Extended H/W error log driver

Commit aaf9d93 only catches condition check before print, but the similar check is needed during printing CPER error sections.

Signed-off-by Chen, Gong <[email protected]>

Reviewed-by Borislav Petkov <[email protected]>

---
 drivers/acpi/apei/cper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/acpi/apei/cper.c +1 -1

index 33dc6a0..f827f02 100644
@@ -353,7 +353,7 @@ void apei_estatus_print(const char *pfx,
 	       cper_severity_str(severity));
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
-	while (data_len > sizeof(*gdata)) {
+	while (data_len >= sizeof(*gdata)) {
 		gedata_len = gdata->error_data_length;
 		apei_estatus_print_section(pfx, gdata, sec_no);
 		data_len -= gedata_len + sizeof(*gdata);

To prepare for the following patches and make related definition more clear, update some definitions about CPER.

v2 -> v1: Update some more definitions suggested by Boris

Signed-off-by Chen, Gong <[email protected]>

To prepare for the following patches and make related definition more clear, update some definitions about CPER.

v2 -> v1: Update some more definitions suggested by Boris

Signed-off-by Chen, Gong <[email protected]>

---
 drivers/acpi/apei/apei-internal.h | 12 ++++----
 drivers/acpi/apei/cper.c          | 58 +++++++++++++++++++--------------------
 drivers/acpi/apei/ghes.c          | 54 ++++++++++++++++++------------------
 include/acpi/actbl1.h             | 14 +++++-----
 include/acpi/ghes.h               |  2 +-
 include/linux/cper.h              |  2 +-
 6 files changed, 71 insertions(+), 71 deletions(-)

drivers/acpi/apei/apei-internal.h +6 -6

index f220d64..21ba34a 100644
@@ -122,11 +122,11 @@ struct dentry;
 struct dentry *apei_get_debugfs_dir(void);
 
 #define apei_estatus_for_each_section(estatus, section)			\
-	for (section = (struct acpi_hest_generic_data *)(estatus + 1);	\
+	for (section = (struct acpi_generic_data *)(estatus + 1);	\
 	     (void *)section - (void *)estatus < estatus->data_length;	\
 	     section = (void *)(section+1) + section->error_data_length)
 
-static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus)
+static inline u32 cper_estatus_len(struct acpi_generic_status *estatus)
 {
 	if (estatus->raw_data_length)
 		return estatus->raw_data_offset + \

@@ -135,10 +135,10 @@ static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus)
 		return sizeof(*estatus) + estatus->data_length;
 }
 
-void apei_estatus_print(const char *pfx,
-			const struct acpi_hest_generic_status *estatus);
-int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus);
-int apei_estatus_check(const struct acpi_hest_generic_status *estatus);
+void cper_estatus_print(const char *pfx,
+			const struct acpi_generic_status *estatus);
+int cper_estatus_check_header(const struct acpi_generic_status *estatus);
+int cper_estatus_check(const struct acpi_generic_status *estatus);
 
 int apei_osc_setup(void);
 #endif

drivers/acpi/apei/cper.c +29 -29

index f827f02..eb5f6d6 100644
@@ -5,7 +5,7 @@
  *	Author: Huang Ying <[email protected]>
  *
  * CPER is the format used to describe platform hardware error by
- * various APEI tables, such as ERST, BERT and HEST etc.
+ * various tables, such as ERST, BERT and HEST etc.
  *
  * For more information about CPER, please refer to Appendix N of UEFI
  * Specification version 2.3.

@@ -73,7 +73,7 @@ static const char *cper_severity_str(unsigned int severity)
  * printed, with @pfx is printed at the beginning of each line.
  */
 void cper_print_bits(const char *pfx, unsigned int bits,
-		     const char *strs[], unsigned int strs_size)
+		     const char * const strs[], unsigned int strs_size)
 {
 	int i, len = 0;
 	const char *str;

@@ -98,32 +98,32 @@ void cper_print_bits(const char *pfx, unsigned int bits,
 		printk("%s\n", buf);
 }
 
-static const char *cper_proc_type_strs[] = {
+static const char * const cper_proc_type_strs[] = {
 	"IA32/X64",
 	"IA64",
 };
 
-static const char *cper_proc_isa_strs[] = {
+static const char * const cper_proc_isa_strs[] = {
 	"IA32",
 	"IA64",
 	"X64",
 };
 
-static const char *cper_proc_error_type_strs[] = {
+static const char * const cper_proc_error_type_strs[] = {
 	"cache error",
 	"TLB error",
 	"bus error",
 	"micro-architectural error",
 };
 
-static const char *cper_proc_op_strs[] = {
+static const char * const cper_proc_op_strs[] = {
 	"unknown or generic",
 	"data read",
 	"data write",
 	"instruction execution",
 };
 
-static const char *cper_proc_flag_strs[] = {
+static const char * const cper_proc_flag_strs[] = {
 	"restartable",
 	"precise IP",
 	"overflow",

@@ -248,7 +248,7 @@ static const char *cper_pcie_port_type_strs[] = {
 };
 
 static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
-			    const struct acpi_hest_generic_data *gdata)
+			    const struct acpi_generic_data *gdata)
 {
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,

@@ -283,17 +283,17 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 }
 
-static const char *apei_estatus_section_flag_strs[] = {
+static const char * const cper_estatus_section_flag_strs[] = {
 	"primary",
 	"containment warning",
 	"reset",
-	"threshold exceeded",
+	"error threshold exceeded",
 	"resource not accessible",
 	"latent error",
 };
 
-static void apei_estatus_print_section(
-	const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+static void cper_estatus_print_section(
+	const char *pfx, const struct acpi_generic_data *gdata, int sec_no)
 {
 	uuid_le *sec_type = (uuid_le *)gdata->section_type;
 	__u16 severity;

@@ -302,8 +302,8 @@ static void apei_estatus_print_section(
 	printk("%s""section: %d, severity: %d, %s\n", pfx, sec_no, severity,
 	       cper_severity_str(severity));
 	printk("%s""flags: 0x%02x\n", pfx, gdata->flags);
-	cper_print_bits(pfx, gdata->flags, apei_estatus_section_flag_strs,
-			ARRAY_SIZE(apei_estatus_section_flag_strs));
+	cper_print_bits(pfx, gdata->flags, cper_estatus_section_flag_strs,
+			ARRAY_SIZE(cper_estatus_section_flag_strs));
 	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
 		printk("%s""fru_id: %pUl\n", pfx, (uuid_le *)gdata->fru_id);
 	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)

@@ -339,34 +339,34 @@ err_section_too_small:
 	pr_err(FW_WARN "error section length is too small\n");
 }
 
-void apei_estatus_print(const char *pfx,
-			const struct acpi_hest_generic_status *estatus)
+void cper_estatus_print(const char *pfx,
+			const struct acpi_generic_status *estatus)
 {
-	struct acpi_hest_generic_data *gdata;
+	struct acpi_generic_data *gdata;
 	unsigned int data_len, gedata_len;
 	int sec_no = 0;
 	__u16 severity;
 
-	printk("%s""APEI generic hardware error status\n", pfx);
+	printk("%s""Generic Hardware Error Status\n", pfx);
 	severity = estatus->error_severity;
 	printk("%s""severity: %d, %s\n", pfx, severity,
 	       cper_severity_str(severity));
 	data_len = estatus->data_length;
-	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+	gdata = (struct acpi_generic_data *)(estatus + 1);
 	while (data_len >= sizeof(*gdata)) {
 		gedata_len = gdata->error_data_length;
-		apei_estatus_print_section(pfx, gdata, sec_no);
+		cper_estatus_print_section(pfx, gdata, sec_no);
 		data_len -= gedata_len + sizeof(*gdata);
 		gdata = (void *)(gdata + 1) + gedata_len;
 		sec_no++;
 	}
 }
-EXPORT_SYMBOL_GPL(apei_estatus_print);
+EXPORT_SYMBOL_GPL(cper_estatus_print);
 
-int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus)
+int cper_estatus_check_header(const struct acpi_generic_status *estatus)
 {
 	if (estatus->data_length &&
-	    estatus->data_length < sizeof(struct acpi_hest_generic_data))
+	    estatus->data_length < sizeof(struct acpi_generic_data))
 		return -EINVAL;
 	if (estatus->raw_data_length &&
 	    estatus->raw_data_offset < sizeof(*estatus) + estatus->data_length)

@@ -374,19 +374,19 @@ int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(apei_estatus_check_header);
+EXPORT_SYMBOL_GPL(cper_estatus_check_header);
 
-int apei_estatus_check(const struct acpi_hest_generic_status *estatus)
+int cper_estatus_check(const struct acpi_generic_status *estatus)
 {
-	struct acpi_hest_generic_data *gdata;
+	struct acpi_generic_data *gdata;
 	unsigned int data_len, gedata_len;
 	int rc;
 
