From: Ma Jun Jun.Ma2@amd.com
[ Upstream commit c02c1960c93eede587576625a1221205a68a904f ]
optimize the code to avoid pass a null pointer (hwmgr->backend) to function smu7_update_edc_leakage_table.
Signed-off-by: Ma Jun Jun.Ma2@amd.com Reviewed-by: Yang Wang kevinyang.wang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 50 +++++++++---------- 1 file changed, 24 insertions(+), 26 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 9bfc465d08fb0..2451cec031dda 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2907,6 +2907,7 @@ static int smu7_update_edc_leakage_table(struct pp_hwmgr *hwmgr)
static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { + struct amdgpu_device *adev = hwmgr->adev; struct smu7_hwmgr *data; int result = 0;
@@ -2943,40 +2944,37 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) /* Initalize Dynamic State Adjustment Rule Settings */ result = phm_initializa_dynamic_state_adjustment_rule_settings(hwmgr);
- if (0 == result) { - struct amdgpu_device *adev = hwmgr->adev; + if (result) + goto fail;
- data->is_tlu_enabled = false; + data->is_tlu_enabled = false;
- hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = + hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = SMU7_MAX_HARDWARE_POWERLEVELS; - hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; - hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; + hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; + hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50;
- data->pcie_gen_cap = adev->pm.pcie_gen_mask; - if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) - data->pcie_spc_cap = 20; - else - data->pcie_spc_cap = 16; - data->pcie_lane_cap = adev->pm.pcie_mlw_mask; - - hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ -/* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ - hwmgr->platform_descriptor.clockStep.engineClock = 500; - hwmgr->platform_descriptor.clockStep.memoryClock = 500; - smu7_thermal_parameter_init(hwmgr); - } else { - /* Ignore return value in here, we are cleaning up a mess. */ - smu7_hwmgr_backend_fini(hwmgr); - } + data->pcie_gen_cap = adev->pm.pcie_gen_mask; + if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + data->pcie_spc_cap = 20; + else + data->pcie_spc_cap = 16; + data->pcie_lane_cap = adev->pm.pcie_mlw_mask; + + hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ + /* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ + hwmgr->platform_descriptor.clockStep.engineClock = 500; + hwmgr->platform_descriptor.clockStep.memoryClock = 500; + smu7_thermal_parameter_init(hwmgr);
result = smu7_update_edc_leakage_table(hwmgr); - if (result) { - smu7_hwmgr_backend_fini(hwmgr); - return result; - } + if (result) + goto fail;
return 0; +fail: + smu7_hwmgr_backend_fini(hwmgr); + return result; }
static int smu7_force_dpm_highest(struct pp_hwmgr *hwmgr)
From: Ma Jun Jun.Ma2@amd.com
[ Upstream commit 4c11d30c95576937c6c35e6f29884761f2dddb43 ]
Check ras_manager before using it
Signed-off-by: Ma Jun Jun.Ma2@amd.com Reviewed-by: Lijo Lazar lijo.lazar@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index c963b87014b69..92a4f07858785 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1509,12 +1509,15 @@ static void amdgpu_ras_interrupt_process_handler(struct work_struct *work) int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev, struct ras_dispatch_if *info) { - struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); - struct ras_ih_data *data = &obj->ih_data; + struct ras_manager *obj; + struct ras_ih_data *data;
+ obj = amdgpu_ras_find_obj(adev, &info->head); if (!obj) return -EINVAL;
+ data = &obj->ih_data; + if (data->inuse == 0) return 0;
From: Ma Jun Jun.Ma2@amd.com
[ Upstream commit d19fb10085a49b77578314f69fff21562f7cd054 ]
Check the pointer value to fix potential null pointer dereference
Acked-by: Yang Wangkevinyang.wang@amd.com Signed-off-by: Ma Jun Jun.Ma2@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 7 +++++-- .../gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c | 14 ++++++++------ .../gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 7 +++++-- 3 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 2451cec031dda..9c7c3c06327d9 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -3275,8 +3275,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct smu7_power_state *smu7_ps = - cast_phw_smu7_power_state(&request_ps->hardware); + struct smu7_power_state *smu7_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3293,6 +3292,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t latency; bool latency_allowed = false;
