From 68ca5d4eebb8c4de246ee5f634eee26bc689562d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 19 Mar 2024 16:38:50 -0700 Subject: bpf: support BPF cookie in raw tracepoint (raw_tp, tp_btf) programs Wire up BPF cookie for raw tracepoint programs (both BTF and non-BTF aware variants). This brings them up to part w.r.t. BPF cookie usage with classic tracepoint and fentry/fexit programs. Acked-by: Stanislav Fomichev Acked-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Message-ID: <20240319233852.1977493-4-andrii@kernel.org> Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c42b9f1bada..9585f5345353 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1662,8 +1662,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ -- cgit v1.2.3 From a3293a85381ec9680aa2929547fbc76c5d87a1b2 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Thu, 14 Mar 2024 16:32:24 +0100 Subject: media: v4l2: Add REMOVE_BUFS ioctl VIDIOC_REMOVE_BUFS ioctl allows to remove buffers from a queue. The number of buffers to remove in given by count field of struct v4l2_remove_buffers and the range start at the index specified in the same structure. Signed-off-by: Benjamin Gaignard Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Hans Verkuil [hverkuil: vidioc-remove-bufs.rst: mention no bufs are freed on error] --- .../userspace-api/media/v4l/user-func.rst | 1 + .../userspace-api/media/v4l/vidioc-remove-bufs.rst | 86 ++++++++++++++++++++++ .../userspace-api/media/v4l/vidioc-reqbufs.rst | 1 + drivers/media/common/videobuf2/videobuf2-core.c | 38 ++++++++++ drivers/media/common/videobuf2/videobuf2-v4l2.c | 20 ++++- drivers/media/v4l2-core/v4l2-dev.c | 3 + drivers/media/v4l2-core/v4l2-ioctl.c | 30 ++++++++ include/media/v4l2-ioctl.h | 4 + include/media/videobuf2-core.h | 10 +++ include/media/videobuf2-v4l2.h | 2 + include/uapi/linux/videodev2.h | 17 +++++ 11 files changed, 211 insertions(+), 1 deletion(-) create mode 100644 Documentation/userspace-api/media/v4l/vidioc-remove-bufs.rst (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/user-func.rst b/Documentation/userspace-api/media/v4l/user-func.rst index 15ff0bf7bbe6..6f661138801c 100644 --- a/Documentation/userspace-api/media/v4l/user-func.rst +++ b/Documentation/userspace-api/media/v4l/user-func.rst @@ -62,6 +62,7 @@ Function Reference vidioc-query-dv-timings vidioc-querystd vidioc-reqbufs + vidioc-remove-bufs vidioc-s-hw-freq-seek vidioc-streamon vidioc-subdev-enum-frame-interval diff --git a/Documentation/userspace-api/media/v4l/vidioc-remove-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-remove-bufs.rst new file mode 100644 index 000000000000..1995b39af9ba --- /dev/null +++ b/Documentation/userspace-api/media/v4l/vidioc-remove-bufs.rst @@ -0,0 +1,86 @@ +.. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: V4L + +.. _VIDIOC_REMOVE_BUFS: + +************************ +ioctl VIDIOC_REMOVE_BUFS +************************ + +Name +==== + +VIDIOC_REMOVE_BUFS - Removes buffers from a queue + +Synopsis +======== + +.. c:macro:: VIDIOC_REMOVE_BUFS + +``int ioctl(int fd, VIDIOC_REMOVE_BUFS, struct v4l2_remove_buffers *argp)`` + +Arguments +========= + +``fd`` + File descriptor returned by :c:func:`open()`. + +``argp`` + Pointer to struct :c:type:`v4l2_remove_buffers`. + +Description +=========== + +Applications can optionally call the :ref:`VIDIOC_REMOVE_BUFS` ioctl to +remove buffers from a queue. +:ref:`VIDIOC_CREATE_BUFS` ioctl support is mandatory to enable :ref:`VIDIOC_REMOVE_BUFS`. +This ioctl is available if the ``V4L2_BUF_CAP_SUPPORTS_REMOVE_BUFS`` capability +is set on the queue when :c:func:`VIDIOC_REQBUFS` or :c:func:`VIDIOC_CREATE_BUFS` +are invoked. + +.. c:type:: v4l2_remove_buffers + +.. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.5cm}| + +.. flat-table:: struct v4l2_remove_buffers + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u32 + - ``index`` + - The starting buffer index to remove. This field is ignored if count == 0. + * - __u32 + - ``count`` + - The number of buffers to be removed with indices 'index' until 'index + count - 1'. + All buffers in this range must be valid and in DEQUEUED state. + :ref:`VIDIOC_REMOVE_BUFS` will always check the validity of ``type`, if it is + invalid it returns ``EINVAL`` error code. + If count is set to 0 :ref:`VIDIOC_REMOVE_BUFS` will do nothing and return 0. + * - __u32 + - ``type`` + - Type of the stream or buffers, this is the same as the struct + :c:type:`v4l2_format` ``type`` field. See + :c:type:`v4l2_buf_type` for valid values. + * - __u32 + - ``reserved``\ [13] + - A place holder for future extensions. Drivers and applications + must set the array to zero. + +Return Value +============ + +On success 0 is returned, on error -1 and the ``errno`` variable is set +appropriately. The generic error codes are described at the +:ref:`Generic Error Codes ` chapter. If an error occurs, no +buffers will be freed and one of the error codes below will be returned: + +EBUSY + File I/O is in progress. + One or more of the buffers in the range ``index`` to ``index + count - 1`` are not + in DEQUEUED state. + +EINVAL + One or more of the buffers in the range ``index`` to ``index + count - 1`` do not + exist in the queue. + The buffer type (``type`` field) is not valid. diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index 0b3a41a45d05..bbc22dd76032 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -121,6 +121,7 @@ aborting or finishing any DMA in progress, an implicit .. _V4L2-BUF-CAP-SUPPORTS-M2M-HOLD-CAPTURE-BUF: .. _V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS: .. _V4L2-BUF-CAP-SUPPORTS-MAX-NUM-BUFFERS: +.. _V4L2-BUF-CAP-SUPPORTS-REMOVE-BUFS: .. raw:: latex diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 009cea95d662..0b2b48e1b2df 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -1691,6 +1691,44 @@ int vb2_core_prepare_buf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb) } EXPORT_SYMBOL_GPL(vb2_core_prepare_buf); +int vb2_core_remove_bufs(struct vb2_queue *q, unsigned int start, unsigned int count) +{ + unsigned int i, ret = 0; + unsigned int q_num_bufs = vb2_get_num_buffers(q); + + if (count == 0) + return 0; + + if (count > q_num_bufs) + return -EINVAL; + + if (start > q->max_num_buffers - count) + return -EINVAL; + + mutex_lock(&q->mmap_lock); + + /* Check that all buffers in the range exist */ + for (i = start; i < start + count; i++) { + struct vb2_buffer *vb = vb2_get_buffer(q, i); + + if (!vb) { + ret = -EINVAL; + goto unlock; + } + if (vb->state != VB2_BUF_STATE_DEQUEUED) { + ret = -EBUSY; + goto unlock; + } + } + __vb2_queue_free(q, start, count); + dprintk(q, 2, "%u buffers removed\n", count); + +unlock: + mutex_unlock(&q->mmap_lock); + return ret; +} +EXPORT_SYMBOL_GPL(vb2_core_remove_bufs); + /* * vb2_start_streaming() - Attempt to start streaming. * @q: videobuf2 queue diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 03e8080a68a8..293f3d5f1c4e 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -685,7 +685,7 @@ static void vb2_set_flags_and_caps(struct vb2_queue *q, u32 memory, *flags &= V4L2_MEMORY_FLAG_NON_COHERENT; } - *caps = V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS; + *caps |= V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS; if (q->io_modes & VB2_MMAP) *caps |= V4L2_BUF_CAP_SUPPORTS_MMAP; if (q->io_modes & VB2_USERPTR) @@ -1001,6 +1001,24 @@ EXPORT_SYMBOL_GPL(vb2_poll); /* vb2 ioctl helpers */ +int vb2_ioctl_remove_bufs(struct file *file, void *priv, + struct v4l2_remove_buffers *d) +{ + struct video_device *vdev = video_devdata(file); + + if (vdev->queue->type != d->type) + return -EINVAL; + + if (d->count == 0) + return 0; + + if (vb2_queue_is_busy(vdev->queue, file)) + return -EBUSY; + + return vb2_core_remove_bufs(vdev->queue, d->index, d->count); +} +EXPORT_SYMBOL_GPL(vb2_ioctl_remove_bufs); + int vb2_ioctl_reqbufs(struct file *file, void *priv, struct v4l2_requestbuffers *p) { diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index d13954bd31fd..e39e9742fdb5 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -722,6 +722,9 @@ static void determine_valid_ioctls(struct video_device *vdev) SET_VALID_IOCTL(ops, VIDIOC_PREPARE_BUF, vidioc_prepare_buf); SET_VALID_IOCTL(ops, VIDIOC_STREAMON, vidioc_streamon); SET_VALID_IOCTL(ops, VIDIOC_STREAMOFF, vidioc_streamoff); + /* VIDIOC_CREATE_BUFS support is mandatory to enable VIDIOC_REMOVE_BUFS */ + if (ops->vidioc_create_bufs) + SET_VALID_IOCTL(ops, VIDIOC_REMOVE_BUFS, vidioc_remove_bufs); } if (is_vid || is_vbi || is_meta) { diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 6e7b8b682d13..5aeff5519407 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -489,6 +489,14 @@ static void v4l_print_create_buffers(const void *arg, bool write_only) v4l_print_format(&p->format, write_only); } +static void v4l_print_remove_buffers(const void *arg, bool write_only) +{ + const struct v4l2_remove_buffers *p = arg; + + pr_cont("type=%s, index=%u, count=%u\n", + prt_names(p->type, v4l2_type_names), p->index, p->count); +} + static void v4l_print_streamparm(const void *arg, bool write_only) { const struct v4l2_streamparm *p = arg; @@ -2092,6 +2100,7 @@ static int v4l_overlay(const struct v4l2_ioctl_ops *ops, static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { + struct video_device *vfd = video_devdata(file); struct v4l2_requestbuffers *p = arg; int ret = check_fmt(file, p->type); @@ -2100,6 +2109,10 @@ static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops, memset_after(p, 0, flags); + p->capabilities = 0; + if (is_valid_ioctl(vfd, VIDIOC_REMOVE_BUFS)) + p->capabilities = V4L2_BUF_CAP_SUPPORTS_REMOVE_BUFS; + return ops->vidioc_reqbufs(file, fh, p); } @@ -2133,6 +2146,7 @@ static int v4l_dqbuf(const struct v4l2_ioctl_ops *ops, static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { + struct video_device *vfd = video_devdata(file); struct v4l2_create_buffers *create = arg; int ret = check_fmt(file, create->format.type); @@ -2143,6 +2157,10 @@ static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops, v4l_sanitize_format(&create->format); + create->capabilities = 0; + if (is_valid_ioctl(vfd, VIDIOC_REMOVE_BUFS)) + create->capabilities = V4L2_BUF_CAP_SUPPORTS_REMOVE_BUFS; + ret = ops->vidioc_create_bufs(file, fh, create); if (create->format.type == V4L2_BUF_TYPE_VIDEO_CAPTURE || @@ -2161,6 +2179,17 @@ static int v4l_prepare_buf(const struct v4l2_ioctl_ops *ops, return ret ? ret : ops->vidioc_prepare_buf(file, fh, b); } +static int v4l_remove_bufs(const struct v4l2_ioctl_ops *ops, + struct file *file, void *fh, void *arg) +{ + struct v4l2_remove_buffers *remove = arg; + + if (ops->vidioc_remove_bufs) + return ops->vidioc_remove_bufs(file, fh, remove); + + return -ENOTTY; +} + static int v4l_g_parm(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { @@ -2910,6 +2939,7 @@ static const struct v4l2_ioctl_info v4l2_ioctls[] = { IOCTL_INFO(VIDIOC_ENUM_FREQ_BANDS, v4l_enum_freq_bands, v4l_print_freq_band, 0), IOCTL_INFO(VIDIOC_DBG_G_CHIP_INFO, v4l_dbg_g_chip_info, v4l_print_dbg_chip_info, INFO_FL_CLEAR(v4l2_dbg_chip_info, match)), IOCTL_INFO(VIDIOC_QUERY_EXT_CTRL, v4l_query_ext_ctrl, v4l_print_query_ext_ctrl, INFO_FL_CTRL | INFO_FL_CLEAR(v4l2_query_ext_ctrl, id)), + IOCTL_INFO(VIDIOC_REMOVE_BUFS, v4l_remove_bufs, v4l_print_remove_buffers, INFO_FL_PRIO | INFO_FL_QUEUE | INFO_FL_CLEAR(v4l2_remove_buffers, type)), }; #define V4L2_IOCTLS ARRAY_SIZE(v4l2_ioctls) diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h index edb733f21604..bdbb7e542321 100644 --- a/include/media/v4l2-ioctl.h +++ b/include/media/v4l2-ioctl.h @@ -163,6 +163,8 @@ struct v4l2_fh; * :ref:`VIDIOC_CREATE_BUFS ` ioctl * @vidioc_prepare_buf: pointer to the function that implements * :ref:`VIDIOC_PREPARE_BUF ` ioctl + * @vidioc_remove_bufs: pointer to the function that implements + * :ref:`VIDIOC_REMOVE_BUFS ` ioctl * @vidioc_overlay: pointer to the function that implements * :ref:`VIDIOC_OVERLAY ` ioctl * @vidioc_g_fbuf: pointer to the function that implements @@ -422,6 +424,8 @@ struct v4l2_ioctl_ops { struct v4l2_create_buffers *b); int (*vidioc_prepare_buf)(struct file *file, void *fh, struct v4l2_buffer *b); + int (*vidioc_remove_bufs)(struct file *file, void *fh, + struct v4l2_remove_buffers *d); int (*vidioc_overlay)(struct file *file, void *fh, unsigned int i); int (*vidioc_g_fbuf)(struct file *file, void *fh, diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index b9333e2c7797..955237ac503d 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -870,6 +870,16 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, */ int vb2_core_prepare_buf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb); +/** + * vb2_core_remove_bufs() - + * @q: pointer to &struct vb2_queue with videobuf2 queue. + * @start: first index of the range of buffers to remove. + * @count: number of buffers to remove. + * + * Return: returns zero on success; an error code otherwise. + */ +int vb2_core_remove_bufs(struct vb2_queue *q, unsigned int start, unsigned int count); + /** * vb2_core_qbuf() - Queue a buffer from userspace * diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index 5a845887850b..77ce8238ab30 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -334,6 +334,8 @@ int vb2_ioctl_streamon(struct file *file, void *priv, enum v4l2_buf_type i); int vb2_ioctl_streamoff(struct file *file, void *priv, enum v4l2_buf_type i); int vb2_ioctl_expbuf(struct file *file, void *priv, struct v4l2_exportbuffer *p); +int vb2_ioctl_remove_bufs(struct file *file, void *priv, + struct v4l2_remove_buffers *p); /* struct v4l2_file_operations helpers */ diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index a8015e5e7fa4..2663213b76a4 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1036,6 +1036,7 @@ struct v4l2_requestbuffers { #define V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF (1 << 5) #define V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS (1 << 6) #define V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS (1 << 7) +#define V4L2_BUF_CAP_SUPPORTS_REMOVE_BUFS (1 << 8) /** * struct v4l2_plane - plane info for multi-planar buffers @@ -2624,6 +2625,20 @@ struct v4l2_create_buffers { __u32 reserved[5]; }; +/** + * struct v4l2_remove_buffers - VIDIOC_REMOVE_BUFS argument + * @index: the first buffer to be removed + * @count: number of buffers to removed + * @type: enum v4l2_buf_type + * @reserved: future extensions + */ +struct v4l2_remove_buffers { + __u32 index; + __u32 count; + __u32 type; + __u32 reserved[13]; +}; + /* * I O C T L C O D E S F O R V I D E O D E V I C E S * @@ -2723,6 +2738,8 @@ struct v4l2_create_buffers { #define VIDIOC_DBG_G_CHIP_INFO _IOWR('V', 102, struct v4l2_dbg_chip_info) #define VIDIOC_QUERY_EXT_CTRL _IOWR('V', 103, struct v4l2_query_ext_ctrl) +#define VIDIOC_REMOVE_BUFS _IOWR('V', 104, struct v4l2_remove_buffers) + /* Reminder: when adding new ioctls please add support for them to drivers/media/v4l2-core/v4l2-compat-ioctl32.c as well! */ -- cgit v1.2.3 From 1c7b963c20650f1ffd787a088680c9a086ee349f Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Tue, 19 Mar 2024 11:26:23 -0700 Subject: wifi: nl80211: rename enum plink_actions kernel-doc flagged the following issue: include/uapi/linux/nl80211.h:6081: warning: expecting prototype for enum nl80211_plink_action. Prototype was for enum plink_actions instead This is because the documentation doesn't match the code. Normally the correct fix for such an issue is to modify the documentation to match the code. However, in this case, since the actual name plink_actions is not referenced by any code, rename it to nl80211_plink_action to give it a proper prefix and match the documentation. Signed-off-by: Jeff Johnson Link: https://msgid.link/20240319-kdoc-nl80211-v1-1-549e09d52866@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f23ecbdd84a2..9397c61a48dc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -6077,7 +6077,7 @@ enum nl80211_plink_state { * @NL80211_PLINK_ACTION_BLOCK: block traffic from this mesh peer * @NUM_NL80211_PLINK_ACTIONS: number of possible actions */ -enum plink_actions { +enum nl80211_plink_action { NL80211_PLINK_ACTION_NO_ACTION, NL80211_PLINK_ACTION_OPEN, NL80211_PLINK_ACTION_BLOCK, -- cgit v1.2.3 From ec3a97d93b88602fffd84ce30a461f6eaeb6f067 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Tue, 19 Mar 2024 11:26:24 -0700 Subject: wifi: nl80211: fix nl80211 uapi comment style issues Currently kernel-doc raises "warning: bad line:" for several comments that have invalid multi-line comment style; they are missing the leading '*'. And checkpatch.pl raises "WARNING: please, no space before tabs" for a large number of comments which have space then tab after the leading '*'. Fix those issues. Signed-off-by: Jeff Johnson Link: https://msgid.link/20240319-kdoc-nl80211-v1-2-549e09d52866@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 166 +++++++++++++++++++++---------------------- 1 file changed, 83 insertions(+), 83 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 9397c61a48dc..4de84fbfd4fa 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -442,11 +442,11 @@ * stations connected and using at least that link as one of its links. * * @NL80211_CMD_GET_MPATH: Get mesh path attributes for mesh path to - * destination %NL80211_ATTR_MAC on the interface identified by - * %NL80211_ATTR_IFINDEX. + * destination %NL80211_ATTR_MAC on the interface identified by + * %NL80211_ATTR_IFINDEX. * @NL80211_CMD_SET_MPATH: Set mesh path attributes for mesh path to - * destination %NL80211_ATTR_MAC on the interface identified by - * %NL80211_ATTR_IFINDEX. + * destination %NL80211_ATTR_MAC on the interface identified by + * %NL80211_ATTR_IFINDEX. * @NL80211_CMD_NEW_MPATH: Create a new mesh path for the destination given by * %NL80211_ATTR_MAC via %NL80211_ATTR_MPATH_NEXT_HOP. * @NL80211_CMD_DEL_MPATH: Delete a mesh path to the destination given by @@ -476,15 +476,15 @@ * after being queried by the kernel. CRDA replies by sending a regulatory * domain structure which consists of %NL80211_ATTR_REG_ALPHA set to our * current alpha2 if it found a match. It also provides - * NL80211_ATTR_REG_RULE_FLAGS, and a set of regulatory rules. Each - * regulatory rule is a nested set of attributes given by - * %NL80211_ATTR_REG_RULE_FREQ_[START|END] and - * %NL80211_ATTR_FREQ_RANGE_MAX_BW with an attached power rule given by - * %NL80211_ATTR_REG_RULE_POWER_MAX_ANT_GAIN and - * %NL80211_ATTR_REG_RULE_POWER_MAX_EIRP. + * NL80211_ATTR_REG_RULE_FLAGS, and a set of regulatory rules. Each + * regulatory rule is a nested set of attributes given by + * %NL80211_ATTR_REG_RULE_FREQ_[START|END] and + * %NL80211_ATTR_FREQ_RANGE_MAX_BW with an attached power rule given by + * %NL80211_ATTR_REG_RULE_POWER_MAX_ANT_GAIN and + * %NL80211_ATTR_REG_RULE_POWER_MAX_EIRP. * @NL80211_CMD_REQ_SET_REG: ask the wireless core to set the regulatory domain - * to the specified ISO/IEC 3166-1 alpha2 country code. The core will - * store this as a valid request and then query userspace for it. + * to the specified ISO/IEC 3166-1 alpha2 country code. The core will + * store this as a valid request and then query userspace for it. * * @NL80211_CMD_GET_MESH_CONFIG: Get mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX @@ -574,31 +574,31 @@ * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries. * * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain - * has been changed and provides details of the request information - * that caused the change such as who initiated the regulatory request - * (%NL80211_ATTR_REG_INITIATOR), the wiphy_idx - * (%NL80211_ATTR_REG_ALPHA2) on which the request was made from if - * the initiator was %NL80211_REGDOM_SET_BY_COUNTRY_IE or - * %NL80211_REGDOM_SET_BY_DRIVER, the type of regulatory domain - * set (%NL80211_ATTR_REG_TYPE), if the type of regulatory domain is - * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on - * to (%NL80211_ATTR_REG_ALPHA2). + * has been changed and provides details of the request information + * that caused the change such as who initiated the regulatory request + * (%NL80211_ATTR_REG_INITIATOR), the wiphy_idx + * (%NL80211_ATTR_REG_ALPHA2) on which the request was made from if + * the initiator was %NL80211_REGDOM_SET_BY_COUNTRY_IE or + * %NL80211_REGDOM_SET_BY_DRIVER, the type of regulatory domain + * set (%NL80211_ATTR_REG_TYPE), if the type of regulatory domain is + * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on + * to (%NL80211_ATTR_REG_ALPHA2). * @NL80211_CMD_REG_BEACON_HINT: indicates to userspace that an AP beacon - * has been found while world roaming thus enabling active scan or - * any mode of operation that initiates TX (beacons) on a channel - * where we would not have been able to do either before. As an example - * if you are world roaming (regulatory domain set to world or if your - * driver is using a custom world roaming regulatory domain) and while - * doing a passive scan on the 5 GHz band you find an AP there (if not - * on a DFS channel) you will now be able to actively scan for that AP - * or use AP mode on your card on that same channel. Note that this will - * never be used for channels 1-11 on the 2 GHz band as they are always - * enabled world wide. This beacon hint is only sent if your device had - * either disabled active scanning or beaconing on a channel. We send to - * userspace the wiphy on which we removed a restriction from - * (%NL80211_ATTR_WIPHY) and the channel on which this occurred - * before (%NL80211_ATTR_FREQ_BEFORE) and after (%NL80211_ATTR_FREQ_AFTER) - * the beacon hint was processed. + * has been found while world roaming thus enabling active scan or + * any mode of operation that initiates TX (beacons) on a channel + * where we would not have been able to do either before. As an example + * if you are world roaming (regulatory domain set to world or if your + * driver is using a custom world roaming regulatory domain) and while + * doing a passive scan on the 5 GHz band you find an AP there (if not + * on a DFS channel) you will now be able to actively scan for that AP + * or use AP mode on your card on that same channel. Note that this will + * never be used for channels 1-11 on the 2 GHz band as they are always + * enabled world wide. This beacon hint is only sent if your device had + * either disabled active scanning or beaconing on a channel. We send to + * userspace the wiphy on which we removed a restriction from + * (%NL80211_ATTR_WIPHY) and the channel on which this occurred + * before (%NL80211_ATTR_FREQ_BEFORE) and after (%NL80211_ATTR_FREQ_AFTER) + * the beacon hint was processed. * * @NL80211_CMD_AUTHENTICATE: authentication request and notification. * This command is used both as a command (request to authenticate) and @@ -1715,21 +1715,21 @@ enum nl80211_commands { * (see &enum nl80211_plink_action). * @NL80211_ATTR_MPATH_NEXT_HOP: MAC address of the next hop for a mesh path. * @NL80211_ATTR_MPATH_INFO: information about a mesh_path, part of mesh path - * info given for %NL80211_CMD_GET_MPATH, nested attribute described at + * info given for %NL80211_CMD_GET_MPATH, nested attribute described at * &enum nl80211_mpath_info. * * @NL80211_ATTR_MNTR_FLAGS: flags, nested element with NLA_FLAG attributes of * &enum nl80211_mntr_flags. * * @NL80211_ATTR_REG_ALPHA2: an ISO-3166-alpha2 country code for which the - * current regulatory domain should be set to or is already set to. - * For example, 'CR', for Costa Rica. This attribute is used by the kernel - * to query the CRDA to retrieve one regulatory domain. This attribute can - * also be used by userspace to query the kernel for the currently set - * regulatory domain. We chose an alpha2 as that is also used by the - * IEEE-802.11 country information element to identify a country. - * Users can also simply ask the wireless core to set regulatory domain - * to a specific alpha2. + * current regulatory domain should be set to or is already set to. + * For example, 'CR', for Costa Rica. This attribute is used by the kernel + * to query the CRDA to retrieve one regulatory domain. This attribute can + * also be used by userspace to query the kernel for the currently set + * regulatory domain. We chose an alpha2 as that is also used by the + * IEEE-802.11 country information element to identify a country. + * Users can also simply ask the wireless core to set regulatory domain + * to a specific alpha2. * @NL80211_ATTR_REG_RULES: a nested array of regulatory domain regulatory * rules. * @@ -1772,9 +1772,9 @@ enum nl80211_commands { * @NL80211_ATTR_BSS: scan result BSS * * @NL80211_ATTR_REG_INITIATOR: indicates who requested the regulatory domain - * currently in effect. This could be any of the %NL80211_REGDOM_SET_BY_* + * currently in effect. This could be any of the %NL80211_REGDOM_SET_BY_* * @NL80211_ATTR_REG_TYPE: indicates the type of the regulatory domain currently - * set. This can be one of the nl80211_reg_type (%NL80211_REGDOM_TYPE_*) + * set. This can be one of the nl80211_reg_type (%NL80211_REGDOM_TYPE_*) * * @NL80211_ATTR_SUPPORTED_COMMANDS: wiphy attribute that specifies * an array of command numbers (i.e. a mapping index to command number) @@ -1793,15 +1793,15 @@ enum nl80211_commands { * a u32 * * @NL80211_ATTR_FREQ_BEFORE: A channel which has suffered a regulatory change - * due to considerations from a beacon hint. This attribute reflects - * the state of the channel _before_ the beacon hint processing. This - * attributes consists of a nested attribute containing - * NL80211_FREQUENCY_ATTR_* + * due to considerations from a beacon hint. This attribute reflects + * the state of the channel _before_ the beacon hint processing. This + * attributes consists of a nested attribute containing + * NL80211_FREQUENCY_ATTR_* * @NL80211_ATTR_FREQ_AFTER: A channel which has suffered a regulatory change - * due to considerations from a beacon hint. This attribute reflects - * the state of the channel _after_ the beacon hint processing. This - * attributes consists of a nested attribute containing - * NL80211_FREQUENCY_ATTR_* + * due to considerations from a beacon hint. This attribute reflects + * the state of the channel _after_ the beacon hint processing. This + * attributes consists of a nested attribute containing + * NL80211_FREQUENCY_ATTR_* * * @NL80211_ATTR_CIPHER_SUITES: a set of u32 values indicating the supported * cipher suites @@ -2416,7 +2416,7 @@ enum nl80211_commands { * scheduled scan is started. Or the delay before a WoWLAN * net-detect scan is started, counting from the moment the * system is suspended. This value is a u32, in seconds. - + * * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device * is operating in an indoor environment. * @@ -3823,7 +3823,7 @@ enum nl80211_sta_bss_param { * (u64, to this station) * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute - * containing info as possible, see &enum nl80211_rate_info + * containing info as possible, see &enum nl80211_rate_info * @NL80211_STA_INFO_RX_PACKETS: total received packet (MSDUs and MMPDUs) * (u32, from this station) * @NL80211_STA_INFO_TX_PACKETS: total transmitted packets (MSDUs and MMPDUs) @@ -4039,7 +4039,7 @@ enum nl80211_mpath_flags { * @NL80211_MPATH_INFO_METRIC: metric (cost) of this mesh path * @NL80211_MPATH_INFO_EXPTIME: expiration time for the path, in msec from now * @NL80211_MPATH_INFO_FLAGS: mesh path flags, enumerated in - * &enum nl80211_mpath_flags; + * &enum nl80211_mpath_flags; * @NL80211_MPATH_INFO_DISCOVERY_TIMEOUT: total path discovery timeout, in msec * @NL80211_MPATH_INFO_DISCOVERY_RETRIES: mesh path discovery retries * @NL80211_MPATH_INFO_HOP_COUNT: hop count to destination @@ -4201,8 +4201,8 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_DISABLED: Channel is disabled in current * regulatory domain. * @NL80211_FREQUENCY_ATTR_NO_IR: no mechanisms that initiate radiation - * are permitted on this channel, this includes sending probe - * requests, or modes of operation that require beaconing. + * are permitted on this channel, this includes sending probe + * requests, or modes of operation that require beaconing. * @NL80211_FREQUENCY_ATTR_RADAR: Radar detection is mandatory * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX_TX_POWER: Maximum transmission power in mBm @@ -4359,14 +4359,14 @@ enum nl80211_bitrate_attr { /** * enum nl80211_initiator - Indicates the initiator of a reg domain request * @NL80211_REGDOM_SET_BY_CORE: Core queried CRDA for a dynamic world - * regulatory domain. + * regulatory domain. * @NL80211_REGDOM_SET_BY_USER: User asked the wireless core to set the - * regulatory domain. + * regulatory domain. * @NL80211_REGDOM_SET_BY_DRIVER: a wireless drivers has hinted to the - * wireless core it thinks its knows the regulatory domain we should be in. + * wireless core it thinks its knows the regulatory domain we should be in. * @NL80211_REGDOM_SET_BY_COUNTRY_IE: the wireless core has received an - * 802.11 country information element with regulatory information it - * thinks we should consider. cfg80211 only processes the country + * 802.11 country information element with regulatory information it + * thinks we should consider. cfg80211 only processes the country * code from the IE, and relies on the regulatory domain information * structure passed by userspace (CRDA) from our wireless-regdb. * If a channel is enabled but the country code indicates it should @@ -4385,11 +4385,11 @@ enum nl80211_reg_initiator { * to a specific country. When this is set you can count on the * ISO / IEC 3166 alpha2 country code being valid. * @NL80211_REGDOM_TYPE_WORLD: the regulatory set domain is the world regulatory - * domain. + * domain. * @NL80211_REGDOM_TYPE_CUSTOM_WORLD: the regulatory domain set is a custom - * driver specific world regulatory domain. These do not apply system-wide - * and are only applicable to the individual devices which have requested - * them to be applied. + * driver specific world regulatory domain. These do not apply system-wide + * and are only applicable to the individual devices which have requested + * them to be applied. * @NL80211_REGDOM_TYPE_INTERSECTION: the regulatory domain set is the product * of an intersection between two regulatory domains -- the previously * set regulatory domain on the system and the last accepted regulatory @@ -4406,21 +4406,21 @@ enum nl80211_reg_type { * enum nl80211_reg_rule_attr - regulatory rule attributes * @__NL80211_REG_RULE_ATTR_INVALID: attribute number 0 is reserved * @NL80211_ATTR_REG_RULE_FLAGS: a set of flags which specify additional - * considerations for a given frequency range. These are the - * &enum nl80211_reg_rule_flags. + * considerations for a given frequency range. These are the + * &enum nl80211_reg_rule_flags. * @NL80211_ATTR_FREQ_RANGE_START: starting frequencry for the regulatory - * rule in KHz. This is not a center of frequency but an actual regulatory - * band edge. + * rule in KHz. This is not a center of frequency but an actual regulatory + * band edge. * @NL80211_ATTR_FREQ_RANGE_END: ending frequency for the regulatory rule - * in KHz. This is not a center a frequency but an actual regulatory - * band edge. + * in KHz. This is not a center a frequency but an actual regulatory + * band edge. * @NL80211_ATTR_FREQ_RANGE_MAX_BW: maximum allowed bandwidth for this * frequency range, in KHz. * @NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN: the maximum allowed antenna gain - * for a given frequency range. The value is in mBi (100 * dBi). - * If you don't have one then don't send this. + * for a given frequency range. The value is in mBi (100 * dBi). + * If you don't have one then don't send this. * @NL80211_ATTR_POWER_RULE_MAX_EIRP: the maximum allowed EIRP for - * a given frequency range. The value is in mBm (100 * dBm). + * a given frequency range. The value is in mBm (100 * dBm). * @NL80211_ATTR_DFS_CAC_TIME: DFS CAC time in milliseconds. * If not present or 0 default CAC time will be used. * @NL80211_ATTR_POWER_RULE_PSD: power spectral density (in dBm). @@ -4507,8 +4507,8 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_PTP_ONLY: this is only for Point To Point links * @NL80211_RRF_PTMP_ONLY: this is only for Point To Multi Point links * @NL80211_RRF_NO_IR: no mechanisms that initiate radiation are allowed, - * this includes probe requests or modes of operation that require - * beaconing. + * this includes probe requests or modes of operation that require + * beaconing. * @NL80211_RRF_AUTO_BW: maximum available bandwidth should be calculated * base on contiguous rules and wider channels will be allowed to cross * multiple contiguous/overlapping frequency ranges. @@ -4522,9 +4522,9 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_EHT: EHT operation not allowed * @NL80211_RRF_PSD: Ruleset has power spectral density value * @NL80211_RRF_DFS_CONCURRENT: Operation on this channel is allowed for - peer-to-peer or adhoc communication under the control of a DFS master - which operates on the same channel (FCC-594280 D01 Section B.3). - Should be used together with %NL80211_RRF_DFS only. + * peer-to-peer or adhoc communication under the control of a DFS master + * which operates on the same channel (FCC-594280 D01 Section B.3). + * Should be used together with %NL80211_RRF_DFS only. * @NL80211_RRF_NO_6GHZ_VLP_CLIENT: Client connection to VLP AP not allowed * @NL80211_RRF_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP not allowed */ -- cgit v1.2.3 From b8cf4f4d700acaa7b3b40eb877a226b9a95164df Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Tue, 19 Mar 2024 11:26:25 -0700 Subject: wifi: nl80211: cleanup nl80211.h kernel-doc Fix all of the kernel-doc issues in nl80211.h. Signed-off-by: Jeff Johnson Link: https://msgid.link/20240319-kdoc-nl80211-v1-3-549e09d52866@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 68 ++++++++++++++++++++++++++------------------ 1 file changed, 40 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 4de84fbfd4fa..f917bc6c9b6f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -413,8 +413,8 @@ * are like for %NL80211_CMD_SET_BEACON, and additionally parameters that * do not change are used, these include %NL80211_ATTR_BEACON_INTERVAL, * %NL80211_ATTR_DTIM_PERIOD, %NL80211_ATTR_SSID, - * %NL80211_ATTR_HIDDEN_SSID, %NL80211_ATTR_CIPHERS_PAIRWISE, - * %NL80211_ATTR_CIPHER_GROUP, %NL80211_ATTR_WPA_VERSIONS, + * %NL80211_ATTR_HIDDEN_SSID, %NL80211_ATTR_CIPHER_SUITES_PAIRWISE, + * %NL80211_ATTR_CIPHER_SUITE_GROUP, %NL80211_ATTR_WPA_VERSIONS, * %NL80211_ATTR_AKM_SUITES, %NL80211_ATTR_PRIVACY, * %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_INACTIVITY_TIMEOUT, * %NL80211_ATTR_ACL_POLICY and %NL80211_ATTR_MAC_ADDRS. @@ -451,11 +451,6 @@ * %NL80211_ATTR_MAC via %NL80211_ATTR_MPATH_NEXT_HOP. * @NL80211_CMD_DEL_MPATH: Delete a mesh path to the destination given by * %NL80211_ATTR_MAC. - * @NL80211_CMD_NEW_PATH: Add a mesh path with given attributes to the - * interface identified by %NL80211_ATTR_IFINDEX. - * @NL80211_CMD_DEL_PATH: Remove a mesh path identified by %NL80211_ATTR_MAC - * or, if no MAC address given, all mesh paths, on the interface identified - * by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_SET_BSS: Set BSS attributes for BSS identified by * %NL80211_ATTR_IFINDEX. * @@ -1120,7 +1115,7 @@ * current configuration is not changed. If it is present but * set to zero, the configuration is changed to don't-care * (i.e. the device can decide what to do). - * @NL80211_CMD_NAN_FUNC_MATCH: Notification sent when a match is reported. + * @NL80211_CMD_NAN_MATCH: Notification sent when a match is reported. * This will contain a %NL80211_ATTR_NAN_MATCH nested attribute and * %NL80211_ATTR_COOKIE. * @@ -1862,12 +1857,6 @@ enum nl80211_commands { * that protected APs should be used. This is also used with NEW_BEACON to * indicate that the BSS is to use protection. * - * @NL80211_ATTR_CIPHERS_PAIRWISE: Used with CONNECT, ASSOCIATE, and NEW_BEACON - * to indicate which unicast key ciphers will be used with the connection - * (an array of u32). - * @NL80211_ATTR_CIPHER_GROUP: Used with CONNECT, ASSOCIATE, and NEW_BEACON to - * indicate which group key cipher will be used with the connection (a - * u32). * @NL80211_ATTR_WPA_VERSIONS: Used with CONNECT, ASSOCIATE, and NEW_BEACON to * indicate which WPA version(s) the AP we want to associate with is using * (a u32 with flags from &enum nl80211_wpa_versions). @@ -1898,6 +1887,7 @@ enum nl80211_commands { * with %NL80211_KEY_* sub-attributes * * @NL80211_ATTR_PID: Process ID of a network namespace. + * @NL80211_ATTR_NETNS_FD: File descriptor of a network namespace. * * @NL80211_ATTR_GENERATION: Used to indicate consistent snapshots for * dumps. This number increases whenever the object list being @@ -1952,6 +1942,7 @@ enum nl80211_commands { * * @NL80211_ATTR_ACK: Flag attribute indicating that the frame was * acknowledged by the recipient. + * @NL80211_ATTR_ACK_SIGNAL: Station's ack signal strength (s32) * * @NL80211_ATTR_PS_STATE: powersave state, using &enum nl80211_ps_state values. * @@ -2149,6 +2140,9 @@ enum nl80211_commands { * @NL80211_ATTR_DISABLE_HE: Force HE capable interfaces to disable * this feature during association. This is a flag attribute. * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_EHT: Force EHT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. * @NL80211_ATTR_HT_CAPABILITY_MASK: Specify which bits of the * ATTR_HT_CAPABILITY to which attention should be paid. * Currently, only mac80211 NICs support this feature. @@ -2158,6 +2152,12 @@ enum nl80211_commands { * All values are treated as suggestions and may be ignored * by the driver as required. The actual values may be seen in * the station debugfs ht_caps file. + * @NL80211_ATTR_VHT_CAPABILITY_MASK: Specify which bits of the + * ATTR_VHT_CAPABILITY to which attention should be paid. + * Currently, only mac80211 NICs support this feature. + * All values are treated as suggestions and may be ignored + * by the driver as required. The actual values may be seen in + * the station debugfs vht_caps file. * * @NL80211_ATTR_DFS_REGION: region for regulatory rules which this country * abides to when initiating radiation on DFS channels. A country maps @@ -3565,7 +3565,7 @@ enum nl80211_sta_flags { * enum nl80211_sta_p2p_ps_status - station support of P2P PS * * @NL80211_P2P_PS_UNSUPPORTED: station doesn't support P2P PS mechanism - * @@NL80211_P2P_PS_SUPPORTED: station supports P2P PS mechanism + * @NL80211_P2P_PS_SUPPORTED: station supports P2P PS mechanism * @NUM_NL80211_P2P_PS_STATUS: number of values */ enum nl80211_sta_p2p_ps_status { @@ -3603,9 +3603,9 @@ enum nl80211_he_gi { /** * enum nl80211_he_ltf - HE long training field - * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec - * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec - * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec + * @NL80211_RATE_INFO_HE_1XLTF: 3.2 usec + * @NL80211_RATE_INFO_HE_2XLTF: 6.4 usec + * @NL80211_RATE_INFO_HE_4XLTF: 12.8 usec */ enum nl80211_he_ltf { NL80211_RATE_INFO_HE_1XLTF, @@ -3720,7 +3720,7 @@ enum nl80211_eht_ru_alloc { * @NL80211_RATE_INFO_HE_GI: HE guard interval identifier * (u8, see &enum nl80211_he_gi) * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1) - * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then + * @NL80211_RATE_INFO_HE_RU_ALLOC: HE RU allocation, if not present then * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc) * @NL80211_RATE_INFO_320_MHZ_WIDTH: 320 MHz bitrate * @NL80211_RATE_INFO_EHT_MCS: EHT MCS index (u8, 0-15) @@ -3852,8 +3852,8 @@ enum nl80211_sta_bss_param { * Contains a nested array of signal strength attributes (u8, dBm) * @NL80211_STA_INFO_CHAIN_SIGNAL_AVG: per-chain signal strength average * Same format as NL80211_STA_INFO_CHAIN_SIGNAL. - * @NL80211_STA_EXPECTED_THROUGHPUT: expected throughput considering also the - * 802.11 header (u32, kbps) + * @NL80211_STA_INFO_EXPECTED_THROUGHPUT: expected throughput considering also + * the 802.11 header (u32, kbps) * @NL80211_STA_INFO_RX_DROP_MISC: RX packets dropped for unspecified reasons * (u64) * @NL80211_STA_INFO_BEACON_RX: number of beacons received from this peer (u64) @@ -4179,7 +4179,7 @@ enum nl80211_band_attr { * @NL80211_WMMR_CW_MAX: Maximum contention window slot. * @NL80211_WMMR_AIFSN: Arbitration Inter Frame Space. * @NL80211_WMMR_TXOP: Maximum allowed tx operation time. - * @nl80211_WMMR_MAX: highest possible wmm rule. + * @NL80211_WMMR_MAX: highest possible wmm rule. * @__NL80211_WMMR_LAST: Internal use. */ enum nl80211_wmm_rule { @@ -4203,6 +4203,7 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_NO_IR: no mechanisms that initiate radiation * are permitted on this channel, this includes sending probe * requests, or modes of operation that require beaconing. + * @__NL80211_FREQUENCY_ATTR_NO_IBSS: obsolete, same as _NO_IR * @NL80211_FREQUENCY_ATTR_RADAR: Radar detection is mandatory * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX_TX_POWER: Maximum transmission power in mBm @@ -4357,7 +4358,7 @@ enum nl80211_bitrate_attr { }; /** - * enum nl80211_initiator - Indicates the initiator of a reg domain request + * enum nl80211_reg_initiator - Indicates the initiator of a reg domain request * @NL80211_REGDOM_SET_BY_CORE: Core queried CRDA for a dynamic world * regulatory domain. * @NL80211_REGDOM_SET_BY_USER: User asked the wireless core to set the @@ -4509,6 +4510,7 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_IR: no mechanisms that initiate radiation are allowed, * this includes probe requests or modes of operation that require * beaconing. + * @__NL80211_RRF_NO_IBSS: obsolete, same as NO_IR * @NL80211_RRF_AUTO_BW: maximum available bandwidth should be calculated * base on contiguous rules and wider channels will be allowed to cross * multiple contiguous/overlapping frequency ranges. @@ -4707,8 +4709,8 @@ enum nl80211_mntr_flags { * alternate between Active and Doze states, but may not wake up * for neighbor's beacons. * - * @__NL80211_MESH_POWER_AFTER_LAST - internal use - * @NL80211_MESH_POWER_MAX - highest possible power save level + * @__NL80211_MESH_POWER_AFTER_LAST: internal use + * @NL80211_MESH_POWER_MAX: highest possible power save level */ enum nl80211_mesh_power_mode { @@ -5728,7 +5730,7 @@ struct nl80211_pattern_support { * "TCP connection wakeup" for more details. This is a nested attribute * containing the exact information for establishing and keeping alive * the TCP connection. - * @NL80211_WOWLAN_TRIG_TCP_WAKEUP_MATCH: For wakeup reporting only, the + * @NL80211_WOWLAN_TRIG_WAKEUP_TCP_MATCH: For wakeup reporting only, the * wakeup packet was received on the TCP connection * @NL80211_WOWLAN_TRIG_WAKEUP_TCP_CONNLOST: For wakeup reporting only, the * TCP connection was lost or failed to be established @@ -6404,6 +6406,7 @@ enum nl80211_feature_flags { * receiving control port frames over nl80211 instead of the netdevice. * @NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT: This driver/device supports * (average) ACK signal strength reporting. + * @NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT: Backward-compatible ID * @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate * TXQs. * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the @@ -6787,6 +6790,8 @@ enum nl80211_acl_policy { * @NL80211_SMPS_STATIC: static SMPS (use a single antenna) * @NL80211_SMPS_DYNAMIC: dynamic smps (start with a single antenna and * turn on other antennas after CTS/RTS). + * @__NL80211_SMPS_AFTER_LAST: internal + * @NL80211_SMPS_MAX: highest used enumeration */ enum nl80211_smps_mode { NL80211_SMPS_OFF, @@ -7008,6 +7013,8 @@ enum nl80211_bss_select_attr { * @NL80211_NAN_FUNC_PUBLISH: function is publish * @NL80211_NAN_FUNC_SUBSCRIBE: function is subscribe * @NL80211_NAN_FUNC_FOLLOW_UP: function is follow-up + * @__NL80211_NAN_FUNC_TYPE_AFTER_LAST: internal use + * @NL80211_NAN_FUNC_MAX_TYPE: internal use */ enum nl80211_nan_function_type { NL80211_NAN_FUNC_PUBLISH, @@ -7168,7 +7175,7 @@ enum nl80211_nan_match_attributes { }; /** - * nl80211_external_auth_action - Action to perform with external + * enum nl80211_external_auth_action - Action to perform with external * authentication request. Used by NL80211_ATTR_EXTERNAL_AUTH_ACTION. * @NL80211_EXTERNAL_AUTH_START: Start the authentication. * @NL80211_EXTERNAL_AUTH_ABORT: Abort the ongoing authentication. @@ -7186,7 +7193,7 @@ enum nl80211_external_auth_action { * @NL80211_FTM_RESP_ATTR_LCI: The content of Measurement Report Element * (9.4.2.22 in 802.11-2016) with type 8 - LCI (9.4.2.22.10), * i.e. starting with the measurement token - * @NL80211_FTM_RESP_ATTR_CIVIC: The content of Measurement Report Element + * @NL80211_FTM_RESP_ATTR_CIVICLOC: The content of Measurement Report Element * (9.4.2.22 in 802.11-2016) with type 11 - Civic (Section 9.4.2.22.13), * i.e. starting with the measurement token * @__NL80211_FTM_RESP_ATTR_LAST: Internal @@ -7829,6 +7836,7 @@ enum nl80211_sae_pwe_mechanism { * * @NL80211_SAR_TYPE_POWER: power limitation specified in 0.25dBm unit * + * @NUM_NL80211_SAR_TYPE: internal */ enum nl80211_sar_type { NL80211_SAR_TYPE_POWER, @@ -7842,6 +7850,8 @@ enum nl80211_sar_type { /** * enum nl80211_sar_attrs - Attributes for SAR spec * + * @__NL80211_SAR_ATTR_INVALID: Invalid + * * @NL80211_SAR_ATTR_TYPE: the SAR type as defined in &enum nl80211_sar_type. * * @NL80211_SAR_ATTR_SPECS: Nested array of SAR power @@ -7873,6 +7883,8 @@ enum nl80211_sar_attrs { /** * enum nl80211_sar_specs_attrs - Attributes for SAR power limit specs * + * @__NL80211_SAR_ATTR_SPECS_INVALID: Invalid + * * @NL80211_SAR_ATTR_SPECS_POWER: Required (s32)value to specify the actual * power limit value in units of 0.25 dBm if type is * NL80211_SAR_TYPE_POWER. (i.e., a value of 44 represents 11 dBm). -- cgit v1.2.3 From 2a82bb02941fb53d1f8df2a360e7798ae3d9d962 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 7 Mar 2024 21:29:12 -0500 Subject: statx: stx_subvol Add a new statx field for (sub)volume identifiers, as implemented by btrfs and bcachefs. This includes bcachefs support; we'll definitely want btrfs support as well. Link: https://lore.kernel.org/linux-fsdevel/2uvhm6gweyl7iyyp2xpfryvcu2g3padagaeqcbiavjyiis6prl@yjm725bizncq/ Signed-off-by: Kent Overstreet Cc: Josef Bacik Cc: Miklos Szeredi Cc: Christian Brauner Cc: David Howells Signed-off-by: Kent Overstreet Link: https://lore.kernel.org/r/20240308022914.196982-1-kent.overstreet@linux.dev Signed-off-by: Johannes Thumshirn Signed-off-by: Christian Brauner --- fs/bcachefs/fs.c | 3 +++ fs/btrfs/inode.c | 3 +++ fs/stat.c | 1 + include/linux/stat.h | 1 + include/uapi/linux/stat.h | 4 +++- 5 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 0ccee05f6887..99a0abeadbe2 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -841,6 +841,9 @@ static int bch2_getattr(struct mnt_idmap *idmap, stat->blksize = block_bytes(c); stat->blocks = inode->v.i_blocks; + stat->subvol = inode->ei_subvol; + stat->result_mask |= STATX_SUBVOL; + if (request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; stat->btime = bch2_time_to_timespec(c, inode->ei_inode.bi_otime); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 37701531eeb1..8cf692c708d7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8779,6 +8779,9 @@ static int btrfs_getattr(struct mnt_idmap *idmap, generic_fillattr(idmap, request_mask, inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; + stat->subvol = BTRFS_I(inode)->root->root_key.objectid; + stat->result_mask |= STATX_SUBVOL; + spin_lock(&BTRFS_I(inode)->lock); delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes; inode_bytes = inode_get_bytes(inode); diff --git a/fs/stat.c b/fs/stat.c index 77cdc69eb422..70bd3e888cfa 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -658,6 +658,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; + tmp.stx_subvol = stat->subvol; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/include/linux/stat.h b/include/linux/stat.h index 52150570d37a..bf92441dbad2 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,7 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + u64 subvol; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 2f2ee82d5517..67626d535316 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,8 +126,9 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[12]; /* Spare space for future expansion */ + __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +156,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ -- cgit v1.2.3 From 5311591fbb349fe9f5c555dcba3b13a5831aa72d Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Tue, 26 Mar 2024 10:17:40 +0000 Subject: bpf: Add support for passing mark with bpf_fib_lookup Extend the bpf_fib_lookup() helper by making it to utilize mark if the BPF_FIB_LOOKUP_MARK flag is set. In order to pass the mark the four bytes of struct bpf_fib_lookup are used, shared with the output-only smac/dmac fields. Signed-off-by: Anton Protopopov Signed-off-by: Daniel Borkmann Reviewed-by: David Ahern Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240326101742.17421-2-aspsk@isovalent.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 20 ++++++++++++++++++-- net/core/filter.c | 12 +++++++++--- tools/include/uapi/linux/bpf.h | 20 ++++++++++++++++++-- 3 files changed, 45 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9585f5345353..96d57e483133 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3394,6 +3394,10 @@ union bpf_attr { * for the nexthop. If the src addr cannot be derived, * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -7120,6 +7124,7 @@ enum { BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), }; enum { @@ -7197,8 +7202,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; }; struct bpf_redir_neigh { diff --git a/net/core/filter.c b/net/core/filter.c index 0c66e4a3fc5b..1205dd777dc2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5884,7 +5884,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { - fl4.flowi4_mark = 0; + if (flags & BPF_FIB_LOOKUP_MARK) + fl4.flowi4_mark = params->mark; + else + fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); @@ -6027,7 +6030,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { - fl6.flowi6_mark = 0; + if (flags & BPF_FIB_LOOKUP_MARK) + fl6.flowi6_mark = params->mark; + else + fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); @@ -6105,7 +6111,7 @@ set_fwd_params: #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ - BPF_FIB_LOOKUP_SRC) + BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9585f5345353..96d57e483133 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3394,6 +3394,10 @@ union bpf_attr { * for the nexthop. If the src addr cannot be derived, * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -7120,6 +7124,7 @@ enum { BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), }; enum { @@ -7197,8 +7202,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; }; struct bpf_redir_neigh { -- cgit v1.2.3 From 5832c4a77d6931cebf9ba737129ae8f14b66ee1d Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 27 Mar 2024 16:23:53 +0100 Subject: ip_tunnel: convert __be16 tunnel flags to bitmaps Historically, tunnel flags like TUNNEL_CSUM or TUNNEL_ERSPAN_OPT have been defined as __be16. Now all of those 16 bits are occupied and there's no more free space for new flags. It can't be simply switched to a bigger container with no adjustments to the values, since it's an explicit Endian storage, and on LE systems (__be16)0x0001 equals to (__be64)0x0001000000000000. We could probably define new 64-bit flags depending on the Endianness, i.e. (__be64)0x0001 on BE and (__be64)0x00010000... on LE, but that would introduce an Endianness dependency and spawn a ton of Sparse warnings. To mitigate them, all of those places which were adjusted with this change would be touched anyway, so why not define stuff properly if there's no choice. Define IP_TUNNEL_*_BIT counterparts as a bit number instead of the value already coded and a fistful of <16 <-> bitmap> converters and helpers. The two flags which have a different bit position are SIT_ISATAP_BIT and VTI_ISVTI_BIT, as they were defined not as __cpu_to_be16(), but as (__force __be16), i.e. had different positions on LE and BE. Now they both have strongly defined places. Change all __be16 fields which were used to store those flags, to IP_TUNNEL_DECLARE_FLAGS() -> DECLARE_BITMAP(__IP_TUNNEL_FLAG_NUM) -> unsigned long[1] for now, and replace all TUNNEL_* occurrences to their bitmap counterparts. Use the converters in the places which talk to the userspace, hardware (NFP) or other hosts (GRE header). The rest must explicitly use the new flags only. This must be done at once, otherwise there will be too many conversions throughout the code in the intermediate commits. Finally, disable the old __be16 flags for use in the kernel code (except for the two 'irregular' flags mentioned above), to prevent any accidental (mis)use of them. For the userspace, nothing is changed, only additions were made. Most noticeable bloat-o-meter difference (.text): vmlinux: 307/-1 (306) gre.ko: 62/0 (62) ip_gre.ko: 941/-217 (724) [*] ip_tunnel.ko: 390/-900 (-510) [**] ip_vti.ko: 138/0 (138) ip6_gre.ko: 534/-18 (516) [*] ip6_tunnel.ko: 118/-10 (108) [*] gre_flags_to_tnl_flags() grew, but still is inlined [**] ip_tunnel_find() got uninlined, hence such decrease The average code size increase in non-extreme case is 100-200 bytes per module, mostly due to sizeof(long) > sizeof(__be16), as %__IP_TUNNEL_FLAG_NUM is less than %BITS_PER_LONG and the compilers are able to expand the majority of bitmap_*() calls here into direct operations on scalars. Reviewed-by: Simon Horman Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- drivers/net/bareudp.c | 19 ++- .../net/ethernet/mellanox/mlx5/core/en/tc_tun.h | 2 +- .../ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 6 +- .../ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c | 12 +- .../ethernet/mellanox/mlx5/core/en/tc_tun_gre.c | 8 +- .../ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c | 9 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 16 ++- .../net/ethernet/mellanox/mlxsw/spectrum_ipip.c | 26 +++-- .../net/ethernet/mellanox/mlxsw/spectrum_span.c | 6 +- drivers/net/ethernet/netronome/nfp/flower/action.c | 27 ++++- drivers/net/geneve.c | 44 ++++--- drivers/net/vxlan/vxlan_core.c | 14 ++- include/net/dst_metadata.h | 10 +- include/net/flow_dissector.h | 2 +- include/net/gre.h | 70 ++++++------ include/net/ip6_tunnel.h | 4 +- include/net/ip_tunnels.h | 119 ++++++++++++++++--- include/net/udp_tunnel.h | 4 +- include/uapi/linux/if_tunnel.h | 33 ++++++ net/bridge/br_vlan_tunnel.c | 9 +- net/core/filter.c | 26 +++-- net/core/flow_dissector.c | 20 +++- net/ipv4/fou_bpf.c | 2 +- net/ipv4/gre_demux.c | 2 +- net/ipv4/ip_gre.c | 127 +++++++++++++-------- net/ipv4/ip_tunnel.c | 54 +++++---- net/ipv4/ip_tunnel_core.c | 80 ++++++++----- net/ipv4/ip_vti.c | 29 +++-- net/ipv4/ipip.c | 21 +++- net/ipv4/udp_tunnel_core.c | 5 +- net/ipv6/ip6_gre.c | 85 ++++++++------ net/ipv6/ip6_tunnel.c | 14 +-- net/ipv6/sit.c | 5 +- net/netfilter/ipvs/ip_vs_core.c | 6 +- net/netfilter/ipvs/ip_vs_xmit.c | 20 ++-- net/netfilter/nft_tunnel.c | 44 ++++--- net/openvswitch/flow_netlink.c | 61 ++++++---- net/psample/psample.c | 26 +++-- net/sched/act_tunnel_key.c | 36 +++--- net/sched/cls_flower.c | 27 ++--- 40 files changed, 715 insertions(+), 415 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 339db6e4a1d5..d5c56ca91b77 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -61,6 +61,7 @@ struct bareudp_dev { static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct metadata_dst *tun_dst = NULL; + IP_TUNNEL_DECLARE_FLAGS(key) = { }; struct bareudp_dev *bareudp; unsigned short family; unsigned int len; @@ -137,7 +138,10 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) bareudp->dev->stats.rx_dropped++; goto drop; } - tun_dst = udp_tun_rx_dst(skb, family, TUNNEL_KEY, 0, 0); + + __set_bit(IP_TUNNEL_KEY_BIT, key); + + tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0); if (!tun_dst) { bareudp->dev->stats.rx_dropped++; goto drop; @@ -285,10 +289,10 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { + bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct socket *sock = rcu_dereference(bareudp->sock); - bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; __be16 sport, df; @@ -316,7 +320,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; - df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? + htons(IP_DF) : 0; skb_scrub_packet(skb, xnet); err = -ENOSPC; @@ -338,7 +343,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, bareudp->port, !net_eq(bareudp->net, dev_net(bareudp->dev)), - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; free_dst: @@ -350,10 +356,10 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { + bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct socket *sock = rcu_dereference(bareudp->sock); - bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr, daddr; @@ -402,7 +408,8 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev, &saddr, &daddr, prio, ttl, info->key.label, sport, bareudp->port, - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; free_dst: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 92065568bb19..6873c1201803 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -117,7 +117,7 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b, - __be16 tun_flags); + u32 tun_type); #endif /* CONFIG_MLX5_ESWITCH */ #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f1d1e1542e81..878cbdbf5ec8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -587,7 +587,7 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b, - __be16 tun_flags) + u32 tun_type) { struct ip_tunnel_info *a_info; struct ip_tunnel_info *b_info; @@ -596,8 +596,8 @@ bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a, if (!mlx5e_tc_tun_encap_info_equal_generic(a, b)) return false; - a_has_opts = !!(a->ip_tun_key->tun_flags & tun_flags); - b_has_opts = !!(b->ip_tun_key->tun_flags & tun_flags); + a_has_opts = test_bit(tun_type, a->ip_tun_key->tun_flags); + b_has_opts = test_bit(tun_type, b->ip_tun_key->tun_flags); /* keys are equal when both don't have any options attached */ if (!a_has_opts && !b_has_opts) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 2bcd10b6d653..bf969212cc77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -106,12 +106,13 @@ static int mlx5e_gen_ip_tunnel_header_geneve(char buf[], memset(geneveh, 0, sizeof(*geneveh)); geneveh->ver = MLX5E_GENEVE_VER; geneveh->opt_len = tun_info->options_len / 4; - geneveh->oam = !!(tun_info->key.tun_flags & TUNNEL_OAM); - geneveh->critical = !!(tun_info->key.tun_flags & TUNNEL_CRIT_OPT); + geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, tun_info->key.tun_flags); + geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, + tun_info->key.tun_flags); mlx5e_tunnel_id_to_vni(tun_info->key.tun_id, geneveh->vni); geneveh->proto_type = htons(ETH_P_TEB); - if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) { if (!geneveh->opt_len) return -EOPNOTSUPP; ip_tunnel_info_opts_get(geneveh->options, tun_info); @@ -188,7 +189,7 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv, /* make sure that we're talking about GENEVE options */ - if (enc_opts.key->dst_opt_type != TUNNEL_GENEVE_OPT) { + if (enc_opts.key->dst_opt_type != IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options: option type is not GENEVE"); netdev_warn(priv->netdev, @@ -337,7 +338,8 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv, static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b) { - return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_GENEVE_OPT); + return mlx5e_tc_tun_encap_info_equal_options(a, b, + IP_TUNNEL_GENEVE_OPT_BIT); } struct mlx5e_tc_tunnel geneve_tunnel = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index ada14f0574dc..579eda89fc76 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -31,12 +31,16 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[], const struct ip_tunnel_key *tun_key = &e->tun_info->key; struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf); __be32 tun_id = tunnel_id_to_key32(tun_key->tun_id); + IP_TUNNEL_DECLARE_FLAGS(unsupp) = { }; int hdr_len; *ip_proto = IPPROTO_GRE; /* the HW does not calculate GRE csum or sequences */ - if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ)) + __set_bit(IP_TUNNEL_CSUM_BIT, unsupp); + __set_bit(IP_TUNNEL_SEQ_BIT, unsupp); + + if (ip_tunnel_flags_intersect(tun_key->tun_flags, unsupp)) return -EOPNOTSUPP; greh->protocol = htons(ETH_P_TEB); @@ -44,7 +48,7 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[], /* GRE key */ hdr_len = mlx5e_tc_tun_calc_hlen_gretap(e); greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags); - if (tun_key->tun_flags & TUNNEL_KEY) { + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); *ptr = tun_id; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index a184d739d5f8..e4e487c8431b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -90,7 +90,7 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], const struct vxlan_metadata *md; struct vxlanhdr *vxh; - if ((tun_key->tun_flags & TUNNEL_VXLAN_OPT) && + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_key->tun_flags) && e->tun_info->options_len != sizeof(*md)) return -EOPNOTSUPP; vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr)); @@ -99,7 +99,7 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], udp->dest = tun_key->tp_dst; vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(tun_id); - if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_key->tun_flags)) { md = ip_tunnel_info_opts(e->tun_info); vxlan_build_gbp_hdr(vxh, md); } @@ -125,7 +125,7 @@ static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (enc_opts.key->dst_opt_type != TUNNEL_VXLAN_OPT) { + if (enc_opts.key->dst_opt_type != IP_TUNNEL_VXLAN_OPT_BIT) { NL_SET_ERR_MSG_MOD(extack, "Wrong VxLAN option type: not GBP"); return -EOPNOTSUPP; } @@ -208,7 +208,8 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, static bool mlx5e_tc_tun_encap_info_equal_vxlan(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b) { - return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_VXLAN_OPT); + return mlx5e_tc_tun_encap_info_equal_options(a, b, + IP_TUNNEL_VXLAN_OPT_BIT); } static int mlx5e_tc_tun_get_remote_ifindex(struct net_device *mirred_dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 31ed26cac9bf..f2f19fa37d91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5464,6 +5464,7 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct tunnel_match_enc_opts enc_opts = {}; struct mlx5_rep_uplink_priv *uplink_priv; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct mlx5e_rep_priv *uplink_rpriv; struct metadata_dst *tun_dst; struct tunnel_match_key key; @@ -5471,6 +5472,8 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb struct net_device *dev; int err; + __set_bit(IP_TUNNEL_KEY_BIT, flags); + enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK; tun_id = tunnel_id >> ENC_OPTS_BITS; @@ -5503,14 +5506,14 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb case FLOW_DISSECTOR_KEY_IPV4_ADDRS: tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst, key.enc_ip.tos, key.enc_ip.ttl, - key.enc_tp.dst, TUNNEL_KEY, + key.enc_tp.dst, flags, key32_to_tunnel_id(key.enc_key_id.keyid), enc_opts.key.len); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst, key.enc_ip.tos, key.enc_ip.ttl, - key.enc_tp.dst, 0, TUNNEL_KEY, + key.enc_tp.dst, 0, flags, key32_to_tunnel_id(key.enc_key_id.keyid), enc_opts.key.len); break; @@ -5528,11 +5531,16 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb tun_dst->u.tun_info.key.tp_src = key.enc_tp.src; - if (enc_opts.key.len) + if (enc_opts.key.len) { + ip_tunnel_flags_zero(flags); + if (enc_opts.key.dst_opt_type) + __set_bit(enc_opts.key.dst_opt_type, flags); + ip_tunnel_info_opts_set(&tun_dst->u.tun_info, enc_opts.key.data, enc_opts.key.len, - enc_opts.key.dst_opt_type); + flags); + } skb_dst_set(skb, (struct dst_entry *)tun_dst); dev = dev_get_by_index(&init_net, key.filter_ifindex); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index d67df358a52f..d761a1235994 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -27,23 +27,23 @@ mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev) static bool mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm_kern *parms) { - return !!(parms->i_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags); } static bool mlxsw_sp_ipip_parms6_has_ikey(const struct __ip6_tnl_parm *parms) { - return !!(parms->i_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags); } static bool mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm_kern *parms) { - return !!(parms->o_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->o_flags); } static bool mlxsw_sp_ipip_parms6_has_okey(const struct __ip6_tnl_parm *parms) { - return !!(parms->o_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->o_flags); } static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm_kern *parms) @@ -242,12 +242,15 @@ static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp, const struct net_device *ol_dev) { struct ip_tunnel *tunnel = netdev_priv(ol_dev); - __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ bool inherit_ttl = tunnel->parms.iph.ttl == 0; bool inherit_tos = tunnel->parms.iph.tos & 0x1; + IP_TUNNEL_DECLARE_FLAGS(okflags) = { }; - return (tunnel->parms.i_flags & ~okflags) == 0 && - (tunnel->parms.o_flags & ~okflags) == 0 && + /* We can't offload any other features. */ + __set_bit(IP_TUNNEL_KEY_BIT, okflags); + + return ip_tunnel_flags_subset(tunnel->parms.i_flags, okflags) && + ip_tunnel_flags_subset(tunnel->parms.o_flags, okflags) && inherit_ttl && inherit_tos && mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV4, ol_dev); } @@ -443,10 +446,13 @@ static bool mlxsw_sp_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev); bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; bool inherit_ttl = tparm.hop_limit == 0; - __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ + IP_TUNNEL_DECLARE_FLAGS(okflags) = { }; + + /* We can't offload any other features. */ + __set_bit(IP_TUNNEL_KEY_BIT, okflags); - return (tparm.i_flags & ~okflags) == 0 && - (tparm.o_flags & ~okflags) == 0 && + return ip_tunnel_flags_subset(tparm.i_flags, okflags) && + ip_tunnel_flags_subset(tparm.o_flags, okflags) && inherit_ttl && inherit_tos && mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV6, ol_dev); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index f0cbc6b9b041..3de69b2eb5c4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -461,7 +461,8 @@ mlxsw_sp_span_entry_gretap4_parms(struct mlxsw_sp *mlxsw_sp, if (!(to_dev->flags & IFF_UP) || /* Reject tunnels with GRE keys, checksums, etc. */ - tparm.i_flags || tparm.o_flags || + !ip_tunnel_flags_empty(tparm.i_flags) || + !ip_tunnel_flags_empty(tparm.o_flags) || /* Require a fixed TTL and a TOS copied from the mirrored packet. */ inherit_ttl || !inherit_tos || /* A destination address may not be "any". */ @@ -565,7 +566,8 @@ mlxsw_sp_span_entry_gretap6_parms(struct mlxsw_sp *mlxsw_sp, if (!(to_dev->flags & IFF_UP) || /* Reject tunnels with GRE keys, checksums, etc. */ - tparm.i_flags || tparm.o_flags || + !ip_tunnel_flags_empty(tparm.i_flags) || + !ip_tunnel_flags_empty(tparm.o_flags) || /* Require a fixed TTL and a TOS copied from the mirrored packet. */ inherit_ttl || !inherit_tos || /* A destination address may not be "any". */ diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 2c3f62907958..aca2a7417af3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -396,6 +396,17 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len, return 0; } +#define NFP_FL_CHECK(flag) ({ \ + IP_TUNNEL_DECLARE_FLAGS(__check) = { }; \ + __be16 __res; \ + \ + __set_bit(IP_TUNNEL_##flag##_BIT, __check); \ + __res = ip_tunnel_flags_to_be16(__check); \ + \ + BUILD_BUG_ON(__builtin_constant_p(__res) && \ + NFP_FL_TUNNEL_##flag != __res); \ +}) + static int nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, const struct flow_action_entry *act, @@ -410,6 +421,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, u32 tmp_set_ip_tun_type_index = 0; /* Currently support one pre-tunnel so index is always 0. */ int pretun_idx = 0; + __be16 tun_flags; if (!IS_ENABLED(CONFIG_IPV6) && ipv6) return -EOPNOTSUPP; @@ -417,9 +429,10 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, if (ipv6 && !(priv->flower_ext_feats & NFP_FL_FEATS_IPV6_TUN)) return -EOPNOTSUPP; - BUILD_BUG_ON(NFP_FL_TUNNEL_CSUM != TUNNEL_CSUM || - NFP_FL_TUNNEL_KEY != TUNNEL_KEY || - NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT); + NFP_FL_CHECK(CSUM); + NFP_FL_CHECK(KEY); + NFP_FL_CHECK(GENEVE_OPT); + if (ip_tun->options_len && (tun_type != NFP_FL_TUNNEL_GENEVE || !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))) { @@ -427,7 +440,9 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, return -EOPNOTSUPP; } - if (ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS) { + tun_flags = ip_tunnel_flags_to_be16(ip_tun->key.tun_flags); + if (!ip_tunnel_flags_is_be16_compat(ip_tun->key.tun_flags) || + (tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS)) { NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support tunnel flag offload"); return -EOPNOTSUPP; @@ -442,7 +457,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, FIELD_PREP(NFP_FL_PRE_TUN_INDEX, pretun_idx); set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index); - if (ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY) + if (tun_flags & NFP_FL_TUNNEL_KEY) set_tun->tun_id = ip_tun->key.tun_id; if (ip_tun->key.ttl) { @@ -486,7 +501,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, } set_tun->tos = ip_tun->key.tos; - set_tun->tun_flags = ip_tun->key.tun_flags; + set_tun->tun_flags = tun_flags; if (tun_type == NFP_FL_TUNNEL_GENEVE) { set_tun->tun_proto = htons(ETH_P_TEB); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 2f6739fe78af..163f94a5a58f 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -225,10 +225,11 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; - flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) | - (gnvh->critical ? TUNNEL_CRIT_OPT : 0); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); + __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), @@ -238,9 +239,11 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, goto drop; } /* Update tunnel dst according to Geneve options. */ + ip_tunnel_flags_zero(flags); + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, - TUNNEL_GENEVE_OPT); + flags); } else { /* Drop packets w/ critical options, * since we don't support any... @@ -745,14 +748,15 @@ static void geneve_build_header(struct genevehdr *geneveh, { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; - geneveh->oam = !!(info->key.tun_flags & TUNNEL_OAM); - geneveh->critical = !!(info->key.tun_flags & TUNNEL_CRIT_OPT); + geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); + geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, + info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } @@ -761,7 +765,7 @@ static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, bool xnet, int ip_hdr_len, bool inner_proto_inherit) { - bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); struct genevehdr *gnvh; __be16 inner_proto; int min_headroom; @@ -878,7 +882,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (geneve->cfg.collect_md) { ttl = key->ttl; - df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? + htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); @@ -910,7 +915,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; } @@ -998,7 +1004,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; } #endif @@ -1297,7 +1304,8 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { - return !(info->key.tun_id || info->key.tun_flags || info->key.tos || + return !(info->key.tun_id || info->key.tos || + !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || memchr_inv(&info->key.u, 0, sizeof(info->key.u))); } @@ -1435,7 +1443,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], @@ -1510,7 +1518,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { @@ -1520,7 +1528,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) - info->key.tun_flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); @@ -1753,7 +1761,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, - !!(info->key.tun_flags & TUNNEL_CSUM))) + test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) @@ -1762,7 +1771,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, - !(info->key.tun_flags & TUNNEL_CSUM))) + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags))) goto nla_put_failure; #endif } diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 3495591a5c29..72ecf6cf809c 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1584,7 +1584,8 @@ static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { - tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, + tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) @@ -1716,9 +1717,11 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; if (vxlan_collect_metadata(vs)) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; - tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) @@ -2403,14 +2406,14 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; - if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; - udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); @@ -2451,7 +2454,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } - } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) { + } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + info->key.tun_flags)) { df = htons(IP_DF); } diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 1b7fae4c6b24..4160731dcb6e 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -198,7 +198,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -215,7 +215,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -230,7 +230,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -243,7 +243,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; - info->key.tun_flags = flags; + ip_tunnel_flags_copy(info->key.tun_flags, flags); info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; @@ -259,7 +259,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 1a7131d6cb0e..9ab376d1a677 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -97,7 +97,7 @@ struct flow_dissector_key_enc_opts { * here but seems difficult to #include */ u8 len; - __be16 dst_opt_type; + u32 dst_opt_type; }; struct flow_dissector_key_keyid { diff --git a/include/net/gre.h b/include/net/gre.h index 4e209708b754..ccd293203284 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -49,67 +49,61 @@ static inline bool netif_is_ip6gretap(const struct net_device *dev) !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } -static inline int gre_calc_hlen(__be16 o_flags) +static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; - if (o_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } -static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { - __be16 tflags = 0; - - if (flags & GRE_CSUM) - tflags |= TUNNEL_CSUM; - if (flags & GRE_ROUTING) - tflags |= TUNNEL_ROUTING; - if (flags & GRE_KEY) - tflags |= TUNNEL_KEY; - if (flags & GRE_SEQ) - tflags |= TUNNEL_SEQ; - if (flags & GRE_STRICT) - tflags |= TUNNEL_STRICT; - if (flags & GRE_REC) - tflags |= TUNNEL_REC; - if (flags & GRE_VERSION) - tflags |= TUNNEL_VERSION; - - return tflags; + IP_TUNNEL_DECLARE_FLAGS(res) = { }; + + __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); + __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); + __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); + __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); + __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); + __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); + __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); + + ip_tunnel_flags_copy(dst, res); } -static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) +static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; - if (tflags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; - if (tflags & TUNNEL_ROUTING) + if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; - if (tflags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; - if (tflags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; - if (tflags & TUNNEL_STRICT) + if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; - if (tflags & TUNNEL_REC) + if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; - if (tflags & TUNNEL_VERSION) + if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, - __be16 flags, __be16 proto, + const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { + IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); @@ -120,18 +114,22 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; - if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __set_bit(IP_TUNNEL_KEY_BIT, cond); + __set_bit(IP_TUNNEL_CSUM_BIT, cond); + __set_bit(IP_TUNNEL_SEQ_BIT, cond); + + if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - if (flags & TUNNEL_SEQ) { + if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } - if (flags & TUNNEL_KEY) { + if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } - if (flags & TUNNEL_CSUM && + if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 74b369bddf49..399592405c72 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -30,8 +30,8 @@ struct __ip6_tnl_parm { struct in6_addr laddr; /* local tunnel end-point address */ struct in6_addr raddr; /* remote tunnel end-point address */ - __be16 i_flags; - __be16 o_flags; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); __be32 i_key; __be32 o_key; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 20f0319ab149..ed8e48cc9054 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -36,6 +36,24 @@ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) +#define __ipt_flag_op(op, ...) \ + op(__VA_ARGS__, __IP_TUNNEL_FLAG_NUM) + +#define IP_TUNNEL_DECLARE_FLAGS(...) \ + __ipt_flag_op(DECLARE_BITMAP, __VA_ARGS__) + +#define ip_tunnel_flags_zero(...) __ipt_flag_op(bitmap_zero, __VA_ARGS__) +#define ip_tunnel_flags_copy(...) __ipt_flag_op(bitmap_copy, __VA_ARGS__) +#define ip_tunnel_flags_and(...) __ipt_flag_op(bitmap_and, __VA_ARGS__) +#define ip_tunnel_flags_or(...) __ipt_flag_op(bitmap_or, __VA_ARGS__) + +#define ip_tunnel_flags_empty(...) \ + __ipt_flag_op(bitmap_empty, __VA_ARGS__) +#define ip_tunnel_flags_intersect(...) \ + __ipt_flag_op(bitmap_intersects, __VA_ARGS__) +#define ip_tunnel_flags_subset(...) \ + __ipt_flag_op(bitmap_subset, __VA_ARGS__) + struct ip_tunnel_key { __be64 tun_id; union { @@ -48,11 +66,11 @@ struct ip_tunnel_key { struct in6_addr dst; } ipv6; } u; - __be16 tun_flags; - u8 tos; /* TOS for IPv4, TC for IPv6 */ - u8 ttl; /* TTL for IPv4, HL for IPv6 */ + IP_TUNNEL_DECLARE_FLAGS(tun_flags); __be32 label; /* Flow Label for IPv6 */ u32 nhid; + u8 tos; /* TOS for IPv4, TC for IPv6 */ + u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be16 tp_src; __be16 tp_dst; __u8 flow_flags; @@ -110,14 +128,14 @@ struct ip_tunnel_prl_entry { struct metadata_dst; -/* Kernel-side copy of ip_tunnel_parm */ +/* Kernel-side variant of ip_tunnel_parm */ struct ip_tunnel_parm_kern { char name[IFNAMSIZ]; - int link; - __be16 i_flags; - __be16 o_flags; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); __be32 i_key; __be32 o_key; + int link; struct iphdr iph; }; @@ -168,7 +186,7 @@ struct ip_tunnel { }; struct tnl_ptk_info { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 proto; __be32 key; __be32 seq; @@ -190,11 +208,77 @@ struct ip_tunnel_net { int type; }; +static inline void ip_tunnel_set_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + + ip_tunnel_flags_or(flags, flags, present); +} + +static inline void ip_tunnel_clear_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + + __ipt_flag_op(bitmap_andnot, flags, flags, present); +} + +static inline bool ip_tunnel_is_options_present(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + + return ip_tunnel_flags_intersect(flags, present); +} + +static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(supp) = { }; + + bitmap_set(supp, 0, BITS_PER_TYPE(__be16)); + __set_bit(IP_TUNNEL_VTI_BIT, supp); + + return ip_tunnel_flags_subset(flags, supp); +} + +static inline void ip_tunnel_flags_from_be16(unsigned long *dst, __be16 flags) +{ + ip_tunnel_flags_zero(dst); + + bitmap_write(dst, be16_to_cpu(flags), 0, BITS_PER_TYPE(__be16)); + __assign_bit(IP_TUNNEL_VTI_BIT, dst, flags & VTI_ISVTI); +} + +static inline __be16 ip_tunnel_flags_to_be16(const unsigned long *flags) +{ + __be16 ret; + + ret = cpu_to_be16(bitmap_read(flags, 0, BITS_PER_TYPE(__be16))); + if (test_bit(IP_TUNNEL_VTI_BIT, flags)) + ret |= VTI_ISVTI; + + return ret; +} + static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, - __be64 tun_id, __be16 tun_flags) + __be64 tun_id, + const unsigned long *tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; @@ -204,7 +288,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, key->tos = tos; key->ttl = ttl; key->label = label; - key->tun_flags = tun_flags; + ip_tunnel_flags_copy(key->tun_flags, tun_flags); /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. @@ -225,12 +309,8 @@ ip_tunnel_dst_cache_usable(const struct sk_buff *skb, { if (skb->mark) return false; - if (!info) - return true; - if (info->key.tun_flags & TUNNEL_NOCACHE) - return false; - return true; + return !info || !test_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info @@ -313,7 +393,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key); @@ -529,12 +609,13 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); - info->key.tun_flags |= flags; + ip_tunnel_flags_or(info->key.tun_flags, info->key.tun_flags, + flags); } } @@ -578,7 +659,7 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = 0; } diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index d716214fe03d..a93dc51f6323 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -179,8 +179,8 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, - int md_size); + const unsigned long *flags, + __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 102119628ff5..838927dd73a4 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -161,6 +161,14 @@ enum { #define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1) +#ifndef __KERNEL__ +/* Historically, tunnel flags have been defined as __be16 and now there are + * no free bits left. It is strongly advised to switch the already existing + * userspace code to the new *_BIT definitions from down below, as __be16 + * can't be simply cast to a wider type on LE systems. All new flags and + * code must use *_BIT only. + */ + #define TUNNEL_CSUM __cpu_to_be16(0x01) #define TUNNEL_ROUTING __cpu_to_be16(0x02) #define TUNNEL_KEY __cpu_to_be16(0x04) @@ -181,5 +189,30 @@ enum { #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \ TUNNEL_GTP_OPT) +#endif + +enum { + IP_TUNNEL_CSUM_BIT = 0U, + IP_TUNNEL_ROUTING_BIT, + IP_TUNNEL_KEY_BIT, + IP_TUNNEL_SEQ_BIT, + IP_TUNNEL_STRICT_BIT, + IP_TUNNEL_REC_BIT, + IP_TUNNEL_VERSION_BIT, + IP_TUNNEL_NO_KEY_BIT, + IP_TUNNEL_DONT_FRAGMENT_BIT, + IP_TUNNEL_OAM_BIT, + IP_TUNNEL_CRIT_OPT_BIT, + IP_TUNNEL_GENEVE_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_VXLAN_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_NOCACHE_BIT, + IP_TUNNEL_ERSPAN_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_GTP_OPT_BIT, /* OPTIONS_PRESENT */ + + IP_TUNNEL_VTI_BIT, + IP_TUNNEL_SIT_ISATAP_BIT = IP_TUNNEL_VTI_BIT, + + __IP_TUNNEL_FLAG_NUM, +}; #endif /* _UAPI_IF_TUNNEL_H_ */ diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 81833ca7a2c7..a966a6ec8263 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -65,13 +65,14 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, { struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err; if (metadata) return -EEXIST; - metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, - key, 0); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, key, 0); if (!metadata) return -EINVAL; @@ -185,6 +186,7 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tunnel_dst; __be64 tunnel_id; int err; @@ -202,7 +204,8 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, return err; if (BR_INPUT_SKB_CB(skb)->backup_nhid) { - tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, tunnel_id, 0); if (!tunnel_dst) return -ENOMEM; diff --git a/net/core/filter.c b/net/core/filter.c index 0c66e4a3fc5b..294670d3850d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4662,7 +4662,7 @@ set_compat: to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) - to->tunnel_flags = info->key.tun_flags; + to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; @@ -4705,7 +4705,7 @@ BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) int err; if (unlikely(!info || - !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) { + !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } @@ -4775,15 +4775,15 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; - if (flags & BPF_F_DONT_FRAGMENT) - info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; - if (flags & BPF_F_ZERO_CSUM_TX) - info->key.tun_flags &= ~TUNNEL_CSUM; - if (flags & BPF_F_SEQ_NUMBER) - info->key.tun_flags |= TUNNEL_SEQ; - if (flags & BPF_F_NO_TUNNEL_KEY) - info->key.tun_flags &= ~TUNNEL_KEY; + __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); + __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, + flags & BPF_F_DONT_FRAGMENT); + __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, + !