October 2019 - Linux-stable-mirror

[PATCH] media: cxd2841er: avoid too many status inquires

by Mauro Carvalho Chehab

As reported at: https://tvheadend.org/issues/5625 Retrieving certain status can cause discontinuity issues. Prevent that by adding a timeout to each status logic. Currently, the timeout is estimated based at the channel bandwidth. There are other parameters that may also affect the timeout, but that would require a per-delivery system calculus and probably more information about how cxd2481er works, with we don't have. So, do a poor man's best guess. Cc: stable(a)vger.kernel.org Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung(a)kernel.org> --- drivers/media/dvb-frontends/cxd2841er.c | 59 +++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c index 1b30cf570803..71428b0d2620 100644 --- a/drivers/media/dvb-frontends/cxd2841er.c +++ b/drivers/media/dvb-frontends/cxd2841er.c @@ -60,6 +60,13 @@ struct cxd2841er_priv { enum cxd2841er_xtal xtal; enum fe_caps caps; u32 flags; + + unsigned long ber_interval; + unsigned long ucb_interval; + + unsigned long ber_time; + unsigned long ucb_time; + unsigned long snr_time; }; static const struct cxd2841er_cnr_data s_cn_data[] = { @@ -1941,12 +1948,20 @@ static void cxd2841er_read_ber(struct dvb_frontend *fe) struct cxd2841er_priv *priv = fe->demodulator_priv; u32 ret, bit_error = 0, bit_count = 0; + if (priv->ber_time && + (!time_after(jiffies, priv->ber_time))) + return; + dev_dbg(&priv->i2c->dev, "%s()\n", __func__); switch (p->delivery_system) { case SYS_DVBC_ANNEX_A: case SYS_DVBC_ANNEX_B: case SYS_DVBC_ANNEX_C: ret = cxd2841er_read_ber_c(priv, &bit_error, &bit_count); + + if (!priv->ber_interval && p->symbol_rate) + priv->ber_interval = (10000000) / (p->symbol_rate / 1000); + break; case SYS_ISDBT: ret = cxd2841er_read_ber_i(priv, &bit_error, &bit_count); @@ -1978,6 +1993,18 @@ static void cxd2841er_read_ber(struct dvb_frontend *fe) p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE; p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE; } + + /* + * If the per-delivery system doesn't specify, set a default timeout + * that will wait for ~12.5 seconds for 8MHz channels + */ + if (!priv->ber_interval && p->bandwidth_hz) + priv->ber_interval = (100000000) / (p->bandwidth_hz / 1000); + + if (priv->ber_interval < 1000) + priv->ber_interval = 1000; + + priv->ber_time = jiffies + msecs_to_jiffies(priv->ber_interval); } static void cxd2841er_read_signal_strength(struct dvb_frontend *fe) @@ -2037,6 +2064,13 @@ static void cxd2841er_read_snr(struct dvb_frontend *fe) struct dtv_frontend_properties *p = &fe->dtv_property_cache; struct cxd2841er_priv *priv = fe->demodulator_priv; + if (priv->snr_time && + (!time_after(jiffies, priv->snr_time))) + return; + + /* Preventing asking SNR more than once per second */ + priv->snr_time = jiffies + msecs_to_jiffies(1000); + dev_dbg(&priv->i2c->dev, "%s()\n", __func__); switch (p->delivery_system) { case SYS_DVBC_ANNEX_A: @@ -2081,12 +2115,18 @@ static void cxd2841er_read_ucblocks(struct dvb_frontend *fe) struct cxd2841er_priv *priv = fe->demodulator_priv; u32 ucblocks = 0; + if (priv->ucb_time && + (!time_after(jiffies, priv->ucb_time))) + return; + dev_dbg(&priv->i2c->dev, "%s()\n", __func__); switch (p->delivery_system) { case SYS_DVBC_ANNEX_A: case SYS_DVBC_ANNEX_B: case SYS_DVBC_ANNEX_C: cxd2841er_read_packet_errors_c(priv, &ucblocks); + if (!priv->ucb_interval && p->symbol_rate) + priv->ucb_interval = (100 * 204 * 1000 * 8) / p->symbol_rate; break; case SYS_DVBT: cxd2841er_read_packet_errors_t(priv, &ucblocks); @@ -2105,6 +2145,18 @@ static void cxd2841er_read_ucblocks(struct dvb_frontend *fe) p->block_error.stat[0].scale = FE_SCALE_COUNTER; p->block_error.stat[0].uvalue = ucblocks; + + /* + * If the per-delivery system doesn't specify, set a default timeout + * that will wait 20-30 seconds + */ + if (!priv->ucb_interval && p->bandwidth_hz) + priv->ucb_interval = (100 * 204 * 1000 * 8) / p->bandwidth_hz; + + if (priv->ucb_interval < 1000) + priv->ucb_interval = 1000; + + priv->ucb_time = jiffies + msecs_to_jiffies(priv->ucb_interval); } static int cxd2841er_dvbt2_set_profile( @@ -3360,6 +3412,13 @@ static int cxd2841er_set_frontend_s(struct dvb_frontend *fe) p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE; p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE; + /* Reset the wait for jiffies logic */ + priv->ber_interval = 0; + priv->ucb_interval = 0; + priv->ber_time = 0; + priv->ucb_time = 0; + priv->snr_time = 0; + return ret; } -- 2.21.0

