlv_num_sockets = (tmp >> 8) & 0x1;
-	intlv_num_dies	  = (tmp >> 10) & 0x3;
-	dram_limit_addr	  = ((tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);
-
-	intlv_addr_bit = intlv_addr_sel + 8;
-
-	/* Re-use intlv_num_chan by setting it equal to log2(#channels) */
-	switch (intlv_num_chan) {
-	case 0:	intlv_num_chan = 0; break;
-	case 1: intlv_num_chan = 1; break;
-	case 3: intlv_num_chan = 2; break;
-	case 5:	intlv_num_chan = 3; break;
-	case 7:	intlv_num_chan = 4; break;
-
-	case 8: intlv_num_chan = 1;
-		hash_enabled = true;
-		break;
-	default:
-		pr_err("%s: Invalid number of interleaved channels %d.\n",
-			__func__, intlv_num_chan);
-		goto out_err;
-	}
-
-	num_intlv_bits = intlv_num_chan;
-
-	if (intlv_num_dies > 2) {
-		pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
-			__func__, intlv_num_dies);
-		goto out_err;
-	}
-
-	num_intlv_bits += intlv_num_dies;
-
-	/* Add a bit if sockets are interleaved. */
-	num_intlv_bits += intlv_num_sockets;
-
-	/* Assert num_intlv_bits <= 4 */
-	if (num_intlv_bits > 4) {
-		pr_err("%s: Invalid interleave bits %d.\n",
-			__func__, num_intlv_bits);
-		goto out_err;
-	}
-
-	if (num_intlv_bits > 0) {
-		u64 temp_addr_x, temp_addr_i, temp_addr_y;
-		u8 die_id_bit, sock_id_bit, cs_fabric_id;
-
-		/*
-		 * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
-		 * This is the fabric id for this coherent slave. Use
-		 * umc/channel# as instance id of the coherent slave
-		 * for FICAA.
-		 */
-		if (amd_df_indirect_read(nid, 0, 0x50, umc, &tmp))
-			goto out_err;
-
-		cs_fabric_id = (tmp >> 8) & 0xFF;
-		die_id_bit   = 0;
-
-		/* If interleaved over more than 1 channel: */
-		if (intlv_num_chan) {
-			die_id_bit = intlv_num_chan;
-			cs_mask	   = (1 << die_id_bit) - 1;
-			cs_id	   = cs_fabric_id & cs_mask;
-		}
-
-		sock_id_bit = die_id_bit;
-
-		/* Read D18F1x208 (SystemFabricIdMask). */
-		if (intlv_num_dies || intlv_num_sockets)
-			if (amd_df_indirect_read(nid, 1, 0x208, umc, &tmp))
-				goto out_err;
-
-		/* If interleaved over more than 1 die. */
-		if (intlv_num_dies) {
-			sock_id_bit  = die_id_bit + intlv_num_dies;
-			die_id_shift = (tmp >> 24) & 0xF;
-			die_id_mask  = (tmp >> 8) & 0xFF;
-
-			cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
-		}
-
-		/* If interleaved over more than 1 socket. */
-		if (intlv_num_sockets) {
-			socket_id_shift	= (tmp >> 28) & 0xF;
-			socket_id_mask	= (tmp >> 16) & 0xFF;
-
-			cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
-		}
-
-		/*
-		 * The pre-interleaved address consists of XXXXXXIIIYYYYY
-		 * where III is the ID for this CS, and XXXXXXYYYYY are the
-		 * address bits from the post-interleaved address.
-		 * "num_intlv_bits" has been calculated to tell us how many "I"
-		 * bits there are. "intlv_addr_bit" tells us how many "Y" bits
-		 * there are (where "I" starts).
-		 */
-		temp_addr_y = ret_addr & GENMASK_ULL(intlv_addr_bit-1, 0);
-		temp_addr_i = (cs_id << intlv_addr_bit);
-		temp_addr_x = (ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
-		ret_addr    = temp_addr_x | temp_addr_i | temp_addr_y;
-	}
-
-	/* Add dram base address */
-	ret_addr += dram_base_addr;
-
-	/* If legacy MMIO hole enabled */
-	if (lgcy_mmio_hole_en) {
-		if (amd_df_indirect_read(nid, 0, 0x104, umc, &tmp))
-			goto out_err;
-
-		dram_hole_base = tmp & GENMASK(31, 24);
-		if (ret_addr >= dram_hole_base)
-			ret_addr += (BIT_ULL(32) - dram_hole_base);
-	}
-
-	if (hash_enabled) {
-		/* Save some parentheses and grab ls-bit at the end. */
-		hashed_bit =	(ret_addr >> 12) ^
-				(ret_addr >> 18) ^
-				(ret_addr >> 21) ^
-				(ret_addr >> 30) ^
-				cs_id;
-
-		hashed_bit &= BIT(0);
-
-		if (hashed_bit != ((ret_addr >> intlv_addr_bit) & BIT(0)))
-			ret_addr ^= BIT(intlv_addr_bit);
-	}
-
-	/* Is calculated system address is above DRAM limit address? */
-	if (ret_addr > dram_limit_addr)
-		goto out_err;
-
-	*sys_addr = ret_addr;
-	return 0;
-
-out_err:
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);
-
 bool amd_mce_is_memory_error(struct mce *m)
 {
 	/* ErrCodeExt[20:16] */
 	u8 xec = (m->status >> 16) & 0x1f;
 
 	if (mce_flags.smca)
-		return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0;
+		return smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC && xec == 0x0;
 
 	return m->bank == 4 && xec == 0x8;
 }
@@ -1211,7 +1033,7 @@ static struct kobj_type threshold_ktype = {
 	.release		= threshold_block_release,
 };
 
