From b73d40c6178f2c8b2d574db566b47f36e3d12072 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 27 Apr 2006 18:40:23 -0700 Subject: [PATCH] s390: instruction processing damage handling In case of an instruction processing damage (IPD) machine check in kernel mode the resulting action is always to stop the kernel. This is not necessarily the best solution since a retry of the failing instruction might succeed. Add logic to retry the instruction if no more than 30 instruction processing damage checks occured in the last 5 minutes. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/s390/s390mach.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) (limited to 'drivers/s390/s390mach.c') diff --git a/drivers/s390/s390mach.c b/drivers/s390/s390mach.c index 3bf466603512..5ae14803091f 100644 --- a/drivers/s390/s390mach.c +++ b/drivers/s390/s390mach.c @@ -362,12 +362,19 @@ s390_revalidate_registers(struct mci *mci) return kill_task; } +#define MAX_IPD_COUNT 29 +#define MAX_IPD_TIME (5 * 60 * 100 * 1000) /* 5 minutes */ + /* * machine check handler. */ void s390_do_machine_check(struct pt_regs *regs) { + static DEFINE_SPINLOCK(ipd_lock); + static unsigned long long last_ipd; + static int ipd_count; + unsigned long long tmp; struct mci *mci; struct mcck_struct *mcck; int umode; @@ -404,11 +411,27 @@ s390_do_machine_check(struct pt_regs *regs) s390_handle_damage("processing backup machine " "check with damage."); } - if (!umode) - s390_handle_damage("processing backup machine " - "check in kernel mode."); - mcck->kill_task = 1; - mcck->mcck_code = *(unsigned long long *) mci; + + /* + * Nullifying exigent condition, therefore we might + * retry this instruction. + */ + + spin_lock(&ipd_lock); + + tmp = get_clock(); + + if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME) + ipd_count++; + else + ipd_count = 1; + + last_ipd = tmp; + + if (ipd_count == MAX_IPD_COUNT) + s390_handle_damage("too many ipd retries."); + + spin_unlock(&ipd_lock); } else { /* Processing damage -> stopping machine */ -- cgit v1.2.3 From 022e4fc0fb2e4e179aaba4ee139dcb8fded0cba2 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 1 May 2006 12:16:14 -0700 Subject: [PATCH] s390: fix ipd handling As pointed out by Paulo Marques MAX_IPD_TIME is by a factor of ten too small. Since this means that we allow ten times more IPDs in the intended time frame this could result in a cpu check stop of a physical cpu. Cc: Martin Schwidefsky Signed-off-by: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/s390/s390mach.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/s390/s390mach.c') diff --git a/drivers/s390/s390mach.c b/drivers/s390/s390mach.c index 5ae14803091f..f99e55308b32 100644 --- a/drivers/s390/s390mach.c +++ b/drivers/s390/s390mach.c @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -363,7 +364,7 @@ s390_revalidate_registers(struct mci *mci) } #define MAX_IPD_COUNT 29 -#define MAX_IPD_TIME (5 * 60 * 100 * 1000) /* 5 minutes */ +#define MAX_IPD_TIME (5 * 60 * USEC_PER_SEC) /* 5 minutes */ /* * machine check handler. -- cgit v1.2.3