| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| A vulnerability was found in Tsinghua Unigroup Electronic Archives System 3.2.210802(62532). The affected element is an unknown function of the file /Using/Subject/downLoad.html. Performing a manipulation of the argument path results in path traversal. The attack may be initiated remotely. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way. |
| InvoicePlane is a self-hosted open source application for managing invoices, clients, and payments. A Stored Cross-Site Scripting (XSS) vulnerability exists in InvoicePlane (latest version) that allows an authenticated user with permissions to manage Invoice Groups to inject malicious JavaScript into the "Identifier Format" field. This script executes when any user views the invoice list or the main dashboard. Version 1.7.1 patches the issue. |
| Orthanc versions before 1.12.10 are affected by an authorisation logic flaw in the application's HTTP Basic Authentication implementation.
Successful exploitation could result in Privilege Escalation, potentially allowing full administrative access. |
| InvoicePlane is a self-hosted open source application for managing invoices, clients, and payments. A Stored Cross-Site Scripting (XSS) vulnerability exists in InvoicePlane 1.7.0 via the Product Unit Name fields. An authenticated administrator can inject malicious JavaScript that executes when any administrator views an invoice containing a product with the malicious unit. Version 1.7.1 patches the issue. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: client: split cached_fid bitfields to avoid shared-byte RMW races
is_open, has_lease and on_list are stored in the same bitfield byte in
struct cached_fid but are updated in different code paths that may run
concurrently. Bitfield assignments generate byte read–modify–write
operations (e.g. `orb $mask, addr` on x86_64), so updating one flag can
restore stale values of the others.
A possible interleaving is:
CPU1: load old byte (has_lease=1, on_list=1)
CPU2: clear both flags (store 0)
CPU1: RMW store (old | IS_OPEN) -> reintroduces cleared bits
To avoid this class of races, convert these flags to separate bool
fields. |
| In the Linux kernel, the following vulnerability has been resolved:
crypto: virtio - Add spinlock protection with virtqueue notification
When VM boots with one virtio-crypto PCI device and builtin backend,
run openssl benchmark command with multiple processes, such as
openssl speed -evp aes-128-cbc -engine afalg -seconds 10 -multi 32
openssl processes will hangup and there is error reported like this:
virtio_crypto virtio0: dataq.0:id 3 is not a head!
It seems that the data virtqueue need protection when it is handled
for virtio done notification. If the spinlock protection is added
in virtcrypto_done_task(), openssl benchmark with multiple processes
works well. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: server: fix leak of active_num_conn in ksmbd_tcp_new_connection()
On kthread_run() failure in ksmbd_tcp_new_connection(), the transport is
freed via free_transport(), which does not decrement active_num_conn,
leaking this counter.
Replace free_transport() with ksmbd_tcp_disconnect(). |
| In the Linux kernel, the following vulnerability has been resolved:
crypto: omap - Allocate OMAP_CRYPTO_FORCE_COPY scatterlists correctly
The existing allocation of scatterlists in omap_crypto_copy_sg_lists()
was allocating an array of scatterlist pointers, not scatterlist objects,
resulting in a 4x too small allocation.
Use sizeof(*new_sg) to get the correct object size. |
| In the Linux kernel, the following vulnerability has been resolved:
bus: fsl-mc: fix use-after-free in driver_override_show()
The driver_override_show() function reads the driver_override string
without holding the device_lock. However, driver_override_store() uses
driver_set_override(), which modifies and frees the string while holding
the device_lock.
This can result in a concurrent use-after-free if the string is freed
by the store function while being read by the show function.
Fix this by holding the device_lock around the read operation. |
| In the Linux kernel, the following vulnerability has been resolved:
mptcp: fix race in mptcp_pm_nl_flush_addrs_doit()
syzbot and Eulgyu Kim reported crashes in mptcp_pm_nl_get_local_id()
and/or mptcp_pm_nl_is_backup()
Root cause is list_splice_init() in mptcp_pm_nl_flush_addrs_doit()
which is not RCU ready.
list_splice_init_rcu() can not be called here while holding pernet->lock
spinlock.
Many thanks to Eulgyu Kim for providing a repro and testing our patches. |
| In the Linux kernel, the following vulnerability has been resolved:
mm/hugetlb: fix hugetlb_pmd_shared()
Patch series "mm/hugetlb: fixes for PMD table sharing (incl. using
mmu_gather)", v3.