-static const char *get_name(unsigned int bank, struct threshold_block *b)
+static const char *get_name(unsigned int cpu, unsigned int bank, struct threshold_block *b)
 {
 	enum smca_bank_types bank_type;
 
@@ -1222,7 +1044,7 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
 		return th_names[bank];
 	}
 
-	bank_type = smca_get_bank_type(bank);
+	bank_type = smca_get_bank_type(cpu, bank);
 	if (bank_type >= N_SMCA_BANK_TYPES)
 		return NULL;
 
@@ -1232,12 +1054,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
 		return NULL;
 	}
 
-	if (smca_banks[bank].hwid->count == 1)
+	if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1)
 		return smca_get_name(bank_type);
 
 	snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
-		 "%s_%x", smca_get_name(bank_type),
-			  smca_banks[bank].sysfs_id);
+		 "%s_%u", smca_get_name(bank_type),
+			  per_cpu(smca_banks, cpu)[bank].sysfs_id);
 	return buf_mcatype;
 }
 
@@ -1293,7 +1115,7 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb
 	else
 		tb->blocks = b;
 
-	err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b));
+	err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(cpu, bank, b));
 	if (err)
 		goto out_free;
 recurse:
@@ -1348,7 +1170,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
 	struct device *dev = this_cpu_read(mce_device);
 	struct amd_northbridge *nb = NULL;
 	struct threshold_bank *b = NULL;
-	const char *name = get_name(bank, NULL);
+	const char *name = get_name(cpu, bank, NULL);
 	int err = 0;
 
 	if (!dev)

arch/x86/kernel/cpu/mce/core.c

@@ -99,7 +99,6 @@ struct mca_config mca_cfg __read_mostly = {
 
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static unsigned long mce_need_notify;
-static int cpu_missing;
 
 /*
  * MCA banks polled by the period polling timer for corrected events.
@@ -128,7 +127,7 @@ static struct irq_work mce_irq_work;
 BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
-noinstr void mce_setup(struct mce *m)
+void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
@@ -267,11 +266,17 @@ static void wait_for_panic(void)
 	panic("Panicing machine check CPU died");
 }
 
-static void mce_panic(const char *msg, struct mce *final, char *exp)
+static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 {
-	int apei_err = 0;
 	struct llist_node *pending;
 	struct mce_evt_llist *l;
+	int apei_err = 0;
+
+	/*
+	 * Allow instrumentation around external facilities usage. Not that it
+	 * matters a whole lot since the machine is going to panic anyway.
+	 */
+	instrumentation_begin();
 
 	if (!fake_panic) {
 		/*
@@ -286,7 +291,7 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 	} else {
 		/* Don't log too much for fake panic */
 		if (atomic_inc_return(&mce_fake_panicked) > 1)
-			return;
+			goto out;
 	}
 	pending = mce_gen_pool_prepare_records();
 	/* First print corrected ones that are still unlogged */
@@ -314,8 +319,6 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 		if (!apei_err)
 			apei_err = apei_write_mce(final);
 	}
-	if (cpu_missing)
-		pr_emerg(HW_ERR "Some CPUs didn't answer in synchronization\n");
 	if (exp)
 		pr_emerg(HW_ERR "Machine check: %s\n", exp);
 	if (!fake_panic) {
@@ -324,6 +327,9 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 		panic(msg);
 	} else
 		pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
+
+out:
+	instrumentation_end();
 }
 
 /* Support code for software error injection */
@@ -365,7 +371,7 @@ void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 }
 
 /* MSR access wrappers used for error injection */
-static noinstr u64 mce_rdmsrl(u32 msr)
+noinstr u64 mce_rdmsrl(u32 msr)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -433,9 +439,15 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
  * check into our "mce" struct so that we can use it later to assess
  * the severity of the problem as we read per-bank specific details.
  */
-static inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
+static noinstr void mce_gather_info(struct mce *m, struct pt_regs *regs)
 {
+	/*
+	 * Enable instrumentation around mce_setup() which calls external
+	 * facilities.
+	 */
+	instrumentation_begin();
 	mce_setup(m);
+	instrumentation_end();
 
 	m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
 	if (regs) {
@@ -636,7 +648,7 @@ static struct notifier_block mce_default_nb = {
 /*
  * Read ADDR and MISC registers.
  */
-static void mce_read_aux(struct mce *m, int i)
+static noinstr void mce_read_aux(struct mce *m, int i)
 {
 	if (m->status & MCI_STATUS_MISCV)
 		m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
@@ -871,8 +883,13 @@ static cpumask_t mce_missing_cpus = CPU_MASK_ALL;
 /*
  * Check if a timeout waiting for other CPUs happened.
  */
-static int mce_timed_out(u64 *t, const char *msg)
+static noinstr int mce_timed_out(u64 *t, const char *msg)
 {
+	int ret = 0;
+
+	/* Enable instrumentation around calls to external facilities */
+	instrumentation_begin();
+
 	/*
 	 * The others already did panic for some reason.
 	 * Bail out like in a timeout.
@@ -891,13 +908,17 @@ static int mce_timed_out(u64 *t, const char *msg)
 					 cpumask_pr_args(&mce_missing_cpus));
 			mce_panic(msg, NULL, NULL);
 		}
-		cpu_missing = 1;
-		return 1;
+		ret = 1;
+		goto out;
 	}
 	*t -= SPINUNIT;
+
 out:
 	touch_nmi_watchdog();
-	return 0;
+
+	instrumentation_end();
+
+	return ret;
 }
 