5 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] platform/chrome: cros_ec_rpmsg: Fix race with host command" failed to apply to 5.3-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.3-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 71cddb7097e2b0feb855d7fd7d59afd12cbee4bb Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih <pihsun(a)chromium.org> Date: Wed, 4 Sep 2019 14:26:13 +0800 Subject: [PATCH] platform/chrome: cros_ec_rpmsg: Fix race with host command when probe failed Since the rpmsg_endpoint is created before probe is called, it's possible that a host event is received during cros_ec_register, and there would be some pending work in the host_event_work workqueue while cros_ec_register is called. If cros_ec_register fails, when the leftover work in host_event_work run, the ec_dev from the drvdata of the rpdev could be already set to NULL, causing kernel crash when trying to run cros_ec_get_next_event. Fix this by creating the rpmsg_endpoint by ourself, and when cros_ec_register fails (or on remove), destroy the endpoint first (to make sure there's no more new calls to cros_ec_rpmsg_callback), and then cancel all works in the host_event_work workqueue. Cc: stable(a)vger.kernel.org Fixes: 2de89fd98958 ("platform/chrome: cros_ec: Add EC host command support using rpmsg") Signed-off-by: Pi-Hsun Shih <pihsun(a)chromium.org> Signed-off-by: Enric Balletbo i Serra <enric.balletbo(a)collabora.com> diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index 8b6bd775cc9a..0c3738c3244d 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -41,6 +41,7 @@ struct cros_ec_rpmsg { struct rpmsg_device *rpdev; struct completion xfer_ack; struct work_struct host_event_work; + struct rpmsg_endpoint *ept; }; /** @@ -72,7 +73,6 @@ static int cros_ec_pkt_xfer_rpmsg(struct cros_ec_device *ec_dev, struct cros_ec_command *ec_msg) { struct cros_ec_rpmsg *ec_rpmsg = ec_dev->priv; - struct rpmsg_device *rpdev = ec_rpmsg->rpdev; struct ec_host_response *response; unsigned long timeout; int len; @@ -85,7 +85,7 @@ static int cros_ec_pkt_xfer_rpmsg(struct cros_ec_device *ec_dev, dev_dbg(ec_dev->dev, "prepared, len=%d\n", len); reinit_completion(&ec_rpmsg->xfer_ack); - ret = rpmsg_send(rpdev->ept, ec_dev->dout, len); + ret = rpmsg_send(ec_rpmsg->ept, ec_dev->dout, len); if (ret) { dev_err(ec_dev->dev, "rpmsg send failed\n"); return ret; @@ -196,11 +196,24 @@ static int cros_ec_rpmsg_callback(struct rpmsg_device *rpdev, void *data, return 0; } +static struct rpmsg_endpoint * +cros_ec_rpmsg_create_ept(struct rpmsg_device *rpdev) +{ + struct rpmsg_channel_info chinfo = {}; + + strscpy(chinfo.name, rpdev->id.name, RPMSG_NAME_SIZE); + chinfo.src = rpdev->src; + chinfo.dst = RPMSG_ADDR_ANY; + + return rpmsg_create_ept(rpdev, cros_ec_rpmsg_callback, NULL, chinfo); +} + static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev) { struct device *dev = &rpdev->dev; struct cros_ec_rpmsg *ec_rpmsg; struct cros_ec_device *ec_dev; + int ret; ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL); if (!ec_dev) @@ -225,7 +238,18 @@ static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev) INIT_WORK(&ec_rpmsg->host_event_work, cros_ec_rpmsg_host_event_function); - return cros_ec_register(ec_dev); + ec_rpmsg->ept = cros_ec_rpmsg_create_ept(rpdev); + if (!ec_rpmsg->ept) + return -ENOMEM; + + ret = cros_ec_register(ec_dev); + if (ret < 0) { + rpmsg_destroy_ept(ec_rpmsg->ept); + cancel_work_sync(&ec_rpmsg->host_event_work); + return ret; + } + + return 0; } static void cros_ec_rpmsg_remove(struct rpmsg_device *rpdev) @@ -234,7 +258,7 @@ static void cros_ec_rpmsg_remove(struct rpmsg_device *rpdev) struct cros_ec_rpmsg *ec_rpmsg = ec_dev->priv; cros_ec_unregister(ec_dev); - + rpmsg_destroy_ept(ec_rpmsg->ept); cancel_work_sync(&ec_rpmsg->host_event_work); } @@ -271,7 +295,6 @@ static struct rpmsg_driver cros_ec_driver_rpmsg = { }, .probe = cros_ec_rpmsg_probe, .remove = cros_ec_rpmsg_remove, - .callback = cros_ec_rpmsg_callback, }; module_rpmsg_driver(cros_ec_driver_rpmsg);