-	rc = apei_estatus_check_header(estatus);
+	rc = cper_estatus_check_header(estatus);
 	if (rc)
 		return rc;
 	data_len = estatus->data_length;
-	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+	gdata = (struct acpi_generic_data *)(estatus + 1);
 	while (data_len >= sizeof(*gdata)) {
 		gedata_len = gdata->error_data_length;
 		if (gedata_len > data_len - sizeof(*gdata))

@@ -399,4 +399,4 @@ int apei_estatus_check(const struct acpi_hest_generic_status *estatus)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(apei_estatus_check);
+EXPORT_SYMBOL_GPL(cper_estatus_check);

drivers/acpi/apei/ghes.c +27 -27

index 8ec37bb..0db6e4f 100644
@@ -75,13 +75,13 @@
 #define GHES_ESTATUS_CACHE_LEN(estatus_len)			\
 	(sizeof(struct ghes_estatus_cache) + (estatus_len))
 #define GHES_ESTATUS_FROM_CACHE(estatus_cache)			\
-	((struct acpi_hest_generic_status *)			\
+	((struct acpi_generic_status *)				\
 	 ((struct ghes_estatus_cache *)(estatus_cache) + 1))
 
 #define GHES_ESTATUS_NODE_LEN(estatus_len)			\
 	(sizeof(struct ghes_estatus_node) + (estatus_len))
-#define GHES_ESTATUS_FROM_NODE(estatus_node)				\
-	((struct acpi_hest_generic_status *)				\
+#define GHES_ESTATUS_FROM_NODE(estatus_node)			\
+	((struct acpi_generic_status *)				\
 	 ((struct ghes_estatus_node *)(estatus_node) + 1))
 
 bool ghes_disable;

@@ -378,17 +378,17 @@ static int ghes_read_estatus(struct ghes *ghes, int silent)
 	ghes->flags |= GHES_TO_CLEAR;
 
 	rc = -EIO;
-	len = apei_estatus_len(ghes->estatus);
+	len = cper_estatus_len(ghes->estatus);
 	if (len < sizeof(*ghes->estatus))
 		goto err_read_block;
 	if (len > ghes->generic->error_block_length)
 		goto err_read_block;
-	if (apei_estatus_check_header(ghes->estatus))
+	if (cper_estatus_check_header(ghes->estatus))
 		goto err_read_block;
 	ghes_copy_tofrom_phys(ghes->estatus + 1,
 			      buf_paddr + sizeof(*ghes->estatus),
 			      len - sizeof(*ghes->estatus), 1);
-	if (apei_estatus_check(ghes->estatus))
+	if (cper_estatus_check(ghes->estatus))
 		goto err_read_block;
 	rc = 0;
 

@@ -409,7 +409,7 @@ static void ghes_clear_estatus(struct ghes *ghes)
 	ghes->flags &= ~GHES_TO_CLEAR;
 }
 
-static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev)
+static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 {
 #ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
 	unsigned long pfn;

@@ -438,10 +438,10 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 }
 
 static void ghes_do_proc(struct ghes *ghes,
-			 const struct acpi_hest_generic_status *estatus)
+			 const struct acpi_generic_status *estatus)
 {
 	int sev, sec_sev;
-	struct acpi_hest_generic_data *gdata;
+	struct acpi_generic_data *gdata;
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {

@@ -496,7 +496,7 @@ static void ghes_do_proc(struct ghes *ghes,
 
 static void __ghes_print_estatus(const char *pfx,
 				 const struct acpi_hest_generic *generic,
-				 const struct acpi_hest_generic_status *estatus)
+				 const struct acpi_generic_status *estatus)
 {
 	static atomic_t seqno;
 	unsigned int curr_seqno;

@@ -513,12 +513,12 @@ static void __ghes_print_estatus(const char *pfx,
 	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno);
 	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
 	       pfx_seq, generic->header.source_id);
-	apei_estatus_print(pfx_seq, estatus);
+	cper_estatus_print(pfx_seq, estatus);
 }
 
 static int ghes_print_estatus(const char *pfx,
 			      const struct acpi_hest_generic *generic,
-			      const struct acpi_hest_generic_status *estatus)
+			      const struct acpi_generic_status *estatus)
 {
 	/* Not more than 2 messages every 5 seconds */
 	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);

@@ -540,15 +540,15 @@ static int ghes_print_estatus(const char *pfx,
  * GHES error status reporting throttle, to report more kinds of
  * errors, instead of just most frequently occurred errors.
  */
-static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
+static int ghes_estatus_cached(struct acpi_generic_status *estatus)
 {
 	u32 len;
 	int i, cached = 0;
 	unsigned long long now;
 	struct ghes_estatus_cache *cache;
-	struct acpi_hest_generic_status *cache_estatus;
+	struct acpi_generic_status *cache_estatus;
 
-	len = apei_estatus_len(estatus);
+	len = cper_estatus_len(estatus);
 	rcu_read_lock();
 	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
 		cache = rcu_dereference(ghes_estatus_caches[i]);

@@ -571,19 +571,19 @@ static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
 
 static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
 	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
+	struct acpi_generic_status *estatus)
 {
 	int alloced;
 	u32 len, cache_len;
 	struct ghes_estatus_cache *cache;
-	struct acpi_hest_generic_status *cache_estatus;
+	struct acpi_generic_status *cache_estatus;
 
 	alloced = atomic_add_return(1, &ghes_estatus_cache_alloced);
 	if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) {
 		atomic_dec(&ghes_estatus_cache_alloced);
 		return NULL;
 	}
-	len = apei_estatus_len(estatus);
+	len = cper_estatus_len(estatus);
 	cache_len = GHES_ESTATUS_CACHE_LEN(len);
 	cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len);
 	if (!cache) {

@@ -603,7 +603,7 @@ static void ghes_estatus_cache_free(struct ghes_estatus_cache *cache)
 {
 	u32 len;
 
-	len = apei_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
+	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
 	len = GHES_ESTATUS_CACHE_LEN(len);
 	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
 	atomic_dec(&ghes_estatus_cache_alloced);

@@ -619,7 +619,7 @@ static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
 
 static void ghes_estatus_cache_add(
 	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
+	struct acpi_generic_status *estatus)
 {
 	int i, slot = -1, count;
 	unsigned long long now, duration, period, max_period = 0;

@@ -751,7 +751,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct llist_node *llnode, *next;
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
-	struct acpi_hest_generic_status *estatus;
+	struct acpi_generic_status *estatus;
 	u32 len, node_len;
 
 	llnode = llist_del_all(&ghes_estatus_llist);

@@ -765,7 +765,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
 					   llnode);
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-		len = apei_estatus_len(estatus);
+		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
 		ghes_do_proc(estatus_node->ghes, estatus);
 		if (!ghes_estatus_cached(estatus)) {

@@ -784,7 +784,7 @@ static void ghes_print_queued_estatus(void)
 	struct llist_node *llnode;
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
-	struct acpi_hest_generic_status *estatus;
+	struct acpi_generic_status *estatus;
 	u32 len, node_len;
 
 	llnode = llist_del_all(&ghes_estatus_llist);

@@ -797,7 +797,7 @@ static void ghes_print_queued_estatus(void)
 		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
 					   llnode);
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-		len = apei_estatus_len(estatus);
+		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
 		generic = estatus_node->generic;
 		ghes_print_estatus(NULL, generic, estatus);

@@ -843,7 +843,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 #ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 		u32 len, node_len;
 		struct ghes_estatus_node *estatus_node;
-		struct acpi_hest_generic_status *estatus;
+		struct acpi_generic_status *estatus;
 #endif
 		if (!(ghes->flags & GHES_TO_CLEAR))
 			continue;

@@ -851,7 +851,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 		if (ghes_estatus_cached(ghes->estatus))
 			goto next;
 		/* Save estatus for further processing in IRQ context */
-		len = apei_estatus_len(ghes->estatus);
+		len = cper_estatus_len(ghes->estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
 		estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool,
 						      node_len);

@@ -923,7 +923,7 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	rc = -EIO;
 	if (generic->error_block_length <
-	    sizeof(struct acpi_hest_generic_status)) {
+	    sizeof(struct acpi_generic_status)) {
 		pr_warning(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
 			   generic->error_block_length,
 			   generic->header.source_id);

include/acpi/actbl1.h +7 -7

index 0bd750e..556c83ee 100644
@@ -596,7 +596,7 @@ struct acpi_hest_generic {
 
 /* Generic Error Status block */
 
-struct acpi_hest_generic_status {
+struct acpi_generic_status {
 	u32 block_status;
 	u32 raw_data_offset;
 	u32 raw_data_length;

