From 12997d1a999cd1b22e21a238c96780f2a55e4e13 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 18 Nov 2013 11:00:29 -0700 Subject: Revert "workqueue: allow work_on_cpu() to be called recursively" This reverts commit c2fda509667b0fda4372a237f5a59ea4570b1627. c2fda509667b removed lockdep annotation from work_on_cpu() to work around the PCI path that calls work_on_cpu() from within a work_on_cpu() work item (PF driver .probe() method -> pci_enable_sriov() -> add VFs -> VF driver .probe method). 961da7fb6b22 ("PCI: Avoid unnecessary CPU switch when calling driver .probe() method) avoids that recursive work_on_cpu() use in a different way, so this revert restores the work_on_cpu() lockdep annotation. Signed-off-by: Bjorn Helgaas Acked-by: Tejun Heo --- kernel/workqueue.c | 32 ++++++++++---------------------- 1 file changed, 10 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 987293d03eb..5690b8eabfb 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2840,19 +2840,6 @@ already_gone: return false; } -static bool __flush_work(struct work_struct *work) -{ - struct wq_barrier barr; - - if (start_flush_work(work, &barr)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - return true; - } else { - return false; - } -} - /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush @@ -2866,10 +2853,18 @@ static bool __flush_work(struct work_struct *work) */ bool flush_work(struct work_struct *work) { + struct wq_barrier barr; + lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); - return __flush_work(work); + if (start_flush_work(work, &barr)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else { + return false; + } } EXPORT_SYMBOL_GPL(flush_work); @@ -4814,14 +4809,7 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); - - /* - * The work item is on-stack and can't lead to deadlock through - * flushing. Use __flush_work() to avoid spurious lockdep warnings - * when work_on_cpu()s are nested. - */ - __flush_work(&wfc.work); - + flush_work(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); -- cgit v1.2.3-70-g09d2 From 4fc9bbf98fd66f879e628d8537ba7c240be2b58e Mon Sep 17 00:00:00 2001 From: Khalid Aziz Date: Wed, 27 Nov 2013 15:19:25 -0700 Subject: PCI: Disable Bus Master only on kexec reboot Add a flag to tell the PCI subsystem that kernel is shutting down in preparation to kexec a kernel. Add code in PCI subsystem to use this flag to clear Bus Master bit on PCI devices only in case of kexec reboot. This fixes a power-off problem on Acer Aspire V5-573G and likely other machines and avoids any other issues caused by clearing Bus Master bit on PCI devices in normal shutdown path. The problem was introduced by b566a22c2332 ("PCI: disable Bus Master on PCI device shutdown"). This patch is based on discussion at http://marc.info/?l=linux-pci&m=138425645204355&w=2 Link: https://bugzilla.kernel.org/show_bug.cgi?id=63861 Reported-by: Chang Liu Signed-off-by: Khalid Aziz Signed-off-by: Bjorn Helgaas Acked-by: Konstantin Khlebnikov Cc: stable@vger.kernel.org # v3.5+ --- drivers/pci/pci-driver.c | 12 +++++++++--- include/linux/kexec.h | 3 +++ kernel/kexec.c | 4 ++++ 3 files changed, 16 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 7edd5c30744..25f0bc65916 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "pci.h" struct pci_dynid { @@ -415,12 +416,17 @@ static void pci_device_shutdown(struct device *dev) pci_msi_shutdown(pci_dev); pci_msix_shutdown(pci_dev); +#ifdef CONFIG_KEXEC /* - * Turn off Bus Master bit on the device to tell it to not - * continue to do DMA. Don't touch devices in D3cold or unknown states. + * If this is a kexec reboot, turn off Bus Master bit on the + * device to tell it to not continue to do DMA. Don't touch + * devices in D3cold or unknown states. + * If it is not a kexec reboot, firmware will hit the PCI + * devices with big hammer and stop their DMA any way. */ - if (pci_dev->current_state <= PCI_D3hot) + if (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot)) pci_clear_master(pci_dev); +#endif } #ifdef CONFIG_PM diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d78d28a733b..5fd33dc1fe3 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -198,6 +198,9 @@ extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; +/* flag to track if kexec reboot is in progress */ +extern bool kexec_in_progress; + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, diff --git a/kernel/kexec.c b/kernel/kexec.c index 490afc03627..d0d8fca5406 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; size_t vmcoreinfo_size; size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); +/* Flag to indicate we are going to kexec a new kernel */ +bool kexec_in_progress = false; + /* Location of the reserved area for the crash kernel */ struct resource crashk_res = { .name = "Crash kernel", @@ -1675,6 +1678,7 @@ int kernel_kexec(void) } else #endif { + kexec_in_progress = true; kernel_restart_prepare(NULL); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); -- cgit v1.2.3-70-g09d2 From 7cfe5b3310a1b45f385ff18647bddb487a6c5525 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 10 Dec 2013 17:42:50 +1030 Subject: Ignore generated file kernel/x509_certificate_list $ git status # On branch pending-rebases # Untracked files: # (use "git add ..." to include in what will be committed) # # kernel/x509_certificate_list nothing added to commit but untracked files present (use "git add" to track) $ Signed-off-by: Rusty Russell Signed-off-by: David Howells --- kernel/.gitignore | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/.gitignore b/kernel/.gitignore index b3097bde4e9..790d83c7d16 100644 --- a/kernel/.gitignore +++ b/kernel/.gitignore @@ -5,3 +5,4 @@ config_data.h config_data.gz timeconst.h hz.bc +x509_certificate_list -- cgit v1.2.3-70-g09d2 From 62226983da070f7e51068ec2e3a4da34672964c7 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Thu, 5 Dec 2013 14:48:22 +0100 Subject: KEYS: correct alignment of system_certificate_list content in assembly file Apart