5 years, 4 months

2
1
0 0

FAILED: patch "[PATCH] Btrfs: fix race setting up and completing qgroup rescan" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 13fc1d271a2e3ab8a02071e711add01fab9271f6 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Tue, 24 Sep 2019 10:49:54 +0100 Subject: [PATCH] Btrfs: fix race setting up and completing qgroup rescan workers There is a race between setting up a qgroup rescan worker and completing a qgroup rescan worker that can lead to callers of the qgroup rescan wait ioctl to either not wait for the rescan worker to complete or to hang forever due to missing wake ups. The following diagram shows a sequence of steps that illustrates the race. CPU 1 CPU 2 CPU 3 btrfs_ioctl_quota_rescan() btrfs_qgroup_rescan() qgroup_rescan_init() mutex_lock(&fs_info->qgroup_rescan_lock) spin_lock(&fs_info->qgroup_lock) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN init_completion( &fs_info->qgroup_rescan_completion) fs_info->qgroup_rescan_running = true mutex_unlock(&fs_info->qgroup_rescan_lock) spin_unlock(&fs_info->qgroup_lock) btrfs_init_work() --> starts the worker btrfs_qgroup_rescan_worker() mutex_lock(&fs_info->qgroup_rescan_lock) fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN mutex_unlock(&fs_info->qgroup_rescan_lock) starts transaction, updates qgroup status item, etc btrfs_ioctl_quota_rescan() btrfs_qgroup_rescan() qgroup_rescan_init() mutex_lock(&fs_info->qgroup_rescan_lock) spin_lock(&fs_info->qgroup_lock) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN init_completion( &fs_info->qgroup_rescan_completion) fs_info->qgroup_rescan_running = true mutex_unlock(&fs_info->qgroup_rescan_lock) spin_unlock(&fs_info->qgroup_lock) btrfs_init_work() --> starts another worker mutex_lock(&fs_info->qgroup_rescan_lock) fs_info->qgroup_rescan_running = false mutex_unlock(&fs_info->qgroup_rescan_lock) complete_all(&fs_info->qgroup_rescan_completion) Before the rescan worker started by the task at CPU 3 completes, if another task calls btrfs_ioctl_quota_rescan(), it will get -EINPROGRESS because the flag BTRFS_QGROUP_STATUS_FLAG_RESCAN is set at fs_info->qgroup_flags, which is expected and correct behaviour. However if other task calls btrfs_ioctl_quota_rescan_wait() before the rescan worker started by the task at CPU 3 completes, it will return immediately without waiting for the new rescan worker to complete, because fs_info->qgroup_rescan_running is set to false by CPU 2. This race is making test case btrfs/171 (from fstests) to fail often: btrfs/171 9s ... - output mismatch (see /home/fdmanana/git/hub/xfstests/results//btrfs/171.out.bad) --- tests/btrfs/171.out 2018-09-16 21:30:48.505104287 +0100 +++ /home/fdmanana/git/hub/xfstests/results//btrfs/171.out.bad 2019-09-19 02:01:36.938486039 +0100 @@ -1,2 +1,3 @@ QA output created by 171 +ERROR: quota rescan failed: Operation now in progress Silence is golden ... (Run 'diff -u /home/fdmanana/git/hub/xfstests/tests/btrfs/171.out /home/fdmanana/git/hub/xfstests/results//btrfs/171.out.bad' to see the entire diff) That is because the test calls the btrfs-progs commands "qgroup quota rescan -w", "qgroup assign" and "qgroup remove" in a sequence that makes calls to the rescan start ioctl fail with -EINPROGRESS (note the "btrfs" commands 'qgroup assign' and 'qgroup remove' often call the rescan start ioctl after calling the qgroup assign ioctl, btrfs_ioctl_qgroup_assign()), since previous waits didn't actually wait for a rescan worker to complete. Another problem the race can cause is missing wake ups for waiters, since the call to complete_all() happens outside a critical section and after clearing the flag BTRFS_QGROUP_STATUS_FLAG_RESCAN. In the sequence diagram above, if we have a waiter for the first rescan task (executed by CPU 2), then fs_info->qgroup_rescan_completion.wait is not empty, and if after the rescan worker clears BTRFS_QGROUP_STATUS_FLAG_RESCAN and before it calls complete_all() against fs_info->qgroup_rescan_completion, the task at CPU 3 calls init_completion() against fs_info->qgroup_rescan_completion which re-initilizes its wait queue to an empty queue, therefore causing the rescan worker at CPU 2 to call complete_all() against an empty queue, never waking up the task waiting for that rescan worker. Fix this by clearing BTRFS_QGROUP_STATUS_FLAG_RESCAN and setting fs_info->qgroup_rescan_running to false in the same critical section, delimited by the mutex fs_info->qgroup_rescan_lock, as well as doing the call to complete_all() in that same critical section. This gives the protection needed to avoid rescan wait ioctl callers not waiting for a running rescan worker and the lost wake ups problem, since setting that rescan flag and boolean as well as initializing the wait queue is done already in a critical section delimited by that mutex (at qgroup_rescan_init()). Fixes: 57254b6ebce4ce ("Btrfs: add ioctl to wait for qgroup rescan completion") Fixes: d2c609b834d62f ("btrfs: properly track when rescan worker is running") CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 8d3bd799ac7d..52701c1be109 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3166,9 +3166,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); - if (!btrfs_fs_closing(fs_info)) - fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; - if (err > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -3184,16 +3181,30 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) trans = btrfs_start_transaction(fs_info->quota_root, 1); if (IS_ERR(trans)) { err = PTR_ERR(trans); + trans = NULL; btrfs_err(fs_info, "fail to start transaction for status update: %d", err); - goto done; } - ret = update_qgroup_status_item(trans); - if (ret < 0) { - err = ret; - btrfs_err(fs_info, "fail to update qgroup status: %d", err); + + mutex_lock(&fs_info->qgroup_rescan_lock); + if (!btrfs_fs_closing(fs_info)) + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + if (trans) { + ret = update_qgroup_status_item(trans); + if (ret < 0) { + err = ret; + btrfs_err(fs_info, "fail to update qgroup status: %d", + err); + } } + fs_info->qgroup_rescan_running = false; + complete_all(&fs_info->qgroup_rescan_completion); + mutex_unlock(&fs_info->qgroup_rescan_lock); + + if (!trans) + return; + btrfs_end_transaction(trans); if (btrfs_fs_closing(fs_info)) { @@ -3204,12 +3215,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) } else { btrfs_err(fs_info, "qgroup scan failed with %d", err); } - -done: - mutex_lock(&fs_info->qgroup_rescan_lock); - fs_info->qgroup_rescan_running = false; - mutex_unlock(&fs_info->qgroup_rescan_lock); - complete_all(&fs_info->qgroup_rescan_completion); } /*

