Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753352AbZIXRlQ (ORCPT ); Thu, 24 Sep 2009 13:41:16 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753120AbZIXRlO (ORCPT ); Thu, 24 Sep 2009 13:41:14 -0400 Received: from casper.infradead.org ([85.118.1.10]:55759 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753152AbZIXRko (ORCPT ); Thu, 24 Sep 2009 13:40:44 -0400 Date: Thu, 24 Sep 2009 10:40:16 -0700 From: Greg KH To: linux-kernel@vger.kernel.org, Andrew Morton , torvalds@linux-foundation.org, stable@kernel.org Cc: lwn@lwn.net Subject: Re: Linux 2.6.31.1 Message-ID: <20090924174016.GF17077@kroah.com> References: <20090924174002.GE17077@kroah.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090924174002.GE17077@kroah.com> User-Agent: Mutt/1.5.17 (2007-11-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 84446 Lines: 2508 diff --git a/Makefile b/Makefile index 60de4ef..ea8734a 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 31 -EXTRAVERSION = +EXTRAVERSION = .1 NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index a34954d..73cae57 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -40,11 +40,16 @@ void *kmap_atomic(struct page *page, enum km_type type) { unsigned int idx; unsigned long vaddr; + void *kmap; pagefault_disable(); if (!PageHighMem(page)) return page_address(page); + kmap = kmap_high_get(page); + if (kmap) + return kmap; + idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM @@ -80,6 +85,9 @@ void kunmap_atomic(void *kvaddr, enum km_type type) #else (void) idx; /* to kill a warning */ #endif + } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { + /* this address was obtained through kmap_high_get() */ + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); } pagefault_enable(); } diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 98c104a..edab67e 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -41,6 +41,7 @@ extern char initial_stab[]; #define SLB_NUM_BOLTED 3 #define SLB_CACHE_ENTRIES 8 +#define SLB_MIN_SIZE 32 /* Bits in the SLB ESID word */ #define SLB_ESID_V ASM_CONST(0x0000000008000000) /* valid */ @@ -296,6 +297,7 @@ extern void slb_flush_and_rebolt(void); extern void stab_initialize(unsigned long stab); extern void slb_vmalloc_update(void); +extern void slb_set_size(u16 size); #endif /* __ASSEMBLY__ */ /* diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h index d6a616a..ccc68b5 100644 --- a/arch/powerpc/include/asm/pmc.h +++ b/arch/powerpc/include/asm/pmc.h @@ -27,10 +27,22 @@ extern perf_irq_t perf_irq; int reserve_pmc_hardware(perf_irq_t new_perf_irq); void release_pmc_hardware(void); +void ppc_enable_pmcs(void); #ifdef CONFIG_PPC64 -void power4_enable_pmcs(void); -void pasemi_enable_pmcs(void); +#include + +static inline void ppc_set_pmu_inuse(int inuse) +{ + get_lppaca()->pmcregs_in_use = inuse; +} + +extern void power4_enable_pmcs(void); + +#else /* CONFIG_PPC64 */ + +static inline void ppc_set_pmu_inuse(int inuse) { } + #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 2419cc7..ed0ac4e 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -35,6 +35,7 @@ #include #include #include +#include #define MODULE_VERS "1.8" #define MODULE_NAME "lparcfg" @@ -537,6 +538,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) seq_printf(m, "shared_processor_mode=%d\n", lppaca[0].shared_proc); + seq_printf(m, "slb_size=%d\n", mmu_slb_size); + return 0; } diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c index 70e1f57..7ceefaf 100644 --- a/arch/powerpc/kernel/perf_counter.c +++ b/arch/powerpc/kernel/perf_counter.c @@ -32,6 +32,9 @@ struct cpu_hw_counters { unsigned long mmcr[3]; struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS]; u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS]; + u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + unsigned long amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + unsigned long avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; }; DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters); @@ -62,7 +65,6 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { return 0; } -static inline void perf_set_pmu_inuse(int inuse) { } static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { } static inline u32 perf_get_misc_flags(struct pt_regs *regs) { @@ -93,11 +95,6 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) return 0; } -static inline void perf_set_pmu_inuse(int inuse) -{ - get_lppaca()->pmcregs_in_use = inuse; -} - /* * The user wants a data address recorded. * If we're not doing instruction sampling, give them the SDAR @@ -245,13 +242,11 @@ static void write_pmc(int idx, unsigned long val) * and see if any combination of alternative codes is feasible. * The feasible set is returned in event[]. */ -static int power_check_constraints(u64 event[], unsigned int cflags[], +static int power_check_constraints(struct cpu_hw_counters *cpuhw, + u64 event[], unsigned int cflags[], int n_ev) { unsigned long mask, value, nv; - u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; - unsigned long amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; - unsigned long avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; unsigned long smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS]; int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS]; int i, j; @@ -266,21 +261,23 @@ static int power_check_constraints(u64 event[], unsigned int cflags[], if ((cflags[i] & PPMU_LIMITED_PMC_REQD) && !ppmu->limited_pmc_event(event[i])) { ppmu->get_alternatives(event[i], cflags[i], - alternatives[i]); - event[i] = alternatives[i][0]; + cpuhw->alternatives[i]); + event[i] = cpuhw->alternatives[i][0]; } - if (ppmu->get_constraint(event[i], &amasks[i][0], - &avalues[i][0])) + if (ppmu->get_constraint(event[i], &cpuhw->amasks[i][0], + &cpuhw->avalues[i][0])) return -1; } value = mask = 0; for (i = 0; i < n_ev; ++i) { - nv = (value | avalues[i][0]) + (value & avalues[i][0] & addf); + nv = (value | cpuhw->avalues[i][0]) + + (value & cpuhw->avalues[i][0] & addf); if ((((nv + tadd) ^ value) & mask) != 0 || - (((nv + tadd) ^ avalues[i][0]) & amasks[i][0]) != 0) + (((nv + tadd) ^ cpuhw->avalues[i][0]) & + cpuhw->amasks[i][0]) != 0) break; value = nv; - mask |= amasks[i][0]; + mask |= cpuhw->amasks[i][0]; } if (i == n_ev) return 0; /* all OK */ @@ -291,10 +288,11 @@ static int power_check_constraints(u64 event[], unsigned int cflags[], for (i = 0; i < n_ev; ++i) { choice[i] = 0; n_alt[i] = ppmu->get_alternatives(event[i], cflags[i], - alternatives[i]); + cpuhw->alternatives[i]); for (j = 1; j < n_alt[i]; ++j) - ppmu->get_constraint(alternatives[i][j], - &amasks[i][j], &avalues[i][j]); + ppmu->get_constraint(cpuhw->alternatives[i][j], + &cpuhw->amasks[i][j], + &cpuhw->avalues[i][j]); } /* enumerate all possibilities and see if any will work */ @@ -313,11 +311,11 @@ static int power_check_constraints(u64 event[], unsigned int cflags[], * where k > j, will satisfy the constraints. */ while (++j < n_alt[i]) { - nv = (value | avalues[i][j]) + - (value & avalues[i][j] & addf); + nv = (value | cpuhw->avalues[i][j]) + + (value & cpuhw->avalues[i][j] & addf); if ((((nv + tadd) ^ value) & mask) == 0 && - (((nv + tadd) ^ avalues[i][j]) - & amasks[i][j]) == 0) + (((nv + tadd) ^ cpuhw->avalues[i][j]) + & cpuhw->amasks[i][j]) == 0) break; } if (j >= n_alt[i]) { @@ -339,7 +337,7 @@ static int power_check_constraints(u64 event[], unsigned int cflags[], svalues[i] = value; smasks[i] = mask; value = nv; - mask |= amasks[i][j]; + mask |= cpuhw->amasks[i][j]; ++i; j = -1; } @@ -347,7 +345,7 @@ static int power_check_constraints(u64 event[], unsigned int cflags[], /* OK, we have a feasible combination, tell the caller the solution */ for (i = 0; i < n_ev; ++i) - event[i] = alternatives[i][choice[i]]; + event[i] = cpuhw->alternatives[i][choice[i]]; return 0; } @@ -531,8 +529,7 @@ void hw_perf_disable(void) * Check if we ever enabled the PMU on this cpu. */ if (!cpuhw->pmcs_enabled) { - if (ppc_md.enable_pmcs) - ppc_md.enable_pmcs(); + ppc_enable_pmcs(); cpuhw->pmcs_enabled = 1; } @@ -594,7 +591,7 @@ void hw_perf_enable(void) mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); if (cpuhw->n_counters == 0) - perf_set_pmu_inuse(0); + ppc_set_pmu_inuse(0); goto out_enable; } @@ -627,7 +624,7 @@ void hw_perf_enable(void) * bit set and set the hardware counters to their initial values. * Then unfreeze the counters. */ - perf_set_pmu_inuse(1); + ppc_set_pmu_inuse(1); mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)) @@ -752,7 +749,7 @@ int hw_perf_group_sched_in(struct perf_counter *group_leader, return -EAGAIN; if (check_excludes(cpuhw->counter, cpuhw->flags, n0, n)) return -EAGAIN; - i = power_check_constraints(cpuhw->events, cpuhw->flags, n + n0); + i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n + n0); if (i < 0) return -EAGAIN; cpuhw->n_counters = n0 + n; @@ -807,7 +804,7 @@ static int power_pmu_enable(struct perf_counter *counter) cpuhw->flags[n0] = counter->hw.counter_base; if (check_excludes(cpuhw->counter, cpuhw->flags, n0, 1)) goto out; - if (power_check_constraints(cpuhw->events, cpuhw->flags, n0 + 1)) + if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1)) goto out; counter->hw.config = cpuhw->events[n0]; @@ -1012,6 +1009,7 @@ const struct pmu *hw_perf_counter_init(struct perf_counter *counter) unsigned int cflags[MAX_HWCOUNTERS]; int n; int err; + struct cpu_hw_counters *cpuhw; if (!ppmu) return ERR_PTR(-ENXIO); @@ -1090,7 +1088,11 @@ const struct pmu *hw_perf_counter_init(struct perf_counter *counter) cflags[n] = flags; if (check_excludes(ctrs, cflags, n, 1)) return ERR_PTR(-EINVAL); - if (power_check_constraints(events, cflags, n + 1)) + + cpuhw = &get_cpu_var(cpu_hw_counters); + err = power_check_constraints(cpuhw, events, cflags, n + 1); + put_cpu_var(cpu_hw_counters); + if (err) return ERR_PTR(-EINVAL); counter->hw.config = events[n]; diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index c434823..bf90361 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -39,6 +39,7 @@ #include #include #include +#include struct rtas_t rtas = { .lock = __RAW_SPIN_LOCK_UNLOCKED @@ -713,6 +714,7 @@ static void rtas_percpu_suspend_me(void *info) { long rc = H_SUCCESS; unsigned long msr_save; + u16 slb_size = mmu_slb_size; int cpu; struct rtas_suspend_me_data *data = (struct rtas_suspend_me_data *)info; @@ -735,13 +737,16 @@ static void rtas_percpu_suspend_me(void *info) /* All other cpus are in H_JOIN, this cpu does * the suspend. */ + slb_set_size(SLB_MIN_SIZE); printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id()); data->error = rtas_call(data->token, 0, 1, NULL); - if (data->error) + if (data->error) { printk(KERN_DEBUG "ibm,suspend-me returned %d\n", data->error); + slb_set_size(slb_size); + } } else { printk(KERN_ERR "H_JOIN on cpu %i failed with rc = %ld\n", smp_processor_id(), rc); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index f41aec8..956ab33 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "cacheinfo.h" @@ -123,6 +124,8 @@ static DEFINE_PER_CPU(char, pmcs_enabled); void ppc_enable_pmcs(void) { + ppc_set_pmu_inuse(1); + /* Only need to enable them once */ if (__get_cpu_var(pmcs_enabled)) return; diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 5b7038f..deb6193 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -240,14 +240,22 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) static inline void patch_slb_encoding(unsigned int *insn_addr, unsigned int immed) { - /* Assume the instruction had a "0" immediate value, just - * "or" in the new value - */ - *insn_addr |= immed; + *insn_addr = (*insn_addr & 0xffff0000) | immed; flush_icache_range((unsigned long)insn_addr, 4+ (unsigned long)insn_addr); } +void slb_set_size(u16 size) +{ + extern unsigned int *slb_compare_rr_to_size; + + if (mmu_slb_size == size) + return; + + mmu_slb_size = size; + patch_slb_encoding(slb_compare_rr_to_size, mmu_slb_size); +} + void slb_initialize(void) { unsigned long linear_llp, vmalloc_llp, io_llp; diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index b6f1b13..2e2bbe1 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -20,6 +20,7 @@ #include #include #include +#include @@ -439,9 +440,15 @@ static int do_update_property(char *buf, size_t bufsize) if (!newprop) return -ENOMEM; + if (!strcmp(name, "slb-size") || !strcmp(name, "ibm,slb-size")) + slb_set_size(*(int *)value); + oldprop = of_find_property(np, name,NULL); - if (!oldprop) + if (!oldprop) { + if (strlen(name)) + return prom_add_property(np, newprop); return -ENODEV; + } rc = prom_update_property(np, newprop, oldprop); if (rc) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8d75ea2..ca5f2e1 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -223,10 +223,6 @@ static void pseries_lpar_enable_pmcs(void) set = 1UL << 63; reset = 0; plpar_hcall_norets(H_PERFMON, set, reset); - - /* instruct hypervisor to maintain PMCs */ - if (firmware_has_feature(FW_FEATURE_SPLPAR)) - get_lppaca()->pmcregs_in_use = 1; } static void __init pseries_discover_pic(void) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index eabdc1c..68d16d2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -618,6 +618,7 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, u32 error_code); +bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); int kvm_pic_set_irq(void *opaque, int irq, int level); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c776826..e597ecc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -403,7 +403,17 @@ extern unsigned long kernel_eflags; extern asmlinkage void ignore_sysret(void); #else /* X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR -DECLARE_PER_CPU(unsigned long, stack_canary); +/* + * Make sure stack canary segment base is cached-aligned: + * "For Intel Atom processors, avoid non zero segment base address + * that is not aligned to cache line boundary at all cost." + * (Optim Ref Manual Assembly/Compiler Coding Rule 15.) + */ +struct stack_canary { + char __pad[20]; /* canary at %gs:20 */ + unsigned long canary; +}; +DECLARE_PER_CPU(struct stack_canary, stack_canary) ____cacheline_aligned; #endif #endif /* X86_64 */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index c2d742c..decad97 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -78,14 +78,14 @@ static __always_inline void boot_init_stack_canary(void) #ifdef CONFIG_X86_64 percpu_write(irq_stack_union.stack_canary, canary); #else - percpu_write(stack_canary, canary); + percpu_write(stack_canary.canary, canary); #endif } static inline void setup_stack_canary_segment(int cpu) { #ifdef CONFIG_X86_32 - unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu) - 20; + unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu); struct desc_struct *gdt_table = get_cpu_gdt_table(cpu); struct desc_struct desc; diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index 643c59b..5bd119b 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -31,7 +31,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, "movl %P[task_canary](%[next]), %%ebx\n\t" \ "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" #define __switch_canary_oparam \ - , [stack_canary] "=m" (per_cpu_var(stack_canary)) + , [stack_canary] "=m" (per_cpu_var(stack_canary.canary)) #define __switch_canary_iparam \ , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) #else /* CC_STACKPROTECTOR */ diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 6c99f50..4607241 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -485,8 +485,6 @@ void amd_iommu_flush_all_devices(void) int i; for (i = 0; i <= amd_iommu_last_bdf; ++i) { - if (amd_iommu_pd_table[i] == NULL) - continue; iommu = amd_iommu_rlookup_table[i]; if (!iommu) diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 8952a58..89174f8 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -167,7 +167,7 @@ static int es7000_apic_is_cluster(void) { /* MPENTIUMIII */ if (boot_cpu_data.x86 == 6 && - (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) + (boot_cpu_data.x86_model >= 7 && boot_cpu_data.x86_model <= 11)) return 1; return 0; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5ce60a8..e338b5c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1043,7 +1043,7 @@ DEFINE_PER_CPU(struct orig_ist, orig_ist); #else /* CONFIG_X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR -DEFINE_PER_CPU(unsigned long, stack_canary); +DEFINE_PER_CPU(struct stack_canary, stack_canary) ____cacheline_aligned; #endif /* Make sure %fs and %gs are initialized properly in idle threads */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index cc827ac..7ffec6b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -439,7 +439,6 @@ is386: movl $2,%ecx # set MP jne 1f movl $per_cpu__gdt_page,%eax movl $per_cpu__stack_canary,%ecx - subl $20, %ecx movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax) shrl $16, %ecx movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index c664d51..63b0ec8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -34,7 +34,6 @@ struct kvm_para_state { u8 mmu_queue[MMU_QUEUE_SIZE]; int mmu_queue_len; - enum paravirt_lazy_mode mode; }; static DEFINE_PER_CPU(struct kvm_para_state, para_state); @@ -77,7 +76,7 @@ static void kvm_deferred_mmu_op(void *buffer, int len) { struct kvm_para_state *state = kvm_para_state(); - if (state->mode != PARAVIRT_LAZY_MMU) { + if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) { kvm_mmu_op(buffer, len); return; } @@ -185,10 +184,7 @@ static void kvm_release_pt(unsigned long pfn) static void kvm_enter_lazy_mmu(void) { - struct kvm_para_state *state = kvm_para_state(); - paravirt_enter_lazy_mmu(); - state->mode = paravirt_get_lazy_mode(); } static void kvm_leave_lazy_mmu(void) @@ -197,7 +193,6 @@ static void kvm_leave_lazy_mmu(void) mmu_queue_flush(state); paravirt_leave_lazy_mmu(); - state->mode = paravirt_get_lazy_mode(); } static void __init paravirt_ops_setup(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 223af43..e5efcdc 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -50,8 +50,8 @@ static unsigned long kvm_get_wallclock(void) struct timespec ts; int low, high; - low = (int)__pa(&wall_clock); - high = ((u64)__pa(&wall_clock) >> 32); + low = (int)__pa_symbol(&wall_clock); + high = ((u64)__pa_symbol(&wall_clock) >> 32); native_write_msr(MSR_KVM_WALL_CLOCK, low, high); vcpu_time = &get_cpu_var(hv_clock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ae99d83..bb6277d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -573,6 +573,15 @@ static void start_apic_timer(struct kvm_lapic *apic) if (!apic->lapic_timer.period) return; + /* + * Do not allow the guest to program periodic timers with small + * interval, since the hrtimers are not throttled by the host + * scheduler. + */ + if (apic_lvtt_period(apic)) { + if (apic->lapic_timer.period < NSEC_PER_MSEC/2) + apic->lapic_timer.period = NSEC_PER_MSEC/2; + } hrtimer_start(&apic->lapic_timer.timer, ktime_add_ns(now, apic->lapic_timer.period), diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 0ef5bb2..a5cdb35 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2633,7 +2633,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { - while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES) { + while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES && + !list_empty(&vcpu->kvm->arch.active_mmu_pages)) { struct kvm_mmu_page *sp; sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 29f9129..b5fa966 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1217,12 +1217,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { /* CR3 accesses and invlpg don't need to cause VM Exits when EPT enabled */ - min &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) - return -EIO; + _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | + CPU_BASED_INVLPG_EXITING); rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, vmx_capability.ept, vmx_capability.vpid); } @@ -2841,6 +2838,8 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) unsigned long val; int dr, reg; + if (!kvm_require_cpl(vcpu, 0)) + return 1; dr = vmcs_readl(GUEST_DR7); if (dr & DR7_GD) { /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3d45290..3d36045 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -215,6 +215,19 @@ static void __queue_exception(struct kvm_vcpu *vcpu) } /* + * Checks if cpl <= required_cpl; if true, return true. Otherwise queue + * a #GP and return false. + */ +bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) +{ + if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl) + return true; + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return false; +} +EXPORT_SYMBOL_GPL(kvm_require_cpl); + +/* * Load the pae pdptrs. Return true is they are all valid. */ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) @@ -2898,6 +2911,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } + if (kvm_x86_ops->get_cpl(vcpu) != 0) { + ret = -KVM_EPERM; + goto out; + } + switch (nr) { case KVM_HC_VAPIC_POLL_IRQ: ret = 0; @@ -2909,6 +2927,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) ret = -KVM_ENOSYS; break; } +out: kvm_register_write(vcpu, VCPU_REGS_RAX, ret); ++vcpu->stat.hypercalls; return r; diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index 616de46..ef4dfca 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -60,6 +60,7 @@ #define SrcImmByte (6<<4) /* 8-bit sign-extended immediate operand. */ #define SrcOne (7<<4) /* Implied '1' */ #define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ +#define SrcImmU (9<<4) /* Immediate operand, unsigned */ #define SrcMask (0xf<<4) /* Generic ModRM decode. */ #define ModRM (1<<8) @@ -195,7 +196,7 @@ static u32 opcode_table[256] = { ByteOp | SrcImmUByte, SrcImmUByte, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImm | Src2Imm16, SrcImmByte | ImplicitOps, + SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* 0xF0 - 0xF7 */ @@ -1027,6 +1028,7 @@ done_prefixes: c->src.type = OP_MEM; break; case SrcImm: + case SrcImmU: c->src.type = OP_IMM; c->src.ptr = (unsigned long *)c->eip; c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; @@ -1044,6 +1046,19 @@ done_prefixes: c->src.val = insn_fetch(s32, 4, c->eip); break; } + if ((c->d & SrcMask) == SrcImmU) { + switch (c->src.bytes) { + case 1: + c->src.val &= 0xff; + break; + case 2: + c->src.val &= 0xffff; + break; + case 4: + c->src.val &= 0xffffffff; + break; + } + } break; case SrcImmByte: case SrcImmUByte: diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 7e600c1..e245775 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -822,6 +822,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, { struct cpa_data cpa; int ret, cache, checkalias; + unsigned long baddr = 0; /* * Check, if we are requested to change a not supported @@ -853,6 +854,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, */ WARN_ON_ONCE(1); } + /* + * Save address for cache flush. *addr is modified in the call + * to __change_page_attr_set_clr() below. + */ + baddr = *addr; } /* Must avoid aliasing mappings in the highmem code */ @@ -900,7 +906,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, cpa_flush_array(addr, numpages, cache, cpa.flags, pages); } else - cpa_flush_range(*addr, numpages, cache); + cpa_flush_range(baddr, numpages, cache); } else cpa_flush_all(cache); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index d3aa2aa..b78c9c3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -40,7 +40,12 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) { struct request_list *rl = &q->rq; unsigned long nr; - int ret = queue_var_store(&nr, page, count); + int ret; + + if (!q->request_fn) + return -EINVAL; + + ret = queue_var_store(&nr, page, count); if (nr < BLKDEV_MIN_RQ) nr = BLKDEV_MIN_RQ; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 072ba5e..e71149b 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -709,7 +709,13 @@ u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev) head = tf->device & 0xf; sect = tf->lbal; - block = (cyl * dev->heads + head) * dev->sectors + sect; + if (!sect) { + ata_dev_printk(dev, KERN_WARNING, "device reported " + "invalid CHS sector 0\n"); + sect = 1; /* oh well */ + } + + block = (cyl * dev->heads + head) * dev->sectors + sect - 1; } return block; diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index c585577..dee0f1f 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -2313,15 +2313,6 @@ static int agp_intel_resume(struct pci_dev *pdev) struct agp_bridge_data *bridge = pci_get_drvdata(pdev); int ret_val; - pci_restore_state(pdev); - - /* We should restore our graphics device's config space, - * as host bridge (00:00) resumes before graphics device (02:00), - * then our access to its pci space can work right. - */ - if (intel_private.pcidev) - pci_restore_state(intel_private.pcidev); - if (bridge->driver == &intel_generic_driver) intel_configure(); else if (bridge->driver == &intel_850_driver) diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index aec1931..0b73e4e 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -450,6 +450,12 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, goto out_err; } + /* Default timeouts */ + chip->vendor.timeout_a = msecs_to_jiffies(TIS_SHORT_TIMEOUT); + chip->vendor.timeout_b = msecs_to_jiffies(TIS_LONG_TIMEOUT); + chip->vendor.timeout_c = msecs_to_jiffies(TIS_SHORT_TIMEOUT); + chip->vendor.timeout_d = msecs_to_jiffies(TIS_SHORT_TIMEOUT); + if (request_locality(chip, 0) != 0) { rc = -ENODEV; goto out_err; @@ -457,12 +463,6 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, vendor = ioread32(chip->vendor.iobase + TPM_DID_VID(0)); - /* Default timeouts */ - chip->vendor.timeout_a = msecs_to_jiffies(TIS_SHORT_TIMEOUT); - chip->vendor.timeout_b = msecs_to_jiffies(TIS_LONG_TIMEOUT); - chip->vendor.timeout_c = msecs_to_jiffies(TIS_SHORT_TIMEOUT); - chip->vendor.timeout_d = msecs_to_jiffies(TIS_SHORT_TIMEOUT); - dev_info(dev, "1.2 TPM (device-id 0x%X, rev-id %d)\n", vendor >> 16, ioread8(chip->vendor.iobase + TPM_RID(0))); diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 6e186b1..652bd33 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -582,7 +582,7 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type, break; case STATUSTYPE_TABLE: sz = 0; - table_args = strstr(lc->usr_argv_str, " "); + table_args = strchr(lc->usr_argv_str, ' '); BUG_ON(!table_args); /* There will always be a ' ' */ table_args++; diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c index b9ceddd..4ff665c 100644 --- a/drivers/net/mlx4/eq.c +++ b/drivers/net/mlx4/eq.c @@ -526,48 +526,6 @@ static void mlx4_unmap_clr_int(struct mlx4_dev *dev) iounmap(priv->clr_base); } -int mlx4_map_eq_icm(struct mlx4_dev *dev, u64 icm_virt) -{ - struct mlx4_priv *priv = mlx4_priv(dev); - int ret; - - /* - * We assume that mapping one page is enough for the whole EQ - * context table. This is fine with all current HCAs, because - * we only use 32 EQs and each EQ uses 64 bytes of context - * memory, or 1 KB total. - */ - priv->eq_table.icm_virt = icm_virt; - priv->eq_table.icm_page = alloc_page(GFP_HIGHUSER); - if (!priv->eq_table.icm_page) - return -ENOMEM; - priv->eq_table.icm_dma = pci_map_page(dev->pdev, priv->eq_table.icm_page, 0, - PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(dev->pdev, priv->eq_table.icm_dma)) { - __free_page(priv->eq_table.icm_page); - return -ENOMEM; - } - - ret = mlx4_MAP_ICM_page(dev, priv->eq_table.icm_dma, icm_virt); - if (ret) { - pci_unmap_page(dev->pdev, priv->eq_table.icm_dma, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL); - __free_page(priv->eq_table.icm_page); - } - - return ret; -} - -void mlx4_unmap_eq_icm(struct mlx4_dev *dev) -{ - struct mlx4_priv *priv = mlx4_priv(dev); - - mlx4_UNMAP_ICM(dev, priv->eq_table.icm_virt, 1); - pci_unmap_page(dev->pdev, priv->eq_table.icm_dma, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL); - __free_page(priv->eq_table.icm_page); -} - int mlx4_alloc_eq_table(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c index dac621b..8e8b79f 100644 --- a/drivers/net/mlx4/main.c +++ b/drivers/net/mlx4/main.c @@ -525,7 +525,10 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap, goto err_unmap_aux; } - err = mlx4_map_eq_icm(dev, init_hca->eqc_base); + err = mlx4_init_icm_table(dev, &priv->eq_table.table, + init_hca->eqc_base, dev_cap->eqc_entry_sz, + dev->caps.num_eqs, dev->caps.num_eqs, + 0, 0); if (err) { mlx4_err(dev, "Failed to map EQ context memory, aborting.