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

Pull RAS updates from Borislav Petkov:

 - Misc fixes to the MCE code all over the place, by Jan H. Schönherr.

 - Initial support for AMD F19h and other cleanups to amd64_edac, by
   Yazen Ghannam.

 - Other small cleanups.

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  EDAC/mce_amd: Make fam_ops static global
  EDAC/amd64: Drop some family checks for newer systems
  EDAC/amd64: Add family ops for Family 19h Models 00h-0Fh
  x86/amd_nb: Add Family 19h PCI IDs
  EDAC/mce_amd: Always load on SMCA systems
  x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType
  x86/mce: Fix use of uninitialized MCE message string
  x86/mce: Fix mce=nobootlog
  x86/mce: Take action on UCNA/Deferred errors again
  x86/mce: Remove mce_inject_log() in favor of mce_log()
  x86/mce: Pass MCE message to mce_panic() on failed kernel recovery
  x86/mce/therm_throt: Mark throttle_active_work() as __maybe_unused

Author: torvalds

arch/x86/include/asm/mce.h

@@ -144,7 +144,7 @@ struct mce_log_buffer {
 
 enum mce_notifier_prios {
 	MCE_PRIO_FIRST		= INT_MAX,
-	MCE_PRIO_SRAO		= INT_MAX - 1,
+	MCE_PRIO_UC		= INT_MAX - 1,
 	MCE_PRIO_EXTLOG		= INT_MAX - 2,
 	MCE_PRIO_NFIT		= INT_MAX - 3,
 	MCE_PRIO_EDAC		= INT_MAX - 4,
@@ -290,6 +290,7 @@ extern void apei_mce_report_mem_error(int corrected,
 /* These may be used by multiple smca_hwid_mcatypes */
 enum smca_bank_types {
 	SMCA_LS = 0,	/* Load Store */
+	SMCA_LS_V2,	/* Load Store */
 	SMCA_IF,	/* Instruction Fetch */
 	SMCA_L2_CACHE,	/* L2 Cache */
 	SMCA_DE,	/* Decoder Unit */

arch/x86/kernel/amd_nb.c

@@ -22,6 +22,7 @@
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
+#define PCI_DEVICE_ID_AMD_19H_DF_F4	0x1654
 
 /* Protect the PCI config register pairs used for SMN and DF indirect access. */
 static DEFINE_MUTEX(smn_mutex);
@@ -52,6 +53,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) },
 	{}
 };
 EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -66,6 +68,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };

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

@@ -78,6 +78,7 @@ struct smca_bank_name {
 
 static struct smca_bank_name smca_names[] = {
 	[SMCA_LS]	= { "load_store",	"Load Store Unit" },
+	[SMCA_LS_V2]	= { "load_store",	"Load Store Unit" },
 	[SMCA_IF]	= { "insn_fetch",	"Instruction Fetch Unit" },
 	[SMCA_L2_CACHE]	= { "l2_cache",		"L2 Cache" },
 	[SMCA_DE]	= { "decode_unit",	"Decode Unit" },
@@ -138,6 +139,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 
 	/* ZN Core (HWID=0xB0) MCA types */
 	{ SMCA_LS,	 HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF },
+	{ SMCA_LS_V2,	 HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF },
 	{ SMCA_IF,	 HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
 	{ SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF },
 	{ SMCA_DE,	 HWID_MCATYPE(0xB0, 0x3), 0x1FF },

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

@@ -53,8 +53,6 @@
 
 #include "internal.h"
 
-static DEFINE_MUTEX(mce_log_mutex);
-
 /* sysfs synchronization */
 static DEFINE_MUTEX(mce_sysfs_mutex);
 
@@ -156,19 +154,10 @@ void mce_log(struct mce *m)
 	if (!mce_gen_pool_add(m))
 		irq_work_queue(&mce_irq_work);
 }
-
-void mce_inject_log(struct mce *m)
-{
-	mutex_lock(&mce_log_mutex);
-	mce_log(m);
-	mutex_unlock(&mce_log_mutex);
-}
-EXPORT_SYMBOL_GPL(mce_inject_log);
-
-static struct notifier_block mce_srao_nb;
+EXPORT_SYMBOL_GPL(mce_log);
 
 /*
- * We run the default notifier if we have only the SRAO, the first and the
+ * We run the default notifier if we have only the UC, the first and the
  * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
  * notifiers registered on the chain.
  */
@@ -594,26 +583,29 @@ static struct notifier_block first_nb = {
 	.priority	= MCE_PRIO_FIRST,
 };
 