5 years, 4 months

2
1
0 0

FAILED: patch "[PATCH] mt76: mt7615: fix mt7615 firmware path definitions" failed to apply to 5.3-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.3-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 9d4d0d06bbf9f7e576b0ebbb2f77672d0fc7f503 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi <lorenzo(a)kernel.org> Date: Sun, 22 Sep 2019 15:36:03 +0200 Subject: [PATCH] mt76: mt7615: fix mt7615 firmware path definitions mt7615 patch/n9/cr4 firmwares are available in mediatek folder in linux-firmware repository. Because of this mt7615 won't work on regular distributions like Ubuntu. Fix path definitions. Moreover remove useless firmware name pointers and use definitions directly Fixes: 04b8e65922f6 ("mt76: add mac80211 driver for MT7615 PCIe-based chipsets") Cc: stable(a)vger.kernel.org Signed-off-by: Lorenzo Bianconi <lorenzo(a)kernel.org> Signed-off-by: Kalle Valo <kvalo(a)codeaurora.org> diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index 275d5eaed3b7..842cd81704db 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -333,7 +333,6 @@ static int mt7615_driver_own(struct mt7615_dev *dev) static int mt7615_load_patch(struct mt7615_dev *dev) { - const char *firmware = MT7615_ROM_PATCH; const struct mt7615_patch_hdr *hdr; const struct firmware *fw = NULL; int len, ret, sem; @@ -349,7 +348,7 @@ static int mt7615_load_patch(struct mt7615_dev *dev) return -EAGAIN; } - ret = request_firmware(&fw, firmware, dev->mt76.dev); + ret = request_firmware(&fw, MT7615_ROM_PATCH, dev->mt76.dev); if (ret) goto out; @@ -447,13 +446,11 @@ mt7615_mcu_send_ram_firmware(struct mt7615_dev *dev, static int mt7615_load_ram(struct mt7615_dev *dev) { - const struct firmware *fw; const struct mt7615_fw_trailer *hdr; - const char *n9_firmware = MT7615_FIRMWARE_N9; - const char *cr4_firmware = MT7615_FIRMWARE_CR4; + const struct firmware *fw; int ret; - ret = request_firmware(&fw, n9_firmware, dev->mt76.dev); + ret = request_firmware(&fw, MT7615_FIRMWARE_N9, dev->mt76.dev); if (ret) return ret; @@ -482,7 +479,7 @@ static int mt7615_load_ram(struct mt7615_dev *dev) release_firmware(fw); - ret = request_firmware(&fw, cr4_firmware, dev->mt76.dev); + ret = request_firmware(&fw, MT7615_FIRMWARE_CR4, dev->mt76.dev); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index cef3fd43cb00..7963e302d705 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -26,9 +26,9 @@ #define MT7615_RX_RING_SIZE 1024 #define MT7615_RX_MCU_RING_SIZE 512 -#define MT7615_FIRMWARE_CR4 "mt7615_cr4.bin" -#define MT7615_FIRMWARE_N9 "mt7615_n9.bin" -#define MT7615_ROM_PATCH "mt7615_rom_patch.bin" +#define MT7615_FIRMWARE_CR4 "mediatek/mt7615_cr4.bin" +#define MT7615_FIRMWARE_N9 "mediatek/mt7615_n9.bin" +#define MT7615_ROM_PATCH "mediatek/mt7615_rom_patch.bin" #define MT7615_EEPROM_SIZE 1024 #define MT7615_TOKEN_SIZE 4096

