[GIT pull] perf/urgent for 5.14-rc5

[GIT pull] perf/urgent for 5.14-rc5

[Thomas Gleixner]

Linus,

please pull the latest perf/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-08-08

up to:  acade6379930: perf/x86/intel: Apply mid ACK for small core


A set of perf fixes:

 - Correct the permission checks for perf event which send SIGTRAP to a
   different process and clean up that code to be more readable.

 - Prevent an out of bound MSR access in the x86 perf code which happened
   due to an incomplete limiting to the actually available hardware
   counters.

 - Prevent access to the AMD64_EVENTSEL_HOSTONLY bit when running inside a
   guest.

 - Handle small core counter re-enabling correctly by issuing an ACK right
   before reenabling it to prevent a stale PEBS record being kept around.

Thanks,

	tglx

------------------>
Kan Liang (1):
      perf/x86/intel: Apply mid ACK for small core

Like Xu (1):
      perf/x86/amd: Don't touch the AMD64_EVENTSEL_HOSTONLY bit inside the guest

Marco Elver (2):
      perf: Fix required permissions if sigtrap is requested
      perf: Refactor permissions check into perf_check_permission()

Peter Zijlstra (1):
      perf/x86: Fix out of bound MSR access


 arch/x86/events/core.c       | 12 +++++++-----
 arch/x86/events/intel/core.c | 23 +++++++++++++++--------
 arch/x86/events/perf_event.h | 18 +++++++++++++++++-
 kernel/events/core.c         | 35 ++++++++++++++++++++++++++++++++---
 4 files changed, 71 insertions(+), 17 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 1eb45139fcc6..3092fbf9dbe4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2489,13 +2489,15 @@ void perf_clear_dirty_counters(void)
 		return;
 
 	for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
-		/* Metrics and fake events don't have corresponding HW counters. */
-		if (is_metric_idx(i) || (i == INTEL_PMC_IDX_FIXED_VLBR))
-			continue;
-		else if (i >= INTEL_PMC_IDX_FIXED)
+		if (i >= INTEL_PMC_IDX_FIXED) {
+			/* Metrics and fake events don't have corresponding HW counters. */
+			if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+				continue;
+
 			wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
-		else
+		} else {
 			wrmsrl(x86_pmu_event_addr(i), 0);
+		}
 	}
 
 	bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fca7a6e2242f..ac6fd2dabf6a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2904,24 +2904,28 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
  */
 static int intel_pmu_handle_irq(struct pt_regs *regs)
 {
-	struct cpu_hw_events *cpuc;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	bool late_ack = hybrid_bit(cpuc->pmu, late_ack);
+	bool mid_ack = hybrid_bit(cpuc->pmu, mid_ack);
 	int loops;
 	u64 status;
 	int handled;
 	int pmu_enabled;
 
-	cpuc = this_cpu_ptr(&cpu_hw_events);
-
 	/*
 	 * Save the PMU state.
 	 * It needs to be restored when leaving the handler.
 	 */
 	pmu_enabled = cpuc->enabled;
 	/*
-	 * No known reason to not always do late ACK,
-	 * but just in case do it opt-in.
+	 * In general, the early ACK is only applied for old platforms.
+	 * For the big core starts from Haswell, the late ACK should be
+	 * applied.
+	 * For the small core after Tremont, we have to do the ACK right
+	 * before re-enabling counters, which is in the middle of the
+	 * NMI handler.
 	 */
-	if (!x86_pmu.late_ack)
+	if (!late_ack && !mid_ack)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	intel_bts_disable_local();
 	cpuc->enabled = 0;
@@ -2958,6 +2962,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 		goto again;
 
 done:
+	if (mid_ack)
+		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
 	cpuc->enabled = pmu_enabled;
 	if (pmu_enabled)
@@ -2969,7 +2975,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	 * have been reset. This avoids spurious NMIs on
 	 * Haswell CPUs.
 	 */
-	if (x86_pmu.late_ack)
+	if (late_ack)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	return handled;
 }
@@ -6129,7 +6135,6 @@ __init int intel_pmu_init(void)
 		static_branch_enable(&perf_is_hybrid);
 		x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS;
 
