renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-16 01:04:08 +08:00
Code

IB/hfi1: Re-order IRQ cleanup to address driver cleanup race

Browse Source 
The pci_request_irq() interfaces always adds the IRQF_SHARED bit to
all IRQ requests.

When the kernel is built with CONFIG_DEBUG_SHIRQ config flag, if the
IRQF_SHARED bit is set, a call to the IRQ handler is made from the
__free_irq() function. This is testing a race condition between the
IRQ cleanup and an IRQ racing the cleanup.  The HFI driver should be
able to handle this race, but does not.

This race can cause traces that start with this footprint:

BUG: unable to handle kernel NULL pointer dereference at   (null)
Call Trace:
 <hfi1 irq handler>
 ...
 __free_irq+0x1b3/0x2d0
 free_irq+0x35/0x70
 pci_free_irq+0x1c/0x30
 clean_up_interrupts+0x53/0xf0 [hfi1]
 hfi1_start_cleanup+0x122/0x190 [hfi1]
 postinit_cleanup+0x1d/0x280 [hfi1]
 remove_one+0x233/0x250 [hfi1]
 pci_device_remove+0x39/0xc0

Export IRQ cleanup function so it can be called from other modules.

Using the exported cleanup function:

  Re-order the driver cleanup code to clean up IRQ resources before
  other resources, eliminating the race.

  Re-order error path for init so that the race does not occur.

Reduce severity on spurious error message for SDMA IRQs to info.

Reviewed-by: Alex Estrin <alex.estrin@intel.com>
Reviewed-by: Patel Jay P <jay.p.patel@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This commit is contained in:
Michael J. Ruhl 2018-02-01 10:43:42 -08:00 committed by Jason Gunthorpe
parent f34727a135
commit 82a9792656
3 changed files with 16 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
drivers/infiniband/hw/hfi1/chip.c
View File

@ -8264,8 +8264,8 @@ static irqreturn_t sdma_interrupt(int irq, void *data)
/* handle the interrupt(s) */
sdma_engine_interrupt(sde, status);
} else {
dd_dev_err_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
sde->this_idx);
dd_dev_info_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
sde->this_idx);
}
return IRQ_HANDLED;
}
@ -12960,7 +12960,14 @@ static void disable_intx(struct pci_dev *pdev)
pci_intx(pdev, 0);
}
static void clean_up_interrupts(struct hfi1_devdata *dd)
/**
* hfi1_clean_up_interrupts() - Free all IRQ resources
* @dd: valid device data data structure
*
* Free the MSI or INTx IRQs and assoicated PCI resources,
* if they have been allocated.
*/
void hfi1_clean_up_interrupts(struct hfi1_devdata *dd)
{
int i;
@ -13321,7 +13328,7 @@ static int set_up_interrupts(struct hfi1_devdata *dd)
return 0;
fail:
clean_up_interrupts(dd);
hfi1_clean_up_interrupts(dd);
return ret;
}
@ -14748,7 +14755,6 @@ void hfi1_start_cleanup(struct hfi1_devdata *dd)
aspm_exit(dd);
free_cntrs(dd);
free_rcverr(dd);
clean_up_interrupts(dd);
finish_chip_resources(dd);
}
@ -15204,7 +15210,7 @@ bail_free_rcverr:
bail_free_cntrs:
free_cntrs(dd);
bail_clear_intr:
clean_up_interrupts(dd);
hfi1_clean_up_interrupts(dd);
bail_cleanup:
hfi1_pcie_ddcleanup(dd);
bail_free:

1
drivers/infiniband/hw/hfi1/hfi.h
View File

@ -1957,6 +1957,7 @@ void hfi1_verbs_unregister_sysfs(struct hfi1_devdata *dd);
int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len);
int hfi1_pcie_init(struct pci_dev *pdev, const struct pci_device_id *ent);
void hfi1_clean_up_interrupts(struct hfi1_devdata *dd);
void hfi1_pcie_cleanup(struct pci_dev *pdev);
int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev);
void hfi1_pcie_ddcleanup(struct hfi1_devdata *);

4
drivers/infiniband/hw/hfi1/init.c
View File

@ -1058,8 +1058,9 @@ static void shutdown_device(struct hfi1_devdata *dd)
}
dd->flags &= ~HFI1_INITTED;
/* mask interrupts, but not errors */
/* mask and clean up interrupts, but not errors */
set_intr_state(dd, 0);
hfi1_clean_up_interrupts(dd);
for (pidx = 0; pidx < dd->num_pports; ++pidx) {
ppd = dd->pport + pidx;
@ -1704,6 +1705,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
dd_dev_err(dd, "Failed to create /dev devices: %d\n", -j);
if (initfail || ret) {
hfi1_clean_up_interrupts(dd);
stop_timers(dd);
flush_workqueue(ib_wq);
for (pidx = 0; pidx < dd->num_pports; ++pidx) {