PM: hibernate: Enforce ordering during image compression/decompression

commit 71cd7e80cfde548959952eac7063aeaea1f2e1c6 upstream.

An S4 (suspend to disk) test on the LoongArch 3A6000 platform sometimes
fails with the following error messaged in the dmesg log:

	Invalid LZO compressed length

That happens because when compressing/decompressing the image, the
synchronization between the control thread and the compress/decompress/crc
thread is based on a relaxed ordering interface, which is unreliable, and the
following situation may occur:

CPU 0					CPU 1
save_image_lzo				lzo_compress_threadfn
					  atomic_set(&d->stop, 1);
  atomic_read(&data[thr].stop)
  data[thr].cmp = data[thr].cmp_len;
	  				  WRITE data[thr].cmp_len

Then CPU0 gets a stale cmp_len and writes it to disk. During resume from S4,
wrong cmp_len is loaded.

To maintain data consistency between the two threads, use the acquire/release
variants of atomic set and read operations.

Fixes: 081a9d043c98 ("PM / Hibernate: Improve performance of LZO/plain hibernation, checksum image")
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Hongchen Zhang <zhanghongchen@loongson.cn>
Co-developed-by: Weihao Li <liweihao@loongson.cn>
Signed-off-by: Weihao Li <liweihao@loongson.cn>
[ rjw: Subject rewrite and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 74edbce..d71c590 100644 (file)
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -605,11 +605,11 @@ static int crc32_threadfn(void *data)
        unsigned i;
 
        while (1) {
-               wait_event(d->go, atomic_read(&d->ready) ||
+               wait_event(d->go, atomic_read_acquire(&d->ready) ||
                                  kthread_should_stop());
                if (kthread_should_stop()) {
                        d->thr = NULL;
-                       atomic_set(&d->stop, 1);
+                       atomic_set_release(&d->stop, 1);
                        wake_up(&d->done);
                        break;
                }
@@ -618,7 +618,7 @@ static int crc32_threadfn(void *data)
                for (i = 0; i < d->run_threads; i++)
                        *d->crc32 = crc32_le(*d->crc32,
                                             d->unc[i], *d->unc_len[i]);
-               atomic_set(&d->stop, 1);
+               atomic_set_release(&d->stop, 1);
                wake_up(&d->done);
        }
        return 0;
@@ -648,12 +648,12 @@ static int lzo_compress_threadfn(void *data)
        struct cmp_data *d = data;
 
        while (1) {
-               wait_event(d->go, atomic_read(&d->ready) ||
+               wait_event(d->go, atomic_read_acquire(&d->ready) ||
                                  kthread_should_stop());
                if (kthread_should_stop()) {
                        d->thr = NULL;
                        d->ret = -1;
-                       atomic_set(&d->stop, 1);
+                       atomic_set_release(&d->stop, 1);
                        wake_up(&d->done);
                        break;
                }
@@ -662,7 +662,7 @@ static int lzo_compress_threadfn(void *data)
                d->ret = lzo1x_1_compress(d->unc, d->unc_len,
                                          d->cmp + LZO_HEADER, &d->cmp_len,
                                          d->wrk);
-               atomic_set(&d->stop, 1);
+               atomic_set_release(&d->stop, 1);
                wake_up(&d->done);
        }
        return 0;
@@ -797,7 +797,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 
                        data[thr].unc_len = off;
 
-                       atomic_set(&data[thr].ready, 1);
+                       atomic_set_release(&data[thr].ready, 1);
                        wake_up(&data[thr].go);
                }
 
@@ -805,12 +805,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
                        break;
 
                crc->run_threads = thr;
-               atomic_set(&crc->ready, 1);
+               atomic_set_release(&crc->ready, 1);
                wake_up(&crc->go);
 
                for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
                        wait_event(data[thr].done,
-                                  atomic_read(&data[thr].stop));
+                               atomic_read_acquire(&data[thr].stop));
                        atomic_set(&data[thr].stop, 0);
 
                        ret = data[thr].ret;
@@ -849,7 +849,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
                        }
                }
 
-               wait_event(crc->done, atomic_read(&crc->stop));
+               wait_event(crc->done, atomic_read_acquire(&crc->stop));
                atomic_set(&crc->stop, 0);
        }
 
@@ -1131,12 +1131,12 @@ static int lzo_decompress_threadfn(void *data)
        struct dec_data *d = data;
 
        while (1) {
-               wait_event(d->go, atomic_read(&d->ready) ||
+               wait_event(d->go, atomic_read_acquire(&d->ready) ||
                                  kthread_should_stop());
                if (kthread_should_stop()) {
                        d->thr = NULL;
                        d->ret = -1;
-                       atomic_set(&d->stop, 1);
+                       atomic_set_release(&d->stop, 1);
                        wake_up(&d->done);
                        break;
                }
@@ -1149,7 +1149,7 @@ static int lzo_decompress_threadfn(void *data)
                        flush_icache_range((unsigned long)d->unc,
                                           (unsigned long)d->unc + d->unc_len);
 
-               atomic_set(&d->stop, 1);
+               atomic_set_release(&d->stop, 1);
                wake_up(&d->done);
        }
        return 0;
@@ -1334,7 +1334,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
                }
 
                if (crc->run_threads) {
-                       wait_event(crc->done, atomic_read(&crc->stop));
+                       wait_event(crc->done, atomic_read_acquire(&crc->stop));
                        atomic_set(&crc->stop, 0);
                        crc->run_threads = 0;
                }
@@ -1370,7 +1370,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
                                        pg = 0;
                        }
 
-                       atomic_set(&data[thr].ready, 1);
+                       atomic_set_release(&data[thr].ready, 1);
                        wake_up(&data[thr].go);
                }
 
@@ -1389,7 +1389,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
                for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
                        wait_event(data[thr].done,
-                                  atomic_read(&data[thr].stop));
+                               atomic_read_acquire(&data[thr].stop));
                        atomic_set(&data[thr].stop, 0);
 
                        ret = data[thr].ret;
@@ -1420,7 +1420,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
                                ret = snapshot_write_next(snapshot);
                                if (ret <= 0) {
                                        crc->run_threads = thr + 1;
-                                       atomic_set(&crc->ready, 1);
+                                       atomic_set_release(&crc->ready, 1);
                                        wake_up(&crc->go);
                                        goto out_finish;
                                }
@@ -1428,13 +1428,13 @@ static int load_image_lzo(struct swap_map_handle *handle,
                }
 
                crc->run_threads = thr;
-               atomic_set(&crc->ready, 1);
+               atomic_set_release(&crc->ready, 1);
                wake_up(&crc->go);
        }
 
 out_finish:
        if (crc->run_threads) {
-               wait_event(crc->done, atomic_read(&crc->stop));
+               wait_event(crc->done, atomic_read_acquire(&crc->stop));
                atomic_set(&crc->stop, 0);
        }
        stop = ktime_get();