 /*
@@ -986,14 +1007,13 @@ static atomic_t global_nwo;
  * in the entry order.
  * TBD double check parallel CPU hotunplug
  */
-static int mce_start(int *no_way_out)
+static noinstr int mce_start(int *no_way_out)
 {
-	int order;
-	int cpus = num_online_cpus();
 	u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC;
+	int order, ret = -1;
 
 	if (!timeout)
-		return -1;
+		return ret;
 
 	atomic_add(*no_way_out, &global_nwo);
 	/*
@@ -1003,14 +1023,17 @@ static int mce_start(int *no_way_out)
 	order = atomic_inc_return(&mce_callin);
 	cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus);
 
+	/* Enable instrumentation around calls to external facilities */
+	instrumentation_begin();
+
 	/*
 	 * Wait for everyone.
 	 */
-	while (atomic_read(&mce_callin) != cpus) {
+	while (atomic_read(&mce_callin) != num_online_cpus()) {
 		if (mce_timed_out(&timeout,
 				  "Timeout: Not all CPUs entered broadcast exception handler")) {
 			atomic_set(&global_nwo, 0);
-			return -1;
+			goto out;
 		}
 		ndelay(SPINUNIT);
 	}
@@ -1036,7 +1059,7 @@ static int mce_start(int *no_way_out)
 			if (mce_timed_out(&timeout,
 					  "Timeout: Subject CPUs unable to finish machine check processing")) {
 				atomic_set(&global_nwo, 0);
-				return -1;
+				goto out;
 			}
 			ndelay(SPINUNIT);
 		}
@@ -1047,17 +1070,25 @@ static int mce_start(int *no_way_out)
 	 */
 	*no_way_out = atomic_read(&global_nwo);
 
-	return order;
+	ret = order;
+
+out:
+	instrumentation_end();
+
+	return ret;
 }
 
 /*
  * Synchronize between CPUs after main scanning loop.
  * This invokes the bulk of the Monarch processing.
  */
-static int mce_end(int order)
+static noinstr int mce_end(int order)
 {
-	int ret = -1;
 	u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC;
+	int ret = -1;
+
+	/* Allow instrumentation around external facilities. */
+	instrumentation_begin();
 
 	if (!timeout)
 		goto reset;
@@ -1070,14 +1101,11 @@ static int mce_end(int order)
 	atomic_inc(&mce_executing);
 
 	if (order == 1) {
-		/* CHECKME: Can this race with a parallel hotplug? */
-		int cpus = num_online_cpus();
-
 		/*
 		 * Monarch: Wait for everyone to go through their scanning
 		 * loops.
 		 */
-		while (atomic_read(&mce_executing) <= cpus) {
+		while (atomic_read(&mce_executing) <= num_online_cpus()) {
 			if (mce_timed_out(&timeout,
 					  "Timeout: Monarch CPU unable to finish machine check processing"))
 				goto reset;
@@ -1101,7 +1129,8 @@ static int mce_end(int order)
 		/*
 		 * Don't reset anything. That's done by the Monarch.
 		 */
-		return 0;
+		ret = 0;
+		goto out;
 	}
 
 	/*
@@ -1117,6 +1146,10 @@ static int mce_end(int order)
 	 * Let others run again.
 	 */
 	atomic_set(&mce_executing, 0);
+
+out:
+	instrumentation_end();
+
 	return ret;
 }
 
@@ -1165,13 +1198,14 @@ static noinstr bool mce_check_crashing_cpu(void)
 	return false;
 }
 
-static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final,
-			    unsigned long *toclear, unsigned long *valid_banks,
-			    int no_way_out, int *worst)
+static __always_inline int
+__mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final,
+		unsigned long *toclear, unsigned long *valid_banks, int no_way_out,
+		int *worst)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
-	int severity, i;
+	int severity, i, taint = 0;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		__clear_bit(i, toclear);
@@ -1198,7 +1232,7 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 			continue;
 
 		/* Set taint even when machine check was not enabled. */
-		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+		taint++;
 
 		severity = mce_severity(m, regs, cfg->tolerant, NULL, true);
 
@@ -1221,7 +1255,13 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 		/* assuming valid severity level != 0 */
 		m->severity = severity;
 
+		/*
+		 * Enable instrumentation around the mce_log() call which is
+		 * done in #MC context, where instrumentation is disabled.
+		 */
+		instrumentation_begin();
 		mce_log(m);
+		instrumentation_end();
 
 		if (severity > *worst) {
 			*final = *m;
@@ -1231,6 +1271,8 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 
 	/* mce_clear_state will clear *final, save locally for use later */
 	*m = *final;
+
+	return taint;
 }
 
 static void kill_me_now(struct callback_head *ch)
@@ -1320,11 +1362,11 @@ static noinstr void unexpected_machine_check(struct pt_regs *regs)
 }
 
 /*
- * The actual machine check handler. This only handles real
- * exceptions when something got corrupted coming in through int 18.
+ * The actual machine check handler. This only handles real exceptions when
+ * something got corrupted coming in through int 18.
  *
- * This is executed in NMI context not subject to normal locking rules. This
- * implies that most kernel services cannot be safely used. Don't even
+ * This is executed in #MC context not subject to normal locking rules.
+ * This implies that most kernel services cannot be safely used. Don't even
  * think about putting a printk in there!
  *
  * On Intel systems this is entered on all CPUs in parallel through
@@ -1336,12 +1378,20 @@ static noinstr void unexpected_machine_check(struct pt_regs *regs)
  * issues: if the machine check was due to a failure of the memory
  * backing the user stack, tracing that reads the user stack will cause
  * potentially infinite recursion.
+ *
+ * Currently, the #MC handler calls out to a number of external facilities
+ * and, therefore, allows instrumentation around them. The optimal thing to
+ * have would be to do the absolutely minimal work required in #MC context
+ * and have instrumentation disabled only around that. Further processing can
+ * then happen in process context where instrumentation is allowed. Achieving
+ * that requires careful auditing and modifications. Until then, the code
+ * allows instrumentation temporarily, where required. *
  */
 noinstr void do_machine_check(struct pt_regs *regs)
 {
-	int worst = 0, order, no_way_out, kill_current_task, lmce;
-	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
-	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
+	int worst = 0, order, no_way_out, kill_current_task, lmce, taint = 0;
+	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS) = { 0 };
+	DECLARE_BITMAP(toclear, MAX_NR_BANKS) = { 0 };
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
 	char *msg = NULL;
@@ -1385,7 +1435,6 @@ noinstr void do_machine_check(struct pt_regs *regs)
 	final = this_cpu_ptr(&mces_seen);
 	*final = m;
 