-		x86_pmu.late_ack = true;
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
@@ -6167,6 +6172,7 @@ __init int intel_pmu_init(void)
 		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
 		pmu->name = "cpu_core";
 		pmu->cpu_type = hybrid_big;
+		pmu->late_ack = true;
 		if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
 			pmu->num_counters = x86_pmu.num_counters + 2;
 			pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
@@ -6192,6 +6198,7 @@ __init int intel_pmu_init(void)
 		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
 		pmu->name = "cpu_atom";
 		pmu->cpu_type = hybrid_small;
+		pmu->mid_ack = true;
 		pmu->num_counters = x86_pmu.num_counters;
 		pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
 		pmu->max_pebs_events = x86_pmu.max_pebs_events;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 2bf1c7ea2758..e3ac05c97b5e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -656,6 +656,10 @@ struct x86_hybrid_pmu {
 	struct event_constraint		*event_constraints;
 	struct event_constraint		*pebs_constraints;
 	struct extra_reg		*extra_regs;
+
+	unsigned int			late_ack	:1,
+					mid_ack		:1,
+					enabled_ack	:1;
 };
 
 static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu)
@@ -686,6 +690,16 @@ extern struct static_key_false perf_is_hybrid;
 	__Fp;						\
 }))
 
+#define hybrid_bit(_pmu, _field)			\
+({							\
+	bool __Fp = x86_pmu._field;			\
+							\
+	if (is_hybrid() && (_pmu))			\
+		__Fp = hybrid_pmu(_pmu)->_field;	\
+							\
+	__Fp;						\
+})
+
 enum hybrid_pmu_type {
 	hybrid_big		= 0x40,
 	hybrid_small		= 0x20,
@@ -755,6 +769,7 @@ struct x86_pmu {
 
 	/* PMI handler bits */
 	unsigned int	late_ack		:1,
+			mid_ack			:1,
 			enabled_ack		:1;
 	/*
 	 * sysfs attrs
@@ -1115,9 +1130,10 @@ void x86_pmu_stop(struct perf_event *event, int flags);
 
 static inline void x86_pmu_disable_event(struct perf_event *event)
 {
+	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
 
 	if (is_counter_pair(hwc))
 		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 464917096e73..1cb1f9b8392e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11917,6 +11917,37 @@ __perf_event_ctx_lock_double(struct perf_event *group_leader,
 	return gctx;
 }
 
+static bool
+perf_check_permission(struct perf_event_attr *attr, struct task_struct *task)
+{
+	unsigned int ptrace_mode = PTRACE_MODE_READ_REALCREDS;
+	bool is_capable = perfmon_capable();
+
+	if (attr->sigtrap) {
+		/*
+		 * perf_event_attr::sigtrap sends signals to the other task.
+		 * Require the current task to also have CAP_KILL.
+		 */
+		rcu_read_lock();
+		is_capable &= ns_capable(__task_cred(task)->user_ns, CAP_KILL);
+		rcu_read_unlock();
+
+		/*
+		 * If the required capabilities aren't available, checks for
+		 * ptrace permissions: upgrade to ATTACH, since sending signals
+		 * can effectively change the target task.
+		 */
+		ptrace_mode = PTRACE_MODE_ATTACH_REALCREDS;
+	}
+
+	/*
+	 * Preserve ptrace permission check for backwards compatibility. The
+	 * ptrace check also includes checks that the current task and other
+	 * task have matching uids, and is therefore not done here explicitly.
+	 */
+	return is_capable || ptrace_may_access(task, ptrace_mode);
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -12163,15 +12194,13 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_file;
 
 		/*
-		 * Preserve ptrace permission check for backwards compatibility.
-		 *
 		 * We must hold exec_update_lock across this and any potential
 		 * perf_install_in_context() call for this new event to
 		 * serialize against exec() altering our credentials (and the
 		 * perf_event_exit_task() that could imply).
 		 */
 		err = -EACCES;
-		if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+		if (!perf_check_permission(&attr, task))
 			goto err_cred;
 	}
 

[GIT pull] sched/urgent for 5.14-rc5

[Thomas Gleixner]

Linus,

please pull the latest sched/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2021-08-08

up to:  f558c2b834ec: sched/rt: Fix double enqueue caused by rt_effective_prio


A single scheduler fix:

 - Prevent a double enqueue caused by rt_effective_prio() being invoked
   twice in __sched_setscheduler().