\n"); goto err_unmap_cmpt; @@ -668,7 +671,7 @@ err_unmap_mtt: mlx4_cleanup_icm_table(dev, &priv->mr_table.mtt_table); err_unmap_eq: - mlx4_unmap_eq_icm(dev); + mlx4_cleanup_icm_table(dev, &priv->eq_table.table); err_unmap_cmpt: mlx4_cleanup_icm_table(dev, &priv->eq_table.cmpt_table); @@ -698,11 +701,11 @@ static void mlx4_free_icms(struct mlx4_dev *dev) mlx4_cleanup_icm_table(dev, &priv->qp_table.qp_table); mlx4_cleanup_icm_table(dev, &priv->mr_table.dmpt_table); mlx4_cleanup_icm_table(dev, &priv->mr_table.mtt_table); + mlx4_cleanup_icm_table(dev, &priv->eq_table.table); mlx4_cleanup_icm_table(dev, &priv->eq_table.cmpt_table); mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table); mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table); mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table); - mlx4_unmap_eq_icm(dev); mlx4_UNMAP_ICM_AUX(dev); mlx4_free_icm(dev, priv->fw.aux_icm, 0); diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h index 5bd79c2..bc72d6e 100644 --- a/drivers/net/mlx4/mlx4.h +++ b/drivers/net/mlx4/mlx4.h @@ -205,9 +205,7 @@ struct mlx4_eq_table { void __iomem **uar_map; u32 clr_mask; struct mlx4_eq *eq; - u64 icm_virt; - struct page *icm_page; - dma_addr_t icm_dma; + struct mlx4_icm_table table; struct mlx4_icm_table cmpt_table; int have_irq; u8 inta_pin; @@ -373,9 +371,6 @@ u64 mlx4_make_profile(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap, struct mlx4_init_hca_param *init_hca); -int mlx4_map_eq_icm(struct mlx4_dev *dev, u64 icm_virt); -void mlx4_unmap_eq_icm(struct mlx4_dev *dev); - int mlx4_cmd_init(struct mlx4_dev *dev); void mlx4_cmd_cleanup(struct mlx4_dev *dev); void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param); diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 029c1bc..ba6d225 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -2676,7 +2676,7 @@ ath5k_reset(struct ath5k_softc *sc, struct ieee80211_channel *chan) sc->curchan = chan; sc->curband = &sc->sbands[chan->band]; } - ret = ath5k_hw_reset(ah, sc->opmode, sc->curchan, true); + ret = ath5k_hw_reset(ah, sc->opmode, sc->curchan, chan != NULL); if (ret) { ATH5K_ERR(sc, "can't reset hardware (%d)\n", ret); goto err; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 06b9656..1073137 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1201,6 +1201,7 @@ static void __init asus_hides_smbus_hostbridge(struct pci_dev *dev) switch(dev->subsystem_device) { case 0x00b8: /* Compaq Evo D510 CMT */ case 0x00b9: /* Compaq Evo D510 SFF */ + case 0x00ba: /* Compaq Evo D510 USDT */ /* Motherboard doesn't have Host bridge * subvendor/subdevice IDs and on-board VGA * controller is disabled if an AGP card is @@ -2382,8 +2383,10 @@ static void __devinit nv_msi_ht_cap_quirk_leaf(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all); static void __devinit quirk_msi_intx_disable_bug(struct pci_dev *dev) { @@ -2492,6 +2495,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e6, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e7, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e8, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150a, quirk_i82576_sriov); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150d, quirk_i82576_sriov); #endif /* CONFIG_PCI_IOV */ diff --git a/drivers/ps3/ps3stor_lib.c b/drivers/ps3/ps3stor_lib.c index 18066d5..af0afa1 100644 --- a/drivers/ps3/ps3stor_lib.c +++ b/drivers/ps3/ps3stor_lib.c @@ -23,6 +23,65 @@ #include #include +/* + * A workaround for flash memory I/O errors when the internal hard disk + * has not been formatted for OtherOS use. Delay disk close until flash + * memory is closed. + */ + +static struct ps3_flash_workaround { + int flash_open; + int disk_open; + struct ps3_system_bus_device *disk_sbd; +} ps3_flash_workaround; + +static int ps3stor_open_hv_device(struct ps3_system_bus_device *sbd) +{ + int error = ps3_open_hv_device(sbd); + + if (error) + return error; + + if (sbd->match_id == PS3_MATCH_ID_STOR_FLASH) + ps3_flash_workaround.flash_open = 1; + + if (sbd->match_id == PS3_MATCH_ID_STOR_DISK) + ps3_flash_workaround.disk_open = 1; + + return 0; +} + +static int ps3stor_close_hv_device(struct ps3_system_bus_device *sbd) +{ + int error; + + if (sbd->match_id == PS3_MATCH_ID_STOR_DISK + && ps3_flash_workaround.disk_open + && ps3_flash_workaround.flash_open) { + ps3_flash_workaround.disk_sbd = sbd; + return 0; + } + + error = ps3_close_hv_device(sbd); + + if (error) + return error; + + if (sbd->match_id == PS3_MATCH_ID_STOR_DISK) + ps3_flash_workaround.disk_open = 0; + + if (sbd->match_id == PS3_MATCH_ID_STOR_FLASH) { + ps3_flash_workaround.flash_open = 0; + + if (ps3_flash_workaround.disk_sbd) { + ps3_close_hv_device(ps3_flash_workaround.disk_sbd); + ps3_flash_workaround.disk_open = 0; + ps3_flash_workaround.disk_sbd = NULL; + } + } + + return 0; +} static int ps3stor_probe_access(struct ps3_storage_device *dev) { @@ -90,7 +149,7 @@ int ps3stor_setup(struct ps3_storage_device *dev, irq_handler_t handler) int error, res, alignment; enum ps3_dma_page_size page_size; - error = ps3_open_hv_device(&dev->sbd); + error = ps3stor_open_hv_device(&dev->sbd); if (error) { dev_err(&dev->sbd.core, "%s:%u: ps3_open_hv_device failed %d\n", __func__, @@ -166,7 +225,7 @@ fail_free_irq: fail_sb_event_receive_port_destroy: ps3_sb_event_receive_port_destroy(&dev->sbd, dev->irq); fail_close_device: - ps3_close_hv_device(&dev->sbd); + ps3stor_close_hv_device(&dev->sbd); fail: return error; } @@ -193,7 +252,7 @@ void ps3stor_teardown(struct ps3_storage_device *dev) "%s:%u: destroy event receive port failed %d\n", __func__, __LINE__, error); - error = ps3_close_hv_device(&dev->sbd); + error = ps3stor_close_hv_device(&dev->sbd); if (error) dev_err(&dev->sbd.core, "%s:%u: ps3_close_hv_device failed %d\n", __func__, diff --git a/drivers/scsi/libsrp.c b/drivers/scsi/libsrp.c index 2742ae8..9ad38e8 100644 --- a/drivers/scsi/libsrp.c +++ b/drivers/scsi/libsrp.c @@ -124,6 +124,7 @@ static void srp_ring_free(struct device *dev, struct srp_buf **ring, size_t max, dma_free_coherent(dev, size, ring[i]->buf, ring[i]->dma); kfree(ring[i]); } + kfree(ring); } int srp_target_alloc(struct srp_target *target, struct device *dev, diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index 35a1386..2e4bc3d 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -94,7 +94,7 @@ _base_fault_reset_work(struct work_struct *work) int rc; spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->ioc_reset_in_progress) + if (ioc->shost_recovery) goto rearm_timer; spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); @@ -1542,6 +1542,8 @@ _base_display_ioc_capabilities(struct MPT2SAS_ADAPTER *ioc) (ioc->bios_pg3.BiosVersion & 0x0000FF00) >> 8, ioc->bios_pg3.BiosVersion & 0x000000FF); + _base_display_dell_branding(ioc); + printk(MPT2SAS_INFO_FMT "Protocol=(", ioc->name); if (ioc->facts.ProtocolFlags & MPI2_IOCFACTS_PROTOCOL_SCSI_INITIATOR) { @@ -1554,8 +1556,6 @@ _base_display_ioc_capabilities(struct MPT2SAS_ADAPTER *ioc) i++; } - _base_display_dell_branding(ioc); - i = 0; printk("), "); printk("Capabilities=("); @@ -1627,6 +1627,9 @@ _base_static_config_pages(struct MPT2SAS_ADAPTER *ioc) u32 iounit_pg1_flags; mpt2sas_config_get_manufacturing_pg0(ioc, &mpi_reply, &ioc->manu_pg0); + if (ioc->ir_firmware) + mpt2sas_config_get_manufacturing_pg10(ioc, &mpi_reply, + &ioc->manu_pg10); mpt2sas_config_get_bios_pg2(ioc, &mpi_reply, &ioc->bios_pg2); mpt2sas_config_get_bios_pg3(ioc, &mpi_reply, &ioc->bios_pg3); mpt2sas_config_get_ioc_pg8(ioc, &mpi_reply, &ioc->ioc_pg8); @@ -3501,20 +3504,13 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag, __func__)); spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->ioc_reset_in_progress) { + if (ioc->shost_recovery) { spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); printk(MPT2SAS_ERR_FMT "%s: busy\n", ioc->name, __func__); return -EBUSY; } - ioc->ioc_reset_in_progress = 1; ioc->shost_recovery = 1; - if (ioc->shost->shost_state == SHOST_RUNNING) { - /* set back to SHOST_RUNNING in mpt2sas_scsih.c */ - scsi_host_set_state(ioc->shost, SHOST_RECOVERY); - printk(MPT2SAS_INFO_FMT "putting controller into " - "SHOST_RECOVERY\n", ioc->name); - } spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); _base_reset_handler(ioc, MPT2_IOC_PRE_RESET); @@ -3534,7 +3530,10 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag, ioc->name, __func__, ((r == 0) ? "SUCCESS" : "FAILED"))); spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - ioc->ioc_reset_in_progress = 0; + ioc->shost_recovery = 0; spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); + + if (!r) + _base_reset_handler(ioc, MPT2_IOC_RUNNING); return r; } diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h b/drivers/scsi/mpt2sas/mpt2sas_base.h index acdcff1..22f84d3 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.h +++ b/drivers/scsi/mpt2sas/mpt2sas_base.h @@ -119,6 +119,7 @@ #define MPT2_IOC_PRE_RESET 1 /* prior to host reset */ #define MPT2_IOC_AFTER_RESET 2 /* just after host reset */ #define MPT2_IOC_DONE_RESET 3 /* links re-initialized */ +#define MPT2_IOC_RUNNING 4 /* shost running */ /* * logging format @@ -196,6 +197,38 @@ struct MPT2SAS_TARGET { * @block: device is in SDEV_BLOCK state * @tlr_snoop_check: flag used in determining whether to disable TLR */ + +/* OEM Identifiers */ +#define MFG10_OEM_ID_INVALID (0x00000000) +#define MFG10_OEM_ID_DELL (0x00000001) +#define MFG10_OEM_ID_FSC (0x00000002) +#define MFG10_OEM_ID_SUN (0x00000003) +#define MFG10_OEM_ID_IBM (0x00000004) + +/* GENERIC Flags 0*/ +#define MFG10_GF0_OCE_DISABLED (0x00000001) +#define MFG10_GF0_R1E_DRIVE_COUNT (0x00000002) +#define MFG10_GF0_R10_DISPLAY (0x00000004) +#define MFG10_GF0_SSD_DATA_SCRUB_DISABLE (0x00000008) +#define MFG10_GF0_SINGLE_DRIVE_R0 (0x00000010) + +/* OEM Specific Flags will come from OEM specific header files */ +typedef struct _MPI2_CONFIG_PAGE_MAN_10 { + MPI2_CONFIG_PAGE_HEADER Header; /* 00h */ + U8 OEMIdentifier; /* 04h */ + U8 Reserved1; /* 05h */ + U16 Reserved2; /* 08h */ + U32 