From 17abc9ec68b73ddeb262a507a62421016b9c54d5 Mon Sep 17 00:00:00 2001 From: Tomasz Duszynski Date: Fri, 14 Dec 2018 19:28:01 +0100 Subject: iio: add IIO_MASSCONCENTRATION channel type Measuring particulate matter in ug / m3 (micro-grams per cubic meter) is de facto standard. Existing air quality sensors usually follow this convention and are capable of returning measurements using this unit. IIO currently does not offer suitable channel type for this type of measurements hence this patch adds this. In addition, extra modifiers are introduced used for distinguishing between fine pm1, pm2p5 and coarse pm4, pm10 particle measurements, i.e IIO_MOD_PM1, IIO_MOD_PM25 and IIO_MOD_PM4, IIO_MOD_PM10. pmX consists of particles with aerodynamic diameter less or equal to X micrometers. Signed-off-by: Tomasz Duszynski Acked-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- include/uapi/linux/iio/types.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 92baabc103ac..c59adac24b1c 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -46,6 +46,7 @@ enum iio_chan_type { IIO_GRAVITY, IIO_POSITIONRELATIVE, IIO_PHASE, + IIO_MASSCONCENTRATION, }; enum iio_modifier { @@ -87,6 +88,10 @@ enum iio_modifier { IIO_MOD_VOC, IIO_MOD_LIGHT_UV, IIO_MOD_LIGHT_DUV, + IIO_MOD_PM1, + IIO_MOD_PM2P5, + IIO_MOD_PM4, + IIO_MOD_PM10, }; enum iio_event_type { -- cgit From b170f7d48443d1ea3e4ffbf409025b5e5b1146fe Mon Sep 17 00:00:00 2001 From: Andreas Brauchli Date: Thu, 13 Dec 2018 15:43:22 +0100 Subject: iio: Add modifiers for ethanol and H2 gases Add ethanol and H2 gas modifiers: * IIO_MOD_ETHANOL * IIO_MOD_H2 Signed-off-by: Andreas Brauchli Acked-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 4 ++++ include/uapi/linux/iio/types.h | 2 ++ tools/iio/iio_event_monitor.c | 4 ++++ 3 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 67fd88bf7910..864f8efd12e5 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1554,6 +1554,10 @@ What: /sys/bus/iio/devices/iio:deviceX/in_concentration_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_co2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_co2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_ethanol_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_ethanol_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_h2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_h2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_voc_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw KernelVersion: 4.3 diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index c59adac24b1c..fdd81affca4b 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -92,6 +92,8 @@ enum iio_modifier { IIO_MOD_PM2P5, IIO_MOD_PM4, IIO_MOD_PM10, + IIO_MOD_ETHANOL, + IIO_MOD_H2, }; enum iio_event_type { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index f6b8003fbe3c..7bf9bde28bcc 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -115,6 +115,8 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_I] = "i", [IIO_MOD_Q] = "q", [IIO_MOD_CO2] = "co2", + [IIO_MOD_ETHANOL] = "ethanol", + [IIO_MOD_H2] = "h2", [IIO_MOD_VOC] = "voc", [IIO_MOD_PM1] = "pm1", [IIO_MOD_PM2P5] = "pm2p5", @@ -205,6 +207,8 @@ static bool event_is_known(struct iio_event_data *event) case IIO_MOD_I: case IIO_MOD_Q: case IIO_MOD_CO2: + case IIO_MOD_ETHANOL: + case IIO_MOD_H2: case IIO_MOD_VOC: case IIO_MOD_PM1: case IIO_MOD_PM2P5: -- cgit From c2eb8effb265ac5cdd960d8e61ecb931e9c767cd Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 24 Oct 2018 06:50:34 -0400 Subject: media: videodev2.h: add v4l2_timeval_to_ns inline function We want to be able to uniquely identify buffers for stateless codecs. The internal timestamp (a u64) as stored internally in the kernel is a suitable candidate for that, but in struct v4l2_buffer it is represented as a struct timeval. Add a v4l2_timeval_to_ns() function that converts the struct timeval into a u64 in the same way that the kernel does. This makes it possible to use this u64 elsewhere as a unique identifier of the buffer. Since timestamps are also copied from the output buffer to the corresponding capture buffer(s) by M2M devices, the u64 can be used to refer to both output and capture buffers. The plan is that in the future we redesign struct v4l2_buffer and use u64 for the timestamp instead of a struct timeval (which has lots of problems with 32 vs 64 bit and y2038 layout changes), and then there is no more need to use this function. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index b5671ce2724f..d6eed479c3a6 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -973,6 +973,18 @@ struct v4l2_buffer { }; }; +/** + * v4l2_timeval_to_ns - Convert timeval to nanoseconds + * @ts: pointer to the timeval variable to be converted + * + * Returns the scalar nanosecond representation of the timeval + * parameter. + */ +static inline __u64 v4l2_timeval_to_ns(const struct timeval *tv) +{ + return (__u64)tv->tv_sec * 1000000000ULL + tv->tv_usec * 1000; +} + /* Flags for 'flags' field */ /* Buffer is mapped (flag) */ #define V4L2_BUF_FLAG_MAPPED 0x00000001 -- cgit From 4b837c6d7ee771f68a30f362c9f68171a95be222 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 14 Jan 2019 09:01:54 -0500 Subject: media: v4l: uAPI: V4L2_BUF_TYPE_META_OUTPUT is an output buffer type V4L2_BUF_TYPE_META_OUTPUT was added by commit 72148d1a57e7 ("media: v4l: Add support for V4L2_BUF_TYPE_META_OUTPUT") but the patch missed adding the type to the macro telling whether a given type is an output type or not. Do that now. Getting this wrong leads to handling the buffer as a capture buffer in a lot of places. Fixes: 72148d1a57e7 ("media: v4l: Add support for V4L2_BUF_TYPE_META_OUTPUT") Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d6eed479c3a6..c0c36c165bf4 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -161,7 +161,8 @@ enum v4l2_buf_type { || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY \ || (type) == V4L2_BUF_TYPE_VBI_OUTPUT \ || (type) == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT \ - || (type) == V4L2_BUF_TYPE_SDR_OUTPUT) + || (type) == V4L2_BUF_TYPE_SDR_OUTPUT \ + || (type) == V4L2_BUF_TYPE_META_OUTPUT) enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, -- cgit From 50656bad786d001b294764e9f047c5d5b3e4db75 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Jan 2019 11:56:09 -0500 Subject: media: v4l2-ctrl: Add control to enable h.264 constrained intra prediction Allow to enable h.264 constrained intra prediction (macroblocks using intra prediction modes are not allowed to use residual data and decoded samples of neighboring macroblocks coded using inter prediction modes). This control directly corresponds to the constrained_intra_pred_flag field in the h.264 picture parameter set. Signed-off-by: Philipp Zabel Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 4 ++++ drivers/media/v4l2-core/v4l2-ctrls.c | 2 ++ include/uapi/linux/v4l2-controls.h | 1 + 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index af4273aa5e85..235d0c293983 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1154,6 +1154,10 @@ enum v4l2_mpeg_video_h264_entropy_mode - ``V4L2_CID_MPEG_VIDEO_H264_8X8_TRANSFORM (boolean)`` Enable 8X8 transform for H264. Applicable to the H264 encoder. +``V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION (boolean)`` + Enable constrained intra prediction for H264. Applicable to the H264 + encoder. + ``V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB (integer)`` Cyclic intra macroblock refresh. This is the number of continuous macroblocks refreshed every frame. Each frame a successive set of diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 8c47d8f00429..50b56185c02e 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -825,6 +825,8 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER:return "H264 Number of HC Layers"; case V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER_QP: return "H264 Set QP Value for HC Layers"; + case V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION: + return "H264 Constrained Intra Pred"; case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP: return "MPEG4 I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP: return "MPEG4 P-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP: return "MPEG4 B-Frame QP Value"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 3dcfc6148f99..fd65c710b144 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -533,6 +533,7 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type { }; #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER (V4L2_CID_MPEG_BASE+381) #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER_QP (V4L2_CID_MPEG_BASE+382) +#define V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION (V4L2_CID_MPEG_BASE+383) #define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_MPEG_BASE+400) #define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_MPEG_BASE+401) #define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_MPEG_BASE+402) -- cgit From d034696cbe5a6e00f76ca4b7869c6cdef66aebd5 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Jan 2019 11:56:10 -0500 Subject: media: v4l2-ctrl: Add control for h.264 chroma qp offset Allow to add fixed quantization parameter offset between luma and chroma quantization parameters. This control directly corresponds to the chroma_qp_index_offset field of the h.264 picture parameter set. Signed-off-by: Philipp Zabel Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 5 +++++ drivers/media/v4l2-core/v4l2-ctrls.c | 1 + include/uapi/linux/v4l2-controls.h | 1 + 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index 235d0c293983..00934efdc9e4 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1158,6 +1158,11 @@ enum v4l2_mpeg_video_h264_entropy_mode - Enable constrained intra prediction for H264. Applicable to the H264 encoder. +``V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET (integer)`` + Specify the offset that should be added to the luma quantization + parameter to determine the chroma quantization parameter. Applicable + to the H264 encoder. + ``V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB (integer)`` Cyclic intra macroblock refresh. This is the number of continuous macroblocks refreshed every frame. Each frame a successive set of diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 50b56185c02e..99308dac2daa 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -827,6 +827,7 @@ const char *v4l2_ctrl_get_name(u32 id) return "H264 Set QP Value for HC Layers"; case V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION: return "H264 Constrained Intra Pred"; + case V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET: return "H264 Chroma QP Index Offset"; case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP: return "MPEG4 I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP: return "MPEG4 P-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP: return "MPEG4 B-Frame QP Value"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index fd65c710b144..06479f2fb3ae 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -534,6 +534,7 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type { #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER (V4L2_CID_MPEG_BASE+381) #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER_QP (V4L2_CID_MPEG_BASE+382) #define V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION (V4L2_CID_MPEG_BASE+383) +#define V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET (V4L2_CID_MPEG_BASE+384) #define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_MPEG_BASE+400) #define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_MPEG_BASE+401) #define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_MPEG_BASE+402) -- cgit From 1c3721b1f22286033abeda30b7e12439b083ed0f Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Wed, 9 Jan 2019 13:30:04 -0500 Subject: media: videodev2.h: Add more field helper macros Adds two helper macros: V4L2_FIELD_IS_SEQUENTIAL: returns true if the given field type is 'sequential', that is a full frame is transmitted, or exists in memory, as all top field lines followed by all bottom field lines, or vice-versa. V4L2_FIELD_IS_INTERLACED: returns true if the given field type is 'interlaced', that is a full frame is transmitted, or exists in memory, as top field lines interlaced with bottom field lines. Signed-off-by: Steve Longerbeam Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c0c36c165bf4..9a920f071ff9 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -130,6 +130,13 @@ enum v4l2_field { ((field) == V4L2_FIELD_BOTTOM ||\ (field) == V4L2_FIELD_TOP ||\ (field) == V4L2_FIELD_ALTERNATE) +#define V4L2_FIELD_IS_INTERLACED(field) \ + ((field) == V4L2_FIELD_INTERLACED ||\ + (field) == V4L2_FIELD_INTERLACED_TB ||\ + (field) == V4L2_FIELD_INTERLACED_BT) +#define V4L2_FIELD_IS_SEQUENTIAL(field) \ + ((field) == V4L2_FIELD_SEQ_TB ||\ + (field) == V4L2_FIELD_SEQ_BT) enum v4l2_buf_type { V4L2_BUF_TYPE_VIDEO_CAPTURE = 1, -- cgit From ad07c8ceb6631a83b62d405a61448bba92adac68 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Thu, 10 Jan 2019 13:53:34 +0000 Subject: perf/core: Remove unused perf_flags Now that perf_flags is not used we remove it. Signed-off-by: Andrew Murray Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Mark Rutland Cc: Matt Turner Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Richard Henderson Cc: Russell King Cc: Sascha Hauer Cc: Shawn Guo Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: robin.murphy@arm.com Cc: suzuki.poulose@arm.com Link: https://lkml.kernel.org/r/1547128414-50693-13-git-send-email-andrew.murray@arm.com Signed-off-by: Ingo Molnar --- include/uapi/linux/perf_event.h | 2 -- tools/include/uapi/linux/perf_event.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 9de8780ac8d9..ea19b5d491bf 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -445,8 +445,6 @@ struct perf_event_query_bpf { __u32 ids[0]; }; -#define perf_flags(attr) (*(&(attr)->read_format + 1)) - /* * Ioctls that can be done on a perf event fd: */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 9de8780ac8d9..ea19b5d491bf 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -445,8 +445,6 @@ struct perf_event_query_bpf { __u32 ids[0]; }; -#define perf_flags(attr) (*(&(attr)->read_format + 1)) - /* * Ioctls that can be done on a perf event fd: */ -- cgit From 76193a94522f1d4edf2447a536f3f796ce56343b Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 17 Jan 2019 08:15:13 -0800 Subject: perf, bpf: Introduce PERF_RECORD_KSYMBOL For better performance analysis of dynamically JITed and loaded kernel functions, such as BPF programs, this patch introduces PERF_RECORD_KSYMBOL, a new perf_event_type that exposes kernel symbol register/unregister information to user space. The following data structure is used for PERF_RECORD_KSYMBOL. /* * struct { * struct perf_event_header header; * u64 addr; * u32 len; * u16 ksym_type; * u16 flags; * char name[]; * struct sample_id sample_id; * }; */ Signed-off-by: Song Liu Reviewed-by: Arnaldo Carvalho de Melo Tested-by: Arnaldo Carvalho de Melo Acked-by: Peter Zijlstra Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Peter Zijlstra Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-2-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 8 ++++ include/uapi/linux/perf_event.h | 26 ++++++++++- kernel/events/core.c | 98 ++++++++++++++++++++++++++++++++++++++++- 3 files changed, 130 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4eb88065a9b5..136fe0495374 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1122,6 +1122,10 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, } extern void perf_event_mmap(struct vm_area_struct *vma); + +extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, + bool unregister, const char *sym); + extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); @@ -1342,6 +1346,10 @@ static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } + +typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); +static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, + bool unregister, const char *sym) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index ea19b5d491bf..1dee5c8f166b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -372,7 +372,8 @@ struct perf_event_attr { context_switch : 1, /* context switch data */ write_backward : 1, /* Write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ - __reserved_1 : 35; + ksymbol : 1, /* include ksymbol events */ + __reserved_1 : 34; union { __u32 wakeup_events; /* wakeup every n events */ @@ -963,9 +964,32 @@ enum perf_event_type { */ PERF_RECORD_NAMESPACES = 16, + /* + * Record ksymbol register/unregister events: + * + * struct { + * struct perf_event_header header; + * u64 addr; + * u32 len; + * u16 ksym_type; + * u16 flags; + * char name[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_KSYMBOL = 17, + PERF_RECORD_MAX, /* non-ABI */ }; +enum perf_record_ksymbol_type { + PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0, + PERF_RECORD_KSYMBOL_TYPE_BPF = 1, + PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */ +}; + +#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) + #define PERF_MAX_STACK_DEPTH 127 #define PERF_MAX_CONTEXTS_PER_STACK 8 diff --git a/kernel/events/core.c b/kernel/events/core.c index bc525cd1615c..e04ab5f325cf 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -385,6 +385,7 @@ static atomic_t nr_namespaces_events __read_mostly; static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; static atomic_t nr_switch_events __read_mostly; +static atomic_t nr_ksymbol_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); @@ -4235,7 +4236,7 @@ static bool is_sb_event(struct perf_event *event) if (attr->mmap || attr->mmap_data || attr->mmap2 || attr->comm || attr->comm_exec || - attr->task || + attr->task || attr->ksymbol || attr->context_switch) return true; return false; @@ -4305,6 +4306,8 @@ static void unaccount_event(struct perf_event *event) dec = true; if (has_branch_stack(event)) dec = true; + if (event->attr.ksymbol) + atomic_dec(&nr_ksymbol_events); if (dec) { if (!atomic_add_unless(&perf_sched_count, -1, 1)) @@ -7653,6 +7656,97 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_output_end(&handle); } +/* + * ksymbol register/unregister tracking + */ + +struct perf_ksymbol_event { + const char *name; + int name_len; + struct { + struct perf_event_header header; + u64 addr; + u32 len; + u16 ksym_type; + u16 flags; + } event_id; +}; + +static int perf_event_ksymbol_match(struct perf_event *event) +{ + return event->attr.ksymbol; +} + +static void perf_event_ksymbol_output(struct perf_event *event, void *data) +{ + struct perf_ksymbol_event *ksymbol_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + if (!perf_event_ksymbol_match(event)) + return; + + perf_event_header__init_id(&ksymbol_event->event_id.header, + &sample, event); + ret = perf_output_begin(&handle, event, + ksymbol_event->event_id.header.size); + if (ret) + return; + + perf_output_put(&handle, ksymbol_event->event_id); + __output_copy(&handle, ksymbol_event->name, ksymbol_event->name_len); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, + const char *sym) +{ + struct perf_ksymbol_event ksymbol_event; + char name[KSYM_NAME_LEN]; + u16 flags = 0; + int name_len; + + if (!atomic_read(&nr_ksymbol_events)) + return; + + if (ksym_type >= PERF_RECORD_KSYMBOL_TYPE_MAX || + ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN) + goto err; + + strlcpy(name, sym, KSYM_NAME_LEN); + name_len = strlen(name) + 1; + while (!IS_ALIGNED(name_len, sizeof(u64))) + name[name_len++] = '\0'; + BUILD_BUG_ON(KSYM_NAME_LEN % sizeof(u64)); + + if (unregister) + flags |= PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER; + + ksymbol_event = (struct perf_ksymbol_event){ + .name = name, + .name_len = name_len, + .event_id = { + .header = { + .type = PERF_RECORD_KSYMBOL, + .size = sizeof(ksymbol_event.event_id) + + name_len, + }, + .addr = addr, + .len = len, + .ksym_type = ksym_type, + .flags = flags, + }, + }; + + perf_iterate_sb(perf_event_ksymbol_output, &ksymbol_event, NULL); + return; +err: + WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type); +} + void perf_event_itrace_started(struct perf_event *event) { event->attach_state |= PERF_ATTACH_ITRACE; @@ -9912,6 +10006,8 @@ static void account_event(struct perf_event *event) inc = true; if (is_cgroup_event(event)) inc = true; + if (event->attr.ksymbol) + atomic_inc(&nr_ksymbol_events); if (inc) { /* -- cgit From 6ee52e2a3fe4ea35520720736e6791df1fb67106 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 17 Jan 2019 08:15:15 -0800 Subject: perf, bpf: Introduce PERF_RECORD_BPF_EVENT For better performance analysis of BPF programs, this patch introduces PERF_RECORD_BPF_EVENT, a new perf_event_type that exposes BPF program load/unload information to user space. Each BPF program may contain up to BPF_MAX_SUBPROGS (256) sub programs. The following example shows kernel symbols for a BPF program with 7 sub programs: ffffffffa0257cf9 t bpf_prog_b07ccb89267cf242_F ffffffffa02592e1 t bpf_prog_2dcecc18072623fc_F ffffffffa025b0e9 t bpf_prog_bb7a405ebaec5d5c_F ffffffffa025dd2c t bpf_prog_a7540d4a39ec1fc7_F ffffffffa025fcca t bpf_prog_05762d4ade0e3737_F ffffffffa026108f t bpf_prog_db4bd11e35df90d4_F ffffffffa0263f00 t bpf_prog_89d64e4abf0f0126_F ffffffffa0257cf9 t bpf_prog_ae31629322c4b018__dummy_tracepoi When a bpf program is loaded, PERF_RECORD_KSYMBOL is generated for each of these sub programs. Therefore, PERF_RECORD_BPF_EVENT is not needed for simple profiling. For annotation, user space need to listen to PERF_RECORD_BPF_EVENT and gather more information about these (sub) programs via sys_bpf. Signed-off-by: Song Liu Reviewed-by: Arnaldo Carvalho de Melo Acked-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Tested-by: Arnaldo Carvalho de Melo Cc: Daniel Borkmann Cc: Peter Zijlstra Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-4-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/filter.h | 7 +++ include/linux/perf_event.h | 6 +++ include/uapi/linux/perf_event.h | 29 +++++++++- kernel/bpf/core.c | 2 +- kernel/bpf/syscall.c | 2 + kernel/events/core.c | 115 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 159 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..d531d4250bff 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -951,6 +951,7 @@ bpf_address_lookup(unsigned long addr, unsigned long *size, void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); +void bpf_get_prog_name(const struct bpf_prog *prog, char *sym); #else /* CONFIG_BPF_JIT */ @@ -1006,6 +1007,12 @@ static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } + +static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) +{ + sym[0] = '\0'; +} + #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 136fe0495374..a79e59fc3b7d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1125,6 +1125,9 @@ extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); +extern void perf_event_bpf_event(struct bpf_prog *prog, + enum perf_bpf_event_type type, + u16 flags); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); @@ -1350,6 +1353,9 @@ static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } +static inline void perf_event_bpf_event(struct bpf_prog *prog, + enum perf_bpf_event_type type, + u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1dee5c8f166b..7198ddd0c6b1 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -373,7 +373,8 @@ struct perf_event_attr { write_backward : 1, /* Write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ - __reserved_1 : 34; + bpf_event : 1, /* include bpf events */ + __reserved_1 : 33; union { __u32 wakeup_events; /* wakeup every n events */ @@ -979,6 +980,25 @@ enum perf_event_type { */ PERF_RECORD_KSYMBOL = 17, + /* + * Record bpf events: + * enum perf_bpf_event_type { + * PERF_BPF_EVENT_UNKNOWN = 0, + * PERF_BPF_EVENT_PROG_LOAD = 1, + * PERF_BPF_EVENT_PROG_UNLOAD = 2, + * }; + * + * struct { + * struct perf_event_header header; + * u16 type; + * u16 flags; + * u32 id; + * u8 tag[BPF_TAG_SIZE]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_BPF_EVENT = 18, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -990,6 +1010,13 @@ enum perf_record_ksymbol_type { #define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) +enum perf_bpf_event_type { + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ +}; + #define PERF_MAX_STACK_DEPTH 127 #define PERF_MAX_CONTEXTS_PER_STACK 8 diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index f908b9356025..19c49313c709 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -495,7 +495,7 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, *symbol_end = addr + hdr->pages * PAGE_SIZE; } -static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) +void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..30ebd085790b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1211,6 +1211,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del_all(prog); @@ -1554,6 +1555,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) } bpf_prog_kallsyms_add(prog); + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); return err; free_used_maps: diff --git a/kernel/events/core.c b/kernel/events/core.c index e04ab5f325cf..236bb8ddb7bc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -386,6 +386,7 @@ static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; static atomic_t nr_switch_events __read_mostly; static atomic_t nr_ksymbol_events __read_mostly; +static atomic_t nr_bpf_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); @@ -4308,6 +4309,8 @@ static void unaccount_event(struct perf_event *event) dec = true; if (event->attr.ksymbol) atomic_dec(&nr_ksymbol_events); + if (event->attr.bpf_event) + atomic_dec(&nr_bpf_events); if (dec) { if (!atomic_add_unless(&perf_sched_count, -1, 1)) @@ -7747,6 +7750,116 @@ err: WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type); } +/* + * bpf program load/unload tracking + */ + +struct perf_bpf_event { + struct bpf_prog *prog; + struct { + struct perf_event_header header; + u16 type; + u16 flags; + u32 id; + u8 tag[BPF_TAG_SIZE]; + } event_id; +}; + +static int perf_event_bpf_match(struct perf_event *event) +{ + return event->attr.bpf_event; +} + +static void perf_event_bpf_output(struct perf_event *event, void *data) +{ + struct perf_bpf_event *bpf_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + if (!perf_event_bpf_match(event)) + return; + + perf_event_header__init_id(&bpf_event->event_id.header, + &sample, event); + ret = perf_output_begin(&handle, event, + bpf_event->event_id.header.size); + if (ret) + return; + + perf_output_put(&handle, bpf_event->event_id); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, + enum perf_bpf_event_type type) +{ + bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD; + char sym[KSYM_NAME_LEN]; + int i; + + if (prog->aux->func_cnt == 0) { + bpf_get_prog_name(prog, sym); + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, + (u64)(unsigned long)prog->bpf_func, + prog->jited_len, unregister, sym); + } else { + for (i = 0; i < prog->aux->func_cnt; i++) { + struct bpf_prog *subprog = prog->aux->func[i]; + + bpf_get_prog_name(subprog, sym); + perf_event_ksymbol( + PERF_RECORD_KSYMBOL_TYPE_BPF, + (u64)(unsigned long)subprog->bpf_func, + subprog->jited_len, unregister, sym); + } + } +} + +void perf_event_bpf_event(struct bpf_prog *prog, + enum perf_bpf_event_type type, + u16 flags) +{ + struct perf_bpf_event bpf_event; + + if (type <= PERF_BPF_EVENT_UNKNOWN || + type >= PERF_BPF_EVENT_MAX) + return; + + switch (type) { + case PERF_BPF_EVENT_PROG_LOAD: + case PERF_BPF_EVENT_PROG_UNLOAD: + if (atomic_read(&nr_ksymbol_events)) + perf_event_bpf_emit_ksymbols(prog, type); + break; + default: + break; + } + + if (!atomic_read(&nr_bpf_events)) + return; + + bpf_event = (struct perf_bpf_event){ + .prog = prog, + .event_id = { + .header = { + .type = PERF_RECORD_BPF_EVENT, + .size = sizeof(bpf_event.event_id), + }, + .type = type, + .flags = flags, + .id = prog->aux->id, + }, + }; + + BUILD_BUG_ON(BPF_TAG_SIZE % sizeof(u64)); + + memcpy(bpf_event.event_id.tag, prog->tag, BPF_TAG_SIZE); + perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL); +} + void perf_event_itrace_started(struct perf_event *event) { event->attach_state |= PERF_ATTACH_ITRACE; @@ -10008,6 +10121,8 @@ static void account_event(struct perf_event *event) inc = true; if (event->attr.ksymbol) atomic_inc(&nr_ksymbol_events); + if (event->attr.bpf_event) + atomic_inc(&nr_bpf_events); if (inc) { /* -- cgit From aefcb7460e0b5f35f72601b7a98eec5ca1639cf2 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: m68k/mac: Fix PRAM accessors PMU-based m68k Macs pre-date PowerMac-style NVRAM. Use the appropriate PMU commands. Also implement the missing XPRAM accessors for VIA-based Macs. Acked-by: Geert Uytterhoeven Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- arch/m68k/mac/misc.c | 43 +++++++++++++++++++++++++++++++++---------- include/uapi/linux/pmu.h | 2 ++ 2 files changed, 35 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index af000a015f68..d016ca2e0d10 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -66,23 +66,22 @@ static unsigned char pmu_pram_read_byte(int offset) { struct adb_request req; - if (pmu_request(&req, NULL, 3, PMU_READ_NVRAM, - (offset >> 8) & 0xFF, offset & 0xFF) < 0) + if (pmu_request(&req, NULL, 3, PMU_READ_XPRAM, + offset & 0xFF, 1) < 0) return 0; - while (!req.complete) - pmu_poll(); - return req.reply[3]; + pmu_wait_complete(&req); + + return req.reply[0]; } static void pmu_pram_write_byte(unsigned char data, int offset) { struct adb_request req; - if (pmu_request(&req, NULL, 4, PMU_WRITE_NVRAM, - (offset >> 8) & 0xFF, offset & 0xFF, data) < 0) + if (pmu_request(&req, NULL, 4, PMU_WRITE_XPRAM, + offset & 0xFF, 1, data) < 0) return; - while (!req.complete) - pmu_poll(); + pmu_wait_complete(&req); } #endif /* CONFIG_ADB_PMU */ @@ -151,6 +150,16 @@ static void via_rtc_send(__u8 data) #define RTC_REG_SECONDS_3 3 #define RTC_REG_WRITE_PROTECT 13 +/* + * Inside Mac has no information about two-byte RTC commands but + * the MAME/MESS source code has the essentials. + */ + +#define RTC_REG_XPRAM 14 +#define RTC_CMD_XPRAM_READ (RTC_CMD_READ(RTC_REG_XPRAM) << 8) +#define RTC_CMD_XPRAM_WRITE (RTC_CMD_WRITE(RTC_REG_XPRAM) << 8) +#define RTC_CMD_XPRAM_ARG(a) (((a & 0xE0) << 3) | ((a & 0x1F) << 2)) + /* * Execute a VIA PRAM/RTC command. For read commands * data should point to a one-byte buffer for the @@ -198,11 +207,25 @@ static void via_rtc_command(int command, __u8 *data) static unsigned char via_pram_read_byte(int offset) { - return 0; + unsigned char temp; + + via_rtc_command(RTC_CMD_XPRAM_READ | RTC_CMD_XPRAM_ARG(offset), &temp); + + return temp; } static void via_pram_write_byte(unsigned char data, int offset) { + unsigned char temp; + + temp = 0x55; + via_rtc_command(RTC_CMD_WRITE(RTC_REG_WRITE_PROTECT), &temp); + + temp = data; + via_rtc_command(RTC_CMD_XPRAM_WRITE | RTC_CMD_XPRAM_ARG(offset), &temp); + + temp = 0x55 | RTC_FLG_WRITE_PROTECT; + via_rtc_command(RTC_CMD_WRITE(RTC_REG_WRITE_PROTECT), &temp); } /* diff --git a/include/uapi/linux/pmu.h b/include/uapi/linux/pmu.h index 97256f90e6df..f2fc1bd80017 100644 --- a/include/uapi/linux/pmu.h +++ b/include/uapi/linux/pmu.h @@ -19,7 +19,9 @@ #define PMU_POWER_CTRL 0x11 /* control power of some devices */ #define PMU_ADB_CMD 0x20 /* send ADB packet */ #define PMU_ADB_POLL_OFF 0x21 /* disable ADB auto-poll */ +#define PMU_WRITE_XPRAM 0x32 /* write eXtended Parameter RAM */ #define PMU_WRITE_NVRAM 0x33 /* write non-volatile RAM */ +#define PMU_READ_XPRAM 0x3a /* read eXtended Parameter RAM */ #define PMU_READ_NVRAM 0x3b /* read non-volatile RAM */ #define PMU_SET_RTC 0x30 /* set real-time clock */ #define PMU_READ_RTC 0x38 /* read real-time clock */ -- cgit From ec74136ded792deed80780a2f8baf3521eeb72f9 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Mon, 14 Jan 2019 09:10:21 -0800 Subject: binder: create node flag to request sender's security context To allow servers to verify client identity, allow a node flag to be set that causes the sender's security context to be delivered with the transaction. The BR_TRANSACTION command is extended in BR_TRANSACTION_SEC_CTX to contain a pointer to the security context string. Signed-off-by: Todd Kjos Reviewed-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 106 ++++++++++++++++++++++++++++-------- include/uapi/linux/android/binder.h | 19 +++++++ 2 files changed, 102 insertions(+), 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index cdfc87629efb..5f6ef5e63b91 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -329,6 +329,8 @@ struct binder_error { * (invariant after initialized) * @min_priority: minimum scheduling priority * (invariant after initialized) + * @txn_security_ctx: require sender's security context + * (invariant after initialized) * @async_todo: list of async work items * (protected by @proc->inner_lock) * @@ -365,6 +367,7 @@ struct binder_node { * invariant after initialization */ u8 accept_fds:1; + u8 txn_security_ctx:1; u8 min_priority; }; bool has_async_transaction; @@ -615,6 +618,7 @@ struct binder_transaction { long saved_priority; kuid_t sender_euid; struct list_head fd_fixups; + binder_uintptr_t security_ctx; /** * @lock: protects @from, @to_proc, and @to_thread * @@ -1152,6 +1156,7 @@ static struct binder_node *binder_init_node_ilocked( node->work.type = BINDER_WORK_NODE; node->min_priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK; node->accept_fds = !!(flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); + node->txn_security_ctx = !!(flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX); spin_lock_init(&node->lock); INIT_LIST_HEAD(&node->work.entry); INIT_LIST_HEAD(&node->async_todo); @@ -2778,6 +2783,8 @@ static void binder_transaction(struct binder_proc *proc, binder_size_t last_fixup_min_off = 0; struct binder_context *context = proc->context; int t_debug_id = atomic_inc_return(&binder_last_id); + char *secctx = NULL; + u32 secctx_sz = 0; e = binder_transaction_log_add(&binder_transaction_log); e->debug_id = t_debug_id; @@ -3020,6 +3027,20 @@ static void binder_transaction(struct binder_proc *proc, t->flags = tr->flags; t->priority = task_nice(current); + if (target_node && target_node->txn_security_ctx) { + u32 secid; + + security_task_getsecid(proc->tsk, &secid); + ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); + if (ret) { + return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; + goto err_get_secctx_failed; + } + extra_buffers_size += ALIGN(secctx_sz, sizeof(u64)); + } + trace_binder_transaction(reply, t, target_node); t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size, @@ -3036,6 +3057,19 @@ static void binder_transaction(struct binder_proc *proc, t->buffer = NULL; goto err_binder_alloc_buf_failed; } + if (secctx) { + size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) + + ALIGN(tr->offsets_size, sizeof(void *)) + + ALIGN(extra_buffers_size, sizeof(void *)) - + ALIGN(secctx_sz, sizeof(u64)); + char *kptr = t->buffer->data + buf_offset; + + t->security_ctx = (uintptr_t)kptr + + binder_alloc_get_user_buffer_offset(&target_proc->alloc); + memcpy(kptr, secctx, secctx_sz); + security_release_secctx(secctx, secctx_sz); + secctx = NULL; + } t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; t->buffer->target_node = target_node; @@ -3305,6 +3339,9 @@ err_copy_data_failed: t->buffer->transaction = NULL; binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: + if (secctx) + security_release_secctx(secctx, secctx_sz); +err_get_secctx_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); err_alloc_tcomplete_failed: @@ -4036,11 +4073,13 @@ retry: while (1) { uint32_t cmd; - struct binder_transaction_data tr; + struct binder_transaction_data_secctx tr; + struct binder_transaction_data *trd = &tr.transaction_data; struct binder_work *w = NULL; struct list_head *list = NULL; struct binder_transaction *t = NULL; struct binder_thread *t_from; + size_t trsize = sizeof(*trd); binder_inner_proc_lock(proc); if (!binder_worklist_empty_ilocked(&thread->todo)) @@ -4240,8 +4279,8 @@ retry: if (t->buffer->target_node) { struct binder_node *target_node = t->buffer->target_node; - tr.target.ptr = target_node->ptr; - tr.cookie = target_node->cookie; + trd->target.ptr = target_node->ptr; + trd->cookie = target_node->cookie; t->saved_priority = task_nice(current); if (t->priority < target_node->min_priority && !(t->flags & TF_ONE_WAY)) @@ -4251,22 +4290,23 @@ retry: binder_set_nice(target_node->min_priority); cmd = BR_TRANSACTION; } else { - tr.target.ptr = 0; - tr.cookie = 0; + trd->target.ptr = 0; + trd->cookie = 0; cmd = BR_REPLY; } - tr.code = t->code; - tr.flags = t->flags; - tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid); + trd->code = t->code; + trd->flags = t->flags; + trd->sender_euid = from_kuid(current_user_ns(), t->sender_euid); t_from = binder_get_txn_from(t); if (t_from) { struct task_struct *sender = t_from->proc->tsk; - tr.sender_pid = task_tgid_nr_ns(sender, - task_active_pid_ns(current)); + trd->sender_pid = + task_tgid_nr_ns(sender, + task_active_pid_ns(current)); } else { - tr.sender_pid = 0; + trd->sender_pid = 0; } ret = binder_apply_fd_fixups(t); @@ -4297,15 +4337,20 @@ retry: } continue; } - tr.data_size = t->buffer->data_size; - tr.offsets_size = t->buffer->offsets_size; - tr.data.ptr.buffer = (binder_uintptr_t) + trd->data_size = t->buffer->data_size; + trd->offsets_size = t->buffer->offsets_size; + trd->data.ptr.buffer = (binder_uintptr_t) ((uintptr_t)t->buffer->data + binder_alloc_get_user_buffer_offset(&proc->alloc)); - tr.data.ptr.offsets = tr.data.ptr.buffer + + trd->data.ptr.offsets = trd->data.ptr.buffer + ALIGN(t->buffer->data_size, sizeof(void *)); + tr.secctx = t->security_ctx; + if (t->security_ctx) { + cmd = BR_TRANSACTION_SEC_CTX; + trsize = sizeof(tr); + } if (put_user(cmd, (uint32_t __user *)ptr)) { if (t_from) binder_thread_dec_tmpref(t_from); @@ -4316,7 +4361,7 @@ retry: return -EFAULT; } ptr += sizeof(uint32_t); - if (copy_to_user(ptr, &tr, sizeof(tr))) { + if (copy_to_user(ptr, &tr, trsize)) { if (t_from) binder_thread_dec_tmpref(t_from); @@ -4325,7 +4370,7 @@ retry: return -EFAULT; } - ptr += sizeof(tr); + ptr += trsize; trace_binder_transaction_received(t); binder_stat_br(proc, thread, cmd); @@ -4333,16 +4378,18 @@ retry: "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n", proc->pid, thread->pid, (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" : - "BR_REPLY", + (cmd == BR_TRANSACTION_SEC_CTX) ? + "BR_TRANSACTION_SEC_CTX" : "BR_REPLY", t->debug_id, t_from ? t_from->proc->pid : 0, t_from ? t_from->pid : 0, cmd, t->buffer->data_size, t->buffer->offsets_size, - (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets); + (u64)trd->data.ptr.buffer, + (u64)trd->data.ptr.offsets); if (t_from) binder_thread_dec_tmpref(t_from); t->buffer->allow_user_free = 1; - if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) { + if (cmd != BR_REPLY && !(t->flags & TF_ONE_WAY)) { binder_inner_proc_lock(thread->proc); t->to_parent = thread->transaction_stack; t->to_thread = thread; @@ -4690,7 +4737,8 @@ out: return ret; } -static int binder_ioctl_set_ctx_mgr(struct file *filp) +static int binder_ioctl_set_ctx_mgr(struct file *filp, + struct flat_binder_object *fbo) { int ret = 0; struct binder_proc *proc = filp->private_data; @@ -4719,7 +4767,7 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp) } else { context->binder_context_mgr_uid = curr_euid; } - new_node = binder_new_node(proc, NULL); + new_node = binder_new_node(proc, fbo); if (!new_node) { ret = -ENOMEM; goto out; @@ -4842,8 +4890,20 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) binder_inner_proc_unlock(proc); break; } + case BINDER_SET_CONTEXT_MGR_EXT: { + struct flat_binder_object fbo; + + if (copy_from_user(&fbo, ubuf, sizeof(fbo))) { + ret = -EINVAL; + goto err; + } + ret = binder_ioctl_set_ctx_mgr(filp, &fbo); + if (ret) + goto err; + break; + } case BINDER_SET_CONTEXT_MGR: - ret = binder_ioctl_set_ctx_mgr(filp); + ret = binder_ioctl_set_ctx_mgr(filp, NULL); if (ret) goto err; break; diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index b9ba520f7e4b..2832134e5397 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -41,6 +41,14 @@ enum { enum { FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff, FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100, + + /** + * @FLAT_BINDER_FLAG_TXN_SECURITY_CTX: request security contexts + * + * Only when set, causes senders to include their security + * context + */ + FLAT_BINDER_FLAG_TXN_SECURITY_CTX = 0x1000, }; #ifdef BINDER_IPC_32BIT @@ -218,6 +226,7 @@ struct binder_node_info_for_ref { #define BINDER_VERSION _IOWR('b', 9, struct binder_version) #define BINDER_GET_NODE_DEBUG_INFO _IOWR('b', 11, struct binder_node_debug_info) #define BINDER_GET_NODE_INFO_FOR_REF _IOWR('b', 12, struct binder_node_info_for_ref) +#define BINDER_SET_CONTEXT_MGR_EXT _IOW('b', 13, struct flat_binder_object) /* * NOTE: Two special error codes you should check for when calling @@ -276,6 +285,11 @@ struct binder_transaction_data { } data; }; +struct binder_transaction_data_secctx { + struct binder_transaction_data transaction_data; + binder_uintptr_t secctx; +}; + struct binder_transaction_data_sg { struct binder_transaction_data transaction_data; binder_size_t buffers_size; @@ -311,6 +325,11 @@ enum binder_driver_return_protocol { BR_OK = _IO('r', 1), /* No parameters! */ + BR_TRANSACTION_SEC_CTX = _IOR('r', 2, + struct binder_transaction_data_secctx), + /* + * binder_transaction_data_secctx: the received command. + */ BR_TRANSACTION = _IOR('r', 2, struct binder_transaction_data), BR_REPLY = _IOR('r', 3, struct binder_transaction_data), /* -- cgit From 71368af9027f18fe5d1c6f372cfdff7e4bde8b48 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 16 Jan 2019 17:01:36 -0500 Subject: x86/speculation: Add PR_SPEC_DISABLE_NOEXEC With the default SPEC_STORE_BYPASS_SECCOMP/SPEC_STORE_BYPASS_PRCTL mode, the TIF_SSBD bit will be inherited when a new task is fork'ed or cloned. It will also remain when a new program is execve'ed. Only certain class of applications (like Java) that can run on behalf of multiple users on a single thread will require disabling speculative store bypass for security purposes. Those applications will call prctl(2) at startup time to disable SSB. They won't rely on the fact the SSB might have been disabled. Other applications that don't need SSBD will just move on without checking if SSBD has been turned on or not. The fact that the TIF_SSBD is inherited across execve(2) boundary will cause performance of applications that don't need SSBD but their predecessors have SSBD on to be unwittingly impacted especially if they write to memory a lot. To remedy this problem, a new PR_SPEC_DISABLE_NOEXEC argument for the PR_SET_SPECULATION_CTRL option of prctl(2) is added to allow applications to specify that the SSBD feature bit on the task structure should be cleared whenever a new program is being execve'ed. Suggested-by: Thomas Gleixner Signed-off-by: Waiman Long Signed-off-by: Thomas Gleixner Cc: Borislav Petkov Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: David Woodhouse Cc: Jiri Kosina Cc: Josh Poimboeuf Cc: Tim Chen Cc: KarimAllah Ahmed Cc: Peter Zijlstra Cc: Konrad Rzeszutek Wilk Link: https://lkml.kernel.org/r/1547676096-3281-1-git-send-email-longman@redhat.com --- Documentation/userspace-api/spec_ctrl.rst | 27 +++++++++++++++------------ arch/x86/kernel/cpu/bugs.c | 12 ++++++++++++ arch/x86/kernel/process.c | 12 ++++++++++++ include/linux/sched.h | 5 +++++ include/uapi/linux/prctl.h | 1 + tools/include/uapi/linux/prctl.h | 1 + 6 files changed, 46 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index c4dbe6f7cdae..1129c7550a48 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -28,18 +28,20 @@ PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature which is selected with arg2 of prctl(2). The return value uses bits 0-3 with the following meaning: -==== ===================== =================================================== -Bit Define Description -==== ===================== =================================================== -0 PR_SPEC_PRCTL Mitigation can be controlled per task by - PR_SET_SPECULATION_CTRL. -1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is - disabled. -2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is - enabled. -3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A - subsequent prctl(..., PR_SPEC_ENABLE) will fail. -==== ===================== =================================================== +==== ====================== ================================================== +Bit Define Description +==== ====================== ================================================== +0 PR_SPEC_PRCTL Mitigation can be controlled per task by + PR_SET_SPECULATION_CTRL. +1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is + disabled. +2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is + enabled. +3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A + subsequent prctl(..., PR_SPEC_ENABLE) will fail. +4 PR_SPEC_DISABLE_NOEXEC Same as PR_SPEC_DISABLE, but the state will be + cleared on :manpage:`execve(2)`. +==== ====================== ================================================== If all bits are 0 the CPU is not affected by the speculation misfeature. @@ -92,6 +94,7 @@ Speculation misfeature controls * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE_NOEXEC, 0, 0); - PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes (Mitigate Spectre V2 style attacks against user processes) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1de0f4170178..2faeaf46347a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -798,15 +798,25 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) if (task_spec_ssb_force_disable(task)) return -EPERM; task_clear_spec_ssb_disable(task); + task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_DISABLE: task_set_spec_ssb_disable(task); + task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_FORCE_DISABLE: task_set_spec_ssb_disable(task); task_set_spec_ssb_force_disable(task); + task_clear_spec_ssb_noexec(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE_NOEXEC: + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_set_spec_ssb_disable(task); + task_set_spec_ssb_noexec(task); task_update_spec_tif(task); break; default: @@ -885,6 +895,8 @@ static int ssb_prctl_get(struct task_struct *task) case SPEC_STORE_BYPASS_PRCTL: if (task_spec_ssb_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_noexec(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC; if (task_spec_ssb_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 90ae0ca51083..58ac7be52c7a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -255,6 +255,18 @@ void arch_setup_new_exec(void) /* If cpuid was previously disabled for this task, re-enable it. */ if (test_thread_flag(TIF_NOCPUID)) enable_cpuid(); + + /* + * Don't inherit TIF_SSBD across exec boundary when + * PR_SPEC_DISABLE_NOEXEC is used. + */ + if (test_thread_flag(TIF_SSBD) && + task_spec_ssb_noexec(current)) { + clear_thread_flag(TIF_SSBD); + task_clear_spec_ssb_disable(current); + task_clear_spec_ssb_noexec(current); + speculation_ctrl_update(task_thread_info(current)->flags); + } } static inline void switch_to_bitmap(struct thread_struct *prev, diff --git a/include/linux/sched.h b/include/linux/sched.h index d2f90fa92468..fc836dc71bba 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1459,6 +1459,7 @@ static inline bool is_percpu_thread(void) #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ +#define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1487,6 +1488,10 @@ TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) +TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) +TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) + TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index b4875a93363a..094bb03b9cc2 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -219,6 +219,7 @@ struct prctl_mm_map { # define PR_SPEC_ENABLE (1UL << 1) # define PR_SPEC_DISABLE (1UL << 2) # define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) /* Reset arm64 pointer authentication keys */ #define PR_PAC_RESET_KEYS 54 diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index b4875a93363a..094bb03b9cc2 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -219,6 +219,7 @@ struct prctl_mm_map { # define PR_SPEC_ENABLE (1UL << 1) # define PR_SPEC_DISABLE (1UL << 2) # define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) /* Reset arm64 pointer authentication keys */ #define PR_PAC_RESET_KEYS 54 -- cgit From 1194c4133195dfcb6c5fc0935d54bbed872a5285 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Tue, 29 Jan 2019 00:56:17 +0000 Subject: nfit: Add Hyper-V NVDIMM DSM command set to white list Add the Hyper-V _DSM command set to the white list of NVDIMM command sets. This command set is documented at http://www.uefi.org/RFIC_LIST (see "Virtual NVDIMM 0x1901"). Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 17 ++++++++++++++--- drivers/acpi/nfit/nfit.h | 6 +++++- include/uapi/linux/ndctl.h | 1 + 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 1598e3a121a6..4a7e8b1fa43b 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1846,9 +1846,17 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, dev_set_drvdata(&adev_dimm->dev, nfit_mem); /* - * Until standardization materializes we need to consider 4 - * different command sets. Note, that checking for function0 (bit0) - * tells us if any commands are reachable through this GUID. + * There are 4 "legacy" NVDIMM command sets + * (NVDIMM_FAMILY_{INTEL,MSFT,HPE1,HPE2}) that were created before + * an EFI working group was established to constrain this + * proliferation. The nfit driver probes for the supported command + * set by GUID. Note, if you're a platform developer looking to add + * a new command set to this probe, consider using an existing set, + * or otherwise seek approval to publish the command set at + * http://www.uefi.org/RFIC_LIST. + * + * Note, that checking for function0 (bit0) tells us if any commands + * are reachable through this GUID. */ for (i = 0; i <= NVDIMM_FAMILY_MAX; i++) if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) @@ -1871,6 +1879,8 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, dsm_mask &= ~(1 << 8); } else if (nfit_mem->family == NVDIMM_FAMILY_MSFT) { dsm_mask = 0xffffffff; + } else if (nfit_mem->family == NVDIMM_FAMILY_HYPERV) { + dsm_mask = 0x1f; } else { dev_dbg(dev, "unknown dimm command family\n"); nfit_mem->family = -1; @@ -3714,6 +3724,7 @@ static __init int nfit_init(void) guid_parse(UUID_NFIT_DIMM_N_HPE1, &nfit_uuid[NFIT_DEV_DIMM_N_HPE1]); guid_parse(UUID_NFIT_DIMM_N_HPE2, &nfit_uuid[NFIT_DEV_DIMM_N_HPE2]); guid_parse(UUID_NFIT_DIMM_N_MSFT, &nfit_uuid[NFIT_DEV_DIMM_N_MSFT]); + guid_parse(UUID_NFIT_DIMM_N_HYPERV, &nfit_uuid[NFIT_DEV_DIMM_N_HYPERV]); nfit_wq = create_singlethread_workqueue("nfit"); if (!nfit_wq) diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 33691aecfcee..4de167b4f76f 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -34,11 +34,14 @@ /* https://msdn.microsoft.com/library/windows/hardware/mt604741 */ #define UUID_NFIT_DIMM_N_MSFT "1ee68b36-d4bd-4a1a-9a16-4f8e53d46e05" +/* http://www.uefi.org/RFIC_LIST (see "Virtual NVDIMM 0x1901") */ +#define UUID_NFIT_DIMM_N_HYPERV "5746c5f2-a9a2-4264-ad0e-e4ddc9e09e80" + #define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \ | ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \ | ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED) -#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_MSFT +#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV #define NVDIMM_STANDARD_CMDMASK \ (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \ @@ -94,6 +97,7 @@ enum nfit_uuids { NFIT_DEV_DIMM_N_HPE1 = NVDIMM_FAMILY_HPE1, NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2, NFIT_DEV_DIMM_N_MSFT = NVDIMM_FAMILY_MSFT, + NFIT_DEV_DIMM_N_HYPERV = NVDIMM_FAMILY_HYPERV, NFIT_SPA_VOLATILE, NFIT_SPA_PM, NFIT_SPA_DCR, diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index f57c9e434d2d..de5d90212409 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -243,6 +243,7 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_HPE1 1 #define NVDIMM_FAMILY_HPE2 2 #define NVDIMM_FAMILY_MSFT 3 +#define NVDIMM_FAMILY_HYPERV 4 #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) -- cgit From 2d908b38d40921a03225d42fd6e48eb51bffd606 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 23 Jan 2019 11:28:19 +0100 Subject: serial: Add Tegra Combined UART driver The Tegra Combined UART (TCU) is a mailbox-based mechanism that allows multiplexing multiple "virtual UARTs" into a single hardware serial port. The TCU is the primary serial port on Tegra194 devices. Add a TCU driver utilizing the mailbox framework, as the used mailboxes are part of Tegra HSP blocks that are already controlled by the Tegra HSP mailbox driver. Based on work by Mikko Perttunen . Signed-off-by: Thierry Reding Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 22 +++ drivers/tty/serial/Makefile | 1 + drivers/tty/serial/tegra-tcu.c | 298 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/serial_core.h | 3 + 4 files changed, 324 insertions(+) create mode 100644 drivers/tty/serial/tegra-tcu.c (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 089a6f285d5e..72966bc0ac76 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -335,6 +335,28 @@ config SERIAL_TEGRA are enabled). This driver uses the APB DMA to achieve higher baudrate and better performance. +config SERIAL_TEGRA_TCU + tristate "NVIDIA Tegra Combined UART" + depends on ARCH_TEGRA && TEGRA_HSP_MBOX + select SERIAL_CORE + help + Support for the mailbox-based TCU (Tegra Combined UART) serial port. + TCU is a virtual serial port that allows multiplexing multiple data + streams into a single hardware serial port. + +config SERIAL_TEGRA_TCU_CONSOLE + bool "Support for console on a Tegra TCU serial port" + depends on SERIAL_TEGRA_TCU=y + select SERIAL_CORE_CONSOLE + default y + ---help--- + If you say Y here, it will be possible to use a the Tegra TCU as the + system console (the system console is the device which receives all + kernel messages and warnings and which allows logins in single user + mode). + + If unsure, say Y. + config SERIAL_MAX3100 tristate "MAX3100 support" depends on SPI diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 1511e8a9f856..40b702aaa85e 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_SERIAL_LANTIQ) += lantiq.o obj-$(CONFIG_SERIAL_XILINX_PS_UART) += xilinx_uartps.o obj-$(CONFIG_SERIAL_SIRFSOC) += sirfsoc_uart.o obj-$(CONFIG_SERIAL_TEGRA) += serial-tegra.o +obj-$(CONFIG_SERIAL_TEGRA_TCU) += tegra-tcu.o obj-$(CONFIG_SERIAL_AR933X) += ar933x_uart.o obj-$(CONFIG_SERIAL_EFM32_UART) += efm32-uart.o obj-$(CONFIG_SERIAL_ARC) += arc_uart.o diff --git a/drivers/tty/serial/tegra-tcu.c b/drivers/tty/serial/tegra-tcu.c new file mode 100644 index 000000000000..aaf8748a6147 --- /dev/null +++ b/drivers/tty/serial/tegra-tcu.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define TCU_MBOX_BYTE(i, x) ((x) << (i * 8)) +#define TCU_MBOX_BYTE_V(x, i) (((x) >> (i * 8)) & 0xff) +#define TCU_MBOX_NUM_BYTES(x) ((x) << 24) +#define TCU_MBOX_NUM_BYTES_V(x) (((x) >> 24) & 0x3) + +struct tegra_tcu { + struct uart_driver driver; +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + struct console console; +#endif + struct uart_port port; + + struct mbox_client tx_client, rx_client; + struct mbox_chan *tx, *rx; +}; + +static unsigned int tegra_tcu_uart_tx_empty(struct uart_port *port) +{ + return TIOCSER_TEMT; +} + +static void tegra_tcu_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ +} + +static unsigned int tegra_tcu_uart_get_mctrl(struct uart_port *port) +{ + return 0; +} + +static void tegra_tcu_uart_stop_tx(struct uart_port *port) +{ +} + +static void tegra_tcu_write_one(struct tegra_tcu *tcu, u32 value, + unsigned int count) +{ + void *msg; + + value |= TCU_MBOX_NUM_BYTES(count); + msg = (void *)(unsigned long)value; + mbox_send_message(tcu->tx, msg); + mbox_flush(tcu->tx, 1000); +} + +static void tegra_tcu_write(struct tegra_tcu *tcu, const char *s, + unsigned int count) +{ + unsigned int written = 0, i = 0; + bool insert_nl = false; + u32 value = 0; + + while (i < count) { + if (insert_nl) { + value |= TCU_MBOX_BYTE(written++, '\n'); + insert_nl = false; + i++; + } else if (s[i] == '\n') { + value |= TCU_MBOX_BYTE(written++, '\r'); + insert_nl = true; + } else { + value |= TCU_MBOX_BYTE(written++, s[i++]); + } + + if (written == 3) { + tegra_tcu_write_one(tcu, value, 3); + value = written = 0; + } + } + + if (written) + tegra_tcu_write_one(tcu, value, written); +} + +static void tegra_tcu_uart_start_tx(struct uart_port *port) +{ + struct tegra_tcu *tcu = port->private_data; + struct circ_buf *xmit = &port->state->xmit; + unsigned long count; + + for (;;) { + count = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE); + if (!count) + break; + + tegra_tcu_write(tcu, &xmit->buf[xmit->tail], count); + xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1); + } + + uart_write_wakeup(port); +} + +static void tegra_tcu_uart_stop_rx(struct uart_port *port) +{ +} + +static void tegra_tcu_uart_break_ctl(struct uart_port *port, int ctl) +{ +} + +static int tegra_tcu_uart_startup(struct uart_port *port) +{ + return 0; +} + +static void tegra_tcu_uart_shutdown(struct uart_port *port) +{ +} + +static void tegra_tcu_uart_set_termios(struct uart_port *port, + struct ktermios *new, + struct ktermios *old) +{ +} + +static const struct uart_ops tegra_tcu_uart_ops = { + .tx_empty = tegra_tcu_uart_tx_empty, + .set_mctrl = tegra_tcu_uart_set_mctrl, + .get_mctrl = tegra_tcu_uart_get_mctrl, + .stop_tx = tegra_tcu_uart_stop_tx, + .start_tx = tegra_tcu_uart_start_tx, + .stop_rx = tegra_tcu_uart_stop_rx, + .break_ctl = tegra_tcu_uart_break_ctl, + .startup = tegra_tcu_uart_startup, + .shutdown = tegra_tcu_uart_shutdown, + .set_termios = tegra_tcu_uart_set_termios, +}; + +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) +static void tegra_tcu_console_write(struct console *cons, const char *s, + unsigned int count) +{ + struct tegra_tcu *tcu = container_of(cons, struct tegra_tcu, console); + + tegra_tcu_write(tcu, s, count); +} + +static int tegra_tcu_console_setup(struct console *cons, char *options) +{ + return 0; +} +#endif + +static void tegra_tcu_receive(struct mbox_client *cl, void *msg) +{ + struct tegra_tcu *tcu = container_of(cl, struct tegra_tcu, rx_client); + struct tty_port *port = &tcu->port.state->port; + u32 value = (u32)(unsigned long)msg; + unsigned int num_bytes, i; + + num_bytes = TCU_MBOX_NUM_BYTES_V(value); + + for (i = 0; i < num_bytes; i++) + tty_insert_flip_char(port, TCU_MBOX_BYTE_V(value, i), + TTY_NORMAL); + + tty_flip_buffer_push(port); +} + +static int tegra_tcu_probe(struct platform_device *pdev) +{ + struct uart_port *port; + struct tegra_tcu *tcu; + int err; + + tcu = devm_kzalloc(&pdev->dev, sizeof(*tcu), GFP_KERNEL); + if (!tcu) + return -ENOMEM; + + tcu->tx_client.dev = &pdev->dev; + tcu->rx_client.dev = &pdev->dev; + tcu->rx_client.rx_callback = tegra_tcu_receive; + + tcu->tx = mbox_request_channel_byname(&tcu->tx_client, "tx"); + if (IS_ERR(tcu->tx)) { + err = PTR_ERR(tcu->tx); + dev_err(&pdev->dev, "failed to get tx mailbox: %d\n", err); + return err; + } + + tcu->rx = mbox_request_channel_byname(&tcu->rx_client, "rx"); + if (IS_ERR(tcu->rx)) { + err = PTR_ERR(tcu->rx); + dev_err(&pdev->dev, "failed to get rx mailbox: %d\n", err); + goto free_tx; + } + +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + /* setup the console */ + strcpy(tcu->console.name, "ttyTCU"); + tcu->console.device = uart_console_device; + tcu->console.flags = CON_PRINTBUFFER | CON_ANYTIME; + tcu->console.index = -1; + tcu->console.write = tegra_tcu_console_write; + tcu->console.setup = tegra_tcu_console_setup; + tcu->console.data = &tcu->driver; +#endif + + /* setup the driver */ + tcu->driver.owner = THIS_MODULE; + tcu->driver.driver_name = "tegra-tcu"; + tcu->driver.dev_name = "ttyTCU"; +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + tcu->driver.cons = &tcu->console; +#endif + tcu->driver.nr = 1; + + err = uart_register_driver(&tcu->driver); + if (err) { + dev_err(&pdev->dev, "failed to register UART driver: %d\n", + err); + goto free_rx; + } + + /* setup the port */ + port = &tcu->port; + spin_lock_init(&port->lock); + port->dev = &pdev->dev; + port->type = PORT_TEGRA_TCU; + port->ops = &tegra_tcu_uart_ops; + port->fifosize = 1; + port->iotype = UPIO_MEM; + port->flags = UPF_BOOT_AUTOCONF; + port->private_data = tcu; + + err = uart_add_one_port(&tcu->driver, port); + if (err) { + dev_err(&pdev->dev, "failed to add UART port: %d\n", err); + goto unregister_uart; + } + + platform_set_drvdata(pdev, tcu); +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + register_console(&tcu->console); +#endif + + return 0; + +unregister_uart: + uart_unregister_driver(&tcu->driver); +free_rx: + mbox_free_channel(tcu->rx); +free_tx: + mbox_free_channel(tcu->tx); + + return err; +} + +static int tegra_tcu_remove(struct platform_device *pdev) +{ + struct tegra_tcu *tcu = platform_get_drvdata(pdev); + +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + unregister_console(&tcu->console); +#endif + uart_remove_one_port(&tcu->driver, &tcu->port); + uart_unregister_driver(&tcu->driver); + mbox_free_channel(tcu->rx); + mbox_free_channel(tcu->tx); + + return 0; +} + +static const struct of_device_id tegra_tcu_match[] = { + { .compatible = "nvidia,tegra194-tcu" }, + { } +}; + +static struct platform_driver tegra_tcu_driver = { + .driver = { + .name = "tegra-tcu", + .of_match_table = tegra_tcu_match, + }, + .probe = tegra_tcu_probe, + .remove = tegra_tcu_remove, +}; +module_platform_driver(tegra_tcu_driver); + +MODULE_AUTHOR("Mikko Perttunen "); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("NVIDIA Tegra Combined UART driver"); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index df4a7534e239..6009ee2c2e99 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -79,6 +79,9 @@ /* Nuvoton UART */ #define PORT_NPCM 40 +/* NVIDIA Tegra Combined UART */ +#define PORT_TEGRA_TCU 41 + /* Intel EG20 */ #define PORT_PCH_8LINE 44 #define PORT_PCH_2LINE 45 -- cgit From d0a060be573bfbf8753a15dca35497db5e968bb0 Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Wed, 30 Jan 2019 12:02:44 +0000 Subject: arm64: add ptrace regsets for ptrauth key management Add two new ptrace regsets, which can be used to request and change the pointer authentication keys of a thread. NT_ARM_PACA_KEYS gives access to the instruction/data address keys, and NT_ARM_PACG_KEYS to the generic authentication key. The keys are also part of the core dump file of the process. The regsets are only exposed if the kernel is compiled with CONFIG_CHECKPOINT_RESTORE=y, as the only intended use case is checkpointing and restoring processes that are using pointer authentication. (This can be changed later if there are other use cases.) Reviewed-by: Dave Martin Signed-off-by: Kristina Martsenko Signed-off-by: Catalin Marinas --- Documentation/arm64/pointer-authentication.txt | 5 + arch/arm64/include/uapi/asm/ptrace.h | 13 +++ arch/arm64/kernel/ptrace.c | 147 +++++++++++++++++++++++++ include/uapi/linux/elf.h | 2 + 4 files changed, 167 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/arm64/pointer-authentication.txt b/Documentation/arm64/pointer-authentication.txt index a25cd21290e9..5baca42ba146 100644 --- a/Documentation/arm64/pointer-authentication.txt +++ b/Documentation/arm64/pointer-authentication.txt @@ -78,6 +78,11 @@ bits can vary between the two. Note that the masks apply to TTBR0 addresses, and are not valid to apply to TTBR1 addresses (e.g. kernel pointers). +Additionally, when CONFIG_CHECKPOINT_RESTORE is also set, the kernel +will expose the NT_ARM_PACA_KEYS and NT_ARM_PACG_KEYS regsets (struct +user_pac_address_keys and struct user_pac_generic_keys). These can be +used to get and set the keys for a thread. + Virtualization -------------- diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 28d77c9ed531..d78623acb649 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -233,6 +233,19 @@ struct user_pac_mask { __u64 insn_mask; }; +/* pointer authentication keys (NT_ARM_PACA_KEYS, NT_ARM_PACG_KEYS) */ + +struct user_pac_address_keys { + __uint128_t apiakey; + __uint128_t apibkey; + __uint128_t apdakey; + __uint128_t apdbkey; +}; + +struct user_pac_generic_keys { + __uint128_t apgakey; +}; + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9dce33b0e260..a86413be5a2d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -979,6 +979,131 @@ static int pac_mask_get(struct task_struct *target, return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &uregs, 0, -1); } + +#ifdef CONFIG_CHECKPOINT_RESTORE +static __uint128_t pac_key_to_user(const struct ptrauth_key *key) +{ + return (__uint128_t)key->hi << 64 | key->lo; +} + +static struct ptrauth_key pac_key_from_user(__uint128_t ukey) +{ + struct ptrauth_key key = { + .lo = (unsigned long)ukey, + .hi = (unsigned long)(ukey >> 64), + }; + + return key; +} + +static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, + const struct ptrauth_keys *keys) +{ + ukeys->apiakey = pac_key_to_user(&keys->apia); + ukeys->apibkey = pac_key_to_user(&keys->apib); + ukeys->apdakey = pac_key_to_user(&keys->apda); + ukeys->apdbkey = pac_key_to_user(&keys->apdb); +} + +static void pac_address_keys_from_user(struct ptrauth_keys *keys, + const struct user_pac_address_keys *ukeys) +{ + keys->apia = pac_key_from_user(ukeys->apiakey); + keys->apib = pac_key_from_user(ukeys->apibkey); + keys->apda = pac_key_from_user(ukeys->apdakey); + keys->apdb = pac_key_from_user(ukeys->apdbkey); +} + +static int pac_address_keys_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_address_keys user_keys; + + if (!system_supports_address_auth()) + return -EINVAL; + + pac_address_keys_to_user(&user_keys, keys); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); +} + +static int pac_address_keys_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_address_keys user_keys; + int ret; + + if (!system_supports_address_auth()) + return -EINVAL; + + pac_address_keys_to_user(&user_keys, keys); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); + if (ret) + return ret; + pac_address_keys_from_user(keys, &user_keys); + + return 0; +} + +static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, + const struct ptrauth_keys *keys) +{ + ukeys->apgakey = pac_key_to_user(&keys->apga); +} + +static void pac_generic_keys_from_user(struct ptrauth_keys *keys, + const struct user_pac_generic_keys *ukeys) +{ + keys->apga = pac_key_from_user(ukeys->apgakey); +} + +static int pac_generic_keys_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_generic_keys user_keys; + + if (!system_supports_generic_auth()) + return -EINVAL; + + pac_generic_keys_to_user(&user_keys, keys); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); +} + +static int pac_generic_keys_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_generic_keys user_keys; + int ret; + + if (!system_supports_generic_auth()) + return -EINVAL; + + pac_generic_keys_to_user(&user_keys, keys); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); + if (ret) + return ret; + pac_generic_keys_from_user(keys, &user_keys); + + return 0; +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ #endif /* CONFIG_ARM64_PTR_AUTH */ enum aarch64_regset { @@ -995,6 +1120,10 @@ enum aarch64_regset { #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, +#ifdef CONFIG_CHECKPOINT_RESTORE + REGSET_PACA_KEYS, + REGSET_PACG_KEYS, +#endif #endif }; @@ -1074,6 +1203,24 @@ static const struct user_regset aarch64_regsets[] = { .get = pac_mask_get, /* this cannot be set dynamically */ }, +#ifdef CONFIG_CHECKPOINT_RESTORE + [REGSET_PACA_KEYS] = { + .core_note_type = NT_ARM_PACA_KEYS, + .n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t), + .size = sizeof(__uint128_t), + .align = sizeof(__uint128_t), + .get = pac_address_keys_get, + .set = pac_address_keys_set, + }, + [REGSET_PACG_KEYS] = { + .core_note_type = NT_ARM_PACG_KEYS, + .n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t), + .size = sizeof(__uint128_t), + .align = sizeof(__uint128_t), + .get = pac_generic_keys_get, + .set = pac_generic_keys_set, + }, +#endif #endif }; diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index e4d6ddd93567..34c02e4290fe 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -421,6 +421,8 @@ typedef struct elf64_shdr { #define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ #define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ #define NT_ARM_PAC_MASK 0x406 /* ARM pointer authentication code masks */ +#define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */ +#define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit From 2c620ff93d9fbd5d644760d4c21d389078ec1080 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 2 Jul 2018 22:44:20 -0700 Subject: time: Add struct __kernel_timex struct timex uses struct timeval internally. struct timeval is not y2038 safe. Introduce a new UAPI type struct __kernel_timex that is y2038 safe. struct __kernel_timex uses a timeval type that is similar to struct __kernel_timespec which preserves the same structure size across 32 bit and 64 bit ABIs. struct __kernel_timex also restructures other members of the structure to make the structure the same on 64 bit and 32 bit architectures. Note that struct __kernel_timex is the same as struct timex on a 64 bit architecture. The above solution is similar to other new y2038 syscalls that are being introduced: both 32 bit and 64 bit ABIs have a common entry, and the compat entry supports the old 32 bit syscall interface. Alternatives considered were: 1. Add new time type to struct timex that makes use of padded bits. This time type could be based on the struct __kernel_timespec. modes will use a flag to notify which time structure should be used internally. This needs some application level changes on both 64 bit and 32 bit architectures. Although 64 bit machines could continue to use the older timeval structure without any changes. 