+ smu7_ps = cast_phw_smu7_power_state(&request_ps->hardware); + if (!smu7_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); data->mclk_ignore_signal = false; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index 03bf8f0692228..f0f8ebffd9f2f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -1051,16 +1051,18 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, struct pp_power_state *prequest_ps, const struct pp_power_state *pcurrent_ps) { - struct smu8_power_state *smu8_ps = - cast_smu8_power_state(&prequest_ps->hardware); - - const struct smu8_power_state *smu8_current_ps = - cast_const_smu8_power_state(&pcurrent_ps->hardware); - + struct smu8_power_state *smu8_ps; + const struct smu8_power_state *smu8_current_ps; struct smu8_hwmgr *data = hwmgr->backend; struct PP_Clocks clocks = {0, 0, 0, 0}; bool force_high;
+ smu8_ps = cast_smu8_power_state(&prequest_ps->hardware); + smu8_current_ps = cast_const_smu8_power_state(&pcurrent_ps->hardware); + + if (!smu8_ps || !smu8_current_ps) + return -EINVAL; + smu8_ps->need_dfs_bypass = true;
data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index e6336654c5655..aba8904ac75f7 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3237,8 +3237,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct vega10_power_state *vega10_ps = - cast_phw_vega10_power_state(&request_ps->hardware); + struct vega10_power_state *vega10_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3256,6 +3255,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0; uint32_t latency;
+ vega10_ps = cast_phw_vega10_power_state(&request_ps->hardware); + if (!vega10_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label);
From: Alex Hung alex.hung@amd.com
[ Upstream commit 8092aa3ab8f7b737a34b71f91492c676a843043a ]
Checks null pointer before passing variables to functions.
This fixes 3 NULL_RETURNS issues reported by Coverity.
Reviewed-by: Harry Wentland harry.wentland@amd.com Acked-by: Hamza Mahfooz hamza.mahfooz@amd.com Signed-off-by: Alex Hung alex.hung@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b821abb56ac3b..333be05418935 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2431,7 +2431,8 @@ static int dm_suspend(void *handle)
dm->cached_dc_state = dc_copy_state(dm->dc->current_state);
- dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); + if (dm->cached_dc_state) + dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false);
amdgpu_dm_commit_zero_streams(dm->dc);
@@ -6884,7 +6885,8 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector) aconnector->dc_sink = aconnector->dc_link->local_sink ? aconnector->dc_link->local_sink : aconnector->dc_em_sink; - dc_sink_retain(aconnector->dc_sink); + if (aconnector->dc_sink) + dc_sink_retain(aconnector->dc_sink); } }
@@ -8218,7 +8220,8 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 640, 480); } else { amdgpu_dm_connector_ddc_get_modes(connector, edid); - amdgpu_dm_connector_add_common_modes(encoder, connector); + if (encoder) + amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, edid); } amdgpu_dm_fbc_init(connector);
From: Ricardo Ribalda ribalda@chromium.org
[ Upstream commit 5cd7c25f6f0576073b3d03bc4cfb1e8ca63a1195 ]
Some SunplusIT cameras took a borderline interpretation of the UVC 1.5 standard, and fill the PTS and SCR fields with invalid data if the package does not contain data.
"STC must be captured when the first video data of a video frame is put on the USB bus."
Some SunplusIT devices send, e.g.,
buffer: 0xa7755c00 len 000012 header:0x8c stc 00000000 sof 0000 pts 00000000 buffer: 0xa7755c00 len 000012 header:0x8c stc 00000000 sof 0000 pts 00000000 buffer: 0xa7755c00 len 000668 header:0x8c stc 73779dba sof 070c pts 7376d37a
While the UVC specification meant that the first two packets shouldn't have had the SCR bit set in the header.
This borderline/buggy interpretation has been implemented in a variety of devices, from directly SunplusIT and from other OEMs that rebrand SunplusIT products. So quirking based on VID:PID will be problematic.
All the affected modules have the following extension unit: VideoControl Interface Descriptor: guidExtensionCode {82066163-7050-ab49-b8cc-b3855e8d221d}
But the vendor plans to use that GUID in the future and fix the bug, this means that we should use heuristic to figure out the broken packets.
