Merge branch 'apei-release' into release

Documentation/acpi/apei/output_format.txt

@@ -92,13 +92,38 @@ vendor_id: <integer>, device_id: <integer>
 class_code: <integer>]
 [serial number: <integer>, <integer>]
 [bridge: secondary_status: <integer>, control: <integer>]
+[aer_status: <integer>, aer_mask: <integer>
+<aer status string>
+[aer_uncor_severity: <integer>]
+aer_layer=<aer layer string>, aer_agent=<aer agent string>
+aer_tlp_header: <integer> <integer> <integer> <integer>]
 
 <pcie port type string>* := PCIe end point | legacy PCI end point | \
 unknown | unknown | root port | upstream switch port | \
 downstream switch port | PCIe to PCI/PCI-X bridge | \
 PCI/PCI-X to PCIe bridge | root complex integrated endpoint device | \
 root complex event collector
 
+if section severity is fatal or recoverable
+<aer status string># :=
+unknown | unknown | unknown | unknown | Data Link Protocol | \
+unknown | unknown | unknown | unknown | unknown | unknown | unknown | \
+Poisoned TLP | Flow Control Protocol | Completion Timeout | \
+Completer Abort | Unexpected Completion | Receiver Overflow | \
+Malformed TLP | ECRC | Unsupported Request
+else
+<aer status string># :=
+Receiver Error | unknown | unknown | unknown | unknown | unknown | \
+Bad TLP | Bad DLLP | RELAY_NUM Rollover | unknown | unknown | unknown | \
+Replay Timer Timeout | Advisory Non-Fatal
+fi
+
+<aer layer string> :=
+Physical Layer | Data Link Layer | Transaction Layer
+
+<aer agent string> :=
+Receiver ID | Requester ID | Completer ID | Transmitter ID
+
 Where, [] designate corresponding content is optional
 
 All <field string> description with * has the following format:

arch/x86/kernel/cpu/mcheck/mce-apei.c

@@ -106,24 +106,34 @@ int apei_write_mce(struct mce *m)
 ssize_t apei_read_mce(struct mce *m, u64 *record_id)
 {
 	struct cper_mce_record rcd;
-	ssize_t len;
-
-	len = erst_read_next(&rcd.hdr, sizeof(rcd));
-	if (len <= 0)
-		return len;
-	/* Can not skip other records in storage via ERST unless clear them */
-	else if (len != sizeof(rcd) ||
-		 uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) {
-		if (printk_ratelimit())
-			pr_warning(
-			"MCE-APEI: Can not skip the unknown record in ERST");
-		return -EIO;
-	}
-
+	int rc, pos;
+
+	rc = erst_get_record_id_begin(&pos);
+	if (rc)
+		return rc;
+retry:
+	rc = erst_get_record_id_next(&pos, record_id);
+	if (rc)
+		goto out;
+	/* no more record */
+	if (*record_id == APEI_ERST_INVALID_RECORD_ID)
+		goto out;
+	rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd));
+	/* someone else has cleared the record, try next one */
+	if (rc == -ENOENT)
+		goto retry;
+	else if (rc < 0)
+		goto out;
+	/* try to skip other type records in storage */
+	else if (rc != sizeof(rcd) ||
+		 uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE))
+		goto retry;
 	memcpy(m, &rcd.mce, sizeof(*m));
-	*record_id = rcd.hdr.record_id;
+	rc = sizeof(*m);
+out:
+	erst_get_record_id_end();
 
-	return sizeof(*m);
+	return rc;
 }
 
 /* Check whether there is record in ERST */

drivers/acpi/apei/Kconfig

@@ -21,6 +21,13 @@ config ACPI_APEI_GHES
 	  by firmware to produce more valuable hardware error
 	  information for Linux.
 