@@ -606,15 +606,15 @@ struct acpi_hest_generic_status {
 
 /* Values for block_status flags above */
 
-#define ACPI_HEST_UNCORRECTABLE             (1)
-#define ACPI_HEST_CORRECTABLE               (1<<1)
-#define ACPI_HEST_MULTIPLE_UNCORRECTABLE    (1<<2)
-#define ACPI_HEST_MULTIPLE_CORRECTABLE      (1<<3)
-#define ACPI_HEST_ERROR_ENTRY_COUNT         (0xFF<<4)	/* 8 bits, error count */
+#define ACPI_GEN_ERR_UC			BIT(0)
+#define ACPI_GEN_ERR_CE			BIT(1)
+#define ACPI_GEN_ERR_MULTI_UC		BIT(2)
+#define ACPI_GEN_ERR_MULTI_CE		BIT(3)
+#define ACPI_GEN_ERR_COUNT_SHIFT	(0xFF<<4) /* 8 bits, error count */
 
 /* Generic Error Data entry */
 
-struct acpi_hest_generic_data {
+struct acpi_generic_data {
 	u8 section_type[16];
 	u32 error_severity;
 	u16 revision;

include/acpi/ghes.h +1 -1

index 720446c..dfd60d0 100644
@@ -14,7 +14,7 @@
 
 struct ghes {
 	struct acpi_hest_generic *generic;
-	struct acpi_hest_generic_status *estatus;
+	struct acpi_generic_status *estatus;
 	u64 buffer_paddr;
 	unsigned long flags;
 	union {

include/linux/cper.h +1 -1

index c230494..09ebe21 100644
@@ -389,6 +389,6 @@ struct cper_sec_pcie {
 
 u64 cper_next_record_id(void);
 void cper_print_bits(const char *prefix, unsigned int bits,
-		     const char *strs[], unsigned int strs_size);
+		     const char * const strs[], unsigned int strs_size);
 
 #endif

GENMASK is used to create a contiguous bitmask([hi:lo]). It is implemented twice in current kernel. One is in EDAC driver, the other is in SiS/XGI FB driver. Move it to a more generic place for other usage.

Signed-off-by Chen, Gong <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Thomas Winischhofer <[email protected]>

Cc Jean-Christophe Plagniol-Villard <[email protected]>

Cc Tomi Valkeinen <[email protected]>

GENMASK is used to create a contiguous bitmask([hi:lo]). It is implemented twice in current kernel. One is in EDAC driver, the other is in SiS/XGI FB driver. Move it to a more generic place for other usage.

Signed-off-by Chen, Gong <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Thomas Winischhofer <[email protected]>

Cc Jean-Christophe Plagniol-Villard <[email protected]>

Cc Tomi Valkeinen <[email protected]>

---
 drivers/edac/amd64_edac.c | 46 ++++++++++++++++++++++++----------------------
 drivers/edac/amd64_edac.h |  8 --------
 drivers/video/sis/init.c  |  5 ++---
 include/linux/bitops.h    |  8 ++++++++
 4 files changed, 34 insertions(+), 33 deletions(-)

drivers/edac/amd64_edac.c +24 -22

index 3c9e4e9..b53d0de 100644
@@ -339,8 +339,8 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 	if (pvt->fam == 0xf && pvt->ext_model < K8_REV_F) {
 		csbase		= pvt->csels[dct].csbases[csrow];
 		csmask		= pvt->csels[dct].csmasks[csrow];
-		base_bits	= GENMASK(21, 31) | GENMASK(9, 15);
-		mask_bits	= GENMASK(21, 29) | GENMASK(9, 15);
+		base_bits	= GENMASK_ULL(31, 21) | GENMASK_ULL(15, 9);
+		mask_bits	= GENMASK_ULL(29, 21) | GENMASK_ULL(15, 9);
 		addr_shift	= 4;
 
 	/*

@@ -352,16 +352,16 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 		csbase          = pvt->csels[dct].csbases[csrow];
 		csmask          = pvt->csels[dct].csmasks[csrow >> 1];
 
-		*base  = (csbase & GENMASK(5,  15)) << 6;
-		*base |= (csbase & GENMASK(19, 30)) << 8;
+		*base  = (csbase & GENMASK_ULL(15,  5)) << 6;
+		*base |= (csbase & GENMASK_ULL(30, 19)) << 8;
 
 		*mask = ~0ULL;
 		/* poke holes for the csmask */
-		*mask &= ~((GENMASK(5, 15)  << 6) |
-			   (GENMASK(19, 30) << 8));
+		*mask &= ~((GENMASK_ULL(15, 5)  << 6) |
+			   (GENMASK_ULL(30, 19) << 8));
 
-		*mask |= (csmask & GENMASK(5, 15))  << 6;
-		*mask |= (csmask & GENMASK(19, 30)) << 8;
+		*mask |= (csmask & GENMASK_ULL(15, 5))  << 6;
+		*mask |= (csmask & GENMASK_ULL(30, 19)) << 8;
 
 		return;
 	} else {

@@ -370,9 +370,11 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 		addr_shift	= 8;
 
 		if (pvt->fam == 0x15)
-			base_bits = mask_bits = GENMASK(19,30) | GENMASK(5,13);
+			base_bits = mask_bits =
+				GENMASK_ULL(30,19) | GENMASK_ULL(13,5);
 		else
-			base_bits = mask_bits = GENMASK(19,28) | GENMASK(5,13);
+			base_bits = mask_bits =
+				GENMASK_ULL(28,19) | GENMASK_ULL(13,5);
 	}
 
 	*base  = (csbase & base_bits) << addr_shift;

@@ -561,7 +563,7 @@ static u64 sys_addr_to_dram_addr(struct mem_ctl_info *mci, u64 sys_addr)
 	 * section 3.4.2 of AMD publication 24592: AMD x86-64 Architecture
 	 * Programmer's Manual Volume 1 Application Programming.
 	 */
-	dram_addr = (sys_addr & GENMASK(0, 39)) - dram_base;
+	dram_addr = (sys_addr & GENMASK_ULL(39, 0)) - dram_base;
 
 	edac_dbg(2, "using DRAM Base register to translate SysAddr 0x%lx to DramAddr 0x%lx\n",
 		 (unsigned long)sys_addr, (unsigned long)dram_addr);

@@ -597,7 +599,7 @@ static u64 dram_addr_to_input_addr(struct mem_ctl_info *mci, u64 dram_addr)
 	 * concerning translating a DramAddr to an InputAddr.
 	 */
 	intlv_shift = num_node_interleave_bits(dram_intlv_en(pvt, 0));
-	input_addr = ((dram_addr >> intlv_shift) & GENMASK(12, 35)) +
+	input_addr = ((dram_addr >> intlv_shift) & GENMASK_ULL(35, 12)) +
 		      (dram_addr & 0xfff);
 
 	edac_dbg(2, "  Intlv Shift=%d DramAddr=0x%lx maps to InputAddr=0x%lx\n",

@@ -849,7 +851,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		end_bit   = 39;
 	}
 
-	addr = m->addr & GENMASK(start_bit, end_bit);
+	addr = m->addr & GENMASK_ULL(end_bit, start_bit);
 
 	/*
 	 * Erratum 637 workaround

@@ -861,7 +863,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		u16 mce_nid;
 		u8 intlv_en;
 
-		if ((addr & GENMASK(24, 47)) >> 24 != 0x00fdf7)
+		if ((addr & GENMASK_ULL(47, 24)) >> 24 != 0x00fdf7)
 			return addr;
 
 		mce_nid	= amd_get_nb_id(m->extcpu);

@@ -871,7 +873,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		intlv_en = tmp >> 21 & 0x7;
 
 		/* add [47:27] + 3 trailing bits */
-		cc6_base  = (tmp & GENMASK(0, 20)) << 3;
+		cc6_base  = (tmp & GENMASK_ULL(20, 0)) << 3;
 
 		/* reverse and add DramIntlvEn */
 		cc6_base |= intlv_en ^ 0x7;

@@ -880,18 +882,18 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		cc6_base <<= 24;
 
 		if (!intlv_en)
-			return cc6_base | (addr & GENMASK(0, 23));
+			return cc6_base | (addr & GENMASK_ULL(23, 0));
 
 		amd64_read_pci_cfg(pvt->F1, DRAM_LOCAL_NODE_BASE, &tmp);
 
 							/* faster log2 */
-		tmp_addr  = (addr & GENMASK(12, 23)) << __fls(intlv_en + 1);
+		tmp_addr  = (addr & GENMASK_ULL(23, 12)) << __fls(intlv_en + 1);
 
 		/* OR DramIntlvSel into bits [14:12] */
-		tmp_addr |= (tmp & GENMASK(21, 23)) >> 9;
+		tmp_addr |= (tmp & GENMASK_ULL(23, 21)) >> 9;
 
 		/* add remaining [11:0] bits from original MC4_ADDR */
-		tmp_addr |= addr & GENMASK(0, 11);
+		tmp_addr |= addr & GENMASK_ULL(11, 0);
 
 		return cc6_base | tmp_addr;
 	}

@@ -952,12 +954,12 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range)
 
 	amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim);
 
-	pvt->ranges[range].lim.lo &= GENMASK(0, 15);
+	pvt->ranges[range].lim.lo &= GENMASK_ULL(15, 0);
 
 				    /* {[39:27],111b} */
 	pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16;
 