Reserved3; /* 0Ch */ + U32 GenericFlags0; /* 10h */ + U32 GenericFlags1; /* 14h */ + U32 Reserved4; /* 18h */ + U32 OEMSpecificFlags0; /* 1Ch */ + U32 OEMSpecificFlags1; /* 20h */ + U32 Reserved5[18]; /* 24h-60h*/ +} MPI2_CONFIG_PAGE_MAN_10, + MPI2_POINTER PTR_MPI2_CONFIG_PAGE_MAN_10, + Mpi2ManufacturingPage10_t, MPI2_POINTER pMpi2ManufacturingPage10_t; + struct MPT2SAS_DEVICE { struct MPT2SAS_TARGET *sas_target; unsigned int lun; @@ -431,7 +464,7 @@ typedef void (*MPT_ADD_SGE)(void *paddr, u32 flags_length, dma_addr_t dma_addr); * @fw_event_list: list of fw events * @aen_event_read_flag: event log was read * @broadcast_aen_busy: broadcast aen waiting to be serviced - * @ioc_reset_in_progress: host reset in progress + * @shost_recovery: host reset in progress * @ioc_reset_in_progress_lock: * @ioc_link_reset_in_progress: phy/hard reset in progress * @ignore_loginfos: ignore loginfos during task managment @@ -460,6 +493,7 @@ typedef void (*MPT_ADD_SGE)(void *paddr, u32 flags_length, dma_addr_t dma_addr); * @facts: static facts data * @pfacts: static port facts data * @manu_pg0: static manufacturing page 0 + * @manu_pg10: static manufacturing page 10 * @bios_pg2: static bios page 2 * @bios_pg3: static bios page 3 * @ioc_pg8: static ioc page 8 @@ -544,7 +578,6 @@ struct MPT2SAS_ADAPTER { /* misc flags */ int aen_event_read_flag; u8 broadcast_aen_busy; - u8 ioc_reset_in_progress; u8 shost_recovery; spinlock_t ioc_reset_in_progress_lock; u8 ioc_link_reset_in_progress; @@ -663,6 +696,7 @@ struct MPT2SAS_ADAPTER { dma_addr_t diag_buffer_dma[MPI2_DIAG_BUF_TYPE_COUNT]; u8 diag_buffer_status[MPI2_DIAG_BUF_TYPE_COUNT]; u32 unique_id[MPI2_DIAG_BUF_TYPE_COUNT]; + Mpi2ManufacturingPage10_t manu_pg10; u32 product_specific[MPI2_DIAG_BUF_TYPE_COUNT][23]; u32 diagnostic_flags[MPI2_DIAG_BUF_TYPE_COUNT]; }; @@ -734,6 +768,8 @@ void mpt2sas_config_done(struct MPT2SAS_ADAPTER *ioc, u16 smid, u8 VF_ID, u32 re int mpt2sas_config_get_number_hba_phys(struct MPT2SAS_ADAPTER *ioc, u8 *num_phys); int mpt2sas_config_get_manufacturing_pg0(struct MPT2SAS_ADAPTER *ioc, Mpi2ConfigReply_t *mpi_reply, Mpi2ManufacturingPage0_t *config_page); +int mpt2sas_config_get_manufacturing_pg10(struct MPT2SAS_ADAPTER *ioc, + Mpi2ConfigReply_t *mpi_reply, Mpi2ManufacturingPage10_t *config_page); int mpt2sas_config_get_bios_pg2(struct MPT2SAS_ADAPTER *ioc, Mpi2ConfigReply_t *mpi_reply, Mpi2BiosPage2_t *config_page); int mpt2sas_config_get_bios_pg3(struct MPT2SAS_ADAPTER *ioc, Mpi2ConfigReply_t @@ -776,7 +812,6 @@ int mpt2sas_config_get_volume_handle(struct MPT2SAS_ADAPTER *ioc, u16 pd_handle, u16 *volume_handle); int mpt2sas_config_get_volume_wwid(struct MPT2SAS_ADAPTER *ioc, u16 volume_handle, u64 *wwid); - /* ctl shared API */ extern struct device_attribute *mpt2sas_host_attrs[]; extern struct device_attribute *mpt2sas_dev_attrs[]; @@ -802,5 +837,7 @@ void mpt2sas_transport_update_phy_link_change(struct MPT2SAS_ADAPTER *ioc, u16 h u16 attached_handle, u8 phy_number, u8 link_rate); extern struct sas_function_template mpt2sas_transport_functions; extern struct scsi_transport_template *mpt2sas_transport_template; +extern int scsi_internal_device_block(struct scsi_device *sdev); +extern int scsi_internal_device_unblock(struct scsi_device *sdev); #endif /* MPT2SAS_BASE_H_INCLUDED */ diff --git a/drivers/scsi/mpt2sas/mpt2sas_config.c b/drivers/scsi/mpt2sas/mpt2sas_config.c index 6ddee16..b9f4d0f 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_config.c +++ b/drivers/scsi/mpt2sas/mpt2sas_config.c @@ -426,6 +426,67 @@ mpt2sas_config_get_manufacturing_pg0(struct MPT2SAS_ADAPTER *ioc, } /** + * mpt2sas_config_get_manufacturing_pg10 - obtain manufacturing page 10 + * @ioc: per adapter object + * @mpi_reply: reply mf payload returned from firmware + * @config_page: contents of the config page + * Context: sleep. + * + * Returns 0 for success, non-zero for failure. + */ +int +mpt2sas_config_get_manufacturing_pg10(struct MPT2SAS_ADAPTER *ioc, + Mpi2ConfigReply_t *mpi_reply, Mpi2ManufacturingPage10_t *config_page) +{ + Mpi2ConfigRequest_t mpi_request; + int r; + struct config_request mem; + + memset(config_page, 0, sizeof(Mpi2ManufacturingPage10_t)); + memset(&mpi_request, 0, sizeof(Mpi2ConfigRequest_t)); + mpi_request.Function = MPI2_FUNCTION_CONFIG; + mpi_request.Action = MPI2_CONFIG_ACTION_PAGE_HEADER; + mpi_request.Header.PageType = MPI2_CONFIG_PAGETYPE_MANUFACTURING; + mpi_request.Header.PageNumber = 10; + mpi_request.Header.PageVersion = MPI2_MANUFACTURING0_PAGEVERSION; + mpt2sas_base_build_zero_len_sge(ioc, &mpi_request.PageBufferSGE); + r = _config_request(ioc, &mpi_request, mpi_reply, + MPT2_CONFIG_PAGE_DEFAULT_TIMEOUT); + if (r) + goto out; + + mpi_request.Action = MPI2_CONFIG_ACTION_PAGE_READ_CURRENT; + mpi_request.Header.PageVersion = mpi_reply->Header.PageVersion; + mpi_request.Header.PageNumber = mpi_reply->Header.PageNumber; + mpi_request.Header.PageType = mpi_reply->Header.PageType; + mpi_request.Header.PageLength = mpi_reply->Header.PageLength; + mem.config_page_sz = le16_to_cpu(mpi_reply->Header.PageLength) * 4; + if (mem.config_page_sz > ioc->config_page_sz) { + r = _config_alloc_config_dma_memory(ioc, &mem); + if (r) + goto out; + } else { + mem.config_page_dma = ioc->config_page_dma; + mem.config_page = ioc->config_page; + } + ioc->base_add_sg_single(&mpi_request.PageBufferSGE, + MPT2_CONFIG_COMMON_SGLFLAGS | mem.config_page_sz, + mem.config_page_dma); + r = _config_request(ioc, &mpi_request, mpi_reply, + MPT2_CONFIG_PAGE_DEFAULT_TIMEOUT); + if (!r) + memcpy(config_page, mem.config_page, + min_t(u16, mem.config_page_sz, + sizeof(Mpi2ManufacturingPage10_t))); + + if (mem.config_page_sz > ioc->config_page_sz) + _config_free_config_dma_memory(ioc, &mem); + + out: + return r; +} + +/** * mpt2sas_config_get_bios_pg2 - obtain bios page 2 * @ioc: per adapter object * @mpi_reply: reply mf payload returned from firmware diff --git a/drivers/scsi/mpt2sas/mpt2sas_ctl.c b/drivers/scsi/mpt2sas/mpt2sas_ctl.c index 14e473d..c2a5101 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_ctl.c +++ b/drivers/scsi/mpt2sas/mpt2sas_ctl.c @@ -1963,7 +1963,6 @@ _ctl_ioctl_main(struct file *file, unsigned int cmd, void __user *arg) { enum block_state state; long ret = -EINVAL; - unsigned long flags; state = (file->f_flags & O_NONBLOCK) ? NON_BLOCKING : BLOCKING; @@ -1989,13 +1988,8 @@ _ctl_ioctl_main(struct file *file, unsigned int cmd, void __user *arg) !ioc) return -ENODEV; - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->shost_recovery) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, - flags); + if (ioc->shost_recovery) return -EAGAIN; - } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); if (_IOC_SIZE(cmd) == sizeof(struct mpt2_ioctl_command)) { uarg = arg; @@ -2098,7 +2092,6 @@ _ctl_compat_mpt_command(struct file *file, unsigned cmd, unsigned long arg) struct mpt2_ioctl_command karg; struct MPT2SAS_ADAPTER *ioc; enum block_state state; - unsigned long flags; if (_IOC_SIZE(cmd) != sizeof(struct mpt2_ioctl_command32)) return -EINVAL; @@ -2113,13 +2106,8 @@ _ctl_compat_mpt_command(struct file *file, unsigned cmd, unsigned long arg) if (_ctl_verify_adapter(karg32.hdr.ioc_number, &ioc) == -1 || !ioc) return -ENODEV; - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->shost_recovery) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, - flags); + if (ioc->shost_recovery) return -EAGAIN; - } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); memset(&karg, 0, sizeof(struct mpt2_ioctl_command)); karg.hdr.ioc_number = karg32.hdr.ioc_number; diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index 2e9a444..c7a0870 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -103,7 +103,6 @@ struct sense_info { }; -#define MPT2SAS_RESCAN_AFTER_HOST_RESET (0xFFFF) /** * struct fw_event_work - firmware event struct * @list: link list framework @@ -1502,7 +1501,13 @@ _scsih_slave_configure(struct scsi_device *sdev) break; case MPI2_RAID_VOL_TYPE_RAID1E: qdepth = MPT2SAS_RAID_QUEUE_DEPTH; - r_level = "RAID1E"; + if (ioc->manu_pg10.OEMIdentifier && + (ioc->manu_pg10.GenericFlags0 & + MFG10_GF0_R10_DISPLAY) && + !(raid_device->num_pds % 2)) + r_level = "RAID10"; + else + r_level = "RAID1E"; break; case MPI2_RAID_VOL_TYPE_RAID1: qdepth = MPT2SAS_RAID_QUEUE_DEPTH; @@ -1786,17 +1791,18 @@ mpt2sas_scsih_issue_tm(struct MPT2SAS_ADAPTER *ioc, u16 handle, uint lun, u32 ioc_state; unsigned long timeleft; u8 VF_ID = 0; - unsigned long flags; - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->tm_cmds.status != MPT2_CMD_NOT_USED || - ioc->shost_recovery) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); + if (ioc->tm_cmds.status != MPT2_CMD_NOT_USED) { + printk(MPT2SAS_INFO_FMT "%s: tm_cmd busy!!!\n", + __func__, ioc->name); + return; + } + + if (ioc->shost_recovery) { printk(MPT2SAS_INFO_FMT "%s: host reset in progress!