April 2019 - Linux-stable-mirror

FAILED: patch "[PATCH] sched/fair: Limit sched_cfs_period_timer() loop to avoid hard" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2e8e19226398db8265a8e675fcc0118b9e80c9e8 Mon Sep 17 00:00:00 2001 From: Phil Auld <pauld(a)redhat.com> Date: Tue, 19 Mar 2019 09:00:05 -0400 Subject: [PATCH] sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup With extremely short cfs_period_us setting on a parent task group with a large number of children the for loop in sched_cfs_period_timer() can run until the watchdog fires. There is no guarantee that the call to hrtimer_forward_now() will ever return 0. The large number of children can make do_sched_cfs_period_timer() take longer than the period. NMI watchdog: Watchdog detected hard LOCKUP on cpu 24 RIP: 0010:tg_nop+0x0/0x10 <IRQ> walk_tg_tree_from+0x29/0xb0 unthrottle_cfs_rq+0xe0/0x1a0 distribute_cfs_runtime+0xd3/0xf0 sched_cfs_period_timer+0xcb/0x160 ? sched_cfs_slack_timer+0xd0/0xd0 __hrtimer_run_queues+0xfb/0x270 hrtimer_interrupt+0x122/0x270 smp_apic_timer_interrupt+0x6a/0x140 apic_timer_interrupt+0xf/0x20 </IRQ> To prevent this we add protection to the loop that detects when the loop has run too many times and scales the period and quota up, proportionally, so that the timer can complete before then next period expires. This preserves the relative runtime quota while preventing the hard lockup. A warning is issued reporting this state and the new values. Signed-off-by: Phil Auld <pauld(a)redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: <stable(a)vger.kernel.org> Cc: Anton Blanchard <anton(a)ozlabs.org> Cc: Ben Segall <bsegall(a)google.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lkml.kernel.org/r/20190319130005.25492-1-pauld@redhat.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 40bd1e27b1b7..a4d9e14bf138 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4885,6 +4885,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -4892,6 +4894,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) unsigned long flags; int overrun; int idle = 0; + int count = 0; raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { @@ -4899,6 +4902,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle)

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] sched/fair: Limit sched_cfs_period_timer() loop to avoid hard" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2e8e19226398db8265a8e675fcc0118b9e80c9e8 Mon Sep 17 00:00:00 2001 From: Phil Auld <pauld(a)redhat.com> Date: Tue, 19 Mar 2019 09:00:05 -0400 Subject: [PATCH] sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup With extremely short cfs_period_us setting on a parent task group with a large number of children the for loop in sched_cfs_period_timer() can run until the watchdog fires. There is no guarantee that the call to hrtimer_forward_now() will ever return 0. The large number of children can make do_sched_cfs_period_timer() take longer than the period. NMI watchdog: Watchdog detected hard LOCKUP on cpu 24 RIP: 0010:tg_nop+0x0/0x10 <IRQ> walk_tg_tree_from+0x29/0xb0 unthrottle_cfs_rq+0xe0/0x1a0 distribute_cfs_runtime+0xd3/0xf0 sched_cfs_period_timer+0xcb/0x160 ? sched_cfs_slack_timer+0xd0/0xd0 __hrtimer_run_queues+0xfb/0x270 hrtimer_interrupt+0x122/0x270 smp_apic_timer_interrupt+0x6a/0x140 apic_timer_interrupt+0xf/0x20 </IRQ> To prevent this we add protection to the loop that detects when the loop has run too many times and scales the period and quota up, proportionally, so that the timer can complete before then next period expires. This preserves the relative runtime quota while preventing the hard lockup. A warning is issued reporting this state and the new values. Signed-off-by: Phil Auld <pauld(a)redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: <stable(a)vger.kernel.org> Cc: Anton Blanchard <anton(a)ozlabs.org> Cc: Ben Segall <bsegall(a)google.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lkml.kernel.org/r/20190319130005.25492-1-pauld@redhat.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 40bd1e27b1b7..a4d9e14bf138 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4885,6 +4885,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -4892,6 +4894,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) unsigned long flags; int overrun; int idle = 0; + int count = 0; raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { @@ -4899,6 +4902,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle)

