RDMA/erdma: Fix CEQ tasklet use-after-free on removal
Subsystems (2)
PATCH 1/1 RDMA/erdma: Fix CEQ tasklet use-after-free on removal
Each CEQ interrupt handler only schedules eqc->tasklet. The tasklet calls erdma_ceq_completion_handler(), which reads the DMA-coherent EQ ring through get_next_valid_eqe() and updates eq->dbrec through notify_eq().
erdma_ceqs_uninit() frees each CEQ IRQ and then destroys its EQ. free_irq() prevents another hard IRQ and waits for an in-flight handler, but it does not drain a tasklet that the handler already scheduled. The tasklet can therefore access eq->qbuf or eq->dbrec after erdma_eq_destroy() frees them.
Clearing ceq_cb->ready does not synchronize with a tasklet that already passed the check at the start of erdma_ceq_completion_handler().
Kill the tasklet after free_irq(), when no handler can schedule it again, and before erdma_ceq_uninit_one() releases the EQ buffers.
---
Found by static analysis only; not tested on ERDMA hardware. Testing on hardware, particularly device removal while CEQ interrupts are active, would be appreciated.
drivers/infiniband/hw/erdma/erdma_eq.c | 1 + 1 file changed, 1 insertion(+)
drivers/infiniband/hw/erdma/erdma_eq.c +1 -0
@@ -220,6 +220,7 @@ static void erdma_free_ceq_irq(struct erdma_dev *dev, u16 ceqn)irq_set_affinity_hint (eqc->irq.msix_vector,NULL );free_irq (eqc->irq.msix_vector, eqc); +tasklet_kill (&eqc->tasklet); }static int create_eq_cmd (struct erdma_dev *dev,u32 eqn,struct erdma_eq *eq)
Signature · 1 line
2.47.1
Quoted 21 lines · Myeonghun Pak
Each CEQ interrupt handler only schedules
eqc->tasklet. The tasklet callserdma_ceq_completion_handler(), which reads the DMA-coherent EQ ring throughget_next_valid_eqe()and updateseq->dbrecthroughnotify_eq().
erdma_ceqs_uninit()frees each CEQ IRQ and then destroys its EQ.free_irq()prevents another hard IRQ and waits for an in-flight handler, but it does not drain a tasklet that the handler already scheduled. The tasklet can therefore accesseq->qbuforeq->dbrecaftererdma_eq_destroy()frees them.Clearing
ceq_cb->readydoes not synchronize with a tasklet that already passed the check at the start oferdma_ceq_completion_handler().Kill the tasklet after
free_irq(), when no handler can schedule it again, and beforeerdma_ceq_uninit_one()releases the EQ buffers.Fixes f2a0a630b953 ("RDMA/erdma: Add event queue implementation")Co-developed-by Ijae Kim <[email protected]>Signed-off-by Ijae Kim <[email protected]>Signed-off-by Myeonghun Pak <[email protected]>
Quoted 8 lines
---
Found by static analysis only; not tested on ERDMA hardware. Testing on hardware, particularly device removal while CEQ interrupts are active, would be appreciated.drivers/infiniband/hw/erdma/erdma_eq.c | 1 + 1 file changed, 1 insertion(+)
Thanks.
While this is unlikely to happen in practice, since the ibdev has already been removed and no CQs should remain to generate CEQ events, this patch makes the CEQ teardown ordering explicit and robust.
Cheng Xu
Quoted 12 lines
drivers/infiniband/hw/erdma/erdma_eq.c +1
-0@@ -220,6 +220,7 @@ static void erdma_free_ceq_irq(struct erdma_dev *dev, u16 ceqn)irq_set_affinity_hint (eqc->irq.msix_vector,NULL );free_irq (eqc->irq.msix_vector, eqc); +tasklet_kill (&eqc->tasklet); }static int create_eq_cmd (struct erdma_dev *dev,u32 eqn,struct erdma_eq *eq)
Hi,
I was looking at this driver and was curious if you also need some type of synchronization after the xa_erase in erdma_destroy_cq.
Otherwise, it seems like the CEQ tasklet could do the xa_load right before erdma_destroy_cq does the xa_erase, then destroy_cq proceeds to return and kfree the CQ while the tasket is in the middle of comp_handler.
Most drivers either do a synchronize_irq (which I don't think would work for this since it's a tasklet) or some form of locked refcounting when accessing the xarray.
Thanks,
Jake
Cheng Xu
maintainerQuoted 5 lines · Jacob Moroni
Hi,
I was looking at this driver and was curious if you also need some type of synchronization after the
xa_eraseinerdma_destroy_cq.
Quoted 8 lines
Otherwise, it seems like the CEQ tasklet could do the
xa_loadright beforeerdma_destroy_cqdoes thexa_erase, thendestroy_cqproceeds to return and kfree the CQ while the tasket is in the middle ofcomp_handler.Most drivers either do a
synchronize_irq(which I don't think would work for this since it's a tasklet) or some form of locked refcounting when accessing the xarray.
Hi Jacob,
Thanks for pointing this out.
For kernel CQs this should be unlikely in practice, since the associated QPs are destroyed first and the kernel QP destroy path drains the WQEs before the CQ is destroyed.
However, the user CQ path does not have the same guarantee, so the race you described still needs to be handled. We need to add synchronization in the CQ destroy path, and I will take a closer look at this.
Thanks,
Cheng Xu
Quoted 2 lines
Thanks,
Jake
Leon Romanovsky
AppliedQuoted 11 lines · Myeonghun Pak
Each CEQ interrupt handler only schedules
eqc->tasklet. The tasklet callserdma_ceq_completion_handler(), which reads the DMA-coherent EQ ring throughget_next_valid_eqe()and updateseq->dbrecthroughnotify_eq().
erdma_ceqs_uninit()frees each CEQ IRQ and then destroys its EQ.free_irq()prevents another hard IRQ and waits for an in-flight handler, but it does not drain a tasklet that the handler already scheduled. The tasklet can therefore accesseq->qbuforeq->dbrecaftererdma_eq_destroy()frees them.[...]
Applied, thanks!
[1/1] RDMA/erdma: Fix CEQ tasklet use-after-free on removal
https://git.kernel.org/rdma/rdma/c/0ca79979384f03
Best regards,
Signature · 1 line
Leon Romanovsky <[email protected]>