5 years, 4 months

2
1
0 0

FAILED: patch "[PATCH] memcg, oom: don't require __GFP_FS when invoking memcg OOM" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From f9c645621a28e37813a1de96d9cbd89cde94a1e4 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa <penguin-kernel(a)i-love.sakura.ne.jp> Date: Mon, 23 Sep 2019 15:37:08 -0700 Subject: [PATCH] memcg, oom: don't require __GFP_FS when invoking memcg OOM killer Masoud Sharbiani noticed that commit 29ef680ae7c21110 ("memcg, oom: move out_of_memory back to the charge path") broke memcg OOM called from __xfs_filemap_fault() path. It turned out that try_charge() is retrying forever without making forward progress because mem_cgroup_oom(GFP_NOFS) cannot invoke the OOM killer due to commit 3da88fb3bacfaa33 ("mm, oom: move GFP_NOFS check to out_of_memory"). Allowing forced charge due to being unable to invoke memcg OOM killer will lead to global OOM situation. Also, just returning -ENOMEM will be risky because OOM path is lost and some paths (e.g. get_user_pages()) will leak -ENOMEM. Therefore, invoking memcg OOM killer (despite GFP_NOFS) will be the only choice we can choose for now. Until 29ef680ae7c21110, we were able to invoke memcg OOM killer when GFP_KERNEL reclaim failed [1]. But since 29ef680ae7c21110, we need to invoke memcg OOM killer when GFP_NOFS reclaim failed [2]. Although in the past we did invoke memcg OOM killer for GFP_NOFS [3], we might get pre-mature memcg OOM reports due to this patch. [1] leaker invoked oom-killer: gfp_mask=0x6200ca(GFP_HIGHUSER_MOVABLE), nodemask=(null), order=0, oom_score_adj=0 CPU: 0 PID: 2746 Comm: leaker Not tainted 4.18.0+ #19 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018 Call Trace: dump_stack+0x63/0x88 dump_header+0x67/0x27a ? mem_cgroup_scan_tasks+0x91/0xf0 oom_kill_process+0x210/0x410 out_of_memory+0x10a/0x2c0 mem_cgroup_out_of_memory+0x46/0x80 mem_cgroup_oom_synchronize+0x2e4/0x310 ? high_work_func+0x20/0x20 pagefault_out_of_memory+0x31/0x76 mm_fault_error+0x55/0x115 ? handle_mm_fault+0xfd/0x220 __do_page_fault+0x433/0x4e0 do_page_fault+0x22/0x30 ? page_fault+0x8/0x30 page_fault+0x1e/0x30 RIP: 0033:0x4009f0 Code: 03 00 00 00 e8 71 fd ff ff 48 83 f8 ff 49 89 c6 74 74 48 89 c6 bf c0 0c 40 00 31 c0 e8 69 fd ff ff 45 85 ff 7e 21 31 c9 66 90 <41> 0f be 14 0e 01 d3 f7 c1 ff 0f 00 00 75 05 41 c6 04 0e 2a 48 83 RSP: 002b:00007ffe29ae96f0 EFLAGS: 00010206 RAX: 000000000000001b RBX: 0000000000000000 RCX: 0000000001ce1000 RDX: 0000000000000000 RSI: 000000007fffffe5 RDI: 0000000000000000 RBP: 000000000000000c R08: 0000000000000000 R09: 00007f94be09220d R10: 0000000000000002 R11: 0000000000000246 R12: 00000000000186a0 R13: 0000000000000003 R14: 00007f949d845000 R15: 0000000002800000 Task in /leaker killed as a result of limit of /leaker memory: usage 524288kB, limit 524288kB, failcnt 158965 memory+swap: usage 0kB, limit 9007199254740988kB, failcnt 0 kmem: usage 2016kB, limit 9007199254740988kB, failcnt 0 Memory cgroup stats for /leaker: cache:844KB rss:521136KB rss_huge:0KB shmem:0KB mapped_file:0KB dirty:132KB writeback:0KB inactive_anon:0KB active_anon:521224KB inactive_file:1012KB active_file:8KB unevictable:0KB Memory cgroup out of memory: Kill process 2746 (leaker) score 998 or sacrifice child Killed process 2746 (leaker) total-vm:536704kB, anon-rss:521176kB, file-rss:1208kB, shmem-rss:0kB oom_reaper: reaped process 2746 (leaker), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB [2] leaker invoked oom-killer: gfp_mask=0x600040(GFP_NOFS), nodemask=(null), order=0, oom_score_adj=0 CPU: 1 PID: 2746 Comm: leaker Not tainted 4.18.0+ #20 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018 Call Trace: dump_stack+0x63/0x88 dump_header+0x67/0x27a ? mem_cgroup_scan_tasks+0x91/0xf0 oom_kill_process+0x210/0x410 out_of_memory+0x109/0x2d0 mem_cgroup_out_of_memory+0x46/0x80 try_charge+0x58d/0x650 ? __radix_tree_replace+0x81/0x100 mem_cgroup_try_charge+0x7a/0x100 __add_to_page_cache_locked+0x92/0x180 add_to_page_cache_lru+0x4d/0xf0 iomap_readpages_actor+0xde/0x1b0 ? iomap_zero_range_actor+0x1d0/0x1d0 iomap_apply+0xaf/0x130 iomap_readpages+0x9f/0x150 ? iomap_zero_range_actor+0x1d0/0x1d0 xfs_vm_readpages+0x18/0x20 [xfs] read_pages+0x60/0x140 __do_page_cache_readahead+0x193/0x1b0 ondemand_readahead+0x16d/0x2c0 page_cache_async_readahead+0x9a/0xd0 filemap_fault+0x403/0x620 ? alloc_set_pte+0x12c/0x540 ? _cond_resched+0x14/0x30 __xfs_filemap_fault+0x66/0x180 [xfs] xfs_filemap_fault+0x27/0x30 [xfs] __do_fault+0x19/0x40 __handle_mm_fault+0x8e8/0xb60 handle_mm_fault+0xfd/0x220 __do_page_fault+0x238/0x4e0 do_page_fault+0x22/0x30 ? page_fault+0x8/0x30 page_fault+0x1e/0x30 RIP: 0033:0x4009f0 Code: 03 00 00 00 e8 71 fd ff ff 48 83 f8 ff 49 89 c6 74 74 48 89 c6 bf c0 0c 40 00 31 c0 e8 69 fd ff ff 45 85 ff 7e 21 31 c9 66 90 <41> 0f be 14 0e 01 d3 f7 c1 ff 0f 00 00 75 05 41 c6 04 0e 2a 48 83 RSP: 002b:00007ffda45c9290 EFLAGS: 00010206 RAX: 000000000000001b RBX: 0000000000000000 RCX: 0000000001a1e000 RDX: 0000000000000000 RSI: 000000007fffffe5 RDI: 0000000000000000 RBP: 000000000000000c R08: 0000000000000000 R09: 00007f6d061ff20d R10: 0000000000000002 R11: 0000000000000246 R12: 00000000000186a0 R13: 0000000000000003 R14: 00007f6ce59b2000 R15: 0000000002800000 Task in /leaker killed as a result of limit of /leaker memory: usage 524288kB, limit 524288kB, failcnt 7221 memory+swap: usage 0kB, limit 9007199254740988kB, failcnt 0 kmem: usage 1944kB, limit 9007199254740988kB, failcnt 0 Memory cgroup stats for /leaker: cache:3632KB rss:518232KB rss_huge:0KB shmem:0KB mapped_file:0KB dirty:0KB writeback:0KB inactive_anon:0KB active_anon:518408KB inactive_file:3908KB active_file:12KB unevictable:0KB Memory cgroup out of memory: Kill process 2746 (leaker) score 992 or sacrifice child Killed process 2746 (leaker) total-vm:536704kB, anon-rss:518264kB, file-rss:1188kB, shmem-rss:0kB oom_reaper: reaped process 2746 (leaker), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB [3] leaker invoked oom-killer: gfp_mask=0x50, order=0, oom_score_adj=0 leaker cpuset=/ mems_allowed=0 CPU: 1 PID: 3206 Comm: leaker Not tainted 3.10.0-957.27.2.el7.x86_64 #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018 Call Trace: [<ffffffffaf364147>] dump_stack+0x19/0x1b [<ffffffffaf35eb6a>] dump_header+0x90/0x229 [<ffffffffaedbb456>] ? find_lock_task_mm+0x56/0xc0 [<ffffffffaee32a38>] ? try_get_mem_cgroup_from_mm+0x28/0x60 [<ffffffffaedbb904>] oom_kill_process+0x254/0x3d0 [<ffffffffaee36c36>] mem_cgroup_oom_synchronize+0x546/0x570 [<ffffffffaee360b0>] ? mem_cgroup_charge_common+0xc0/0xc0 [<ffffffffaedbc194>] pagefault_out_of_memory+0x14/0x90 [<ffffffffaf35d072>] mm_fault_error+0x6a/0x157 [<ffffffffaf3717c8>] __do_page_fault+0x3c8/0x4f0 [<ffffffffaf371925>] do_page_fault+0x35/0x90 [<ffffffffaf36d768>] page_fault+0x28/0x30 Task in /leaker killed as a result of limit of /leaker memory: usage 524288kB, limit 524288kB, failcnt 20628 memory+swap: usage 524288kB, limit 9007199254740988kB, failcnt 0 kmem: usage 0kB, limit 9007199254740988kB, failcnt 0 Memory cgroup stats for /leaker: cache:840KB rss:523448KB rss_huge:0KB mapped_file:0KB swap:0KB inactive_anon:0KB active_anon:523448KB inactive_file:464KB active_file:376KB unevictable:0KB Memory cgroup out of memory: Kill process 3206 (leaker) score 970 or sacrifice child Killed process 3206 (leaker) total-vm:536692kB, anon-rss:523304kB, file-rss:412kB, shmem-rss:0kB Bisected by Masoud Sharbiani. Link: http://lkml.kernel.org/r/cbe54ed1-b6ba-a056-8899-2dc42526371d@i-love.sakura… Fixes: 3da88fb3bacfaa33 ("mm, oom: move GFP_NOFS check to out_of_memory") [necessary after 29ef680ae7c21110] Signed-off-by: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Reported-by: Masoud Sharbiani <msharbiani(a)apple.com> Tested-by: Masoud Sharbiani <msharbiani(a)apple.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.19+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 95872bdfec4e..a6b76624f5b8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -1069,9 +1069,10 @@ bool out_of_memory(struct oom_control *oc) * The OOM killer does not compensate for IO-less reclaim. * pagefault_out_of_memory lost its gfp context so we have to * make sure exclude 0 mask - all other users should have at least - * ___GFP_DIRECT_RECLAIM to get here. + * ___GFP_DIRECT_RECLAIM to get here. But mem_cgroup_oom() has to + * invoke the OOM killer even if it is a GFP_NOFS allocation. */ - if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS)) + if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc)) return true; /*