Thanks,

	tglx

------------------>
Peter Zijlstra (1):
      sched/rt: Fix double enqueue caused by rt_effective_prio


 kernel/sched/core.c | 90 +++++++++++++++++++++--------------------------------
 1 file changed, 35 insertions(+), 55 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d9ff40f4661..20ffcc044134 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1981,12 +1981,18 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-/*
- * __normal_prio - return the priority that is based on the static prio
- */
-static inline int __normal_prio(struct task_struct *p)
+static inline int __normal_prio(int policy, int rt_prio, int nice)
 {
-	return p->static_prio;
+	int prio;
+
+	if (dl_policy(policy))
+		prio = MAX_DL_PRIO - 1;
+	else if (rt_policy(policy))
+		prio = MAX_RT_PRIO - 1 - rt_prio;
+	else
+		prio = NICE_TO_PRIO(nice);
+
+	return prio;
 }
 
 /*
@@ -1998,15 +2004,7 @@ static inline int __normal_prio(struct task_struct *p)
  */
 static inline int normal_prio(struct task_struct *p)
 {
-	int prio;
-
-	if (task_has_dl_policy(p))
-		prio = MAX_DL_PRIO-1;
-	else if (task_has_rt_policy(p))
-		prio = MAX_RT_PRIO-1 - p->rt_priority;
-	else
-		prio = __normal_prio(p);
-	return prio;
+	return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio));
 }
 
 /*
@@ -4099,7 +4097,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		} else if (PRIO_TO_NICE(p->static_prio) < 0)
 			p->static_prio = NICE_TO_PRIO(0);
 
-		p->prio = p->normal_prio = __normal_prio(p);
+		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
 
 		/*
@@ -6341,6 +6339,18 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag
 }
 EXPORT_SYMBOL(default_wake_function);
 
+static void __setscheduler_prio(struct task_struct *p, int prio)
+{
+	if (dl_prio(prio))
+		p->sched_class = &dl_sched_class;
+	else if (rt_prio(prio))
+		p->sched_class = &rt_sched_class;
+	else
+		p->sched_class = &fair_sched_class;
+
+	p->prio = prio;
+}
+
 #ifdef CONFIG_RT_MUTEXES
 
 static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
@@ -6456,22 +6466,19 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		} else {
 			p->dl.pi_se = &p->dl;
 		}
-		p->sched_class = &dl_sched_class;
 	} else if (rt_prio(prio)) {
 		if (dl_prio(oldprio))
 			p->dl.pi_se = &p->dl;
 		if (oldprio < prio)
 			queue_flag |= ENQUEUE_HEAD;
-		p->sched_class = &rt_sched_class;
 	} else {
 		if (dl_prio(oldprio))
 			p->dl.pi_se = &p->dl;
 		if (rt_prio(oldprio))
 			p->rt.timeout = 0;
-		p->sched_class = &fair_sched_class;
 	}
 
-	p->prio = prio;
+	__setscheduler_prio(p, prio);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -6824,35 +6831,6 @@ static void __setscheduler_params(struct task_struct *p,
 	set_load_weight(p, true);
 }
 
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
-			   const struct sched_attr *attr, bool keep_boost)
-{
-	/*
-	 * If params can't change scheduling class changes aren't allowed
-	 * either.
-	 */
-	if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
-		return;
-
-	__setscheduler_params(p, attr);
-
-	/*
-	 * Keep a potential priority boosting if called from
-	 * sched_setscheduler().
-	 */
-	p->prio = normal_prio(p);
-	if (keep_boost)
-		p->prio = rt_effective_prio(p, p->prio);
-
-	if (dl_prio(p->prio))
-		p->sched_class = &dl_sched_class;
-	else if (rt_prio(p->prio))
-		p->sched_class = &rt_sched_class;
-	else
-		p->sched_class = &fair_sched_class;
-}
-
 /*
  * Check the target process has a UID that matches the current process's:
  */
@@ -6873,10 +6851,8 @@ static int __sched_setscheduler(struct task_struct *p,
 				const struct sched_attr *attr,
 				bool user, bool pi)
 {
-	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
-		      MAX_RT_PRIO - 1 - attr->sched_priority;
-	int retval, oldprio, oldpolicy = -1, queued, running;
-	int new_effective_prio, policy = attr->sched_policy;
+	int oldpolicy = -1, policy = attr->sched_policy;
+	int retval, oldprio, newprio, queued, running;
 	const struct sched_class *prev_class;
 	struct callback_head *head;
 	struct rq_flags rf;
@@ -7074,6 +7050,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	p->sched_reset_on_fork = reset_on_fork;
 	oldprio = p->prio;
 