-	pvt->ranges[range].lim.hi &= GENMASK(0, 7);
+	pvt->ranges[range].lim.hi &= GENMASK_ULL(7, 0);
 
 				    /* [47:40] */
 	pvt->ranges[range].lim.hi |= llim >> 13;

@@ -1330,7 +1332,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range,
 			chan_off = dram_base;
 	}
 
-	return (sys_addr & GENMASK(6,47)) - (chan_off & GENMASK(23,47));
+	return (sys_addr & GENMASK_ULL(47,6)) - (chan_off & GENMASK_ULL(47,23));
 }
 
 /*

drivers/edac/amd64_edac.h +0 -8

index d2443cf..6dc1fcc 100644
@@ -160,14 +160,6 @@
 #define OFF false
 
 /*
- * Create a contiguous bitmask starting at bit position @lo and ending at
- * position @hi. For example
- *
- * GENMASK(21, 39) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(lo, hi)			(((1ULL << ((hi) - (lo) + 1)) - 1) << (lo))
-
-/*
  * PCI-defined configuration space registers
  */
 #define PCI_DEVICE_ID_AMD_15H_M30H_NB_F1 0x141b

drivers/video/sis/init.c +2 -3

index f082ae5..4f26bc2 100644
@@ -3320,9 +3320,8 @@ SiSSetMode(struct SiS_Private *SiS_Pr, unsigned short ModeNo)
 }
 
 #ifndef GETBITSTR
-#define BITMASK(h,l)    	(((unsigned)(1U << ((h)-(l)+1))-1)<<(l))
-#define GENMASK(mask)   	BITMASK(1?mask,0?mask)
-#define GETBITS(var,mask)   	(((var) & GENMASK(mask)) >> (0?mask))
+#define GENBITSMASK(mask)   	GENMASK(1?mask,0?mask)
+#define GETBITS(var,mask)   	(((var) & GENBITSMASK(mask)) >> (0?mask))
 #define GETBITSTR(val,from,to)  ((GETBITS(val,from)) << (0?to))
 #endif
 

include/linux/bitops.h +8 -0

index a3b6b82..bd0c459 100644
@@ -10,6 +10,14 @@
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l)		(((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK_ULL(h, l)	(((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
+
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
 extern unsigned int __sw_hweight32(unsigned int w);

Date: Wed, 16 Oct 2013 14:02:21 -0300
From: Mauro Carvalho Chehab <[email protected]>
To: "Chen, Gong" <[email protected]>
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected], [email protected], [email protected], Thomas Winischhofer <[email protected]>, Jean-Christophe Plagniol-Villard <[email protected]>, Tomi Valkeinen <[email protected]>
Subject: Re: [PATCH v2 3/9] bitops: Introduce a more generic BITMASK macro
X-Mailer: Claws Mail 3.9.2 (GTK+ 2.24.19; x86_64-redhat-linux-gnu)

Em Wed, 16 Oct 2013 10:56:00 -0400
"Chen, Gong" <[email protected]> escreveu:

Quoted 10 lines

GENMASK is used to create a contiguous bitmask([hi:lo]). It is implemented twice in current kernel. One is in EDAC driver, the other is in SiS/XGI FB driver. Move it to a more generic place for other usage.

Signed-off-by Chen, Gong <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Thomas Winischhofer <[email protected]>

Cc Jean-Christophe Plagniol-Villard <[email protected]>

Cc Tomi Valkeinen <[email protected]>

Acked-by Mauro Carvalho Chehab <[email protected]>

Btw, there's another incarnation of it at sb_edac.c (GET_BITFIELD). It could make sense to also replace it by the newly bitops.h macro.

Regards,
Mauro

GENMASK is used to create a contiguous bitmask([hi:lo]). It is implemented twice in current kernel. One is in EDAC driver, the other is in SiS/XGI FB driver. Move it to a more generic place for other usage.

Date: Wed, 16 Oct 2013 19:59:09 -0700
From: Joe Perches <[email protected]>
To: "Chen, Gong" <[email protected]>
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected], [email protected], [email protected], Thomas Winischhofer <[email protected]>, Jean-Christophe Plagniol-Villard <[email protected]>, Tomi Valkeinen <[email protected]>
Subject: Re: [PATCH v2 3/9] bitops: Introduce a more generic BITMASK macro
X-Mailer: Evolution 3.6.4-0ubuntu1

Quoted 4 lines · Gong

GENMASK is used to create a contiguous bitmask([hi:lo]). It is implemented twice in current kernel. One is in EDAC driver, the other is in SiS/XGI FB driver. Move it to a more generic place for other usage.

[]

include/linux/bitops.h

Quoted 1 line

include/linux/bitops.h +0 -0

[]

include/linux/bitops.h line 16

Quoted 8 lines

include/linux/bitops.h +4 -0

@@ -10,6 +10,14 @@
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.

ull

include/linux/bitops.h line 19

Quoted 3 lines

include/linux/bitops.h +3 -0

+ */
+#define GENMASK(h, l)		(((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK_ULL(h, l)	(((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))

Maybe add a

BUILD_BUG_ON(__builtin_constant_p(l) && __builtin_constant_p(h) && \
	     (h) < (l))

On Wed, Oct 16, 2013 at 07:59:09PM -0700, Joe Perches wrote:

Quoted 5 lines

Maybe add a

BUILD_BUG_ON(__builtin_constant_p(l) && __builtin_constant_p(h) && \
	     (h) < (l))

No, if so, users can't use variables for this macro.

Date: Wed, 16 Oct 2013 23:58:56 -0700
From: Joe Perches <[email protected]>
To: Chen Gong <[email protected]>
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected], [email protected], [email protected], Thomas Winischhofer <[email protected]>, Jean-Christophe Plagniol-Villard <[email protected]>, Tomi Valkeinen <[email protected]>
Subject: Re: [PATCH v2 3/9] bitops: Introduce a more generic BITMASK macro
X-Mailer: Evolution 3.6.4-0ubuntu1

Quoted 1 line · Chen Gong

On Wed, Oct 16, 2013 at 07:59:09PM -0700, Joe Perches wrote:

[]

Quoted 6 lines

Quoted 5 lines

Maybe add a

BUILD_BUG_ON(__builtin_constant_p(l) && __builtin_constant_p(h) && \
	     (h) < (l))

No, if so, users can't use variables for this macro.

__builtin_constant_p checks for constants

Built-in Function: int __builtin_constant_p (exp)
You can use the built-in function __builtin_constant_p to determine if a value is known to be constant at compile-time and hence that GCC can perform constant-folding on expressions involving that value. The argument of the function is the value to test. The function returns the integer 1 if the argument is known to be a compile-time constant and 0 if it is not known to be a compile-time constant. A return of 0 does not indicate that the value is not a constant, but merely that GCC cannot prove it is a constant with the specified value of the -O option.

the point is we can use GENMASK like GENMASK(end_bit, start_bit) but we don't know the value of end_bit/start_bit at compile-time.

Quoted 2 lines · Chen Gong

the point is we can use GENMASK like GENMASK(end_bit, start_bit) but we don't know the value of end_bit/start_bit at compile-time.

True.

The BUILD_BUG_ON idea is just to avoid people using

	GENMASK(1, 2)

Quoted 6 lines · Joe Perches

Quoted 2 lines · Chen Gong

the point is we can use GENMASK like GENMASK(end_bit, start_bit) but we don't know the value of end_bit/start_bit at compile-time.

True.

Quoted 2 lines

The BUILD_BUG_ON idea is just to avoid people using

	GENMASK(1, 2)

They'll notice the 0 pretty quickly when they test their code.

Let's add those checks only when it is really necessary and people have actually made that mistake repeatedly.