2. Add a new u8 type to struct timex that makes use of padded bits. This can be used to save higher order tv_sec bits. modes will use a flag to notify presence of such a type. This will need some application level changes on 32 bit architectures. 3. Add a new compat_timex structure that differs in only the size of the time type; keep rest of struct timex the same. This requires extra syscalls to manage all 3 cases on 64 bit architectures. This will not need any application level changes but will add more complexity from kernel side. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/timex.h | 7 +++++++ include/uapi/linux/timex.h | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 39c25dbebfe8..7f40e9e42ecc 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -53,6 +53,13 @@ #ifndef _LINUX_TIMEX_H #define _LINUX_TIMEX_H +/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path + * and 32-bit emulation. + */ +#ifndef CONFIG_64BIT_TIME +#define __kernel_timex timex +#endif + #include #define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ diff --git a/include/uapi/linux/timex.h b/include/uapi/linux/timex.h index 92685d826444..a1c6b73016a5 100644 --- a/include/uapi/linux/timex.h +++ b/include/uapi/linux/timex.h @@ -92,6 +92,47 @@ struct timex { int :32; int :32; int :32; }; +struct __kernel_timex_timeval { + __kernel_time64_t tv_sec; + long long tv_usec; +}; + +#ifndef __kernel_timex +struct __kernel_timex { + unsigned int modes; /* mode selector */ + int :32; /* pad */ + long long offset; /* time offset (usec) */ + long long freq; /* frequency offset (scaled ppm) */ + long long maxerror;/* maximum error (usec) */ + long long esterror;/* estimated error (usec) */ + int status; /* clock command/status */ + int :32; /* pad */ + long long constant;/* pll time constant */ + long long precision;/* clock precision (usec) (read only) */ + long long tolerance;/* clock frequency tolerance (ppm) + * (read only) + */ + struct __kernel_timex_timeval time; /* (read only, except for ADJ_SETOFFSET) */ + long long tick; /* (modified) usecs between clock ticks */ + + long long ppsfreq;/* pps frequency (scaled ppm) (ro) */ + long long jitter; /* pps jitter (us) (ro) */ + int shift; /* interval duration (s) (shift) (ro) */ + int :32; /* pad */ + long long stabil; /* pps stability (scaled ppm) (ro) */ + long long jitcnt; /* jitter limit exceeded (ro) */ + long long calcnt; /* calibration intervals (ro) */ + long long errcnt; /* calibration errors (ro) */ + long long stbcnt; /* stability limit exceeded (ro) */ + + int tai; /* TAI offset (ro) */ + + int :32; int :32; int :32; int :32; + int :32; int :32; int :32; int :32; + int :32; int :32; int :32; +}; +#endif + /* * Mode codes (timex.mode) */ -- cgit From c70a772fda11570ebddecbce1543a3fda008db4a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 7 Jan 2019 00:00:34 +0100 Subject: y2038: remove struct definition redirects We now use 64-bit time_t on all architectures, so the __kernel_timex, __kernel_timeval and __kernel_timespec redirects can be removed after having served their purpose. This makes it all much less confusing, as the __kernel_* types now always refer to the same layout based on 64-bit time_t across all 32-bit and 64-bit architectures. Signed-off-by: Arnd Bergmann --- include/linux/time64.h | 8 -------- include/linux/timex.h | 7 ------- include/uapi/linux/time.h | 4 ---- include/uapi/linux/timex.h | 2 -- 4 files changed, 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index 05634afba0db..f38d382ffec1 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -7,14 +7,6 @@ typedef __s64 time64_t; typedef __u64 timeu64_t; -/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path - * and 32-bit emulation. - */ -#ifndef CONFIG_64BIT_TIME -#define __kernel_timespec timespec -#define __kernel_itimerspec itimerspec -#endif - #include struct timespec64 { diff --git a/include/linux/timex.h b/include/linux/timex.h index 4aff9f0d1367..ce0859763670 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -53,13 +53,6 @@ #ifndef _LINUX_TIMEX_H #define _LINUX_TIMEX_H -/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path - * and 32-bit emulation. - */ -#ifndef CONFIG_64BIT_TIME -#define __kernel_timex timex -#endif - #include #define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 6b56a2208be7..b03f8717c312 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -42,19 +42,15 @@ struct itimerval { struct timeval it_value; /* current value */ }; -#ifndef __kernel_timespec struct __kernel_timespec { __kernel_time64_t tv_sec; /* seconds */ long long tv_nsec; /* nanoseconds */ }; -#endif -#ifndef __kernel_itimerspec struct __kernel_itimerspec { struct __kernel_timespec it_interval; /* timer period */ struct __kernel_timespec it_value; /* timer expiration */ }; -#endif /* * legacy timeval structure, only embedded in structures that diff --git a/include/uapi/linux/timex.h b/include/uapi/linux/timex.h index a1c6b73016a5..9f517f9010bb 100644 --- a/include/uapi/linux/timex.h +++ b/include/uapi/linux/timex.h @@ -97,7 +97,6 @@ struct __kernel_timex_timeval { long long tv_usec; }; -#ifndef __kernel_timex struct __kernel_timex { unsigned int modes; /* mode selector */ int :32; /* pad */ @@ -131,7 +130,6 @@ struct __kernel_timex { int :32; int :32; int :32; int :32; int :32; int :32; int :32; }; -#endif /* * Mode codes (timex.mode) -- cgit From e9e0c8903009477b630e37a8b6364b26a00720da Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 10 Jan 2019 19:04:34 +0200 Subject: fanotify: encode file identifier for FAN_REPORT_FID When user requests the flag FAN_REPORT_FID in fanotify_init(), a unique file identifier of the event target object will be reported with the event. The file identifier includes the filesystem's fsid (i.e. from statfs(2)) and an NFS file handle of the file (i.e. from name_to_handle_at(2)). The file identifier makes holding the path reference and passing a file descriptor to user redundant, so those are disabled in a group with FAN_REPORT_FID. Encode fid and store it in event for a group with FAN_REPORT_FID. Up to 12 bytes of file handle on 32bit arch (16 bytes on 64bit arch) are stored inline in fanotify_event struct. Larger file handles are stored in an external allocated buffer. On failure to encode fid, we print a warning and queue the event without the fid information. [JK: Fold part of later patched into this one to use exportfs_encode_inode_fh() right away] Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 84 +++++++++++++++++++++++++++++++++++--- fs/notify/fanotify/fanotify.h | 78 +++++++++++++++++++++++++++++++++-- fs/notify/fanotify/fanotify_user.c | 6 +-- include/uapi/linux/fanotify.h | 1 + 4 files changed, 156 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d8e3b6e50844..dd33227e518a 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "fanotify.h" @@ -25,10 +26,18 @@ static bool should_merge(struct fsnotify_event *old_fsn, old = FANOTIFY_E(old_fsn); new = FANOTIFY_E(new_fsn); - if (old_fsn->inode == new_fsn->inode && old->pid == new->pid && - old->path.mnt == new->path.mnt && - old->path.dentry == new->path.dentry) - return true; + if (old_fsn->inode != new_fsn->inode || old->pid != new->pid || + old->fh_type != new->fh_type || old->fh_len != new->fh_len) + return false; + + if (fanotify_event_has_path(old)) { + return old->path.mnt == new->path.mnt && + old->path.dentry == new->path.dentry; + } else if (fanotify_event_has_fid(old)) { + return fanotify_fid_equal(&old->fid, &new->fid, old->fh_len); + } + + /* Do not merge events if we failed to encode fid */ return false; } @@ -143,6 +152,60 @@ static u32 fanotify_group_event_mask(struct fsnotify_iter_info *iter_info, ~marks_ignored_mask; } +static int fanotify_encode_fid(struct fanotify_event *event, + const struct path *path, gfp_t gfp) +{ + struct fanotify_fid *fid = &event->fid; + int dwords, bytes = 0; + struct kstatfs stat; + int err, type; + + stat.f_fsid.val[0] = stat.f_fsid.val[1] = 0; + fid->ext_fh = NULL; + dwords = 0; + err = -ENOENT; + type = exportfs_encode_inode_fh(d_inode(path->dentry), NULL, &dwords, + NULL); + if (!dwords) + goto out_err; + + err = vfs_statfs(path, &stat); + if (err) + goto out_err; + + bytes = dwords << 2; + if (bytes > FANOTIFY_INLINE_FH_LEN) { + /* Treat failure to allocate fh as failure to allocate event */ + err = -ENOMEM; + fid->ext_fh = kmalloc(bytes, gfp); + if (!fid->ext_fh) + goto out_err; + } + + type = exportfs_encode_inode_fh(d_inode(path->dentry), + fanotify_fid_fh(fid, bytes), &dwords, + NULL); + err = -EINVAL; + if (!type || type == FILEID_INVALID || bytes != dwords << 2) + goto out_err; + + fid->fsid = stat.f_fsid; + event->fh_len = bytes; + + return type; + +out_err: + pr_warn_ratelimited("fanotify: failed to encode fid (fsid=%x.%x, " + "type=%d, bytes=%d, err=%i)\n", + stat.f_fsid.val[0], stat.f_fsid.val[1], + type, bytes, err); + kfree(fid->ext_fh); + fid->ext_fh = NULL; + event->fh_len = 0; + + return FILEID_INVALID; +} + struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, struct inode *inode, u32 mask, const struct path *path) @@ -181,10 +244,16 @@ init: __maybe_unused event->pid = get_pid(task_pid(current)); else event->pid = get_pid(task_tgid(current)); - if (path) { + event->fh_len = 0; + if (path && FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + /* Report the event without a file identifier on encode error */ + event->fh_type = fanotify_encode_fid(event, path, gfp); + } else if (path) { + event->fh_type = FILEID_ROOT; event->path = *path; path_get(&event->path); } else { + event->fh_type = FILEID_INVALID; event->path.mnt = NULL; event->path.dentry = NULL; } @@ -281,7 +350,10 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event) struct fanotify_event *event; event = FANOTIFY_E(fsn_event); - path_put(&event->path); + if (fanotify_event_has_path(event)) + path_put(&event->path); + else if (fanotify_event_has_ext_fh(event)) + kfree(event->fid.ext_fh); put_pid(event->pid); if (fanotify_is_perm_event(event->mask)) { kmem_cache_free(fanotify_perm_event_cachep, diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 898b5b2bc1c7..271482fb9611 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -2,11 +2,49 @@ #include #include #include +#include extern struct kmem_cache *fanotify_mark_cache; extern struct kmem_cache *fanotify_event_cachep; extern struct kmem_cache *fanotify_perm_event_cachep; +/* + * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation). + * For 32bit arch, fid increases the size of fanotify_event by 12 bytes and + * fh_* fields increase the size of fanotify_event by another 4 bytes. + * For 64bit arch, fid increases the size of fanotify_fid by 8 bytes and + * fh_* fields are packed in a hole after mask. + */ +#if BITS_PER_LONG == 32 +#define FANOTIFY_INLINE_FH_LEN (3 << 2) +#else +#define FANOTIFY_INLINE_FH_LEN (4 << 2) +#endif + +struct fanotify_fid { + __kernel_fsid_t fsid; + union { + unsigned char fh[FANOTIFY_INLINE_FH_LEN]; + unsigned char *ext_fh; + }; +}; + +static inline void *fanotify_fid_fh(struct fanotify_fid *fid, + unsigned int fh_len) +{ + return fh_len <= FANOTIFY_INLINE_FH_LEN ? fid->fh : fid->ext_fh; +} + +static inline bool fanotify_fid_equal(struct fanotify_fid *fid1, + struct fanotify_fid *fid2, + unsigned int fh_len) +{ + return fid1->fsid.val[0] == fid2->fsid.val[0] && + fid1->fsid.val[1] == fid2->fsid.val[1] && + !memcmp(fanotify_fid_fh(fid1, fh_len), + fanotify_fid_fh(fid2, fh_len), fh_len); +} + /* * Structure for normal fanotify events. It gets allocated in * fanotify_handle_event() and freed when the information is retrieved by @@ -16,13 +54,47 @@ struct fanotify_event { struct fsnotify_event fse; u32 mask; /* - * We hold ref to this path so it may be dereferenced at any point - * during this object's lifetime + * Those fields are outside fanotify_fid to pack fanotify_event nicely + * on 64bit arch and to use fh_type as an indication of whether path + * or fid are used in the union: + * FILEID_ROOT (0) for path, > 0 for fid, FILEID_INVALID for neither. */ - struct path path; + u8 fh_type; + u8 fh_len; + u16 pad; + union { + /* + * We hold ref to this path so it may be dereferenced at any + * point during this object's lifetime + */ + struct path path; + /* + * With FAN_REPORT_FID, we do not hold any reference on the + * victim object. Instead we store its NFS file handle and its + * filesystem's fsid as a unique identifier. + */ + struct fanotify_fid fid; + }; struct pid *pid; }; +static inline bool fanotify_event_has_path(struct fanotify_event *event) +{ + return event->fh_type == FILEID_ROOT; +} + +static inline bool fanotify_event_has_fid(struct fanotify_event *event) +{ + return event->fh_type != FILEID_ROOT && + event->fh_type != FILEID_INVALID; +} + +static inline bool fanotify_event_has_ext_fh(struct fanotify_event *event) +{ + return fanotify_event_has_fid(event) && + event->fh_len > FANOTIFY_INLINE_FH_LEN; +} + /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 096503bd0edb..c965fcf4979e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -181,7 +181,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fanotify_event_metadata metadata; struct fanotify_event *event; struct file *f = NULL; - int fd, ret; + int ret, fd = FAN_NOFD; pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event); @@ -193,9 +193,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS; metadata.pid = pid_vnr(event->pid); - if (unlikely(event->mask & FAN_Q_OVERFLOW)) { - fd = FAN_NOFD; - } else { + if (fanotify_event_has_path(event)) { fd = create_fd(group, event, &f); if (fd < 0) return fd; diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 909c98fcace2..d07f3cbc2786 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -44,6 +44,7 @@ /* Flags to determine fanotify event format */ #define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ +#define FAN_REPORT_FID 0x00000200 /* Report unique file id */ /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ -- cgit From 5e469c830fdb5a1ebaa69b375b87f583326fd296 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 10 Jan 2019 19:04:35 +0200 Subject: fanotify: copy event fid info to user If group requested FAN_REPORT_FID and event has file identifier, copy that information to user reading the event after event metadata. fid information is formatted as struct fanotify_event_info_fid that includes a generic header struct fanotify_event_info_header, so that other info types could be defined in the future using the same header. metadata->event_len includes the length of the fid information. The fid information includes the filesystem's fsid (see statfs(2)) followed by an NFS file handle of the file that could be passed as an argument to open_by_handle_at(2). Cc: Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.h | 5 +++ fs/notify/fanotify/fanotify_user.c | 82 +++++++++++++++++++++++++++++++++++--- include/uapi/linux/fanotify.h | 20 ++++++++++ 3 files changed, 102 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 271482fb9611..4aafc7144c3d 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -95,6 +95,11 @@ static inline bool fanotify_event_has_ext_fh(struct fanotify_event *event) event->fh_len > FANOTIFY_INLINE_FH_LEN; } +static inline void *fanotify_event_fh(struct fanotify_event *event) +{ + return fanotify_fid_fh(&event->fid, event->fh_len); +} + /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index c965fcf4979e..cd82dd713c91 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -47,6 +47,18 @@ struct kmem_cache *fanotify_mark_cache __read_mostly; struct kmem_cache *fanotify_event_cachep __read_mostly; struct kmem_cache *fanotify_perm_event_cachep __read_mostly; +#define FANOTIFY_EVENT_ALIGN 4 + +static int fanotify_event_info_len(struct fanotify_event *event) +{ + if (!fanotify_event_has_fid(event)) + return 0; + + return roundup(sizeof(struct fanotify_event_info_fid) + + sizeof(struct file_handle) + event->fh_len, + FANOTIFY_EVENT_ALIGN); +} + /* * Get an fsnotify notification event if one exists and is small * enough to fit in "count". Return an error pointer if the count @@ -57,6 +69,9 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; static struct fsnotify_event *get_one_event(struct fsnotify_group *group, size_t count) { + size_t event_size = FAN_EVENT_METADATA_LEN; + struct fanotify_event *event; + assert_spin_locked(&group->notification_lock); pr_debug("%s: group=%p count=%zd\n", __func__, group, count); @@ -64,11 +79,18 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, if (fsnotify_notify_queue_is_empty(group)) return NULL; - if (FAN_EVENT_METADATA_LEN > count) + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + event = FANOTIFY_E(fsnotify_peek_first_event(group)); + event_size += fanotify_event_info_len(event); + } + + if (event_size > count) return ERR_PTR(-EINVAL); - /* held the notification_lock the whole time, so this is the - * same event we peeked above */ + /* + * Held the notification_lock the whole time, so this is the + * same event we peeked above + */ return fsnotify_remove_first_event(group); } @@ -174,6 +196,48 @@ static int process_access_response(struct fsnotify_group *group, return 0; } +static int copy_fid_to_user(struct fanotify_event *event, char __user *buf) +{ + struct fanotify_event_info_fid info = { }; + struct file_handle handle = { }; + size_t fh_len = event->fh_len; + size_t len = fanotify_event_info_len(event); + + if (!len) + return 0; + + if (WARN_ON_ONCE(len < sizeof(info) + sizeof(handle) + fh_len)) + return -EFAULT; + + /* Copy event info fid header followed by vaiable sized file handle */ + info.hdr.info_type = FAN_EVENT_INFO_TYPE_FID; + info.hdr.len = len; + info.fsid = event->fid.fsid; + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + buf += sizeof(info); + len -= sizeof(info); + handle.handle_type = event->fh_type; + handle.handle_bytes = fh_len; + if (copy_to_user(buf, &handle, sizeof(handle))) + return -EFAULT; + + buf += sizeof(handle); + len -= sizeof(handle); + if (copy_to_user(buf, fanotify_event_fh(event), fh_len)) + return -EFAULT; + + /* Pad with 0's */ + buf += fh_len; + len -= fh_len; + WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN); + if (len > 0 && clear_user(buf, len)) + return -EFAULT; + + return 0; +} + static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fsnotify_event *fsn_event, char __user *buf, size_t count) @@ -197,6 +261,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fd = create_fd(group, event, &f); if (fd < 0) return fd; + } else if (fanotify_event_has_fid(event)) { + metadata.event_len += fanotify_event_info_len(event); } metadata.fd = fd; @@ -208,14 +274,20 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (WARN_ON_ONCE(metadata.event_len > count)) goto out_close_fd; - if (copy_to_user(buf, &metadata, metadata.event_len)) + if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN)) goto out_close_fd; if (fanotify_is_perm_event(event->mask)) FANOTIFY_PE(fsn_event)->fd = fd; - if (fd != FAN_NOFD) + if (fanotify_event_has_path(event)) { fd_install(fd, f); + } else if (fanotify_event_has_fid(event)) { + ret = copy_fid_to_user(event, buf + FAN_EVENT_METADATA_LEN); + if (ret < 0) + return ret; + } + return metadata.event_len; out_close_fd: diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index d07f3cbc2786..959ae2bdc7ca 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -107,6 +107,26 @@ struct fanotify_event_metadata { __s32 pid; }; +#define FAN_EVENT_INFO_TYPE_FID 1 + +/* Variable length info record following event metadata */ +struct fanotify_event_info_header { + __u8 info_type; + __u8 pad; + __u16 len; +}; + +/* Unique file identifier info record */ +struct fanotify_event_info_fid { + struct fanotify_event_info_header hdr; + __kernel_fsid_t fsid; + /* + * Following is an opaque struct file_handle that can be passed as + * an argument to open_by_handle_at(2). + */ + unsigned char handle[0]; +}; + struct fanotify_response { __s32 fd; __u32 response; -- cgit From 235328d1fa4251c6dcb32351219bb553a58838d2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 10 Jan 2019 19:04:43 +0200 Subject: fanotify: add support for create/attrib/move/delete events Add support for events with data type FSNOTIFY_EVENT_INODE (e.g. create/attrib/move/delete) for inode and filesystem mark types. The "inode" events do not carry enough information (i.e. path) to report event->fd, so we do not allow setting a mask for those events unless group supports reporting fid. The "inode" events are not supported on a mount mark, because they do not carry enough information (i.e. path) to be filtered by mount point. The "dirent" events (create/move/delete) report the fid of the parent directory where events took place without specifying the filename of the child. In the future, fanotify may get support for reporting filename information for those events. Cc: Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 9 ++++++++- fs/notify/fanotify/fanotify_user.c | 12 ++++++++++++ include/linux/fanotify.h | 22 ++++++++++++++++++++-- include/uapi/linux/fanotify.h | 8 ++++++++ 4 files changed, 48 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 974239b03442..158c69acb04d 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -313,9 +313,16 @@ static int fanotify_handle_event(struct fsnotify_group *group, BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS); BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY); + BUILD_BUG_ON(FAN_ATTRIB != FS_ATTRIB); BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE); BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE); BUILD_BUG_ON(FAN_OPEN != FS_OPEN); + BUILD_BUG_ON(FAN_MOVED_TO != FS_MOVED_TO); + BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM); + BUILD_BUG_ON(FAN_CREATE != FS_CREATE); + BUILD_BUG_ON(FAN_DELETE != FS_DELETE); + BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF); + BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF); BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD); BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW); BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM); @@ -324,7 +331,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 12); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); mask = fanotify_group_event_mask(group, iter_info, mask, data, data_type); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index bf06fd6ef761..6c61a06d0ef5 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -976,6 +976,18 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group->priority == FS_PRIO_0) goto fput_and_out; + /* + * Events with data type inode do not carry enough information to report + * event->fd, so we do not allow setting a mask for inode events unless + * group supports reporting fid. + * inode events are not supported on a mount mark, because they do not + * carry enough information (i.e. path) to be filtered by mount point. + */ + if (mask & FANOTIFY_INODE_EVENTS && + (!FAN_GROUP_FLAG(group, FAN_REPORT_FID) || + mark_type == FAN_MARK_MOUNT)) + goto fput_and_out; + if (flags & FAN_MARK_FLUSH) { ret = 0; if (mark_type == FAN_MARK_MOUNT) diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index f59be967f72b..e9d45387089f 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -35,10 +35,28 @@ FAN_MARK_IGNORED_SURV_MODIFY | \ FAN_MARK_FLUSH) -/* Events that user can request to be notified on */ -#define FANOTIFY_EVENTS (FAN_ACCESS | FAN_MODIFY | \ +/* + * Events that can be reported with data type FSNOTIFY_EVENT_PATH. + * Note that FAN_MODIFY can also be reported with data type + * FSNOTIFY_EVENT_INODE. + */ +#define FANOTIFY_PATH_EVENTS (FAN_ACCESS | FAN_MODIFY | \ FAN_CLOSE | FAN_OPEN | FAN_OPEN_EXEC) +/* + * Directory entry modification events - reported only to directory + * where entry is modified and not to a watching parent. + */ +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) + +/* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ +#define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ + FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) + +/* Events that user can request to be notified on */ +#define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ + FANOTIFY_INODE_EVENTS) + /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ FAN_OPEN_EXEC_PERM) diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 959ae2bdc7ca..b9effa6f8503 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -7,9 +7,16 @@ /* the following events that user-space can register for */ #define FAN_ACCESS 0x00000001 /* File was accessed */ #define FAN_MODIFY 0x00000002 /* File was modified */ +#define FAN_ATTRIB 0x00000004 /* Metadata changed */ #define FAN_CLOSE_WRITE 0x00000008 /* Writtable file closed */ #define FAN_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ #define FAN_OPEN 0x00000020 /* File was opened */ +#define FAN_MOVED_FROM 0x00000040 /* File was moved from X */ +#define FAN_MOVED_TO 0x00000080 /* File was moved to Y */ +#define FAN_CREATE 0x00000100 /* Subfile was created */ +#define FAN_DELETE 0x00000200 /* Subfile was deleted */ +#define FAN_DELETE_SELF 0x00000400 /* Self was deleted */ +#define FAN_MOVE_SELF 0x00000800 /* Self was moved */ #define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ @@ -24,6 +31,7 @@ /* helper events */ #define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ +#define FAN_MOVE (FAN_MOVED_FROM | FAN_MOVED_TO) /* moves */ /* flags used for fanotify_init() */ #define FAN_CLOEXEC 0x00000001 -- cgit From d9a9ea94f748f47b1d75c6c5e33edcf74476c445 Mon Sep 17 00:00:00 2001 From: Chad Austin Date: Mon, 7 Jan 2019 16:53:17 -0800 Subject: fuse: support clients that don't implement 'opendir' Allow filesystems to return ENOSYS from opendir, preventing the kernel from sending opendir and releasedir messages in the future. This avoids userspace transitions when filesystems don't need to keep track of state per directory handle. A new capability flag, FUSE_NO_OPENDIR_SUPPORT, parallels FUSE_NO_OPEN_SUPPORT, indicating the new semantics for returning ENOSYS from opendir. Signed-off-by: Chad Austin Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 11 +++++++---- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 3 ++- include/uapi/linux/fuse.h | 7 ++++++- 4 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 8ee0446a8322..cc6ffd23b80f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -90,7 +90,7 @@ static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir) if (refcount_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - if (ff->fc->no_open && !isdir) { + if (isdir ? ff->fc->no_opendir : ff->fc->no_open) { /* * Drop the release request when client does not * implement 'open' @@ -125,7 +125,7 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file, ff->fh = 0; ff->open_flags = FOPEN_KEEP_CACHE; /* Default for no-open */ - if (!fc->no_open || isdir) { + if (isdir ? !fc->no_opendir : !fc->no_open) { struct fuse_open_out outarg; int err; @@ -134,11 +134,14 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file, ff->fh = outarg.fh; ff->open_flags = outarg.open_flags; - } else if (err != -ENOSYS || isdir) { + } else if (err != -ENOSYS) { fuse_file_free(ff); return err; } else { - fc->no_open = 1; + if (isdir) + fc->no_opendir = 1; + else + fc->no_open = 1; } } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 033e30af519f..0920c0c032a0 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -630,6 +630,9 @@ struct fuse_conn { /** Is open/release not implemented by fs? */ unsigned no_open:1; + /** Is opendir/releasedir not implemented by fs? */ + unsigned no_opendir:1; + /** Is fsync not implemented by fs? */ unsigned no_fsync:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2bbb7c59d6da..1b3f3b67d9f0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -972,7 +972,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | - FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS; + FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | + FUSE_NO_OPENDIR_SUPPORT; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index b4967d48bfda..2ac598614a8f 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -122,6 +122,9 @@ * - add FOPEN_CACHE_DIR * - add FUSE_MAX_PAGES, add max_pages to init_out * - add FUSE_CACHE_SYMLINKS + * + * 7.29 + * - add FUSE_NO_OPENDIR_SUPPORT flag */ #ifndef _LINUX_FUSE_H @@ -157,7 +160,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 28 +#define FUSE_KERNEL_MINOR_VERSION 29 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -259,6 +262,7 @@ struct fuse_file_lock { * FUSE_ABORT_ERROR: reading the device after abort returns ECONNABORTED * FUSE_MAX_PAGES: init_out.max_pages contains the max number of req pages * FUSE_CACHE_SYMLINKS: cache READLINK responses + * FUSE_NO_OPENDIR_SUPPORT: kernel supports zero-message opendir */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -284,6 +288,7 @@ struct fuse_file_lock { #define FUSE_ABORT_ERROR (1 << 21) #define FUSE_MAX_PAGES (1 << 22) #define FUSE_CACHE_SYMLINKS (1 << 23) +#define FUSE_NO_OPENDIR_SUPPORT (1 << 24) /** * CUSE INIT request/reply flags -- cgit From 746c9398f5ac2b3f5730da4ed09e99ef4bb50b4a Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 8 Feb 2019 01:02:55 -0500 Subject: arch: move common mmap flags to linux/mman.h Now that we have 3 mmap flags shared by all architectures, let's move them into the common header. This will help discourage future architectures from duplicating code. Signed-off-by: Michael S. Tsirkin Signed-off-by: Arnd Bergmann --- arch/alpha/include/uapi/asm/mman.h | 4 +--- arch/mips/include/uapi/asm/mman.h | 4 +--- arch/parisc/include/uapi/asm/mman.h | 4 +--- arch/xtensa/include/uapi/asm/mman.h | 4 +--- include/uapi/asm-generic/mman-common.h | 4 +--- include/uapi/linux/mman.h | 4 ++++ 6 files changed, 9 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index f9d4e6b6d4bd..ac23379b7a87 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -10,9 +10,7 @@ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ -#define MAP_SHARED 0x01 /* Share changes */ -#define MAP_PRIVATE 0x02 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x0f /* Mask for type of mapping (OSF/1 is _wrong_) */ #define MAP_FIXED 0x100 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x10 /* don't use a file */ diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 3035ca499cd8..c2b40969eb1f 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -27,9 +27,7 @@ /* * Flags for mmap */ -#define MAP_SHARED 0x001 /* Share changes */ -#define MAP_PRIVATE 0x002 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x003 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x00f /* Mask for type of mapping */ #define MAP_FIXED 0x010 /* Interpret addr exactly */ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 870fbf8c7088..c98162f494db 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -10,9 +10,7 @@ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ -#define MAP_SHARED 0x01 /* Share changes */ -#define MAP_PRIVATE 0x02 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x2b /* Mask for type of mapping, includes bits 0x08 and 0x20 */ #define MAP_FIXED 0x04 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x10 /* don't use a file */ diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 58f29a9d895d..be726062412b 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -34,9 +34,7 @@ /* * Flags for mmap */ -#define MAP_SHARED 0x001 /* Share changes */ -#define MAP_PRIVATE 0x002 