Merge branch 'linux-3.0.y' into HEAD

3 files changed, 70 insertions, 7 deletions

diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index effff47..43876f1 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -31,6 +31,56 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
 	ptep->pte_low = pte.pte_low;
 }
 
+#define pmd_read_atomic pmd_read_atomic
+/*
+ * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
+ * a "*pmdp" dereference done by gcc. Problem is, in certain places
+ * where pte_offset_map_lock is called, concurrent page faults are
+ * allowed, if the mmap_sem is hold for reading. An example is mincore
+ * vs page faults vs MADV_DONTNEED. On the page fault side
+ * pmd_populate rightfully does a set_64bit, but if we're reading the
+ * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
+ * because gcc will not read the 64bit of the pmd atomically. To fix
+ * this all places running pmd_offset_map_lock() while holding the
+ * mmap_sem in read mode, shall read the pmdp pointer using this
+ * function to know if the pmd is null nor not, and in turn to know if
+ * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
+ * operations.
+ *
+ * Without THP if the mmap_sem is hold for reading, the
+ * pmd can only transition from null to not null while pmd_read_atomic runs.
+ * So there's no need of literally reading it atomically.
+ *
+ * With THP if the mmap_sem is hold for reading, the pmd can become
+ * THP or null or point to a pte (and in turn become "stable") at any
+ * time under pmd_read_atomic, so it's mandatory to read it atomically
+ * with cmpxchg8b.
+ */
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	pmdval_t ret;
+	u32 *tmp = (u32 *)pmdp;
+
+	ret = (pmdval_t) (*tmp);
+	if (ret) {
+		/*
+		 * If the low part is null, we must not read the high part
+		 * or we can end up with a partial pmd.
+		 */
+		smp_rmb();
+		ret |= ((pmdval_t)*(tmp + 1)) << 32;
+	}
+
+	return (pmd_t) { ret };
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	return (pmd_t) { atomic64_read((atomic64_t *)pmdp) };
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
 	set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 1e8d66c..362190b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -101,15 +101,19 @@ static struct severity {
 };
 
 /*
- * If the EIPV bit is set, it means the saved IP is the
- * instruction which caused the MCE.
+ * If mcgstatus indicated that ip/cs on the stack were
+ * no good, then "m->cs" will be zero and we will have
+ * to assume the worst case (IN_KERNEL) as we actually
+ * have no idea what we were executing when the machine
+ * check hit.
+ * If we do have a good "m->cs" (or a faked one in the
+ * case we were executing in VM86 mode) we can use it to
+ * distinguish an exception taken in user from from one
+ * taken in the kernel.
  */
 static int error_context(struct mce *m)
 {
-	if (m->mcgstatus & MCG_STATUS_EIPV)
-		return (m->ip && (m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
-	/* Unknown, assume kernel */
-	return IN_KERNEL;
+	return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
 }
 
 int mce_severity(struct mce *a, int tolerant, char **msg)
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index fe29c1d..4b50c96 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -437,6 +437,7 @@ static __initconst const struct x86_pmu amd_pmu = {
  * 0x023	DE	PERF_CTL[2:0]
  * 0x02D	LS	PERF_CTL[3]
  * 0x02E	LS	PERF_CTL[3,0]
+ * 0x031	LS	PERF_CTL[2:0] (**)
  * 0x043	CU	PERF_CTL[2:0]
  * 0x045	CU	PERF_CTL[2:0]
  * 0x046	CU	PERF_CTL[2:0]
@@ -450,10 +451,12 @@ static __initconst const struct x86_pmu amd_pmu = {
  * 0x0DD	LS	PERF_CTL[5:0]
  * 0x0DE	LS	PERF_CTL[5:0]
  * 0x0DF	LS	PERF_CTL[5:0]
+ * 0x1C0	EX	PERF_CTL[5:3]
  * 0x1D6	EX	PERF_CTL[5:0]
  * 0x1D8	EX	PERF_CTL[5:0]
  *
- * (*) depending on the umask all FPU counters may be used
+ * (*)  depending on the umask all FPU counters may be used
+ * (**) only one unitmask enabled at a time
  */
 
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -503,6 +506,12 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
 			return &amd_f15_PMC3;
 		case 0x02E:
 			return &amd_f15_PMC30;
+		case 0x031:
+			if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+				return &amd_f15_PMC20;
+			return &emptyconstraint;
+		case 0x1C0:
+			return &amd_f15_PMC53;
 		default:
 			return &amd_f15_PMC50;
 		}