It's cost free to add the BUILD_BUG_ON
and perhaps you underestimate the runtime
bug checking effort,

Quoted 3 lines · Joe Perches

It's cost free to add the BUILD_BUG_ON
and perhaps you underestimate the runtime
bug checking effort,

This looks OK to me. Gong: This doesn't stop people from using variables as arguments ... they just won't get a check for (h) < (l).

drivers/acpi/Kconfig +0 -0

index 22327e6..819c06b 100644
@@ -372,4 +372,13 @@ config ACPI_BGRT
 

drivers/acpi/Kconfig +1 -0

+
 endif	# ACPI

drivers/acpi/Makefile +2 -0

index cdaf68b..bce34af 100644
@@ -82,3 +82,5 @@ processor-$(CONFIG_CPU_FREQ)	+= processor_perflib.o
 obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o
 
 obj-$(CONFIG_ACPI_APEI)		+= apei/
+
+obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o

drivers/acpi/acpi_extlog.c new file +9 -0

new file mode 100644
index 0000000..d55b072
@@ -0,0 +1,319 @@
+/*
+ * Extended Error Log driver
+ *
+ * Copyright (C) 2013 Intel Corp.
+ * Author: Chen, Gong <[email protected]>
+ *
+ * This file is licensed under GPLv2.
+ */
+

drivers/acpi/acpi_extlog.c new file +20 -0

+static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret)
+{
+	struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL};
+	struct acpi_object_list input;
+	union acpi_object params[4], *obj;
+	u8 uuid[16];
+	int i;
+
+	acpi_str_to_uuid(extlog_dsm_uuid, uuid);
+	input.count = 4;
+	input.pointer = params;
+	params[0].type = ACPI_TYPE_BUFFER;
+	params[0].buffer.length = 16;
+	params[0].buffer.pointer = uuid;
+	params[1].type = ACPI_TYPE_INTEGER;
+	params[1].integer.value = rev;
+	params[2].type = ACPI_TYPE_INTEGER;
+	params[2].integer.value = func;
+	params[3].type = ACPI_TYPE_PACKAGE;
+	params[3].package.count = 0;

drivers/acpi/acpi_extlog.c new file +10 -0

+		if (obj->buffer.length <= 8) {
+			for (i = 0; i < obj->buffer.length; i++)
+				*ret |= (obj->buffer.pointer[i] << (i * 8));
+		}
+	}
+	kfree(buf.pointer);
+
+	return 0;
+}
+

This patch adds a new interface to decode memory device (type 17) to help error reporting on DIMMs.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Acked-by Naveen N. Rao <[email protected]>

This patch adds a new interface to decode memory device (type 17) to help error reporting on DIMMs.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Acked-by Naveen N. Rao <[email protected]>

---
 arch/ia64/kernel/setup.c    |  1 +
 arch/x86/kernel/setup.c     |  1 +
 drivers/firmware/dmi_scan.c | 60 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dmi.h         |  5 ++++
 4 files changed, 67 insertions(+)

arch/ia64/kernel/setup.c +1 -0

index 4fc2e95..d86669b 100644
@@ -1063,6 +1063,7 @@ check_bugs (void)
 static int __init run_dmi_scan(void)
 {
 	dmi_scan_machine();
+	dmi_memdev_walk();
 	dmi_set_dump_stack_arch_desc();
 	return 0;
 }

arch/x86/kernel/setup.c +1 -0

index f0de629..918d489 100644
@@ -993,6 +993,7 @@ void __init setup_arch(char **cmdline_p)
 		efi_init();
 
 	dmi_scan_machine();
+	dmi_memdev_walk();
 	dmi_set_dump_stack_arch_desc();
 
 	/*

drivers/firmware/dmi_scan.c +60 -0

index fa0affb..59579a7 100644
@@ -25,6 +25,13 @@ static int dmi_initialized;
 /* DMI system identification string used during boot */
 static char dmi_ids_string[128] __initdata;
 
+static struct dmi_memdev_info {
+	const char *device;
+	const char *bank;
+	u16 handle;
+} *dmi_memdev;
+static int dmi_memdev_nr;
+
 static const char * __init dmi_string_nosave(const struct dmi_header *dm, u8 s)
 {
 	const u8 *bp = ((u8 *) dm) + dm->length;

@@ -322,6 +329,42 @@ static void __init dmi_save_extended_devices(const struct dmi_header *dm)
 	dmi_save_one_device(*d & 0x7f, dmi_string_nosave(dm, *(d - 1)));
 }
 
+static void __init count_mem_devices(const struct dmi_header *dm, void *v)
+{
+	if (dm->type != DMI_ENTRY_MEM_DEVICE)
+		return;
+	dmi_memdev_nr++;
+}
+
+static void __init save_mem_devices(const struct dmi_header *dm, void *v)
+{
+	const char *d = (const char *)dm;
+	static int nr;
+
+	if (dm->type != DMI_ENTRY_MEM_DEVICE)
+		return;
+	if (nr >= dmi_memdev_nr) {
+		pr_warn(FW_BUG "Too many DIMM entries in SMBIOS table\n");
+		return;
+	}
+	dmi_memdev[nr].handle = dm->handle;
+	dmi_memdev[nr].device = dmi_string(dm, d[0x10]);
+	dmi_memdev[nr].bank = dmi_string(dm, d[0x11]);
+	nr++;
+}
+
+void __init dmi_memdev_walk(void)
+{
+	if (!dmi_available)
+		return;
+
+	if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) {
+		dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr);
+		if (dmi_memdev)
+			dmi_walk_early(save_mem_devices);
+	}
+}
+
 /*
  *	Process a DMI table entry. Right now all we care about are the BIOS
  *	and machine entries. For 2.5 we should pull the smbus controller info

@@ -815,3 +858,20 @@ bool dmi_match(enum dmi_field f, const char *str)
 	return !strcmp(info, str);
 }
 EXPORT_SYMBOL_GPL(dmi_match);
+
+void dmi_memdev_name(u16 handle, const char **bank, const char **device)
+{
+	int n;
+
+	if (dmi_memdev == NULL)
+		return;
+
+	for (n = 0; n < dmi_memdev_nr; n++) {
+		if (handle == dmi_memdev[n].handle) {
+			*bank = dmi_memdev[n].bank;
+			*device = dmi_memdev[n].device;
+			break;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(dmi_memdev_name);

include/linux/dmi.h +5 -0

index b6eb7a0..f820f0a 100644
@@ -99,6 +99,7 @@ extern const char * dmi_get_system_info(int field);
 extern const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from);
 extern void dmi_scan_machine(void);
+extern void dmi_memdev_walk(void);
 extern void dmi_set_dump_stack_arch_desc(void);
 extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp);
 extern int dmi_name_in_vendors(const char *str);

@@ -107,6 +108,7 @@ extern int dmi_available;
 extern int dmi_walk(void (*decode)(const struct dmi_header *, void *),
 	void *private_data);
 extern bool dmi_match(enum dmi_field f, const char *str);
+extern void dmi_memdev_name(u16 handle, const char **bank, const char **device);
 
 #else
 

@@ -115,6 +117,7 @@ static inline const char * dmi_get_system_info(int field) { return NULL; }
 static inline const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from) { return NULL; }
 static inline void dmi_scan_machine(void) { return; }
+static inline void dmi_memdev_walk(void) { }
 static inline void dmi_set_dump_stack_arch_desc(void) { }
 static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp)
 {

@@ -133,6 +136,8 @@ static inline int dmi_walk(void (*decode)(const struct dmi_header *, void *),
 	void *private_data) { return -1; }
 static inline bool dmi_match(enum dmi_field f, const char *str)
 	{ return false; }
+static inline void dmi_memdev_name(u16 handle, const char **bank,
+		const char **device) { }
 static inline const struct dmi_system_id *
 	dmi_first_match(const struct dmi_system_id *list) { return NULL; }
 

In latest UEFI spec(by now it is 2.4) memory error definition for CPER (UEFI 2.4 Appendix N Common Platform Error Record) adds some new fields. These fields help people to locate memory error on actual DIMM location.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Reviewed-by Borislav Petkov <[email protected]>

---
 arch/x86/kernel/cpu/mcheck/mce-apei.c |  3 +--
 drivers/acpi/apei/cper.c              |  7 ++++---
 drivers/acpi/apei/ghes.c              |  4 ++--
 drivers/edac/ghes_edac.c              |  5 ++---
 include/linux/cper.h                  | 11 +++++++++--
 5 files changed, 18 insertions(+), 12 deletions(-)

arch/x86/kernel/cpu/mcheck/mce-apei.c +1 -2

index cd8b166..de8b60a 100644
@@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
 	struct mce m;
 
 	/* Only corrected MC is reported */
-	if (!corrected || !(mem_err->validation_bits &
-				CPER_MEM_VALID_PHYSICAL_ADDRESS))
+	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
 	mce_setup(&m);

drivers/acpi/apei/cper.c +4 -3

index eb5f6d6..946ef52 100644
@@ -8,7 +8,7 @@
  * various tables, such as ERST, BERT and HEST etc.
  *
  * For more information about CPER, please refer to Appendix N of UEFI
- * Specification version 2.3.
+ * Specification version 2.4.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version

@@ -191,16 +191,17 @@ static const char *cper_mem_err_type_strs[] = {
 	"memory sparing",
 	"scrub corrected error",
 	"scrub uncorrected error",
+	"physical memory map-out event",
 };
 
 static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 {
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)
+	if (mem->validation_bits & CPER_MEM_VALID_PA)
 		printk("%s""physical_address: 0x%016llx\n",
 		       pfx, mem->physical_addr);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK)
+	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
 		printk("%s""physical_address_mask: 0x%016llx\n",
 		       pfx, mem->physical_addr_mask);
 	if (mem->validation_bits & CPER_MEM_VALID_NODE)

drivers/acpi/apei/ghes.c +2 -2

index 0db6e4f..a30bc31 100644
@@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 
 	if (sec_sev == GHES_SEV_CORRECTED &&
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
-	    (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
+	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		if (pfn_valid(pfn))
 			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);

