From 7e01b5acd88b3f3108d8c4ce44e3205d67437202 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 16 Apr 2015 14:47:33 +0200 Subject: kexec: allocate the kexec control page with KEXEC_CONTROL_MEMORY_GFP Introduce KEXEC_CONTROL_MEMORY_GFP to allow the architecture code to override the gfp flags of the allocation for the kexec control page. The loop in kimage_alloc_normal_control_pages allocates pages with GFP_KERNEL until a page is found that happens to have an address smaller than the KEXEC_CONTROL_MEMORY_LIMIT. On systems with a large memory size but a small KEXEC_CONTROL_MEMORY_LIMIT the loop will keep allocating memory until the oom killer steps in. Signed-off-by: Martin Schwidefsky --- kernel/kexec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kexec.c b/kernel/kexec.c index 38c25b1f2fd5..7a36fdcca5bf 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -707,7 +707,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, do { unsigned long pfn, epfn, addr, eaddr; - pages = kimage_alloc_pages(GFP_KERNEL, order); + pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; pfn = page_to_pfn(pages); -- cgit From 73459e2a1ada09a68c02cc5b73f3116fc8194b3d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 23 Apr 2015 13:20:18 +0200 Subject: x86: pvclock: Really remove the sched notifier for cross-cpu migrations This reverts commits 0a4e6be9ca17c54817cf814b4b5aa60478c6df27 and 80f7fdb1c7f0f9266421f823964fd1962681f6ce. The task migration notifier was originally introduced in order to support the pvclock vsyscall with non-synchronized TSC, but KVM only supports it with synchronized TSC. Hence, on KVM the race condition is only needed due to a bad implementation on the host side, and even then it's so rare that it's mostly theoretical. As far as KVM is concerned it's possible to fix the host, avoiding the additional complexity in the vDSO and the (re)introduction of the task migration notifier. Xen, on the other hand, hasn't yet implemented vsyscall support at all, so we do not care about its plans for non-synchronized TSC. Reported-by: Peter Zijlstra Suggested-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/pvclock.h | 1 - arch/x86/kernel/pvclock.c | 44 ------------------------------------------ arch/x86/vdso/vclock_gettime.c | 34 ++++++++++++++------------------ include/linux/sched.h | 8 -------- kernel/sched/core.c | 15 -------------- 5 files changed, 15 insertions(+), 87 deletions(-) (limited to 'kernel') diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 25b1cc07d496..d6b078e9fa28 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; - u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index e5ecd20e72dd..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 40d2473836c9..9793322751e0 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; - u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * When looping to get a consistent (time-info, tsc) pair, we - * also need to deal with the possibility we can switch vcpus, - * so make sure we always re-fetch time-info for the current vcpu. + * Note: hypervisor must guarantee that: + * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. + * 2. that per-CPU pvclock time info is updated if the + * underlying CPU changes. + * 3. that version is increased whenever underlying CPU + * changes. + * */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - /* Make sure migrate_count will change if we leave the VCPU. */ - do { - pvti = get_pvti(cpu); - migrate_count = pvti->migrate_count; - - cpu1 = cpu; - cpu = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1)); + pvti = get_pvti(cpu); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * - We must read TSC of pvti's VCPU. - * - KVM doesn't follow the versioning protocol, so data could - * change before version if we left the VCPU. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. */ - smp_rmb(); - } while (unlikely((pvti->pvti.version & 1) || - pvti->pvti.version != version || - pvti->migrate_count != migrate_count)); + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/include/linux/sched.h b/include/linux/sched.h index 8222ae40ecb0..26a2e6122734 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -175,14 +175,6 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); extern void update_cpu_load_nohz(void); -/* Notifier for when a task gets migrated to a new CPU */ -struct task_migration_notifier { - struct task_struct *task; - int from_cpu; - int to_cpu; -}; -extern void register_task_migration_notifier(struct notifier_block *n); - extern unsigned long get_parent_ip(unsigned long addr); extern void dump_cpu_task(int cpu); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f9123a82cbb6..fe22f7510bce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } -static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); - -void register_task_migration_notifier(struct notifier_block *n) -{ - atomic_notifier_chain_register(&task_migration_notifier, n); -} - #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1053,18 +1046,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { - struct task_migration_notifier tmn; - if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); - - tmn.task = p; - tmn.from_cpu = task_cpu(p); - tmn.to_cpu = new_cpu; - - atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); -- cgit From 876a7ae65b86d8cec8efe7d15d050ac61116874e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 27 Apr 2015 14:40:37 -0700 Subject: bpf: fix 64-bit divide ALU64_DIV instruction should be dividing 64-bit by 64-bit, whereas do_div() does 64-bit by 32-bit divide. x64 and arm64 JITs correctly implement 64 by 64 unsigned divide. llvm BPF backend emits code assuming that ALU64_DIV does 64 by 64. Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets") Reported-by: Michael Holzheu Acked-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4139a0f8b558..54f0e7fcd0e2 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -357,8 +357,8 @@ select_insn: ALU64_MOD_X: if (unlikely(SRC == 0)) return 0; - tmp = DST; - DST = do_div(tmp, SRC); + div64_u64_rem(DST, SRC, &tmp); + DST = tmp; CONT; ALU_MOD_X: if (unlikely(SRC == 0)) @@ -367,8 +367,8 @@ select_insn: DST = do_div(tmp, (u32) SRC); CONT; ALU64_MOD_K: - tmp = DST; - DST = do_div(tmp, IMM); + div64_u64_rem(DST, IMM, &tmp); + DST = tmp; CONT; ALU_MOD_K: tmp = (u32) DST; @@ -377,7 +377,7 @@ select_insn: ALU64_DIV_X: if (unlikely(SRC == 0)) return 0; - do_div(DST, SRC); + DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: if (unlikely(SRC == 0)) @@ -387,7 +387,7 @@ select_insn: DST = (u32) tmp; CONT; ALU64_DIV_K: - do_div(DST, IMM); + DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: tmp = (u32) DST; -- cgit From df8d9eeadd0f7a216f2476351d5aee43c6550bf0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 29 Apr 2015 15:19:21 +0200 Subject: cpuidle: Run tick_broadcast_exit() with disabled interrupts Commit 335f49196fd6 (sched/idle: Use explicit broadcast oneshot control function) replaced clockevents_notify() invocations in cpuidle_idle_call() with direct calls to tick_broadcast_enter() and tick_broadcast_exit(), but it overlooked the fact that interrupts were already enabled before calling the latter which led to functional breakage on systems using idle states with the CPUIDLE_FLAG_TIMER_STOP flag set. Fix that by moving the invocations of tick_broadcast_enter() and tick_broadcast_exit() down into cpuidle_enter_state() where interrupts are still disabled when tick_broadcast_exit() is called. Also ensure that interrupts will be disabled before running tick_broadcast_exit() even if they have been enabled by the idle state's ->enter callback. Trigger a WARN_ON_ONCE() in that case, as we generally don't want that to happen for states with CPUIDLE_FLAG_TIMER_STOP set. Fixes: 335f49196fd6 (sched/idle: Use explicit broadcast oneshot control function) Reported-and-tested-by: Linus Walleij Acked-by: Peter Zijlstra (Intel) Acked-by: Daniel Lezcano Reported-and-tested-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 16 ++++++++++++++++ kernel/sched/idle.c | 16 ++-------------- 2 files changed, 18 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 7a73a279e179..61c417b9e53f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -158,9 +158,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, int entered_state; struct cpuidle_state *target_state = &drv->states[index]; + bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); ktime_t time_start, time_end; s64 diff; + /* + * Tell the time framework to switch to a broadcast timer because our + * local timer will be shut down. If a local timer is used from another + * CPU as a broadcast timer, this call may fail if it is not available. + */ + if (broadcast && tick_broadcast_enter()) + return -EBUSY; + trace_cpu_idle_rcuidle(index, dev->cpu); time_start = ktime_get(); @@ -169,6 +178,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, time_end = ktime_get(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + if (broadcast) { + if (WARN_ON_ONCE(!irqs_disabled())) + local_irq_disable(); + + tick_broadcast_exit(); + } + if (!cpuidle_state_is_coupled(dev, drv, entered_state)) local_irq_enable(); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index deef1caa94c6..fefcb1fa5160 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -81,7 +81,6 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - unsigned int broadcast; bool reflect; /* @@ -150,17 +149,6 @@ static void cpuidle_idle_call(void) goto exit_idle; } - broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP; - - /* - * Tell the time framework to switch to a broadcast timer - * because our local timer will be shutdown. If a local timer - * is used from another cpu as a broadcast timer, this call may - * fail if it is not available - */ - if (broadcast && tick_broadcast_enter()) - goto use_default; - /* Take note of the planned idle state. */ idle_set_state(this_rq(), &drv->states[next_state]); @@ -174,8 +162,8 @@ static void cpuidle_idle_call(void) /* The cpu is no longer idle or about to enter idle. */ idle_set_state(this_rq(), NULL); - if (broadcast) - tick_broadcast_exit(); + if (entered_state == -EBUSY) + goto use_default; /* * Give the governor an opportunity to reflect on the outcome -- cgit From 9c4249c8e0221e5cfae758d35b768aee84abf6c0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Apr 2015 14:58:43 +0100 Subject: modsign: change default key details Change default key details to be more obviously unspecified. Reported-by: Linus Torvalds Signed-off-by: David Howells Acked-by: James Morris Signed-off-by: Linus Torvalds --- Documentation/module-signing.txt | 6 +++--- kernel/Makefile | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt index 09c2382ad055..c72702ec1ded 100644 --- a/Documentation/module-signing.txt +++ b/Documentation/module-signing.txt @@ -119,9 +119,9 @@ Most notably, in the x509.genkey file, the req_distinguished_name section should be altered from the default: [ req_distinguished_name ] - O = Magrathea - CN = Glacier signing key - emailAddress = slartibartfast@magrathea.h2g2 + #O = Unspecified company + CN = Build time autogenerated kernel key + #emailAddress = unspecified.user@unspecified.company The generated RSA key size can also be set with: diff --git a/kernel/Makefile b/kernel/Makefile index 0f8f8b0bc1bf..60c302cfb4d3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -197,9 +197,9 @@ x509.genkey: @echo >>x509.genkey "x509_extensions = myexts" @echo >>x509.genkey @echo >>x509.genkey "[ req_distinguished_name ]" - @echo >>x509.genkey "O = Magrathea" - @echo >>x509.genkey "CN = Glacier signing key" - @echo >>x509.genkey "emailAddress = slartibartfast@magrathea.h2g2" + @echo >>x509.genkey "#O = Unspecified company" + @echo >>x509.genkey "CN = Build time autogenerated kernel key" + @echo >>x509.genkey "#emailAddress = unspecified.user@unspecified.company" @echo >>x509.genkey @echo >>x509.genkey "[ myexts ]" @echo >>x509.genkey "basicConstraints=critical,CA:FALSE" -- cgit