5 years, 4 months

2
1
0 0

FAILED: patch "[PATCH] mm/compaction.c: clear total_{migrate, free}_scanned before" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a94b525241c0fff3598809131d7cfcfe1d572d8c Mon Sep 17 00:00:00 2001 From: Yafang Shao <laoar.shao(a)gmail.com> Date: Mon, 23 Sep 2019 15:36:54 -0700 Subject: [PATCH] mm/compaction.c: clear total_{migrate,free}_scanned before scanning a new zone total_{migrate,free}_scanned will be added to COMPACTMIGRATE_SCANNED and COMPACTFREE_SCANNED in compact_zone(). We should clear them before scanning a new zone. In the proc triggered compaction, we forgot clearing them. [laoar.shao(a)gmail.com: introduce a helper compact_zone_counters_init()] Link: http://lkml.kernel.org/r/1563869295-25748-1-git-send-email-laoar.shao@gmail… [akpm(a)linux-foundation.org: expand compact_zone_counters_init() into its single callsite, per mhocko] [vbabka(a)suse.cz: squash compact_zone() list_head init as well] Link: http://lkml.kernel.org/r/1fb6f7da-f776-9e42-22f8-bbb79b030b98@suse.cz [akpm(a)linux-foundation.org: kcompactd_do_work(): avoid unnecessary initialization of cc.zone] Link: http://lkml.kernel.org/r/1563789275-9639-1-git-send-email-laoar.shao@gmail.… Fixes: 7f354a548d1c ("mm, compaction: add vmstats for kcompactd work") Signed-off-by: Yafang Shao <laoar.shao(a)gmail.com> Signed-off-by: Vlastimil Babka <vbabka(a)suse.cz> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Cc: David Rientjes <rientjes(a)google.com> Cc: Yafang Shao <shaoyafang(a)didiglobal.com> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Michal Hocko <mhocko(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/compaction.c b/mm/compaction.c index 777c088e9113..d99d59412c75 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2078,6 +2078,17 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) const bool sync = cc->mode != MIGRATE_ASYNC; bool update_cached; + /* + * These counters track activities during zone compaction. Initialize + * them before compacting a new zone. + */ + cc->total_migrate_scanned = 0; + cc->total_free_scanned = 0; + cc->nr_migratepages = 0; + cc->nr_freepages = 0; + INIT_LIST_HEAD(&cc->freepages); + INIT_LIST_HEAD(&cc->migratepages); + cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask); ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags, cc->classzone_idx); @@ -2281,10 +2292,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, { enum compact_result ret; struct compact_control cc = { - .nr_freepages = 0, - .nr_migratepages = 0, - .total_migrate_scanned = 0, - .total_free_scanned = 0, .order = order, .search_order = order, .gfp_mask = gfp_mask, @@ -2305,8 +2312,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, if (capture) current->capture_control = &capc; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); ret = compact_zone(&cc, &capc); @@ -2408,8 +2413,6 @@ static void compact_node(int nid) struct zone *zone; struct compact_control cc = { .order = -1, - .total_migrate_scanned = 0, - .total_free_scanned = 0, .mode = MIGRATE_SYNC, .ignore_skip_hint = true, .whole_zone = true, @@ -2423,11 +2426,7 @@ static void compact_node(int nid) if (!populated_zone(zone)) continue; - cc.nr_freepages = 0; - cc.nr_migratepages = 0; cc.zone = zone; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); compact_zone(&cc, NULL); @@ -2529,8 +2528,6 @@ static void kcompactd_do_work(pg_data_t *pgdat) struct compact_control cc = { .order = pgdat->kcompactd_max_order, .search_order = pgdat->kcompactd_max_order, - .total_migrate_scanned = 0, - .total_free_scanned = 0, .classzone_idx = pgdat->kcompactd_classzone_idx, .mode = MIGRATE_SYNC_LIGHT, .ignore_skip_hint = false, @@ -2554,16 +2551,10 @@ static void kcompactd_do_work(pg_data_t *pgdat) COMPACT_CONTINUE) continue; - cc.nr_freepages = 0; - cc.nr_migratepages = 0; - cc.total_migrate_scanned = 0; - cc.total_free_scanned = 0; - cc.zone = zone; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); - if (kthread_should_stop()) return; + + cc.zone = zone; status = compact_zone(&cc, NULL); if (status == COMPACT_SUCCESS) {

5 years, 4 months

2
1
0 0

[PATCH] staging: wlan-ng: fix uninitialized variable

by Denis Efremov

The result variable in prism2_connect() can be used uninitialized on path !channel --> ... --> is_wep --> sme->key --> sme->key_idx >= NUM_WEPKEYS. This patch initializes result with 0. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: stable(a)vger.kernel.org Signed-off-by: Denis Efremov <efremov(a)linux.com> --- drivers/staging/wlan-ng/cfg80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c index eee1998c4b18..d426905e187e 100644 --- a/drivers/staging/wlan-ng/cfg80211.c +++ b/drivers/staging/wlan-ng/cfg80211.c @@ -441,7 +441,7 @@ static int prism2_connect(struct wiphy *wiphy, struct net_device *dev, int chan = -1; int is_wep = (sme->crypto.cipher_group == WLAN_CIPHER_SUITE_WEP40) || (sme->crypto.cipher_group == WLAN_CIPHER_SUITE_WEP104); - int result; + int result = 0; int err = 0; /* Set the channel */ -- 2.21.0