(flags & BPF_F_ZERO_CSUM_TX)); + __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, + flags & BPF_F_SEQ_NUMBER); + __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, + !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; @@ -4821,13 +4821,15 @@ BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); + IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; - ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT); + ip_tunnel_set_options_present(present); + ip_tunnel_info_opts_set(info, from, size, present); return 0; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 272f09251343..f82e9a7d3b37 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -455,17 +455,25 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + u32 val; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); - if (info->options_len) { - enc_opt->len = info->options_len; - ip_tunnel_info_opts_get(enc_opt->data, info); - enc_opt->dst_opt_type = info->key.tun_flags & - TUNNEL_OPTIONS_PRESENT; - } + if (!info->options_len) + return; + + enc_opt->len = info->options_len; + ip_tunnel_info_opts_get(enc_opt->data, info); + + ip_tunnel_set_options_present(flags); + ip_tunnel_flags_and(flags, info->key.tun_flags, flags); + + val = find_next_bit(flags, __IP_TUNNEL_FLAG_NUM, + IP_TUNNEL_GENEVE_OPT_BIT); + enc_opt->dst_opt_type = val < __IP_TUNNEL_FLAG_NUM ? val : 0; } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 06e5572f296f..54984f3170a8 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -64,7 +64,7 @@ __bpf_kfunc int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, info->encap.type = TUNNEL_ENCAP_NONE; } - if (info->key.tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) info->encap.flags |= TUNNEL_ENCAP_FLAG_CSUM; info->encap.sport = encap->sport; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 3757fd93523f..6701a98d9a9f 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -73,7 +73,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; - tpi->flags = gre_flags_to_tnl_flags(greh->flags); + gre_flags_to_tnl_flags(tpi->flags, greh->flags); hdr_len = gre_calc_hlen(tpi->flags); if (!pskb_may_pull(skb, nhs + hdr_len)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8853c065a985..3c46a7fef8db 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -265,6 +265,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; + IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -272,18 +273,20 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int ver; int len; + ip_tunnel_flags_copy(flags, tpi->flags); + itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } @@ -307,10 +310,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, @@ -333,7 +335,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); } @@ -376,10 +379,13 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; - flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + ip_tunnel_flags_and(flags, tpi->flags, flags); + tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) @@ -459,12 +465,15 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags = tunnel->parms.o_flags; + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -478,10 +487,10 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; - __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -495,14 +504,19 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; /* Push Tunnel header. */ - if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto err_free_skb; - flags = tun_info->key.tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); + gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -516,6 +530,7 @@ err_free_skb: static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; @@ -531,7 +546,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; @@ -584,8 +599,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; } - gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -659,7 +675,8 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, tnl_params = &tunnel->parms.iph; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); @@ -701,7 +718,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); - tunnel->parms.o_flags &= ~TUNNEL_SEQ; + __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, @@ -716,7 +733,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; } - tunnel->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; @@ -739,7 +756,8 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) @@ -757,7 +775,6 @@ free_skb: static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags; int len; len = tunnel->tun_hlen; @@ -773,10 +790,9 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); - flags = tunnel->parms.o_flags; - - if (flags & TUNNEL_SEQ || - (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || + (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { @@ -789,17 +805,25 @@ static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { + __be16 i_flags, o_flags; int err; + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + i_flags = ip_tunnel_flags_to_be16(p->i_flags); + o_flags = ip_tunnel_flags_to_be16(p->o_flags); + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || - ((p->i_flags | p->o_flags) & (GRE_VERSION | GRE_ROUTING))) + ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } - p->i_flags = gre_flags_to_tnl_flags(p->i_flags); - p->o_flags = gre_flags_to_tnl_flags(p->o_flags); + gre_flags_to_tnl_flags(p->i_flags, i_flags); + gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) @@ -808,15 +832,18 @@ static int ipgre_tunnel_ctl(struct net_device *dev, if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } - p->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); - p->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); + ip_tunnel_flags_from_be16(p->i_flags, i_flags); + o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + ip_tunnel_flags_from_be16(p->o_flags, o_flags); + return 0; } @@ -956,7 +983,6 @@ static void ipgre_tunnel_setup(struct net_device *dev) static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; - __be16 flags; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); @@ -968,14 +994,13 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= GRE_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE_FEATURES; - flags = tunnel->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1148,10 +1173,12 @@ static int ipgre_netlink_parms(struct net_device *dev, parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -1411,8 +1438,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); @@ -1440,8 +1467,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } @@ -1498,7 +1525,9 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; - __be16 o_flags = p->o_flags; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1546,7 +1575,7 @@ static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) - t->parms.o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d10f41f81463..f65170a28106 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -57,16 +57,12 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) } static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, - __be16 flags, __be32 key) + const unsigned long *flags, __be32 key) { - if (p->i_flags & TUNNEL_KEY) { - if (flags & TUNNEL_KEY) - return key == p->i_key; - else - /* key expected, none present */ - return false; - } else - return !(flags & TUNNEL_KEY); + if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) + return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); + + return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options @@ -81,7 +77,7 @@ static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { @@ -143,7 +139,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, } hlist_for_each_entry_rcu(t, head, hash_node) { - if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || + if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && + t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) @@ -182,7 +179,8 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, else remote = 0; - if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && + test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); @@ -211,12 +209,14 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; + IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; - __be16 flags = parms->i_flags; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); + ip_tunnel_flags_copy(flags, parms->i_flags); + hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && @@ -386,15 +386,15 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, } #endif - if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || - ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags&TUNNEL_SEQ) { - if (!(tpi->flags&TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); @@ -638,7 +638,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { @@ -928,10 +928,10 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); - if (!(p->i_flags & VTI_ISVTI)) { - if (!(p->i_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { + if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; - if (!(p->o_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } @@ -1016,8 +1016,8 @@ bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, strscpy(kp->name, p.name); kp->link = p.link; - kp->i_flags = p.i_flags; - kp->o_flags = p.o_flags; + ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); + ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); kp->i_key = p.i_key; kp->o_key = p.o_key; memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); @@ -1030,10 +1030,14 @@ bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) { struct ip_tunnel_parm p; + if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || + !ip_tunnel_flags_is_be16_compat(kp->o_flags)) + return false; + strscpy(p.name, kp->name); p.link = kp->link; - p.i_flags = kp->i_flags; - p.o_flags = kp->o_flags; + p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); + p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); p.i_key = kp->i_key; p.o_key = kp->o_key; memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 98f136b07191..a3676155be78 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -125,6 +125,7 @@ EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) { + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; struct metadata_dst *res; struct ip_tunnel_info *dst, *src; @@ -144,10 +145,10 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, sizeof(struct in6_addr)); else dst->key.u.ipv4.dst = src->key.u.ipv4.src; - dst->key.tun_flags = src->key.tun_flags; + ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags); dst->mode = src->mode | IP_TUNNEL_INFO_TX; ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src), - src->options_len, 0); + src->options_len, tun_flags); return res; } @@ -497,7 +498,7 @@ static int ip_tun_parse_opts_geneve(struct nlattr *attr, opt->opt_class = nla_get_be16(attr); attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE]; opt->type = nla_get_u8(attr); - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); } return sizeof(struct geneve_opt) + data_len; @@ -525,7 +526,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr, attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); md->gbp &= VXLAN_GBP_MASK; - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct vxlan_metadata); @@ -574,7 +575,7 @@ static int ip_tun_parse_opts_erspan(struct nlattr *attr, set_hwid(&md->u.md2, nla_get_u8(attr)); } - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct erspan_metadata); @@ -585,7 +586,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, { int err, rem, opt_len, opts_len = 0; struct nlattr *nla; - __be16 type = 0; + u32 type = 0; if (!attr) return 0; @@ -598,7 +599,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { switch (nla_type(nla)) { case LWTUNNEL_IP_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len, extack); @@ -607,7 +608,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) return -EINVAL; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case LWTUNNEL_IP_OPTS_VXLAN: if (type) @@ -617,7 +618,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case LWTUNNEL_IP_OPTS_ERSPAN: if (type) @@ -627,7 +628,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; default: return -EINVAL; @@ -705,10 +706,16 @@ static int ip_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_from_be16(flags, + nla_get_be16(tb[LWTUNNEL_IP_FLAGS])); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX; tun_info->options_len = opt_len; @@ -812,18 +819,18 @@ static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type, struct nlattr *nest; int err = 0; - if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(tun_info->key.tun_flags)) return 0; nest = nla_nest_start_noflag(skb, type); if (!nest) return -ENOMEM; - if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_geneve(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT) + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_vxlan(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_erspan(skb, tun_info); if (err) { @@ -846,7 +853,8 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info)) return -ENOMEM; @@ -857,11 +865,11 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) { int opt_len; - if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(info->key.tun_flags)) return 0; opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */ - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { struct geneve_opt *opt; int offset = 0; @@ -874,10 +882,10 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) /* OPT_GENEVE_DATA */ offset += sizeof(*opt) + opt->length * 4; } - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */ + nla_total_size(4); /* OPT_VXLAN_GBP */ - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { struct erspan_metadata *md = ip_tunnel_info_opts(info); opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */ @@ -984,10 +992,17 @@ static int ip6_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP6_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + __be16 data; + + data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); + ip_tunnel_flags_from_be16(flags, data); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; tun_info->options_len = opt_len; @@ -1008,7 +1023,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info)) return -ENOMEM; @@ -1139,8 +1155,12 @@ void ip_tunnel_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); - if (data[IFLA_IPTUN_FLAGS]) - parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + if (data[IFLA_IPTUN_FLAGS]) { + __be16 flags; + + flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + ip_tunnel_flags_from_be16(parms->i_flags, flags); + } if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 7e595f619615..14536da9f5dc 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -51,8 +51,11 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -322,8 +325,11 @@ static int vti4_err(struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; @@ -375,6 +381,7 @@ static int vti4_err(struct sk_buff *skb, u32 info) static int vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { @@ -383,20 +390,26 @@ vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) return -EINVAL; } - if (!(p->i_flags & GRE_KEY)) + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + if (!(ip_tunnel_flags_to_be16(p->i_flags) & GRE_KEY)) p->i_key = 0; - if (!(p->o_flags & GRE_KEY)) + if (!(ip_tunnel_flags_to_be16(p->o_flags) & GRE_KEY)) p->o_key = 0; - p->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, flags); + ip_tunnel_flags_copy(p->i_flags, flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p->i_flags |= GRE_KEY; - p->o_flags |= GRE_KEY; + ip_tunnel_flags_from_be16(flags, GRE_KEY); + ip_tunnel_flags_or(p->i_flags, p->i_flags, flags); + ip_tunnel_flags_or(p->o_flags, p->o_flags, flags); } return 0; } @@ -541,7 +554,7 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; - parms->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, parms->i_flags); if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index db960cd08a3b..923a2ef68c2f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,13 +130,16 @@ static int ipip_err(struct sk_buff *skb, u32 info) struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; int err = 0; - t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->daddr, iph->saddr, 0); + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + t = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, + iph->saddr, 0); if (!t) { err = -ENOENT; goto out; @@ -213,13 +216,16 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + iph = ip_hdr(skb); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->saddr, iph->daddr, 0); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, + iph->daddr, 0); if (tunnel) { const struct tnl_ptk_info *tpi; @@ -238,7 +244,9 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (tunnel->collect_md) { - tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + ip_tunnel_flags_zero(flags); + + tun_dst = ip_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) return 0; ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); @@ -340,7 +348,8 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) } p->i_key = p->o_key = 0; - p->i_flags = p->o_flags = 0; + ip_tunnel_flags_zero(p->i_flags); + ip_tunnel_flags_zero(p->o_flags); return ip_tunnel_ctl(dev, p, cmd); } diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 860aff5f8599..e4e0fa869fa4 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -183,7 +183,8 @@ void udp_tunnel_sock_release(struct socket *sock) EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, int md_size) + const unsigned long *flags, + __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; @@ -199,7 +200,7 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ca7e77e84283..2146cf69d8e2 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -496,11 +496,11 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) tpi->proto); if (tunnel) { if (tunnel->parms.collect_md) { + IP_TUNNEL_DECLARE_FLAGS(flags); struct metadata_dst *tun_dst; __be64 tun_id; - __be16 flags; - flags = tpi->flags; + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, 0); @@ -548,14 +548,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (tunnel->parms.collect_md) { struct erspan_metadata *pkt_md, *md; + IP_TUNNEL_DECLARE_FLAGS(flags); struct metadata_dst *tun_dst; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, @@ -577,7 +577,8 @@ static int ip6erspan_rcv(struct sk_buff *skb, md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); @@ -745,8 +746,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 protocol; - __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -778,8 +779,11 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, fl6->fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; - flags = key->tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + ip_tunnel_flags_zero(flags); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, flags, key->tun_flags); tun_hlen = gre_calc_hlen(flags); if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) @@ -788,19 +792,21 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) - : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : + 0); } else { if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) return -ENOMEM; - flags = tunnel->parms.o_flags; + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) - : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : + 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -822,7 +828,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_ipv4(skb, dev, &fl6, &dsfield, &encap_limit); - err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); + err = gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags)); if (err) return -1; @@ -856,7 +863,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; - if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags))) return -1; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, @@ -883,7 +891,8 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_other(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; - err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); + err = gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags)); if (err) return err; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); @@ -936,6 +945,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; bool truncate = false; int encap_limit = -1; __u8 dsfield = false; @@ -979,7 +989,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; - t->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); IPCB(skb)->flags = 0; /* For collect_md mode, derive fl6 from the tunnel key, @@ -1004,7 +1014,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, fl6.fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_info->key.tun_flags)) goto tx_err; if (tun_info->options_len < sizeof(*md)) goto tx_err; @@ -1065,7 +1076,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, } /* Push GRE header. */ - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) @@ -1208,8 +1221,8 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, t->parms.proto = p->proto; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); t->parms.fwmark = p->fwmark; t->parms.erspan_ver = p->erspan_ver; t->parms.index = p->index; @@ -1238,8 +1251,8 @@ static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p, p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; - p->i_flags = gre_flags_to_tnl_flags(u->i_flags); - p->o_flags = gre_flags_to_tnl_flags(u->o_flags); + gre_flags_to_tnl_flags(p->i_flags, u->i_flags); + gre_flags_to_tnl_flags(p->o_flags, u->o_flags); memcpy(p->name, u->name, sizeof(u->name)); } @@ -1391,7 +1404,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, ipv6h->daddr = t->parms.raddr; p = (__be16 *)(ipv6h + 1); - p[0] = t->parms.o_flags; + p[0] = ip_tunnel_flags_to_be16(t->parms.o_flags); p[1] = htons(type); /* @@ -1455,19 +1468,17 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static void ip6gre_tnl_init_features(struct net_device *dev) { struct ip6_tnl *nt = netdev_priv(dev); - __be16 flags; dev->features |= GRE6_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE6_FEATURES; - flags = nt->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, nt->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && nt->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, nt->parms.o_flags) && + nt->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1792,12 +1803,12 @@ static void ip6gre_netlink_parms(struct nlattr *data[], parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags( - nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags( - nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -2144,11 +2155,13 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; - __be16 o_flags = p->o_flags; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (p->erspan_ver == 1 || p->erspan_ver == 2) { if (!p->collect_md) - o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) goto nla_put_failure; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e9cc315832cb..57bb3b3ea0c5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -798,17 +798,15 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, const struct ipv6hdr *ipv6h; int nh, err; - if ((!(tpi->flags & TUNNEL_CSUM) && - (tunnel->parms.i_flags & TUNNEL_CSUM)) || - ((tpi->flags & TUNNEL_CSUM) && - !(tunnel->parms.i_flags & TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags & TUNNEL_SEQ) { - if (!(tpi->flags & TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); @@ -946,7 +944,9 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (t->parms.collect_md) { - tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + tun_dst = ipv6_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) goto drop; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 894e6a4c4be3..83b195f09561 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -207,7 +207,7 @@ static int ipip6_tunnel_create(struct net_device *dev) __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); - if ((__force u16)t->parms.i_flags & SIT_ISATAP) + if (test_bit(IP_TUNNEL_SIT_ISATAP_BIT, t->parms.i_flags)) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; @@ -1700,7 +1700,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || - nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, + ip_tunnel_flags_to_be16(parm->i_flags)) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a2c16b501087..c7a8a08b7308 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1550,6 +1550,7 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 type; /* Only support version 0 and C (csum) */ @@ -1560,7 +1561,10 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; - return gre_calc_hlen(gre_flags_to_tnl_flags(greh->flags)); + + gre_flags_to_tnl_flags(flags, greh->flags); + + return gre_calc_hlen(flags); } unk: diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 65e0259178da..39b5fd6bbf65 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -390,10 +390,10 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, skb->ip_summed == CHECKSUM_PARTIAL) mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); mtu -= gre_calc_hlen(tflags); } if (mtu < 68) { @@ -553,10 +553,10 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, skb->ip_summed == CHECKSUM_PARTIAL) mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); mtu -= gre_calc_hlen(tflags); } if (mtu < IPV6_MIN_MTU) { @@ -1082,11 +1082,11 @@ ipvs_gre_encap(struct net *net, struct sk_buff *skb, { __be16 proto = *next_protocol == IPPROTO_IPIP ? htons(ETH_P_IP) : htons(ETH_P_IPV6); - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t hdrlen; if (cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); hdrlen = gre_calc_hlen(tflags); gre_build_header(skb, hdrlen, tflags, proto, 0, 0); @@ -1165,11 +1165,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom += sizeof(struct udphdr) + gue_hdrlen; } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t gre_hdrlen; - __be16 tflags = 0; if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); gre_hdrlen = gre_calc_hlen(tflags); max_headroom += gre_hdrlen; @@ -1310,11 +1310,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom += sizeof(struct udphdr) + gue_hdrlen; } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t gre_hdrlen; - __be16 tflags = 0; if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); gre_hdrlen = gre_calc_hlen(tflags); max_headroom += gre_hdrlen; diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index f735d79d8be5..60a76e6e348e 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -174,8 +174,8 @@ struct nft_tunnel_opts { struct erspan_metadata erspan; u8 data[IP_TUNNEL_OPTS_MAX]; } u; + IP_TUNNEL_DECLARE_FLAGS(flags); u32 len; - __be16 flags; }; struct nft_tunnel_obj { @@ -271,7 +271,8 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP])); opts->len = sizeof(struct vxlan_metadata); - opts->flags = TUNNEL_VXLAN_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, opts->flags); return 0; } @@ -325,7 +326,8 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, opts->u.erspan.version = version; opts->len = sizeof(struct erspan_metadata); - opts->flags = TUNNEL_ERSPAN_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, opts->flags); return 0; } @@ -366,7 +368,8 @@ static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, opt->length = data_len / 4; opt->opt_class = nla_get_be16(tb[NFTA_TUNNEL_KEY_GENEVE_CLASS]); opt->type = nla_get_u8(tb[NFTA_TUNNEL_KEY_GENEVE_TYPE]); - opts->flags = TUNNEL_GENEVE_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, opts->flags); return 0; } @@ -385,8 +388,8 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, struct nft_tunnel_opts *opts) { struct nlattr *nla; - __be16 type = 0; int err, rem; + u32 type = 0; err = nla_validate_nested_deprecated(attr, NFTA_TUNNEL_KEY_OPTS_MAX, nft_tunnel_opts_policy, NULL); @@ -401,7 +404,7 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, err = nft_tunnel_obj_vxlan_init(nla, opts); if (err) return err; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case NFTA_TUNNEL_KEY_OPTS_ERSPAN: if (type) @@ -409,15 +412,15 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, err = nft_tunnel_obj_erspan_init(nla, opts); if (err) return err; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; case NFTA_TUNNEL_KEY_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; err = nft_tunnel_obj_geneve_init(nla, opts); if (err) return err; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; default: return -EOPNOTSUPP; @@ -454,7 +457,9 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, memset(&info, 0, sizeof(info)); info.mode = IP_TUNNEL_INFO_TX; info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID])); - info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + __set_bit(IP_TUNNEL_KEY_BIT, info.key.tun_flags); + __set_bit(IP_TUNNEL_CSUM_BIT, info.key.tun_flags); + __set_bit(IP_TUNNEL_NOCACHE_BIT, info.key.tun_flags); if (tb[NFTA_TUNNEL_KEY_IP]) { err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info); @@ -483,11 +488,12 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX) - info.key.tun_flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, info.key.tun_flags); if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT) - info.key.tun_flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + info.key.tun_flags); if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER) - info.key.tun_flags |= TUNNEL_SEQ; + __set_bit(IP_TUNNEL_SEQ_BIT, info.key.tun_flags); } if (tb[NFTA_TUNNEL_KEY_TOS]) info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); @@ -583,7 +589,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, if (!nest) return -1; - if (opts->flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, opts->flags)) { inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_VXLAN); if (!inner) goto failure; @@ -591,7 +597,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, htonl(opts->u.vxlan.gbp))) goto inner_failure; nla_nest_end(skb, inner); - } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, opts->flags)) { inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_ERSPAN); if (!inner) goto failure; @@ -613,7 +619,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, break; } nla_nest_end(skb, inner); - } else if (opts->flags & TUNNEL_GENEVE_OPT) { + } else if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, opts->flags)) { struct geneve_opt *opt; int offset = 0; @@ -658,11 +664,11 @@ static int nft_tunnel_flags_dump(struct sk_buff *skb, { u32 flags = 0; - if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_DONT_FRAGMENT; - if (!(info->key.tun_flags & TUNNEL_CSUM)) + if (!test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_ZERO_CSUM_TX; - if (info->key.tun_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_SEQ_NUMBER; if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ebc5728aab4e..f224d9bcea5e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -152,6 +152,13 @@ static void update_range(struct sw_flow_match *match, sizeof((match)->key->field)); \ } while (0) +#define SW_FLOW_KEY_BITMAP_COPY(match, field, value_p, nbits, is_mask) ({ \ + update_range(match, offsetof(struct sw_flow_key, field), \ + bitmap_size(nbits), is_mask); \ + bitmap_copy(is_mask ? (match)->mask->key.field : (match)->key->field, \ + value_p, nbits); \ +}) + static bool match_validate(const struct sw_flow_match *match, u64 key_attrs, u64 mask_attrs, bool log) { @@ -670,8 +677,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, bool log) { bool ttl = false, ipv4 = false, ipv6 = false; + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; bool info_bridge_mode = false; - __be16 tun_flags = 0; int opts_type = 0; struct nlattr *a; int rem; @@ -697,7 +704,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_ID: SW_FLOW_KEY_PUT(match, tun_key.tun_id, nla_get_be64(a), is_mask); - tun_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, @@ -729,10 +736,10 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, ttl = true; break; case OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT: - tun_flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_CSUM: - tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_TP_SRC: SW_FLOW_KEY_PUT(match, tun_key.tp_src, @@ -743,7 +750,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, nla_get_be16(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_OAM: - tun_flags |= TUNNEL_OAM; + __set_bit(IP_TUNNEL_OAM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: if (opts_type) { @@ -755,7 +762,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: @@ -768,7 +775,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_PAD: @@ -784,7 +791,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE: @@ -798,7 +805,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, } } - SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask); + SW_FLOW_KEY_BITMAP_COPY(match, tun_key.tun_flags, tun_flags, + __IP_TUNNEL_FLAG_NUM, is_mask); if (is_mask) SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); else @@ -823,13 +831,15 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, } if (ipv4) { if (info_bridge_mode) { + __clear_bit(IP_TUNNEL_KEY_BIT, tun_flags); + if (match->key->tun_key.u.ipv4.src || match->key->tun_key.u.ipv4.dst || match->key->tun_key.tp_src || match->key->tun_key.tp_dst || match->key->tun_key.ttl || match->key->tun_key.tos || - tun_flags & ~TUNNEL_KEY) { + !ip_tunnel_flags_empty(tun_flags)) { OVS_NLERR(log, "IPv4 tun info is not correct"); return -EINVAL; } @@ -874,7 +884,7 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len, unsigned short tun_proto, u8 mode) { - if (output->tun_flags & TUNNEL_KEY && + if (test_bit(IP_TUNNEL_KEY_BIT, output->tun_flags) && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id, OVS_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; @@ -910,10 +920,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ttl)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) && + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_CSUM) && + if (test_bit(IP_TUNNEL_CSUM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (output->tp_src && @@ -922,18 +932,20 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, if (output->tp_dst && nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_OAM) && + if (test_bit(IP_TUNNEL_OAM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (swkey_tun_opts_len) { - if (output->tun_flags & TUNNEL_GENEVE_OPT && + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_VXLAN_OPT && + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, + output->tun_flags) && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; @@ -2029,7 +2041,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if ((swkey->tun_proto || is_mask)) { const void *opts = NULL; - if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) + if (ip_tunnel_is_options_present(output->tun_key.tun_flags)) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); if (ip_tun_to_nlattr(skb, &output->tun_key, opts, @@ -2752,7 +2764,8 @@ static int validate_geneve_opts(struct sw_flow_key *key) opts_len -= len; } - key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + if (crit_opt) + __set_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_key.tun_flags); return 0; } @@ -2760,6 +2773,7 @@ static int validate_geneve_opts(struct sw_flow_key *key) static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_actions **sfa, bool log) { + IP_TUNNEL_DECLARE_FLAGS(dst_opt_type) = { }; struct sw_flow_match match; struct sw_flow_key key; struct metadata_dst *tun_dst; @@ -2767,9 +2781,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; - __be16 dst_opt_type; - dst_opt_type = 0; ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) @@ -2781,13 +2793,14 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, err = validate_geneve_opts(&key); if (err < 0) return err; - dst_opt_type = TUNNEL_GENEVE_OPT; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: - dst_opt_type = TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - dst_opt_type = TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, dst_opt_type); break; } } diff --git a/net/psample/psample.c b/net/psample/psample.c index ddd211a151d0..a5d9b8446f77 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -221,7 +221,7 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, const struct ip_tunnel_key *tun_key = &tun_info->key; int tun_opts_len = tun_info->options_len; - if (tun_key->tun_flags & TUNNEL_KEY && + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags) && nla_put_be64(skb, PSAMPLE_TUNNEL_KEY_ATTR_ID, tun_key->tun_id, PSAMPLE_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; @@ -257,10 +257,10 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u8(skb, PSAMPLE_TUNNEL_KEY_ATTR_TTL, tun_key->ttl)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) && + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_CSUM) && + if (test_bit(IP_TUNNEL_CSUM_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (tun_key->tp_src && @@ -269,15 +269,16 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, if (tun_key->tp_dst && nla_put_be16(skb, PSAMPLE_TUNNEL_KEY_ATTR_TP_DST, tun_key->tp_dst)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_OAM) && + if (test_bit(IP_TUNNEL_OAM_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (tun_opts_len) { - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT && + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_key->tun_flags) && nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_GENEVE_OPTS, tun_opts_len, tun_opts)) return -EMSGSIZE; - else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT && + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_key->tun_flags) && nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_ERSPAN_OPTS, tun_opts_len, tun_opts)) return -EMSGSIZE; @@ -314,7 +315,7 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) int tun_opts_len = tun_info->options_len; int sum = nla_total_size(0); /* PSAMPLE_ATTR_TUNNEL */ - if (tun_key->tun_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags)) sum += nla_total_size_64bit(sizeof(u64)); if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE) @@ -337,20 +338,21 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) if (tun_key->tos) sum += nla_total_size(sizeof(u8)); sum += nla_total_size(sizeof(u8)); /* TTL */ - if (tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_key->tun_flags)) sum += nla_total_size(0); - if (tun_key->tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tun_key->tun_flags)) sum += nla_total_size(0); if (tun_key->tp_src) sum += nla_total_size(sizeof(u16)); if (tun_key->tp_dst) sum += nla_total_size(sizeof(u16)); - if (tun_key->tun_flags & TUNNEL_OAM) + if (test_bit(IP_TUNNEL_OAM_BIT, tun_key->tun_flags)) sum += nla_total_size(0); if (tun_opts_len) { - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_key->tun_flags)) sum += nla_total_size(tun_opts_len); - else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_key->tun_flags)) sum += nla_total_size(tun_opts_len); } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 1536f8b16f1b..af7c99845948 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -230,7 +230,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, nla_for_each_attr(attr, head, len, rem) { switch (nla_type(attr)) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) { + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } @@ -247,7 +247,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, dst_len -= opt_len; dst += opt_len; } - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: if (type) { @@ -259,7 +259,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: if (type) { @@ -271,7 +271,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; } } @@ -302,7 +302,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, switch (nla_type(nla_data(nla))) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -310,7 +310,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #endif case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -318,7 +318,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #endif case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -363,6 +363,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *metadata = NULL; struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; @@ -371,7 +372,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 dst_port = 0; __be64 key_id = 0; int opts_len = 0; - __be16 flags = 0; u8 tos, ttl; int ret = 0; u32 index; @@ -412,16 +412,16 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); key_id = key32_to_tunnel_id(key32); - flags = TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, flags); } - flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, flags); if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) - flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, flags); if (nla_get_flag(tb[TCA_TUNNEL_KEY_NO_FRAG])) - flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, flags); if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); @@ -663,15 +663,15 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (!start) return -EMSGSIZE; - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) goto err_out; - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_vxlan_opts_dump(skb, info); if (err) goto err_out; - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_erspan_opts_dump(skb, info); if (err) goto err_out; @@ -741,7 +741,7 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); - if (((key->tun_flags & TUNNEL_KEY) && + if ((test_bit(IP_TUNNEL_KEY_BIT, key->tun_flags) && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || @@ -749,8 +749,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, - !(key->tun_flags & TUNNEL_CSUM)) || - ((key->tun_flags & TUNNEL_DONT_FRAGMENT) && + !test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) || + (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) && nla_put_flag(skb, TCA_TUNNEL_KEY_NO_FRAG)) || tunnel_key_opts_dump(skb, info)) goto nla_put_failure; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e1314674b4a9..ae14d649140f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1454,12 +1454,13 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, switch (nla_type(nla_opt_key)) { case TCA_FLOWER_KEY_ENC_OPTS_GENEVE: if (key->enc_opts.dst_opt_type && - key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) { + key->enc_opts.dst_opt_type != + IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; option_len = fl_set_geneve_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1470,7 +1471,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; option_len = fl_set_geneve_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1489,7 +1490,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; option_len = fl_set_vxlan_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1500,7 +1501,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; option_len = fl_set_vxlan_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1519,7 +1520,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; option_len = fl_set_erspan_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1530,7 +1531,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; option_len = fl_set_erspan_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1550,7 +1551,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; option_len = fl_set_gtp_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1561,7 +1562,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; option_len = fl_set_gtp_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -3202,22 +3203,22 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, goto nla_put_failure; switch (enc_opts->dst_opt_type) { - case TUNNEL_GENEVE_OPT: + case IP_TUNNEL_GENEVE_OPT_BIT: err = fl_dump_key_geneve_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_VXLAN_OPT: + case IP_TUNNEL_VXLAN_OPT_BIT: err = fl_dump_key_vxlan_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_ERSPAN_OPT: + case IP_TUNNEL_ERSPAN_OPT_BIT: err = fl_dump_key_erspan_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_GTP_OPT: + case IP_TUNNEL_GTP_OPT_BIT: err = fl_dump_key_gtp_opt(skb, enc_opts); if (err) goto nla_put_failure; -- cgit v1.2.3 From 6dd514f48110ebb4bf36875b9e7e02d07b589caa Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Wed, 27 Mar 2024 16:23:56 +0100 Subject: pfcp: always set pfcp metadata In PFCP receive path set metadata needed by flower code to do correct classification based on this metadata. Signed-off-by: Michal Swiatkowski Signed-off-by: Marcin Szycik Reviewed-by: Simon Horman Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- drivers/net/pfcp.c | 81 ++++++++++++++++++++++++++++++- include/net/ip_tunnels.h | 3 ++ include/net/pfcp.h | 73 ++++++++++++++++++++++++++++ include/uapi/linux/if_tunnel.h | 3 ++ include/uapi/linux/pkt_cls.h | 14 ++++++ net/core/net_test.c | 7 +-- net/sched/cls_flower.c | 107 +++++++++++++++++++++++++++++++++++++++++ 7 files changed, 282 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c index 3f1ee0ae7111..cc5b28c5f99f 100644 --- a/drivers/net/pfcp.c +++ b/drivers/net/pfcp.c @@ -21,6 +21,8 @@ struct pfcp_dev { struct socket *sock; struct net_device *dev; struct net *net; + + struct gro_cells gro_cells; }; static unsigned int pfcp_net_id __read_mostly; @@ -29,6 +31,78 @@ struct pfcp_net { struct list_head pfcp_dev_list; }; +static void +pfcp_session_recv(struct pfcp_dev *pfcp, struct sk_buff *skb, + struct pfcp_metadata *md) +{ + struct pfcphdr_session *unparsed = pfcp_hdr_session(skb); + + md->seid = unparsed->seid; + md->type = PFCP_TYPE_SESSION; +} + +static void +pfcp_node_recv(struct pfcp_dev *pfcp, struct sk_buff *skb, + struct pfcp_metadata *md) +{ + md->type = PFCP_TYPE_NODE; +} + +static int pfcp_encap_recv(struct sock *sk, struct sk_buff *skb) +{ + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + struct metadata_dst *tun_dst; + struct pfcp_metadata *md; + struct pfcphdr *unparsed; + struct pfcp_dev *pfcp; + + if (unlikely(!pskb_may_pull(skb, PFCP_HLEN))) + goto drop; + + pfcp = rcu_dereference_sk_user_data(sk); + if (unlikely(!pfcp)) + goto drop; + + unparsed = pfcp_hdr(skb); + + ip_tunnel_flags_zero(flags); + tun_dst = udp_tun_rx_dst(skb, sk->sk_family, flags, 0, + sizeof(*md)); + if (unlikely(!tun_dst)) + goto drop; + + md = ip_tunnel_info_opts(&tun_dst->u.tun_info); + if (unlikely(!md)) + goto drop; + + if (unparsed->flags & PFCP_SEID_FLAG) + pfcp_session_recv(pfcp, skb, md); + else + pfcp_node_recv(pfcp, skb, md); + + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, flags); + ip_tunnel_info_opts_set(&tun_dst->u.tun_info, md, sizeof(*md), + flags); + + if (unlikely(iptunnel_pull_header(skb, PFCP_HLEN, skb->protocol, + !net_eq(sock_net(sk), + dev_net(pfcp->dev))))) + goto drop; + + skb_dst_set(skb, (struct dst_entry *)tun_dst); + + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + skb->dev = pfcp->dev; + + gro_cells_receive(&pfcp->gro_cells, skb); + + return 0; +drop: + kfree_skb(skb); + return 0; +} + static void pfcp_del_sock(struct pfcp_dev *pfcp) { udp_tunnel_sock_release(pfcp->sock); @@ -39,6 +113,7 @@ static void pfcp_dev_uninit(struct net_device *dev) { struct pfcp_dev *pfcp = netdev_priv(dev); + gro_cells_destroy(&pfcp->gro_cells); pfcp_del_sock(pfcp); } @@ -48,7 +123,7 @@ static int pfcp_dev_init(struct net_device *dev) pfcp->dev = dev; - return 0; + return gro_cells_init(&pfcp->gro_cells, dev); } static const struct net_device_ops pfcp_netdev_ops = { @@ -94,6 +169,10 @@ static struct socket *pfcp_create_sock(struct pfcp_dev *pfcp) if (err) return ERR_PTR(err); + tuncfg.sk_user_data = pfcp; + tuncfg.encap_rcv = pfcp_encap_recv; + tuncfg.encap_type = 1; + setup_udp_tunnel_sock(net, sock, &tuncfg); return sock; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index ed8e48cc9054..d8f574fbb11e 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -216,6 +216,7 @@ static inline void ip_tunnel_set_options_present(unsigned long *flags) __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); ip_tunnel_flags_or(flags, flags, present); } @@ -228,6 +229,7 @@ static inline void ip_tunnel_clear_options_present(unsigned long *flags) __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); __ipt_flag_op(bitmap_andnot, flags, flags, present); } @@ -240,6 +242,7 @@ static inline bool ip_tunnel_is_options_present(const unsigned long *flags) __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); return ip_tunnel_flags_intersect(flags, present); } diff --git a/include/net/pfcp.h b/include/net/pfcp.h index 3f9ebf27a8ff..af14f970b80e 100644 --- a/include/net/pfcp.h +++ b/include/net/pfcp.h @@ -2,12 +2,85 @@ #ifndef _PFCP_H_ #define _PFCP_H_ +#include +#include #include +#include +#include +#include +#include #include #include +#include #define PFCP_PORT 8805 +/* PFCP protocol header */ +struct pfcphdr { + u8 flags; + u8 message_type; + __be16 message_length; +}; + +/* PFCP header flags */ +#define PFCP_SEID_FLAG BIT(0) +#define PFCP_MP_FLAG BIT(1) + +#define PFCP_VERSION_MASK GENMASK(4, 0) + +#define PFCP_HLEN (sizeof(struct udphdr) + sizeof(struct pfcphdr)) + +/* PFCP node related messages */ +struct pfcphdr_node { + u8 seq_number[3]; + u8 reserved; +}; + +/* PFCP session related messages */ +struct pfcphdr_session { + __be64 seid; + u8 seq_number[3]; +#ifdef __LITTLE_ENDIAN_BITFIELD + u8 message_priority:4, + reserved:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + message_priprity:4; +#else +#error "Please fix " +#endif +}; + +struct pfcp_metadata { + u8 type; + __be64 seid; +} __packed; + +enum { + PFCP_TYPE_NODE = 0, + PFCP_TYPE_SESSION = 1, +}; + +#define PFCP_HEADROOM (sizeof(struct iphdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) +#define PFCP6_HEADROOM (sizeof(struct ipv6hdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) + +static inline struct pfcphdr *pfcp_hdr(struct sk_buff *skb) +{ + return (struct pfcphdr *)(udp_hdr(skb) + 1); +} + +static inline struct pfcphdr_node *pfcp_hdr_node(struct sk_buff *skb) +{ + return (struct pfcphdr_node *)(pfcp_hdr(skb) + 1); +} + +static inline struct pfcphdr_session *pfcp_hdr_session(struct sk_buff *skb) +{ + return (struct pfcphdr_session *)(pfcp_hdr(skb) + 1); +} + static inline bool netif_is_pfcp(const struct net_device *dev) { return dev->rtnl_link_ops && diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 838927dd73a4..e1a246dd8c62 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -212,6 +212,9 @@ enum { IP_TUNNEL_VTI_BIT, IP_TUNNEL_SIT_ISATAP_BIT = IP_TUNNEL_VTI_BIT, + /* Flags starting from here are not available via the old UAPI */ + IP_TUNNEL_PFCP_OPT_BIT, /* OPTIONS_PRESENT */ + __IP_TUNNEL_FLAG_NUM, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ea277039f89d..229fc925ec3a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -587,6 +587,10 @@ enum { * TCA_FLOWER_KEY_ENC_OPT_GTP_ * attributes */ + TCA_FLOWER_KEY_ENC_OPTS_PFCP, /* Nested + * TCA_FLOWER_KEY_ENC_IPT_PFCP + * attributes + */ __TCA_FLOWER_KEY_ENC_OPTS_MAX, }; @@ -636,6 +640,16 @@ enum { #define TCA_FLOWER_KEY_ENC_OPT_GTP_MAX \ (__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1) +enum { + TCA_FLOWER_KEY_ENC_OPT_PFCP_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, /* be64 */ + __TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX - 1) + enum { TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC, TCA_FLOWER_KEY_MPLS_OPTS_LSE, diff --git a/net/core/net_test.c b/net/core/net_test.c index 30062b9621e4..9c3a590865d2 100644 --- a/net/core/net_test.c +++ b/net/core/net_test.c @@ -335,11 +335,8 @@ static const struct ip_tunnel_flags_test ip_tunnel_flags_test[] = { ip_tunnel_flags_1), IP_TUNNEL_FLAGS_TEST("conflict", ip_tunnel_flags_2_src, true, VTI_ISVTI, ip_tunnel_flags_2_exp), - IP_TUNNEL_FLAGS_TEST("new", ip_tunnel_flags_3_src, - /* This must be set to ``false`` once - * ``__IP_TUNNEL_FLAG_NUM`` goes above 17. - */ - true, cpu_to_be16(BIT(IP_TUNNEL_VXLAN_OPT_BIT)), + IP_TUNNEL_FLAGS_TEST("new", ip_tunnel_flags_3_src, false, + cpu_to_be16(BIT(IP_TUNNEL_VXLAN_OPT_BIT)), ip_tunnel_flags_3_exp), }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index ae14d649140f..fd9a6f20b60b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -741,6 +742,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_PFCP] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -770,6 +772,12 @@ gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_GTP_QFI] = { .type = NLA_U8 }, }; +static const struct nla_policy +pfcp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID] = { .type = NLA_U64 }, +}; + static const struct nla_policy mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, @@ -1419,6 +1427,44 @@ static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key, return sizeof(*sinfo); } +static int fl_set_pfcp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1]; + struct pfcp_metadata *md; + int err; + + md = (struct pfcp_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_PFCP) { + NL_SET_ERR_MSG_MOD(extack, "Non-pfcp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, nla, + pfcp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing tunnel key pfcp option type"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) + md->type = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]) + md->seid = nla_get_be64(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]); + + return sizeof(*md); +} + static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1576,6 +1622,36 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } break; + case TCA_FLOWER_KEY_ENC_OPTS_PFCP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, "Duplicate type for pfcp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); return -EINVAL; @@ -3118,6 +3194,32 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_pfcp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct pfcp_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_PFCP); + if (!nest) + goto nla_put_failure; + + md = (struct pfcp_metadata *)&enc_opts->data[0]; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, md->type)) + goto nla_put_failure; + + if (nla_put_be64(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, + md->seid, 0)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int fl_dump_key_ct(struct sk_buff *skb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask) @@ -3223,6 +3325,11 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, if (err) goto nla_put_failure; break; + case IP_TUNNEL_PFCP_OPT_BIT: + err = fl_dump_key_pfcp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; default: goto nla_put_failure; } -- cgit v1.2.3 From 29ce50e078b857977202205394f200a25889636e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 Mar 2024 20:48:21 -0700 Subject: crypto: remove CONFIG_CRYPTO_STATS Remove support for the "Crypto usage statistics" feature (CONFIG_CRYPTO_STATS). This feature does not appear to have ever been used, and it is harmful because it significantly reduces performance and is a large maintenance burden. Covering each of these points in detail: 1. Feature is not being used Since these generic crypto statistics are only readable using netlink, it's fairly straightforward to look for programs that use them. I'm unable to find any evidence that any such programs exist. For example, Debian Code Search returns no hits except the kernel header and kernel code itself and translations of the kernel header: https://codesearch.debian.net/search?q=CRYPTOCFGA_STAT&literal=1&perpkg=1 The patch series that added this feature in 2018 (https://lore.kernel.org/linux-crypto/1537351855-16618-1-git-send-email-clabbe@baylibre.com/) said "The goal is to have an ifconfig for crypto device." This doesn't appear to have happened. It's not clear that there is real demand for crypto statistics. Just because the kernel provides other types of statistics such as I/O and networking statistics and some people find those useful does not mean that crypto statistics are useful too. Further evidence that programs are not using CONFIG_CRYPTO_STATS is that it was able to be disabled in RHEL and Fedora as a bug fix (https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/2947). Even further evidence comes from the fact that there are and have been bugs in how the stats work, but they were never reported. For example, before Linux v6.7 hash stats were double-counted in most cases. There has also never been any documentation for this feature, so it might be hard to use even if someone wanted to. 2. CONFIG_CRYPTO_STATS significantly reduces performance Enabling CONFIG_CRYPTO_STATS significantly reduces the performance of the crypto API, even if no program ever retrieves the statistics. This primarily affects systems with a large number of CPUs. For example, https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2039576 reported that Lustre client encryption performance improved from 21.7GB/s to 48.2GB/s by disabling CONFIG_CRYPTO_STATS. It can be argued that this means that CONFIG_CRYPTO_STATS should be optimized with per-cpu counters similar to many of the networking counters. But no one has done this in 5+ years. This is consistent with the fact that the feature appears to be unused, so there seems to be little interest in improving it as opposed to just disabling it. It can be argued that because CONFIG_CRYPTO_STATS is off by default, performance doesn't matter. But Linux distros tend to error on the side of enabling options. The option is enabled in Ubuntu and Arch Linux, and until recently was enabled in RHEL and Fedora (see above). So, even just having the option available is harmful to users. 3. CONFIG_CRYPTO_STATS is a large maintenance burden There are over 1000 lines of code associated with CONFIG_CRYPTO_STATS, spread among 32 files. It significantly complicates much of the implementation of the crypto API. After the initial submission, many fixes and refactorings have consumed effort of multiple people to keep this feature "working". We should be spending this effort elsewhere. Acked-by: Ard Biesheuvel Acked-by: Corentin Labbe Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/s390/configs/debug_defconfig | 1 - arch/s390/configs/defconfig | 1 - crypto/Kconfig | 20 -- crypto/Makefile | 2 - crypto/acompress.c | 33 --- crypto/aead.c | 84 +----- crypto/ahash.c | 63 +---- crypto/akcipher.c | 31 --- crypto/compress.h | 3 - crypto/crypto_user.c | 522 +++++++++++++++++++++++++++++++++++ crypto/crypto_user_base.c | 516 ---------------------------------- crypto/crypto_user_stat.c | 176 ------------ crypto/hash.h | 30 -- crypto/kpp.c | 30 -- crypto/lskcipher.c | 73 +---- crypto/rng.c | 44 +-- crypto/scompress.c | 3 - crypto/shash.c | 75 +---- crypto/sig.c | 13 - crypto/skcipher.c | 86 +----- crypto/skcipher.h | 10 - include/crypto/acompress.h | 73 +---- include/crypto/aead.h | 21 -- include/crypto/akcipher.h | 78 +----- include/crypto/algapi.h | 3 - include/crypto/hash.h | 22 -- include/crypto/internal/acompress.h | 1 - include/crypto/internal/cryptouser.h | 16 -- include/crypto/internal/scompress.h | 1 - include/crypto/kpp.h | 58 +--- include/crypto/rng.h | 51 +--- include/crypto/skcipher.h | 25 -- include/uapi/linux/cryptouser.h | 30 +- 33 files changed, 585 insertions(+), 1610 deletions(-) create mode 100644 crypto/crypto_user.c delete mode 100644 crypto/crypto_user_base.c delete mode 100644 crypto/crypto_user_stat.c delete mode 100644 include/crypto/internal/cryptouser.h (limited to 'include/uapi/linux') diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index f1fb01cd5a25..145342e46ea8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -760,7 +760,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_STATS=y CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_SHA1_S390=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index d33f814f78b2..dc237896f99d 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -745,7 +745,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_STATS=y CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_SHA1_S390=m diff --git a/crypto/Kconfig b/crypto/Kconfig index 2903ce19f15c..5688d42a59c2 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1456,26 +1456,6 @@ config CRYPTO_USER_API_ENABLE_OBSOLETE already been phased out from internal use by the kernel, and are only useful for userspace clients that still rely on them. -config CRYPTO_STATS - bool "Crypto usage statistics" - depends on CRYPTO_USER - help - Enable the gathering of crypto stats. - - Enabling this option reduces the performance of the crypto API. It - should only be enabled when there is actually a use case for it. - - This collects data sizes, numbers of requests, and numbers - of errors processed by: - - AEAD ciphers (encrypt, decrypt) - - asymmetric key ciphers (encrypt, decrypt, verify, sign) - - symmetric key ciphers (encrypt, decrypt) - - compression algorithms (compress, decompress) - - hash algorithms (hash) - - key-agreement protocol primitives (setsecret, generate - public key, compute shared secret) - - RNG (generate, seed) - endmenu config CRYPTO_HASH_INFO diff --git a/crypto/Makefile b/crypto/Makefile index 408f0a1f9ab9..de9a3312a2c8 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -69,8 +69,6 @@ cryptomgr-y := algboss.o testmgr.o obj-$(CONFIG_CRYPTO_MANAGER2) += cryptomgr.o obj-$(CONFIG_CRYPTO_USER) += crypto_user.o -crypto_user-y := crypto_user_base.o -crypto_user-$(CONFIG_CRYPTO_STATS) += crypto_user_stat.o obj-$(CONFIG_CRYPTO_CMAC) += cmac.o obj-$(CONFIG_CRYPTO_HMAC) += hmac.o obj-$(CONFIG_CRYPTO_VMAC) += vmac.o diff --git a/crypto/acompress.c b/crypto/acompress.c index 1c682810a484..6fdf0ff9f3c0 100644 --- a/crypto/acompress.c +++ b/crypto/acompress.c @@ -93,32 +93,6 @@ static unsigned int crypto_acomp_extsize(struct crypto_alg *alg) return extsize; } -static inline int __crypto_acomp_report_stat(struct sk_buff *skb, - struct crypto_alg *alg) -{ - struct comp_alg_common *calg = __crypto_comp_alg_common(alg); - struct crypto_istat_compress *istat = comp_get_stat(calg); - struct crypto_stat_compress racomp; - - memset(&racomp, 0, sizeof(racomp)); - - strscpy(racomp.type, "acomp", sizeof(racomp.type)); - racomp.stat_compress_cnt = atomic64_read(&istat->compress_cnt); - racomp.stat_compress_tlen = atomic64_read(&istat->compress_tlen); - racomp.stat_decompress_cnt = atomic64_read(&istat->decompress_cnt); - racomp.stat_decompress_tlen = atomic64_read(&istat->decompress_tlen); - racomp.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_ACOMP, sizeof(racomp), &racomp); -} - -#ifdef CONFIG_CRYPTO_STATS -int crypto_acomp_report_stat(struct sk_buff *skb, struct crypto_alg *alg) -{ - return __crypto_acomp_report_stat(skb, alg); -} -#endif - static const struct crypto_type crypto_acomp_type = { .extsize = crypto_acomp_extsize, .init_tfm = crypto_acomp_init_tfm, @@ -127,9 +101,6 @@ static const struct crypto_type crypto_acomp_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_acomp_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_acomp_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_ACOMPRESS_MASK, @@ -184,13 +155,9 @@ EXPORT_SYMBOL_GPL(acomp_request_free); void comp_prepare_alg(struct comp_alg_common *alg) { - struct crypto_istat_compress *istat = comp_get_stat(alg); struct crypto_alg *base = &alg->base; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); } int crypto_register_acomp(struct acomp_alg *alg) diff --git a/crypto/aead.c b/crypto/aead.c index 54906633566a..0e75a69189df 100644 --- a/crypto/aead.c +++ b/crypto/aead.c @@ -20,15 +20,6 @@ #include "internal.h" -static inline struct crypto_istat_aead *aead_get_stat(struct aead_alg *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key, unsigned int keylen) { @@ -90,62 +81,28 @@ int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize) } EXPORT_SYMBOL_GPL(crypto_aead_setauthsize); -static inline int crypto_aead_errstat(struct crypto_istat_aead *istat, int err) -{ - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&istat->err_cnt); - - return err; -} - int crypto_aead_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); - struct aead_alg *alg = crypto_aead_alg(aead); - struct crypto_istat_aead *istat; - int ret; - - istat = aead_get_stat(alg); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - atomic64_inc(&istat->encrypt_cnt); - atomic64_add(req->cryptlen, &istat->encrypt_tlen); - } if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else - ret = alg->encrypt(req); + return -ENOKEY; - return crypto_aead_errstat(istat, ret); + return crypto_aead_alg(aead)->encrypt(req); } EXPORT_SYMBOL_GPL(crypto_aead_encrypt); int crypto_aead_decrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); - struct aead_alg *alg = crypto_aead_alg(aead); - struct crypto_istat_aead *istat; - int ret; - - istat = aead_get_stat(alg); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - atomic64_inc(&istat->encrypt_cnt); - atomic64_add(req->cryptlen, &istat->encrypt_tlen); - } if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else if (req->cryptlen < crypto_aead_authsize(aead)) - ret = -EINVAL; - else - ret = alg->decrypt(req); + return -ENOKEY; + + if (req->cryptlen < crypto_aead_authsize(aead)) + return -EINVAL; - return crypto_aead_errstat(istat, ret); + return crypto_aead_alg(aead)->decrypt(req); } EXPORT_SYMBOL_GPL(crypto_aead_decrypt); @@ -215,26 +172,6 @@ static void crypto_aead_free_instance(struct crypto_instance *inst) aead->free(aead); } -static int __maybe_unused crypto_aead_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - struct aead_alg *aead = container_of(alg, struct aead_alg, base); - struct crypto_istat_aead *istat = aead_get_stat(aead); - struct crypto_stat_aead raead; - - memset(&raead, 0, sizeof(raead)); - - strscpy(raead.type, "aead", sizeof(raead.type)); - - raead.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt); - raead.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen); - raead.stat_decrypt_cnt = atomic64_read(&istat->decrypt_cnt); - raead.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen); - raead.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_AEAD, sizeof(raead), &raead); -} - static const struct crypto_type crypto_aead_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_aead_init_tfm, @@ -244,9 +181,6 @@ static const struct crypto_type crypto_aead_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_aead_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_aead_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, @@ -277,7 +211,6 @@ EXPORT_SYMBOL_GPL(crypto_has_aead); static int aead_prepare_alg(struct aead_alg *alg) { - struct crypto_istat_aead *istat = aead_get_stat(alg); struct crypto_alg *base = &alg->base; if (max3(alg->maxauthsize, alg->ivsize, alg->chunksize) > @@ -291,9 +224,6 @@ static int aead_prepare_alg(struct aead_alg *alg) base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_AEAD; - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); - return 0; } diff --git a/crypto/ahash.c b/crypto/ahash.c index 0ac83f7f701d..bcd9de009a91 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -27,22 +27,6 @@ #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e -static inline struct crypto_istat_hash *ahash_get_stat(struct ahash_alg *alg) -{ - return hash_get_stat(&alg->halg); -} - -static inline int crypto_ahash_errstat(struct ahash_alg *alg, int err) -{ - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&ahash_get_stat(alg)->err_cnt); - - return err; -} - /* * For an ahash tfm that is using an shash algorithm (instead of an ahash * algorithm), this returns the underlying shash tfm. @@ -344,75 +328,47 @@ static void ahash_restore_req(struct ahash_request *req, int err) int crypto_ahash_update(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct ahash_alg *alg; if (likely(tfm->using_shash)) return shash_ahash_update(req, ahash_request_ctx(req)); - alg = crypto_ahash_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_add(req->nbytes, &ahash_get_stat(alg)->hash_tlen); - return crypto_ahash_errstat(alg, alg->update(req)); + return crypto_ahash_alg(tfm)->update(req); } EXPORT_SYMBOL_GPL(crypto_ahash_update); int crypto_ahash_final(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct ahash_alg *alg; if (likely(tfm->using_shash)) return crypto_shash_final(ahash_request_ctx(req), req->result); - alg = crypto_ahash_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&ahash_get_stat(alg)->hash_cnt); - return crypto_ahash_errstat(alg, alg->final(req)); + return crypto_ahash_alg(tfm)->final(req); } EXPORT_SYMBOL_GPL(crypto_ahash_final); int crypto_ahash_finup(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct ahash_alg *alg; if (likely(tfm->using_shash)) return shash_ahash_finup(req, ahash_request_ctx(req)); - alg = crypto_ahash_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_hash *istat = ahash_get_stat(alg); - - atomic64_inc(&istat->hash_cnt); - atomic64_add(req->nbytes, &istat->hash_tlen); - } - return crypto_ahash_errstat(alg, alg->finup(req)); + return crypto_ahash_alg(tfm)->finup(req); } EXPORT_SYMBOL_GPL(crypto_ahash_finup); int crypto_ahash_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct ahash_alg *alg; - int err; if (likely(tfm->using_shash)) return shash_ahash_digest(req, prepare_shash_desc(req, tfm)); - alg = crypto_ahash_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_hash *istat = ahash_get_stat(alg); - - atomic64_inc(&istat->hash_cnt); - atomic64_add(req->nbytes, &istat->hash_tlen); - } - if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - err = -ENOKEY; - else - err = alg->digest(req); + return -ENOKEY; - return crypto_ahash_errstat(alg, err); + return crypto_ahash_alg(tfm)->digest(req); } EXPORT_SYMBOL_GPL(crypto_ahash_digest); @@ -571,12 +527,6 @@ static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg) __crypto_hash_alg_common(alg)->digestsize); } -static int __maybe_unused crypto_ahash_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - return crypto_hash_report_stat(skb, alg, "ahash"); -} - static const struct crypto_type crypto_ahash_type = { .extsize = crypto_ahash_extsize, .init_tfm = crypto_ahash_init_tfm, @@ -586,9 +536,6 @@ static const struct crypto_type crypto_ahash_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_ahash_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_ahash_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_AHASH_MASK, diff --git a/crypto/akcipher.c b/crypto/akcipher.c index 52813f0b19e4..e0ff5f4dda6d 100644 --- a/crypto/akcipher.c +++ b/crypto/akcipher.c @@ -70,30 +70,6 @@ static void crypto_akcipher_free_instance(struct crypto_instance *inst) akcipher->free(akcipher); } -static int __maybe_unused crypto_akcipher_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - struct akcipher_alg *akcipher = __crypto_akcipher_alg(alg); - struct crypto_istat_akcipher *istat; - struct crypto_stat_akcipher rakcipher; - - istat = akcipher_get_stat(akcipher); - - memset(&rakcipher, 0, sizeof(rakcipher)); - - strscpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); - rakcipher.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt); - rakcipher.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen); - rakcipher.stat_decrypt_cnt = atomic64_read(&istat->decrypt_cnt); - rakcipher.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen); - rakcipher.stat_sign_cnt = atomic64_read(&istat->sign_cnt); - rakcipher.stat_verify_cnt = atomic64_read(&istat->verify_cnt); - rakcipher.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_AKCIPHER, - sizeof(rakcipher), &rakcipher); -} - static const struct crypto_type crypto_akcipher_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_akcipher_init_tfm, @@ -103,9 +79,6 @@ static const struct crypto_type crypto_akcipher_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_akcipher_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_akcipher_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_AHASH_MASK, @@ -131,15 +104,11 @@ EXPORT_SYMBOL_GPL(crypto_alloc_akcipher); static void akcipher_prepare_alg(struct akcipher_alg *alg) { - struct crypto_istat_akcipher *istat = akcipher_get_stat(alg); struct crypto_alg *base = &alg->base; base->cra_type = &crypto_akcipher_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); } static int akcipher_default_op(struct akcipher_request *req) diff --git a/crypto/compress.h b/crypto/compress.h index 19f65516d699..c3cedfb5e606 100644 --- a/crypto/compress.h +++ b/crypto/compress.h @@ -13,14 +13,11 @@ struct acomp_req; struct comp_alg_common; -struct sk_buff; int crypto_init_scomp_ops_async(struct crypto_tfm *tfm); struct acomp_req *crypto_acomp_scomp_alloc_ctx(struct acomp_req *req); void crypto_acomp_scomp_free_ctx(struct acomp_req *req); -int crypto_acomp_report_stat(struct sk_buff *skb, struct crypto_alg *alg); - void comp_prepare_alg(struct comp_alg_common *alg); #endif /* _LOCAL_CRYPTO_COMPRESS_H */ diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c new file mode 100644 index 000000000000..6c571834e86a --- /dev/null +++ b/crypto/crypto_user.c @@ -0,0 +1,522 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Crypto user configuration API. + * + * Copyright (C) 2011 secunet Security Networks AG + * Copyright (C) 2011 Steffen Klassert + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) + +static DEFINE_MUTEX(crypto_cfg_mutex); + +struct crypto_dump_info { + struct sk_buff *in_skb; + struct sk_buff *out_skb; + u32 nlmsg_seq; + u16 nlmsg_flags; +}; + +static struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact) +{ + struct crypto_alg *q, *alg = NULL; + + down_read(&crypto_alg_sem); + + list_for_each_entry(q, &crypto_alg_list, cra_list) { + int match = 0; + + if (crypto_is_larval(q)) + continue; + + if ((q->cra_flags ^ p->cru_type) & p->cru_mask) + continue; + + if (strlen(p->cru_driver_name)) + match = !strcmp(q->cra_driver_name, + p->cru_driver_name); + else if (!exact) + match = !strcmp(q->cra_name, p->cru_name); + + if (!match) + continue; + + if (unlikely(!crypto_mod_get(q))) + continue; + + alg = q; + break; + } + + up_read(&crypto_alg_sem); + + return alg; +} + +static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_cipher rcipher; + + memset(&rcipher, 0, sizeof(rcipher)); + + strscpy(rcipher.type, "cipher", sizeof(rcipher.type)); + + rcipher.blocksize = alg->cra_blocksize; + rcipher.min_keysize = alg->cra_cipher.cia_min_keysize; + rcipher.max_keysize = alg->cra_cipher.cia_max_keysize; + + return nla_put(skb, CRYPTOCFGA_REPORT_CIPHER, + sizeof(rcipher), &rcipher); +} + +static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_comp rcomp; + + memset(&rcomp, 0, sizeof(rcomp)); + + strscpy(rcomp.type, "compression", sizeof(rcomp.type)); + + return nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, sizeof(rcomp), &rcomp); +} + +static int crypto_report_one(struct crypto_alg *alg, + struct crypto_user_alg *ualg, struct sk_buff *skb) +{ + memset(ualg, 0, sizeof(*ualg)); + + strscpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); + strscpy(ualg->cru_driver_name, alg->cra_driver_name, + sizeof(ualg->cru_driver_name)); + strscpy(ualg->cru_module_name, module_name(alg->cra_module), + sizeof(ualg->cru_module_name)); + + ualg->cru_type = 0; + ualg->cru_mask = 0; + ualg->cru_flags = alg->cra_flags; + ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); + + if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) + goto nla_put_failure; + if (alg->cra_flags & CRYPTO_ALG_LARVAL) { + struct crypto_report_larval rl; + + memset(&rl, 0, sizeof(rl)); + strscpy(rl.type, "larval", sizeof(rl.type)); + if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL, sizeof(rl), &rl)) + goto nla_put_failure; + goto out; + } + + if (alg->cra_type && alg->cra_type->report) { + if (alg->cra_type->report(skb, alg)) + goto nla_put_failure; + + goto out; + } + + switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { + case CRYPTO_ALG_TYPE_CIPHER: + if (crypto_report_cipher(skb, alg)) + goto nla_put_failure; + + break; + case CRYPTO_ALG_TYPE_COMPRESS: + if (crypto_report_comp(skb, alg)) + goto nla_put_failure; + + break; + } + +out: + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_alg(struct crypto_alg *alg, + struct crypto_dump_info *info) +{ + struct sk_buff *in_skb = info->in_skb; + struct sk_buff *skb = info->out_skb; + struct nlmsghdr *nlh; + struct crypto_user_alg *ualg; + int err = 0; + + nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, + CRYPTO_MSG_GETALG, sizeof(*ualg), info->nlmsg_flags); + if (!nlh) { + err = -EMSGSIZE; + goto out; + } + + ualg = nlmsg_data(nlh); + + err = crypto_report_one(alg, ualg, skb); + if (err) { + nlmsg_cancel(skb, nlh); + goto out; + } + + nlmsg_end(skb, nlh); + +out: + return err; +} + +static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, + struct nlattr **attrs) +{ + struct net *net = sock_net(in_skb->sk); + struct crypto_user_alg *p = nlmsg_data(in_nlh); + struct crypto_alg *alg; + struct sk_buff *skb; + struct crypto_dump_info info; + int err; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 0); + if (!alg) + return -ENOENT; + + err = -ENOMEM; + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + goto drop_alg; + + info.in_skb = in_skb; + info.out_skb = skb; + info.nlmsg_seq = in_nlh->nlmsg_seq; + info.nlmsg_flags = 0; + + err = crypto_report_alg(alg, &info); + +drop_alg: + crypto_mod_put(alg); + + if (err) { + kfree_skb(skb); + return err; + } + + return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid); +} + +static int crypto_dump_report(struct sk_buff *skb, struct netlink_callback *cb) +{ + const size_t start_pos = cb->args[0]; + size_t pos = 0; + struct crypto_dump_info info; + struct crypto_alg *alg; + int res; + + info.in_skb = cb->skb; + info.out_skb = skb; + info.nlmsg_seq = cb->nlh->nlmsg_seq; + info.nlmsg_flags = NLM_F_MULTI; + + down_read(&crypto_alg_sem); + list_for_each_entry(alg, &crypto_alg_list, cra_list) { + if (pos >= start_pos) { + res = crypto_report_alg(alg, &info); + if (res == -EMSGSIZE) + break; + if (res) + goto out; + } + pos++; + } + cb->args[0] = pos; + res = skb->len; +out: + up_read(&crypto_alg_sem); + return res; +} + +static int crypto_dump_report_done(struct netlink_callback *cb) +{ + return 0; +} + +static int crypto_update_alg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + struct crypto_alg *alg; + struct crypto_user_alg *p = nlmsg_data(nlh); + struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; + LIST_HEAD(list); + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + if (priority && !strlen(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 1); + if (!alg) + return -ENOENT; + + down_write(&crypto_alg_sem); + + crypto_remove_spawns(alg, &list, NULL); + + if (priority) + alg->cra_priority = nla_get_u32(priority); + + up_write(&crypto_alg_sem); + + crypto_mod_put(alg); + crypto_remove_final(&list); + + return 0; +} + +static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + struct crypto_alg *alg; + struct crypto_user_alg *p = nlmsg_data(nlh); + int err; + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 1); + if (!alg) + return -ENOENT; + + /* We can not unregister core algorithms such as aes-generic. + * We would loose the reference in the crypto_alg_list to this algorithm + * if we try to unregister. Unregistering such an algorithm without + * removing the module is not possible, so we restrict to crypto + * instances that are build from templates. */ + err = -EINVAL; + if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE)) + goto drop_alg; + + err = -EBUSY; + if (refcount_read(&alg->cra_refcnt) > 2) + goto drop_alg; + + crypto_unregister_instance((struct crypto_instance *)alg); + err = 0; + +drop_alg: + crypto_mod_put(alg); + return err; +} + +static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + int exact = 0; + const char *name; + struct crypto_alg *alg; + struct crypto_user_alg *p = nlmsg_data(nlh); + struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + if (strlen(p->cru_driver_name)) + exact = 1; + + if (priority && !exact) + return -EINVAL; + + alg = crypto_alg_match(p, exact); + if (alg) { + crypto_mod_put(alg); + return -EEXIST; + } + + if (strlen(p->cru_driver_name)) + name = p->cru_driver_name; + else + name = p->cru_name; + + alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask); + if (IS_ERR(alg)) + return PTR_ERR(alg); + + down_write(&crypto_alg_sem); + + if (priority) + alg->cra_priority = nla_get_u32(priority); + + up_write(&crypto_alg_sem); + + crypto_mod_put(alg); + + return 0; +} + +static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + return crypto_del_default_rng(); +} + +static int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, + struct nlattr **attrs) +{ + /* No longer supported */ + return -ENOTSUPP; +} + +#define MSGSIZE(type) sizeof(struct type) + +static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { + [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, + [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), +}; + +static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = { + [CRYPTOCFGA_PRIORITY_VAL] = { .type = NLA_U32}, +}; + +#undef MSGSIZE + +static const struct crypto_link { + int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **); + int (*dump)(struct sk_buff *, struct netlink_callback *); + int (*done)(struct netlink_callback *); +} crypto_dispatch[CRYPTO_NR_MSGTYPES] = { + [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = { .doit = crypto_add_alg}, + [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = { .doit = crypto_del_alg}, + [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = { .doit = crypto_update_alg}, + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = { .doit = crypto_report, + .dump = crypto_dump_report, + .done = crypto_dump_report_done}, + [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = { .doit = crypto_del_rng }, + [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = { .doit = crypto_reportstat}, +}; + +static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *attrs[CRYPTOCFGA_MAX+1]; + const struct crypto_link *link; + int type, err; + + type = nlh->nlmsg_type; + if (type > CRYPTO_MSG_MAX) + return -EINVAL; + + type -= CRYPTO_MSG_BASE; + link = &crypto_dispatch[type]; + + if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && + (nlh->nlmsg_flags & NLM_F_DUMP))) { + struct crypto_alg *alg; + unsigned long dump_alloc = 0; + + if (link->dump == NULL) + return -EINVAL; + + down_read(&crypto_alg_sem); + list_for_each_entry(alg, &crypto_alg_list, cra_list) + dump_alloc += CRYPTO_REPORT_MAXSIZE; + up_read(&crypto_alg_sem); + + { + struct netlink_dump_control c = { + .dump = link->dump, + .done = link->done, + .min_dump_alloc = min(dump_alloc, 65535UL), + }; + err = netlink_dump_start(net->crypto_nlsk, skb, nlh, &c); + } + + return err; + } + + err = nlmsg_parse_deprecated(nlh, crypto_msg_min[type], attrs, + CRYPTOCFGA_MAX, crypto_policy, extack); + if (err < 0) + return err; + + if (link->doit == NULL) + return -EINVAL; + + return link->doit(skb, nlh, attrs); +} + +static void crypto_netlink_rcv(struct sk_buff *skb) +{ + mutex_lock(&crypto_cfg_mutex); + netlink_rcv_skb(skb, &crypto_user_rcv_msg); + mutex_unlock(&crypto_cfg_mutex); +} + +static int __net_init crypto_netlink_init(struct net *net) +{ + struct netlink_kernel_cfg cfg = { + .input = crypto_netlink_rcv, + }; + + net->crypto_nlsk = netlink_kernel_create(net, NETLINK_CRYPTO, &cfg); + return net->crypto_nlsk == NULL ? -ENOMEM : 0; +} + +static void __net_exit crypto_netlink_exit(struct net *net) +{ + netlink_kernel_release(net->crypto_nlsk); + net->crypto_nlsk = NULL; +} + +static struct pernet_operations crypto_netlink_net_ops = { + .init = crypto_netlink_init, + .exit = crypto_netlink_exit, +}; + +static int __init crypto_user_init(void) +{ + return register_pernet_subsys(&crypto_netlink_net_ops); +} + +static void __exit crypto_user_exit(void) +{ + unregister_pernet_subsys(&crypto_netlink_net_ops); +} + +module_init(crypto_user_init); +module_exit(crypto_user_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Steffen Klassert "); +MODULE_DESCRIPTION("Crypto userspace configuration API"); +MODULE_ALIAS("net-pf-16-proto-21"); diff --git a/crypto/crypto_user_base.c b/crypto/crypto_user_base.c deleted file mode 100644 index 3fa20f12989f..000000000000 --- a/crypto/crypto_user_base.c +++ /dev/null @@ -1,516 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Crypto user configuration API. - * - * Copyright (C) 2011 secunet Security Networks AG - * Copyright (C) 2011 Steffen Klassert - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" - -#define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) - -static DEFINE_MUTEX(crypto_cfg_mutex); - -struct crypto_dump_info { - struct sk_buff *in_skb; - struct sk_buff *out_skb; - u32 nlmsg_seq; - u16 nlmsg_flags; -}; - -struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact) -{ - struct crypto_alg *q, *alg = NULL; - - down_read(&crypto_alg_sem); - - list_for_each_entry(q, &crypto_alg_list, cra_list) { - int match = 0; - - if (crypto_is_larval(q)) - continue; - - if ((q->cra_flags ^ p->cru_type) & p->cru_mask) - continue; - - if (strlen(p->cru_driver_name)) - match = !strcmp(q->cra_driver_name, - p->cru_driver_name); - else if (!exact) - match = !strcmp(q->cra_name, p->cru_name); - - if (!match) - continue; - - if (unlikely(!crypto_mod_get(q))) - continue; - - alg = q; - break; - } - - up_read(&crypto_alg_sem); - - return alg; -} - -static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_cipher rcipher; - - memset(&rcipher, 0, sizeof(rcipher)); - - strscpy(rcipher.type, "cipher", sizeof(rcipher.type)); - - rcipher.blocksize = alg->cra_blocksize; - rcipher.min_keysize = alg->cra_cipher.cia_min_keysize; - rcipher.max_keysize = alg->cra_cipher.cia_max_keysize; - - return nla_put(skb, CRYPTOCFGA_REPORT_CIPHER, - sizeof(rcipher), &rcipher); -} - -static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_comp