-static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
-				void *data)
+static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
+			      void *data)
 {
 	struct mce *mce = (struct mce *)data;
 	unsigned long pfn;
 
-	if (!mce)
+	if (!mce || !mce_usable_address(mce))
 		return NOTIFY_DONE;
 
-	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
-		pfn = mce->addr >> PAGE_SHIFT;
-		if (!memory_failure(pfn, 0))
-			set_mce_nospec(pfn);
-	}
+	if (mce->severity != MCE_AO_SEVERITY &&
+	    mce->severity != MCE_DEFERRED_SEVERITY)
+		return NOTIFY_DONE;
+
+	pfn = mce->addr >> PAGE_SHIFT;
+	if (!memory_failure(pfn, 0))
+		set_mce_nospec(pfn);
 
 	return NOTIFY_OK;
 }
-static struct notifier_block mce_srao_nb = {
-	.notifier_call	= srao_decode_notifier,
-	.priority	= MCE_PRIO_SRAO,
+
+static struct notifier_block mce_uc_nb = {
+	.notifier_call	= uc_decode_notifier,
+	.priority	= MCE_PRIO_UC,
 };
 
 static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
@@ -763,26 +755,22 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 log_it:
 		error_seen = true;
 
-		mce_read_aux(&m, i);
+		if (flags & MCP_DONTLOG)
+			goto clear_it;
 
+		mce_read_aux(&m, i);
 		m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
-
 		/*
 		 * Don't get the IP here because it's unlikely to
 		 * have anything to do with the actual error location.
 		 */
-		if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
-			mce_log(&m);
-		else if (mce_usable_address(&m)) {
-			/*
-			 * Although we skipped logging this, we still want
-			 * to take action. Add to the pool so the registered
-			 * notifiers will see it.
-			 */
-			if (!mce_gen_pool_add(&m))
-				mce_schedule_work();
-		}
 
+		if (mca_cfg.dont_log_ce && !mce_usable_address(&m))
+			goto clear_it;
+
+		mce_log(&m);
+
+clear_it:
 		/*
 		 * Clear state for this bank.
 		 */
@@ -807,7 +795,7 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
 static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			  struct pt_regs *regs)
 {
-	char *tmp;
+	char *tmp = *msg;
 	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
@@ -1232,8 +1220,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	struct mca_config *cfg = &mca_cfg;
 	int cpu = smp_processor_id();
-	char *msg = "Unknown";
 	struct mce m, *final;
+	char *msg = NULL;
 	int worst = 0;
 
 	/*
@@ -1365,7 +1353,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		ist_end_non_atomic();
 	} else {
 		if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
-			mce_panic("Failed kernel mode recovery", &m, NULL);
+			mce_panic("Failed kernel mode recovery", &m, msg);
 	}
 
 out_ist:
@@ -2041,7 +2029,7 @@ int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
 	mce_register_decode_chain(&first_nb);
-	mce_register_decode_chain(&mce_srao_nb);
+	mce_register_decode_chain(&mce_uc_nb);
 	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
 

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

@@ -494,7 +494,7 @@ static void do_inject(void)
 		i_mce.status |= MCI_STATUS_SYNDV;
 
 	if (inj_type == SW_INJ) {
-		mce_inject_log(&i_mce);
+		mce_log(&i_mce);
 		return;
 	}
 

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

@@ -84,8 +84,6 @@ static inline int apei_clear_mce(u64 record_id)
 }
 #endif
 
-void mce_inject_log(struct mce *m);
-
 /*
  * We consider records to be equivalent if bank+status+addr+misc all match.
  * This is only used when the system is going down because of a fatal error

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

@@ -235,7 +235,7 @@ static void get_therm_status(int level, bool *proc_hot, u8 *temp)
 	*temp = (msr_val >> 16) & 0x7F;
 }
 
-static void throttle_active_work(struct work_struct *work)
+static void __maybe_unused throttle_active_work(struct work_struct *work)
 {
 	struct _thermal_state *state = container_of(to_delayed_work(work),
 						struct _thermal_state, therm_work);

drivers/edac/amd64_edac.c

@@ -214,7 +214,7 @@ static int __set_scrub_rate(struct amd64_pvt *pvt, u32 new_bw, u32 min_rate)
 
 	scrubval = scrubrates[i].scrubval;
 