One functional fix, one performance regression fix, and two related
comment fixes.
I cleaned up my prototype I recently shared [1] for the performance fix,
deferring most of the cleanups I had in the prototype to a later point.
While doing that I identified the other things.
The goal of this patch set is to be backported to stable trees "fairly"
easily. At least patch #1 and #4.
Patch #1 fixes hugetlb_pmd_shared() not detecting any sharing
Patch #2 + #3 are simple comment fixes that patch #4 interacts with.
Patch #4 is a fix for the reported performance regression due to excessive
IPI broadcasts during fork()+exit().
The last patch is all about TLB flushes, IPIs and mmu_gather.
Read: complicated
There are plenty of cleanups in the future to be had + one reasonable
optimization on x86. But that's all out of scope for this series.
Runtime tested, with a focus on fixing the performance regression using
the original reproducer [2] on x86.
This patch (of 4):
We switched from (wrongly) using the page count to an independent shared
count. Now, shared page tables have a refcount of 1 (excluding
speculative references) and instead use ptdesc->pt_share_count to identify
sharing.
We didn't convert hugetlb_pmd_shared(), so right now, we would never
detect a shared PMD table as such, because sharing/unsharing no longer
touches the refcount of a PMD table.
Page migration, like mbind() or migrate_pages() would allow for migrating
folios mapped into such shared PMD tables, even though the folios are not
exclusive. In smaps we would account them as "private" although they are
"shared", and we would be wrongly setting the PM_MMAP_EXCLUSIVE in the
pagemap interface.
Fix it by properly using ptdesc_pmd_is_shared() in hugetlb_pmd_shared(). |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| In the Linux kernel, the following vulnerability has been resolved:
nilfs2: Fix potential block overflow that cause system hang
When a user executes the FITRIM command, an underflow can occur when
calculating nblocks if end_block is too small. Since nblocks is of
type sector_t, which is u64, a negative nblocks value will become a
very large positive integer. This ultimately leads to the block layer
function __blkdev_issue_discard() taking an excessively long time to
process the bio chain, and the ns_segctor_sem lock remains held for a
long period. This prevents other tasks from acquiring the ns_segctor_sem
lock, resulting in the hang reported by syzbot in [1].
If the ending block is too small, typically if it is smaller than 4KiB
range, depending on the usage of the segment 0, it may be possible to
attempt a discard request beyond the device size causing the hang.
Exiting successfully and assign the discarded size (0 in this case)
to range->len.
Although the start and len values in the user input range are too small,
a conservative strategy is adopted here to safely ignore them, which is
equivalent to a no-op; it will not perform any trimming and will not
throw an error.
[1]
task:segctord state:D stack:28968 pid:6093 tgid:6093 ppid:2 task_flags:0x200040 flags:0x00080000
Call Trace:
rwbase_write_lock+0x3dd/0x750 kernel/locking/rwbase_rt.c:272
nilfs_transaction_lock+0x253/0x4c0 fs/nilfs2/segment.c:357
nilfs_segctor_thread_construct fs/nilfs2/segment.c:2569 [inline]
nilfs_segctor_thread+0x6ec/0xe00 fs/nilfs2/segment.c:2684
[ryusuke: corrected part of the commit message about the consequences] |
| In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Validate sp before freeing associated memory
System crash with the following signature
[154563.214890] nvme nvme2: NVME-FC{1}: controller connect complete
[154564.169363] qla2xxx [0000:b0:00.1]-3002:2: nvme: Sched: Set ZIO exchange threshold to 3.
[154564.169405] qla2xxx [0000:b0:00.1]-ffffff:2: SET ZIO Activity exchange threshold to 5.
[154565.539974] qla2xxx [0000:b0:00.1]-5013:2: RSCN database changed – 0078 0080 0000.
[154565.545744] qla2xxx [0000:b0:00.1]-5013:2: RSCN database changed – 0078 00a0 0000.
[154565.545857] qla2xxx [0000:b0:00.1]-11a2:2: FEC=enabled (data rate).
[154565.552760] qla2xxx [0000:b0:00.1]-11a2:2: FEC=enabled (data rate).