5 years, 4 months

2
2
0 0

[PATCH v2] KEYS: asym_tpm: Switch to get_random_bytes()

by Jarkko Sakkinen

Only the kernel random pool should be used for generating random numbers. TPM contributes to that pool among the other sources of entropy. In here it is not, agreed, absolutely critical because TPM is what is trusted anyway but in order to remove tpm_get_random() we need to first remove all the call sites. Cc: stable(a)vger.kernel.org Fixes: 0c36264aa1d5 ("KEYS: asym_tpm: Add loadkey2 and flushspecific [ver #2]") Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen(a)linux.intel.com> --- v2: * Changed two remaining call sites to use get_random_bytes() * Removed "stating the obvious" comments. crypto/asymmetric_keys/asym_tpm.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c index 76d2ce3a1b5b..4eaf57483b9a 100644 --- a/crypto/asymmetric_keys/asym_tpm.c +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/seq_file.h> #include <linux/scatterlist.h> +#include <linux/random.h> #include <linux/tpm.h> #include <linux/tpm_command.h> #include <crypto/akcipher.h> @@ -53,12 +54,7 @@ static int tpm_loadkey2(struct tpm_buf *tb, return ret; } - /* generate odd nonce */ - ret = tpm_get_random(NULL, nonceodd, TPM_NONCE_SIZE); - if (ret < 0) { - pr_info("tpm_get_random failed (%d)\n", ret); - return ret; - } + get_random_bytes(nonceodd, TPM_NONCE_SIZE); /* calculate authorization HMAC value */ ret = TSS_authhmac(authdata, keyauth, SHA1_DIGEST_SIZE, enonce, @@ -139,12 +135,7 @@ static int tpm_unbind(struct tpm_buf *tb, return ret; } - /* generate odd nonce */ - ret = tpm_get_random(NULL, nonceodd, TPM_NONCE_SIZE); - if (ret < 0) { - pr_info("tpm_get_random failed (%d)\n", ret); - return ret; - } + get_random_bytes(nonceodd, TPM_NONCE_SIZE); /* calculate authorization HMAC value */ ret = TSS_authhmac(authdata, keyauth, SHA1_DIGEST_SIZE, enonce, @@ -225,12 +216,7 @@ static int tpm_sign(struct tpm_buf *tb, return ret; } - /* generate odd nonce */ - ret = tpm_get_random(NULL, nonceodd, TPM_NONCE_SIZE); - if (ret < 0) { - pr_info("tpm_get_random failed (%d)\n", ret); - return ret; - } + get_random_bytes(nonceodd, TPM_NONCE_SIZE); /* calculate authorization HMAC value */ ret = TSS_authhmac(authdata, keyauth, SHA1_DIGEST_SIZE, enonce, -- 2.20.1

5 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] md/raid0: avoid RAID0 data corruption due to layout" failed to apply to 5.3-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.3-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From c84a1372df929033cb1a0441fb57bd3932f39ac9 Mon Sep 17 00:00:00 2001 From: NeilBrown <neilb(a)suse.de> Date: Mon, 9 Sep 2019 16:30:02 +1000 Subject: [PATCH] md/raid0: avoid RAID0 data corruption due to layout confusion. If the drives in a RAID0 are not all the same size, the array is divided into zones. The first zone covers all drives, to the size of the smallest. The second zone covers all drives larger than the smallest, up to the size of the second smallest - etc. A change in Linux 3.14 unintentionally changed the layout for the second and subsequent zones. All the correct data is still stored, but each chunk may be assigned to a different device than in pre-3.14 kernels. This can lead to data corruption. It is not possible to determine what layout to use - it depends which kernel the data was written by. So we add a module parameter to allow the old (0) or new (1) layout to be specified, and refused to assemble an affected array if that parameter is not set. Fixes: 20d0189b1012 ("block: Introduce new bio_split()") cc: stable(a)vger.kernel.org (3.14+) Acked-by: Guoqing Jiang <guoqing.jiang(a)cloud.ionos.com> Signed-off-by: NeilBrown <neilb(a)suse.de> Signed-off-by: Song Liu <songliubraving(a)fb.com> diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index bc422eae2c95..ec611abda835 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -19,6 +19,9 @@ #include "raid0.h" #include "raid5.h" +static int default_layout = 0; +module_param(default_layout, int, 0644); + #define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_HAS_JOURNAL) | \ (1L << MD_JOURNAL_CLEAN) | \ @@ -139,6 +142,19 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); + + if (conf->nr_strip_zones == 1) { + conf->layout = RAID0_ORIG_LAYOUT; + } else if (default_layout == RAID0_ORIG_LAYOUT || + default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = default_layout; + } else { + pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", + mdname(mddev)); + pr_err("md/raid0: please set raid.default_layout to 1 or 2\n"); + err = -ENOTSUPP; + goto abort; + } /* * now since we have the hard sector sizes, we can make sure * chunk size is a multiple of that sector size @@ -547,10 +563,12 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) static bool raid0_make_request(struct mddev *mddev, struct bio *bio) { + struct r0conf *conf = mddev->private; struct strip_zone *zone; struct md_rdev *tmp_dev; sector_t bio_sector; sector_t sector; + sector_t orig_sector; unsigned chunk_sects; unsigned sectors; @@ -584,8 +602,20 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio = split; } + orig_sector = sector; zone = find_zone(mddev->private, &sector); - tmp_dev = map_sector(mddev, zone, sector, &sector); + switch (conf->layout) { + case RAID0_ORIG_LAYOUT: + tmp_dev = map_sector(mddev, zone, orig_sector, &sector); + break; + case RAID0_ALT_MULTIZONE_LAYOUT: + tmp_dev = map_sector(mddev, zone, sector, &sector); + break; + default: + WARN("md/raid0:%s: Invalid layout\n", mdname(mddev)); + bio_io_error(bio); + return true; + } if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) { bio_io_error(bio); diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h index 540e65d92642..3816e5477db1 100644 --- a/drivers/md/raid0.h +++ b/drivers/md/raid0.h @@ -8,11 +8,25 @@ struct strip_zone { int nb_dev; /* # of devices attached to the zone */ }; +/* Linux 3.14 (20d0189b101) made an unintended change to + * the RAID0 layout for multi-zone arrays (where devices aren't all + * the same size. + * RAID0_ORIG_LAYOUT restores the original layout + * RAID0_ALT_MULTIZONE_LAYOUT uses the altered layout + * The layouts are identical when there is only one zone (all + * devices the same size). + */ + +enum r0layout { + RAID0_ORIG_LAYOUT = 1, + RAID0_ALT_MULTIZONE_LAYOUT = 2, +}; struct r0conf { struct strip_zone *strip_zone; struct md_rdev **devlist; /* lists of rdevs, pointed to * by strip_zone->dev */ int nr_strip_zones; + enum r0layout layout; }; #endif