\n", __func__, ioc->name); return; } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); ioc_state = mpt2sas_base_get_iocstate(ioc, 0); if (ioc_state & MPI2_DOORBELL_USED) { @@ -2222,7 +2228,7 @@ _scsih_ublock_io_device(struct MPT2SAS_ADAPTER *ioc, u16 handle) MPT2SAS_INFO_FMT "SDEV_RUNNING: " "handle(0x%04x)\n", ioc->name, handle)); sas_device_priv_data->block = 0; - scsi_device_set_state(sdev, SDEV_RUNNING); + scsi_internal_device_unblock(sdev); } } } @@ -2251,7 +2257,7 @@ _scsih_block_io_device(struct MPT2SAS_ADAPTER *ioc, u16 handle) MPT2SAS_INFO_FMT "SDEV_BLOCK: " "handle(0x%04x)\n", ioc->name, handle)); sas_device_priv_data->block = 1; - scsi_device_set_state(sdev, SDEV_BLOCK); + scsi_internal_device_block(sdev); } } } @@ -2327,6 +2333,7 @@ _scsih_block_io_to_children_attached_directly(struct MPT2SAS_ADAPTER *ioc, u16 handle; u16 reason_code; u8 phy_number; + u8 link_rate; for (i = 0; i < event_data->NumEntries; i++) { handle = le16_to_cpu(event_data->PHY[i].AttachedDevHandle); @@ -2337,6 +2344,11 @@ _scsih_block_io_to_children_attached_directly(struct MPT2SAS_ADAPTER *ioc, MPI2_EVENT_SAS_TOPO_RC_MASK; if (reason_code == MPI2_EVENT_SAS_TOPO_RC_DELAY_NOT_RESPONDING) _scsih_block_io_device(ioc, handle); + if (reason_code == MPI2_EVENT_SAS_TOPO_RC_PHY_CHANGED) { + link_rate = event_data->PHY[i].LinkRate >> 4; + if (link_rate >= MPI2_SAS_NEG_LINK_RATE_1_5) + _scsih_ublock_io_device(ioc, handle); + } } } @@ -2405,27 +2417,6 @@ _scsih_check_topo_delete_events(struct MPT2SAS_ADAPTER *ioc, } /** - * _scsih_queue_rescan - queue a topology rescan from user context - * @ioc: per adapter object - * - * Return nothing. - */ -static void -_scsih_queue_rescan(struct MPT2SAS_ADAPTER *ioc) -{ - struct fw_event_work *fw_event; - - if (ioc->wait_for_port_enable_to_complete) - return; - fw_event = kzalloc(sizeof(struct fw_event_work), GFP_ATOMIC); - if (!fw_event) - return; - fw_event->event = MPT2SAS_RESCAN_AFTER_HOST_RESET; - fw_event->ioc = ioc; - _scsih_fw_event_add(ioc, fw_event); -} - -/** * _scsih_flush_running_cmds - completing outstanding commands. * @ioc: per adapter object * @@ -2456,46 +2447,6 @@ _scsih_flush_running_cmds(struct MPT2SAS_ADAPTER *ioc) } /** - * mpt2sas_scsih_reset_handler - reset callback handler (for scsih) - * @ioc: per adapter object - * @reset_phase: phase - * - * The handler for doing any required cleanup or initialization. - * - * The reset phase can be MPT2_IOC_PRE_RESET, MPT2_IOC_AFTER_RESET, - * MPT2_IOC_DONE_RESET - * - * Return nothing. - */ -void -mpt2sas_scsih_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) -{ - switch (reset_phase) { - case MPT2_IOC_PRE_RESET: - dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " - "MPT2_IOC_PRE_RESET\n", ioc->name, __func__)); - _scsih_fw_event_off(ioc); - break; - case MPT2_IOC_AFTER_RESET: - dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " - "MPT2_IOC_AFTER_RESET\n", ioc->name, __func__)); - if (ioc->tm_cmds.status & MPT2_CMD_PENDING) { - ioc->tm_cmds.status |= MPT2_CMD_RESET; - mpt2sas_base_free_smid(ioc, ioc->tm_cmds.smid); - complete(&ioc->tm_cmds.done); - } - _scsih_fw_event_on(ioc); - _scsih_flush_running_cmds(ioc); - break; - case MPT2_IOC_DONE_RESET: - dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " - "MPT2_IOC_DONE_RESET\n", ioc->name, __func__)); - _scsih_queue_rescan(ioc); - break; - } -} - -/** * _scsih_setup_eedp - setup MPI request for EEDP transfer * @scmd: pointer to scsi command object * @mpi_request: pointer to the SCSI_IO reqest message frame @@ -2615,7 +2566,6 @@ _scsih_qcmd(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *)) Mpi2SCSIIORequest_t *mpi_request; u32 mpi_control; u16 smid; - unsigned long flags; scmd->scsi_done = done; sas_device_priv_data = scmd->device->hostdata; @@ -2634,13 +2584,10 @@ _scsih_qcmd(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *)) } /* see if we are busy with task managment stuff */ - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (sas_target_priv_data->tm_busy || - ioc->shost_recovery || ioc->ioc_link_reset_in_progress) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); + if (sas_target_priv_data->tm_busy) + return SCSI_MLQUEUE_DEVICE_BUSY; + else if (ioc->shost_recovery || ioc->ioc_link_reset_in_progress) return SCSI_MLQUEUE_HOST_BUSY; - } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); if (scmd->sc_data_direction == DMA_FROM_DEVICE) mpi_control = MPI2_SCSIIO_CONTROL_READ; @@ -3436,6 +3383,9 @@ _scsih_expander_add(struct MPT2SAS_ADAPTER *ioc, u16 handle) if (!handle) return -1; + if (ioc->shost_recovery) + return -1; + if ((mpt2sas_config_get_expander_pg0(ioc, &mpi_reply, &expander_pg0, MPI2_SAS_EXPAND_PGAD_FORM_HNDL, handle))) { printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n", @@ -3572,6 +3522,9 @@ _scsih_expander_remove(struct MPT2SAS_ADAPTER *ioc, u16 handle) struct _sas_node *sas_expander; unsigned long flags; + if (ioc->shost_recovery) + return; + spin_lock_irqsave(&ioc->sas_node_lock, flags); sas_expander = mpt2sas_scsih_expander_find_by_handle(ioc, handle); spin_unlock_irqrestore(&ioc->sas_node_lock, flags); @@ -3743,6 +3696,8 @@ _scsih_remove_device(struct MPT2SAS_ADAPTER *ioc, u16 handle) mutex_unlock(&ioc->tm_cmds.mutex); dewtprintk(ioc, printk(MPT2SAS_INFO_FMT "issue target reset " "done: handle(0x%04x)\n", ioc->name, device_handle)); + if (ioc->shost_recovery) + goto out; } /* SAS_IO_UNIT_CNTR - send REMOVE_DEVICE */ @@ -3765,6 +3720,9 @@ _scsih_remove_device(struct MPT2SAS_ADAPTER *ioc, u16 handle) le32_to_cpu(mpi_reply.IOCLogInfo))); out: + + _scsih_ublock_io_device(ioc, handle); + mpt2sas_transport_port_remove(ioc, sas_device->sas_address, sas_device->parent_handle); @@ -3908,6 +3866,8 @@ _scsih_sas_topology_change_event(struct MPT2SAS_ADAPTER *ioc, u8 VF_ID, "expander event\n", ioc->name)); return; } + if (ioc->shost_recovery) + return; if (event_data->PHY[i].PhyStatus & MPI2_EVENT_SAS_TOPO_PHYSTATUS_VACANT) continue; @@ -3942,10 +3902,6 @@ _scsih_sas_topology_change_event(struct MPT2SAS_ADAPTER *ioc, u8 VF_ID, link_rate_); } } - if (reason_code == MPI2_EVENT_SAS_TOPO_RC_PHY_CHANGED) { - if (link_rate_ >= MPI2_SAS_NEG_LINK_RATE_1_5) - _scsih_ublock_io_device(ioc, handle); - } if (reason_code == MPI2_EVENT_SAS_TOPO_RC_TARG_ADDED) { if (link_rate_ < MPI2_SAS_NEG_LINK_RATE_1_5) break; @@ -5156,22 +5112,9 @@ static void _scsih_remove_unresponding_devices(struct MPT2SAS_ADAPTER *ioc) { struct _sas_device *sas_device, *sas_device_next; - struct _sas_node *sas_expander, *sas_expander_next; + struct _sas_node *sas_expander; struct _raid_device *raid_device, *raid_device_next; - unsigned long flags; - _scsih_search_responding_sas_devices(ioc); - _scsih_search_responding_raid_devices(ioc); - _scsih_search_responding_expanders(ioc); - - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - ioc->shost_recovery = 0; - if (ioc->shost->shost_state == SHOST_RECOVERY) { - printk(MPT2SAS_INFO_FMT "putting controller into " - "SHOST_RUNNING\n", ioc->name); - scsi_host_set_state(ioc->shost, SHOST_RUNNING); - } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); list_for_each_entry_safe(sas_device, sas_device_next, &ioc->sas_device_list, list) { @@ -5207,16 +5150,63 @@ _scsih_remove_unresponding_devices(struct MPT2SAS_ADAPTER *ioc) _scsih_raid_device_remove(ioc, raid_device); } - list_for_each_entry_safe(sas_expander, sas_expander_next, - &ioc->sas_expander_list, list) { + retry_expander_search: + sas_expander = NULL; + list_for_each_entry(sas_expander, &ioc->sas_expander_list, list) { if (sas_expander->responding) { sas_expander->responding = 0; continue; } - printk("\tremoving expander: handle(0x%04x), " - " sas_addr(0x%016llx)\n", sas_expander->handle, - (unsigned long long)sas_expander->sas_address); _scsih_expander_remove(ioc, sas_expander->handle); + goto retry_expander_search; + } +} + +/** + * mpt2sas_scsih_reset_handler - reset callback handler (for scsih) + * @ioc: per adapter object + * @reset_phase: phase + * + * The handler for doing any required cleanup or initialization. + * + * The reset phase can be MPT2_IOC_PRE_RESET, MPT2_IOC_AFTER_RESET, + * MPT2_IOC_DONE_RESET + * + * Return nothing. + */ +void +mpt2sas_scsih_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) +{ + switch (reset_phase) { + case MPT2_IOC_PRE_RESET: + dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " + "MPT2_IOC_PRE_RESET\n", ioc->name, __func__)); + _scsih_fw_event_off(ioc); + break; + case MPT2_IOC_AFTER_RESET: + dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " + "MPT2_IOC_AFTER_RESET\n", ioc->name, __func__)); + if (ioc->tm_cmds.status & MPT2_CMD_PENDING) { + ioc->tm_cmds.status |= MPT2_CMD_RESET; + mpt2sas_base_free_smid(ioc, ioc->tm_cmds.smid); + complete(&ioc->tm_cmds.done); + } + _scsih_fw_event_on(ioc); + _scsih_flush_running_cmds(ioc); + break; + case MPT2_IOC_DONE_RESET: + dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " + "MPT2_IOC_DONE_RESET\n", ioc->name, __func__)); + _scsih_sas_host_refresh(ioc, 0); + _scsih_search_responding_sas_devices(ioc); + _scsih_search_responding_raid_devices(ioc); + _scsih_search_responding_expanders(ioc); + break; + case MPT2_IOC_RUNNING: + dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " + "MPT2_IOC_RUNNING\n", ioc->name, __func__)); + _scsih_remove_unresponding_devices(ioc); + break; } } @@ -5236,14 +5226,6 @@ _firmware_event_work(struct work_struct *work) unsigned long flags; struct MPT2SAS_ADAPTER *ioc = fw_event->ioc; - /* This is invoked by calling _scsih_queue_rescan(). */ - if (fw_event->event == MPT2SAS_RESCAN_AFTER_HOST_RESET) { - _scsih_fw_event_free(ioc, fw_event); - _scsih_sas_host_refresh(ioc, 1); - _scsih_remove_unresponding_devices(ioc); - return; - } - /* the queue is being flushed so ignore this event */ spin_lock_irqsave(&ioc->fw_event_lock, flags); if (ioc->fw_events_off || ioc->remove_host) { @@ -5253,13 +5235,10 @@ _firmware_event_work(struct work_struct *work) } spin_unlock_irqrestore(&ioc->fw_event_lock, flags); - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); if (ioc->shost_recovery) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); _scsih_fw_event_requeue(ioc, fw_event, 1000); return; } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); switch (fw_event->event) { case MPI2_EVENT_SAS_TOPOLOGY_CHANGE_LIST: @@ -5461,6 +5440,8 @@ _scsih_expander_node_remove(struct MPT2SAS_ADAPTER *ioc, if (!sas_device) continue; _scsih_remove_device(ioc, sas_device->handle); + if (ioc->shost_recovery) + return; goto retry_device_search; } } @@ -5482,6 +5463,8 @@ _scsih_expander_node_remove(struct MPT2SAS_ADAPTER *ioc, if (!expander_sibling) continue; _scsih_expander_remove(ioc, expander_sibling->handle); + if (ioc->shost_recovery) + return; goto retry_expander_search; } } diff --git a/drivers/scsi/mpt2sas/mpt2sas_transport.c b/drivers/scsi/mpt2sas/mpt2sas_transport.c index 686695b..a53086d 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_transport.c +++ b/drivers/scsi/mpt2sas/mpt2sas_transport.c @@ -140,11 +140,18 @@ _transport_set_identify(struct MPT2SAS_ADAPTER *ioc, u16 handle, u32 device_info; u32 ioc_status; + if (ioc->shost_recovery) { + printk(MPT2SAS_INFO_FMT "%s: host reset in progress!