-	if (pvt->fam == 0x17 || pvt->fam == 0x18) {
+	if (pvt->umc) {
 		__f17h_set_scrubval(pvt, scrubval);
 	} else if (pvt->fam == 0x15 && pvt->model == 0x60) {
 		f15h_select_dct(pvt, 0);
@@ -256,18 +256,7 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
 	int i, retval = -EINVAL;
 	u32 scrubval = 0;
 
-	switch (pvt->fam) {
-	case 0x15:
-		/* Erratum #505 */
-		if (pvt->model < 0x10)
-			f15h_select_dct(pvt, 0);
-
-		if (pvt->model == 0x60)
-			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
-		break;
-
-	case 0x17:
-	case 0x18:
+	if (pvt->umc) {
 		amd64_read_pci_cfg(pvt->F6, F17H_SCR_BASE_ADDR, &scrubval);
 		if (scrubval & BIT(0)) {
 			amd64_read_pci_cfg(pvt->F6, F17H_SCR_LIMIT_ADDR, &scrubval);
@@ -276,11 +265,15 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
 		} else {
 			scrubval = 0;
 		}
-		break;
+	} else if (pvt->fam == 0x15) {
+		/* Erratum #505 */
+		if (pvt->model < 0x10)
+			f15h_select_dct(pvt, 0);
 
-	default:
+		if (pvt->model == 0x60)
+			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
+	} else {
 		amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
-		break;
 	}
 
 	scrubval = scrubval & 0x001F;
@@ -1055,6 +1048,16 @@ static void determine_memory_type(struct amd64_pvt *pvt)
 {
 	u32 dram_ctrl, dcsm;
 
+	if (pvt->umc) {
+		if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(5))
+			pvt->dram_type = MEM_LRDDR4;
+		else if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(4))
+			pvt->dram_type = MEM_RDDR4;
+		else
+			pvt->dram_type = MEM_DDR4;
+		return;
+	}
+
 	switch (pvt->fam) {
 	case 0xf:
 		if (pvt->ext_model >= K8_REV_F)
@@ -1100,16 +1103,6 @@ static void determine_memory_type(struct amd64_pvt *pvt)
 	case 0x16:
 		goto ddr3;
 
-	case 0x17:
-	case 0x18:
-		if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(5))
-			pvt->dram_type = MEM_LRDDR4;
-		else if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(4))
-			pvt->dram_type = MEM_RDDR4;
-		else
-			pvt->dram_type = MEM_DDR4;
-		return;
-
 	default:
 		WARN(1, KERN_ERR "%s: Family??? 0x%x\n", __func__, pvt->fam);
 		pvt->dram_type = MEM_EMPTY;
@@ -2336,6 +2329,16 @@ static struct amd64_family_type family_types[] = {
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
 		}
 	},
+	[F19_CPUS] = {
+		.ctl_name = "F19h",
+		.f0_id = PCI_DEVICE_ID_AMD_19H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_19H_DF_F6,
+		.max_mcs = 8,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_addr_mask_to_cs_size,
+		}
+	},
 };
 
 /*
@@ -3368,6 +3371,12 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			family_types[F17_CPUS].ctl_name = "F18h";
 		break;
 
+	case 0x19:
+		fam_type	= &family_types[F19_CPUS];
+		pvt->ops	= &family_types[F19_CPUS].ops;
+		family_types[F19_CPUS].ctl_name = "F19h";
+		break;
+
 	default:
 		amd64_err("Unsupported family!\n");
 		return NULL;
@@ -3623,6 +3632,7 @@ static const struct x86_cpu_id amd64_cpuids[] = {
 	{ X86_VENDOR_AMD, 0x16, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ X86_VENDOR_AMD, 0x17, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ X86_VENDOR_HYGON, 0x18, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
+	{ X86_VENDOR_AMD, 0x19, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, amd64_cpuids);

drivers/edac/amd64_edac.h

@@ -122,6 +122,8 @@
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F0 0x1440
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F6 0x1446
+#define PCI_DEVICE_ID_AMD_19H_DF_F0	0x1650
+#define PCI_DEVICE_ID_AMD_19H_DF_F6	0x1656
 
 /*
  * Function 1 - Address Map
@@ -292,6 +294,7 @@ enum amd_families {
 	F17_M10H_CPUS,
 	F17_M30H_CPUS,
 	F17_M70H_CPUS,
+	F19_CPUS,
 	NUM_FAMILIES,
 };