@@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 	}
 	if (sev == GHES_SEV_RECOVERABLE &&
 	    sec_sev == GHES_SEV_RECOVERABLE &&
-	    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		memory_failure_queue(pfn, 0, 0);
 	}

drivers/edac/ghes_edac.c +2 -3

index bb53467..0ad797b 100644
@@ -297,15 +297,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 	}
 
 	/* Error address */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
 		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
 	}
 
 	/* Error grain */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
 		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
-	}
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;

include/linux/cper.h +9 -2

index 09ebe21..2fc0ec3 100644
@@ -218,8 +218,8 @@ enum {
 #define CPER_PROC_VALID_IP			0x1000
 
 #define CPER_MEM_VALID_ERROR_STATUS		0x0001
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS		0x0002
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK	0x0004
+#define CPER_MEM_VALID_PA			0x0002
+#define CPER_MEM_VALID_PA_MASK			0x0004
 #define CPER_MEM_VALID_NODE			0x0008
 #define CPER_MEM_VALID_CARD			0x0010
 #define CPER_MEM_VALID_MODULE			0x0020

@@ -232,6 +232,9 @@ enum {
 #define CPER_MEM_VALID_RESPONDER_ID		0x1000
 #define CPER_MEM_VALID_TARGET_ID		0x2000
 #define CPER_MEM_VALID_ERROR_TYPE		0x4000
+#define CPER_MEM_VALID_RANK_NUMBER		0x8000
+#define CPER_MEM_VALID_CARD_HANDLE		0x10000
+#define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002

@@ -347,6 +350,10 @@ struct cper_sec_mem_err {
 	__u64	responder_id;
 	__u64	target_id;
 	__u8	error_type;
+	__u8	reserved;
+	__u16	rank;
+	__u16	mem_array_handle;	/* card handle in UEFI 2.4 */
+	__u16	mem_dev_handle;		/* module handle in UEFI 2.4 */
 };
 
 struct cper_sec_pcie {

In latest UEFI spec(by now it is 2.4) memory error definition for CPER (UEFI 2.4 Appendix N Common Platform Error Record) adds some new fields. These fields help people to locate memory error on actual DIMM location.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Reviewed-by Borislav Petkov <[email protected]>

---
 arch/x86/kernel/cpu/mcheck/mce-apei.c |  3 +--
 drivers/acpi/apei/cper.c              |  7 ++++---
 drivers/acpi/apei/ghes.c              |  4 ++--
 drivers/edac/ghes_edac.c              |  5 ++---
 include/linux/cper.h                  | 11 +++++++++--
 5 files changed, 18 insertions(+), 12 deletions(-)

arch/x86/kernel/cpu/mcheck/mce-apei.c +1 -2

index cd8b166..de8b60a 100644
@@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
 	struct mce m;
 
 	/* Only corrected MC is reported */
-	if (!corrected || !(mem_err->validation_bits &
-				CPER_MEM_VALID_PHYSICAL_ADDRESS))
+	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
 	mce_setup(&m);

drivers/acpi/apei/cper.c +4 -3

index eb5f6d6..946ef52 100644
@@ -8,7 +8,7 @@
  * various tables, such as ERST, BERT and HEST etc.
  *
  * For more information about CPER, please refer to Appendix N of UEFI
- * Specification version 2.3.
+ * Specification version 2.4.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version

@@ -191,16 +191,17 @@ static const char *cper_mem_err_type_strs[] = {
 	"memory sparing",
 	"scrub corrected error",
 	"scrub uncorrected error",
+	"physical memory map-out event",
 };
 
 static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 {
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)
+	if (mem->validation_bits & CPER_MEM_VALID_PA)
 		printk("%s""physical_address: 0x%016llx\n",
 		       pfx, mem->physical_addr);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK)
+	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
 		printk("%s""physical_address_mask: 0x%016llx\n",
 		       pfx, mem->physical_addr_mask);
 	if (mem->validation_bits & CPER_MEM_VALID_NODE)

drivers/acpi/apei/ghes.c +2 -2

index 0db6e4f..a30bc31 100644
@@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 
 	if (sec_sev == GHES_SEV_CORRECTED &&
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
-	    (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
+	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		if (pfn_valid(pfn))
 			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);

@@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 	}
 	if (sev == GHES_SEV_RECOVERABLE &&
 	    sec_sev == GHES_SEV_RECOVERABLE &&
-	    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		memory_failure_queue(pfn, 0, 0);
 	}

drivers/edac/ghes_edac.c +2 -3

index bb53467..0ad797b 100644
@@ -297,15 +297,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 	}
 
 	/* Error address */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
 		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
 	}
 
 	/* Error grain */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
 		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
-	}
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;

include/linux/cper.h +5 -2

index 09ebe21..2fc0ec3 100644
@@ -218,8 +218,8 @@ enum {
 #define CPER_PROC_VALID_IP			0x1000
 
 #define CPER_MEM_VALID_ERROR_STATUS		0x0001
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS		0x0002
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK	0x0004
+#define CPER_MEM_VALID_PA			0x0002
+#define CPER_MEM_VALID_PA_MASK			0x0004
 #define CPER_MEM_VALID_NODE			0x0008
 #define CPER_MEM_VALID_CARD			0x0010
 #define CPER_MEM_VALID_MODULE			0x0020

@@ -232,6 +232,9 @@ enum {
 #define CPER_MEM_VALID_RESPONDER_ID		0x1000
 #define CPER_MEM_VALID_TARGET_ID		0x2000
 #define CPER_MEM_VALID_ERROR_TYPE		0x4000
+#define CPER_MEM_VALID_RANK_NUMBER		0x8000
+#define CPER_MEM_VALID_CARD_HANDLE		0x10000
+#define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002

include/linux/cper.h +0 -0

 };
 
 struct cper_sec_pcie {

Date: Thu, 17 Oct 2013 07:23:06 -0300
From: Mauro Carvalho Chehab <[email protected]>
To: "Chen, Gong" <[email protected]>
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected], [email protected], [email protected]
Subject: Re: [PATCH v2 6/9] ACPI, APEI, CPER: Add UEFI 2.4 support for
memory error
X-Mailer: Claws Mail 3.9.2 (GTK+ 2.24.19; x86_64-redhat-linux-gnu)

Em Wed, 16 Oct 2013 10:56:03 -0400
"Chen, Gong" <[email protected]> escreveu:

Quoted 130 lines

In latest UEFI spec(by now it is 2.4) memory error definition for CPER (UEFI 2.4 Appendix N Common Platform Error Record) adds some new fields. These fields help people to locate memory error on actual DIMM location.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Reviewed-by Borislav Petkov <[email protected]>

---
 arch/x86/kernel/cpu/mcheck/mce-apei.c |  3 +--
 drivers/acpi/apei/cper.c              |  7 ++++---
 drivers/acpi/apei/ghes.c              |  4 ++--
 drivers/edac/ghes_edac.c              |  5 ++---
 include/linux/cper.h                  | 11 +++++++++--
 5 files changed, 18 insertions(+), 12 deletions(-)

arch/x86/kernel/cpu/mcheck/mce-apei.c +1 -2

index cd8b166..de8b60a 100644
@@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
 	struct mce m;
 
 	/* Only corrected MC is reported */
-	if (!corrected || !(mem_err->validation_bits &
-				CPER_MEM_VALID_PHYSICAL_ADDRESS))
+	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
 	mce_setup(&m);

drivers/acpi/apei/cper.c +4 -3

index eb5f6d6..946ef52 100644
@@ -8,7 +8,7 @@
  * various tables, such as ERST, BERT and HEST etc.
  *
  * For more information about CPER, please refer to Appendix N of UEFI
- * Specification version 2.3.
+ * Specification version 2.4.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version

@@ -191,16 +191,17 @@ static const char *cper_mem_err_type_strs[] = {
 	"memory sparing",
 	"scrub corrected error",
 	"scrub uncorrected error",
+	"physical memory map-out event",
 };
 
 static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 {
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)
+	if (mem->validation_bits & CPER_MEM_VALID_PA)
 		printk("%s""physical_address: 0x%016llx\n",
 		       pfx, mem->physical_addr);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK)
+	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
 		printk("%s""physical_address_mask: 0x%016llx\n",
 		       pfx, mem->physical_addr_mask);
 	if (mem->validation_bits & CPER_MEM_VALID_NODE)

drivers/acpi/apei/ghes.c +2 -2

index 0db6e4f..a30bc31 100644
@@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 
 	if (sec_sev == GHES_SEV_CORRECTED &&
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
-	    (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
+	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		if (pfn_valid(pfn))
 			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);

@@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 	}
 	if (sev == GHES_SEV_RECOVERABLE &&
 	    sec_sev == GHES_SEV_RECOVERABLE &&
-	    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		memory_failure_queue(pfn, 0, 0);
 	}

drivers/edac/ghes_edac.c +2 -3

index bb53467..0ad797b 100644
@@ -297,15 +297,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 	}
 
 	/* Error address */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
 		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
 	}
 
