Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/pti updates from Thomas Gleixner:
 "Another set of melted spectrum updates:

   - Iron out the last late microcode loading issues by actually
     checking whether new microcode is present and preventing the CPU
     synchronization to run into a timeout induced hang.

   - Remove Skylake C2 from the microcode blacklist according to the
     latest Intel documentation

   - Fix the VM86 POPF emulation which traps if VIP is set, but VIF is
     not. Enhance the selftests to catch that kind of issue

   - Annotate indirect calls/jumps for objtool on 32bit. This is not a
     functional issue, but for consistency sake its the right thing to
     do.

   - Fix a jump label build warning observed on SPARC64 which uses 32bit
     storage for the code location which is casted to 64 bit pointer w/o
     extending it to 64bit first.

   - Add two new cpufeature bits. Not really an urgent issue, but
     provides them for both x86 and x86/kvm work. No impact on the
     current kernel"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/microcode: Fix CPU synchronization routine
  x86/microcode: Attempt late loading only when new microcode is present
  x86/speculation: Remove Skylake C2 from Speculation Control microcode blacklist
  jump_label: Fix sparc64 warning
  x86/speculation, objtool: Annotate indirect calls/jumps for objtool on 32-bit kernels
  x86/vm86/32: Fix POPF emulation
  selftests/x86/entry_from_vm86: Add test cases for POPF
  selftests/x86/entry_from_vm86: Exit with 1 if we fail
  x86/cpufeatures: Add Intel PCONFIG cpufeature
  x86/cpufeatures: Add Intel Total Memory Encryption cpufeature

1 files changed, 44 insertions, 32 deletions

diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 70ecbc8099c9..10c4fc2c91f8 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -517,7 +517,29 @@ static int check_online_cpus(void)
 	return -EINVAL;
 }
 
-static atomic_t late_cpus;
+static atomic_t late_cpus_in;
+static atomic_t late_cpus_out;
+
+static int __wait_for_cpus(atomic_t *t, long long timeout)
+{
+	int all_cpus = num_online_cpus();
+
+	atomic_inc(t);
+
+	while (atomic_read(t) < all_cpus) {
+		if (timeout < SPINUNIT) {
+			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+				all_cpus - atomic_read(t));
+			return 1;
+		}
+
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+
+		touch_nmi_watchdog();
+	}
+	return 0;
+}
 
 /*
  * Returns:
@@ -527,30 +549,16 @@ static atomic_t late_cpus;
  */
 static int __reload_late(void *info)
 {
-	unsigned int timeout = NSEC_PER_SEC;
-	int all_cpus = num_online_cpus();
 	int cpu = smp_processor_id();
 	enum ucode_state err;
 	int ret = 0;
 
-	atomic_dec(&late_cpus);
-
 	/*
 	 * Wait for all CPUs to arrive. A load will not be attempted unless all
 	 * CPUs show up.
 	 * */
-	while (atomic_read(&late_cpus)) {
-		if (timeout < SPINUNIT) {
-			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
-				atomic_read(&late_cpus));
-			return -1;
-		}
-
-		ndelay(SPINUNIT);
-		timeout -= SPINUNIT;
-
-		touch_nmi_watchdog();
-	}
+	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
+		return -1;
 
 	spin_lock(&update_lock);
 	apply_microcode_local(&err);
@@ -558,15 +566,22 @@ static int __reload_late(void *info)
 
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
-		ret = -1;
-	} else if (err == UCODE_UPDATED) {
+		return -1;
+	/* siblings return UCODE_OK because their engine got updated already */
+	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
 		ret = 1;
+	} else {
+		return ret;
 	}
 
-	atomic_inc(&late_cpus);
-
-	while (atomic_read(&late_cpus) != all_cpus)
-		cpu_relax();
+	/*
+	 * Increase the wait timeout to a safe value here since we're
+	 * serializing the microcode update and that could take a while on a
+	 * large number of CPUs. And that is fine as the *actual* timeout will
+	 * be determined by the last CPU finished updating and thus cut short.
+	 */
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
+		panic("Timeout during microcode update!\n");
 
 	return ret;
 }
@@ -579,12 +594,11 @@ static int microcode_reload_late(void)
 {
 	int ret;
 
-	atomic_set(&late_cpus, num_online_cpus());
+	atomic_set(&late_cpus_in,  0);
+	atomic_set(&late_cpus_out, 0);
 
 	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
-	if (ret < 0)
-		return ret;
-	else if (ret > 0)
+	if (ret > 0)
 		microcode_check();
 
 	return ret;
@@ -607,7 +621,7 @@ static ssize_t reload_store(struct device *dev,
 		return size;
 
 	tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
-	if (tmp_ret != UCODE_OK)
+	if (tmp_ret != UCODE_NEW)
 		return size;
 
 	get_online_cpus();
@@ -691,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
 	if (system_state != SYSTEM_RUNNING)
 		return UCODE_NFOUND;
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
-						     refresh_fw);
-
-	if (ustate == UCODE_OK) {
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, refresh_fw);
+	if (ustate == UCODE_NEW) {
 		pr_debug("CPU%d updated upon init\n", cpu);
 		apply_microcode_on_target(cpu);
 	}