From: Kairui Song kasong@tencent.com
mainline inclusion from mainline-v6.12 commit 0ec8bc9e880eb576dc4492e8e0c7153ed0a71031 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBC5I1
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
There are two flags used to synchronize allocation and scanning with swapoff: SWP_WRITEOK and SWP_SCANNING.
SWP_WRITEOK: Swapoff will first unset this flag, at this point any further swap allocation or scanning on this device should just abort so no more new entries will be referencing this device. Swapoff will then unuse all existing swap entries.
SWP_SCANNING: This flag is set when device is being scanned. Swapoff will wait for all scanner to stop before the final release of the swap device structures to avoid UAF. Note this flag is the highest used bit of si->flags so it could be added up arithmetically, if there are multiple scanner.
commit 5f843a9a3a1e ("mm: swap: separate SSD allocation from scan_swap_map_slots()") ignored SWP_SCANNING and SWP_WRITEOK flags while separating cluster allocation path from the old allocation path. Add the flags back to fix swapoff race. The race is hard to trigger as si->lock prevents most parallel operations, but si->lock could be dropped for reclaim or discard. This issue is found during code review.
This commit fixes this problem. For SWP_SCANNING, Just like before, set the flag before scan and remove it afterwards.
For SWP_WRITEOK, there are several places where si->lock could be dropped, it will be error-prone and make the code hard to follow if we try to cover these places one by one. So just do one check before the real allocation, which is also very similar like before. With new cluster allocator it may waste a bit of time iterating the clusters but won't take long, and swapoff is not performance sensitive.
Link: https://lkml.kernel.org/r/20241112083414.78174-1-ryncsn@gmail.com Fixes: 5f843a9a3a1e ("mm: swap: separate SSD allocation from scan_swap_map_slots()") Reported-by: "Huang, Ying" ying.huang@intel.com Closes: https://lore.kernel.org/linux-mm/87a5es3f1f.fsf@yhuang6-desk2.ccr.corp.intel... Signed-off-by: Kairui Song kasong@tencent.com Cc: Barry Song v-songbaohua@oppo.com Cc: Chris Li chrisl@kernel.org Cc: Hugh Dickins hughd@google.com Cc: Kalesh Singh kaleshsingh@google.com Cc: Ryan Roberts ryan.roberts@arm.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Liu Shixin liushixin2@huawei.com --- mm/swapfile.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c index 389e14f0fc3c..e620040b9181 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -643,12 +643,15 @@ static bool cluster_scan_range(struct swap_info_struct *si, return true; }
-static void cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, +static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order;
+ if (!(si->flags & SWP_WRITEOK)) + return false; + if (cluster_is_free(ci)) { if (nr_pages < SWAPFILE_CLUSTER) { list_move_tail(&ci->list, &si->nonfull_clusters[order]); @@ -669,6 +672,8 @@ static void cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster list_move_tail(&ci->list, &si->full_clusters); ci->flags = CLUSTER_FLAG_FULL; } + + return true; }
static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset, @@ -692,7 +697,10 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigne
while (offset <= end) { if (cluster_scan_range(si, ci, offset, nr_pages)) { - cluster_alloc_range(si, ci, offset, usage, order); + if (!cluster_alloc_range(si, ci, offset, usage, order)) { + offset = SWAP_NEXT_INVALID; + goto done; + } *foundp = offset; if (ci->count == SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; @@ -775,7 +783,11 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o if (!list_empty(&si->free_clusters)) { ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); - VM_BUG_ON(!found); + /* + * Either we didn't touch the cluster due to swapoff, + * or the allocation must success. + */ + VM_BUG_ON((si->flags & SWP_WRITEOK) && !found); goto done; }
@@ -997,6 +1009,8 @@ static int cluster_alloc_swap(struct swap_info_struct *si,
VM_BUG_ON(!si->cluster_info);
+ si->flags += SWP_SCANNING; + while (n_ret < nr) { unsigned long offset = cluster_alloc_swap_entry(si, order, usage);
@@ -1005,6 +1019,8 @@ static int cluster_alloc_swap(struct swap_info_struct *si, slots[n_ret++] = swp_entry(si->type, offset); }
+ si->flags -= SWP_SCANNING; + return n_ret; }