mm, slub: prevent VM_BUG_ON in PageSlabPfmemalloc from ___slab_alloc

Clark Williams reported [1] a VM_BUG_ON in PageSlabPfmemalloc:

 page:000000009ac5dd73 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1ab3db
 flags: 0x17ffffc0000000(node=0|zone=2|lastcpupid=0x1fffff)
 raw: 0017ffffc0000000 ffffee1286aceb88 ffffee1287b66288 0000000000000000
 raw: 0000000000000000 0000000000100000 00000000ffffffff 0000000000000000
 page dumped because: VM_BUG_ON_PAGE(!PageSlab(page))
 ------------[ cut here ]------------
 kernel BUG at include/linux/page-flags.h:814!
 invalid opcode: 0000 [#1] PREEMPT_RT SMP PTI
 CPU: 3 PID: 12345 Comm: hackbench Not tainted 5.14.0-rc5-rt8+ #12
 Hardware name:  /NUC5i7RYB, BIOS RYBDWi35.86A.0359.2016.0906.1028 09/06/2016
 RIP: 0010:___slab_alloc+0x340/0x940
 Code: c6 48 0f a3 05 b1 7b 57 03 72 99 c7 85 78 ff ff ff ff ff ff ff 48 8b 7d 88 e9 8d fd ff ff 48 c7 c6 50 5a 7c b0 e>
 RSP: 0018:ffffba1c4a8b7ab0 EFLAGS: 00010293
 RAX: 0000000000000000 RBX: 0000000000000002 RCX: ffff9bb765118000
 RDX: 0000000000000000 RSI: ffffffffaf426050 RDI: 00000000ffffffff
 RBP: ffffba1c4a8b7b70 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9bb7410d3600
 R13: 0000000000400cc0 R14: 00000000001f7770 R15: ffff9bbe76df7770
 FS:  00007f474b1be740(0000) GS:ffff9bbe76c00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f60c04bdaf8 CR3: 0000000124f3a003 CR4: 00000000003706e0
 Call Trace:
  ? __alloc_skb+0x1db/0x270
  ? __alloc_skb+0x1db/0x270
  ? kmem_cache_alloc_node+0xa4/0x2b0
  kmem_cache_alloc_node+0xa4/0x2b0
  __alloc_skb+0x1db/0x270
  alloc_skb_with_frags+0x64/0x250
  sock_alloc_send_pskb+0x260/0x2b0
  ? bpf_lsm_socket_getpeersec_dgram+0xa/0x10
  unix_stream_sendmsg+0x27c/0x550
  ? unix_seqpacket_recvmsg+0x60/0x60
  sock_sendmsg+0xbd/0xd0
  sock_write_iter+0xb9/0x120
  new_sync_write+0x175/0x200
  vfs_write+0x3c4/0x510
  ksys_write+0xc9/0x110
  do_syscall_64+0x3b/0x90
  entry_SYSCALL_64_after_hwframe+0x44/0xae

The problem is that we are opportunistically checking flags on a page in
irq enabled section.  If we are interrupted and the page is freed, it's
not an issue as we detect it after disabling irqs.  But on kernels with
CONFIG_DEBUG_VM.  The check for PageSlab flag in PageSlabPfmemalloc() can
fail.

Fix this by creating an "unsafe" version of the check that doesn't check
PageSlab.

[1] https://lore.kernel.org/lkml/20210812151803.52f84aaf@theseus.lan/

Link: https://lkml.kernel.org/r/f4756ee5-a7e9-ab02-3aba-1355f77b7c79@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Clark Williams <williams@redhat.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5922031ffab6e533e34ab81a72b1920a6849bee2..7fda4fb85bdcab0cbd3e306fcb4cc539577233c8 100644 (file)
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -815,6 +815,15 @@ static inline int PageSlabPfmemalloc(struct page *page)
        return PageActive(page);
 }
 
+/*
+ * A version of PageSlabPfmemalloc() for opportunistic checks where the page
+ * might have been freed under us and not be a PageSlab anymore.
+ */
+static inline int __PageSlabPfmemalloc(struct page *page)
+{
+       return PageActive(page);
+}
+
 static inline void SetPageSlabPfmemalloc(struct page *page)
 {
        VM_BUG_ON_PAGE(!PageSlab(page), page);

diff --git a/mm/slub.c b/mm/slub.c
index d1d39135d9f9999d14c6e6831a2764dc3aededc6..38458e347810322016ef1d3f1e4f696c0a84a6fd 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2606,6 +2606,19 @@ static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
        return true;
 }
 
+/*
+ * A variant of pfmemalloc_match() that tests page flags without asserting
+ * PageSlab. Intended for opportunistic checks before taking a lock and
+ * rechecking that nobody else freed the page under us.
+ */
+static inline bool pfmemalloc_match_unsafe(struct page *page, gfp_t gfpflags)
+{
+       if (unlikely(__PageSlabPfmemalloc(page)))
+               return gfp_pfmemalloc_allowed(gfpflags);
+
+       return true;
+}
+
 /*
  * Check the page->freelist of a page and either transfer the freelist to the
  * per cpu freelist or deactivate the page.
@@ -2707,7 +2720,7 @@ redo:
         * PFMEMALLOC but right now, we are losing the pfmemalloc
         * information when the page leaves the per-cpu allocator
         */
-       if (unlikely(!pfmemalloc_match(page, gfpflags)))
+       if (unlikely(!try_pfmemalloc_match(page, gfpflags)))
                goto deactivate_slab;
 
        /* must check again c->page in case IRQ handler changed it */