5 years, 4 months

2
1
0 0

FAILED: patch "[PATCH] platform/chrome: cros_ec_rpmsg: Fix race with host command" failed to apply to 5.2-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.2-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 71cddb7097e2b0feb855d7fd7d59afd12cbee4bb Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih <pihsun(a)chromium.org> Date: Wed, 4 Sep 2019 14:26:13 +0800 Subject: [PATCH] platform/chrome: cros_ec_rpmsg: Fix race with host command when probe failed Since the rpmsg_endpoint is created before probe is called, it's possible that a host event is received during cros_ec_register, and there would be some pending work in the host_event_work workqueue while cros_ec_register is called. If cros_ec_register fails, when the leftover work in host_event_work run, the ec_dev from the drvdata of the rpdev could be already set to NULL, causing kernel crash when trying to run cros_ec_get_next_event. Fix this by creating the rpmsg_endpoint by ourself, and when cros_ec_register fails (or on remove), destroy the endpoint first (to make sure there's no more new calls to cros_ec_rpmsg_callback), and then cancel all works in the host_event_work workqueue. Cc: stable(a)vger.kernel.org Fixes: 2de89fd98958 ("platform/chrome: cros_ec: Add EC host command support using rpmsg") Signed-off-by: Pi-Hsun Shih <pihsun(a)chromium.org> Signed-off-by: Enric Balletbo i Serra <enric.balletbo(a)collabora.com> diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index 8b6bd775cc9a..0c3738c3244d 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -41,6 +41,7 @@ struct cros_ec_rpmsg { struct rpmsg_device *rpdev; struct completion xfer_ack; struct work_struct host_event_work; + struct rpmsg_endpoint *ept; }; /** @@ -72,7 +73,6 @@ static int cros_ec_pkt_xfer_rpmsg(struct cros_ec_device *ec_dev, struct cros_ec_command *ec_msg) { struct cros_ec_rpmsg *ec_rpmsg = ec_dev->priv; - struct rpmsg_device *rpdev = ec_rpmsg->rpdev; struct ec_host_response *response; unsigned long timeout; int len; @@ -85,7 +85,7 @@ static int cros_ec_pkt_xfer_rpmsg(struct cros_ec_device *ec_dev, dev_dbg(ec_dev->dev, "prepared, len=%d\n", len); reinit_completion(&ec_rpmsg->xfer_ack); - ret = rpmsg_send(rpdev->ept, ec_dev->dout, len); + ret = rpmsg_send(ec_rpmsg->ept, ec_dev->dout, len); if (ret) { dev_err(ec_dev->dev, "rpmsg send failed\n"); return ret; @@ -196,11 +196,24 @@ static int cros_ec_rpmsg_callback(struct rpmsg_device *rpdev, void *data, return 0; } +static struct rpmsg_endpoint * +cros_ec_rpmsg_create_ept(struct rpmsg_device *rpdev) +{ + struct rpmsg_channel_info chinfo = {}; + + strscpy(chinfo.name, rpdev->id.name, RPMSG_NAME_SIZE); + chinfo.src = rpdev->src; + chinfo.dst = RPMSG_ADDR_ANY; + + return rpmsg_create_ept(rpdev, cros_ec_rpmsg_callback, NULL, chinfo); +} + static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev) { struct device *dev = &rpdev->dev; struct cros_ec_rpmsg *ec_rpmsg; struct cros_ec_device *ec_dev; + int ret; ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL); if (!ec_dev) @@ -225,7 +238,18 @@ static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev) INIT_WORK(&ec_rpmsg->host_event_work, cros_ec_rpmsg_host_event_function); - return cros_ec_register(ec_dev); + ec_rpmsg->ept = cros_ec_rpmsg_create_ept(rpdev); + if (!ec_rpmsg->ept) + return -ENOMEM; + + ret = cros_ec_register(ec_dev); + if (ret < 0) { + rpmsg_destroy_ept(ec_rpmsg->ept); + cancel_work_sync(&ec_rpmsg->host_event_work); + return ret; + } + + return 0; } static void cros_ec_rpmsg_remove(struct rpmsg_device *rpdev) @@ -234,7 +258,7 @@ static void cros_ec_rpmsg_remove(struct rpmsg_device *rpdev) struct cros_ec_rpmsg *ec_rpmsg = ec_dev->priv; cros_ec_unregister(ec_dev); - + rpmsg_destroy_ept(ec_rpmsg->ept); cancel_work_sync(&ec_rpmsg->host_event_work); } @@ -271,7 +295,6 @@ static struct rpmsg_driver cros_ec_driver_rpmsg = { }, .probe = cros_ec_rpmsg_probe, .remove = cros_ec_rpmsg_remove, - .callback = cros_ec_rpmsg_callback, }; module_rpmsg_driver(cros_ec_driver_rpmsg);

5 years, 4 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2019