 	/* Error grain */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
 		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
-	}
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;

include/linux/cper.h +5 -2

index 09ebe21..2fc0ec3 100644
@@ -218,8 +218,8 @@ enum {
 #define CPER_PROC_VALID_IP			0x1000
 
 #define CPER_MEM_VALID_ERROR_STATUS		0x0001
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS		0x0002
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK	0x0004
+#define CPER_MEM_VALID_PA			0x0002
+#define CPER_MEM_VALID_PA_MASK			0x0004
 #define CPER_MEM_VALID_NODE			0x0008
 #define CPER_MEM_VALID_CARD			0x0010
 #define CPER_MEM_VALID_MODULE			0x0020

@@ -232,6 +232,9 @@ enum {
 #define CPER_MEM_VALID_RESPONDER_ID		0x1000
 #define CPER_MEM_VALID_TARGET_ID		0x2000
 #define CPER_MEM_VALID_ERROR_TYPE		0x4000
+#define CPER_MEM_VALID_RANK_NUMBER		0x8000
+#define CPER_MEM_VALID_CARD_HANDLE		0x10000
+#define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 

include/linux/cper.h struct cper_sec_mem_err { · line 356

Quoted 10 lines

include/linux/cper.h +4 -0

 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002

@@ -347,6 +350,10 @@ struct cper_sec_mem_err {
 	__u64	responder_id;
 	__u64	target_id;
 	__u8	error_type;
+	__u8	reserved;
+	__u16	rank;
+	__u16	mem_array_handle;	/* card handle in UEFI 2.4 */
+	__u16	mem_dev_handle;		/* module handle in UEFI 2.4 */

Hmm... you're adding 3 new types here and the corresponding space inside the structure (rank, card_handle and module_handle), but the code that parses and prints it is missing, at apei_mce_report_mem_error(), cper_print_mem(), ghes_handle_memory_failure() and ghes_edac_report_mem_error().

Quoted 3 lines

include/linux/cper.h +0 -0

 };
 
 struct cper_sec_pcie {

Signature · 2 lines

Cheers,
Mauro

In latest UEFI spec(by now it is 2.4) memory error definition for CPER (UEFI 2.4 Appendix N Common Platform Error Record) adds some new fields. These fields help people to locate memory error on actual DIMM location.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Reviewed-by Borislav Petkov <[email protected]>

---
  arch/x86/kernel/cpu/mcheck/mce-apei.c |  3 +--
  drivers/acpi/apei/cper.c              |  7 ++++---
  drivers/acpi/apei/ghes.c              |  4 ++--
  drivers/edac/ghes_edac.c              |  5 ++---
  include/linux/cper.h                  | 11 +++++++++--
  5 files changed, 18 insertions(+), 12 deletions(-)

After H/W error happens under FFM enabled mode, lots of information are shown but some important parts like DIMM location missed. This patch is used to show these extra fileds.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Acked-by Naveen N. Rao <[email protected]>

After H/W error happens under FFM enabled mode, lots of information are shown but some important parts like DIMM location missed. This patch is used to show these extra fileds.

Original-author: Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Acked-by Naveen N. Rao <[email protected]>

---
 drivers/acpi/apei/cper.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

drivers/acpi/apei/cper.c +12 -0

index 946ef52..b1a8a55 100644
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/time.h>
 #include <linux/cper.h>
+#include <linux/dmi.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
 #include <linux/aer.h>

@@ -210,6 +211,8 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 		printk("%s""card: %d\n", pfx, mem->card);
 	if (mem->validation_bits & CPER_MEM_VALID_MODULE)
 		printk("%s""module: %d\n", pfx, mem->module);
+	if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
+		printk("%s""rank: %d\n", pfx, mem->rank);
 	if (mem->validation_bits & CPER_MEM_VALID_BANK)
 		printk("%s""bank: %d\n", pfx, mem->bank);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)

@@ -232,6 +235,15 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 		       etype < ARRAY_SIZE(cper_mem_err_type_strs) ?
 		       cper_mem_err_type_strs[etype] : "unknown");
 	}
+	if (mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
+		const char *bank = NULL, *device = NULL;
+		dmi_memdev_name(mem->mem_dev_handle, &bank, &device);
+		if (bank != NULL && device != NULL)
+			printk("%s""DIMM location: %s %s", pfx, bank, device);
+		else
+			printk("%s""DIMM DMI handle: 0x%.4x",
+			       pfx, mem->mem_dev_handle);
+	}
 }
 
 static const char *cper_pcie_port_type_strs[] = {

Keep up only the most important fields for memory error reporting. The detail information will be moved to perf/trace interface.

Suggested-by Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

---
 drivers/acpi/apei/cper.c | 69 +++++++++++++++++++++++-------------------------
 1 file changed, 33 insertions(+), 36 deletions(-)

drivers/acpi/apei/cper.c +0 -0

index b1a8a55..f5bc227 100644

Quoted 6 lines

Keep up only the most important fields for memory error reporting. The detail information will be moved to perf/trace interface.

Suggested-by Tony Luck <[email protected]>

Signed-off-by Chen, Gong <[email protected]>

Quoted 9 lines

---
 drivers/acpi/apei/cper.c | 69 +++++++++++++++++++++++-------------------------
 1 file changed, 33 insertions(+), 36 deletions(-)

drivers/acpi/apei/cper.c +0 -0

index b1a8a55..f5bc227 100644

drivers/acpi/apei/cper.c line 38

Quoted 6 lines

drivers/acpi/apei/cper.c +3 -0

@@ -33,6 +33,9 @@
 #include <linux/pci.h>
 #include <linux/aer.h>
 
+#define INDENT_SP	" "
+#define HW_CE_INFO \
+	"Above error has been corrected by h/w and no further action required"

Leftover?

drivers/acpi/apei/cper.c void cper_estatus_print(const char *pfx, · line 372

Quoted 4 lines

drivers/acpi/apei/cper.c +4 -0

+	if (severity != CPER_SEV_FATAL)
+		printk("%s%s\n", pfx,
+		       "Above error has been corrected by h/w "
+		       "and require no further action");

Let's write it out and correct grammar:

"Above error has been corrected by the hardware and requires no further action."

Thanks.

Use trace interface to elaborate all H/W error related information.

v2 -> v1: move trace interface into ras_event.h

Signed-off-by Chen, Gong <[email protected]>

---
 drivers/acpi/Kconfig        |   7 ++-
 drivers/acpi/Makefile       |   4 ++
 drivers/acpi/acpi_extlog.c  |  28 +++++++++++-
 drivers/acpi/apei/cper.c    |  13 ++++--
 drivers/acpi/extlog_trace.c | 107 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/extlog_trace.h |  16 +++++++
 include/linux/cper.h        |   2 +
 include/ras/ras_event.h     |  61 +++++++++++++++++++++++++
 8 files changed, 232 insertions(+), 6 deletions(-)
 create mode 100644 drivers/acpi/extlog_trace.c
 create mode 100644 drivers/acpi/extlog_trace.h

drivers/acpi/Kconfig +6 -1

index 819c06b..0cc8fc8 100644
@@ -372,13 +372,18 @@ config ACPI_BGRT
 
 source "drivers/acpi/apei/Kconfig"
 
+config EXTLOG_TRACE
+	def_bool n
+
 config ACPI_EXTLOG
 	tristate "Extended Error Log support"
 	depends on X86_MCE
+	select EXTLOG_TRACE
 	default n
 	help
 	  Enhanced MCA Logging allows firmware to provide additional error
 	  information to system software, synchronous with MCE or CMCI. This
-	  driver adds support for that functionality.
+	  driver adds support for that functionality plus an additional special
+	  tracepoint which carries that information to userspace.
 
 endif	# ACPI

drivers/acpi/Makefile +4 -0

index bce34af..a6e41b7 100644
@@ -83,4 +83,8 @@ obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o
 
 obj-$(CONFIG_ACPI_APEI)		+= apei/
 
+# extended log support
+acpi-$(CONFIG_EXTLOG_TRACE)	+= extlog_trace.o
+CFLAGS_extlog_trace.o := -I$(src)
+
 obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o

drivers/acpi/acpi_extlog.c +26 -2

index d55b072..01e6a89 100644
@@ -15,6 +15,7 @@
 #include <asm/mce.h>
 
 #include "apei/apei-internal.h"
+#include "extlog_trace.h"
 
 #define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(52, 0) /* elog entry address mask */
 

@@ -44,6 +45,8 @@ struct extlog_l1_head {
 
 static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295";
 
+static const uuid_le invalid_uuid = NULL_UUID_LE;
+
 /* L1 table related physical address */
 static u64 elog_base;
 static size_t elog_size;

@@ -132,7 +135,12 @@ static int print_extlog_rcd(const char *pfx,
 
 static int extlog_print(const char *pfx, int cpu, int bank)
 {
-	struct acpi_generic_status *estatus;
+	struct acpi_generic_status *estatus, *tmp;
+	struct acpi_generic_data *gdata;
+	const uuid_le *fru_id = &invalid_uuid;
+	char *fru_text = "";
+	uuid_le *sec_type;
+	static u64 err_count;
 	int rc;
 
 	estatus = extlog_elog_entry_check(cpu, bank);