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] x86/speculation: Prevent deadlock on ssb_state::lock" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2f5fb19341883bb6e37da351bc3700489d8506a7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Sun, 14 Apr 2019 19:51:06 +0200 Subject: [PATCH] x86/speculation: Prevent deadlock on ssb_state::lock Mikhail reported a lockdep splat related to the AMD specific ssb_state lock: CPU0 CPU1 lock(&st->lock); local_irq_disable(); lock(&(&sighand->siglock)->rlock); lock(&st->lock); <Interrupt> lock(&(&sighand->siglock)->rlock); *** DEADLOCK *** The connection between sighand->siglock and st->lock comes through seccomp, which takes st->lock while holding sighand->siglock. Make sure interrupts are disabled when __speculation_ctrl_update() is invoked via prctl() -> speculation_ctrl_update(). Add a lockdep assert to catch future offenders. Fixes: 1f50ddb4f418 ("x86/speculation: Handle HT correctly on AMD") Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov(a)gmail.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov(a)gmail.com> Cc: Thomas Lendacky <thomas.lendacky(a)amd.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1904141948200.4917@nanos.tec.linu… diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 58ac7be52c7a..957eae13b370 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, u64 msr = x86_spec_ctrl_base; bool updmsr = false; + lockdep_assert_irqs_disabled(); + /* * If TIF_SSBD is different, select the proper mitigation * method. Note that if SSBD mitigation is disabled or permanentely @@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) void speculation_ctrl_update(unsigned long tif) { + unsigned long flags; + /* Forced update. Make sure all relevant TIF flags are different */ - preempt_disable(); + local_irq_save(flags); __speculation_ctrl_update(~tif, tif); - preempt_enable(); + local_irq_restore(flags); } /* Called from seccomp/prctl update */

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] x86/speculation: Prevent deadlock on ssb_state::lock" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2f5fb19341883bb6e37da351bc3700489d8506a7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Sun, 14 Apr 2019 19:51:06 +0200 Subject: [PATCH] x86/speculation: Prevent deadlock on ssb_state::lock Mikhail reported a lockdep splat related to the AMD specific ssb_state lock: CPU0 CPU1 lock(&st->lock); local_irq_disable(); lock(&(&sighand->siglock)->rlock); lock(&st->lock); <Interrupt> lock(&(&sighand->siglock)->rlock); *** DEADLOCK *** The connection between sighand->siglock and st->lock comes through seccomp, which takes st->lock while holding sighand->siglock. Make sure interrupts are disabled when __speculation_ctrl_update() is invoked via prctl() -> speculation_ctrl_update(). Add a lockdep assert to catch future offenders. Fixes: 1f50ddb4f418 ("x86/speculation: Handle HT correctly on AMD") Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov(a)gmail.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov(a)gmail.com> Cc: Thomas Lendacky <thomas.lendacky(a)amd.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1904141948200.4917@nanos.tec.linu… diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 58ac7be52c7a..957eae13b370 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, u64 msr = x86_spec_ctrl_base; bool updmsr = false; + lockdep_assert_irqs_disabled(); + /* * If TIF_SSBD is different, select the proper mitigation * method. Note that if SSBD mitigation is disabled or permanentely @@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) void speculation_ctrl_update(unsigned long tif) { + unsigned long flags; + /* Forced update. Make sure all relevant TIF flags are different */ - preempt_disable(); + local_irq_save(flags); __speculation_ctrl_update(~tif, tif); - preempt_enable(); + local_irq_restore(flags); } /* Called from seccomp/prctl update */

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] x86/kprobes: Avoid kretprobe recursion bug" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From b191fa96ea6dc00d331dcc28c1f7db5e075693a0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu <mhiramat(a)kernel.org> Date: Sun, 24 Feb 2019 01:50:49 +0900 Subject: [PATCH] x86/kprobes: Avoid kretprobe recursion bug Avoid kretprobe recursion loop bg by setting a dummy kprobes to current_kprobe per-CPU variable. This bug has been introduced with the asm-coded trampoline code, since previously it used another kprobe for hooking the function return placeholder (which only has a nop) and trampoline handler was called from that kprobe. This revives the old lost kprobe again. With this fix, we don't see deadlock anymore. And you can see that all inner-called kretprobe are skipped. event_1 235 0 event_2 19375 19612 The 1st column is recorded count and the 2nd is missed count. Above shows (event_1 rec) + (event_2 rec) ~= (event_2 missed) (some difference are here because the counter is racy) Reported-by: Andrea Righi <righi.andrea(a)gmail.com> Tested-by: Andrea Righi <righi.andrea(a)gmail.com> Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org> Acked-by: Steven Rostedt <rostedt(a)goodmis.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Fixes: c9becf58d935 ("[PATCH] kretprobe: kretprobe-booster") Link: http://lkml.kernel.org/r/155094064889.6137.972160690963039.stgit@devbox Signed-off-by: Ingo Molnar <mingo(a)kernel.org> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 18fbe9be2d68..fed46ddb1eef 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -749,11 +749,16 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -763,6 +768,17 @@ static __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ @@ -838,10 +854,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -857,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri);