from data-type specific alignment constraints, there are also architecture-specific alignment requirements. For example, on s390 symbols must be on even addresses implying a 2-byte alignment. If the system_certificate_list_end symbol is on an odd address and if this address is loaded, the least-significant bit is ignored. As a result, the load_system_certificate_list() fails to load the certificates because of a wrong certificate length calculation. To be safe, align system_certificate_list on an 8-byte boundary. Also improve the length calculation of the system_certificate_list content. Introduce a system_certificate_list_size (8-byte aligned because of unsigned long) variable that stores the length. Let the linker calculate this size by introducing a start and end label for the certificate content. Signed-off-by: Hendrik Brueckner Signed-off-by: David Howells --- kernel/system_certificates.S | 14 ++++++++++++-- kernel/system_keyring.c | 4 ++-- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S index 4aef390671c..3e9868d4753 100644 --- a/kernel/system_certificates.S +++ b/kernel/system_certificates.S @@ -3,8 +3,18 @@ __INITRODATA + .align 8 .globl VMLINUX_SYMBOL(system_certificate_list) VMLINUX_SYMBOL(system_certificate_list): +__cert_list_start: .incbin "kernel/x509_certificate_list" - .globl VMLINUX_SYMBOL(system_certificate_list_end) -VMLINUX_SYMBOL(system_certificate_list_end): +__cert_list_end: + + .align 8 + .globl VMLINUX_SYMBOL(system_certificate_list_size) +VMLINUX_SYMBOL(system_certificate_list_size): +#ifdef CONFIG_64BIT + .quad __cert_list_end - __cert_list_start +#else + .long __cert_list_end - __cert_list_start +#endif diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c index 564dd93430a..52ebc70263f 100644 --- a/kernel/system_keyring.c +++ b/kernel/system_keyring.c @@ -22,7 +22,7 @@ struct key *system_trusted_keyring; EXPORT_SYMBOL_GPL(system_trusted_keyring); extern __initconst const u8 system_certificate_list[]; -extern __initconst const u8 system_certificate_list_end[]; +extern __initconst const unsigned long system_certificate_list_size; /* * Load the compiled-in keys @@ -60,8 +60,8 @@ static __init int load_system_certificate_list(void) pr_notice("Loading compiled-in X.509 certificates\n"); - end = system_certificate_list_end; p = system_certificate_list; + end = p + system_certificate_list_size; while (p < end) { /* Each cert begins with an ASN.1 SEQUENCE tag and must be more * than 256 bytes in size. -- cgit v1.2.3-70-g09d2 From 8e8339a3a1069141985daaa2521ba304509ddecd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 11 Dec 2013 11:09:53 +0100 Subject: sched: Initialize power_orig for overlapping groups Yinghai reported that he saw a /0 in sg_capacity on his EX parts. Make sure to always initialize power_orig now that we actually use it. Ideally build_sched_domains() -> init_sched_groups_power() would also initialize this; but for some yet unexplained reason some setups seem to miss updates there. Reported-by: Yinghai Lu Tested-by: Yinghai Lu Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-l8ng2m9uml6fhibln8wqpom7@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e85cda20ab2..19af58f3a26 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5112,6 +5112,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) * die on a /0 trap. */ sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span); + sg->sgp->power_orig = sg->sgp->power; /* * Make sure the first group of this domain contains the -- cgit v1.2.3-70-g09d2 From 9dbdb155532395ba000c5d5d187658b0e17e529f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Nov 2013 18:27:06 +0100 Subject: sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer Signed-off-by: Peter Zijlstra Cc: fweisbec@gmail.com Cc: Paul Turner Cc: Stanislaw Gruszka Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +- kernel/sched/fair.c | 144 ++++++++++++++++++++++---------------------------- 2 files changed, 66 insertions(+), 81 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 96d674ba387..53f97eb8dbc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -930,7 +930,8 @@ struct pipe_inode_info; struct uts_namespace; struct load_weight { - unsigned long weight, inv_weight; + unsigned long weight; + u32 inv_weight; }; struct sched_avg { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fd773ade1a3..9030da7bcb1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -178,59 +178,61 @@ void sched_init_granularity(void) update_sysctl(); } -#if BITS_PER_LONG == 32 -# define WMULT_CONST (~0UL) -#else -# define WMULT_CONST (1UL << 32) -#endif - +#define WMULT_CONST (~0U) #define WMULT_SHIFT 32 -/* - * Shift right and round: - */ -#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) +static void __update_inv_weight(struct load_weight *lw) +{ + unsigned long w; + + if (likely(lw->inv_weight)) + return; + + w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) + lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; + else + lw->inv_weight = WMULT_CONST / w; +} /* - * delta *= weight / lw + * delta_exec * weight / lw.weight + * OR + * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT + * + * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case + * we're guaranteed shift stays positive because inv_weight is guaranteed to + * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. + * + * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus + * weight/lw.weight <= 1, and therefore our shift will also be positive. */ -static unsigned long -calc_delta_mine(unsigned long delta_exec, unsigned long weight, - struct load_weight *lw) +static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw) { - u64 tmp; + u64 fact = scale_load_down(weight); + int shift = WMULT_SHIFT; - /* - * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched - * entities since MIN_SHARES = 2. Treat weight as 1 if less than - * 2^SCHED_LOAD_RESOLUTION. - */ - if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION))) - tmp = (u64)delta_exec * scale_load_down(weight); - else - tmp = (u64)delta_exec; + __update_inv_weight(lw); - if (!lw->inv_weight) { - unsigned long w = scale_load_down(lw->weight); - - if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) - lw->inv_weight = 1; - else if (unlikely(!w)) - lw->inv_weight = WMULT_CONST; - else - lw->inv_weight = WMULT_CONST / w; + if (unlikely(fact >> 32)) { + while (fact >> 32) { + fact >>= 1; + shift--; + } } - /* - * Check whether we'd overflow the 64-bit multiplication: - */ - if (unlikely(tmp > WMULT_CONST)) - tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, - WMULT_SHIFT/2); - else - tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); + /* hint to use a 32x32->64 mul */ + fact = (u64)(u32)fact * lw->inv_weight; + + while (fact >> 32) { + fact >>= 1; + shift--; + } - return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); + return mul_u64_u32_shr(delta_exec, fact, shift); } @@ -443,7 +445,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) #endif /* CONFIG_FAIR_GROUP_SCHED */ static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec); +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -612,11 +614,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write, /* * delta /= w */ -static inline unsigned long -calc_delta_fair(unsigned long delta, struct sched_entity *se) +static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) { if (unlikely(se->load.weight != NICE_0_LOAD)) - delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load); + delta = __calc_delta(delta, NICE_0_LOAD, &se->load); return delta; } @@ -665,7 +666,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_add(&lw, se->load.weight); load = &lw; } - slice = calc_delta_mine(slice, se->load.weight, load); + slice = __calc_delta(slice, se->load.weight, load); } return slice; } @@ -703,47 +704,32 @@ void init_task_runnable_average(struct task_struct *p) #endif /* - * Update the current task's runtime statistics. Skip current tasks that - * are not in our scheduling class. + * Update the current task's runtime statistics. */ -static inline void -__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, - unsigned long delta_exec) -{ - unsigned long delta_exec_weighted; - - schedstat_set(curr->statistics.exec_max, - max((u64)delta_exec, curr->statistics.exec_max)); - - curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = calc_delta_fair(delta_exec, curr); - - curr->vruntime += delta_exec_weighted; - update_min_vruntime(cfs_rq); -} - static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; u64 now = rq_clock_task(rq_of(cfs_rq)); - unsigned long delta_exec; + u64 delta_exec; if (unlikely(!curr)) return; - /* - * Get the amount of time the current task was running - * since the last time we changed load (this cannot - * overflow on 32 bits): - */ - delta_exec = (unsigned long)(now - curr->exec_start); - if (!delta_exec) + delta_exec = now - curr->exec_start; + if (unlikely((s64)delta_exec <= 0)) return; - __update_curr(cfs_rq, curr, delta_exec); curr->exec_start = now; + schedstat_set(curr->statistics.exec_max, + max(delta_exec, curr->statistics.exec_max)); + + curr->sum_exec_runtime += delta_exec; + schedstat_add(cfs_rq, exec_clock, delta_exec); + + curr->vruntime += calc_delta_fair(delta_exec, curr); + update_min_vruntime(cfs_rq); + if (entity_is_task(curr)) { struct task_struct *curtask = task_of(curr); @@ -3015,8 +3001,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) } } -static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) +static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; @@ -3034,7 +3019,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, } static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) return; @@ -3574,8 +3559,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) return rq_clock_task(rq_of(cfs_rq)); } -static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) {} +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} -- cgit v1.2.3-70-g09d2 From f12d5bfceb7e1f9051563381ec047f7f13956c3c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 12 Dec 2013 09:38:42 -0800 Subject: futex: fix handling of read-only-mapped hugepages The hugepage code had the exact same bug that regular pages had in commit 7485d0d3758e ("futexes: Remove rw parameter from get_futex_key()"). The regular page case was fixed by commit 9ea71503a8ed ("futex: Fix regression with read only mappings"), but the transparent hugepage case (added in a5b338f2b0b1: "thp: update futex compound knowledge") case remained broken. Found by Dave Jones and his trinity tool. Reported-and-tested-by: Dave Jones Cc: stable@kernel.org # v2.6.38+ Acked-by: Thomas Gleixner Cc: Mel Gorman Cc: Darren Hart Cc: Andrea Arcangeli Cc: Oleg Nesterov Signed-off-by: Linus Torvalds --- kernel/futex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 80ba086f021..02febad0079 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -288,7 +288,7 @@ again: put_page(page); /* serialize against __split_huge_page_splitting() */ local_irq_disable(); - if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) { + if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) { page_head = compound_head(page); /* * page_head is valid pointer but we must pin -- cgit v1.2.3-70-g09d2 From 5cdec2d833748fbd27d3682f7209225c504c79c5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 12 Dec 2013 09:53:51 -0800 Subject: futex: move user address verification up to common code When debugging the read-only hugepage case, I was confused by the fact that get_futex_key() did an access_ok() only for the non-shared futex case, since the user address checking really isn't in any way specific to the private key handling. Now, it turns out that the shared key handling does effectively do the equivalent checks inside get_user_pages_fast() (it doesn't actually check the address range on x86, but does check the page protections for being a user page). So it wasn't actually a bug, but the fact that we treat the address differently for private and shared futexes threw me for a loop. Just move the check up, so that it gets done for both cases. Also, use the 'rw' parameter for the type, even if it doesn't actually matter any more (it's a historical artifact of the old racy i386 "page faults from kernel space don't check write protections"). Cc: Thomas Gleixner Signed-off-by: Linus Torvalds --- kernel/futex.