-	memset(valid_banks, 0, sizeof(valid_banks));
 	no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs);
 
 	barrier();
@@ -1419,7 +1468,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		order = mce_start(&no_way_out);
 	}
 
-	__mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst);
+	taint = __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst);
 
 	if (!no_way_out)
 		mce_clear_state(toclear);
@@ -1451,6 +1500,16 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 	}
 
+	/*
+	 * Enable instrumentation around the external facilities like task_work_add()
+	 * (via queue_task_work()), fixup_exception() etc. For now, that is. Fixing this
+	 * properly would need a lot more involved reorganization.
+	 */
+	instrumentation_begin();
+
+	if (taint)
+		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	if (worst != MCE_AR_SEVERITY && !kill_current_task)
 		goto out;
 
@@ -1482,7 +1541,10 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
 			queue_task_work(&m, msg, kill_me_never);
 	}
+
 out:
+	instrumentation_end();
+
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
@@ -2702,7 +2764,6 @@ struct dentry *mce_get_debugfs_dir(void)
 
 static void mce_reset(void)
 {
-	cpu_missing = 0;
 	atomic_set(&mce_fake_panicked, 0);
 	atomic_set(&mce_executing, 0);
 	atomic_set(&mce_callin, 0);

arch/x86/kernel/cpu/mce/inject.c

@@ -74,7 +74,6 @@ MCE_INJECT_SET(status);
 MCE_INJECT_SET(misc);
 MCE_INJECT_SET(addr);
 MCE_INJECT_SET(synd);
-MCE_INJECT_SET(ipid);
 
 #define MCE_INJECT_GET(reg)						\
 static int inj_##reg##_get(void *data, u64 *val)			\
@@ -95,6 +94,20 @@ DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n");
 DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n");
 DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n");
 DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n");
+
+/* Use the user provided IPID value on a sw injection. */
+static int inj_ipid_set(void *data, u64 val)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
+		if (inj_type == SW_INJ)
+			m->ipid = val;
+	}
+
+	return 0;
+}
+
 DEFINE_SIMPLE_ATTRIBUTE(ipid_fops, inj_ipid_get, inj_ipid_set, "%llx\n");
 
 static void setup_inj_struct(struct mce *m)
@@ -350,7 +363,7 @@ static ssize_t flags_write(struct file *filp, const char __user *ubuf,
 	char buf[MAX_FLAG_OPT_SIZE], *__buf;
 	int err;
 
-	if (cnt > MAX_FLAG_OPT_SIZE)
+	if (!cnt || cnt > MAX_FLAG_OPT_SIZE)
 		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
@@ -490,6 +503,8 @@ static void do_inject(void)
 
 	i_mce.tsc = rdtsc_ordered();
 
+	i_mce.status |= MCI_STATUS_VAL;
+
 	if (i_mce.misc)
 		i_mce.status |= MCI_STATUS_MISCV;
 
@@ -577,6 +592,33 @@ static int inj_bank_set(void *data, u64 val)
 	}
 
 	m->bank = val;
+
+	/*
+	 * sw-only injection allows to write arbitrary values into the MCA
+	 * registers because it tests only the decoding paths.
+	 */
+	if (inj_type == SW_INJ)
+		goto inject;
+
+	/*
+	 * Read IPID value to determine if a bank is populated on the target
+	 * CPU.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
+		u64 ipid;
+
+		if (rdmsrl_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
+			pr_err("Error reading IPID on CPU%d\n", m->extcpu);
+			return -EINVAL;
+		}
+
+		if (!ipid) {
+			pr_err("Cannot inject into unpopulated bank %llu\n", val);
+			return -ENODEV;
+		}
+	}
+
+inject:
 	do_inject();
 
 	/* Reset injection struct */

arch/x86/kernel/cpu/mce/internal.h

@@ -207,4 +207,6 @@ static inline void pentium_machine_check(struct pt_regs *regs) {}
 static inline void winchip_machine_check(struct pt_regs *regs) {}
 #endif
 
+noinstr u64 mce_rdmsrl(u32 msr);
+
 #endif /* __X86_MCE_INTERNAL_H__ */

arch/x86/kernel/cpu/mce/severity.c

@@ -222,6 +222,9 @@ static bool is_copy_from_user(struct pt_regs *regs)
 	struct insn insn;
 	int ret;
 
+	if (!regs)
+		return false;
+
 	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
 		return false;
 
@@ -263,24 +266,36 @@ static bool is_copy_from_user(struct pt_regs *regs)
  * distinguish an exception taken in user from from one
  * taken in the kernel.
  */
-static int error_context(struct mce *m, struct pt_regs *regs)
+static noinstr int error_context(struct mce *m, struct pt_regs *regs)
 {
+	int fixup_type;
+	bool copy_user;
+
 	if ((m->cs & 3) == 3)
 		return IN_USER;
+
 	if (!mc_recoverable(m->mcgstatus))
 		return IN_KERNEL;
 