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] x86/kprobes: Avoid kretprobe recursion bug" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From b191fa96ea6dc00d331dcc28c1f7db5e075693a0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu <mhiramat(a)kernel.org> Date: Sun, 24 Feb 2019 01:50:49 +0900 Subject: [PATCH] x86/kprobes: Avoid kretprobe recursion bug Avoid kretprobe recursion loop bg by setting a dummy kprobes to current_kprobe per-CPU variable. This bug has been introduced with the asm-coded trampoline code, since previously it used another kprobe for hooking the function return placeholder (which only has a nop) and trampoline handler was called from that kprobe. This revives the old lost kprobe again. With this fix, we don't see deadlock anymore. And you can see that all inner-called kretprobe are skipped. event_1 235 0 event_2 19375 19612 The 1st column is recorded count and the 2nd is missed count. Above shows (event_1 rec) + (event_2 rec) ~= (event_2 missed) (some difference are here because the counter is racy) Reported-by: Andrea Righi <righi.andrea(a)gmail.com> Tested-by: Andrea Righi <righi.andrea(a)gmail.com> Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org> Acked-by: Steven Rostedt <rostedt(a)goodmis.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Fixes: c9becf58d935 ("[PATCH] kretprobe: kretprobe-booster") Link: http://lkml.kernel.org/r/155094064889.6137.972160690963039.stgit@devbox Signed-off-by: Ingo Molnar <mingo(a)kernel.org> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 18fbe9be2d68..fed46ddb1eef 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -749,11 +749,16 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -763,6 +768,17 @@ static __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ @@ -838,10 +854,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -857,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri);

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] x86/kprobes: Avoid kretprobe recursion bug" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From b191fa96ea6dc00d331dcc28c1f7db5e075693a0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu <mhiramat(a)kernel.org> Date: Sun, 24 Feb 2019 01:50:49 +0900 Subject: [PATCH] x86/kprobes: Avoid kretprobe recursion bug Avoid kretprobe recursion loop bg by setting a dummy kprobes to current_kprobe per-CPU variable. This bug has been introduced with the asm-coded trampoline code, since previously it used another kprobe for hooking the function return placeholder (which only has a nop) and trampoline handler was called from that kprobe. This revives the old lost kprobe again. With this fix, we don't see deadlock anymore. And you can see that all inner-called kretprobe are skipped. event_1 235 0 event_2 19375 19612 The 1st column is recorded count and the 2nd is missed count. Above shows (event_1 rec) + (event_2 rec) ~= (event_2 missed) (some difference are here because the counter is racy) Reported-by: Andrea Righi <righi.andrea(a)gmail.com> Tested-by: Andrea Righi <righi.andrea(a)gmail.com> Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org> Acked-by: Steven Rostedt <rostedt(a)goodmis.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Fixes: c9becf58d935 ("[PATCH] kretprobe: kretprobe-booster") Link: http://lkml.kernel.org/r/155094064889.6137.972160690963039.stgit@devbox Signed-off-by: Ingo Molnar <mingo(a)kernel.org> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 18fbe9be2d68..fed46ddb1eef 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -749,11 +749,16 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -763,6 +768,17 @@ static __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ @@ -838,10 +854,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -857,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri);

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] x86/kprobes: Avoid kretprobe recursion bug" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From b191fa96ea6dc00d331dcc28c1f7db5e075693a0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu <mhiramat(a)kernel.org> Date: Sun, 24 Feb 2019 01:50:49 +0900 Subject: [PATCH] x86/kprobes: Avoid kretprobe recursion bug Avoid kretprobe recursion loop bg by setting a dummy kprobes to current_kprobe per-CPU variable. This bug has been introduced with the asm-coded trampoline code, since previously it used another kprobe for hooking the function return placeholder (which only has a nop) and trampoline handler was called from that kprobe. This revives the old lost kprobe again. With this fix, we don't see deadlock anymore. And you can see that all inner-called kretprobe are skipped. event_1 235 0 event_2 19375 19612 The 1st column is recorded count and the 2nd is missed count. Above shows (event_1 rec) + (event_2 rec) ~= (event_2 missed) (some difference are here because the counter is racy) Reported-by: Andrea Righi <righi.andrea(a)gmail.com> Tested-by: Andrea Righi <righi.andrea(a)gmail.com> Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org> Acked-by: Steven Rostedt <rostedt(a)goodmis.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Fixes: c9becf58d935 ("[PATCH] kretprobe: kretprobe-booster") Link: http://lkml.kernel.org/r/155094064889.6137.972160690963039.stgit@devbox Signed-off-by: Ingo Molnar <mingo(a)kernel.org> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 18fbe9be2d68..fed46ddb1eef 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -749,11 +749,16 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -763,6 +768,17 @@ static __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ @@ -838,10 +854,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -857,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri);