\n", + __func__, ioc->name); + return -EFAULT; + } + if ((mpt2sas_config_get_sas_device_pg0(ioc, &mpi_reply, &sas_device_pg0, MPI2_SAS_DEVICE_PGAD_FORM_HANDLE, handle))) { printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n", + ioc->name, __FILE__, __LINE__, __func__); - return -1; + return -ENXIO; } ioc_status = le16_to_cpu(mpi_reply.IOCStatus) & @@ -153,7 +160,7 @@ _transport_set_identify(struct MPT2SAS_ADAPTER *ioc, u16 handle, printk(MPT2SAS_ERR_FMT "handle(0x%04x), ioc_status(0x%04x)" "\nfailure at %s:%d/%s()!\n", ioc->name, handle, ioc_status, __FILE__, __LINE__, __func__); - return -1; + return -EIO; } memset(identify, 0, sizeof(identify)); @@ -288,21 +295,17 @@ _transport_expander_report_manufacture(struct MPT2SAS_ADAPTER *ioc, void *psge; u32 sgl_flags; u8 issue_reset = 0; - unsigned long flags; void *data_out = NULL; dma_addr_t data_out_dma; u32 sz; u64 *sas_address_le; u16 wait_state_count; - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->ioc_reset_in_progress) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); + if (ioc->shost_recovery) { printk(MPT2SAS_INFO_FMT "%s: host reset in progress!\n", __func__, ioc->name); return -EFAULT; } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); mutex_lock(&ioc->transport_cmds.mutex); @@ -806,6 +809,12 @@ mpt2sas_transport_update_phy_link_change(struct MPT2SAS_ADAPTER *ioc, struct _sas_node *sas_node; struct _sas_phy *mpt2sas_phy; + if (ioc->shost_recovery) { + printk(MPT2SAS_INFO_FMT "%s: host reset in progress!\n", + __func__, ioc->name); + return; + } + spin_lock_irqsave(&ioc->sas_node_lock, flags); sas_node = _transport_sas_node_find_by_handle(ioc, handle); spin_unlock_irqrestore(&ioc->sas_node_lock, flags); @@ -1025,7 +1034,6 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy, void *psge; u32 sgl_flags; u8 issue_reset = 0; - unsigned long flags; dma_addr_t dma_addr_in = 0; dma_addr_t dma_addr_out = 0; u16 wait_state_count; @@ -1045,14 +1053,11 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy, return -EINVAL; } - spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags); - if (ioc->ioc_reset_in_progress) { - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); + if (ioc->shost_recovery) { printk(MPT2SAS_INFO_FMT "%s: host reset in progress!\n", __func__, ioc->name); return -EFAULT; } - spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags); rc = mutex_lock_interruptible(&ioc->transport_cmds.mutex); if (rc) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b7b9fec..a89c421 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2021,6 +2021,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie) sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", sdp->removable ? "removable " : ""); + put_device(&sdkp->dev); } /** @@ -2106,6 +2107,7 @@ static int sd_probe(struct device *dev) get_device(&sdp->sdev_gendev); + get_device(&sdkp->dev); /* prevent release before async_schedule */ async_schedule(sd_probe_async, sdkp); return 0; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 9230402..4968c4c 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1811,7 +1811,7 @@ retry: return 0; out: for (i = 0; i < k; i++) - __free_pages(schp->pages[k], order); + __free_pages(schp->pages[i], order); if (--order >= 0) goto retry; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index b7c1603..7c1e65d 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -501,22 +501,22 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, } } - /* - * Now fill out the bss section. First pad the last page up - * to the page boundary, and then perform a mmap to make sure - * that there are zero-mapped pages up to and including the - * last bss page. - */ - if (padzero(elf_bss)) { - error = -EFAULT; - goto out_close; - } + if (last_bss > elf_bss) { + /* + * Now fill out the bss section. First pad the last page up + * to the page boundary, and then perform a mmap to make sure + * that there are zero-mapped pages up to and including the + * last bss page. + */ + if (padzero(elf_bss)) { + error = -EFAULT; + goto out_close; + } - /* What we have mapped so far */ - elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1); + /* What we have mapped so far */ + elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1); - /* Map the last of the bss segment */ - if (last_bss > elf_bss) { + /* Map the last of the bss segment */ down_write(¤t->mm->mmap_sem); error = do_brk(elf_bss, last_bss - elf_bss); up_write(¤t->mm->mmap_sem); diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index 3ddce03..d731092 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -13,6 +13,7 @@ #define KVM_ENOSYS 1000 #define KVM_EFAULT EFAULT #define KVM_E2BIG E2BIG +#define KVM_EPERM EPERM #define KVM_HC_VAPIC_POLL_IRQ 1 #define KVM_HC_MMU_OP 2 diff --git a/ipc/shm.c b/ipc/shm.c index 1bc4701..30162a5 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -410,7 +410,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) return error; no_id: - if (shp->mlock_user) /* shmflg & SHM_HUGETLB case */ + if (is_file_hugepages(file) && shp->mlock_user) user_shm_unlock(size, shp->mlock_user); fput(file); no_file: diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index d7cbc57..3f49f53 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -469,7 +469,8 @@ static void update_counter_times(struct perf_counter *counter) struct perf_counter_context *ctx = counter->ctx; u64 run_end; - if (counter->state < PERF_COUNTER_STATE_INACTIVE) + if (counter->state < PERF_COUNTER_STATE_INACTIVE || + counter->group_leader->state < PERF_COUNTER_STATE_INACTIVE) return; counter->total_time_enabled = ctx->time - counter->tstamp_enabled; @@ -518,7 +519,7 @@ static void __perf_counter_disable(void *info) */ if (counter->state >= PERF_COUNTER_STATE_INACTIVE) { update_context_time(ctx); - update_counter_times(counter); + update_group_times(counter); if (counter == counter->group_leader) group_sched_out(counter, cpuctx, ctx); else @@ -573,7 +574,7 @@ static void perf_counter_disable(struct perf_counter *counter) * in, so we can change the state safely. */ if (counter->state == PERF_COUNTER_STATE_INACTIVE) { - update_counter_times(counter); + update_group_times(counter); counter->state = PERF_COUNTER_STATE_OFF; } @@ -851,6 +852,27 @@ retry: } /* + * Put a counter into inactive state and update time fields. + * Enabling the leader of a group effectively enables all + * the group members that aren't explicitly disabled, so we + * have to update their ->tstamp_enabled also. + * Note: this works for group members as well as group leaders + * since the non-leader members' sibling_lists will be empty. + */ +static void __perf_counter_mark_enabled(struct perf_counter *counter, + struct perf_counter_context *ctx) +{ + struct perf_counter *sub; + + counter->state = PERF_COUNTER_STATE_INACTIVE; + counter->tstamp_enabled = ctx->time - counter->total_time_enabled; + list_for_each_entry(sub, &counter->sibling_list, list_entry) + if (sub->state >= PERF_COUNTER_STATE_INACTIVE) + sub->tstamp_enabled = + ctx->time - sub->total_time_enabled; +} + +/* * Cross CPU call to enable a performance counter */ static void __perf_counter_enable(void *info) @@ -877,8 +899,7 @@ static void __perf_counter_enable(void *info) if (counter->state >= PERF_COUNTER_STATE_INACTIVE) goto unlock; - counter->state = PERF_COUNTER_STATE_INACTIVE; - counter->tstamp_enabled = ctx->time - counter->total_time_enabled; + __perf_counter_mark_enabled(counter, ctx); /* * If the counter is in a group and isn't the group leader, @@ -971,11 +992,9 @@ static void perf_counter_enable(struct perf_counter *counter) * Since we have the lock this context can't be scheduled * in, so we can change the state safely. */ - if (counter->state == PERF_COUNTER_STATE_OFF) { - counter->state = PERF_COUNTER_STATE_INACTIVE; - counter->tstamp_enabled = - ctx->time - counter->total_time_enabled; - } + if (counter->state == PERF_COUNTER_STATE_OFF) + __perf_counter_mark_enabled(counter, ctx); + out: spin_unlock_irq(&ctx->lock); } @@ -1479,9 +1498,7 @@ static void perf_counter_enable_on_exec(struct task_struct *task) counter->attr.enable_on_exec = 0; if (counter->state >= PERF_COUNTER_STATE_INACTIVE) continue; - counter->state = PERF_COUNTER_STATE_INACTIVE; - counter->tstamp_enabled = - ctx->time - counter->total_time_enabled; + __perf_counter_mark_enabled(counter, ctx); enabled = 1; } @@ -4171,6 +4188,7 @@ static int perf_copy_attr(struct perf_counter_attr __user *uattr, if (val) goto err_size; } + size = sizeof(*attr); } ret = copy_from_user(attr, uattr, size); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7e595ce..46c101a 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -97,7 +97,7 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *dev) dev->bss_generation++; } -static u8 *find_ie(u8 num, u8 *ies, size_t len) +static u8 *find_ie(u8 num, u8 *ies, int len) { while (len > 2 && ies[0] != num) { len -= ies[1] + 2; diff --git a/sound/pci/cs46xx/cs46xx_lib.h b/sound/pci/cs46xx/cs46xx_lib.h index 4eb55aa..b518949 100644 --- a/sound/pci/cs46xx/cs46xx_lib.h +++ b/sound/pci/cs46xx/cs46xx_lib.h @@ -35,7 +35,7 @@ #ifdef CONFIG_SND_CS46XX_NEW_DSP -#define CS46XX_MIN_PERIOD_SIZE 1 +#define CS46XX_MIN_PERIOD_SIZE 64 #define CS46XX_MAX_PERIOD_SIZE 1024*1024 #else #define CS46XX_MIN_PERIOD_SIZE 2048 diff --git a/sound/pci/oxygen/oxygen_io.c b/sound/pci/oxygen/oxygen_io.c index c1eb923..09b2b2a 100644 --- a/sound/pci/oxygen/oxygen_io.c +++ b/sound/pci/oxygen/oxygen_io.c @@ -215,17 +215,8 @@ EXPORT_SYMBOL(oxygen_write_spi); void oxygen_write_i2c(struct oxygen *chip, u8 device, u8 map, u8 data) { - unsigned long timeout; - /* should not need more than about 300 us */ - timeout = jiffies + msecs_to_jiffies(1); - do { - if (!