| From c10a0f877fe007021d70f9cada240f42adc2b5db Mon Sep 17 00:00:00 2001 |
| From: Lang Yu <lang.yu@amd.com> |
| Date: Thu, 3 Feb 2022 20:49:37 -0800 |
| Subject: mm/kmemleak: avoid scanning potential huge holes |
| |
| From: Lang Yu <lang.yu@amd.com> |
| |
| commit c10a0f877fe007021d70f9cada240f42adc2b5db upstream. |
| |
| When using devm_request_free_mem_region() and devm_memremap_pages() to |
| add ZONE_DEVICE memory, if requested free mem region's end pfn were |
| huge(e.g., 0x400000000), the node_end_pfn() will be also huge (see |
| move_pfn_range_to_zone()). Thus it creates a huge hole between |
| node_start_pfn() and node_end_pfn(). |
| |
| We found on some AMD APUs, amdkfd requested such a free mem region and |
| created a huge hole. In such a case, following code snippet was just |
| doing busy test_bit() looping on the huge hole. |
| |
| for (pfn = start_pfn; pfn < end_pfn; pfn++) { |
| struct page *page = pfn_to_online_page(pfn); |
| if (!page) |
| continue; |
| ... |
| } |
| |
| So we got a soft lockup: |
| |
| watchdog: BUG: soft lockup - CPU#6 stuck for 26s! [bash:1221] |
| CPU: 6 PID: 1221 Comm: bash Not tainted 5.15.0-custom #1 |
| RIP: 0010:pfn_to_online_page+0x5/0xd0 |
| Call Trace: |
| ? kmemleak_scan+0x16a/0x440 |
| kmemleak_write+0x306/0x3a0 |
| ? common_file_perm+0x72/0x170 |
| full_proxy_write+0x5c/0x90 |
| vfs_write+0xb9/0x260 |
| ksys_write+0x67/0xe0 |
| __x64_sys_write+0x1a/0x20 |
| do_syscall_64+0x3b/0xc0 |
| entry_SYSCALL_64_after_hwframe+0x44/0xae |
| |
| I did some tests with the patch. |
| |
| (1) amdgpu module unloaded |
| |
| before the patch: |
| |
| real 0m0.976s |
| user 0m0.000s |
| sys 0m0.968s |
| |
| after the patch: |
| |
| real 0m0.981s |
| user 0m0.000s |
| sys 0m0.973s |
| |
| (2) amdgpu module loaded |
| |
| before the patch: |
| |
| real 0m35.365s |
| user 0m0.000s |
| sys 0m35.354s |
| |
| after the patch: |
| |
| real 0m1.049s |
| user 0m0.000s |
| sys 0m1.042s |
| |
| Link: https://lkml.kernel.org/r/20211108140029.721144-1-lang.yu@amd.com |
| Signed-off-by: Lang Yu <lang.yu@amd.com> |
| Acked-by: David Hildenbrand <david@redhat.com> |
| Acked-by: Catalin Marinas <catalin.marinas@arm.com> |
| Cc: Oscar Salvador <osalvador@suse.de> |
| Cc: <stable@vger.kernel.org> |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| --- |
| mm/kmemleak.c | 13 +++++++------ |
| 1 file changed, 7 insertions(+), 6 deletions(-) |
| |
| --- a/mm/kmemleak.c |
| +++ b/mm/kmemleak.c |
| @@ -1401,7 +1401,8 @@ static void kmemleak_scan(void) |
| { |
| unsigned long flags; |
| struct kmemleak_object *object; |
| - int i; |
| + struct zone *zone; |
| + int __maybe_unused i; |
| int new_leaks = 0; |
| |
| jiffies_last_scan = jiffies; |
| @@ -1441,9 +1442,9 @@ static void kmemleak_scan(void) |
| * Struct page scanning for each node. |
| */ |
| get_online_mems(); |
| - for_each_online_node(i) { |
| - unsigned long start_pfn = node_start_pfn(i); |
| - unsigned long end_pfn = node_end_pfn(i); |
| + for_each_populated_zone(zone) { |
| + unsigned long start_pfn = zone->zone_start_pfn; |
| + unsigned long end_pfn = zone_end_pfn(zone); |
| unsigned long pfn; |
| |
| for (pfn = start_pfn; pfn < end_pfn; pfn++) { |
| @@ -1452,8 +1453,8 @@ static void kmemleak_scan(void) |
| if (!page) |
| continue; |
| |
| - /* only scan pages belonging to this node */ |
| - if (page_to_nid(page) != i) |
| + /* only scan pages belonging to this zone */ |
| + if (page_zone(page) != zone) |
| continue; |
| /* only scan if page is in use */ |
| if (page_count(page) == 0) |