Linux-ACPI Archive on lore.kernel.org
 help / color / Atom feed
From: Punit Agrawal <punit1.agrawal@toshiba.co.jp>
To: Ard Biesheuvel <ardb@kernel.org>
Cc: linux-kernel@vger.kernel.org,
	Punit Agrawal <punit1.agrawal@toshiba.co.jp>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	Borislav Petkov <bp@alien8.de>, James Morse <james.morse@arm.com>,
	linux-acpi@vger.kernel.org, linux-efi@vger.kernel.org
Subject: [Patch v2] efi: cper: Add support for printing Firmware Error Record Reference
Date: Tue, 12 May 2020 13:55:02 +0900
Message-ID: <20200512045502.3810339-1-punit1.agrawal@toshiba.co.jp> (raw)

While debugging a boot failure, the following unknown error record was
seen in the boot logs.

    <...>
    BERT: Error records from previous boot:
    [Hardware Error]: event severity: fatal
    [Hardware Error]:  Error 0, type: fatal
    [Hardware Error]:   section type: unknown, 81212a96-09ed-4996-9471-8d729c8e69ed
    [Hardware Error]:   section length: 0x290
    [Hardware Error]:   00000000: 00000001 00000000 00000000 00020002  ................
    [Hardware Error]:   00000010: 00020002 0000001f 00000320 00000000  ........ .......
    [Hardware Error]:   00000020: 00000000 00000000 00000000 00000000  ................
    [Hardware Error]:   00000030: 00000000 00000000 00000000 00000000  ................
    <...>

On further investigation, it was found that the error record with
UUID (81212a96-09ed-4996-9471-8d729c8e69ed) has been defined in the
UEFI Specification at least since v2.4 and has recently had additional
fields defined in v2.7 Section N.2.10 Firmware Error Record Reference.

Add support for parsing and printing the defined fields to give users
a chance to figure out what went wrong.

Signed-off-by: Punit Agrawal <punit1.agrawal@toshiba.co.jp>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: James Morse <james.morse@arm.com>
Cc: linux-acpi@vger.kernel.org
Cc: linux-efi@vger.kernel.org
---
Hi Ard,

I've updated the patch based on your feedback.

As you noted, some aspects of the spec make it a bit tricky to support
all revisions in a nice way (e.g., size check) but this version should
fix existing issues.

Thanks,
Punit

v1[0] -> v2:
* Simplified error record structure definition
* Fixed size check
* Added comment to clarify offset calculation for dumped data
* Style fixes for multiline if blocks

[0] https://lkml.kernel.org/lkml/20200427085242.2380614-1-punit1.agrawal@toshiba.co.jp/
---
 drivers/firmware/efi/cper.c | 62 +++++++++++++++++++++++++++++++++++++
 include/linux/cper.h        |  9 ++++++
 2 files changed, 71 insertions(+)

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 9d2512913d25..f564e15fbc7e 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -407,6 +407,58 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	}
 }
 
+static const char * const fw_err_rec_type_strs[] = {
+	"IPF SAL Error Record",
+	"SOC Firmware Error Record Type1 (Legacy CrashLog Support)",
+	"SOC Firmware Error Record Type2",
+};
+
+static void cper_print_fw_err(const char *pfx,
+			      struct acpi_hest_generic_data *gdata,
+			      const struct cper_sec_fw_err_rec_ref *fw_err)
+{
+	void *buf = acpi_hest_get_payload(gdata);
+	u32 offset, length = gdata->error_data_length;
+
+	printk("%s""Firmware Error Record Type: %s\n", pfx,
+	       fw_err->record_type < ARRAY_SIZE(fw_err_rec_type_strs) ?
+	       fw_err_rec_type_strs[fw_err->record_type] : "unknown");
+	printk("%s""Revision: %d\n", pfx, fw_err->revision);
+
+	/* Record Type based on UEFI 2.7 */
+	if (fw_err->revision == 0) {
+		printk("%s""Record Identifier: %08llx\n", pfx,
+		       fw_err->record_identifier);
+	} else if (fw_err->revision == 2) {
+		printk("%s""Record Identifier: %pUl\n", pfx,
+		       &fw_err->record_identifier_guid);
+	}
+
+	/*
+	 * The FW error record may contain trailing data beyond the
+	 * structure defined by the specification. As the fields
+	 * defined (and hence the offset of any trailing data) vary
+	 * with the revision, set the offset to account for this
+	 * variation.
+	 */
+	if (fw_err->revision == 0) {
+		/* record_identifier_guid not defined */
+		offset = offsetof(struct cper_sec_fw_err_rec_ref,
+				  record_identifier_guid);
+	} else if (fw_err->revision == 1) {
+		/* record_identifier not defined */
+		offset = offsetof(struct cper_sec_fw_err_rec_ref,
+				  record_identifier);
+	} else {
+		offset = sizeof(*fw_err);
+	}
+
+	buf += offset;
+	length -= offset;
+
+	print_hex_dump(pfx, "", DUMP_PREFIX_OFFSET, 16, 4, buf, length, true);
+}
+
 static void cper_print_tstamp(const char *pfx,
 				   struct acpi_hest_generic_data_v300 *gdata)
 {
@@ -494,6 +546,16 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #endif
+	} else if (guid_equal(sec_type, &CPER_SEC_FW_ERR_REC_REF)) {
+		struct cper_sec_fw_err_rec_ref *fw_err = acpi_hest_get_payload(gdata);
+
+		printk("%ssection_type: Firmware Error Record Reference\n",
+		       newpfx);
+		/* The minimal FW Error Record contains 16 bytes */
+		if (gdata->error_data_length >= SZ_16)
+			cper_print_fw_err(newpfx, gdata, fw_err);
+		else
+			goto err_section_too_small;
 	} else {
 		const void *err = acpi_hest_get_payload(gdata);
 
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 4f005d95ce88..8537e9282a65 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -521,6 +521,15 @@ struct cper_sec_pcie {
 	u8	aer_info[96];
 };
 
+/* Firmware Error Record Reference, UEFI v2.7 sec N.2.10  */
+struct cper_sec_fw_err_rec_ref {
+	u8 record_type;
+	u8 revision;
+	u8 reserved[6];
+	u64 record_identifier;
+	guid_t record_identifier_guid;
+};
+
 /* Reset to default packing */
 #pragma pack()
 
-- 
2.26.2


             reply index

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-12  4:55 Punit Agrawal [this message]
2020-05-12 10:47 ` Ard Biesheuvel
2020-05-13  2:36   ` Punit Agrawal
2020-05-22 18:30 ` [tip: efi/urgent] " tip-bot2 for Punit Agrawal

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200512045502.3810339-1-punit1.agrawal@toshiba.co.jp \
    --to=punit1.agrawal@toshiba.co.jp \
    --cc=ardb@kernel.org \
    --cc=bp@alien8.de \
    --cc=james.morse@arm.com \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-efi@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rjw@rjwysocki.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-ACPI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-acpi/0 linux-acpi/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-acpi linux-acpi/ https://lore.kernel.org/linux-acpi \
		linux-acpi@vger.kernel.org
	public-inbox-index linux-acpi

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-acpi


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git