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] kvm: mmu: Fix overflow on kvm mmu page limit calculation" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From bc8a3d8925a8fa09fa550e0da115d95851ce33c6 Mon Sep 17 00:00:00 2001 From: Ben Gardon <bgardon(a)google.com> Date: Mon, 8 Apr 2019 11:07:30 -0700 Subject: [PATCH] kvm: mmu: Fix overflow on kvm mmu page limit calculation KVM bases its memory usage limits on the total number of guest pages across all memslots. However, those limits, and the calculations to produce them, use 32 bit unsigned integers. This can result in overflow if a VM has more guest pages that can be represented by a u32. As a result of this overflow, KVM can use a low limit on the number of MMU pages it will allocate. This makes KVM unable to map all of guest memory at once, prompting spurious faults. Tested: Ran all kvm-unit-tests on an Intel Haswell machine. This patch introduced no new failures. Signed-off-by: Ben Gardon <bgardon(a)google.com> Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 159b5988292f..9b7b731a0032 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) } #define KVM_PERMILLE_MMU_PAGES 20 -#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 @@ -844,9 +844,9 @@ enum kvm_irqchip_mode { }; struct kvm_arch { - unsigned int n_used_mmu_pages; - unsigned int n_requested_mmu_pages; - unsigned int n_max_mmu_pages; + unsigned long n_used_mmu_pages; + unsigned long n_requested_mmu_pages; + unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* @@ -1256,8 +1256,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); bool pdptrs_changed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 85f753728953..e10962dfc203 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt) * aggregate version in order to make the slab shrinker * faster */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr) { kvm->arch.n_used_mmu_pages += nr; percpu_counter_add(&kvm_total_used_mmu_pages, nr); @@ -2763,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock */ -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { LIST_HEAD(invalid_list); @@ -6031,10 +6031,10 @@ int kvm_mmu_module_init(void) /* * Calculate mmu pages needed for kvm. */ -unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) { - unsigned int nr_mmu_pages; - unsigned int nr_pages = 0; + unsigned long nr_mmu_pages; + unsigned long nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i; @@ -6047,8 +6047,7 @@ unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bbdc60f2fae8..54c2a377795b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); -static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) +static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm) { if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages) return kvm->arch.n_max_mmu_pages - diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 099b851dabaf..455f156f56ed 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4270,7 +4270,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, - u32 kvm_nr_mmu_pages) + unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; @@ -4284,7 +4284,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) { return kvm->arch.n_max_mmu_pages; }

5 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] kvm: mmu: Fix overflow on kvm mmu page limit calculation" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From bc8a3d8925a8fa09fa550e0da115d95851ce33c6 Mon Sep 17 00:00:00 2001 From: Ben Gardon <bgardon(a)google.com> Date: Mon, 8 Apr 2019 11:07:30 -0700 Subject: [PATCH] kvm: mmu: Fix overflow on kvm mmu page limit calculation KVM bases its memory usage limits on the total number of guest pages across all memslots. However, those limits, and the calculations to produce them, use 32 bit unsigned integers. This can result in overflow if a VM has more guest pages that can be represented by a u32. As a result of this overflow, KVM can use a low limit on the number of MMU pages it will allocate. This makes KVM unable to map all of guest memory at once, prompting spurious faults. Tested: Ran all kvm-unit-tests on an Intel Haswell machine. This patch introduced no new failures. Signed-off-by: Ben Gardon <bgardon(a)google.com> Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 159b5988292f..9b7b731a0032 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) } #define KVM_PERMILLE_MMU_PAGES 20 -#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 @@ -844,9 +844,9 @@ enum kvm_irqchip_mode { }; struct kvm_arch { - unsigned int n_used_mmu_pages; - unsigned int n_requested_mmu_pages; - unsigned int n_max_mmu_pages; + unsigned long n_used_mmu_pages; + unsigned long n_requested_mmu_pages; + unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* @@ -1256,8 +1256,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); bool pdptrs_changed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 85f753728953..e10962dfc203 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt) * aggregate version in order to make the slab shrinker * faster */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr) { kvm->arch.n_used_mmu_pages += nr; percpu_counter_add(&kvm_total_used_mmu_pages, nr); @@ -2763,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock */ -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { LIST_HEAD(invalid_list); @@ -6031,10 +6031,10 @@ int kvm_mmu_module_init(void) /* * Calculate mmu pages needed for kvm. */ -unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) { - unsigned int nr_mmu_pages; - unsigned int nr_pages = 0; + unsigned long nr_mmu_pages; + unsigned long nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i; @@ -6047,8 +6047,7 @@ unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bbdc60f2fae8..54c2a377795b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); -static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) +static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm) { if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages) return kvm->arch.n_max_mmu_pages - diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 099b851dabaf..455f156f56ed 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4270,7 +4270,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, - u32 kvm_nr_mmu_pages) + unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; @@ -4284,7 +4284,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) { return kvm->arch.n_max_mmu_pages; }

5 years, 8 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2019