The patch titled
gru: improve messages for malfunctioning GRUs
has been added to the -mm tree. Its filename is
gru-improve-messages-for-malfunctioning-grus.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: gru: improve messages for malfunctioning GRUs
From: Jack Steiner <steiner@xxxxxxx>
Improve error messages for malfunctioning GRUs. Identify the type of
instruction that is failing.
Signed-off-by: Jack Steiner <steiner@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/misc/sgi-gru/gruhandles.c | 22 +++++++++++++++++++---
drivers/misc/sgi-gru/gruhandles.h | 6 ++++++
2 files changed, 25 insertions(+), 3 deletions(-)
diff -puN drivers/misc/sgi-gru/gruhandles.c~gru-improve-messages-for-malfunctioning-grus drivers/misc/sgi-gru/gruhandles.c
--- a/drivers/misc/sgi-gru/gruhandles.c~gru-improve-messages-for-malfunctioning-grus
+++ a/drivers/misc/sgi-gru/gruhandles.c
@@ -54,6 +54,21 @@ static void start_instruction(void *h)
gru_flush_cache(h);
}
+static void report_instruction_timeout(void *h)
+{
+ unsigned long goff = GSEGPOFF((unsigned long)h);
+ char *id = "???";
+
+ if (TYPE_IS(CCH, goff))
+ id = "CCH";
+ else if (TYPE_IS(TGH, goff))
+ id = "TGH";
+ else if (TYPE_IS(TFH, goff))
+ id = "TFH";
+
+ panic(KERN_ALERT "GRU %p (%s) is malfunctioning\n", h, id);
+}
+
static int wait_instruction_complete(void *h, enum mcs_op opc)
{
int status;
@@ -64,9 +79,10 @@ static int wait_instruction_complete(voi
status = GET_MSEG_HANDLE_STATUS(h);
if (status != CCHSTATUS_ACTIVE)
break;
- if (GRU_OPERATION_TIMEOUT < (get_cycles() - start_time))
- panic("GRU %p is malfunctioning: start %ld, end %ld\n",
- h, start_time, (unsigned long)get_cycles());
+ if (GRU_OPERATION_TIMEOUT < (get_cycles() - start_time)) {
+ report_instruction_timeout(h);
+ start_time = get_cycles();
+ }
}
if (gru_options & OPT_STATS)
update_mcs_stats(opc, get_cycles() - start_time);
diff -puN drivers/misc/sgi-gru/gruhandles.h~gru-improve-messages-for-malfunctioning-grus drivers/misc/sgi-gru/gruhandles.h
--- a/drivers/misc/sgi-gru/gruhandles.h~gru-improve-messages-for-malfunctioning-grus
+++ a/drivers/misc/sgi-gru/gruhandles.h
@@ -91,6 +91,12 @@
/* Convert an arbitrary handle address to the beginning of the GRU segment */
#define GRUBASE(h) ((void *)((unsigned long)(h) & ~(GRU_SIZE - 1)))
+/* Test a valid handle address to determine the type */
+#define TYPE_IS(hn, h) ((h) >= GRU_##hn##_BASE && (h) < \
+ GRU_##hn##_BASE + GRU_NUM_##hn * GRU_HANDLE_STRIDE && \
+ (((h) & (GRU_HANDLE_STRIDE - 1)) == 0))
+
+
/* General addressing macros. */
static inline void *get_gseg_base_address(void *base, int ctxnum)
{
_
Patches currently in -mm which might be from steiner@xxxxxxx are
linux-next.patch
x86-uv-introduce-a-means-to-translate-from-gpa-socket_paddr.patch
x86-uv-xpc-needs-to-provide-an-abstraction-for-uv_gpa.patch
x86-uv-introduce-uv_gpa_is_mmr.patch
x86-uv-implement-a-gru_read_gpa-kernel-function.patch
x86-uv-update-xpc-to-handle-updated-bios-interface.patch
x86-uv-xpc-null-deref-when-mesq-becomes-empty.patch
x86-uv-xpc_make_first_contact-hang-due-to-not-accepting-active-state.patch
x86-uv-xpc-receive-message-reuse-triggers-invalid-bug_on.patch
gru-initial-gru-based-on-blade-topology.patch
gru-add-comments-raised-in-previous-code-reviews.patch
gru-fix-istatus-race-in-gru-tlb-dropin.patch
gru-handle-blades-without-memory.patch
gru-allow-users-to-specify-gru-chiplet-1.patch
gru-allow-users-to-specify-gru-chiplet-2.patch
gru-allow-users-to-specify-gru-chiplet-3.patch
gru-fix-bug-in-module-unload.patch
gru-improve-messages-for-malfunctioning-grus.patch
gru-support-64-bit-gru-addresses.patch
gru-handle-failures-to-mmu_notifier_register.patch
gru-add-debug-option-for-cache-flushing.patch
gru-add-test-for-gru_copy_gpa.patch
gru-check-for-valid-vma.patch
gru-fix-prefetch-and-speculation-bugs.patch
gru-update-irq-infrastructure.patch
gru-add-additional-gru-statistics.patch
gru-expicitly-set-instruction-status-to-active.patch
gru-preload-tlb-for-bcopy-instructions.patch
gru-fix-bug-in-exception-handling.patch
gru-add-symbolic-names-for-gru-error-code.patch
gru-remove-stray-local_irq_enable.patch
gru-check-for-correct-gru-chiplet-assignment.patch
gru-update-gru-structures-to-match-latest-hardware-spec.patch
gru-fix-bug-in-allocation-of-kernel-contexts.patch
gru-add-hugepage-support.patch
gru-fix-gru-interrupt-race-at-deallocate.patch
gru-improve-gru-tlb-dropin-statistics.patch
gru-update-driver-version-number.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