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 02febad0079..f6ff0191ecf 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -251,6 +251,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) return -EINVAL; address -= key->both.offset; + if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) + return -EFAULT; + /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs @@ -259,8 +262,6 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) * but access_ok() should be faster than find_vma() */ if (!fshared) { - if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) - return -EFAULT; key->private.mm = mm; key->private.address = address; get_futex_key_refs(key); -- cgit v1.2.3-70-g09d2 From d7ec435fdd03cfee70dba934ee384acc87bd6d00 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 13 Dec 2013 15:20:19 +0000 Subject: X.509: Fix certificate gathering Fix the gathering of certificates from both the source tree and the build tree to correctly calculate the pathnames of all the certificates. The problem was that if the default generated cert, signing_key.x509, didn't exist then it would not have a path attached and if it did, it would have a path attached. This means that the contents of kernel/.x509.list would change between the first compilation in a directory and the second. After the second it would remain stable because the signing_key.x509 file exists. The consequence was that the kernel would get relinked unconditionally on the second recompilation. The second recompilation would also show something like this: X.509 certificate list changed CERTS kernel/x509_certificate_list - Including cert /home/torvalds/v2.6/linux/signing_key.x509 AS kernel/system_certificates.o LD kernel/built-in.o which is why the relink would happen. Unfortunately, it isn't a simple matter of just sticking a path on the front of the filename of the certificate in the build directory as make can't then work out how to build it. So the path has to be prepended to the name for sorting and duplicate elimination and then removed for the make rule if it is in the build tree. Reported-by: Linus Torvalds Signed-off-by: David Howells --- kernel/Makefile | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index bbaf7d59c1b..c23bb0b3029 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -137,9 +137,10 @@ $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE ############################################################################### ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y) X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509) -X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509 -X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \ +X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509 +X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \ $(or $(realpath $(CERT)),$(CERT)))) +X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw)) ifeq ($(X509_CERTIFICATES),) $(warning *** No X.509 certificates found ***) -- cgit v1.2.3-70-g09d2 From f46a3cbbebdaa5ca7b3ab23d7b81925dbe152bcb Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Tue, 10 Dec 2013 22:39:57 +0400 Subject: KEYS: Remove files generated when SYSTEM_TRUSTED_KEYRING=y Always remove generated SYSTEM_TRUSTED_KEYRING files while doing make mrproper. Signed-off-by: Kirill Tkhai Signed-off-by: David Howells --- kernel/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index c23bb0b3029..bc010ee272b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -165,9 +165,9 @@ $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list targets += $(obj)/.x509.list $(obj)/.x509.list: @echo $(X509_CERTIFICATES) >$@ +endif clean-files := x509_certificate_list .x509.list -endif ifeq ($(CONFIG_MODULE_SIG),y) ############################################################################### -- cgit v1.2.3-70-g09d2 From 6bd364d82920be726c2d678e7ba9e27112686e11 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Fri, 13 Dec 2013 15:00:32 +0800 Subject: KEYS: fix uninitialized persistent_keyring_register_sem We run into this bug: [ 2736.063245] Unable to handle kernel paging request for data at address 0x00000000 [ 2736.063293] Faulting instruction address: 0xc00000000037efb0 [ 2736.063300] Oops: Kernel access of bad area, sig: 11 [#1] [ 2736.063303] SMP NR_CPUS=2048 NUMA pSeries [ 2736.063310] Modules linked in: sg nfsv3 rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6table_mangle ip6table_security ip6table_raw ip6t_REJECT iptable_nat nf_nat_ipv4 iptable_mangle iptable_security iptable_raw ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack ebtable_filter ebtables ip6table_filter iptable_filter ip_tables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 nf_nat nf_conntrack ip6_tables ibmveth pseries_rng nx_crypto nfsd auth_rpcgss nfs_acl lockd sunrpc binfmt_misc xfs libcrc32c dm_service_time sd_mod crc_t10dif crct10dif_common ibmvfc scsi_transport_fc scsi_tgt dm_mirror dm_region_hash dm_log dm_multipath dm_mod [ 2736.063383] CPU: 1 PID: 7128 Comm: ssh Not tainted 3.10.0-48.el7.ppc64 #1 [ 2736.063389] task: c000000131930120 ti: c0000001319a0000 task.ti: c0000001319a0000 [ 2736.063394] NIP: c00000000037efb0 LR: c0000000006c40f8 CTR: 0000000000000000 [ 2736.063399] REGS: c0000001319a3870 TRAP: 0300 Not tainted (3.10.0-48.el7.ppc64) [ 2736.063403] MSR: 8000000000009032 CR: 28824242 XER: 20000000 [ 2736.063415] SOFTE: 0 [ 2736.063418] CFAR: c00000000000908c [ 2736.063421] DAR: 0000000000000000, DSISR: 40000000 [ 2736.063425] GPR00: c0000000006c40f8 c0000001319a3af0 c000000001074788 c0000001319a3bf0 GPR04: 0000000000000000 0000000000000000 0000000000000020 000000000000000a GPR08: fffffffe00000002 00000000ffff0000 0000000080000001 c000000000924888 GPR12: 0000000028824248 c000000007e00400 00001fffffa0f998 0000000000000000 GPR16: 0000000000000022 00001fffffa0f998 0000010022e92470 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR24: 0000000000000000 c000000000f4a828 00003ffffe527108 0000000000000000 GPR28: c000000000f4a730 c000000000f4a828 0000000000000000 c0000001319a3bf0 [ 2736.063498] NIP [c00000000037efb0] .