drm/amdgpu/ras: Move ras data alloc before bad page check

In the rare event if eeprom has only invalid address entries,
allocation is skipped, this causes following NULL pointer issue
[  547.103445] BUG: kernel NULL pointer dereference, address: 0000000000000010
[  547.118897] #PF: supervisor read access in kernel mode
[  547.130292] #PF: error_code(0x0000) - not-present page
[  547.141689] PGD 124757067 P4D 0
[  547.148842] Oops: 0000 [#1] PREEMPT SMP NOPTI
[  547.158504] CPU: 49 PID: 8167 Comm: cat Tainted: G           OE      6.8.0-38-generic #38-Ubuntu
[  547.177998] Hardware name: Supermicro AS -8126GS-TNMR/H14DSG-OD, BIOS 1.7 09/12/2025
[  547.195178] RIP: 0010:amdgpu_ras_sysfs_badpages_read+0x2f2/0x5d0 [amdgpu]
[  547.210375] Code: e8 63 78 82 c0 45 31 d2 45 3b 75 08 48 8b 45 a0 73 44 44 89 f1 48 8b 7d 88 48 89 ca 48 c1 e2 05 48 29 ca 49 8b 4d 00 48 01 d1 <48> 83 79 10 00 74 17 49 63 f2 48 8b 49 08 41 83 c2 01 48 8d 34 76
[  547.252045] RSP: 0018:ffa0000067287ac0 EFLAGS: 00010246
[  547.263636] RAX: ff11000167c28130 RBX: ff11000127600000 RCX: 0000000000000000
[  547.279467] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ff11000125b1c800
[  547.295298] RBP: ffa0000067287b50 R08: 0000000000000000 R09: 0000000000000000
[  547.311129] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[  547.326959] R13: ff11000217b1de00 R14: 0000000000000000 R15: 0000000000000092
[  547.342790] FS:  0000746e59d14740(0000) GS:ff11017dfda80000(0000) knlGS:0000000000000000
[  547.360744] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  547.373489] CR2: 0000000000000010 CR3: 000000019585e001 CR4: 0000000000f71ef0
[  547.389321] PKRU: 55555554
[  547.395316] Call Trace:
[  547.400737]  <TASK>
[  547.405386]  ? show_regs+0x6d/0x80
[  547.412929]  ? __die+0x24/0x80
[  547.419697]  ? page_fault_oops+0x99/0x1b0
[  547.428588]  ? do_user_addr_fault+0x2ee/0x6b0
[  547.438249]  ? exc_page_fault+0x83/0x1b0
[  547.446949]  ? asm_exc_page_fault+0x27/0x30
[  547.456225]  ? amdgpu_ras_sysfs_badpages_read+0x2f2/0x5d0 [amdgpu]
[  547.470040]  ? mas_wr_modify+0xcd/0x140
[  547.478548]  sysfs_kf_bin_read+0x63/0xb0
[  547.487248]  kernfs_file_read_iter+0xa1/0x190
[  547.496909]  kernfs_fop_read_iter+0x25/0x40
[  547.506182]  vfs_read+0x255/0x390

This also result in space left assigned to negative values.
Moving data alloc call before bad page check resolves both the issue.

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index d79b41ce21240500538ca4208857445ef7bbf67e..3d51a3c8852ad36938339e8285641847451da459 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3076,6 +3076,11 @@ static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev,
        struct ras_err_handler_data *data = con->eh_data;
 
        for (j = 0; j < count; j++) {
+               if (!data->space_left &&
+                   amdgpu_ras_realloc_eh_data_space(adev, data, 256)) {
+                       return -ENOMEM;
+               }
+
                if (amdgpu_ras_check_bad_page_unlock(con,
                        bps[j].retired_page << AMDGPU_GPU_PAGE_SHIFT)) {
                        data->count++;
@@ -3083,11 +3088,6 @@ static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev,
                        continue;
                }
 
-               if (!data->space_left &&
-                   amdgpu_ras_realloc_eh_data_space(adev, data, 256)) {
-                       return -ENOMEM;
-               }
-
                amdgpu_ras_reserve_page(adev, bps[j].retired_page);
 
                memcpy(&data->bps[data->count], &(bps[j]),