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x003 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x00f /* Mask for type of mapping */ #define MAP_FIXED 0x010 /* Interpret addr exactly */ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index e7ee32861d51..abd238d0f7a4 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -15,9 +15,7 @@ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ -#define MAP_SHARED 0x01 /* Share changes */ -#define MAP_PRIVATE 0x02 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x0f /* Mask for type of mapping */ #define MAP_FIXED 0x10 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x20 /* don't use a file */ diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index d0f515d53299..fc1a64c3447b 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -12,6 +12,10 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ + /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page * size other than the default is desired. See hugetlb_encode.h. -- cgit From a7fe4ca72b1fe7877de5672640d0b4e023d0fdca Mon Sep 17 00:00:00 2001 From: Vivek Kasireddy Date: Thu, 7 Feb 2019 22:18:43 -0500 Subject: media: v4l: Add 32-bit packed YUV formats The formats added in this patch include: V4L2_PIX_FMT_AYUV32 V4L2_PIX_FMT_XYUV32 V4L2_PIX_FMT_VUYA32 V4L2_PIX_FMT_VUYX32 These formats enable the trasmission of alpha channel data to other drivers and userspace applications in addition to YUV data. For example, buffers generated by drivers in one of these formats can be used by the Weston compositor to display as a texture or flipped directly onto the overlay planes with the help of a DRM driver. Signed-off-by: Vivek Kasireddy Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/pixfmt-packed-yuv.rst | 170 ++++++++++++++++++++- drivers/media/v4l2-core/v4l2-ioctl.c | 4 + include/uapi/linux/videodev2.h | 4 + 3 files changed, 177 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/v4l/pixfmt-packed-yuv.rst b/Documentation/media/uapi/v4l/pixfmt-packed-yuv.rst index f53e8f57a003..7fcee1c11ac4 100644 --- a/Documentation/media/uapi/v4l/pixfmt-packed-yuv.rst +++ b/Documentation/media/uapi/v4l/pixfmt-packed-yuv.rst @@ -190,6 +190,170 @@ component of each pixel in one 16 or 32 bit word. - Cr\ :sub:`2` - Cr\ :sub:`1` - Cr\ :sub:`0` + - + * .. _V4L2-PIX-FMT-AYUV32: + + - ``V4L2_PIX_FMT_AYUV32`` + - 'AYUV' + + - a\ :sub:`7` + - a\ :sub:`6` + - a\ :sub:`5` + - a\ :sub:`4` + - a\ :sub:`3` + - a\ :sub:`2` + - a\ :sub:`1` + - a\ :sub:`0` + + - Y'\ :sub:`7` + - Y'\ :sub:`6` + - Y'\ :sub:`5` + - Y'\ :sub:`4` + - Y'\ :sub:`3` + - Y'\ :sub:`2` + - Y'\ :sub:`1` + - Y'\ :sub:`0` + + - Cb\ :sub:`7` + - Cb\ :sub:`6` + - Cb\ :sub:`5` + - Cb\ :sub:`4` + - Cb\ :sub:`3` + - Cb\ :sub:`2` + - Cb\ :sub:`1` + - Cb\ :sub:`0` + + - Cr\ :sub:`7` + - Cr\ :sub:`6` + - Cr\ :sub:`5` + - Cr\ :sub:`4` + - Cr\ :sub:`3` + - Cr\ :sub:`2` + - Cr\ :sub:`1` + - Cr\ :sub:`0` + - + * .. _V4L2-PIX-FMT-XYUV32: + + - ``V4L2_PIX_FMT_XYUV32`` + - 'XYUV' + + - + - + - + - + - + - + - + - + + - Y'\ :sub:`7` + - Y'\ :sub:`6` + - Y'\ :sub:`5` + - Y'\ :sub:`4` + - Y'\ :sub:`3` + - Y'\ :sub:`2` + - Y'\ :sub:`1` + - Y'\ :sub:`0` + + - Cb\ :sub:`7` + - Cb\ :sub:`6` + - Cb\ :sub:`5` + - Cb\ :sub:`4` + - Cb\ :sub:`3` + - Cb\ :sub:`2` + - Cb\ :sub:`1` + - Cb\ :sub:`0` + + - Cr\ :sub:`7` + - Cr\ :sub:`6` + - Cr\ :sub:`5` + - Cr\ :sub:`4` + - Cr\ :sub:`3` + - Cr\ :sub:`2` + - Cr\ :sub:`1` + - Cr\ :sub:`0` + - + * .. _V4L2-PIX-FMT-VUYA32: + + - ``V4L2_PIX_FMT_VUYA32`` + - 'VUYA' + + - Cr\ :sub:`7` + - Cr\ :sub:`6` + - Cr\ :sub:`5` + - Cr\ :sub:`4` + - Cr\ :sub:`3` + - Cr\ :sub:`2` + - Cr\ :sub:`1` + - Cr\ :sub:`0` + + - Cb\ :sub:`7` + - Cb\ :sub:`6` + - Cb\ :sub:`5` + - Cb\ :sub:`4` + - Cb\ :sub:`3` + - Cb\ :sub:`2` + - Cb\ :sub:`1` + - Cb\ :sub:`0` + + - Y'\ :sub:`7` + - Y'\ :sub:`6` + - Y'\ :sub:`5` + - Y'\ :sub:`4` + - Y'\ :sub:`3` + - Y'\ :sub:`2` + - Y'\ :sub:`1` + - Y'\ :sub:`0` + + - a\ :sub:`7` + - a\ :sub:`6` + - a\ :sub:`5` + - a\ :sub:`4` + - a\ :sub:`3` + - a\ :sub:`2` + - a\ :sub:`1` + - a\ :sub:`0` + - + * .. _V4L2-PIX-FMT-VUYX32: + + - ``V4L2_PIX_FMT_VUYX32`` + - 'VUYX' + + - Cr\ :sub:`7` + - Cr\ :sub:`6` + - Cr\ :sub:`5` + - Cr\ :sub:`4` + - Cr\ :sub:`3` + - Cr\ :sub:`2` + - Cr\ :sub:`1` + - Cr\ :sub:`0` + + - Cb\ :sub:`7` + - Cb\ :sub:`6` + - Cb\ :sub:`5` + - Cb\ :sub:`4` + - Cb\ :sub:`3` + - Cb\ :sub:`2` + - Cb\ :sub:`1` + - Cb\ :sub:`0` + + - Y'\ :sub:`7` + - Y'\ :sub:`6` + - Y'\ :sub:`5` + - Y'\ :sub:`4` + - Y'\ :sub:`3` + - Y'\ :sub:`2` + - Y'\ :sub:`1` + - Y'\ :sub:`0` + + - + - + - + - + - + - + - + - .. raw:: latex @@ -202,4 +366,8 @@ component of each pixel in one 16 or 32 bit word. #) The value of a = alpha bits is undefined when reading from the driver, ignored when writing to the driver, except when alpha blending has been negotiated for a :ref:`Video Overlay ` or - :ref:`Video Output Overlay `. + :ref:`Video Output Overlay ` for the formats Y444, YUV555 and + YUV4. However, for formats AYUV32 and VUYA32, the alpha component is + expected to contain a meaningful value that can be used by drivers + and applications. And, the formats XYUV32 and VUYX32 contain undefined + alpha values that must be ignored by all applications and drivers. diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 206b7348797e..6f707466b5d2 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1220,6 +1220,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_YUV555: descr = "16-bit A/XYUV 1-5-5-5"; break; case V4L2_PIX_FMT_YUV565: descr = "16-bit YUV 5-6-5"; break; case V4L2_PIX_FMT_YUV32: descr = "32-bit A/XYUV 8-8-8-8"; break; + case V4L2_PIX_FMT_AYUV32: descr = "32-bit AYUV 8-8-8-8"; break; + case V4L2_PIX_FMT_XYUV32: descr = "32-bit XYUV 8-8-8-8"; break; + case V4L2_PIX_FMT_VUYA32: descr = "32-bit VUYA 8-8-8-8"; break; + case V4L2_PIX_FMT_VUYX32: descr = "32-bit VUYX 8-8-8-8"; break; case V4L2_PIX_FMT_YUV410: descr = "Planar YUV 4:1:0"; break; case V4L2_PIX_FMT_YUV420: descr = "Planar YUV 4:2:0"; break; case V4L2_PIX_FMT_HI240: descr = "8-bit Dithered RGB (BTTV)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9a920f071ff9..1db220da3bcc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -562,6 +562,10 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YUV555 v4l2_fourcc('Y', 'U', 'V', 'O') /* 16 YUV-5-5-5 */ #define V4L2_PIX_FMT_YUV565 v4l2_fourcc('Y', 'U', 'V', 'P') /* 16 YUV-5-6-5 */ #define V4L2_PIX_FMT_YUV32 v4l2_fourcc('Y', 'U', 'V', '4') /* 32 YUV-8-8-8-8 */ +#define V4L2_PIX_FMT_AYUV32 v4l2_fourcc('A', 'Y', 'U', 'V') /* 32 AYUV-8-8-8-8 */ +#define V4L2_PIX_FMT_XYUV32 v4l2_fourcc('X', 'Y', 'U', 'V') /* 32 XYUV-8-8-8-8 */ +#define V4L2_PIX_FMT_VUYA32 v4l2_fourcc('V', 'U', 'Y', 'A') /* 32 VUYA-8-8-8-8 */ +#define V4L2_PIX_FMT_VUYX32 v4l2_fourcc('V', 'U', 'Y', 'X') /* 32 VUYX-8-8-8-8 */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* 8 8-bit color */ #define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ #define V4L2_PIX_FMT_M420 v4l2_fourcc('M', '4', '2', '0') /* 12 YUV 4:2:0 2 lines y, 1 line uv interleaved */ -- cgit From 721074b03411327e7bf41555d4cc7c18f49313f7 Mon Sep 17 00:00:00 2001 From: Patrick Lerda Date: Thu, 17 Jan 2019 03:50:13 -0500 Subject: media: rc: rcmm decoder and encoder media: add support for RCMM infrared remote controls. Signed-off-by: Patrick Lerda Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/lirc.h.rst.exceptions | 3 + MAINTAINERS | 5 + drivers/media/rc/Kconfig | 13 ++ drivers/media/rc/Makefile | 1 + drivers/media/rc/ir-rcmm-decoder.c | 254 ++++++++++++++++++++++++++++++ drivers/media/rc/rc-core-priv.h | 5 + drivers/media/rc/rc-main.c | 9 ++ include/media/rc-map.h | 14 +- include/uapi/linux/lirc.h | 6 + tools/include/uapi/linux/lirc.h | 12 ++ tools/testing/selftests/ir/ir_loopback.c | 9 ++ 11 files changed, 328 insertions(+), 3 deletions(-) create mode 100644 drivers/media/rc/ir-rcmm-decoder.c (limited to 'include/uapi/linux') diff --git a/Documentation/media/lirc.h.rst.exceptions b/Documentation/media/lirc.h.rst.exceptions index 379b9e7df5d0..7a8b8ff4f076 100644 --- a/Documentation/media/lirc.h.rst.exceptions +++ b/Documentation/media/lirc.h.rst.exceptions @@ -60,6 +60,9 @@ ignore symbol RC_PROTO_SHARP ignore symbol RC_PROTO_XMP ignore symbol RC_PROTO_CEC ignore symbol RC_PROTO_IMON +ignore symbol RC_PROTO_RCMM12 +ignore symbol RC_PROTO_RCMM24 +ignore symbol RC_PROTO_RCMM32 # Undocumented macros diff --git a/MAINTAINERS b/MAINTAINERS index 914d333ee73d..9662ad6c58e4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16536,6 +16536,11 @@ M: David Härdeman S: Maintained F: drivers/media/rc/winbond-cir.c +RCMM REMOTE CONTROLS DECODER +M: Patrick Lerda +S: Maintained +F: drivers/media/rc/ir-rcmm-decoder.c + WINSYSTEMS EBC-C384 WATCHDOG DRIVER M: William Breathitt Gray L: linux-watchdog@vger.kernel.org diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig index 8a216068a35a..8e95f6eac89d 100644 --- a/drivers/media/rc/Kconfig +++ b/drivers/media/rc/Kconfig @@ -133,6 +133,19 @@ config IR_IMON_DECODER remote control and you would like to use it with a raw IR receiver, or if you wish to use an encoder to transmit this IR. +config IR_RCMM_DECODER + tristate "Enable IR raw decoder for the RC-MM protocol" + depends on RC_CORE + help + Enable this option when you have IR with RC-MM protocol, and + you need the software decoder. The driver supports 12, + 24 and 32 bits RC-MM variants. You can enable or disable the + different modes using the following RC protocol keywords: + 'rc-mm-12', 'rc-mm-24' and 'rc-mm-32'. + + To compile this driver as a module, choose M here: the module + will be called ir-rcmm-decoder. + endif #RC_DECODERS menuconfig RC_DEVICES diff --git a/drivers/media/rc/Makefile b/drivers/media/rc/Makefile index 92c163816849..48d23433b3c0 100644 --- a/drivers/media/rc/Makefile +++ b/drivers/media/rc/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_IR_SHARP_DECODER) += ir-sharp-decoder.o obj-$(CONFIG_IR_MCE_KBD_DECODER) += ir-mce_kbd-decoder.o obj-$(CONFIG_IR_XMP_DECODER) += ir-xmp-decoder.o obj-$(CONFIG_IR_IMON_DECODER) += ir-imon-decoder.o +obj-$(CONFIG_IR_RCMM_DECODER) += ir-rcmm-decoder.o # stand-alone IR receivers/transmitters obj-$(CONFIG_RC_ATI_REMOTE) += ati_remote.o diff --git a/drivers/media/rc/ir-rcmm-decoder.c b/drivers/media/rc/ir-rcmm-decoder.c new file mode 100644 index 000000000000..f1096ac1e5c5 --- /dev/null +++ b/drivers/media/rc/ir-rcmm-decoder.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0+ +// ir-rcmm-decoder.c - A decoder for the RCMM IR protocol +// +// Copyright (C) 2018 by Patrick Lerda + +#include "rc-core-priv.h" +#include +#include + +#define RCMM_UNIT 166667 /* nanosecs */ +#define RCMM_PREFIX_PULSE 416666 /* 166666.666666666*2.5 */ +#define RCMM_PULSE_0 277777 /* 166666.666666666*(1+2/3) */ +#define RCMM_PULSE_1 444444 /* 166666.666666666*(2+2/3) */ +#define RCMM_PULSE_2 611111 /* 166666.666666666*(3+2/3) */ +#define RCMM_PULSE_3 777778 /* 166666.666666666*(4+2/3) */ + +enum rcmm_state { + STATE_INACTIVE, + STATE_LOW, + STATE_BUMP, + STATE_VALUE, + STATE_FINISHED, +}; + +static bool rcmm_mode(const struct rcmm_dec *data) +{ + return !((0x000c0000 & data->bits) == 0x000c0000); +} + +static int rcmm_miscmode(struct rc_dev *dev, struct rcmm_dec *data) +{ + switch (data->count) { + case 24: + if (dev->enabled_protocols & RC_PROTO_BIT_RCMM24) { + rc_keydown(dev, RC_PROTO_RCMM24, data->bits, 0); + data->state = STATE_INACTIVE; + return 0; + } + return -1; + + case 12: + if (dev->enabled_protocols & RC_PROTO_BIT_RCMM12) { + rc_keydown(dev, RC_PROTO_RCMM12, data->bits, 0); + data->state = STATE_INACTIVE; + return 0; + } + return -1; + } + + return -1; +} + +/** + * ir_rcmm_decode() - Decode one RCMM pulse or space + * @dev: the struct rc_dev descriptor of the device + * @ev: the struct ir_raw_event descriptor of the pulse/space + * + * This function returns -EINVAL if the pulse violates the state machine + */ +static int ir_rcmm_decode(struct rc_dev *dev, struct ir_raw_event ev) +{ + struct rcmm_dec *data = &dev->raw->rcmm; + u32 scancode; + u8 toggle; + int value; + + if (!(dev->enabled_protocols & (RC_PROTO_BIT_RCMM32 | + RC_PROTO_BIT_RCMM24 | + RC_PROTO_BIT_RCMM12))) + return 0; + + if (!is_timing_event(ev)) { + if (ev.reset) + data->state = STATE_INACTIVE; + return 0; + } + + switch (data->state) { + case STATE_INACTIVE: + if (!ev.pulse) + break; + + if (!eq_margin(ev.duration, RCMM_PREFIX_PULSE, RCMM_UNIT / 2)) + break; + + data->state = STATE_LOW; + data->count = 0; + data->bits = 0; + return 0; + + case STATE_LOW: + if (ev.pulse) + break; + + if (!eq_margin(ev.duration, RCMM_PULSE_0, RCMM_UNIT / 2)) + break; + + data->state = STATE_BUMP; + return 0; + + case STATE_BUMP: + if (!ev.pulse) + break; + + if (!eq_margin(ev.duration, RCMM_UNIT, RCMM_UNIT / 2)) + break; + + data->state = STATE_VALUE; + return 0; + + case STATE_VALUE: + if (ev.pulse) + break; + + if (eq_margin(ev.duration, RCMM_PULSE_0, RCMM_UNIT / 2)) + value = 0; + else if (eq_margin(ev.duration, RCMM_PULSE_1, RCMM_UNIT / 2)) + value = 1; + else if (eq_margin(ev.duration, RCMM_PULSE_2, RCMM_UNIT / 2)) + value = 2; + else if (eq_margin(ev.duration, RCMM_PULSE_3, RCMM_UNIT / 2)) + value = 3; + else + value = -1; + + if (value == -1) { + if (!rcmm_miscmode(dev, data)) + return 0; + break; + } + + data->bits <<= 2; + data->bits |= value; + + data->count += 2; + + if (data->count < 32) + data->state = STATE_BUMP; + else + data->state = STATE_FINISHED; + + return 0; + + case STATE_FINISHED: + if (!ev.pulse) + break; + + if (!eq_margin(ev.duration, RCMM_UNIT, RCMM_UNIT / 2)) + break; + + if (rcmm_mode(data)) { + toggle = !!(0x8000 & data->bits); + scancode = data->bits & ~0x8000; + } else { + toggle = 0; + scancode = data->bits; + } + + if (dev->enabled_protocols & RC_PROTO_BIT_RCMM32) { + rc_keydown(dev, RC_PROTO_RCMM32, scancode, toggle); + data->state = STATE_INACTIVE; + return 0; + } + + break; + } + + data->state = STATE_INACTIVE; + return -EINVAL; +} + +static const int rcmmspace[] = { + RCMM_PULSE_0, + RCMM_PULSE_1, + RCMM_PULSE_2, + RCMM_PULSE_3, +}; + +static int ir_rcmm_rawencoder(struct ir_raw_event **ev, unsigned int max, + unsigned int n, u32 data) +{ + int i; + int ret; + + ret = ir_raw_gen_pulse_space(ev, &max, RCMM_PREFIX_PULSE, RCMM_PULSE_0); + if (ret) + return ret; + + for (i = n - 2; i >= 0; i -= 2) { + const unsigned int space = rcmmspace[(data >> i) & 3]; + + ret = ir_raw_gen_pulse_space(ev, &max, RCMM_UNIT, space); + if (ret) + return ret; + } + + return ir_raw_gen_pulse_space(ev, &max, RCMM_UNIT, RCMM_PULSE_3 * 2); +} + +static int ir_rcmm_encode(enum rc_proto protocol, u32 scancode, + struct ir_raw_event *events, unsigned int max) +{ + struct ir_raw_event *e = events; + int ret; + + switch (protocol) { + case RC_PROTO_RCMM32: + ret = ir_rcmm_rawencoder(&e, max, 32, scancode); + break; + case RC_PROTO_RCMM24: + ret = ir_rcmm_rawencoder(&e, max, 24, scancode); + break; + case RC_PROTO_RCMM12: + ret = ir_rcmm_rawencoder(&e, max, 12, scancode); + break; + default: + ret = -EINVAL; + } + + if (ret < 0) + return ret; + + return e - events; +} + +static struct ir_raw_handler rcmm_handler = { + .protocols = RC_PROTO_BIT_RCMM32 | + RC_PROTO_BIT_RCMM24 | + RC_PROTO_BIT_RCMM12, + .decode = ir_rcmm_decode, + .encode = ir_rcmm_encode, + .carrier = 36000, + .min_timeout = RCMM_PULSE_3 + RCMM_UNIT, +}; + +static int __init ir_rcmm_decode_init(void) +{ + ir_raw_handler_register(&rcmm_handler); + + pr_info("IR RCMM protocol handler initialized\n"); + return 0; +} + +static void __exit ir_rcmm_decode_exit(void) +{ + ir_raw_handler_unregister(&rcmm_handler); +} + +module_init(ir_rcmm_decode_init); +module_exit(ir_rcmm_decode_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick Lerda"); +MODULE_DESCRIPTION("RCMM IR protocol decoder"); diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h index c2cbe7f6266c..9f21b3e8b377 100644 --- a/drivers/media/rc/rc-core-priv.h +++ b/drivers/media/rc/rc-core-priv.h @@ -131,6 +131,11 @@ struct ir_raw_event_ctrl { unsigned int bits; bool stick_keyboard; } imon; + struct rcmm_dec { + int state; + unsigned int count; + u32 bits; + } rcmm; }; /* Mutex for locking raw IR processing and handler change */ diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 66a174979b3c..dc38e9c0a2ff 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -70,6 +70,12 @@ static const struct { [RC_PROTO_CEC] = { .name = "cec", .repeat_period = 0 }, [RC_PROTO_IMON] = { .name = "imon", .scancode_bits = 0x7fffffff, .repeat_period = 114 }, + [RC_PROTO_RCMM12] = { .name = "rc-mm-12", + .scancode_bits = 0x00000fff, .repeat_period = 114 }, + [RC_PROTO_RCMM24] = { .name = "rc-mm-24", + .scancode_bits = 0x00ffffff, .repeat_period = 114 }, + [RC_PROTO_RCMM32] = { .name = "rc-mm-32", + .scancode_bits = 0xffffffff, .repeat_period = 114 }, }; /* Used to keep track of known keymaps */ @@ -1006,6 +1012,9 @@ static const struct { { RC_PROTO_BIT_XMP, "xmp", "ir-xmp-decoder" }, { RC_PROTO_BIT_CEC, "cec", NULL }, { RC_PROTO_BIT_IMON, "imon", "ir-imon-decoder" }, + { RC_PROTO_BIT_RCMM12 | + RC_PROTO_BIT_RCMM24 | + RC_PROTO_BIT_RCMM32, "rc-mm", "ir-rcmm-decoder" }, }; /** diff --git a/include/media/rc-map.h b/include/media/rc-map.h index d621acadfbf3..e5e86d595645 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -37,6 +37,9 @@ #define RC_PROTO_BIT_XMP BIT_ULL(RC_PROTO_XMP) #define RC_PROTO_BIT_CEC BIT_ULL(RC_PROTO_CEC) #define RC_PROTO_BIT_IMON BIT_ULL(RC_PROTO_IMON) +#define RC_PROTO_BIT_RCMM12 BIT_ULL(RC_PROTO_RCMM12) +#define RC_PROTO_BIT_RCMM24 BIT_ULL(RC_PROTO_RCMM24) +#define RC_PROTO_BIT_RCMM32 BIT_ULL(RC_PROTO_RCMM32) #define RC_PROTO_BIT_ALL \ (RC_PROTO_BIT_UNKNOWN | RC_PROTO_BIT_OTHER | \ @@ -51,7 +54,8 @@ RC_PROTO_BIT_RC6_6A_24 | RC_PROTO_BIT_RC6_6A_32 | \ RC_PROTO_BIT_RC6_MCE | RC_PROTO_BIT_SHARP | \ RC_PROTO_BIT_XMP | RC_PROTO_BIT_CEC | \ - RC_PROTO_BIT_IMON) + RC_PROTO_BIT_IMON | RC_PROTO_BIT_RCMM12 | \ + RC_PROTO_BIT_RCMM24 | RC_PROTO_BIT_RCMM32) /* All rc protocols for which we have decoders */ #define RC_PROTO_BIT_ALL_IR_DECODER \ (RC_PROTO_BIT_RC5 | RC_PROTO_BIT_RC5X_20 | \ @@ -64,7 +68,9 @@ RC_PROTO_BIT_RC6_0 | RC_PROTO_BIT_RC6_6A_20 | \ RC_PROTO_BIT_RC6_6A_24 | RC_PROTO_BIT_RC6_6A_32 | \ RC_PROTO_BIT_RC6_MCE | RC_PROTO_BIT_SHARP | \ - RC_PROTO_BIT_XMP | RC_PROTO_BIT_IMON) + RC_PROTO_BIT_XMP | RC_PROTO_BIT_IMON | \ + RC_PROTO_BIT_RCMM12 | RC_PROTO_BIT_RCMM24 | \ + RC_PROTO_BIT_RCMM32) #define RC_PROTO_BIT_ALL_IR_ENCODER \ (RC_PROTO_BIT_RC5 | RC_PROTO_BIT_RC5X_20 | \ @@ -77,7 +83,9 @@ RC_PROTO_BIT_RC6_0 | RC_PROTO_BIT_RC6_6A_20 | \ RC_PROTO_BIT_RC6_6A_24 | \ RC_PROTO_BIT_RC6_6A_32 | RC_PROTO_BIT_RC6_MCE | \ - RC_PROTO_BIT_SHARP | RC_PROTO_BIT_IMON) + RC_PROTO_BIT_SHARP | RC_PROTO_BIT_IMON | \ + RC_PROTO_BIT_RCMM12 | RC_PROTO_BIT_RCMM24 | \ + RC_PROTO_BIT_RCMM32) #define RC_SCANCODE_UNKNOWN(x) (x) #define RC_SCANCODE_OTHER(x) (x) diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 6b319581882f..45fcbf99d72e 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -192,6 +192,9 @@ struct lirc_scancode { * @RC_PROTO_XMP: XMP protocol * @RC_PROTO_CEC: CEC protocol * @RC_PROTO_IMON: iMon Pad protocol + * @RC_PROTO_RCMM12: RC-MM protocol 12 bits + * @RC_PROTO_RCMM24: RC-MM protocol 24 bits + * @RC_PROTO_RCMM32: RC-MM protocol 32 bits */ enum rc_proto { RC_PROTO_UNKNOWN = 0, @@ -218,6 +221,9 @@ enum rc_proto { RC_PROTO_XMP = 21, RC_PROTO_CEC = 22, RC_PROTO_IMON = 23, + RC_PROTO_RCMM12 = 24, + RC_PROTO_RCMM24 = 25, + RC_PROTO_RCMM32 = 26, }; #endif diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h index f189931042a7..45fcbf99d72e 100644 --- a/tools/include/uapi/linux/lirc.h +++ b/tools/include/uapi/linux/lirc.h @@ -133,6 +133,12 @@ #define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) +/* + * Return the recording timeout, which is either set by + * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols. + */ +#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32) + /* * struct lirc_scancode - decoded scancode with protocol for use with * LIRC_MODE_SCANCODE @@ -186,6 +192,9 @@ struct lirc_scancode { * @RC_PROTO_XMP: XMP protocol * @RC_PROTO_CEC: CEC protocol * @RC_PROTO_IMON: iMon Pad protocol + * @RC_PROTO_RCMM12: RC-MM protocol 12 bits + * @RC_PROTO_RCMM24: RC-MM protocol 24 bits + * @RC_PROTO_RCMM32: RC-MM protocol 32 bits */ enum rc_proto { RC_PROTO_UNKNOWN = 0, @@ -212,6 +221,9 @@ enum rc_proto { RC_PROTO_XMP = 21, RC_PROTO_CEC = 22, RC_PROTO_IMON = 23, + RC_PROTO_RCMM12 = 24, + RC_PROTO_RCMM24 = 25, + RC_PROTO_RCMM32 = 26, }; #endif diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index 858c19caf224..570a7358942c 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -51,6 +51,10 @@ static const struct { { RC_PROTO_RC6_6A_32, "rc-6-6a-32", 0xffffffff, "rc-6" }, { RC_PROTO_RC6_MCE, "rc-6-mce", 0x00007fff, "rc-6" }, { RC_PROTO_SHARP, "sharp", 0x1fff, "sharp" }, + { RC_PROTO_IMON, "imon", 0x7fffffff, "imon" }, + { RC_PROTO_RCMM12, "rcmm-12", 0x00000fff, "rcmm" }, + { RC_PROTO_RCMM24, "rcmm-24", 0x00ffffff, "rcmm" }, + { RC_PROTO_RCMM32, "rcmm-32", 0xffffffff, "rcmm" }, }; int lirc_open(const char *rc) @@ -139,6 +143,11 @@ int main(int argc, char **argv) (((scancode >> 8) ^ ~scancode) & 0xff) == 0) continue; + if (rc_proto == RC_PROTO_RCMM32 && + (scancode & 0x000c0000) != 0x000c0000 && + scancode & 0x00008000) + continue; + struct lirc_scancode lsc = { .rc_proto = rc_proto, .scancode = scancode -- cgit From fadccd8fc2d06cf7fd222245d7e04b00fae946cf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Feb 2019 09:37:13 +0100 Subject: nvme_ioctl.h: remove duplicate GPL boilerplate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We already have a Ð…PDX header, so no need to duplicate the information. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg --- include/linux/nvme.h | 10 +--------- include/uapi/linux/nvme_ioctl.h | 9 --------- 2 files changed, 1 insertion(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bbcc83886899..baa49e6a23cc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1,15 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions for the NVM Express interface * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef _LINUX_NVME_H diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 6e74b1eaf541..1c215ea1798e 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -2,15 +2,6 @@ /* * Definitions for the NVM Express ioctl interface * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef _UAPI_LINUX_NVME_IOCTL_H -- cgit From 61697a6abd24acba941359c6268a94f4afe4a53d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 18 Jan 2019 14:19:26 -0500 Subject: dm: eliminate 'split_discard_bios' flag from DM target interface There is no need to have DM core split discards on behalf of a DM target now that blk_queue_split() handles splitting discards based on the queue_limits. A DM target just needs to set max_discard_sectors, discard_granularity, etc, in queue_limits. Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-target.c | 1 - drivers/md/dm-raid.c | 14 +++++++++----- drivers/md/dm-thin.c | 1 - drivers/md/dm-zoned-target.c | 1 - drivers/md/dm.c | 25 ++++++------------------- include/linux/device-mapper.h | 6 ------ include/uapi/linux/dm-ioctl.h | 4 ++-- 7 files changed, 17 insertions(+), 35 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index b29a8327eed1..adc529f12b6b 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2496,7 +2496,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) ti->num_discard_bios = 1; ti->discards_supported = true; - ti->split_discard_bios = false; ti->per_io_data_size = sizeof(struct per_bio_data); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index adcfe8ae10aa..9fdef6897316 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2986,11 +2986,6 @@ static void configure_discard_support(struct raid_set *rs) } } - /* - * RAID1 and RAID10 personalities require bio splitting, - * RAID0/4/5/6 don't and process large discard bios properly. - */ - ti->split_discard_bios = !!(rs_is_raid1(rs) || rs_is_raid10(rs)); ti->num_discard_bios = 1; } @@ -3747,6 +3742,15 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, chunk_size); blk_limits_io_opt(limits, chunk_size * mddev_data_stripes(rs)); + + /* + * RAID1 and RAID10 personalities require bio splitting, + * RAID0/4/5/6 don't and process large discard bios properly. + */ + if (rs_is_raid1(rs) || rs_is_raid10(rs)) { + limits->discard_granularity = chunk_size; + limits->max_discard_sectors = chunk_size; + } } static void raid_postsuspend(struct dm_target *ti) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index e83b63608262..0d9ded0f5e50 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -4227,7 +4227,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) if (tc->pool->pf.discard_enabled) { ti->discards_supported = true; ti->num_discard_bios = 1; - ti->split_discard_bios = false; } mutex_unlock(&dm_thin_pool_table.mutex); diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 6af5babe6837..8865c1709e16 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -727,7 +727,6 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->per_io_data_size = sizeof(struct dmz_bioctx); ti->flush_supported = true; ti->discards_supported = true; - ti->split_discard_bios = true; /* The exposed capacity is the number of chunks that can be mapped */ ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7a774fcd0194..55f12df3589d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1478,17 +1478,10 @@ static unsigned get_num_write_zeroes_bios(struct dm_target *ti) return ti->num_write_zeroes_bios; } -typedef bool (*is_split_required_fn)(struct dm_target *ti); - -static bool is_split_required_for_discard(struct dm_target *ti) -{ - return ti->split_discard_bios; -} - static int __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti, - unsigned num_bios, bool is_split_required) + unsigned num_bios) { - unsigned len; + unsigned len = ci->sector_count; /* * Even though the device advertised support for this type of @@ -1499,11 +1492,6 @@ static int __send_changing_extent_only(struct clone_info *ci, struct dm_target * if (!num_bios) return -EOPNOTSUPP; - if (!is_split_required) - len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti)); - else - len = min((sector_t)ci->sector_count, max_io_len(ci->sector, ti)); - __send_duplicate_bios(ci, ti, num_bios, &len); ci->sector += len; @@ -1514,23 +1502,22 @@ static int __send_changing_extent_only(struct clone_info *ci, struct dm_target * static int __send_discard(struct clone_info *ci, struct dm_target *ti) { - return __send_changing_extent_only(ci, ti, get_num_discard_bios(ti), - is_split_required_for_discard(ti)); + return __send_changing_extent_only(ci, ti, get_num_discard_bios(ti)); } static int __send_secure_erase(struct clone_info *ci, struct dm_target *ti) { - return __send_changing_extent_only(ci, ti, get_num_secure_erase_bios(ti), false); + return __send_changing_extent_only(ci, ti, get_num_secure_erase_bios(ti)); } static int __send_write_same(struct clone_info *ci, struct dm_target *ti) { - return __send_changing_extent_only(ci, ti, get_num_write_same_bios(ti), false); + return __send_changing_extent_only(ci, ti, get_num_write_same_bios(ti)); } static int __send_write_zeroes(struct clone_info *ci, struct dm_target *ti) { - return __send_changing_extent_only(ci, ti, get_num_write_zeroes_bios(ti), false); + return __send_changing_extent_only(ci, ti, get_num_write_zeroes_bios(ti)); } static bool is_abnormal_io(struct bio *bio) diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e528baebad69..0f5b3d7c6cb3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -315,12 +315,6 @@ struct dm_target { * whether or not its underlying devices have support. */ bool discards_supported:1; - - /* - * Set if the target required discard bios to be split - * on max_io_len boundary. - */ - bool split_discard_bios:1; }; /* Each target can link one of these into the table */ diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index d1e49514977b..f396a82dfd3e 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -270,9 +270,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 39 +#define DM_VERSION_MINOR 40 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2018-04-03)" +#define DM_VERSION_EXTRA "-ioctl (2019-01-18)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit From 228a73abde5c04428678e917b271f8526cfd90ed Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 4 Jan 2019 13:31:54 +0800 Subject: btrfs: introduce new ioctl to unregister a btrfs device Support for a new command that can be used eg. as a command $ btrfs device scan --forget [dev]' (the final name may change though) to undo the effects of 'btrfs device scan [dev]'. For this purpose this patch proposes to use ioctl #5 as it was empty and is next to the SCAN ioctl. The new ioctl BTRFS_IOC_FORGET_DEV works only on the control device (/dev/btrfs-control) to unregister one or all devices, devices that are not mounted. The argument is struct btrfs_ioctl_vol_args, ::name specifies the device path. To unregister all device, the path is an empty string. Again, the devices are removed only if they aren't part of a mounte filesystem. This new ioctl provides: - release of unwanted btrfs_fs_devices and btrfs_devices structures from memory if the device is not going to be mounted - ability to mount filesystem in degraded mode, when one devices is corrupted like in split brain raid1 - running test cases which would require reloading the kernel module but this is not possible eg. due to mounted filesystem or built-in Signed-off-by: Anand Jain Reviewed-by: David Sterba [ update changelog ] Signed-off-by: David Sterba --- fs/btrfs/super.c | 3 +++ fs/btrfs/volumes.c | 11 +++++++++++ fs/btrfs/volumes.h | 1 + include/uapi/linux/btrfs.h | 2 ++ 4 files changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0a3f122dd61f..f9d13a30aa8a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2190,6 +2190,9 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, ret = PTR_ERR_OR_ZERO(device); mutex_unlock(&uuid_mutex); break; + case BTRFS_IOC_FORGET_DEV: + ret = btrfs_forget_devices(vol->name); + break; case BTRFS_IOC_DEVICES_READY: mutex_lock(&uuid_mutex); device = btrfs_scan_one_device(vol->name, FMODE_READ, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 7ca31c83e730..fe122e6099ae 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1446,6 +1446,17 @@ static int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr, return 0; } +int btrfs_forget_devices(const char *path) +{ + int ret; + + mutex_lock(&uuid_mutex); + ret = btrfs_free_stale_devices(strlen(path) ? path : NULL, NULL); + mutex_unlock(&uuid_mutex); + + return ret; +} + /* * Look for a btrfs signature on a device. This may be called out of the mount path * and we are not allowed to call set_blocksize during the scan. The superblock diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 656ea8d85770..3ad9d58d1b66 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -416,6 +416,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fmode_t flags, void *holder); struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, void *holder); +int btrfs_forget_devices(const char *path); int btrfs_close_devices(struct btrfs_fs_devices *fs_devices); void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step); void btrfs_assign_next_active_device(struct btrfs_device *device, diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index e0763bc4158e..c195896d478f 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -837,6 +837,8 @@ enum btrfs_err_code { struct btrfs_ioctl_vol_args) #define BTRFS_IOC_SCAN_DEV _IOW(BTRFS_IOCTL_MAGIC, 4, \ struct btrfs_ioctl_vol_args) +#define BTRFS_IOC_FORGET_DEV _IOW(BTRFS_IOCTL_MAGIC, 5, \ + struct btrfs_ioctl_vol_args) /* trans start and trans end are dangerous, and only for * use by applications that know how to avoid the * resulting deadlocks -- cgit From e5567f5f67621877726f99be040af9fbedda37dc Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Tue, 19 Feb 2019 11:04:51 -0800 Subject: PCI/ATS: Add pci_prg_resp_pasid_required() interface. Return the PRG Response PASID Required bit in the Page Request Status Register. As per PCIe spec r4.0, sec 10.5.2.3, if this bit is Set, the device expects a PASID TLP Prefix on PRG Response Messages when the corresponding Page Requests had a PASID TLP Prefix. If Clear, the device does not expect PASID TLP Prefixes on any PRG Response Message, and the device behavior is undefined if the device receives a PRG Response Message with a PASID TLP Prefix. Also the device behavior is undefined if this bit is Set and the device receives a PRG Response Message with no PASID TLP Prefix when the corresponding Page Requests had a PASID TLP Prefix. This function will be used by drivers like IOMMU, if it is required to check the status of the PRG Response PASID Required bit before enabling the PASID support of the device. Cc: Ashok Raj Cc: Jacob Pan Cc: Keith Busch Suggested-by: Ashok Raj Signed-off-by: Kuppuswamy Sathyanarayanan Acked-by: Bjorn Helgaas Signed-off-by: Joerg Roedel --- drivers/pci/ats.c | 30 ++++++++++++++++++++++++++++++ include/linux/pci-ats.h | 5 +++++ include/uapi/linux/pci_regs.h | 1 + 3 files changed, 36 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 5b78f3b1b918..420cd0a578d0 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -368,6 +368,36 @@ int pci_pasid_features(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(pci_pasid_features); +/** + * pci_prg_resp_pasid_required - Return PRG Response PASID Required bit + * status. + * @pdev: PCI device structure + * + * Returns 1 if PASID is required in PRG Response Message, 0 otherwise. + * + * Even though the PRG response PASID status is read from PRI Status + * Register, since this API will mainly be used by PASID users, this + * function is defined within #ifdef CONFIG_PCI_PASID instead of + * CONFIG_PCI_PRI. + */ +int pci_prg_resp_pasid_required(struct pci_dev *pdev) +{ + u16 status; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); + if (!pos) + return 0; + + pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + + if (status & PCI_PRI_STATUS_PASID) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); + #define PASID_NUMBER_SHIFT 8 #define PASID_NUMBER_MASK (0x1f << PASID_NUMBER_SHIFT) /** diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 7c4b8e27268c..facfd6a18fe1 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -40,6 +40,7 @@ void pci_disable_pasid(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); +int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ @@ -66,6 +67,10 @@ static inline int pci_max_pasids(struct pci_dev *pdev) return -EINVAL; } +static int pci_prg_resp_pasid_required(struct pci_dev *pdev) +{ + return 0; +} #endif /* CONFIG_PCI_PASID */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e1e9888c85e6..898be572b010 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -880,6 +880,7 @@ #define PCI_PRI_STATUS_RF 0x001 /* Response Failure */ #define PCI_PRI_STATUS_UPRGI 0x002 /* Unexpected PRG index */ #define PCI_PRI_STATUS_STOPPED 0x100 /* PRI Stopped */ +#define PCI_PRI_STATUS_PASID 0x8000 /* PRG Response PASID Required */ #define PCI_PRI_MAX_REQ 0x08 /* PRI max reqs supported */ #define PCI_PRI_ALLOC_REQ 0x0c /* PRI max reqs allowed */ #define PCI_EXT_CAP_PRI_SIZEOF 16 -- cgit From 8c938ddc6df3bbe72809db1be6c9f3af83f5d7a9 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Tue, 19 Feb 2019 11:06:09 -0800 Subject: PCI/ATS: Add pci_ats_page_aligned() interface Return the Page Aligned Request bit in the ATS Capability Register. As per PCIe spec r4.0, sec 10.5.1.2, if the Page Aligned Request bit is set, it indicates the Untranslated Addresses generated by the device are always aligned to a 4096 byte boundary. An IOMMU that can only translate page-aligned addresses can only be used with devices that always produce aligned Untranslated Addresses. This interface will be used by drivers for such IOMMUs to determine whether devices can use the ATS service. Cc: Ashok Raj Cc: Jacob Pan Cc: Keith Busch Suggested-by: Ashok Raj Signed-off-by: Kuppuswamy Sathyanarayanan Acked-by: Bjorn Helgaas Signed-off-by: Joerg Roedel --- drivers/pci/ats.c | 27 +++++++++++++++++++++++++++ include/linux/pci.h | 2 ++ include/uapi/linux/pci_regs.h | 1 + 3 files changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 420cd0a578d0..97c08146534a 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -142,6 +142,33 @@ int pci_ats_queue_depth(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_ats_queue_depth); +/** + * pci_ats_page_aligned - Return Page Aligned Request bit status. + * @pdev: the PCI device + * + * Returns 1, if the Untranslated Addresses generated by the device + * are always aligned or 0 otherwise. + * + * Per PCIe spec r4.0, sec 10.5.1.2, if the Page Aligned Request bit + * is set, it indicates the Untranslated Addresses generated by the + * device are always aligned to a 4096 byte boundary. + */ +int pci_ats_page_aligned(struct pci_dev *pdev) +{ + u16 cap; + + if (!pdev->ats_cap) + return 0; + + pci_read_config_word(pdev, pdev->ats_cap + PCI_ATS_CAP, &cap); + + if (cap & PCI_ATS_CAP_PAGE_ALIGNED) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_ats_page_aligned); + #ifdef CONFIG_PCI_PRI /** * pci_enable_pri - Enable PRI capability diff --git a/include/linux/pci.h b/include/linux/pci.h index 65f1d8c2f082..9724a8c0496b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1524,11 +1524,13 @@ void pci_ats_init(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); +int pci_ats_page_aligned(struct pci_dev *dev); #else static inline void pci_ats_init(struct pci_dev *d) { } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } +static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } #endif #ifdef CONFIG_PCIE_PTM diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 898be572b010..5c98133f2c94 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -866,6 +866,7 @@ #define PCI_ATS_CAP 0x04 /* ATS Capability Register */ #define PCI_ATS_CAP_QDEP(x) ((x) & 0x1f) /* Invalidate Queue Depth */ #define PCI_ATS_MAX_QDEP 32 /* Max Invalidate Queue Depth */ +#define PCI_ATS_CAP_PAGE_ALIGNED 0x0020 /* Page Aligned Request */ #define PCI_ATS_CTRL 0x06 /* ATS Control Register */ #define PCI_ATS_CTRL_ENABLE 0x8000 /* ATS Enable */ #define PCI_ATS_CTRL_STU(x) ((x) & 0x1f) /* Smallest Translation Unit */ -- cgit From 2b188cc1bb857a9d4701ae59aa7768b5124e262e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 7 Jan 2019 10:46:33 -0700 Subject: Add io_uring IO interface The submission queue (SQ) and completion queue (CQ) rings are shared between the application and the kernel. This eliminates the need to copy data back and forth to submit and complete IO. IO submissions use the io_uring_sqe data structure, and completions are generated in the form of io_uring_cqe data structures. The SQ ring is an index into the io_uring_sqe array, which makes it possible to submit a batch of IOs without them being contiguous in the ring. The CQ ring is always contiguous, as completion events are inherently unordered, and hence any io_uring_cqe entry can point back to an arbitrary submission. Two new system calls are added for this: io_uring_setup(entries, params) Sets up an io_uring instance for doing async IO. On success, returns a file descriptor that the application can mmap to gain access to the SQ ring, CQ ring, and io_uring_sqes. io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize) Initiates IO against the rings mapped to this fd, or waits for them to complete, or both. The behavior is controlled by the parameters passed in. If 'to_submit' is non-zero, then we'll try and submit new IO. If IORING_ENTER_GETEVENTS is set, the kernel will wait for 'min_complete' events, if they aren't already available. It's valid to set IORING_ENTER_GETEVENTS and 'min_complete' == 0 at the same time, this allows the kernel to return already completed events without waiting for them. This is useful only for polling, as for IRQ driven IO, the application can just check the CQ ring without entering the kernel. With this setup, it's possible to do async IO with a single system call. Future developments will enable polled IO with this interface, and polled submission as well. The latter will enable an application to do IO without doing ANY system calls at all. For IRQ driven IO, an application only needs to enter the kernel for completions if it wants to wait for them to occur. Each io_uring is backed by a workqueue, to support buffered async IO as well. We will only punt to an async context if the command would need to wait for IO on the device side. Any data that can be accessed directly in the page cache is done inline. This avoids the slowness issue of usual threadpools, since cached data is accessed as quickly as a sync interface. Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- arch/x86/entry/syscalls/syscall_32.tbl | 2 + arch/x86/entry/syscalls/syscall_64.tbl | 2 + fs/Makefile | 1 + fs/io_uring.c | 1255 ++++++++++++++++++++++++++++++++ include/linux/fs.h | 9 + include/linux/sched/user.h | 2 +- include/linux/syscalls.h | 6 + include/uapi/asm-generic/unistd.h | 6 +- include/uapi/linux/io_uring.h | 95 +++ init/Kconfig | 9 + kernel/sys_ni.c | 2 + net/unix/garbage.c | 3 + 12 files changed, 1390 insertions(+), 2 deletions(-) create mode 100644 fs/io_uring.c create mode 100644 include/uapi/linux/io_uring.h (limited to 'include/uapi/linux') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 3cf7b533b3d1..481c126259e9 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -398,3 +398,5 @@ 384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl 385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents 386 i386 rseq sys_rseq __ia32_sys_rseq +425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup +426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f0b1709a5ffb..6a32a430c8e0 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -343,6 +343,8 @@ 332 common statx __x64_sys_statx 333 common io_pgetevents __x64_sys_io_pgetevents 334 common rseq __x64_sys_rseq +425 common io_uring_setup __x64_sys_io_uring_setup +426 common io_uring_enter __x64_sys_io_uring_enter # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/fs/Makefile b/fs/Makefile index 293733f61594..8e15d6fc4340 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o +obj-$(CONFIG_IO_URING) += io_uring.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FILE_LOCKING) += locks.o diff --git a/fs/io_uring.c b/fs/io_uring.c new file mode 100644 index 000000000000..f68052290426 --- /dev/null +++ b/fs/io_uring.c @@ -0,0 +1,1255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shared application/kernel submission and completion ring pairs, for + * supporting fast/efficient IO. + * + * A note on the read/write ordering memory barriers that are matched between + * the application and kernel side. When the application reads the CQ ring + * tail, it must use an appropriate smp_rmb() to order with the smp_wmb() + * the kernel uses after writing the tail. Failure to do so could cause a + * delay in when the application notices that completion events available. + * This isn't a fatal condition. Likewise, the application must use an + * appropriate smp_wmb() both before writing the SQ tail, and after writing + * the SQ tail. The first one orders the sqe writes with the tail write, and + * the latter is paired with the smp_rmb() the kernel will issue before + * reading the SQ tail on submission. + * + * Also see the examples in the liburing library: + * + * git://git.kernel.dk/liburing + * + * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens + * from data shared between the kernel and application. This is done both + * for ordering purposes, but also to ensure that once a value is loaded from + * data that the application could potentially modify, it remains stable. + * + * Copyright (C) 2018-2019 Jens Axboe + */ +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +#define IORING_MAX_ENTRIES 4096 + +struct io_uring { + u32 head ____cacheline_aligned_in_smp; + u32 tail ____cacheline_aligned_in_smp; +}; + +struct io_sq_ring { + struct io_uring r; + u32 ring_mask; + u32 ring_entries; + u32 dropped; + u32 flags; + u32 array[]; +}; + +struct io_cq_ring { + struct io_uring r; + u32 ring_mask; + u32 ring_entries; + u32 overflow; + struct io_uring_cqe cqes[]; +}; + +struct io_ring_ctx { + struct { + struct percpu_ref refs; + } ____cacheline_aligned_in_smp; + + struct { + unsigned int flags; + bool compat; + bool account_mem; + + /* SQ ring */ + struct io_sq_ring *sq_ring; + unsigned cached_sq_head; + unsigned sq_entries; + unsigned sq_mask; + struct io_uring_sqe *sq_sqes; + } ____cacheline_aligned_in_smp; + + /* IO offload */ + struct workqueue_struct *sqo_wq; + struct mm_struct *sqo_mm; + + struct { + /* CQ ring */ + struct io_cq_ring *cq_ring; + unsigned cached_cq_tail; + unsigned cq_entries; + unsigned cq_mask; + struct wait_queue_head cq_wait; + struct fasync_struct *cq_fasync; + } ____cacheline_aligned_in_smp; + + struct user_struct *user; + + struct completion ctx_done; + + struct { + struct mutex uring_lock; + wait_queue_head_t wait; + } ____cacheline_aligned_in_smp; + + struct { + spinlock_t completion_lock; + } ____cacheline_aligned_in_smp; + +#if defined(CONFIG_UNIX) + struct socket *ring_sock; +#endif +}; + +struct sqe_submit { + const struct io_uring_sqe *sqe; + unsigned short index; + bool has_user; +}; + +struct io_kiocb { + struct kiocb rw; + + struct sqe_submit submit; + + struct io_ring_ctx *ctx; + struct list_head list; + unsigned int flags; +#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ + u64 user_data; + + struct work_struct work; +}; + +#define IO_PLUG_THRESHOLD 2 + +static struct kmem_cache *req_cachep; + +static const struct file_operations io_uring_fops; + +struct sock *io_uring_get_socket(struct file *file) +{ +#if defined(CONFIG_UNIX) + if (file->f_op == &io_uring_fops) { + struct io_ring_ctx *ctx = file->private_data; + + return ctx->ring_sock->sk; + } +#endif + return NULL; +} +EXPORT_SYMBOL(io_uring_get_socket); + +static void io_ring_ctx_ref_free(struct percpu_ref *ref) +{ + struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); + + complete(&ctx->ctx_done); +} + +static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) +{ + struct io_ring_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, 0, GFP_KERNEL)) { + kfree(ctx); + return NULL; + } + + ctx->flags = p->flags; + init_waitqueue_head(&ctx->cq_wait); + init_completion(&ctx->ctx_done); + mutex_init(&ctx->uring_lock); + init_waitqueue_head(&ctx->wait); + spin_lock_init(&ctx->completion_lock); + return ctx; +} + +static void io_commit_cqring(struct io_ring_ctx *ctx) +{ + struct io_cq_ring *ring = ctx->cq_ring; + + if (ctx->cached_cq_tail != READ_ONCE(ring->r.tail)) { + /* order cqe stores with ring update */ + smp_store_release(&ring->r.tail, ctx->cached_cq_tail); + + /* + * Write sider barrier of tail update, app has read side. See + * comment at the top of this file. + */ + smp_wmb(); + + if (wq_has_sleeper(&ctx->cq_wait)) { + wake_up_interruptible(&ctx->cq_wait); + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); + } + } +} + +static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) +{ + struct io_cq_ring *ring = ctx->cq_ring; + unsigned tail; + + tail = ctx->cached_cq_tail; + /* See comment at the top of the file */ + smp_rmb(); + if (tail + 1 == READ_ONCE(ring->r.head)) + return NULL; + + ctx->cached_cq_tail++; + return &ring->cqes[tail & ctx->cq_mask]; +} + +static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, + long res, unsigned ev_flags) +{ + struct io_uring_cqe *cqe; + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqring(ctx); + if (cqe) { + WRITE_ONCE(cqe->user_data, ki_user_data); + WRITE_ONCE(cqe->res, res); + WRITE_ONCE(cqe->flags, ev_flags); + } else { + unsigned overflow = READ_ONCE(ctx->cq_ring->overflow); + + WRITE_ONCE(ctx->cq_ring->overflow, overflow + 1); + } +} + +static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data, + long res, unsigned ev_flags) +{ + unsigned long flags; + + spin_lock_irqsave(&ctx->completion_lock, flags); + io_cqring_fill_event(ctx, ki_user_data, res, ev_flags); + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); +} + +static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) +{ + percpu_ref_put_many(&ctx->refs, refs); + + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); +} + +static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx) +{ + struct io_kiocb *req; + + if (!percpu_ref_tryget(&ctx->refs)) + return NULL; + + req = kmem_cache_alloc(req_cachep, __GFP_NOWARN); + if (req) { + req->ctx = ctx; + req->flags = 0; + return req; + } + + io_ring_drop_ctx_refs(ctx, 1); + return NULL; +} + +static void io_free_req(struct io_kiocb *req) +{ + io_ring_drop_ctx_refs(req->ctx, 1); + kmem_cache_free(req_cachep, req); +} + +static void kiocb_end_write(struct kiocb *kiocb) +{ + if (kiocb->ki_flags & IOCB_WRITE) { + struct inode *inode = file_inode(kiocb->ki_filp); + + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + if (S_ISREG(inode->i_mode)) + __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); + file_end_write(kiocb->ki_filp); + } +} + +static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + + kiocb_end_write(kiocb); + + fput(kiocb->ki_filp); + io_cqring_add_event(req->ctx, req->user_data, res, 0); + io_free_req(req); +} + +/* + * If we tracked the file through the SCM inflight mechanism, we could support + * any file. For now, just ensure that anything potentially problematic is done + * inline. + */ +static bool io_file_supports_async(struct file *file) +{ + umode_t mode = file_inode(file)->i_mode; + + if (S_ISBLK(mode) || S_ISCHR(mode)) + return true; + if (S_ISREG(mode) && file->f_op != &io_uring_fops) + return true; + + return false; +} + +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) +{ + struct kiocb *kiocb = &req->rw; + unsigned ioprio; + int fd, ret; + + /* For -EAGAIN retry, everything is already prepped */ + if (kiocb->ki_filp) + return 0; + + fd = READ_ONCE(sqe->fd); + kiocb->ki_filp = fget(fd); + if (unlikely(!kiocb->ki_filp)) + return -EBADF; + if (force_nonblock && !io_file_supports_async(kiocb->ki_filp)) + force_nonblock = false; + kiocb->ki_pos = READ_ONCE(sqe->off); + kiocb->ki_flags = iocb_flags(kiocb->ki_filp); + kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); + + ioprio = READ_ONCE(sqe->ioprio); + if (ioprio) { + ret = ioprio_check_cap(ioprio); + if (ret) + goto out_fput; + + kiocb->ki_ioprio = ioprio; + } else + kiocb->ki_ioprio = get_current_ioprio(); + + ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); + if (unlikely(ret)) + goto out_fput; + if (force_nonblock) { + kiocb->ki_flags |= IOCB_NOWAIT; + req->flags |= REQ_F_FORCE_NONBLOCK; + } + if (kiocb->ki_flags & IOCB_HIPRI) { + ret = -EINVAL; + goto out_fput; + } + + kiocb->ki_complete = io_complete_rw; + return 0; +out_fput: + fput(kiocb->ki_filp); + return ret; +} + +static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) +{ + switch (ret) { + case -EIOCBQUEUED: + break; + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + /* + * We can't just restart the syscall, since previously + * submitted sqes may already be in progress. Just fail this + * IO with EINTR. + */ + ret = -EINTR; + /* fall through */ + default: + kiocb->ki_complete(kiocb, ret, 0); + } +} + +static int io_import_iovec(struct io_ring_ctx *ctx, int rw, + const struct sqe_submit *s, struct iovec **iovec, + struct iov_iter *iter) +{ + const struct io_uring_sqe *sqe = s->sqe; + void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + size_t sqe_len = READ_ONCE(sqe->len); + + if (!s->has_user) + return -EFAULT; + +#ifdef CONFIG_COMPAT + if (ctx->compat) + return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV, + iovec, iter); +#endif + + return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter); +} + +static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s, + bool force_nonblock) +{ + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct kiocb *kiocb = &req->rw; + struct iov_iter iter; + struct file *file; + ssize_t ret; + + ret = io_prep_rw(req, s->sqe, force_nonblock); + if (ret) + return ret; + file = kiocb->ki_filp; + + ret = -EBADF; + if (unlikely(!(file->f_mode & FMODE_READ))) + goto out_fput; + ret = -EINVAL; + if (unlikely(!file->f_op->read_iter)) + goto out_fput; + + ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter); + if (ret) + goto out_fput; + + ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_iter_count(&iter)); + if (!ret) { + ssize_t ret2; + + /* Catch -EAGAIN return for forced non-blocking submission */ + ret2 = call_read_iter(file, kiocb, &iter); + if (!force_nonblock || ret2 != -EAGAIN) + io_rw_done(kiocb, ret2); + else + ret = -EAGAIN; + } + kfree(iovec); +out_fput: + /* Hold on to the file for -EAGAIN */ + if (unlikely(ret && ret != -EAGAIN)) + fput(file); + return ret; +} + +static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, + bool force_nonblock) +{ + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct kiocb *kiocb = &req->rw; + struct iov_iter iter; + struct file *file; + ssize_t ret; + + ret = io_prep_rw(req, s->sqe, force_nonblock); + if (ret) + return ret; + /* Hold on to the file for -EAGAIN */ + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) + return -EAGAIN; + + ret = -EBADF; + file = kiocb->ki_filp; + if (unlikely(!(file->f_mode & FMODE_WRITE))) + goto out_fput; + ret = -EINVAL; + if (unlikely(!file->f_op->write_iter)) + goto out_fput; + + ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter); + if (ret) + goto out_fput; + + ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, + iov_iter_count(&iter)); + if (!ret) { + /* + * Open-code file_start_write here to grab freeze protection, + * which will be released by another thread in + * io_complete_rw(). Fool lockdep by telling it the lock got + * released so that it doesn't complain about the held lock when + * we return to userspace. + */ + if (S_ISREG(file_inode(file)->i_mode)) { + __sb_start_write(file_inode(file)->i_sb, + SB_FREEZE_WRITE, true); + __sb_writers_release(file_inode(file)->i_sb, + SB_FREEZE_WRITE); + } + kiocb->ki_flags |= IOCB_WRITE; + io_rw_done(kiocb, call_write_iter(file, kiocb, &iter)); + } + kfree(iovec); +out_fput: + if (unlikely(ret)) + fput(file); + return ret; +} + +/* + * IORING_OP_NOP just posts a completion event, nothing else. + */ +static int io_nop(struct io_kiocb *req, u64 user_data) +{ + struct io_ring_ctx *ctx = req->ctx; + long err = 0; + + /* + * Twilight zone - it's possible that someone issued an opcode that + * has a file attached, then got -EAGAIN on submission, and changed + * the sqe before we retried it from async context. Avoid dropping + * a file reference for this malicious case, and flag the error. + */ + if (req->rw.ki_filp) { + err = -EBADF; + fput(req->rw.ki_filp); + } + io_cqring_add_event(ctx, user_data, err, 0); + io_free_req(req); + return 0; +} + +static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct sqe_submit *s, bool force_nonblock) +{ + ssize_t ret; + int opcode; + + if (unlikely(s->index >= ctx->sq_entries)) + return -EINVAL; + req->user_data = READ_ONCE(s->sqe->user_data); + + opcode = READ_ONCE(s->sqe->opcode); + switch (opcode) { + case IORING_OP_NOP: + ret = io_nop(req, req->user_data); + break; + case IORING_OP_READV: + ret = io_read(req, s, force_nonblock); + break; + case IORING_OP_WRITEV: + ret = io_write(req, s, force_nonblock); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static void io_sq_wq_submit_work(struct work_struct *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct sqe_submit *s = &req->submit; + const struct io_uring_sqe *sqe = s->sqe; + struct io_ring_ctx *ctx = req->ctx; + mm_segment_t old_fs = get_fs(); + int ret; + + /* Ensure we clear previously set forced non-block flag */ + req->flags &= ~REQ_F_FORCE_NONBLOCK; + req->rw.ki_flags &= ~IOCB_NOWAIT; + + if (!mmget_not_zero(ctx->sqo_mm)) { + ret = -EFAULT; + goto err; + } + + use_mm(ctx->sqo_mm); + set_fs(USER_DS); + s->has_user = true; + + ret = __io_submit_sqe(ctx, req, s, false); + + set_fs(old_fs); + unuse_mm(ctx->sqo_mm); + mmput(ctx->sqo_mm); +err: + if (ret) { + io_cqring_add_event(ctx, sqe->user_data, ret, 0); + io_free_req(req); + } + + /* async context always use a copy of the sqe */ + kfree(sqe); +} + +static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s) +{ + struct io_kiocb *req; + ssize_t ret; + + /* enforce forwards compatibility on users */ + if (unlikely(s->sqe->flags)) + return -EINVAL; + + req = io_get_req(ctx); + if (unlikely(!req)) + return -EAGAIN; + + req->rw.ki_filp = NULL; + + ret = __io_submit_sqe(ctx, req, s, true); + if (ret == -EAGAIN) { + struct io_uring_sqe *sqe_copy; + + sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); + if (sqe_copy) { + memcpy(sqe_copy, s->sqe, sizeof(*sqe_copy)); + s->sqe = sqe_copy; + + memcpy(&req->submit, s, sizeof(*s)); + INIT_WORK(&req->work, io_sq_wq_submit_work); + queue_work(ctx->sqo_wq, &req->work); + ret = 0; + } + } + if (ret) + io_free_req(req); + + return ret; +} + +static void io_commit_sqring(struct io_ring_ctx *ctx) +{ + struct io_sq_ring *ring = ctx->sq_ring; + + if (ctx->cached_sq_head != READ_ONCE(ring->r.head)) { + /* + * Ensure any loads from the SQEs are done at this point, + * since once we write the new head, the application could + * write new data to them. + */ + smp_store_release(&ring->r.head, ctx->cached_sq_head); + + /* + * write side barrier of head update, app has read side. See + * comment at the top of this file + */ + smp_wmb(); + } +} + +/* + * Undo last io_get_sqring() + */ +static void io_drop_sqring(struct io_ring_ctx *ctx) +{ + ctx->cached_sq_head--; +} + +/* + * Fetch an sqe, if one is available. Note that s->sqe will point to memory + * that is mapped by userspace. This means that care needs to be taken to + * ensure that reads are stable, as we cannot rely on userspace always + * being a good citizen. If members of the sqe are validated and then later + * used, it's important that those reads are done through READ_ONCE() to + * prevent a re-load down the line. + */ +static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) +{ + struct io_sq_ring *ring = ctx->sq_ring; + unsigned head; + + /* + * The cached sq head (or cq tail) serves two purposes: + * + * 1) allows us to batch the cost of updating the user visible + * head updates. + * 2) allows the kernel side to track the head on its own, even + * though the application is the one updating it. + */ + head = ctx->cached_sq_head; + /* See comment at the top of this file */ + smp_rmb(); + if (head == READ_ONCE(ring->r.tail)) + return false; + + head = READ_ONCE(ring->array[head & ctx->sq_mask]); + if (head < ctx->sq_entries) { + s->index = head; + s->sqe = &ctx->sq_sqes[head]; + ctx->cached_sq_head++; + return true; + } + + /* drop invalid entries */ + ctx->cached_sq_head++; + ring->dropped++; + /* See comment at the top of this file */ + smp_wmb(); + return false; +} + +static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) +{ + int i, ret = 0, submit = 0; + struct blk_plug plug; + + if (to_submit > IO_PLUG_THRESHOLD) + blk_start_plug(&plug); + + for (i = 0; i < to_submit; i++) { + struct sqe_submit s; + + if (!io_get_sqring(ctx, &s)) + break; + + s.has_user = true; + ret = io_submit_sqe(ctx, &s); + if (ret) { + io_drop_sqring(ctx); + break; + } + + submit++; + } + io_commit_sqring(ctx); + + if (to_submit > IO_PLUG_THRESHOLD) + blk_finish_plug(&plug); + + return submit ? submit : ret; +} + +static unsigned io_cqring_events(struct io_cq_ring *ring) +{ + return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head); +} + +/* + * Wait until events become available, if we don't already have some. The + * application must reap them itself, as they reside on the shared cq ring. + */ +static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, + const sigset_t __user *sig, size_t sigsz) +{ + struct io_cq_ring *ring = ctx->cq_ring; + sigset_t ksigmask, sigsaved; + DEFINE_WAIT(wait); + int ret; + + /* See comment at the top of this file */ + smp_rmb(); + if (io_cqring_events(ring) >= min_events) + return 0; + + if (sig) { + ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz); + if (ret) + return ret; + } + + do { + prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE); + + ret = 0; + /* See comment at the top of this file */ + smp_rmb(); + if (io_cqring_events(ring) >= min_events) + break; + + schedule(); + + ret = -EINTR; + if (signal_pending(current)) + break; + } while (1); + + finish_wait(&ctx->wait, &wait); + + if (sig) + restore_user_sigmask(sig, &sigsaved); + + return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0; +} + +static int io_sq_offload_start(struct io_ring_ctx *ctx) +{ + int ret; + + mmgrab(current->mm); + ctx->sqo_mm = current->mm; + + /* Do QD, or 2 * CPUS, whatever is smallest */ + ctx->sqo_wq = alloc_workqueue("io_ring-wq", WQ_UNBOUND | WQ_FREEZABLE, + min(ctx->sq_entries - 1, 2 * num_online_cpus())); + if (!ctx->sqo_wq) { + ret = -ENOMEM; + goto err; + } + + return 0; +err: + mmdrop(ctx->sqo_mm); + ctx->sqo_mm = NULL; + return ret; +} + +static void io_unaccount_mem(struct user_struct *user, unsigned long nr_pages) +{ + atomic_long_sub(nr_pages, &user->locked_vm); +} + +static int io_account_mem(struct user_struct *user, unsigned long nr_pages) +{ + unsigned long page_limit, cur_pages, new_pages; + + /* Don't allow more pages than we can safely lock */ + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + do { + cur_pages = atomic_long_read(&user->locked_vm); + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return -ENOMEM; + } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, + new_pages) != cur_pages); + + return 0; +} + +static void io_mem_free(void *ptr) +{ + struct page *page = virt_to_head_page(ptr); + + if (put_page_testzero(page)) + free_compound_page(page); +} + +static void *io_mem_alloc(size_t size) +{ + gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP | + __GFP_NORETRY; + + return (void *) __get_free_pages(gfp_flags, get_order(size)); +} + +static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries) +{ + struct io_sq_ring *sq_ring; + struct io_cq_ring *cq_ring; + size_t bytes; + + bytes = struct_size(sq_ring, array, sq_entries); + bytes += array_size(sizeof(struct io_uring_sqe), sq_entries); + bytes += struct_size(cq_ring, cqes, cq_entries); + + return (bytes + PAGE_SIZE - 1) / PAGE_SIZE; +} + +static void io_ring_ctx_free(struct io_ring_ctx *ctx) +{ + if (ctx->sqo_wq) + destroy_workqueue(ctx->sqo_wq); + if (ctx->sqo_mm) + mmdrop(ctx->sqo_mm); +#if defined(CONFIG_UNIX) + if (ctx->ring_sock) + sock_release(ctx->ring_sock); +#endif + + io_mem_free(ctx->sq_ring); + io_mem_free(ctx->sq_sqes); + io_mem_free(ctx->cq_ring); + + percpu_ref_exit(&ctx->refs); + if (ctx->account_mem) + io_unaccount_mem(ctx->user, + ring_pages(ctx->sq_entries, ctx->cq_entries)); + free_uid(ctx->user); + kfree(ctx); +} + +static __poll_t io_uring_poll(struct file *file, poll_table *wait) +{ + struct io_ring_ctx *ctx = file->private_data; + __poll_t mask = 0; + + poll_wait(file, &ctx->cq_wait, wait); + /* See comment at the top of this file */ + smp_rmb(); + if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head) + mask |= EPOLLOUT | EPOLLWRNORM; + if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static int io_uring_fasync(int fd, struct file *file, int on) +{ + struct io_ring_ctx *ctx = file->private_data; + + return fasync_helper(fd, file, on, &ctx->cq_fasync); +} + +static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) +{ + mutex_lock(&ctx->uring_lock); + percpu_ref_kill(&ctx->refs); + mutex_unlock(&ctx->uring_lock); + + wait_for_completion(&ctx->ctx_done); + io_ring_ctx_free(ctx); +} + +static int io_uring_release(struct inode *inode, struct file *file) +{ + struct io_ring_ctx *ctx = file->private_data; + + file->private_data = NULL; + io_ring_ctx_wait_and_kill(ctx); + return 0; +} + +static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) +{ + loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT; + unsigned long sz = vma->vm_end - vma->vm_start; + struct io_ring_ctx *ctx = file->private_data; + unsigned long pfn; + struct page *page; + void *ptr; + + switch (offset) { + case IORING_OFF_SQ_RING: + ptr = ctx->sq_ring; + break; + case IORING_OFF_SQES: + ptr = ctx->sq_sqes; + break; + case IORING_OFF_CQ_RING: + ptr = ctx->cq_ring; + break; + default: + return -EINVAL; + } + + page = virt_to_head_page(ptr); + if (sz > (PAGE_SIZE << compound_order(page))) + return -EINVAL; + + pfn = virt_to_phys(ptr) >> PAGE_SHIFT; + return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); +} + +SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, + u32, min_complete, u32, flags, const sigset_t __user *, sig, + size_t, sigsz) +{ + struct io_ring_ctx *ctx; + long ret = -EBADF; + int submitted = 0; + struct fd f; + + if (flags & ~IORING_ENTER_GETEVENTS) + return -EINVAL; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = -EOPNOTSUPP; + if (f.file->f_op != &io_uring_fops) + goto out_fput; + + ret = -ENXIO; + ctx = f.file->private_data; + if (!percpu_ref_tryget(&ctx->refs)) + goto out_fput; + + ret = 0; + if (to_submit) { + to_submit = min(to_submit, ctx->sq_entries); + + mutex_lock(&ctx->uring_lock); + submitted = io_ring_submit(ctx, to_submit); + mutex_unlock(&ctx->uring_lock); + + if (submitted < 0) + goto out_ctx; + } + if (flags & IORING_ENTER_GETEVENTS) { + min_complete = min(min_complete, ctx->cq_entries); + + /* + * The application could have included the 'to_submit' count + * in how many events it wanted to wait for. If we failed to + * submit the desired count, we may need to adjust the number + * of events to poll/wait for. + */ + if (submitted < to_submit) + min_complete = min_t(unsigned, submitted, min_complete); + + ret = io_cqring_wait(ctx, min_complete, sig, sigsz); + } + +out_ctx: + io_ring_drop_ctx_refs(ctx, 1); +out_fput: + fdput(f); + return submitted ? submitted : ret; +} + +static const struct file_operations io_uring_fops = { + .release = io_uring_release, + .mmap = io_uring_mmap, + .poll = io_uring_poll, + .fasync = io_uring_fasync, +}; + +static int io_allocate_scq_urings(struct io_ring_ctx *ctx, + struct io_uring_params *p) +{ + struct io_sq_ring *sq_ring; + struct io_cq_ring *cq_ring; + size_t size; + + sq_ring = io_mem_alloc(struct_size(sq_ring, array, p->sq_entries)); + if (!sq_ring) + return -ENOMEM; + + ctx->sq_ring = sq_ring; + sq_ring->ring_mask = p->sq_entries - 1; + sq_ring->ring_entries = p->sq_entries; + ctx->sq_mask = sq_ring->ring_mask; + ctx->sq_entries = sq_ring->ring_entries; + + size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); + if (size == SIZE_MAX) + return -EOVERFLOW; + + ctx->sq_sqes = io_mem_alloc(size); + if (!ctx->sq_sqes) { + io_mem_free(ctx->sq_ring); + return -ENOMEM; + } + + cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries)); + if (!cq_ring) { + io_mem_free(ctx->sq_ring); + io_mem_free(ctx->sq_sqes); + return -ENOMEM; + } + + ctx->cq_ring = cq_ring; + cq_ring->ring_mask = p->cq_entries - 1; + cq_ring->ring_entries = p->cq_entries; + ctx->cq_mask = cq_ring->ring_mask; + ctx->cq_entries = cq_ring->ring_entries; + return 0; +} + +/* + * Allocate an anonymous fd, this is what constitutes the application + * visible backing of an io_uring instance. The application mmaps this + * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, + * we have to tie this fd to a socket for file garbage collection purposes. + */ +static int io_uring_get_fd(struct io_ring_ctx *ctx) +{ + struct file *file; + int ret; + +#if defined(CONFIG_UNIX) + ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, + &ctx->ring_sock); + if (ret) + return ret; +#endif + + ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + if (ret < 0) + goto