From: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
When disabling and removing a receive context, it is possible for an
asynchronous event (i.e IRQ) to occur. Because of this there is a
race between cleaning up the context, and the context being used by
the asynchronous event.
cpu 0 (context cleanup)
rc->ref_count-- (ref_count == 0)
hfi1_rcd_free()
cpu 1 (IRQ (with rcd index))
rcd_get_by_index()
lock
ref_count+++ <-- reference count race (WARNING)
return rcd
unlock
cpu 0
hfi1_free_ctxtdata() <-- incorrect free location
lock
remove rcd from array
unlock
free rcd
This race will cause the following WARNING trace:
WARNING: CPU: 0 PID: 175027 at include/linux/kref.h:52 hfi1_rcd_get_by_index+0x84/0xa0 [hfi1]
CPU: 0 PID: 175027 Comm: IMB-MPI1 Kdump: loaded Tainted: G OE ------------ 3.10.0-957.el7.x86_64 #1
Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.11.01.0076.C4.111920150602 11/19/2015
Call Trace:
dump_stack+0x19/0x1b
__warn+0xd8/0x100
warn_slowpath_null+0x1d/0x20
hfi1_rcd_get_by_index+0x84/0xa0 [hfi1]
is_rcv_urgent_int+0x24/0x90 [hfi1]
general_interrupt+0x1b6/0x210 [hfi1]
__handle_irq_event_percpu+0x44/0x1c0
handle_irq_event_percpu+0x32/0x80
handle_irq_event+0x3c/0x60
handle_edge_irq+0x7f/0x150
handle_irq+0xe4/0x1a0
do_IRQ+0x4d/0xf0
common_interrupt+0x162/0x162
The race can also lead to a use after free which could be similar
to:
general protection fault: 0000 1 SMP
CPU: 71 PID: 177147 Comm: IMB-MPI1 Kdump: loaded Tainted: G W OE ------------ 3.10.0-957.el7.x86_64 #1
Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.11.01.0076.C4.111920150602 11/19/2015
task: ffff9962a8098000 ti: ffff99717a508000 task.ti: ffff99717a508000 __kmalloc+0x94/0x230
Call Trace:
? hfi1_user_sdma_process_request+0x9c8/0x1250 [hfi1]
hfi1_user_sdma_process_request+0x9c8/0x1250 [hfi1]
hfi1_aio_write+0xba/0x110 [hfi1]
do_sync_readv_writev+0x7b/0xd0
do_readv_writev+0xce/0x260
? handle_mm_fault+0x39d/0x9b0
? pick_next_task_fair+0x5f/0x1b0
? sched_clock_cpu+0x85/0xc0
? __schedule+0x13a/0x890
vfs_writev+0x35/0x60
SyS_writev+0x7f/0x110
system_call_fastpath+0x22/0x27
Introduce a context enable flag to indicate if the context is enabled.
Reorder context cleanup to ensure context removal before cleanup
occurs correctly.
Cc: stable@xxxxxxxxxxxxxxx # v4.14.0+
Fixes: f683c80ca68e ("IB/hfi1: Resolve kernel panics by reference counting receive contexts")
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx>
---
drivers/infiniband/hw/hfi1/file_ops.c | 2 ++
drivers/infiniband/hw/hfi1/hfi.h | 3 ++-
drivers/infiniband/hw/hfi1/init.c | 8 +++++---
3 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index c22ebc7..0ba0cf5 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -671,6 +671,8 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
}
spin_unlock_irqrestore(&dd->uctxt_lock, flags);
+ uctxt->del_pend = 1;
+
/*
* Disable receive context and interrupt available, reset all
* RcvCtxtCtrl bits to default values.
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index dc8ba43..ea99768 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -284,7 +284,8 @@ struct hfi1_ctxtdata {
u16 expected_base;
/* Device context index */
u8 ctxt;
-
+ /* ctxt deletion is pending */
+ u8 del_pend;
/* PSM Specific fields */
/* lock protecting all Expected TID data */
struct mutex exp_mutex;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 044d9a8..d2ac3ef 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -215,12 +215,11 @@ static void hfi1_rcd_free(struct kref *kref)
struct hfi1_ctxtdata *rcd =
container_of(kref, struct hfi1_ctxtdata, kref);
- hfi1_free_ctxtdata(rcd->dd, rcd);
-
spin_lock_irqsave(&rcd->dd->uctxt_lock, flags);
rcd->dd->rcd[rcd->ctxt] = NULL;
spin_unlock_irqrestore(&rcd->dd->uctxt_lock, flags);
+ hfi1_free_ctxtdata(rcd->dd, rcd);
kfree(rcd);
}
@@ -326,7 +325,10 @@ struct hfi1_ctxtdata *hfi1_rcd_get_by_index(struct hfi1_devdata *dd, u16 ctxt)
spin_lock_irqsave(&dd->uctxt_lock, flags);
if (dd->rcd[ctxt]) {
rcd = dd->rcd[ctxt];
- hfi1_rcd_get(rcd);
+ if (rcd->del_pend)
+ rcd = NULL;
+ else
+ hfi1_rcd_get(rcd);
}
spin_unlock_irqrestore(&dd->uctxt_lock, flags);
