* [PATCH V1] accel/amdxdna: Skip unmapped range in aie2_populate_range()
@ 2026-08-12 20:56 Lizhi Hou
2026-08-12 21:26 ` Max Zhen
0 siblings, 1 reply; 3+ messages in thread
From: Lizhi Hou @ 2026-08-12 20:56 UTC (permalink / raw)
To: ogabbay, quic_jhugo, dri-devel, mario.limonciello, karol.wachowski
Cc: Lizhi Hou, linux-kernel, max.zhen, sonal.santan
aie2_populate_range() incorrectly failed jobs for BOs with multiple
mmaps: if the unmapped entry appeared first in umap_list, the loop would
pick it up, call hmm_range_fault() on a gone VMA, and return -EFAULT
without ever trying the remaining valid mapps.
Fix it by skipping unmapped entries. After the loop, if the map list is
empty or all maps are valid, map_invalid can be cleared normally.
Fixes: e486147c912f ("accel/amdxdna: Add BO import and export")
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
---
drivers/accel/amdxdna/aie2_ctx.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 4b3a62aa8798..8d9c283f606a 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -1052,6 +1052,16 @@ static int aie2_populate_range(struct amdxdna_gem_obj *abo)
found = false;
down_write(&xdna->notifier_lock);
list_for_each_entry(mapp, &abo->mem.umap_list, node) {
+ /*
+ * Skip entries that have already been unmapped.
+ *
+ * If userspace unmaps the address and later submits I/O using
+ * it, the IOMMU will reject the access and report a fault.
+ * Ignore such entries here.
+ */
+ if (mapp->unmapped)
+ continue;
+
if (mapp->invalid && kref_get_unless_zero(&mapp->refcnt)) {
found = true;
break;
@@ -1059,6 +1069,12 @@ static int aie2_populate_range(struct amdxdna_gem_obj *abo)
}
if (!found) {
+ /*
+ * This also covers the case where all mappings have been
+ * removed. There are no invalid mappings left to process.
+ * Any subsequent I/O using the unmapped address will be
+ * rejected by the IOMMU.
+ */
abo->mem.map_invalid = false;
up_write(&xdna->notifier_lock);
return 0;
--
2.34.1
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH V1] accel/amdxdna: Skip unmapped range in aie2_populate_range()
2026-08-12 20:56 [PATCH V1] accel/amdxdna: Skip unmapped range in aie2_populate_range() Lizhi Hou
@ 2026-08-12 21:26 ` Max Zhen
2026-08-13 6:17 ` Lizhi Hou
0 siblings, 1 reply; 3+ messages in thread
From: Max Zhen @ 2026-08-12 21:26 UTC (permalink / raw)
To: Lizhi Hou, ogabbay, quic_jhugo, dri-devel, mario.limonciello,
karol.wachowski
Cc: linux-kernel, sonal.santan
On 8/12/2026 Wed 13:56, Lizhi Hou wrote:
> aie2_populate_range() incorrectly failed jobs for BOs with multiple
> mmaps: if the unmapped entry appeared first in umap_list, the loop would
> pick it up, call hmm_range_fault() on a gone VMA, and return -EFAULT
> without ever trying the remaining valid mapps.
>
> Fix it by skipping unmapped entries. After the loop, if the map list is
> empty or all maps are valid, map_invalid can be cleared normally.
>
> Fixes: e486147c912f ("accel/amdxdna: Add BO import and export")
> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Max Zhen <max.zhen@amd.com>
> ---
> drivers/accel/amdxdna/aie2_ctx.c | 16 ++++++++++++++++
> 1 file changed, 16 insertions(+)
>
> diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
> index 4b3a62aa8798..8d9c283f606a 100644
> --- a/drivers/accel/amdxdna/aie2_ctx.c
> +++ b/drivers/accel/amdxdna/aie2_ctx.c
> @@ -1052,6 +1052,16 @@ static int aie2_populate_range(struct amdxdna_gem_obj *abo)
> found = false;
> down_write(&xdna->notifier_lock);
> list_for_each_entry(mapp, &abo->mem.umap_list, node) {
> + /*
> + * Skip entries that have already been unmapped.