+config ACPI_APEI_PCIEAER
+	bool "APEI PCIe AER logging/recovering support"
+	depends on ACPI_APEI && PCIEAER
+	help
+	  PCIe AER errors may be reported via APEI firmware first mode.
+	  Turn on this option to enable the corresponding support.
+
 config ACPI_APEI_EINJ
 	tristate "APEI Error INJection (EINJ)"
 	depends on ACPI_APEI && DEBUG_FS

drivers/acpi/apei/cper.c

@@ -29,6 +29,7 @@
 #include <linux/time.h>
 #include <linux/cper.h>
 #include <linux/acpi.h>
+#include <linux/aer.h>
 
 /*
  * CPER record ID need to be unique even after reboot, because record
@@ -70,8 +71,8 @@ static const char *cper_severity_str(unsigned int severity)
  * If the output length is longer than 80, multiple line will be
  * printed, with @pfx is printed at the beginning of each line.
  */
-static void cper_print_bits(const char *pfx, unsigned int bits,
-			    const char *strs[], unsigned int strs_size)
+void cper_print_bits(const char *pfx, unsigned int bits,
+		     const char *strs[], unsigned int strs_size)
 {
 	int i, len = 0;
 	const char *str;
@@ -81,6 +82,8 @@ static void cper_print_bits(const char *pfx, unsigned int bits,
 		if (!(bits & (1U << i)))
 			continue;
 		str = strs[i];
+		if (!str)
+			continue;
 		if (len && len + strlen(str) + 2 > 80) {
 			printk("%s\n", buf);
 			len = 0;
@@ -243,7 +246,8 @@ static const char *cper_pcie_port_type_strs[] = {
 	"root complex event collector",
 };
 
-static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie)
+static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
+			    const struct acpi_hest_generic_data *gdata)
 {
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
@@ -276,6 +280,12 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie)
 		printk(
 	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) {
+		struct aer_capability_regs *aer_regs = (void *)pcie->aer_info;
+		cper_print_aer(pfx, gdata->error_severity, aer_regs);
+	}
+#endif
 }
 
 static const char *apei_estatus_section_flag_strs[] = {
@@ -322,7 +332,7 @@ static void apei_estatus_print_section(
 		struct cper_sec_pcie *pcie = (void *)(gdata + 1);
 		printk("%s""section_type: PCIe error\n", pfx);
 		if (gdata->error_data_length >= sizeof(*pcie))
-			cper_print_pcie(pfx, pcie);
+			cper_print_pcie(pfx, pcie, gdata);
 		else
 			goto err_section_too_small;
 	} else

drivers/acpi/apei/erst-dbg.c

@@ -43,12 +43,27 @@ static DEFINE_MUTEX(erst_dbg_mutex);
 
 static int erst_dbg_open(struct inode *inode, struct file *file)
 {
+	int rc, *pos;
+
 	if (erst_disable)
 		return -ENODEV;
 
+	pos = (int *)&file->private_data;
+
+	rc = erst_get_record_id_begin(pos);
+	if (rc)
+		return rc;
+
 	return nonseekable_open(inode, file);
 }
 
+static int erst_dbg_release(struct inode *inode, struct file *file)
+{
+	erst_get_record_id_end();
+
+	return 0;
+}
+
 static long erst_dbg_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
 	int rc;
@@ -79,18 +94,20 @@ static long erst_dbg_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 static ssize_t erst_dbg_read(struct file *filp, char __user *ubuf,
 			     size_t usize, loff_t *off)
 {
-	int rc;
+	int rc, *pos;
 	ssize_t len = 0;
 	u64 id;
 
-	if (*off != 0)
+	if (*off)
 		return -EINVAL;
 
 	if (mutex_lock_interruptible(&erst_dbg_mutex) != 0)
 		return -EINTR;
 
+	pos = (int *)&filp->private_data;
+
 retry_next:
-	rc = erst_get_next_record_id(&id);
+	rc = erst_get_record_id_next(pos, &id);
 	if (rc)
 		goto out;
 	/* no more record */
@@ -181,6 +198,7 @@ static ssize_t erst_dbg_write(struct file *filp, const char __user *ubuf,
 static const struct file_operations erst_dbg_ops = {
 	.owner		= THIS_MODULE,
 	.open		= erst_dbg_open,
+	.release	= erst_dbg_release,
 	.read		= erst_dbg_read,
 	.write		= erst_dbg_write,
 	.unlocked_ioctl	= erst_dbg_ioctl,