err; + + file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, + O_RDWR | O_CLOEXEC); + if (IS_ERR(file)) { + put_unused_fd(ret); + ret = PTR_ERR(file); + goto err; + } + +#if defined(CONFIG_UNIX) + ctx->ring_sock->file = file; +#endif + fd_install(ret, file); + return ret; +err: +#if defined(CONFIG_UNIX) + sock_release(ctx->ring_sock); + ctx->ring_sock = NULL; +#endif + return ret; +} + +static int io_uring_create(unsigned entries, struct io_uring_params *p) +{ + struct user_struct *user = NULL; + struct io_ring_ctx *ctx; + bool account_mem; + int ret; + + if (!entries || entries > IORING_MAX_ENTRIES) + return -EINVAL; + + /* + * Use twice as many entries for the CQ ring. It's possible for the + * application to drive a higher depth than the size of the SQ ring, + * since the sqes are only used at submission time. This allows for + * some flexibility in overcommitting a bit. + */ + p->sq_entries = roundup_pow_of_two(entries); + p->cq_entries = 2 * p->sq_entries; + + user = get_uid(current_user()); + account_mem = !capable(CAP_IPC_LOCK); + + if (account_mem) { + ret = io_account_mem(user, + ring_pages(p->sq_entries, p->cq_entries)); + if (ret) { + free_uid(user); + return ret; + } + } + + ctx = io_ring_ctx_alloc(p); + if (!ctx) { + if (account_mem) + io_unaccount_mem(user, ring_pages(p->sq_entries, + p->cq_entries)); + free_uid(user); + return -ENOMEM; + } + ctx->compat = in_compat_syscall(); + ctx->account_mem = account_mem; + ctx->user = user; + + ret = io_allocate_scq_urings(ctx, p); + if (ret) + goto err; + + ret = io_sq_offload_start(ctx); + if (ret) + goto err; + + ret = io_uring_get_fd(ctx); + if (ret < 0) + goto err; + + memset(&p->sq_off, 0, sizeof(p->sq_off)); + p->sq_off.head = offsetof(struct io_sq_ring, r.head); + p->sq_off.tail = offsetof(struct io_sq_ring, r.tail); + p->sq_off.ring_mask = offsetof(struct io_sq_ring, ring_mask); + p->sq_off.ring_entries = offsetof(struct io_sq_ring, ring_entries); + p->sq_off.flags = offsetof(struct io_sq_ring, flags); + p->sq_off.dropped = offsetof(struct io_sq_ring, dropped); + p->sq_off.array = offsetof(struct io_sq_ring, array); + + memset(&p->cq_off, 0, sizeof(p->cq_off)); + p->cq_off.head = offsetof(struct io_cq_ring, r.head); + p->cq_off.tail = offsetof(struct io_cq_ring, r.tail); + p->cq_off.ring_mask = offsetof(struct io_cq_ring, ring_mask); + p->cq_off.ring_entries = offsetof(struct io_cq_ring, ring_entries); + p->cq_off.overflow = offsetof(struct io_cq_ring, overflow); + p->cq_off.cqes = offsetof(struct io_cq_ring, cqes); + return ret; +err: + io_ring_ctx_wait_and_kill(ctx); + return ret; +} + +/* + * Sets up an aio uring context, and returns the fd. Applications asks for a + * ring size, we return the actual sq/cq ring sizes (among other things) in the + * params structure passed in. + */ +static long io_uring_setup(u32 entries, struct io_uring_params __user *params) +{ + struct io_uring_params p; + long ret; + int i; + + if (copy_from_user(&p, params, sizeof(p))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(p.resv); i++) { + if (p.resv[i]) + return -EINVAL; + } + + if (p.flags) + return -EINVAL; + + ret = io_uring_create(entries, &p); + if (ret < 0) + return ret; + + if (copy_to_user(params, &p, sizeof(p))) + return -EFAULT; + + return ret; +} + +SYSCALL_DEFINE2(io_uring_setup, u32, entries, + struct io_uring_params __user *, params) +{ + return io_uring_setup(entries, params); +} + +static int __init io_uring_init(void) +{ + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + return 0; +}; +__initcall(io_uring_init); diff --git a/include/linux/fs.h b/include/linux/fs.h index dedcc2e9265c..61aa210f0c2b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3517,4 +3517,13 @@ extern void inode_nohighmem(struct inode *inode); extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); +#if defined(CONFIG_IO_URING) +extern struct sock *io_uring_get_socket(struct file *file); +#else +static inline struct sock *io_uring_get_socket(struct file *file) +{ + return NULL; +} +#endif + #endif /* _LINUX_FS_H */ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 39ad98c09c58..c7b5f86b91a1 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -40,7 +40,7 @@ struct user_struct { kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ - defined(CONFIG_NET) + defined(CONFIG_NET) || defined(CONFIG_IO_URING) atomic_long_t locked_vm; #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 257cccba3062..3072dbaa7869 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -69,6 +69,7 @@ struct file_handle; struct sigaltstack; struct rseq; union bpf_attr; +struct io_uring_params; #include #include @@ -309,6 +310,11 @@ asmlinkage long sys_io_pgetevents_time32(aio_context_t ctx_id, struct io_event __user *events, struct old_timespec32 __user *timeout, const struct __aio_sigset *sig); +asmlinkage long sys_io_uring_setup(u32 entries, + struct io_uring_params __user *p); +asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, + u32 min_complete, u32 flags, + const sigset_t __user *sig, size_t sigsz); /* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index d90127298f12..87871e7b7ea7 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -740,9 +740,13 @@ __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) +#define __NR_io_uring_setup 425 +__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) +#define __NR_io_uring_enter 426 +__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) #undef __NR_syscalls -#define __NR_syscalls 295 +#define __NR_syscalls 427 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h new file mode 100644 index 000000000000..ac692823d6f4 --- /dev/null +++ b/include/uapi/linux/io_uring.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Header file for the io_uring interface. + * + * Copyright (C) 2019 Jens Axboe + * Copyright (C) 2019 Christoph Hellwig + */ +#ifndef LINUX_IO_URING_H +#define LINUX_IO_URING_H + +#include +#include + +/* + * IO submission data structure (Submission Queue Entry) + */ +struct io_uring_sqe { + __u8 opcode; /* type of operation for this sqe */ + __u8 flags; /* as of now unused */ + __u16 ioprio; /* ioprio for the request */ + __s32 fd; /* file descriptor to do IO on */ + __u64 off; /* offset into file */ + __u64 addr; /* pointer to buffer or iovecs */ + __u32 len; /* buffer size or number of iovecs */ + union { + __kernel_rwf_t rw_flags; + __u32 __resv; + }; + __u64 user_data; /* data to be passed back at completion time */ + __u64 __pad2[3]; +}; + +#define IORING_OP_NOP 0 +#define IORING_OP_READV 1 +#define IORING_OP_WRITEV 2 + +/* + * IO completion data structure (Completion Queue Entry) + */ +struct io_uring_cqe { + __u64 user_data; /* sqe->data submission passed back */ + __s32 res; /* result code for this event */ + __u32 flags; +}; + +/* + * Magic offsets for the application to mmap the data it needs + */ +#define IORING_OFF_SQ_RING 0ULL +#define IORING_OFF_CQ_RING 0x8000000ULL +#define IORING_OFF_SQES 0x10000000ULL + +/* + * Filled with the offset for mmap(2) + */ +struct io_sqring_offsets { + __u32 head; + __u32 tail; + __u32 ring_mask; + __u32 ring_entries; + __u32 flags; + __u32 dropped; + __u32 array; + __u32 resv1; + __u64 resv2; +}; + +struct io_cqring_offsets { + __u32 head; + __u32 tail; + __u32 ring_mask; + __u32 ring_entries; + __u32 overflow; + __u32 cqes; + __u64 resv[2]; +}; + +/* + * io_uring_enter(2) flags + */ +#define IORING_ENTER_GETEVENTS (1U << 0) + +/* + * Passed in for io_uring_setup(2). Copied back with updated info on success + */ +struct io_uring_params { + __u32 sq_entries; + __u32 cq_entries; + __u32 flags; + __u32 resv[7]; + struct io_sqring_offsets sq_off; + struct io_cqring_offsets cq_off; +}; + +#endif diff --git a/init/Kconfig b/init/Kconfig index c9386a365eea..53b54214a36e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1414,6 +1414,15 @@ config AIO by some high performance threaded applications. Disabling this option saves about 7k. +config IO_URING + bool "Enable IO uring support" if EXPERT + select ANON_INODES + default y + help + This option enables support for the io_uring interface, enabling + applications to submit and complete IO through submission and + completion rings that are shared between the kernel and application. + config ADVISE_SYSCALLS bool "Enable madvise/fadvise syscalls" if EXPERT default y diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index ab9d0e3c6d50..ee5e523564bb 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -46,6 +46,8 @@ COND_SYSCALL(io_getevents); COND_SYSCALL(io_pgetevents); COND_SYSCALL_COMPAT(io_getevents); COND_SYSCALL_COMPAT(io_pgetevents); +COND_SYSCALL(io_uring_setup); +COND_SYSCALL(io_uring_enter); /* fs/xattr.c */ diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c36757e72844..f81854d74c7d 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -108,6 +108,9 @@ struct sock *unix_get_socket(struct file *filp) /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; + } else { + /* Could be an io_uring instance */ + u_sock = io_uring_get_socket(filp); } return u_sock; } -- cgit From c992fe2925d776be066d9f6cc13f9ea11d78b657 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Jan 2019 09:43:02 -0700 Subject: io_uring: add fsync support Add a new fsync opcode, which either syncs a range if one is passed, or the whole file if the offset and length fields are both cleared to zero. A flag is provided to use fdatasync semantics, that is only force out metadata which is required to retrieve the file data, but not others like metadata. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/io_uring.c | 54 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/io_uring.h | 8 ++++++- 2 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index f68052290426..745413d92712 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -24,6 +24,7 @@ * data that the application could potentially modify, it remains stable. * * Copyright (C) 2018-2019 Jens Axboe + * Copyright (c) 2018-2019 Christoph Hellwig */ #include #include @@ -557,6 +558,56 @@ static int io_nop(struct io_kiocb *req, u64 user_data) return 0; } +static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + int fd; + + /* Prep already done */ + if (req->rw.ki_filp) + return 0; + + if (unlikely(sqe->addr || sqe->ioprio)) + return -EINVAL; + + fd = READ_ONCE(sqe->fd); + req->rw.ki_filp = fget(fd); + if (unlikely(!req->rw.ki_filp)) + return -EBADF; + + return 0; +} + +static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) +{ + loff_t sqe_off = READ_ONCE(sqe->off); + loff_t sqe_len = READ_ONCE(sqe->len); + loff_t end = sqe_off + sqe_len; + unsigned fsync_flags; + int ret; + + fsync_flags = READ_ONCE(sqe->fsync_flags); + if (unlikely(fsync_flags & ~IORING_FSYNC_DATASYNC)) + return -EINVAL; + + ret = io_prep_fsync(req, sqe); + if (ret) + return ret; + + /* fsync always requires a blocking context */ + if (force_nonblock) + return -EAGAIN; + + ret = vfs_fsync_range(req->rw.ki_filp, sqe_off, + end > 0 ? end : LLONG_MAX, + fsync_flags & IORING_FSYNC_DATASYNC); + + fput(req->rw.ki_filp); + io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_free_req(req); + return 0; +} + static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct sqe_submit *s, bool force_nonblock) { @@ -578,6 +629,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, case IORING_OP_WRITEV: ret = io_write(req, s, force_nonblock); break; + case IORING_OP_FSYNC: + ret = io_fsync(req, s->sqe, force_nonblock); + break; default: ret = -EINVAL; break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ac692823d6f4..4589d56d0b68 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -24,7 +24,7 @@ struct io_uring_sqe { __u32 len; /* buffer size or number of iovecs */ union { __kernel_rwf_t rw_flags; - __u32 __resv; + __u32 fsync_flags; }; __u64 user_data; /* data to be passed back at completion time */ __u64 __pad2[3]; @@ -33,6 +33,12 @@ struct io_uring_sqe { #define IORING_OP_NOP 0 #define IORING_OP_READV 1 #define IORING_OP_WRITEV 2 +#define IORING_OP_FSYNC 3 + +/* + * sqe->fsync_flags + */ +#define IORING_FSYNC_DATASYNC (1U << 0) /* * IO completion data structure (Completion Queue Entry) -- cgit From def596e9557c91d9846fc4d84d26f2c564644416 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Jan 2019 08:59:42 -0700 Subject: io_uring: support for IO polling Add support for a polled io_uring instance. When a read or write is submitted to a polled io_uring, the application must poll for completions on the CQ ring through io_uring_enter(2). Polled IO may not generate IRQ completions, hence they need to be actively found by the application itself. To use polling, io_uring_setup() must be used with the IORING_SETUP_IOPOLL flag being set. It is illegal to mix and match polled and non-polled IO on an io_uring. Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- fs/io_uring.c | 275 ++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/io_uring.h | 5 + 2 files changed, 271 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 745413d92712..578797a4f318 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -124,6 +124,14 @@ struct io_ring_ctx { struct { spinlock_t completion_lock; + bool poll_multi_file; + /* + * ->poll_list is protected by the ctx->uring_lock for + * io_uring instances that don't use IORING_SETUP_SQPOLL. + * For SQPOLL, only the single threaded io_sq_thread() will + * manipulate the list, hence no extra locking is needed there. + */ + struct list_head poll_list; } ____cacheline_aligned_in_smp; #if defined(CONFIG_UNIX) @@ -135,6 +143,7 @@ struct sqe_submit { const struct io_uring_sqe *sqe; unsigned short index; bool has_user; + bool needs_lock; }; struct io_kiocb { @@ -146,12 +155,15 @@ struct io_kiocb { struct list_head list; unsigned int flags; #define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ +#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ u64 user_data; + u64 error; struct work_struct work; }; #define IO_PLUG_THRESHOLD 2 +#define IO_IOPOLL_BATCH 8 static struct kmem_cache *req_cachep; @@ -196,6 +208,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->wait); spin_lock_init(&ctx->completion_lock); + INIT_LIST_HEAD(&ctx->poll_list); return ctx; } @@ -297,12 +310,153 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx) return NULL; } +static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) +{ + if (*nr) { + kmem_cache_free_bulk(req_cachep, *nr, reqs); + io_ring_drop_ctx_refs(ctx, *nr); + *nr = 0; + } +} + static void io_free_req(struct io_kiocb *req) { io_ring_drop_ctx_refs(req->ctx, 1); kmem_cache_free(req_cachep, req); } +/* + * Find and free completed poll iocbs + */ +static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, + struct list_head *done) +{ + void *reqs[IO_IOPOLL_BATCH]; + struct io_kiocb *req; + int to_free = 0; + + while (!list_empty(done)) { + req = list_first_entry(done, struct io_kiocb, list); + list_del(&req->list); + + io_cqring_fill_event(ctx, req->user_data, req->error, 0); + + reqs[to_free++] = req; + (*nr_events)++; + + fput(req->rw.ki_filp); + if (to_free == ARRAY_SIZE(reqs)) + io_free_req_many(ctx, reqs, &to_free); + } + io_commit_cqring(ctx); + + io_free_req_many(ctx, reqs, &to_free); +} + +static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, + long min) +{ + struct io_kiocb *req, *tmp; + LIST_HEAD(done); + bool spin; + int ret; + + /* + * Only spin for completions if we don't have multiple devices hanging + * off our complete list, and we're under the requested amount. + */ + spin = !ctx->poll_multi_file && *nr_events < min; + + ret = 0; + list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) { + struct kiocb *kiocb = &req->rw; + + /* + * Move completed entries to our local list. If we find a + * request that requires polling, break out and complete + * the done list first, if we have entries there. + */ + if (req->flags & REQ_F_IOPOLL_COMPLETED) { + list_move_tail(&req->list, &done); + continue; + } + if (!list_empty(&done)) + break; + + ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); + if (ret < 0) + break; + + if (ret && spin) + spin = false; + ret = 0; + } + + if (!list_empty(&done)) + io_iopoll_complete(ctx, nr_events, &done); + + return ret; +} + +/* + * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a + * non-spinning poll check - we'll still enter the driver poll loop, but only + * as a non-spinning completion check. + */ +static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events, + long min) +{ + while (!list_empty(&ctx->poll_list)) { + int ret; + + ret = io_do_iopoll(ctx, nr_events, min); + if (ret < 0) + return ret; + if (!min || *nr_events >= min) + return 0; + } + + return 1; +} + +/* + * We can't just wait for polled events to come to us, we have to actively + * find and complete them. + */ +static void io_iopoll_reap_events(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_IOPOLL)) + return; + + mutex_lock(&ctx->uring_lock); + while (!list_empty(&ctx->poll_list)) { + unsigned int nr_events = 0; + + io_iopoll_getevents(ctx, &nr_events, 1); + } + mutex_unlock(&ctx->uring_lock); +} + +static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) +{ + int ret = 0; + + do { + int tmin = 0; + + if (*nr_events < min) + tmin = min - *nr_events; + + ret = io_iopoll_getevents(ctx, nr_events, tmin); + if (ret <= 0) + break; + ret = 0; + } while (min && !*nr_events && !need_resched()); + + return ret; +} + static void kiocb_end_write(struct kiocb *kiocb) { if (kiocb->ki_flags & IOCB_WRITE) { @@ -329,6 +483,53 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) io_free_req(req); } +static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + + kiocb_end_write(kiocb); + + req->error = res; + if (res != -EAGAIN) + req->flags |= REQ_F_IOPOLL_COMPLETED; +} + +/* + * After the iocb has been issued, it's safe to be found on the poll list. + * Adding the kiocb to the list AFTER submission ensures that we don't + * find it from a io_iopoll_getevents() thread before the issuer is done + * accessing the kiocb cookie. + */ +static void io_iopoll_req_issued(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + /* + * Track whether we have multiple files in our lists. This will impact + * how we do polling eventually, not spinning if we're on potentially + * different devices. + */ + if (list_empty(&ctx->poll_list)) { + ctx->poll_multi_file = false; + } else if (!ctx->poll_multi_file) { + struct io_kiocb *list_req; + + list_req = list_first_entry(&ctx->poll_list, struct io_kiocb, + list); + if (list_req->rw.ki_filp != req->rw.ki_filp) + ctx->poll_multi_file = true; + } + + /* + * For fast devices, IO may have already completed. If it has, add + * it to the front so we find it first. + */ + if (req->flags & REQ_F_IOPOLL_COMPLETED) + list_add(&req->list, &ctx->poll_list); + else + list_add_tail(&req->list, &ctx->poll_list); +} + /* * If we tracked the file through the SCM inflight mechanism, we could support * any file. For now, just ensure that anything potentially problematic is done @@ -349,6 +550,7 @@ static bool io_file_supports_async(struct file *file) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, bool force_nonblock) { + struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw; unsigned ioprio; int fd, ret; @@ -384,12 +586,22 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, kiocb->ki_flags |= IOCB_NOWAIT; req->flags |= REQ_F_FORCE_NONBLOCK; } - if (kiocb->ki_flags & IOCB_HIPRI) { - ret = -EINVAL; - goto out_fput; - } + if (ctx->flags & IORING_SETUP_IOPOLL) { + ret = -EOPNOTSUPP; + if (!(kiocb->ki_flags & IOCB_DIRECT) || + !kiocb->ki_filp->f_op->iopoll) + goto out_fput; - kiocb->ki_complete = io_complete_rw; + req->error = 0; + kiocb->ki_flags |= IOCB_HIPRI; + kiocb->ki_complete = io_complete_rw_iopoll; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) { + ret = -EINVAL; + goto out_fput; + } + kiocb->ki_complete = io_complete_rw; + } return 0; out_fput: fput(kiocb->ki_filp); @@ -543,6 +755,9 @@ static int io_nop(struct io_kiocb *req, u64 user_data) struct io_ring_ctx *ctx = req->ctx; long err = 0; + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + /* * Twilight zone - it's possible that someone issued an opcode that * has a file attached, then got -EAGAIN on submission, and changed @@ -566,6 +781,8 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->rw.ki_filp) return 0; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio)) return -EINVAL; @@ -637,7 +854,22 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, break; } - return ret; + if (ret) + return ret; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (req->error == -EAGAIN) + return -EAGAIN; + + /* workqueue context doesn't hold uring_lock, grab it now */ + if (s->needs_lock) + mutex_lock(&ctx->uring_lock); + io_iopoll_req_issued(req); + if (s->needs_lock) + mutex_unlock(&ctx->uring_lock); + } + + return 0; } static void io_sq_wq_submit_work(struct work_struct *work) @@ -661,8 +893,19 @@ static void io_sq_wq_submit_work(struct work_struct *work) use_mm(ctx->sqo_mm); set_fs(USER_DS); s->has_user = true; + s->needs_lock = true; - ret = __io_submit_sqe(ctx, req, s, false); + do { + ret = __io_submit_sqe(ctx, req, s, false); + /* + * We can get EAGAIN for polled IO even though we're forcing + * a sync submission from here, since we can't wait for + * request slots on the block side. + */ + if (ret != -EAGAIN) + break; + cond_resched(); + } while (1); set_fs(old_fs); unuse_mm(ctx->sqo_mm); @@ -799,6 +1042,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) break; s.has_user = true; + s.needs_lock = false; + ret = io_submit_sqe(ctx, &s); if (ret) { io_drop_sqring(ctx); @@ -947,6 +1192,9 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) destroy_workqueue(ctx->sqo_wq); if (ctx->sqo_mm) mmdrop(ctx->sqo_mm); + + io_iopoll_reap_events(ctx); + #if defined(CONFIG_UNIX) if (ctx->ring_sock) sock_release(ctx->ring_sock); @@ -993,6 +1241,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) percpu_ref_kill(&ctx->refs); mutex_unlock(&ctx->uring_lock); + io_iopoll_reap_events(ctx); wait_for_completion(&ctx->ctx_done); io_ring_ctx_free(ctx); } @@ -1074,6 +1323,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, goto out_ctx; } if (flags & IORING_ENTER_GETEVENTS) { + unsigned nr_events = 0; + min_complete = min(min_complete, ctx->cq_entries); /* @@ -1085,7 +1336,13 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, if (submitted < to_submit) min_complete = min_t(unsigned, submitted, min_complete); - ret = io_cqring_wait(ctx, min_complete, sig, sigsz); + if (ctx->flags & IORING_SETUP_IOPOLL) { + mutex_lock(&ctx->uring_lock); + ret = io_iopoll_check(ctx, &nr_events, min_complete); + mutex_unlock(&ctx->uring_lock); + } else { + ret = io_cqring_wait(ctx, min_complete, sig, sigsz); + } } out_ctx: @@ -1282,7 +1539,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) return -EINVAL; } - if (p.flags) + if (p.flags & ~IORING_SETUP_IOPOLL) return -EINVAL; ret = io_uring_create(entries, &p); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4589d56d0b68..5c457ea396e6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -30,6 +30,11 @@ struct io_uring_sqe { __u64 __pad2[3]; }; +/* + * io_uring_setup() flags + */ +#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */ + #define IORING_OP_NOP 0 #define IORING_OP_READV 1 #define IORING_OP_WRITEV 2 -- cgit From edafccee56ff31678a091ddb7219aba9b28bc3cb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Jan 2019 09:16:05 -0700 Subject: io_uring: add support for pre-mapped user IO buffers If we have fixed user buffers, we can map them into the kernel when we setup the io_uring. That avoids the need to do get_user_pages() for each and every IO. To utilize this feature, the application must call io_uring_register() after having setup an io_uring instance, passing in IORING_REGISTER_BUFFERS as the opcode. The argument must be a pointer to an iovec array, and the nr_args should contain how many iovecs the application wishes to map. If successful, these buffers are now mapped into the kernel, eligible for IO. To use these fixed buffers, the application must use the IORING_OP_READ_FIXED and IORING_OP_WRITE_FIXED opcodes, and then set sqe->index to the desired buffer index. sqe->addr..sqe->addr+seq->len must point to somewhere inside the indexed buffer. The application may register buffers throughout the lifetime of the io_uring instance. It can call io_uring_register() with IORING_UNREGISTER_BUFFERS as the opcode to unregister the current set of buffers, and then register a new set. The application need not unregister buffers explicitly before shutting down the io_uring instance. It's perfectly valid to setup a larger buffer, and then sometimes only use parts of it for an IO. As long as the range is within the originally mapped region, it will work just fine. For now, buffers must not be file backed. If file backed buffers are passed in, the registration will fail with -1/EOPNOTSUPP. This restriction may be relaxed in the future. RLIMIT_MEMLOCK is used to check how much memory we can pin. A somewhat arbitrary 1G per buffer size is also imposed. Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + fs/io_uring.c | 374 +++++++++++++++++++++++++++++++-- include/linux/syscalls.h | 2 + include/uapi/asm-generic/unistd.h | 4 +- include/uapi/linux/io_uring.h | 13 +- kernel/sys_ni.c | 1 + 7 files changed, 381 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 481c126259e9..2eefd2a7c1ce 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -400,3 +400,4 @@ 386 i386 rseq sys_rseq __ia32_sys_rseq 425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup 426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter +427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 6a32a430c8e0..65c026185e61 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,7 @@ 334 common rseq __x64_sys_rseq 425 common io_uring_setup __x64_sys_io_uring_setup 426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/fs/io_uring.c b/fs/io_uring.c index 31f43ed894ba..c0c0f68568b5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -52,6 +53,8 @@ #include #include #include +#include +#include #include @@ -81,6 +84,13 @@ struct io_cq_ring { struct io_uring_cqe cqes[]; }; +struct io_mapped_ubuf { + u64 ubuf; + size_t len; + struct bio_vec *bvec; + unsigned int nr_bvecs; +}; + struct io_ring_ctx { struct { struct percpu_ref refs; @@ -113,6 +123,10 @@ struct io_ring_ctx { struct fasync_struct *cq_fasync; } ____cacheline_aligned_in_smp; + /* if used, fixed mapped user buffers */ + unsigned nr_user_bufs; + struct io_mapped_ubuf *user_bufs; + struct user_struct *user; struct completion ctx_done; @@ -732,6 +746,46 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } +static int io_import_fixed(struct io_ring_ctx *ctx, int rw, + const struct io_uring_sqe *sqe, + struct iov_iter *iter) +{ + size_t len = READ_ONCE(sqe->len); + struct io_mapped_ubuf *imu; + unsigned index, buf_index; + size_t offset; + u64 buf_addr; + + /* attempt to use fixed buffers without having provided iovecs */ + if (unlikely(!ctx->user_bufs)) + return -EFAULT; + + buf_index = READ_ONCE(sqe->buf_index); + if (unlikely(buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + + index = array_index_nospec(buf_index, ctx->nr_user_bufs); + imu = &ctx->user_bufs[index]; + buf_addr = READ_ONCE(sqe->addr); + + /* overflow */ + if (buf_addr + len < buf_addr) + return -EFAULT; + /* not inside the mapped region */ + if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len) + return -EFAULT; + + /* + * May not be a start of buffer, set size appropriately + * and advance us to the beginning. + */ + offset = buf_addr - imu->ubuf; + iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); + if (offset) + iov_iter_advance(iter, offset); + return 0; +} + static int io_import_iovec(struct io_ring_ctx *ctx, int rw, const struct sqe_submit *s, struct iovec **iovec, struct iov_iter *iter) @@ -739,6 +793,23 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw, const struct io_uring_sqe *sqe = s->sqe; void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); size_t sqe_len = READ_ONCE(sqe->len); + u8 opcode; + + /* + * We're reading ->opcode for the second time, but the first read + * doesn't care whether it's _FIXED or not, so it doesn't matter + * whether ->opcode changes concurrently. The first read does care + * about whether it is a READ or a WRITE, so we don't trust this read + * for that purpose and instead let the caller pass in the read/write + * flag. + */ + opcode = READ_ONCE(sqe->opcode); + if (opcode == IORING_OP_READ_FIXED || + opcode == IORING_OP_WRITE_FIXED) { + ssize_t ret = io_import_fixed(ctx, rw, sqe, iter); + *iovec = NULL; + return ret; + } if (!s->has_user) return -EFAULT; @@ -886,7 +957,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (unlikely(sqe->addr || sqe->ioprio)) + if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; fd = READ_ONCE(sqe->fd); @@ -945,9 +1016,19 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ret = io_nop(req, req->user_data); break; case IORING_OP_READV: + if (unlikely(s->sqe->buf_index)) + return -EINVAL; ret = io_read(req, s, force_nonblock, state); break; case IORING_OP_WRITEV: + if (unlikely(s->sqe->buf_index)) + return -EINVAL; + ret = io_write(req, s, force_nonblock, state); + break; + case IORING_OP_READ_FIXED: + ret = io_read(req, s, force_nonblock, state); + break; + case IORING_OP_WRITE_FIXED: ret = io_write(req, s, force_nonblock, state); break; case IORING_OP_FSYNC: @@ -976,28 +1057,46 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } +static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +{ + u8 opcode = READ_ONCE(sqe->opcode); + + return !(opcode == IORING_OP_READ_FIXED || + opcode == IORING_OP_WRITE_FIXED); +} + static void io_sq_wq_submit_work(struct work_struct *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; struct io_ring_ctx *ctx = req->ctx; - mm_segment_t old_fs = get_fs(); + mm_segment_t old_fs; + bool needs_user; int ret; /* Ensure we clear previously set forced non-block flag */ req->flags &= ~REQ_F_FORCE_NONBLOCK; req->rw.ki_flags &= ~IOCB_NOWAIT; - if (!mmget_not_zero(ctx->sqo_mm)) { - ret = -EFAULT; - goto err; - } - - use_mm(ctx->sqo_mm); - set_fs(USER_DS); - s->has_user = true; s->needs_lock = true; + s->has_user = false; + + /* + * If we're doing IO to fixed buffers, we don't need to get/set + * user context + */ + needs_user = io_sqe_needs_user(s->sqe); + if (needs_user) { + if (!mmget_not_zero(ctx->sqo_mm)) { + ret = -EFAULT; + goto err; + } + use_mm(ctx->sqo_mm); + old_fs = get_fs(); + set_fs(USER_DS); + s->has_user = true; + } do { ret = __io_submit_sqe(ctx, req, s, false, NULL); @@ -1011,9 +1110,11 @@ static void io_sq_wq_submit_work(struct work_struct *work) cond_resched(); } while (1); - set_fs(old_fs); - unuse_mm(ctx->sqo_mm); - mmput(ctx->sqo_mm); + if (needs_user) { + set_fs(old_fs); + unuse_mm(ctx->sqo_mm); + mmput(ctx->sqo_mm); + } err: if (ret) { io_cqring_add_event(ctx, sqe->user_data, ret, 0); @@ -1317,6 +1418,198 @@ static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries) return (bytes + PAGE_SIZE - 1) / PAGE_SIZE; } +static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) +{ + int i, j; + + if (!ctx->user_bufs) + return -ENXIO; + + for (i = 0; i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + + for (j = 0; j < imu->nr_bvecs; j++) + put_page(imu->bvec[j].bv_page); + + if (ctx->account_mem) + io_unaccount_mem(ctx->user, imu->nr_bvecs); + kfree(imu->bvec); + imu->nr_bvecs = 0; + } + + kfree(ctx->user_bufs); + ctx->user_bufs = NULL; + ctx->nr_user_bufs = 0; + return 0; +} + +static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, + void __user *arg, unsigned index) +{ + struct iovec __user *src; + +#ifdef CONFIG_COMPAT + if (ctx->compat) { + struct compat_iovec __user *ciovs; + struct compat_iovec ciov; + + ciovs = (struct compat_iovec __user *) arg; + if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) + return -EFAULT; + + dst->iov_base = (void __user *) (unsigned long) ciov.iov_base; + dst->iov_len = ciov.iov_len; + return 0; + } +#endif + src = (struct iovec __user *) arg; + if (copy_from_user(dst, &src[index], sizeof(*dst))) + return -EFAULT; + return 0; +} + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct vm_area_struct **vmas = NULL; + struct page **pages = NULL; + int i, j, got_pages = 0; + int ret = -EINVAL; + + if (ctx->user_bufs) + return -EBUSY; + if (!nr_args || nr_args > UIO_MAXIOV) + return -EINVAL; + + ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf), + GFP_KERNEL); + if (!ctx->user_bufs) + return -ENOMEM; + + for (i = 0; i < nr_args; i++) { + struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + unsigned long off, start, end, ubuf; + int pret, nr_pages; + struct iovec iov; + size_t size; + + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + ret = -EFAULT; + if (!iov.iov_base || !iov.iov_len) + goto err; + + /* arbitrary limit, but we need something */ + if (iov.iov_len > SZ_1G) + goto err; + + ubuf = (unsigned long) iov.iov_base; + end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; + + if (ctx->account_mem) { + ret = io_account_mem(ctx->user, nr_pages); + if (ret) + goto err; + } + + ret = 0; + if (!pages || nr_pages > got_pages) { + kfree(vmas); + kfree(pages); + pages = kmalloc_array(nr_pages, sizeof(struct page *), + GFP_KERNEL); + vmas = kmalloc_array(nr_pages, + sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!pages || !vmas) { + ret = -ENOMEM; + if (ctx->account_mem) + io_unaccount_mem(ctx->user, nr_pages); + goto err; + } + got_pages = nr_pages; + } + + imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec), + GFP_KERNEL); + ret = -ENOMEM; + if (!imu->bvec) { + if (ctx->account_mem) + io_unaccount_mem(ctx->user, nr_pages); + goto err; + } + + ret = 0; + down_read(¤t->mm->mmap_sem); + pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE, + pages, vmas); + if (pret == nr_pages) { + /* don't support file backed memory */ + for (j = 0; j < nr_pages; j++) { + struct vm_area_struct *vma = vmas[j]; + + if (vma->vm_file && + !is_file_hugepages(vma->vm_file)) { + ret = -EOPNOTSUPP; + break; + } + } + } else { + ret = pret < 0 ? pret : -EFAULT; + } + up_read(¤t->mm->mmap_sem); + if (ret) { + /* + * if we did partial map, or found file backed vmas, + * release any pages we did get + */ + if (pret > 0) { + for (j = 0; j < pret; j++) + put_page(pages[j]); + } + if (ctx->account_mem) + io_unaccount_mem(ctx->user, nr_pages); + goto err; + } + + off = ubuf & ~PAGE_MASK; + size = iov.iov_len; + for (j = 0; j < nr_pages; j++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[j].bv_page = pages[j]; + imu->bvec[j].bv_len = vec_len; + imu->bvec[j].