__list_add+0x30/0x110 [ 2736.063504] LR [c0000000006c40f8] .rwsem_down_write_failed+0x78/0x264 [ 2736.063508] PACATMSCRATCH [800000000280f032] [ 2736.063511] Call Trace: [ 2736.063516] [c0000001319a3af0] [c0000001319a3b80] 0xc0000001319a3b80 (unreliable) [ 2736.063523] [c0000001319a3b80] [c0000000006c40f8] .rwsem_down_write_failed+0x78/0x264 [ 2736.063530] [c0000001319a3c50] [c0000000006c1bb0] .down_write+0x70/0x78 [ 2736.063536] [c0000001319a3cd0] [c0000000002e5ffc] .keyctl_get_persistent+0x20c/0x320 [ 2736.063542] [c0000001319a3dc0] [c0000000002e2388] .SyS_keyctl+0x238/0x260 [ 2736.063548] [c0000001319a3e30] [c000000000009e7c] syscall_exit+0x0/0x7c [ 2736.063553] Instruction dump: [ 2736.063556] 7c0802a6 fba1ffe8 fbc1fff0 fbe1fff8 7cbd2b78 7c9e2378 7c7f1b78 f8010010 [ 2736.063566] f821ff71 e8a50008 7fa52040 40de00c0 7fbd2840 40de0094 7fbff040 [ 2736.063579] ---[ end trace 2708241785538296 ]--- It's caused by uninitialized persistent_keyring_register_sem. The bug was introduced by commit f36f8c75, two typos are in that commit: CONFIG_KEYS_KERBEROS_CACHE should be CONFIG_PERSISTENT_KEYRINGS and krb_cache_register_sem should be persistent_keyring_register_sem. Signed-off-by: Xiao Guangrong Signed-off-by: David Howells --- kernel/user.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index a3a0dbfda32..c006131beb7 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,9 +51,9 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, -#ifdef CONFIG_KEYS_KERBEROS_CACHE - .krb_cache_register_sem = - __RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem), +#ifdef CONFIG_PERSISTENT_KEYRINGS + .persistent_keyring_register_sem = + __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem), #endif }; EXPORT_SYMBOL_GPL(init_user_ns); -- cgit v1.2.3-70-g09d2 From c4602c1c818bd6626178d6d3fcc152d9f2f48ac0 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Mon, 16 Dec 2013 15:20:01 +0800 Subject: ftrace: Initialize the ftrace profiler for each possible cpu Ftrace currently initializes only the online CPUs. This implementation has two problems: - If we online a CPU after we enable the function profile, and then run the test, we will lose the trace information on that CPU. Steps to reproduce: # echo 0 > /sys/devices/system/cpu/cpu1/online # cd /tracing/ # echo >> set_ftrace_filter # echo 1 > function_profile_enabled # echo 1 > /sys/devices/system/cpu/cpu1/online # run test - If we offline a CPU before we enable the function profile, we will not clear the trace information when we enable the function profile. It will trouble the users. Steps to reproduce: # cd /tracing/ # echo >> set_ftrace_filter # echo 1 > function_profile_enabled # run test # cat trace_stat/function* # echo 0 > /sys/devices/system/cpu/cpu1/online # echo 0 > function_profile_enabled # echo 1 > function_profile_enabled # cat trace_stat/function* # run test # cat trace_stat/function* So it is better that we initialize the ftrace profiler for each possible cpu every time we enable the function profile instead of just the online ones. Link: http://lkml.kernel.org/r/1387178401-10619-1-git-send-email-miaox@cn.fujitsu.com Cc: stable@vger.kernel.org # 2.6.31+ Signed-off-by: Miao Xie Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0e9f9eaade2..72a0f81dc5a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -775,7 +775,7 @@ static int ftrace_profile_init(void) int cpu; int ret = 0; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { ret = ftrace_profile_init_cpu(cpu); if (ret) break; -- cgit v1.2.3-70-g09d2 From 443772776c69ac9293d66b4d69fd9af16299cc2a Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Mon, 16 Dec 2013 14:17:36 +0200 Subject: perf: Disable all pmus on unthrottling and rescheduling Currently, only one PMU in a context gets disabled during unthrottling and event_sched_{out,in}(), however, events in one context may belong to different pmus, which results in PMUs being reprogrammed while they are still enabled. This means that mixed PMU use [which is rare in itself] resulted in potentially completely unreliable results: corrupted events, bogus results, etc. This patch temporarily disables PMUs that correspond to each event in the context while these events are being modified. Signed-off-by: Alexander Shishkin Reviewed-by: Andi Kleen Signed-off-by: Peter Zijlstra Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Stephane Eranian Cc: Alexander Shishkin Link: http://lkml.kernel.org/r/1387196256-8030-1-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 72348dc192c..f5744010a8d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1396,6 +1396,8 @@ event_sched_out(struct perf_event *event, if (event->state != PERF_EVENT_STATE_ACTIVE) return; + perf_pmu_disable(event->pmu); + event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; @@ -1412,6 +1414,8 @@ event_sched_out(struct perf_event *event, ctx->nr_freq--; if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; + + perf_pmu_enable(event->pmu); } static void @@ -1652,6 +1656,7 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx) { u64 tstamp = perf_event_time(event); + int ret = 0; if (event->state <= PERF_EVENT_STATE_OFF) return 0; @@ -1674,10 +1679,13 @@ event_sched_in(struct perf_event *event, */ smp_wmb(); + perf_pmu_disable(event->pmu); + if (event->pmu->add(event, PERF_EF_START)) { event->state = PERF_EVENT_STATE_INACTIVE; event->oncpu = -1; - return -EAGAIN; + ret = -EAGAIN; + goto out; } event->tstamp_running += tstamp - event->tstamp_stopped; @@ -1693,7 +1701,10 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; - return 