-	switch (ex_get_fixup_type(m->ip)) {
+	/* Allow instrumentation around external facilities usage. */
+	instrumentation_begin();
+	fixup_type = ex_get_fixup_type(m->ip);
+	copy_user  = is_copy_from_user(regs);
+	instrumentation_end();
+
+	switch (fixup_type) {
 	case EX_TYPE_UACCESS:
 	case EX_TYPE_COPY:
-		if (!regs || !is_copy_from_user(regs))
+		if (!copy_user)
 			return IN_KERNEL;
 		m->kflags |= MCE_IN_KERNEL_COPYIN;
 		fallthrough;
+
 	case EX_TYPE_FAULT_MCE_SAFE:
 	case EX_TYPE_DEFAULT_MCE_SAFE:
 		m->kflags |= MCE_IN_KERNEL_RECOV;
 		return IN_KERNEL_RECOV;
+
 	default:
 		return IN_KERNEL;
 	}
@@ -288,8 +303,7 @@ static int error_context(struct mce *m, struct pt_regs *regs)
 
 static int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
 {
-	u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
-	u32 low, high;
+	u64 mcx_cfg;
 
 	/*
 	 * We need to look at the following bits:
@@ -300,11 +314,10 @@ static int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
 	if (!mce_flags.succor)
 		return MCE_PANIC_SEVERITY;
 
-	if (rdmsr_safe(addr, &low, &high))
-		return MCE_PANIC_SEVERITY;
+	mcx_cfg = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(m->bank));
 
 	/* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */
-	if ((low & MCI_CONFIG_MCAX) &&
+	if ((mcx_cfg & MCI_CONFIG_MCAX) &&
 	    (m->status & MCI_STATUS_TCC) &&
 	    (err_ctx == IN_KERNEL))
 		return MCE_PANIC_SEVERITY;
@@ -317,8 +330,8 @@ 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, struct pt_regs *regs, int tolerant,
-			    char **msg, bool is_excp)
+static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant,
+				    char **msg, bool is_excp)
 {
 	enum context ctx = error_context(m, regs);
 
@@ -370,8 +383,8 @@ static int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant,
 	return MCE_KEEP_SEVERITY;
 }
 
-static int mce_severity_intel(struct mce *m, struct pt_regs *regs,
-			      int tolerant, char **msg, bool is_excp)
+static noinstr 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, regs);
@@ -407,8 +420,8 @@ static int mce_severity_intel(struct mce *m, struct pt_regs *regs,
 	}
 }
 
-int mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg,
-		 bool is_excp)
+int noinstr mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg,
+			 bool is_excp)
 {
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)

arch/x86/lib/copy_user_64.S

@@ -225,6 +225,7 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string)
  * Don't try to copy the tail if machine check happened
  *
  * Input:
+ * eax trap number written by ex_handler_copy()
  * rdi destination
  * rsi source
  * rdx count
@@ -233,12 +234,20 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string)
  * eax uncopied bytes or 0 if successful.
  */
 SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail)
+	cmp $X86_TRAP_MC,%eax
+	je 3f
+
 	movl %edx,%ecx
 1:	rep movsb
 2:	mov %ecx,%eax
 	ASM_CLAC
 	ret
 
+3:
+	movl %edx,%eax
+	ASM_CLAC
+	RET
+
 	_ASM_EXTABLE_CPY(1b, 2b)
 SYM_CODE_END(.Lcopy_user_handle_tail)
 

drivers/edac/amd64_edac.c

@@ -988,6 +988,281 @@ static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr)
 	return csrow;
 }
 