@@ -143,7 +151,23 @@ static int extlog_print(const char *pfx, int cpu, int bank)
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
 
-	rc = print_extlog_rcd(pfx, (struct acpi_generic_status *)elog_buf, cpu);
+	tmp = (struct acpi_generic_status *)elog_buf;
+	gdata = (struct acpi_generic_data *)(tmp + 1);
+	rc = print_extlog_rcd(pfx, tmp, cpu);
+
+	/* trace extended error log */
+	err_count++;
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+		fru_id = (uuid_le *)gdata->fru_id;
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+		fru_text = gdata->fru_text;
+	sec_type = (uuid_le *)gdata->section_type;
+	if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
+		if (gdata->error_data_length >= sizeof(*mem_err))
+			trace_mem_error(fru_id, fru_text, err_count,
+					gdata->error_severity, mem_err);
+	}
 
 	return rc;
 }

drivers/acpi/apei/cper.c +10 -3

index f5bc227..44bde6a 100644
@@ -59,11 +59,12 @@ static const char *cper_severity_strs[] = {
 	"info",
 };
 
-static const char *cper_severity_str(unsigned int severity)
+const char *cper_severity_str(unsigned int severity)
 {
 	return severity < ARRAY_SIZE(cper_severity_strs) ?
 		cper_severity_strs[severity] : "unknown";
 }
+EXPORT_SYMBOL_GPL(cper_severity_str);
 
 /*
  * cper_print_bits - print strings for set bits

@@ -198,6 +199,13 @@ static const char *cper_mem_err_type_strs[] = {
 	"physical memory map-out event",
 };
 
+const char *cper_mem_err_type_str(unsigned int etype)
+{
+	return etype < ARRAY_SIZE(cper_mem_err_type_strs) ?
+		cper_mem_err_type_strs[etype] : "unknown";
+}
+EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
+
 static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 {
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)

@@ -235,8 +243,7 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
 		u8 etype = mem->error_type;
 		printk("%s""error_type: %d, %s\n", pfx, etype,
-		       etype < ARRAY_SIZE(cper_mem_err_type_strs) ?
-		       cper_mem_err_type_strs[etype] : "unknown");
+			cper_mem_err_type_str(etype));
 	}
 	if (mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
 		const char *bank = NULL, *device = NULL;

drivers/acpi/extlog_trace.c new file +107 -0

new file mode 100644
index 0000000..2864080
@@ -0,0 +1,107 @@
+#include <linux/export.h>
+#include <linux/dmi.h>
+#include "extlog_trace.h"
+
+#define CREATE_TRACE_POINTS
+#define TRACE_INCLUDE_PATH ../../include/ras
+#include <ras/ras_event.h>
+
+static char mem_location[LOC_LEN];
+static char dimm_location[LOC_LEN];
+
+static void mem_err_location(struct cper_sec_mem_err *mem)
+{
+	char *p;
+	u32 n = 0;
+
+	memset(mem_location, 0, LOC_LEN);
+	p = mem_location;
+	if (mem->validation_bits & CPER_MEM_VALID_NODE)
+		n += sprintf(p + n, " node: %d", mem->node);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_CARD)
+		n += sprintf(p + n, " card: %d", mem->card);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_MODULE)
+		n += sprintf(p + n, " module: %d", mem->module);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
+		n += sprintf(p + n, " rank: %d", mem->rank);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_BANK)
+		n += sprintf(p + n, " bank: %d", mem->bank);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
+		n += sprintf(p + n, " device: %d", mem->device);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_ROW)
+		n += sprintf(p + n, " row: %d", mem->row);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
+		n += sprintf(p + n, " column: %d", mem->column);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
+		n += sprintf(p + n, " bit_position: %d", mem->bit_pos);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
+		n += sprintf(p + n, " requestor_id: 0x%016llx",
+				mem->requestor_id);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
+		n += sprintf(p + n, " responder_id: 0x%016llx",
+				mem->responder_id);
+	if (n >= LOC_LEN)
+		goto end;
+	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
+		n += sprintf(p + n, " target_id: 0x%016llx", mem->target_id);
+end:
+	return;
+}
+
+static void dimm_err_location(struct cper_sec_mem_err *mem)
+{
+	const char *bank = NULL, *device = NULL;
+
+	memset(dimm_location, 0, LOC_LEN);
+	if (!(mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE))
+		return;
+
+	dmi_memdev_name(mem->mem_dev_handle, &bank, &device);
+	if (bank != NULL && device != NULL)
+		snprintf(dimm_location, LOC_LEN - 1, "%s %s", bank, device);
+	else
+		snprintf(dimm_location, LOC_LEN - 1, "DMI handle: 0x%.4x",
+			 mem->mem_dev_handle);
+}
+
+void trace_mem_error(const uuid_le *fru_id, char *fru_text,
+			    u64 err_count, u32 severity,
+			    struct cper_sec_mem_err *mem)
+{
+	u32 etype = ~0U;
+	u64 phy_addr = 0;
+
+	if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
+		etype = mem->error_type;
+	if (mem->validation_bits & CPER_MEM_VALID_PA) {
+		phy_addr = mem->physical_addr;
+		if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
+			phy_addr &= mem->physical_addr_mask;
+	}
+	mem_err_location(mem);
+	dimm_err_location(mem);
+
+	trace_extlog_mem_event(etype, dimm_location, fru_id, fru_text,
+			       err_count, severity, phy_addr, mem_location);
+}
+EXPORT_SYMBOL_GPL(trace_mem_error);

drivers/acpi/extlog_trace.h new file +16 -0

new file mode 100644
index 0000000..67bb2c5
@@ -0,0 +1,16 @@
+#ifndef __DEBUG_EXTLOG_H
+#define __DEBUG_EXTLOG_H
+
+#include <linux/cper.h>
+
+#ifdef CONFIG_EXTLOG_TRACE
+extern void trace_mem_error(const uuid_le *fru_id, char *fru_text,
+		u64 err_count, u32 severity, struct cper_sec_mem_err *mem);
+#else
+void trace_mem_error(const uuid_le *fru_id, char *fru_text,
+		u64 err_count, u32 severity, struct cper_sec_mem_err *mem)
+{
+}
+#endif
+
+#endif

include/linux/cper.h +2 -0

index 2fc0ec3..c6d87fc 100644
@@ -395,6 +395,8 @@ struct cper_sec_pcie {
 #pragma pack()
 
 u64 cper_next_record_id(void);
+const char *cper_severity_str(unsigned int);
+const char *cper_mem_err_type_str(unsigned int);
 void cper_print_bits(const char *prefix, unsigned int bits,
 		     const char * const strs[], unsigned int strs_size);
 

include/ras/ras_event.h +61 -0

index 21cdb0b..fce14b6 100644
@@ -8,6 +8,67 @@
 #include <linux/tracepoint.h>
 #include <linux/edac.h>
 #include <linux/ktime.h>
+#include <linux/cper.h>
+
+/*
+ * MCE Extended Error Log trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event.
+ *
+ */
+
+/* memory trace event */
+
+#define LOC_LEN		512
+#define MSG_LEN		((LOC_LEN) * 2)
+
+TRACE_EVENT(extlog_mem_event,
+	TP_PROTO(u32 etype,
+		char *dimm_loc,
+		const uuid_le *fru_id,
+		char *fru_text,
+		u64 error_count,
+		u32 severity,
+		u64 phy_addr,
+		char *mem_loc),
+
+	TP_ARGS(etype, dimm_loc, fru_id, fru_text, error_count, severity,
+		phy_addr, mem_loc),
+
+	TP_STRUCT__entry(
+		__field(u32, etype)
+		__dynamic_array(char, dimm_info, LOC_LEN)
+		__field(u64, error_count)
+		__field(u32, severity)
+		__dynamic_array(char, msg, MSG_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->error_count = error_count;
+		__entry->severity = severity;
+		__entry->etype = etype;
+		if (dimm_loc[0] != '\0')
+			snprintf(__get_dynamic_array(dimm_info), LOC_LEN - 1,
+				"on %s", dimm_loc);
+		else
+			__assign_str(dimm_info, "");
+		if (phy_addr != 0)
+			snprintf(__get_dynamic_array(msg), MSG_LEN - 1,
+				"(FRU: %pUl %.20s physical addr: 0x%016llx%s)",
+				fru_id, fru_text, phy_addr, mem_loc);
+		else
+			__assign_str(msg, "");
+	),
+
+	TP_printk("%llu %s error%s: %s %s %s",
+			__entry->error_count,
+			cper_severity_str(__entry->severity),
+			__entry->error_count > 1 ? "s" : "",
+			cper_mem_err_type_str(__entry->etype),
+			__get_str(dimm_info),
+			__get_str(msg))
+);
 
 /*
  * Hardware Events Report