0; +out: + perf_pmu_enable(event->pmu); + + return ret; } static int @@ -2743,6 +2754,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, if (!event_filter_match(event)) continue; + perf_pmu_disable(event->pmu); + hwc = &event->hw; if (hwc->interrupts == MAX_INTERRUPTS) { @@ -2752,7 +2765,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, } if (!event->attr.freq || !event->attr.sample_freq) - continue; + goto next; /* * stop the event and update event->count @@ -2774,6 +2787,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, perf_adjust_period(event, period, delta, false); event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0); + next: + perf_pmu_enable(event->pmu); } perf_pmu_enable(ctx->pmu); -- cgit v1.2.3-70-g09d2 From 5d4cf996cf134e8ddb4f906b8197feb9267c2b77 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 17 Dec 2013 09:21:25 +0000 Subject: sched: Assign correct scheduling domain to 'sd_llc' Commit 42eb088e (sched: Avoid NULL dereference on sd_busy) corrected a NULL dereference on sd_busy but the fix also altered what scheduling domain it used for the 'sd_llc' percpu variable. One impact of this is that a task selecting a runqueue may consider idle CPUs that are not cache siblings as candidates for running. Tasks are then running on CPUs that are not cache hot. This was found through bisection where ebizzy threads were not seeing equal performance and it looked like a scheduling fairness issue. This patch mitigates but does not completely fix the problem on all machines tested implying there may be an additional bug or a common root cause. Here are the average range of performance seen by individual ebizzy threads. It was tested on top of candidate patches related to x86 TLB range flushing. 4-core machine 3.13.0-rc3 3.13.0-rc3 vanilla fixsd-v3r3 Mean 1 0.00 ( 0.00%) 0.00 ( 0.00%) Mean 2 0.34 ( 0.00%) 0.10 ( 70.59%) Mean 3 1.29 ( 0.00%) 0.93 ( 27.91%) Mean 4 7.08 ( 0.00%) 0.77 ( 89.12%) Mean 5 193.54 ( 0.00%) 2.14 ( 98.89%) Mean 6 151.12 ( 0.00%) 2.06 ( 98.64%) Mean 7 115.38 ( 0.00%) 2.04 ( 98.23%) Mean 8 108.65 ( 0.00%) 1.92 ( 98.23%) 8-core machine Mean 1 0.00 ( 0.00%) 0.00 ( 0.00%) Mean 2 0.40 ( 0.00%) 0.21 ( 47.50%) Mean 3 23.73 ( 0.00%) 0.89 ( 96.25%) Mean 4 12.79 ( 0.00%) 1.04 ( 91.87%) Mean 5 13.08 ( 0.00%) 2.42 ( 81.50%) Mean 6 23.21 ( 0.00%) 69.46 (-199.27%) Mean 7 15.85 ( 0.00%) 101.72 (-541.77%) Mean 8 109.37 ( 0.00%) 19.13 ( 82.51%) Mean 12 124.84 ( 0.00%) 28.62 ( 77.07%) Mean 16 113.50 ( 0.00%) 24.16 ( 78.71%) It's eliminated for one machine and reduced for another. Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra Cc: Alex Shi Cc: Andrew Morton Cc: Fengguang Wu Cc: H Peter Anvin Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20131217092124.GV11295@suse.de Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 19af58f3a26..a88f4a485c5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4902,6 +4902,7 @@ DEFINE_PER_CPU(struct sched_domain *, sd_asym); static void update_top_cache_domain(int cpu) { struct sched_domain *sd; + struct sched_domain *busy_sd = NULL; int id = cpu; int size = 1; @@ -4909,9 +4910,9 @@ static void update_top_cache_domain(int cpu) if (sd) { id = cpumask_first(sched_domain_span(sd)); size = cpumask_weight(sched_domain_span(sd)); - sd = sd->parent; /* sd_busy */ + busy_sd = sd->parent; /* sd_busy */ } - rcu_assign_pointer(per_cpu(sd_busy, cpu), sd); + rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd); rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); per_cpu(sd_llc_size, cpu) = size; -- cgit v1.2.3-70-g09d2 From 757dfcaa41844595964f1220f1d33182dae49976 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Wed, 27 Nov 2013 19:59:13 +0400 Subject: sched/rt: Fix rq's cpupri leak while enqueue/dequeue child RT entities This patch touches the RT group scheduling case. Functions inc_rt_prio_smp() and dec_rt_prio_smp() change (global) rq's priority, while rt_rq passed to them may be not the top-level rt_rq. This is wrong, because changing of priority on a child level does not guarantee that the priority is the highest all over the rq. So, this leak makes RT balancing unusable. The short example: the task having the highest priority among all rq's RT tasks (no one other task has the same priority) are waking on a throttle rt_rq. The rq's cpupri is set to the task's priority equivalent, but real rq->rt.highest_prio.curr is less. The patch below fixes the problem. Signed-off-by: Kirill Tkhai Signed-off-by: Peter Zijlstra CC: Steven Rostedt CC: stable@vger.kernel.org Link: http://lkml.kernel.org/r/49231385567953@web4m.yandex.ru Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7d57275fc39..1c4065575fa 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -901,6 +901,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && prio < prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, prio); } @@ -910,6 +917,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && rt_rq->highest_prio.curr != prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); } -- cgit v1.2.3-70-g09d2 From c97102ba96324da330078ad8619ba4dfe840dbe3 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 18 Dec 2013 17:08:31 -0800 Subject: kexec: migrate to reboot cpu Commit 1b3a5d02ee07 ("reboot: move arch/x86 reboot= handling to generic kernel") moved reboot= handling to generic code. In the process it also removed the code in native_machine_shutdown() which are moving reboot process to reboot_cpu/cpu0. I guess that thought must have been that all reboot paths are calling migrate_to_reboot_cpu(), so we don't need this special handling. But kexec reboot path (kernel_kexec()) is not calling migrate_to_reboot_cpu() so above change broke kexec. Now reboot can happen on non-boot cpu and when INIT is sent in second kerneo to bring up BP, it brings down the machine. So start calling migrate_to_reboot_cpu() in kexec reboot path to avoid this problem. Bisected by WANG Chao. Reported-by: Matthew Whitehead Reported-by: Dave Young Signed-off-by: Vivek Goyal