[154565.553079] BUG: kernel NULL pointer dereference, address: 00000000000000f8
[154565.553080] #PF: supervisor read access in kernel mode
[154565.553082] #PF: error_code(0x0000) - not-present page
[154565.553084] PGD 80000010488ab067 P4D 80000010488ab067 PUD 104978a067 PMD 0
[154565.553089] Oops: 0000 1 PREEMPT SMP PTI
[154565.553092] CPU: 10 PID: 858 Comm: qla2xxx_2_dpc Kdump: loaded Tainted: G OE ------- --- 5.14.0-503.11.1.el9_5.x86_64 #1
[154565.553096] Hardware name: HPE Synergy 660 Gen10/Synergy 660 Gen10 Compute Module, BIOS I43 09/30/2024
[154565.553097] RIP: 0010:qla_fab_async_scan.part.0+0x40b/0x870 [qla2xxx]
[154565.553141] Code: 00 00 e8 58 a3 ec d4 49 89 e9 ba 12 20 00 00 4c 89 e6 49 c7 c0 00 ee a8 c0 48 c7 c1 66 c0 a9 c0 bf 00 80 00 10 e8 15 69 00 00 <4c> 8b 8d f8 00 00 00 4d 85 c9 74 35 49 8b 84 24 00 19 00 00 48 8b
[154565.553143] RSP: 0018:ffffb4dbc8aebdd0 EFLAGS: 00010286
[154565.553145] RAX: 0000000000000000 RBX: ffff8ec2cf0908d0 RCX: 0000000000000002
[154565.553147] RDX: 0000000000000000 RSI: ffffffffc0a9c896 RDI: ffffb4dbc8aebd47
[154565.553148] RBP: 0000000000000000 R08: ffffb4dbc8aebd45 R09: 0000000000ffff0a
[154565.553150] R10: 0000000000000000 R11: 000000000000000f R12: ffff8ec2cf0908d0
[154565.553151] R13: ffff8ec2cf090900 R14: 0000000000000102 R15: ffff8ec2cf084000
[154565.553152] FS: 0000000000000000(0000) GS:ffff8ed27f800000(0000) knlGS:0000000000000000
[154565.553154] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[154565.553155] CR2: 00000000000000f8 CR3: 000000113ae0a005 CR4: 00000000007706f0
[154565.553157] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[154565.553158] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[154565.553159] PKRU: 55555554
[154565.553160] Call Trace:
[154565.553162] <TASK>
[154565.553165] ? show_trace_log_lvl+0x1c4/0x2df
[154565.553172] ? show_trace_log_lvl+0x1c4/0x2df
[154565.553177] ? qla_fab_async_scan.part.0+0x40b/0x870 [qla2xxx]
[154565.553215] ? __die_body.cold+0x8/0xd
[154565.553218] ? page_fault_oops+0x134/0x170
[154565.553223] ? snprintf+0x49/0x70
[154565.553229] ? exc_page_fault+0x62/0x150
[154565.553238] ? asm_exc_page_fault+0x22/0x30
Check for sp being non NULL before freeing any associated memory |
| In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Delay module unload while fabric scan in progress
System crash seen during load/unload test in a loop.
