mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
To: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>,
	acpica-devel@lists.linux.dev, linux-acpi@vger.kernel.org,
	linux-edac@vger.kernel.org, linux-efi@vger.kernel.org,
	linux-kernel@vger.kernel.org, Ankit Agrawal <ankita@nvidia.com>,
	Borislav Petkov <bp@alien8.de>, Breno Leitao <leitao@debian.org>,
	Hanjun Guo <guohanjun@huawei.com>, Ingo Molnar <mingo@kernel.org>,
	Jason Tian <jason@os.amperecomputing.com>,
	Jonathan Cameron <jonathan.cameron@huawei.com>,
	Len Brown <lenb@kernel.org>,
	Mauro Carvalho Chehab <mchehab@kernel.org>,
	Shuai Xue <xueshuai@linux.alibaba.com>,
	Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>,
	Tony Luck <tony.luck@intel.com>
Subject: [PATCH v5 1/4] apei/ghes: ARM processor Error: don't go past allocated memory
Date: Wed,  7 Jan 2026 17:41:49 +0100	[thread overview]
Message-ID: <7fd9f38413be05ee2d7cfdb0dc31ea2274cf1a54.1767804050.git.mchehab+huawei@kernel.org> (raw)
In-Reply-To: <cover.1767804050.git.mchehab+huawei@kernel.org>

If the BIOS generates a very small ARM Processor Error, or
an incomplete one, the current logic will fail to deferrence

	err->section_length
and
	ctx_info->size

Add checks to avoid that. With such changes, such GHESv2
records won't cause OOPSes like this:

[    1.492129] Internal error: Oops: 0000000096000005 [#1]  SMP
[    1.495449] Modules linked in:
[    1.495820] CPU: 0 UID: 0 PID: 9 Comm: kworker/0:0 Not tainted 6.18.0-rc1-00017-gabadcc3553dd-dirty #18 PREEMPT
[    1.496125] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 02/02/2022
[    1.496433] Workqueue: kacpi_notify acpi_os_execute_deferred
[    1.496967] pstate: 814000c5 (Nzcv daIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[    1.497199] pc : log_arm_hw_error+0x5c/0x200
[    1.497380] lr : ghes_handle_arm_hw_error+0x94/0x220

0xffff8000811c5324 is in log_arm_hw_error (../drivers/ras/ras.c:75).
70		err_info = (struct cper_arm_err_info *)(err + 1);
71		ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
72		ctx_err = (u8 *)ctx_info;
73
74		for (n = 0; n < err->context_info_num; n++) {
75			sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
76			ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
77			ctx_len += sz;
78		}
79

and similar ones while trying to access section_length on an
error dump with too small size.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
---
 drivers/acpi/apei/ghes.c | 32 ++++++++++++++++++++++++++++----
 drivers/ras/ras.c        |  6 +++++-
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0dc767392a6c..fc3f8aed99d5 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -552,21 +552,45 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
 	int flags = sync ? MF_ACTION_REQUIRED : 0;
+	int length = gdata->error_data_length;
 	char error_type[120];
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
 
 	sec_sev = ghes_severity(gdata->error_severity);
-	log_arm_hw_error(err, sec_sev);
+	if (length >= sizeof(*err)) {
+		log_arm_hw_error(err, sec_sev);
+	} else {
+		pr_warn(FW_BUG "arm error length: %d\n", length);
+		pr_warn(FW_BUG "length is too small\n");
+		pr_warn(FW_BUG "firmware-generated error record is incorrect\n");
+		return false;
+	}
+
 	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
 		return false;
 
 	p = (char *)(err + 1);
+	length -= sizeof(err);
+
 	for (i = 0; i < err->err_info_num; i++) {
-		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
-		bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
-		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
+		struct cper_arm_err_info *err_info;
+		bool is_cache, has_pa;
+
+		/* Ensure we have enough data for the error info header */
+		if (length < sizeof(*err_info))
+			break;
+
+		err_info = (struct cper_arm_err_info *)p;
+
+		/* Validate the claimed length before using it */
+		length -= err_info->length;
+		if (length < 0)
+			break;
+
+		is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
+		has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
 
 		/*
 		 * The field (err_info->error_info & BIT(26)) is fixed to set to
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 2a5b5a9fdcb3..03df3db62334 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -72,7 +72,11 @@ void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
 	ctx_err = (u8 *)ctx_info;
 
 	for (n = 0; n < err->context_info_num; n++) {
-		sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
+		sz = sizeof(struct cper_arm_ctx_info);
+
+		if (sz + (long)ctx_info - (long)err >= err->section_length)
+			sz += ctx_info->size;
+
 		ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
 		ctx_len += sz;
 	}
-- 
2.52.0


  reply	other threads:[~2026-01-07 16:42 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-07 16:41 [PATCH v5 0/4] apei/ghes: don't OOPS with bad ARM error CPER records Mauro Carvalho Chehab
2026-01-07 16:41 ` Mauro Carvalho Chehab [this message]
2026-01-07 16:41 ` [PATCH v5 2/4] efi/cper: don't go past the ARM processor CPER record buffer Mauro Carvalho Chehab
2026-01-07 16:41 ` [PATCH v5 3/4] apei/ghes: ensure that won't go past CPER allocated record Mauro Carvalho Chehab
2026-01-07 17:07   ` Jonathan Cameron
2026-01-07 16:41 ` [PATCH v5 4/4] efi/cper: don't dump the entire memory region Mauro Carvalho Chehab
2026-01-07 17:53   ` Jonathan Cameron

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=7fd9f38413be05ee2d7cfdb0dc31ea2274cf1a54.1767804050.git.mchehab+huawei@kernel.org \
    --to=mchehab+huawei@kernel.org \
    --cc=Smita.KoralahalliChannabasappa@amd.com \
    --cc=acpica-devel@lists.linux.dev \
    --cc=ankita@nvidia.com \
    --cc=bp@alien8.de \
    --cc=guohanjun@huawei.com \
    --cc=jason@os.amperecomputing.com \
    --cc=jonathan.cameron@huawei.com \
    --cc=leitao@debian.org \
    --cc=lenb@kernel.org \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-edac@vger.kernel.org \
    --cc=linux-efi@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mchehab@kernel.org \
    --cc=mingo@kernel.org \
    --cc=rafael@kernel.org \
    --cc=tony.luck@intel.com \
    --cc=xueshuai@linux.alibaba.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®