[PATCH AUTOSEL 5.4 49/57] drm/amdkfd: Fix cat debugfs hang_hws file causes system crash bug

From: Sasha Levin
Date: Mon May 03 2021 - 12:57:33 EST


From: Qu Huang <jinsdb@xxxxxxx>

[ Upstream commit d73610211eec8aa027850982b1a48980aa1bc96e ]

Here is the system crash log:
[ 1272.884438] BUG: unable to handle kernel NULL pointer dereference at
(null)
[ 1272.884444] IP: [< (null)>] (null)
[ 1272.884447] PGD 825b09067 PUD 8267c8067 PMD 0
[ 1272.884452] Oops: 0010 [#1] SMP
[ 1272.884509] CPU: 13 PID: 3485 Comm: cat Kdump: loaded Tainted: G
[ 1272.884515] task: ffff9a38dbd4d140 ti: ffff9a37cd3b8000 task.ti:
ffff9a37cd3b8000
[ 1272.884517] RIP: 0010:[<0000000000000000>] [< (null)>]
(null)
[ 1272.884520] RSP: 0018:ffff9a37cd3bbe68 EFLAGS: 00010203
[ 1272.884522] RAX: 0000000000000000 RBX: 0000000000000000 RCX:
0000000000014d5f
[ 1272.884524] RDX: fffffffffffffff4 RSI: 0000000000000001 RDI:
ffff9a38aca4d200
[ 1272.884526] RBP: ffff9a37cd3bbed0 R08: ffff9a38dcd5f1a0 R09:
ffff9a31ffc07300
[ 1272.884527] R10: ffff9a31ffc07300 R11: ffffffffaddd5e9d R12:
ffff9a38b4e0fb00
[ 1272.884529] R13: 0000000000000001 R14: ffff9a37cd3bbf18 R15:
ffff9a38aca4d200
[ 1272.884532] FS: 00007feccaa67740(0000) GS:ffff9a38dcd40000(0000)
knlGS:0000000000000000
[ 1272.884534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1272.884536] CR2: 0000000000000000 CR3: 00000008267c0000 CR4:
00000000003407e0
[ 1272.884537] Call Trace:
[ 1272.884544] [<ffffffffade68940>] ? seq_read+0x130/0x440
[ 1272.884548] [<ffffffffade40f8f>] vfs_read+0x9f/0x170
[ 1272.884552] [<ffffffffade41e4f>] SyS_read+0x7f/0xf0
[ 1272.884557] [<ffffffffae374ddb>] system_call_fastpath+0x22/0x27
[ 1272.884558] Code: Bad RIP value.
[ 1272.884562] RIP [< (null)>] (null)
[ 1272.884564] RSP <ffff9a37cd3bbe68>
[ 1272.884566] CR2: 0000000000000000

Signed-off-by: Qu Huang <jinsdb@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 511712c2e382..673d5e34f213 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -33,6 +33,11 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file)

return single_open(file, show, NULL);
}
+static int kfd_debugfs_hang_hws_read(struct seq_file *m, void *data)
+{
+ seq_printf(m, "echo gpu_id > hang_hws\n");
+ return 0;
+}

static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
const char __user *user_buf, size_t size, loff_t *ppos)
@@ -94,7 +99,7 @@ void kfd_debugfs_init(void)
debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
kfd_debugfs_rls_by_device, &kfd_debugfs_fops);
debugfs_create_file("hang_hws", S_IFREG | 0200, debugfs_root,
- NULL, &kfd_debugfs_hang_hws_fops);
+ kfd_debugfs_hang_hws_read, &kfd_debugfs_hang_hws_fops);
}

void kfd_debugfs_fini(void)
--
2.30.2