Tested-by: Baoquan He Tested-by: WANG Chao Acked-by: H. Peter Anvin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reboot.h | 1 + kernel/kexec.c | 1 + kernel/reboot.c | 2 +- 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 8e00f9f6f96..9e7db9e73cc 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -43,6 +43,7 @@ extern int unregister_reboot_notifier(struct notifier_block *); * Architecture-specific implementations of sys_reboot commands. */ +extern void migrate_to_reboot_cpu(void); extern void machine_restart(char *cmd); extern void machine_halt(void); extern void machine_power_off(void); diff --git a/kernel/kexec.c b/kernel/kexec.c index d0d8fca5406..9c970167e40 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1680,6 +1680,7 @@ int kernel_kexec(void) { kexec_in_progress = true; kernel_restart_prepare(NULL); + migrate_to_reboot_cpu(); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); } diff --git a/kernel/reboot.c b/kernel/reboot.c index f813b347464..662c83fc16b 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_reboot_notifier); -static void migrate_to_reboot_cpu(void) +void migrate_to_reboot_cpu(void) { /* The boot cpu is always logical cpu 0 */ int cpu = reboot_cpu; -- cgit v1.2.3-70-g09d2 From 3c67f474558748b604e247d92b55dfe89654c81d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 18 Dec 2013 17:08:40 -0800 Subject: sched: numa: skip inaccessible VMAs Inaccessible VMA should not be trapping NUMA hint faults. Skip them. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Alex Thorlton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/fair.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9030da7bcb1..c7395d97e4c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1738,6 +1738,13 @@ void task_numa_work(struct callback_head *work) (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) continue; + /* + * Skip inaccessible VMAs to avoid any confusion between + * PROT_NONE and NUMA hinting ptes + */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) + continue; + do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); -- cgit v1.2.3-70-g09d2 From 20841405940e7be0617612d521e206e4b6b325db Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 18 Dec 2013 17:08:44 -0800 Subject: mm: fix TLB flush race between migration, and change_protection_range There are a few subtle races, between change_protection_range (used by mprotect and change_prot_numa) on one side, and NUMA page migration and compaction on the other side. The basic race is that there is a time window between when the PTE gets made non-present (PROT_NONE or NUMA), and the TLB is flushed. During that time, a CPU may continue writing to the page. This is fine most of the time, however compaction or the NUMA migration code may come in, and migrate the page away. When that happens, the CPU may continue writing, through the cached translation, to what is no longer the current memory location of the process. This only affects x86, which has a somewhat optimistic pte_accessible. All other architectures appear to be safe, and will either always flush, or flush whenever there is a valid mapping, even with no permissions (SPARC). The basic race looks like this: CPU A CPU B CPU C load TLB entry make entry PTE/PMD_NUMA fault on entry read/write old page start migrating page change PTE/PMD to new page read/write old page [*] flush TLB reload TLB from new entry read/write new page lose data [*] the old page may belong to a new user at this point! The obvious fix is to flush remote TLB entries, by making sure that pte_accessible aware of the fact that PROT_NONE and PROT_NUMA memory may still be accessible if there is a TLB flush pending for the mm. This should fix both NUMA migration and compaction. [mgorman@suse.de: fix build] Signed-off-by: Rik van Riel Signed-off-by: Mel Gorman Cc: Alex Thorlton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/include/asm/pgtable_64.h | 4 ++-- arch/x86/include/asm/pgtable.h | 11 ++++++++-- include/asm-generic/pgtable.h | 2 +- include/linux/mm_types.h | 44 +++++++++++++++++++++++++++++++++++++ kernel/fork.c | 1 + mm/huge_memory.c | 7 ++++++ mm/mprotect.c | 2 ++ mm/pgtable-generic.c | 5 +++-- 8 files changed, 69 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 8358dc14495..0f9e94537ee 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte) } #define pte_accessible pte_accessible -static inline unsigned long pte_accessible(pte_t a) +static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) { return pte_val(a) & _PAGE_VALID; } @@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U * and SUN4V pte layout, so this inline test is fine. */ - if (likely(mm != &init_mm) && pte_accessible(orig)) + if (likely(mm != &init_mm) && pte_accessible(mm, orig)) tlb_batch_add(mm, addr, ptep, orig, fullmm); } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 3d199945870..bbc8b12fa44 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -452,9 +452,16 @@ static inline int pte_present(pte_t a) } #define pte_accessible pte_accessible -static inline int pte_accessible(pte_t a) +static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { - return pte_flags(a) & _PAGE_PRESENT; + if (pte_flags(a) & _PAGE_PRESENT) + return true; + + if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) && + mm_tlb_flush_pending(mm)) + return true; + + return false; } static inline int pte_hidden(pte_t pte) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f330d28e4d0..b12079afbd5 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -217,7 +217,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) #endif #ifndef pte_accessible -# define pte_accessible(pte) ((void)(pte),1) +# define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bd299418a93..e5c49c30460 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -442,6 +442,14 @@ struct mm_struct { /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; +#endif +#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) + /* + * An operation with batched