rcomp; - - memset(&rcomp, 0, sizeof(rcomp)); - - strscpy(rcomp.type, "compression", sizeof(rcomp.type)); - - return nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, sizeof(rcomp), &rcomp); -} - -static int crypto_report_one(struct crypto_alg *alg, - struct crypto_user_alg *ualg, struct sk_buff *skb) -{ - memset(ualg, 0, sizeof(*ualg)); - - strscpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); - strscpy(ualg->cru_driver_name, alg->cra_driver_name, - sizeof(ualg->cru_driver_name)); - strscpy(ualg->cru_module_name, module_name(alg->cra_module), - sizeof(ualg->cru_module_name)); - - ualg->cru_type = 0; - ualg->cru_mask = 0; - ualg->cru_flags = alg->cra_flags; - ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); - - if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) - goto nla_put_failure; - if (alg->cra_flags & CRYPTO_ALG_LARVAL) { - struct crypto_report_larval rl; - - memset(&rl, 0, sizeof(rl)); - strscpy(rl.type, "larval", sizeof(rl.type)); - if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL, sizeof(rl), &rl)) - goto nla_put_failure; - goto out; - } - - if (alg->cra_type && alg->cra_type->report) { - if (alg->cra_type->report(skb, alg)) - goto nla_put_failure; - - goto out; - } - - switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { - case CRYPTO_ALG_TYPE_CIPHER: - if (crypto_report_cipher(skb, alg)) - goto nla_put_failure; - - break; - case CRYPTO_ALG_TYPE_COMPRESS: - if (crypto_report_comp(skb, alg)) - goto nla_put_failure; - - break; - } - -out: - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_alg(struct crypto_alg *alg, - struct crypto_dump_info *info) -{ - struct sk_buff *in_skb = info->in_skb; - struct sk_buff *skb = info->out_skb; - struct nlmsghdr *nlh; - struct crypto_user_alg *ualg; - int err = 0; - - nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, - CRYPTO_MSG_GETALG, sizeof(*ualg), info->nlmsg_flags); - if (!nlh) { - err = -EMSGSIZE; - goto out; - } - - ualg = nlmsg_data(nlh); - - err = crypto_report_one(alg, ualg, skb); - if (err) { - nlmsg_cancel(skb, nlh); - goto out; - } - - nlmsg_end(skb, nlh); - -out: - return err; -} - -static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, - struct nlattr **attrs) -{ - struct net *net = sock_net(in_skb->sk); - struct crypto_user_alg *p = nlmsg_data(in_nlh); - struct crypto_alg *alg; - struct sk_buff *skb; - struct crypto_dump_info info; - int err; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 0); - if (!alg) - return -ENOENT; - - err = -ENOMEM; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - goto drop_alg; - - info.in_skb = in_skb; - info.out_skb = skb; - info.nlmsg_seq = in_nlh->nlmsg_seq; - info.nlmsg_flags = 0; - - err = crypto_report_alg(alg, &info); - -drop_alg: - crypto_mod_put(alg); - - if (err) { - kfree_skb(skb); - return err; - } - - return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid); -} - -static int crypto_dump_report(struct sk_buff *skb, struct netlink_callback *cb) -{ - const size_t start_pos = cb->args[0]; - size_t pos = 0; - struct crypto_dump_info info; - struct crypto_alg *alg; - int res; - - info.in_skb = cb->skb; - info.out_skb = skb; - info.nlmsg_seq = cb->nlh->nlmsg_seq; - info.nlmsg_flags = NLM_F_MULTI; - - down_read(&crypto_alg_sem); - list_for_each_entry(alg, &crypto_alg_list, cra_list) { - if (pos >= start_pos) { - res = crypto_report_alg(alg, &info); - if (res == -EMSGSIZE) - break; - if (res) - goto out; - } - pos++; - } - cb->args[0] = pos; - res = skb->len; -out: - up_read(&crypto_alg_sem); - return res; -} - -static int crypto_dump_report_done(struct netlink_callback *cb) -{ - return 0; -} - -static int crypto_update_alg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - struct crypto_alg *alg; - struct crypto_user_alg *p = nlmsg_data(nlh); - struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; - LIST_HEAD(list); - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - if (priority && !strlen(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 1); - if (!alg) - return -ENOENT; - - down_write(&crypto_alg_sem); - - crypto_remove_spawns(alg, &list, NULL); - - if (priority) - alg->cra_priority = nla_get_u32(priority); - - up_write(&crypto_alg_sem); - - crypto_mod_put(alg); - crypto_remove_final(&list); - - return 0; -} - -static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - struct crypto_alg *alg; - struct crypto_user_alg *p = nlmsg_data(nlh); - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 1); - if (!alg) - return -ENOENT; - - /* We can not unregister core algorithms such as aes-generic. - * We would loose the reference in the crypto_alg_list to this algorithm - * if we try to unregister. Unregistering such an algorithm without - * removing the module is not possible, so we restrict to crypto - * instances that are build from templates. */ - err = -EINVAL; - if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE)) - goto drop_alg; - - err = -EBUSY; - if (refcount_read(&alg->cra_refcnt) > 2) - goto drop_alg; - - crypto_unregister_instance((struct crypto_instance *)alg); - err = 0; - -drop_alg: - crypto_mod_put(alg); - return err; -} - -static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - int exact = 0; - const char *name; - struct crypto_alg *alg; - struct crypto_user_alg *p = nlmsg_data(nlh); - struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - if (strlen(p->cru_driver_name)) - exact = 1; - - if (priority && !exact) - return -EINVAL; - - alg = crypto_alg_match(p, exact); - if (alg) { - crypto_mod_put(alg); - return -EEXIST; - } - - if (strlen(p->cru_driver_name)) - name = p->cru_driver_name; - else - name = p->cru_name; - - alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask); - if (IS_ERR(alg)) - return PTR_ERR(alg); - - down_write(&crypto_alg_sem); - - if (priority) - alg->cra_priority = nla_get_u32(priority); - - up_write(&crypto_alg_sem); - - crypto_mod_put(alg); - - return 0; -} - -static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - return crypto_del_default_rng(); -} - -#define MSGSIZE(type) sizeof(struct type) - -static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { - [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, - [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), -}; - -static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = { - [CRYPTOCFGA_PRIORITY_VAL] = { .type = NLA_U32}, -}; - -#undef MSGSIZE - -static const struct crypto_link { - int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **); - int (*dump)(struct sk_buff *, struct netlink_callback *); - int (*done)(struct netlink_callback *); -} crypto_dispatch[CRYPTO_NR_MSGTYPES] = { - [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = { .doit = crypto_add_alg}, - [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = { .doit = crypto_del_alg}, - [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = { .doit = crypto_update_alg}, - [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = { .doit = crypto_report, - .dump = crypto_dump_report, - .done = crypto_dump_report_done}, - [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = { .doit = crypto_del_rng }, - [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = { .doit = crypto_reportstat}, -}; - -static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct nlattr *attrs[CRYPTOCFGA_MAX+1]; - const struct crypto_link *link; - int type, err; - - type = nlh->nlmsg_type; - if (type > CRYPTO_MSG_MAX) - return -EINVAL; - - type -= CRYPTO_MSG_BASE; - link = &crypto_dispatch[type]; - - if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && - (nlh->nlmsg_flags & NLM_F_DUMP))) { - struct crypto_alg *alg; - unsigned long dump_alloc = 0; - - if (link->dump == NULL) - return -EINVAL; - - down_read(&crypto_alg_sem); - list_for_each_entry(alg, &crypto_alg_list, cra_list) - dump_alloc += CRYPTO_REPORT_MAXSIZE; - up_read(&crypto_alg_sem); - - { - struct netlink_dump_control c = { - .dump = link->dump, - .done = link->done, - .min_dump_alloc = min(dump_alloc, 65535UL), - }; - err = netlink_dump_start(net->crypto_nlsk, skb, nlh, &c); - } - - return err; - } - - err = nlmsg_parse_deprecated(nlh, crypto_msg_min[type], attrs, - CRYPTOCFGA_MAX, crypto_policy, extack); - if (err < 0) - return err; - - if (link->doit == NULL) - return -EINVAL; - - return link->doit(skb, nlh, attrs); -} - -static void crypto_netlink_rcv(struct sk_buff *skb) -{ - mutex_lock(&crypto_cfg_mutex); - netlink_rcv_skb(skb, &crypto_user_rcv_msg); - mutex_unlock(&crypto_cfg_mutex); -} - -static int __net_init crypto_netlink_init(struct net *net) -{ - struct netlink_kernel_cfg cfg = { - .input = crypto_netlink_rcv, - }; - - net->crypto_nlsk = netlink_kernel_create(net, NETLINK_CRYPTO, &cfg); - return net->crypto_nlsk == NULL ? -ENOMEM : 0; -} - -static void __net_exit crypto_netlink_exit(struct net *net) -{ - netlink_kernel_release(net->crypto_nlsk); - net->crypto_nlsk = NULL; -} - -static struct pernet_operations crypto_netlink_net_ops = { - .init = crypto_netlink_init, - .exit = crypto_netlink_exit, -}; - -static int __init crypto_user_init(void) -{ - return register_pernet_subsys(&crypto_netlink_net_ops); -} - -static void __exit crypto_user_exit(void) -{ - unregister_pernet_subsys(&crypto_netlink_net_ops); -} - -module_init(crypto_user_init); -module_exit(crypto_user_exit); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Steffen Klassert "); -MODULE_DESCRIPTION("Crypto userspace configuration API"); -MODULE_ALIAS("net-pf-16-proto-21"); diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c deleted file mode 100644 index d4f3d39b5137..000000000000 --- a/crypto/crypto_user_stat.c +++ /dev/null @@ -1,176 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Crypto user configuration API. - * - * Copyright (C) 2017-2018 Corentin Labbe - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) - -struct crypto_dump_info { - struct sk_buff *in_skb; - struct sk_buff *out_skb; - u32 nlmsg_seq; - u16 nlmsg_flags; -}; - -static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_stat_cipher rcipher; - - memset(&rcipher, 0, sizeof(rcipher)); - - strscpy(rcipher.type, "cipher", sizeof(rcipher.type)); - - return nla_put(skb, CRYPTOCFGA_STAT_CIPHER, sizeof(rcipher), &rcipher); -} - -static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_stat_compress rcomp; - - memset(&rcomp, 0, sizeof(rcomp)); - - strscpy(rcomp.type, "compression", sizeof(rcomp.type)); - - return nla_put(skb, CRYPTOCFGA_STAT_COMPRESS, sizeof(rcomp), &rcomp); -} - -static int crypto_reportstat_one(struct crypto_alg *alg, - struct crypto_user_alg *ualg, - struct sk_buff *skb) -{ - memset(ualg, 0, sizeof(*ualg)); - - strscpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); - strscpy(ualg->cru_driver_name, alg->cra_driver_name, - sizeof(ualg->cru_driver_name)); - strscpy(ualg->cru_module_name, module_name(alg->cra_module), - sizeof(ualg->cru_module_name)); - - ualg->cru_type = 0; - ualg->cru_mask = 0; - ualg->cru_flags = alg->cra_flags; - ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); - - if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) - goto nla_put_failure; - if (alg->cra_flags & CRYPTO_ALG_LARVAL) { - struct crypto_stat_larval rl; - - memset(&rl, 0, sizeof(rl)); - strscpy(rl.type, "larval", sizeof(rl.type)); - if (nla_put(skb, CRYPTOCFGA_STAT_LARVAL, sizeof(rl), &rl)) - goto nla_put_failure; - goto out; - } - - if (alg->cra_type && alg->cra_type->report_stat) { - if (alg->cra_type->report_stat(skb, alg)) - goto nla_put_failure; - goto out; - } - - switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { - case CRYPTO_ALG_TYPE_CIPHER: - if (crypto_report_cipher(skb, alg)) - goto nla_put_failure; - break; - case CRYPTO_ALG_TYPE_COMPRESS: - if (crypto_report_comp(skb, alg)) - goto nla_put_failure; - break; - default: - pr_err("ERROR: Unhandled alg %d in %s\n", - alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL), - __func__); - } - -out: - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_reportstat_alg(struct crypto_alg *alg, - struct crypto_dump_info *info) -{ - struct sk_buff *in_skb = info->in_skb; - struct sk_buff *skb = info->out_skb; - struct nlmsghdr *nlh; - struct crypto_user_alg *ualg; - int err = 0; - - nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, - CRYPTO_MSG_GETSTAT, sizeof(*ualg), info->nlmsg_flags); - if (!nlh) { - err = -EMSGSIZE; - goto out; - } - - ualg = nlmsg_data(nlh); - - err = crypto_reportstat_one(alg, ualg, skb); - if (err) { - nlmsg_cancel(skb, nlh); - goto out; - } - - nlmsg_end(skb, nlh); - -out: - return err; -} - -int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, - struct nlattr **attrs) -{ - struct net *net = sock_net(in_skb->sk); - struct crypto_user_alg *p = nlmsg_data(in_nlh); - struct crypto_alg *alg; - struct sk_buff *skb; - struct crypto_dump_info info; - int err; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 0); - if (!alg) - return -ENOENT; - - err = -ENOMEM; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); - if (!skb) - goto drop_alg; - - info.in_skb = in_skb; - info.out_skb = skb; - info.nlmsg_seq = in_nlh->nlmsg_seq; - info.nlmsg_flags = 0; - - err = crypto_reportstat_alg(alg, &info); - -drop_alg: - crypto_mod_put(alg); - - if (err) { - kfree_skb(skb); - return err; - } - - return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid); -} - -MODULE_LICENSE("GPL"); diff --git a/crypto/hash.h b/crypto/hash.h index 93f6ba0df263..cf9aee07f77d 100644 --- a/crypto/hash.h +++ b/crypto/hash.h @@ -8,39 +8,9 @@ #define _LOCAL_CRYPTO_HASH_H #include -#include #include "internal.h" -static inline struct crypto_istat_hash *hash_get_stat( - struct hash_alg_common *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - -static inline int crypto_hash_report_stat(struct sk_buff *skb, - struct crypto_alg *alg, - const char *type) -{ - struct hash_alg_common *halg = __crypto_hash_alg_common(alg); - struct crypto_istat_hash *istat = hash_get_stat(halg); - struct crypto_stat_hash rhash; - - memset(&rhash, 0, sizeof(rhash)); - - strscpy(rhash.type, type, sizeof(rhash.type)); - - rhash.stat_hash_cnt = atomic64_read(&istat->hash_cnt); - rhash.stat_hash_tlen = atomic64_read(&istat->hash_tlen); - rhash.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_HASH, sizeof(rhash), &rhash); -} - extern const struct crypto_type crypto_shash_type; int hash_prepare_alg(struct hash_alg_common *alg); diff --git a/crypto/kpp.c b/crypto/kpp.c index 33d44e59387f..ecc63a1a948d 100644 --- a/crypto/kpp.c +++ b/crypto/kpp.c @@ -66,29 +66,6 @@ static void crypto_kpp_free_instance(struct crypto_instance *inst) kpp->free(kpp); } -static int __maybe_unused crypto_kpp_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - struct kpp_alg *kpp = __crypto_kpp_alg(alg); - struct crypto_istat_kpp *istat; - struct crypto_stat_kpp rkpp; - - istat = kpp_get_stat(kpp); - - memset(&rkpp, 0, sizeof(rkpp)); - - strscpy(rkpp.type, "kpp", sizeof(rkpp.type)); - - rkpp.stat_setsecret_cnt = atomic64_read(&istat->setsecret_cnt); - rkpp.stat_generate_public_key_cnt = - atomic64_read(&istat->generate_public_key_cnt); - rkpp.stat_compute_shared_secret_cnt = - atomic64_read(&istat->compute_shared_secret_cnt); - rkpp.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_KPP, sizeof(rkpp), &rkpp); -} - static const struct crypto_type crypto_kpp_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_kpp_init_tfm, @@ -98,9 +75,6 @@ static const struct crypto_type crypto_kpp_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_kpp_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_kpp_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, @@ -131,15 +105,11 @@ EXPORT_SYMBOL_GPL(crypto_has_kpp); static void kpp_prepare_alg(struct kpp_alg *alg) { - struct crypto_istat_kpp *istat = kpp_get_stat(alg); struct crypto_alg *base = &alg->base; base->cra_type = &crypto_kpp_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_KPP; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); } int crypto_register_kpp(struct kpp_alg *alg) diff --git a/crypto/lskcipher.c b/crypto/lskcipher.c index 0f1bd7dcde24..cdb4897c63e6 100644 --- a/crypto/lskcipher.c +++ b/crypto/lskcipher.c @@ -29,25 +29,6 @@ static inline struct lskcipher_alg *__crypto_lskcipher_alg( return container_of(alg, struct lskcipher_alg, co.base); } -static inline struct crypto_istat_cipher *lskcipher_get_stat( - struct lskcipher_alg *alg) -{ - return skcipher_get_stat_common(&alg->co); -} - -static inline int crypto_lskcipher_errstat(struct lskcipher_alg *alg, int err) -{ - struct crypto_istat_cipher *istat = lskcipher_get_stat(alg); - - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err) - atomic64_inc(&istat->err_cnt); - - return err; -} - static int lskcipher_setkey_unaligned(struct crypto_lskcipher *tfm, const u8 *key, unsigned int keylen) { @@ -147,20 +128,13 @@ static int crypto_lskcipher_crypt(struct crypto_lskcipher *tfm, const u8 *src, u32 flags)) { unsigned long alignmask = crypto_lskcipher_alignmask(tfm); - struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm); - int ret; if (((unsigned long)src | (unsigned long)dst | (unsigned long)iv) & - alignmask) { - ret = crypto_lskcipher_crypt_unaligned(tfm, src, dst, len, iv, - crypt); - goto out; - } + alignmask) + return crypto_lskcipher_crypt_unaligned(tfm, src, dst, len, iv, + crypt); - ret = crypt(tfm, src, dst, len, iv, CRYPTO_LSKCIPHER_FLAG_FINAL); - -out: - return crypto_lskcipher_errstat(alg, ret); + return crypt(tfm, src, dst, len, iv, CRYPTO_LSKCIPHER_FLAG_FINAL); } int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src, @@ -168,13 +142,6 @@ int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src, { struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_cipher *istat = lskcipher_get_stat(alg); - - atomic64_inc(&istat->encrypt_cnt); - atomic64_add(len, &istat->encrypt_tlen); - } - return crypto_lskcipher_crypt(tfm, src, dst, len, iv, alg->encrypt); } EXPORT_SYMBOL_GPL(crypto_lskcipher_encrypt); @@ -184,13 +151,6 @@ int crypto_lskcipher_decrypt(struct crypto_lskcipher *tfm, const u8 *src, { struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_cipher *istat = lskcipher_get_stat(alg); - - atomic64_inc(&istat->decrypt_cnt); - atomic64_add(len, &istat->decrypt_tlen); - } - return crypto_lskcipher_crypt(tfm, src, dst, len, iv, alg->decrypt); } EXPORT_SYMBOL_GPL(crypto_lskcipher_decrypt); @@ -320,28 +280,6 @@ static int __maybe_unused crypto_lskcipher_report( sizeof(rblkcipher), &rblkcipher); } -static int __maybe_unused crypto_lskcipher_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - struct lskcipher_alg *skcipher = __crypto_lskcipher_alg(alg); - struct crypto_istat_cipher *istat; - struct crypto_stat_cipher rcipher; - - istat = lskcipher_get_stat(skcipher); - - memset(&rcipher, 0, sizeof(rcipher)); - - strscpy(rcipher.type, "cipher", sizeof(rcipher.type)); - - rcipher.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt); - rcipher.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen); - rcipher.stat_decrypt_cnt = atomic64_read(&istat->decrypt_cnt); - rcipher.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen); - rcipher.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_CIPHER, sizeof(rcipher), &rcipher); -} - static const struct crypto_type crypto_lskcipher_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_lskcipher_init_tfm, @@ -351,9 +289,6 @@ static const struct crypto_type crypto_lskcipher_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_lskcipher_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_lskcipher_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, diff --git a/crypto/rng.c b/crypto/rng.c index 279dffdebf59..9d8804e46422 100644 --- a/crypto/rng.c +++ b/crypto/rng.c @@ -30,30 +30,24 @@ static int crypto_default_rng_refcnt; int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) { - struct rng_alg *alg = crypto_rng_alg(tfm); u8 *buf = NULL; int err; - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&rng_get_stat(alg)->seed_cnt); - if (!seed && slen) { buf = kmalloc(slen, GFP_KERNEL); - err = -ENOMEM; if (!buf) - goto out; + return -ENOMEM; err = get_random_bytes_wait(buf, slen); if (err) - goto free_buf; + goto out; seed = buf; } - err = alg->seed(tfm, seed, slen); -free_buf: - kfree_sensitive(buf); + err = crypto_rng_alg(tfm)->seed(tfm, seed, slen); out: - return crypto_rng_errstat(alg, err); + kfree_sensitive(buf); + return err; } EXPORT_SYMBOL_GPL(crypto_rng_reset); @@ -91,27 +85,6 @@ static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg) seq_printf(m, "seedsize : %u\n", seedsize(alg)); } -static int __maybe_unused crypto_rng_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - struct rng_alg *rng = __crypto_rng_alg(alg); - struct crypto_istat_rng *istat; - struct crypto_stat_rng rrng; - - istat = rng_get_stat(rng); - - memset(&rrng, 0, sizeof(rrng)); - - strscpy(rrng.type, "rng", sizeof(rrng.type)); - - rrng.stat_generate_cnt = atomic64_read(&istat->generate_cnt); - rrng.stat_generate_tlen = atomic64_read(&istat->generate_tlen); - rrng.stat_seed_cnt = atomic64_read(&istat->seed_cnt); - rrng.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_RNG, sizeof(rrng), &rrng); -} - static const struct crypto_type crypto_rng_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_rng_init_tfm, @@ -120,9 +93,6 @@ static const struct crypto_type crypto_rng_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_rng_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_rng_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, @@ -199,7 +169,6 @@ EXPORT_SYMBOL_GPL(crypto_del_default_rng); int crypto_register_rng(struct rng_alg *alg) { - struct crypto_istat_rng *istat = rng_get_stat(alg); struct crypto_alg *base = &alg->base; if (alg->seedsize > PAGE_SIZE / 8) @@ -209,9 +178,6 @@ int crypto_register_rng(struct rng_alg *alg) base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_RNG; - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); - return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_rng); diff --git a/crypto/scompress.c b/crypto/scompress.c index 60bbb7ea4060..1cef6bb06a81 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -270,9 +270,6 @@ static const struct crypto_type crypto_scomp_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_scomp_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_acomp_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, diff --git a/crypto/shash.c b/crypto/shash.c index c3f7f6a25280..301ab42bf849 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -16,18 +16,6 @@ #include "hash.h" -static inline struct crypto_istat_hash *shash_get_stat(struct shash_alg *alg) -{ - return hash_get_stat(&alg->halg); -} - -static inline int crypto_shash_errstat(struct shash_alg *alg, int err) -{ - if (IS_ENABLED(CONFIG_CRYPTO_STATS) && err) - atomic64_inc(&shash_get_stat(alg)->err_cnt); - return err; -} - int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { @@ -61,29 +49,13 @@ EXPORT_SYMBOL_GPL(crypto_shash_setkey); int crypto_shash_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - struct shash_alg *shash = crypto_shash_alg(desc->tfm); - int err; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_add(len, &shash_get_stat(shash)->hash_tlen); - - err = shash->update(desc, data, len); - - return crypto_shash_errstat(shash, err); + return crypto_shash_alg(desc->tfm)->update(desc, data, len); } EXPORT_SYMBOL_GPL(crypto_shash_update); int crypto_shash_final(struct shash_desc *desc, u8 *out) { - struct shash_alg *shash = crypto_shash_alg(desc->tfm); - int err; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&shash_get_stat(shash)->hash_cnt); - - err = shash->final(desc, out); - - return crypto_shash_errstat(shash, err); + return crypto_shash_alg(desc->tfm)->final(desc, out); } EXPORT_SYMBOL_GPL(crypto_shash_final); @@ -99,20 +71,7 @@ static int shash_default_finup(struct shash_desc *desc, const u8 *data, int crypto_shash_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - struct crypto_shash *tfm = desc->tfm; - struct shash_alg *shash = crypto_shash_alg(tfm); - int err; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_hash *istat = shash_get_stat(shash); - - atomic64_inc(&istat->hash_cnt); - atomic64_add(len, &istat->hash_tlen); - } - - err = shash->finup(desc, data, len, out); - - return crypto_shash_errstat(shash, err); + return crypto_shash_alg(desc->tfm)->finup(desc, data, len, out); } EXPORT_SYMBOL_GPL(crypto_shash_finup); @@ -129,22 +88,11 @@ int crypto_shash_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct crypto_shash *tfm = desc->tfm; - struct shash_alg *shash = crypto_shash_alg(tfm); - int err; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_hash *istat = shash_get_stat(shash); - - atomic64_inc(&istat->hash_cnt); - atomic64_add(len, &istat->hash_tlen); - } if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - err = -ENOKEY; - else - err = shash->digest(desc, data, len, out); + return -ENOKEY; - return crypto_shash_errstat(shash, err); + return crypto_shash_alg(tfm)->digest(desc, data, len, out); } EXPORT_SYMBOL_GPL(crypto_shash_digest); @@ -265,12 +213,6 @@ static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg) seq_printf(m, "digestsize : %u\n", salg->digestsize); } -static int __maybe_unused crypto_shash_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - return crypto_hash_report_stat(skb, alg, "shash"); -} - const struct crypto_type crypto_shash_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_shash_init_tfm, @@ -280,9 +222,6 @@ const struct crypto_type crypto_shash_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_shash_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_shash_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, @@ -350,7 +289,6 @@ EXPORT_SYMBOL_GPL(crypto_clone_shash); int hash_prepare_alg(struct hash_alg_common *alg) { - struct crypto_istat_hash *istat = hash_get_stat(alg); struct crypto_alg *base = &alg->base; if (alg->digestsize > HASH_MAX_DIGESTSIZE) @@ -362,9 +300,6 @@ int hash_prepare_alg(struct hash_alg_common *alg) base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); - return 0; } diff --git a/crypto/sig.c b/crypto/sig.c index 224c47019297..7645bedf3a1f 100644 --- a/crypto/sig.c +++ b/crypto/sig.c @@ -45,16 +45,6 @@ static int __maybe_unused crypto_sig_report(struct sk_buff *skb, return nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER, sizeof(rsig), &rsig); } -static int __maybe_unused crypto_sig_report_stat(struct sk_buff *skb, - struct crypto_alg *alg) -{ - struct crypto_stat_akcipher rsig = {}; - - strscpy(rsig.type, "sig", sizeof(rsig.type)); - - return nla_put(skb, CRYPTOCFGA_STAT_AKCIPHER, sizeof(rsig), &rsig); -} - static const struct crypto_type crypto_sig_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_sig_init_tfm, @@ -63,9 +53,6 @@ static const struct crypto_type crypto_sig_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_sig_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_sig_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_SIG_MASK, diff --git a/crypto/skcipher.c b/crypto/skcipher.c index bc70e159d27d..ceed7f33a67b 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -89,25 +89,6 @@ static inline struct skcipher_alg *__crypto_skcipher_alg( return container_of(alg, struct skcipher_alg, base); } -static inline struct crypto_istat_cipher *skcipher_get_stat( - struct skcipher_alg *alg) -{ - return skcipher_get_stat_common(&alg->co); -} - -static inline int crypto_skcipher_errstat(struct skcipher_alg *alg, int err) -{ - struct crypto_istat_cipher *istat = skcipher_get_stat(alg); - - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&istat->err_cnt); - - return err; -} - static int skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize) { u8 *addr; @@ -654,23 +635,12 @@ int crypto_skcipher_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); - int ret; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_cipher *istat = skcipher_get_stat(alg); - - atomic64_inc(&istat->encrypt_cnt); - atomic64_add(req->cryptlen, &istat->encrypt_tlen); - } if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else if (alg->co.base.cra_type != &crypto_skcipher_type) - ret = crypto_lskcipher_encrypt_sg(req); - else - ret = alg->encrypt(req); - - return crypto_skcipher_errstat(alg, ret); + return -ENOKEY; + if (alg->co.base.cra_type != &crypto_skcipher_type) + return crypto_lskcipher_encrypt_sg(req); + return alg->encrypt(req); } EXPORT_SYMBOL_GPL(crypto_skcipher_encrypt); @@ -678,23 +648,12 @@ int crypto_skcipher_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); - int ret; - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_cipher *istat = skcipher_get_stat(alg); - - atomic64_inc(&istat->decrypt_cnt); - atomic64_add(req->cryptlen, &istat->decrypt_tlen); - } if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else if (alg->co.base.cra_type != &crypto_skcipher_type) - ret = crypto_lskcipher_decrypt_sg(req); - else - ret = alg->decrypt(req); - - return crypto_skcipher_errstat(alg, ret); + return -ENOKEY; + if (alg->co.base.cra_type != &crypto_skcipher_type) + return crypto_lskcipher_decrypt_sg(req); + return alg->decrypt(req); } EXPORT_SYMBOL_GPL(crypto_skcipher_decrypt); @@ -846,28 +805,6 @@ static int __maybe_unused crypto_skcipher_report( sizeof(rblkcipher), &rblkcipher); } -static int __maybe_unused crypto_skcipher_report_stat( - struct sk_buff *skb, struct crypto_alg *alg) -{ - struct skcipher_alg *skcipher = __crypto_skcipher_alg(alg); - struct crypto_istat_cipher *istat; - struct crypto_stat_cipher rcipher; - - istat = skcipher_get_stat(skcipher); - - memset(&rcipher, 0, sizeof(rcipher)); - - strscpy(rcipher.type, "cipher", sizeof(rcipher.type)); - - rcipher.stat_encrypt_cnt = atomic64_read(&istat->encrypt_cnt); - rcipher.stat_encrypt_tlen = atomic64_read(&istat->encrypt_tlen); - rcipher.stat_decrypt_cnt = atomic64_read(&istat->decrypt_cnt); - rcipher.stat_decrypt_tlen = atomic64_read(&istat->decrypt_tlen); - rcipher.stat_err_cnt = atomic64_read(&istat->err_cnt); - - return nla_put(skb, CRYPTOCFGA_STAT_CIPHER, sizeof(rcipher), &rcipher); -} - static const struct crypto_type crypto_skcipher_type = { .extsize = crypto_skcipher_extsize, .init_tfm = crypto_skcipher_init_tfm, @@ -877,9 +814,6 @@ static const struct crypto_type crypto_skcipher_type = { #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_skcipher_report, -#endif -#ifdef CONFIG_CRYPTO_STATS - .report_stat = crypto_skcipher_report_stat, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_SKCIPHER_MASK, @@ -935,7 +869,6 @@ EXPORT_SYMBOL_GPL(crypto_has_skcipher); int skcipher_prepare_alg_common(struct skcipher_alg_common *alg) { - struct crypto_istat_cipher *istat = skcipher_get_stat_common(alg); struct crypto_alg *base = &alg->base; if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8 || @@ -948,9 +881,6 @@ int skcipher_prepare_alg_common(struct skcipher_alg_common *alg) base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - memset(istat, 0, sizeof(*istat)); - return 0; } diff --git a/crypto/skcipher.h b/crypto/skcipher.h index 16c9484360da..703651367dd8 100644 --- a/crypto/skcipher.h +++ b/crypto/skcipher.h @@ -10,16 +10,6 @@ #include #include "internal.h" -static inline struct crypto_istat_cipher *skcipher_get_stat_common( - struct skcipher_alg_common *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - int crypto_lskcipher_encrypt_sg(struct skcipher_request *req); int crypto_lskcipher_decrypt_sg(struct skcipher_request *req); int crypto_init_lskcipher_ops_sg(struct crypto_tfm *tfm); diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h index 80e243611fe2..54937b615239 100644 --- a/include/crypto/acompress.h +++ b/include/crypto/acompress.h @@ -56,31 +56,7 @@ struct crypto_acomp { struct crypto_tfm base; }; -/* - * struct crypto_istat_compress - statistics for compress algorithm - * @compress_cnt: number of compress requests - * @compress_tlen: total data size handled by compress requests - * @decompress_cnt: number of decompress requests - * @decompress_tlen: total data size handled by decompress requests - * @err_cnt: number of error for compress requests - */ -struct crypto_istat_compress { - atomic64_t compress_cnt; - atomic64_t compress_tlen; - atomic64_t decompress_cnt; - atomic64_t decompress_tlen; - atomic64_t err_cnt; -}; - -#ifdef CONFIG_CRYPTO_STATS -#define COMP_ALG_COMMON_STATS struct crypto_istat_compress stat; -#else -#define COMP_ALG_COMMON_STATS -#endif - #define COMP_ALG_COMMON { \ - COMP_ALG_COMMON_STATS \ - \ struct crypto_alg base; \ } struct comp_alg_common COMP_ALG_COMMON; @@ -261,27 +237,6 @@ static inline void acomp_request_set_params(struct acomp_req *req, req->flags |= CRYPTO_ACOMP_ALLOC_OUTPUT; } -static inline struct crypto_istat_compress *comp_get_stat( - struct comp_alg_common *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - -static inline int crypto_comp_errstat(struct comp_alg_common *alg, int err) -{ - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&comp_get_stat(alg)->err_cnt); - - return err; -} - /** * crypto_acomp_compress() -- Invoke asynchronous compress operation * @@ -293,19 +248,7 @@ static inline int crypto_comp_errstat(struct comp_alg_common *alg, int err) */ static inline int crypto_acomp_compress(struct acomp_req *req) { - struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); - struct comp_alg_common *alg; - - alg = crypto_comp_alg_common(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_compress *istat = comp_get_stat(alg); - - atomic64_inc(&istat->compress_cnt); - atomic64_add(req->slen, &istat->compress_tlen); - } - - return crypto_comp_errstat(alg, tfm->compress(req)); + return crypto_acomp_reqtfm(req)->compress(req); } /** @@ -319,19 +262,7 @@ static inline int crypto_acomp_compress(struct acomp_req *req) */ static inline int crypto_acomp_decompress(struct acomp_req *req) { - struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); - struct comp_alg_common *alg; - - alg = crypto_comp_alg_common(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_compress *istat = comp_get_stat(alg); - - atomic64_inc(&istat->decompress_cnt); - atomic64_add(req->slen, &istat->decompress_tlen); - } - - return crypto_comp_errstat(alg, tfm->decompress(req)); + return crypto_acomp_reqtfm(req)->decompress(req); } #endif diff --git a/include/crypto/aead.h b/include/crypto/aead.h index 51382befbe37..0e8a41638678 100644 --- a/include/crypto/aead.h +++ b/include/crypto/aead.h @@ -101,22 +101,6 @@ struct aead_request { void *__ctx[] CRYPTO_MINALIGN_ATTR; }; -/* - * struct crypto_istat_aead - statistics for AEAD algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @err_cnt: number of error for AEAD requests - */ -struct crypto_istat_aead { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t err_cnt; -}; - /** * struct aead_alg - AEAD cipher definition * @maxauthsize: Set the maximum authentication tag size supported by the @@ -135,7 +119,6 @@ struct crypto_istat_aead { * @setkey: see struct skcipher_alg * @encrypt: see struct skcipher_alg * @decrypt: see struct skcipher_alg - * @stat: statistics for AEAD algorithm * @ivsize: see struct skcipher_alg * @chunksize: see struct skcipher_alg * @init: Initialize the cryptographic transformation object. This function @@ -162,10 +145,6 @@ struct aead_alg { int (*init)(struct crypto_aead *tfm); void (*exit)(struct crypto_aead *tfm); -#ifdef CONFIG_CRYPTO_STATS - struct crypto_istat_aead stat; -#endif - unsigned int ivsize; unsigned int maxauthsize; unsigned int chunksize; diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h index 31c111bebb68..18a10cad07aa 100644 --- a/include/crypto/akcipher.h +++ b/include/crypto/akcipher.h @@ -54,26 +54,6 @@ struct crypto_akcipher { struct crypto_tfm base; }; -/* - * struct crypto_istat_akcipher - statistics for akcipher algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @verify_cnt: number of verify operation - * @sign_cnt: number of sign requests - * @err_cnt: number of error for akcipher requests - */ -struct crypto_istat_akcipher { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t verify_cnt; - atomic64_t sign_cnt; - atomic64_t err_cnt; -}; - /** * struct akcipher_alg - generic public key algorithm * @@ -110,7 +90,6 @@ struct crypto_istat_akcipher { * @exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @init, used to remove various changes set in * @init. - * @stat: Statistics for akcipher algorithm * * @base: Common crypto API algorithm data structure */ @@ -127,10 +106,6 @@ struct akcipher_alg { int (*init)(struct crypto_akcipher *tfm); void (*exit)(struct crypto_akcipher *tfm); -#ifdef CONFIG_CRYPTO_STATS - struct crypto_istat_akcipher stat; -#endif - struct crypto_alg base; }; @@ -302,27 +277,6 @@ static inline unsigned int crypto_akcipher_maxsize(struct crypto_akcipher *tfm) return alg->max_size(tfm); } -static inline struct crypto_istat_akcipher *akcipher_get_stat( - struct akcipher_alg *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - -static inline int crypto_akcipher_errstat(struct akcipher_alg *alg, int err) -{ - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&akcipher_get_stat(alg)->err_cnt); - - return err; -} - /** * crypto_akcipher_encrypt() - Invoke public key encrypt operation * @@ -336,16 +290,8 @@ static inline int crypto_akcipher_errstat(struct akcipher_alg *alg, int err) static inline int crypto_akcipher_encrypt(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); - struct akcipher_alg *alg = crypto_akcipher_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_akcipher *istat = akcipher_get_stat(alg); - - atomic64_inc(&istat->encrypt_cnt); - atomic64_add(req->src_len, &istat->encrypt_tlen); - } - - return crypto_akcipher_errstat(alg, alg->encrypt(req)); + return crypto_akcipher_alg(tfm)->encrypt(req); } /** @@ -361,16 +307,8 @@ static inline int crypto_akcipher_encrypt(struct akcipher_request *req) static inline int crypto_akcipher_decrypt(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); - struct akcipher_alg *alg = crypto_akcipher_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_akcipher *istat = akcipher_get_stat(alg); - - atomic64_inc(&istat->decrypt_cnt); - atomic64_add(req->src_len, &istat->decrypt_tlen); - } - - return crypto_akcipher_errstat(alg, alg->decrypt(req)); + return crypto_akcipher_alg(tfm)->decrypt(req); } /** @@ -422,12 +360,8 @@ int crypto_akcipher_sync_decrypt(struct crypto_akcipher *tfm, static inline int crypto_akcipher_sign(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); - struct akcipher_alg *alg = crypto_akcipher_alg(tfm); - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&akcipher_get_stat(alg)->sign_cnt); - - return crypto_akcipher_errstat(alg, alg->sign(req)); + return crypto_akcipher_alg(tfm)->sign(req); } /** @@ -447,12 +381,8 @@ static inline int crypto_akcipher_sign(struct akcipher_request *req) static inline int crypto_akcipher_verify(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); - struct akcipher_alg *alg = crypto_akcipher_alg(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&akcipher_get_stat(alg)->verify_cnt); - return crypto_akcipher_errstat(alg, alg->verify(req)); + return crypto_akcipher_alg(tfm)->verify(req); } /** diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 7a4a71af653f..156de41ca760 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -61,9 +61,6 @@ struct crypto_type { void (*show)(struct seq_file *m, struct crypto_alg *alg); int (*report)(struct sk_buff *skb, struct crypto_alg *alg); void (*free)(struct crypto_instance *inst); -#ifdef CONFIG_CRYPTO_STATS - int (*report_stat)(struct sk_buff *skb, struct crypto_alg *alg); -#endif unsigned int type; unsigned int maskclear; diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 5d61f576cfc8..0014bdd81ab7 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -23,27 +23,8 @@ struct crypto_ahash; * crypto_unregister_shash(). */ -/* - * struct crypto_istat_hash - statistics for has algorithm - * @hash_cnt: number of hash requests - * @hash_tlen: total data size hashed - * @err_cnt: number of error for hash requests - */ -struct crypto_istat_hash { - atomic64_t hash_cnt; - atomic64_t hash_tlen; - atomic64_t err_cnt; -}; - -#ifdef CONFIG_CRYPTO_STATS -#define HASH_ALG_COMMON_STAT struct crypto_istat_hash stat; -#else -#define HASH_ALG_COMMON_STAT -#endif - /* * struct hash_alg_common - define properties of message digest - * @stat: Statistics for hash algorithm. * @digestsize: Size of the result of the transformation. A buffer of this size * must be available to the @final and @finup calls, so they can * store the resulting hash into it. For various predefined sizes, @@ -60,8 +41,6 @@ struct crypto_istat_hash { * information. */ #define HASH_ALG_COMMON { \ - HASH_ALG_COMMON_STAT \ - \ unsigned int digestsize; \ unsigned int statesize; \ \ @@ -243,7 +222,6 @@ struct shash_alg { }; }; #undef HASH_ALG_COMMON -#undef HASH_ALG_COMMON_STAT struct crypto_ahash { bool using_shash; /* Underlying algorithm is shash, not ahash */ diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h index 4ac46bafba9d..d00392d1988e 100644 --- a/include/crypto/internal/acompress.h +++ b/include/crypto/internal/acompress.h @@ -31,7 +31,6 @@ * @init. * * @reqsize: Context size for (de)compression requests - * @stat: Statistics for compress algorithm * @base: Common crypto API algorithm data structure * @calg: Cmonn algorithm data structure shared with scomp */ diff --git a/include/crypto/internal/cryptouser.h b/include/crypto/internal/cryptouser.h deleted file mode 100644 index fd54074332f5..000000000000 --- a/include/crypto/internal/cryptouser.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include -#include - -struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact); - -#ifdef CONFIG_CRYPTO_STATS -int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct nlattr **attrs); -#else -static inline int crypto_reportstat(struct sk_buff *in_skb, - struct nlmsghdr *in_nlh, - struct nlattr **attrs) -{ - return -ENOTSUPP; -} -#endif diff --git a/include/crypto/internal/scompress.h b/include/crypto/internal/scompress.h index 858fe3965ae3..07a10fd2d321 100644 --- a/include/crypto/internal/scompress.h +++ b/include/crypto/internal/scompress.h @@ -27,7 +27,6 @@ struct crypto_scomp { * @free_ctx: Function frees context allocated with alloc_ctx * @compress: Function performs a compress operation * @decompress: Function performs a de-compress operation - * @stat: Statistics for compress algorithm * @base: Common crypto API algorithm data structure * @calg: Cmonn algorithm data structure shared with acomp */ diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h index 1988e24a0d1d..2d9c4de57b69 100644 --- a/include/crypto/kpp.h +++ b/include/crypto/kpp.h @@ -51,20 +51,6 @@ struct crypto_kpp { struct crypto_tfm base; }; -/* - * struct crypto_istat_kpp - statistics for KPP algorithm - * @setsecret_cnt: number of setsecrey operation - * @generate_public_key_cnt: number of generate_public_key operation - * @compute_shared_secret_cnt: number of compute_shared_secret operation - * @err_cnt: number of error for KPP requests - */ -struct crypto_istat_kpp { - atomic64_t setsecret_cnt; - atomic64_t generate_public_key_cnt; - atomic64_t compute_shared_secret_cnt; - atomic64_t err_cnt; -}; - /** * struct kpp_alg - generic key-agreement protocol primitives * @@ -87,7 +73,6 @@ struct crypto_istat_kpp { * @exit: Undo everything @init did. * * @base: Common crypto API algorithm data structure - * @stat: Statistics for KPP algorithm */ struct kpp_alg { int (*set_secret)(struct crypto_kpp *tfm, const void *buffer, @@ -100,10 +85,6 @@ struct kpp_alg { int (*init)(struct crypto_kpp *tfm); void (*exit)(struct crypto_kpp *tfm); -#ifdef CONFIG_CRYPTO_STATS - struct crypto_istat_kpp stat; -#endif - struct crypto_alg base; }; @@ -291,26 +272,6 @@ struct kpp_secret { unsigned short len; }; -static inline struct crypto_istat_kpp *kpp_get_stat(struct kpp_alg *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - -static inline int crypto_kpp_errstat(struct kpp_alg *alg, int err) -{ - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&kpp_get_stat(alg)->err_cnt); - - return err; -} - /** * crypto_kpp_set_secret() - Invoke kpp operation * @@ -329,12 +290,7 @@ static inline int crypto_kpp_errstat(struct kpp_alg *alg, int err) static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, const void *buffer, unsigned int len) { - struct kpp_alg *alg = crypto_kpp_alg(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&kpp_get_stat(alg)->setsecret_cnt); - - return crypto_kpp_errstat(alg, alg->set_secret(tfm, buffer, len)); + return crypto_kpp_alg(tfm)->set_secret(tfm, buffer, len); } /** @@ -353,12 +309,8 @@ static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, static inline int crypto_kpp_generate_public_key(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); - struct kpp_alg *alg = crypto_kpp_alg(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&kpp_get_stat(alg)->generate_public_key_cnt); - return crypto_kpp_errstat(alg, alg->generate_public_key(req)); + return crypto_kpp_alg(tfm)->generate_public_key(req); } /** @@ -374,12 +326,8 @@ static inline int crypto_kpp_generate_public_key(struct kpp_request *req) static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); - struct kpp_alg *alg = crypto_kpp_alg(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) - atomic64_inc(&kpp_get_stat(alg)->compute_shared_secret_cnt); - return crypto_kpp_errstat(alg, alg->compute_shared_secret(req)); + return crypto_kpp_alg(tfm)->compute_shared_secret(req); } /** diff --git a/include/crypto/rng.h b/include/crypto/rng.h index 6abe5102e5fb..5ac4388f50e1 100644 --- a/include/crypto/rng.h +++ b/include/crypto/rng.h @@ -15,20 +15,6 @@ struct crypto_rng; -/* - * struct crypto_istat_rng: statistics for RNG algorithm - * @generate_cnt: number of RNG generate requests - * @generate_tlen: total data size of generated data by the RNG - * @seed_cnt: number of times the RNG was seeded - * @err_cnt: number of error for RNG requests - */ -struct crypto_istat_rng { - atomic64_t generate_cnt; - atomic64_t generate_tlen; - atomic64_t seed_cnt; - atomic64_t err_cnt; -}; - /** * struct rng_alg - random number generator definition * @@ -46,7 +32,6 @@ struct crypto_istat_rng { * size of the seed is defined with @seedsize . * @set_ent: Set entropy that would otherwise be obtained from * entropy source. Internal use only. - * @stat: Statistics for rng algorithm * @seedsize: The seed size required for a random number generator * initialization defined with this variable. Some * random number generators does not require a seed @@ -63,10 +48,6 @@ struct rng_alg { void (*set_ent)(struct crypto_rng *tfm, const u8 *data, unsigned int len); -#ifdef CONFIG_CRYPTO_STATS - struct crypto_istat_rng stat; -#endif - unsigned int seedsize; struct crypto_alg base; @@ -144,26 +125,6 @@ static inline void crypto_free_rng(struct crypto_rng *tfm) crypto_destroy_tfm(tfm, crypto_rng_tfm(tfm)); } -static inline struct crypto_istat_rng *rng_get_stat(struct rng_alg *alg) -{ -#ifdef CONFIG_CRYPTO_STATS - return &alg->stat; -#else - return NULL; -#endif -} - -static inline int crypto_rng_errstat(struct rng_alg *alg, int err) -{ - if (!IS_ENABLED(CONFIG_CRYPTO_STATS)) - return err; - - if (err && err != -EINPROGRESS && err != -EBUSY) - atomic64_inc(&rng_get_stat(alg)->err_cnt); - - return err; -} - /** * crypto_rng_generate() - get random number * @tfm: cipher handle @@ -182,17 +143,7 @@ static inline int crypto_rng_generate(struct crypto_rng *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int dlen) { - struct rng_alg *alg = crypto_rng_alg(tfm); - - if (IS_ENABLED(CONFIG_CRYPTO_STATS)) { - struct crypto_istat_rng *istat = rng_get_stat(alg); - - atomic64_inc(&istat->generate_cnt); - atomic64_add(dlen, &istat->generate_tlen); - } - - return crypto_rng_errstat(alg, - alg->generate(tfm, src, slen, dst, dlen)); + return crypto_rng_alg(tfm)->generate(tfm, src, slen, dst, dlen); } /** diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index c8857d7bdb37..74d47e23374e 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -64,28 +64,6 @@ struct crypto_lskcipher { struct crypto_tfm base; }; -/* - * struct crypto_istat_cipher - statistics for cipher algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @err_cnt: number of error for cipher requests - */ -struct crypto_istat_cipher { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t err_cnt; -}; - -#ifdef CONFIG_CRYPTO_STATS -#define SKCIPHER_ALG_COMMON_STAT struct crypto_istat_cipher stat; -#else -#define SKCIPHER_ALG_COMMON_STAT -#endif - /* * struct skcipher_alg_common - common properties of skcipher_alg * @min_keysize: Minimum key size supported by the transformation. This is the @@ -103,7 +81,6 @@ struct crypto_istat_cipher { * @chunksize: Equal to the block size except for stream ciphers such as * CTR where it is set to the underlying block size. * @statesize: Size of the internal state for the algorithm. - * @stat: Statistics for cipher algorithm * @base: Definition of a generic crypto algorithm. */ #define SKCIPHER_ALG_COMMON { \ @@ -113,8 +90,6 @@ struct crypto_istat_cipher { unsigned int chunksize; \ unsigned int statesize; \ \ - SKCIPHER_ALG_COMMON_STAT \ - \ struct crypto_alg base; \ } struct skcipher_alg_common SKCIPHER_ALG_COMMON; diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h index 5730c67f0617..20a6c0fc149e 100644 --- a/include/uapi/linux/cryptouser.h +++ b/include/uapi/linux/cryptouser.h @@ -32,7 +32,7 @@ enum { CRYPTO_MSG_UPDATEALG, CRYPTO_MSG_GETALG, CRYPTO_MSG_DELRNG, - CRYPTO_MSG_GETSTAT, + CRYPTO_MSG_GETSTAT, /* No longer supported, do not use. */ __CRYPTO_MSG_MAX }; #define CRYPTO_MSG_MAX (__CRYPTO_MSG_MAX - 1) @@ -54,16 +54,16 @@ enum crypto_attr_type_t { CRYPTOCFGA_REPORT_AKCIPHER, /* struct crypto_report_akcipher */ CRYPTOCFGA_REPORT_KPP, /* struct crypto_report_kpp */ CRYPTOCFGA_REPORT_ACOMP, /* struct crypto_report_acomp */ - CRYPTOCFGA_STAT_LARVAL, /* struct crypto_stat */ - CRYPTOCFGA_STAT_HASH, /* struct crypto_stat */ - CRYPTOCFGA_STAT_BLKCIPHER, /* struct crypto_stat */ - CRYPTOCFGA_STAT_AEAD, /* struct crypto_stat */ - CRYPTOCFGA_STAT_COMPRESS, /* struct crypto_stat */ - CRYPTOCFGA_STAT_RNG, /* struct crypto_stat */ - CRYPTOCFGA_STAT_CIPHER, /* struct crypto_stat */ - CRYPTOCFGA_STAT_AKCIPHER, /* struct crypto_stat */ - CRYPTOCFGA_STAT_KPP, /* struct crypto_stat */ - CRYPTOCFGA_STAT_ACOMP, /* struct crypto_stat */ + CRYPTOCFGA_STAT_LARVAL, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_HASH, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_BLKCIPHER, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_AEAD, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_COMPRESS, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_RNG, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_CIPHER, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_AKCIPHER, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_KPP, /* No longer supported, do not use. */ + CRYPTOCFGA_STAT_ACOMP, /* No longer supported, do not use. */ __CRYPTOCFGA_MAX #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1) @@ -79,6 +79,7 @@ struct crypto_user_alg { __u32 cru_flags; }; +/* No longer supported, do not use. */ struct crypto_stat_aead { char type[CRYPTO_MAX_NAME]; __u64 stat_encrypt_cnt; @@ -88,6 +89,7 @@ struct crypto_stat_aead { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_akcipher { char type[CRYPTO_MAX_NAME]; __u64 stat_encrypt_cnt; @@ -99,6 +101,7 @@ struct crypto_stat_akcipher { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_cipher { char type[CRYPTO_MAX_NAME]; __u64 stat_encrypt_cnt; @@ -108,6 +111,7 @@ struct crypto_stat_cipher { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_compress { char type[CRYPTO_MAX_NAME]; __u64 stat_compress_cnt; @@ -117,6 +121,7 @@ struct crypto_stat_compress { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_hash { char type[CRYPTO_MAX_NAME]; __u64 stat_hash_cnt; @@ -124,6 +129,7 @@ struct crypto_stat_hash { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_kpp { char type[CRYPTO_MAX_NAME]; __u64 stat_setsecret_cnt; @@ -132,6 +138,7 @@ struct crypto_stat_kpp { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_rng { char type[CRYPTO_MAX_NAME]; __u64 stat_generate_cnt; @@ -140,6 +147,7 @@ struct crypto_stat_rng { __u64 stat_err_cnt; }; +/* No longer supported, do not use. */ struct crypto_stat_larval { char type[CRYPTO_MAX_NAME]; }; -- cgit v1.2.3 From ca4ddc26f8acaa9cb451fcb20f7ab0f02e4970cb Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 29 Mar 2024 10:28:46 -0500 Subject: bpf: Fix typo in uapi doc comments In a few places in the bpf uapi headers, EOPNOTSUPP is missing a "P" in the doc comments. This adds the missing "P". Signed-off-by: David Lechner Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240329152900.398260-2-dlechner@baylibre.com --- include/uapi/linux/bpf.h | 4 ++-- tools/include/uapi/linux/bpf.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 96d57e483133..79c548276b6b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5026,7 +5026,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5512,7 +5512,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * * void *bpf_kptr_xchg(void *map_value, void *ptr) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 96d57e483133..79c548276b6b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5026,7 +5026,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5512,7 +5512,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * * void *bpf_kptr_xchg(void *map_value, void *ptr) -- cgit v1.2.3 From e57ba7e3d7bccd12b6ac9298a9fe0fd8d92ea31d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 1 Apr 2024 11:10:04 +0800 Subject: uapi: team: use header file generated from YAML spec generated with: $ ./tools/net/ynl/ynl-gen-c.py --mode uapi \ > --spec Documentation/netlink/specs/team.yaml \ > --header -o include/uapi/linux/if_team.h Signed-off-by: Hangbin Liu Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20240401031004.1159713-5-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_team.h | 116 ++++++++++++++++--------------------------- 1 file changed, 43 insertions(+), 73 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_team.h b/include/uapi/linux/if_team.h index 13c61fecb78b..a5c06243a435 100644 --- a/include/uapi/linux/if_team.h +++ b/include/uapi/linux/if_team.h @@ -1,108 +1,78 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* - * include/linux/if_team.h - Network team device driver header - * Copyright (c) 2011 Jiri Pirko - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/team.yaml */ +/* YNL-GEN uapi header */ -#ifndef _UAPI_LINUX_IF_TEAM_H_ -#define _UAPI_LINUX_IF_TEAM_H_ +#ifndef _UAPI_LINUX_IF_TEAM_H +#define _UAPI_LINUX_IF_TEAM_H +#define TEAM_GENL_NAME "team" +#define TEAM_GENL_VERSION 1 -#define TEAM_STRING_MAX_LEN 32 - -/********************************** - * NETLINK_GENERIC netlink family. - **********************************/ - -enum { - TEAM_CMD_NOOP, - TEAM_CMD_OPTIONS_SET, - TEAM_CMD_OPTIONS_GET, - TEAM_CMD_PORT_LIST_GET, - - __TEAM_CMD_MAX, - TEAM_CMD_MAX = (__TEAM_CMD_MAX - 1), -}; +#define TEAM_STRING_MAX_LEN 32 +#define TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME "change_event" enum { TEAM_ATTR_UNSPEC, - TEAM_ATTR_TEAM_IFINDEX, /* u32 */ - TEAM_ATTR_LIST_OPTION, /* nest */ - TEAM_ATTR_LIST_PORT, /* nest */ + TEAM_ATTR_TEAM_IFINDEX, + TEAM_ATTR_LIST_OPTION, + TEAM_ATTR_LIST_PORT, __TEAM_ATTR_MAX, - TEAM_ATTR_MAX = __TEAM_ATTR_MAX - 1, + TEAM_ATTR_MAX = (__TEAM_ATTR_MAX - 1) }; -/* Nested layout of get/set msg: - * - * [TEAM_ATTR_LIST_OPTION] - * [TEAM_ATTR_ITEM_OPTION] - * [TEAM_ATTR_OPTION_*], ... - * [TEAM_ATTR_ITEM_OPTION] - * [TEAM_ATTR_OPTION_*], ... - * ... - * [TEAM_ATTR_LIST_PORT] - * [TEAM_ATTR_ITEM_PORT] - * [TEAM_ATTR_PORT_*], ... - * [TEAM_ATTR_ITEM_PORT] - * [TEAM_ATTR_PORT_*], ... - * ... - */ - enum { TEAM_ATTR_ITEM_OPTION_UNSPEC, - TEAM_ATTR_ITEM_OPTION, /* nest */ + TEAM_ATTR_ITEM_OPTION, __TEAM_ATTR_ITEM_OPTION_MAX, - TEAM_ATTR_ITEM_OPTION_MAX = __TEAM_ATTR_ITEM_OPTION_MAX - 1, + TEAM_ATTR_ITEM_OPTION_MAX = (__TEAM_ATTR_ITEM_OPTION_MAX - 1) }; enum { TEAM_ATTR_OPTION_UNSPEC, - TEAM_ATTR_OPTION_NAME, /* string */ - TEAM_ATTR_OPTION_CHANGED, /* flag */ - TEAM_ATTR_OPTION_TYPE, /* u8 */ - TEAM_ATTR_OPTION_DATA, /* dynamic */ - TEAM_ATTR_OPTION_REMOVED, /* flag */ - TEAM_ATTR_OPTION_PORT_IFINDEX, /* u32 */ /* for per-port options */ - TEAM_ATTR_OPTION_ARRAY_INDEX, /* u32 */ /* for array options */ + TEAM_ATTR_OPTION_NAME, + TEAM_ATTR_OPTION_CHANGED, + TEAM_ATTR_OPTION_TYPE, + TEAM_ATTR_OPTION_DATA, + TEAM_ATTR_OPTION_REMOVED, + TEAM_ATTR_OPTION_PORT_IFINDEX, + TEAM_ATTR_OPTION_ARRAY_INDEX, __TEAM_ATTR_OPTION_MAX, - TEAM_ATTR_OPTION_MAX = __TEAM_ATTR_OPTION_MAX - 1, + TEAM_ATTR_OPTION_MAX = (__TEAM_ATTR_OPTION_MAX - 1) }; enum { TEAM_ATTR_ITEM_PORT_UNSPEC, - TEAM_ATTR_ITEM_PORT, /* nest */ + TEAM_ATTR_ITEM_PORT, __TEAM_ATTR_ITEM_PORT_MAX, - TEAM_ATTR_ITEM_PORT_MAX = __TEAM_ATTR_ITEM_PORT_MAX - 1, + TEAM_ATTR_ITEM_PORT_MAX = (__TEAM_ATTR_ITEM_PORT_MAX - 1) }; enum { TEAM_ATTR_PORT_UNSPEC, - TEAM_ATTR_PORT_IFINDEX, /* u32 */ - TEAM_ATTR_PORT_CHANGED, /* flag */ - TEAM_ATTR_PORT_LINKUP, /* flag */ - TEAM_ATTR_PORT_SPEED, /* u32 */ - TEAM_ATTR_PORT_DUPLEX, /* u8 */ - TEAM_ATTR_PORT_REMOVED, /* flag */ + TEAM_ATTR_PORT_IFINDEX, + TEAM_ATTR_PORT_CHANGED, + TEAM_ATTR_PORT_LINKUP, + TEAM_ATTR_PORT_SPEED, + TEAM_ATTR_PORT_DUPLEX, + TEAM_ATTR_PORT_REMOVED, __TEAM_ATTR_PORT_MAX, - TEAM_ATTR_PORT_MAX = __TEAM_ATTR_PORT_MAX - 1, + TEAM_ATTR_PORT_MAX = (__TEAM_ATTR_PORT_MAX - 1) }; -/* - * NETLINK_GENERIC related info - */ -#define TEAM_GENL_NAME "team" -#define TEAM_GENL_VERSION 0x1 -#define TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME "change_event" +enum { + TEAM_CMD_NOOP, + TEAM_CMD_OPTIONS_SET, + TEAM_CMD_OPTIONS_GET, + TEAM_CMD_PORT_LIST_GET, + + __TEAM_CMD_MAX, + TEAM_CMD_MAX = (__TEAM_CMD_MAX - 1) +}; -#endif /* _UAPI_LINUX_IF_TEAM_H_ */ +#endif /* _UAPI_LINUX_IF_TEAM_H */ -- cgit v1.2.3 From c835e5a3153cae2956efdbb9948b90f2b9e5e64d Mon Sep 17 00:00:00 2001 From: Balint Dobszay Date: Mon, 25 Mar 2024 16:11:03 +0100 Subject: tee: tstee: Add Trusted Services TEE driver The Trusted Services project provides a framework for developing and deploying device Root of Trust services in FF-A Secure Partitions. The FF-A SPs are accessible through the FF-A driver, but this doesn't provide a user space interface. The goal of this TEE driver is to make Trusted Services SPs accessible for user space clients. All TS SPs have the same FF-A UUID, it identifies the RPC protocol used by TS. A TS SP can host one or more services, a service is identified by its service UUID. The same type of service cannot be present twice in the same SP. During SP boot each service in an SP is assigned an interface ID, this is just a short ID to simplify message addressing. There is 1:1 mapping between TS SPs and TEE devices, i.e. a separate TEE device is registered for each TS SP. This is required since contrary to the generic TEE design where memory is shared with the whole TEE implementation, in case of FF-A, memory is shared with a specific SP. A user space client has to be able to separately share memory with each SP based on its endpoint ID. Acked-by: Sumit Garg Signed-off-by: Balint Dobszay Signed-off-by: Jens Wiklander --- drivers/tee/Kconfig | 1 + drivers/tee/Makefile | 1 + drivers/tee/tstee/Kconfig | 11 + drivers/tee/tstee/Makefile | 3 + drivers/tee/tstee/core.c | 480 ++++++++++++++++++++++++++++++++++++++ drivers/tee/tstee/tstee_private.h | 92 ++++++++ include/uapi/linux/tee.h | 1 + 7 files changed, 589 insertions(+) create mode 100644 drivers/tee/tstee/Kconfig create mode 100644 drivers/tee/tstee/Makefile create mode 100644 drivers/tee/tstee/core.c create mode 100644 drivers/tee/tstee/tstee_private.h (limited to 'include/uapi/linux') diff --git a/drivers/tee/Kconfig b/drivers/tee/Kconfig index 73a147202e88..61b507c18780 100644 --- a/drivers/tee/Kconfig +++ b/drivers/tee/Kconfig @@ -15,5 +15,6 @@ if TEE source "drivers/tee/optee/Kconfig" source "drivers/tee/amdtee/Kconfig" +source "drivers/tee/tstee/Kconfig" endif diff --git a/drivers/tee/Makefile b/drivers/tee/Makefile index 68da044afbfa..5488cba30bd2 100644 --- a/drivers/tee/Makefile +++ b/drivers/tee/Makefile @@ -5,3 +5,4 @@ tee-objs += tee_shm.o tee-objs += tee_shm_pool.o obj-$(CONFIG_OPTEE) += optee/ obj-$(CONFIG_AMDTEE) += amdtee/ +obj-$(CONFIG_ARM_TSTEE) += tstee/ diff --git a/drivers/tee/tstee/Kconfig b/drivers/tee/tstee/Kconfig new file mode 100644 index 000000000000..d32f91d47398 --- /dev/null +++ b/drivers/tee/tstee/Kconfig @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only +config ARM_TSTEE + tristate "Arm Trusted Services TEE driver" + depends on ARM_FFA_TRANSPORT + default n + help + The Trusted Services project provides a framework for developing and + deploying device Root of Trust services in FF-A Secure Partitions. + This driver provides an interface to make Trusted Services Secure + Partitions accessible for user space clients, since the FF-A driver + doesn't implement a user space interface directly. diff --git a/drivers/tee/tstee/Makefile b/drivers/tee/tstee/Makefile new file mode 100644 index 000000000000..5227020ebd30 --- /dev/null +++ b/drivers/tee/tstee/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +arm-tstee-objs := core.o +obj-$(CONFIG_ARM_TSTEE) = arm-tstee.o diff --git a/drivers/tee/tstee/core.c b/drivers/tee/tstee/core.c new file mode 100644 index 000000000000..533425e9e9e7 --- /dev/null +++ b/drivers/tee/tstee/core.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023, Arm Limited + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "tstee_private.h" + +#define FFA_DIRECT_REQ_ARG_NUM 5 +#define FFA_INVALID_MEM_HANDLE U64_MAX + +static void arg_list_to_ffa_data(const u32 *args, + struct ffa_send_direct_data *data) +{ + data->data0 = args[0]; + data->data1 = args[1]; + data->data2 = args[2]; + data->data3 = args[3]; + data->data4 = args[4]; +} + +static void arg_list_from_ffa_data(const struct ffa_send_direct_data *data, + u32 *args) +{ + args[0] = lower_32_bits(data->data0); + args[1] = lower_32_bits(data->data1); + args[2] = lower_32_bits(data->data2); + args[3] = lower_32_bits(data->data3); + args[4] = lower_32_bits(data->data4); +} + +static void tstee_get_version(struct tee_device *teedev, + struct tee_ioctl_version_data *vers) +{ + struct tstee *tstee = tee_get_drvdata(teedev); + struct tee_ioctl_version_data v = { + .impl_id = TEE_IMPL_ID_TSTEE, + /* FF-A endpoint ID only uses the lower 16 bits */ + .impl_caps = lower_16_bits(tstee->ffa_dev->vm_id), + .gen_caps = 0, + }; + + *vers = v; +} + +static int tstee_open(struct tee_context *ctx) +{ + struct ts_context_data *ctxdata; + + ctxdata = kzalloc(sizeof(*ctxdata), GFP_KERNEL); + if (!ctxdata) + return -ENOMEM; + + xa_init_flags(&ctxdata->sess_list, XA_FLAGS_ALLOC); + + ctx->data = ctxdata; + + return 0; +} + +static void tstee_release(struct tee_context *ctx) +{ + struct ts_context_data *ctxdata = ctx->data; + struct ts_session *sess; + unsigned long idx; + + if (!ctxdata) + return; + + xa_for_each(&ctxdata->sess_list, idx, sess) { + xa_erase(&ctxdata->sess_list, idx); + kfree(sess); + } + + xa_destroy(&ctxdata->sess_list); + + kfree(ctxdata); + ctx->data = NULL; +} + +static int tstee_open_session(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param __always_unused) +{ + struct tstee *tstee = tee_get_drvdata(ctx->teedev); + struct ffa_device *ffa_dev = tstee->ffa_dev; + struct ts_context_data *ctxdata = ctx->data; + struct ffa_send_direct_data ffa_data; + struct ts_session *sess = NULL; + u32 ffa_args[FFA_DIRECT_REQ_ARG_NUM] = {}; + u32 sess_id; + int rc; + + ffa_args[TS_RPC_CTRL_REG] = + TS_RPC_CTRL_PACK_IFACE_OPCODE(TS_RPC_MGMT_IFACE_ID, + TS_RPC_OP_SERVICE_INFO); + + memcpy(ffa_args + TS_RPC_SERVICE_INFO_UUID0, arg->uuid, UUID_SIZE); + + arg_list_to_ffa_data(ffa_args, &ffa_data); + rc = ffa_dev->ops->msg_ops->sync_send_receive(ffa_dev, &ffa_data); + if (rc) + return rc; + + arg_list_from_ffa_data(&ffa_data, ffa_args); + + if (ffa_args[TS_RPC_SERVICE_INFO_RPC_STATUS] != TS_RPC_OK) + return -ENODEV; + + if (ffa_args[TS_RPC_SERVICE_INFO_IFACE] > U8_MAX) + return -EINVAL; + + sess = kzalloc(sizeof(*sess), GFP_KERNEL); + if (!sess) + return -ENOMEM; + + sess->iface_id = ffa_args[TS_RPC_SERVICE_INFO_IFACE]; + + rc = xa_alloc(&ctxdata->sess_list, &sess_id, sess, xa_limit_32b, + GFP_KERNEL); + if (rc) { + kfree(sess); + return rc; + } + + arg->session = sess_id; + arg->ret = 0; + + return 0; +} + +static int tstee_close_session(struct tee_context *ctx, u32 session) +{ + struct ts_context_data *ctxdata = ctx->data; + struct ts_session *sess; + + /* Calls xa_lock() internally */ + sess = xa_erase(&ctxdata->sess_list, session); + if (!sess) + return -EINVAL; + + kfree(sess); + + return 0; +} + +static int tstee_invoke_func(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param) +{ + struct tstee *tstee = tee_get_drvdata(ctx->teedev); + struct ffa_device *ffa_dev = tstee->ffa_dev; + struct ts_context_data *ctxdata = ctx->data; + struct ffa_send_direct_data ffa_data; + struct tee_shm *shm = NULL; + struct ts_session *sess; + u32 req_len, ffa_args[FFA_DIRECT_REQ_ARG_NUM] = {}; + int shm_id, rc; + u8 iface_id; + u64 handle; + u16 opcode; + + xa_lock(&ctxdata->sess_list); + sess = xa_load(&ctxdata->sess_list, arg->session); + + /* + * Do this while holding the lock to make sure that the session wasn't + * closed meanwhile + */ + if (sess) + iface_id = sess->iface_id; + + xa_unlock(&ctxdata->sess_list); + if (!sess) + return -EINVAL; + + opcode = lower_16_bits(arg->func); + shm_id = lower_32_bits(param[0].u.value.a); + req_len = lower_32_bits(param[0].u.value.b); + + if (shm_id != 0) { + shm = tee_shm_get_from_id(ctx, shm_id); + if (IS_ERR(shm)) + return PTR_ERR(shm); + + if (shm->size < req_len) { + dev_err(&ffa_dev->dev, + "request doesn't fit into shared memory buffer\n"); + rc = -EINVAL; + goto out; + } + + handle = shm->sec_world_id; + } else { + handle = FFA_INVALID_MEM_HANDLE; + } + + ffa_args[TS_RPC_CTRL_REG] = TS_RPC_CTRL_PACK_IFACE_OPCODE(iface_id, + opcode); + ffa_args[TS_RPC_SERVICE_MEM_HANDLE_LSW] = lower_32_bits(handle); + ffa_args[TS_RPC_SERVICE_MEM_HANDLE_MSW] = upper_32_bits(handle); + ffa_args[TS_RPC_SERVICE_REQ_LEN] = req_len; + ffa_args[TS_RPC_SERVICE_CLIENT_ID] = 0; + + arg_list_to_ffa_data(ffa_args, &ffa_data); + rc = ffa_dev->ops->msg_ops->sync_send_receive(ffa_dev, &ffa_data); + if (rc) + goto out; + + arg_list_from_ffa_data(&ffa_data, ffa_args); + + if (ffa_args[TS_RPC_SERVICE_RPC_STATUS] != TS_RPC_OK) { + dev_err(&ffa_dev->dev, "invoke_func rpc status: %d\n", + ffa_args[TS_RPC_SERVICE_RPC_STATUS]); + rc = -EINVAL; + goto out; + } + + arg->ret = ffa_args[TS_RPC_SERVICE_STATUS]; + if (shm && shm->size >= ffa_args[TS_RPC_SERVICE_RESP_LEN]) + param[0].u.value.a = ffa_args[TS_RPC_SERVICE_RESP_LEN]; + +out: + if (shm) + tee_shm_put(shm); + + return rc; +} + +static int tstee_shm_register(struct tee_context *ctx, struct tee_shm *shm, + struct page **pages, size_t num_pages, + unsigned long start __always_unused) +{ + struct tstee *tstee = tee_get_drvdata(ctx->teedev); + struct ffa_device *ffa_dev = tstee->ffa_dev; + struct ffa_mem_region_attributes mem_attr = { + .receiver = tstee->ffa_dev->vm_id, + .attrs = FFA_MEM_RW, + .flag = 0, + }; + struct ffa_mem_ops_args mem_args = { + .attrs = &mem_attr, + .use_txbuf = true, + .nattrs = 1, + .flags = 0, + }; + struct ffa_send_direct_data ffa_data; + struct sg_table sgt; + u32 ffa_args[FFA_DIRECT_REQ_ARG_NUM] = {}; + int rc; + + rc = sg_alloc_table_from_pages(&sgt, pages, num_pages, 0, + num_pages * PAGE_SIZE, GFP_KERNEL); + if (rc) + return rc; + + mem_args.sg = sgt.sgl; + rc = ffa_dev->ops->mem_ops->memory_share(&mem_args); + sg_free_table(&sgt); + if (rc) + return rc; + + shm->sec_world_id = mem_args.g_handle; + + ffa_args[TS_RPC_CTRL_REG] = + TS_RPC_CTRL_PACK_IFACE_OPCODE(TS_RPC_MGMT_IFACE_ID, + TS_RPC_OP_RETRIEVE_MEM); + ffa_args[TS_RPC_RETRIEVE_MEM_HANDLE_LSW] = + lower_32_bits(shm->sec_world_id); + ffa_args[TS_RPC_RETRIEVE_MEM_HANDLE_MSW] = + upper_32_bits(shm->sec_world_id); + ffa_args[TS_RPC_RETRIEVE_MEM_TAG_LSW] = 0; + ffa_args[TS_RPC_RETRIEVE_MEM_TAG_MSW] = 0; + + arg_list_to_ffa_data(ffa_args, &ffa_data); + rc = ffa_dev->ops->msg_ops->sync_send_receive(ffa_dev, &ffa_data); + if (rc) { + (void)ffa_dev->ops->mem_ops->memory_reclaim(shm->sec_world_id, + 0); + return rc; + } + + arg_list_from_ffa_data(&ffa_data, ffa_args); + + if (ffa_args[TS_RPC_RETRIEVE_MEM_RPC_STATUS] != TS_RPC_OK) { + dev_err(&ffa_dev->dev, "shm_register rpc status: %d\n", + ffa_args[TS_RPC_RETRIEVE_MEM_RPC_STATUS]); + ffa_dev->ops->mem_ops->memory_reclaim(shm->sec_world_id, 0); + return -EINVAL; + } + + return 0; +} + +static int tstee_shm_unregister(struct tee_context *ctx, struct tee_shm *shm) +{ + struct tstee *tstee = tee_get_drvdata(ctx->teedev); + struct ffa_device *ffa_dev = tstee->ffa_dev; + struct ffa_send_direct_data ffa_data; + u32 ffa_args[FFA_DIRECT_REQ_ARG_NUM] = {}; + int rc; + + ffa_args[TS_RPC_CTRL_REG] = + TS_RPC_CTRL_PACK_IFACE_OPCODE(TS_RPC_MGMT_IFACE_ID, + TS_RPC_OP_RELINQ_MEM); + ffa_args[TS_RPC_RELINQ_MEM_HANDLE_LSW] = + lower_32_bits(shm->sec_world_id); + ffa_args[TS_RPC_RELINQ_MEM_HANDLE_MSW] = + upper_32_bits(shm->sec_world_id); + + arg_list_to_ffa_data(ffa_args, &ffa_data); + rc = ffa_dev->ops->msg_ops->sync_send_receive(ffa_dev, &ffa_data); + if (rc) + return rc; + arg_list_from_ffa_data(&ffa_data, ffa_args); + + if (ffa_args[TS_RPC_RELINQ_MEM_RPC_STATUS] != TS_RPC_OK) { + dev_err(&ffa_dev->dev, "shm_unregister rpc status: %d\n", + ffa_args[TS_RPC_RELINQ_MEM_RPC_STATUS]); + return -EINVAL; + } + + rc = ffa_dev->ops->mem_ops->memory_reclaim(shm->sec_world_id, 0); + + return rc; +} + +static const struct tee_driver_ops tstee_ops = { + .get_version = tstee_get_version, + .open = tstee_open, + .release = tstee_release, + .open_session = tstee_open_session, + .close_session = tstee_close_session, + .invoke_func = tstee_invoke_func, +}; + +static const struct tee_desc tstee_desc = { + .name = "tstee-clnt", + .ops = &tstee_ops, + .owner = THIS_MODULE, +}; + +static int pool_op_alloc(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align) +{ + return tee_dyn_shm_alloc_helper(shm, size, align, tstee_shm_register); +} + +static void pool_op_free(struct tee_shm_pool *pool, struct tee_shm *shm) +{ + tee_dyn_shm_free_helper(shm, tstee_shm_unregister); +} + +static void pool_op_destroy_pool(struct tee_shm_pool *pool) +{ + kfree(pool); +} + +static const struct tee_shm_pool_ops pool_ops = { + .alloc = pool_op_alloc, + .free = pool_op_free, + .destroy_pool = pool_op_destroy_pool, +}; + +static struct tee_shm_pool *tstee_create_shm_pool(void) +{ + struct tee_shm_pool *pool = kzalloc(sizeof(*pool), GFP_KERNEL); + + if (!pool) + return ERR_PTR(-ENOMEM); + + pool->ops = &pool_ops; + + return pool; +} + +static bool tstee_check_rpc_compatible(struct ffa_device *ffa_dev) +{ + struct ffa_send_direct_data ffa_data; + u32 ffa_args[FFA_DIRECT_REQ_ARG_NUM] = {}; + + ffa_args[TS_RPC_CTRL_REG] = + TS_RPC_CTRL_PACK_IFACE_OPCODE(TS_RPC_MGMT_IFACE_ID, + TS_RPC_OP_GET_VERSION); + + arg_list_to_ffa_data(ffa_args, &ffa_data); + if (ffa_dev->ops->msg_ops->sync_send_receive(ffa_dev, &ffa_data)) + return false; + + arg_list_from_ffa_data(&ffa_data, ffa_args); + + return ffa_args[TS_RPC_GET_VERSION_RESP] == TS_RPC_PROTOCOL_VERSION; +} + +static int tstee_probe(struct ffa_device *ffa_dev) +{ + struct tstee *tstee; + int rc; + + ffa_dev->ops->msg_ops->mode_32bit_set(ffa_dev); + + if (!tstee_check_rpc_compatible(ffa_dev)) + return -EINVAL; + + tstee = kzalloc(sizeof(*tstee), GFP_KERNEL); + if (!tstee) + return -ENOMEM; + + tstee->ffa_dev = ffa_dev; + + tstee->pool = tstee_create_shm_pool(); + if (IS_ERR(tstee->pool)) { + rc = PTR_ERR(tstee->pool); + tstee->pool = NULL; + goto err_free_tstee; + } + + tstee->teedev = tee_device_alloc(&tstee_desc, NULL, tstee->pool, tstee); + if (IS_ERR(tstee->teedev)) { + rc = PTR_ERR(tstee->teedev); + tstee->teedev = NULL; + goto err_free_pool; + } + + rc = tee_device_register(tstee->teedev); + if (rc) + goto err_unreg_teedev; + + ffa_dev_set_drvdata(ffa_dev, tstee); + + return 0; + +err_unreg_teedev: + tee_device_unregister(tstee->teedev); +err_free_pool: + tee_shm_pool_free(tstee->pool); +err_free_tstee: + kfree(tstee); + return rc; +} + +static void tstee_remove(struct ffa_device *ffa_dev) +{ + struct tstee *tstee = ffa_dev->dev.driver_data; + + tee_device_unregister(tstee->teedev); + tee_shm_pool_free(tstee->pool); + kfree(tstee); +} + +static const struct ffa_device_id tstee_device_ids[] = { + /* TS RPC protocol UUID: bdcd76d7-825e-4751-963b-86d4f84943ac */ + { TS_RPC_UUID }, + {} +}; + +static struct ffa_driver tstee_driver = { + .name = "arm_tstee", + .probe = tstee_probe, + .remove = tstee_remove, + .id_table = tstee_device_ids, +}; + +module_ffa_driver(tstee_driver); + +MODULE_AUTHOR("Balint Dobszay "); +MODULE_DESCRIPTION("Arm Trusted Services TEE driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/tee/tstee/tstee_private.h b/drivers/tee/tstee/tstee_private.h new file mode 100644 index 000000000000..8e58725b57eb --- /dev/null +++ b/drivers/tee/tstee/tstee_private.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023, Arm Limited + */ + +#ifndef TSTEE_PRIVATE_H +#define TSTEE_PRIVATE_H + +#include +#include +#include +#include +#include +#include + +/* + * The description of the ABI implemented in this file is available at + * https://trusted-services.readthedocs.io/en/v1.0.0/developer/service-access-protocols.html#abi + */ + +/* UUID of this protocol */ +#define TS_RPC_UUID UUID_INIT(0xbdcd76d7, 0x825e, 0x4751, \ + 0x96, 0x3b, 0x86, 0xd4, 0xf8, 0x49, 0x43, 0xac) + +/* Protocol version*/ +#define TS_RPC_PROTOCOL_VERSION (1) + +/* Status codes */ +#define TS_RPC_OK (0) + +/* RPC control register */ +#define TS_RPC_CTRL_REG (0) +#define OPCODE_MASK GENMASK(15, 0) +#define IFACE_ID_MASK GENMASK(23, 16) +#define TS_RPC_CTRL_OPCODE(x) ((u16)(FIELD_GET(OPCODE_MASK, (x)))) +#define TS_RPC_CTRL_IFACE_ID(x) ((u8)(FIELD_GET(IFACE_ID_MASK, (x)))) +#define TS_RPC_CTRL_PACK_IFACE_OPCODE(i, o) \ + (FIELD_PREP(IFACE_ID_MASK, (i)) | FIELD_PREP(OPCODE_MASK, (o))) +#define TS_RPC_CTRL_SAP_RC BIT(30) +#define TS_RPC_CTRL_SAP_ERR BIT(31) + +/* Interface ID for RPC management operations */ +#define TS_RPC_MGMT_IFACE_ID (0xff) + +/* Management calls */ +#define TS_RPC_OP_GET_VERSION (0x0000) +#define TS_RPC_GET_VERSION_RESP (1) + +#define TS_RPC_OP_RETRIEVE_MEM (0x0001) +#define TS_RPC_RETRIEVE_MEM_HANDLE_LSW (1) +#define TS_RPC_RETRIEVE_MEM_HANDLE_MSW (2) +#define TS_RPC_RETRIEVE_MEM_TAG_LSW (3) +#define TS_RPC_RETRIEVE_MEM_TAG_MSW (4) +#define TS_RPC_RETRIEVE_MEM_RPC_STATUS (1) + +#define TS_RPC_OP_RELINQ_MEM (0x0002) +#define TS_RPC_RELINQ_MEM_HANDLE_LSW (1) +#define TS_RPC_RELINQ_MEM_HANDLE_MSW (2) +#define TS_RPC_RELINQ_MEM_RPC_STATUS (1) + +#define TS_RPC_OP_SERVICE_INFO (0x0003) +#define TS_RPC_SERVICE_INFO_UUID0 (1) +#define TS_RPC_SERVICE_INFO_UUID1 (2) +#define TS_RPC_SERVICE_INFO_UUID2 (3) +#define TS_RPC_SERVICE_INFO_UUID3 (4) +#define TS_RPC_SERVICE_INFO_RPC_STATUS (1) +#define TS_RPC_SERVICE_INFO_IFACE (2) + +/* Service call */ +#define TS_RPC_SERVICE_MEM_HANDLE_LSW (1) +#define TS_RPC_SERVICE_MEM_HANDLE_MSW (2) +#define TS_RPC_SERVICE_REQ_LEN (3) +#define TS_RPC_SERVICE_CLIENT_ID (4) +#define TS_RPC_SERVICE_RPC_STATUS (1) +#define TS_RPC_SERVICE_STATUS (2) +#define TS_RPC_SERVICE_RESP_LEN (3) + +struct tstee { + struct ffa_device *ffa_dev; + struct tee_device *teedev; + struct tee_shm_pool *pool; +}; + +struct ts_session { + u8 iface_id; +}; + +struct ts_context_data { + struct xarray sess_list; +}; + +#endif /* TSTEE_PRIVATE_H */ diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 23e57164693c..d0430bee8292 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -56,6 +56,7 @@ */ #define TEE_IMPL_ID_OPTEE 1 #define TEE_IMPL_ID_AMDTEE 2 +#define TEE_IMPL_ID_TSTEE 3 /* * OP-TEE specific capabilities -- cgit v1.2.3 From 9cc8a6e62624e4a0e0bcf8dfd10cc89db6e0f14b Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Tue, 2 Apr 2024 22:11:19 +0200 Subject: net: ethtool: Add impedance mismatch result code to cable test Some PHYs can recognize during a cable test if the impedance in the cable is okay. They can detect reflections caused by impedance discontinuity between a regular 100 Ohm cable and an abnormal part with a higher or lower impedance. This commit introduces a new result code: ETHTOOL_A_CABLE_RESULT_CODE_IMPEDANCE_MISMATCH, which represents the results of a cable test indicating issues with impedance integrity. Signed-off-by: Pawel Dembicki Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20240402201123.2961909-2-paweldembicki@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool_netlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 3f89074aa06c..accbb1a231df 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -515,6 +515,10 @@ enum { ETHTOOL_A_CABLE_RESULT_CODE_OPEN, ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT, ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT, + /* detected reflection caused by the impedance discontinuity between + * a regular 100 Ohm cable and a part with the abnormal impedance value + */ + ETHTOOL_A_CABLE_RESULT_CODE_IMPEDANCE_MISMATCH, }; enum { -- cgit v1.2.3 From f91717007217d975aa975ddabd91ae1a107b9bff Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 3 Apr 2024 14:33:03 +0200 Subject: bpf: Pack struct bpf_fib_lookup The struct bpf_fib_lookup is supposed to be of size 64. A recent commit 59b418c7063d ("bpf: Add a check for struct bpf_fib_lookup size") added a static assertion to check this property so that future changes to the structure will not accidentally break this assumption. As it immediately turned out, on some 32-bit arm systems, when AEABI=n, the total size of the structure was equal to 68, see [1]. This happened because the bpf_fib_lookup structure contains a union of two 16-bit fields: union { __u16 tot_len; __u16 mtu_result; }; which was supposed to compile to a 16-bit-aligned 16-bit field. On the aforementioned setups it was instead both aligned and padded to 32-bits. Declare this inner union as __attribute__((packed, aligned(2))) such that it always is of size 2 and is aligned to 16 bits. [1] https://lore.kernel.org/all/CA+G9fYtsoP51f-oP_Sp5MOq-Ffv8La2RztNpwvE6+R1VtFiLrw@mail.gmail.com/#t Reported-by: Naresh Kamboju Fixes: e1850ea9bd9e ("bpf: bpf_fib_lookup return MTU value as output when looked up") Signed-off-by: Anton Protopopov Signed-off-by: Andrii Nakryiko Reviewed-by: Alexander Lobakin Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240403123303.1452184-1-aspsk@isovalent.com --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 79c548276b6b..6fe9f11c8abe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7157,7 +7157,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 79c548276b6b..6fe9f11c8abe 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7157,7 +7157,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ -- cgit v1.2.3 From 0e9c127729be19adcdf2f5cc1f3450a4322fdf3a Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Wed, 3 Apr 2024 14:28:39 -0700 Subject: ethtool: add interface to read Tx hardware timestamping statistics Multiple network devices that support hardware timestamping appear to have common behavior with regards to timestamp handling. Implement common Tx hardware timestamping statistics in a tx_stats struct_group. Common Rx hardware timestamping statistics can subsequently be implemented in a rx_stats struct_group for ethtool_ts_stats. Signed-off-by: Rahul Rameshbabu Reviewed-by: Dragos Tatulea Link: https://lore.kernel.org/r/20240403212931.128541-2-rrameshbabu@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 17 +++++++++ Documentation/networking/ethtool-netlink.rst | 9 +++++ include/linux/ethtool.h | 27 ++++++++++++++- include/uapi/linux/ethtool_netlink.h | 14 ++++++++ net/ethtool/tsinfo.c | 52 +++++++++++++++++++++++++++- 5 files changed, 117 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index d0e4a47e0f21..b76916394ec9 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -565,6 +565,18 @@ attribute-sets: - name: tx-lpi-timer type: u32 + - + name: ts-stat + attributes: + - + name: tx-pkts + type: uint + - + name: tx-lost + type: uint + - + name: tx-err + type: uint - name: tsinfo attributes: @@ -587,6 +599,10 @@ attribute-sets: - name: phc-index type: u32 + - + name: stats + type: nest + nested-attributes: ts-stat - name: cable-result attributes: @@ -1394,6 +1410,7 @@ operations: - tx-types - rx-filters - phc-index + - stats dump: *tsinfo-get-op - name: cable-test-act diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d583d9abf2f8..08d330b0f50f 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1237,12 +1237,21 @@ Kernel response contents: ``ETHTOOL_A_TSINFO_TX_TYPES`` bitset supported Tx types ``ETHTOOL_A_TSINFO_RX_FILTERS`` bitset supported Rx filters ``ETHTOOL_A_TSINFO_PHC_INDEX`` u32 PTP hw clock index + ``ETHTOOL_A_TSINFO_STATS`` nested HW timestamping statistics ===================================== ====== ========================== ``ETHTOOL_A_TSINFO_PHC_INDEX`` is absent if there is no associated PHC (there is no special value for this case). The bitset attributes are omitted if they would be empty (no bit set). +Additional hardware timestamping statistics response contents: + + ===================================== ====== =================================== + ``ETHTOOL_A_TS_STAT_TX_PKTS`` u64 Packets with Tx HW timestamps + ``ETHTOOL_A_TS_STAT_TX_LOST`` u64 Tx HW timestamp not arrived count + ``ETHTOOL_A_TS_STAT_TX_ERR`` u64 HW error request Tx timestamp count + ===================================== ====== =================================== + CABLE_TEST ========== diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9901e563f706..6fd9107d3cc0 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -480,6 +480,26 @@ struct ethtool_rmon_stats { ); }; +/** + * struct ethtool_ts_stats - HW timestamping statistics + * @pkts: Number of packets successfully timestamped by the hardware. + * @lost: Number of hardware timestamping requests where the timestamping + * information from the hardware never arrived for submission with + * the skb. + * @err: Number of arbitrary timestamp generation error events that the + * hardware encountered, exclusive of @lost statistics. Cases such + * as resource exhaustion, unavailability, firmware errors, and + * detected illogical timestamp values not submitted with the skb + * are inclusive to this counter. + */ +struct ethtool_ts_stats { + struct_group(tx_stats, + u64 pkts; + u64 lost; + u64 err; + ); +}; + #define ETH_MODULE_EEPROM_PAGE_LEN 128 #define ETH_MODULE_MAX_I2C_ADDRESS 0x7f @@ -755,7 +775,10 @@ struct ethtool_rxfh_param { * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. * It may be called with RCU, or rtnl or reference on the device. * Drivers supporting transmit time stamps in software should set this to - * ethtool_op_get_ts_info(). + * ethtool_op_get_ts_info(). Drivers must not zero statistics which they + * don't report. The stats structure is initialized to ETHTOOL_STAT_NOT_SET + * indicating driver does not report statistics. + * @get_ts_stats: Query the device hardware timestamping statistics. * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module @@ -898,6 +921,8 @@ struct ethtool_ops { struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); int (*get_ts_info)(struct net_device *, struct ethtool_ts_info *); + void (*get_ts_stats)(struct net_device *dev, + struct ethtool_ts_stats *ts_stats); int (*get_module_info)(struct net_device *, struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index accbb1a231df..708272026d80 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -478,12 +478,26 @@ enum { ETHTOOL_A_TSINFO_TX_TYPES, /* bitset */ ETHTOOL_A_TSINFO_RX_FILTERS, /* bitset */ ETHTOOL_A_TSINFO_PHC_INDEX, /* u32 */ + ETHTOOL_A_TSINFO_STATS, /* nest - _A_TSINFO_STAT */ /* add new constants above here */ __ETHTOOL_A_TSINFO_CNT, ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) }; +enum { + ETHTOOL_A_TS_STAT_UNSPEC, + + ETHTOOL_A_TS_STAT_TX_PKTS, /* u64 */ + ETHTOOL_A_TS_STAT_TX_LOST, /* u64 */ + ETHTOOL_A_TS_STAT_TX_ERR, /* u64 */ + + /* add new constants above here */ + __ETHTOOL_A_TS_STAT_CNT, + ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1) + +}; + /* PHC VCLOCKS */ enum { diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 9daed0aab162..be2755c8d8fd 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -13,14 +13,18 @@ struct tsinfo_req_info { struct tsinfo_reply_data { struct ethnl_reply_data base; struct ethtool_ts_info ts_info; + struct ethtool_ts_stats stats; }; #define TSINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct tsinfo_reply_data, base) +#define ETHTOOL_TS_STAT_CNT \ + (__ETHTOOL_A_TS_STAT_CNT - (ETHTOOL_A_TS_STAT_UNSPEC + 1)) + const struct nla_policy ethnl_tsinfo_get_policy[] = { [ETHTOOL_A_TSINFO_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, @@ -34,6 +38,12 @@ static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; + if (req_base->flags & ETHTOOL_FLAG_STATS && + dev->ethtool_ops->get_ts_stats) { + ethtool_stats_init((u64 *)&data->stats, + sizeof(data->stats) / sizeof(u64)); + dev->ethtool_ops->get_ts_stats(dev, &data->stats); + } ret = __ethtool_get_ts_info(dev, &data->ts_info); ethnl_ops_complete(dev); @@ -79,10 +89,47 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base, } if (ts_info->phc_index >= 0) len += nla_total_size(sizeof(u32)); /* _TSINFO_PHC_INDEX */ + if (req_base->flags & ETHTOOL_FLAG_STATS) + len += nla_total_size(0) + /* _TSINFO_STATS */ + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT; return len; } +static int tsinfo_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) +{ + if (val == ETHTOOL_STAT_NOT_SET) + return 0; + if (nla_put_uint(skb, attrtype, val)) + return -EMSGSIZE; + return 0; +} + +static int tsinfo_put_stats(struct sk_buff *skb, + const struct ethtool_ts_stats *stats) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_TSINFO_STATS); + if (!nest) + return -EMSGSIZE; + + if (tsinfo_put_stat(skb, stats->tx_stats.pkts, + ETHTOOL_A_TS_STAT_TX_PKTS) || + tsinfo_put_stat(skb, stats->tx_stats.lost, + ETHTOOL_A_TS_STAT_TX_LOST) || + tsinfo_put_stat(skb, stats->tx_stats.err, + ETHTOOL_A_TS_STAT_TX_ERR)) + goto err_cancel; + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int tsinfo_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) @@ -119,6 +166,9 @@ static int tsinfo_fill_reply(struct sk_buff *skb, if (ts_info->phc_index >= 0 && nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, ts_info->phc_index)) return -EMSGSIZE; + if (req_base->flags & ETHTOOL_FLAG_STATS && + tsinfo_put_stats(skb, &data->stats)) + return -EMSGSIZE; return 0; } -- cgit v1.2.3 From ff8877b04ef282b2bdb16c9dccc2e42216a34f62 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 5 Apr 2024 22:22:38 -0700 Subject: netlink: specs: ethtool: define header-flags as an enum Recent changes added header flags to the spec. Use an enum instead of defines for more seamless codegen. [Jakub: drop the already applied parts and rewrite message] Signed-off-by: Rahul Rameshbabu Reviewed-by: Dragos Tatulea Link: https://lore.kernel.org/r/20240403212931.128541-6-rrameshbabu@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 1 - include/uapi/linux/ethtool_netlink.h | 11 +++++------ 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index b76916394ec9..87ae7b397984 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -18,7 +18,6 @@ definitions: entries: [] - name: header-flags - enum-name: type: flags entries: [ compact-bitsets, omit-reply, stats ] diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 708272026d80..e06a34cded78 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -117,12 +117,11 @@ enum { /* request header */ -/* use compact bitsets in reply */ -#define ETHTOOL_FLAG_COMPACT_BITSETS (1 << 0) -/* provide optional reply for SET or ACT requests */ -#define ETHTOOL_FLAG_OMIT_REPLY (1 << 1) -/* request statistics, if supported by the driver */ -#define ETHTOOL_FLAG_STATS (1 << 2) +enum ethtool_header_flags { + ETHTOOL_FLAG_COMPACT_BITSETS = 1 << 0, /* use compact bitsets in reply */ + ETHTOOL_FLAG_OMIT_REPLY = 1 << 1, /* provide optional reply for SET or ACT requests */ + ETHTOOL_FLAG_STATS = 1 << 2, /* request statistics, if supported by the driver */ +}; #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \ ETHTOOL_FLAG_OMIT_REPLY | \ -- cgit v1.2.3 From 6916e461e7933d3d003441291c543938f2ccb371 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Thu, 4 Apr 2024 11:29:51 +0200 Subject: net: phy: Introduce ethernet link topology representation Link topologies containing multiple network PHYs attached to the same net_device can be found when using a PHY as a media converter for use with an SFP connector, on which an SFP transceiver containing a PHY can be used. With the current model, the transceiver's PHY can't be used for operations such as cable testing, timestamping, macsec offload, etc. The reason being that most of the logic for these configuration, coming from either ethtool netlink or ioctls tend to use netdev->phydev, which in multi-phy systems will reference the PHY closest to the MAC. Introduce a numbering scheme allowing to enumerate PHY devices that belong to any netdev, which can in turn allow userspace to take more precise decisions with regard to each PHY's configuration. The numbering is maintained per-netdev, in a phy_device_list. The numbering works similarly to a netdevice's ifindex, with identifiers that are only recycled once INT_MAX has been reached. This prevents races that could occur between PHY listing and SFP transceiver removal/insertion. The identifiers are assigned at phy_attach time, as the numbering depends on the netdevice the phy is attached to. The PHY index can be re-used for PHYs that are persistent. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- MAINTAINERS | 2 + drivers/net/phy/Makefile | 2 +- drivers/net/phy/phy_device.c | 7 +++ drivers/net/phy/phy_link_topology.c | 105 +++++++++++++++++++++++++++++++++ include/linux/netdevice.h | 4 +- include/linux/phy.h | 4 ++ include/linux/phy_link_topology.h | 72 ++++++++++++++++++++++ include/linux/phy_link_topology_core.h | 25 ++++++++ include/uapi/linux/ethtool.h | 16 +++++ net/core/dev.c | 9 +++ 10 files changed, 244 insertions(+), 2 deletions(-) create mode 100644 drivers/net/phy/phy_link_topology.c create mode 100644 include/linux/phy_link_topology.h create mode 100644 include/linux/phy_link_topology_core.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 046598b471b7..4745ea94d463 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8015,6 +8015,8 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h +F: include/linux/phy_link_topology.h +F: include/linux/phy_link_topology_core.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 202ed7f450da..1d8be374915f 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o + linkmode.o phy_link_topology.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 6c6ec9475709..452fc8b3406d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -1511,6 +1512,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; + + err = phy_link_topo_add_phy(dev->link_topo, phydev, + PHY_UPSTREAM_MAC, dev); + if (err) + goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1938,6 +1944,7 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; + phy_link_topo_del_phy(dev->link_topo, phydev); } phydev->phylink = NULL; diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c new file mode 100644 index 000000000000..985941c5c558 --- /dev/null +++ b/drivers/net/phy/phy_link_topology.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Infrastructure to handle all PHY devices connected to a given netdev, + * either directly or indirectly attached. + * + * Copyright (c) 2023 Maxime Chevallier + */ + +#include +#include +#include +#include +#include + +struct phy_link_topology *phy_link_topo_create(struct net_device *dev) +{ + struct phy_link_topology *topo; + + topo = kzalloc(sizeof(*topo), GFP_KERNEL); + if (!topo) + return ERR_PTR(-ENOMEM); + + xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); + topo->next_phy_index = 1; + + return topo; +} + +void phy_link_topo_destroy(struct phy_link_topology *topo) +{ + if (!topo) + return; + + xa_destroy(&topo->phys); + kfree(topo); +} + +int phy_link_topo_add_phy(struct phy_link_topology *topo, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + struct phy_device_node *pdn; + int ret; + + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + if (!pdn) + return -ENOMEM; + + pdn->phy = phy; + switch (upt) { + case PHY_UPSTREAM_MAC: + pdn->upstream.netdev = (struct net_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; + break; + case PHY_UPSTREAM_PHY: + pdn->upstream.phydev = (struct phy_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; + break; + default: + ret = -EINVAL; + goto err; + } + pdn->upstream_type = upt; + + /* Attempt to re-use a previously allocated phy_index */ + if (phy->phyindex) { + ret = xa_insert(&topo->phys, phy->phyindex, pdn, GFP_KERNEL); + + /* Errors could be either -ENOMEM or -EBUSY. If the phy has an + * index, and there's another entry at the same index, this is + * unexpected and we still error-out + */ + if (ret) + goto err; + return 0; + } + + ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, xa_limit_32b, + &topo->next_phy_index, GFP_KERNEL); + if (ret) + goto err; + + return 0; + +err: + kfree(pdn); + return ret; +} +EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); + +void phy_link_topo_del_phy(struct phy_link_topology *topo, + struct phy_device *phy) +{ + struct phy_device_node *pdn = xa_erase(&topo->phys, phy->phyindex); + + /* We delete the PHY from the topology, however we don't re-set the + * phy->phyindex field. If the PHY isn't gone, we can re-assign it the + * same index next time it's added back to the topology + */ + + kfree(pdn); +} +EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0c198620ac93..d45f330d083d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include #endif #include - #include #include #include @@ -52,6 +51,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -1974,6 +1974,7 @@ enum netdev_reg_state { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2364,6 +2365,7 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; diff --git a/include/linux/phy.h b/include/linux/phy.h index e6e83304558e..8c848c79b1fd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -550,6 +550,9 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. + * @phyindex: Unique id across the phy's parent tree of phys to address the PHY + * from userspace, similar to ifindex. A zero index means the PHY + * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -650,6 +653,7 @@ struct phy_device { struct device_link *devlink; + u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h new file mode 100644 index 000000000000..6b79feb607e7 --- /dev/null +++ b/include/linux/phy_link_topology.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PHY device list allow maintaining a list of PHY devices that are + * part of a netdevice's link topology. PHYs can for example be chained, + * as is the case when using a PHY that exposes an SFP module, on which an + * SFP transceiver that embeds a PHY is connected. + * + * This list can then be used by userspace to leverage individual PHY + * capabilities. + */ +#ifndef __PHY_LINK_TOPOLOGY_H +#define __PHY_LINK_TOPOLOGY_H + +#include +#include + +struct xarray; +struct phy_device; +struct net_device; +struct sfp_bus; + +struct phy_device_node { + enum phy_upstream upstream_type; + + union { + struct net_device *netdev; + struct phy_device *phydev; + } upstream; + + struct sfp_bus *parent_sfp_bus; + + struct phy_device *phy; +}; + +struct phy_link_topology { + struct xarray phys; + u32 next_phy_index; +}; + +static inline struct phy_device * +phy_link_topo_get_phy(struct phy_link_topology *topo, u32 phyindex) +{ + struct phy_device_node *pdn = xa_load(&topo->phys, phyindex); + + if (pdn) + return pdn->phy; + + return NULL; +} + +#if IS_REACHABLE(CONFIG_PHYLIB) +int phy_link_topo_add_phy(struct phy_link_topology *topo, + struct phy_device *phy, + enum phy_upstream upt, void *upstream); + +void phy_link_topo_del_phy(struct phy_link_topology *lt, struct phy_device *phy); + +#else +static inline int phy_link_topo_add_phy(struct phy_link_topology *topo, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + return 0; +} + +static inline void phy_link_topo_del_phy(struct phy_link_topology *topo, + struct phy_device *phy) +{ +} +#endif + +#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/linux/phy_link_topology_core.h b/include/linux/phy_link_topology_core.h new file mode 100644 index 000000000000..0a6479055745 --- /dev/null +++ b/include/linux/phy_link_topology_core.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PHY_LINK_TOPOLOGY_CORE_H +#define __PHY_LINK_TOPOLOGY_CORE_H + +struct phy_link_topology; + +#if IS_REACHABLE(CONFIG_PHYLIB) + +struct phy_link_topology *phy_link_topo_create(struct net_device *dev); +void phy_link_topo_destroy(struct phy_link_topology *topo); + +#else + +static inline struct phy_link_topology *phy_link_topo_create(struct net_device *dev) +{ + return NULL; +} + +static inline void phy_link_topo_destroy(struct phy_link_topology *topo) +{ +} + +#endif + +#endif /* __PHY_LINK_TOPOLOGY_CORE_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 11fc18988bc2..95c2f09f0d0a 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2268,4 +2268,20 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; + +/** + * enum phy_upstream - Represents the upstream component a given PHY device + * is connected to, as in what is on the other end of the MII bus. Most PHYs + * will be attached to an Ethernet MAC controller, but in some cases, there's + * an intermediate PHY used as a media-converter, which will driver another + * MII interface as its output. + * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, + * or ethernet controller) + * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) + */ +enum phy_upstream { + PHY_UPSTREAM_MAC, + PHY_UPSTREAM_PHY, +}; + #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/dev.c b/net/core/dev.c index 92f5bddbc2de..854a3a28a8d8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,6 +158,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" @@ -10962,6 +10963,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif + dev->link_topo = phy_link_topo_create(dev); + if (IS_ERR(dev->link_topo)) { + dev->link_topo = NULL; + goto free_all; + } + dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); @@ -11050,6 +11057,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; + phy_link_topo_destroy(dev->link_topo); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); -- cgit v1.2.3 From 841942bc62122c59f654f799c2d00ce3fda93efa Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Thu, 4 Apr 2024 11:29:55 +0200 Subject: net: ethtool: Allow passing a phy index for some commands Some netlink commands are target towards ethernet PHYs, to control some of their features. As there's several such commands, add the ability to pass a PHY index in the ethnl request, which will populate the generic ethnl_req_info with the relevant phydev when the command targets a PHY. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 7 ++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.c | 48 ++++++++++++++++++++++++++-- net/ethtool/netlink.h | 5 +++ 4 files changed, 59 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 08d330b0f50f..5dc42f7ce429 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -57,6 +57,7 @@ Structure of this header is ``ETHTOOL_A_HEADER_DEV_INDEX`` u32 device ifindex ``ETHTOOL_A_HEADER_DEV_NAME`` string device name ``ETHTOOL_A_HEADER_FLAGS`` u32 flags common for all requests + ``ETHTOOL_A_HEADER_PHY_INDEX`` u32 phy device index ============================== ====== ============================= ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the @@ -81,6 +82,12 @@ the behaviour is backward compatible, i.e. requests from old clients not aware of the flag should be interpreted the way the client expects. A client must not set flags it does not understand. +``ETHTOOL_A_HEADER_PHY_INDEX`` identifies the Ethernet PHY the message relates to. +As there are numerous commands that are related to PHY configuration, and because +there may be more than one PHY on the link, the PHY index can be passed in the +request for the commands that needs it. It is, however, not mandatory, and if it +is not passed for commands that target a PHY, the net_device.phydev pointer +is used. Bit sets ======== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index e06a34cded78..23e225f00fb0 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -132,6 +132,7 @@ enum { ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ ETHTOOL_A_HEADER_DEV_NAME, /* string */ ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ + ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_HEADER_CNT, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index bd04f28d5cf4..563e94e0cbd8 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -4,6 +4,7 @@ #include #include #include "netlink.h" +#include static struct genl_family ethtool_genl_family; @@ -30,6 +31,24 @@ const struct nla_policy ethnl_header_policy_stats[] = { ETHTOOL_FLAGS_STATS), }; +const struct nla_policy ethnl_header_policy_phy[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_BASIC), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +const struct nla_policy ethnl_header_policy_phy_stats[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_STATS), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + int ethnl_ops_begin(struct net_device *dev) { int ret; @@ -89,8 +108,9 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; + struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; const struct nlattr *devname_attr; + struct phy_device *phydev = NULL; struct net_device *dev = NULL; u32 flags = 0; int ret; @@ -104,7 +124,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ - ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, + ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, NULL, extack); if (ret < 0) return ret; @@ -145,6 +165,30 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } + if (dev) { + if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { + struct nlattr *phy_id; + + phy_id = tb[ETHTOOL_A_HEADER_PHY_INDEX]; + phydev = phy_link_topo_get_phy(dev->link_topo, + nla_get_u32(phy_id)); + if (!phydev) { + NL_SET_BAD_ATTR(extack, phy_id); + return -ENODEV; + } + } else { + /* If we need a PHY but no phy index is specified, fallback + * to dev->phydev + */ + phydev = dev->phydev; + } + } else if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { + NL_SET_ERR_MSG_ATTR(extack, header, + "can't target a PHY without a netdev"); + return -EINVAL; + } + + req_info->phydev = phydev; req_info->dev = dev; req_info->flags = flags; return 0; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 9a333a8d04c1..d57a890b5d9e 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -250,6 +250,7 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types + * @phydev: phy_device connected to @dev this request is for (may be null) * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -259,6 +260,7 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; + struct phy_device *phydev; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -395,9 +397,12 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; +extern const struct ethnl_request_ops ethnl_phy_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; +extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; -- cgit v1.2.3 From 5af3e3876d567fb79a355bec1cb48e432d69b4fb Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sat, 6 Apr 2024 04:05:37 +0300 Subject: devlink: Support setting max_io_eqs Many devices send event notifications for the IO queues, such as tx and rx queues, through event queues. Enable a privileged owner, such as a hypervisor PF, to set the number of IO event queues for the VF and SF during the provisioning stage. example: Get maximum IO event queues of the VF device:: $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 ipsec_packet disabled max_io_eqs 10 Set maximum IO event queues of the VF device:: $ devlink port function set pci/0000:06:00.0/2 max_io_eqs 32 $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 ipsec_packet disabled max_io_eqs 32 Reviewed-by: Jiri Pirko Reviewed-by: Shay Drory Signed-off-by: Parav Pandit Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-port.rst | 33 ++++++++++++++ include/net/devlink.h | 14 ++++++ include/uapi/linux/devlink.h | 1 + net/devlink/port.c | 53 +++++++++++++++++++++++ 4 files changed, 101 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 562f46b41274..9d22d41a7cd1 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -134,6 +134,9 @@ Users may also set the IPsec crypto capability of the function using Users may also set the IPsec packet capability of the function using `devlink port function set ipsec_packet` command. +Users may also set the maximum IO event queues of the function +using `devlink port function set max_io_eqs` command. + Function attributes =================== @@ -295,6 +298,36 @@ policy is processed in software by the kernel. function: hw_addr 00:00:00:00:00:00 ipsec_packet enabled +Maximum IO events queues setup +------------------------------ +When user sets maximum number of IO event queues for a SF or +a VF, such function driver is limited to consume only enforced +number of IO event queues. + +IO event queues deliver events related to IO queues, including network +device transmit and receive queues (txq and rxq) and RDMA Queue Pairs (QPs). +For example, the number of netdevice channels and RDMA device completion +vectors are derived from the function's IO event queues. Usually, the number +of interrupt vectors consumed by the driver is limited by the number of IO +event queues per device, as each of the IO event queues is connected to an +interrupt vector. + +- Get maximum IO event queues of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 ipsec_packet disabled max_io_eqs 10 + +- Set maximum IO event queues of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 max_io_eqs 32 + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 ipsec_packet disabled max_io_eqs 32 + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index 9ac394bdfbe4..bb1af599d101 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1602,6 +1602,14 @@ void devlink_free(struct devlink *devlink); * capability. Should be used by device drivers to * enable/disable ipsec_packet capability of a * function managed by the devlink port. + * @port_fn_max_io_eqs_get: Callback used to get port function's maximum number + * of event queues. Should be used by device drivers to + * report the maximum event queues of a function + * managed by the devlink port. + * @port_fn_max_io_eqs_set: Callback used to set port function's maximum number + * of event queues. Should be used by device drivers to + * configure maximum number of event queues + * of a function managed by the devlink port. * * Note: Driver should return -EOPNOTSUPP if it doesn't support * port function (@port_fn_*) handling for a particular port. @@ -1651,6 +1659,12 @@ struct devlink_port_ops { int (*port_fn_ipsec_packet_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + int (*port_fn_max_io_eqs_get)(struct devlink_port *devlink_port, + u32 *max_eqs, + struct netlink_ext_ack *extack); + int (*port_fn_max_io_eqs_set)(struct devlink_port *devlink_port, + u32 max_eqs, + struct netlink_ext_ack *extack); }; void devlink_port_init(struct devlink *devlink, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 2da0c7eb6710..9401aa343673 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -686,6 +686,7 @@ enum devlink_port_function_attr { DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ DEVLINK_PORT_FN_ATTR_CAPS, /* bitfield32 */ DEVLINK_PORT_FN_ATTR_DEVLINK, /* nested */ + DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, /* u32 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 diff --git a/net/devlink/port.c b/net/devlink/port.c index 118d130d2afd..be9158b4453c 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -16,6 +16,7 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ DEVLINK_PORT_FN_STATE_ACTIVE), [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), + [DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] = { .type = NLA_U32 }, }; #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ @@ -182,6 +183,30 @@ static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, return 0; } +static int devlink_port_fn_max_io_eqs_fill(struct devlink_port *port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + u32 max_io_eqs; + int err; + + if (!port->ops->port_fn_max_io_eqs_get) + return 0; + + err = port->ops->port_fn_max_io_eqs_get(port, &max_io_eqs, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put_u32(msg, DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, max_io_eqs); + if (err) + return err; + *msg_updated = true; + return 0; +} + int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) { if (devlink_nl_put_handle(msg, devlink_port->devlink)) @@ -409,6 +434,18 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, return 0; } +static int +devlink_port_fn_max_io_eqs_set(struct devlink_port *devlink_port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + u32 max_io_eqs; + + max_io_eqs = nla_get_u32(attr); + return devlink_port->ops->port_fn_max_io_eqs_set(devlink_port, + max_io_eqs, extack); +} + static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) @@ -428,6 +465,9 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por if (err) goto out; err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); + if (err) + goto out; + err = devlink_port_fn_max_io_eqs_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_rel_devlink_handle_put(msg, port->devlink, @@ -726,6 +766,12 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, } } } + if (tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] && + !ops->port_fn_max_io_eqs_set) { + NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS], + "Function does not support max_io_eqs setting"); + return -EOPNOTSUPP; + } return 0; } @@ -761,6 +807,13 @@ static int devlink_port_function_set(struct devlink_port *port, return err; } + attr = tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS]; + if (attr) { + err = devlink_port_fn_max_io_eqs_set(port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. -- cgit v1.2.3 From eebab7e3eb4bb906a8ebc3b70d28059ff1d9271c Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Thu, 7 Mar 2024 13:20:06 +1100 Subject: PCI/DOE: Support discovery version 2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe r6.1, sec 6.30.1.1 defines a "DOE Discovery Version" field in the DOE Discovery Request Data Object Contents (3rd DW) as: 15:8 DOE Discovery Version – must be 02h if the Capability Version in the Data Object Exchange Extended Capability is 02h or greater. Add support for the version on devices with the DOE v2 capability. Link: https://lore.kernel.org/r/20240307022006.3657433-1-aik@amd.com Signed-off-by: Alexey Kardashevskiy Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan --- drivers/pci/doe.c | 12 +++++++++--- include/uapi/linux/pci_regs.h | 1 + 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index e3aab5edaf70..652d63df9d22 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -383,11 +383,13 @@ static void pci_doe_task_complete(struct pci_doe_task *task) complete(task->private); } -static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, +static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 capver, u8 *index, u16 *vid, u8 *protocol) { u32 request_pl = FIELD_PREP(PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX, - *index); + *index) | + FIELD_PREP(PCI_DOE_DATA_OBJECT_DISC_REQ_3_VER, + (capver >= 2) ? 2 : 0); __le32 request_pl_le = cpu_to_le32(request_pl); __le32 response_pl_le; u32 response_pl; @@ -421,13 +423,17 @@ static int pci_doe_cache_protocols(struct pci_doe_mb *doe_mb) { u8 index = 0; u8 xa_idx = 0; + u32 hdr = 0; + + pci_read_config_dword(doe_mb->pdev, doe_mb->cap_offset, &hdr); do { int rc; u16 vid; u8 prot; - rc = pci_doe_discovery(doe_mb, &index, &vid, &prot); + rc = pci_doe_discovery(doe_mb, PCI_EXT_CAP_VER(hdr), &index, + &vid, &prot); if (rc) return rc; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index a39193213ff2..fbca743b2b86 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1144,6 +1144,7 @@ #define PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH 0x0003ffff #define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX 0x000000ff +#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_VER 0x0000ff00 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID 0x0000ffff #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000 -- cgit v1.2.3 From 65f35aa76c0e21b0243fd734e513fd2263f22a18 Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Tue, 9 Apr 2024 16:25:16 -0700 Subject: ethtool: update tsinfo statistics attribute docs with correct type nla_put_uint can either write a u32 or u64 netlink attribute value. The size depends on whether the value can be represented with a u32 or requires a u64. Use a uint annotation in various documentation to represent this. Signed-off-by: Rahul Rameshbabu Link: https://lore.kernel.org/r/20240409232520.237613-2-rrameshbabu@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 6 +++--- include/uapi/linux/ethtool_netlink.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 5dc42f7ce429..4e63d3708ed9 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1254,9 +1254,9 @@ would be empty (no bit set). Additional hardware timestamping statistics response contents: ===================================== ====== =================================== - ``ETHTOOL_A_TS_STAT_TX_PKTS`` u64 Packets with Tx HW timestamps - ``ETHTOOL_A_TS_STAT_TX_LOST`` u64 Tx HW timestamp not arrived count - ``ETHTOOL_A_TS_STAT_TX_ERR`` u64 HW error request Tx timestamp count + ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx HW timestamps + ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp not arrived count + ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request Tx timestamp count ===================================== ====== =================================== CABLE_TEST diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 23e225f00fb0..b4f0d233d048 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -488,9 +488,9 @@ enum { enum { ETHTOOL_A_TS_STAT_UNSPEC, - ETHTOOL_A_TS_STAT_TX_PKTS, /* u64 */ - ETHTOOL_A_TS_STAT_TX_LOST, /* u64 */ - ETHTOOL_A_TS_STAT_TX_ERR, /* u64 */ + ETHTOOL_A_TS_STAT_TX_PKTS, /* uint */ + ETHTOOL_A_TS_STAT_TX_LOST, /* uint */ + ETHTOOL_A_TS_STAT_TX_ERR, /* uint */ /* add new constants above here */ __ETHTOOL_A_TS_STAT_CNT, -- cgit v1.2.3 From 699c23f02c65cbfc3e638f14ce0d70c23a2e1f02 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 9 Apr 2024 21:35:27 -0700 Subject: bpf: Add bpf_link support for sk_msg and sk_skb progs Add bpf_link support for sk_msg and sk_skb programs. We have an internal request to support bpf_link for sk_msg programs so user space can have a uniform handling with bpf_link based libbpf APIs. Using bpf_link based libbpf API also has a benefit which makes system robust by decoupling prog life cycle and attachment life cycle. Reviewed-by: John Fastabend Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20240410043527.3737160-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 + include/linux/skmsg.h | 4 + include/uapi/linux/bpf.h | 5 + kernel/bpf/syscall.c | 4 + net/core/sock_map.c | 263 ++++++++++++++++++++++++++++++++++++++--- tools/include/uapi/linux/bpf.h | 5 + 6 files changed, 271 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 62762390c93d..5034c1b4ded7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2996,6 +2996,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); @@ -3094,6 +3095,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..9c8dd4c01412 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,10 @@ struct sk_psock_progs { struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; + struct bpf_link *msg_parser_link; + struct bpf_link *stream_parser_link; + struct bpf_link *stream_verdict_link; + struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6fe9f11c8abe..cee0a7915c08 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1135,6 +1135,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, __MAX_BPF_LINK_TYPE, }; @@ -6724,6 +6725,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e44c276e8617..7d392ec83655 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5213,6 +5213,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_SK_SKB: + ret = sock_map_link_create(attr, prog); + break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 27d733c0f65e..63c016b4c169 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -24,8 +24,16 @@ struct bpf_stab { #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +/* This mutex is used to + * - protect race between prog/link attach/detach and link prog update, and + * - protect race between releasing and accessing map in bpf_link. + * A single global mutex lock is used since it is expected contention is low. + */ +static DEFINE_MUTEX(sockmap_mutex); + static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which); + struct bpf_prog *old, struct bpf_link *link, + u32 which); static struct sk_psock_progs *sock_map_progs(struct bpf_map *map); static struct bpf_map *sock_map_alloc(union bpf_attr *attr) @@ -71,7 +79,9 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + mutex_lock(&sockmap_mutex); + ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type); + mutex_unlock(&sockmap_mutex); fdput(f); return ret; } @@ -103,7 +113,9 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) goto put_prog; } - ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); + mutex_lock(&sockmap_mutex); + ret = sock_map_prog_update(map, NULL, prog, NULL, attr->attach_type); + mutex_unlock(&sockmap_mutex); put_prog: bpf_prog_put(prog); put_map: @@ -1454,55 +1466,84 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) return NULL; } -static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog, - u32 which) +static int sock_map_prog_link_lookup(struct bpf_map *map, struct bpf_prog ***pprog, + struct bpf_link ***plink, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **cur_pprog; + struct bpf_link **cur_plink; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - *pprog = &progs->msg_parser; + cur_pprog = &progs->msg_parser; + cur_plink = &progs->msg_parser_link; break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: - *pprog = &progs->stream_parser; + cur_pprog = &progs->stream_parser; + cur_plink = &progs->stream_parser_link; break; #endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; - *pprog = &progs->stream_verdict; + cur_pprog = &progs->stream_verdict; + cur_plink = &progs->stream_verdict_link; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; - *pprog = &progs->skb_verdict; + cur_pprog = &progs->skb_verdict; + cur_plink = &progs->skb_verdict_link; break; default: return -EOPNOTSUPP; } + *pprog = cur_pprog; + if (plink) + *plink = cur_plink; return 0; } +/* Handle the following four cases: + * prog_attach: prog != NULL, old == NULL, link == NULL + * prog_detach: prog == NULL, old != NULL, link == NULL + * link_attach: prog != NULL, old == NULL, link != NULL + * link_detach: prog == NULL, old != NULL, link != NULL + */ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which) + struct bpf_prog *old, struct bpf_link *link, + u32 which) { struct bpf_prog **pprog; + struct bpf_link **plink; int ret; - ret = sock_map_prog_lookup(map, &pprog, which); + ret = sock_map_prog_link_lookup(map, &pprog, &plink, which); if (ret) return ret; - if (old) - return psock_replace_prog(pprog, prog, old); + /* for prog_attach/prog_detach/link_attach, return error if a bpf_link + * exists for that prog. + */ + if ((!link || prog) && *plink) + return -EBUSY; - psock_set_prog(pprog, prog); - return 0; + if (old) { + ret = psock_replace_prog(pprog, prog, old); + if (!ret) + *plink = NULL; + } else { + psock_set_prog(pprog, prog); + if (link) + *plink = link; + } + + return ret; } int sock_map_bpf_prog_query(const union bpf_attr *attr, @@ -1527,7 +1568,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, rcu_read_lock(); - ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type); + ret = sock_map_prog_link_lookup(map, &pprog, NULL, attr->query.attach_type); if (ret) goto end; @@ -1657,6 +1698,196 @@ void sock_map_close(struct sock *sk, long timeout) } EXPORT_SYMBOL_GPL(sock_map_close); +struct sockmap_link { + struct bpf_link link; + struct bpf_map *map; + enum bpf_attach_type attach_type; +}; + +static void sock_map_link_release(struct bpf_link *link) +{ + struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + + mutex_lock(&sockmap_mutex); + if (!sockmap_link->map) + goto out; + + WARN_ON_ONCE(sock_map_prog_update(sockmap_link->map, NULL, link->prog, link, + sockmap_link->attach_type)); + + bpf_map_put_with_uref(sockmap_link->map); + sockmap_link->map = NULL; +out: + mutex_unlock(&sockmap_mutex); +} + +static int sock_map_link_detach(struct bpf_link *link) +{ + sock_map_link_release(link); + return 0; +} + +static void sock_map_link_dealloc(struct bpf_link *link) +{ + kfree(link); +} + +/* Handle the following two cases: + * case 1: link != NULL, prog != NULL, old != NULL + * case 2: link != NULL, prog != NULL, old == NULL + */ +static int sock_map_link_update_prog(struct bpf_link *link, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + struct bpf_prog **pprog, *old_link_prog; + struct bpf_link **plink; + int ret = 0; + + mutex_lock(&sockmap_mutex); + + /* If old prog is not NULL, ensure old prog is the same as link->prog. */ + if (old && link->prog != old) { + ret = -EPERM; + goto out; + } + /* Ensure link->prog has the same type/attach_type as the new prog. */ + if (link->prog->type != prog->type || + link->prog->expected_attach_type != prog->expected_attach_type) { + ret = -EINVAL; + goto out; + } + + ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink, + sockmap_link->attach_type); + if (ret) + goto out; + + /* return error if the stored bpf_link does not match the incoming bpf_link. */ + if (link != *plink) { + ret = -EBUSY; + goto out; + } + + if (old) { + ret = psock_replace_prog(pprog, prog, old); + if (ret) + goto out; + } else { + psock_set_prog(pprog, prog); + } + + bpf_prog_inc(prog); + old_link_prog = xchg(&link->prog, prog); + bpf_prog_put(old_link_prog); + +out: + mutex_unlock(&sockmap_mutex); + return ret; +} + +static u32 sock_map_link_get_map_id(const struct sockmap_link *sockmap_link) +{ + u32 map_id = 0; + + mutex_lock(&sockmap_mutex); + if (sockmap_link->map) + map_id = sockmap_link->map->id; + mutex_unlock(&sockmap_mutex); + return map_id; +} + +static int sock_map_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + u32 map_id = sock_map_link_get_map_id(sockmap_link); + + info->sockmap.map_id = map_id; + info->sockmap.attach_type = sockmap_link->attach_type; + return 0; +} + +static void sock_map_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + u32 map_id = sock_map_link_get_map_id(sockmap_link); + + seq_printf(seq, "map_id:\t%u\n", map_id); + seq_printf(seq, "attach_type:\t%u\n", sockmap_link->attach_type); +} + +static const struct bpf_link_ops sock_map_link_ops = { + .release = sock_map_link_release, + .dealloc = sock_map_link_dealloc, + .detach = sock_map_link_detach, + .update_prog = sock_map_link_update_prog, + .fill_link_info = sock_map_link_fill_info, + .show_fdinfo = sock_map_link_show_fdinfo, +}; + +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct sockmap_link *sockmap_link; + enum bpf_attach_type attach_type; + struct bpf_map *map; + int ret; + + if (attr->link_create.flags) + return -EINVAL; + + map = bpf_map_get_with_uref(attr->link_create.target_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) { + ret = -EINVAL; + goto out; + } + + sockmap_link = kzalloc(sizeof(*sockmap_link), GFP_USER); + if (!sockmap_link) { + ret = -ENOMEM; + goto out; + } + + attach_type = attr->link_create.attach_type; + bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog); + sockmap_link->map = map; + sockmap_link->attach_type = attach_type; + + ret = bpf_link_prime(&sockmap_link->link, &link_primer); + if (ret) { + kfree(sockmap_link); + goto out; + } + + mutex_lock(&sockmap_mutex); + ret = sock_map_prog_update(map, prog, NULL, &sockmap_link->link, attach_type); + mutex_unlock(&sockmap_mutex); + if (ret) { + bpf_link_cleanup(&link_primer); + goto out; + } + + /* Increase refcnt for the prog since when old prog is replaced with + * psock_replace_prog() and psock_set_prog() its refcnt will be decreased. + * + * Actually, we do not need to increase refcnt for the prog since bpf_link + * will hold a reference. But in order to have less complexity w.r.t. + * replacing/setting prog, let us increase the refcnt to make things simpler. + */ + bpf_prog_inc(prog); + + return bpf_link_settle(&link_primer); + +out: + bpf_map_put_with_uref(map); + return ret; +} + static int sock_map_iter_attach_target(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6fe9f11c8abe..cee0a7915c08 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1135,6 +1135,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, __MAX_BPF_LINK_TYPE, }; @@ -6724,6 +6725,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From b46271ec40a05580d55f917c9ac52cb93553160a Mon Sep 17 00:00:00 2001 From: Elizabeth Figura Date: Thu, 28 Mar 2024 19:05:53 -0500 Subject: ntsync: Introduce NTSYNC_IOC_CREATE_SEM. This corresponds to the NT syscall NtCreateSemaphore(). Semaphores are one of three types of object to be implemented in this driver, the others being mutexes and events. An NT semaphore contains a 32-bit counter, and is signaled and can be acquired when the counter is nonzero. The counter has a maximum value which is specified at creation time. The initial value of the semaphore is also specified at creation time. There are no restrictions on the maximum and initial value. Each object is exposed as an file, to which any number of fds may be opened. When all fds are closed, the object is deleted. Objects hold a pointer to the ntsync_device that created them. The device's reference count is driven by struct file. Signed-off-by: Elizabeth Figura Link: https://lore.kernel.org/r/20240329000621.148791-3-zfigura@codeweavers.com Signed-off-by: Greg Kroah-Hartman --- Documentation/userspace-api/ioctl/ioctl-number.rst | 2 + drivers/misc/ntsync.c | 131 +++++++++++++++++++++ include/uapi/linux/ntsync.h | 21 ++++ 3 files changed, 154 insertions(+) create mode 100644 include/uapi/linux/ntsync.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index c472423412bf..a141e8e65c5d 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -174,6 +174,8 @@ Code Seq# Include File Comments 'M' 00-0F drivers/video/fsl-diu-fb.h conflict! 'N' 00-1F drivers/usb/scanner.h 'N' 40-7F drivers/block/nvme.c +'N' 80-8F uapi/linux/ntsync.h NT synchronization primitives + 'O' 00-06 mtd/ubi-user.h UBI 'P' all linux/soundcard.h conflict! 'P' 60-6F sound/sscape_ioctl.h conflict! diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index bd76e653d83e..20158ec148bc 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -5,26 +5,157 @@ * Copyright (C) 2024 Elizabeth Figura */ +#include +#include #include #include #include +#include +#include #define NTSYNC_NAME "ntsync" +enum ntsync_type { + NTSYNC_TYPE_SEM, +}; + +/* + * Individual synchronization primitives are represented by + * struct ntsync_obj, and each primitive is backed by a file. + * + * The whole namespace is represented by a struct ntsync_device also + * backed by a file. + * + * Both rely on struct file for reference counting. Individual + * ntsync_obj objects take a reference to the device when created. + */ + +struct ntsync_obj { + enum ntsync_type type; + + union { + struct { + __u32 count; + __u32 max; + } sem; + } u; + + struct file *file; + struct ntsync_device *dev; +}; + +struct ntsync_device { + struct file *file; +}; + +static int ntsync_obj_release(struct inode *inode, struct file *file) +{ + struct ntsync_obj *obj = file->private_data; + + fput(obj->dev->file); + kfree(obj); + + return 0; +} + +static const struct file_operations ntsync_obj_fops = { + .owner = THIS_MODULE, + .release = ntsync_obj_release, + .llseek = no_llseek, +}; + +static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev, + enum ntsync_type type) +{ + struct ntsync_obj *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) + return NULL; + obj->type = type; + obj->dev = dev; + get_file(dev->file); + + return obj; +} + +static int ntsync_obj_get_fd(struct ntsync_obj *obj) +{ + struct file *file; + int fd; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + file = anon_inode_getfile("ntsync", &ntsync_obj_fops, obj, O_RDWR); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + obj->file = file; + fd_install(fd, file); + + return fd; +} + +static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp) +{ + struct ntsync_sem_args __user *user_args = argp; + struct ntsync_sem_args args; + struct ntsync_obj *sem; + int fd; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + if (args.count > args.max) + return -EINVAL; + + sem = ntsync_alloc_obj(dev, NTSYNC_TYPE_SEM); + if (!sem) + return -ENOMEM; + sem->u.sem.count = args.count; + sem->u.sem.max = args.max; + fd = ntsync_obj_get_fd(sem); + if (fd < 0) { + kfree(sem); + return fd; + } + + return put_user(fd, &user_args->sem); +} + static int ntsync_char_open(struct inode *inode, struct file *file) { + struct ntsync_device *dev; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + file->private_data = dev; + dev->file = file; return nonseekable_open(inode, file); } static int ntsync_char_release(struct inode *inode, struct file *file) { + struct ntsync_device *dev = file->private_data; + + kfree(dev); + return 0; } static long ntsync_char_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { + struct ntsync_device *dev = file->private_data; + void __user *argp = (void __user *)parm; + switch (cmd) { + case NTSYNC_IOC_CREATE_SEM: + return ntsync_create_sem(dev, argp); default: return -ENOIOCTLCMD; } diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h new file mode 100644 index 000000000000..6a4867a6c97b --- /dev/null +++ b/include/uapi/linux/ntsync.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Kernel support for NT synchronization primitive emulation + * + * Copyright (C) 2021-2022 Elizabeth Figura + */ + +#ifndef __LINUX_NTSYNC_H +#define __LINUX_NTSYNC_H + +#include + +struct ntsync_sem_args { + __u32 sem; + __u32 count; + __u32 max; +}; + +#define NTSYNC_IOC_CREATE_SEM _IOWR('N', 0x80, struct ntsync_sem_args) + +#endif -- cgit v1.2.3 From dc806bd48abc1b8a4ae72709a37e65db42a32048 Mon Sep 17 00:00:00 2001 From: Elizabeth Figura Date: Thu, 28 Mar 2024 19:05:54 -0500 Subject: ntsync: Introduce NTSYNC_IOC_SEM_POST. This corresponds to the NT syscall NtReleaseSemaphore(). This increases the semaphore's internal counter by the given value, and returns the previous value. If the counter would overflow the defined maximum, the function instead fails and returns -EOVERFLOW. Signed-off-by: Elizabeth Figura Link: https://lore.kernel.org/r/20240329000621.148791-4-zfigura@codeweavers.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/ntsync.c | 72 +++++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/ntsync.h | 2 ++ 2 files changed, 71 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 20158ec148bc..3c2f743c58b0 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -10,7 +10,9 @@ #include #include #include +#include #include +#include #include #define NTSYNC_NAME "ntsync" @@ -31,23 +33,70 @@ enum ntsync_type { */ struct ntsync_obj { + spinlock_t lock; + enum ntsync_type type; + struct file *file; + struct ntsync_device *dev; + + /* The following fields are protected by the object lock. */ union { struct { __u32 count; __u32 max; } sem; } u; - - struct file *file; - struct ntsync_device *dev; }; struct ntsync_device { struct file *file; }; +/* + * Actually change the semaphore state, returning -EOVERFLOW if it is made + * invalid. + */ +static int post_sem_state(struct ntsync_obj *sem, __u32 count) +{ + __u32 sum; + + lockdep_assert_held(&sem->lock); + + if (check_add_overflow(sem->u.sem.count, count, &sum) || + sum > sem->u.sem.max) + return -EOVERFLOW; + + sem->u.sem.count = sum; + return 0; +} + +static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp) +{ + __u32 __user *user_args = argp; + __u32 prev_count; + __u32 args; + int ret; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + if (sem->type != NTSYNC_TYPE_SEM) + return -EINVAL; + + spin_lock(&sem->lock); + + prev_count = sem->u.sem.count; + ret = post_sem_state(sem, args); + + spin_unlock(&sem->lock); + + if (!ret && put_user(prev_count, user_args)) + ret = -EFAULT; + + return ret; +} + static int ntsync_obj_release(struct inode *inode, struct file *file) { struct ntsync_obj *obj = file->private_data; @@ -58,9 +107,25 @@ static int ntsync_obj_release(struct inode *inode, struct file *file) return 0; } +static long ntsync_obj_ioctl(struct file *file, unsigned int cmd, + unsigned long parm) +{ + struct ntsync_obj *obj = file->private_data; + void __user *argp = (void __user *)parm; + + switch (cmd) { + case NTSYNC_IOC_SEM_POST: + return ntsync_sem_post(obj, argp); + default: + return -ENOIOCTLCMD; + } +} + static const struct file_operations ntsync_obj_fops = { .owner = THIS_MODULE, .release = ntsync_obj_release, + .unlocked_ioctl = ntsync_obj_ioctl, + .compat_ioctl = compat_ptr_ioctl, .llseek = no_llseek, }; @@ -75,6 +140,7 @@ static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev, obj->type = type; obj->dev = dev; get_file(dev->file); + spin_lock_init(&obj->lock); return obj; } diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index 6a4867a6c97b..dcfa38fdc93c 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -18,4 +18,6 @@ struct ntsync_sem_args { #define NTSYNC_IOC_CREATE_SEM _IOWR('N', 0x80, struct ntsync_sem_args) +#define NTSYNC_IOC_SEM_POST _IOWR('N', 0x81, __u32) + #endif -- cgit v1.2.3 From 18d82cde743237def9f80171e32be1153f5cadac Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 10 Apr 2024 11:48:24 +0200 Subject: mptcp: add last time fields in mptcp_info This patch adds "last time" fields last_data_sent, last_data_recv and last_ack_recv in struct mptcp_sock to record the last time data_sent, data_recv and ack_recv happened. They all are initialized as tcp_jiffies32 in __mptcp_init_sock(), and updated as tcp_jiffies32 too when data is sent in __subflow_push_pending(), data is received in __mptcp_move_skbs_from_subflow(), and ack is received in ack_update_msk(). Similar to tcpi_last_data_sent, tcpi_last_data_recv and tcpi_last_ack_recv exposed with TCP, this patch exposes the last time "an action happened" for MPTCP in mptcp_info, named mptcpi_last_data_sent, mptcpi_last_data_recv and mptcpi_last_ack_recv, calculated in mptcp_diag_fill_info() as the time deltas between now and the newly added last time fields in mptcp_sock. Since msk->last_ack_recv needs to be protected by mptcp_data_lock/unlock, and lock_sock_fast can sleep and be quite slow, move the entire mptcp_data_lock/unlock block after the lock/unlock_sock_fast block. Then mptcpi_last_data_sent and mptcpi_last_data_recv are set in lock/unlock_sock_fast block, while mptcpi_last_ack_recv is set in mptcp_data_lock/unlock block, which is protected by a spinlock and should not block for too long. Also add three reserved bytes in struct mptcp_info not to have holes in this structure exposed to userspace. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/446 Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240410-upstream-net-next-20240405-mptcp-last-time-info-v2-1-f95bd6b33e51@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 4 ++++ net/mptcp/options.c | 1 + net/mptcp/protocol.c | 7 +++++++ net/mptcp/protocol.h | 3 +++ net/mptcp/sockopt.c | 16 +++++++++++----- 5 files changed, 26 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 74cfe496891e..67d015df8893 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -58,6 +58,10 @@ struct mptcp_info { __u64 mptcpi_bytes_received; __u64 mptcpi_bytes_acked; __u8 mptcpi_subflows_total; + __u8 reserved[3]; + __u32 mptcpi_last_data_sent; + __u32 mptcpi_last_data_recv; + __u32 mptcpi_last_ack_recv; }; /* MPTCP Reset reason codes, rfc8684 */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 27ca42c77b02..8e8dcfbc2993 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1068,6 +1068,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } + msk->last_ack_recv = tcp_jiffies32; mptcp_data_unlock(sk); trace_ack_update_msk(mp_opt->data_ack, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 995b53cd021c..f8bc34f0d973 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -706,6 +706,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } while (more_data_avail); + if (moved > 0) + msk->last_data_recv = tcp_jiffies32; *bytes += moved; return done; } @@ -1556,6 +1558,8 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, err = copied; out: + if (err > 0) + msk->last_data_sent = tcp_jiffies32; return err; } @@ -2793,6 +2797,9 @@ static void __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; msk->subflow_id = 1; + msk->last_data_sent = tcp_jiffies32; + msk->last_data_recv = tcp_jiffies32; + msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 46f4655b7123..fdfa843e2d88 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -282,6 +282,9 @@ struct mptcp_sock { u64 bytes_acked; u64 snd_una; u64 wnd_end; + u32 last_data_sent; + u32 last_data_recv; + u32 last_ack_recv; unsigned long timer_ival; u32 token; int rmem_released; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 9d5d42a77bcc..1fea43f5b6f3 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -898,6 +898,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) struct sock *sk = (struct sock *)msk; u32 flags = 0; bool slow; + u32 now; memset(info, 0, sizeof(*info)); @@ -926,11 +927,6 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; - mptcp_data_lock(sk); - info->mptcpi_snd_una = msk->snd_una; - info->mptcpi_rcv_nxt = msk->ack_seq; - info->mptcpi_bytes_acked = msk->bytes_acked; - mptcp_data_unlock(sk); slow = lock_sock_fast(sk); info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); @@ -942,7 +938,17 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_bytes_retrans = msk->bytes_retrans; info->mptcpi_subflows_total = info->mptcpi_subflows + __mptcp_has_initial_subflow(msk); + now = tcp_jiffies32; + info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent); + info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv); unlock_sock_fast(sk, slow); + + mptcp_data_lock(sk); + info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv); + info->mptcpi_snd_una = msk->snd_una; + info->mptcpi_rcv_nxt = msk->ack_seq; + info->mptcpi_bytes_acked = msk->bytes_acked; + mptcp_data_unlock(sk); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); -- cgit v1.2.3 From 2abcd952e1999d0f1006068c455a524bec37883d Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 10 Apr 2024 12:24:38 +0000 Subject: media: dvb: Fix dtvs_stats packing. The structure is packed, which requires that all its fields need to be also packed. ./include/uapi/linux/dvb/frontend.h:854:2: warning: field within 'struct dtv_stats' is less aligned than 'union dtv_stats::(anonymous at ./include/uapi/linux/dvb/frontend.h:854:2)' and is usually due to 'struct dtv_stats' being packed, which can lead to unaligned accesses [-Wunaligned-access] Explicitly set the inner union as packed. Marking the inner union as 'packed' does not change the layout, since the whole struct is already packed, it just silences the clang warning. See also this llvm discussion: https://github.com/llvm/llvm-project/issues/55520 Signed-off-by: Ricardo Ribalda Signed-off-by: Hans Verkuil --- include/uapi/linux/dvb/frontend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 7e0983b987c2..8d38c6befda8 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -854,7 +854,7 @@ struct dtv_stats { union { __u64 uvalue; /* for counters and relative scales */ __s64 svalue; /* for 0.001 dB measures */ - }; + } __attribute__ ((packed)); } __attribute__ ((packed)); -- cgit v1.2.3 From 81741e804ef4692e8a6741380352625397a3288b Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 10 Apr 2024 12:24:39 +0000 Subject: media: videodev2: Fix v4l2_ext_control packing. The structure is packed, which requires that all its fields need to be also packed. ./include/uapi/linux/videodev2.h:1810:2: warning: field within 'struct v4l2_ext_control' is less aligned than 'union v4l2_ext_control::(anonymous at ./include/uapi/linux/videodev2.h:1810:2)' and is usually due to 'struct v4l2_ext_control' being packed, which can lead to unaligned accesses [-Wunaligned-access] Explicitly set the inner union as packed. Marking the inner union as 'packed' does not change the layout, since the whole struct is already packed, it just silences the clang warning. See also this llvm discussion: https://github.com/llvm/llvm-project/issues/55520 Signed-off-by: Ricardo Ribalda Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 2663213b76a4..bf12860d570a 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1842,7 +1842,7 @@ struct v4l2_ext_control { struct v4l2_ctrl_hdr10_cll_info __user *p_hdr10_cll_info; struct v4l2_ctrl_hdr10_mastering_display __user *p_hdr10_mastering_display; void __user *ptr; - }; + } __attribute__ ((packed)); } __attribute__ ((packed)); struct v4l2_ext_controls { -- cgit v1.2.3 From 0f21a9574b1d04afbf818a3e6a60cb95eb04a616 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 28 Mar 2024 17:09:35 -0400 Subject: io_uring: Avoid anonymous enums in io_uring uapi While valid C, anonymous enums confuse Cython (Python to C translator), as reported by Ritesh (YoSTEALTH) [1] . Since people rely on it when building against liburing and we want to keep this header in sync with the library version, let's name the existing enums in the uapi header. [1] https://github.com/cython/cython/issues/3240 Signed-off-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20240328210935.25640-1-krisman@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 7bd10201a02b..a7f847543a7f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -115,7 +115,7 @@ struct io_uring_sqe { */ #define IORING_FILE_INDEX_ALLOC (~0U) -enum { +enum io_uring_sqe_flags_bit { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, IOSQE_IO_LINK_BIT, @@ -374,7 +374,7 @@ enum io_uring_op { /* * IORING_OP_MSG_RING command types, stored in sqe->addr */ -enum { +enum io_uring_msg_ring_flags { IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ IORING_MSG_SEND_FD, /* send a registered fd to another ring */ }; @@ -425,9 +425,7 @@ struct io_uring_cqe { #define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) #define IORING_CQE_F_NOTIF (1U << 3) -enum { - IORING_CQE_BUFFER_SHIFT = 16, -}; +#define IORING_CQE_BUFFER_SHIFT 16 /* * Magic offsets for the application to mmap the data it needs @@ -526,7 +524,7 @@ struct io_uring_params { /* * io_uring_register(2) opcodes and arguments */ -enum { +enum io_uring_register_op { IORING_REGISTER_BUFFERS = 0, IORING_UNREGISTER_BUFFERS = 1, IORING_REGISTER_FILES = 2, @@ -583,7 +581,7 @@ enum { }; /* io-wq worker categories */ -enum { +enum io_wq_type { IO_WQ_BOUND, IO_WQ_UNBOUND, }; @@ -688,7 +686,7 @@ struct io_uring_buf_ring { * IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT) * to get a virtual mapping for the ring. */ -enum { +enum io_uring_register_pbuf_ring_flags { IOU_PBUF_RING_MMAP = 1, }; @@ -719,7 +717,7 @@ struct io_uring_napi { /* * io_uring_restriction->opcode values */ -enum { +enum io_uring_register_restriction_op { /* Allow an io_uring_register(2) opcode */ IORING_RESTRICTION_REGISTER_OP = 0, @@ -775,7 +773,7 @@ struct io_uring_recvmsg_out { /* * Argument for IORING_OP_URING_CMD when file is a socket */ -enum { +enum io_uring_socket_op { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, SOCKET_URING_OP_GETSOCKOPT, -- cgit v1.2.3 From 8c467f3300591a206fa8dcc6988d768910799872 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Wed, 17 Apr 2024 19:37:35 +0200 Subject: VT: Use macros to define ioctls All other headers use _IOC() macros to describe ioctls for a long time now. This header is stuck in the last century. Simply use the _IO() macro. No other changes. Signed-off-by: Alexey Gladkov Link: https://lore.kernel.org/r/e4229fe2933a003341e338b558ab1ea8b63a51f6.1713375378.git.legion@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/kd.h | 96 +++++++++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 47 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h index 6b384065c013..8ddb2219a84b 100644 --- a/include/uapi/linux/kd.h +++ b/include/uapi/linux/kd.h @@ -5,60 +5,61 @@ #include /* 0x4B is 'K', to avoid collision with termios and vt */ +#define KD_IOCTL_BASE 'K' -#define GIO_FONT 0x4B60 /* gets font in expanded form */ -#define PIO_FONT 0x4B61 /* use font in expanded form */ +#define GIO_FONT _IO(KD_IOCTL_BASE, 0x60) /* gets font in expanded form */ +#define PIO_FONT _IO(KD_IOCTL_BASE, 0x61) /* use font in expanded form */ -#define GIO_FONTX 0x4B6B /* get font using struct consolefontdesc */ -#define PIO_FONTX 0x4B6C /* set font using struct consolefontdesc */ +#define GIO_FONTX _IO(KD_IOCTL_BASE, 0x6B) /* get font using struct consolefontdesc */ +#define PIO_FONTX _IO(KD_IOCTL_BASE, 0x6C) /* set font using struct consolefontdesc */ struct consolefontdesc { unsigned short charcount; /* characters in font (256 or 512) */ unsigned short charheight; /* scan lines per character (1-32) */ char __user *chardata; /* font data in expanded form */ }; -#define PIO_FONTRESET 0x4B6D /* reset to default font */ +#define PIO_FONTRESET _IO(KD_IOCTL_BASE, 0x6D) /* reset to default font */ -#define GIO_CMAP 0x4B70 /* gets colour palette on VGA+ */ -#define PIO_CMAP 0x4B71 /* sets colour palette on VGA+ */ +#define GIO_CMAP _IO(KD_IOCTL_BASE, 0x70) /* gets colour palette on VGA+ */ +#define PIO_CMAP _IO(KD_IOCTL_BASE, 0x71) /* sets colour palette on VGA+ */ -#define KIOCSOUND 0x4B2F /* start sound generation (0 for off) */ -#define KDMKTONE 0x4B30 /* generate tone */ +#define KIOCSOUND _IO(KD_IOCTL_BASE, 0x2F) /* start sound generation (0 for off) */ +#define KDMKTONE _IO(KD_IOCTL_BASE, 0x30) /* generate tone */ -#define KDGETLED 0x4B31 /* return current led state */ -#define KDSETLED 0x4B32 /* set led state [lights, not flags] */ +#define KDGETLED _IO(KD_IOCTL_BASE, 0x31) /* return current led state */ +#define KDSETLED _IO(KD_IOCTL_BASE, 0x32) /* set led state [lights, not flags] */ #define LED_SCR 0x01 /* scroll lock led */ #define LED_NUM 0x02 /* num lock led */ #define LED_CAP 0x04 /* caps lock led */ -#define KDGKBTYPE 0x4B33 /* get keyboard type */ +#define KDGKBTYPE _IO(KD_IOCTL_BASE, 0x33) /* get keyboard type */ #define KB_84 0x01 #define KB_101 0x02 /* this is what we always answer */ #define KB_OTHER 0x03 -#define KDADDIO 0x4B34 /* add i/o port as valid */ -#define KDDELIO 0x4B35 /* del i/o port as valid */ -#define KDENABIO 0x4B36 /* enable i/o to video board */ -#define KDDISABIO 0x4B37 /* disable i/o to video board */ +#define KDADDIO _IO(KD_IOCTL_BASE, 0x34) /* add i/o port as valid */ +#define KDDELIO _IO(KD_IOCTL_BASE, 0x35) /* del i/o port as valid */ +#define KDENABIO _IO(KD_IOCTL_BASE, 0x36) /* enable i/o to video board */ +#define KDDISABIO _IO(KD_IOCTL_BASE, 0x37) /* disable i/o to video board */ -#define KDSETMODE 0x4B3A /* set text/graphics mode */ +#define KDSETMODE _IO(KD_IOCTL_BASE, 0x3A) /* set text/graphics mode */ #define KD_TEXT 0x00 #define KD_GRAPHICS 0x01 #define KD_TEXT0 0x02 /* obsolete */ #define KD_TEXT1 0x03 /* obsolete */ -#define KDGETMODE 0x4B3B /* get current mode */ +#define KDGETMODE _IO(KD_IOCTL_BASE, 0x3B) /* get current mode */ -#define KDMAPDISP 0x4B3C /* map display into address space */ -#define KDUNMAPDISP 0x4B3D /* unmap display from address space */ +#define KDMAPDISP _IO(KD_IOCTL_BASE, 0x3C) /* map display into address space */ +#define KDUNMAPDISP _IO(KD_IOCTL_BASE, 0x3D) /* unmap display from address space */ typedef char scrnmap_t; #define E_TABSZ 256 -#define GIO_SCRNMAP 0x4B40 /* get screen mapping from kernel */ -#define PIO_SCRNMAP 0x4B41 /* put screen mapping table in kernel */ -#define GIO_UNISCRNMAP 0x4B69 /* get full Unicode screen mapping */ -#define PIO_UNISCRNMAP 0x4B6A /* set full Unicode screen mapping */ +#define GIO_SCRNMAP _IO(KD_IOCTL_BASE, 0x40) /* get screen mapping from kernel */ +#define PIO_SCRNMAP _IO(KD_IOCTL_BASE, 0x41) /* put screen mapping table in kernel */ +#define GIO_UNISCRNMAP _IO(KD_IOCTL_BASE, 0x69) /* get full Unicode screen mapping */ +#define PIO_UNISCRNMAP _IO(KD_IOCTL_BASE, 0x6A) /* set full Unicode screen mapping */ -#define GIO_UNIMAP 0x4B66 /* get unicode-to-font mapping from kernel */ +#define GIO_UNIMAP _IO(KD_IOCTL_BASE, 0x66) /* get unicode-to-font mapping from kernel */ struct unipair { unsigned short unicode; unsigned short fontpos; @@ -67,8 +68,8 @@ struct unimapdesc { unsigned short entry_ct; struct unipair __user *entries; }; -#define PIO_UNIMAP 0x4B67 /* put unicode-to-font mapping in kernel */ -#define PIO_UNIMAPCLR 0x4B68 /* clear table, possibly advise hash algorithm */ +#define PIO_UNIMAP _IO(KD_IOCTL_BASE, 0x67) /* put unicode-to-font mapping in kernel */ +#define PIO_UNIMAPCLR _IO(KD_IOCTL_BASE, 0x68) /* clear table, possibly advise hash algorithm */ struct unimapinit { unsigned short advised_hashsize; /* 0 if no opinion */ unsigned short advised_hashstep; /* 0 if no opinion */ @@ -83,19 +84,19 @@ struct unimapinit { #define K_MEDIUMRAW 0x02 #define K_UNICODE 0x03 #define K_OFF 0x04 -#define KDGKBMODE 0x4B44 /* gets current keyboard mode */ -#define KDSKBMODE 0x4B45 /* sets current keyboard mode */ +#define KDGKBMODE _IO(KD_IOCTL_BASE, 0x44) /* gets current keyboard mode */ +#define KDSKBMODE _IO(KD_IOCTL_BASE, 0x45) /* sets current keyboard mode */ #define K_METABIT 0x03 #define K_ESCPREFIX 0x04 -#define KDGKBMETA 0x4B62 /* gets meta key handling mode */ -#define KDSKBMETA 0x4B63 /* sets meta key handling mode */ +#define KDGKBMETA _IO(KD_IOCTL_BASE, 0x62) /* gets meta key handling mode */ +#define KDSKBMETA _IO(KD_IOCTL_BASE, 0x63) /* sets meta key handling mode */ #define K_SCROLLLOCK 0x01 #define K_NUMLOCK 0x02 #define K_CAPSLOCK 0x04 -#define KDGKBLED 0x4B64 /* get led flags (not lights) */ -#define KDSKBLED 0x4B65 /* set led flags (not lights) */ +#define KDGKBLED _IO(KD_IOCTL_BASE, 0x64) /* get led flags (not lights) */ +#define KDSKBLED _IO(KD_IOCTL_BASE, 0x65) /* set led flags (not lights) */ struct kbentry { unsigned char kb_table; @@ -107,15 +108,15 @@ struct kbentry { #define K_ALTTAB 0x02 #define K_ALTSHIFTTAB 0x03 -#define KDGKBENT 0x4B46 /* gets one entry in translation table */ -#define KDSKBENT 0x4B47 /* sets one entry in translation table */ +#define KDGKBENT _IO(KD_IOCTL_BASE, 0x46) /* gets one entry in translation table */ +#define KDSKBENT _IO(KD_IOCTL_BASE, 0x47) /* sets one entry in translation table */ struct kbsentry { unsigned char kb_func; unsigned char kb_string[512]; }; -#define KDGKBSENT 0x4B48 /* gets one function key string entry */ -#define KDSKBSENT 0x4B49 /* sets one function key string entry */ +#define KDGKBSENT _IO(KD_IOCTL_BASE, 0x48) /* gets one function key string entry */ +#define KDSKBSENT _IO(KD_IOCTL_BASE, 0x49) /* sets one function key string entry */ struct kbdiacr { unsigned char diacr, base, result; @@ -124,8 +125,8 @@ struct kbdiacrs { unsigned int kb_cnt; /* number of entries in following array */ struct kbdiacr kbdiacr[256]; /* MAX_DIACR from keyboard.h */ }; -#define KDGKBDIACR 0x4B4A /* read kernel accent table */ -#define KDSKBDIACR 0x4B4B /* write kernel accent table */ +#define KDGKBDIACR _IO(KD_IOCTL_BASE, 0x4A) /* read kernel accent table */ +#define KDSKBDIACR _IO(KD_IOCTL_BASE, 0x4B) /* write kernel accent table */ struct kbdiacruc { unsigned int diacr, base, result; @@ -134,16 +135,16 @@ struct kbdiacrsuc { unsigned int kb_cnt; /* number of entries in following array */ struct kbdiacruc kbdiacruc[256]; /* MAX_DIACR from keyboard.h */ }; -#define KDGKBDIACRUC 0x4BFA /* read kernel accent table - UCS */ -#define KDSKBDIACRUC 0x4BFB /* write kernel accent table - UCS */ +#define KDGKBDIACRUC _IO(KD_IOCTL_BASE, 0xFA) /* read kernel accent table - UCS */ +#define KDSKBDIACRUC _IO(KD_IOCTL_BASE, 0xFB) /* write kernel accent table - UCS */ struct kbkeycode { unsigned int scancode, keycode; }; -#define KDGETKEYCODE 0x4B4C /* read kernel keycode table entry */ -#define KDSETKEYCODE 0x4B4D /* write kernel keycode table entry */ +#define KDGETKEYCODE _IO(KD_IOCTL_BASE, 0x4C) /* read kernel keycode table entry */ +#define KDSETKEYCODE _IO(KD_IOCTL_BASE, 0x4D) /* write kernel keycode table entry */ -#define KDSIGACCEPT 0x4B4E /* accept kbd generated signals */ +#define KDSIGACCEPT _IO(KD_IOCTL_BASE, 0x4E) /* accept kbd generated signals */ struct kbd_repeat { int delay; /* in msec; <= 0: don't change */ @@ -151,10 +152,11 @@ struct kbd_repeat { /* earlier this field was misnamed "rate" */ }; -#define KDKBDREP 0x4B52 /* set keyboard delay/repeat rate; - * actually used values are returned */ +#define KDKBDREP _IO(KD_IOCTL_BASE, 0x52) /* set keyboard delay/repeat rate; + * actually used values are returned + */ -#define KDFONTOP 0x4B72 /* font operations */ +#define KDFONTOP _IO(KD_IOCTL_BASE, 0x72) /* font operations */ struct console_font_op { unsigned int op; /* operation code KD_FONT_OP_* */ -- cgit v1.2.3 From aeb48a428d7dbe636203ae892e981bcc3e2ac042 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Fri, 12 Apr 2024 13:50:44 +0200 Subject: udpencap: Remove Obsolete UDP_ENCAP_ESPINUDP_NON_IKE Support The UDP_ENCAP_ESPINUDP_NON_IKE mode, introduced into the Linux kernel in 2004 [2], has remained inactive and obsolete for an extended period. This mode was originally defined in an early version of an IETF draft [1] from 2001. By the time it was integrated into the kernel in 2004 [2], it had already been replaced by UDP_ENCAP_ESPINUDP [3] in later versions of draft-ietf-ipsec-udp-encaps, particularly in version 06. Over time, UDP_ENCAP_ESPINUDP_NON_IKE has lost its relevance, with no known use cases. With this commit, we remove support for UDP_ENCAP_ESPINUDP_NON_IKE, simplifying the codebase and eliminating unnecessary complexity. Kernel will return an error -ENOPROTOOPT if the userspace tries to set this option. References: [1] https://datatracker.ietf.org/doc/html/draft-ietf-ipsec-udp-encaps-00.txt [2] Commit that added UDP_ENCAP_ESPINUDP_NON_IKE to the Linux historic repository. Author: Andreas Gruenbacher Date: Fri Apr 9 01:47:47 2004 -0700 [IPSEC]: Support draft-ietf-ipsec-udp-encaps-00/01, some ipec impls need it. [3] Commit that added UDP_ENCAP_ESPINUDP to the Linux historic repository. Author: Derek Atkins Date: Wed Apr 2 13:21:02 2003 -0800 [IPSEC]: Implement UDP Encapsulation framework. Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- include/uapi/linux/udp.h | 2 +- net/ipv4/esp4.c | 12 ------------ net/ipv4/udp.c | 2 -- net/ipv4/xfrm4_input.c | 13 ------------- net/ipv6/esp6.c | 12 ------------ net/ipv6/xfrm6_input.c | 13 ------------- 6 files changed, 1 insertion(+), 53 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 4828794efcf8..1a0fe8b151fb 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -36,7 +36,7 @@ struct udphdr { #define UDP_GRO 104 /* This socket can receive UDP GRO packets */ /* UDP encapsulation types */ -#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */ +#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* unused draft-ietf-ipsec-nat-t-ike-00/01 */ #define UDP_ENCAP_ESPINUDP 2 /* draft-ietf-ipsec-udp-encaps-06 */ #define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */ #define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */ diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 3d647c9a7a21..7d38ddd64115 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -347,7 +347,6 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, __be16 dport) { struct udphdr *uh; - __be32 *udpdata32; unsigned int len; len = skb->len + esp->tailen - skb_transport_offset(skb); @@ -362,12 +361,6 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, *skb_mac_header(skb) = IPPROTO_UDP; - if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - return (struct ip_esp_hdr *)(udpdata32 + 2); - } - return (struct ip_esp_hdr *)(uh + 1); } @@ -423,7 +416,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb, switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport); break; case TCP_ENCAP_ESPINTCP: @@ -775,7 +767,6 @@ int esp_input_done2(struct sk_buff *skb, int err) source = th->source; break; case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: source = uh->source; break; default: @@ -1179,9 +1170,6 @@ static int esp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); - break; #ifdef CONFIG_INET_ESPINTCP case TCP_ENCAP_ESPINTCP: /* only the length field, TCP encap is done by diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7613daa339b0..4ca781065a07 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2699,8 +2699,6 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: set_xfrm_gro_udp_encap_rcv(val, sk->sk_family, sk); - fallthrough; - case UDP_ENCAP_ESPINUDP_NON_IKE: #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) WRITE_ONCE(up->encap_rcv, diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index dae35101d189..0918b0682174 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -113,19 +113,6 @@ static int __xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull /* Must be an IKE packet.. pass it through */ return 1; break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return -EINVAL; - } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && - udpdata32[0] == 0 && udpdata32[1] == 0) { - - /* ESP Packet with Non-IKE marker */ - len = sizeof(struct udphdr) + 2 * sizeof(u32); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; } /* At this point we are sure that this is an ESPinUDP packet, diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index fe8d53f5a5ee..27df148530a6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -383,7 +383,6 @@ static struct ip_esp_hdr *esp6_output_udp_encap(struct sk_buff *skb, __be16 dport) { struct udphdr *uh; - __be32 *udpdata32; unsigned int len; len = skb->len + esp->tailen - skb_transport_offset(skb); @@ -398,12 +397,6 @@ static struct ip_esp_hdr *esp6_output_udp_encap(struct sk_buff *skb, *skb_mac_header(skb) = IPPROTO_UDP; - if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - return (struct ip_esp_hdr *)(udpdata32 + 2); - } - return (struct ip_esp_hdr *)(uh + 1); } @@ -459,7 +452,6 @@ static int esp6_output_encap(struct xfrm_state *x, struct sk_buff *skb, switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: esph = esp6_output_udp_encap(skb, encap_type, esp, sport, dport); break; case TCP_ENCAP_ESPINTCP: @@ -822,7 +814,6 @@ int esp6_input_done2(struct sk_buff *skb, int err) source = th->source; break; case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: source = uh->source; break; default: @@ -1232,9 +1223,6 @@ static int esp6_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); - break; #ifdef CONFIG_INET6_ESPINTCP case TCP_ENCAP_ESPINTCP: /* only the length field, TCP encap is done by diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index a17d783dc7c0..2c6aeb090b7a 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -109,19 +109,6 @@ static int __xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull /* Must be an IKE packet.. pass it through */ return 1; break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return -EINVAL; - } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && - udpdata32[0] == 0 && udpdata32[1] == 0) { - - /* ESP Packet with Non-IKE marker */ - len = sizeof(struct udphdr) + 2 * sizeof(u32); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; } /* At this point we are sure that this is an ESPinUDP packet, -- cgit v1.2.3 From 6b9391b581fddd8579239dad4de4f0393149e10a Mon Sep 17 00:00:00 2001 From: Charlie Jenkins Date: Tue, 12 Mar 2024 16:53:41 -0700 Subject: riscv: Include riscv_set_icache_flush_ctx prctl Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable optimization of cross modifying code. This prctl enables userspace code to use icache flushing instructions such as fence.i with the guarantee that the icache will continue to be clean after thread migration. Signed-off-by: Charlie Jenkins Reviewed-by: Atish Patra Reviewed-by: Alexandre Ghiti Reviewed-by: Samuel Holland Link: https://lore.kernel.org/r/20240312-fencei-v13-2-4b6bdc2bbf32@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/mmu.h | 2 + arch/riscv/include/asm/processor.h | 10 ++++ arch/riscv/include/asm/switch_to.h | 23 ++++++++ arch/riscv/mm/cacheflush.c | 113 +++++++++++++++++++++++++++++++++++++ arch/riscv/mm/context.c | 19 ++++--- include/uapi/linux/prctl.h | 6 ++ kernel/sys.c | 6 ++ 7 files changed, 171 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index 355504b37f8e..60be458e94da 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -19,6 +19,8 @@ typedef struct { #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; + /* Force local icache flush on all migrations. */ + bool force_icache_flush; #endif #ifdef CONFIG_BINFMT_ELF_FDPIC unsigned long exec_fdpic_loadmap; diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index a8509cc31ab2..cca62013c3c0 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -69,6 +69,7 @@ #endif #ifndef __ASSEMBLY__ +#include struct task_struct; struct pt_regs; @@ -123,6 +124,12 @@ struct thread_struct { struct __riscv_v_ext_state vstate; unsigned long align_ctl; struct __riscv_v_ext_state kernel_vstate; +#ifdef CONFIG_SMP + /* Flush the icache on migration */ + bool force_icache_flush; + /* A forced icache flush is not needed if migrating to the previous cpu. */ + unsigned int prev_cpu; +#endif }; /* Whitelist the fstate from the task_struct for hardened usercopy */ @@ -184,6 +191,9 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); #define GET_UNALIGN_CTL(tsk, addr) get_unalign_ctl((tsk), (addr)) #define SET_UNALIGN_CTL(tsk, val) set_unalign_ctl((tsk), (val)) +#define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2) riscv_set_icache_flush_ctx(arg1, arg2) +extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PROCESSOR_H */ diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 7efdb0584d47..7594df37cc9f 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -72,14 +73,36 @@ static __always_inline bool has_fpu(void) { return false; } extern struct task_struct *__switch_to(struct task_struct *, struct task_struct *); +static inline bool switch_to_should_flush_icache(struct task_struct *task) +{ +#ifdef CONFIG_SMP + bool stale_mm = task->mm && task->mm->context.force_icache_flush; + bool stale_thread = task->thread.force_icache_flush; + bool thread_migrated = smp_processor_id() != task->thread.prev_cpu; + + return thread_migrated && (stale_mm || stale_thread); +#else + return false; +#endif +} + +#ifdef CONFIG_SMP +#define __set_prev_cpu(thread) ((thread).prev_cpu = smp_processor_id()) +#else +#define __set_prev_cpu(thread) +#endif + #define switch_to(prev, next, last) \ do { \ struct task_struct *__prev = (prev); \ struct task_struct *__next = (next); \ + __set_prev_cpu(__prev->thread); \ if (has_fpu()) \ __switch_to_fpu(__prev, __next); \ if (has_vector()) \ __switch_to_vector(__prev, __next); \ + if (switch_to_should_flush_icache(__next)) \ + local_flush_icache_all(); \ ((last) = __switch_to(__prev, __next)); \ } while (0) diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 55a34f2020a8..15a95578e670 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -5,6 +5,7 @@ #include #include +#include #include #include @@ -152,3 +153,115 @@ void __init riscv_init_cbo_blocksizes(void) if (cboz_block_size) riscv_cboz_block_size = cboz_block_size; } + +#ifdef CONFIG_SMP +static void set_icache_stale_mask(void) +{ + cpumask_t *mask; + bool stale_cpu; + + /* + * Mark every other hart's icache as needing a flush for + * this MM. Maintain the previous value of the current + * cpu to handle the case when this function is called + * concurrently on different harts. + */ + mask = ¤t->mm->context.icache_stale_mask; + stale_cpu = cpumask_test_cpu(smp_processor_id(), mask); + + cpumask_setall(mask); + assign_bit(cpumask_check(smp_processor_id()), cpumask_bits(mask), stale_cpu); +} +#endif + +/** + * riscv_set_icache_flush_ctx() - Enable/disable icache flushing instructions in + * userspace. + * @ctx: Set the type of icache flushing instructions permitted/prohibited in + * userspace. Supported values described below. + * + * Supported values for ctx: + * + * * %PR_RISCV_CTX_SW_FENCEI_ON: Allow fence.i in user space. + * + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in user space. All threads in + * a process will be affected when ``scope == PR_RISCV_SCOPE_PER_PROCESS``. + * Therefore, caution must be taken; use this flag only when you can guarantee + * that no thread in the process will emit fence.i from this point onward. + * + * @scope: Set scope of where icache flushing instructions are allowed to be + * emitted. Supported values described below. + * + * Supported values for scope: + * + * * %PR_RISCV_SCOPE_PER_PROCESS: Ensure the icache of any thread in this process + * is coherent with instruction storage upon + * migration. + * + * * %PR_RISCV_SCOPE_PER_THREAD: Ensure the icache of the current thread is + * coherent with instruction storage upon + * migration. + * + * When ``scope == PR_RISCV_SCOPE_PER_PROCESS``, all threads in the process are + * permitted to emit icache flushing instructions. Whenever any thread in the + * process is migrated, the corresponding hart's icache will be guaranteed to be + * consistent with instruction storage. This does not enforce any guarantees + * outside of migration. If a thread modifies an instruction that another thread + * may attempt to execute, the other thread must still emit an icache flushing + * instruction before attempting to execute the potentially modified + * instruction. This must be performed by the user-space program. + * + * In per-thread context (eg. ``scope == PR_RISCV_SCOPE_PER_THREAD``) only the + * thread calling this function is permitted to emit icache flushing + * instructions. When the thread is migrated, the corresponding hart's icache + * will be guaranteed to be consistent with instruction storage. + * + * On kernels configured without SMP, this function is a nop as migrations + * across harts will not occur. + */ +int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope) +{ +#ifdef CONFIG_SMP + switch (ctx) { + case PR_RISCV_CTX_SW_FENCEI_ON: + switch (scope) { + case PR_RISCV_SCOPE_PER_PROCESS: + current->mm->context.force_icache_flush = true; + break; + case PR_RISCV_SCOPE_PER_THREAD: + current->thread.force_icache_flush = true; + break; + default: + return -EINVAL; + } + break; + case PR_RISCV_CTX_SW_FENCEI_OFF: + switch (scope) { + case PR_RISCV_SCOPE_PER_PROCESS: + current->mm->context.force_icache_flush = false; + + set_icache_stale_mask(); + break; + case PR_RISCV_SCOPE_PER_THREAD: + current->thread.force_icache_flush = false; + + set_icache_stale_mask(); + break; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + return 0; +#else + switch (ctx) { + case PR_RISCV_CTX_SW_FENCEI_ON: + case PR_RISCV_CTX_SW_FENCEI_OFF: + return 0; + default: + return -EINVAL; + } +#endif +} diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 217fd4de6134..beef30f42d5c 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -15,6 +15,7 @@ #include #include #include +#include #ifdef CONFIG_MMU @@ -297,21 +298,23 @@ static inline void set_mm(struct mm_struct *prev, * * The "cpu" argument must be the current local CPU number. */ -static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu) +static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu, + struct task_struct *task) { #ifdef CONFIG_SMP - cpumask_t *mask = &mm->context.icache_stale_mask; - - if (cpumask_test_cpu(cpu, mask)) { - cpumask_clear_cpu(cpu, mask); + if (cpumask_test_and_clear_cpu(cpu, &mm->context.icache_stale_mask)) { /* * Ensure the remote hart's writes are visible to this hart. * This pairs with a barrier in flush_icache_mm. */ smp_mb(); - local_flush_icache_all(); - } + /* + * If cache will be flushed in switch_to, no need to flush here. + */ + if (!