> + *
> + * If userspace unmaps the address and later submits I/O using
> + * it, the IOMMU will reject the access and report a fault.
> + * Ignore such entries here.
> + */
> + if (mapp->unmapped)
> + continue;
> +
> if (mapp->invalid && kref_get_unless_zero(&mapp->refcnt)) {
> found = true;
> break;
> @@ -1059,6 +1069,12 @@ static int aie2_populate_range(struct amdxdna_gem_obj *abo)
> }
>
> if (!found) {
> + /*
> + * This also covers the case where all mappings have been
> + * removed. There are no invalid mappings left to process.
> + * Any subsequent I/O using the unmapped address will be
> + * rejected by the IOMMU.
> + */
> abo->mem.map_invalid = false;
> up_write(&xdna->notifier_lock);
> return 0;
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH V1] accel/amdxdna: Skip unmapped range in aie2_populate_range()
2026-08-12 21:26 ` Max Zhen
@ 2026-08-13 6:17 ` Lizhi Hou
0 siblings, 0 replies; 3+ messages in thread
From: Lizhi Hou @ 2026-08-13 6:17 UTC (permalink / raw)
To: Max Zhen, ogabbay, quic_jhugo, dri-devel, mario.limonciello,
karol.wachowski
Cc: linux-kernel, sonal.santan
Applied to drm-misc-fixes
On 8/12/26 14:26, Max Zhen wrote:
>
>
> On 8/12/2026 Wed 13:56, Lizhi Hou wrote:
>> aie2_populate_range() incorrectly failed jobs for BOs with multiple
>> mmaps: if the unmapped entry appeared first in umap_list, the loop would
>> pick it up, call hmm_range_fault() on a gone VMA, and return -EFAULT
>> without ever trying the remaining valid mapps.
>>
>> Fix it by skipping unmapped entries. After the loop, if the map list is
>> empty or all maps are valid, map_invalid can be cleared normally.
>>
>> Fixes: e486147c912f ("accel/amdxdna: Add BO import and export")
>> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
> Reviewed-by: Max Zhen <max.zhen@amd.com>
>> ---
>> drivers/accel/amdxdna/aie2_ctx.c | 16 ++++++++++++++++
>> 1 file changed, 16 insertions(+)
>>
>> diff --git a/drivers/accel/amdxdna/aie2_ctx.c
>> b/drivers/accel/amdxdna/aie2_ctx.c
>> index 4b3a62aa8798..8d9c283f606a 100644
>> --- a/drivers/accel/amdxdna/aie2_ctx.c
>> +++ b/drivers/accel/amdxdna/aie2_ctx.c
>> @@ -1052,6 +1052,16 @@ static int aie2_populate_range(struct
>> amdxdna_gem_obj *abo)
>> found = false;
>> down_write(&xdna->notifier_lock);
>> list_for_each_entry(mapp, &abo->mem.umap_list, node) {
>> + /*
>> + * Skip entries that have already been unmapped.
>> + *
>> + * If userspace unmaps the address and later submits I/O using
>> + * it, the IOMMU will reject the access and report a fault.
>> + * Ignore such entries here.
>> + */
>> + if (mapp->unmapped)
>> + continue;
>> +
>> if (mapp->invalid && kref_get_unless_zero(&mapp->refcnt)) {
>> found = true;
>> break;
>> @@ -1059,6 +1069,12 @@ static int aie2_populate_range(struct
>> amdxdna_gem_obj *abo)
>> }
>> if (!found) {
>> + /*
>> + * This also covers the case where all mappings have been
>> + * removed. There are no invalid mappings left to process.
>> + * Any subsequent I/O using the unmapped address will be
>> + * rejected by the IOMMU.
>> + */
>> abo->mem.map_invalid = false;
>> up_write(&xdna->notifier_lock);
>> return 0;
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-08-13 6:17 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-08-12 20:56 [PATCH V1] accel/amdxdna: Skip unmapped range in aie2_populate_range() Lizhi Hou
2026-08-12 21:26 ` Max Zhen
2026-08-13 6:17 ` Lizhi Hou
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®