From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EDCEF78B60; Wed, 21 Feb 2024 14:16:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708524998; cv=none; b=caEBQu7rIAoyddtvPnbNzbxT07MSC8h/RgLtAGbJThw+eQGk/+ZSSTGjngkxFCi8Hk4pUXj0hfQgwK3FdKnzSWkvRN/ovpGlWEymWP4lWxljmAjwQ2VS8jiFqUqeiKPxR1iYzaii6O1Z094VuZTAl8eYomG4QFXi7gL5yXT7iIA= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708524998; c=relaxed/simple; bh=Ibbp1vXvSh/90E17kPjUAZ7KegSVp+rQqemNMuRmQjU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Z3yHkC8rdUDCxq0+2fjrJEvbd3iGrh4lPn9sJcUolgIjpO06aDVCuOvyp7IrszT1d+AS44Cf5uFJH+ffSgWEk+PLNlLj6FBTflHe2jhCNInO8Cj+2IAiE1okBAN1Qviqd6c0Gd8wOwdc7nYoUb9fbNifrhUb66QdAHKPJAej2uc= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=GhczRHDC; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b="GhczRHDC" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 5C3E9C433C7; Wed, 21 Feb 2024 14:16:37 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1708524997; bh=Ibbp1vXvSh/90E17kPjUAZ7KegSVp+rQqemNMuRmQjU=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=GhczRHDCEsyP+CnM9QXr7X6o34z54TuXkvX9ScIDHUP6YHl5ODZSkmkdbNisys9q/ /leGm/WGI/aNvlju//igy80O4YPRbFo5V4yM44/o4ei6+m9HBJTHSd8x9vE3cZu5bn x2ru/Ismdl1v1H9uoY6pKeYvQJbK+iMV7lebVNDI= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, Hongchen Zhang , Weihao Li , "Rafael J. Wysocki" Subject: [PATCH 5.4 011/267] PM: hibernate: Enforce ordering during image compression/decompression Date: Wed, 21 Feb 2024 14:05:52 +0100 Message-ID: <20240221125940.415150759@linuxfoundation.org> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240221125940.058369148@linuxfoundation.org> References: <20240221125940.058369148@linuxfoundation.org> User-Agent: quilt/0.67 X-stable: review X-Patchwork-Hint: ignore Precedence: bulk X-Mailing-List: patches@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 5.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Hongchen Zhang 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 Signed-off-by: Hongchen Zhang Co-developed-by: Weihao Li Signed-off-by: Weihao Li [ rjw: Subject rewrite and changelog edits ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- kernel/power/swap.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -594,11 +594,11 @@ 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; } @@ -607,7 +607,7 @@ 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; @@ -637,12 +637,12 @@ static int lzo_compress_threadfn(void *d 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; } @@ -651,7 +651,7 @@ static int lzo_compress_threadfn(void *d 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; @@ -789,7 +789,7 @@ static int save_image_lzo(struct swap_ma data[thr].unc_len = off; - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -797,12 +797,12 @@ static int save_image_lzo(struct swap_ma 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; @@ -841,7 +841,7 @@ static int save_image_lzo(struct swap_ma } } - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } @@ -1121,12 +1121,12 @@ static int lzo_decompress_threadfn(void 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; } @@ -1139,7 +1139,7 @@ static int lzo_decompress_threadfn(void 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; @@ -1327,7 +1327,7 @@ static int load_image_lzo(struct swap_ma } 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; } @@ -1363,7 +1363,7 @@ static int load_image_lzo(struct swap_ma pg = 0; } - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -1382,7 +1382,7 @@ static int load_image_lzo(struct swap_ma 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; @@ -1413,7 +1413,7 @@ static int load_image_lzo(struct swap_ma 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; } @@ -1421,13 +1421,13 @@ static int load_image_lzo(struct swap_ma } 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();