+	newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice);
 	if (pi) {
 		/*
 		 * Take priority boosted tasks into account. If the new
@@ -7082,8 +7059,8 @@ static int __sched_setscheduler(struct task_struct *p,
 		 * the runqueue. This will be done when the task deboost
 		 * itself.
 		 */
-		new_effective_prio = rt_effective_prio(p, newprio);
-		if (new_effective_prio == oldprio)
+		newprio = rt_effective_prio(p, newprio);
+		if (newprio == oldprio)
 			queue_flags &= ~DEQUEUE_MOVE;
 	}
 
@@ -7096,7 +7073,10 @@ static int __sched_setscheduler(struct task_struct *p,
 
 	prev_class = p->sched_class;
 
-	__setscheduler(rq, p, attr, pi);
+	if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
+		__setscheduler_params(p, attr);
+		__setscheduler_prio(p, newprio);
+	}
 	__setscheduler_uclamp(p, attr);
 
 	if (queued) {

[GIT pull] timers/urgent for 5.14-rc5

[Thomas Gleixner]

Linus,

please pull the latest timers/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2021-08-08

up to:  bb7262b29547: timers: Move clearing of base::timer_running under base:: Lock


A single timer fix:

 - Prevent a memory ordering issue in the timer expiry code which makes it
   possible to observe falsely that the callback has been executed already
   while that's not the case, which violates the guarantee of del_timer_sync().


Thanks,

	tglx

------------------>
Thomas Gleixner (1):
      timers: Move clearing of base::timer_running under base:: Lock


 kernel/time/timer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 9eb11c2209e5..e3d2c23c413d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1265,8 +1265,10 @@ static inline void timer_base_unlock_expiry(struct timer_base *base)
 static void timer_sync_wait_running(struct timer_base *base)
 {
 	if (atomic_read(&base->timer_waiters)) {
+		raw_spin_unlock_irq(&base->lock);
 		spin_unlock(&base->expiry_lock);
 		spin_lock(&base->expiry_lock);
+		raw_spin_lock_irq(&base->lock);
 	}
 }
 
@@ -1457,14 +1459,14 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 		if (timer->flags & TIMER_IRQSAFE) {
 			raw_spin_unlock(&base->lock);
 			call_timer_fn(timer, fn, baseclk);
-			base->running_timer = NULL;
 			raw_spin_lock(&base->lock);
+			base->running_timer = NULL;
 		} else {
 			raw_spin_unlock_irq(&base->lock);
 			call_timer_fn(timer, fn, baseclk);
+			raw_spin_lock_irq(&base->lock);
 			base->running_timer = NULL;
 			timer_sync_wait_running(base);
-			raw_spin_lock_irq(&base->lock);
 		}
 	}
 }

Re: [GIT pull] perf/urgent for 5.14-rc5

[pr-tracker-bot]

The pull request you sent on Sun, 08 Aug 2021 11:33:54 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-08-08

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/74eedeba459d878484634cbfd5d1c2fbaf7178b9

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Re: [GIT pull] sched/urgent for 5.14-rc5

[pr-tracker-bot]

The pull request you sent on Sun, 08 Aug 2021 11:33:56 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2021-08-08

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/713f0f37e8128e8a0190a98f5a4be71fb32a671a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Re: [GIT pull] timers/urgent for 5.14-rc5

[pr-tracker-bot]

The pull request you sent on Sun, 08 Aug 2021 11:33:57 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2021-08-08

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/cceb634774efca60f8cc57041234f00faf97f22d

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html