From 5ee7737379b1d7f0c977c0f1661fbaf01a8d4721 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Fri, 27 Oct 2006 19:49:53 +0900 Subject: [IA64] cpu-hotplug: Fixing confliction between CPU hot-add and IPI Signed-off-by: Kenji Kaneshige Acked-by: Satoru Takeuchi Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Tony Luck --- arch/ia64/kernel/smp.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/ia64') diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index 657ac99a451..2763e791778 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -328,10 +328,14 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic, int wait) { struct call_data_struct data; - int cpus = num_online_cpus()-1; + int cpus; - if (!cpus) + spin_lock(&call_lock); + cpus = num_online_cpus() - 1; + if (!cpus) { + spin_unlock(&call_lock); return 0; + } /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); @@ -343,8 +347,6 @@ smp_call_function (void (*func) (void *info), void *info, int nonatomic, int wai if (wait) atomic_set(&data.finished, 0); - spin_lock(&call_lock); - call_data = &data; mb(); /* ensure store to call_data precedes setting of IPI_CALL_FUNC */ send_IPI_allbutself(IPI_CALL_FUNC); -- cgit v1.2.3 From 264b0f99308436deaee38bab99e586612d012fc1 Mon Sep 17 00:00:00 2001 From: Russ Anderson Date: Wed, 25 Oct 2006 17:59:47 -0500 Subject: [IA64] MCA recovery: Montecito support The information in MCA records is filled in slightly differently on Montecito than on Madison/McKinley. Usually, the cache check and bus check target identifiers have the same address. On Montecito the cache check and bus check target identifiers can be different if a corrected error (ie SBE or unconsumed poison data) was encountered and then an uncorrected error (ie DBE) was consumed. In that case, the cache check target identifier is the physical address of the DBE (that caused the MCA to surface) while the bus check target identifier is the physical address of the SBE. This patch correctly finds the target identifier that triggered the MCA. If there are multiple valid cache target identifiers in the same error record then use the one with the lowest cache level. Signed-off-by: Russ Anderson (rja@sgi.com) Signed-off-by: Tony Luck --- arch/ia64/kernel/mca_drv.c | 95 +++++++++++++++++++++++++++++++++------------- 1 file changed, 68 insertions(+), 27 deletions(-) (limited to 'arch/ia64') diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index a45009d2bc9..afc1403799c 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -434,6 +434,50 @@ is_mca_global(peidx_table_t *peidx, pal_bus_check_info_t *pbci, return MCA_IS_GLOBAL; } +/** + * get_target_identifier - Get the valid Cache or Bus check target identifier. + * @peidx: pointer of index of processor error section + * + * Return value: + * target address on Success / 0 on Failue + */ +static u64 +get_target_identifier(peidx_table_t *peidx) +{ + u64 target_address = 0; + sal_log_mod_error_info_t *smei; + pal_cache_check_info_t *pcci; + int i, level = 9; + + /* + * Look through the cache checks for a valid target identifier + * If more than one valid target identifier, return the one + * with the lowest cache level. + */ + for (i = 0; i < peidx_cache_check_num(peidx); i++) { + smei = (sal_log_mod_error_info_t *)peidx_cache_check(peidx, i); + if (smei->valid.target_identifier && smei->target_identifier) { + pcci = (pal_cache_check_info_t *)&(smei->check_info); + if (!target_address || (pcci->level < level)) { + target_address = smei->target_identifier; + level = pcci->level; + continue; + } + } + } + if (target_address) + return target_address; + + /* + * Look at the bus check for a valid target identifier + */ + smei = peidx_bus_check(peidx, 0); + if (smei && smei->valid.target_identifier) + return smei->target_identifier; + + return 0; +} + /** * recover_from_read_error - Try to recover the errors which type are "read"s. * @slidx: pointer of index of SAL error record @@ -450,13 +494,14 @@ recover_from_read_error(slidx_table_t *slidx, peidx_table_t *peidx, pal_bus_check_info_t *pbci, struct ia64_sal_os_state *sos) { - sal_log_mod_error_info_t *smei; + u64 target_identifier; pal_min_state_area_t *pmsa; struct ia64_psr *psr1, *psr2; ia64_fptr_t *mca_hdlr_bh = (ia64_fptr_t*)mca_handler_bhhook; /* Is target address valid? */ - if (!pbci->tv) + target_identifier = get_target_identifier(peidx); + if (!target_identifier) return fatal_mca("target address not valid"); /* @@ -487,32 +532,28 @@ recover_from_read_error(slidx_table_t *slidx, pmsa = sos->pal_min_state; if (psr1->cpl != 0 || ((psr2->cpl != 0) && mca_recover_range(pmsa->pmsa_iip))) { - smei = peidx_bus_check(peidx, 0); - if (smei->valid.target_identifier) { - /* - * setup for resume to bottom half of MCA, - * "mca_handler_bhhook" - */ - /* pass to bhhook as argument (gr8, ...) */ - pmsa->pmsa_gr[8-1] = smei->target_identifier; - pmsa->pmsa_gr[9-1] = pmsa->pmsa_iip; - pmsa->pmsa_gr[10-1] = pmsa->pmsa_ipsr; - /* set interrupted return address (but no use) */ - pmsa->pmsa_br0 = pmsa->pmsa_iip; - /* change resume address to bottom half */ - pmsa->pmsa_iip = mca_hdlr_bh->fp; - pmsa->pmsa_gr[1-1] = mca_hdlr_bh->gp; - /* set cpl with kernel mode */ - psr2 = (struct ia64_psr *)&pmsa->pmsa_ipsr; - psr2->cpl = 0; - psr2->ri = 0; - psr2->bn = 1; - psr2->i = 0; - - return mca_recovered("user memory corruption. " + /* + * setup for resume to bottom half of MCA, + * "mca_handler_bhhook" + */ + /* pass to bhhook as argument (gr8, ...) */ + pmsa->pmsa_gr[8-1] = target_identifier; + pmsa->pmsa_gr[9-1] = pmsa->pmsa_iip; + pmsa->pmsa_gr[10-1] = pmsa->pmsa_ipsr; + /* set interrupted return address (but no use) */ + pmsa->pmsa_br0 = pmsa->pmsa_iip; + /* change resume address to bottom half */ + pmsa->pmsa_iip = mca_hdlr_bh->fp; + pmsa->pmsa_gr[1-1] = mca_hdlr_bh->gp; + /* set cpl with kernel mode */ + psr2 = (struct ia64_psr *)&pmsa->pmsa_ipsr; + psr2->cpl = 0; + psr2->ri = 0; + psr2->bn = 1; + psr2->i = 0; + + return mca_recovered("user memory corruption. " "kill affected process - recovered."); - } - } return fatal_mca("kernel context not recovered, iip 0x%lx\n", -- cgit v1.2.3 From fa1d19e5d9a94120f31e5783ab44758f46892d94 Mon Sep 17 00:00:00 2001 From: Troy Heber Date: Wed, 25 Oct 2006 14:46:15 -0600 Subject: [IA64] move SAL_CACHE_FLUSH check later in boot The check to see if the firmware drops interrupts during a SAL_CACHE_FLUSH is done to early in the boot. SAL_CACHE_FLUSH expects to be able to make PAL calls in virtual mode, on some cell based machines a fault occurs causing a MCA. This patch moves the check after mmu_context_init so the TLB and VHPT are properly setup. Signed-off-by Troy Heber Signed-off-by: Tony Luck --- arch/ia64/kernel/sal.c | 11 +++++++---- arch/ia64/kernel/setup.c | 2 ++ 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'arch/ia64') diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c index 642fdc7b969..20bad78b507 100644 --- a/arch/ia64/kernel/sal.c +++ b/arch/ia64/kernel/sal.c @@ -223,12 +223,13 @@ static void __init sal_desc_ap_wakeup(void *p) { } */ static int sal_cache_flush_drops_interrupts; -static void __init +void __init check_sal_cache_flush (void) { unsigned long flags; int cpu; - u64 vector; + u64 vector, cache_type = 3; + struct ia64_sal_retval isrv; cpu = get_cpu(); local_irq_save(flags); @@ -243,7 +244,10 @@ check_sal_cache_flush (void) while (!ia64_get_irr(IA64_TIMER_VECTOR)) cpu_relax(); - ia64_sal_cache_flush(3); + SAL_CALL(isrv, SAL_CACHE_FLUSH, cache_type, 0, 0, 0, 0, 0, 0); + + if (isrv.status) + printk(KERN_ERR "SAL_CAL_FLUSH failed with %ld\n", isrv.status); if (ia64_get_irr(IA64_TIMER_VECTOR)) { vector = ia64_get_ivr(); @@ -331,7 +335,6 @@ ia64_sal_init (struct ia64_sal_systab *systab) p += SAL_DESC_SIZE(*p); } - check_sal_cache_flush(); } int diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index c4caa800349..d10404a4175 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -457,6 +457,8 @@ setup_arch (char **cmdline_p) cpu_init(); /* initialize the bootstrap CPU */ mmu_context_init(); /* initialize context_id bitmap */ + check_sal_cache_flush(); + #ifdef CONFIG_ACPI acpi_boot_init(); #endif -- cgit v1.2.3 From 024e4f2c5175a482c234cf67ed22368d770bf78f Mon Sep 17 00:00:00 2001 From: Keith Owens Date: Wed, 18 Oct 2006 15:36:49 +1000 Subject: [IA64] Correct definition of handle_IPI The declaration of handle_IPI in arch/ia64/kernel/smp.c was changed but not the definition of this function. Remove struct pt_regs from handle_IPI(). Signed-off-by: Keith Owens Signed-off-by: Tony Luck --- arch/ia64/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/ia64') diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index 2763e791778..6ab95ceaf9d 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -108,7 +108,7 @@ cpu_die(void) } irqreturn_t -handle_IPI (int irq, void *dev_id, struct pt_regs *regs) +handle_IPI (int irq, void *dev_id) { int this_cpu = get_cpu(); unsigned long *pending_ipis = &__ia64_per_cpu_var(ipi_operation); -- cgit v1.2.3