diff options
author | Al Cooper <alcooperx@gmail.com> | 2011-11-08 09:59:01 -0500 |
---|---|---|
committer | Ralf Baechle <ralf@linux-mips.org> | 2011-11-08 17:59:22 +0000 |
commit | 4f1a1eb530071c39fb239fd26c912a64284b1408 (patch) | |
tree | e4b00b9dab468604f97e2fbe1585ba0e87f37991 /arch/mips/kernel/cevt-r4k.c | |
parent | e63fb7a9dae820b3ff6754f794fd713f83e32fff (diff) | |
download | talos-obmc-linux-4f1a1eb530071c39fb239fd26c912a64284b1408.tar.gz talos-obmc-linux-4f1a1eb530071c39fb239fd26c912a64284b1408.zip |
MIPS: Kernel hangs occasionally during boot.
The Kernel hangs occasionally during boot after "Calibrating delay loop..".
This is caused by the c0_compare_int_usable() routine in cevt-r4k.c
returning false which causes the system to disable the timer and hang later.
The false return happens because the routine is using a series of four calls
to irq_disable_hazard() as a delay while it waits for the timer changes to
propagate to the cp0 cause register. On newer MIPS cores, like the 74K, the
series of irq_disable_hazard() calls turn into ehb instructions and can take
as little as a few clock ticks for all 4 instructions. This is not enough of
a delay, so the routine thinks the timer is not working. This fix uses up
to a max number of cycle counter ticks for the delay and uses
back_to_back_c0_hazard() instead of irq_disable_hazard() to handle the
hazard condition between cp0 writes and cp0 reads.
Signed-off-by: Al Cooper <alcooperx@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/2911/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Diffstat (limited to 'arch/mips/kernel/cevt-r4k.c')
-rw-r--r-- | arch/mips/kernel/cevt-r4k.c | 38 |
1 files changed, 19 insertions, 19 deletions
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 98c5a9737c14..e2d8e199be32 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -103,19 +103,10 @@ static int c0_compare_int_pending(void) /* * Compare interrupt can be routed and latched outside the core, - * so a single execution hazard barrier may not be enough to give - * it time to clear as seen in the Cause register. 4 time the - * pipeline depth seems reasonably conservative, and empirically - * works better in configurations with high CPU/bus clock ratios. + * so wait up to worst case number of cycle counter ticks for timer interrupt + * changes to propagate to the cause register. */ - -#define compare_change_hazard() \ - do { \ - irq_disable_hazard(); \ - irq_disable_hazard(); \ - irq_disable_hazard(); \ - irq_disable_hazard(); \ - } while (0) +#define COMPARE_INT_SEEN_TICKS 50 int c0_compare_int_usable(void) { @@ -126,8 +117,12 @@ int c0_compare_int_usable(void) * IP7 already pending? Try to clear it by acking the timer. */ if (c0_compare_int_pending()) { - write_c0_compare(read_c0_count()); - compare_change_hazard(); + cnt = read_c0_count(); + write_c0_compare(cnt); + back_to_back_c0_hazard(); + while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS)) + if (!c0_compare_int_pending()) + break; if (c0_compare_int_pending()) return 0; } @@ -136,7 +131,7 @@ int c0_compare_int_usable(void) cnt = read_c0_count(); cnt += delta; write_c0_compare(cnt); - compare_change_hazard(); + back_to_back_c0_hazard(); if ((int)(read_c0_count() - cnt) < 0) break; /* increase delta if the timer was already expired */ @@ -145,12 +140,17 @@ int c0_compare_int_usable(void) while ((int)(read_c0_count() - cnt) <= 0) ; /* Wait for expiry */ - compare_change_hazard(); + while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS)) + if (c0_compare_int_pending()) + break; if (!c0_compare_int_pending()) return 0; - - write_c0_compare(read_c0_count()); - compare_change_hazard(); + cnt = read_c0_count(); + write_c0_compare(cnt); + back_to_back_c0_hazard(); + while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS)) + if (!c0_compare_int_pending()) + break; if (c0_compare_int_pending()) return 0; |