From: Maximilian Heyne mheyne@amazon.de
stable inclusion from stable-5.10.60 commit dff830e5e7237a60f6c91b3f028b914a1001790f bugzilla: 177018 https://gitee.com/openeuler/kernel/issues/I4EAUG
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 88ca2521bd5b4e8b83743c01a2d4cb09325b51e9 ]
There is a TOCTOU issue in set_evtchn_to_irq. Rows in the evtchn_to_irq mapping are lazily allocated in this function. The check whether the row is already present and the row initialization is not synchronized. Two threads can at the same time allocate a new row for evtchn_to_irq and add the irq mapping to the their newly allocated row. One thread will overwrite what the other has set for evtchn_to_irq[row] and therefore the irq mapping is lost. This will trigger a BUG_ON later in bind_evtchn_to_cpu:
INFO: pci 0000:1a:15.4: [1d0f:8061] type 00 class 0x010802 INFO: nvme 0000:1a:12.1: enabling device (0000 -> 0002) INFO: nvme nvme77: 1/0/0 default/read/poll queues CRIT: kernel BUG at drivers/xen/events/events_base.c:427! WARN: invalid opcode: 0000 [#1] SMP NOPTI WARN: Workqueue: nvme-reset-wq nvme_reset_work [nvme] WARN: RIP: e030:bind_evtchn_to_cpu+0xc2/0xd0 WARN: Call Trace: WARN: set_affinity_irq+0x121/0x150 WARN: irq_do_set_affinity+0x37/0xe0 WARN: irq_setup_affinity+0xf6/0x170 WARN: irq_startup+0x64/0xe0 WARN: __setup_irq+0x69e/0x740 WARN: ? request_threaded_irq+0xad/0x160 WARN: request_threaded_irq+0xf5/0x160 WARN: ? nvme_timeout+0x2f0/0x2f0 [nvme] WARN: pci_request_irq+0xa9/0xf0 WARN: ? pci_alloc_irq_vectors_affinity+0xbb/0x130 WARN: queue_request_irq+0x4c/0x70 [nvme] WARN: nvme_reset_work+0x82d/0x1550 [nvme] WARN: ? check_preempt_wakeup+0x14f/0x230 WARN: ? check_preempt_curr+0x29/0x80 WARN: ? nvme_irq_check+0x30/0x30 [nvme] WARN: process_one_work+0x18e/0x3c0 WARN: worker_thread+0x30/0x3a0 WARN: ? process_one_work+0x3c0/0x3c0 WARN: kthread+0x113/0x130 WARN: ? kthread_park+0x90/0x90 WARN: ret_from_fork+0x3a/0x50
This patch sets evtchn_to_irq rows via a cmpxchg operation so that they will be set only once. The row is now cleared before writing it to evtchn_to_irq in order to not create a race once the row is visible for other threads.
While at it, do not require the page to be zeroed, because it will be overwritten with -1's in clear_evtchn_to_irq_row anyway.
Signed-off-by: Maximilian Heyne mheyne@amazon.de Fixes: d0b075ffeede ("xen/events: Refactor evtchn_to_irq array to be dynamically allocated") Link: https://lore.kernel.org/r/20210812130930.127134-1-mheyne@amazon.de Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Chen Jun chenjun102@huawei.com Acked-by: Weilong Chen chenweilong@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- drivers/xen/events/events_base.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index af0f6ad32522..fba78daee449 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -192,12 +192,12 @@ static void disable_dynirq(struct irq_data *data);
static DEFINE_PER_CPU(unsigned int, irq_epoch);
-static void clear_evtchn_to_irq_row(unsigned row) +static void clear_evtchn_to_irq_row(int *evtchn_row) { unsigned col;
for (col = 0; col < EVTCHN_PER_ROW; col++) - WRITE_ONCE(evtchn_to_irq[row][col], -1); + WRITE_ONCE(evtchn_row[col], -1); }
static void clear_evtchn_to_irq_all(void) @@ -207,7 +207,7 @@ static void clear_evtchn_to_irq_all(void) for (row = 0; row < EVTCHN_ROW(xen_evtchn_max_channels()); row++) { if (evtchn_to_irq[row] == NULL) continue; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_to_irq[row]); } }
@@ -215,6 +215,7 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) { unsigned row; unsigned col; + int *evtchn_row;
if (evtchn >= xen_evtchn_max_channels()) return -EINVAL; @@ -227,11 +228,18 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) if (irq == -1) return 0;
- evtchn_to_irq[row] = (int *)get_zeroed_page(GFP_KERNEL); - if (evtchn_to_irq[row] == NULL) + evtchn_row = (int *) __get_free_pages(GFP_KERNEL, 0); + if (evtchn_row == NULL) return -ENOMEM;
- clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_row); + + /* + * We've prepared an empty row for the mapping. If a different + * thread was faster inserting it, we can drop ours. + */ + if (cmpxchg(&evtchn_to_irq[row], NULL, evtchn_row) != NULL) + free_page((unsigned long) evtchn_row); }
WRITE_ONCE(evtchn_to_irq[row][col], irq);