From: Patel Jay P <jay.p.patel@xxxxxxxxx>
A sporadic crash occurs when handle_8051_interrupt handler is invoked
while doing rmmod. Actually, handler is invoked after all workqueue
related resources are freed which results into crash.
Call Trace:
queue_work_on+0x27/0x40
handle_8051_interrupt+0x417/0x710 [hfi1]
? handle_dcc_err+0x212/0x660 [hfi1]
? check_preempt_wakeup+0x119/0x250
? tracing_is_on+0x15/0x30
? tracing_record_taskinfo_skip+0x1e/0x40
? radix_tree_next_chunk+0x10b/0x2e0
? __slab_free+0x9b/0x2c0
interrupt_clear_down+0x43/0x120 [hfi1]
is_dc_int+0x2f/0xa0 [hfi1]
general_interrupt+0x18c/0x1f0 [hfi1]
__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
When kernel is built with CONFIG_DEBUG_SHIRQ config flag, an extra call
to IRQ handler is made from _free_irq() function. The driver should be
prepared for this fake call.
Adding a mechanism which detects whether handler is invoked after
disabling interrupts. hfi_intr_mask field is added to hfi1_devdata
structure which is replica of interrupt mask register of hfi device.
The field is updated while writing a value to register.
Destroying link_wq workqueue after calling free_irq. This will make sure
that if interrupt handler is invoked before or while calling free_irq
then workqueue is destroyed after interrupt is handled.
Fixes: 05cb18fda926 ("IB/hfi1: Update HFI to use the latest PCI API")
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
Reviewed-by: Sebastian Sanchez <sebastian.sanchez@xxxxxxxxx>
Signed-off-by: Patel Jay P <jay.p.patel@xxxxxxxxx>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx>
---
drivers/infiniband/hw/hfi1/chip.c | 8 +++++++-
drivers/infiniband/hw/hfi1/hfi.h | 4 ++++
drivers/infiniband/hw/hfi1/init.c | 31 ++++++++++++++++++++++---------
3 files changed, 33 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 4f057e8..87748a6 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -8224,6 +8224,8 @@ static irqreturn_t general_interrupt(int irq, void *data)
/* only clear if anything is set */
if (regs[i])
write_csr(dd, CCE_INT_CLEAR + (8 * i), regs[i]);
+
+ regs[i] &= dd->hfi_intr_mask[i];
}
/* phase 2: call the appropriate handler */
@@ -12942,12 +12944,15 @@ void set_intr_state(struct hfi1_devdata *dd, u32 enable)
u64 mask = get_int_mask(dd, i);
write_csr(dd, CCE_INT_MASK + (8 * i), mask);
+ dd->hfi_intr_mask[i] = mask;
}
init_qsfp_int(dd);
} else {
- for (i = 0; i < CCE_NUM_INT_CSRS; i++)
+ for (i = 0; i < CCE_NUM_INT_CSRS; i++) {
write_csr(dd, CCE_INT_MASK + (8 * i), 0ull);
+ dd->hfi_intr_mask[i] = 0ull;
+ }
}
}
@@ -14773,6 +14778,7 @@ void hfi1_start_cleanup(struct hfi1_devdata *dd)
free_cntrs(dd);
free_rcverr(dd);
clean_up_interrupts(dd);
+ clean_up_workqueues(dd);
finish_chip_resources(dd);
}
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 4a9b4d7..e12a80b 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1188,6 +1188,9 @@ struct hfi1_devdata {
/* INTx information */
u32 requested_intx_irq; /* did we request one? */
+ /* copy of interrupt mask register */
+ u64 hfi_intr_mask[CCE_NUM_INT_CSRS];
+
/* general interrupt: mask of handled interrupts */
u64 gi_mask[CCE_NUM_INT_CSRS];
@@ -1993,6 +1996,7 @@ static inline void flush_wc(void)
int kdeth_process_eager(struct hfi1_packet *packet);
int process_receive_invalid(struct hfi1_packet *packet);
void seqfile_dump_rcd(struct seq_file *s, struct hfi1_ctxtdata *rcd);
+void clean_up_workqueues(struct hfi1_devdata *dd);
/* global module parameter variables */
extern unsigned int hfi1_max_mtu;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 8e3b3e7..c84af52 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -823,6 +823,28 @@ static int create_workqueues(struct hfi1_devdata *dd)
}
/**
+ * clean_up_workqueues - destroys hfi1_wq and link_wq workqueues
+ * @dd: the hfi1_ib device
+ */
+void clean_up_workqueues(struct hfi1_devdata *dd)
+{
+ int pidx;
+ struct hfi1_pportdata *ppd;
+
+ for (pidx = 0; pidx < dd->num_pports; ++pidx) {
+ ppd = dd->pport + pidx;
+ if (ppd->hfi1_wq) {
+ destroy_workqueue(ppd->hfi1_wq);
+ ppd->hfi1_wq = NULL;
+ }
+ if (ppd->link_wq) {
+ destroy_workqueue(ppd->link_wq);
+ ppd->link_wq = NULL;
+ }
+ }
+}
+
+/**
* hfi1_init - do the actual initialization sequence on the chip
* @dd: the hfi1_ib device
* @reinit: re-initializing, so don't allocate new memory
@@ -1102,15 +1124,6 @@ static void shutdown_device(struct hfi1_devdata *dd)
* We can't count on interrupts since we are stopping.
*/
hfi1_quiet_serdes(ppd);
-
- if (ppd->hfi1_wq) {
- destroy_workqueue(ppd->hfi1_wq);
- ppd->hfi1_wq = NULL;
- }
- if (ppd->link_wq) {
- destroy_workqueue(ppd->link_wq);
- ppd->link_wq = NULL;
- }
}
sdma_exit(dd);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
