[GIT PULL] RAS fix

[GIT PULL] RAS fix

[Ingo Molnar]

Linus,

Please pull the latest ras-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git ras-urgent-for-linus

   # HEAD: 978370956d2046b19313659ce65ed12d5b996626 x86/mce/therm_throt: Do not access uninitialized therm_work

Fix a thermal throttling race that can result in easy to trigger boot 
crashes on certain Ice Lake platforms.

 Thanks,

	Ingo

------------------>
Chuansheng Liu (1):
      x86/mce/therm_throt: Do not access uninitialized therm_work


 arch/x86/kernel/cpu/mce/therm_throt.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index b38010b541d6..6c3e1c92f183 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -467,6 +467,7 @@ static int thermal_throttle_online(unsigned int cpu)
 {
 	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
+	u32 l;
 
 	state->package_throttle.level = PACKAGE_LEVEL;
 	state->core_throttle.level = CORE_LEVEL;
@@ -474,6 +475,10 @@ static int thermal_throttle_online(unsigned int cpu)
 	INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
 	INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
 
+	/* Unmask the thermal vector after the above workqueues are initialized. */
+	l = apic_read(APIC_LVTTHMR);
+	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+
 	return thermal_throttle_add_dev(dev, cpu);
 }
 
@@ -722,10 +727,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 	wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
 
-	/* Unmask the thermal vector: */
-	l = apic_read(APIC_LVTTHMR);
-	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
-
 	pr_info_once("CPU0: Thermal monitoring enabled (%s)\n",
 		      tm2 ? "TM2" : "TM1");
 

Re: [GIT PULL] RAS fix

[pr-tracker-bot]

The pull request you sent on Sat, 18 Jan 2020 19:29:49 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git ras-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/a186c112c7a44fefdf9e4208f2b38c31b53f3c1d

Thank you!

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

[GIT PULL] RAS fix

[Ingo Molnar]

Linus,

Please pull the latest ras-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git ras-urgent-for-linus

   # HEAD: 7298f08ea8870d44d36c7d6cd07dd0303faef6c2 x86/mcelog: Get rid of RCU remnants

Fix an RCU warning that triggers when /dev/mcelog is used.

 Thanks,

	Ingo

------------------>
Borislav Petkov (1):
      x86/mcelog: Get rid of RCU remnants


 arch/x86/kernel/cpu/mcheck/dev-mcelog.c | 121 +++++++-------------------------
 1 file changed, 27 insertions(+), 94 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 10cec43aac38..7f85b76f43bc 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -24,14 +24,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
 static char mce_helper[128];
 static char *mce_helper_argv[2] = { mce_helper, NULL };
 
-#define mce_log_get_idx_check(p) \
-({ \
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
-			 !lockdep_is_held(&mce_chrdev_read_mutex), \
-			 "suspicious mce_log_get_idx_check() usage"); \
-	smp_load_acquire(&(p)); \
-})
-
 /*
  * Lockless MCE logging infrastructure.
  * This avoids deadlocks on printk locks without having to break locks. Also
@@ -53,43 +45,32 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
 	struct mce *mce = (struct mce *)data;
-	unsigned int next, entry;
-
-	wmb();
-	for (;;) {
-		entry = mce_log_get_idx_check(mcelog.next);
-		for (;;) {
-
-			/*
-			 * When the buffer fills up discard new entries.
-			 * Assume that the earlier errors are the more
-			 * interesting ones:
-			 */
-			if (entry >= MCE_LOG_LEN) {
-				set_bit(MCE_OVERFLOW,
-					(unsigned long *)&mcelog.flags);
-				return NOTIFY_OK;
-			}
-			/* Old left over entry. Skip: */
-			if (mcelog.entry[entry].finished) {
-				entry++;
-				continue;
-			}
-			break;
-		}
-		smp_rmb();
-		next = entry + 1;
-		if (cmpxchg(&mcelog.next, entry, next) == entry)
-			break;
+	unsigned int entry;
+
+	mutex_lock(&mce_chrdev_read_mutex);
+
+	entry = mcelog.next;
+
+	/*
+	 * When the buffer fills up discard new entries. Assume that the
+	 * earlier errors are the more interesting ones:
+	 */
+	if (entry >= MCE_LOG_LEN) {
+		set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags);
+		goto unlock;
 	}
+
+	mcelog.next = entry + 1;
+
 	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
-	wmb();
 	mcelog.entry[entry].finished = 1;
-	wmb();
 
 	/* wake processes polling /dev/mcelog */
 	wake_up_interruptible(&mce_chrdev_wait);
 
+unlock:
+	mutex_unlock(&mce_chrdev_read_mutex);
+
 	return NOTIFY_OK;
 }
 
@@ -177,13 +158,6 @@ static int mce_chrdev_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static void collect_tscs(void *data)
-{
-	unsigned long *cpu_tsc = (unsigned long *)data;
-
-	cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
 static int mce_apei_read_done;
 
 /* Collect MCE record of previous boot in persistent storage via APEI ERST. */
@@ -231,14 +205,9 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 				size_t usize, loff_t *off)
 {
 	char __user *buf = ubuf;
-	unsigned long *cpu_tsc;
-	unsigned prev, next;
+	unsigned next;
 	int i, err;
 
-	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
-	if (!cpu_tsc)
-		return -ENOMEM;
-
 	mutex_lock(&mce_chrdev_read_mutex);
 
 	if (!mce_apei_read_done) {
@@ -247,65 +216,29 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 			goto out;
 	}
 
-	next = mce_log_get_idx_check(mcelog.next);
-
 	/* Only supports full reads right now */
 	err = -EINVAL;
 	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
 		goto out;
 
+	next = mcelog.next;
 	err = 0;
-	prev = 0;
-	do {
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			struct mce *m = &mcelog.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2)) {
-					memset(m, 0, sizeof(*m));
-					goto timeout;
-				}
-				cpu_relax();
-			}
-			smp_rmb();
-			err |= copy_to_user(buf, m, sizeof(*m));
-			buf += sizeof(*m);
-timeout:
-			;
-		}
-
-		memset(mcelog.entry + prev, 0,
-		       (next - prev) * sizeof(struct mce));
-		prev = next;
-		next = cmpxchg(&mcelog.next, prev, 0);
-	} while (next != prev);
-
-	synchronize_sched();
 
-	/*
-	 * Collect entries that were still getting written before the
-	 * synchronize.
-	 */
-	on_each_cpu(collect_tscs, cpu_tsc, 1);
-
-	for (i = next; i < MCE_LOG_LEN; i++) {
+	for (i = 0; i < next; i++) {
 		struct mce *m = &mcelog.entry[i];
 
-		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
-			err |= copy_to_user(buf, m, sizeof(*m));
-			smp_rmb();
-			buf += sizeof(*m);
-			memset(m, 0, sizeof(*m));
-		}
+		err |= copy_to_user(buf, m, sizeof(*m));
+		buf += sizeof(*m);
 	}
 
+	memset(mcelog.entry, 0, next * sizeof(struct mce));
+	mcelog.next = 0;
+
 	if (err)
 		err = -EFAULT;
 
 out:
 	mutex_unlock(&mce_chrdev_read_mutex);
-	kfree(cpu_tsc);
 
 	return err ? err : buf - ubuf;
 }