(task && switch_to_should_flush_icache(task))) + local_flush_icache_all(); + } #endif } @@ -332,5 +335,5 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, set_mm(prev, next, cpu); - flush_icache_deferred(next, cpu); + flush_icache_deferred(next, cpu, task); } diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 370ed14b1ae0..524d546d697b 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -306,4 +306,10 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index e219fcfa112d..69afdd8b430f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -146,6 +146,9 @@ #ifndef RISCV_V_GET_CONTROL # define RISCV_V_GET_CONTROL() (-EINVAL) #endif +#ifndef RISCV_SET_ICACHE_FLUSH_CTX +# define RISCV_SET_ICACHE_FLUSH_CTX(a, b) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -2743,6 +2746,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_RISCV_V_GET_CONTROL: error = RISCV_V_GET_CONTROL(); break; + case PR_RISCV_SET_ICACHE_FLUSH_CTX: + error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); + break; default: error = -EINVAL; break; -- cgit v1.2.3 From b58be8db6327b21e0c7fbee559b8eb47f5110efe Mon Sep 17 00:00:00 2001 From: "Kory Maincent (Dent Project)" Date: Wed, 17 Apr 2024 16:39:49 +0200 Subject: ethtool: Expand Ethernet Power Equipment with c33 (PoE) alongside PoDL In the current PSE interface for Ethernet Power Equipment, support is limited to PoDL. This patch extends the interface to accommodate the objects specified in IEEE 802.3-2022 145.2 for Power sourcing Equipment (PSE). The following objects are now supported and considered mandatory: - IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus - IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState - IEEE 802.3-2022 30.9.1.2.1 aPSEAdminControl To avoid confusion between "PoDL PSE" and "PoE PSE", which have similar names but distinct values, we have followed the suggestion of Oleksij Rempel and Andrew Lunn to maintain separate naming schemes for each, using c33 (clause 33) prefix for "PoE PSE". You can find more details in the discussion threads here: https://lore.kernel.org/netdev/20230912110637.GI780075@pengutronix.de/ https://lore.kernel.org/netdev/2539b109-72ad-470a-9dae-9f53de4f64ec@lunn.ch/ Reviewed-by: Andrew Lunn Reviewed-by: Oleksij Rempel Signed-off-by: Kory Maincent Link: https://lore.kernel.org/r/20240417-feature_poe-v9-1-242293fd1900@bootlin.com Signed-off-by: Jakub Kicinski --- Documentation/networking/index.rst | 1 + Documentation/networking/pse-pd/index.rst | 9 +++ Documentation/networking/pse-pd/introduction.rst | 73 ++++++++++++++++++++++++ include/linux/pse-pd/pse.h | 9 +++ include/uapi/linux/ethtool.h | 43 ++++++++++++++ include/uapi/linux/ethtool_netlink.h | 3 + 6 files changed, 138 insertions(+) create mode 100644 Documentation/networking/pse-pd/index.rst create mode 100644 Documentation/networking/pse-pd/introduction.rst (limited to 'include/uapi/linux') diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 473d72c36d61..7664c0bfe461 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -93,6 +93,7 @@ Contents: plip ppp_generic proc_net_tcp + pse-pd/index radiotap-headers rds regulatory diff --git a/Documentation/networking/pse-pd/index.rst b/Documentation/networking/pse-pd/index.rst new file mode 100644 index 000000000000..18197bc7303d --- /dev/null +++ b/Documentation/networking/pse-pd/index.rst @@ -0,0 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Power Sourcing Equipment (PSE) Documentation +============================================ + +.. toctree:: + :maxdepth: 2 + + introduction diff --git a/Documentation/networking/pse-pd/introduction.rst b/Documentation/networking/pse-pd/introduction.rst new file mode 100644 index 000000000000..e3d3faaef717 --- /dev/null +++ b/Documentation/networking/pse-pd/introduction.rst @@ -0,0 +1,73 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Power Sourcing Equipment (PSE) in IEEE 802.3 Standard +===================================================== + +Overview +-------- + +Power Sourcing Equipment (PSE) is essential in networks for delivering power +along with data over Ethernet cables. It usually refers to devices like +switches and hubs that supply power to Powered Devices (PDs) such as IP +cameras, VoIP phones, and wireless access points. + +PSE vs. PoDL PSE +---------------- + +PSE in the IEEE 802.3 standard generally refers to equipment that provides +power alongside data over Ethernet cables, typically associated with Power over +Ethernet (PoE). + +PoDL PSE, or Power over Data Lines PSE, specifically denotes PSEs operating +with single balanced twisted-pair PHYs, as per Clause 104 of IEEE 802.3. PoDL +is significant in contexts like automotive and industrial controls where power +and data delivery over a single pair is advantageous. + +IEEE 802.3-2018 Addendums and Related Clauses +--------------------------------------------- + +Key addenda to the IEEE 802.3-2018 standard relevant to power delivery over +Ethernet are as follows: + +- **802.3af (Approved in 2003-06-12)**: Known as PoE in the market, detailed in + Clause 33, delivering up to 15.4W of power. +- **802.3at (Approved in 2009-09-11)**: Marketed as PoE+, enhancing PoE as + covered in Clause 33, increasing power delivery to up to 30W. +- **802.3bt (Approved in 2018-09-27)**: Known as 4PPoE in the market, outlined + in Clause 33. Type 3 delivers up to 60W, and Type 4 up to 100W. +- **802.3bu (Approved in 2016-12-07)**: Formerly referred to as PoDL, detailed + in Clause 104. Introduces Classes 0 - 9. Class 9 PoDL PSE delivers up to ~65W + +Kernel Naming Convention Recommendations +---------------------------------------- + +For clarity and consistency within the Linux kernel's networking subsystem, the +following naming conventions are recommended: + +- For general PSE (PoE) code, use "c33_pse" key words. For example: + ``enum ethtool_c33_pse_admin_state c33_admin_control;``. + This aligns with Clause 33, encompassing various PoE forms. + +- For PoDL PSE - specific code, use "podl_pse". For example: + ``enum ethtool_podl_pse_admin_state podl_admin_control;`` to differentiate + PoDL PSE settings according to Clause 104. + +Summary of Clause 33: Data Terminal Equipment (DTE) Power via Media Dependent Interface (MDI) +--------------------------------------------------------------------------------------------- + +Clause 33 of the IEEE 802.3 standard defines the functional and electrical +characteristics of Powered Device (PD) and Power Sourcing Equipment (PSE). +These entities enable power delivery using the same generic cabling as for data +transmission, integrating power with data communication for devices such as +10BASE-T, 100BASE-TX, or 1000BASE-T. + +Summary of Clause 104: Power over Data Lines (PoDL) of Single Balanced Twisted-Pair Ethernet +-------------------------------------------------------------------------------------------- + +Clause 104 of the IEEE 802.3 standard delineates the functional and electrical +characteristics of PoDL Powered Devices (PDs) and PoDL Power Sourcing Equipment +(PSEs). These are designed for use with single balanced twisted-pair Ethernet +Physical Layers. In this clause, 'PSE' refers specifically to PoDL PSE, and +'PD' to PoDL PD. The key intent is to provide devices with a unified interface +for both data and the power required to process this data over a single +balanced twisted-pair Ethernet connection. diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 199cf4ae3cf2..be4e5754eb24 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -17,9 +17,12 @@ struct pse_controller_dev; * * @podl_admin_control: set PoDL PSE admin control as described in * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + * @c33_admin_control: set PSE admin control as described in + * IEEE 802.3-2022 30.9.1.2.1 acPSEAdminControl */ struct pse_control_config { enum ethtool_podl_pse_admin_state podl_admin_control; + enum ethtool_c33_pse_admin_state c33_admin_control; }; /** @@ -29,10 +32,16 @@ struct pse_control_config { * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState * @podl_pw_status: power detection status of the PoDL PSE. * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: */ struct pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_admin_state c33_admin_state; + enum ethtool_c33_pse_pw_d_status c33_pw_status; }; /** diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 95c2f09f0d0a..7b9a3d890949 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -752,6 +752,49 @@ enum ethtool_module_power_mode { ETHTOOL_MODULE_POWER_MODE_HIGH, }; +/** + * enum ethtool_c33_pse_admin_state - operational state of the PoDL PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN: state of PSE functions is unknown + * @ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED: PSE functions are disabled + * @ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED: PSE functions are enabled + */ +enum ethtool_c33_pse_admin_state { + ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN = 1, + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED, +}; + +/** + * enum ethtool_c33_pse_pw_d_status - power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.3 aPoDLPSEPowerDetectionStatus: + * @ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN: PSE status is unknown + * @ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED: The enumeration "disabled" + * indicates that the PSE State diagram is in the state DISABLED. + * @ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING: The enumeration "searching" + * indicates the PSE State diagram is in a state other than those + * listed. + * @ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING: The enumeration + * "deliveringPower" indicates that the PSE State diagram is in the + * state POWER_ON. + * @ETHTOOL_C33_PSE_PW_D_STATUS_TEST: The enumeration "test" indicates that + * the PSE State diagram is in the state TEST_MODE. + * @ETHTOOL_C33_PSE_PW_D_STATUS_FAULT: The enumeration "fault" indicates that + * the PSE State diagram is in the state TEST_ERROR. + * @ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT: The enumeration "otherFault" + * indicates that the PSE State diagram is in the state IDLE due to + * the variable error_condition = true. + */ +enum ethtool_c33_pse_pw_d_status { + ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN = 1, + ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED, + ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING, + ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING, + ETHTOOL_C33_PSE_PW_D_STATUS_TEST, + ETHTOOL_C33_PSE_PW_D_STATUS_FAULT, + ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT, +}; + /** * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b4f0d233d048..f17dbe54bf5e 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -913,6 +913,9 @@ enum { ETHTOOL_A_PODL_PSE_ADMIN_STATE, /* u32 */ ETHTOOL_A_PODL_PSE_ADMIN_CONTROL, /* u32 */ ETHTOOL_A_PODL_PSE_PW_D_STATUS, /* u32 */ + ETHTOOL_A_C33_PSE_ADMIN_STATE, /* u32 */ + ETHTOOL_A_C33_PSE_ADMIN_CONTROL, /* u32 */ + ETHTOOL_A_C33_PSE_PW_D_STATUS, /* u32 */ /* add new constants above here */ __ETHTOOL_A_PSE_CNT, -- cgit v1.2.3 From 47e0dd53c5eb9dab66689592523f31ea39fc32fa Mon Sep 17 00:00:00 2001 From: "Kory Maincent (Dent Project)" Date: Wed, 17 Apr 2024 16:39:50 +0200 Subject: net: pse-pd: Introduce PSE types enumeration Introduce an enumeration to define PSE types (C33 or PoDL), utilizing a bitfield for potential future support of both types. Include 'pse_get_types' helper for external access to PSE type info. Reviewed-by: Andrew Lunn Signed-off-by: Kory Maincent Link: https://lore.kernel.org/r/20240417-feature_poe-v9-2-242293fd1900@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/pse-pd/pse_core.c | 12 ++++++++++++ drivers/net/pse-pd/pse_regulator.c | 1 + include/linux/pse-pd/pse.h | 15 +++++++++++++++ include/uapi/linux/ethtool.h | 12 ++++++++++++ 4 files changed, 40 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 146b81f08a89..fed006cbc185 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -312,3 +312,15 @@ int pse_ethtool_set_config(struct pse_control *psec, return err; } EXPORT_SYMBOL_GPL(pse_ethtool_set_config); + +bool pse_has_podl(struct pse_control *psec) +{ + return psec->pcdev->types & ETHTOOL_PSE_PODL; +} +EXPORT_SYMBOL_GPL(pse_has_podl); + +bool pse_has_c33(struct pse_control *psec) +{ + return psec->pcdev->types & ETHTOOL_PSE_C33; +} +EXPORT_SYMBOL_GPL(pse_has_c33); diff --git a/drivers/net/pse-pd/pse_regulator.c b/drivers/net/pse-pd/pse_regulator.c index 1dedf4de296e..547af384764b 100644 --- a/drivers/net/pse-pd/pse_regulator.c +++ b/drivers/net/pse-pd/pse_regulator.c @@ -116,6 +116,7 @@ pse_reg_probe(struct platform_device *pdev) priv->pcdev.owner = THIS_MODULE; priv->pcdev.ops = &pse_reg_ops; priv->pcdev.dev = dev; + priv->pcdev.types = ETHTOOL_PSE_PODL; ret = devm_pse_controller_register(dev, &priv->pcdev); if (ret) { dev_err(dev, "failed to register PSE controller (%pe)\n", diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index be4e5754eb24..19589571157f 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -77,6 +77,7 @@ struct pse_control; * device tree to id as given to the PSE control ops * @nr_lines: number of PSE controls in this controller device * @lock: Mutex for serialization access to the PSE controller + * @types: types of the PSE controller */ struct pse_controller_dev { const struct pse_controller_ops *ops; @@ -89,6 +90,7 @@ struct pse_controller_dev { const struct of_phandle_args *pse_spec); unsigned int nr_lines; struct mutex lock; + enum ethtool_pse_types types; }; #if IS_ENABLED(CONFIG_PSE_CONTROLLER) @@ -108,6 +110,9 @@ int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); +bool pse_has_podl(struct pse_control *psec); +bool pse_has_c33(struct pse_control *psec); + #else static inline struct pse_control *of_pse_control_get(struct device_node *node) @@ -133,6 +138,16 @@ static inline int pse_ethtool_set_config(struct pse_control *psec, return -ENOTSUPP; } +static inline bool pse_has_podl(struct pse_control *psec) +{ + return false; +} + +static inline bool pse_has_c33(struct pse_control *psec) +{ + return false; +} + #endif #endif diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7b9a3d890949..041e09c3515d 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -752,6 +752,18 @@ enum ethtool_module_power_mode { ETHTOOL_MODULE_POWER_MODE_HIGH, }; +/** + * enum ethtool_pse_types - Types of PSE controller. + * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown + * @ETHTOOL_PSE_PODL: PSE controller which support PoDL + * @ETHTOOL_PSE_C33: PSE controller which support Clause 33 (PoE) + */ +enum ethtool_pse_types { + ETHTOOL_PSE_UNKNOWN = 1 << 0, + ETHTOOL_PSE_PODL = 1 << 1, + ETHTOOL_PSE_C33 = 1 << 2, +}; + /** * enum ethtool_c33_pse_admin_state - operational state of the PoDL PSE * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState -- cgit v1.2.3 From a05d1f625c7aa681d8816bc0f10089289ad07aad Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 5 Mar 2024 13:10:04 -0700 Subject: io_uring/net: support bundles for send If IORING_OP_SEND is used with provided buffers, the caller may also set IORING_RECVSEND_BUNDLE to turn it into a multi-buffer send. The idea is that an application can fill outgoing buffers in a provided buffer group, and then arm a single send that will service them all. Once there are no more buffers to send, or if the requested length has been sent, the request posts a single completion for all the buffers. This only enables it for IORING_OP_SEND, IORING_OP_SENDMSG is coming in a separate patch. However, this patch does do a lot of the prep work that makes wiring up the sendmsg variant pretty trivial. They share the prep side. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 9 +++ io_uring/net.c | 145 +++++++++++++++++++++++++++++++++++++----- 2 files changed, 137 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a7f847543a7f..7f583927c908 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -351,11 +351,20 @@ enum io_uring_op { * 0 is reported if zerocopy was actually possible. * IORING_NOTIF_USAGE_ZC_COPIED if data was copied * (at least partially). + * + * IORING_RECVSEND_BUNDLE Used with IOSQE_BUFFER_SELECT. If set, send will + * grab as many buffers from the buffer group ID + * given and send them all. The completion result + * will be the number of buffers send, with the + * starting buffer ID in cqe->flags as per usual + * for provided buffer usage. The buffers will be + * contigious from the starting buffer ID. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) #define IORING_SEND_ZC_REPORT_USAGE (1U << 3) +#define IORING_RECVSEND_BUNDLE (1U << 4) /* * cqe.res for IORING_CQE_F_NOTIF if diff --git a/io_uring/net.c b/io_uring/net.c index 13685d133582..3e326576254b 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -57,7 +57,7 @@ struct io_sr_msg { struct user_msghdr __user *umsg; void __user *buf; }; - unsigned len; + int len; unsigned done_io; unsigned msg_flags; unsigned nr_multishot_loops; @@ -389,6 +389,8 @@ static int io_sendmsg_prep_setup(struct io_kiocb *req, int is_msg) return ret; } +#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE) + int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); @@ -407,11 +409,20 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); - if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + if (sr->flags & ~SENDMSG_FLAGS) return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; + if (sr->flags & IORING_RECVSEND_BUNDLE) { + if (req->opcode == IORING_OP_SENDMSG) + return -EINVAL; + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + sr->msg_flags |= MSG_WAITALL; + sr->buf_group = req->buf_index; + req->buf_list = NULL; + } #ifdef CONFIG_COMPAT if (req->ctx->compat) @@ -427,6 +438,79 @@ static void io_req_msg_cleanup(struct io_kiocb *req, io_netmsg_recycle(req, issue_flags); } +/* + * For bundle completions, we need to figure out how many segments we consumed. + * A bundle could be using a single ITER_UBUF if that's all we mapped, or it + * could be using an ITER_IOVEC. If the latter, then if we consumed all of + * the segments, then it's a trivial questiont o answer. If we have residual + * data in the iter, then loop the segments to figure out how much we + * transferred. + */ +static int io_bundle_nbufs(struct io_async_msghdr *kmsg, int ret) +{ + struct iovec *iov; + int nbufs; + + /* no data is always zero segments, and a ubuf is always 1 segment */ + if (ret <= 0) + return 0; + if (iter_is_ubuf(&kmsg->msg.msg_iter)) + return 1; + + iov = kmsg->free_iov; + if (!iov) + iov = &kmsg->fast_iov; + + /* if all data was transferred, it's basic pointer math */ + if (!iov_iter_count(&kmsg->msg.msg_iter)) + return iter_iov(&kmsg->msg.msg_iter) - iov; + + /* short transfer, count segments */ + nbufs = 0; + do { + int this_len = min_t(int, iov[nbufs].iov_len, ret); + + nbufs++; + ret -= this_len; + } while (ret); + + return nbufs; +} + +static inline bool io_send_finish(struct io_kiocb *req, int *ret, + struct io_async_msghdr *kmsg, + unsigned issue_flags) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + bool bundle_finished = *ret <= 0; + unsigned int cflags; + + if (!(sr->flags & IORING_RECVSEND_BUNDLE)) { + cflags = io_put_kbuf(req, issue_flags); + goto finish; + } + + cflags = io_put_kbufs(req, io_bundle_nbufs(kmsg, *ret), issue_flags); + + if (bundle_finished || req->flags & REQ_F_BL_EMPTY) + goto finish; + + /* + * Fill CQE for this receive and see if we should keep trying to + * receive from this socket. + */ + if (io_req_post_cqe(req, *ret, cflags | IORING_CQE_F_MORE)) { + io_mshot_prep_retry(req, kmsg); + return false; + } + + /* Otherwise stop bundle and use the current result. */ +finish: + io_req_set_res(req, *ret, cflags); + *ret = IOU_OK; + return true; +} + int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); @@ -482,7 +566,6 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); struct io_async_msghdr *kmsg = req->async_data; struct socket *sock; - unsigned int cflags; unsigned flags; int min_ret = 0; int ret; @@ -495,21 +578,47 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return -EAGAIN; + flags = sr->msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) + flags |= MSG_DONTWAIT; + +retry_bundle: if (io_do_buffer_select(req)) { - size_t len = sr->len; - void __user *buf; + struct buf_sel_arg arg = { + .iovs = &kmsg->fast_iov, + .max_len = min_not_zero(sr->len, INT_MAX), + .nr_iovs = 1, + .mode = KBUF_MODE_EXPAND, + }; + + if (kmsg->free_iov) { + arg.nr_iovs = kmsg->free_iov_nr; + arg.iovs = kmsg->free_iov; + arg.mode |= KBUF_MODE_FREE; + } - buf = io_buffer_select(req, &len, issue_flags); - if (unlikely(!buf)) - return -ENOBUFS; - sr->buf = buf; - sr->len = len; + if (!(sr->flags & IORING_RECVSEND_BUNDLE)) + arg.nr_iovs = 1; + + ret = io_buffers_select(req, &arg, issue_flags); + if (unlikely(ret < 0)) + return ret; + + sr->len = arg.out_len; + iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE, arg.iovs, ret, + arg.out_len); + if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) { + kmsg->free_iov_nr = ret; + kmsg->free_iov = arg.iovs; + } } - flags = sr->msg_flags; - if (issue_flags & IO_URING_F_NONBLOCK) - flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) + /* + * If MSG_WAITALL is set, or this is a bundle send, then we need + * the full amount. If just bundle is set, if we do a short send + * then we complete the bundle sequence rather than continue on. + */ + if (flags & MSG_WAITALL || sr->flags & IORING_RECVSEND_BUNDLE) min_ret = iov_iter_count(&kmsg->msg.msg_iter); flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; @@ -534,10 +643,12 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; + + if (!io_send_finish(req, &ret, kmsg, issue_flags)) + goto retry_bundle; + io_req_msg_cleanup(req, issue_flags); - cflags = io_put_kbuf(req, issue_flags); - io_req_set_res(req, ret, cflags); - return IOU_OK; + return ret; } static int io_recvmsg_mshot_prep(struct io_kiocb *req, -- cgit v1.2.3 From 2f9c9515bdfde9e4df1f35782284074d3625ff8a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 5 Mar 2024 16:22:04 -0700 Subject: io_uring/net: support bundles for recv If IORING_OP_RECV is used with provided buffers, the caller may also set IORING_RECVSEND_BUNDLE to turn it into a multi-buffer recv. This grabs buffers available and receives into them, posting a single completion for all of it. This can be used with multishot receive as well, or without it. Now that both send and receive support bundles, add a feature flag for it as well. If IORING_FEAT_RECVSEND_BUNDLE is set after registering the ring, then the kernel supports bundles for recv and send. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 15 +++--- io_uring/io_uring.c | 3 +- io_uring/net.c | 116 ++++++++++++++++++++++++++++++++++-------- 3 files changed, 105 insertions(+), 29 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 7f583927c908..f093cb2300d9 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -352,13 +352,13 @@ enum io_uring_op { * IORING_NOTIF_USAGE_ZC_COPIED if data was copied * (at least partially). * - * IORING_RECVSEND_BUNDLE Used with IOSQE_BUFFER_SELECT. If set, send will - * grab as many buffers from the buffer group ID - * given and send them all. The completion result - * will be the number of buffers send, with the - * starting buffer ID in cqe->flags as per usual - * for provided buffer usage. The buffers will be - * contigious from the starting buffer ID. + * IORING_RECVSEND_BUNDLE Used with IOSQE_BUFFER_SELECT. If set, send or + * recv will grab as many buffers from the buffer + * group ID given and send them all. The completion + * result will be the number of buffers send, with + * the starting buffer ID in cqe->flags as per + * usual for provided buffer usage. The buffers + * will be contigious from the starting buffer ID. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) @@ -529,6 +529,7 @@ struct io_uring_params { #define IORING_FEAT_CQE_SKIP (1U << 11) #define IORING_FEAT_LINKED_FILE (1U << 12) #define IORING_FEAT_REG_REG_RING (1U << 13) +#define IORING_FEAT_RECVSEND_BUNDLE (1U << 14) /* * io_uring_register(2) opcodes and arguments diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index c67ae6e36c4f..64845634d89f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3583,7 +3583,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | - IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING; + IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING | + IORING_FEAT_RECVSEND_BUNDLE; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; diff --git a/io_uring/net.c b/io_uring/net.c index 3e326576254b..51c41d771c50 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -747,7 +747,8 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req) return ret; } -#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT) +#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT | \ + IORING_RECVSEND_BUNDLE) int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { @@ -761,21 +762,14 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); - if (sr->flags & ~(RECVMSG_FLAGS)) + if (sr->flags & ~RECVMSG_FLAGS) return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags); if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; if (sr->msg_flags & MSG_ERRQUEUE) req->flags |= REQ_F_CLEAR_POLLIN; - if (sr->flags & IORING_RECV_MULTISHOT) { - if (!(req->flags & REQ_F_BUFFER_SELECT)) - return -EINVAL; - if (sr->msg_flags & MSG_WAITALL) - return -EINVAL; - if (req->opcode == IORING_OP_RECV && sr->len) - return -EINVAL; - req->flags |= REQ_F_APOLL_MULTISHOT; + if (req->flags & REQ_F_BUFFER_SELECT) { /* * Store the buffer group for this multishot receive separately, * as if we end up doing an io-wq based issue that selects a @@ -785,6 +779,20 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) * restore it. */ sr->buf_group = req->buf_index; + req->buf_list = NULL; + } + if (sr->flags & IORING_RECV_MULTISHOT) { + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + if (sr->msg_flags & MSG_WAITALL) + return -EINVAL; + if (req->opcode == IORING_OP_RECV && sr->len) + return -EINVAL; + req->flags |= REQ_F_APOLL_MULTISHOT; + } + if (sr->flags & IORING_RECVSEND_BUNDLE) { + if (req->opcode == IORING_OP_RECVMSG) + return -EINVAL; } #ifdef CONFIG_COMPAT @@ -805,19 +813,28 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, struct io_async_msghdr *kmsg, bool mshot_finished, unsigned issue_flags) { + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); unsigned int cflags; - cflags = io_put_kbuf(req, issue_flags); + if (sr->flags & IORING_RECVSEND_BUNDLE) + cflags = io_put_kbufs(req, io_bundle_nbufs(kmsg, *ret), + issue_flags); + else + cflags = io_put_kbuf(req, issue_flags); + if (kmsg->msg.msg_inq > 0) cflags |= IORING_CQE_F_SOCK_NONEMPTY; + /* bundle with no more immediate buffers, we're done */ + if (sr->flags & IORING_RECVSEND_BUNDLE && req->flags & REQ_F_BL_EMPTY) + goto finish; + /* * Fill CQE for this receive and see if we should keep trying to * receive from this socket. */ if ((req->flags & REQ_F_APOLL_MULTISHOT) && !mshot_finished && io_req_post_cqe(req, *ret, cflags | IORING_CQE_F_MORE)) { - struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); int mshot_retry_ret = IOU_ISSUE_SKIP_COMPLETE; io_mshot_prep_retry(req, kmsg); @@ -837,6 +854,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, } /* Finish the request / stop multishot. */ +finish: io_req_set_res(req, *ret, cflags); if (issue_flags & IO_URING_F_MULTISHOT) @@ -1020,6 +1038,69 @@ retry_multishot: return ret; } +static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg, + size_t *len, unsigned int issue_flags) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + int ret; + + /* + * If the ring isn't locked, then don't use the peek interface + * to grab multiple buffers as we will lock/unlock between + * this selection and posting the buffers. + */ + if (!(issue_flags & IO_URING_F_UNLOCKED) && + sr->flags & IORING_RECVSEND_BUNDLE) { + struct buf_sel_arg arg = { + .iovs = &kmsg->fast_iov, + .nr_iovs = 1, + .mode = KBUF_MODE_EXPAND, + }; + + if (kmsg->free_iov) { + arg.nr_iovs = kmsg->free_iov_nr; + arg.iovs = kmsg->free_iov; + arg.mode |= KBUF_MODE_FREE; + } + + if (kmsg->msg.msg_inq > 0) + arg.max_len = min_not_zero(sr->len, kmsg->msg.msg_inq); + + ret = io_buffers_peek(req, &arg); + if (unlikely(ret < 0)) + return ret; + + /* special case 1 vec, can be a fast path */ + if (ret == 1) { + sr->buf = arg.iovs[0].iov_base; + sr->len = arg.iovs[0].iov_len; + goto map_ubuf; + } + iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret, + arg.out_len); + if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) { + kmsg->free_iov_nr = ret; + kmsg->free_iov = arg.iovs; + } + } else { + void __user *buf; + + *len = sr->len; + buf = io_buffer_select(req, len, issue_flags); + if (!buf) + return -ENOBUFS; + sr->buf = buf; + sr->len = *len; +map_ubuf: + ret = import_ubuf(ITER_DEST, sr->buf, sr->len, + &kmsg->msg.msg_iter); + if (unlikely(ret)) + return ret; + } + + return 0; +} + int io_recv(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); @@ -1044,17 +1125,10 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) retry_multishot: if (io_do_buffer_select(req)) { - void __user *buf; - - buf = io_buffer_select(req, &len, issue_flags); - if (!buf) - return -ENOBUFS; - sr->buf = buf; - sr->len = len; - ret = import_ubuf(ITER_DEST, sr->buf, sr->len, - &kmsg->msg.msg_iter); + ret = io_recv_buf_select(req, kmsg, &len, issue_flags); if (unlikely(ret)) goto out_free; + sr->buf = NULL; } kmsg->msg.msg_inq = -1; -- cgit v1.2.3 From 79365026f86948b52c3cb7bf099dded92c559b4c Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:09 +0530 Subject: crash: add a new kexec flag for hotplug support Commit a72bbec70da2 ("crash: hotplug support for kexec_load()") introduced a new kexec flag, `KEXEC_UPDATE_ELFCOREHDR`. Kexec tool uses this flag to indicate to the kernel that it is safe to modify the elfcorehdr of the kdump image loaded using the kexec_load system call. However, it is possible that architectures may need to update kexec segments other then elfcorehdr. For example, FDT (Flatten Device Tree) on PowerPC. Introducing a new kexec flag for every new kexec segment may not be a good solution. Hence, a generic kexec flag bit, `KEXEC_CRASH_HOTPLUG_SUPPORT`, is introduced to share the CPU/Memory hotplug support intent between the kexec tool and the kernel for the kexec_load system call. Now we have two kexec flags that enables crash hotplug support for kexec_load system call. First is KEXEC_UPDATE_ELFCOREHDR (only used in x86), and second is KEXEC_CRASH_HOTPLUG_SUPPORT (for all architectures). To simplify the process of finding and reporting the crash hotplug support the following changes are introduced. 1. Define arch specific function to process the kexec flags and determine crash hotplug support 2. Rename the @update_elfcorehdr member of struct kimage to @hotplug_support and populate it for both kexec_load and kexec_file_load syscalls, because architecture can update more than one kexec segment 3. Let generic function crash_check_hotplug_support report hotplug support for loaded kdump image based on value of @hotplug_support To bring the x86 crash hotplug support in line with the above points, the following changes have been made: - Introduce the arch_crash_hotplug_support function to process kexec flags and determine crash hotplug support - Remove the arch_crash_hotplug_[cpu|memory]_support functions Signed-off-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-3-sourabhjain@linux.ibm.com --- arch/x86/include/asm/kexec.h | 11 ++--------- arch/x86/kernel/crash.c | 28 +++++++++++++++++----------- drivers/base/cpu.c | 2 +- drivers/base/memory.c | 2 +- include/linux/crash_core.h | 13 ++++++------- include/linux/kexec.h | 11 +++++++---- include/uapi/linux/kexec.h | 1 + kernel/crash_core.c | 15 ++++++--------- kernel/kexec.c | 4 ++-- kernel/kexec_file.c | 5 +++++ 10 files changed, 48 insertions(+), 44 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index cb1320ebbc23..ae5482a2f0ca 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -210,15 +210,8 @@ extern void kdump_nmi_shootdown_cpus(void); void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void); -#define crash_hotplug_cpu_support arch_crash_hotplug_cpu_support -#endif - -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void); -#define crash_hotplug_memory_support arch_crash_hotplug_memory_support -#endif +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); +#define arch_crash_hotplug_support arch_crash_hotplug_support unsigned int arch_crash_get_elfcorehdr_size(void); #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2a682fe86352..f06501445cd9 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -402,20 +402,26 @@ int crash_load_segments(struct kimage *image) #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt -/* These functions provide the value for the sysfs crash_hotplug nodes */ -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void) +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) { - return crash_check_update_elfcorehdr(); -} -#endif -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void) -{ - return crash_check_update_elfcorehdr(); -} +#ifdef CONFIG_KEXEC_FILE + if (image->file_mode) + return 1; #endif + /* + * Initially, crash hotplug support for kexec_load was added + * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this + * functionality was expanded to accommodate multiple kexec + * segment updates, leading to the introduction of the + * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently, + * when the kexec tool sends either of these flags, it indicates + * that the required kexec segment (elfcorehdr) is excluded from + * the SHA calculation. + */ + return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR || + kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT); +} unsigned int arch_crash_get_elfcorehdr_size(void) { diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 56fba44ba391..c61ecb0c2ae2 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -306,7 +306,7 @@ static ssize_t crash_hotplug_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", crash_hotplug_cpu_support()); + return sysfs_emit(buf, "%d\n", crash_check_hotplug_support()); } static DEVICE_ATTR_ADMIN_RO(crash_hotplug); #endif diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c0436f46cfb7..67858eeb92ed 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -535,7 +535,7 @@ static DEVICE_ATTR_RW(auto_online_blocks); static ssize_t crash_hotplug_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", crash_hotplug_memory_support()); + return sysfs_emit(buf, "%d\n", crash_check_hotplug_support()); } static DEVICE_ATTR_RO(crash_hotplug); #endif diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 647e928efee8..44305336314e 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -40,14 +40,13 @@ static inline void arch_kexec_unprotect_crashkres(void) { } static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { } #endif -int crash_check_update_elfcorehdr(void); +int crash_check_hotplug_support(void); -#ifndef crash_hotplug_cpu_support -static inline int crash_hotplug_cpu_support(void) { return 0; } -#endif - -#ifndef crash_hotplug_memory_support -static inline int crash_hotplug_memory_support(void) { return 0; } +#ifndef arch_crash_hotplug_support +static inline int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ + return 0; +} #endif #ifndef crash_get_elfcorehdr_size diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 060835bb82d5..5b93a5767413 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -319,8 +319,10 @@ struct kimage { /* If set, we are using file mode kexec syscall */ unsigned int file_mode:1; #ifdef CONFIG_CRASH_HOTPLUG - /* If set, allow changes to elfcorehdr of kexec_load'd image */ - unsigned int update_elfcorehdr:1; + /* If set, it is safe to update kexec segments that are + * excluded from SHA calculation. + */ + unsigned int hotplug_support:1; #endif #ifdef ARCH_HAS_KIMAGE_ARCH @@ -391,9 +393,10 @@ bool kexec_load_permitted(int kexec_image_type); /* List of defined/legal kexec flags */ #ifndef CONFIG_KEXEC_JUMP -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR | KEXEC_CRASH_HOTPLUG_SUPPORT) #else -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR | \ + KEXEC_CRASH_HOTPLUG_SUPPORT) #endif /* List of defined/legal kexec file flags */ diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index c17bb096ea68..5ae1741ea8ea 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -13,6 +13,7 @@ #define KEXEC_ON_CRASH 0x00000001 #define KEXEC_PRESERVE_CONTEXT 0x00000002 #define KEXEC_UPDATE_ELFCOREHDR 0x00000004 +#define KEXEC_CRASH_HOTPLUG_SUPPORT 0x00000008 #define KEXEC_ARCH_MASK 0xffff0000 /* diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 70fa8111a9d6..394db3ebe835 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -493,10 +493,10 @@ static DEFINE_MUTEX(__crash_hotplug_lock); /* * This routine utilized when the crash_hotplug sysfs node is read. - * It reflects the kernel's ability/permission to update the crash - * elfcorehdr directly. + * It reflects the kernel's ability/permission to update the kdump + * image directly. */ -int crash_check_update_elfcorehdr(void) +int crash_check_hotplug_support(void) { int rc = 0; @@ -508,10 +508,7 @@ int crash_check_update_elfcorehdr(void) return 0; } if (kexec_crash_image) { - if (kexec_crash_image->file_mode) - rc = 1; - else - rc = kexec_crash_image->update_elfcorehdr; + rc = kexec_crash_image->hotplug_support; } /* Release lock now that update complete */ kexec_unlock(); @@ -552,8 +549,8 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, image = kexec_crash_image; - /* Check that updating elfcorehdr is permitted */ - if (!(image->file_mode || image->update_elfcorehdr)) + /* Check that kexec segments update is permitted */ + if (!image->hotplug_support) goto out; if (hp_action == KEXEC_CRASH_HP_ADD_CPU || diff --git a/kernel/kexec.c b/kernel/kexec.c index bab542fc1463..a6b3f96bb50c 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -135,8 +135,8 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, image->preserve_context = 1; #ifdef CONFIG_CRASH_HOTPLUG - if (flags & KEXEC_UPDATE_ELFCOREHDR) - image->update_elfcorehdr = 1; + if ((flags & KEXEC_ON_CRASH) && arch_crash_hotplug_support(image, flags)) + image->hotplug_support = 1; #endif ret = machine_kexec_prepare(image); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 2d1db05fbf04..3d64290d24c9 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -376,6 +376,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; +#ifdef CONFIG_CRASH_HOTPLUG + if ((flags & KEXEC_FILE_ON_CRASH) && arch_crash_hotplug_support(image, flags)) + image->hotplug_support = 1; +#endif + ret = machine_kexec_prepare(image); if (ret) goto out; -- cgit v1.2.3 From d56b63cf0c0f71e1b2e04dd8220b408f049e67ff Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Sat, 20 Apr 2024 11:09:05 +0200 Subject: bpf: add support for bpf_wq user type Mostly a copy/paste from the bpf_timer API, without the initialization and free, as they will be done in a separate patch. Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20240420-bpf_wq-v2-5-6c986a5a741f@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 ++++++++++- include/uapi/linux/bpf.h | 4 ++++ kernel/bpf/btf.c | 17 +++++++++++++++++ kernel/bpf/syscall.c | 6 +++++- kernel/bpf/verifier.c | 9 +++++++++ 5 files changed, 45 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5034c1b4ded7..c7dcfd395555 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -185,7 +185,7 @@ struct bpf_map_ops { enum { /* Support at most 10 fields in a BTF type */ - BTF_FIELDS_MAX = 10, + BTF_FIELDS_MAX = 11, }; enum btf_field_type { @@ -202,6 +202,7 @@ enum btf_field_type { BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), + BPF_WORKQUEUE = (1 << 10), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +239,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -312,6 +314,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; + case BPF_WORKQUEUE: + return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; @@ -340,6 +344,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); + case BPF_WORKQUEUE: + return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -367,6 +373,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); + case BPF_WORKQUEUE: + return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -406,6 +414,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cee0a7915c08..e4ae83550fb3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7306,6 +7306,10 @@ struct bpf_timer { __u64 __opaque[2]; } __attribute__((aligned(8))); +struct bpf_wq { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + struct bpf_dynptr { __u64 __opaque[2]; } __attribute__((aligned(8))); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6d46cee47ae3..8291fbfd27b1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3464,6 +3464,15 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_WORKQUEUE) { + if (!strcmp(name, "bpf_wq")) { + if (*seen_mask & BPF_WORKQUEUE) + return -E2BIG; + *seen_mask |= BPF_WORKQUEUE; + type = BPF_WORKQUEUE; + goto end; + } + } field_mask_test_name(BPF_LIST_HEAD, "bpf_list_head"); field_mask_test_name(BPF_LIST_NODE, "bpf_list_node"); field_mask_test_name(BPF_RB_ROOT, "bpf_rb_root"); @@ -3515,6 +3524,7 @@ static int btf_find_struct_field(const struct btf *btf, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: @@ -3582,6 +3592,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: @@ -3816,6 +3827,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec->spin_lock_off = -EINVAL; rec->timer_off = -EINVAL; + rec->wq_off = -EINVAL; rec->refcount_off = -EINVAL; for (i = 0; i < cnt; i++) { field_type_size = btf_field_type_size(info_arr[i].type); @@ -3846,6 +3858,11 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type /* Cache offset for faster lookup at runtime */ rec->timer_off = rec->fields[i].offset; break; + case BPF_WORKQUEUE: + WARN_ON_ONCE(rec->wq_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->wq_off = rec->fields[i].offset; + break; case BPF_REFCOUNT: WARN_ON_ONCE(rec->refcount_off >= 0); /* Cache offset for faster lookup at runtime */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7d392ec83655..0848e4141b00 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -559,6 +559,7 @@ void btf_record_free(struct btf_record *rec) case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: + case BPF_WORKQUEUE: /* Nothing to release */ break; default: @@ -608,6 +609,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: + case BPF_WORKQUEUE: /* Nothing to acquire */ break; default: @@ -679,6 +681,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; + case BPF_WORKQUEUE: + break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; @@ -1085,7 +1089,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | - BPF_RB_ROOT | BPF_REFCOUNT, + BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5a7e34e83a5b..89490a95b120 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1838,6 +1838,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) */ if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER)) reg->map_uid = reg->id; + if (btf_record_has_field(map->inner_map_meta->record, BPF_WORKQUEUE)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -18141,6 +18143,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_wq yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); -- cgit v1.2.3 From dbc8fc9d6de17b618591d4d2a6227dee27fe0f51 Mon Sep 17 00:00:00 2001 From: Shivaprasad G Bhat Date: Sat, 27 Jan 2024 12:57:00 -0600 Subject: powerpc/papr_scm: Move duplicate definitions to common header files papr_scm and ndtest share common PDSM payload structs like nd_papr_pdsm_health. Presently these structs are duplicated across papr_pdsm.h and ndtest.h header files. Since 'ndtest' is essentially arch independent and can run on platforms other than PPC64, a way needs to be deviced to avoid redundancy and duplication of PDSM structs in future. So the patch proposes moving the PDSM header from arch/powerpc/include- -/uapi/ to the generic include/uapi/linux directory. Also, there are some #defines common between papr_scm and ndtest which are not exported to the user space. So, move them to a header file which can be shared across ndtest and papr_scm via newly introduced include/linux/papr_scm.h. Signed-off-by: Shivaprasad G Bhat Signed-off-by: Vaibhav Jain Suggested-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/170638176942.112443.2937254675538057083.stgit@ltcd48-lp2.aus.stglab.ibm.com Signed-off-by: Ira Weiny --- MAINTAINERS | 2 + arch/powerpc/include/uapi/asm/papr_pdsm.h | 165 ------------------------------ arch/powerpc/platforms/pseries/papr_scm.c | 43 +------- include/linux/papr_scm.h | 49 +++++++++ include/uapi/linux/papr_pdsm.h | 165 ++++++++++++++++++++++++++++++ tools/testing/nvdimm/test/ndtest.c | 2 + tools/testing/nvdimm/test/ndtest.h | 31 ------ 7 files changed, 220 insertions(+), 237 deletions(-) delete mode 100644 arch/powerpc/include/uapi/asm/papr_pdsm.h create mode 100644 include/linux/papr_scm.h create mode 100644 include/uapi/linux/papr_pdsm.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index ebf03f5f0619..0960c519f949 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12497,6 +12497,8 @@ F: drivers/rtc/rtc-opal.c F: drivers/scsi/ibmvscsi/ F: drivers/tty/hvc/hvc_opal.c F: drivers/watchdog/wdrtas.c +F: include/linux/papr_scm.h +F: include/uapi/linux/papr_pdsm.h F: tools/testing/selftests/powerpc N: /pmac N: powermac diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h deleted file mode 100644 index 17439925045c..000000000000 --- a/arch/powerpc/include/uapi/asm/papr_pdsm.h +++ /dev/null @@ -1,165 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl - * - * (C) Copyright IBM 2020 - * - * Author: Vaibhav Jain - */ - -#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_ -#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_ - -#include -#include - -/* - * PDSM Envelope: - * - * The ioctl ND_CMD_CALL exchange data between user-space and kernel via - * envelope which consists of 2 headers sections and payload sections as - * illustrated below: - * +-----------------+---------------+---------------------------+ - * | 64-Bytes | 8-Bytes | Max 184-Bytes | - * +-----------------+---------------+---------------------------+ - * | ND-HEADER | PDSM-HEADER | PDSM-PAYLOAD | - * +-----------------+---------------+---------------------------+ - * | nd_family | | | - * | nd_size_out | cmd_status | | - * | nd_size_in | reserved | nd_pdsm_payload | - * | nd_command | payload --> | | - * | nd_fw_size | | | - * | nd_payload ---> | | | - * +---------------+-----------------+---------------------------+ - * - * ND Header: - * This is the generic libnvdimm header described as 'struct nd_cmd_pkg' - * which is interpreted by libnvdimm before passed on to papr_scm. Important - * member fields used are: - * 'nd_family' : (In) NVDIMM_FAMILY_PAPR_SCM - * 'nd_size_in' : (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0) - * 'nd_size_out' : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD - * 'nd_command' : (In) One of PAPR_PDSM_XXX - * 'nd_fw_size' : (Out) PDSM-HEADER + size of actual payload returned - * - * PDSM Header: - * This is papr-scm specific header that precedes the payload. This is defined - * as nd_cmd_pdsm_pkg. Following fields aare available in this header: - * - * 'cmd_status' : (Out) Errors if any encountered while servicing PDSM. - * 'reserved' : Not used, reserved for future and should be set to 0. - * 'payload' : A union of all the possible payload structs - * - * PDSM Payload: - * - * The layout of the PDSM Payload is defined by various structs shared between - * papr_scm and libndctl so that contents of payload can be interpreted. As such - * its defined as a union of all possible payload structs as - * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command' - * appropriate member of the union is accessed. - */ - -/* Max payload size that we can handle */ -#define ND_PDSM_PAYLOAD_MAX_SIZE 184 - -/* Max payload size that we can handle */ -#define ND_PDSM_HDR_SIZE \ - (sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE) - -/* Various nvdimm health indicators */ -#define PAPR_PDSM_DIMM_HEALTHY 0 -#define PAPR_PDSM_DIMM_UNHEALTHY 1 -#define PAPR_PDSM_DIMM_CRITICAL 2 -#define PAPR_PDSM_DIMM_FATAL 3 - -/* struct nd_papr_pdsm_health.extension_flags field flags */ - -/* Indicate that the 'dimm_fuel_gauge' field is valid */ -#define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1 - -/* Indicate that the 'dimm_dsc' field is valid */ -#define PDSM_DIMM_DSC_VALID 2 - -/* - * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH - * Various flags indicate the health status of the dimm. - * - * extension_flags : Any extension fields present in the struct. - * dimm_unarmed : Dimm not armed. So contents wont persist. - * dimm_bad_shutdown : Previous shutdown did not persist contents. - * dimm_bad_restore : Contents from previous shutdown werent restored. - * dimm_scrubbed : Contents of the dimm have been scrubbed. - * dimm_locked : Contents of the dimm cant be modified until CEC reboot - * dimm_encrypted : Contents of dimm are encrypted. - * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX - * dimm_fuel_gauge : Life remaining of DIMM as a percentage from 0-100 - */ -struct nd_papr_pdsm_health { - union { - struct { - __u32 extension_flags; - __u8 dimm_unarmed; - __u8 dimm_bad_shutdown; - __u8 dimm_bad_restore; - __u8 dimm_scrubbed; - __u8 dimm_locked; - __u8 dimm_encrypted; - __u16 dimm_health; - - /* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */ - __u16 dimm_fuel_gauge; - - /* Extension flag PDSM_DIMM_DSC_VALID */ - __u64 dimm_dsc; - }; - __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; - }; -}; - -/* Flags for injecting specific smart errors */ -#define PDSM_SMART_INJECT_HEALTH_FATAL (1 << 0) -#define PDSM_SMART_INJECT_BAD_SHUTDOWN (1 << 1) - -struct nd_papr_pdsm_smart_inject { - union { - struct { - /* One or more of PDSM_SMART_INJECT_ */ - __u32 flags; - __u8 fatal_enable; - __u8 unsafe_shutdown_enable; - }; - __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; - }; -}; - -/* - * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel - * via 'nd_cmd_pkg.nd_command' member of the ioctl struct - */ -enum papr_pdsm { - PAPR_PDSM_MIN = 0x0, - PAPR_PDSM_HEALTH, - PAPR_PDSM_SMART_INJECT, - PAPR_PDSM_MAX, -}; - -/* Maximal union that can hold all possible payload types */ -union nd_pdsm_payload { - struct nd_papr_pdsm_health health; - struct nd_papr_pdsm_smart_inject smart_inject; - __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; -} __packed; - -/* - * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm - * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command' - * that should always precede this struct when sent to papr_scm via CMD_CALL - * interface. - */ -struct nd_pkg_pdsm { - __s32 cmd_status; /* Out: Sub-cmd status returned back */ - __u16 reserved[2]; /* Ignored and to be set as '0' */ - union nd_pdsm_payload payload; -} __packed; - -#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */ diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index c233f9db039b..9b6420eb3567 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -16,7 +16,8 @@ #include #include -#include +#include +#include #include #include #include @@ -29,46 +30,6 @@ (1ul << ND_CMD_SET_CONFIG_DATA) | \ (1ul << ND_CMD_CALL)) -/* DIMM health bitmap indicators */ -/* SCM device is unable to persist memory contents */ -#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) -/* SCM device failed to persist memory contents */ -#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) -/* SCM device contents are persisted from previous IPL */ -#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2)) -/* SCM device contents are not persisted from previous IPL */ -#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) -/* SCM device memory life remaining is critically low */ -#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) -/* SCM device will be garded off next IPL due to failure */ -#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) -/* SCM contents cannot persist due to current platform health status */ -#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) -/* SCM device is unable to persist memory contents in certain conditions */ -#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7)) -/* SCM device is encrypted */ -#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8)) -/* SCM device has been scrubbed and locked */ -#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9)) - -/* Bits status indicators for health bitmap indicating unarmed dimm */ -#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ - PAPR_PMEM_HEALTH_UNHEALTHY) - -/* Bits status indicators for health bitmap indicating unflushed dimm */ -#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) - -/* Bits status indicators for health bitmap indicating unrestored dimm */ -#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) - -/* Bit status indicators for smart event notification */ -#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ - PAPR_PMEM_HEALTH_FATAL | \ - PAPR_PMEM_HEALTH_UNHEALTHY) - -#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) -#define PAPR_SCM_PERF_STATS_VERSION 0x1 - /* Struct holding a single performance metric */ struct papr_scm_perf_stat { u8 stat_id[8]; diff --git a/include/linux/papr_scm.h b/include/linux/papr_scm.h new file mode 100644 index 000000000000..eb36453813db --- /dev/null +++ b/include/linux/papr_scm.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __LINUX_PAPR_SCM_H +#define __LINUX_PAPR_SCM_H + +/* DIMM health bitmap indicators */ +/* SCM device is unable to persist memory contents */ +#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) +/* SCM device failed to persist memory contents */ +#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) +/* SCM device contents are persisted from previous IPL */ +#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2)) +/* SCM device contents are not persisted from previous IPL */ +#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) +/* SCM device memory life remaining is critically low */ +#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) +/* SCM device will be garded off next IPL due to failure */ +#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) +/* SCM contents cannot persist due to current platform health status */ +#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) +/* SCM device is unable to persist memory contents in certain conditions */ +#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7)) +/* SCM device is encrypted */ +#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8)) +/* SCM device has been scrubbed and locked */ +#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9)) + +#define PAPR_PMEM_SAVE_FAILED (1ULL << (63 - 10)) + +/* Bits status indicators for health bitmap indicating unarmed dimm */ +#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* Bits status indicators for health bitmap indicating unflushed dimm */ +#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) + +/* Bits status indicators for health bitmap indicating unrestored dimm */ +#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) + +/* Bit status indicators for smart event notification */ +#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ + PAPR_PMEM_HEALTH_FATAL | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +#define PAPR_PMEM_SAVE_MASK (PAPR_PMEM_SAVE_FAILED) + +#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) +#define PAPR_SCM_PERF_STATS_VERSION 0x1 + +#endif /* __LINUX_PAPR_SCM_H */ diff --git a/include/uapi/linux/papr_pdsm.h b/include/uapi/linux/papr_pdsm.h new file mode 100644 index 000000000000..17439925045c --- /dev/null +++ b/include/uapi/linux/papr_pdsm.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl + * + * (C) Copyright IBM 2020 + * + * Author: Vaibhav Jain + */ + +#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_ +#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_ + +#include +#include + +/* + * PDSM Envelope: + * + * The ioctl ND_CMD_CALL exchange data between user-space and kernel via + * envelope which consists of 2 headers sections and payload sections as + * illustrated below: + * +-----------------+---------------+---------------------------+ + * | 64-Bytes | 8-Bytes | Max 184-Bytes | + * +-----------------+---------------+---------------------------+ + * | ND-HEADER | PDSM-HEADER | PDSM-PAYLOAD | + * +-----------------+---------------+---------------------------+ + * | nd_family | | | + * | nd_size_out | cmd_status | | + * | nd_size_in | reserved | nd_pdsm_payload | + * | nd_command | payload --> | | + * | nd_fw_size | | | + * | nd_payload ---> | | | + * +---------------+-----------------+---------------------------+ + * + * ND Header: + * This is the generic libnvdimm header described as 'struct nd_cmd_pkg' + * which is interpreted by libnvdimm before passed on to papr_scm. Important + * member fields used are: + * 'nd_family' : (In) NVDIMM_FAMILY_PAPR_SCM + * 'nd_size_in' : (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0) + * 'nd_size_out' : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD + * 'nd_command' : (In) One of PAPR_PDSM_XXX + * 'nd_fw_size' : (Out) PDSM-HEADER + size of actual payload returned + * + * PDSM Header: + * This is papr-scm specific header that precedes the payload. This is defined + * as nd_cmd_pdsm_pkg. Following fields aare available in this header: + * + * 'cmd_status' : (Out) Errors if any encountered while servicing PDSM. + * 'reserved' : Not used, reserved for future and should be set to 0. + * 'payload' : A union of all the possible payload structs + * + * PDSM Payload: + * + * The layout of the PDSM Payload is defined by various structs shared between + * papr_scm and libndctl so that contents of payload can be interpreted. As such + * its defined as a union of all possible payload structs as + * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command' + * appropriate member of the union is accessed. + */ + +/* Max payload size that we can handle */ +#define ND_PDSM_PAYLOAD_MAX_SIZE 184 + +/* Max payload size that we can handle */ +#define ND_PDSM_HDR_SIZE \ + (sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE) + +/* Various nvdimm health indicators */ +#define PAPR_PDSM_DIMM_HEALTHY 0 +#define PAPR_PDSM_DIMM_UNHEALTHY 1 +#define PAPR_PDSM_DIMM_CRITICAL 2 +#define PAPR_PDSM_DIMM_FATAL 3 + +/* struct nd_papr_pdsm_health.extension_flags field flags */ + +/* Indicate that the 'dimm_fuel_gauge' field is valid */ +#define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1 + +/* Indicate that the 'dimm_dsc' field is valid */ +#define PDSM_DIMM_DSC_VALID 2 + +/* + * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH + * Various flags indicate the health status of the dimm. + * + * extension_flags : Any extension fields present in the struct. + * dimm_unarmed : Dimm not armed. So contents wont persist. + * dimm_bad_shutdown : Previous shutdown did not persist contents. + * dimm_bad_restore : Contents from previous shutdown werent restored. + * dimm_scrubbed : Contents of the dimm have been scrubbed. + * dimm_locked : Contents of the dimm cant be modified until CEC reboot + * dimm_encrypted : Contents of dimm are encrypted. + * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX + * dimm_fuel_gauge : Life remaining of DIMM as a percentage from 0-100 + */ +struct nd_papr_pdsm_health { + union { + struct { + __u32 extension_flags; + __u8 dimm_unarmed; + __u8 dimm_bad_shutdown; + __u8 dimm_bad_restore; + __u8 dimm_scrubbed; + __u8 dimm_locked; + __u8 dimm_encrypted; + __u16 dimm_health; + + /* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */ + __u16 dimm_fuel_gauge; + + /* Extension flag PDSM_DIMM_DSC_VALID */ + __u64 dimm_dsc; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + +/* Flags for injecting specific smart errors */ +#define PDSM_SMART_INJECT_HEALTH_FATAL (1 << 0) +#define PDSM_SMART_INJECT_BAD_SHUTDOWN (1 << 1) + +struct nd_papr_pdsm_smart_inject { + union { + struct { + /* One or more of PDSM_SMART_INJECT_ */ + __u32 flags; + __u8 fatal_enable; + __u8 unsafe_shutdown_enable; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + +/* + * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel + * via 'nd_cmd_pkg.nd_command' member of the ioctl struct + */ +enum papr_pdsm { + PAPR_PDSM_MIN = 0x0, + PAPR_PDSM_HEALTH, + PAPR_PDSM_SMART_INJECT, + PAPR_PDSM_MAX, +}; + +/* Maximal union that can hold all possible payload types */ +union nd_pdsm_payload { + struct nd_papr_pdsm_health health; + struct nd_papr_pdsm_smart_inject smart_inject; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; +} __packed; + +/* + * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm + * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command' + * that should always precede this struct when sent to papr_scm via CMD_CALL + * interface. + */ +struct nd_pkg_pdsm { + __s32 cmd_status; /* Out: Sub-cmd status returned back */ + __u16 reserved[2]; /* Ignored and to be set as '0' */ + union nd_pdsm_payload payload; +} __packed; + +#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */ diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index b8419f460368..fa9d1327fc71 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include "../watermark.h" #include "nfit_test.h" diff --git a/tools/testing/nvdimm/test/ndtest.h b/tools/testing/nvdimm/test/ndtest.h index 2c54c9cbb90c..8f27ad6f7319 100644 --- a/tools/testing/nvdimm/test/ndtest.h +++ b/tools/testing/nvdimm/test/ndtest.h @@ -5,37 +5,6 @@ #include #include -/* SCM device is unable to persist memory contents */ -#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) -/* SCM device failed to persist memory contents */ -#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) -/* SCM device contents are not persisted from previous IPL */ -#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) -#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) -/* SCM device will be garded off next IPL due to failure */ -#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) -/* SCM contents cannot persist due to current platform health status */ -#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) - -/* Bits status indicators for health bitmap indicating unarmed dimm */ -#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ - PAPR_PMEM_HEALTH_UNHEALTHY) - -#define PAPR_PMEM_SAVE_FAILED (1ULL << (63 - 10)) - -/* Bits status indicators for health bitmap indicating unflushed dimm */ -#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) - -/* Bits status indicators for health bitmap indicating unrestored dimm */ -#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) - -/* Bit status indicators for smart event notification */ -#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ - PAPR_PMEM_HEALTH_FATAL | \ - PAPR_PMEM_HEALTH_UNHEALTHY) - -#define PAPR_PMEM_SAVE_MASK (PAPR_PMEM_SAVE_FAILED) - struct ndtest_config; struct ndtest_priv { -- cgit v1.2.3 From 48e2cd3e3dcfe04f212df4fb189fa04c2a87b980 Mon Sep 17 00:00:00 2001 From: Philo Lu Date: Fri, 26 Apr 2024 00:17:23 +0800 Subject: bpf: add mrtt and srtt as BPF_SOCK_OPS_RTT_CB args Two important arguments in RTT estimation, mrtt and srtt, are passed to tcp_bpf_rtt(), so that bpf programs get more information about RTT computation in BPF_SOCK_OPS_RTT_CB. The difference between bpf_sock_ops->srtt_us and the srtt here is: the former is an old rtt before update, while srtt passed by tcp_bpf_rtt() is that after update. Signed-off-by: Philo Lu Link: https://lore.kernel.org/r/20240425161724.73707-2-lulie@linux.alibaba.com Signed-off-by: Martin KaFai Lau --- include/net/tcp.h | 4 ++-- include/uapi/linux/bpf.h | 2 ++ net/ipv4/tcp_input.c | 4 ++-- tools/include/uapi/linux/bpf.h | 2 ++ 4 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ae35199d3b3..0f75d03287c2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2706,10 +2706,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } -static inline void tcp_bpf_rtt(struct sock *sk) +static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) - tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); + tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e4ae83550fb3..d94a72593ead 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6947,6 +6947,8 @@ enum { * socket transition to LISTEN state. */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt */ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. * It will be called to handle diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5d874817a78d..d1115d7c3936 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -911,7 +911,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->rtt_seq = tp->snd_nxt; tp->mdev_max_us = tcp_rto_min_us(sk); - tcp_bpf_rtt(sk); + tcp_bpf_rtt(sk, mrtt_us, srtt); } } else { /* no previous measure. */ @@ -921,7 +921,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; - tcp_bpf_rtt(sk); + tcp_bpf_rtt(sk, mrtt_us, srtt); } tp->srtt_us = max(1U, srtt); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e4ae83550fb3..d94a72593ead 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6947,6 +6947,8 @@ enum { * socket transition to LISTEN state. */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt */ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. * It will be called to handle -- cgit v1.2.3 From 5055cccfc2d1cc1a7306f6bcdcd0ee9521d707f5 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Tue, 23 Apr 2024 14:49:04 +0200 Subject: net: hsr: Provide RedBox support (HSR-SAN) Introduce RedBox support (HSR-SAN to be more precise) for HSR networks. Following traffic reduction optimizations have been implemented: - Do not send HSR supervisory frames to Port C (interlink) - Do not forward to HSR ring frames addressed to Port C - Do not forward to Port C frames from HSR ring - Do not send duplicate HSR frame to HSR ring when destination is Port C The corresponding patch to modify iptable2 sources has already been sent: https://lore.kernel.org/netdev/20240308145729.490863-1-lukma@denx.de/T/ Testing procedure (veth and netns): ----------------------------------- One shall run: linux-vanila/tools/testing/selftests/net/hsr/hsr_redbox.sh (Detailed description of the setup one can find in the test script file). Testing procedure (real hardware): ---------------------------------- The EVB-KSZ9477 has been used for testing on net-next branch (SHA1: 5fc68320c1fb3c7d456ddcae0b4757326a043e6f). Ports 4/5 were used for SW managed HSR (hsr1) as first hsr0 for ports 1/2 (with HW offloading for ksz9477) was created. Port 3 has been used as interlink port (single USB-ETH dongle). Configuration - RedBox (EVB-KSZ9477): if link set lan1 down;ip link set lan2 down ip link add name hsr0 type hsr slave1 lan1 slave2 lan2 supervision 45 version 1 ip link add name hsr1 type hsr slave1 lan4 slave2 lan5 interlink lan3 supervision 45 version 1 ip link set lan4 up;ip link set lan5 up ip link set lan3 up ip addr add 192.168.0.11/24 dev hsr1 ip link set hsr1 up Configuration - DAN-H (EVB-KSZ9477): ip link set lan1 down;ip link set lan2 down ip link add name hsr0 type hsr slave1 lan1 slave2 lan2 supervision 45 version 1 ip link add name hsr1 type hsr slave1 lan4 slave2 lan5 supervision 45 version 1 ip link set lan4 up;ip link set lan5 up ip addr add 192.168.0.12/24 dev hsr1 ip link set hsr1 up This approach uses only SW based HSR devices (hsr1). -------------- ----------------- ------------ DAN-H Port5 | <------> | Port5 | | Port4 | <------> | Port4 Port3 | <---> | PC | | (RedBox) | | (USB-ETH) EVB-KSZ9477 | | EVB-KSZ9477 | | -------------- ----------------- ------------ Signed-off-by: Lukasz Majewski Signed-off-by: Paolo Abeni --- include/uapi/linux/if_link.h | 1 + net/hsr/hsr_device.c | 36 +++++++++++++++++-- net/hsr/hsr_device.h | 4 +-- net/hsr/hsr_forward.c | 85 +++++++++++++++++++++++++++++++++++++++----- net/hsr/hsr_framereg.c | 52 +++++++++++++++++++++++++++ net/hsr/hsr_framereg.h | 4 +++ net/hsr/hsr_main.h | 7 ++++ net/hsr/hsr_netlink.c | 30 ++++++++++++++-- net/hsr/hsr_slave.c | 1 + 9 files changed, 204 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ffa637b38c93..e9f10860ec8e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1771,6 +1771,7 @@ enum { IFLA_HSR_PROTOCOL, /* Indicate different protocol than * HSR. For example PRP. */ + IFLA_HSR_INTERLINK, /* HSR interlink network device */ __IFLA_HSR_MAX, }; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e9d45133d641..cd1e7c6d2fc0 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -146,6 +146,9 @@ static int hsr_dev_open(struct net_device *dev) case HSR_PT_SLAVE_B: designation = "Slave B"; break; + case HSR_PT_INTERLINK: + designation = "Interlink"; + break; default: designation = "Unknown"; } @@ -285,6 +288,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, struct hsr_priv *hsr = master->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; + struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; @@ -324,6 +328,16 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); + if (hsr->redbox) { + hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); + hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; + hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); + + /* Payload: MacAddressRedBox */ + hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); + ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); + } + if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; @@ -405,6 +419,10 @@ void hsr_del_ports(struct hsr_priv *hsr) if (port) hsr_del_port(port); + port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); + if (port) + hsr_del_port(port); + port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); @@ -534,8 +552,8 @@ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], - unsigned char multicast_spec, u8 protocol_version, - struct netlink_ext_ack *extack) + struct net_device *interlink, unsigned char multicast_spec, + u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; @@ -544,6 +562,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); + INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); @@ -569,6 +588,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; + hsr->interlink_sequence_nr = HSR_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); @@ -604,6 +624,18 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], if (res) goto err_unregister; + if (interlink) { + res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); + if (res) + goto err_unregister; + + hsr->redbox = true; + ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); + timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); + mod_timer(&hsr->prune_proxy_timer, + jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); + } + hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index 9060c92168f9..655284095b78 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -16,8 +16,8 @@ void hsr_del_ports(struct hsr_priv *hsr); void hsr_dev_setup(struct net_device *dev); int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], - unsigned char multicast_spec, u8 protocol_version, - struct netlink_ext_ack *extack); + struct net_device *interlink, unsigned char multicast_spec, + u8 protocol_version, struct netlink_ext_ack *extack); void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); int hsr_get_max_mtu(struct hsr_priv *hsr); #endif /* __HSR_DEVICE_H */ diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 5d68cb181695..05a61b8286ec 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -377,6 +377,15 @@ static int hsr_xmit(struct sk_buff *skb, struct hsr_port *port, */ ether_addr_copy(eth_hdr(skb)->h_source, port->dev->dev_addr); } + + /* When HSR node is used as RedBox - the frame received from HSR ring + * requires source MAC address (SA) replacement to one which can be + * recognized by SAN devices (otherwise, frames are dropped by switch) + */ + if (port->type == HSR_PT_INTERLINK) + ether_addr_copy(eth_hdr(skb)->h_source, + port->hsr->macaddress_redbox); + return dev_queue_xmit(skb); } @@ -390,9 +399,57 @@ bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) { + struct sk_buff *skb; + if (port->dev->features & NETIF_F_HW_HSR_FWD) return prp_drop_frame(frame, port); + /* RedBox specific frames dropping policies + * + * Do not send HSR supervisory frames to SAN devices + */ + if (frame->is_supervision && port->type == HSR_PT_INTERLINK) + return true; + + /* Do not forward to other HSR port (A or B) unicast frames which + * are addressed to interlink port (and are in the ProxyNodeTable). + */ + skb = frame->skb_hsr; + if (skb && prp_drop_frame(frame, port) && + is_unicast_ether_addr(eth_hdr(skb)->h_dest) && + hsr_is_node_in_db(&port->hsr->proxy_node_db, + eth_hdr(skb)->h_dest)) { + return true; + } + + /* Do not forward to port C (Interlink) frames from nodes A and B + * if DA is in NodeTable. + */ + if ((frame->port_rcv->type == HSR_PT_SLAVE_A || + frame->port_rcv->type == HSR_PT_SLAVE_B) && + port->type == HSR_PT_INTERLINK) { + skb = frame->skb_hsr; + if (skb && is_unicast_ether_addr(eth_hdr(skb)->h_dest) && + hsr_is_node_in_db(&port->hsr->node_db, + eth_hdr(skb)->h_dest)) { + return true; + } + } + + /* Do not forward to port A and B unicast frames received on the + * interlink port if it is addressed to one of nodes registered in + * the ProxyNodeTable. + */ + if ((port->type == HSR_PT_SLAVE_A || port->type == HSR_PT_SLAVE_B) && + frame->port_rcv->type == HSR_PT_INTERLINK) { + skb = frame->skb_std; + if (skb && is_unicast_ether_addr(eth_hdr(skb)->h_dest) && + hsr_is_node_in_db(&port->hsr->proxy_node_db, + eth_hdr(skb)->h_dest)) { + return true; + } + } + return false; } @@ -448,13 +505,14 @@ static void hsr_forward_do(struct hsr_frame_info *frame) } /* Check if frame is to be dropped. Eg. for PRP no forward - * between ports. + * between ports, or sending HSR supervision to RedBox. */ if (hsr->proto_ops->drop_frame && hsr->proto_ops->drop_frame(frame, port)) continue; - if (port->type != HSR_PT_MASTER) + if (port->type == HSR_PT_SLAVE_A || + port->type == HSR_PT_SLAVE_B) skb = hsr->proto_ops->create_tagged_frame(frame, port); else skb = hsr->proto_ops->get_untagged_frame(frame, port); @@ -469,7 +527,9 @@ static void hsr_forward_do(struct hsr_frame_info *frame) hsr_deliver_master(skb, port->dev, frame->node_src); } else { if (!hsr_xmit(skb, port, frame)) - sent = true; + if (port->type == HSR_PT_SLAVE_A || + port->type == HSR_PT_SLAVE_B) + sent = true; } } } @@ -503,10 +563,12 @@ static void handle_std_frame(struct sk_buff *skb, frame->skb_prp = NULL; frame->skb_std = skb; - if (port->type != HSR_PT_MASTER) { + if (port->type != HSR_PT_MASTER) frame->is_from_san = true; - } else { - /* Sequence nr for the master node */ + + if (port->type == HSR_PT_MASTER || + port->type == HSR_PT_INTERLINK) { + /* Sequence nr for the master/interlink node */ lockdep_assert_held(&hsr->seqnr_lock); frame->sequence_nr = hsr->sequence_nr; hsr->sequence_nr++; @@ -564,6 +626,7 @@ static int fill_frame_info(struct hsr_frame_info *frame, { struct hsr_priv *hsr = port->hsr; struct hsr_vlan_ethhdr *vlan_hdr; + struct list_head *n_db; struct ethhdr *ethhdr; __be16 proto; int ret; @@ -574,9 +637,13 @@ static int fill_frame_info(struct hsr_frame_info *frame, memset(frame, 0, sizeof(*frame)); frame->is_supervision = is_supervision_frame(port->hsr, skb); - frame->node_src = hsr_get_node(port, &hsr->node_db, skb, - frame->is_supervision, - port->type); + + n_db = &hsr->node_db; + if (port->type == HSR_PT_INTERLINK) + n_db = &hsr->proxy_node_db; + + frame->node_src = hsr_get_node(port, n_db, skb, + frame->is_supervision, port->type); if (!frame->node_src) return -1; /* Unknown node and !is_supervision, or no mem */ diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 26329db09210..614df9649794 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -71,6 +71,14 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, return NULL; } +/* Check if node for a given MAC address is already present in data base + */ +bool hsr_is_node_in_db(struct list_head *node_db, + const unsigned char addr[ETH_ALEN]) +{ + return !!find_node_by_addr_A(node_db, addr); +} + /* Helper for device init; the self_node is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ @@ -223,6 +231,15 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, } } + /* Check if required node is not in proxy nodes table */ + list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { + if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { + if (hsr->proto_ops->update_san_info) + hsr->proto_ops->update_san_info(node, is_sup); + return node; + } + } + /* Everyone may create a node entry, connected node to a HSR/PRP * device. */ @@ -418,6 +435,10 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); + if (!node_dst && port->hsr->redbox) + node_dst = find_node_by_addr_A(&port->hsr->proxy_node_db, + eth_hdr(skb)->h_dest); + if (!node_dst) { if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); @@ -561,6 +582,37 @@ void hsr_prune_nodes(struct timer_list *t) jiffies + msecs_to_jiffies(PRUNE_PERIOD)); } +void hsr_prune_proxy_nodes(struct timer_list *t) +{ + struct hsr_priv *hsr = from_timer(hsr, t, prune_proxy_timer); + unsigned long timestamp; + struct hsr_node *node; + struct hsr_node *tmp; + + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_safe(node, tmp, &hsr->proxy_node_db, mac_list) { + timestamp = node->time_in[HSR_PT_INTERLINK]; + + /* Prune old entries */ + if (time_is_before_jiffies(timestamp + + msecs_to_jiffies(HSR_PROXY_NODE_FORGET_TIME))) { + hsr_nl_nodedown(hsr, node->macaddress_A); + if (!node->removed) { + list_del_rcu(&node->mac_list); + node->removed = true; + /* Note that we need to free this entry later: */ + kfree_rcu(node, rcu_head); + } + } + } + + spin_unlock_bh(&hsr->list_lock); + + /* Restart timer */ + mod_timer(&hsr->prune_proxy_timer, + jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); +} + void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index b23556251d62..7619e31c1d2d 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -46,6 +46,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr); void hsr_prune_nodes(struct timer_list *t); +void hsr_prune_proxy_nodes(struct timer_list *t); int hsr_create_self_node(struct hsr_priv *hsr, const unsigned char addr_a[ETH_ALEN], @@ -67,6 +68,9 @@ void prp_handle_san_frame(bool san, enum hsr_port_type port, struct hsr_node *node); void prp_update_san_info(struct hsr_node *node, bool is_sup); +bool hsr_is_node_in_db(struct list_head *node_db, + const unsigned char addr[ETH_ALEN]); + struct hsr_node { struct list_head mac_list; /* Protect R/W access to seq_out */ diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 18e01791ad79..23850b16d1ea 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -21,6 +21,7 @@ */ #define HSR_LIFE_CHECK_INTERVAL 2000 /* ms */ #define HSR_NODE_FORGET_TIME 60000 /* ms */ +#define HSR_PROXY_NODE_FORGET_TIME 60000 /* ms */ #define HSR_ANNOUNCE_INTERVAL 100 /* ms */ #define HSR_ENTRY_FORGET_TIME 400 /* ms */ @@ -35,6 +36,7 @@ * HSR_NODE_FORGET_TIME? */ #define PRUNE_PERIOD 3000 /* ms */ +#define PRUNE_PROXY_PERIOD 3000 /* ms */ #define HSR_TLV_EOT 0 /* End of TLVs */ #define HSR_TLV_ANNOUNCE 22 #define HSR_TLV_LIFE_CHECK 23 @@ -192,11 +194,14 @@ struct hsr_priv { struct rcu_head rcu_head; struct list_head ports; struct list_head node_db; /* Known HSR nodes */ + struct list_head proxy_node_db; /* RedBox HSR proxy nodes */ struct hsr_self_node __rcu *self_node; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ struct timer_list prune_timer; + struct timer_list prune_proxy_timer; int announce_count; u16 sequence_nr; + u16 interlink_sequence_nr; /* Interlink port seq_nr */ u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ enum hsr_version prot_version; /* Indicate if HSRv0, HSRv1 or PRPv1 */ spinlock_t seqnr_lock; /* locking for sequence_nr */ @@ -209,6 +214,8 @@ struct hsr_priv { * of lan_id */ bool fwd_offloaded; /* Forwarding offloaded to HW */ + bool redbox; /* Device supports HSR RedBox */ + unsigned char macaddress_redbox[ETH_ALEN]; unsigned char sup_multicast_addr[ETH_ALEN] __aligned(sizeof(u16)); /* Align to u16 boundary to avoid unaligned access * in ether_addr_equal diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 78fe40eb9f01..898f18c6da53 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -23,6 +23,7 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { [IFLA_HSR_SUPERVISION_ADDR] = { .len = ETH_ALEN }, [IFLA_HSR_SEQ_NR] = { .type = NLA_U16 }, [IFLA_HSR_PROTOCOL] = { .type = NLA_U8 }, + [IFLA_HSR_INTERLINK] = { .type = NLA_U32 }, }; /* Here, it seems a netdevice has already been allocated for us, and the @@ -35,8 +36,8 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, enum hsr_version proto_version; unsigned char multicast_spec; u8 proto = HSR_PROTOCOL_HSR; - struct net_device *link[2]; + struct net_device *link[2], *interlink = NULL; if (!data) { NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); return -EINVAL; @@ -67,6 +68,20 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; } + if (data[IFLA_HSR_INTERLINK]) + interlink = __dev_get_by_index(src_net, + nla_get_u32(data[IFLA_HSR_INTERLINK])); + + if (interlink && interlink == link[0]) { + NL_SET_ERR_MSG_MOD(extack, "Interlink and Slave1 are the same"); + return -EINVAL; + } + + if (interlink && interlink == link[1]) { + NL_SET_ERR_MSG_MOD(extack, "Interlink and Slave2 are the same"); + return -EINVAL; + } + if (!data[IFLA_HSR_MULTICAST_SPEC]) multicast_spec = 0; else @@ -96,10 +111,17 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, } } - if (proto == HSR_PROTOCOL_PRP) + if (proto == HSR_PROTOCOL_PRP) { proto_version = PRP_V1; + if (interlink) { + NL_SET_ERR_MSG_MOD(extack, + "Interlink only works with HSR"); + return -EINVAL; + } + } - return hsr_dev_finalize(dev, link, multicast_spec, proto_version, extack); + return hsr_dev_finalize(dev, link, interlink, multicast_spec, + proto_version, extack); } static void hsr_dellink(struct net_device *dev, struct list_head *head) @@ -107,6 +129,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) struct hsr_priv *hsr = netdev_priv(dev); del_timer_sync(&hsr->prune_timer); + del_timer_sync(&hsr->prune_proxy_timer); del_timer_sync(&hsr->announce_timer); hsr_debugfs_term(hsr); @@ -114,6 +137,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); + hsr_del_nodes(&hsr->proxy_node_db); unregister_netdevice_queue(dev, head); } diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 1b6457f357bd..af6cf64a00e0 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -55,6 +55,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && + port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; -- cgit v1.2.3 From c580efb94abed05f99bb80245abe96cf5d49128c Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 2 Apr 2024 02:37:25 +0300 Subject: media: v4l2-subdev: Clearly document that the crop API won't be extended The V4L2 subdev crop API has been marked as obsolete, deprecated by the selection API. Despite this, it has recently been extended with streams support. In hindsight this was a mistake. Make sure it doesn't happen again by clearly documenting that no new extensions will be accepted. Suggested-by: Hans Verkuil Signed-off-by: Laurent Pinchart Acked-by: Sakari Ailus Reviewed-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst | 6 +++--- include/uapi/linux/v4l2-subdev.h | 4 ++++ 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst index 92d933631fda..88a748103a71 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst @@ -37,9 +37,9 @@ Description .. note:: - This is an :ref:`obsolete` interface and may be removed - in the future. It is superseded by - :ref:`the selection API `. + This is an :ref:`obsolete` interface and may be removed in the future. It is + superseded by :ref:`the selection API `. No new + extensions to the :c:type:`v4l2_subdev_crop` structure will be accepted. To retrieve the current crop rectangle applications set the ``pad`` field of a struct :c:type:`v4l2_subdev_crop` to the diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 7048c51581c6..81a24bd38003 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -50,6 +50,10 @@ struct v4l2_subdev_format { * @rect: pad crop rectangle boundaries * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array + * + * The subdev crop API is an obsolete interface and may be removed in the + * future. It is superseded by the selection API. No new extensions to this + * structure will be accepted. */ struct v4l2_subdev_crop { __u32 which; -- cgit v1.2.3 From f28bdda2f87aa0c299ad3ddef3e1fa5134ae8e47 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 25 Apr 2023 16:50:25 +0300 Subject: media: uapi: Add generic serial metadata mbus formats Add generic serial metadata mbus formats. These formats describe data width and packing but not the content itself. The reason for specifying such formats is that the formats as such are fairly device specific but they are still handled by CSI-2 receiver drivers that should not be aware of device specific formats. What makes generic metadata formats possible is that these formats are parsed by software only, after capturing the data to system memory. Also add a definition for "Data Unit" to cover what is essentially a pixel but is not image data. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/glossary.rst | 7 + .../userspace-api/media/v4l/subdev-formats.rst | 254 +++++++++++++++++++++ include/uapi/linux/media-bus-format.h | 9 + 3 files changed, 270 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/glossary.rst b/Documentation/userspace-api/media/glossary.rst index 5759f4c78398..55a9c37130ba 100644 --- a/Documentation/userspace-api/media/glossary.rst +++ b/Documentation/userspace-api/media/glossary.rst @@ -25,6 +25,13 @@ Glossary See :ref:`cec`. + Data Unit + + Unit of data transported by a bus. On parallel buses, the data unit + consists of one or more related samples while on serial buses the data + unit is logical. If the data unit is image data, it may also be called a + pixel. + Device Driver Part of the Linux Kernel that implements support for a hardware component. diff --git a/Documentation/userspace-api/media/v4l/subdev-formats.rst b/Documentation/userspace-api/media/v4l/subdev-formats.rst index eb3cd20b0cf2..c2cebf61d528 100644 --- a/Documentation/userspace-api/media/v4l/subdev-formats.rst +++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst @@ -8306,3 +8306,257 @@ The following table lists the existing metadata formats. both sides of the link and the bus format is a fixed metadata format that is not configurable from userspace. Width and height will be set to 0 for this format. + +Generic Serial Metadata Formats +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Generic serial metadata formats are used on serial buses where the actual data +content is more or less device specific but the data is transmitted and received +by multiple devices that do not process the data in any way, simply writing +it to system memory for processing in software at the end of the pipeline. + +"b" in an array cell signifies a byte of data, followed by the number of the bit +and finally the bit number in subscript. "x" indicates a padding bit. + +.. _media-bus-format-generic-meta: + +.. cssclass: longtable + +.. flat-table:: Generic Serial Metadata Formats + :header-rows: 2 + :stub-columns: 0 + + * - Identifier + - Code + - + - :cspan:`23` Data organization within bus :term:`Data Unit` + * - + - + - Bit + - 23 + - 22 + - 21 + - 20 + - 19 + - 18 + - 17 + - 16 + - 15 + - 14 + - 13 + - 12 + - 11 + - 10 + - 9 + - 8 + - 7 + - 6 + - 5 + - 4 + - 3 + - 2 + - 1 + - 0 + * .. _MEDIA-BUS-FMT-META-8: + + - MEDIA_BUS_FMT_META_8 + - 0x8001 + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + * .. _MEDIA-BUS-FMT-META-10: + + - MEDIA_BUS_FMT_META_10 + - 0x8002 + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + - x + - x + * .. _MEDIA-BUS-FMT-META-12: + + - MEDIA_BUS_FMT_META_12 + - 0x8003 + - + - + - + - + - + - + - + - + - + - + - + - + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + - x + - x + - x + - x + * .. _MEDIA-BUS-FMT-META-14: + + - MEDIA_BUS_FMT_META_14 + - 0x8004 + - + - + - + - + - + - + - + - + - + - + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + - x + - x + - x + - x + - x + - x + * .. _MEDIA-BUS-FMT-META-16: + + - MEDIA_BUS_FMT_META_16 + - 0x8005 + - + - + - + - + - + - + - + - + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + - x + - x + - x + - x + - x + - x + - x + - x + * .. _MEDIA-BUS-FMT-META-20: + + - MEDIA_BUS_FMT_META_20 + - 0x8006 + - + - + - + - + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + * .. _MEDIA-BUS-FMT-META-24: + + - MEDIA_BUS_FMT_META_24 + - 0x8007 + - + - b0\ :sub:`7` + - b0\ :sub:`6` + - b0\ :sub:`5` + - b0\ :sub:`4` + - b0\ :sub:`3` + - b0\ :sub:`2` + - b0\ :sub:`1` + - b0\ :sub:`0` + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x + - x diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index f05f747e444d..d4c1d991014b 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -174,4 +174,13 @@ */ #define MEDIA_BUS_FMT_METADATA_FIXED 0x7001 +/* Generic line based metadata formats for serial buses. Next is 0x8008. */ +#define MEDIA_BUS_FMT_META_8 0x8001 +#define MEDIA_BUS_FMT_META_10 0x8002 +#define MEDIA_BUS_FMT_META_12 0x8003 +#define MEDIA_BUS_FMT_META_14 0x8004 +#define MEDIA_BUS_FMT_META_16 0x8005 +#define MEDIA_BUS_FMT_META_20 0x8006 +#define MEDIA_BUS_FMT_META_24 0x8007 + #endif /* __LINUX_MEDIA_BUS_FORMAT_H */ -- cgit v1.2.3 From ac5214a47336b8a8f7e54f406ee4f7eed9223599 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 1 Aug 2023 16:15:36 +0300 Subject: media: uapi: Document which mbus format fields are valid for metadata Now that metadata mbus formats have been added, it is necessary to define which fields in struct v4l2_mbus_format are applicable to them (not many). Signed-off-by: Sakari Ailus Reviewed-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/subdev-formats.rst | 15 ++++++++------- include/uapi/linux/v4l2-mediabus.h | 18 ++++++++++++------ 2 files changed, 20 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/subdev-formats.rst b/Documentation/userspace-api/media/v4l/subdev-formats.rst index c2cebf61d528..d2a6cd2e1eb2 100644 --- a/Documentation/userspace-api/media/v4l/subdev-formats.rst +++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst @@ -33,7 +33,7 @@ Media Bus Formats * - __u32 - ``field`` - Field order, from enum :c:type:`v4l2_field`. See - :ref:`field-order` for details. + :ref:`field-order` for details. Zero for metadata mbus codes. * - __u32 - ``colorspace`` - Image colorspace, from enum :c:type:`v4l2_colorspace`. @@ -45,7 +45,7 @@ Media Bus Formats conversion is supported by setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE in the corresponding struct :c:type:`v4l2_subdev_mbus_code_enum` during enumeration. - See :ref:`v4l2-subdev-mbus-code-flags`. + See :ref:`v4l2-subdev-mbus-code-flags`. Zero for metadata mbus codes. * - union { - (anonymous) * - __u16 @@ -61,7 +61,7 @@ Media Bus Formats that ycbcr_enc conversion is supported by setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC in the corresponding struct :c:type:`v4l2_subdev_mbus_code_enum` during enumeration. - See :ref:`v4l2-subdev-mbus-code-flags`. + See :ref:`v4l2-subdev-mbus-code-flags`. Zero for metadata mbus codes. * - __u16 - ``hsv_enc`` - HSV encoding, from enum :c:type:`v4l2_hsv_encoding`. @@ -75,7 +75,7 @@ Media Bus Formats that hsv_enc conversion is supported by setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC in the corresponding struct :c:type:`v4l2_subdev_mbus_code_enum` during enumeration. - See :ref:`v4l2-subdev-mbus-code-flags` + See :ref:`v4l2-subdev-mbus-code-flags`. Zero for metadata mbus codes. * - } - * - __u16 @@ -90,8 +90,8 @@ Media Bus Formats The driver indicates that quantization conversion is supported by setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION in the corresponding struct :c:type:`v4l2_subdev_mbus_code_enum` - during enumeration. See :ref:`v4l2-subdev-mbus-code-flags`. - + during enumeration. See :ref:`v4l2-subdev-mbus-code-flags`. Zero for + metadata mbus codes. * - __u16 - ``xfer_func`` - Transfer function, from enum :c:type:`v4l2_xfer_func`. @@ -104,7 +104,8 @@ Media Bus Formats The driver indicates that the transfer function conversion is supported by setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC in the corresponding struct :c:type:`v4l2_subdev_mbus_code_enum` - during enumeration. See :ref:`v4l2-subdev-mbus-code-flags`. + during enumeration. See :ref:`v4l2-subdev-mbus-code-flags`. Zero for + metadata mbus codes. * - __u16 - ``flags`` - flags See: :ref:v4l2-mbus-framefmt-flags diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h index 6b07b73473b5..946520bc49f1 100644 --- a/include/uapi/linux/v4l2-mediabus.h +++ b/include/uapi/linux/v4l2-mediabus.h @@ -19,12 +19,18 @@ * @width: image width * @height: image height * @code: data format code (from enum v4l2_mbus_pixelcode) - * @field: used interlacing type (from enum v4l2_field) - * @colorspace: colorspace of the data (from enum v4l2_colorspace) - * @ycbcr_enc: YCbCr encoding of the data (from enum v4l2_ycbcr_encoding) - * @hsv_enc: HSV encoding of the data (from enum v4l2_hsv_encoding) - * @quantization: quantization of the data (from enum v4l2_quantization) - * @xfer_func: transfer function of the data (from enum v4l2_xfer_func) + * @field: used interlacing type (from enum v4l2_field), zero for metadata + * mbus codes + * @colorspace: colorspace of the data (from enum v4l2_colorspace), zero on + * metadata mbus codes + * @ycbcr_enc: YCbCr encoding of the data (from enum v4l2_ycbcr_encoding), zero + * for metadata mbus codes + * @hsv_enc: HSV encoding of the data (from enum v4l2_hsv_encoding), zero for + * metadata mbus codes + * @quantization: quantization of the data (from enum v4l2_quantization), zero + * for metadata mbus codes + * @xfer_func: transfer function of the data (from enum v4l2_xfer_func), zero + * for metadata mbus codes * @flags: flags (V4L2_MBUS_FRAMEFMT_*) * @reserved: reserved bytes that can be later used */ -- cgit v1.2.3 From 1d92152339587174363c3c9f7561de95646d5625 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 26 Apr 2023 13:28:48 +0300 Subject: media: uapi: v4l: Add generic 8-bit metadata format definitions Generic 8-bit metadata formats define the in-memory data layout but not the format of the data itself. The reasoning for having such formats is to allow CSI-2 receiver drivers to receive and DMA drivers to write the data to memory without knowing a large number of device-specific formats. These formats may be used only in conjunction with a Media Controller pipeline where the internal pad of the source sub-device defines the specific format of the data (using an mbus code). Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/dev-subdev.rst | 2 + .../userspace-api/media/v4l/meta-formats.rst | 3 +- .../userspace-api/media/v4l/metafmt-generic.rst | 340 +++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 7 + include/uapi/linux/videodev2.h | 8 + 5 files changed, 359 insertions(+), 1 deletion(-) create mode 100644 Documentation/userspace-api/media/v4l/metafmt-generic.rst (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/dev-subdev.rst b/Documentation/userspace-api/media/v4l/dev-subdev.rst index 43988516acdd..f375b820ab68 100644 --- a/Documentation/userspace-api/media/v4l/dev-subdev.rst +++ b/Documentation/userspace-api/media/v4l/dev-subdev.rst @@ -506,6 +506,8 @@ source pads. subdev-formats +.. _subdev-routing: + Streams, multiplexed media pads and internal routing ---------------------------------------------------- diff --git a/Documentation/userspace-api/media/v4l/meta-formats.rst b/Documentation/userspace-api/media/v4l/meta-formats.rst index 0bb61fc5bc00..c23aac823d2c 100644 --- a/Documentation/userspace-api/media/v4l/meta-formats.rst +++ b/Documentation/userspace-api/media/v4l/meta-formats.rst @@ -13,9 +13,10 @@ These formats are used for the :ref:`metadata` interface only. :maxdepth: 1 metafmt-d4xx + metafmt-generic metafmt-intel-ipu3 metafmt-rkisp1 metafmt-uvc + metafmt-vivid metafmt-vsp1-hgo metafmt-vsp1-hgt - metafmt-vivid diff --git a/Documentation/userspace-api/media/v4l/metafmt-generic.rst b/Documentation/userspace-api/media/v4l/metafmt-generic.rst new file mode 100644 index 000000000000..78ab56b21682 --- /dev/null +++ b/Documentation/userspace-api/media/v4l/metafmt-generic.rst @@ -0,0 +1,340 @@ +.. SPDX-License-Identifier: GPL-2.0 OR GFDL-1.1-no-invariants-or-later + +******************************************************************************************************************************************************************************************************************************************************************************** +V4L2_META_FMT_GENERIC_8 ('MET8'), V4L2_META_FMT_GENERIC_CSI2_10 ('MC1A'), V4L2_META_FMT_GENERIC_CSI2_12 ('MC1C'), V4L2_META_FMT_GENERIC_CSI2_14 ('MC1E'), V4L2_META_FMT_GENERIC_CSI2_16 ('MC1G'), V4L2_META_FMT_GENERIC_CSI2_20 ('MC1K'), V4L2_META_FMT_GENERIC_CSI2_24 ('MC1O') +******************************************************************************************************************************************************************************************************************************************************************************** + + +Generic line-based metadata formats + + +Description +=========== + +These generic line-based metadata formats define the memory layout of the data +without defining the format or meaning of the metadata itself. + +.. _v4l2-meta-fmt-generic-8: + +V4L2_META_FMT_GENERIC_8 +----------------------- + +The V4L2_META_FMT_GENERIC_8 format is a plain 8-bit metadata format. This format +is used on CSI-2 for 8 bits per :term:`Data Unit`. + +Additionally it is used for 16 bits per Data Unit when two bytes of metadata are +packed into one 16-bit Data Unit. Otherwise the 16 bits per pixel dataformat is +:ref:`V4L2_META_FMT_GENERIC_CSI2_16 `. + +**Byte Order Of V4L2_META_FMT_GENERIC_8.** +Each cell is one byte. "M" denotes a byte of metadata. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - M\ :sub:`10` + - M\ :sub:`20` + - M\ :sub:`30` + * - start + 4: + - M\ :sub:`01` + - M\ :sub:`11` + - M\ :sub:`21` + - M\ :sub:`31` + +.. _v4l2-meta-fmt-generic-csi2-10: + +V4L2_META_FMT_GENERIC_CSI2_10 +----------------------------- + +V4L2_META_FMT_GENERIC_CSI2_10 contains 8-bit generic metadata packed in 10-bit +Data Units, with one padding byte after every four bytes of metadata. This +format is typically used by CSI-2 receivers with a source that transmits +MEDIA_BUS_FMT_META_10 and the CSI-2 receiver writes the received data to memory +as-is. + +The packing of the data follows the MIPI CSI-2 specification and the padding of +the data is defined in the MIPI CCS specification. + +This format is also used in conjunction with 20 bits per :term:`Data Unit` +formats that pack two bytes of metadata into one Data Unit. Otherwise the +20 bits per pixel dataformat is :ref:`V4L2_META_FMT_GENERIC_CSI2_20 +`. + +This format is little endian. + +**Byte Order Of V4L2_META_FMT_GENERIC_CSI2_10.** +Each cell is one byte. "M" denotes a byte of metadata and "x" a byte of padding. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{.8cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - M\ :sub:`10` + - M\ :sub:`20` + - M\ :sub:`30` + - x + * - start + 5: + - M\ :sub:`01` + - M\ :sub:`11` + - M\ :sub:`21` + - M\ :sub:`31` + - x + +.. _v4l2-meta-fmt-generic-csi2-12: + +V4L2_META_FMT_GENERIC_CSI2_12 +----------------------------- + +V4L2_META_FMT_GENERIC_CSI2_12 contains 8-bit generic metadata packed in 12-bit +Data Units, with one padding byte after every two bytes of metadata. This format +is typically used by CSI-2 receivers with a source that transmits +MEDIA_BUS_FMT_META_12 and the CSI-2 receiver writes the received data to memory +as-is. + +The packing of the data follows the MIPI CSI-2 specification and the padding of +the data is defined in the MIPI CCS specification. + +This format is also used in conjunction with 24 bits per :term:`Data Unit` +formats that pack two bytes of metadata into one Data Unit. Otherwise the +24 bits per pixel dataformat is :ref:`V4L2_META_FMT_GENERIC_CSI2_24 +`. + +This format is little endian. + +**Byte Order Of V4L2_META_FMT_GENERIC_CSI2_12.** +Each cell is one byte. "M" denotes a byte of metadata and "x" a byte of padding. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{.8cm}|p{.8cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - M\ :sub:`10` + - x + - M\ :sub:`20` + - M\ :sub:`30` + - x + * - start + 6: + - M\ :sub:`01` + - M\ :sub:`11` + - x + - M\ :sub:`21` + - M\ :sub:`31` + - x + +.. _v4l2-meta-fmt-generic-csi2-14: + +V4L2_META_FMT_GENERIC_CSI2_14 +----------------------------- + +V4L2_META_FMT_GENERIC_CSI2_14 contains 8-bit generic metadata packed in 14-bit +Data Units, with three padding bytes after every four bytes of metadata. This +format is typically used by CSI-2 receivers with a source that transmits +MEDIA_BUS_FMT_META_14 and the CSI-2 receiver writes the received data to memory +as-is. + +The packing of the data follows the MIPI CSI-2 specification and the padding of +the data is defined in the MIPI CCS specification. + +This format is little endian. + +**Byte Order Of V4L2_META_FMT_GENERIC_CSI2_14.** +Each cell is one byte. "M" denotes a byte of metadata and "x" a byte of padding. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{1.2cm}|p{.8cm}|p{.8cm}|p{.8cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - M\ :sub:`10` + - M\ :sub:`20` + - M\ :sub:`30` + - x + - x + - x + * - start + 7: + - M\ :sub:`01` + - M\ :sub:`11` + - M\ :sub:`21` + - M\ :sub:`31` + - x + - x + - x + +.. _v4l2-meta-fmt-generic-csi2-16: + +V4L2_META_FMT_GENERIC_CSI2_16 +----------------------------- + +V4L2_META_FMT_GENERIC_CSI2_16 contains 8-bit generic metadata packed in 16-bit +Data Units, with one padding byte after every byte of metadata. This format is +typically used by CSI-2 receivers with a source that transmits +MEDIA_BUS_FMT_META_16 and the CSI-2 receiver writes the received data to memory +as-is. + +The packing of the data follows the MIPI CSI-2 specification and the padding of +the data is defined in the MIPI CCS specification. + +Some devices support more efficient packing of metadata in conjunction with +16-bit image data. In that case the dataformat is +:ref:`V4L2_META_FMT_GENERIC_8 `. + +This format is little endian. + +**Byte Order Of V4L2_META_FMT_GENERIC_CSI2_16.** +Each cell is one byte. "M" denotes a byte of metadata and "x" a byte of padding. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{1.2cm}|p{.8cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - x + - M\ :sub:`10` + - x + - M\ :sub:`20` + - x + - M\ :sub:`30` + - x + * - start + 8: + - M\ :sub:`01` + - x + - M\ :sub:`11` + - x + - M\ :sub:`21` + - x + - M\ :sub:`31` + - x + +.. _v4l2-meta-fmt-generic-csi2-20: + +V4L2_META_FMT_GENERIC_CSI2_20 +----------------------------- + +V4L2_META_FMT_GENERIC_CSI2_20 contains 8-bit generic metadata packed in 20-bit +Data Units, with alternating one or two padding bytes after every byte of +metadata. This format is typically used by CSI-2 receivers with a source that +transmits MEDIA_BUS_FMT_META_20 and the CSI-2 receiver writes the received data +to memory as-is. + +The packing of the data follows the MIPI CSI-2 specification and the padding of +the data is defined in the MIPI CCS specification. + +Some devices support more efficient packing of metadata in conjunction with +16-bit image data. In that case the dataformat is +:ref:`V4L2_META_FMT_GENERIC_CSI2_10 `. + +This format is little endian. + +**Byte Order Of V4L2_META_FMT_GENERIC_CSI2_20.** +Each cell is one byte. "M" denotes a byte of metadata and "x" a byte of padding. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{.8cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 8 8 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - x + - M\ :sub:`10` + - x + - x + - M\ :sub:`20` + - x + - M\ :sub:`30` + - x + - x + * - start + 10: + - M\ :sub:`01` + - x + - M\ :sub:`11` + - x + - x + - M\ :sub:`21` + - x + - M\ :sub:`31` + - x + - x + +.. _v4l2-meta-fmt-generic-csi2-24: + +V4L2_META_FMT_GENERIC_CSI2_24 +----------------------------- + +V4L2_META_FMT_GENERIC_CSI2_24 contains 8-bit generic metadata packed in 24-bit +Data Units, with two padding bytes after every byte of metadata. This format is +typically used by CSI-2 receivers with a source that transmits +MEDIA_BUS_FMT_META_24 and the CSI-2 receiver writes the received data to memory +as-is. + +The packing of the data follows the MIPI CSI-2 specification and the padding of +the data is defined in the MIPI CCS specification. + +Some devices support more efficient packing of metadata in conjunction with +16-bit image data. In that case the dataformat is +:ref:`V4L2_META_FMT_GENERIC_CSI2_12 `. + +This format is little endian. + +**Byte Order Of V4L2_META_FMT_GENERIC_CSI2_24.** +Each cell is one byte. "M" denotes a byte of metadata and "x" a byte of padding. + +.. tabularcolumns:: |p{2.4cm}|p{1.2cm}|p{.8cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{.8cm}|p{1.2cm}|p{.8cm}|p{.8cm}| + +.. flat-table:: Sample 4x2 Metadata Frame + :header-rows: 0 + :stub-columns: 0 + :widths: 12 8 8 8 8 8 8 8 8 8 8 8 8 + + * - start + 0: + - M\ :sub:`00` + - x + - x + - M\ :sub:`10` + - x + - x + - M\ :sub:`20` + - x + - x + - M\ :sub:`30` + - x + - x + * - start + 12: + - M\ :sub:`01` + - x + - x + - M\ :sub:`11` + - x + - x + - M\ :sub:`21` + - x + - x + - M\ :sub:`31` + - x + - x diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 5aeff5519407..ae2dca7f2817 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1460,6 +1460,13 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y210: descr = "10-bit YUYV Packed"; break; case V4L2_PIX_FMT_Y212: descr = "12-bit YUYV Packed"; break; case V4L2_PIX_FMT_Y216: descr = "16-bit YUYV Packed"; break; + case V4L2_META_FMT_GENERIC_8: descr = "8-bit Generic Metadata"; break; + case V4L2_META_FMT_GENERIC_CSI2_10: descr = "8-bit Generic Meta, 10b CSI-2"; break; + case V4L2_META_FMT_GENERIC_CSI2_12: descr = "8-bit Generic Meta, 12b CSI-2"; break; + case V4L2_META_FMT_GENERIC_CSI2_14: descr = "8-bit Generic Meta, 14b CSI-2"; break; + case V4L2_META_FMT_GENERIC_CSI2_16: descr = "8-bit Generic Meta, 16b CSI-2"; break; + case V4L2_META_FMT_GENERIC_CSI2_20: descr = "8-bit Generic Meta, 20b CSI-2"; break; + case V4L2_META_FMT_GENERIC_CSI2_24: descr = "8-bit Generic Meta, 24b CSI-2"; break; default: /* Compressed formats */ diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index bf12860d570a..0f44b8486ea8 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -839,6 +839,14 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_PARAMS v4l2_fourcc('R', 'K', '1', 'P') /* Rockchip ISP1 3A Parameters */ #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ +#define V4L2_META_FMT_GENERIC_8 v4l2_fourcc('M', 'E', 'T', '8') /* Generic 8-bit metadata */ +#define V4L2_META_FMT_GENERIC_CSI2_10 v4l2_fourcc('M', 'C', '1', 'A') /* 10-bit CSI-2 packed 8-bit metadata */ +#define V4L2_META_FMT_GENERIC_CSI2_12 v4l2_fourcc('M', 'C', '1', 'C') /* 12-bit CSI-2 packed 8-bit metadata */ +#define V4L2_META_FMT_GENERIC_CSI2_14 v4l2_fourcc('M', 'C', '1', 'E') /* 14-bit CSI-2 packed 8-bit metadata */ +#define V4L2_META_FMT_GENERIC_CSI2_16 v4l2_fourcc('M', 'C', '1', 'G') /* 16-bit CSI-2 packed 8-bit metadata */ +#define V4L2_META_FMT_GENERIC_CSI2_20 v4l2_fourcc('M', 'C', '1', 'K') /* 20-bit CSI-2 packed 8-bit metadata */ +#define V4L2_META_FMT_GENERIC_CSI2_24 v4l2_fourcc('M', 'C', '1', 'O') /* 24-bit CSI-2 packed 8-bit metadata */ + /* priv field value to indicates that subsequent fields are valid. */ #define V4L2_PIX_FMT_PRIV_MAGIC 0xfeedcafe -- cgit v1.2.3 From 89345c2a6ff9c48c5f1ea336e66e46dfc38a467a Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 21 Feb 2023 19:37:29 +0200 Subject: media: v4l: Support line-based metadata capture Many camera sensors, among other devices, transmit embedded data and image data for each CSI-2 frame. This embedded data typically contains register configuration of the sensor that has been used to capture the image data of the same frame. The embedded data is received by the CSI-2 receiver and has the same properties as the image data, including that it is line based: it has width, height and bytesperline (stride). Add these fields to struct v4l2_meta_format and document them. Also add V4L2_FMT_FLAG_META_LINE_BASED to tell a given format is line-based i.e. these fields of struct v4l2_meta_format are valid for it. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/dev-meta.rst | 21 +++++++++++++++++++++ .../userspace-api/media/v4l/vidioc-enum-fmt.rst | 7 +++++++ .../userspace-api/media/videodev2.h.rst.exceptions | 1 + drivers/media/v4l2-core/v4l2-ioctl.c | 5 +++-- include/uapi/linux/videodev2.h | 10 ++++++++++ 5 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/dev-meta.rst b/Documentation/userspace-api/media/v4l/dev-meta.rst index 0e7e1ee1471a..5eee9ab60395 100644 --- a/Documentation/userspace-api/media/v4l/dev-meta.rst +++ b/Documentation/userspace-api/media/v4l/dev-meta.rst @@ -47,6 +47,12 @@ member of the ``fmt`` union as needed per the desired operation. Both drivers and applications must set the remainder of the :c:type:`v4l2_format` structure to 0. +Devices that capture metadata by line have the struct v4l2_fmtdesc +``V4L2_FMT_FLAG_META_LINE_BASED`` flag set for :c:func:`VIDIOC_ENUM_FMT`. Such +devices can typically also :ref:`capture image data `. This primarily +involves devices that receive the data from a different devices such as a camera +sensor. + .. c:type:: v4l2_meta_format .. tabularcolumns:: |p{1.4cm}|p{2.4cm}|p{13.5cm}| @@ -65,3 +71,18 @@ to 0. - ``buffersize`` - Maximum buffer size in bytes required for data. The value is set by the driver. + * - __u32 + - ``width`` + - Width of a line of metadata in Data Units. Valid when + :c:type`v4l2_fmtdesc` flag ``V4L2_FMT_FLAG_META_LINE_BASED`` is set, + otherwise zero. See :c:func:`VIDIOC_ENUM_FMT`. + * - __u32 + - ``height`` + - Number of rows of metadata. Valid when :c:type`v4l2_fmtdesc` flag + ``V4L2_FMT_FLAG_META_LINE_BASED`` is set, otherwise zero. See + :c:func:`VIDIOC_ENUM_FMT`. + * - __u32 + - ``bytesperline`` + - Offset in bytes between the beginning of two consecutive lines. Valid + when :c:type`v4l2_fmtdesc` flag ``V4L2_FMT_FLAG_META_LINE_BASED`` is + set, otherwise zero. See :c:func:`VIDIOC_ENUM_FMT`. diff --git a/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst b/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst index 000c154b0f98..3adb3d205531 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst @@ -227,6 +227,13 @@ the ``mbus_code`` field is handled differently: The application can ask to configure the quantization of the capture device when calling the :ref:`VIDIOC_S_FMT ` ioctl with :ref:`V4L2_PIX_FMT_FLAG_SET_CSC ` set. + * - ``V4L2_FMT_FLAG_META_LINE_BASED`` + - 0x0200 + - The metadata format is line-based. In this case the ``width``, + ``height`` and ``bytesperline`` fields of :c:type:`v4l2_meta_format` are + valid. The buffer consists of ``height`` lines, each having ``width`` + Data Units of data and the offset (in bytes) between the beginning of + each two consecutive lines is ``bytesperline``. Return Value ============ diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 3e58aac4ef0b..bdc628e8c1d6 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -215,6 +215,7 @@ replace define V4L2_FMT_FLAG_CSC_XFER_FUNC fmtdesc-flags replace define V4L2_FMT_FLAG_CSC_YCBCR_ENC fmtdesc-flags replace define V4L2_FMT_FLAG_CSC_HSV_ENC fmtdesc-flags replace define V4L2_FMT_FLAG_CSC_QUANTIZATION fmtdesc-flags +replace define V4L2_FMT_FLAG_META_LINE_BASED fmtdesc-flags # V4L2 timecode types replace define V4L2_TC_TYPE_24FPS timecode-type diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ae2dca7f2817..2cfc9106857a 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -343,8 +343,9 @@ static void v4l_print_format(const void *arg, bool write_only) case V4L2_BUF_TYPE_META_OUTPUT: meta = &p->fmt.meta; pixelformat = meta->dataformat; - pr_cont(", dataformat=%p4cc, buffersize=%u\n", - &pixelformat, meta->buffersize); + pr_cont(", dataformat=%p4cc, buffersize=%u, width=%u, height=%u, bytesperline=%u\n", + &pixelformat, meta->buffersize, meta->width, + meta->height, meta->bytesperline); break; } } diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 0f44b8486ea8..647ce3419bd8 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -877,6 +877,7 @@ struct v4l2_fmtdesc { #define V4L2_FMT_FLAG_CSC_YCBCR_ENC 0x0080 #define V4L2_FMT_FLAG_CSC_HSV_ENC V4L2_FMT_FLAG_CSC_YCBCR_ENC #define V4L2_FMT_FLAG_CSC_QUANTIZATION 0x0100 +#define V4L2_FMT_FLAG_META_LINE_BASED 0x0200 /* Frame Size and frame rate enumeration */ /* @@ -2424,10 +2425,19 @@ struct v4l2_sdr_format { * struct v4l2_meta_format - metadata format definition * @dataformat: little endian four character code (fourcc) * @buffersize: maximum size in bytes required for data + * @width: number of data units of data per line (valid for line + * based formats only, see format documentation) + * @height: number of lines of data per buffer (valid for line based + * formats only) + * @bytesperline: offset between the beginnings of two adjacent lines in + * bytes (valid for line based formats only) */ struct v4l2_meta_format { __u32 dataformat; __u32 buffersize; + __u32 width; + __u32 height; + __u32 bytesperline; } __attribute__ ((packed)); /** -- cgit v1.2.3 From 21828609f0a652d825f73dca621f783a2f225762 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 23 Apr 2024 10:39:47 +0300 Subject: media: v4l: Set line based metadata flag in V4L2 core Set (and unset) the V4L2_FMT_FLAG_META_LINE_BASED flag in struct v4l2_fmtdesc based on the format after returning the driver callback for enumerating formats. This way the drivers don't need to care about the flag. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- drivers/media/v4l2-core/v4l2-ioctl.c | 16 ++++++++++++++++ include/uapi/linux/videodev2.h | 4 ++++ 2 files changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 2cfc9106857a..5e928e2a2beb 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1538,6 +1538,22 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) } } + if (fmt->type == V4L2_BUF_TYPE_META_CAPTURE) { + switch (fmt->pixelformat) { + case V4L2_META_FMT_GENERIC_8: + case V4L2_META_FMT_GENERIC_CSI2_10: + case V4L2_META_FMT_GENERIC_CSI2_12: + case V4L2_META_FMT_GENERIC_CSI2_14: + case V4L2_META_FMT_GENERIC_CSI2_16: + case V4L2_META_FMT_GENERIC_CSI2_20: + case V4L2_META_FMT_GENERIC_CSI2_24: + fmt->flags |= V4L2_FMT_FLAG_META_LINE_BASED; + break; + default: + fmt->flags &= ~V4L2_FMT_FLAG_META_LINE_BASED; + } + } + if (descr) WARN_ON(strscpy(fmt->description, descr, sz) < 0); fmt->flags |= flags; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 647ce3419bd8..d944db7ae1ed 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -839,6 +839,10 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_PARAMS v4l2_fourcc('R', 'K', '1', 'P') /* Rockchip ISP1 3A Parameters */ #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ +/* + * Line-based metadata formats. Remember to update v4l_fill_fmtdesc() when + * adding new ones! + */ #define V4L2_META_FMT_GENERIC_8 v4l2_fourcc('M', 'E', 'T', '8') /* Generic 8-bit metadata */ #define V4L2_META_FMT_GENERIC_CSI2_10 v4l2_fourcc('M', 'C', '1', 'A') /* 10-bit CSI-2 packed 8-bit metadata */ #define V4L2_META_FMT_GENERIC_CSI2_12 v4l2_fourcc('M', 'C', '1', 'C') /* 12-bit CSI-2 packed 8-bit metadata */ -- cgit v1.2.3 From 83a22a07cd9d51b7ffd18a8904e1857061eda28f Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Aug 2023 14:56:28 +0300 Subject: media: v4l: subdev: Add len_routes field to struct v4l2_subdev_routing The len_routes field is used to tell the size of the routes array in struct v4l2_subdev_routing. This way the number of routes returned from S_ROUTING IOCTL may be larger than the number of routes provided, in case there are more routes returned by the driver. Note that this uAPI is still disabled in the code, so this change can safely be done. Anyone who manually patched the code to enable this uAPI must update their code. The patch also increases the number of reserved fields in struct v4l2_subdev_routing. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- .../media/v4l/vidioc-subdev-g-routing.rst | 46 +++++++++++++++------- drivers/media/v4l2-core/v4l2-ioctl.c | 4 +- drivers/media/v4l2-core/v4l2-subdev.c | 12 +++--- include/media/v4l2-subdev.h | 2 + include/uapi/linux/v4l2-subdev.h | 10 +++-- 5 files changed, 49 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-routing.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-routing.rst index 26b5004bfe6d..cbd9370006b6 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-routing.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-routing.rst @@ -43,23 +43,38 @@ The routing configuration determines the flows of data inside an entity. Drivers report their current routing tables using the ``VIDIOC_SUBDEV_G_ROUTING`` ioctl and application may enable or disable routes with the ``VIDIOC_SUBDEV_S_ROUTING`` ioctl, by adding or removing routes and -setting or clearing flags of the ``flags`` field of a -struct :c:type:`v4l2_subdev_route`. +setting or clearing flags of the ``flags`` field of a struct +:c:type:`v4l2_subdev_route`. -All stream configurations are reset when ``VIDIOC_SUBDEV_S_ROUTING`` is called. This -means that the userspace must reconfigure all streams after calling the ioctl -with e.g. ``VIDIOC_SUBDEV_S_FMT``. +All stream configurations are reset when ``VIDIOC_SUBDEV_S_ROUTING`` is called. +This means that the userspace must reconfigure all stream formats and selections +after calling the ioctl with e.g. ``VIDIOC_SUBDEV_S_FMT``. Only subdevices which have both sink and source pads can support routing. -When inspecting routes through ``VIDIOC_SUBDEV_G_ROUTING`` and the application -provided ``num_routes`` is not big enough to contain all the available routes -the subdevice exposes, drivers return the ENOSPC error code and adjust the -value of the ``num_routes`` field. Application should then reserve enough memory -for all the route entries and call ``VIDIOC_SUBDEV_G_ROUTING`` again. - -On a successful ``VIDIOC_SUBDEV_G_ROUTING`` call the driver updates the -``num_routes`` field to reflect the actual number of routes returned. +The ``len_routes`` field indicates the number of routes that can fit in the +``routes`` array allocated by userspace. It is set by applications for both +ioctls to indicate how many routes the kernel can return, and is never modified +by the kernel. + +The ``num_routes`` field indicates the number of routes in the routing +table. For ``VIDIOC_SUBDEV_S_ROUTING``, it is set by userspace to the number of +routes that the application stored in the ``routes`` array. For both ioctls, it +is returned by the kernel and indicates how many routes are stored in the +subdevice routing table. This may be smaller or larger than the value of +``num_routes`` set by the application for ``VIDIOC_SUBDEV_S_ROUTING``, as +drivers may adjust the requested routing table. + +The kernel can return a ``num_routes`` value larger than ``len_routes`` from +both ioctls. This indicates thare are more routes in the routing table than fits +the ``routes`` array. In this case, the ``routes`` array is filled by the kernel +with the first ``len_routes`` entries of the subdevice routing table. This is +not considered to be an error, and the ioctl call succeeds. If the applications +wants to retrieve the missing routes, it can issue a new +``VIDIOC_SUBDEV_G_ROUTING`` call with a large enough ``routes`` array. + +``VIDIOC_SUBDEV_S_ROUTING`` may return more routes than the user provided in +``num_routes`` field due to e.g. hardware properties. .. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}| @@ -74,6 +89,9 @@ On a successful ``VIDIOC_SUBDEV_G_ROUTING`` call the driver updates the - ``which`` - Routing table to be accessed, from enum :ref:`v4l2_subdev_format_whence `. + * - __u32 + - ``len_routes`` + - The length of the array (as in memory reserved for the array) * - struct :c:type:`v4l2_subdev_route` - ``routes[]`` - Array of struct :c:type:`v4l2_subdev_route` entries @@ -81,7 +99,7 @@ On a successful ``VIDIOC_SUBDEV_G_ROUTING`` call the driver updates the - ``num_routes`` - Number of entries of the routes array * - __u32 - - ``reserved``\ [5] + - ``reserved``\ [11] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 0260acef97d2..aab671fae45b 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -3201,13 +3201,13 @@ static int check_array_args(unsigned int cmd, void *parg, size_t *array_size, case VIDIOC_SUBDEV_S_ROUTING: { struct v4l2_subdev_routing *routing = parg; - if (routing->num_routes > 256) + if (routing->len_routes > 256) return -E2BIG; *user_ptr = u64_to_user_ptr(routing->routes); *kernel_ptr = (void **)&routing->routes; *array_size = sizeof(struct v4l2_subdev_route) - * routing->num_routes; + * routing->len_routes; ret = 1; break; } diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 779583447eac..b565f202df67 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -960,14 +960,10 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, krouting = &state->routing; - if (routing->num_routes < krouting->num_routes) { - routing->num_routes = krouting->num_routes; - return -ENOSPC; - } - memcpy((struct v4l2_subdev_route *)(uintptr_t)routing->routes, krouting->routes, - krouting->num_routes * sizeof(*krouting->routes)); + min(krouting->num_routes, routing->len_routes) * + sizeof(*krouting->routes)); routing->num_routes = krouting->num_routes; return 0; @@ -989,6 +985,9 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, if (routing->which != V4L2_SUBDEV_FORMAT_TRY && ro_subdev) return -EPERM; + if (routing->num_routes > routing->len_routes) + return -EINVAL; + memset(routing->reserved, 0, sizeof(routing->reserved)); for (i = 0; i < routing->num_routes; ++i) { @@ -1015,6 +1014,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, } krouting.num_routes = routing->num_routes; + krouting.len_routes = routing->len_routes; krouting.routes = routes; return v4l2_subdev_call(sd, pad, set_routing, state, diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index e22c50ce7e05..e30c463d90e5 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -714,12 +714,14 @@ struct v4l2_subdev_stream_configs { /** * struct v4l2_subdev_krouting - subdev routing table * + * @len_routes: length of routes array, in routes * @num_routes: number of routes * @routes: &struct v4l2_subdev_route * * This structure contains the routing table for a subdev. */ struct v4l2_subdev_krouting { + unsigned int len_routes; unsigned int num_routes; struct v4l2_subdev_route *routes; }; diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 81a24bd38003..2347e266cf75 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -228,15 +228,19 @@ struct v4l2_subdev_route { * struct v4l2_subdev_routing - Subdev routing information * * @which: configuration type (from enum v4l2_subdev_format_whence) - * @num_routes: the total number of routes in the routes array + * @len_routes: the length of the routes array, in routes; set by the user, not + * modified by the kernel * @routes: pointer to the routes array + * @num_routes: the total number of routes, possibly more than fits in the + * routes array * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_routing { __u32 which; - __u32 num_routes; + __u32 len_routes; __u64 routes; - __u32 reserved[6]; + __u32 num_routes; + __u32 reserved[11]; }; /* -- cgit v1.2.3 From 1810477630404ed798f97e4babee4d6dd07a6095 Mon Sep 17 00:00:00 2001 From: Jean-Michel Hautbois Date: Wed, 24 Apr 2024 18:35:37 +0300 Subject: media: v4l: Add V4L2-PIX-FMT-Y12P format This is a packed grey-scale image format with a depth of 12 bits per pixel. Two consecutive pixels are packed into 3 bytes. The first 2 bytes contain the 8 high order bits of the pixels, and the 3rd byte contains the 4 least significants bits of each pixel, in the same order. Add the entry in userspace API, and document it. Signed-off-by: Jean-Michel Hautbois Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst | 11 +++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst index cf8e4dfbfbd4..a650ceda7cdb 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst @@ -114,6 +114,17 @@ are often referred to as greyscale formats. - ... - ... + * .. _V4L2-PIX-FMT-Y12P: + + - ``V4L2_PIX_FMT_Y12P`` + - 'Y12P' + + - Y'\ :sub:`0`\ [11:4] + - Y'\ :sub:`1`\ [11:4] + - Y'\ :sub:`1`\ [3:0] Y'\ :sub:`0`\ [3:0] + - ... + - ... + * .. _V4L2-PIX-FMT-Y14: - ``V4L2_PIX_FMT_Y14`` diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index aab671fae45b..94fe2a1d13cd 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1321,6 +1321,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y10BPACK: descr = "10-bit Greyscale (Packed)"; break; case V4L2_PIX_FMT_Y10P: descr = "10-bit Greyscale (MIPI Packed)"; break; case V4L2_PIX_FMT_IPU3_Y10: descr = "10-bit greyscale (IPU3 Packed)"; break; + case V4L2_PIX_FMT_Y12P: descr = "12-bit Greyscale (MIPI Packed)"; break; case V4L2_PIX_FMT_Y8I: descr = "Interleaved 8-bit Greyscale"; break; case V4L2_PIX_FMT_Y12I: descr = "Interleaved 12-bit Greyscale"; break; case V4L2_PIX_FMT_Z16: descr = "16-bit Depth"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d944db7ae1ed..760fb8ed7f69 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -599,6 +599,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Y10BPACK v4l2_fourcc('Y', '1', '0', 'B') /* 10 Greyscale bit-packed */ #define V4L2_PIX_FMT_Y10P v4l2_fourcc('Y', '1', '0', 'P') /* 10 Greyscale, MIPI RAW10 packed */ #define V4L2_PIX_FMT_IPU3_Y10 v4l2_fourcc('i', 'p', '3', 'y') /* IPU3 packed 10-bit greyscale */ +#define V4L2_PIX_FMT_Y12P v4l2_fourcc('Y', '1', '2', 'P') /* 12 Greyscale, MIPI RAW12 packed */ /* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ -- cgit v1.2.3 From adb1d4655e53829658f42f13bd81657528a7a60d Mon Sep 17 00:00:00 2001 From: Jean-Michel Hautbois Date: Wed, 24 Apr 2024 18:35:38 +0300 Subject: media: v4l: Add V4L2-PIX-FMT-Y14P format This is a packed grey-scale image format with a depth of 14 bits per pixel. Every four consecutive samples are packed into seven bytes. Each of the first four bytes contain the eight high order bits of the pixels, and the three following bytes contains the six least significants bits of each pixel, in the same order. As the other formats only needed 5 bytes before, append two bytes in the documentation array. Signed-off-by: Jean-Michel Hautbois Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-yuv-luma.rst | 37 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst index a650ceda7cdb..b3c5779521d8 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst @@ -36,6 +36,8 @@ are often referred to as greyscale formats. - Byte 2 - Byte 3 - Byte 4 + - Byte 5 + - Byte 6 * .. _V4L2-PIX-FMT-GREY: @@ -47,6 +49,8 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... * .. _V4L2-PIX-FMT-IPU3-Y10: @@ -58,6 +62,8 @@ are often referred to as greyscale formats. - Y'\ :sub:`2`\ [3:0] Y'\ :sub:`1`\ [9:6] - Y'\ :sub:`3`\ [1:0] Y'\ :sub:`2`\ [9:4] - Y'\ :sub:`3`\ [9:2] + - ... + - ... * .. _V4L2-PIX-FMT-Y10: @@ -69,6 +75,8 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... * .. _V4L2-PIX-FMT-Y10BPACK: @@ -80,6 +88,8 @@ are often referred to as greyscale formats. - Y'\ :sub:`1`\ [3:0] Y'\ :sub:`2`\ [9:6] - Y'\ :sub:`2`\ [5:0] Y'\ :sub:`3`\ [9:8] - Y'\ :sub:`3`\ [7:0] + - ... + - ... * .. _V4L2-PIX-FMT-Y10P: @@ -91,6 +101,8 @@ are often referred to as greyscale formats. - Y'\ :sub:`2`\ [9:2] - Y'\ :sub:`3`\ [9:2] - Y'\ :sub:`3`\ [1:0] Y'\ :sub:`2`\ [1:0] Y'\ :sub:`1`\ [1:0] Y'\ :sub:`0`\ [1:0] + - ... + - ... * .. _V4L2-PIX-FMT-Y12: @@ -102,6 +114,8 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... * .. _V4L2-PIX-FMT-Y012: @@ -113,6 +127,8 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... * .. _V4L2-PIX-FMT-Y12P: @@ -124,6 +140,8 @@ are often referred to as greyscale formats. - Y'\ :sub:`1`\ [3:0] Y'\ :sub:`0`\ [3:0] - ... - ... + - ... + - ... * .. _V4L2-PIX-FMT-Y14: @@ -135,6 +153,21 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... + + * .. _V4L2-PIX-FMT-Y14P: + + - ``V4L2_PIX_FMT_Y14P`` + - 'Y14P' + + - Y'\ :sub:`0`\ [13:6] + - Y'\ :sub:`1`\ [13:6] + - Y'\ :sub:`2`\ [13:6] + - Y'\ :sub:`3`\ [13:6] + - Y'\ :sub:`1`\ [1:0] Y'\ :sub:`0`\ [5:0] + - Y'\ :sub:`2`\ [3:0] Y'\ :sub:`1`\ [5:2] + - Y'\ :sub:`3`\ [5:0] Y'\ :sub:`2`\ [5:4] * .. _V4L2-PIX-FMT-Y16: @@ -146,6 +179,8 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... * .. _V4L2-PIX-FMT-Y16-BE: @@ -157,6 +192,8 @@ are often referred to as greyscale formats. - ... - ... - ... + - ... + - ... .. raw:: latex diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 94fe2a1d13cd..4c76d17b4629 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1322,6 +1322,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y10P: descr = "10-bit Greyscale (MIPI Packed)"; break; case V4L2_PIX_FMT_IPU3_Y10: descr = "10-bit greyscale (IPU3 Packed)"; break; case V4L2_PIX_FMT_Y12P: descr = "12-bit Greyscale (MIPI Packed)"; break; + case V4L2_PIX_FMT_Y14P: descr = "14-bit Greyscale (MIPI Packed)"; break; case V4L2_PIX_FMT_Y8I: descr = "Interleaved 8-bit Greyscale"; break; case V4L2_PIX_FMT_Y12I: descr = "Interleaved 12-bit Greyscale"; break; case V4L2_PIX_FMT_Z16: descr = "16-bit Depth"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 760fb8ed7f69..2f9762842313 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -600,6 +600,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Y10P v4l2_fourcc('Y', '1', '0', 'P') /* 10 Greyscale, MIPI RAW10 packed */ #define V4L2_PIX_FMT_IPU3_Y10 v4l2_fourcc('i', 'p', '3', 'y') /* IPU3 packed 10-bit greyscale */ #define V4L2_PIX_FMT_Y12P v4l2_fourcc('Y', '1', '2', 'P') /* 12 Greyscale, MIPI RAW12 packed */ +#define V4L2_PIX_FMT_Y14P v4l2_fourcc('Y', '1', '4', 'P') /* 14 Greyscale, MIPI RAW14 packed */ /* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ -- cgit v1.2.3 From d69c8429ea80af02e89e5b3eecb78e417ad049c8 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 26 Apr 2024 18:33:19 +0300 Subject: media: uapi: v4l: Don't expose generic metadata formats to userspace The generic metadata pixel formats (V4L2_META_FMT_GENERIC_*) are meant to be used in conjunction with device-specific media bus codes. Those codes are work in progress and not available in the upstream kernel yet. To make sure the generic metadata pixel formats won't be used by userspace until we have the full infrastructure in place, keep their definition private to the kernel for now. Signed-off-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 2f9762842313..fe6b67e83751 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -841,6 +841,7 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_PARAMS v4l2_fourcc('R', 'K', '1', 'P') /* Rockchip ISP1 3A Parameters */ #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ +#ifdef __KERNEL__ /* * Line-based metadata formats. Remember to update v4l_fill_fmtdesc() when * adding new ones! @@ -852,6 +853,7 @@ struct v4l2_pix_format { #define V4L2_META_FMT_GENERIC_CSI2_16 v4l2_fourcc('M', 'C', '1', 'G') /* 16-bit CSI-2 packed 8-bit metadata */ #define V4L2_META_FMT_GENERIC_CSI2_20 v4l2_fourcc('M', 'C', '1', 'K') /* 20-bit CSI-2 packed 8-bit metadata */ #define V4L2_META_FMT_GENERIC_CSI2_24 v4l2_fourcc('M', 'C', '1', 'O') /* 24-bit CSI-2 packed 8-bit metadata */ +#endif /* priv field value to indicates that subsequent fields are valid. */ #define V4L2_PIX_FMT_PRIV_MAGIC 0xfeedcafe -- cgit v1.2.3 From 34cfe87221363d98160f74788dd060b1c43bae0d Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Fri, 26 Apr 2024 11:39:22 +0800 Subject: virtio_net: introduce device stats feature and structures The virtio-net device stats spec: https://github.com/oasis-tcs/virtio-spec/commit/42f389989823039724f95bbbd243291ab0064f82 We introduce the relative feature and structures. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Signed-off-by: Paolo Abeni --- include/uapi/linux/virtio_net.h | 143 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 143 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index cc65ef0f3c3e..ac9174717ef1 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -56,6 +56,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ +#define VIRTIO_NET_F_DEVICE_STATS 50 /* Device can provide device-level statistics. */ #define VIRTIO_NET_F_VQ_NOTF_COAL 52 /* Device supports virtqueue notification coalescing */ #define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ #define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */ @@ -406,4 +407,146 @@ struct virtio_net_ctrl_coal_vq { struct virtio_net_ctrl_coal coal; }; +/* + * Device Statistics + */ +#define VIRTIO_NET_CTRL_STATS 8 +#define VIRTIO_NET_CTRL_STATS_QUERY 0 +#define VIRTIO_NET_CTRL_STATS_GET 1 + +struct virtio_net_stats_capabilities { + +#define VIRTIO_NET_STATS_TYPE_CVQ (1ULL << 32) + +#define VIRTIO_NET_STATS_TYPE_RX_BASIC (1ULL << 0) +#define VIRTIO_NET_STATS_TYPE_RX_CSUM (1ULL << 1) +#define VIRTIO_NET_STATS_TYPE_RX_GSO (1ULL << 2) +#define VIRTIO_NET_STATS_TYPE_RX_SPEED (1ULL << 3) + +#define VIRTIO_NET_STATS_TYPE_TX_BASIC (1ULL << 16) +#define VIRTIO_NET_STATS_TYPE_TX_CSUM (1ULL << 17) +#define VIRTIO_NET_STATS_TYPE_TX_GSO (1ULL << 18) +#define VIRTIO_NET_STATS_TYPE_TX_SPEED (1ULL << 19) + + __le64 supported_stats_types[1]; +}; + +struct virtio_net_ctrl_queue_stats { + struct { + __le16 vq_index; + __le16 reserved[3]; + __le64 types_bitmap[1]; + } stats[1]; +}; + +struct virtio_net_stats_reply_hdr { +#define VIRTIO_NET_STATS_TYPE_REPLY_CVQ 32 + +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC 0 +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM 1 +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_GSO 2 +#define VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED 3 + +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC 16 +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_CSUM 17 +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO 18 +#define VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED 19 + __u8 type; + __u8 reserved; + __le16 vq_index; + __le16 reserved1; + __le16 size; +}; + +struct virtio_net_stats_cvq { + struct virtio_net_stats_reply_hdr hdr; + + __le64 command_num; + __le64 ok_num; +}; + +struct virtio_net_stats_rx_basic { + struct virtio_net_stats_reply_hdr hdr; + + __le64 rx_notifications; + + __le64 rx_packets; + __le64 rx_bytes; + + __le64 rx_interrupts; + + __le64 rx_drops; + __le64 rx_drop_overruns; +}; + +struct virtio_net_stats_tx_basic { + struct virtio_net_stats_reply_hdr hdr; + + __le64 tx_notifications; + + __le64 tx_packets; + __le64 tx_bytes; + + __le64 tx_interrupts; + + __le64 tx_drops; + __le64 tx_drop_malformed; +}; + +struct virtio_net_stats_rx_csum { + struct virtio_net_stats_reply_hdr hdr; + + __le64 rx_csum_valid; + __le64 rx_needs_csum; + __le64 rx_csum_none; + __le64 rx_csum_bad; +}; + +struct virtio_net_stats_tx_csum { + struct virtio_net_stats_reply_hdr hdr; + + __le64 tx_csum_none; + __le64 tx_needs_csum; +}; + +struct virtio_net_stats_rx_gso { + struct virtio_net_stats_reply_hdr hdr; + + __le64 rx_gso_packets; + __le64 rx_gso_bytes; + __le64 rx_gso_packets_coalesced; + __le64 rx_gso_bytes_coalesced; +}; + +struct virtio_net_stats_tx_gso { + struct virtio_net_stats_reply_hdr hdr; + + __le64 tx_gso_packets; + __le64 tx_gso_bytes; + __le64 tx_gso_segments; + __le64 tx_gso_segments_bytes; + __le64 tx_gso_packets_noseg; + __le64 tx_gso_bytes_noseg; +}; + +struct virtio_net_stats_rx_speed { + struct virtio_net_stats_reply_hdr hdr; + + /* rx_{packets,bytes}_allowance_exceeded are too long. So rename to + * short name. + */ + __le64 rx_ratelimit_packets; + __le64 rx_ratelimit_bytes; +}; + +struct virtio_net_stats_tx_speed { + struct virtio_net_stats_reply_hdr hdr; + + /* tx_{packets,bytes}_allowance_exceeded are too long. So rename to + * short name. + */ + __le64 tx_ratelimit_packets; + __le64 tx_ratelimit_bytes; +}; + #endif /* _UAPI_LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From 0cfe71f45f420e412fda2395807a56c453a6e0b6 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Fri, 26 Apr 2024 11:39:27 +0800 Subject: netdev: add queue stats These stats are commonly. Support reporting those via netdev-genl queue stats. name: rx-hw-drops name: rx-hw-drop-overruns name: rx-csum-unnecessary name: rx-csum-none name: rx-csum-bad name: rx-hw-gro-packets name: rx-hw-gro-bytes name: rx-hw-gro-wire-packets name: rx-hw-gro-wire-bytes name: rx-hw-drop-ratelimits name: tx-hw-drops name: tx-hw-drop-errors name: tx-csum-none name: tx-needs-csum name: tx-hw-gso-packets name: tx-hw-gso-bytes name: tx-hw-gso-wire-packets name: tx-hw-gso-wire-bytes name: tx-hw-drop-ratelimits Signed-off-by: Xuan Zhuo Reviewed-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 104 ++++++++++++++++++++++++++++++++ include/net/netdev_queues.h | 27 +++++++++ include/uapi/linux/netdev.h | 19 ++++++ net/core/netdev-genl.c | 23 ++++++- tools/include/uapi/linux/netdev.h | 19 ++++++ 5 files changed, 190 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 679c4130707c..2be4b3714d17 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -335,6 +335,110 @@ attribute-sets: Allocation failure may, or may not result in a packet drop, depending on driver implementation and whether system recovers quickly. type: uint + - + name: rx-hw-drops + doc: | + Number of all packets which entered the device, but never left it, + including but not limited to: packets dropped due to lack of buffer + space, processing errors, explicit or implicit policies and packet + filters. + type: uint + - + name: rx-hw-drop-overruns + doc: | + Number of packets dropped due to transient lack of resources, such as + buffer space, host descriptors etc. + type: uint + - + name: rx-csum-unnecessary + doc: Number of packets that were marked as CHECKSUM_UNNECESSARY. + type: uint + - + name: rx-csum-none + doc: Number of packets that were not checksummed by device. + type: uint + - + name: rx-csum-bad + doc: | + Number of packets with bad checksum. The packets are not discarded, + but still delivered to the stack. + type: uint + - + name: rx-hw-gro-packets + doc: | + Number of packets that were coalesced from smaller packets by the device. + Counts only packets coalesced with the HW-GRO netdevice feature, + LRO-coalesced packets are not counted. + type: uint + - + name: rx-hw-gro-bytes + doc: See `rx-hw-gro-packets`. + type: uint + - + name: rx-hw-gro-wire-packets + doc: | + Number of packets that were coalesced to bigger packetss with the HW-GRO + netdevice feature. LRO-coalesced packets are not counted. + type: uint + - + name: rx-hw-gro-wire-bytes + doc: See `rx-hw-gro-wire-packets`. + type: uint + - + name: rx-hw-drop-ratelimits + doc: | + Number of the packets dropped by the device due to the received + packets bitrate exceeding the device rate limit. + type: uint + - + name: tx-hw-drops + doc: | + Number of packets that arrived at the device but never left it, + encompassing packets dropped for reasons such as processing errors, as + well as those affected by explicitly defined policies and packet + filtering criteria. + type: uint + - + name: tx-hw-drop-errors + doc: Number of packets dropped because they were invalid or malformed. + type: uint + - + name: tx-csum-none + doc: | + Number of packets that did not require the device to calculate the + checksum. + type: uint + - + name: tx-needs-csum + doc: | + Number of packets that required the device to calculate the checksum. + type: uint + - + name: tx-hw-gso-packets + doc: | + Number of packets that necessitated segmentation into smaller packets + by the device. + type: uint + - + name: tx-hw-gso-bytes + doc: See `tx-hw-gso-packets`. + type: uint + - + name: tx-hw-gso-wire-packets + doc: | + Number of wire-sized packets generated by processing + `tx-hw-gso-packets` + type: uint + - + name: tx-hw-gso-wire-bytes + doc: See `tx-hw-gso-wire-packets`. + type: uint + - + name: tx-hw-drop-ratelimits + doc: | + Number of the packets dropped by the device due to the transmit + packets bitrate exceeding the device rate limit. + type: uint operations: list: diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 1ec408585373..c7ac4539eafc 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -9,11 +9,38 @@ struct netdev_queue_stats_rx { u64 bytes; u64 packets; u64 alloc_fail; + + u64 hw_drops; + u64 hw_drop_overruns; + + u64 csum_unnecessary; + u64 csum_none; + u64 csum_bad; + + u64 hw_gro_packets; + u64 hw_gro_bytes; + u64 hw_gro_wire_packets; + u64 hw_gro_wire_bytes; + + u64 hw_drop_ratelimits; }; struct netdev_queue_stats_tx { u64 bytes; u64 packets; + + u64 hw_drops; + u64 hw_drop_errors; + + u64 csum_none; + u64 needs_csum; + + u64 hw_gso_packets; + u64 hw_gso_bytes; + u64 hw_gso_wire_packets; + u64 hw_gso_wire_bytes; + + u64 hw_drop_ratelimits; }; /** diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index bb65ee840cda..cf24f1d9adf8 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -146,6 +146,25 @@ enum { NETDEV_A_QSTATS_TX_PACKETS, NETDEV_A_QSTATS_TX_BYTES, NETDEV_A_QSTATS_RX_ALLOC_FAIL, + NETDEV_A_QSTATS_RX_HW_DROPS, + NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, + NETDEV_A_QSTATS_RX_CSUM_NONE, + NETDEV_A_QSTATS_RX_CSUM_BAD, + NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_BYTES, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, + NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_HW_DROPS, + NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, + NETDEV_A_QSTATS_TX_CSUM_NONE, + NETDEV_A_QSTATS_TX_NEEDS_CSUM, + NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_BYTES, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, + NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index dd6510f2c652..4b5054087309 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -489,7 +489,17 @@ netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || - netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail)) + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, rx->hw_gro_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_BYTES, rx->hw_gro_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, rx->hw_gro_wire_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, rx->hw_gro_wire_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, rx->hw_drop_ratelimits)) return -EMSGSIZE; return 0; } @@ -498,7 +508,16 @@ static int netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || - netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROPS, tx->hw_drops) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, tx->hw_drop_errors) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_CSUM_NONE, tx->csum_none) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_NEEDS_CSUM, tx->needs_csum) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, tx->hw_gso_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits)) return -EMSGSIZE; return 0; } diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index bb65ee840cda..cf24f1d9adf8 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -146,6 +146,25 @@ enum { NETDEV_A_QSTATS_TX_PACKETS, NETDEV_A_QSTATS_TX_BYTES, NETDEV_A_QSTATS_RX_ALLOC_FAIL, + NETDEV_A_QSTATS_RX_HW_DROPS, + NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, + NETDEV_A_QSTATS_RX_CSUM_NONE, + NETDEV_A_QSTATS_RX_CSUM_BAD, + NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_BYTES, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, + NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_HW_DROPS, + NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, + NETDEV_A_QSTATS_TX_CSUM_NONE, + NETDEV_A_QSTATS_TX_NEEDS_CSUM, + NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_BYTES, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, + NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) -- cgit v1.2.3 From 155ce502e9adf9001d6fa35ca85843b7f0e538c7 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Fri, 5 Apr 2024 15:46:50 -0400 Subject: drm/amdgpu: Support contiguous VRAM allocation RDMA device with limited scatter-gather ability requires contiguous VRAM buffer allocation for RDMA peer direct support. Add a new KFD alloc memory flag and store as bo alloc flag AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS. When pin this bo to export for RDMA peerdirect access, this will set TTM_PL_FLAG_CONTIFUOUS flag, and ask VRAM buddy allocator to get contiguous VRAM. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++++ include/uapi/linux/kfd_ioctl.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index e4d4e55c08ad..5c06279c6bef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1712,6 +1712,10 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ? AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0; + + /* For contiguous VRAM allocation */ + if (flags & KFD_IOC_ALLOC_MEM_FLAGS_CONTIGUOUS) + alloc_flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; } xcp_id = fpriv->xcp_id == AMDGPU_XCP_NO_PARTITION ? 0 : fpriv->xcp_id; diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2040a470ddb4..d09c4a18e571 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -407,6 +407,7 @@ struct kfd_ioctl_acquire_vm_args { #define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT (1 << 26) #define KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED (1 << 25) #define KFD_IOC_ALLOC_MEM_FLAGS_EXT_COHERENT (1 << 24) +#define KFD_IOC_ALLOC_MEM_FLAGS_CONTIGUOUS (1 << 23) /* Allocate memory for later SVM (shared virtual memory) mapping. * -- cgit v1.2.3 From 52666d8cc7f9c7810d25d5ef41f1a0b62153f368 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 8 Apr 2024 09:26:56 -0400 Subject: drm/amdkfd: Bump kfd version for contiguous VRAM allocation Bump the kfd ioctl minor version to delcare the contiguous VRAM allocation flag support. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index d09c4a18e571..f8e9d3c1d117 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -41,9 +41,10 @@ * - 1.13 - Add debugger API * - 1.14 - Update kfd_event_data * - 1.15 - Enable managing mappings in compute VMs with GEM_VA ioctl + * - 1.16 - Add contiguous VRAM allocation flag */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 15 +#define KFD_IOCTL_MINOR_VERSION 16 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From 940325add1c54e3018277d6d783ec419262729e8 Mon Sep 17 00:00:00 2001 From: Srinivasulu Thanneeru Date: Wed, 13 Mar 2024 12:42:17 +0530 Subject: cxl/mbox: Add Get Log Capabilities and Get Supported Logs Sub-List commands Adding UAPI support for 1. CXL r3.1 8.2.9.5.3 Get Log Capabilities. 2. CXL r3.1 8.2.9.5.6 Get Supported Logs Sub-List. Signed-off-by: Srinivasulu Thanneeru Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240313071218.729-2-sthanneeru.opensrc@micron.com Signed-off-by: Dave Jiang --- drivers/cxl/core/mbox.c | 2 ++ drivers/cxl/cxlmem.h | 2 ++ include/uapi/linux/cxl_mem.h | 2 ++ 3 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 65185c9fa001..dbfee67b6319 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -56,6 +56,8 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_LSA, 0x8, CXL_VARIABLE_PAYLOAD, 0), CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), CXL_CMD(GET_LOG, 0x18, CXL_VARIABLE_PAYLOAD, CXL_CMD_FLAG_FORCE_ENABLE), + CXL_CMD(GET_LOG_CAPS, 0x10, 0x4, 0), + CXL_CMD(GET_SUP_LOG_SUBLIST, 0x2, CXL_VARIABLE_PAYLOAD, 0), CXL_CMD(SET_PARTITION_INFO, 0x0a, 0, 0), CXL_CMD(SET_LSA, CXL_VARIABLE_PAYLOAD, 0, 0), CXL_CMD(GET_ALERT_CONFIG, 0, 0x10, 0), diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 36cee9c30ceb..39e06bf45a43 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -527,6 +527,8 @@ enum cxl_opcode { CXL_MBOX_OP_SET_TIMESTAMP = 0x0301, CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, CXL_MBOX_OP_GET_LOG = 0x0401, + CXL_MBOX_OP_GET_LOG_CAPS = 0x0402, + CXL_MBOX_OP_GET_SUP_LOG_SUBLIST = 0x0405, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 42066f4eb890..49c25056c222 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -47,6 +47,8 @@ ___DEPRECATED(SCAN_MEDIA, "Scan Media"), \ ___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"), \ ___C(GET_TIMESTAMP, "Get Timestamp"), \ + ___C(GET_LOG_CAPS, "Get Log Capabilities"), \ + ___C(GET_SUP_LOG_SUBLIST, "Get Supported Logs Sub-List"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit v1.2.3 From 206f9fa9d55592c8cea0ccf84a5242b7c7cf3748 Mon Sep 17 00:00:00 2001 From: Srinivasulu Thanneeru Date: Wed, 13 Mar 2024 12:42:18 +0530 Subject: cxl/mbox: Add Clear Log mailbox command Adding UAPI support for CXL r3.1 8.2.9.5.4 Clear Log command. This proposed patch will be useful for clearing and populating the Vendor debug log in certain scenarios, allowing for the aggregation of results over time. Signed-off-by: Srinivasulu Thanneeru Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240313071218.729-3-sthanneeru.opensrc@micron.com Signed-off-by: Dave Jiang --- drivers/cxl/core/mbox.c | 10 ++++++++++ drivers/cxl/cxlmem.h | 1 + include/uapi/linux/cxl_mem.h | 1 + 3 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index dbfee67b6319..0c6216d1c586 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -57,6 +57,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), CXL_CMD(GET_LOG, 0x18, CXL_VARIABLE_PAYLOAD, CXL_CMD_FLAG_FORCE_ENABLE), CXL_CMD(GET_LOG_CAPS, 0x10, 0x4, 0), + CXL_CMD(CLEAR_LOG, 0x10, 0, 0), CXL_CMD(GET_SUP_LOG_SUBLIST, 0x2, CXL_VARIABLE_PAYLOAD, 0), CXL_CMD(SET_PARTITION_INFO, 0x0a, 0, 0), CXL_CMD(SET_LSA, CXL_VARIABLE_PAYLOAD, 0, 0), @@ -333,6 +334,15 @@ static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in) return false; break; } + case CXL_MBOX_OP_CLEAR_LOG: { + const uuid_t *uuid = (uuid_t *)payload_in; + + /* + * Restrict the ‘Clear log’ action to only apply to + * Vendor debug logs. + */ + return uuid_equal(uuid, &DEFINE_CXL_VENDOR_DEBUG_UUID); + } default: break; } diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 39e06bf45a43..19aba81cdf13 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -528,6 +528,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, CXL_MBOX_OP_GET_LOG = 0x0401, CXL_MBOX_OP_GET_LOG_CAPS = 0x0402, + CXL_MBOX_OP_CLEAR_LOG = 0x0403, CXL_MBOX_OP_GET_SUP_LOG_SUBLIST = 0x0405, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 49c25056c222..c6c0fe27495d 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -48,6 +48,7 @@ ___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"), \ ___C(GET_TIMESTAMP, "Get Timestamp"), \ ___C(GET_LOG_CAPS, "Get Log Capabilities"), \ + ___C(CLEAR_LOG, "Clear Log"), \ ___C(GET_SUP_LOG_SUBLIST, "Get Supported Logs Sub-List"), \ ___C(MAX, "invalid / last command") -- cgit v1.2.3 From 535a3692ba7245792e6f23654507865d4293c850 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Apr 2024 13:28:24 +0200 Subject: bpf: Add support for kprobe session attach Adding support to attach bpf program for entry and return probe of the same function. This is common use case which at the moment requires to create two kprobe multi links. Adding new BPF_TRACE_KPROBE_SESSION attach type that instructs kernel to attach single link program to both entry and exit probe. It's possible to control execution of the bpf program on return probe simply by returning zero or non zero from the entry bpf program execution to execute or not the bpf program on return probe respectively. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240430112830.1184228-2-jolsa@kernel.org --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 7 ++++++- kernel/trace/bpf_trace.c | 28 ++++++++++++++++++++-------- tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 28 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d94a72593ead..90706a47f6ff 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f655adf42e39..13ad74ecf2cd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4016,11 +4016,15 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; + if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && + attach_type != BPF_TRACE_KPROBE_SESSION) + return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && + attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; return 0; @@ -5281,7 +5285,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); - else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI) + else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || + attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI) ret = bpf_uprobe_multi_link_attach(attr, prog); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0ba722b57af3..06a9671834b6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1631,6 +1631,17 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static bool is_kprobe_multi(const struct bpf_prog *prog) +{ + return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI || + prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; +} + +static inline bool is_kprobe_session(const struct bpf_prog *prog) +{ + return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; +} + static const struct bpf_func_proto * kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1646,13 +1657,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_override_return_proto; #endif case BPF_FUNC_get_func_ip: - if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + if (is_kprobe_multi(prog)) return &bpf_get_func_ip_proto_kprobe_multi; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) return &bpf_get_func_ip_proto_uprobe_multi; return &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: - if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + if (is_kprobe_multi(prog)) return &bpf_get_attach_cookie_proto_kmulti; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) return &bpf_get_attach_cookie_proto_umulti; @@ -2834,10 +2845,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, void *data) { struct bpf_kprobe_multi_link *link; + int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); - return 0; + err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); + return is_kprobe_session(link->link.prog) ? err : 0; } static void @@ -2981,7 +2993,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (sizeof(u64) != sizeof(void *)) return -EOPNOTSUPP; - if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI) + if (!is_kprobe_multi(prog)) return -EINVAL; flags = attr->link_create.kprobe_multi.flags; @@ -3062,10 +3074,10 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (err) goto error; - if (flags & BPF_F_KPROBE_MULTI_RETURN) - link->fp.exit_handler = kprobe_multi_link_exit_handler; - else + if (!(flags & BPF_F_KPROBE_MULTI_RETURN)) link->fp.entry_handler = kprobe_multi_link_handler; + if ((flags & BPF_F_KPROBE_MULTI_RETURN) || is_kprobe_session(prog)) + link->fp.exit_handler = kprobe_multi_link_exit_handler; link->addrs = addrs; link->cookies = cookies; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d94a72593ead..90706a47f6ff 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From a4a87fa4e96c7746e009de06a567688fd9af6013 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Tue, 30 Apr 2024 09:08:52 +0200 Subject: xfrm: Add Direction to the SA in or out This patch introduces the 'dir' attribute, 'in' or 'out', to the xfrm_state, SA, enhancing usability by delineating the scope of values based on direction. An input SA will restrict values pertinent to input, effectively segregating them from output-related values. And an output SA will restrict attributes for output. This change aims to streamline the configuration process and improve the overall consistency of SA attributes during configuration. This feature sets the groundwork for future patches, including the upcoming IP-TFS patch. Signed-off-by: Antony Antony Reviewed-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 + include/uapi/linux/xfrm.h | 6 ++ net/xfrm/xfrm_compat.c | 7 ++- net/xfrm/xfrm_device.c | 6 ++ net/xfrm/xfrm_replay.c | 3 +- net/xfrm/xfrm_state.c | 8 +++ net/xfrm/xfrm_user.c | 138 ++++++++++++++++++++++++++++++++++++++++++++-- 7 files changed, 160 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 57c743b7e4fe..7c9be06f8302 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -291,6 +291,7 @@ struct xfrm_state { /* Private data of this transformer, format is opaque, * interpreted by xfrm_type methods. */ void *data; + u8 dir; }; static inline struct net *xs_net(struct xfrm_state *x) diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 6a77328be114..18ceaba8486e 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -141,6 +141,11 @@ enum { XFRM_POLICY_MAX = 3 }; +enum xfrm_sa_dir { + XFRM_SA_DIR_IN = 1, + XFRM_SA_DIR_OUT = 2 +}; + enum { XFRM_SHARE_ANY, /* No limitations */ XFRM_SHARE_SESSION, /* For this session only */ @@ -315,6 +320,7 @@ enum xfrm_attr_type_t { XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ + XFRMA_SA_DIR, /* __u8 */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 655fe4ff8621..703d4172c7d7 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -98,6 +98,7 @@ static const int compat_msg_min[XFRM_NR_MSGTYPES] = { }; static const struct nla_policy compat_policy[XFRMA_MAX+1] = { + [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, @@ -129,6 +130,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, + [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -277,9 +279,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: + case XFRMA_SA_DIR: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -434,7 +437,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6346690d5c69..2455a76a1cff 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -253,6 +253,12 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, return -EINVAL; } + if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || + (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { + NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); + return -EINVAL; + } + is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support UDP encapsulation and TFC padding. */ diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index ce56d659c55a..bc56c6305725 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -778,7 +778,8 @@ int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack) } if (x->props.flags & XFRM_STATE_ESN) { - if (replay_esn->replay_window == 0) { + if (replay_esn->replay_window == 0 && + (!x->dir || x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "ESN replay window must be > 0"); return -EINVAL; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0c306473a79d..649bb739df0d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1292,6 +1292,7 @@ found: if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; + x->dir = XFRM_SA_DIR_OUT; list_add(&x->km.all, &net->xfrm.state_all); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, @@ -1744,6 +1745,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; + x->dir = orig->dir; return x; @@ -1864,8 +1866,14 @@ int xfrm_state_update(struct xfrm_state *x) } if (x1->km.state == XFRM_STATE_ACQ) { + if (x->dir && x1->dir != x->dir) + goto out; + __xfrm_state_insert(x); x = NULL; + } else { + if (x1->dir != x->dir) + goto out; } err = 0; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 810b520493f3..f5eb3af4fb81 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -130,7 +130,7 @@ static inline int verify_sec_ctx_len(struct nlattr **attrs, struct netlink_ext_a } static inline int verify_replay(struct xfrm_usersa_info *p, - struct nlattr **attrs, + struct nlattr **attrs, u8 sa_dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; @@ -168,6 +168,30 @@ static inline int verify_replay(struct xfrm_usersa_info *p, return -EINVAL; } + if (sa_dir == XFRM_SA_DIR_OUT) { + if (rs->replay_window) { + NL_SET_ERR_MSG(extack, "Replay window should be 0 for output SA"); + return -EINVAL; + } + if (rs->seq || rs->seq_hi) { + NL_SET_ERR_MSG(extack, + "Replay seq and seq_hi should be 0 for output SA"); + return -EINVAL; + } + if (rs->bmp_len) { + NL_SET_ERR_MSG(extack, "Replay bmp_len should 0 for output SA"); + return -EINVAL; + } + } + + if (sa_dir == XFRM_SA_DIR_IN) { + if (rs->oseq || rs->oseq_hi) { + NL_SET_ERR_MSG(extack, + "Replay oseq and oseq_hi should be 0 for input SA"); + return -EINVAL; + } + } + return 0; } @@ -176,6 +200,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, struct netlink_ext_ack *extack) { int err; + u8 sa_dir = attrs[XFRMA_SA_DIR] ? nla_get_u8(attrs[XFRMA_SA_DIR]) : 0; err = -EINVAL; switch (p->family) { @@ -334,7 +359,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; if ((err = verify_sec_ctx_len(attrs, extack))) goto out; - if ((err = verify_replay(p, attrs, extack))) + if ((err = verify_replay(p, attrs, sa_dir, extack))) goto out; err = -EINVAL; @@ -358,6 +383,77 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; goto out; } + + if (sa_dir == XFRM_SA_DIR_OUT) { + NL_SET_ERR_MSG(extack, + "MTIMER_THRESH attribute should not be set on output SA"); + err = -EINVAL; + goto out; + } + } + + if (sa_dir == XFRM_SA_DIR_OUT) { + if (p->flags & XFRM_STATE_DECAP_DSCP) { + NL_SET_ERR_MSG(extack, "Flag DECAP_DSCP should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (p->flags & XFRM_STATE_ICMP) { + NL_SET_ERR_MSG(extack, "Flag ICMP should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (p->flags & XFRM_STATE_WILDRECV) { + NL_SET_ERR_MSG(extack, "Flag WILDRECV should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (p->replay_window) { + NL_SET_ERR_MSG(extack, "Replay window should be 0 for output SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_REPLAY_VAL]) { + struct xfrm_replay_state *replay; + + replay = nla_data(attrs[XFRMA_REPLAY_VAL]); + + if (replay->seq || replay->bitmap) { + NL_SET_ERR_MSG(extack, + "Replay seq and bitmap should be 0 for output SA"); + err = -EINVAL; + goto out; + } + } + } + + if (sa_dir == XFRM_SA_DIR_IN) { + if (p->flags & XFRM_STATE_NOPMTUDISC) { + NL_SET_ERR_MSG(extack, "Flag NOPMTUDISC should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_SA_EXTRA_FLAGS]) { + u32 xflags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); + + if (xflags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP) { + NL_SET_ERR_MSG(extack, "Flag DONT_ENCAP_DSCP should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (xflags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP) { + NL_SET_ERR_MSG(extack, "Flag OSEQ_MAY_WRAP should not be set for input SA"); + err = -EINVAL; + goto out; + } + + } } out: @@ -734,6 +830,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_IF_ID]) x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (attrs[XFRMA_SA_DIR]) + x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack); if (err) goto error; @@ -1182,8 +1281,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (ret) goto out; } - if (x->mapping_maxage) + if (x->mapping_maxage) { ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage); + if (ret) + goto out; + } + if (x->dir) + ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); out: return ret; } @@ -1618,6 +1722,9 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto out; + if (attrs[XFRMA_SA_DIR]) + x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq); if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); @@ -2402,7 +2509,8 @@ static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x) + nla_total_size_64bit(sizeof(struct xfrm_lifetime_cur)) + nla_total_size(sizeof(struct xfrm_mark)) + nla_total_size(4) /* XFRM_AE_RTHR */ - + nla_total_size(4); /* XFRM_AE_ETHR */ + + nla_total_size(4) /* XFRM_AE_ETHR */ + + nla_total_size(sizeof(x->dir)); /* XFRMA_SA_DIR */ } static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) @@ -2459,6 +2567,12 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; + if (x->dir) { + err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + if (err) + goto out_cancel; + } + nlmsg_end(skb, nlh); return 0; @@ -3018,6 +3132,7 @@ EXPORT_SYMBOL_GPL(xfrm_msg_min); #undef XMSGSIZE const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { + [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = sizeof(struct xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = sizeof(struct xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, @@ -3049,6 +3164,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, + [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), }; EXPORT_SYMBOL_GPL(xfrma_policy); @@ -3189,8 +3305,9 @@ static void xfrm_netlink_rcv(struct sk_buff *skb) static inline unsigned int xfrm_expire_msgsize(void) { - return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) - + nla_total_size(sizeof(struct xfrm_mark)); + return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) + + nla_total_size(sizeof(struct xfrm_mark)) + + nla_total_size(sizeof_field(struct xfrm_state, dir)); } static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) @@ -3217,6 +3334,12 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; + if (x->dir) { + err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + if (err) + return err; + } + nlmsg_end(skb, nlh); return 0; } @@ -3324,6 +3447,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->mapping_maxage) l += nla_total_size(sizeof(x->mapping_maxage)); + if (x->dir) + l += nla_total_size(sizeof(x->dir)); + return l; } -- cgit v1.2.3 From 601a0867f86cbb5e137ce485a7eb60cbf9fc5180 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Tue, 30 Apr 2024 09:09:09 +0200 Subject: xfrm: Add dir validation to "out" data path lookup Introduces validation for the x->dir attribute within the XFRM output data lookup path. If the configured direction does not match the expected direction, output, increment the XfrmOutStateDirError counter and drop the packet to ensure data integrity and correct flow handling. grep -vw 0 /proc/net/xfrm_stat XfrmOutPolError 1 XfrmOutStateDirError 1 Signed-off-by: Antony Antony Reviewed-by: Sabrina Dubroca Reviewed-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- Documentation/networking/xfrm_proc.rst | 3 +++ include/uapi/linux/snmp.h | 1 + net/xfrm/xfrm_policy.c | 6 ++++++ net/xfrm/xfrm_proc.c | 1 + 4 files changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/xfrm_proc.rst b/Documentation/networking/xfrm_proc.rst index 0a771c5a7399..5ac3acf4cf51 100644 --- a/Documentation/networking/xfrm_proc.rst +++ b/Documentation/networking/xfrm_proc.rst @@ -111,3 +111,6 @@ XfrmOutPolError: XfrmOutStateInvalid: State is invalid, perhaps expired + +XfrmOutStateDirError: + State direction mismatch (lookup found an input state on the output path, expected output or no direction) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index a0819c6a5988..23792b8412bd 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -337,6 +337,7 @@ enum LINUX_MIB_XFRMFWDHDRERROR, /* XfrmFwdHdrError*/ LINUX_MIB_XFRMOUTSTATEINVALID, /* XfrmOutStateInvalid */ LINUX_MIB_XFRMACQUIREERROR, /* XfrmAcquireError */ + LINUX_MIB_XFRMOUTSTATEDIRERROR, /* XfrmOutStateDirError */ __LINUX_MIB_XFRMMAX }; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6affe5cd85d8..298b3a9eb48d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2489,6 +2489,12 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family, policy->if_id); + if (x && x->dir && x->dir != XFRM_SA_DIR_OUT) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEDIRERROR); + xfrm_state_put(x); + error = -EINVAL; + goto fail; + } if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 5f9bf8e5c933..98606f1078f7 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -41,6 +41,7 @@ static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR), SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID), SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR), + SNMP_MIB_ITEM("XfrmOutStateDirError", LINUX_MIB_XFRMOUTSTATEDIRERROR), SNMP_MIB_SENTINEL }; -- cgit v1.2.3 From 304b44f0d5a4c2f91f82f7c31538d00485fb484c Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Tue, 30 Apr 2024 09:09:29 +0200 Subject: xfrm: Add dir validation to "in" data path lookup Introduces validation for the x->dir attribute within the XFRM input data lookup path. If the configured direction does not match the expected direction, input, increment the XfrmInStateDirError counter and drop the packet to ensure data integrity and correct flow handling. grep -vw 0 /proc/net/xfrm_stat XfrmInStateDirError 1 Signed-off-by: Antony Antony Reviewed-by: Sabrina Dubroca Reviewed-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- Documentation/networking/xfrm_proc.rst | 3 +++ include/uapi/linux/snmp.h | 1 + net/ipv6/xfrm6_input.c | 7 +++++++ net/xfrm/xfrm_input.c | 11 +++++++++++ net/xfrm/xfrm_proc.c | 1 + 5 files changed, 23 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/xfrm_proc.rst b/Documentation/networking/xfrm_proc.rst index 5ac3acf4cf51..973d1571acac 100644 --- a/Documentation/networking/xfrm_proc.rst +++ b/Documentation/networking/xfrm_proc.rst @@ -73,6 +73,9 @@ XfrmAcquireError: XfrmFwdHdrError: Forward routing of a packet is not allowed +XfrmInStateDirError: + State direction mismatch (lookup found an output state on the input path, expected input or no direction) + Outbound errors ~~~~~~~~~~~~~~~ XfrmOutError: diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 23792b8412bd..adf5fd78dd50 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -338,6 +338,7 @@ enum LINUX_MIB_XFRMOUTSTATEINVALID, /* XfrmOutStateInvalid */ LINUX_MIB_XFRMACQUIREERROR, /* XfrmAcquireError */ LINUX_MIB_XFRMOUTSTATEDIRERROR, /* XfrmOutStateDirError */ + LINUX_MIB_XFRMINSTATEDIRERROR, /* XfrmInStateDirError */ __LINUX_MIB_XFRMMAX }; diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 2c6aeb090b7a..d5bac0d76b6e 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -266,6 +266,13 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, if (!x) continue; + if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); + xfrm_state_put(x); + x = NULL; + continue; + } + spin_lock(&x->lock); if ((!i || (x->props.flags & XFRM_STATE_WILDRECV)) && diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 161f535c8b94..71b42de6e3c9 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -466,6 +466,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) if (encap_type < 0 || (xo && xo->flags & XFRM_GRO)) { x = xfrm_input_state(skb); + if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); + goto drop; + } + if (unlikely(x->km.state != XFRM_STATE_VALID)) { if (x->km.state == XFRM_STATE_ACQ) XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); @@ -571,6 +576,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } + if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); + xfrm_state_put(x); + goto drop; + } + skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 98606f1078f7..eeb984be03a7 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -42,6 +42,7 @@ static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID), SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR), SNMP_MIB_ITEM("XfrmOutStateDirError", LINUX_MIB_XFRMOUTSTATEDIRERROR), + SNMP_MIB_ITEM("XfrmInStateDirError", LINUX_MIB_XFRMINSTATEDIRERROR), SNMP_MIB_SENTINEL }; -- cgit v1.2.3 From 9243240bed3859fba2d15c016902a4c73a186249 Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Mon, 21 Aug 2023 11:47:47 -0400 Subject: drm/amdkfd: enable single alu ops for gfx12 GFX12 debugging requires setting up precise ALU operation for catching ALU exceptions. Signed-off-by: Jonathan Kim Tested-by: Lancelot Six Reviewed-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_debug.c | 15 +++++++++++++-- drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 4 ++++ include/uapi/linux/kfd_ioctl.h | 1 + include/uapi/linux/kfd_sysfs.h | 19 ++++++++++--------- 4 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c index d889e3545120..45b1975b149a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c @@ -25,6 +25,7 @@ #include "kfd_topology.h" #include #include +#include #define MAX_WATCH_ADDRESSES 4 @@ -497,14 +498,24 @@ int kfd_dbg_trap_set_flags(struct kfd_process *target, uint32_t *flags) int i, r = 0, rewind_count = 0; for (i = 0; i < target->n_pdds; i++) { - if (!kfd_dbg_is_per_vmid_supported(target->pdds[i]->dev) && + struct kfd_topology_device *topo_dev = + kfd_topology_device_by_id(target->pdds[i]->dev->id); + uint32_t caps = topo_dev->node_props.capability; + + if (!(caps | HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED) && (*flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP)) { *flags = prev_flags; return -EACCES; } + + if (!