+/* Protect the PCI config register pairs used for DF indirect access. */
+static DEFINE_MUTEX(df_indirect_mutex);
+
+/*
+ * Data Fabric Indirect Access uses FICAA/FICAD.
+ *
+ * Fabric Indirect Configuration Access Address (FICAA): Constructed based
+ * on the device's Instance Id and the PCI function and register offset of
+ * the desired register.
+ *
+ * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO
+ * and FICAD HI registers but so far we only need the LO register.
+ *
+ * Use Instance Id 0xFF to indicate a broadcast read.
+ */
+#define DF_BROADCAST	0xFF
+static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+	struct pci_dev *F4;
+	u32 ficaa;
+	int err = -ENODEV;
+
+	if (node >= amd_nb_num())
+		goto out;
+
+	F4 = node_to_amd_nb(node)->link;
+	if (!F4)
+		goto out;
+
+	ficaa  = (instance_id == DF_BROADCAST) ? 0 : 1;
+	ficaa |= reg & 0x3FC;
+	ficaa |= (func & 0x7) << 11;
+	ficaa |= instance_id << 16;
+
+	mutex_lock(&df_indirect_mutex);
+
+	err = pci_write_config_dword(F4, 0x5C, ficaa);
+	if (err) {
+		pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
+		goto out_unlock;
+	}
+
+	err = pci_read_config_dword(F4, 0x98, lo);
+	if (err)
+		pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
+
+out_unlock:
+	mutex_unlock(&df_indirect_mutex);
+
+out:
+	return err;
+}
+
+static int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+	return __df_indirect_read(node, func, reg, instance_id, lo);
+}
+
+static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo)
+{
+	return __df_indirect_read(node, func, reg, DF_BROADCAST, lo);
+}
+
+struct addr_ctx {
+	u64 ret_addr;
+	u32 tmp;
+	u16 nid;
+	u8 inst_id;
+};
+
+static int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
+{
+	u64 dram_base_addr, dram_limit_addr, dram_hole_base;
+
+	u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
+	u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
+	u8 intlv_addr_sel, intlv_addr_bit;
+	u8 num_intlv_bits, hashed_bit;
+	u8 lgcy_mmio_hole_en, base = 0;
+	u8 cs_mask, cs_id = 0;
+	bool hash_enabled = false;
+
+	struct addr_ctx ctx;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	/* Start from the normalized address */
+	ctx.ret_addr = norm_addr;
+
+	ctx.nid = nid;
+	ctx.inst_id = umc;
+
+	/* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
+	if (df_indirect_read_instance(nid, 0, 0x1B4, umc, &ctx.tmp))
+		goto out_err;
+
+	/* Remove HiAddrOffset from normalized address, if enabled: */
+	if (ctx.tmp & BIT(0)) {
+		u64 hi_addr_offset = (ctx.tmp & GENMASK_ULL(31, 20)) << 8;
+
+		if (norm_addr >= hi_addr_offset) {
+			ctx.ret_addr -= hi_addr_offset;
+			base = 1;
+		}
+	}
+
+	/* Read D18F0x110 (DramBaseAddress). */
+	if (df_indirect_read_instance(nid, 0, 0x110 + (8 * base), umc, &ctx.tmp))
+		goto out_err;
+
+	/* Check if address range is valid. */
+	if (!(ctx.tmp & BIT(0))) {
+		pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
+			__func__, ctx.tmp);
+		goto out_err;
+	}
+
+	lgcy_mmio_hole_en = ctx.tmp & BIT(1);
+	intlv_num_chan	  = (ctx.tmp >> 4) & 0xF;
+	intlv_addr_sel	  = (ctx.tmp >> 8) & 0x7;
+	dram_base_addr	  = (ctx.tmp & GENMASK_ULL(31, 12)) << 16;
+
+	/* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
+	if (intlv_addr_sel > 3) {
+		pr_err("%s: Invalid interleave address select %d.\n",
+			__func__, intlv_addr_sel);
+		goto out_err;
+	}
+
+	/* Read D18F0x114 (DramLimitAddress). */
+	if (df_indirect_read_instance(nid, 0, 0x114 + (8 * base), umc, &ctx.tmp))
+		goto out_err;
+
+	intlv_num_sockets = (ctx.tmp >> 8) & 0x1;
+	intlv_num_dies	  = (ctx.tmp >> 10) & 0x3;
+	dram_limit_addr	  = ((ctx.tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);
+
+	intlv_addr_bit = intlv_addr_sel + 8;
+
+	/* Re-use intlv_num_chan by setting it equal to log2(#channels) */
+	switch (intlv_num_chan) {
+	case 0:	intlv_num_chan = 0; break;
+	case 1: intlv_num_chan = 1; break;
+	case 3: intlv_num_chan = 2; break;
+	case 5:	intlv_num_chan = 3; break;
+	case 7:	intlv_num_chan = 4; break;
+
+	case 8: intlv_num_chan = 1;
+		hash_enabled = true;
+		break;
+	default:
+		pr_err("%s: Invalid number of interleaved channels %d.\n",
+			__func__, intlv_num_chan);
+		goto out_err;
+	}
+
+	num_intlv_bits = intlv_num_chan;
+
+	if (intlv_num_dies > 2) {
+		pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
+			__func__, intlv_num_dies);
+		goto out_err;
+	}
+
+	num_intlv_bits += intlv_num_dies;
+
+	/* Add a bit if sockets are interleaved. */
+	num_intlv_bits += intlv_num_sockets;
+
+	/* Assert num_intlv_bits <= 4 */
+	if (num_intlv_bits > 4) {
+		pr_err("%s: Invalid interleave bits %d.\n",
+			__func__, num_intlv_bits);
+		goto out_err;
+	}
+
+	if (num_intlv_bits > 0) {
+		u64 temp_addr_x, temp_addr_i, temp_addr_y;
+		u8 die_id_bit, sock_id_bit, cs_fabric_id;
+
+		/*
+		 * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
+		 * This is the fabric id for this coherent slave. Use
+		 * umc/channel# as instance id of the coherent slave
+		 * for FICAA.
+		 */
+		if (df_indirect_read_instance(nid, 0, 0x50, umc, &ctx.tmp))
+			goto out_err;
+
+		cs_fabric_id = (ctx.tmp >> 8) & 0xFF;
+		die_id_bit   = 0;
+
+		/* If interleaved over more than 1 channel: */
+		if (intlv_num_chan) {
+			die_id_bit = intlv_num_chan;
+			cs_mask	   = (1 << die_id_bit) - 1;
+			cs_id	   = cs_fabric_id & cs_mask;
+		}
+
+		sock_id_bit = die_id_bit;
+
+		/* Read D18F1x208 (SystemFabricIdMask). */
+		if (intlv_num_dies || intlv_num_sockets)
+			if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp))
+				goto out_err;
+
+		/* If interleaved over more than 1 die. */
+		if (intlv_num_dies) {
+			sock_id_bit  = die_id_bit + intlv_num_dies;
+			die_id_shift = (ctx.tmp >> 24) & 0xF;
+			die_id_mask  = (ctx.tmp >> 8) & 0xFF;
+
+			cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
+		}
+
+		/* If interleaved over more than 1 socket. */
+		if (intlv_num_sockets) {
+			socket_id_shift	= (ctx.tmp >> 28) & 0xF;
+			socket_id_mask	= (ctx.tmp >> 16) & 0xFF;
+
+			cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
+		}
+
+		/*
+		 * The pre-interleaved address consists of XXXXXXIIIYYYYY
+		 * where III is the ID for this CS, and XXXXXXYYYYY are the
+		 * address bits from the post-interleaved address.
+		 * "num_intlv_bits" has been calculated to tell us how many "I"
+		 * bits there are. "intlv_addr_bit" tells us how many "Y" bits
+		 * there are (where "I" starts).
+		 */
+		temp_addr_y = ctx.ret_addr & GENMASK_ULL(intlv_addr_bit - 1, 0);
+		temp_addr_i = (cs_id << intlv_addr_bit);
+		temp_addr_x = (ctx.ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
+		ctx.ret_addr    = temp_addr_x | temp_addr_i | temp_addr_y;
+	}
+
+	/* Add dram base address */
+	ctx.ret_addr += dram_base_addr;
+
+	/* If legacy MMIO hole enabled */
+	if (lgcy_mmio_hole_en) {
+		if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp))
+			goto out_err;
+
+		dram_hole_base = ctx.tmp & GENMASK(31, 24);
+		if (ctx.ret_addr >= dram_hole_base)
+			ctx.ret_addr += (BIT_ULL(32) - dram_hole_base);
+	}
+
+	if (hash_enabled) {
+		/* Save some parentheses and grab ls-bit at the end. */
+		hashed_bit =	(ctx.ret_addr >> 12) ^
+				(ctx.ret_addr >> 18) ^
+				(ctx.ret_addr >> 21) ^
+				(ctx.ret_addr >> 30) ^
+				cs_id;
+
+		hashed_bit &= BIT(0);
+
+		if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0)))
+			ctx.ret_addr ^= BIT(intlv_addr_bit);
+	}
+
+	/* Is calculated system address is above DRAM limit address? */
+	if (ctx.ret_addr > dram_limit_addr)
+		goto out_err;
+
+	*sys_addr = ctx.ret_addr;
+	return 0;
+
+out_err:
+	return -EINVAL;
+}
+
 static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16);
 
