The logic at ghes_new() prevents allocating too large records, by
checking if they're bigger than GHES_ESTATUS_MAX_SIZE (currently, 64KB).
Yet, the allocation is done with the actual number of pages from the
CPER bios table location, which can be smaller.
Yet, a bad firmware could send data with a different size, which might
be bigger than the allocated memory, causing an OOPS:
[13095.899926] Unable to handle kernel paging request at virtual address fff00000f9b40000
[13095.899961] Mem abort info:
[13095.900017] ESR = 0x0000000096000007
[13095.900088] EC = 0x25: DABT (current EL), IL = 32 bits
[13095.900156] SET = 0, FnV = 0
[13095.900181] EA = 0, S1PTW = 0
[13095.900211] FSC = 0x07: level 3 translation fault
[13095.900255] Data abort info:
[13095.900421] ISV = 0, ISS = 0x00000007, ISS2 = 0x00000000
[13095.900486] CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[13095.900525] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[13095.900713] swapper pgtable: 4k pages, 52-bit VAs, pgdp=000000008ba16000
[13095.900752] [fff00000f9b40000] pgd=180000013ffff403, p4d=180000013fffe403, pud=180000013f85b403, pmd=180000013f68d403, pte=0000000000000000
[13095.901312] Internal error: Oops: 0000000096000007 [#1] SMP
[13095.901659] Modules linked in:
[13095.902201] CPU: 0 UID: 0 PID: 303 Comm: kworker/0:1 Not tainted 6.19.0-rc1-00002-gda407d200220 #34 PREEMPT
[13095.902461] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 02/02/2022
[13095.902719] Workqueue: kacpi_notify acpi_os_execute_deferred
[13095.903778] pstate: 214020c5 (nzCv daIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[13095.903892] pc : hex_dump_to_buffer+0x30c/0x4a0
[13095.904146] lr : hex_dump_to_buffer+0x328/0x4a0
[13095.904204] sp : ffff800080e13880
[13095.904291] x29: ffff800080e13880 x28: ffffac9aba86f6a8 x27: 0000000000000083
[13095.904704] x26: fff00000f9b3fffc x25: 0000000000000004 x24: 0000000000000004
[13095.905335] x23: ffff800080e13905 x22: 0000000000000010 x21: 0000000000000083
[13095.905483] x20: 0000000000000001 x19: 0000000000000008 x18: 0000000000000010
[13095.905617] x17: 0000000000000001 x16: 00000007c7f20fec x15: 0000000000000020
[13095.905850] x14: 0000000000000008 x13: 0000000000081020 x12: 0000000000000008
[13095.906175] x11: ffff800080e13905 x10: ffff800080e13988 x9 : 0000000000000000
[13095.906733] x8 : 0000000000000000 x7 : 0000000000000001 x6 : 0000000000000020
[13095.907197] x5 : 0000000000000030 x4 : 00000000fffffffe x3 : 0000000000000000
[13095.907623] x2 : ffffac9aba78c1c8 x1 : ffffac9aba76d0a8 x0 : 0000000000000008
[13095.908284] Call trace:
[13095.908866] hex_dump_to_buffer+0x30c/0x4a0 (P)
[13095.909135] print_hex_dump+0xac/0x170
[13095.909179] cper_estatus_print_section+0x90c/0x968
[13095.909336] cper_estatus_print+0xf0/0x158
[13095.909348] __ghes_print_estatus+0xa0/0x148
[13095.909656] ghes_proc+0x1bc/0x220
[13095.909883] ghes_notify_hed+0x5c/0xb8
[13095.909957] notifier_call_chain+0x78/0x148
[13095.910180] blocking_notifier_call_chain+0x4c/0x80
[13095.910246] acpi_hed_notify+0x28/0x40
[13095.910558] acpi_ev_notify_dispatch+0x50/0x80
[13095.910576] acpi_os_execute_deferred+0x24/0x48
[13095.911161] process_one_work+0x15c/0x3b0
[13095.911326] worker_thread+0x2d0/0x400
[13095.911775] kthread+0x148/0x228
[13095.912082] ret_from_fork+0x10/0x20
[13095.912687] Code: 6b14033f 540001ad a94707e2 f100029f (b8747b44)
[13095.914085] ---[ end trace 0000000000000000 ]---
Prevent that by taking the actual allocated are into account when
checking for CPER length.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
drivers/acpi/apei/ghes.c | 6 +++++-
include/acpi/ghes.h | 1 +
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index fc3f8aed99d5..77ea7a5b761f 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -29,6 +29,7 @@
#include <linux/cper.h>
#include <linux/cleanup.h>
#include <linux/platform_device.h>
+#include <linux/minmax.h>
#include <linux/mutex.h>
#include <linux/ratelimit.h>
#include <linux/vmalloc.h>
@@ -294,6 +295,7 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
error_block_length = GHES_ESTATUS_MAX_SIZE;
}
ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
+ ghes->estatus_length = error_block_length;
if (!ghes->estatus) {
rc = -ENOMEM;
goto err_unmap_status_addr;
@@ -365,13 +367,15 @@ static int __ghes_check_estatus(struct ghes *ghes,
struct acpi_hest_generic_status *estatus)
{
u32 len = cper_estatus_len(estatus);
+ u32 max_len = min(ghes->generic->error_block_length,
+ ghes->estatus_length);
if (len < sizeof(*estatus)) {
pr_warn_ratelimited(FW_WARN GHES_PFX "Truncated error status block!\n");
