linux-kernel - [PATCH v3 1/2] apei/ghes: ARM processor Error: don't go past allocated memory

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <e80bc4eba43d0211713fe66958ec0c582d9bfda7.1766140788.git.mchehab+huawei@kernel.org>
Date: Fri, 19 Dec 2025 11:49:59 +0100
From: Mauro Carvalho Chehab <mchehab+huawei@...nel.org>
To: "Rafael J. Wysocki" <rafael@...nel.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@...nel.org>,
	"Ankit Agrawal" <ankita@...dia.com>,
	"Borislav Petkov" <bp@...en8.de>,
	"Breno Leitao" <leitao@...ian.org>,
	"Hanjun Guo" <guohanjun@...wei.com>,
	"Ingo Molnar" <mingo@...nel.org>,
	"Jason Tian" <jason@...amperecomputing.com>,
	"Jonathan Cameron" <Jonathan.Cameron@...wei.com>,
	"Len Brown" <lenb@...nel.org>,
	"Mauro Carvalho Chehab" <mchehab@...nel.org>,
	"Shuai Xue" <xueshuai@...ux.alibaba.com>,
	"Smita Koralahalli" <Smita.KoralahalliChannabasappa@....com>,
	"Tony Luck" <tony.luck@...el.com>,
	linux-efi@...r.kernel.org,
	linux-acpi@...r.kernel.org,
	linux-edac@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH v3 1/2] apei/ghes: ARM processor Error: don't go past allocated memory

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@...nel.org>
---
 drivers/acpi/apei/ghes.c | 33 +++++++++++++++++++++++++++++----
 drivers/ras/ras.c        |  6 +++++-
 2 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0dc767392a6c..9bf4ec84f160 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -552,21 +552,46 @@ 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 */
+		length -= sizeof(*err_info);
+		if (length < 0)
+			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