 /*

drivers/edac/mce_amd.c

@@ -399,6 +399,63 @@ static const char * const smca_mp5_mce_desc[] = {
 	"Instruction Tag Cache Bank B ECC or parity error",
 };
 
+static const char * const smca_mpdma_mce_desc[] = {
+	"Main SRAM [31:0] bank ECC or parity error",
+	"Main SRAM [63:32] bank ECC or parity error",
+	"Main SRAM [95:64] bank ECC or parity error",
+	"Main SRAM [127:96] bank ECC or parity error",
+	"Data Cache Bank A ECC or parity error",
+	"Data Cache Bank B ECC or parity error",
+	"Data Tag Cache Bank A ECC or parity error",
+	"Data Tag Cache Bank B ECC or parity error",
+	"Instruction Cache Bank A ECC or parity error",
+	"Instruction Cache Bank B ECC or parity error",
+	"Instruction Tag Cache Bank A ECC or parity error",
+	"Instruction Tag Cache Bank B ECC or parity error",
+	"Data Cache Bank A ECC or parity error",
+	"Data Cache Bank B ECC or parity error",
+	"Data Tag Cache Bank A ECC or parity error",
+	"Data Tag Cache Bank B ECC or parity error",
+	"Instruction Cache Bank A ECC or parity error",
+	"Instruction Cache Bank B ECC or parity error",
+	"Instruction Tag Cache Bank A ECC or parity error",
+	"Instruction Tag Cache Bank B ECC or parity error",
+	"Data Cache Bank A ECC or parity error",
+	"Data Cache Bank B ECC or parity error",
+	"Data Tag Cache Bank A ECC or parity error",
+	"Data Tag Cache Bank B ECC or parity error",
+	"Instruction Cache Bank A ECC or parity error",
+	"Instruction Cache Bank B ECC or parity error",
+	"Instruction Tag Cache Bank A ECC or parity error",
+	"Instruction Tag Cache Bank B ECC or parity error",
+	"System Hub Read Buffer ECC or parity error",
+	"MPDMA TVF DVSEC Memory ECC or parity error",
+	"MPDMA TVF MMIO Mailbox0 ECC or parity error",
+	"MPDMA TVF MMIO Mailbox1 ECC or parity error",
+	"MPDMA TVF Doorbell Memory ECC or parity error",
+	"MPDMA TVF SDP Slave Memory 0 ECC or parity error",
+	"MPDMA TVF SDP Slave Memory 1 ECC or parity error",
+	"MPDMA TVF SDP Slave Memory 2 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 0 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 1 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 2 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 3 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 4 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 5 ECC or parity error",
+	"MPDMA TVF SDP Master Memory 6 ECC or parity error",
+	"MPDMA PTE Command FIFO ECC or parity error",
+	"MPDMA PTE Hub Data FIFO ECC or parity error",
+	"MPDMA PTE Internal Data FIFO ECC or parity error",
+	"MPDMA PTE Command Memory DMA ECC or parity error",
+	"MPDMA PTE Command Memory Internal ECC or parity error",
+	"MPDMA PTE DMA Completion FIFO ECC or parity error",
+	"MPDMA PTE Tablewalk Completion FIFO ECC or parity error",
+	"MPDMA PTE Descriptor Completion FIFO ECC or parity error",
+	"MPDMA PTE ReadOnly Completion FIFO ECC or parity error",
+	"MPDMA PTE DirectWrite Completion FIFO ECC or parity error",
+	"SDP Watchdog Timer expired",
+};
+
 static const char * const smca_nbio_mce_desc[] = {
 	"ECC or Parity error",
 	"PCIE error",
@@ -448,7 +505,7 @@ static const char * const smca_xgmipcs_mce_desc[] = {
 	"Rx Replay Timeout Error",
 	"LinkSub Tx Timeout Error",
 	"LinkSub Rx Timeout Error",
-	"Rx CMD Pocket Error",
+	"Rx CMD Packet Error",
 };
 
 static const char * const smca_xgmiphy_mce_desc[] = {
@@ -458,11 +515,66 @@ static const char * const smca_xgmiphy_mce_desc[] = {
 	"PHY APB error",
 };
 