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = ubuf; + imu->len = iov.iov_len; + imu->nr_bvecs = nr_pages; + + ctx->nr_user_bufs++; + } + kfree(pages); + kfree(vmas); + return 0; +err: + kfree(pages); + kfree(vmas); + io_sqe_buffer_unregister(ctx); + return ret; +} + static void io_ring_ctx_free(struct io_ring_ctx *ctx) { if (ctx->sqo_wq) @@ -1325,6 +1618,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) mmdrop(ctx->sqo_mm); io_iopoll_reap_events(ctx); + io_sqe_buffer_unregister(ctx); #if defined(CONFIG_UNIX) if (ctx->ring_sock) @@ -1689,6 +1983,60 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, return io_uring_setup(entries, params); } +static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, + void __user *arg, unsigned nr_args) +{ + int ret; + + percpu_ref_kill(&ctx->refs); + wait_for_completion(&ctx->ctx_done); + + switch (opcode) { + case IORING_REGISTER_BUFFERS: + ret = io_sqe_buffer_register(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_BUFFERS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_buffer_unregister(ctx); + break; + default: + ret = -EINVAL; + break; + } + + /* bring the ctx back to life */ + reinit_completion(&ctx->ctx_done); + percpu_ref_reinit(&ctx->refs); + return ret; +} + +SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, + void __user *, arg, unsigned int, nr_args) +{ + struct io_ring_ctx *ctx; + long ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = -EOPNOTSUPP; + if (f.file->f_op != &io_uring_fops) + goto out_fput; + + ctx = f.file->private_data; + + mutex_lock(&ctx->uring_lock); + ret = __io_uring_register(ctx, opcode, arg, nr_args); + mutex_unlock(&ctx->uring_lock); +out_fput: + fdput(f); + return ret; +} + static int __init io_uring_init(void) { req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3072dbaa7869..3681c05ac538 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -315,6 +315,8 @@ asmlinkage long sys_io_uring_setup(u32 entries, asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, u32 min_complete, u32 flags, const sigset_t __user *sig, size_t sigsz); +asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, + void __user *arg, unsigned int nr_args); /* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 87871e7b7ea7..d346229a1eb0 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -744,9 +744,11 @@ __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) __SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) #define __NR_io_uring_enter 426 __SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register) #undef __NR_syscalls -#define __NR_syscalls 427 +#define __NR_syscalls 428 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 5c457ea396e6..cf28f7a11f12 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -27,7 +27,10 @@ struct io_uring_sqe { __u32 fsync_flags; }; __u64 user_data; /* data to be passed back at completion time */ - __u64 __pad2[3]; + union { + __u16 buf_index; /* index into fixed buffers, if used */ + __u64 __pad2[3]; + }; }; /* @@ -39,6 +42,8 @@ struct io_uring_sqe { #define IORING_OP_READV 1 #define IORING_OP_WRITEV 2 #define IORING_OP_FSYNC 3 +#define IORING_OP_READ_FIXED 4 +#define IORING_OP_WRITE_FIXED 5 /* * sqe->fsync_flags @@ -103,4 +108,10 @@ struct io_uring_params { struct io_cqring_offsets cq_off; }; +/* + * io_uring_register(2) opcodes and arguments + */ +#define IORING_REGISTER_BUFFERS 0 +#define IORING_UNREGISTER_BUFFERS 1 + #endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index ee5e523564bb..1bb6604dc19f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -48,6 +48,7 @@ COND_SYSCALL_COMPAT(io_getevents); COND_SYSCALL_COMPAT(io_pgetevents); COND_SYSCALL(io_uring_setup); COND_SYSCALL(io_uring_enter); +COND_SYSCALL(io_uring_register); /* fs/xattr.c */ -- cgit From 6b06314c47e141031be043539900d80d2c7ba10f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Jan 2019 22:13:58 -0700 Subject: io_uring: add file set registration We normally have to fget/fput for each IO we do on a file. Even with the batching we do, the cost of the atomic inc/dec of the file usage count adds up. This adds IORING_REGISTER_FILES, and IORING_UNREGISTER_FILES opcodes for the io_uring_register(2) system call. The arguments passed in must be an array of __s32 holding file descriptors, and nr_args should hold the number of file descriptors the application wishes to pin for the duration of the io_uring instance (or until IORING_UNREGISTER_FILES is called). When used, the application must set IOSQE_FIXED_FILE in the sqe->flags member. Then, instead of setting sqe->fd to the real fd, it sets sqe->fd to the index in the array passed in to IORING_REGISTER_FILES. Files are automatically unregistered when the io_uring instance is torn down. An application need only unregister if it wishes to register a new set of fds. Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- fs/io_uring.c | 311 +++++++++++++++++++++++++++++++++++++----- include/uapi/linux/io_uring.h | 9 +- 2 files changed, 288 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index c0c0f68568b5..5eaa1c4a3f7c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include #include @@ -61,6 +62,7 @@ #include "internal.h" #define IORING_MAX_ENTRIES 4096 +#define IORING_MAX_FIXED_FILES 1024 struct io_uring { u32 head ____cacheline_aligned_in_smp; @@ -123,6 +125,14 @@ struct io_ring_ctx { struct fasync_struct *cq_fasync; } ____cacheline_aligned_in_smp; + /* + * If used, fixed file set. Writers must ensure that ->refs is dead, + * readers must ensure that ->refs is alive as long as the file* is + * used. Only updated through io_uring_register(2). + */ + struct file **user_files; + unsigned nr_user_files; + /* if used, fixed mapped user buffers */ unsigned nr_user_bufs; struct io_mapped_ubuf *user_bufs; @@ -170,6 +180,7 @@ struct io_kiocb { unsigned int flags; #define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ #define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ +#define REQ_F_FIXED_FILE 4 /* ctx owns file */ u64 user_data; u64 error; @@ -404,15 +415,17 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, * Batched puts of the same file, to avoid dirtying the * file usage count multiple times, if avoidable. */ - if (!file) { - file = req->rw.ki_filp; - file_count = 1; - } else if (file == req->rw.ki_filp) { - file_count++; - } else { - fput_many(file, file_count); - file = req->rw.ki_filp; - file_count = 1; + if (!(req->flags & REQ_F_FIXED_FILE)) { + if (!file) { + file = req->rw.ki_filp; + file_count = 1; + } else if (file == req->rw.ki_filp) { + file_count++; + } else { + fput_many(file, file_count); + file = req->rw.ki_filp; + file_count = 1; + } } if (to_free == ARRAY_SIZE(reqs)) @@ -544,13 +557,19 @@ static void kiocb_end_write(struct kiocb *kiocb) } } +static void io_fput(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_FIXED_FILE)) + fput(req->rw.ki_filp); +} + static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); kiocb_end_write(kiocb); - fput(kiocb->ki_filp); + io_fput(req); io_cqring_add_event(req->ctx, req->user_data, res, 0); io_free_req(req); } @@ -666,19 +685,29 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw; - unsigned ioprio; + unsigned ioprio, flags; int fd, ret; /* For -EAGAIN retry, everything is already prepped */ if (kiocb->ki_filp) return 0; + flags = READ_ONCE(sqe->flags); fd = READ_ONCE(sqe->fd); - kiocb->ki_filp = io_file_get(state, fd); - if (unlikely(!kiocb->ki_filp)) - return -EBADF; - if (force_nonblock && !io_file_supports_async(kiocb->ki_filp)) - force_nonblock = false; + + if (flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || + (unsigned) fd >= ctx->nr_user_files)) + return -EBADF; + kiocb->ki_filp = ctx->user_files[fd]; + req->flags |= REQ_F_FIXED_FILE; + } else { + kiocb->ki_filp = io_file_get(state, fd); + if (unlikely(!kiocb->ki_filp)) + return -EBADF; + if (force_nonblock && !io_file_supports_async(kiocb->ki_filp)) + force_nonblock = false; + } kiocb->ki_pos = READ_ONCE(sqe->off); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); @@ -718,10 +747,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, } return 0; out_fput: - /* in case of error, we didn't use this file reference. drop it. */ - if (state) - state->used_refs--; - io_file_put(state, kiocb->ki_filp); + if (!(flags & IOSQE_FIXED_FILE)) { + /* + * in case of error, we didn't use this file reference. drop it. + */ + if (state) + state->used_refs--; + io_file_put(state, kiocb->ki_filp); + } return ret; } @@ -863,7 +896,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s, out_fput: /* Hold on to the file for -EAGAIN */ if (unlikely(ret && ret != -EAGAIN)) - fput(file); + io_fput(req); return ret; } @@ -917,7 +950,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, kfree(iovec); out_fput: if (unlikely(ret)) - fput(file); + io_fput(req); return ret; } @@ -940,7 +973,7 @@ static int io_nop(struct io_kiocb *req, u64 user_data) */ if (req->rw.ki_filp) { err = -EBADF; - fput(req->rw.ki_filp); + io_fput(req); } io_cqring_add_event(ctx, user_data, err, 0); io_free_req(req); @@ -949,21 +982,32 @@ static int io_nop(struct io_kiocb *req, u64 user_data) static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + struct io_ring_ctx *ctx = req->ctx; + unsigned flags; int fd; /* Prep already done */ if (req->rw.ki_filp) return 0; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; fd = READ_ONCE(sqe->fd); - req->rw.ki_filp = fget(fd); - if (unlikely(!req->rw.ki_filp)) - return -EBADF; + flags = READ_ONCE(sqe->flags); + + if (flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files)) + return -EBADF; + req->rw.ki_filp = ctx->user_files[fd]; + req->flags |= REQ_F_FIXED_FILE; + } else { + req->rw.ki_filp = fget(fd); + if (unlikely(!req->rw.ki_filp)) + return -EBADF; + } return 0; } @@ -993,7 +1037,7 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, end > 0 ? end : LLONG_MAX, fsync_flags & IORING_FSYNC_DATASYNC); - fput(req->rw.ki_filp); + io_fput(req); io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); io_free_req(req); return 0; @@ -1132,7 +1176,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, ssize_t ret; /* enforce forwards compatibility on users */ - if (unlikely(s->sqe->flags)) + if (unlikely(s->sqe->flags & ~IOSQE_FIXED_FILE)) return -EINVAL; req = io_get_req(ctx, state); @@ -1344,6 +1388,201 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0; } +static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ +#if defined(CONFIG_UNIX) + if (ctx->ring_sock) { + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff *skb; + + while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) + kfree_skb(skb); + } +#else + int i; + + for (i = 0; i < ctx->nr_user_files; i++) + fput(ctx->user_files[i]); +#endif +} + +static int io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ + if (!ctx->user_files) + return -ENXIO; + + __io_sqe_files_unregister(ctx); + kfree(ctx->user_files); + ctx->user_files = NULL; + ctx->nr_user_files = 0; + return 0; +} + +static void io_finish_async(struct io_ring_ctx *ctx) +{ + if (ctx->sqo_wq) { + destroy_workqueue(ctx->sqo_wq); + ctx->sqo_wq = NULL; + } +} + +#if defined(CONFIG_UNIX) +static void io_destruct_skb(struct sk_buff *skb) +{ + struct io_ring_ctx *ctx = skb->sk->sk_user_data; + + io_finish_async(ctx); + unix_destruct_scm(skb); +} + +/* + * Ensure the UNIX gc is aware of our file set, so we are certain that + * the io_uring can be safely unregistered on process exit, even if we have + * loops in the file referencing. + */ +static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) +{ + struct sock *sk = ctx->ring_sock->sk; + struct scm_fp_list *fpl; + struct sk_buff *skb; + int i; + + if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { + unsigned long inflight = ctx->user->unix_inflight + nr; + + if (inflight > task_rlimit(current, RLIMIT_NOFILE)) + return -EMFILE; + } + + fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); + if (!fpl) + return -ENOMEM; + + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) { + kfree(fpl); + return -ENOMEM; + } + + skb->sk = sk; + skb->destructor = io_destruct_skb; + + fpl->user = get_uid(ctx->user); + for (i = 0; i < nr; i++) { + fpl->fp[i] = get_file(ctx->user_files[i + offset]); + unix_inflight(fpl->user, fpl->fp[i]); + } + + fpl->max = fpl->count = nr; + UNIXCB(skb).fp = fpl; + refcount_add(skb->truesize, &sk->sk_wmem_alloc); + skb_queue_head(&sk->sk_receive_queue, skb); + + for (i = 0; i < nr; i++) + fput(fpl->fp[i]); + + return 0; +} + +/* + * If UNIX sockets are enabled, fd passing can cause a reference cycle which + * causes regular reference counting to break down. We rely on the UNIX + * garbage collection to take care of this problem for us. + */ +static int io_sqe_files_scm(struct io_ring_ctx *ctx) +{ + unsigned left, total; + int ret = 0; + + total = 0; + left = ctx->nr_user_files; + while (left) { + unsigned this_files = min_t(unsigned, left, SCM_MAX_FD); + int ret; + + ret = __io_sqe_files_scm(ctx, this_files, total); + if (ret) + break; + left -= this_files; + total += this_files; + } + + if (!ret) + return 0; + + while (total < ctx->nr_user_files) { + fput(ctx->user_files[total]); + total++; + } + + return ret; +} +#else +static int io_sqe_files_scm(struct io_ring_ctx *ctx) +{ + return 0; +} +#endif + +static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + __s32 __user *fds = (__s32 __user *) arg; + int fd, ret = 0; + unsigned i; + + if (ctx->user_files) + return -EBUSY; + if (!nr_args) + return -EINVAL; + if (nr_args > IORING_MAX_FIXED_FILES) + return -EMFILE; + + ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL); + if (!ctx->user_files) + return -ENOMEM; + + for (i = 0; i < nr_args; i++) { + ret = -EFAULT; + if (copy_from_user(&fd, &fds[i], sizeof(fd))) + break; + + ctx->user_files[i] = fget(fd); + + ret = -EBADF; + if (!ctx->user_files[i]) + break; + /* + * Don't allow io_uring instances to be registered. If UNIX + * isn't enabled, then this causes a reference cycle and this + * instance can never get freed. If UNIX is enabled we'll + * handle it just fine, but there's still no point in allowing + * a ring fd as it doesn't support regular read/write anyway. + */ + if (ctx->user_files[i]->f_op == &io_uring_fops) { + fput(ctx->user_files[i]); + break; + } + ctx->nr_user_files++; + ret = 0; + } + + if (ret) { + for (i = 0; i < ctx->nr_user_files; i++) + fput(ctx->user_files[i]); + + kfree(ctx->user_files); + ctx->nr_user_files = 0; + return ret; + } + + ret = io_sqe_files_scm(ctx); + if (ret) + io_sqe_files_unregister(ctx); + + return ret; +} + static int io_sq_offload_start(struct io_ring_ctx *ctx) { int ret; @@ -1612,13 +1851,13 @@ err: static void io_ring_ctx_free(struct io_ring_ctx *ctx) { - if (ctx->sqo_wq) - destroy_workqueue(ctx->sqo_wq); + io_finish_async(ctx); if (ctx->sqo_mm) mmdrop(ctx->sqo_mm); io_iopoll_reap_events(ctx); io_sqe_buffer_unregister(ctx); + io_sqe_files_unregister(ctx); #if defined(CONFIG_UNIX) if (ctx->ring_sock) @@ -1858,6 +2097,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; + ctx->ring_sock->sk->sk_user_data = ctx; #endif fd_install(ret, file); return ret; @@ -2001,6 +2241,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sqe_buffer_unregister(ctx); break; + case IORING_REGISTER_FILES: + ret = io_sqe_files_register(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_FILES: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_files_unregister(ctx); + break; default: ret = -EINVAL; break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cf28f7a11f12..6257478d55e9 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -16,7 +16,7 @@ */ struct io_uring_sqe { __u8 opcode; /* type of operation for this sqe */ - __u8 flags; /* as of now unused */ + __u8 flags; /* IOSQE_ flags */ __u16 ioprio; /* ioprio for the request */ __s32 fd; /* file descriptor to do IO on */ __u64 off; /* offset into file */ @@ -33,6 +33,11 @@ struct io_uring_sqe { }; }; +/* + * sqe->flags + */ +#define IOSQE_FIXED_FILE (1U << 0) /* use fixed fileset */ + /* * io_uring_setup() flags */ @@ -113,5 +118,7 @@ struct io_uring_params { */ #define IORING_REGISTER_BUFFERS 0 #define IORING_UNREGISTER_BUFFERS 1 +#define IORING_REGISTER_FILES 2 +#define IORING_UNREGISTER_FILES 3 #endif -- cgit From 6c271ce2f1d572f7fa225700a13cfe7ced492434 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Jan 2019 11:22:30 -0700 Subject: io_uring: add submission polling This enables an application to do IO, without ever entering the kernel. By using the SQ ring to fill in new sqes and watching for completions on the CQ ring, we can submit and reap IOs without doing a single system call. The kernel side thread will poll for new submissions, and in case of HIPRI/polled IO, it'll also poll for completions. By default, we allow 1 second of active spinning. This can by changed by passing in a different grace period at io_uring_register(2) time. If the thread exceeds this idle time without having any work to do, it will set: sq_ring->flags |= IORING_SQ_NEED_WAKEUP. The application will have to call io_uring_enter() to start things back up again. If IO is kept busy, that will never be needed. Basically an application that has this feature enabled will guard it's io_uring_enter(2) call with: read_barrier(); if (*sq_ring->flags & IORING_SQ_NEED_WAKEUP) io_uring_enter(fd, 0, 0, IORING_ENTER_SQ_WAKEUP); instead of calling it unconditionally. It's mandatory to use fixed files with this feature. Failure to do so will result in the application getting an -EBADF CQ entry when submitting IO. Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- fs/io_uring.c | 249 ++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/io_uring.h | 12 +- 2 files changed, 253 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 5eaa1c4a3f7c..0a4caedf82c1 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include @@ -108,12 +109,16 @@ struct io_ring_ctx { unsigned cached_sq_head; unsigned sq_entries; unsigned sq_mask; + unsigned sq_thread_idle; struct io_uring_sqe *sq_sqes; } ____cacheline_aligned_in_smp; /* IO offload */ struct workqueue_struct *sqo_wq; + struct task_struct *sqo_thread; /* if using sq thread polling */ struct mm_struct *sqo_mm; + wait_queue_head_t sqo_wait; + unsigned sqo_stop; struct { /* CQ ring */ @@ -168,6 +173,7 @@ struct sqe_submit { unsigned short index; bool has_user; bool needs_lock; + bool needs_fixed_file; }; struct io_kiocb { @@ -327,6 +333,8 @@ static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data, if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); + if (waitqueue_active(&ctx->sqo_wait)) + wake_up(&ctx->sqo_wait); } static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) @@ -680,9 +688,10 @@ static bool io_file_supports_async(struct file *file) return false; } -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, +static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, bool force_nonblock, struct io_submit_state *state) { + const struct io_uring_sqe *sqe = s->sqe; struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw; unsigned ioprio, flags; @@ -702,6 +711,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, kiocb->ki_filp = ctx->user_files[fd]; req->flags |= REQ_F_FIXED_FILE; } else { + if (s->needs_fixed_file) + return -EBADF; kiocb->ki_filp = io_file_get(state, fd); if (unlikely(!kiocb->ki_filp)) return -EBADF; @@ -865,7 +876,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s, struct file *file; ssize_t ret; - ret = io_prep_rw(req, s->sqe, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock, state); if (ret) return ret; file = kiocb->ki_filp; @@ -909,7 +920,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, struct file *file; ssize_t ret; - ret = io_prep_rw(req, s->sqe, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock, state); if (ret) return ret; /* Hold on to the file for -EAGAIN */ @@ -1301,6 +1312,169 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) return false; } +static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, + unsigned int nr, bool has_user, bool mm_fault) +{ + struct io_submit_state state, *statep = NULL; + int ret, i, submitted = 0; + + if (nr > IO_PLUG_THRESHOLD) { + io_submit_state_start(&state, ctx, nr); + statep = &state; + } + + for (i = 0; i < nr; i++) { + if (unlikely(mm_fault)) { + ret = -EFAULT; + } else { + sqes[i].has_user = has_user; + sqes[i].needs_lock = true; + sqes[i].needs_fixed_file = true; + ret = io_submit_sqe(ctx, &sqes[i], statep); + } + if (!ret) { + submitted++; + continue; + } + + io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret, 0); + } + + if (statep) + io_submit_state_end(&state); + + return submitted; +} + +static int io_sq_thread(void *data) +{ + struct sqe_submit sqes[IO_IOPOLL_BATCH]; + struct io_ring_ctx *ctx = data; + struct mm_struct *cur_mm = NULL; + mm_segment_t old_fs; + DEFINE_WAIT(wait); + unsigned inflight; + unsigned long timeout; + + old_fs = get_fs(); + set_fs(USER_DS); + + timeout = inflight = 0; + while (!kthread_should_stop() && !ctx->sqo_stop) { + bool all_fixed, mm_fault = false; + int i; + + if (inflight) { + unsigned nr_events = 0; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + /* + * We disallow the app entering submit/complete + * with polling, but we still need to lock the + * ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); + io_iopoll_check(ctx, &nr_events, 0); + mutex_unlock(&ctx->uring_lock); + } else { + /* + * Normal IO, just pretend everything completed. + * We don't have to poll completions for that. + */ + nr_events = inflight; + } + + inflight -= nr_events; + if (!inflight) + timeout = jiffies + ctx->sq_thread_idle; + } + + if (!io_get_sqring(ctx, &sqes[0])) { + /* + * We're polling. If we're within the defined idle + * period, then let us spin without work before going + * to sleep. + */ + if (inflight || !time_after(jiffies, timeout)) { + cpu_relax(); + continue; + } + + /* + * Drop cur_mm before scheduling, we can't hold it for + * long periods (or over schedule()). Do this before + * adding ourselves to the waitqueue, as the unuse/drop + * may sleep. + */ + if (cur_mm) { + unuse_mm(cur_mm); + mmput(cur_mm); + cur_mm = NULL; + } + + prepare_to_wait(&ctx->sqo_wait, &wait, + TASK_INTERRUPTIBLE); + + /* Tell userspace we may need a wakeup call */ + ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP; + smp_wmb(); + + if (!io_get_sqring(ctx, &sqes[0])) { + if (kthread_should_stop()) { + finish_wait(&ctx->sqo_wait, &wait); + break; + } + if (signal_pending(current)) + flush_signals(current); + schedule(); + finish_wait(&ctx->sqo_wait, &wait); + + ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; + smp_wmb(); + continue; + } + finish_wait(&ctx->sqo_wait, &wait); + + ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; + smp_wmb(); + } + + i = 0; + all_fixed = true; + do { + if (all_fixed && io_sqe_needs_user(sqes[i].sqe)) + all_fixed = false; + + i++; + if (i == ARRAY_SIZE(sqes)) + break; + } while (io_get_sqring(ctx, &sqes[i])); + + /* Unless all new commands are FIXED regions, grab mm */ + if (!all_fixed && !cur_mm) { + mm_fault = !mmget_not_zero(ctx->sqo_mm); + if (!mm_fault) { + use_mm(ctx->sqo_mm); + cur_mm = ctx->sqo_mm; + } + } + + inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL, + mm_fault); + + /* Commit SQ ring head once we've consumed all SQEs */ + io_commit_sqring(ctx); + } + + set_fs(old_fs); + if (cur_mm) { + unuse_mm(cur_mm); + mmput(cur_mm); + } + return 0; +} + static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) { struct io_submit_state state, *statep = NULL; @@ -1319,6 +1493,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) s.has_user = true; s.needs_lock = false; + s.needs_fixed_file = false; ret = io_submit_sqe(ctx, &s, statep); if (ret) { @@ -1418,8 +1593,20 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) return 0; } +static void io_sq_thread_stop(struct io_ring_ctx *ctx) +{ + if (ctx->sqo_thread) { + ctx->sqo_stop = 1; + mb(); + kthread_stop(ctx->sqo_thread); + ctx->sqo_thread = NULL; + } +} + static void io_finish_async(struct io_ring_ctx *ctx) { + io_sq_thread_stop(ctx); + if (ctx->sqo_wq) { destroy_workqueue(ctx->sqo_wq); ctx->sqo_wq = NULL; @@ -1583,13 +1770,47 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return ret; } -static int io_sq_offload_start(struct io_ring_ctx *ctx) +static int io_sq_offload_start(struct io_ring_ctx *ctx, + struct io_uring_params *p) { int ret; + init_waitqueue_head(&ctx->sqo_wait); mmgrab(current->mm); ctx->sqo_mm = current->mm; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; + + ret = -EINVAL; + if (!cpu_possible(p->sq_thread_cpu)) + goto err; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (p->flags & IORING_SETUP_SQ_AFF) { + int cpu; + + cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS); + ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread, + ctx, cpu, + "io_uring-sq"); + } else { + ctx->sqo_thread = kthread_create(io_sq_thread, ctx, + "io_uring-sq"); + } + if (IS_ERR(ctx->sqo_thread)) { + ret = PTR_ERR(ctx->sqo_thread); + ctx->sqo_thread = NULL; + goto err; + } + wake_up_process(ctx->sqo_thread); + } else if (p->flags & IORING_SETUP_SQ_AFF) { + /* Can't have SQ_AFF without SQPOLL */ + ret = -EINVAL; + goto err; + } + /* Do QD, or 2 * CPUS, whatever is smallest */ ctx->sqo_wq = alloc_workqueue("io_ring-wq", WQ_UNBOUND | WQ_FREEZABLE, min(ctx->sq_entries - 1, 2 * num_online_cpus())); @@ -1600,6 +1821,7 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx) return 0; err: + io_sq_thread_stop(ctx); mmdrop(ctx->sqo_mm); ctx->sqo_mm = NULL; return ret; @@ -1959,7 +2181,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, int submitted = 0; struct fd f; - if (flags & ~IORING_ENTER_GETEVENTS) + if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP)) return -EINVAL; f = fdget(fd); @@ -1975,6 +2197,18 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, if (!percpu_ref_tryget(&ctx->refs)) goto out_fput; + /* + * For SQ polling, the thread will do all submissions and completions. + * Just return the requested submit count, and wake the thread if + * we were asked to. + */ + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (flags & IORING_ENTER_SQ_WAKEUP) + wake_up(&ctx->sqo_wait); + submitted = to_submit; + goto out_ctx; + } + ret = 0; if (to_submit) { to_submit = min(to_submit, ctx->sq_entries); @@ -2156,7 +2390,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret) goto err; - ret = io_sq_offload_start(ctx); + ret = io_sq_offload_start(ctx, p); if (ret) goto err; @@ -2204,7 +2438,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) return -EINVAL; } - if (p.flags & ~IORING_SETUP_IOPOLL) + if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | + IORING_SETUP_SQ_AFF)) return -EINVAL; ret = io_uring_create(entries, &p); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6257478d55e9..0ec74bab8dbe 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -42,6 +42,8 @@ struct io_uring_sqe { * io_uring_setup() flags */ #define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */ +#define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */ +#define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */ #define IORING_OP_NOP 0 #define IORING_OP_READV 1 @@ -86,6 +88,11 @@ struct io_sqring_offsets { __u64 resv2; }; +/* + * sq_ring->flags + */ +#define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ + struct io_cqring_offsets { __u32 head; __u32 tail; @@ -100,6 +107,7 @@ struct io_cqring_offsets { * io_uring_enter(2) flags */ #define IORING_ENTER_GETEVENTS (1U << 0) +#define IORING_ENTER_SQ_WAKEUP (1U << 1) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -108,7 +116,9 @@ struct io_uring_params { __u32 sq_entries; __u32 cq_entries; __u32 flags; - __u32 resv[7]; + __u32 sq_thread_cpu; + __u32 sq_thread_idle; + __u32 resv[5]; struct io_sqring_offsets sq_off; struct io_cqring_offsets cq_off; }; -- cgit From ca215086b14b89a0e70fc211314944aa6ce50020 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:23 -0800 Subject: mm: convert PG_balloon to PG_offline PG_balloon was introduced to implement page migration/compaction for pages inflated in virtio-balloon. Nowadays, it is only a marker that a page is part of virtio-balloon and therefore logically offline. We also want to make use of this flag in other balloon drivers - for inflated pages or when onlining a section but keeping some pages offline (e.g. used right now by XEN and Hyper-V via set_online_page_callback()). We are going to expose this flag to dump tools like makedumpfile. But instead of exposing PG_balloon, let's generalize the concept of marking pages as logically offline, so it can be reused for other purposes later on. Rename PG_balloon to PG_offline. This is an indicator that the page is logically offline, the content stale and that it should not be touched (e.g. a hypervisor would have to allocate backing storage in order for the guest to dump an unused page). We can then e.g. exclude such pages from dumps. We replace and reuse KPF_BALLOON (23), as this shouldn't really harm (and for now the semantics stay the same). In following patches, we will make use of this bit also in other balloon drivers. While at it, document PGTABLE. [akpm@linux-foundation.org: fix comment text, per David] Link: http://lkml.kernel.org/r/20181119101616.8901-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Konstantin Khlebnikov Acked-by: Michael S. Tsirkin Acked-by: Pankaj gupta Cc: Jonathan Corbet Cc: Alexey Dobriyan Cc: Mike Rapoport Cc: Christian Hansen Cc: Vlastimil Babka Cc: "Kirill A. Shutemov" Cc: Stephen Rothwell Cc: Matthew Wilcox Cc: Michal Hocko Cc: Pavel Tatashin Cc: Alexander Duyck Cc: Naoya Horiguchi Cc: Miles Chen Cc: David Rientjes Cc: Kazuhito Hagio Cc: Arnd Bergmann Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Dave Young Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Lianbo Jiang Cc: Michal Hocko Cc: Nadav Amit Cc: Omar Sandoval Cc: Pavel Machek Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Vitaly Kuznetsov Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/pagemap.rst | 9 ++++++--- fs/proc/page.c | 4 ++-- include/linux/balloon_compaction.h | 8 ++++---- include/linux/page-flags.h | 11 +++++++---- include/uapi/linux/kernel-page-flags.h | 2 +- tools/vm/page-types.c | 2 +- 6 files changed, 21 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index 3f7bade2c231..340a5aee9b80 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -75,9 +75,10 @@ number of times a page is mapped. 