[Patch 27/29] GRU - Fix GRU interrupt race at deallocate

From: steiner
Date: Tue Nov 24 2009 - 10:08:10 EST


From: Jack Steiner <steiner@xxxxxxx>

Fix a race where an interrupt could be received for a GRU context that
has been deallocated.


Signed-off-by: Jack Steiner <steiner@xxxxxxx>


---
drivers/misc/sgi-gru/grufault.c | 24 +++++++++++++++++-------
drivers/misc/sgi-gru/gruprocfs.c | 1 +
drivers/misc/sgi-gru/grutables.h | 1 +
3 files changed, 19 insertions(+), 7 deletions(-)

Index: linux/drivers/misc/sgi-gru/grufault.c
===================================================================
--- linux.orig/drivers/misc/sgi-gru/grufault.c 2009-11-20 09:32:38.000000000 -0600
+++ linux/drivers/misc/sgi-gru/grufault.c 2009-11-20 09:32:38.000000000 -0600
@@ -360,7 +360,8 @@ static void gru_preload_tlb(struct gru_s
* < 0 = error code
*
*/
-static int gru_try_dropin(struct gru_thread_state *gts,
+static int gru_try_dropin(struct gru_state *gru,
+ struct gru_thread_state *gts,
struct gru_tlb_fault_handle *tfh,
struct gru_instruction_bits *cbk)
{
@@ -432,7 +433,7 @@ static int gru_try_dropin(struct gru_thr
}

if (unlikely(cbe) && pageshift == PAGE_SHIFT) {
- gru_preload_tlb(gts->ts_gru, gts, atomic, vaddr, asid, write, tlb_preload_count, tfh, cbe);
+ gru_preload_tlb(gru, gts, atomic, vaddr, asid, write, tlb_preload_count, tfh, cbe);
gru_flush_cache_cbe(cbe);
}

@@ -442,7 +443,7 @@ static int gru_try_dropin(struct gru_thr
gru_dbg(grudev,
"%s: gid %d, gts 0x%p, tfh 0x%p, vaddr 0x%lx, asid 0x%x, indexway 0x%x,"
" rw %d, ps %d, gpa 0x%lx\n",
- atomic ? "atomic" : "non-atomic", gts->ts_gru->gs_gid, gts, tfh, vaddr, asid,
+ atomic ? "atomic" : "non-atomic", gru->gs_gid, gts, tfh, vaddr, asid,
indexway, write, pageshift, gpa);
STAT(tlb_dropin);
return 0;
@@ -528,6 +529,7 @@ static irqreturn_t gru_intr(int chiplet,
struct gru_tlb_fault_map imap, dmap;
struct gru_thread_state *gts;
struct gru_tlb_fault_handle *tfh = NULL;
+ struct completion *cmp;
int cbrnum, ctxnum;

STAT(intr);
@@ -547,9 +549,11 @@ static irqreturn_t gru_intr(int chiplet,

for_each_cbr_in_tfm(cbrnum, dmap.fault_bits) {
STAT(intr_cbr);
- complete(gru->gs_blade->bs_async_wq);
+ cmp = gru->gs_blade->bs_async_wq;
+ if (cmp)
+ complete(cmp);
gru_dbg(grudev, "gid %d, cbr_done %d, done %d\n",
- gru->gs_gid, cbrnum, gru->gs_blade->bs_async_wq->done);
+ gru->gs_gid, cbrnum, cmp ? cmp->done : -1);
}

for_each_cbr_in_tfm(cbrnum, imap.fault_bits) {
@@ -566,6 +570,12 @@ static irqreturn_t gru_intr(int chiplet,
ctxnum = tfh->ctxnum;
gts = gru->gs_gts[ctxnum];

+ /* Spurious interrupts can cause this. Ignore. */
+ if (!gts) {
+ STAT(intr_spurious);
+ continue;
+ }
+
/*
* This is running in interrupt context. Trylock the mmap_sem.
* If it fails, retry the fault in user context.
@@ -573,7 +583,7 @@ static irqreturn_t gru_intr(int chiplet,
if (!gts->ts_force_cch_reload &&
down_read_trylock(&gts->ts_mm->mmap_sem)) {
gts->ustats.fmm_tlbdropin++;
- gru_try_dropin(gts, tfh, NULL);
+ gru_try_dropin(gru, gts, tfh, NULL);
up_read(&gts->ts_mm->mmap_sem);
} else {
tfh_user_polling_mode(tfh);
@@ -619,7 +629,7 @@ static int gru_user_dropin(struct gru_th
wait_event(gms->ms_wait_queue,
atomic_read(&gms->ms_range_active) == 0);
prefetchw(tfh); /* Helps on hdw, required for emulator */
- ret = gru_try_dropin(gts, tfh, cb);
+ ret = gru_try_dropin(gts->ts_gru, gts, tfh, cb);
if (ret <= 0)
return ret;
STAT(call_os_wait_queue);
Index: linux/drivers/misc/sgi-gru/gruprocfs.c
===================================================================
--- linux.orig/drivers/misc/sgi-gru/gruprocfs.c 2009-11-20 09:32:35.000000000 -0600
+++ linux/drivers/misc/sgi-gru/gruprocfs.c 2009-11-20 09:32:38.000000000 -0600
@@ -66,6 +66,7 @@ static int statistics_show(struct seq_fi
printstat(s, intr);
printstat(s, intr_cbr);
printstat(s, intr_tfh);
+ printstat(s, intr_spurious);
printstat(s, intr_mm_lock_failed);
printstat(s, call_os);
printstat(s, call_os_wait_queue);
Index: linux/drivers/misc/sgi-gru/grutables.h
===================================================================
--- linux.orig/drivers/misc/sgi-gru/grutables.h 2009-11-20 09:32:35.000000000 -0600
+++ linux/drivers/misc/sgi-gru/grutables.h 2009-11-20 09:32:38.000000000 -0600
@@ -192,6 +192,7 @@ struct gru_stats_s {
atomic_long_t intr;
atomic_long_t intr_cbr;
atomic_long_t intr_tfh;
+ atomic_long_t intr_spurious;
atomic_long_t intr_mm_lock_failed;
atomic_long_t call_os;
atomic_long_t call_os_wait_queue;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/