[105954.384919] RBP: ffff914589838dc0 R08: 0000000000000000 R09: 0000000000000086
[105954.384920] R10: 000000000000000f R11: ffffa31240904be5 R12: ffff914605f868e0
[105954.384921] R13: ffff914605f86910 R14: 0000000000008010 R15: 00000000ddb7c000
[105954.384923] FS: 0000000000000000(0000) GS:ffff9163fec40000(0000) knlGS:0000000000000000
[105954.384925] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[105954.384926] CR2: 000055d31ce1d6a0 CR3: 0000000119f5e001 CR4: 0000000000770ee0
[105954.384928] PKRU: 55555554
[105954.384929] Call Trace:
[105954.384931] <IRQ>
[105954.384934] qla24xx_sp_unmap+0x1f3/0x2a0 [qla2xxx]
[105954.384962] ? qla_async_scan_sp_done+0x114/0x1f0 [qla2xxx]
[105954.384980] ? qla24xx_els_ct_entry+0x4de/0x760 [qla2xxx]
[105954.384999] ? __wake_up_common+0x80/0x190
[105954.385004] ? qla24xx_process_response_queue+0xc2/0xaa0 [qla2xxx]
[105954.385023] ? qla24xx_msix_rsp_q+0x44/0xb0 [qla2xxx]
[105954.385040] ? __handle_irq_event_percpu+0x3d/0x190
[105954.385044] ? handle_irq_event+0x58/0xb0
[105954.385046] ? handle_edge_irq+0x93/0x240
[105954.385050] ? __common_interrupt+0x41/0xa0
[105954.385055] ? common_interrupt+0x3e/0xa0
[105954.385060] ? asm_common_interrupt+0x22/0x40
The root cause of this was that there was a free (dma_free_attrs) in the
interrupt context. There was a device discovery/fabric scan in
progress. A module unload was issued which set the UNLOADING flag. As
part of the discovery, after receiving an interrupt a work queue was
scheduled (which involved a work to be queued). Since the UNLOADING
flag is set, the work item was not allocated and the mapped memory had
to be freed. The free occurred in interrupt context leading to system
crash. Delay the driver unload until the fabric scan is complete to
avoid the crash. |
| In the Linux kernel, the following vulnerability has been resolved:
PCI: endpoint: Avoid creating sub-groups asynchronously
The asynchronous creation of sub-groups by a delayed work could lead to a
NULL pointer dereference when the driver directory is removed before the
work completes.
The crash can be easily reproduced with the following commands:
# cd /sys/kernel/config/pci_ep/functions/pci_epf_test
# for i in {1..20}; do mkdir test && rmdir test; done
BUG: kernel NULL pointer dereference, address: 0000000000000088
...
Call Trace:
configfs_register_group+0x3d/0x190
pci_epf_cfs_work+0x41/0x110
process_one_work+0x18f/0x350
worker_thread+0x25a/0x3a0
Fix this issue by using configfs_add_default_group() API which does not
have the deadlock problem as configfs_register_group() and does not require
the delayed work handler.
[mani: slightly reworded the description and added stable list] |
| In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Free sp in error path to fix system crash
System crash seen during load/unload test in a loop,
[61110.449331] qla2xxx [0000:27:00.0]-0042:0: Disabled MSI-X.
[61110.467494] =============================================================================
[61110.467498] BUG qla2xxx_srbs (Tainted: G OE -------- --- ): Objects remaining in qla2xxx_srbs on __kmem_cache_shutdown()
[61110.467501] -----------------------------------------------------------------------------
[61110.467502] Slab 0x000000000ffc8162 objects=51 used=1 fp=0x00000000e25d3d85 flags=0x57ffffc0010200(slab|head|node=1|zone=2|lastcpupid=0x1fffff)
[61110.467509] CPU: 53 PID: 455206 Comm: rmmod Kdump: loaded Tainted: G OE -------- --- 5.14.0-284.11.1.el9_2.x86_64 #1
[61110.467513] Hardware name: HPE ProLiant DL385 Gen10 Plus v2/ProLiant DL385 Gen10 Plus v2, BIOS A42 08/17/2023
[61110.467515] Call Trace:
[61110.467516] <TASK>
[61110.467519] dump_stack_lvl+0x34/0x48
[61110.467526] slab_err.cold+0x53/0x67
[61110.467534] __kmem_cache_shutdown+0x16e/0x320
[61110.467540] kmem_cache_destroy+0x51/0x160
[61110.467544] qla2x00_module_exit+0x93/0x99 [qla2xxx]
[61110.467607] ? __do_sys_delete_module.constprop.0+0x178/0x280