(oxygen_read16(chip, OXYGEN_2WIRE_BUS_STATUS) - & OXYGEN_2WIRE_BUSY)) - break; - udelay(1); - cond_resched(); - } while (time_after_eq(timeout, jiffies)); + msleep(1); oxygen_write8(chip, OXYGEN_2WIRE_MAP, map); oxygen_write8(chip, OXYGEN_2WIRE_DATA, data); diff --git a/sound/soc/codecs/wm8350.c b/sound/soc/codecs/wm8350.c index e7348d3..b3a2de8 100644 --- a/sound/soc/codecs/wm8350.c +++ b/sound/soc/codecs/wm8350.c @@ -613,7 +613,7 @@ SOC_DAPM_SINGLE("Switch", WM8350_BEEP_VOLUME, 15, 1, 1); /* Out4 Capture Mux */ static const struct snd_kcontrol_new wm8350_out4_capture_controls = -SOC_DAPM_ENUM("Route", wm8350_enum[8]); +SOC_DAPM_ENUM("Route", wm8350_enum[7]); static const struct snd_soc_dapm_widget wm8350_dapm_widgets[] = { diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b4b06c7..e874ad4 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -82,19 +82,32 @@ static u64 runtime_cycles[MAX_RUN]; static u64 event_res[MAX_RUN][MAX_COUNTERS][3]; static u64 event_scaled[MAX_RUN][MAX_COUNTERS]; -static u64 event_res_avg[MAX_COUNTERS][3]; -static u64 event_res_noise[MAX_COUNTERS][3]; +struct stats +{ + double sum; + double sum_sq; +}; -static u64 event_scaled_avg[MAX_COUNTERS]; +static double avg_stats(struct stats *stats) +{ + return stats->sum / run_count; +} -static u64 runtime_nsecs_avg; -static u64 runtime_nsecs_noise; +/* + * stddev = sqrt(1/N (\Sum n_i^2) - avg(n)^2) + */ +static double stddev_stats(struct stats *stats) +{ + double avg = stats->sum / run_count; -static u64 walltime_nsecs_avg; -static u64 walltime_nsecs_noise; + return sqrt(stats->sum_sq/run_count - avg*avg); +} -static u64 runtime_cycles_avg; -static u64 runtime_cycles_noise; +struct stats event_res_stats[MAX_COUNTERS][3]; +struct stats event_scaled_stats[MAX_COUNTERS]; +struct stats runtime_nsecs_stats; +struct stats walltime_nsecs_stats; +struct stats runtime_cycles_stats; #define MATCH_EVENT(t, c, counter) \ (attrs[counter].type == PERF_TYPE_##t && \ @@ -278,42 +291,37 @@ static int run_perf_stat(int argc __used, const char **argv) return WEXITSTATUS(status); } -static void print_noise(u64 *count, u64 *noise) +static void print_noise(double avg, double stddev) { if (run_count > 1) - fprintf(stderr, " ( +- %7.3f%% )", - (double)noise[0]/(count[0]+1)*100.0); + fprintf(stderr, " ( +- %7.3f%% )", 100*stddev / avg); } -static void nsec_printout(int counter, u64 *count, u64 *noise) +static void nsec_printout(int counter, double avg, double stddev) { - double msecs = (double)count[0] / 1000000; + double msecs = avg / 1e6; fprintf(stderr, " %14.6f %-24s", msecs, event_name(counter)); if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) { - if (walltime_nsecs_avg) - fprintf(stderr, " # %10.3f CPUs ", - (double)count[0] / (double)walltime_nsecs_avg); + fprintf(stderr, " # %10.3f CPUs ", + avg / avg_stats(&walltime_nsecs_stats)); } - print_noise(count, noise); + print_noise(avg, stddev); } -static void abs_printout(int counter, u64 *count, u64 *noise) +static void abs_printout(int counter, double avg, double stddev) { - fprintf(stderr, " %14Ld %-24s", count[0], event_name(counter)); + fprintf(stderr, " %14.0f %-24s", avg, event_name(counter)); - if (runtime_cycles_avg && - MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) { + if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) { fprintf(stderr, " # %10.3f IPC ", - (double)count[0] / (double)runtime_cycles_avg); + avg / avg_stats(&runtime_cycles_stats)); } else { - if (runtime_nsecs_avg) { - fprintf(stderr, " # %10.3f M/sec", - (double)count[0]/runtime_nsecs_avg*1000.0); - } + fprintf(stderr, " # %10.3f M/sec", + 1000.0 * avg / avg_stats(&runtime_nsecs_stats)); } - print_noise(count, noise); + print_noise(avg, stddev); } /* @@ -321,12 +329,12 @@ static void abs_printout(int counter, u64 *count, u64 *noise) */ static void print_counter(int counter) { - u64 *count, *noise; + double avg, stddev; int scaled; - count = event_res_avg[counter]; - noise = event_res_noise[counter]; - scaled = event_scaled_avg[counter]; + avg = avg_stats(&event_res_stats[counter][0]); + stddev = stddev_stats(&event_res_stats[counter][0]); + scaled = avg_stats(&event_scaled_stats[counter]); if (scaled == -1) { fprintf(stderr, " %14s %-24s\n", @@ -335,36 +343,34 @@ static void print_counter(int counter) } if (nsec_counter(counter)) - nsec_printout(counter, count, noise); + nsec_printout(counter, avg, stddev); else - abs_printout(counter, count, noise); + abs_printout(counter, avg, stddev); + + if (scaled) { + double avg_enabled, avg_running; + + avg_enabled = avg_stats(&event_res_stats[counter][1]); + avg_running = avg_stats(&event_res_stats[counter][2]); - if (scaled) fprintf(stderr, " (scaled from %.2f%%)", - (double) count[2] / count[1] * 100); + 100 * avg_running / avg_enabled); + } fprintf(stderr, "\n"); } -/* - * normalize_noise noise values down to stddev: - */ -static void normalize_noise(u64 *val) +static void update_stats(const char *name, int idx, struct stats *stats, u64 *val) { - double res; + double sq = *val; - res = (double)*val / (run_count * sqrt((double)run_count)); - - *val = (u64)res; -} - -static void update_avg(const char *name, int idx, u64 *avg, u64 *val) -{ - *avg += *val; + stats->sum += *val; + stats->sum_sq += sq * sq; if (verbose > 1) fprintf(stderr, "debug: %20s[%d]: %Ld\n", name, idx, *val); } + /* * Calculate the averages and noises: */ @@ -376,61 +382,22 @@ static void calc_avg(void) fprintf(stderr, "\n"); for (i = 0; i < run_count; i++) { - update_avg("runtime", 0, &runtime_nsecs_avg, runtime_nsecs + i); - update_avg("walltime", 0, &walltime_nsecs_avg, walltime_nsecs + i); - update_avg("runtime_cycles", 0, &runtime_cycles_avg, runtime_cycles + i); + update_stats("runtime", 0, &runtime_nsecs_stats, runtime_nsecs + i); + update_stats("walltime", 0, &walltime_nsecs_stats, walltime_nsecs + i); + update_stats("runtime_cycles", 0, &runtime_cycles_stats, runtime_cycles + i); for (j = 0; j < nr_counters; j++) { - update_avg("counter/0", j, - event_res_avg[j]+0, event_res[i][j]+0); - update_avg("counter/1", j, - event_res_avg[j]+1, event_res[i][j]+1); - update_avg("counter/2", j, - event_res_avg[j]+2, event_res[i][j]+2); + update_stats("counter/0", j, + event_res_stats[j]+0, event_res[i][j]+0); + update_stats("counter/1", j, + event_res_stats[j]+1, event_res[i][j]+1); + update_stats("counter/2", j, + event_res_stats[j]+2, event_res[i][j]+2); if (event_scaled[i][j] != (u64)-1) - update_avg("scaled", j, - event_scaled_avg + j, event_scaled[i]+j); - else - event_scaled_avg[j] = -1; + update_stats("scaled", j, + event_scaled_stats + j, event_scaled[i]+j); } } - runtime_nsecs_avg /= run_count; - walltime_nsecs_avg /= run_count; - runtime_cycles_avg /= run_count; - - for (j = 0; j < nr_counters; j++) { - event_res_avg[j][0] /= run_count; - event_res_avg[j][1] /= run_count; - event_res_avg[j][2] /= run_count; - } - - for (i = 0; i < run_count; i++) { - runtime_nsecs_noise += - abs((s64)(runtime_nsecs[i] - runtime_nsecs_avg)); - walltime_nsecs_noise += - abs((s64)(walltime_nsecs[i] - walltime_nsecs_avg)); - runtime_cycles_noise += - abs((s64)(runtime_cycles[i] - runtime_cycles_avg)); - - for (j = 0; j < nr_counters; j++) { - event_res_noise[j][0] += - abs((s64)(event_res[i][j][0] - event_res_avg[j][0])); - event_res_noise[j][1] += - abs((s64)(event_res[i][j][1] - event_res_avg[j][1])); - event_res_noise[j][2] += - abs((s64)(event_res[i][j][2] - event_res_avg[j][2])); - } - } - - normalize_noise(&runtime_nsecs_noise); - normalize_noise(&walltime_nsecs_noise); - normalize_noise(&runtime_cycles_noise); - - for (j = 0; j < nr_counters; j++) { - normalize_noise(&event_res_noise[j][0]); - normalize_noise(&event_res_noise[j][1]); - normalize_noise(&event_res_noise[j][2]); - } } static void print_stat(int argc, const char **argv) @@ -457,10 +424,11 @@ static void print_stat(int argc, const char **argv) fprintf(stderr, "\n"); fprintf(stderr, " %14.9f seconds time elapsed", - (double)walltime_nsecs_avg/1e9); + avg_stats(&walltime_nsecs_stats)/1e9); if (run_count > 1) { fprintf(stderr, " ( +- %7.3f%% )", - 100.0*(double)walltime_nsecs_noise/(double)walltime_nsecs_avg); + 100*stddev_stats(&walltime_nsecs_stats) / + avg_stats(&walltime_nsecs_stats)); } fprintf(stderr, "\n\n"); } diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 1150c6d..5f39805 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -188,6 +188,8 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) if ((edge && old_irr != ioapic->irr) || (!edge && !entry.fields.remote_irr)) ret = ioapic_service(ioapic, irq); + else + ret = 0; /* report coalesced interrupt */ } } return ret; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/