This patch takes care of this.
lsusb of one of the affected cameras:
Bus 001 Device 003: ID 1bcf:2a01 Sunplus Innovation Technology Inc. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.01 bDeviceClass 239 Miscellaneous Device bDeviceSubClass 2 ? bDeviceProtocol 1 Interface Association bMaxPacketSize0 64 idVendor 0x1bcf Sunplus Innovation Technology Inc. idProduct 0x2a01 bcdDevice 0.02 iManufacturer 1 SunplusIT Inc iProduct 2 HanChen Wise Camera iSerial 3 01.00.00 bNumConfigurations 1
Tested-by: HungNien Chen hn.chen@sunplusit.com Reviewed-by: Sergey Senozhatsky senozhatsky@chromium.org Reviewed-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Signed-off-by: Ricardo Ribalda ribalda@chromium.org Reviewed-by: Tomasz Figa tfiga@chromium.org Link: https://lore.kernel.org/r/20240323-resend-hwtimestamp-v10-2-b08e590d97c7@chr... Signed-off-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/uvc/uvc_video.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-)
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index f477cfbbb905a..dbba68701b4a1 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -471,6 +471,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, ktime_t time; u16 host_sof; u16 dev_sof; + u32 dev_stc;
switch (data[1] & (UVC_STREAM_PTS | UVC_STREAM_SCR)) { case UVC_STREAM_PTS | UVC_STREAM_SCR: @@ -515,6 +516,34 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, if (dev_sof == stream->clock.last_sof) return;
+ dev_stc = get_unaligned_le32(&data[header_size - 6]); + + /* + * STC (Source Time Clock) is the clock used by the camera. The UVC 1.5 + * standard states that it "must be captured when the first video data + * of a video frame is put on the USB bus". This is generally understood + * as requiring devices to clear the payload header's SCR bit before + * the first packet containing video data. + * + * Most vendors follow that interpretation, but some (namely SunplusIT + * on some devices) always set the `UVC_STREAM_SCR` bit, fill the SCR + * field with 0's,and expect that the driver only processes the SCR if + * there is data in the packet. + * + * Ignore all the hardware timestamp information if we haven't received + * any data for this frame yet, the packet contains no data, and both + * STC and SOF are zero. This heuristics should be safe on compliant + * devices. This should be safe with compliant devices, as in the very + * unlikely case where a UVC 1.1 device would send timing information + * only before the first packet containing data, and both STC and SOF + * happen to be zero for a particular frame, we would only miss one + * clock sample from many and the clock recovery algorithm wouldn't + * suffer from this condition. + */ + if (buf && buf->bytesused == 0 && len == header_size && + dev_stc == 0 && dev_sof == 0) + return; + stream->clock.last_sof = dev_sof;
host_sof = usb_get_current_frame_number(stream->dev->udev); @@ -552,7 +581,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, spin_lock_irqsave(&stream->clock.lock, flags);
sample = &stream->clock.samples[stream->clock.head]; - sample->dev_stc = get_unaligned_le32(&data[header_size - 6]); + sample->dev_stc = dev_stc; sample->dev_sof = dev_sof; sample->host_sof = host_sof; sample->host_time = time;
From: Michal Pecio michal.pecio@gmail.com
[ Upstream commit 9e3d55fbd160b3ca376599a68b4cddfdc67d4153 ]
The bandwidth fixup quirk doesn't know that SuperSpeed exists and has the same 8 service intervals per millisecond as High Speed, hence its calculations are wrong.
Assume that all speeds from HS up use 8 intervals per millisecond.
No further changes are needed, updated code has been confirmed to work with all speeds from FS to SS.
Signed-off-by: Michal Pecio michal.pecio@gmail.com Reviewed-by: Ricardo Ribalda ribalda@chromium.org Reviewed-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Link: https://lore.kernel.org/r/20240414190040.2255a0bc@foxbook Signed-off-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/uvc/uvc_video.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index dbba68701b4a1..30c8bcdda437f 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -210,13 +210,13 @@ static void uvc_fixup_video_ctrl(struct uvc_streaming *stream, /* Compute a bandwidth estimation by multiplying the frame * size by the number of video frames per second, divide the * result by the number of USB frames (or micro-frames for - * high-speed devices) per second and add the UVC header size - * (assumed to be 12 bytes long). + * high- and super-speed devices) per second and add the UVC + * header size (assumed to be 12 bytes long). */ bandwidth = frame->wWidth * frame->wHeight / 8 * format->bpp; bandwidth *= 10000000 / interval + 1; bandwidth /= 1000; - if (stream->dev->udev->speed == USB_SPEED_HIGH) + if (stream->dev->udev->speed >= USB_SPEED_HIGH) bandwidth /= 8; bandwidth += 12;
From: Xiaxi Shen shenxiaxi26@gmail.com
[ Upstream commit 8dc9c3da79c84b13fdb135e2fb0a149a8175bffe ]
Syzbot has found an uninit-value bug in ext4_inlinedir_to_tree
This error happens because ext4_inlinedir_to_tree does not handle the case when ext4fs_dirhash returns an error
This can be avoided by checking the return value of ext4fs_dirhash and propagating the error, similar to how it's done with ext4_htree_store_dirent
Signed-off-by: Xiaxi Shen shenxiaxi26@gmail.com Reported-and-tested-by: syzbot+eaba5abe296837a640c0@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=eaba5abe296837a640c0 Link: https://patch.msgid.link/20240501033017.220000-1-shenxiaxi26@gmail.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/inline.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 6fe665de1b203..bc7f6417888dc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1446,7 +1446,11 @@ int ext4_inlinedir_to_tree(struct file *dir_file, hinfo->hash = EXT4_DIRENT_HASH(de); hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); } else { - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + err = ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + if (err) { + ret = err; + goto out; + } } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) &&
From: Kemeng Shi shikemeng@huaweicloud.com
[ Upstream commit cc102aa24638b90e04364d64e4f58a1fa91a1976 ]
The new_bh is from alloc_buffer_head, we should call free_buffer_head to free it in error case.