[61110.467613] ? syscall_trace_enter.constprop.0+0x145/0x1d0
[61110.467616] ? do_syscall_64+0x5c/0x90
[61110.467619] ? exc_page_fault+0x62/0x150
[61110.467622] ? entry_SYSCALL_64_after_hwframe+0x63/0xcd
[61110.467626] </TASK>
[61110.467627] Disabling lock debugging due to kernel taint
[61110.467635] Object 0x0000000026f7e6e6 @offset=16000
[61110.467639] ------------[ cut here ]------------
[61110.467639] kmem_cache_destroy qla2xxx_srbs: Slab cache still has objects when called from qla2x00_module_exit+0x93/0x99 [qla2xxx]
[61110.467659] WARNING: CPU: 53 PID: 455206 at mm/slab_common.c:520 kmem_cache_destroy+0x14d/0x160
[61110.467718] CPU: 53 PID: 455206 Comm: rmmod Kdump: loaded Tainted: G B OE -------- --- 5.14.0-284.11.1.el9_2.x86_64 #1
[61110.467720] Hardware name: HPE ProLiant DL385 Gen10 Plus v2/ProLiant DL385 Gen10 Plus v2, BIOS A42 08/17/2023
[61110.467721] RIP: 0010:kmem_cache_destroy+0x14d/0x160
[61110.467724] Code: 99 7d 07 00 48 89 ef e8 e1 6a 07 00 eb b3 48 8b 55 60 48 8b 4c 24 20 48 c7 c6 70 fc 66 90 48 c7 c7 f8 ef a1 90 e8 e1 ed 7c 00 <0f> 0b eb 93 c3 cc cc cc cc 66 2e 0f 1f 84 00 00 00 00 00 55 48 89
[61110.467725] RSP: 0018:ffffa304e489fe80 EFLAGS: 00010282
[61110.467727] RAX: 0000000000000000 RBX: ffffffffc0d9a860 RCX: 0000000000000027
[61110.467729] RDX: ffff8fd5ff9598a8 RSI: 0000000000000001 RDI: ffff8fd5ff9598a0
[61110.467730] RBP: ffff8fb6aaf78700 R08: 0000000000000000 R09: 0000000100d863b7
[61110.467731] R10: ffffa304e489fd20 R11: ffffffff913bef48 R12: 0000000040002000
[61110.467731] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[61110.467733] FS: 00007f64c89fb740(0000) GS:ffff8fd5ff940000(0000) knlGS:0000000000000000
[61110.467734] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[61110.467735] CR2: 00007f0f02bfe000 CR3: 00000020ad6dc005 CR4: 0000000000770ee0
[61110.467736] PKRU: 55555554
[61110.467737] Call Trace:
[61110.467738] <TASK>
[61110.467739] qla2x00_module_exit+0x93/0x99 [qla2xxx]
[61110.467755] ? __do_sys_delete_module.constprop.0+0x178/0x280
Free sp in the error path to fix the crash. |
| In the Linux kernel, the following vulnerability has been resolved:
mptcp: ensure context reset on disconnect()
After the blamed commit below, if the MPC subflow is already in TCP_CLOSE
status or has fallback to TCP at mptcp_disconnect() time,
mptcp_do_fastclose() skips setting the `send_fastclose flag` and the later
__mptcp_close_ssk() does not reset anymore the related subflow context.
Any later connection will be created with both the `request_mptcp` flag
and the msk-level fallback status off (it is unconditionally cleared at
MPTCP disconnect time), leading to a warning in subflow_data_ready():
WARNING: CPU: 26 PID: 8996 at net/mptcp/subflow.c:1519 subflow_data_ready (net/mptcp/subflow.c:1519 (discriminator 13))
Modules linked in:
CPU: 26 UID: 0 PID: 8996 Comm: syz.22.39 Not tainted 6.18.0-rc7-05427-g11fc074f6c36 #1 PREEMPT(voluntary)
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
RIP: 0010:subflow_data_ready (net/mptcp/subflow.c:1519 (discriminator 13))
Code: 90 0f 0b 90 90 e9 04 fe ff ff e8 b7 1e f5 fe 89 ee bf 07 00 00 00 e8 db 19 f5 fe 83 fd 07 0f 84 35 ff ff ff e8 9d 1e f5 fe 90 <0f> 0b 90 e9 27 ff ff ff e8 8f 1e f5 fe 4c 89 e7 48 89 de e8 14 09
RSP: 0018:ffffc9002646fb30 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff88813b218000 RCX: ffffffff825c8435
RDX: ffff8881300b3580 RSI: ffffffff825c8443 RDI: 0000000000000005
RBP: 000000000000000b R08: ffffffff825c8435 R09: 000000000000000b
R10: 0000000000000005 R11: 0000000000000007 R12: ffff888131ac0000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS: 00007f88330af6c0(0000) GS:ffff888a93dd2000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f88330aefe8 CR3: 000000010ff59000 CR4: 0000000000350ef0
Call Trace:
<TASK>
tcp_data_ready (net/ipv4/tcp_input.c:5356)
tcp_data_queue (net/ipv4/tcp_input.c:5445)
tcp_rcv_state_process (net/ipv4/tcp_input.c:7165)
tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1955)
__release_sock (include/net/sock.h:1158 (discriminator 6) net/core/sock.c:3180 (discriminator 6))
release_sock (net/core/sock.c:3737)
mptcp_sendmsg (net/mptcp/protocol.c:1763 net/mptcp/protocol.c:1857)
inet_sendmsg (net/ipv4/af_inet.c:853 (discriminator 7))
__sys_sendto (net/socket.c:727 (discriminator 15) net/socket.c:742 (discriminator 15) net/socket.c:2244 (discriminator 15))
__x64_sys_sendto (net/socket.c:2247)
do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
RIP: 0033:0x7f883326702d
Address the issue setting an explicit `fastclosing` flag at fastclose
time, and checking such flag after mptcp_do_fastclose(). |
| In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix racy bitfield write in btrfs_clear_space_info_full()
From the memory-barriers.txt document regarding memory barrier ordering
guarantees:
(*) These guarantees do not apply to bitfields, because compilers often
generate code to modify these using non-atomic read-modify-write
sequences. Do not attempt to use bitfields to synchronize parallel
algorithms.
(*) Even in cases where bitfields are protected by locks, all fields
in a given bitfield must be protected by one lock. If two fields
in a given bitfield are protected by different locks, the compiler's
non-atomic read-modify-write sequences can cause an update to one
field to corrupt the value of an adjacent field.
btrfs_space_info has a bitfield sharing an underlying word consisting of
the fields full, chunk_alloc, and flush:
struct btrfs_space_info {
struct btrfs_fs_info * fs_info; /* 0 8 */
struct btrfs_space_info * parent; /* 8 8 */
...
int clamp; /* 172 4 */
unsigned int full:1; /* 176: 0 4 */
unsigned int chunk_alloc:1; /* 176: 1 4 */
unsigned int flush:1; /* 176: 2 4 */
...
Therefore, to be safe from parallel read-modify-writes losing a write to
one of the bitfield members protected by a lock, all writes to all the
bitfields must use the lock. They almost universally do, except for
btrfs_clear_space_info_full() which iterates over the space_infos and
writes out found->full = 0 without a lock.
Imagine that we have one thread completing a transaction in which we
finished deleting a block_group and are thus calling
btrfs_clear_space_info_full() while simultaneously the data reclaim
ticket infrastructure is running do_async_reclaim_data_space():
T1 T2
btrfs_commit_transaction
btrfs_clear_space_info_full
data_sinfo->full = 0
READ: full:0, chunk_alloc:0, flush:1
do_async_reclaim_data_space(data_sinfo)
spin_lock(&space_info->lock);
if(list_empty(tickets))
space_info->flush = 0;
READ: full: 0, chunk_alloc:0, flush:1
MOD/WRITE: full: 0, chunk_alloc:0, flush:0
spin_unlock(&space_info->lock);
return;
MOD/WRITE: full:0, chunk_alloc:0, flush:1
and now data_sinfo->flush is 1 but the reclaim worker has exited. This
breaks the invariant that flush is 0 iff there is no work queued or
running. Once this invariant is violated, future allocations that go
into __reserve_bytes() will add tickets to space_info->tickets but will
see space_info->flush is set to 1 and not queue the work. After this,
they will block forever on the resulting ticket, as it is now impossible
to kick the worker again.
I also confirmed by looking at the assembly of the affected kernel that
it is doing RMW operations. For example, to set the flush (3rd) bit to 0,
the assembly is:
andb $0xfb,0x60(%rbx)
and similarly for setting the full (1st) bit to 0:
andb $0xfe,-0x20(%rax)
So I think this is really a bug on practical systems. I have observed
a number of systems in this exact state, but am currently unable to
reproduce it.
Rather than leaving this footgun lying around for the future, take
advantage of the fact that there is room in the struct anyway, and that
it is already quite large and simply change the three bitfield members to
bools. This avoids writes to space_info->full having any effect on
---truncated--- |