TLB flushing is going on. Anything that + * can move process memory needs to flush the TLB when moving a + * PROT_NONE or PROT_NUMA mapped page. + */ + bool tlb_flush_pending; #endif struct uprobes_state uprobes_state; }; @@ -459,4 +467,40 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return mm->cpu_vm_mask_var; } +#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) +/* + * Memory barriers to keep this state in sync are graciously provided by + * the page table locks, outside of which no page table modifications happen. + * The barriers below prevent the compiler from re-ordering the instructions + * around the memory barriers that are already present in the code. + */ +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + barrier(); + return mm->tlb_flush_pending; +} +static inline void set_tlb_flush_pending(struct mm_struct *mm) +{ + mm->tlb_flush_pending = true; + barrier(); +} +/* Clearing is done after a TLB flush, which also provides a barrier. */ +static inline void clear_tlb_flush_pending(struct mm_struct *mm) +{ + barrier(); + mm->tlb_flush_pending = false; +} +#else +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + return false; +} +static inline void set_tlb_flush_pending(struct mm_struct *mm) +{ +} +static inline void clear_tlb_flush_pending(struct mm_struct *mm) +{ +} +#endif + #endif /* _LINUX_MM_TYPES_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 728d5be9548..5721f0e3f2d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) spin_lock_init(&mm->page_table_lock); mm_init_aio(mm); mm_init_owner(mm, p); + clear_tlb_flush_pending(mm); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7de1bf85f68..3d2783e1059 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1376,6 +1376,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, goto clear_pmdnuma; } + /* + * The page_table_lock above provides a memory barrier + * with change_protection_range. + */ + if (mm_tlb_flush_pending(mm)) + flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE); + /* * Migrate the THP to the requested node, returns with page unlocked * and pmd_numa cleared. diff --git a/mm/mprotect.c b/mm/mprotect.c index f8421722acb..bb53a6591ae 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -188,6 +188,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); + set_tlb_flush_pending(mm); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) @@ -199,6 +200,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, /* Only flush the TLB if we actually modified any entries: */ if (pages) flush_tlb_range(vma, start, end); + clear_tlb_flush_pending(mm); return pages; } diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index e84cad27a80..a8b91992593 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -110,9 +110,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + struct mm_struct *mm = (vma)->vm_mm; pte_t pte; - pte = ptep_get_and_clear((vma)->vm_mm, address, ptep); - if (pte_accessible(pte)) + pte = ptep_get_and_clear(mm, address, ptep); + if (pte_accessible(mm, pte)) flush_tlb_page(vma, address); return pte; } -- cgit v1.2.3-70-g09d2 From 597d795a2a786d22dd872332428e2b9439ede639 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 20 Dec 2013 13:35:58 +0200 Subject: mm: do not allocate page->ptl dynamically, if spinlock_t fits to long In struct page we have enough space to fit long-size page->ptl there, but we use dynamically-allocated page->ptl if size(spinlock_t) is larger than sizeof(int). It hurts 64-bit architectures with CONFIG_GENERIC_LOCKBREAK, where sizeof(spinlock_t) == 8, but it easily fits into struct page. Signed-off-by: Kirill A. Shutemov Acked-by: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 2 +- include/linux/mm.h | 6 +++--- include/linux/mm_types.h | 3 ++- kernel/bounds.c | 2 +- mm/memory.c | 2 +- 5 files changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c8929c3832d..4bfde0e99ed 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -19,7 +19,7 @@ #define USE_CMPXCHG_LOCKREF \ (IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \ - IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS) + IS_ENABLED(CONFIG_SMP) && SPINLOCK_SIZE <= 4) struct lockref { union { diff --git a/include/linux/mm.h b/include/linux/mm.h index 1cedd000cf2..35527173cf5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1317,7 +1317,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ #if USE_SPLIT_PTE_PTLOCKS -#if BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); @@ -1325,7 +1325,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } -#else /* BLOATED_SPINLOCKS */ +#else /* ALLOC_SPLIT_PTLOCKS */ static inline bool ptlock_alloc(struct page *page) { return true; @@ -1339,7 +1339,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } -#endif /* BLOATED_SPINLOCKS */ +#endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ad0616f2fe2..290901a8c1d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -26,6 +26,7 @@ struct address_space; #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) +#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* * Each physical page in the system has a struct page associated with @@ -155,7 +156,7 @@ struct page { * system if PG_buddy is set. */ #if USE_SPLIT_PTE_PTLOCKS -#if BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; diff --git a/kernel/bounds.c b/kernel/bounds.c index 5253204afdc..9fd4246b04b 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -22,6 +22,6 @@ void foo(void) #ifdef CONFIG_SMP DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); #endif - DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int)); + DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); /* End of constants */ } diff --git a/mm/memory.c b/mm/memory.c index 5d9025f3b3e..b6e211b779d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4271,7 +4271,7 @@ void copy_user_huge_page(struct page *dst, struct page *src, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS bool ptlock_alloc(struct page *page) { spinlock_t *ptl; -- cgit v1.2.3-70-g09d2