(caps | HSA_CAP_TRAP_DEBUG_PRECISE_ALU_OPERATIONS_SUPPORTED) && + (*flags & KFD_DBG_TRAP_FLAG_SINGLE_ALU_OP)) { + *flags = prev_flags; + return -EACCES; + } } - target->dbg_flags = *flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP; + target->dbg_flags = *flags; *flags = prev_flags; for (i = 0; i < target->n_pdds; i++) { struct kfd_process_device *pdd = target->pdds[i]; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 71bea1fcb838..ba326b43bec5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1929,6 +1929,10 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev) if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(11, 0, 0)) dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED; + + if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(12, 0, 0)) + dev->node_props.capability |= + HSA_CAP_TRAP_DEBUG_PRECISE_ALU_OPERATIONS_SUPPORTED; } kfd_topology_set_dbg_firmware_support(dev); diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f8e9d3c1d117..285a36601dc9 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -854,6 +854,7 @@ enum kfd_dbg_trap_address_watch_mode { /* Additional wave settings */ enum kfd_dbg_trap_flags { KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP = 1, + KFD_DBG_TRAP_FLAG_SINGLE_ALU_OP = 2, }; /* Trap exceptions */ diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h index a51b7331e0b4..5e8d28617efa 100644 --- a/include/uapi/linux/kfd_sysfs.h +++ b/include/uapi/linux/kfd_sysfs.h @@ -51,15 +51,16 @@ /* Old buggy user mode depends on this being 0 */ #define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 -#define HSA_CAP_MEM_EDCSUPPORTED 0x00100000 -#define HSA_CAP_RASEVENTNOTIFY 0x00200000 -#define HSA_CAP_ASIC_REVISION_MASK 0x03c00000 -#define HSA_CAP_ASIC_REVISION_SHIFT 22 -#define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 -#define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 -#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 -#define HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED 0x20000000 -#define HSA_CAP_RESERVED 0xe00f8000 +#define HSA_CAP_MEM_EDCSUPPORTED 0x00100000 +#define HSA_CAP_RASEVENTNOTIFY 0x00200000 +#define HSA_CAP_ASIC_REVISION_MASK 0x03c00000 +#define HSA_CAP_ASIC_REVISION_SHIFT 22 +#define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 +#define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 +#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 +#define HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED 0x20000000 +#define HSA_CAP_TRAP_DEBUG_PRECISE_ALU_OPERATIONS_SUPPORTED 0x40000000 +#define HSA_CAP_RESERVED 0x800f8000 /* debug_prop bits in node properties */ #define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK 0x0000000f -- cgit v1.2.3 From 4a3540a8bf3c13dc3955f0c0895332b9c653be3f Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Wed, 6 Mar 2024 15:18:04 +0100 Subject: netfilter: conntrack: fix ct-state for ICMPv6 Multicast Router Discovery MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far Multicast Router Advertisements and Multicast Router Solicitations from the Multicast Router Discovery protocol (RFC4286) would be marked as INVALID for IPv6, even if they are in fact intact and adhering to RFC4286. This broke MRA reception and by that multicast reception on IPv6 multicast routers in a Proxmox managed setup, where Proxmox would install a rule like "-m conntrack --ctstate INVALID -j DROP" at the top of the FORWARD chain with br-nf-call-ip6tables enabled by default. Similar to as it's done for MLDv1, MLDv2 and IPv6 Neighbor Discovery already, fix this issue by excluding MRD from connection tracking handling as MRD always uses predefined multicast destinations for its messages, too. This changes the ct-state for ICMPv6 MRD messages from INVALID to UNTRACKED. This issue was found and fixed with the help of the mrdisc tool (https://github.com/troglobit/mrdisc). Signed-off-by: Linus Lüssing Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/icmpv6.h | 1 + net/netfilter/nf_conntrack_proto_icmpv6.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index ecaece3af38d..4eaab89e2856 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -112,6 +112,7 @@ struct icmp6hdr { #define ICMPV6_MOBILE_PREFIX_ADV 147 #define ICMPV6_MRDISC_ADV 151 +#define ICMPV6_MRDISC_SOL 152 #define ICMPV6_MSG_MAX 255 diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 1020d67600a9..327b8059025d 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -62,7 +62,9 @@ static const u_int8_t noct_valid_new[] = { [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, - [ICMPV6_MLD2_REPORT - 130] = 1 + [ICMPV6_MLD2_REPORT - 130] = 1, + [ICMPV6_MRDISC_ADV - 130] = 1, + [ICMPV6_MRDISC_SOL - 130] = 1 }; bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, -- cgit v1.2.3 From 628d701f2de5b9a16d1dd82bea68fd895f56f1a1 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Wed, 17 Apr 2024 21:23:20 +1000 Subject: powerpc/dexcr: Add DEXCR prctl interface Now that we track a DEXCR on a per-task basis, individual tasks are free to configure it as they like. The interface is a pair of getter/setter prctl's that work on a single aspect at a time (multiple aspects at once is more difficult if there are different rules applied for each aspect, now or in future). The getter shows the current state of the process config, and the setter allows setting/clearing the aspect. Signed-off-by: Benjamin Gray [mpe: Account for PR_RISCV_SET_ICACHE_FLUSH_CTX, shrink some longs lines] Signed-off-by: Michael Ellerman Link: https://msgid.link/20240417112325.728010-5-bgray@linux.ibm.com --- arch/powerpc/include/asm/processor.h | 10 ++++ arch/powerpc/kernel/dexcr.c | 101 +++++++++++++++++++++++++++++++++++ include/uapi/linux/prctl.h | 16 ++++++ kernel/sys.c | 16 ++++++ 4 files changed, 143 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index aad85a24134a..e44cac0da346 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -334,6 +334,16 @@ extern int set_endian(struct task_struct *tsk, unsigned int val); extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr); extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); +#ifdef CONFIG_PPC_BOOK3S_64 + +#define PPC_GET_DEXCR_ASPECT(tsk, asp) get_dexcr_prctl((tsk), (asp)) +#define PPC_SET_DEXCR_ASPECT(tsk, asp, val) set_dexcr_prctl((tsk), (asp), (val)) + +int get_dexcr_prctl(struct task_struct *tsk, unsigned long asp); +int set_dexcr_prctl(struct task_struct *tsk, unsigned long asp, unsigned long val); + +#endif + extern void load_fp_state(struct thread_fp_state *fp); extern void store_fp_state(struct thread_fp_state *fp); extern void load_vr_state(struct thread_vr_state *vr); diff --git a/arch/powerpc/kernel/dexcr.c b/arch/powerpc/kernel/dexcr.c index d5cd77421088..3a0358e91c60 100644 --- a/arch/powerpc/kernel/dexcr.c +++ b/arch/powerpc/kernel/dexcr.c @@ -21,3 +21,104 @@ static int __init init_task_dexcr(void) return 0; } early_initcall(init_task_dexcr) + +/* Allow thread local configuration of these by default */ +#define DEXCR_PRCTL_EDITABLE ( \ + DEXCR_PR_IBRTPD | \ + DEXCR_PR_SRAPD | \ + DEXCR_PR_NPHIE) + +static int prctl_to_aspect(unsigned long which, unsigned int *aspect) +{ + switch (which) { + case PR_PPC_DEXCR_SBHE: + *aspect = DEXCR_PR_SBHE; + break; + case PR_PPC_DEXCR_IBRTPD: + *aspect = DEXCR_PR_IBRTPD; + break; + case PR_PPC_DEXCR_SRAPD: + *aspect = DEXCR_PR_SRAPD; + break; + case PR_PPC_DEXCR_NPHIE: + *aspect = DEXCR_PR_NPHIE; + break; + default: + return -ENODEV; + } + + return 0; +} + +int get_dexcr_prctl(struct task_struct *task, unsigned long which) +{ + unsigned int aspect; + int ret; + + ret = prctl_to_aspect(which, &aspect); + if (ret) + return ret; + + if (aspect & DEXCR_PRCTL_EDITABLE) + ret |= PR_PPC_DEXCR_CTRL_EDITABLE; + + if (aspect & mfspr(SPRN_DEXCR)) + ret |= PR_PPC_DEXCR_CTRL_SET; + else + ret |= PR_PPC_DEXCR_CTRL_CLEAR; + + if (aspect & task->thread.dexcr_onexec) + ret |= PR_PPC_DEXCR_CTRL_SET_ONEXEC; + else + ret |= PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC; + + return ret; +} + +int set_dexcr_prctl(struct task_struct *task, unsigned long which, unsigned long ctrl) +{ + unsigned long dexcr; + unsigned int aspect; + int err = 0; + + err = prctl_to_aspect(which, &aspect); + if (err) + return err; + + if (!(aspect & DEXCR_PRCTL_EDITABLE)) + return -EPERM; + + if (ctrl & ~PR_PPC_DEXCR_CTRL_MASK) + return -EINVAL; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET && ctrl & PR_PPC_DEXCR_CTRL_CLEAR) + return -EINVAL; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC && ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC) + return -EINVAL; + + /* + * We do not want an unprivileged process being able to disable + * a setuid process's hash check instructions + */ + if (aspect == DEXCR_PR_NPHIE && + ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + + dexcr = mfspr(SPRN_DEXCR); + + if (ctrl & PR_PPC_DEXCR_CTRL_SET) + dexcr |= aspect; + else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR) + dexcr &= ~aspect; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC) + task->thread.dexcr_onexec |= aspect; + else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC) + task->thread.dexcr_onexec &= ~aspect; + + mtspr(SPRN_DEXCR, dexcr); + + return 0; +} diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 370ed14b1ae0..713d28788df7 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -306,4 +306,20 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f +/* PowerPC Dynamic Execution Control Register (DEXCR) controls */ +#define PR_PPC_GET_DEXCR 72 +#define PR_PPC_SET_DEXCR 73 +/* DEXCR aspect to act on */ +# define PR_PPC_DEXCR_SBHE 0 /* Speculative branch hint enable */ +# define PR_PPC_DEXCR_IBRTPD 1 /* Indirect branch recurrent target prediction disable */ +# define PR_PPC_DEXCR_SRAPD 2 /* Subroutine return address prediction disable */ +# define PR_PPC_DEXCR_NPHIE 3 /* Non-privileged hash instruction enable */ +/* Action to apply / return */ +# define PR_PPC_DEXCR_CTRL_EDITABLE 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */ +# define PR_PPC_DEXCR_CTRL_SET 0x2 /* Set the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_CLEAR 0x4 /* Clear the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_MASK 0x1f + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 8bb106a56b3a..f9c95410278c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -146,6 +146,12 @@ #ifndef RISCV_V_GET_CONTROL # define RISCV_V_GET_CONTROL() (-EINVAL) #endif +#ifndef PPC_GET_DEXCR_ASPECT +# define PPC_GET_DEXCR_ASPECT(a, b) (-EINVAL) +#endif +#ifndef PPC_SET_DEXCR_ASPECT +# define PPC_SET_DEXCR_ASPECT(a, b, c) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -2726,6 +2732,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_MDWE: error = prctl_get_mdwe(arg2, arg3, arg4, arg5); break; + case PR_PPC_GET_DEXCR: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = PPC_GET_DEXCR_ASPECT(me, arg2); + break; + case PR_PPC_SET_DEXCR: + if (arg4 || arg5) + return -EINVAL; + error = PPC_SET_DEXCR_ASPECT(me, arg2, arg3); + break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; -- cgit v1.2.3 From 924f4fb003ba114c60b3c07a011dcd86a8956cd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 23 Apr 2024 15:25:40 +0200 Subject: NFSD: convert write_threads to netlink command Introduce write_threads netlink command similar to the one available through the procfs. Tested-by: Jeff Layton Reviewed-by: Jeff Layton Co-developed-by: Jeff Layton Signed-off-by: Jeff Layton Signed-off-by: Lorenzo Bianconi Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 39 ++++++++++ fs/nfsd/netlink.c | 20 +++++ fs/nfsd/netlink.h | 2 + fs/nfsd/nfsctl.c | 143 ++++++++++++++++++++++++++++++++++ include/uapi/linux/nfsd_netlink.h | 12 +++ 5 files changed, 216 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 05acc73e2e33..703c2d11d0a9 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -62,6 +62,22 @@ attribute-sets: name: compound-ops type: u32 multi-attr: true + - + name: server + attributes: + - + name: threads + type: u32 + multi-attr: true + - + name: gracetime + type: u32 + - + name: leasetime + type: u32 + - + name: scope + type: string operations: list: @@ -87,3 +103,26 @@ operations: - sport - dport - compound-ops + - + name: threads-set + doc: set the number of running threads + attribute-set: server + flags: [ admin-perm ] + do: + request: + attributes: + - threads + - gracetime + - leasetime + - scope + - + name: threads-get + doc: get the number of running threads + attribute-set: server + do: + reply: + attributes: + - threads + - gracetime + - leasetime + - scope diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 0e1d635ec5f9..fe9eef5c7f27 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -10,6 +10,14 @@ #include +/* NFSD_CMD_THREADS_SET - do */ +static const struct nla_policy nfsd_threads_set_nl_policy[NFSD_A_SERVER_SCOPE + 1] = { + [NFSD_A_SERVER_THREADS] = { .type = NLA_U32, }, + [NFSD_A_SERVER_GRACETIME] = { .type = NLA_U32, }, + [NFSD_A_SERVER_LEASETIME] = { .type = NLA_U32, }, + [NFSD_A_SERVER_SCOPE] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -19,6 +27,18 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .done = nfsd_nl_rpc_status_get_done, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NFSD_CMD_THREADS_SET, + .doit = nfsd_nl_threads_set_doit, + .policy = nfsd_threads_set_nl_policy, + .maxattr = NFSD_A_SERVER_SCOPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_THREADS_GET, + .doit = nfsd_nl_threads_get_doit, + .flags = GENL_CMD_CAP_DO, + }, }; struct genl_family nfsd_nl_family __ro_after_init = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index d83dd6bdee92..4137fac477e4 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -16,6 +16,8 @@ int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb); int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info); extern struct genl_family nfsd_nl_family; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 34148d73b6c1..5bfdebb2e7e9 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -1653,6 +1654,148 @@ int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb) return 0; } +/** + * nfsd_nl_threads_set_doit - set the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + int nthreads = 0, count = 0, nrpools, ret = -EOPNOTSUPP, rem; + struct net *net = genl_info_net(info); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + const struct nlattr *attr; + const char *scope = NULL; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_THREADS)) + return -EINVAL; + + /* count number of SERVER_THREADS values */ + nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + if (nla_type(attr) == NFSD_A_SERVER_THREADS) + count++; + } + + mutex_lock(&nfsd_mutex); + + nrpools = nfsd_nrpools(net); + if (nrpools && count > nrpools) + count = nrpools; + + /* XXX: make this handle non-global pool-modes */ + if (count > 1) + goto out_unlock; + + nthreads = nla_get_u32(info->attrs[NFSD_A_SERVER_THREADS]); + if (info->attrs[NFSD_A_SERVER_GRACETIME] || + info->attrs[NFSD_A_SERVER_LEASETIME] || + info->attrs[NFSD_A_SERVER_SCOPE]) { + ret = -EBUSY; + if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads) + goto out_unlock; + + ret = -EINVAL; + attr = info->attrs[NFSD_A_SERVER_GRACETIME]; + if (attr) { + u32 gracetime = nla_get_u32(attr); + + if (gracetime < 10 || gracetime > 3600) + goto out_unlock; + + nn->nfsd4_grace = gracetime; + } + + attr = info->attrs[NFSD_A_SERVER_LEASETIME]; + if (attr) { + u32 leasetime = nla_get_u32(attr); + + if (leasetime < 10 || leasetime > 3600) + goto out_unlock; + + nn->nfsd4_lease = leasetime; + } + + attr = info->attrs[NFSD_A_SERVER_SCOPE]; + if (attr) + scope = nla_data(attr); + } + + ret = nfsd_svc(nthreads, net, get_current_cred(), scope); + +out_unlock: + mutex_unlock(&nfsd_mutex); + + return ret == nthreads ? 0 : ret; +} + +/** + * nfsd_nl_threads_get_doit - get the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + void *hdr; + int err; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_iput(skb, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_free_msg; + } + + mutex_lock(&nfsd_mutex); + + err = nla_put_u32(skb, NFSD_A_SERVER_GRACETIME, + nn->nfsd4_grace) || + nla_put_u32(skb, NFSD_A_SERVER_LEASETIME, + nn->nfsd4_lease) || + nla_put_string(skb, NFSD_A_SERVER_SCOPE, + nn->nfsd_name); + if (err) + goto err_unlock; + + if (nn->nfsd_serv) { + int i; + + for (i = 0; i < nfsd_nrpools(net); ++i) { + struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i]; + + err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, + atomic_read(&sp->sp_nrthreads)); + if (err) + goto err_unlock; + } + } else { + err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, 0); + if (err) + goto err_unlock; + } + + mutex_unlock(&nfsd_mutex); + + genlmsg_end(skb, hdr); + + return genlmsg_reply(skb, info); + +err_unlock: + mutex_unlock(&nfsd_mutex); +err_free_msg: + nlmsg_free(skb); + + return err; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 3cd044edee5d..4bbccd5db7cd 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -29,8 +29,20 @@ enum { NFSD_A_RPC_STATUS_MAX = (__NFSD_A_RPC_STATUS_MAX - 1) }; +enum { + NFSD_A_SERVER_THREADS = 1, + NFSD_A_SERVER_GRACETIME, + NFSD_A_SERVER_LEASETIME, + NFSD_A_SERVER_SCOPE, + + __NFSD_A_SERVER_MAX, + NFSD_A_SERVER_MAX = (__NFSD_A_SERVER_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, + NFSD_CMD_THREADS_SET, + NFSD_CMD_THREADS_GET, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.2.3 From 5a939bea25be9793d9aa5d8494df667dfe625e6b Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 23 Apr 2024 15:25:41 +0200 Subject: NFSD: add write_version to netlink command Introduce write_version netlink command through a "declarative" interface. This patch introduces a change in behavior since for version-set userspace is expected to provide a NFS major/minor version list it wants to enable while all the other ones will be disabled. (procfs write_version command implements imperative interface where the admin writes +3/-3 to enable/disable a single version. Reviewed-by: Jeff Layton Tested-by: Jeff Layton Signed-off-by: Lorenzo Bianconi Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 37 +++++++++ fs/nfsd/netlink.c | 24 ++++++ fs/nfsd/netlink.h | 5 ++ fs/nfsd/netns.h | 1 + fs/nfsd/nfsctl.c | 150 ++++++++++++++++++++++++++++++++++ fs/nfsd/nfssvc.c | 3 +- include/uapi/linux/nfsd_netlink.h | 18 ++++ 7 files changed, 236 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 703c2d11d0a9..77adda1425e2 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -78,6 +78,26 @@ attribute-sets: - name: scope type: string + - + name: version + attributes: + - + name: major + type: u32 + - + name: minor + type: u32 + - + name: enabled + type: flag + - + name: server-proto + attributes: + - + name: version + type: nest + nested-attributes: version + multi-attr: true operations: list: @@ -126,3 +146,20 @@ operations: - gracetime - leasetime - scope + - + name: version-set + doc: set nfs enabled versions + attribute-set: server-proto + flags: [ admin-perm ] + do: + request: + attributes: + - version + - + name: version-get + doc: get nfs enabled versions + attribute-set: server-proto + do: + reply: + attributes: + - version diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index fe9eef5c7f27..b23b0b84a59a 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -10,6 +10,13 @@ #include +/* Common nested types */ +const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1] = { + [NFSD_A_VERSION_MAJOR] = { .type = NLA_U32, }, + [NFSD_A_VERSION_MINOR] = { .type = NLA_U32, }, + [NFSD_A_VERSION_ENABLED] = { .type = NLA_FLAG, }, +}; + /* NFSD_CMD_THREADS_SET - do */ static const struct nla_policy nfsd_threads_set_nl_policy[NFSD_A_SERVER_SCOPE + 1] = { [NFSD_A_SERVER_THREADS] = { .type = NLA_U32, }, @@ -18,6 +25,11 @@ static const struct nla_policy nfsd_threads_set_nl_policy[NFSD_A_SERVER_SCOPE + [NFSD_A_SERVER_SCOPE] = { .type = NLA_NUL_STRING, }, }; +/* NFSD_CMD_VERSION_SET - do */ +static const struct nla_policy nfsd_version_set_nl_policy[NFSD_A_SERVER_PROTO_VERSION + 1] = { + [NFSD_A_SERVER_PROTO_VERSION] = NLA_POLICY_NESTED(nfsd_version_nl_policy), +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -39,6 +51,18 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .doit = nfsd_nl_threads_get_doit, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_VERSION_SET, + .doit = nfsd_nl_version_set_doit, + .policy = nfsd_version_set_nl_policy, + .maxattr = NFSD_A_SERVER_PROTO_VERSION, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_VERSION_GET, + .doit = nfsd_nl_version_get_doit, + .flags = GENL_CMD_CAP_DO, + }, }; struct genl_family nfsd_nl_family __ro_after_init = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 4137fac477e4..c7c0da275481 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -11,6 +11,9 @@ #include +/* Common nested types */ +extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1]; + int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb); int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb); @@ -18,6 +21,8 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info); extern struct genl_family nfsd_nl_family; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index d4be519b5734..14ec15656320 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -218,6 +218,7 @@ struct nfsd_net { /* Simple check to find out if a given net was properly initialized */ #define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl) +extern bool nfsd_support_version(int vers); extern void nfsd_netns_free_versions(struct nfsd_net *nn); extern unsigned int nfsd_net_id; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 5bfdebb2e7e9..b6b405437aa0 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1796,6 +1796,156 @@ err_free_msg: return err; } +/** + * nfsd_nl_version_set_doit - set the nfs enabled versions + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + const struct nlattr *attr; + struct nfsd_net *nn; + int i, rem; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_PROTO_VERSION)) + return -EINVAL; + + mutex_lock(&nfsd_mutex); + + nn = net_generic(genl_info_net(info), nfsd_net_id); + if (nn->nfsd_serv) { + mutex_unlock(&nfsd_mutex); + return -EBUSY; + } + + /* clear current supported versions. */ + nfsd_vers(nn, 2, NFSD_CLEAR); + nfsd_vers(nn, 3, NFSD_CLEAR); + for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) + nfsd_minorversion(nn, i, NFSD_CLEAR); + + nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_VERSION_MAX + 1]; + u32 major, minor = 0; + bool enabled; + + if (nla_type(attr) != NFSD_A_SERVER_PROTO_VERSION) + continue; + + if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr, + nfsd_version_nl_policy, info->extack) < 0) + continue; + + if (!tb[NFSD_A_VERSION_MAJOR]) + continue; + + major = nla_get_u32(tb[NFSD_A_VERSION_MAJOR]); + if (tb[NFSD_A_VERSION_MINOR]) + minor = nla_get_u32(tb[NFSD_A_VERSION_MINOR]); + + enabled = nla_get_flag(tb[NFSD_A_VERSION_ENABLED]); + + switch (major) { + case 4: + nfsd_minorversion(nn, minor, enabled ? NFSD_SET : NFSD_CLEAR); + break; + case 3: + case 2: + if (!minor) + nfsd_vers(nn, major, enabled ? NFSD_SET : NFSD_CLEAR); + break; + default: + break; + } + } + + mutex_unlock(&nfsd_mutex); + + return 0; +} + +/** + * nfsd_nl_version_get_doit - get the enabled status for all supported nfs versions + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nfsd_net *nn; + int i, err; + void *hdr; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_iput(skb, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_free_msg; + } + + mutex_lock(&nfsd_mutex); + nn = net_generic(genl_info_net(info), nfsd_net_id); + + for (i = 2; i <= 4; i++) { + int j; + + for (j = 0; j <= NFSD_SUPPORTED_MINOR_VERSION; j++) { + struct nlattr *attr; + + /* Don't record any versions the kernel doesn't have + * compiled in + */ + if (!nfsd_support_version(i)) + continue; + + /* NFSv{2,3} does not support minor numbers */ + if (i < 4 && j) + continue; + + attr = nla_nest_start(skb, + NFSD_A_SERVER_PROTO_VERSION); + if (!attr) { + err = -EINVAL; + goto err_nfsd_unlock; + } + + if (nla_put_u32(skb, NFSD_A_VERSION_MAJOR, i) || + nla_put_u32(skb, NFSD_A_VERSION_MINOR, j)) { + err = -EINVAL; + goto err_nfsd_unlock; + } + + /* Set the enabled flag if the version is enabled */ + if (nfsd_vers(nn, i, NFSD_TEST) && + (i < 4 || nfsd_minorversion(nn, j, NFSD_TEST)) && + nla_put_flag(skb, NFSD_A_VERSION_ENABLED)) { + err = -EINVAL; + goto err_nfsd_unlock; + } + + nla_nest_end(skb, attr); + } + } + + mutex_unlock(&nfsd_mutex); + genlmsg_end(skb, hdr); + + return genlmsg_reply(skb, info); + +err_nfsd_unlock: + mutex_unlock(&nfsd_mutex); +err_free_msg: + nlmsg_free(skb); + + return err; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index e25b9b829749..cd9a6a1a9fc8 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -133,8 +133,7 @@ struct svc_program nfsd_program = { .pg_rpcbind_set = nfsd_rpcbind_set, }; -static bool -nfsd_support_version(int vers) +bool nfsd_support_version(int vers) { if (vers >= NFSD_MINVERS && vers < NFSD_NRVERS) return nfsd_version[vers] != NULL; diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 4bbccd5db7cd..7176cd8e6f09 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -39,10 +39,28 @@ enum { NFSD_A_SERVER_MAX = (__NFSD_A_SERVER_MAX - 1) }; +enum { + NFSD_A_VERSION_MAJOR = 1, + NFSD_A_VERSION_MINOR, + NFSD_A_VERSION_ENABLED, + + __NFSD_A_VERSION_MAX, + NFSD_A_VERSION_MAX = (__NFSD_A_VERSION_MAX - 1) +}; + +enum { + NFSD_A_SERVER_PROTO_VERSION = 1, + + __NFSD_A_SERVER_PROTO_MAX, + NFSD_A_SERVER_PROTO_MAX = (__NFSD_A_SERVER_PROTO_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, NFSD_CMD_THREADS_GET, + NFSD_CMD_VERSION_SET, + NFSD_CMD_VERSION_GET, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.2.3 From 16a471177496c8e04a9793812c187a2c1a2192fa Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 23 Apr 2024 15:25:44 +0200 Subject: NFSD: add listener-{set,get} netlink command Introduce write_ports netlink command. For listener-set, userspace is expected to provide a NFS listeners list it wants enabled. All other sockets will be closed. Reviewed-by: Jeff Layton Co-developed-by: Jeff Layton Signed-off-by: Jeff Layton Signed-off-by: Lorenzo Bianconi Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 34 ++++++ fs/nfsd/netlink.c | 22 ++++ fs/nfsd/netlink.h | 3 + fs/nfsd/nfsctl.c | 220 ++++++++++++++++++++++++++++++++++ include/uapi/linux/nfsd_netlink.h | 17 +++ 5 files changed, 296 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 77adda1425e2..d21234097167 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -98,6 +98,23 @@ attribute-sets: type: nest nested-attributes: version multi-attr: true + - + name: sock + attributes: + - + name: addr + type: binary + - + name: transport-name + type: string + - + name: server-sock + attributes: + - + name: addr + type: nest + nested-attributes: sock + multi-attr: true operations: list: @@ -163,3 +180,20 @@ operations: reply: attributes: - version + - + name: listener-set + doc: set nfs running sockets + attribute-set: server-sock + flags: [ admin-perm ] + do: + request: + attributes: + - addr + - + name: listener-get + doc: get nfs running listeners + attribute-set: server-sock + do: + reply: + attributes: + - addr diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index b23b0b84a59a..62d2586d9902 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -11,6 +11,11 @@ #include /* Common nested types */ +const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1] = { + [NFSD_A_SOCK_ADDR] = { .type = NLA_BINARY, }, + [NFSD_A_SOCK_TRANSPORT_NAME] = { .type = NLA_NUL_STRING, }, +}; + const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1] = { [NFSD_A_VERSION_MAJOR] = { .type = NLA_U32, }, [NFSD_A_VERSION_MINOR] = { .type = NLA_U32, }, @@ -30,6 +35,11 @@ static const struct nla_policy nfsd_version_set_nl_policy[NFSD_A_SERVER_PROTO_VE [NFSD_A_SERVER_PROTO_VERSION] = NLA_POLICY_NESTED(nfsd_version_nl_policy), }; +/* NFSD_CMD_LISTENER_SET - do */ +static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_ADDR + 1] = { + [NFSD_A_SERVER_SOCK_ADDR] = NLA_POLICY_NESTED(nfsd_sock_nl_policy), +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -63,6 +73,18 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .doit = nfsd_nl_version_get_doit, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_LISTENER_SET, + .doit = nfsd_nl_listener_set_doit, + .policy = nfsd_listener_set_nl_policy, + .maxattr = NFSD_A_SERVER_SOCK_ADDR, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_LISTENER_GET, + .doit = nfsd_nl_listener_get_doit, + .flags = GENL_CMD_CAP_DO, + }, }; struct genl_family nfsd_nl_family __ro_after_init = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index c7c0da275481..e3724637d64d 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -12,6 +12,7 @@ #include /* Common nested types */ +extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1]; extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1]; int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb); @@ -23,6 +24,8 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info); extern struct genl_family nfsd_nl_family; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b6b405437aa0..202140df8f82 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1946,6 +1946,226 @@ err_free_msg: return err; } +/** + * nfsd_nl_listener_set_doit - set the nfs running sockets + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct svc_xprt *xprt, *tmp; + const struct nlattr *attr; + struct svc_serv *serv; + LIST_HEAD(permsocks); + struct nfsd_net *nn; + int err, rem; + + mutex_lock(&nfsd_mutex); + + err = nfsd_create_serv(net); + if (err) { + mutex_unlock(&nfsd_mutex); + return err; + } + + nn = net_generic(net, nfsd_net_id); + serv = nn->nfsd_serv; + + spin_lock_bh(&serv->sv_lock); + + /* Move all of the old listener sockets to a temp list */ + list_splice_init(&serv->sv_permsocks, &permsocks); + + /* + * Walk the list of server_socks from userland and move any that match + * back to sv_permsocks + */ + nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; + const char *xcl_name; + struct sockaddr *sa; + + if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR) + continue; + + if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, + nfsd_sock_nl_policy, info->extack) < 0) + continue; + + if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) + continue; + + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) + continue; + + xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); + sa = nla_data(tb[NFSD_A_SOCK_ADDR]); + + /* Put back any matching sockets */ + list_for_each_entry_safe(xprt, tmp, &permsocks, xpt_list) { + /* This shouldn't be possible */ + if (WARN_ON_ONCE(xprt->xpt_net != net)) { + list_move(&xprt->xpt_list, &serv->sv_permsocks); + continue; + } + + /* If everything matches, put it back */ + if (!strcmp(xprt->xpt_class->xcl_name, xcl_name) && + rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) { + list_move(&xprt->xpt_list, &serv->sv_permsocks); + break; + } + } + } + + /* For now, no removing old sockets while server is running */ + if (serv->sv_nrthreads && !list_empty(&permsocks)) { + list_splice_init(&permsocks, &serv->sv_permsocks); + spin_unlock_bh(&serv->sv_lock); + err = -EBUSY; + goto out_unlock_mtx; + } + + /* Close the remaining sockets on the permsocks list */ + while (!list_empty(&permsocks)) { + xprt = list_first_entry(&permsocks, struct svc_xprt, xpt_list); + list_move(&xprt->xpt_list, &serv->sv_permsocks); + + /* + * Newly-created sockets are born with the BUSY bit set. Clear + * it if there are no threads, since nothing can pick it up + * in that case. + */ + if (!serv->sv_nrthreads) + clear_bit(XPT_BUSY, &xprt->xpt_flags); + + set_bit(XPT_CLOSE, &xprt->xpt_flags); + spin_unlock_bh(&serv->sv_lock); + svc_xprt_close(xprt); + spin_lock_bh(&serv->sv_lock); + } + + spin_unlock_bh(&serv->sv_lock); + + /* walk list of addrs again, open any that still don't exist */ + nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; + const char *xcl_name; + struct sockaddr *sa; + int ret; + + if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR) + continue; + + if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, + nfsd_sock_nl_policy, info->extack) < 0) + continue; + + if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) + continue; + + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) + continue; + + xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); + sa = nla_data(tb[NFSD_A_SOCK_ADDR]); + + xprt = svc_find_listener(serv, xcl_name, net, sa); + if (xprt) { + svc_xprt_put(xprt); + continue; + } + + ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, + SVC_SOCK_ANONYMOUS, + get_current_cred()); + /* always save the latest error */ + if (ret < 0) + err = ret; + } + + if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) + nfsd_destroy_serv(net); + +out_unlock_mtx: + mutex_unlock(&nfsd_mutex); + + return err; +} + +/** + * nfsd_nl_listener_get_doit - get the nfs running listeners + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct svc_xprt *xprt; + struct svc_serv *serv; + struct nfsd_net *nn; + void *hdr; + int err; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_iput(skb, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_free_msg; + } + + mutex_lock(&nfsd_mutex); + nn = net_generic(genl_info_net(info), nfsd_net_id); + + /* no nfs server? Just send empty socket list */ + if (!nn->nfsd_serv) + goto out_unlock_mtx; + + serv = nn->nfsd_serv; + spin_lock_bh(&serv->sv_lock); + list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) { + struct nlattr *attr; + + attr = nla_nest_start(skb, NFSD_A_SERVER_SOCK_ADDR); + if (!attr) { + err = -EINVAL; + goto err_serv_unlock; + } + + if (nla_put_string(skb, NFSD_A_SOCK_TRANSPORT_NAME, + xprt->xpt_class->xcl_name) || + nla_put(skb, NFSD_A_SOCK_ADDR, + sizeof(struct sockaddr_storage), + &xprt->xpt_local)) { + err = -EINVAL; + goto err_serv_unlock; + } + + nla_nest_end(skb, attr); + } + spin_unlock_bh(&serv->sv_lock); +out_unlock_mtx: + mutex_unlock(&nfsd_mutex); + genlmsg_end(skb, hdr); + + return genlmsg_reply(skb, info); + +err_serv_unlock: + spin_unlock_bh(&serv->sv_lock); + mutex_unlock(&nfsd_mutex); +err_free_msg: + nlmsg_free(skb); + + return err; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 7176cd8e6f09..24c86dbc7ed5 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -55,12 +55,29 @@ enum { NFSD_A_SERVER_PROTO_MAX = (__NFSD_A_SERVER_PROTO_MAX - 1) }; +enum { + NFSD_A_SOCK_ADDR = 1, + NFSD_A_SOCK_TRANSPORT_NAME, + + __NFSD_A_SOCK_MAX, + NFSD_A_SOCK_MAX = (__NFSD_A_SOCK_MAX - 1) +}; + +enum { + NFSD_A_SERVER_SOCK_ADDR = 1, + + __NFSD_A_SERVER_SOCK_MAX, + NFSD_A_SERVER_SOCK_MAX = (__NFSD_A_SERVER_SOCK_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, NFSD_CMD_THREADS_GET, NFSD_CMD_VERSION_SET, NFSD_CMD_VERSION_GET, + NFSD_CMD_LISTENER_SET, + NFSD_CMD_LISTENER_GET, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.2.3 From 939cb14d51a150e3c12ef7a8ce0ba04ce6131bd2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 6 May 2024 12:30:05 -0400 Subject: NFS/knfsd: Remove the invalid NFS error 'NFSERR_OPNOTSUPP' NFSERR_OPNOTSUPP is not described by any RFC, and should not be used. Signed-off-by: Trond Myklebust Signed-off-by: Chuck Lever --- fs/nfsd/nfsd.h | 1 - include/trace/misc/nfs.h | 2 -- include/uapi/linux/nfs.h | 1 - 3 files changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 2f6c6f3815b4..8f4f239d9f8a 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -230,7 +230,6 @@ void nfsd_lockd_shutdown(void); #define nfserr_nospc cpu_to_be32(NFSERR_NOSPC) #define nfserr_rofs cpu_to_be32(NFSERR_ROFS) #define nfserr_mlink cpu_to_be32(NFSERR_MLINK) -#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP) #define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG) #define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY) #define nfserr_dquot cpu_to_be32(NFSERR_DQUOT) diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h index e43e74591561..7b221d51133a 100644 --- a/include/trace/misc/nfs.h +++ b/include/trace/misc/nfs.h @@ -28,7 +28,6 @@ TRACE_DEFINE_ENUM(NFSERR_FBIG); TRACE_DEFINE_ENUM(NFSERR_NOSPC); TRACE_DEFINE_ENUM(NFSERR_ROFS); TRACE_DEFINE_ENUM(NFSERR_MLINK); -TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); TRACE_DEFINE_ENUM(NFSERR_DQUOT); @@ -64,7 +63,6 @@ TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); { NFSERR_NOSPC, "NOSPC" }, \ { NFSERR_ROFS, "ROFS" }, \ { NFSERR_MLINK, "MLINK" }, \ - { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ { NFSERR_DQUOT, "DQUOT" }, \ diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index 946cb62d64b0..f356f2ba3814 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -61,7 +61,6 @@ NFSERR_NOSPC = 28, /* v2 v3 v4 */ NFSERR_ROFS = 30, /* v2 v3 v4 */ NFSERR_MLINK = 31, /* v3 v4 */ - NFSERR_OPNOTSUPP = 45, /* v2 v3 */ NFSERR_NAMETOOLONG = 63, /* v2 v3 v4 */ NFSERR_NOTEMPTY = 66, /* v2 v3 v4 */ NFSERR_DQUOT = 69, /* v2 v3 v4 */ -- cgit v1.2.3 From 999cb275c807b92662f8a74fdaee9619700f64a5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 7 May 2024 01:12:08 +0200 Subject: gtp: add IPv6 support Add new iflink attributes to configure in-kernel UDP listener socket address: IFLA_GTP_LOCAL and IFLA_GTP_LOCAL6. If none of these attributes are specified, default is still to IPv4 INADDR_ANY for backward compatibility. Add new attributes to set up family and IPv6 address of GTP tunnels: GTPA_FAMILY, GTPA_PEER_ADDR6 and GTPA_MS_ADDR6. If no GTPA_FAMILY is specified, AF_INET is assumed for backward compatibility. setsockopt IPV6_ADDRFORM allows to downgrade socket from IPv6 to IPv4 after socket is bound. Assumption is that socket listener that is attached to the gtp device needs to be either IPv4 or IPv6. Therefore, GTP socket listener does not allow for IPv4-mapped-IPv6 listener. Signed-off-by: Pablo Neira Ayuso --- drivers/net/gtp.c | 396 ++++++++++++++++++++++++++++++++++++++++--- include/uapi/linux/gtp.h | 3 + include/uapi/linux/if_link.h | 2 + 3 files changed, 374 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 811e4a660636..84ff502a38bc 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -52,9 +53,11 @@ struct pdp_ctx { union { struct in_addr addr; + struct in6_addr addr6; } ms; union { struct in_addr addr; + struct in6_addr addr6; } peer; struct sock *sk; @@ -131,6 +134,11 @@ static inline u32 ipv4_hashfn(__be32 ip) return jhash_1word((__force u32)ip, gtp_h_initval); } +static u32 ipv6_hashfn(const struct in6_addr *ip6) +{ + return jhash(ip6, sizeof(*ip6), gtp_h_initval); +} + /* Resolve a PDP context structure based on the 64bit TID. */ static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid) { @@ -180,6 +188,23 @@ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr) return NULL; } +static struct pdp_ctx *ipv6_pdp_find(struct gtp_dev *gtp, + const struct in6_addr *ms_addr) +{ + struct hlist_head *head; + struct pdp_ctx *pdp; + + head = >p->addr_hash[ipv6_hashfn(ms_addr) % gtp->hash_size]; + + hlist_for_each_entry_rcu(pdp, head, hlist_addr) { + if (pdp->af == AF_INET6 && + memcmp(&pdp->ms.addr6, ms_addr, sizeof(struct in6_addr)) == 0) + return pdp; + } + + return NULL; +} + static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx, unsigned int hdrlen, unsigned int role) { @@ -196,6 +221,28 @@ static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx, return iph->saddr == pctx->ms.addr.s_addr; } +static bool gtp_check_ms_ipv6(struct sk_buff *skb, struct pdp_ctx *pctx, + unsigned int hdrlen, unsigned int role) +{ + struct ipv6hdr *ip6h; + int ret; + + if (!pskb_may_pull(skb, hdrlen + sizeof(struct ipv6hdr))) + return false; + + ip6h = (struct ipv6hdr *)(skb->data + hdrlen); + + if (role == GTP_ROLE_SGSN) { + ret = memcmp(&ip6h->daddr, &pctx->ms.addr6, + sizeof(struct in6_addr)); + } else { + ret = memcmp(&ip6h->saddr, &pctx->ms.addr6, + sizeof(struct in6_addr)); + } + + return ret == 0; +} + /* Check if the inner IP address in this packet is assigned to any * existing mobile subscriber. */ @@ -205,6 +252,8 @@ static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx, switch (ntohs(skb->protocol)) { case ETH_P_IP: return gtp_check_ms_ipv4(skb, pctx, hdrlen, role); + case ETH_P_IPV6: + return gtp_check_ms_ipv6(skb, pctx, hdrlen, role); } return false; } @@ -260,6 +309,27 @@ static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, return ip_route_output_key(sock_net(sk), fl4); } +static struct rt6_info *ip6_route_output_gtp(struct net *net, + struct flowi6 *fl6, + const struct sock *sk, + const struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct dst_entry *dst; + + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_oif = sk->sk_bound_dev_if; + fl6->daddr = *daddr; + fl6->saddr = *saddr; + fl6->flowi6_proto = sk->sk_protocol; + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, fl6, NULL); + if (IS_ERR(dst)) + return ERR_PTR(-ENETUNREACH); + + return (struct rt6_info *)dst; +} + /* GSM TS 09.60. 7.3 * In all Path Management messages: * - TID: is not used and shall be set to 0. @@ -838,12 +908,15 @@ struct gtp_pktinfo { struct sock *sk; union { struct iphdr *iph; + struct ipv6hdr *ip6h; }; union { struct flowi4 fl4; + struct flowi6 fl6; }; union { struct rtable *rt; + struct rt6_info *rt6; }; struct pdp_ctx *pctx; struct net_device *dev; @@ -878,6 +951,20 @@ static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo, pktinfo->dev = dev; } +static void gtp_set_pktinfo_ipv6(struct gtp_pktinfo *pktinfo, + struct sock *sk, struct ipv6hdr *ip6h, + struct pdp_ctx *pctx, struct rt6_info *rt6, + struct flowi6 *fl6, + struct net_device *dev) +{ + pktinfo->sk = sk; + pktinfo->ip6h = ip6h; + pktinfo->pctx = pctx; + pktinfo->rt6 = rt6; + pktinfo->fl6 = *fl6; + pktinfo->dev = dev; +} + static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo) { @@ -959,6 +1046,81 @@ err: return -EBADMSG; } +static int gtp_build_skb_ip6(struct sk_buff *skb, struct net_device *dev, + struct gtp_pktinfo *pktinfo) +{ + struct gtp_dev *gtp = netdev_priv(dev); + struct net *net = gtp->net; + struct dst_entry *dst; + struct pdp_ctx *pctx; + struct ipv6hdr *ip6h; + struct rt6_info *rt; + struct flowi6 fl6; + int mtu; + + /* Read the IP destination address and resolve the PDP context. + * Prepend PDP header with TEI/TID from PDP ctx. + */ + ip6h = ipv6_hdr(skb); + if (gtp->role == GTP_ROLE_SGSN) + pctx = ipv6_pdp_find(gtp, &ip6h->saddr); + else + pctx = ipv6_pdp_find(gtp, &ip6h->daddr); + + if (!pctx) { + netdev_dbg(dev, "no PDP ctx found for %pI6, skip\n", + &ip6h->daddr); + return -ENOENT; + } + netdev_dbg(dev, "found PDP context %p\n", pctx); + + rt = ip6_route_output_gtp(net, &fl6, pctx->sk, &pctx->peer.addr6, + &inet6_sk(pctx->sk)->saddr); + if (IS_ERR(rt)) { + netdev_dbg(dev, "no route to SSGN %pI6\n", + &pctx->peer.addr6); + dev->stats.tx_carrier_errors++; + goto err; + } + dst = &rt->dst; + + if (rt->dst.dev == dev) { + netdev_dbg(dev, "circular route to SSGN %pI6\n", + &pctx->peer.addr6); + dev->stats.collisions++; + goto err_rt; + } + + mtu = dst_mtu(&rt->dst) - dev->hard_header_len - + sizeof(struct ipv6hdr) - sizeof(struct udphdr); + switch (pctx->gtp_version) { + case GTP_V0: + mtu -= sizeof(struct gtp0_header); + break; + case GTP_V1: + mtu -= sizeof(struct gtp1_header); + break; + } + + skb_dst_update_pmtu_no_confirm(skb, mtu); + + if ((!skb_is_gso(skb) && skb->len > mtu) || + (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))) { + netdev_dbg(dev, "packet too big, fragmentation needed\n"); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + goto err_rt; + } + + gtp_set_pktinfo_ipv6(pktinfo, pctx->sk, ip6h, pctx, rt, &fl6, dev); + gtp_push_header(skb, pktinfo); + + return 0; +err_rt: + dst_release(dst); +err: + return -EBADMSG; +} + static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned int proto = ntohs(skb->protocol); @@ -977,6 +1139,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) case ETH_P_IP: err = gtp_build_skb_ip4(skb, dev, &pktinfo); break; + case ETH_P_IPV6: + err = gtp_build_skb_ip6(skb, dev, &pktinfo); + break; default: err = -EOPNOTSUPP; break; @@ -1000,6 +1165,21 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) dev_net(dev)), false); break; + case ETH_P_IPV6: +#if IS_ENABLED(CONFIG_IPV6) + netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI6 dst: %pI6\n", + &pktinfo.ip6h->saddr, &pktinfo.ip6h->daddr); + udp_tunnel6_xmit_skb(&pktinfo.rt6->dst, pktinfo.sk, skb, dev, + &pktinfo.fl6.saddr, &pktinfo.fl6.daddr, + ipv6_get_dsfield(pktinfo.ip6h), + ip6_dst_hoplimit(&pktinfo.rt->dst), + 0, + pktinfo.gtph_port, pktinfo.gtph_port, + false); +#else + goto tx_err; +#endif + break; } return NETDEV_TX_OK; @@ -1057,17 +1237,45 @@ static void gtp_destructor(struct net_device *dev) kfree(gtp->tid_hash); } -static struct sock *gtp_create_sock(int type, struct gtp_dev *gtp) +static int gtp_sock_udp_config(struct udp_port_cfg *udp_conf, + const struct nlattr *nla, int family) +{ + udp_conf->family = family; + + switch (udp_conf->family) { + case AF_INET: + udp_conf->local_ip.s_addr = nla_get_be32(nla); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + udp_conf->local_ip6 = nla_get_in6_addr(nla); + break; +#endif + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static struct sock *gtp_create_sock(int type, struct gtp_dev *gtp, + const struct nlattr *nla, int family) { struct udp_tunnel_sock_cfg tuncfg = {}; - struct udp_port_cfg udp_conf = { - .local_ip.s_addr = htonl(INADDR_ANY), - .family = AF_INET, - }; + struct udp_port_cfg udp_conf = {}; struct net *net = gtp->net; struct socket *sock; int err; + if (nla) { + err = gtp_sock_udp_config(&udp_conf, nla, family); + if (err < 0) + return ERR_PTR(err); + } else { + udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + udp_conf.family = AF_INET; + } + if (type == UDP_ENCAP_GTP0) udp_conf.local_udp_port = htons(GTP0_PORT); else if (type == UDP_ENCAP_GTP1U) @@ -1089,16 +1297,17 @@ static struct sock *gtp_create_sock(int type, struct gtp_dev *gtp) return sock->sk; } -static int gtp_create_sockets(struct gtp_dev *gtp, struct nlattr *data[]) +static int gtp_create_sockets(struct gtp_dev *gtp, const struct nlattr *nla, + int family) { struct sock *sk1u; struct sock *sk0; - sk0 = gtp_create_sock(UDP_ENCAP_GTP0, gtp); + sk0 = gtp_create_sock(UDP_ENCAP_GTP0, gtp, nla, family); if (IS_ERR(sk0)) return PTR_ERR(sk0); - sk1u = gtp_create_sock(UDP_ENCAP_GTP1U, gtp); + sk1u = gtp_create_sock(UDP_ENCAP_GTP1U, gtp, nla, family); if (IS_ERR(sk1u)) { udp_tunnel_sock_release(sk0->sk_socket); return PTR_ERR(sk1u); @@ -1111,6 +1320,9 @@ static int gtp_create_sockets(struct gtp_dev *gtp, struct nlattr *data[]) return 0; } +#define GTP_TH_MAXLEN (sizeof(struct udphdr) + sizeof(struct gtp0_header)) +#define GTP_IPV6_MAXLEN (sizeof(struct ipv6hdr) + GTP_TH_MAXLEN) + static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -1120,6 +1332,11 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, struct gtp_net *gn; int hashsize, err; +#if !IS_ENABLED(CONFIG_IPV6) + if (data[IFLA_GTP_LOCAL6]) + return -EAFNOSUPPORT; +#endif + gtp = netdev_priv(dev); if (!data[IFLA_GTP_PDP_HASHSIZE]) { @@ -1148,13 +1365,24 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - if (data[IFLA_GTP_CREATE_SOCKETS]) - err = gtp_create_sockets(gtp, data); - else + if (data[IFLA_GTP_CREATE_SOCKETS]) { + if (data[IFLA_GTP_LOCAL6]) + err = gtp_create_sockets(gtp, data[IFLA_GTP_LOCAL6], AF_INET6); + else + err = gtp_create_sockets(gtp, data[IFLA_GTP_LOCAL], AF_INET); + } else { err = gtp_encap_enable(gtp, data); + } + if (err < 0) goto out_hashtable; + if ((gtp->sk0 && gtp->sk0->sk_family == AF_INET6) || + (gtp->sk1u && gtp->sk1u->sk_family == AF_INET6)) { + dev->mtu = ETH_DATA_LEN - GTP_IPV6_MAXLEN; + dev->needed_headroom = LL_MAX_HEADER + GTP_IPV6_MAXLEN; + } + err = register_netdevice(dev); if (err < 0) { netdev_dbg(dev, "failed to register new netdev %d\n", err); @@ -1199,6 +1427,8 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_ROLE] = { .type = NLA_U32 }, [IFLA_GTP_CREATE_SOCKETS] = { .type = NLA_U8 }, [IFLA_GTP_RESTART_COUNT] = { .type = NLA_U8 }, + [IFLA_GTP_LOCAL] = { .type = NLA_U32 }, + [IFLA_GTP_LOCAL6] = { .len = sizeof(struct in6_addr) }, }; static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1298,6 +1528,12 @@ static struct sock *gtp_encap_enable_socket(int fd, int type, goto out_sock; } + if (sk->sk_family == AF_INET6 && + !sk->sk_ipv6only) { + sk = ERR_PTR(-EADDRNOTAVAIL); + goto out_sock; + } + lock_sock(sk); if (sk->sk_user_data) { sk = ERR_PTR(-EBUSY); @@ -1349,6 +1585,13 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) gtp->sk0 = sk0; gtp->sk1u = sk1u; + if (sk0 && sk1u && + sk0->sk_family != sk1u->sk_family) { + gtp_encap_disable_sock(sk0); + gtp_encap_disable_sock(sk1u); + return -EINVAL; + } + return 0; } @@ -1378,14 +1621,9 @@ static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[]) return gtp; } -static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) +static void gtp_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) { pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]); - pctx->af = AF_INET; - pctx->peer.addr.s_addr = - nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]); - pctx->ms.addr.s_addr = - nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); switch (pctx->gtp_version) { case GTP_V0: @@ -1405,21 +1643,78 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } +static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) +{ + pctx->peer.addr.s_addr = + nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]); + pctx->ms.addr.s_addr = + nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); + gtp_pdp_fill(pctx, info); +} + +static void ipv6_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) +{ + pctx->peer.addr6 = nla_get_in6_addr(info->attrs[GTPA_PEER_ADDR6]); + pctx->ms.addr6 = nla_get_in6_addr(info->attrs[GTPA_MS_ADDR6]); + gtp_pdp_fill(pctx, info); +} + static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, struct genl_info *info) { struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; + struct in6_addr ms_addr6; unsigned int version; bool found = false; __be32 ms_addr; + int family; - ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); - hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size; version = nla_get_u32(info->attrs[GTPA_VERSION]); - pctx = ipv4_pdp_find(gtp, ms_addr); + if (info->attrs[GTPA_FAMILY]) + family = nla_get_u8(info->attrs[GTPA_FAMILY]); + else + family = AF_INET; + +#if !IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + return ERR_PTR(-EAFNOSUPPORT); +#endif + + if ((info->attrs[GTPA_PEER_ADDRESS] && + sk->sk_family == AF_INET6) || + (info->attrs[GTPA_PEER_ADDR6] && + sk->sk_family == AF_INET)) + return ERR_PTR(-EAFNOSUPPORT); + + switch (family) { + case AF_INET: + if (!info->attrs[GTPA_MS_ADDRESS] || + !info->attrs[GTPA_PEER_ADDRESS] || + info->attrs[GTPA_MS_ADDR6] || + info->attrs[GTPA_PEER_ADDR6]) + return ERR_PTR(-EINVAL); + + ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); + hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size; + pctx = ipv4_pdp_find(gtp, ms_addr); + break; + case AF_INET6: + if (!info->attrs[GTPA_MS_ADDR6] || + !info->attrs[GTPA_PEER_ADDR6] || + info->attrs[GTPA_MS_ADDRESS] || + info->attrs[GTPA_PEER_ADDRESS]) + return ERR_PTR(-EINVAL); + + ms_addr6 = nla_get_in6_addr(info->attrs[GTPA_MS_ADDR6]); + hash_ms = ipv6_hashfn(&ms_addr6) % gtp->hash_size; + pctx = ipv6_pdp_find(gtp, &ms_addr6); + break; + default: + return ERR_PTR(-EAFNOSUPPORT); + } if (pctx) found = true; if (version == GTP_V0) @@ -1442,7 +1737,14 @@ static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, if (!pctx) pctx = pctx_tid; - ipv4_pdp_fill(pctx, info); + switch (pctx->af) { + case AF_INET: + ipv4_pdp_fill(pctx, info); + break; + case AF_INET6: + ipv6_pdp_fill(pctx, info); + break; + } if (pctx->gtp_version == GTP_V0) netdev_dbg(dev, "GTPv0-U: update tunnel id = %llx (pdp %p)\n", @@ -1462,7 +1764,30 @@ static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, sock_hold(sk); pctx->sk = sk; pctx->dev = gtp->dev; - ipv4_pdp_fill(pctx, info); + pctx->af = family; + + switch (pctx->af) { + case AF_INET: + if (!info->attrs[GTPA_MS_ADDRESS] || + !info->attrs[GTPA_PEER_ADDRESS]) { + sock_put(sk); + kfree(pctx); + return ERR_PTR(-EINVAL); + } + + ipv4_pdp_fill(pctx, info); + break; + case AF_INET6: + if (!info->attrs[GTPA_MS_ADDR6] || + !info->attrs[GTPA_PEER_ADDR6]) { + sock_put(sk); + kfree(pctx); + return ERR_PTR(-EINVAL); + } + + ipv6_pdp_fill(pctx, info); + break; + } atomic_set(&pctx->tx_seq, 0); switch (pctx->gtp_version) { @@ -1524,9 +1849,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) int err; if (!info->attrs[GTPA_VERSION] || - !info->attrs[GTPA_LINK] || - !info->attrs[GTPA_PEER_ADDRESS] || - !info->attrs[GTPA_MS_ADDRESS]) + !info->attrs[GTPA_LINK]) return -EINVAL; version = nla_get_u32(info->attrs[GTPA_VERSION]); @@ -1593,6 +1916,10 @@ static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net, __be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]); return ipv4_pdp_find(gtp, ip); + } else if (nla[GTPA_MS_ADDR6]) { + struct in6_addr addr = nla_get_in6_addr(nla[GTPA_MS_ADDR6]); + + return ipv6_pdp_find(gtp, &addr); } else if (nla[GTPA_VERSION]) { u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]); @@ -1663,10 +1990,22 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) || nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) || - nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer.addr.s_addr) || - nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms.addr.s_addr)) + nla_put_u8(skb, GTPA_FAMILY, pctx->af)) goto nla_put_failure; + switch (pctx->af) { + case AF_INET: + if (nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer.addr.s_addr) || + nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms.addr.s_addr)) + goto nla_put_failure; + break; + case AF_INET6: + if (nla_put_in6_addr(skb, GTPA_PEER_ADDR6, &pctx->peer.addr6) || + nla_put_in6_addr(skb, GTPA_MS_ADDR6, &pctx->ms.addr6)) + goto nla_put_failure; + break; + } + switch (pctx->gtp_version) { case GTP_V0: if (nla_put_u64_64bit(skb, GTPA_TID, pctx->u.v0.tid, GTPA_PAD) || @@ -1893,6 +2232,9 @@ static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = { [GTPA_NET_NS_FD] = { .type = NLA_U32, }, [GTPA_I_TEI] = { .type = NLA_U32, }, [GTPA_O_TEI] = { .type = NLA_U32, }, + [GTPA_PEER_ADDR6] = { .len = sizeof(struct in6_addr), }, + [GTPA_MS_ADDR6] = { .len = sizeof(struct in6_addr), }, + [GTPA_FAMILY] = { .type = NLA_U8, }, }; static const struct genl_small_ops gtp_genl_ops[] = { diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 3dcdb9e33cba..40f5388d6de0 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -31,6 +31,9 @@ enum gtp_attrs { GTPA_I_TEI, /* for GTPv1 only */ GTPA_O_TEI, /* for GTPv1 only */ GTPA_PAD, + GTPA_PEER_ADDR6, + GTPA_MS_ADDR6, + GTPA_FAMILY, __GTPA_MAX, }; #define GTPA_MAX (__GTPA_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e9f10860ec8e..6dc258993b17 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1466,6 +1466,8 @@ enum { IFLA_GTP_ROLE, IFLA_GTP_CREATE_SOCKETS, IFLA_GTP_RESTART_COUNT, + IFLA_GTP_LOCAL, + IFLA_GTP_LOCAL6, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From 651d61bc8b7d8bb622cfc24be2ee92eebb4ed3cc Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Tue, 11 Apr 2023 15:44:46 +0930 Subject: KVM: PPC: Fix documentation for ppc mmu caps The documentation mentions KVM_CAP_PPC_RADIX_MMU, but the defines in the kvm headers spell it KVM_CAP_PPC_MMU_RADIX. Similarly with KVM_CAP_PPC_MMU_HASH_V3. Fixes: c92701322711 ("KVM: PPC: Book3S HV: Add userspace interfaces for POWER9 MMU") Signed-off-by: Joel Stanley Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman Link: https://msgid.link/20230411061446.26324-1-joel@jms.id.au --- Documentation/virt/kvm/api.rst | 8 ++++---- include/uapi/linux/kvm.h | 4 ++-- tools/include/uapi/linux/kvm.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0b5a33ee71ee..636e6794828f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4300,7 +4300,7 @@ operating system that uses the PIT for timing (e.g. Linux 2.4.x). 4.100 KVM_PPC_CONFIGURE_V3_MMU ------------------------------ -:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 +:Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 :Architectures: ppc :Type: vm ioctl :Parameters: struct kvm_ppc_mmuv3_cfg (in) @@ -4334,7 +4334,7 @@ the Power ISA V3.00, Book III section 5.7.6.1. 4.101 KVM_PPC_GET_RMMU_INFO --------------------------- -:Capability: KVM_CAP_PPC_RADIX_MMU +:Capability: KVM_CAP_PPC_MMU_RADIX :Architectures: ppc :Type: vm ioctl :Parameters: struct kvm_ppc_rmmu_info (out) @@ -8095,7 +8095,7 @@ capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this will disable the use of APIC hardware virtualization even if supported by the CPU, as it's incompatible with SynIC auto-EOI behavior. -8.3 KVM_CAP_PPC_RADIX_MMU +8.3 KVM_CAP_PPC_MMU_RADIX ------------------------- :Architectures: ppc @@ -8105,7 +8105,7 @@ available, means that the kernel can support guests using the radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 processor). -8.4 KVM_CAP_PPC_HASH_MMU_V3 +8.4 KVM_CAP_PPC_MMU_HASH_V3 --------------------------- :Architectures: ppc diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2190adbe3002..d03842abae57 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1221,9 +1221,9 @@ struct kvm_vfio_spapr_tce { /* Available with KVM_CAP_SPAPR_RESIZE_HPT */ #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) #define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) -/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */ #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) -/* Available with KVM_CAP_PPC_RADIX_MMU */ +/* Available with KVM_CAP_PPC_MMU_RADIX */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* Available with KVM_CAP_PPC_GET_CPU_CHAR */ #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c3308536482b..4b6b635b8bd1 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1502,7 +1502,7 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_SPAPR_RESIZE_HPT */ #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) #define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) -/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_MMU_HASH_V3 */ #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) /* Available with KVM_CAP_PPC_RADIX_MMU */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) -- cgit v1.2.3 From 6d305cbef1aa01b9714e01e35f3d5c28544cf04d Mon Sep 17 00:00:00 2001 From: Erick Archer Date: Tue, 7 May 2024 19:33:18 +0200 Subject: uapi: stddef.h: Provide UAPI macros for __counted_by_{le, be} This commit can be considered an addition to commit ca7e324e8ad3 ("compiler_types: add Endianness-dependent __counted_by_{le,be}") [1]. In the commit referenced above the __counted_by_{le,be}() attributes were defined based on platform's endianness with the goal to that the structures contain flexible arrays at the end, and the counter for, can be annotated with these attributes. So, this commit only provide UAPI macros for UAPI structs that will gain annotations for __counted_by_{le, be} attributes. And it is the previous step to be able to use these attributes in UAPI. Link: https://lore.kernel.org/r/20240327142241.1745989-2-aleksander.lobakin@intel.com Suggested-by: Sven Eckelmann Signed-off-by: Erick Archer Link: https://lore.kernel.org/r/AS8PR02MB72372E45071E8821C07236F78BE42@AS8PR02MB7237.eurprd02.prod.outlook.com Fixes: ca7e324e8ad3 ("compiler_types: add Endianness-dependent __counted_by_{le,be}") Signed-off-by: Kees Cook --- include/uapi/linux/stddef.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 2ec6f35cda32..58154117d9b0 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -55,4 +55,12 @@ #define __counted_by(m) #endif +#ifndef __counted_by_le +#define __counted_by_le(m) +#endif + +#ifndef __counted_by_be +#define __counted_by_be(m) +#endif + #endif /* _UAPI_LINUX_STDDEF_H */ -- cgit v1.2.3 From b1956e2d0713e210a56ae65ad3488ae36f833e76 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 2 May 2024 09:57:32 -0700 Subject: PCI/CXL: Fail bus reset if upstream CXL Port has SBR masked Per CXL spec r3.1, sec 8.1.5.2, the Secondary Bus Reset (SBR) bit in the Bridge Control register of a CXL port has no effect unless the "Unmask SBR" bit is set. Return -ENOTTY if we attempt a bus reset on a device below a CXL Port where "Unmask SBR" is 0. Otherwise, the bus reset would appear to have succeeded even though setting the bridge SBR bit had no effect. Link: https://lore.kernel.org/linux-cxl/20240220203956.GA1502351@bhelgaas/ Link: https://lore.kernel.org/r/20240502165851.1948523-4-dave.jiang@intel.com Signed-off-by: Dave Jiang [bhelgaas: simplify commit log and comments] Signed-off-by: Bjorn Helgaas Reviewed-by: Jonathan Cameron Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Dan Williams --- drivers/pci/pci.c | 42 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pci_regs.h | 5 +++++ 2 files changed, 47 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c63142352844..225cec964f25 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4928,10 +4928,52 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, bool probe) return pci_reset_hotplug_slot(dev->slot->hotplug, probe); } +static u16 cxl_port_dvsec(struct pci_dev *dev) +{ + return pci_find_dvsec_capability(dev, PCI_VENDOR_ID_CXL, + PCI_DVSEC_CXL_PORT); +} + +static bool cxl_sbr_masked(struct pci_dev *dev) +{ + u16 dvsec, reg; + int rc; + + dvsec = cxl_port_dvsec(dev); + if (!dvsec) + return false; + + rc = pci_read_config_word(dev, dvsec + PCI_DVSEC_CXL_PORT_CTL, ®); + if (rc || PCI_POSSIBLE_ERROR(reg)) + return false; + + /* + * Per CXL spec r3.1, sec 8.1.5.2, when "Unmask SBR" is 0, the SBR + * bit in Bridge Control has no effect. When 1, the Port generates + * hot reset when the SBR bit is set to 1. + */ + if (reg & PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR) + return false; + + return true; +} + static int pci_reset_bus_function(struct pci_dev *dev, bool probe) { + struct pci_dev *bridge = pci_upstream_bridge(dev); int rc; + /* + * If "dev" is below a CXL port that has SBR control masked, SBR + * won't do anything, so return error. + */ + if (bridge && cxl_sbr_masked(bridge)) { + if (probe) + return 0; + + return -ENOTTY; + } + rc = pci_dev_reset_slot_function(dev, probe); if (rc != -ENOTTY) return rc; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index a39193213ff2..6024eb2e9a2f 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1148,4 +1148,9 @@ #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000 +/* Compute Express Link (CXL r3.1, sec 8.1.5) */ +#define PCI_DVSEC_CXL_PORT 3 +#define PCI_DVSEC_CXL_PORT_CTL 0x0c +#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From e2f48c48090dea172c0c571101041de64634dae5 Mon Sep 17 00:00:00 2001 From: Petr Vorel Date: Tue, 7 May 2024 17:37:57 +0200 Subject: bcachefs: Move BCACHEFS_STATFS_MAGIC value to UAPI magic.h Move BCACHEFS_STATFS_MAGIC value to UAPI under BCACHEFS_SUPER_MAGIC definition (use common approach for name) and reuse the definition in bcachefs_format.h BCACHEFS_STATFS_MAGIC. There are other bcachefs magic definitions: BCACHE_MAGIC, BCHFS_MAGIC, which use UUID_INIT() and are used only in libbcachefs. Therefore move only BCACHEFS_STATFS_MAGIC value, which can be used outside of libbcachefs for f_type field in struct statfs in statfs() or fstatfs(). Suggested-by: Su Yue Signed-off-by: Petr Vorel Acked-by: Brian Foster Signed-off-by: Kent Overstreet --- fs/bcachefs/bcachefs_format.h | 3 ++- include/uapi/linux/magic.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index d5b90439e581..1bebba881d89 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -76,6 +76,7 @@ #include #include #include +#include #include "vstructs.h" #ifdef __KERNEL__ @@ -1290,7 +1291,7 @@ enum bch_compression_opts { UUID_INIT(0xc68573f6, 0x66ce, 0x90a9, \ 0xd9, 0x6a, 0x60, 0xcf, 0x80, 0x3d, 0xf7, 0xef) -#define BCACHEFS_STATFS_MAGIC 0xca451a4e +#define BCACHEFS_STATFS_MAGIC BCACHEFS_SUPER_MAGIC #define JSET_MAGIC __cpu_to_le64(0x245235c1a3625032ULL) #define BSET_MAGIC __cpu_to_le64(0x90135c78b99e07f5ULL) diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 1b40a968ba91..bb575f3ab45e 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -37,6 +37,7 @@ #define HOSTFS_SUPER_MAGIC 0x00c0ffee #define OVERLAYFS_SUPER_MAGIC 0x794c7630 #define FUSE_SUPER_MAGIC 0x65735546 +#define BCACHEFS_SUPER_MAGIC 0xca451a4e #define MINIX_SUPER_MAGIC 0x137F /* minix v1 fs, 14 char names */ #define MINIX_SUPER_MAGIC2 0x138F /* minix v1 fs, 30 char names */ -- cgit v1.2.3 From 7dcc758cca432510f77b2fe1077be2314bc3785b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 May 2024 14:06:15 -0600 Subject: io_uring/net: add IORING_ACCEPT_DONTWAIT flag This allows the caller to perform a non-blocking attempt, similarly to how recvmsg has MSG_DONTWAIT. If set, and we get -EAGAIN on a connection attempt, propagate the result to userspace rather than arm poll and wait for a retry. Suggested-by: Norman Maurer Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 15 +++++++++------ 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f093cb2300d9..4a645d15516f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -379,6 +379,7 @@ enum io_uring_op { * accept flags stored in sqe->ioprio */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +#define IORING_ACCEPT_DONTWAIT (1U << 1) /* * IORING_OP_MSG_RING command types, stored in sqe->addr diff --git a/io_uring/net.c b/io_uring/net.c index b0bf8471ecb7..7861bc8fe8b1 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -28,6 +28,7 @@ struct io_accept { struct sockaddr __user *addr; int __user *addr_len; int flags; + int iou_flags; u32 file_slot; unsigned long nofile; }; @@ -1489,7 +1490,6 @@ void io_sendrecv_fail(struct io_kiocb *req) int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = io_kiocb_to_cmd(req, struct io_accept); - unsigned flags; if (sqe->len || sqe->buf_index) return -EINVAL; @@ -1498,15 +1498,15 @@ int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); - flags = READ_ONCE(sqe->ioprio); - if (flags & ~IORING_ACCEPT_MULTISHOT) + accept->iou_flags = READ_ONCE(sqe->ioprio); + if (accept->iou_flags & ~(IORING_ACCEPT_MULTISHOT | IORING_ACCEPT_DONTWAIT)) return -EINVAL; accept->file_slot = READ_ONCE(sqe->file_index); if (accept->file_slot) { if (accept->flags & SOCK_CLOEXEC) return -EINVAL; - if (flags & IORING_ACCEPT_MULTISHOT && + if (accept->iou_flags & IORING_ACCEPT_MULTISHOT && accept->file_slot != IORING_FILE_INDEX_ALLOC) return -EINVAL; } @@ -1514,8 +1514,10 @@ int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - if (flags & IORING_ACCEPT_MULTISHOT) + if (accept->iou_flags & IORING_ACCEPT_MULTISHOT) req->flags |= REQ_F_APOLL_MULTISHOT; + if (accept->iou_flags & IORING_ACCEPT_DONTWAIT) + req->flags |= REQ_F_NOWAIT; return 0; } @@ -1540,7 +1542,8 @@ retry: if (!fixed) put_unused_fd(fd); ret = PTR_ERR(file); - if (ret == -EAGAIN && force_nonblock) { + if (ret == -EAGAIN && force_nonblock && + !(accept->iou_flags & IORING_ACCEPT_DONTWAIT)) { /* * if it's multishot and polled, we don't need to * return EAGAIN to arm the poll infra since it -- cgit v1.2.3 From d3da8e98592693811c14c31f05380f378411fea1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 8 May 2024 08:17:50 -0600 Subject: io_uring/net: add IORING_ACCEPT_POLL_FIRST flag Similarly to how polling first is supported for receive, it makes sense to provide the same for accept. An accept operation does a lot of expensive setup, like allocating an fd, a socket/inode, etc. If no connection request is already pending, this is wasted and will just be cleaned up and freed, only to retry via the usual poll trigger. Add IORING_ACCEPT_POLL_FIRST, which tells accept to only initiate the accept request if poll says we have something to accept. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 9 ++++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4a645d15516f..6dbac55f8686 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -380,6 +380,7 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) #define IORING_ACCEPT_DONTWAIT (1U << 1) +#define IORING_ACCEPT_POLL_FIRST (1U << 2) /* * IORING_OP_MSG_RING command types, stored in sqe->addr diff --git a/io_uring/net.c b/io_uring/net.c index 7861bc8fe8b1..070dea9a4eda 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1487,6 +1487,9 @@ void io_sendrecv_fail(struct io_kiocb *req) req->cqe.flags |= IORING_CQE_F_MORE; } +#define ACCEPT_FLAGS (IORING_ACCEPT_MULTISHOT | IORING_ACCEPT_DONTWAIT | \ + IORING_ACCEPT_POLL_FIRST) + int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = io_kiocb_to_cmd(req, struct io_accept); @@ -1499,7 +1502,7 @@ int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); accept->iou_flags = READ_ONCE(sqe->ioprio); - if (accept->iou_flags & ~(IORING_ACCEPT_MULTISHOT | IORING_ACCEPT_DONTWAIT)) + if (accept->iou_flags & ~ACCEPT_FLAGS) return -EINVAL; accept->file_slot = READ_ONCE(sqe->file_index); @@ -1530,6 +1533,10 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; + if (!(req->flags & REQ_F_POLLED) && + accept->iou_flags & IORING_ACCEPT_POLL_FIRST) + return -EAGAIN; + retry: if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); -- cgit v1.2.3 From c62b758bae6af16fee94f556091fa74883a96b1e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 9 May 2024 13:04:24 +0200 Subject: fcntl: add F_DUPFD_QUERY fcntl() Often userspace needs to know whether two file descriptors refer to the same struct file. For example, systemd uses this to filter out duplicate file descriptors in it's file descriptor store (cf. [1]) and vulkan uses it to compare dma-buf fds (cf. [2]). The only api we provided for this was kcmp() but that's not generally available or might be disallowed because it is way more powerful (allows ordering of file pointers, operates on non-current task) etc. So give userspace a simple way of comparing two file descriptors for sameness adding a new fcntl() F_DUDFD_QUERY. Link: https://github.com/systemd/systemd/blob/a4f0e0da3573a10bc5404142be8799418760b1d1/src/basic/fd-util.c#L517 [1] Link: https://gitlab.freedesktop.org/wlroots/wlroots/-/blob/master/render/vulkan/texture.c#L490 [2] Signed-off-by: Linus Torvalds [brauner: commit message] Signed-off-by: Christian Brauner --- fs/fcntl.c | 20 ++++++++++++++++++++ include/uapi/linux/fcntl.h | 14 ++++++++------ 2 files changed, 28 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fcntl.c b/fs/fcntl.c index 54cc85d3338e..300e5d9ad913 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -327,6 +327,22 @@ static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, return 0; } +/* Is the file descriptor a dup of the file? */ +static long f_dupfd_query(int fd, struct file *filp) +{ + CLASS(fd_raw, f)(fd); + + /* + * We can do the 'fdput()' immediately, as the only thing that + * matters is the pointer value which isn't changed by the fdput. + * + * Technically we didn't need a ref at all, and 'fdget()' was + * overkill, but given our lockless file pointer lookup, the + * alternatives are complicated. + */ + return f.file == filp; +} + static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { @@ -342,6 +358,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; + case F_DUPFD_QUERY: + err = f_dupfd_query(argi, filp); + break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; @@ -446,6 +465,7 @@ static int check_fcntl_cmd(unsigned cmd) switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: + case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 282e90aeb163..c0bcc185fa48 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -8,6 +8,14 @@ #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) +/* + * Request nofications on a directory. + * See below for events that may be notified. + */ +#define F_NOTIFY (F_LINUX_SPECIFIC_BASE + 2) + +#define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3) + /* * Cancel a blocking posix lock; internal use only until we expose an * asynchronous lock api to userspace: @@ -17,12 +25,6 @@ /* Create a file descriptor with FD_CLOEXEC set. */ #define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6) -/* - * Request nofications on a directory. - * See below for events that may be notified. - */ -#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2) - /* * Set and get of pipe page size array */ -- cgit v1.2.3 From deb1e496a83557896fe0cca0b8af01c2a97c0dc6 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 10 May 2024 11:50:28 +0800 Subject: io_uring: support to inject result for NOP Support to inject result for NOP so that we can inject failure from userspace. It is very helpful for covering failure handling code in io_uring core change. With nop flags, it becomes possible to add more test features on NOP in future. Suggested-by: Jens Axboe Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20240510035031.78874-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ io_uring/nop.c | 26 +++++++++++++++++++++----- 2 files changed, 29 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6dbac55f8686..994bf7af0efe 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -72,6 +72,7 @@ struct io_uring_sqe { __u32 waitid_flags; __u32 futex_flags; __u32 install_fd_flags; + __u32 nop_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -407,6 +408,13 @@ enum io_uring_msg_ring_flags { */ #define IORING_FIXED_FD_NO_CLOEXEC (1U << 0) +/* + * IORING_OP_NOP flags (sqe->nop_flags) + * + * IORING_NOP_INJECT_RESULT Inject result from sqe->result + */ +#define IORING_NOP_INJECT_RESULT (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ diff --git a/io_uring/nop.c b/io_uring/nop.c index 1a4e312dfe51..a5bcf3d6984f 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -10,18 +10,34 @@ #include "io_uring.h" #include "nop.h" +struct io_nop { + /* NOTE: kiocb has the file as the first member, so don't do it here */ + struct file *file; + int result; +}; + int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (READ_ONCE(sqe->rw_flags)) + unsigned int flags; + struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); + + flags = READ_ONCE(sqe->nop_flags); + if (flags & ~IORING_NOP_INJECT_RESULT) return -EINVAL; + + if (flags & IORING_NOP_INJECT_RESULT) + nop->result = READ_ONCE(sqe->len); + else + nop->result = 0; return 0; } -/* - * IORING_OP_NOP just posts a completion event, nothing else. - */ int io_nop(struct io_kiocb *req, unsigned int issue_flags) { - io_req_set_res(req, 0, 0); + struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); + + if (nop->result < 0) + req_set_fail(req); + io_req_set_res(req, nop->result, 0); return IOU_OK; } -- cgit v1.2.3 From b25f7415eb4108aa32dd3e74289d7f997090708f Mon Sep 17 00:00:00 2001 From: Günther Noack Date: Fri, 19 Apr 2024 16:11:12 +0000 Subject: landlock: Add IOCTL access right for character and block devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduces the LANDLOCK_ACCESS_FS_IOCTL_DEV right and increments the Landlock ABI version to 5. This access right applies to device-custom IOCTL commands when they are invoked on block or character device files. Like the truncate right, this right is associated with a file descriptor at the time of open(2), and gets respected even when the file descriptor is used outside of the thread which it was originally opened in. Therefore, a newly enabled Landlock policy does not apply to file descriptors which are already open. If the LANDLOCK_ACCESS_FS_IOCTL_DEV right is handled, only a small number of safe IOCTL commands will be permitted on newly opened device files. These include FIOCLEX, FIONCLEX, FIONBIO and FIOASYNC, as well as other IOCTL commands for regular files which are implemented in fs/ioctl.c. Noteworthy scenarios which require special attention: TTY devices are often passed into a process from the parent process, and so a newly enabled Landlock policy does not retroactively apply to them automatically. In the past, TTY devices have often supported IOCTL commands like TIOCSTI and some TIOCLINUX subcommands, which were letting callers control the TTY input buffer (and simulate keypresses). This should be restricted to CAP_SYS_ADMIN programs on modern kernels though. Known limitations: The LANDLOCK_ACCESS_FS_IOCTL_DEV access right is a coarse-grained control over IOCTL commands. Landlock users may use path-based restrictions in combination with their knowledge about the file system layout to control what IOCTLs can be done. Cc: Paul Moore Cc: Christian Brauner Cc: Arnd Bergmann Signed-off-by: Günther Noack Link: https://lore.kernel.org/r/20240419161122.2023765-2-gnoack@google.com Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 38 ++++- security/landlock/fs.c | 225 ++++++++++++++++++++++++++- security/landlock/limits.h | 2 +- security/landlock/syscalls.c | 2 +- tools/testing/selftests/landlock/base_test.c | 2 +- tools/testing/selftests/landlock/fs_test.c | 5 +- 6 files changed, 258 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 25c8d7677539..68625e728f43 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -128,7 +128,7 @@ struct landlock_net_port_attr { * files and directories. Files or directories opened before the sandboxing * are not subject to these restrictions. * - * A file can only receive these access rights: + * The following access rights apply only to files: * * - %LANDLOCK_ACCESS_FS_EXECUTE: Execute a file. * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. Note that @@ -138,12 +138,13 @@ struct landlock_net_port_attr { * - %LANDLOCK_ACCESS_FS_READ_FILE: Open a file with read access. * - %LANDLOCK_ACCESS_FS_TRUNCATE: Truncate a file with :manpage:`truncate(2)`, * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with - * ``O_TRUNC``. Whether an opened file can be truncated with - * :manpage:`ftruncate(2)` is determined during :manpage:`open(2)`, in the - * same way as read and write permissions are checked during - * :manpage:`open(2)` using %LANDLOCK_ACCESS_FS_READ_FILE and - * %LANDLOCK_ACCESS_FS_WRITE_FILE. This access right is available since the - * third version of the Landlock ABI. + * ``O_TRUNC``. This access right is available since the third version of the + * Landlock ABI. + * + * Whether an opened file can be truncated with :manpage:`ftruncate(2)` or used + * with `ioctl(2)` is determined during :manpage:`open(2)`, in the same way as + * read and write permissions are checked during :manpage:`open(2)` using + * %LANDLOCK_ACCESS_FS_READ_FILE and %LANDLOCK_ACCESS_FS_WRITE_FILE. * * A directory can receive access rights related to files or directories. The * following access right is applied to the directory itself, and the @@ -198,13 +199,33 @@ struct landlock_net_port_attr { * If multiple requirements are not met, the ``EACCES`` error code takes * precedence over ``EXDEV``. * + * The following access right applies both to files and directories: + * + * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened + * character or block device. + * + * This access right applies to all `ioctl(2)` commands implemented by device + * drivers. However, the following common IOCTL commands continue to be + * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: + * + * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), + * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), + * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, + * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) + * * Some IOCTL commands which do not make sense when used with devices, but + * whose implementations are safe and return the right error codes + * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) + * + * This access right is available since the fifth version of the Landlock + * ABI. + * * .. warning:: * * It is currently not possible to restrict some file-related actions * accessible through these syscall families: :manpage:`chdir(2)`, * :manpage:`stat(2)`, :manpage:`flock(2)`, :manpage:`chmod(2)`, * :manpage:`chown(2)`, :manpage:`setxattr(2)`, :manpage:`utime(2)`, - * :manpage:`ioctl(2)`, :manpage:`fcntl(2)`, :manpage:`access(2)`. + * :manpage:`fcntl(2)`, :manpage:`access(2)`. * Future Landlock evolutions will enable to restrict them. */ /* clang-format off */ @@ -223,6 +244,7 @@ struct landlock_net_port_attr { #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) #define LANDLOCK_ACCESS_FS_REFER (1ULL << 13) #define LANDLOCK_ACCESS_FS_TRUNCATE (1ULL << 14) +#define LANDLOCK_ACCESS_FS_IOCTL_DEV (1ULL << 15) /* clang-format on */ /** diff --git a/security/landlock/fs.c b/security/landlock/fs.c index c15559432d3d..22d8b7c28074 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -5,8 +5,11 @@ * Copyright © 2016-2020 Mickaël Salaün * Copyright © 2018-2020 ANSSI * Copyright © 2021-2022 Microsoft Corporation + * Copyright © 2022 Günther Noack + * Copyright © 2023-2024 Google LLC */ +#include #include #include #include @@ -14,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -29,6 +33,7 @@ #include #include #include +#include #include #include "common.h" @@ -84,6 +89,160 @@ static const struct landlock_object_underops landlock_fs_underops = { .release = release_inode }; +/* IOCTL helpers */ + +/** + * is_masked_device_ioctl - Determine whether an IOCTL command is always + * permitted with Landlock for device files. These commands can not be + * restricted on device files by enforcing a Landlock policy. + * + * @cmd: The IOCTL command that is supposed to be run. + * + * By default, any IOCTL on a device file requires the + * LANDLOCK_ACCESS_FS_IOCTL_DEV right. However, we blanket-permit some + * commands, if: + * + * 1. The command is implemented in fs/ioctl.c's do_vfs_ioctl(), + * not in f_ops->unlocked_ioctl() or f_ops->compat_ioctl(). + * + * 2. The command is harmless when invoked on devices. + * + * We also permit commands that do not make sense for devices, but where the + * do_vfs_ioctl() implementation returns a more conventional error code. + * + * Any new IOCTL commands that are implemented in fs/ioctl.c's do_vfs_ioctl() + * should be considered for inclusion here. + * + * Returns: true if the IOCTL @cmd can not be restricted with Landlock for + * device files. + */ +static __attribute_const__ bool is_masked_device_ioctl(const unsigned int cmd) +{ + switch (cmd) { + /* + * FIOCLEX, FIONCLEX, FIONBIO and FIOASYNC manipulate the FD's + * close-on-exec and the file's buffered-IO and async flags. These + * operations are also available through fcntl(2), and are + * unconditionally permitted in Landlock. + */ + case FIOCLEX: + case FIONCLEX: + case FIONBIO: + case FIOASYNC: + /* + * FIOQSIZE queries the size of a regular file, directory, or link. + * + * We still permit it, because it always returns -ENOTTY for + * other file types. + */ + case FIOQSIZE: + /* + * FIFREEZE and FITHAW freeze and thaw the file system which the + * given file belongs to. Requires CAP_SYS_ADMIN. + * + * These commands operate on the file system's superblock rather + * than on the file itself. The same operations can also be + * done through any other file or directory on the same file + * system, so it is safe to permit these. + */ + case FIFREEZE: + case FITHAW: + /* + * FS_IOC_FIEMAP queries information about the allocation of + * blocks within a file. + * + * This IOCTL command only makes sense for regular files and is + * not implemented by devices. It is harmless to permit. + */ + case FS_IOC_FIEMAP: + /* + * FIGETBSZ queries the file system's block size for a file or + * directory. + * + * This command operates on the file system's superblock rather + * than on the file itself. The same operation can also be done + * through any other file or directory on the same file system, + * so it is safe to permit it. + */ + case FIGETBSZ: + /* + * FICLONE, FICLONERANGE and FIDEDUPERANGE make files share + * their underlying storage ("reflink") between source and + * destination FDs, on file systems which support that. + * + * These IOCTL commands only apply to regular files + * and are harmless to permit for device files. + */ + case FICLONE: + case FICLONERANGE: + case FIDEDUPERANGE: + /* + * FS_IOC_GETFSUUID and FS_IOC_GETFSSYSFSPATH both operate on + * the file system superblock, not on the specific file, so + * these operations are available through any other file on the + * same file system as well. + */ + case FS_IOC_GETFSUUID: + case FS_IOC_GETFSSYSFSPATH: + return true; + + /* + * FIONREAD, FS_IOC_GETFLAGS, FS_IOC_SETFLAGS, FS_IOC_FSGETXATTR and + * FS_IOC_FSSETXATTR are forwarded to device implementations. + */ + + /* + * file_ioctl() commands (FIBMAP, FS_IOC_RESVSP, FS_IOC_RESVSP64, + * FS_IOC_UNRESVSP, FS_IOC_UNRESVSP64 and FS_IOC_ZERO_RANGE) are + * forwarded to device implementations, so not permitted. + */ + + /* Other commands are guarded by the access right. */ + default: + return false; + } +} + +/* + * is_masked_device_ioctl_compat - same as the helper above, but checking the + * "compat" IOCTL commands. + * + * The IOCTL commands with special handling in compat-mode should behave the + * same as their non-compat counterparts. + */ +static __attribute_const__ bool +is_masked_device_ioctl_compat(const unsigned int cmd) +{ + switch (cmd) { + /* FICLONE is permitted, same as in the non-compat variant. */ + case FICLONE: + return true; + +#if defined(CONFIG_X86_64) + /* + * FS_IOC_RESVSP_32, FS_IOC_RESVSP64_32, FS_IOC_UNRESVSP_32, + * FS_IOC_UNRESVSP64_32, FS_IOC_ZERO_RANGE_32: not blanket-permitted, + * for consistency with their non-compat variants. + */ + case FS_IOC_RESVSP_32: + case FS_IOC_RESVSP64_32: + case FS_IOC_UNRESVSP_32: + case FS_IOC_UNRESVSP64_32: + case FS_IOC_ZERO_RANGE_32: +#endif + + /* + * FS_IOC32_GETFLAGS, FS_IOC32_SETFLAGS are forwarded to their device + * implementations. + */ + case FS_IOC32_GETFLAGS: + case FS_IOC32_SETFLAGS: + return false; + default: + return is_masked_device_ioctl(cmd); + } +} + /* Ruleset management */ static struct landlock_object *get_inode_object(struct inode *const inode) @@ -148,7 +307,8 @@ retry: LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE | \ - LANDLOCK_ACCESS_FS_TRUNCATE) + LANDLOCK_ACCESS_FS_TRUNCATE | \ + LANDLOCK_ACCESS_FS_IOCTL_DEV) /* clang-format on */ /* @@ -1332,11 +1492,18 @@ static int hook_file_alloc_security(struct file *const file) return 0; } +static bool is_device(const struct file *const file) +{ + const struct inode *inode = file_inode(file); + + return S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode); +} + static int hook_file_open(struct file *const file) { layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; - access_mask_t open_access_request, full_access_request, allowed_access; - const access_mask_t optional_access = LANDLOCK_ACCESS_FS_TRUNCATE; + access_mask_t open_access_request, full_access_request, allowed_access, + optional_access; const struct landlock_ruleset *const dom = get_fs_domain(landlock_cred(file->f_cred)->domain); @@ -1354,6 +1521,10 @@ static int hook_file_open(struct file *const file) * We look up more access than what we immediately need for open(), so * that we can later authorize operations on opened files. */ + optional_access = LANDLOCK_ACCESS_FS_TRUNCATE; + if (is_device(file)) + optional_access |= LANDLOCK_ACCESS_FS_IOCTL_DEV; + full_access_request = open_access_request | optional_access; if (is_access_to_paths_allowed( @@ -1410,6 +1581,52 @@ static int hook_file_truncate(struct file *const file) return -EACCES; } +static int hook_file_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + access_mask_t allowed_access = landlock_file(file)->allowed_access; + + /* + * It is the access rights at the time of opening the file which + * determine whether IOCTL can be used on the opened file later. + * + * The access right is attached to the opened file in hook_file_open(). + */ + if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV) + return 0; + + if (!is_device(file)) + return 0; + + if (is_masked_device_ioctl(cmd)) + return 0; + + return -EACCES; +} + +static int hook_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg) +{ + access_mask_t allowed_access = landlock_file(file)->allowed_access; + + /* + * It is the access rights at the time of opening the file which + * determine whether IOCTL can be used on the opened file later. + * + * The access right is attached to the opened file in hook_file_open(). + */ + if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV) + return 0; + + if (!is_device(file)) + return 0; + + if (is_masked_device_ioctl_compat(cmd)) + return 0; + + return -EACCES; +} + static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_free_security, hook_inode_free_security), @@ -1432,6 +1649,8 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security), LSM_HOOK_INIT(file_open, hook_file_open), LSM_HOOK_INIT(file_truncate, hook_file_truncate), + LSM_HOOK_INIT(file_ioctl, hook_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, hook_file_ioctl_compat), }; __init void landlock_add_fs_hooks(void) diff --git a/security/landlock/limits.h b/security/landlock/limits.h index 93c9c6f91556..20fdb5ff3514 100644 --- a/security/landlock/limits.h +++ b/security/landlock/limits.h @@ -18,7 +18,7 @@ #define LANDLOCK_MAX_NUM_LAYERS 16 #define LANDLOCK_MAX_NUM_RULES U32_MAX -#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_TRUNCATE +#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_IOCTL_DEV #define LANDLOCK_MASK_ACCESS_FS ((LANDLOCK_LAST_ACCESS_FS << 1) - 1) #define LANDLOCK_NUM_ACCESS_FS __const_hweight64(LANDLOCK_MASK_ACCESS_FS) #define LANDLOCK_SHIFT_ACCESS_FS 0 diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 6788e73b6681..03b470f5a85a 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -149,7 +149,7 @@ static const struct file_operations ruleset_fops = { .write = fop_dummy_write, }; -#define LANDLOCK_ABI_VERSION 4 +#define LANDLOCK_ABI_VERSION 5 /** * sys_landlock_create_ruleset - Create a new ruleset diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index a6f89aaea77d..3c1e9f35b531 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -75,7 +75,7 @@ TEST(abi_version) const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, }; - ASSERT_EQ(4, landlock_create_ruleset(NULL, 0, + ASSERT_EQ(5, landlock_create_ruleset(NULL, 0, LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 27744524df51..17b00e6c778d 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -536,9 +536,10 @@ TEST_F_FORK(layout1, inval) LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE | \ - LANDLOCK_ACCESS_FS_TRUNCATE) + LANDLOCK_ACCESS_FS_TRUNCATE | \ + LANDLOCK_ACCESS_FS_IOCTL_DEV) -#define ACCESS_LAST LANDLOCK_ACCESS_FS_TRUNCATE +#define ACCESS_LAST LANDLOCK_ACCESS_FS_IOCTL_DEV #define ACCESS_ALL ( \ ACCESS_FILE | \ -- cgit v1.2.3 From c084ebd77a00b1a16d9daa57b6ecdfdf1f43c78a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Thu, 9 May 2024 20:10:10 +0200 Subject: tcp: socket option to check for MPTCP fallback to TCP A way for an application to know if an MPTCP connection fell back to TCP is to use getsockopt(MPTCP_INFO) and look for errors. The issue with this technique is that the same errors -- EOPNOTSUPP (IPv4) and ENOPROTOOPT (IPv6) -- are returned if there was a fallback, *or* if the kernel doesn't support this socket option. The userspace then has to look at the kernel version to understand what the errors mean. It is not clean, and it doesn't take into account older kernels where the socket option has been backported. A cleaner way would be to expose this info to the TCP socket level. In case of MPTCP socket where no fallback happened, the socket options for the TCP level will be handled in MPTCP code, in mptcp_getsockopt_sol_tcp(). If not, that will be in TCP code, in do_tcp_getsockopt(). So MPTCP simply has to set the value 1, while TCP has to set 0. If the socket option is not supported, one of these two errors will be reported: - EOPNOTSUPP (95 - Operation not supported) for MPTCP sockets - ENOPROTOOPT (92 - Protocol not available) for TCP sockets, e.g. on the socket received after an 'accept()', when the client didn't request to use MPTCP: this socket will be a TCP one, even if the listen socket was an MPTCP one. With this new option, the kernel can return a clear answer to both "Is this kernel new enough to tell me the fallback status?" and "If it is new enough, is it currently a TCP or MPTCP socket?" questions, while not breaking the previous method. Acked-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240509-upstream-net-next-20240509-mptcp-tcp_is_mptcp-v1-1-f846df999202@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 3 +++ net/mptcp/sockopt.c | 2 ++ 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c07e9f90c084..dbf896f3146c 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -135,6 +135,8 @@ enum { #define TCP_AO_GET_KEYS 41 /* List MKT(s) */ #define TCP_AO_REPAIR 42 /* Get/Set SNEs and ISNs */ +#define TCP_IS_MPTCP 43 /* Is MPTCP being used? */ + #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 #define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 06aab937d60a..681b54e1f3a6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4363,6 +4363,9 @@ zerocopy_rcv_out: return err; } + case TCP_IS_MPTCP: + val = 0; + break; default: return -ENOPROTOOPT; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 1fea43f5b6f3..eaa3b79651a4 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1348,6 +1348,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return mptcp_put_int_option(msk, optval, optlen, msk->nodelay); case TCP_NOTSENT_LOWAT: return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); + case TCP_IS_MPTCP: + return mptcp_put_int_option(msk, optval, optlen, 1); } return -EOPNOTSUPP; } -- cgit v1.2.3 From b56035101e1cdd9c4420ea5da17f09f87fb69285 Mon Sep 17 00:00:00 2001 From: Daniel Jurgens Date: Fri, 10 May 2024 23:19:26 +0300 Subject: netdev: Add queue stats for TX stop and wake TX queue stop and wake are counted by some drivers. Support reporting these via netdev-genl queue stats. Signed-off-by: Daniel Jurgens Reviewed-by: Jiri Pirko Reviewed-by: Jason Xing Link: https://lore.kernel.org/r/20240510201927.1821109-2-danielj@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 14 ++++++++++++++ include/net/netdev_queues.h | 3 +++ include/uapi/linux/netdev.h | 2 ++ net/core/netdev-genl.c | 4 +++- tools/include/uapi/linux/netdev.h | 2 ++ 5 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 2be4b3714d17..11a32373365a 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -439,6 +439,20 @@ attribute-sets: Number of the packets dropped by the device due to the transmit packets bitrate exceeding the device rate limit. type: uint + - + name: tx-stop + doc: | + Number of times driver paused accepting new tx packets + from the stack to this queue, because the queue was full. + Note that if BQL is supported and enabled on the device + the networking stack will avoid queuing a lot of data at once. + type: uint + - + name: tx-wake + doc: | + Number of times driver re-started accepting send + requests to this queue from the stack. + type: uint operations: list: diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index e7b84f018cee..a8a7e48dfa6c 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -41,6 +41,9 @@ struct netdev_queue_stats_tx { u64 hw_gso_wire_bytes; u64 hw_drop_ratelimits; + + u64 stop; + u64 wake; }; /** diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index cf24f1d9adf8..a8188202413e 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -165,6 +165,8 @@ enum { NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_STOP, + NETDEV_A_QSTATS_TX_WAKE, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 4b5054087309..1f6ae6379e0f 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -517,7 +517,9 @@ netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) || - netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits)) + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_STOP, tx->stop) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_WAKE, tx->wake)) return -EMSGSIZE; return 0; } diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index cf24f1d9adf8..a8188202413e 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -165,6 +165,8 @@ enum { NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_STOP, + NETDEV_A_QSTATS_TX_WAKE, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) -- cgit v1.2.3 From 117c39200d9d760cbd5944bb89efb7b9c51965aa Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 10 May 2024 15:04:31 +0100 Subject: ring-buffer: Introducing ring-buffer mapping functions In preparation for allowing the user-space to map a ring-buffer, add a set of mapping functions: ring_buffer_{map,unmap}() And controls on the ring-buffer: ring_buffer_map_get_reader() /* swap reader and head */ Mapping the ring-buffer also involves: A unique ID for each subbuf of the ring-buffer, currently they are only identified through their in-kernel VA. A meta-page, where are stored ring-buffer statistics and a description for the current reader The linear mapping exposes the meta-page, and each subbuf of the ring-buffer, ordered following their unique ID, assigned during the first mapping. Once mapped, no subbuf can get in or out of the ring-buffer: the buffer size will remain unmodified and the splice enabling functions will in reality simply memcpy the data instead of swapping subbufs. Link: https://lore.kernel.org/linux-trace-kernel/20240510140435.3550353-3-vdonnefort@google.com CC: Signed-off-by: Vincent Donnefort Acked-by: David Hildenbrand Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 6 + include/uapi/linux/trace_mmap.h | 46 +++++ kernel/trace/ring_buffer.c | 414 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 463 insertions(+), 3 deletions(-) create mode 100644 include/uapi/linux/trace_mmap.h (limited to 'include/uapi/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dc5ae4e96aee..96d2140b471e 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -6,6 +6,8 @@ #include #include +#include + struct trace_buffer; struct ring_buffer_iter; @@ -223,4 +225,8 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); #define trace_rb_cpu_prepare NULL #endif +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma); +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h new file mode 100644 index 000000000000..b682e9925539 --- /dev/null +++ b/include/uapi/linux/trace_mmap.