APEI/GHES: ensure that won't go past CPER allocated record

[ Upstream commit fa2408a ]

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:

    Unable to handle kernel paging request at virtual address fff00000f9b40000
    Mem abort info:
      ESR = 0x0000000096000007
      EC = 0x25: DABT (current EL), IL = 32 bits
      SET = 0, FnV = 0
      EA = 0, S1PTW = 0
      FSC = 0x07: level 3 translation fault
    Data abort info:
      ISV = 0, ISS = 0x00000007, ISS2 = 0x00000000
      CM = 0, WnR = 0, TnD = 0, TagAccess = 0
      GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
    swapper pgtable: 4k pages, 52-bit VAs, pgdp=000000008ba16000
    [fff00000f9b40000] pgd=180000013ffff403, p4d=180000013fffe403, pud=180000013f85b403, pmd=180000013f68d403, pte=0000000000000000
    Internal error: Oops: 0000000096000007 [#1]  SMP
    Modules linked in:
    CPU: 0 UID: 0 PID: 303 Comm: kworker/0:1 Not tainted 6.19.0-rc1-00002-gda407d200220 #34 PREEMPT
    Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 02/02/2022
    Workqueue: kacpi_notify acpi_os_execute_deferred
    pstate: 214020c5 (nzCv daIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
    pc : hex_dump_to_buffer+0x30c/0x4a0
    lr : hex_dump_to_buffer+0x328/0x4a0
    sp : ffff800080e13880
    x29: ffff800080e13880 x28: ffffac9aba86f6a8 x27: 0000000000000083
    x26: fff00000f9b3fffc x25: 0000000000000004 x24: 0000000000000004
    x23: ffff800080e13905 x22: 0000000000000010 x21: 0000000000000083
    x20: 0000000000000001 x19: 0000000000000008 x18: 0000000000000010
    x17: 0000000000000001 x16: 00000007c7f20fec x15: 0000000000000020
    x14: 0000000000000008 x13: 0000000000081020 x12: 0000000000000008
    x11: ffff800080e13905 x10: ffff800080e13988 x9 : 0000000000000000
    x8 : 0000000000000000 x7 : 0000000000000001 x6 : 0000000000000020
    x5 : 0000000000000030 x4 : 00000000fffffffe x3 : 0000000000000000
    x2 : ffffac9aba78c1c8 x1 : ffffac9aba76d0a8 x0 : 0000000000000008
    Call trace:
     hex_dump_to_buffer+0x30c/0x4a0 (P)
     print_hex_dump+0xac/0x170
     cper_estatus_print_section+0x90c/0x968
     cper_estatus_print+0xf0/0x158
     __ghes_print_estatus+0xa0/0x148
     ghes_proc+0x1bc/0x220
     ghes_notify_hed+0x5c/0xb8
     notifier_call_chain+0x78/0x148
     blocking_notifier_call_chain+0x4c/0x80
     acpi_hed_notify+0x28/0x40
     acpi_ev_notify_dispatch+0x50/0x80
     acpi_os_execute_deferred+0x24/0x48
     process_one_work+0x15c/0x3b0
     worker_thread+0x2d0/0x400
     kthread+0x148/0x228
     ret_from_fork+0x10/0x20
    Code: 6b14033f 540001ad a94707e2 f100029f (b8747b44)
    ---[ 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>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
[ rjw: Subject tweaks ]
Link: https://patch.msgid.link/4e70310a816577fabf37d94ed36cde4ad62b1e0a.1767871950.git.mchehab+huawei@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

Author: mchehab

drivers/acpi/apei/ghes.c

@@ -28,6 +28,7 @@
 #include <linux/timer.h>
 #include <linux/cper.h>
 #include <linux/platform_device.h>
+#include <linux/minmax.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
@@ -290,6 +291,7 @@ 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;
@@ -361,13 +363,15 @@ 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;
 	}

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;