return -EIO;
}
- if (len > ghes->generic->error_block_length) {
+ if (!len || len > max_len) {
pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid error status block length!\n");
return -EIO;
}
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index ebd21b05fe6e..93db60da5934 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -21,6 +21,7 @@ struct ghes {
struct acpi_hest_generic_v2 *generic_v2;
};
struct acpi_hest_generic_status *estatus;
+ unsigned int estatus_length;
unsigned long flags;
union {
struct list_head list;
--
2.52.0On Wed, 7 Jan 2026 17:41:51 +0100 Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > The logic at ghes_new() prevents allocating too large records, by > checking if they're bigger than GHES_ESTATUS_MAX_SIZE (currently, 64KB). > Yet, the allocation is done with the actual number of pages from the > CPER bios table location, which can be smaller. > > Yet, a bad firmware could send data with a different size, which might > be bigger than the allocated memory, causing an OOPS: > > [13095.899926] Unable to handle kernel paging request at virtual address fff00000f9b40000 Could tidy this up a bit to make for a more readable commit message. Drop timestamps for example. Other than that LGTM. Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com> > [13095.899961] Mem abort info: > [13095.900017] ESR = 0x0000000096000007 > [13095.900088] EC = 0x25: DABT (current EL), IL = 32 bits > [13095.900156] SET = 0, FnV = 0 > [13095.900181] EA = 0, S1PTW = 0 > [13095.900211] FSC = 0x07: level 3 translation fault > [13095.900255] Data abort info: > [13095.900421] ISV = 0, ISS = 0x00000007, ISS2 = 0x00000000 > [13095.900486] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 > [13095.900525] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 > [13095.900713] swapper pgtable: 4k pages, 52-bit VAs, pgdp=000000008ba16000 > [13095.900752] [fff00000f9b40000] pgd=180000013ffff403, p4d=180000013fffe403, pud=180000013f85b403, pmd=180000013f68d403, pte=0000000000000000 > [13095.901312] Internal error: Oops: 0000000096000007 [#1] SMP > [13095.901659] Modules linked in: > [13095.902201] CPU: 0 UID: 0 PID: 303 Comm: kworker/0:1 Not tainted 6.19.0-rc1-00002-gda407d200220 #34 PREEMPT > [13095.902461] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 02/02/2022 > [13095.902719] Workqueue: kacpi_notify acpi_os_execute_deferred > [13095.903778] pstate: 214020c5 (nzCv daIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--) > [13095.903892] pc : hex_dump_to_buffer+0x30c/0x4a0 > [13095.904146] lr : hex_dump_to_buffer+0x328/0x4a0 > [13095.904204] sp : ffff800080e13880 > [13095.904291] x29: ffff800080e13880 x28: ffffac9aba86f6a8 x27: 0000000000000083 > [13095.904704] x26: fff00000f9b3fffc x25: 0000000000000004 x24: 0000000000000004 > [13095.905335] x23: ffff800080e13905 x22: 0000000000000010 x21: 0000000000000083 > [13095.905483] x20: 0000000000000001 x19: 0000000000000008 x18: 0000000000000010 > [13095.905617] x17: 0000000000000001 x16: 00000007c7f20fec x15: 0000000000000020 > [13095.905850] x14: 0000000000000008 x13: 0000000000081020 x12: 0000000000000008 > [13095.906175] x11: ffff800080e13905 x10: ffff800080e13988 x9 : 0000000000000000 > [13095.906733] x8 : 0000000000000000 x7 : 0000000000000001 x6 : 0000000000000020 > [13095.907197] x5 : 0000000000000030 x4 : 00000000fffffffe x3 : 0000000000000000 > [13095.907623] x2 : ffffac9aba78c1c8 x1 : ffffac9aba76d0a8 x0 : 0000000000000008 > [13095.908284] Call trace: > [13095.908866] hex_dump_to_buffer+0x30c/0x4a0 (P) > [13095.909135] print_hex_dump+0xac/0x170 > [13095.909179] cper_estatus_print_section+0x90c/0x968 > [13095.909336] cper_estatus_print+0xf0/0x158 > [13095.909348] __ghes_print_estatus+0xa0/0x148 > [13095.909656] ghes_proc+0x1bc/0x220 > [13095.909883] ghes_notify_hed+0x5c/0xb8 > [13095.909957] notifier_call_chain+0x78/0x148 > [13095.910180] blocking_notifier_call_chain+0x4c/0x80 > [13095.910246] acpi_hed_notify+0x28/0x40 > [13095.910558] acpi_ev_notify_dispatch+0x50/0x80 > [13095.910576] acpi_os_execute_deferred+0x24/0x48 > [13095.911161] process_one_work+0x15c/0x3b0 > [13095.911326] worker_thread+0x2d0/0x400 > [13095.911775] kthread+0x148/0x228 > [13095.912082] ret_from_fork+0x10/0x20 > [13095.912687] Code: 6b14033f 540001ad a94707e2 f100029f (b8747b44) > [13095.914085] ---[ end trace 0000000000000000 ]--- > > Prevent that by taking the actual allocated are into account when > checking for CPER length. > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
© 2016 - 2026 Red Hat, Inc.