Signed-off-by: Kemeng Shi shikemeng@huaweicloud.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://patch.msgid.link/20240514112438.1269037-2-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jbd2/journal.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index b7af1727a0160..ae59efa9e4469 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -412,6 +412,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); if (!tmp) { brelse(new_bh); + free_buffer_head(new_bh); return -ENOMEM; } spin_lock(&jh_in->b_state_lock);
From: Peter Oberparleiter oberpar@linux.ibm.com
[ Upstream commit bf365071ea92b9579d5a272679b74052a5643e35 ]
When a task waiting for completion of a Store Data operation is interrupted, an attempt is made to halt this operation. If this attempt fails due to a hardware or firmware problem, there is a chance that the SCLP facility might store data into buffers referenced by the original operation at a later time.
Handle this situation by not releasing the referenced data buffers if the halt attempt fails. For current use cases, this might result in a leak of few pages of memory in case of a rare hardware/firmware malfunction.
Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Peter Oberparleiter oberpar@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/s390/char/sclp_sd.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/s390/char/sclp_sd.c b/drivers/s390/char/sclp_sd.c index 1e244f78f1929..64581433c3349 100644 --- a/drivers/s390/char/sclp_sd.c +++ b/drivers/s390/char/sclp_sd.c @@ -319,8 +319,14 @@ static int sclp_sd_store_data(struct sclp_sd_data *result, u8 di) &esize); if (rc) { /* Cancel running request if interrupted */ - if (rc == -ERESTARTSYS) - sclp_sd_sync(page, SD_EQ_HALT, di, 0, 0, NULL, NULL); + if (rc == -ERESTARTSYS) { + if (sclp_sd_sync(page, SD_EQ_HALT, di, 0, 0, NULL, NULL)) { + pr_warn("Could not stop Store Data request - leaking at least %zu bytes\n", + (size_t)dsize * PAGE_SIZE); + data = NULL; + asce = 0; + } + } vfree(data); goto out; }
From: Benjamin Coddington bcodding@redhat.com
[ Upstream commit ed0172af5d6fc07d1b40ca82f5ca3979300369f7 ]
We've observed NFS clients with sync tasks sleeping in __rpc_execute waiting on RPC_TASK_QUEUED that have not responded to a wake-up from rpc_make_runnable(). I suspect this problem usually goes unnoticed, because on a busy client the task will eventually be re-awoken by another task completion or xprt event. However, if the state manager is draining the slot table, a sync task missing a wake-up can result in a hung client.
We've been able to prove that the waker in rpc_make_runnable() successfully calls wake_up_bit() (ie- there's no race to tk_runstate), but the wake_up_bit() call fails to wake the waiter. I suspect the waker is missing the load of the bit's wait_queue_head, so waitqueue_active() is false. There are some very helpful comments about this problem above wake_up_bit(), prepare_to_wait(), and waitqueue_active().
Fix this by inserting smp_mb__after_atomic() before the wake_up_bit(), which pairs with prepare_to_wait() calling set_current_state().
Signed-off-by: Benjamin Coddington bcodding@redhat.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/sched.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index a00890962e115..540220264b31e 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -348,8 +348,10 @@ static void rpc_make_runnable(struct workqueue_struct *wq, if (RPC_IS_ASYNC(task)) { INIT_WORK(&task->u.tk_work, rpc_async_schedule); queue_work(wq, &task->u.tk_work); - } else + } else { + smp_mb__after_atomic(); wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED); + } }
/*
linux-stable-mirror@lists.linaro.org