-static const char * const smca_waflphy_mce_desc[] = {
-	"RAM ECC Error",
-	"ARC instruction buffer parity error",
-	"ARC data buffer parity error",
-	"PHY APB error",
+static const char * const smca_nbif_mce_desc[] = {
+	"Timeout error from GMI",
+	"SRAM ECC error",
+	"NTB Error Event",
+	"SDP Parity error",
+};
+
+static const char * const smca_sata_mce_desc[] = {
+	"Parity error for port 0",
+	"Parity error for port 1",
+	"Parity error for port 2",
+	"Parity error for port 3",
+	"Parity error for port 4",
+	"Parity error for port 5",
+	"Parity error for port 6",
+	"Parity error for port 7",
+};
+
+static const char * const smca_usb_mce_desc[] = {
+	"Parity error or ECC error for S0 RAM0",
+	"Parity error or ECC error for S0 RAM1",
+	"Parity error or ECC error for S0 RAM2",
+	"Parity error for PHY RAM0",
+	"Parity error for PHY RAM1",
+	"AXI Slave Response error",
+};
+
+static const char * const smca_gmipcs_mce_desc[] = {
+	"Data Loss Error",
+	"Training Error",
+	"Replay Parity Error",
+	"Rx Fifo Underflow Error",
+	"Rx Fifo Overflow Error",
+	"CRC Error",
+	"BER Exceeded Error",
+	"Tx Fifo Underflow Error",
+	"Replay Buffer Parity Error",
+	"Tx Overflow Error",
+	"Replay Fifo Overflow Error",
+	"Replay Fifo Underflow Error",
+	"Elastic Fifo Overflow Error",
+	"Deskew Error",
+	"Offline Error",
+	"Data Startup Limit Error",
+	"FC Init Timeout Error",
+	"Recovery Timeout Error",
+	"Ready Serial Timeout Error",
+	"Ready Serial Attempt Error",
+	"Recovery Attempt Error",
+	"Recovery Relock Attempt Error",
+	"Deskew Abort Error",
+	"Rx Buffer Error",
+	"Rx LFDS Fifo Overflow Error",
+	"Rx LFDS Fifo Underflow Error",
+	"LinkSub Tx Timeout Error",
+	"LinkSub Rx Timeout Error",
+	"Rx CMD Packet Error",
+	"LFDS Training Timeout Error",
+	"LFDS FC Init Timeout Error",
+	"Data Loss Error",
 };
 
 struct smca_mce_desc {
@@ -490,12 +602,21 @@ static struct smca_mce_desc smca_mce_descs[] = {
 	[SMCA_SMU]	= { smca_smu_mce_desc,	ARRAY_SIZE(smca_smu_mce_desc)	},
 	[SMCA_SMU_V2]	= { smca_smu2_mce_desc,	ARRAY_SIZE(smca_smu2_mce_desc)	},
 	[SMCA_MP5]	= { smca_mp5_mce_desc,	ARRAY_SIZE(smca_mp5_mce_desc)	},
+	[SMCA_MPDMA]	= { smca_mpdma_mce_desc,	ARRAY_SIZE(smca_mpdma_mce_desc)	},
 	[SMCA_NBIO]	= { smca_nbio_mce_desc,	ARRAY_SIZE(smca_nbio_mce_desc)	},
 	[SMCA_PCIE]	= { smca_pcie_mce_desc,	ARRAY_SIZE(smca_pcie_mce_desc)	},
 	[SMCA_PCIE_V2]	= { smca_pcie2_mce_desc,   ARRAY_SIZE(smca_pcie2_mce_desc)	},
 	[SMCA_XGMI_PCS]	= { smca_xgmipcs_mce_desc, ARRAY_SIZE(smca_xgmipcs_mce_desc)	},
+	/* NBIF and SHUB have the same error descriptions, for now. */
+	[SMCA_NBIF]	= { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc)	},
+	[SMCA_SHUB]	= { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc)	},
+	[SMCA_SATA]	= { smca_sata_mce_desc, ARRAY_SIZE(smca_sata_mce_desc)	},
+	[SMCA_USB]	= { smca_usb_mce_desc,	ARRAY_SIZE(smca_usb_mce_desc)	},
+	[SMCA_GMI_PCS]	= { smca_gmipcs_mce_desc,  ARRAY_SIZE(smca_gmipcs_mce_desc)	},
+	/* All the PHY bank types have the same error descriptions, for now. */
 	[SMCA_XGMI_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
-	[SMCA_WAFL_PHY]	= { smca_waflphy_mce_desc, ARRAY_SIZE(smca_waflphy_mce_desc)	},
+	[SMCA_WAFL_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
+	[SMCA_GMI_PHY]	= { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc)	},
 };
 
 static bool f12h_mc0_mce(u16 ec, u8 xec)
@@ -1045,20 +1166,13 @@ static void decode_mc6_mce(struct mce *m)
 /* Decode errors according to Scalable MCA specification */
 static void decode_smca_error(struct mce *m)
 {
-	struct smca_hwid *hwid;
-	enum smca_bank_types bank_type;
+	enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank);
 	const char *ip_name;
 	u8 xec = XEC(m->status, xec_mask);
 
-	if (m->bank >= ARRAY_SIZE(smca_banks))
+	if (bank_type >= N_SMCA_BANK_TYPES)
 		return;
 
-	hwid = smca_banks[m->bank].hwid;
-	if (!hwid)
-		return;
-
-	bank_type = hwid->bank_type;
-
 	if (bank_type == SMCA_RESERVED) {
 		pr_emerg(HW_ERR "Bank %d is reserved.\n", m->bank);
 		return;

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -2647,7 +2647,7 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb,
 	 * and error occurred in DramECC (Extended error code = 0) then only
 	 * process the error, else bail out.
 	 */
-	if (!m || !((smca_get_bank_type(m->bank) == SMCA_UMC_V2) &&
+	if (!m || !((smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC_V2) &&
 		    (XEC(m->status, 0x3f) == 0x0)))
 		return NOTIFY_DONE;