From 682367c494869008eb89ef733f196e99415ae862 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Wed, 18 Jun 2014 17:21:19 +0300 Subject: KVM: x86: Increase the number of fixed MTRR regs to 10 Recent Intel CPUs have 10 variable range MTRRs. Since operating systems sometime make assumptions on CPUs while they ignore capability MSRs, it is better for KVM to be consistent with recent CPUs. Reporting more MTRRs than actually supported has no functional implications. Signed-off-by: Nadav Amit Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 49314155b66c..0bab29de7f1b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -95,7 +95,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 80 #define KVM_NR_FIXED_MTRR_REGION 88 -#define KVM_NR_VAR_MTRR 8 +#define KVM_NR_VAR_MTRR 10 #define ASYNC_PF_PER_VCPU 64 -- cgit v1.2.3 From 7cb060a91c0efc5ff94f83c6df3ed705e143cdb9 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 19 Jun 2014 11:40:18 +0200 Subject: KVM: x86: preserve the high 32-bits of the PAT register KVM does not really do much with the PAT, so this went unnoticed for a long time. It is exposed however if you try to do rdmsr on the PAT register. Reported-by: Valentine Sinitsyn Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0bab29de7f1b..49205d01b9ad 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -461,7 +461,7 @@ struct kvm_vcpu_arch { bool nmi_injected; /* Trying to inject an NMI this entry */ struct mtrr_state_type mtrr_state; - u32 pat; + u64 pat; unsigned switch_db_regs; unsigned long db[KVM_NR_DB_REGS]; -- cgit v1.2.3 From f3aca3d09525f87731ba6b892c9b010570bc54b4 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 23 Jun 2014 13:22:05 -0700 Subject: nmi: provide the option to issue an NMI back trace to every cpu but current Sometimes it is preferred not to use the trigger_all_cpu_backtrace() routine when one wants to avoid capturing a back trace for current. For instance if one was previously captured recently. This patch provides a new routine namely trigger_allbutself_cpu_backtrace() which offers the flexibility to issue an NMI to every cpu but current and capture a back trace accordingly. Patch x86 and sparc to support new routine. [dzickus@redhat.com: add stub in #else clause] [dzickus@redhat.com: don't print message in single processor case, wrap with get/put_cpu based on Oleg's suggestion] [sfr@canb.auug.org.au: undo C99ism] Signed-off-by: Aaron Tomlin Signed-off-by: Don Zickus Acked-by: David S. Miller Cc: Mateusz Guzik Cc: Oleg Nesterov Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/include/asm/irq_64.h | 2 +- arch/sparc/kernel/process_64.c | 18 ++++++++++++------ arch/x86/include/asm/irq.h | 2 +- arch/x86/kernel/apic/hw_nmi.c | 18 ++++++++++++++---- include/linux/nmi.h | 11 ++++++++++- 5 files changed, 38 insertions(+), 13 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index 375cffcf7dbd..91d219381306 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -89,7 +89,7 @@ static inline unsigned long get_softint(void) return retval; } -void arch_trigger_all_cpu_backtrace(void); +void arch_trigger_all_cpu_backtrace(bool); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace extern void *hardirq_stack[NR_CPUS]; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index b2988f25e230..027e09986194 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp) } } -void arch_trigger_all_cpu_backtrace(void) +void arch_trigger_all_cpu_backtrace(bool include_self) { struct thread_info *tp = current_thread_info(); struct pt_regs *regs = get_irq_regs(); @@ -251,16 +251,22 @@ void arch_trigger_all_cpu_backtrace(void) spin_lock_irqsave(&global_cpu_snapshot_lock, flags); - memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); - this_cpu = raw_smp_processor_id(); - __global_reg_self(tp, regs, this_cpu); + memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); + + if (include_self) + __global_reg_self(tp, regs, this_cpu); smp_fetch_global_regs(); for_each_online_cpu(cpu) { - struct global_reg_snapshot *gp = &global_cpu_snapshot[cpu].reg; + struct global_reg_snapshot *gp; + + if (!include_self && cpu == this_cpu) + continue; + + gp = &global_cpu_snapshot[cpu].reg; __global_reg_poll(gp); @@ -292,7 +298,7 @@ void arch_trigger_all_cpu_backtrace(void) static void sysrq_handle_globreg(int key) { - arch_trigger_all_cpu_backtrace(); + arch_trigger_all_cpu_backtrace(true); } static struct sysrq_key_op sparc_globalreg_op = { diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index cb6cfcd034cf..a80cbb88ea91 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -43,7 +43,7 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC -void arch_trigger_all_cpu_backtrace(void); +void arch_trigger_all_cpu_backtrace(bool); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace #endif diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index c3fcb5de5083..6a1e71bde323 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -33,31 +33,41 @@ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; /* "in progress" flag of arch_trigger_all_cpu_backtrace */ static unsigned long backtrace_flag; -void arch_trigger_all_cpu_backtrace(void) +void arch_trigger_all_cpu_backtrace(bool include_self) { int i; + int cpu = get_cpu(); - if (test_and_set_bit(0, &backtrace_flag)) + if (test_and_set_bit(0, &backtrace_flag)) { /* * If there is already a trigger_all_cpu_backtrace() in progress * (backtrace_flag == 1), don't output double cpu dump infos. */ + put_cpu(); return; + } cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); + if (!include_self) + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - printk(KERN_INFO "sending NMI to all CPUs:\n"); - apic->send_IPI_all(NMI_VECTOR); + if (!cpumask_empty(to_cpumask(backtrace_mask))) { + pr_info("sending NMI to %s CPUs:\n", + (include_self ? "all" : "other")); + apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR); + } /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { if (cpumask_empty(to_cpumask(backtrace_mask))) break; mdelay(1); + touch_softlockup_watchdog(); } clear_bit(0, &backtrace_flag); smp_mb__after_atomic(); + put_cpu(); } static int diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 6a45fb583ff1..a17ab6398d7c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -32,15 +32,24 @@ static inline void touch_nmi_watchdog(void) #ifdef arch_trigger_all_cpu_backtrace static inline bool trigger_all_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(); + arch_trigger_all_cpu_backtrace(true); return true; } +static inline bool trigger_allbutself_cpu_backtrace(void) +{ + arch_trigger_all_cpu_backtrace(false); + return true; +} #else static inline bool trigger_all_cpu_backtrace(void) { return false; } +static inline bool trigger_allbutself_cpu_backtrace(void) +{ + return false; +} #endif #ifdef CONFIG_LOCKUP_DETECTOR -- cgit v1.2.3 From b9cd18de4db3c9ffa7e17b0dc0ca99ed5aa4d43a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Jul 2014 15:43:15 -0400 Subject: ptrace,x86: force IRET path after a ptrace_stop() The 'sysret' fastpath does not correctly restore even all regular registers, much less any segment registers or reflags values. That is very much part of why it's faster than 'iret'. Normally that isn't a problem, because the normal ptrace() interface catches the process using the signal handler infrastructure, which always returns with an iret. However, some paths can get caught using ptrace_event() instead of the signal path, and for those we need to make sure that we aren't going to return to user space using 'sysret'. Otherwise the modifications that may have been done to the register set by the tracer wouldn't necessarily take effect. Fix it by forcing IRET path by setting TIF_NOTIFY_RESUME from arch_ptrace_stop_needed() which is invoked from ptrace_stop(). Signed-off-by: Tejun Heo Reported-by: Andy Lutomirski Acked-by: Oleg Nesterov Suggested-by: Linus Torvalds Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- arch/x86/include/asm/ptrace.h | 16 ++++++++++++++++ include/linux/ptrace.h | 3 +++ 2 files changed, 19 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 14fd6fd75a19..6205f0c434db 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -231,6 +231,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, #define ARCH_HAS_USER_SINGLE_STEP_INFO +/* + * When hitting ptrace_stop(), we cannot return using SYSRET because + * that does not restore the full CPU state, only a minimal set. The + * ptracer can change arbitrary register values, which is usually okay + * because the usual ptrace stops run off the signal delivery path which + * forces IRET; however, ptrace_event() stops happen in arbitrary places + * in the kernel and don't force IRET path. + * + * So force IRET path after a ptrace stop. + */ +#define arch_ptrace_stop_needed(code, info) \ +({ \ + set_thread_flag(TIF_NOTIFY_RESUME); \ + false; \ +}) + struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 077904c8b70d..cc79eff4a1ad 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -334,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, * calling arch_ptrace_stop() when it would be superfluous. For example, * if the thread has not been back to user mode since the last stop, the * thread state might indicate that nothing needs to be done. + * + * This is guaranteed to be invoked once before a task stops for ptrace and + * may include arch-specific operations necessary prior to a ptrace stop. */ #define arch_ptrace_stop_needed(code, info) (0) #endif -- cgit v1.2.3