Some drivers (such as rxe) may legitimately call hmm_dma_map_alloc() with a
NULL device pointer, which leads to a NULL pointer dereference. This patch
adds NULL checks to safely bypass device-specific DMA features when no
device is provided.
This fixes the following kernel oops:
BUG: kernel NULL pointer dereference, address: 00000000000002fc
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 1028eb067 P4D 1028eb067 PUD 105da0067 PMD 0
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 3 UID: 1000 PID: 1854 Comm: python3 Tainted: G W 6.15.0-rc1+ #11 PREEMPT(voluntary)
Tainted: [W]=WARN
Hardware name: Trigkey Key N/Key N, BIOS KEYN101 09/02/2024
RIP: 0010:hmm_dma_map_alloc+0x25/0x100
Code: 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 49 89 d6 49 c1 e6 0c 41 55 41 54 53 49 39 ce 0f 82 c6 00 00 00 49 89 fc <f6> 87 fc 02 00 00 20 0f 84 af 00 00 00 49 89 f5 48 89 d3 49 89 cf
RSP: 0018:ffffd3d3420eb830 EFLAGS: 00010246
RAX: 0000000000001000 RBX: ffff8b727c7f7400 RCX: 0000000000001000
RDX: 0000000000000001 RSI: ffff8b727c7f74b0 RDI: 0000000000000000
RBP: ffffd3d3420eb858 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 00007262a622a000 R14: 0000000000001000 R15: ffff8b727c7f74b0
FS: 00007262a62a1080(0000) GS:ffff8b762ac3e000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000002fc CR3: 000000010a1f0004 CR4: 0000000000f72ef0
PKRU: 55555554
Call Trace:
<TASK>
ib_init_umem_odp+0xb6/0x110 [ib_uverbs]
ib_umem_odp_get+0xf0/0x150 [ib_uverbs]
rxe_odp_mr_init_user+0x71/0x170 [rdma_rxe]
rxe_reg_user_mr+0x217/0x2e0 [rdma_rxe]
ib_uverbs_reg_mr+0x19e/0x2e0 [ib_uverbs]
ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xd9/0x150 [ib_uverbs]
ib_uverbs_cmd_verbs+0xd19/0xee0 [ib_uverbs]
? mmap_region+0x63/0xd0
? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs]
ib_uverbs_ioctl+0xba/0x130 [ib_uverbs]
__x64_sys_ioctl+0xa4/0xe0
x64_sys_call+0x1178/0x2660
do_syscall_64+0x7e/0x170
? syscall_exit_to_user_mode+0x4e/0x250
? do_syscall_64+0x8a/0x170
? do_syscall_64+0x8a/0x170
? syscall_exit_to_user_mode+0x4e/0x250
? do_syscall_64+0x8a/0x170
? syscall_exit_to_user_mode+0x4e/0x250
? do_syscall_64+0x8a/0x170
? do_user_addr_fault+0x1d2/0x8d0
? irqentry_exit_to_user_mode+0x43/0x250
? irqentry_exit+0x43/0x50
? exc_page_fault+0x93/0x1d0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7262a6124ded
Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1a 48 8b 45 c8 64 48 2b 04 25 28 00 00 00
RSP: 002b:00007fffd08c3960 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007fffd08c39f0 RCX: 00007262a6124ded
RDX: 00007fffd08c3a10 RSI: 00000000c0181b01 RDI: 0000000000000007
RBP: 00007fffd08c39b0 R08: 0000000014107820 R09: 00007fffd08c3b44
R10: 000000000000000c R11: 0000000000000246 R12: 00007fffd08c3b44
R13: 000000000000000c R14: 00007fffd08c3b58 R15: 0000000014107960
</TASK>
Fixes: 1efe8c0670d6 ("RDMA/core: Convert UMEM ODP DMA mapping to caching IOVA and page linkage")
Closes: https://lore.kernel.org/all/3e8f343f-7d66-4f7a-9f08-3910623e322f@xxxxxxxxx/
Signed-off-by: Daisuke Matsuda <dskmtsd@xxxxxxxxx>
---
mm/hmm.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/mm/hmm.c b/mm/hmm.c
index a8bf097677f3..311141124e67 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -638,7 +638,7 @@ int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map,
size_t nr_entries, size_t dma_entry_size)
{
bool dma_need_sync = false;
- bool use_iova;
+ bool use_iova = false;
if (!(nr_entries * PAGE_SIZE / dma_entry_size))
return -EINVAL;
@@ -649,9 +649,9 @@ int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map,
* best approximation to ensure no swiotlb buffering happens.
*/
#ifdef CONFIG_DMA_NEED_SYNC
- dma_need_sync = !dev->dma_skip_sync;
+ dma_need_sync = dev ? !dev->dma_skip_sync : false;
#endif /* CONFIG_DMA_NEED_SYNC */
- if (dma_need_sync || dma_addressing_limited(dev))
+ if (dev && (dma_need_sync || dma_addressing_limited(dev)))
return -EOPNOTSUPP;
map->dma_entry_size = dma_entry_size;
@@ -660,9 +660,11 @@ int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map,
if (!map->pfn_list)
return -ENOMEM;
- use_iova = dma_iova_try_alloc(dev, &map->state, 0,
- nr_entries * PAGE_SIZE);
- if (!use_iova && dma_need_unmap(dev)) {
+ if (dev)
+ use_iova = dma_iova_try_alloc(dev, &map->state, 0,
+ nr_entries * PAGE_SIZE);
+
+ if (!dev || (!use_iova && dma_need_unmap(dev))) {
map->dma_list = kvcalloc(nr_entries, sizeof(*map->dma_list),
GFP_KERNEL | __GFP_NOWARN);
if (!map->dma_list)
--
2.43.0