20. NOPAGE 21. KSM 22. THP - 23. BALLOON + 23. OFFLINE 24. ZERO_PAGE 25. IDLE + 26. PGTABLE * ``/proc/kpagecgroup``. This file contains a 64-bit inode number of the memory cgroup each page is charged to, indexed by PFN. Only available when @@ -118,8 +119,8 @@ Short descriptions to the page flags identical memory pages dynamically shared between one or more processes 22 - THP contiguous pages which construct transparent hugepages -23 - BALLOON - balloon compaction page +23 - OFFLINE + page is logically offline 24 - ZERO_PAGE zero page for pfn_zero or huge_zero page 25 - IDLE @@ -128,6 +129,8 @@ Short descriptions to the page flags Note that this flag may be stale in case the page was accessed via a PTE. To make sure the flag is up-to-date one has to read ``/sys/kernel/mm/page_idle/bitmap`` first. +26 - PGTABLE + page is in use as a page table IO related page flags --------------------- diff --git a/fs/proc/page.c b/fs/proc/page.c index 40b05e0d4274..544d1ee15aee 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page) else if (page_count(page) == 0 && is_free_buddy_page(page)) u |= 1 << KPF_BUDDY; - if (PageBalloon(page)) - u |= 1 << KPF_BALLOON; + if (PageOffline(page)) + u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index cbe50da5a59d..f111c780ef1d 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -95,7 +95,7 @@ extern int balloon_page_migrate(struct address_space *mapping, static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { - __SetPageBalloon(page); + __SetPageOffline(page); __SetPageMovable(page, balloon->inode->i_mapping); set_page_private(page, (unsigned long)balloon); list_add(&page->lru, &balloon->pages); @@ -111,7 +111,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, */ static inline void balloon_page_delete(struct page *page) { - __ClearPageBalloon(page); + __ClearPageOffline(page); __ClearPageMovable(page); set_page_private(page, 0); /* @@ -141,13 +141,13 @@ static inline gfp_t balloon_mapping_gfp_mask(void) static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { - __SetPageBalloon(page); + __SetPageOffline(page); list_add(&page->lru, &balloon->pages); } static inline void balloon_page_delete(struct page *page) { - __ClearPageBalloon(page); + __ClearPageOffline(page); list_del(&page->lru); } diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 39b4494e29f1..808b4183e30d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -671,7 +671,7 @@ PAGEFLAG_FALSE(DoubleMap) /* Reserve 0x0000007f to catch underflows of page_mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 -#define PG_balloon 0x00000100 +#define PG_offline 0x00000100 #define PG_kmemcg 0x00000200 #define PG_table 0x00000400 @@ -706,10 +706,13 @@ static __always_inline void __ClearPage##uname(struct page *page) \ PAGE_TYPE_OPS(Buddy, buddy) /* - * PageBalloon() is true for pages that are on the balloon page list - * (see mm/balloon_compaction.c). + * PageOffline() indicates that the page is logically offline although the + * containing section is online. (e.g. inflated in a balloon driver or + * not onlined when onlining the section). + * The content of these pages is effectively stale. Such pages should not + * be touched (read/write/dump/save) except by their owner. */ -PAGE_TYPE_OPS(Balloon, balloon) +PAGE_TYPE_OPS(Offline, offline) /* * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 21b9113c69da..6f2f2720f3ac 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -32,7 +32,7 @@ #define KPF_KSM 21 #define KPF_THP 22 -#define KPF_BALLOON 23 +#define KPF_OFFLINE 23 #define KPF_ZERO_PAGE 24 #define KPF_IDLE 25 #define KPF_PGTABLE 26 diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 1ff3a6c0367b..6f64b2b93234 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -133,7 +133,7 @@ static const char * const page_flag_names[] = { [KPF_NOPAGE] = "n:nopage", [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", - [KPF_BALLOON] = "o:balloon", + [KPF_OFFLINE] = "o:offline", [KPF_PGTABLE] = "g:pgtable", [KPF_ZERO_PAGE] = "z:zero_page", [KPF_IDLE] = "i:idle_page", -- cgit From ab3948f58ff841e51feb845720624665ef5b7ef3 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Tue, 5 Mar 2019 15:47:54 -0800 Subject: mm/memfd: add an F_SEAL_FUTURE_WRITE seal to memfd Android uses ashmem for sharing memory regions. We are looking forward to migrating all usecases of ashmem to memfd so that we can possibly remove the ashmem driver in the future from staging while also benefiting from using memfd and contributing to it. Note staging drivers are also not ABI and generally can be removed at anytime. One of the main usecases Android has is the ability to create a region and mmap it as writeable, then add protection against making any "future" writes while keeping the existing already mmap'ed writeable-region active. This allows us to implement a usecase where receivers of the shared memory buffer can get a read-only view, while the sender continues to write to the buffer. See CursorWindow documentation in Android for more details: https://developer.android.com/reference/android/database/CursorWindow This usecase cannot be implemented with the existing F_SEAL_WRITE seal. To support the usecase, this patch adds a new F_SEAL_FUTURE_WRITE seal which prevents any future mmap and write syscalls from succeeding while keeping the existing mmap active. A better way to do F_SEAL_FUTURE_WRITE seal was discussed [1] last week where we don't need to modify core VFS structures to get the same behavior of the seal. This solves several side-effects pointed by Andy. self-tests are provided in later patch to verify the expected semantics. [1] https://lore.kernel.org/lkml/20181111173650.GA256781@google.com/ Thanks a lot to Andy for suggestions to improve code. Link: http://lkml.kernel.org/r/20190112203816.85534-2-joel@joelfernandes.org Signed-off-by: Joel Fernandes (Google) Acked-by: John Stultz Cc: Andy Lutomirski Cc: Minchan Kim Cc: Jann Horn Cc: Al Viro Cc: Andy Lutomirski Cc: Hugh Dickins Cc: J. Bruce Fields Cc: Jeff Layton Cc: Marc-Andr Lureau Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- include/uapi/linux/fcntl.h | 1 + mm/memfd.c | 3 ++- mm/shmem.c | 25 ++++++++++++++++++++++--- 4 files changed, 26 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a7fa037b876b..b0eef008de67 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -530,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); /* protected by i_mutex */ - if (info->seals & F_SEAL_WRITE) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 6448cdd9a350..a2f8658f1c55 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -41,6 +41,7 @@ #define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ +#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/mm/memfd.c b/mm/memfd.c index 97264c79d2cd..650e65a46b9c 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -131,7 +131,8 @@ static unsigned int *memfd_file_seals_ptr(struct file *file) #define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ - F_SEAL_WRITE) + F_SEAL_WRITE | \ + F_SEAL_FUTURE_WRITE) static int memfd_add_seals(struct file *file, unsigned int seals) { diff --git a/mm/shmem.c b/mm/shmem.c index 283a1833dafc..b3db3779a30a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2190,6 +2190,24 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { + struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + + if (info->seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since the F_SEAL_FUTURE_WRITE seals allow for a MAP_SHARED + * read-only mapping, take care to not allow mprotect to revert + * protections. + */ + vma->vm_flags &= ~(VM_MAYWRITE); + } + file_accessed(file); vma->vm_ops = &shmem_vm_ops; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && @@ -2440,8 +2458,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping, pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ - if (unlikely(info->seals & (F_SEAL_WRITE | F_SEAL_GROW))) { - if (info->seals & F_SEAL_WRITE) + if (unlikely(info->seals & (F_SEAL_GROW | + F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) return -EPERM; if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) return -EPERM; @@ -2704,7 +2723,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); /* protected by i_mutex */ - if (info->seals & F_SEAL_WRITE) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { error = -EPERM; goto out; } -- cgit From 221c5eb2338232f7340386de1c43decc32682e58 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Jan 2019 09:41:58 -0700 Subject: io_uring: add support for IORING_OP_POLL This is basically a direct port of bfe4037e722e, which implements a one-shot poll command through aio. Description below is based on that commit as well. However, instead of adding a POLL command and relying on io_cancel(2) to remove it, we mimic the epoll(2) interface of having a command to add a poll notification, IORING_OP_POLL_ADD, and one to remove it again, IORING_OP_POLL_REMOVE. To poll for a file descriptor the application should submit an sqe of type IORING_OP_POLL. It will poll the fd for the events specified in the poll_events field. Unlike poll or epoll without EPOLLONESHOT this interface always works in one shot mode, that is once the sqe is completed, it will have to be resubmitted. Reviewed-by: Hannes Reinecke Based-on-code-from: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/io_uring.c | 263 +++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/io_uring.h | 3 + 2 files changed, 265 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index d2a3a1bc85cc..85b914bd823c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -161,6 +161,7 @@ struct io_ring_ctx { * manipulate the list, hence no extra locking is needed there. */ struct list_head poll_list; + struct list_head cancel_list; } ____cacheline_aligned_in_smp; #if defined(CONFIG_UNIX) @@ -176,8 +177,20 @@ struct sqe_submit { bool needs_fixed_file; }; +struct io_poll_iocb { + struct file *file; + struct wait_queue_head *head; + __poll_t events; + bool woken; + bool canceled; + struct wait_queue_entry wait; +}; + struct io_kiocb { - struct kiocb rw; + union { + struct kiocb rw; + struct io_poll_iocb poll; + }; struct sqe_submit submit; @@ -261,6 +274,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_waitqueue_head(&ctx->wait); spin_lock_init(&ctx->completion_lock); INIT_LIST_HEAD(&ctx->poll_list); + INIT_LIST_HEAD(&ctx->cancel_list); return ctx; } @@ -1058,6 +1072,246 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, return 0; } +static void io_poll_remove_one(struct io_kiocb *req) +{ + struct io_poll_iocb *poll = &req->poll; + + spin_lock(&poll->head->lock); + WRITE_ONCE(poll->canceled, true); + if (!list_empty(&poll->wait.entry)) { + list_del_init(&poll->wait.entry); + queue_work(req->ctx->sqo_wq, &req->work); + } + spin_unlock(&poll->head->lock); + + list_del_init(&req->list); +} + +static void io_poll_remove_all(struct io_ring_ctx *ctx) +{ + struct io_kiocb *req; + + spin_lock_irq(&ctx->completion_lock); + while (!list_empty(&ctx->cancel_list)) { + req = list_first_entry(&ctx->cancel_list, struct io_kiocb,list); + io_poll_remove_one(req); + } + spin_unlock_irq(&ctx->completion_lock); +} + +/* + * Find a running poll command that matches one specified in sqe->addr, + * and remove it if found. + */ +static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *poll_req, *next; + int ret = -ENOENT; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || + sqe->poll_events) + return -EINVAL; + + spin_lock_irq(&ctx->completion_lock); + list_for_each_entry_safe(poll_req, next, &ctx->cancel_list, list) { + if (READ_ONCE(sqe->addr) == poll_req->user_data) { + io_poll_remove_one(poll_req); + ret = 0; + break; + } + } + spin_unlock_irq(&ctx->completion_lock); + + io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_free_req(req); + return 0; +} + +static void io_poll_complete(struct io_kiocb *req, __poll_t mask) +{ + io_cqring_add_event(req->ctx, req->user_data, mangle_poll(mask), 0); + io_fput(req); + io_free_req(req); +} + +static void io_poll_complete_work(struct work_struct *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_poll_iocb *poll = &req->poll; + struct poll_table_struct pt = { ._key = poll->events }; + struct io_ring_ctx *ctx = req->ctx; + __poll_t mask = 0; + + if (!READ_ONCE(poll->canceled)) + mask = vfs_poll(poll->file, &pt) & poll->events; + + /* + * Note that ->ki_cancel callers also delete iocb from active_reqs after + * calling ->ki_cancel. We need the ctx_lock roundtrip here to + * synchronize with them. In the cancellation case the list_del_init + * itself is not actually needed, but harmless so we keep it in to + * avoid further branches in the fast path. + */ + spin_lock_irq(&ctx->completion_lock); + if (!mask && !READ_ONCE(poll->canceled)) { + add_wait_queue(poll->head, &poll->wait); + spin_unlock_irq(&ctx->completion_lock); + return; + } + list_del_init(&req->list); + spin_unlock_irq(&ctx->completion_lock); + + io_poll_complete(req, mask); +} + +static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, + void *key) +{ + struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, + wait); + struct io_kiocb *req = container_of(poll, struct io_kiocb, poll); + struct io_ring_ctx *ctx = req->ctx; + __poll_t mask = key_to_poll(key); + + poll->woken = true; + + /* for instances that support it check for an event match first: */ + if (mask) { + unsigned long flags; + + if (!(mask & poll->events)) + return 0; + + /* try to complete the iocb inline if we can: */ + if (spin_trylock_irqsave(&ctx->completion_lock, flags)) { + list_del(&req->list); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + + list_del_init(&poll->wait.entry); + io_poll_complete(req, mask); + return 1; + } + } + + list_del_init(&poll->wait.entry); + queue_work(ctx->sqo_wq, &req->work); + return 1; +} + +struct io_poll_table { + struct poll_table_struct pt; + struct io_kiocb *req; + int error; +}; + +static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, + struct poll_table_struct *p) +{ + struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + + if (unlikely(pt->req->poll.head)) { + pt->error = -EINVAL; + return; + } + + pt->error = 0; + pt->req->poll.head = head; + add_wait_queue(head, &pt->req->poll.wait); +} + +static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_poll_iocb *poll = &req->poll; + struct io_ring_ctx *ctx = req->ctx; + struct io_poll_table ipt; + unsigned flags; + __poll_t mask; + u16 events; + int fd; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) + return -EINVAL; + + INIT_WORK(&req->work, io_poll_complete_work); + events = READ_ONCE(sqe->poll_events); + poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; + + flags = READ_ONCE(sqe->flags); + fd = READ_ONCE(sqe->fd); + + if (flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files)) + return -EBADF; + poll->file = ctx->user_files[fd]; + req->flags |= REQ_F_FIXED_FILE; + } else { + poll->file = fget(fd); + } + if (unlikely(!poll->file)) + return -EBADF; + + poll->head = NULL; + poll->woken = false; + poll->canceled = false; + + ipt.pt._qproc = io_poll_queue_proc; + ipt.pt._key = poll->events; + ipt.req = req; + ipt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ + + /* initialized the list so that we can do list_empty checks */ + INIT_LIST_HEAD(&poll->wait.entry); + init_waitqueue_func_entry(&poll->wait, io_poll_wake); + + /* one for removal from waitqueue, one for this function */ + refcount_set(&req->refs, 2); + + mask = vfs_poll(poll->file, &ipt.pt) & poll->events; + if (unlikely(!poll->head)) { + /* we did not manage to set up a waitqueue, done */ + goto out; + } + + spin_lock_irq(&ctx->completion_lock); + spin_lock(&poll->head->lock); + if (poll->woken) { + /* wake_up context handles the rest */ + mask = 0; + ipt.error = 0; + } else if (mask || ipt.error) { + /* if we get an error or a mask we are done */ + WARN_ON_ONCE(list_empty(&poll->wait.entry)); + list_del_init(&poll->wait.entry); + } else { + /* actually waiting for an event */ + list_add_tail(&req->list, &ctx->cancel_list); + } + spin_unlock(&poll->head->lock); + spin_unlock_irq(&ctx->completion_lock); + +out: + if (unlikely(ipt.error)) { + if (!(flags & IOSQE_FIXED_FILE)) + fput(poll->file); + /* + * Drop one of our refs to this req, __io_submit_sqe() will + * drop the other one since we're returning an error. + */ + io_free_req(req); + return ipt.error; + } + + if (mask) + io_poll_complete(req, mask); + io_free_req(req); + return 0; +} + static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct sqe_submit *s, bool force_nonblock, struct io_submit_state *state) @@ -1093,6 +1347,12 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, case IORING_OP_FSYNC: ret = io_fsync(req, s->sqe, force_nonblock); break; + case IORING_OP_POLL_ADD: + ret = io_poll_add(req, s->sqe); + break; + case IORING_OP_POLL_REMOVE: + ret = io_poll_remove(req, s->sqe); + break; default: ret = -EINVAL; break; @@ -2131,6 +2391,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) percpu_ref_kill(&ctx->refs); mutex_unlock(&ctx->uring_lock); + io_poll_remove_all(ctx); io_iopoll_reap_events(ctx); wait_for_completion(&ctx->ctx_done); io_ring_ctx_free(ctx); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0ec74bab8dbe..e23408692118 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -25,6 +25,7 @@ struct io_uring_sqe { union { __kernel_rwf_t rw_flags; __u32 fsync_flags; + __u16 poll_events; }; __u64 user_data; /* data to be passed back at completion time */ union { @@ -51,6 +52,8 @@ struct io_uring_sqe { #define IORING_OP_FSYNC 3 #define IORING_OP_READ_FIXED 4 #define IORING_OP_WRITE_FIXED 5 +#define IORING_OP_POLL_ADD 6 +#define IORING_OP_POLL_REMOVE 7 /* * sqe->fsync_flags -- cgit From 54d50897d544c874562253e2a8f70dfcad22afe8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 7 Mar 2019 16:27:14 -0800 Subject: linux/kernel.h: split *_MAX and *_MIN macros into tends to be cluttered because we often put various sort of unrelated stuff in it. So, we have split out a sensible chunk of code into a separate header from time to time. This commit splits out the *_MAX and *_MIN defines. The standard header contains various MAX, MIN constants including numerial limits. [1] I think it makes sense to move in-kernel MAX, MIN constants into include/linux/limits.h. We already have include/uapi/linux/limits.h to contain some user-space constants. I changed its include guard to _UAPI_LINUX_LIMITS_H. This change has no impact to the user-space because scripts/headers_install.sh rips off the '_UAPI' prefix from the include guards of exported headers. [1] http://pubs.opengroup.org/onlinepubs/009604499/basedefs/limits.h.html Link: http://lkml.kernel.org/r/1549156242-20806-2-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Alex Elder Cc: Alexey Dobriyan Cc: Zhang Yanmin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 29 +---------------------------- include/linux/limits.h | 36 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/limits.h | 4 ++-- 3 files changed, 39 insertions(+), 30 deletions(-) create mode 100644 include/linux/limits.h (limited to 'include/uapi/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a9ff66977e10..34a5036debd3 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -4,6 +4,7 @@ #include +#include #include #include #include @@ -17,34 +18,6 @@ #include #include -#define USHRT_MAX ((unsigned short)~0U) -#define SHRT_MAX ((short)(USHRT_MAX>>1)) -#define SHRT_MIN ((short)(-SHRT_MAX - 1)) -#define INT_MAX ((int)(~0U>>1)) -#define INT_MIN (-INT_MAX - 1) -#define UINT_MAX (~0U) -#define LONG_MAX ((long)(~0UL>>1)) -#define LONG_MIN (-LONG_MAX - 1) -#define ULONG_MAX (~0UL) -#define LLONG_MAX ((long long)(~0ULL>>1)) -#define LLONG_MIN (-LLONG_MAX - 1) -#define ULLONG_MAX (~0ULL) -#define SIZE_MAX (~(size_t)0) -#define PHYS_ADDR_MAX (~(phys_addr_t)0) - -#define U8_MAX ((u8)~0U) -#define S8_MAX ((s8)(U8_MAX>>1)) -#define S8_MIN ((s8)(-S8_MAX - 1)) -#define U16_MAX ((u16)~0U) -#define S16_MAX ((s16)(U16_MAX>>1)) -#define S16_MIN ((s16)(-S16_MAX - 1)) -#define U32_MAX ((u32)~0U) -#define S32_MAX ((s32)(U32_MAX>>1)) -#define S32_MIN ((s32)(-S32_MAX - 1)) -#define U64_MAX ((u64)~0ULL) -#define S64_MAX ((s64)(U64_MAX>>1)) -#define S64_MIN ((s64)(-S64_MAX - 1)) - #define STACK_MAGIC 0xdeadbeef /** diff --git a/include/linux/limits.h b/include/linux/limits.h new file mode 100644 index 000000000000..76afcd24ff8c --- /dev/null +++ b/include/linux/limits.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LIMITS_H +#define _LINUX_LIMITS_H + +#include +#include + +#define USHRT_MAX ((unsigned short)~0U) +#define SHRT_MAX ((short)(USHRT_MAX >> 1)) +#define SHRT_MIN ((short)(-SHRT_MAX - 1)) +#define INT_MAX ((int)(~0U >> 1)) +#define INT_MIN (-INT_MAX - 1) +#define UINT_MAX (~0U) +#define LONG_MAX ((long)(~0UL >> 1)) +#define LONG_MIN (-LONG_MAX - 1) +#define ULONG_MAX (~0UL) +#define LLONG_MAX ((long long)(~0ULL >> 1)) +#define LLONG_MIN (-LLONG_MAX - 1) +#define ULLONG_MAX (~0ULL) +#define SIZE_MAX (~(size_t)0) +#define PHYS_ADDR_MAX (~(phys_addr_t)0) + +#define U8_MAX ((u8)~0U) +#define S8_MAX ((s8)(U8_MAX >> 1)) +#define S8_MIN ((s8)(-S8_MAX - 1)) +#define U16_MAX ((u16)~0U) +#define S16_MAX ((s16)(U16_MAX >> 1)) +#define S16_MIN ((s16)(-S16_MAX - 1)) +#define U32_MAX ((u32)~0U) +#define S32_MAX ((s32)(U32_MAX >> 1)) +#define S32_MIN ((s32)(-S32_MAX - 1)) +#define U64_MAX ((u64)~0ULL) +#define S64_MAX ((s64)(U64_MAX >> 1)) +#define S64_MIN ((s64)(-S64_MAX - 1)) + +#endif /* _LINUX_LIMITS_H */ diff --git a/include/uapi/linux/limits.h b/include/uapi/linux/limits.h index c3547f07605c..6bcbe3068761 100644 --- a/include/uapi/linux/limits.h +++ b/include/uapi/linux/limits.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _LINUX_LIMITS_H -#define _LINUX_LIMITS_H +#ifndef _UAPI_LINUX_LIMITS_H +#define _UAPI_LINUX_LIMITS_H #define NR_OPEN 1024 -- cgit From 60d6d04ca3abb34d5e89f030dbea440d9715a168 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Thu, 7 Mar 2019 16:29:09 -0800 Subject: autofs: add ignore mount option Add an autofs file system mount option that can be used to provide a generic indicator to applications that the mount entry should be ignored when displaying mount information. In other OSes that provide autofs and that provide a mount list to user space based on the kernel mount list a no-op mount option ("ignore" is the one use on the most common OS) is allowed so that autofs file system users can optionally use it. The idea is that it be used by user space programs to exclude autofs mounts from consideration when reading the mounts list. Prior to the change to link /etc/mtab to /proc/self/mounts all I needed to do to achieve this was to use mount(2) and not update the mtab but now that no longer works. I know the symlinking happened a long time ago and I considered doing this then but, at the time I couldn't remember the commonly used option name and thought persuading the various utility maintainers would be too hard. But now I have a RHEL request to do this for compatibility for a widely used product so I want to go ahead with it and try and enlist the help of some utility package maintainers. Clearly, without the option nothing can be done so it's at least a start. Link: http://lkml.kernel.org/r/154725123970.11260.6113771566924907275.stgit@pluto-themaw-net Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs/autofs_i.h | 1 + fs/autofs/inode.c | 9 ++++++++- include/uapi/linux/auto_fs.h | 2 +- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 3e59f0ed777b..b735f2b1e462 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -105,6 +105,7 @@ struct autofs_wait_queue { #define AUTOFS_SBI_CATATONIC 0x0001 #define AUTOFS_SBI_STRICTEXPIRE 0x0002 +#define AUTOFS_SBI_IGNORE 0x0004 struct autofs_sb_info { u32 magic; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 078992eee299..8647ecaa89fc 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -89,6 +89,8 @@ static int autofs_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",indirect"); if (sbi->flags & AUTOFS_SBI_STRICTEXPIRE) seq_printf(m, ",strictexpire"); + if (sbi->flags & AUTOFS_SBI_IGNORE) + seq_printf(m, ",ignore"); #ifdef CONFIG_CHECKPOINT_RESTORE if (sbi->pipe) seq_printf(m, ",pipe_ino=%ld", file_inode(sbi->pipe)->i_ino); @@ -111,7 +113,8 @@ static const struct super_operations autofs_sops = { }; enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto, - Opt_indirect, Opt_direct, Opt_offset, Opt_strictexpire}; + Opt_indirect, Opt_direct, Opt_offset, Opt_strictexpire, + Opt_ignore}; static const match_table_t tokens = { {Opt_fd, "fd=%u"}, @@ -124,6 +127,7 @@ static const match_table_t tokens = { {Opt_direct, "direct"}, {Opt_offset, "offset"}, {Opt_strictexpire, "strictexpire"}, + {Opt_ignore, "ignore"}, {Opt_err, NULL} }; @@ -206,6 +210,9 @@ static int parse_options(char *options, case Opt_strictexpire: sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; break; + case Opt_ignore: + sbi->flags |= AUTOFS_SBI_IGNORE; + break; default: return 1; } diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h index 082119630b49..1f7925afad2d 100644 --- a/include/uapi/linux/auto_fs.h +++ b/include/uapi/linux/auto_fs.h @@ -23,7 +23,7 @@ #define AUTOFS_MIN_PROTO_VERSION 3 #define AUTOFS_MAX_PROTO_VERSION 5 -#define AUTOFS_PROTO_SUBVERSION 4 +#define AUTOFS_PROTO_SUBVERSION 5 /* * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed -- cgit From 6eb3c3d0a52dca337e327ae8868ca1f44a712e02 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 7 Mar 2019 16:29:26 -0800 Subject: exec: increase BINPRM_BUF_SIZE to 256 Large enterprise clients often run applications out of networked file systems where the IT mandated layout of project volumes can end up leading to paths that are longer than 128 characters. Bumping this up to the next order of two solves this problem in all but the most egregious case while still fitting into a 512b slab. [oleg@redhat.com: update comment, per Kees] Link: http://lkml.kernel.org/r/20181112160956.GA28472@redhat.com Signed-off-by: Oleg Nesterov Reported-by: Ben Woodard Reviewed-by: Andrew Morton Acked-by: Michal Hocko Acked-by: Kees Cook Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- include/uapi/linux/binfmts.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/exec.c b/fs/exec.c index bf0ace3841ad..2e0033348d8e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1563,7 +1563,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm) /* * Fill the binprm structure from the inode. - * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes + * Check permissions, then read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */ diff --git a/include/uapi/linux/binfmts.h b/include/uapi/linux/binfmts.h index 4abad03a8853..689025d9c185 100644 --- a/include/uapi/linux/binfmts.h +++ b/include/uapi/linux/binfmts.h @@ -16,6 +16,6 @@ struct pt_regs; #define MAX_ARG_STRINGS 0x7FFFFFFF /* sizeof(linux_binprm->buf) */ -#define BINPRM_BUF_SIZE 128 +#define BINPRM_BUF_SIZE 256 #endif /* _UAPI_LINUX_BINFMTS_H */ -- cgit From dbafd7ddd62369b2f3926ab847cbf8fc40e800b7 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 12 Mar 2019 10:23:04 -0700 Subject: bpf: Add bpf_get_listener_sock(struct bpf_sock *sk) helper Add a new helper "struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)" which returns a bpf_sock in TCP_LISTEN state. It will trace back to the listener sk from a request_sock if possible. It returns NULL for all other cases. No reference is taken because the helper ensures the sk is in SOCK_RCU_FREE (where the TCP_LISTEN sock should be in). Hence, bpf_sk_release() is unnecessary and the verifier does not allow bpf_sk_release(listen_sk) to be called either. The following is also allowed because the bpf_prog is run under rcu_read_lock(): sk = bpf_sk_lookup_tcp(); /* if (!sk) { ... } */ listen_sk = bpf_get_listener_sock(sk); /* if (!listen_sk) { ... } */ bpf_sk_release(sk); src_port = listen_sk->src_port; /* Allowed */ Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 11 ++++++++++- net/core/filter.c | 21 +++++++++++++++++++++ 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c38ac9a92a7..983b25cb608d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2366,6 +2366,14 @@ union bpf_attr { * current value is ect (ECN capable). Works with IPv6 and IPv4. * Return * 1 if set, 0 if not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in TCP_LISTEN state. + * bpf_sk_release() is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or NULL in + * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2465,7 +2473,8 @@ union bpf_attr { FN(spin_unlock), \ FN(sk_fullsock), \ FN(tcp_sock), \ - FN(skb_ecn_set_ce), + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/net/core/filter.c b/net/core/filter.c index 36b6afacf83c..647c63a7b25b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5418,6 +5418,23 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = { .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; +BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) +{ + sk = sk_to_full_sk(sk); + + if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +static const struct bpf_func_proto bpf_get_listener_sock_proto = { + .func = bpf_get_listener_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, +}; + BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; @@ -5603,6 +5620,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; + case BPF_FUNC_get_listener_sock: + return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif @@ -5698,6 +5717,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; + case BPF_FUNC_get_listener_sock: + return &bpf_get_listener_sock_proto; #endif default: return bpf_base_func_proto(func_id); -- cgit From 62369db2df8d1edfa040878203b446e023a16802 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 14 Mar 2019 12:38:39 +0000 Subject: bpf: fix documentation for eBPF helpers Another round of minor fixes for the documentation of the BPF helpers located in the UAPI bpf.h header file. Changes include: - Moving around description of some helpers, to keep the descriptions in the same order as helpers are declared (bpf_map_push_elem(), leftover from commit 90b1023f68c7 ("bpf: fix documentation for eBPF helpers"), bpf_rc_keydown(), and bpf_skb_ancestor_cgroup_id()). - Fixing typos ("contex" -> "context"). - Harmonising return types ("void* " -> "void *", "uint64_t" -> "u64"). - Addition of the "bpf_" prefix to bpf_get_storage(). - Light additions of RST markup on some keywords. - Empty line deletion between description and return value for bpf_tcp_sock(). - Edit for the description for bpf_skb_ecn_set_ce() (capital letters, acronym expansion, no effect if ECT not set, more details on return value). Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 128 ++++++++++++++++++++++++----------------------- 1 file changed, 65 insertions(+), 63 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 983b25cb608d..4465d00d3493 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -502,16 +502,6 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) - * Description - * Push an element *value* in *map*. *flags* is one of: - * - * **BPF_EXIST** - * If the queue/stack is full, the oldest element is removed to - * make room for this. - * Return - * 0 on success, or a negative error in case of failure. - * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1435,14 +1425,14 @@ union bpf_attr { * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return * A 8-byte long non-decreasing number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return * A 8-byte long non-decreasing number. * @@ -2098,52 +2088,52 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * int bpf_rc_repeat(void *ctx) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded key press with *scancode*, - * *toggle* value in the given *protocol*. The scancode will be - * translated to a keycode using the rc keymap, and reported as - * an input key down event. After a period a key up event is - * generated. This period can be extended by calling either - * **bpf_rc_keydown**\ () again with the same values, or calling - * **bpf_rc_repeat**\ (). + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. * - * Some protocols include a toggle bit, in case the button was - * released and pressed again between consecutive scancodes. + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. * * The *ctx* should point to the lirc sample as passed into * the program. * - * The *protocol* is the decoded protocol number (see - * **enum rc_proto** for some predefined values). - * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * int bpf_rc_repeat(void *ctx) + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded repeat key message. This delays - * the generation of a key up event for previously generated - * key down event. + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). * - * Some IR protocols like NEC have a special IR message for - * repeating last button, for when a button is held down. + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. * * The *ctx* should point to the lirc sample as passed into * the program. * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) * Description * Return the cgroup v2 id of the socket associated with the *skb*. * This is roughly similar to the **bpf_get_cgroup_classid**\ () @@ -2159,30 +2149,12 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) - * Description - * Return id of cgroup v2 that is ancestor of cgroup associated - * with the *skb* at the *ancestor_level*. The root cgroup is at - * *ancestor_level* zero and each step down the hierarchy - * increments the level. If *ancestor_level* == level of cgroup - * associated with *skb*, then return value will be same as that - * of **bpf_skb_cgroup_id**\ (). - * - * The helper is useful to implement policies based on cgroups - * that are upper in hierarchy than immediate cgroup associated - * with *skb*. - * - * The format of returned id and helper limitations are same as in - * **bpf_skb_cgroup_id**\ (). - * Return - * The id is returned or 0 in case the id could not be retrieved. - * * u64 bpf_get_current_cgroup_id(void) * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. * - * void* get_local_storage(void *map, u64 flags) + * void *bpf_get_local_storage(void *map, u64 flags) * Description * Get the pointer to the local storage area. * The type and the size of the local storage is defined @@ -2209,6 +2181,24 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for TCP socket matching *tuple*, optionally in a child @@ -2289,6 +2279,16 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_map_pop_elem(struct bpf_map *map, void *value) * Description * Pop an element from *map*. @@ -2346,33 +2346,35 @@ union bpf_attr { * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_sock** pointer such - * that all the fields in bpf_sock can be accessed. + * that all the fields in this **bpf_sock** can be accessed. * Return - * A **struct bpf_sock** pointer on success, or NULL in + * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. * * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_tcp_sock** pointer from a * **struct bpf_sock** pointer. - * * Return - * A **struct bpf_tcp_sock** pointer on success, or NULL in + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * * int bpf_skb_ecn_set_ce(struct sk_buf *skb) - * Description - * Sets ECN of IP header to ce (congestion encountered) if - * current value is ect (ECN capable). Works with IPv6 and IPv4. - * Return - * 1 if set, 0 if not set. + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. * * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) * Description - * Return a **struct bpf_sock** pointer in TCP_LISTEN state. - * bpf_sk_release() is unnecessary and not allowed. + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. * Return - * A **struct bpf_sock** pointer on success, or NULL in + * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ -- cgit From 0eb0978528d47699edd091dc2c337952ad8da436 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 14 Mar 2019 12:38:40 +0000 Subject: bpf: add documentation for helpers bpf_spin_lock(), bpf_spin_unlock() Add documentation for the BPF spinlock-related helpers to the doc in bpf.h. I added the constraints and restrictions coming with the use of spinlocks for BPF: not all of it is directly related to the use of the helper, but I thought it would be nice for users to find them in the man page. This list of restrictions is nearly a verbatim copy of the list in Alexei's commit log for those helpers. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4465d00d3493..929c8e537a14 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2343,6 +2343,61 @@ union bpf_attr { * Return * 0 * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_sock** pointer such -- cgit