x86, mce: fix a race condition in mce_read()

Impact: bugfix

Considering the situation as follow:

before: mcelog.next == 1, mcelog.entry[0].finished = 1

+--------------------------------------------------------------------------
R                   W1                  W2                  W3

read mcelog.next (1)
                    mcelog.next++ (2)
                    (working on entry 1,
                    finished == 0)

mcelog.next = 0
                                        mcelog.next++ (1)
                                        (working on entry 0)
                                                           mcelog.next++ (2)
                                                           (working on entry 1)
                        <----------------- race ---------------->
                    (done on entry 1,
                    finished = 1)
                                                           (done on entry 1,
                                                           finished = 1)

To fix the race condition, a cmpxchg loop is added to mce_read() to
ensure no new MCE record can be added between mcelog.next reading and
mcelog.next = 0.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

1 files changed, 24 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 1db94c0d5aaf..870d08deccf7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -595,7 +595,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
 {
         unsigned long *cpu_tsc;
         static DEFINE_MUTEX(mce_read_mutex);
-        unsigned next;
+        unsigned prev, next;
         char __user *buf = ubuf;
         int i, err;
 
@@ -614,25 +614,32 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
         }
 
         err = 0;
-        for (i = 0; i < next; i++) {
-                unsigned long start = jiffies;
-
-                while (!mcelog.entry[i].finished) {
-                        if (time_after_eq(jiffies, start + 2)) {
-                                memset(mcelog.entry + i,0, sizeof(struct mce));
-                                goto timeout;
+        prev = 0;
+        do {
+                for (i = prev; i < next; i++) {
+                        unsigned long start = jiffies;
+
+                        while (!mcelog.entry[i].finished) {
+                                if (time_after_eq(jiffies, start + 2)) {
+                                        memset(mcelog.entry + i, 0,
+                                               sizeof(struct mce));
+                                        goto timeout;
+                                }
+                                cpu_relax();
                         }
-                        cpu_relax();
+                        smp_rmb();
+                        err |= copy_to_user(buf, mcelog.entry + i,
+                                            sizeof(struct mce));
+                        buf += sizeof(struct mce);
+timeout:
+                        ;
                 }
-                smp_rmb();
-                err |= copy_to_user(buf, mcelog.entry + i, sizeof(struct mce));
-                buf += sizeof(struct mce);
- timeout:
-                ;
-        }
 
-        memset(mcelog.entry, 0, next * sizeof(struct mce));
-        mcelog.next = 0;
+                memset(mcelog.entry + prev, 0,
+                       (next - prev) * sizeof(struct mce));
+                prev = next;
+                next = cmpxchg(&mcelog.next, prev, 0);
+        } while (next != prev);
 
         synchronize_sched();