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _TRACE_MMAP_H_ +#define _TRACE_MMAP_H_ + +#include + +/** + * struct trace_buffer_meta - Ring-buffer Meta-page description + * @meta_page_size: Size of this meta-page. + * @meta_struct_len: Size of this structure. + * @subbuf_size: Size of each sub-buffer. + * @nr_subbufs: Number of subbfs in the ring-buffer, including the reader. + * @reader.lost_events: Number of events lost at the time of the reader swap. + * @reader.id: subbuf ID of the current reader. ID range [0 : @nr_subbufs - 1] + * @reader.read: Number of bytes read on the reader subbuf. + * @flags: Placeholder for now, 0 until new features are supported. + * @entries: Number of entries in the ring-buffer. + * @overrun: Number of entries lost in the ring-buffer. + * @read: Number of entries that have been read. + * @Reserved1: Internal use only. + * @Reserved2: Internal use only. + */ +struct trace_buffer_meta { + __u32 meta_page_size; + __u32 meta_struct_len; + + __u32 subbuf_size; + __u32 nr_subbufs; + + struct { + __u64 lost_events; + __u32 id; + __u32 read; + } reader; + + __u64 flags; + + __u64 entries; + __u64 overrun; + __u64 read; + + __u64 Reserved1; + __u64 Reserved2; +}; + +#endif /* _TRACE_MMAP_H_ */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1e011733f6a..cb303052bff2 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,7 @@ #include #include #include +#include #include #include @@ -338,6 +340,7 @@ struct buffer_page { local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ unsigned order; /* order of the page */ + u32 id; /* ID for external mapping */ struct buffer_data_page *page; /* Actual data page */ }; @@ -484,6 +487,12 @@ struct ring_buffer_per_cpu { u64 read_stamp; /* pages removed since last reset */ unsigned long pages_removed; + + unsigned int mapped; + struct mutex mapping_lock; + unsigned long *subbuf_ids; /* ID to subbuf VA */ + struct trace_buffer_meta *meta_page; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; struct list_head new_pages; /* new pages to add */ @@ -1599,6 +1608,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&cpu_buffer->irq_work.waiters); init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); + mutex_init(&cpu_buffer->mapping_lock); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1789,8 +1799,6 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer) return buffer->time_stamp_abs; } -static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); - static inline unsigned long rb_page_entries(struct buffer_page *bpage) { return local_read(&bpage->entries) & RB_WRITE_MASK; @@ -5211,6 +5219,22 @@ static void rb_clear_buffer_page(struct buffer_page *page) page->read = 0; } +static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct trace_buffer_meta *meta = cpu_buffer->meta_page; + + meta->reader.read = cpu_buffer->reader_page->read; + meta->reader.id = cpu_buffer->reader_page->id; + meta->reader.lost_events = cpu_buffer->lost_events; + + meta->entries = local_read(&cpu_buffer->entries); + meta->overrun = local_read(&cpu_buffer->overrun); + meta->read = cpu_buffer->read; + + /* Some archs do not have data cache coherency between kernel and user-space */ + flush_dcache_folio(virt_to_folio(cpu_buffer->meta_page)); +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { @@ -5255,6 +5279,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->lost_events = 0; cpu_buffer->last_overrun = 0; + if (cpu_buffer->mapped) + rb_update_meta_page(cpu_buffer); + rb_head_page_activate(cpu_buffer); cpu_buffer->pages_removed = 0; } @@ -5469,6 +5496,12 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; + /* It's up to the callers to not try to swap mapped buffers */ + if (WARN_ON_ONCE(cpu_buffer_a->mapped || cpu_buffer_b->mapped)) { + ret = -EBUSY; + goto out; + } + /* At least make sure the two buffers are somewhat the same */ if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; @@ -5733,7 +5766,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, * Otherwise, we can simply swap the page with the one passed in. */ if (read || (len < (commit - read)) || - cpu_buffer->reader_page == cpu_buffer->commit_page) { + cpu_buffer->reader_page == cpu_buffer->commit_page || + cpu_buffer->mapped) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; @@ -5956,6 +5990,11 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) cpu_buffer = buffer->buffers[cpu]; + if (cpu_buffer->mapped) { + err = -EBUSY; + goto error; + } + /* Update the number of pages to match the new size */ nr_pages = old_size * buffer->buffers[cpu]->nr_pages; nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size); @@ -6057,6 +6096,375 @@ error: } EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set); +static int rb_alloc_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct page *page; + + if (cpu_buffer->meta_page) + return 0; + + page = alloc_page(GFP_USER | __GFP_ZERO); + if (!page) + return -ENOMEM; + + cpu_buffer->meta_page = page_to_virt(page); + + return 0; +} + +static void rb_free_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + unsigned long addr = (unsigned long)cpu_buffer->meta_page; + + free_page(addr); + cpu_buffer->meta_page = NULL; +} + +static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long *subbuf_ids) +{ + struct trace_buffer_meta *meta = cpu_buffer->meta_page; + unsigned int nr_subbufs = cpu_buffer->nr_pages + 1; + struct buffer_page *first_subbuf, *subbuf; + int id = 0; + + subbuf_ids[id] = (unsigned long)cpu_buffer->reader_page->page; + cpu_buffer->reader_page->id = id++; + + first_subbuf = subbuf = rb_set_head_page(cpu_buffer); + do { + if (WARN_ON(id >= nr_subbufs)) + break; + + subbuf_ids[id] = (unsigned long)subbuf->page; + subbuf->id = id; + + rb_inc_page(&subbuf); + id++; + } while (subbuf != first_subbuf); + + /* install subbuf ID to kern VA translation */ + cpu_buffer->subbuf_ids = subbuf_ids; + + meta->meta_page_size = PAGE_SIZE; + meta->meta_struct_len = sizeof(*meta); + meta->nr_subbufs = nr_subbufs; + meta->subbuf_size = cpu_buffer->buffer->subbuf_size + BUF_PAGE_HDR_SIZE; + + rb_update_meta_page(cpu_buffer); +} + +static struct ring_buffer_per_cpu * +rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return ERR_PTR(-EINVAL); + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + mutex_unlock(&cpu_buffer->mapping_lock); + return ERR_PTR(-ENODEV); + } + + return cpu_buffer; +} + +static void rb_put_mapped_buffer(struct ring_buffer_per_cpu *cpu_buffer) +{ + mutex_unlock(&cpu_buffer->mapping_lock); +} + +/* + * Fast-path for rb_buffer_(un)map(). Called whenever the meta-page doesn't need + * to be set-up or torn-down. + */ +static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer, + bool inc) +{ + unsigned long flags; + + lockdep_assert_held(&cpu_buffer->mapping_lock); + + if (inc && cpu_buffer->mapped == UINT_MAX) + return -EBUSY; + + if (WARN_ON(!inc && cpu_buffer->mapped == 0)) + return -EINVAL; + + mutex_lock(&cpu_buffer->buffer->mutex); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + if (inc) + cpu_buffer->mapped++; + else + cpu_buffer->mapped--; + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + mutex_unlock(&cpu_buffer->buffer->mutex); + + return 0; +} + +/* + * +--------------+ pgoff == 0 + * | meta page | + * +--------------+ pgoff == 1 + * | subbuffer 0 | + * | | + * +--------------+ pgoff == (1 + (1 << subbuf_order)) + * | subbuffer 1 | + * | | + * ... + */ +#ifdef CONFIG_MMU +static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, + struct vm_area_struct *vma) +{ + unsigned long nr_subbufs, nr_pages, vma_pages, pgoff = vma->vm_pgoff; + unsigned int subbuf_pages, subbuf_order; + struct page **pages; + int p = 0, s = 0; + int err; + + /* Refuse MP_PRIVATE or writable mappings */ + if (vma->vm_flags & VM_WRITE || vma->vm_flags & VM_EXEC || + !(vma->vm_flags & VM_MAYSHARE)) + return -EPERM; + + /* + * Make sure the mapping cannot become writable later. Also tell the VM + * to not touch these pages (VM_DONTCOPY | VM_DONTEXPAND). + */ + vm_flags_mod(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP, + VM_MAYWRITE); + + lockdep_assert_held(&cpu_buffer->mapping_lock); + + subbuf_order = cpu_buffer->buffer->subbuf_order; + subbuf_pages = 1 << subbuf_order; + + nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ + nr_pages = ((nr_subbufs) << subbuf_order) - pgoff + 1; /* + meta-page */ + + vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + if (!vma_pages || vma_pages > nr_pages) + return -EINVAL; + + nr_pages = vma_pages; + + pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + if (!pgoff) { + pages[p++] = virt_to_page(cpu_buffer->meta_page); + + /* + * TODO: Align sub-buffers on their size, once + * vm_insert_pages() supports the zero-page. + */ + } else { + /* Skip the meta-page */ + pgoff--; + + if (pgoff % subbuf_pages) { + err = -EINVAL; + goto out; + } + + s += pgoff / subbuf_pages; + } + + while (p < nr_pages) { + struct page *page = virt_to_page(cpu_buffer->subbuf_ids[s]); + int off = 0; + + if (WARN_ON_ONCE(s >= nr_subbufs)) { + err = -EINVAL; + goto out; + } + + for (; off < (1 << (subbuf_order)); off++, page++) { + if (p >= nr_pages) + break; + + pages[p++] = page; + } + s++; + } + + err = vm_insert_pages(vma, vma->vm_start, pages, &nr_pages); + +out: + kfree(pages); + + return err; +} +#else +static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, + struct vm_area_struct *vma) +{ + return -EOPNOTSUPP; +} +#endif + +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags, *subbuf_ids; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (cpu_buffer->mapped) { + err = __rb_map_vma(cpu_buffer, vma); + if (!err) + err = __rb_inc_dec_mapped(cpu_buffer, true); + mutex_unlock(&cpu_buffer->mapping_lock); + return err; + } + + /* prevent another thread from changing buffer/sub-buffer sizes */ + mutex_lock(&buffer->mutex); + + err = rb_alloc_meta_page(cpu_buffer); + if (err) + goto unlock; + + /* subbuf_ids include the reader while nr_pages does not */ + subbuf_ids = kcalloc(cpu_buffer->nr_pages + 1, sizeof(*subbuf_ids), GFP_KERNEL); + if (!subbuf_ids) { + rb_free_meta_page(cpu_buffer); + err = -ENOMEM; + goto unlock; + } + + atomic_inc(&cpu_buffer->resize_disabled); + + /* + * Lock all readers to block any subbuf swap until the subbuf IDs are + * assigned. + */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_setup_ids_meta_page(cpu_buffer, subbuf_ids); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + err = __rb_map_vma(cpu_buffer, vma); + if (!err) { + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + cpu_buffer->mapped = 1; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } else { + kfree(cpu_buffer->subbuf_ids); + cpu_buffer->subbuf_ids = NULL; + rb_free_meta_page(cpu_buffer); + } + +unlock: + mutex_unlock(&buffer->mutex); + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + err = -ENODEV; + goto out; + } else if (cpu_buffer->mapped > 1) { + __rb_inc_dec_mapped(cpu_buffer, false); + goto out; + } + + mutex_lock(&buffer->mutex); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + cpu_buffer->mapped = 0; + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + kfree(cpu_buffer->subbuf_ids); + cpu_buffer->subbuf_ids = NULL; + rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); + + mutex_unlock(&buffer->mutex); + +out: + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long reader_size; + unsigned long flags; + + cpu_buffer = rb_get_mapped_buffer(buffer, cpu); + if (IS_ERR(cpu_buffer)) + return (int)PTR_ERR(cpu_buffer); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + +consume: + if (rb_per_cpu_empty(cpu_buffer)) + goto out; + + reader_size = rb_page_size(cpu_buffer->reader_page); + + /* + * There are data to be read on the current reader page, we can + * return to the caller. But before that, we assume the latter will read + * everything. Let's update the kernel reader accordingly. + */ + if (cpu_buffer->reader_page->read < reader_size) { + while (cpu_buffer->reader_page->read < reader_size) + rb_advance_reader(cpu_buffer); + goto out; + } + + if (WARN_ON(!rb_get_reader_page(cpu_buffer))) + goto out; + + goto consume; + +out: + /* Some archs do not have data cache coherency between kernel and user-space */ + flush_dcache_folio(virt_to_folio(cpu_buffer->reader_page->page)); + + rb_update_meta_page(cpu_buffer); + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + rb_put_mapped_buffer(cpu_buffer); + + return 0; +} + /* * We only allocate new buffers, never free them if the CPU goes down. * If we were to free the buffer, then the user would lose any trace that was in -- cgit v1.2.3 From cf9f0f7c4c5bb45e7bb270e48bab6f7837825a64 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 10 May 2024 15:04:32 +0100 Subject: tracing: Allow user-space mapping of the ring-buffer Currently, user-space extracts data from the ring-buffer via splice, which is handy for storage or network sharing. However, due to splice limitations, it is imposible to do real-time analysis without a copy. A solution for that problem is to let the user-space map the ring-buffer directly. The mapping is exposed via the per-CPU file trace_pipe_raw. The first element of the mapping is the meta-page. It is followed by each subbuffer constituting the ring-buffer, ordered by their unique page ID: * Meta-page -- include/uapi/linux/trace_mmap.h for a description * Subbuf ID 0 * Subbuf ID 1 ... It is therefore easy to translate a subbuf ID into an offset in the mapping: reader_id = meta->reader->id; reader_offset = meta->meta_page_size + reader_id * meta->subbuf_size; When new data is available, the mapper must call a newly introduced ioctl: TRACE_MMAP_IOCTL_GET_READER. This will update the Meta-page reader ID to point to the next reader containing unread data. Mapping will prevent snapshot and buffer size modifications. Link: https://lore.kernel.org/linux-trace-kernel/20240510140435.3550353-4-vdonnefort@google.com CC: Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/trace_mmap.h | 2 + kernel/trace/trace.c | 104 ++++++++++++++++++++++++++++++++++++++-- kernel/trace/trace.h | 1 + 3 files changed, 102 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h index b682e9925539..bd1066754220 100644 --- a/include/uapi/linux/trace_mmap.h +++ b/include/uapi/linux/trace_mmap.h @@ -43,4 +43,6 @@ struct trace_buffer_meta { __u64 Reserved2; }; +#define TRACE_MMAP_IOCTL_GET_READER _IO('T', 0x1) + #endif /* _TRACE_MMAP_H_ */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 233d1af39fff..a35e7f598233 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1191,6 +1191,12 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, return; } + if (tr->mapped) { + trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); + return; + } + local_irq_save(flags); update_max_tr(tr, current, smp_processor_id(), cond_data); local_irq_restore(flags); @@ -1323,7 +1329,7 @@ static int tracing_arm_snapshot_locked(struct trace_array *tr) lockdep_assert_held(&trace_types_lock); spin_lock(&tr->snapshot_trigger_lock); - if (tr->snapshot == UINT_MAX) { + if (tr->snapshot == UINT_MAX || tr->mapped) { spin_unlock(&tr->snapshot_trigger_lock); return -EBUSY; } @@ -6068,7 +6074,7 @@ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; - + tr->current_trace->enabled--; if (tr->current_trace->reset) @@ -8194,15 +8200,32 @@ out: return ret; } -/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; + int err; + + if (cmd == TRACE_MMAP_IOCTL_GET_READER) { + if (!(file->f_flags & O_NONBLOCK)) { + err = ring_buffer_wait(iter->array_buffer->buffer, + iter->cpu_file, + iter->tr->buffer_percent, + NULL, NULL); + if (err) + return err; + } - if (cmd) - return -ENOIOCTLCMD; + return ring_buffer_map_get_reader(iter->array_buffer->buffer, + iter->cpu_file); + } else if (cmd) { + return -ENOTTY; + } + /* + * An ioctl call with cmd 0 to the ring buffer file will wake up all + * waiters + */ mutex_lock(&trace_types_lock); /* Make sure the waiters see the new wait_index */ @@ -8214,6 +8237,76 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned return 0; } +#ifdef CONFIG_TRACER_MAX_TRACE +static int get_snapshot_map(struct trace_array *tr) +{ + int err = 0; + + /* + * Called with mmap_lock held. lockdep would be unhappy if we would now + * take trace_types_lock. Instead use the specific + * snapshot_trigger_lock. + */ + spin_lock(&tr->snapshot_trigger_lock); + + if (tr->snapshot || tr->mapped == UINT_MAX) + err = -EBUSY; + else + tr->mapped++; + + spin_unlock(&tr->snapshot_trigger_lock); + + /* Wait for update_max_tr() to observe iter->tr->mapped */ + if (tr->mapped == 1) + synchronize_rcu(); + + return err; + +} +static void put_snapshot_map(struct trace_array *tr) +{ + spin_lock(&tr->snapshot_trigger_lock); + if (!WARN_ON(!tr->mapped)) + tr->mapped--; + spin_unlock(&tr->snapshot_trigger_lock); +} +#else +static inline int get_snapshot_map(struct trace_array *tr) { return 0; } +static inline void put_snapshot_map(struct trace_array *tr) { } +#endif + +static void tracing_buffers_mmap_close(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file)); + put_snapshot_map(iter->tr); +} + +static const struct vm_operations_struct tracing_buffers_vmops = { + .close = tracing_buffers_mmap_close, +}; + +static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + int ret = 0; + + ret = get_snapshot_map(iter->tr); + if (ret) + return ret; + + ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma); + if (ret) + put_snapshot_map(iter->tr); + + vma->vm_ops = &tracing_buffers_vmops; + + return ret; +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, @@ -8223,6 +8316,7 @@ static const struct file_operations tracing_buffers_fops = { .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, + .mmap = tracing_buffers_mmap, }; static ssize_t diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 64450615ca0c..749a182dab48 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -336,6 +336,7 @@ struct trace_array { bool allocated_snapshot; spinlock_t snapshot_trigger_lock; unsigned int snapshot; + unsigned int mapped; unsigned long max_latency; #ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; -- cgit v1.2.3 From 5c1672705a1a2389f5ad78e0fea6f08ed32d6f18 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 13 May 2024 08:41:55 -0700 Subject: net: revert partially applied PHY topology series The series is causing issues with PHY drivers built as modules. Since it was only partially applied and the merge window has opened let's revert and try again for v6.11. Revert 6916e461e793 ("net: phy: Introduce ethernet link topology representation") Revert 0ec5ed6c130e ("net: sfp: pass the phy_device when disconnecting an sfp module's PHY") Revert e75e4e074c44 ("net: phy: add helpers to handle sfp phy connect/disconnect") Revert fdd353965b52 ("net: sfp: Add helper to return the SFP bus name") Revert 841942bc6212 ("net: ethtool: Allow passing a phy index for some commands") Link: https://lore.kernel.org/all/171242462917.4000.9759453824684907063.git-patchwork-notify@kernel.org/ Link: https://lore.kernel.org/all/20240507102822.2023826-1-maxime.chevallier@bootlin.com/ Link: https://lore.kernel.org/r/20240513154156.104281-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 7 -- MAINTAINERS | 2 - drivers/net/phy/Makefile | 2 +- drivers/net/phy/marvell-88x2222.c | 2 - drivers/net/phy/marvell.c | 2 - drivers/net/phy/marvell10g.c | 2 - drivers/net/phy/phy_device.c | 55 -------------- drivers/net/phy/phy_link_topology.c | 105 --------------------------- drivers/net/phy/phylink.c | 3 +- drivers/net/phy/qcom/at803x.c | 2 - drivers/net/phy/qcom/qca807x.c | 2 - drivers/net/phy/sfp-bus.c | 15 +--- include/linux/netdevice.h | 4 +- include/linux/phy.h | 6 -- include/linux/phy_link_topology.h | 72 ------------------ include/linux/phy_link_topology_core.h | 25 ------- include/linux/sfp.h | 8 +- include/uapi/linux/ethtool.h | 16 ---- include/uapi/linux/ethtool_netlink.h | 1 - net/core/dev.c | 9 --- net/ethtool/netlink.c | 48 +----------- net/ethtool/netlink.h | 5 -- 22 files changed, 8 insertions(+), 385 deletions(-) delete mode 100644 drivers/net/phy/phy_link_topology.c delete mode 100644 include/linux/phy_link_topology.h delete mode 100644 include/linux/phy_link_topology_core.h (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 8bc71f249448..160bfb0ae8ba 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -57,7 +57,6 @@ Structure of this header is ``ETHTOOL_A_HEADER_DEV_INDEX`` u32 device ifindex ``ETHTOOL_A_HEADER_DEV_NAME`` string device name ``ETHTOOL_A_HEADER_FLAGS`` u32 flags common for all requests - ``ETHTOOL_A_HEADER_PHY_INDEX`` u32 phy device index ============================== ====== ============================= ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the @@ -82,12 +81,6 @@ the behaviour is backward compatible, i.e. requests from old clients not aware of the flag should be interpreted the way the client expects. A client must not set flags it does not understand. -``ETHTOOL_A_HEADER_PHY_INDEX`` identifies the Ethernet PHY the message relates to. -As there are numerous commands that are related to PHY configuration, and because -there may be more than one PHY on the link, the PHY index can be passed in the -request for the commands that needs it. It is, however, not mandatory, and if it -is not passed for commands that target a PHY, the net_device.phydev pointer -is used. Bit sets ======== diff --git a/MAINTAINERS b/MAINTAINERS index 40eb26e6c60c..b4ed6480e919 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8027,8 +8027,6 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h -F: include/linux/phy_link_topology.h -F: include/linux/phy_link_topology_core.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 1d8be374915f..202ed7f450da 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o phy_link_topology.o + linkmode.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index 0b777cdd7078..b88398e6872b 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -553,8 +553,6 @@ static const struct sfp_upstream_ops sfp_phy_ops = { .link_down = mv2222_sfp_link_down, .attach = phy_sfp_attach, .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int mv2222_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 9964bf3dea2f..b89fbffa6a93 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -3613,8 +3613,6 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = { .module_remove = m88e1510_sfp_remove, .attach = phy_sfp_attach, .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int m88e1510_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 6642eb642d4b..ad43e280930c 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -503,8 +503,6 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) static const struct sfp_upstream_ops mv3310_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, .module_insert = mv3310_sfp_insert, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 616bd7ba46cb..6c6ec9475709 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include @@ -277,14 +276,6 @@ static void phy_mdio_device_remove(struct mdio_device *mdiodev) static struct phy_driver genphy_driver; -static struct phy_link_topology *phy_get_link_topology(struct phy_device *phydev) -{ - if (phydev->attached_dev) - return phydev->attached_dev->link_topo; - - return NULL; -} - static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock); @@ -1378,46 +1369,6 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(phy_standalone); -/** - * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY - * @upstream: pointer to the upstream phy device - * @phy: pointer to the SFP module's phy device - * - * This helper allows keeping track of PHY devices on the link. It adds the - * SFP module's phy to the phy namespace of the upstream phy - */ -int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) -{ - struct phy_device *phydev = upstream; - struct phy_link_topology *topo = phy_get_link_topology(phydev); - - if (topo) - return phy_link_topo_add_phy(topo, phy, PHY_UPSTREAM_PHY, phydev); - - return 0; -} -EXPORT_SYMBOL(phy_sfp_connect_phy); - -/** - * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY - * @upstream: pointer to the upstream phy device - * @phy: pointer to the SFP module's phy device - * - * This helper allows keeping track of PHY devices on the link. It removes the - * SFP module's phy to the phy namespace of the upstream phy. As the module phy - * will be destroyed, re-inserting the same module will add a new phy with a - * new index. - */ -void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) -{ - struct phy_device *phydev = upstream; - struct phy_link_topology *topo = phy_get_link_topology(phydev); - - if (topo) - phy_link_topo_del_phy(topo, phy); -} -EXPORT_SYMBOL(phy_sfp_disconnect_phy); - /** * phy_sfp_attach - attach the SFP bus to the PHY upstream network device * @upstream: pointer to the phy device @@ -1560,11 +1511,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; - - err = phy_link_topo_add_phy(dev->link_topo, phydev, - PHY_UPSTREAM_MAC, dev); - if (err) - goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1992,7 +1938,6 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; - phy_link_topo_del_phy(dev->link_topo, phydev); } phydev->phylink = NULL; diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c deleted file mode 100644 index 985941c5c558..000000000000 --- a/drivers/net/phy/phy_link_topology.c +++ /dev/null @@ -1,105 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Infrastructure to handle all PHY devices connected to a given netdev, - * either directly or indirectly attached. - * - * Copyright (c) 2023 Maxime Chevallier - */ - -#include -#include -#include -#include -#include - -struct phy_link_topology *phy_link_topo_create(struct net_device *dev) -{ - struct phy_link_topology *topo; - - topo = kzalloc(sizeof(*topo), GFP_KERNEL); - if (!topo) - return ERR_PTR(-ENOMEM); - - xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); - topo->next_phy_index = 1; - - return topo; -} - -void phy_link_topo_destroy(struct phy_link_topology *topo) -{ - if (!topo) - return; - - xa_destroy(&topo->phys); - kfree(topo); -} - -int phy_link_topo_add_phy(struct phy_link_topology *topo, - struct phy_device *phy, - enum phy_upstream upt, void *upstream) -{ - struct phy_device_node *pdn; - int ret; - - pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); - if (!pdn) - return -ENOMEM; - - pdn->phy = phy; - switch (upt) { - case PHY_UPSTREAM_MAC: - pdn->upstream.netdev = (struct net_device *)upstream; - if (phy_on_sfp(phy)) - pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; - break; - case PHY_UPSTREAM_PHY: - pdn->upstream.phydev = (struct phy_device *)upstream; - if (phy_on_sfp(phy)) - pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; - break; - default: - ret = -EINVAL; - goto err; - } - pdn->upstream_type = upt; - - /* Attempt to re-use a previously allocated phy_index */ - if (phy->phyindex) { - ret = xa_insert(&topo->phys, phy->phyindex, pdn, GFP_KERNEL); - - /* Errors could be either -ENOMEM or -EBUSY. If the phy has an - * index, and there's another entry at the same index, this is - * unexpected and we still error-out - */ - if (ret) - goto err; - return 0; - } - - ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, xa_limit_32b, - &topo->next_phy_index, GFP_KERNEL); - if (ret) - goto err; - - return 0; - -err: - kfree(pdn); - return ret; -} -EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); - -void phy_link_topo_del_phy(struct phy_link_topology *topo, - struct phy_device *phy) -{ - struct phy_device_node *pdn = xa_erase(&topo->phys, phy->phyindex); - - /* We delete the PHY from the topology, however we don't re-set the - * phy->phyindex field. If the PHY isn't gone, we can re-assign it the - * same index next time it's added back to the topology - */ - - kfree(pdn); -} -EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index b7e5c669dc8e..994471fad833 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -3411,8 +3411,7 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) return ret; } -static void phylink_sfp_disconnect_phy(void *upstream, - struct phy_device *phydev) +static void phylink_sfp_disconnect_phy(void *upstream) { phylink_disconnect_phy(upstream); } diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 105602581a03..c8f83e5f78ab 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -770,8 +770,6 @@ static const struct sfp_upstream_ops at8031_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, .module_insert = at8031_sfp_insert, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int at8031_parse_dt(struct phy_device *phydev) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 5eb0ab1cb70e..672c6929119a 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -699,8 +699,6 @@ static const struct sfp_upstream_ops qca807x_sfp_ops = { .detach = phy_sfp_detach, .module_insert = qca807x_sfp_insert, .module_remove = qca807x_sfp_remove, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, }; static int qca807x_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 37c85f1e6534..2f44fc51848f 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -487,7 +487,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) bus->socket_ops->stop(bus->sfp); bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream, bus->phydev); + ops->disconnect_phy(bus->upstream); } bus->registered = false; } @@ -743,7 +743,7 @@ void sfp_remove_phy(struct sfp_bus *bus) const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus); if (ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream, bus->phydev); + ops->disconnect_phy(bus->upstream); bus->phydev = NULL; } EXPORT_SYMBOL_GPL(sfp_remove_phy); @@ -860,14 +860,3 @@ void sfp_unregister_socket(struct sfp_bus *bus) sfp_bus_put(bus); } EXPORT_SYMBOL_GPL(sfp_unregister_socket); - -const char *sfp_get_name(struct sfp_bus *bus) -{ - ASSERT_RTNL(); - - if (bus->sfp_dev) - return dev_name(bus->sfp_dev); - - return NULL; -} -EXPORT_SYMBOL_GPL(sfp_get_name); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf261fb89d73..d20c6c99eb88 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,6 +40,7 @@ #include #endif #include + #include #include #include @@ -51,7 +52,6 @@ #include #include #include -#include struct netpoll_info; struct device; @@ -1975,7 +1975,6 @@ enum netdev_reg_state { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one - * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2368,7 +2367,6 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif - struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; diff --git a/include/linux/phy.h b/include/linux/phy.h index 3ddfe7fe781a..e6e83304558e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -550,9 +550,6 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. - * @phyindex: Unique id across the phy's parent tree of phys to address the PHY - * from userspace, similar to ifindex. A zero index means the PHY - * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -653,7 +650,6 @@ struct phy_device { struct device_link *devlink; - u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; @@ -1758,8 +1754,6 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); -int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); -void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h deleted file mode 100644 index 6b79feb607e7..000000000000 --- a/include/linux/phy_link_topology.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * PHY device list allow maintaining a list of PHY devices that are - * part of a netdevice's link topology. PHYs can for example be chained, - * as is the case when using a PHY that exposes an SFP module, on which an - * SFP transceiver that embeds a PHY is connected. - * - * This list can then be used by userspace to leverage individual PHY - * capabilities. - */ -#ifndef __PHY_LINK_TOPOLOGY_H -#define __PHY_LINK_TOPOLOGY_H - -#include -#include - -struct xarray; -struct phy_device; -struct net_device; -struct sfp_bus; - -struct phy_device_node { - enum phy_upstream upstream_type; - - union { - struct net_device *netdev; - struct phy_device *phydev; - } upstream; - - struct sfp_bus *parent_sfp_bus; - - struct phy_device *phy; -}; - -struct phy_link_topology { - struct xarray phys; - u32 next_phy_index; -}; - -static inline struct phy_device * -phy_link_topo_get_phy(struct phy_link_topology *topo, u32 phyindex) -{ - struct phy_device_node *pdn = xa_load(&topo->phys, phyindex); - - if (pdn) - return pdn->phy; - - return NULL; -} - -#if IS_REACHABLE(CONFIG_PHYLIB) -int phy_link_topo_add_phy(struct phy_link_topology *topo, - struct phy_device *phy, - enum phy_upstream upt, void *upstream); - -void phy_link_topo_del_phy(struct phy_link_topology *lt, struct phy_device *phy); - -#else -static inline int phy_link_topo_add_phy(struct phy_link_topology *topo, - struct phy_device *phy, - enum phy_upstream upt, void *upstream) -{ - return 0; -} - -static inline void phy_link_topo_del_phy(struct phy_link_topology *topo, - struct phy_device *phy) -{ -} -#endif - -#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/linux/phy_link_topology_core.h b/include/linux/phy_link_topology_core.h deleted file mode 100644 index 0a6479055745..000000000000 --- a/include/linux/phy_link_topology_core.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PHY_LINK_TOPOLOGY_CORE_H -#define __PHY_LINK_TOPOLOGY_CORE_H - -struct phy_link_topology; - -#if IS_REACHABLE(CONFIG_PHYLIB) - -struct phy_link_topology *phy_link_topo_create(struct net_device *dev); -void phy_link_topo_destroy(struct phy_link_topology *topo); - -#else - -static inline struct phy_link_topology *phy_link_topo_create(struct net_device *dev) -{ - return NULL; -} - -static inline void phy_link_topo_destroy(struct phy_link_topology *topo) -{ -} - -#endif - -#endif /* __PHY_LINK_TOPOLOGY_CORE_H */ diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 5ebc57f78c95..a45da7eef9a2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -544,7 +544,7 @@ struct sfp_upstream_ops { void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); - void (*disconnect_phy)(void *priv, struct phy_device *); + void (*disconnect_phy)(void *priv); }; #if IS_ENABLED(CONFIG_SFP) @@ -570,7 +570,6 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); -const char *sfp_get_name(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -649,11 +648,6 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } - -static inline const char *sfp_get_name(struct sfp_bus *bus) -{ - return NULL; -} #endif #endif diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 041e09c3515d..8733a3117902 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2323,20 +2323,4 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; - -/** - * enum phy_upstream - Represents the upstream component a given PHY device - * is connected to, as in what is on the other end of the MII bus. Most PHYs - * will be attached to an Ethernet MAC controller, but in some cases, there's - * an intermediate PHY used as a media-converter, which will driver another - * MII interface as its output. - * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, - * or ethernet controller) - * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) - */ -enum phy_upstream { - PHY_UPSTREAM_MAC, - PHY_UPSTREAM_PHY, -}; - #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index f17dbe54bf5e..b49b804b9495 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -132,7 +132,6 @@ enum { ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ ETHTOOL_A_HEADER_DEV_NAME, /* string */ ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ - ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_HEADER_CNT, diff --git a/net/core/dev.c b/net/core/dev.c index d2ce91a334c1..e1bb6d7856d9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,7 +158,6 @@ #include #include #include -#include #include "dev.h" #include "net-sysfs.h" @@ -10998,12 +10997,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif - dev->link_topo = phy_link_topo_create(dev); - if (IS_ERR(dev->link_topo)) { - dev->link_topo = NULL; - goto free_all; - } - dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); @@ -11092,8 +11085,6 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; - phy_link_topo_destroy(dev->link_topo); - /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 563e94e0cbd8..bd04f28d5cf4 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -4,7 +4,6 @@ #include #include #include "netlink.h" -#include static struct genl_family ethtool_genl_family; @@ -31,24 +30,6 @@ const struct nla_policy ethnl_header_policy_stats[] = { ETHTOOL_FLAGS_STATS), }; -const struct nla_policy ethnl_header_policy_phy[] = { - [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, - [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, - .len = ALTIFNAMSIZ - 1 }, - [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, - ETHTOOL_FLAGS_BASIC), - [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), -}; - -const struct nla_policy ethnl_header_policy_phy_stats[] = { - [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, - [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, - .len = ALTIFNAMSIZ - 1 }, - [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, - ETHTOOL_FLAGS_STATS), - [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), -}; - int ethnl_ops_begin(struct net_device *dev) { int ret; @@ -108,9 +89,8 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; + struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; const struct nlattr *devname_attr; - struct phy_device *phydev = NULL; struct net_device *dev = NULL; u32 flags = 0; int ret; @@ -124,7 +104,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ - ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, + ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, NULL, extack); if (ret < 0) return ret; @@ -165,30 +145,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } - if (dev) { - if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { - struct nlattr *phy_id; - - phy_id = tb[ETHTOOL_A_HEADER_PHY_INDEX]; - phydev = phy_link_topo_get_phy(dev->link_topo, - nla_get_u32(phy_id)); - if (!phydev) { - NL_SET_BAD_ATTR(extack, phy_id); - return -ENODEV; - } - } else { - /* If we need a PHY but no phy index is specified, fallback - * to dev->phydev - */ - phydev = dev->phydev; - } - } else if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { - NL_SET_ERR_MSG_ATTR(extack, header, - "can't target a PHY without a netdev"); - return -EINVAL; - } - - req_info->phydev = phydev; req_info->dev = dev; req_info->flags = flags; return 0; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index d57a890b5d9e..9a333a8d04c1 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -250,7 +250,6 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types - * @phydev: phy_device connected to @dev this request is for (may be null) * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -260,7 +259,6 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; - struct phy_device *phydev; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -397,12 +395,9 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; -extern const struct ethnl_request_ops ethnl_phy_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; -extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; -extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; -- cgit v1.2.3 From 84a4bb6548a29326564f0e659fb8064503ecc1c7 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 6 May 2024 18:33:52 -0400 Subject: Bluetooth: HCI: Remove HCI_AMP support Since BT_HS has been remove HCI_AMP controllers no longer has any use so remove it along with the capability of creating AMP controllers. Since we no longer need to differentiate between AMP and Primary controllers, as only HCI_PRIMARY is left, this also remove hdev->dev_type altogether. Fixes: e7b02296fb40 ("Bluetooth: Remove BT_HS") Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btmrvl_main.c | 9 --- drivers/bluetooth/btrsi.c | 1 - drivers/bluetooth/btsdio.c | 8 --- drivers/bluetooth/btusb.c | 5 -- drivers/bluetooth/hci_bcm4377.c | 1 - drivers/bluetooth/hci_ldisc.c | 6 -- drivers/bluetooth/hci_serdev.c | 5 -- drivers/bluetooth/hci_uart.h | 1 - drivers/bluetooth/hci_vhci.c | 10 +-- drivers/bluetooth/virtio_bt.c | 2 - include/net/bluetooth/hci.h | 114 ------------------------------ include/net/bluetooth/hci_core.h | 46 +----------- include/uapi/linux/virtio_bt.h | 1 - net/bluetooth/hci_conn.c | 3 +- net/bluetooth/hci_core.c | 132 +++-------------------------------- net/bluetooth/hci_event.c | 147 --------------------------------------- net/bluetooth/hci_sock.c | 5 +- net/bluetooth/hci_sync.c | 112 ++--------------------------- net/bluetooth/l2cap_core.c | 21 ++---- net/bluetooth/mgmt.c | 84 +++++++--------------- 20 files changed, 49 insertions(+), 664 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 9658b33c824a..18f34998a120 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -121,13 +121,6 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb) ((event->data[2] == MODULE_BROUGHT_UP) || (event->data[2] == MODULE_ALREADY_UP)) ? "Bring-up succeed" : "Bring-up failed"); - - if (event->length > 3 && event->data[3]) - priv->btmrvl_dev.dev_type = HCI_AMP; - else - priv->btmrvl_dev.dev_type = HCI_PRIMARY; - - BT_DBG("dev_type: %d", priv->btmrvl_dev.dev_type); } else if (priv->btmrvl_dev.sendcmdflag && event->data[1] == MODULE_SHUTDOWN_REQ) { BT_DBG("EVENT:%s", (event->data[2]) ? @@ -686,8 +679,6 @@ int btmrvl_register_hdev(struct btmrvl_private *priv) hdev->wakeup = btmrvl_wakeup; SET_HCIDEV_DEV(hdev, &card->func->dev); - hdev->dev_type = priv->btmrvl_dev.dev_type; - ret = hci_register_dev(hdev); if (ret < 0) { BT_ERR("Can not register HCI device"); diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c index 634cf8f5ed2d..0c91d7635ac3 100644 --- a/drivers/bluetooth/btrsi.c +++ b/drivers/bluetooth/btrsi.c @@ -134,7 +134,6 @@ static int rsi_hci_attach(void *priv, struct rsi_proto_ops *ops) hdev->bus = HCI_USB; hci_set_drvdata(hdev, h_adapter); - hdev->dev_type = HCI_PRIMARY; hdev->open = rsi_hci_open; hdev->close = rsi_hci_close; hdev->flush = rsi_hci_flush; diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index f19d31ee37ea..fdcfe9c50313 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -32,9 +32,6 @@ static const struct sdio_device_id btsdio_table[] = { /* Generic Bluetooth Type-B SDIO device */ { SDIO_DEVICE_CLASS(SDIO_CLASS_BT_B) }, - /* Generic Bluetooth AMP controller */ - { SDIO_DEVICE_CLASS(SDIO_CLASS_BT_AMP) }, - { } /* Terminating entry */ }; @@ -319,11 +316,6 @@ static int btsdio_probe(struct sdio_func *func, hdev->bus = HCI_SDIO; hci_set_drvdata(hdev, data); - if (id->class == SDIO_CLASS_BT_AMP) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - data->hdev = hdev; SET_HCIDEV_DEV(hdev, &func->dev); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 90d1f1697357..e384ef6ff050 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4359,11 +4359,6 @@ static int btusb_probe(struct usb_interface *intf, hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); - if (id->driver_info & BTUSB_AMP) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - data->hdev = hdev; SET_HCIDEV_DEV(hdev, &intf->dev); diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 9a7243d5db71..0c2f15235b4c 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -2361,7 +2361,6 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id) bcm4377->hdev = hdev; hdev->bus = HCI_PCI; - hdev->dev_type = HCI_PRIMARY; hdev->open = bcm4377_hci_open; hdev->close = bcm4377_hci_close; hdev->send = bcm4377_hci_send_frame; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index a26367e9fb19..17a2f158a0df 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -667,11 +667,6 @@ static int hci_uart_register_dev(struct hci_uart *hu) if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags)) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); - if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags)) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - /* Only call open() for the protocol after hdev is fully initialized as * open() (or a timer/workqueue it starts) may attempt to reference it. */ @@ -722,7 +717,6 @@ static int hci_uart_set_flags(struct hci_uart *hu, unsigned long flags) { unsigned long valid_flags = BIT(HCI_UART_RAW_DEVICE) | BIT(HCI_UART_RESET_ON_INIT) | - BIT(HCI_UART_CREATE_AMP) | BIT(HCI_UART_INIT_PENDING) | BIT(HCI_UART_EXT_CONFIG) | BIT(HCI_UART_VND_DETECT); diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 85c0d9b68f5f..89a22e9b3253 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -366,11 +366,6 @@ int hci_uart_register_device_priv(struct hci_uart *hu, if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags)) set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); - if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags)) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index 68c8c7e95d64..00bf7ae82c5b 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -37,7 +37,6 @@ #define HCI_UART_RAW_DEVICE 0 #define HCI_UART_RESET_ON_INIT 1 -#define HCI_UART_CREATE_AMP 2 #define HCI_UART_INIT_PENDING 3 #define HCI_UART_EXT_CONFIG 4 #define HCI_UART_VND_DETECT 5 diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 572d68d52965..28750a40f0ed 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -384,17 +384,10 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; struct sk_buff *skb; - __u8 dev_type; if (data->hdev) return -EBADFD; - /* bits 0-1 are dev_type (Primary or AMP) */ - dev_type = opcode & 0x03; - - if (dev_type != HCI_PRIMARY && dev_type != HCI_AMP) - return -EINVAL; - /* bits 2-5 are reserved (must be zero) */ if (opcode & 0x3c) return -EINVAL; @@ -412,7 +405,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) data->hdev = hdev; hdev->bus = HCI_VIRTUAL; - hdev->dev_type = dev_type; hci_set_drvdata(hdev, data); hdev->open = vhci_open_dev; @@ -634,7 +626,7 @@ static void vhci_open_timeout(struct work_struct *work) struct vhci_data *data = container_of(work, struct vhci_data, open_timeout.work); - vhci_create_device(data, amp ? HCI_AMP : HCI_PRIMARY); + vhci_create_device(data, 0x00); } static int vhci_open(struct inode *inode, struct file *file) diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 2ac70b560c46..18208e152a36 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -274,7 +274,6 @@ static int virtbt_probe(struct virtio_device *vdev) switch (type) { case VIRTIO_BT_CONFIG_TYPE_PRIMARY: - case VIRTIO_BT_CONFIG_TYPE_AMP: break; default: return -EINVAL; @@ -303,7 +302,6 @@ static int virtbt_probe(struct virtio_device *vdev) vbt->hdev = hdev; hdev->bus = HCI_VIRTIO; - hdev->dev_type = type; hci_set_drvdata(hdev, vbt); hdev->open = virtbt_open; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index de530262d824..fe932ca3bc8c 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -33,9 +33,6 @@ #define HCI_MAX_FRAME_SIZE (HCI_MAX_ACL_SIZE + 4) #define HCI_LINK_KEY_SIZE 16 -#define HCI_AMP_LINK_KEY_SIZE (2 * HCI_LINK_KEY_SIZE) - -#define HCI_MAX_AMP_ASSOC_SIZE 672 #define HCI_MAX_CPB_DATA_SIZE 252 @@ -71,26 +68,6 @@ #define HCI_SMD 9 #define HCI_VIRTIO 10 -/* HCI controller types */ -#define HCI_PRIMARY 0x00 -#define HCI_AMP 0x01 - -/* First BR/EDR Controller shall have ID = 0 */ -#define AMP_ID_BREDR 0x00 - -/* AMP controller types */ -#define AMP_TYPE_BREDR 0x00 -#define AMP_TYPE_80211 0x01 - -/* AMP controller status */ -#define AMP_STATUS_POWERED_DOWN 0x00 -#define AMP_STATUS_BLUETOOTH_ONLY 0x01 -#define AMP_STATUS_NO_CAPACITY 0x02 -#define AMP_STATUS_LOW_CAPACITY 0x03 -#define AMP_STATUS_MEDIUM_CAPACITY 0x04 -#define AMP_STATUS_HIGH_CAPACITY 0x05 -#define AMP_STATUS_FULL_CAPACITY 0x06 - /* HCI device quirks */ enum { /* When this quirk is set, the HCI Reset command is send when @@ -527,7 +504,6 @@ enum { #define ESCO_LINK 0x02 /* Low Energy links do not have defined link type. Use invented one */ #define LE_LINK 0x80 -#define AMP_LINK 0x81 #define ISO_LINK 0x82 #define INVALID_LINK 0xff @@ -943,56 +919,6 @@ struct hci_cp_io_capability_neg_reply { __u8 reason; } __packed; -#define HCI_OP_CREATE_PHY_LINK 0x0435 -struct hci_cp_create_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_ACCEPT_PHY_LINK 0x0436 -struct hci_cp_accept_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_DISCONN_PHY_LINK 0x0437 -struct hci_cp_disconn_phy_link { - __u8 phy_handle; - __u8 reason; -} __packed; - -struct ext_flow_spec { - __u8 id; - __u8 stype; - __le16 msdu; - __le32 sdu_itime; - __le32 acc_lat; - __le32 flush_to; -} __packed; - -#define HCI_OP_CREATE_LOGICAL_LINK 0x0438 -#define HCI_OP_ACCEPT_LOGICAL_LINK 0x0439 -struct hci_cp_create_accept_logical_link { - __u8 phy_handle; - struct ext_flow_spec tx_flow_spec; - struct ext_flow_spec rx_flow_spec; -} __packed; - -#define HCI_OP_DISCONN_LOGICAL_LINK 0x043a -struct hci_cp_disconn_logical_link { - __le16 log_handle; -} __packed; - -#define HCI_OP_LOGICAL_LINK_CANCEL 0x043b -struct hci_cp_logical_link_cancel { - __u8 phy_handle; - __u8 flow_spec_id; -} __packed; - #define HCI_OP_ENHANCED_SETUP_SYNC_CONN 0x043d struct hci_coding_format { __u8 id; @@ -1614,46 +1540,6 @@ struct hci_rp_read_enc_key_size { __u8 key_size; } __packed; -#define HCI_OP_READ_LOCAL_AMP_INFO 0x1409 -struct hci_rp_read_local_amp_info { - __u8 status; - __u8 amp_status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le32 max_pdu; - __u8 amp_type; - __le16 pal_cap; - __le16 max_assoc_size; - __le32 max_flush_to; - __le32 be_flush_to; -} __packed; - -#define HCI_OP_READ_LOCAL_AMP_ASSOC 0x140a -struct hci_cp_read_local_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 max_len; -} __packed; -struct hci_rp_read_local_amp_assoc { - __u8 status; - __u8 phy_handle; - __le16 rem_len; - __u8 frag[]; -} __packed; - -#define HCI_OP_WRITE_REMOTE_AMP_ASSOC 0x140b -struct hci_cp_write_remote_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 rem_len; - __u8 frag[]; -} __packed; -struct hci_rp_write_remote_amp_assoc { - __u8 status; - __u8 phy_handle; -} __packed; - #define HCI_OP_GET_MWS_TRANSPORT_CONFIG 0x140c #define HCI_OP_ENABLE_DUT_MODE 0x1803 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index be012f393bcb..431d0c8a0e27 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -126,7 +126,6 @@ enum suspended_state { struct hci_conn_hash { struct list_head list; unsigned int acl_num; - unsigned int amp_num; unsigned int sco_num; unsigned int iso_num; unsigned int le_num; @@ -341,14 +340,6 @@ struct adv_monitor { /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 -struct amp_assoc { - __u16 len; - __u16 offset; - __u16 rem_len; - __u16 len_so_far; - __u8 data[HCI_MAX_AMP_ASSOC_SIZE]; -}; - #define HCI_MAX_PAGES 3 struct hci_dev { @@ -361,7 +352,6 @@ struct hci_dev { unsigned long flags; __u16 id; __u8 bus; - __u8 dev_type; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; @@ -467,21 +457,6 @@ struct hci_dev { __u16 sniff_min_interval; __u16 sniff_max_interval; - __u8 amp_status; - __u32 amp_total_bw; - __u32 amp_max_bw; - __u32 amp_min_latency; - __u32 amp_max_pdu; - __u8 amp_type; - __u16 amp_pal_cap; - __u16 amp_assoc_size; - __u32 amp_max_flush_to; - __u32 amp_be_flush_to; - - struct amp_assoc loc_assoc; - - __u8 flow_ctl_mode; - unsigned int auto_accept_delay; unsigned long quirks; @@ -501,11 +476,6 @@ struct hci_dev { unsigned int le_pkts; unsigned int iso_pkts; - __u16 block_len; - __u16 block_mtu; - __u16 num_blocks; - __u16 block_cnt; - unsigned long acl_last_tx; unsigned long sco_last_tx; unsigned long le_last_tx; @@ -778,7 +748,6 @@ struct hci_conn { void *l2cap_data; void *sco_data; void *iso_data; - struct amp_mgr *amp_mgr; struct list_head link_list; struct hci_conn *parent; @@ -805,7 +774,6 @@ struct hci_chan { struct sk_buff_head data_q; unsigned int sent; __u8 state; - bool amp; }; struct hci_conn_params { @@ -1014,9 +982,6 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num++; break; - case AMP_LINK: - h->amp_num++; - break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) @@ -1043,9 +1008,6 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num--; break; - case AMP_LINK: - h->amp_num--; - break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) @@ -1067,8 +1029,6 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) switch (type) { case ACL_LINK: return h->acl_num; - case AMP_LINK: - return h->amp_num; case LE_LINK: return h->le_num; case SCO_LINK: @@ -1085,7 +1045,7 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->amp_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->iso_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) @@ -1610,10 +1570,6 @@ static inline void hci_conn_drop(struct hci_conn *conn) } break; - case AMP_LINK: - timeo = conn->disc_timeout; - break; - default: timeo = 0; break; diff --git a/include/uapi/linux/virtio_bt.h b/include/uapi/linux/virtio_bt.h index af798f4c9680..3cc7d633456b 100644 --- a/include/uapi/linux/virtio_bt.h +++ b/include/uapi/linux/virtio_bt.h @@ -13,7 +13,6 @@ enum virtio_bt_config_type { VIRTIO_BT_CONFIG_TYPE_PRIMARY = 0, - VIRTIO_BT_CONFIG_TYPE_AMP = 1, }; enum virtio_bt_config_vendor { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index f21e7c73021d..0c76dcde5361 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1168,8 +1168,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) list_for_each_entry(d, &hci_dev_list, list) { if (!test_bit(HCI_UP, &d->flags) || - hci_dev_test_flag(d, HCI_USER_CHANNEL) || - d->dev_type != HCI_PRIMARY) + hci_dev_test_flag(d, HCI_USER_CHANNEL)) continue; /* Simple routing: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b52125512985..7bc431af7b04 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -402,11 +402,6 @@ int hci_inquiry(void __user *arg) goto done; } - if (hdev->dev_type != HCI_PRIMARY) { - err = -EOPNOTSUPP; - goto done; - } - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; @@ -759,11 +754,6 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) goto done; } - if (hdev->dev_type != HCI_PRIMARY) { - err = -EOPNOTSUPP; - goto done; - } - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; @@ -917,7 +907,7 @@ int hci_get_dev_info(void __user *arg) strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; - di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); + di.type = (hdev->bus & 0x0f); di.flags = flags; di.pkt_type = hdev->pkt_type; if (lmp_bredr_capable(hdev)) { @@ -1033,8 +1023,7 @@ static void hci_power_on(struct work_struct *work) */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || - (hdev->dev_type == HCI_PRIMARY && - !bacmp(&hdev->bdaddr, BDADDR_ANY) && + (!bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_do_close(hdev); @@ -2642,21 +2631,7 @@ int hci_register_dev(struct hci_dev *hdev) if (!hdev->open || !hdev->close || !hdev->send) return -EINVAL; - /* Do not allow HCI_AMP devices to register at index 0, - * so the index can be used as the AMP controller ID. - */ - switch (hdev->dev_type) { - case HCI_PRIMARY: - id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); - break; - case HCI_AMP: - id = ida_alloc_range(&hci_index_ida, 1, HCI_MAX_ID - 1, - GFP_KERNEL); - break; - default: - return -EINVAL; - } - + id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); if (id < 0) return id; @@ -2708,12 +2683,10 @@ int hci_register_dev(struct hci_dev *hdev) hci_dev_set_flag(hdev, HCI_SETUP); hci_dev_set_flag(hdev, HCI_AUTO_OFF); - if (hdev->dev_type == HCI_PRIMARY) { - /* Assume BR/EDR support until proven otherwise (such as - * through reading supported features during init. - */ - hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); - } + /* Assume BR/EDR support until proven otherwise (such as + * through reading supported features during init. + */ + hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); write_lock(&hci_dev_list_lock); list_add(&hdev->list, &hci_dev_list); @@ -3249,17 +3222,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; - switch (hdev->dev_type) { - case HCI_PRIMARY: - hci_add_acl_hdr(skb, conn->handle, flags); - break; - case HCI_AMP: - hci_add_acl_hdr(skb, chan->handle, flags); - break; - default: - bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); - return; - } + hci_add_acl_hdr(skb, conn->handle, flags); list = skb_shinfo(skb)->frag_list; if (!list) { @@ -3419,9 +3382,6 @@ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote) case ACL_LINK: cnt = hdev->acl_cnt; break; - case AMP_LINK: - cnt = hdev->block_cnt; - break; case SCO_LINK: case ESCO_LINK: cnt = hdev->sco_cnt; @@ -3619,12 +3579,6 @@ static void hci_prio_recalculate(struct hci_dev *hdev, __u8 type) } -static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb) -{ - /* Calculate count of blocks used by this packet */ - return DIV_ROUND_UP(skb->len - HCI_ACL_HDR_SIZE, hdev->block_len); -} - static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type) { unsigned long last_tx; @@ -3738,81 +3692,15 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev) hci_prio_recalculate(hdev, ACL_LINK); } -static void hci_sched_acl_blk(struct hci_dev *hdev) -{ - unsigned int cnt = hdev->block_cnt; - struct hci_chan *chan; - struct sk_buff *skb; - int quote; - u8 type; - - BT_DBG("%s", hdev->name); - - if (hdev->dev_type == HCI_AMP) - type = AMP_LINK; - else - type = ACL_LINK; - - __check_timeout(hdev, cnt, type); - - while (hdev->block_cnt > 0 && - (chan = hci_chan_sent(hdev, type, "e))) { - u32 priority = (skb_peek(&chan->data_q))->priority; - while (quote > 0 && (skb = skb_peek(&chan->data_q))) { - int blocks; - - BT_DBG("chan %p skb %p len %d priority %u", chan, skb, - skb->len, skb->priority); - - /* Stop if priority has changed */ - if (skb->priority < priority) - break; - - skb = skb_dequeue(&chan->data_q); - - blocks = __get_blocks(hdev, skb); - if (blocks > hdev->block_cnt) - return; - - hci_conn_enter_active_mode(chan->conn, - bt_cb(skb)->force_active); - - hci_send_frame(hdev, skb); - hdev->acl_last_tx = jiffies; - - hdev->block_cnt -= blocks; - quote -= blocks; - - chan->sent += blocks; - chan->conn->sent += blocks; - } - } - - if (cnt != hdev->block_cnt) - hci_prio_recalculate(hdev, type); -} - static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); /* No ACL link over BR/EDR controller */ - if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_PRIMARY) - return; - - /* No AMP link over AMP controller */ - if (!hci_conn_num(hdev, AMP_LINK) && hdev->dev_type == HCI_AMP) + if (!hci_conn_num(hdev, ACL_LINK)) return; - switch (hdev->flow_ctl_mode) { - case HCI_FLOW_CTL_MODE_PACKET_BASED: - hci_sched_acl_pkt(hdev); - break; - - case HCI_FLOW_CTL_MODE_BLOCK_BASED: - hci_sched_acl_blk(hdev); - break; - } + hci_sched_acl_pkt(hdev); } static void hci_sched_le(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 97c6f34ba640..a487f9df8145 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -913,21 +913,6 @@ static u8 hci_cc_read_local_ext_features(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_read_flow_control_mode(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_read_flow_control_mode *rp = data; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - hdev->flow_ctl_mode = rp->mode; - - return rp->status; -} - static u8 hci_cc_read_buffer_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -1071,28 +1056,6 @@ static u8 hci_cc_write_page_scan_type(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_read_data_block_size(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_read_data_block_size *rp = data; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - hdev->block_mtu = __le16_to_cpu(rp->max_acl_len); - hdev->block_len = __le16_to_cpu(rp->block_len); - hdev->num_blocks = __le16_to_cpu(rp->num_blocks); - - hdev->block_cnt = hdev->num_blocks; - - BT_DBG("%s blk mtu %d cnt %d len %d", hdev->name, hdev->block_mtu, - hdev->block_cnt, hdev->block_len); - - return rp->status; -} - static u8 hci_cc_read_clock(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -1127,30 +1090,6 @@ unlock: return rp->status; } -static u8 hci_cc_read_local_amp_info(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_info *rp = data; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - hdev->amp_status = rp->amp_status; - hdev->amp_total_bw = __le32_to_cpu(rp->total_bw); - hdev->amp_max_bw = __le32_to_cpu(rp->max_bw); - hdev->amp_min_latency = __le32_to_cpu(rp->min_latency); - hdev->amp_max_pdu = __le32_to_cpu(rp->max_pdu); - hdev->amp_type = rp->amp_type; - hdev->amp_pal_cap = __le16_to_cpu(rp->pal_cap); - hdev->amp_assoc_size = __le16_to_cpu(rp->max_assoc_size); - hdev->amp_be_flush_to = __le32_to_cpu(rp->be_flush_to); - hdev->amp_max_flush_to = __le32_to_cpu(rp->max_flush_to); - - return rp->status; -} - static u8 hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -4120,12 +4059,6 @@ static const struct hci_cc { HCI_CC(HCI_OP_READ_PAGE_SCAN_TYPE, hci_cc_read_page_scan_type, sizeof(struct hci_rp_read_page_scan_type)), HCI_CC_STATUS(HCI_OP_WRITE_PAGE_SCAN_TYPE, hci_cc_write_page_scan_type), - HCI_CC(HCI_OP_READ_DATA_BLOCK_SIZE, hci_cc_read_data_block_size, - sizeof(struct hci_rp_read_data_block_size)), - HCI_CC(HCI_OP_READ_FLOW_CONTROL_MODE, hci_cc_read_flow_control_mode, - sizeof(struct hci_rp_read_flow_control_mode)), - HCI_CC(HCI_OP_READ_LOCAL_AMP_INFO, hci_cc_read_local_amp_info, - sizeof(struct hci_rp_read_local_amp_info)), HCI_CC(HCI_OP_READ_CLOCK, hci_cc_read_clock, sizeof(struct hci_rp_read_clock)), HCI_CC(HCI_OP_READ_ENC_KEY_SIZE, hci_cc_read_enc_key_size, @@ -4461,11 +4394,6 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, flex_array_size(ev, handles, ev->num))) return; - if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_PACKET_BASED) { - bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode); - return; - } - bt_dev_dbg(hdev, "num %d", ev->num); for (i = 0; i < ev->num; i++) { @@ -4533,78 +4461,6 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, queue_work(hdev->workqueue, &hdev->tx_work); } -static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev, - __u16 handle) -{ - struct hci_chan *chan; - - switch (hdev->dev_type) { - case HCI_PRIMARY: - return hci_conn_hash_lookup_handle(hdev, handle); - case HCI_AMP: - chan = hci_chan_lookup_handle(hdev, handle); - if (chan) - return chan->conn; - break; - default: - bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); - break; - } - - return NULL; -} - -static void hci_num_comp_blocks_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_num_comp_blocks *ev = data; - int i; - - if (!hci_ev_skb_pull(hdev, skb, HCI_EV_NUM_COMP_BLOCKS, - flex_array_size(ev, handles, ev->num_hndl))) - return; - - if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_BLOCK_BASED) { - bt_dev_err(hdev, "wrong event for mode %d", - hdev->flow_ctl_mode); - return; - } - - bt_dev_dbg(hdev, "num_blocks %d num_hndl %d", ev->num_blocks, - ev->num_hndl); - - for (i = 0; i < ev->num_hndl; i++) { - struct hci_comp_blocks_info *info = &ev->handles[i]; - struct hci_conn *conn = NULL; - __u16 handle, block_count; - - handle = __le16_to_cpu(info->handle); - block_count = __le16_to_cpu(info->blocks); - - conn = __hci_conn_lookup_handle(hdev, handle); - if (!conn) - continue; - - conn->sent -= block_count; - - switch (conn->type) { - case ACL_LINK: - case AMP_LINK: - hdev->block_cnt += block_count; - if (hdev->block_cnt > hdev->num_blocks) - hdev->block_cnt = hdev->num_blocks; - break; - - default: - bt_dev_err(hdev, "unknown type %d conn %p", - conn->type, conn); - break; - } - } - - queue_work(hdev->workqueue, &hdev->tx_work); -} - static void hci_mode_change_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -7520,9 +7376,6 @@ static const struct hci_ev { /* [0x3e = HCI_EV_LE_META] */ HCI_EV_REQ_VL(HCI_EV_LE_META, hci_le_meta_evt, sizeof(struct hci_ev_le_meta), HCI_MAX_EVENT_SIZE), - /* [0x48 = HCI_EV_NUM_COMP_BLOCKS] */ - HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, - sizeof(struct hci_ev_num_comp_blocks)), /* [0xff = HCI_EV_VENDOR] */ HCI_EV_VL(HCI_EV_VENDOR, msft_vendor_evt, 0, HCI_MAX_EVENT_SIZE), }; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 703b84bd48d5..69c2ba1e843e 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -485,7 +485,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) return NULL; ni = skb_put(skb, HCI_MON_NEW_INDEX_SIZE); - ni->type = hdev->dev_type; + ni->type = 0x00; /* Old hdev->dev_type */ ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, @@ -1007,9 +1007,6 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return -EOPNOTSUPP; - if (hdev->dev_type != HCI_PRIMARY) - return -EOPNOTSUPP; - switch (cmd) { case HCISETRAW: if (!capable(CAP_NET_ADMIN)) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 813c11d61bca..891cae8a30da 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3511,10 +3511,6 @@ static int hci_unconf_init_sync(struct hci_dev *hdev) /* Read Local Supported Features. */ static int hci_read_local_features_sync(struct hci_dev *hdev) { - /* Not all AMP controllers support this command */ - if (hdev->dev_type == HCI_AMP && !(hdev->commands[14] & 0x20)) - return 0; - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_FEATURES, 0, NULL, HCI_CMD_TIMEOUT); } @@ -3549,51 +3545,6 @@ static int hci_read_local_cmds_sync(struct hci_dev *hdev) return 0; } -/* Read Local AMP Info */ -static int hci_read_local_amp_info_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_AMP_INFO, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* Read Data Blk size */ -static int hci_read_data_block_size_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_DATA_BLOCK_SIZE, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* Read Flow Control Mode */ -static int hci_read_flow_control_mode_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_FLOW_CONTROL_MODE, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* Read Location Data */ -static int hci_read_location_data_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCATION_DATA, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* AMP Controller init stage 1 command sequence */ -static const struct hci_init_stage amp_init1[] = { - /* HCI_OP_READ_LOCAL_VERSION */ - HCI_INIT(hci_read_local_version_sync), - /* HCI_OP_READ_LOCAL_COMMANDS */ - HCI_INIT(hci_read_local_cmds_sync), - /* HCI_OP_READ_LOCAL_AMP_INFO */ - HCI_INIT(hci_read_local_amp_info_sync), - /* HCI_OP_READ_DATA_BLOCK_SIZE */ - HCI_INIT(hci_read_data_block_size_sync), - /* HCI_OP_READ_FLOW_CONTROL_MODE */ - HCI_INIT(hci_read_flow_control_mode_sync), - /* HCI_OP_READ_LOCATION_DATA */ - HCI_INIT(hci_read_location_data_sync), - {} -}; - static int hci_init1_sync(struct hci_dev *hdev) { int err; @@ -3607,28 +3558,9 @@ static int hci_init1_sync(struct hci_dev *hdev) return err; } - switch (hdev->dev_type) { - case HCI_PRIMARY: - hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_PACKET_BASED; - return hci_init_stage_sync(hdev, br_init1); - case HCI_AMP: - hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_BLOCK_BASED; - return hci_init_stage_sync(hdev, amp_init1); - default: - bt_dev_err(hdev, "Unknown device type %d", hdev->dev_type); - break; - } - - return 0; + return hci_init_stage_sync(hdev, br_init1); } -/* AMP Controller init stage 2 command sequence */ -static const struct hci_init_stage amp_init2[] = { - /* HCI_OP_READ_LOCAL_FEATURES */ - HCI_INIT(hci_read_local_features_sync), - {} -}; - /* Read Buffer Size (ACL mtu, max pkt, etc.) */ static int hci_read_buffer_size_sync(struct hci_dev *hdev) { @@ -3886,9 +3818,6 @@ static int hci_init2_sync(struct hci_dev *hdev) bt_dev_dbg(hdev, ""); - if (hdev->dev_type == HCI_AMP) - return hci_init_stage_sync(hdev, amp_init2); - err = hci_init_stage_sync(hdev, hci_init2); if (err) return err; @@ -4716,13 +4645,6 @@ static int hci_init_sync(struct hci_dev *hdev) if (err < 0) return err; - /* HCI_PRIMARY covers both single-mode LE, BR/EDR and dual-mode - * BR/EDR/LE type controllers. AMP controllers only need the - * first two stages of init. - */ - if (hdev->dev_type != HCI_PRIMARY) - return 0; - err = hci_init3_sync(hdev); if (err < 0) return err; @@ -4951,12 +4873,8 @@ int hci_dev_open_sync(struct hci_dev *hdev) * In case of user channel usage, it is not important * if a public address or static random address is * available. - * - * This check is only valid for BR/EDR controllers - * since AMP controllers do not have an address. */ if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - hdev->dev_type == HCI_PRIMARY && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY)) { ret = -EADDRNOTAVAIL; @@ -4991,8 +4909,7 @@ int hci_dev_open_sync(struct hci_dev *hdev) !hci_dev_test_flag(hdev, HCI_CONFIG) && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - hci_dev_test_flag(hdev, HCI_MGMT) && - hdev->dev_type == HCI_PRIMARY) { + hci_dev_test_flag(hdev, HCI_MGMT)) { ret = hci_powered_update_sync(hdev); mgmt_power_on(hdev, ret); } @@ -5137,8 +5054,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF); - if (!auto_off && hdev->dev_type == HCI_PRIMARY && - !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + if (!auto_off && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hci_dev_test_flag(hdev, HCI_MGMT)) __mgmt_power_off(hdev); @@ -5200,9 +5116,6 @@ int hci_dev_close_sync(struct hci_dev *hdev) hdev->flags &= BIT(HCI_RAW); hci_dev_clear_volatile_flags(hdev); - /* Controller radio is available but is currently powered down */ - hdev->amp_status = AMP_STATUS_POWERED_DOWN; - memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); bacpy(&hdev->random_addr, BDADDR_ANY); @@ -5239,8 +5152,7 @@ static int hci_power_on_sync(struct hci_dev *hdev) */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || - (hdev->dev_type == HCI_PRIMARY && - !bacmp(&hdev->bdaddr, BDADDR_ANY) && + (!bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_close_sync(hdev); @@ -5342,27 +5254,11 @@ int hci_stop_discovery_sync(struct hci_dev *hdev) return 0; } -static int hci_disconnect_phy_link_sync(struct hci_dev *hdev, u16 handle, - u8 reason) -{ - struct hci_cp_disconn_phy_link cp; - - memset(&cp, 0, sizeof(cp)); - cp.phy_handle = HCI_PHY_HANDLE(handle); - cp.reason = reason; - - return __hci_cmd_sync_status(hdev, HCI_OP_DISCONN_PHY_LINK, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); -} - static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { struct hci_cp_disconnect cp; - if (conn->type == AMP_LINK) - return hci_disconnect_phy_link_sync(hdev, conn->handle, reason); - if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) { /* This is a BIS connection, hci_conn_del will * do the necessary cleanup. diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index adc8f990f13e..5b509b767557 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3932,7 +3932,7 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, } static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, - u8 *data, u8 rsp_code, u8 amp_id) + u8 *data, u8 rsp_code) { struct l2cap_conn_req *req = (struct l2cap_conn_req *) data; struct l2cap_conn_rsp rsp; @@ -4011,17 +4011,8 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, status = L2CAP_CS_AUTHOR_PEND; chan->ops->defer(chan); } else { - /* Force pending result for AMP controllers. - * The connection will succeed after the - * physical link is up. - */ - if (amp_id == AMP_ID_BREDR) { - l2cap_state_change(chan, BT_CONFIG); - result = L2CAP_CR_SUCCESS; - } else { - l2cap_state_change(chan, BT_CONNECT2); - result = L2CAP_CR_PEND; - } + l2cap_state_change(chan, BT_CONNECT2); + result = L2CAP_CR_PEND; status = L2CAP_CS_NO_INFO; } } else { @@ -4086,7 +4077,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn, mgmt_device_connected(hdev, hcon, NULL, 0); hci_dev_unlock(hdev); - l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0); + l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP); return 0; } @@ -7491,10 +7482,6 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) struct l2cap_conn *conn = hcon->l2cap_data; int len; - /* For AMP controller do not create l2cap conn */ - if (!conn && hcon->hdev->dev_type != HCI_PRIMARY) - goto drop; - if (!conn) conn = l2cap_conn_add(hcon); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 965f621ef865..80f220b7e19d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -443,8 +443,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, count = 0; list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_PRIMARY && - !hci_dev_test_flag(d, HCI_UNCONFIGURED)) + if (!hci_dev_test_flag(d, HCI_UNCONFIGURED)) count++; } @@ -468,8 +467,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_PRIMARY && - !hci_dev_test_flag(d, HCI_UNCONFIGURED)) { + if (!hci_dev_test_flag(d, HCI_UNCONFIGURED)) { rp->index[count++] = cpu_to_le16(d->id); bt_dev_dbg(hdev, "Added hci%u", d->id); } @@ -503,8 +501,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, count = 0; list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_PRIMARY && - hci_dev_test_flag(d, HCI_UNCONFIGURED)) + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) count++; } @@ -528,8 +525,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_PRIMARY && - hci_dev_test_flag(d, HCI_UNCONFIGURED)) { + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) { rp->index[count++] = cpu_to_le16(d->id); bt_dev_dbg(hdev, "Added hci%u", d->id); } @@ -561,10 +557,8 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, read_lock(&hci_dev_list_lock); count = 0; - list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_PRIMARY || d->dev_type == HCI_AMP) - count++; - } + list_for_each_entry(d, &hci_dev_list, list) + count++; rp = kmalloc(struct_size(rp, entry, count), GFP_ATOMIC); if (!rp) { @@ -585,16 +579,10 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_PRIMARY) { - if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) - rp->entry[count].type = 0x01; - else - rp->entry[count].type = 0x00; - } else if (d->dev_type == HCI_AMP) { - rp->entry[count].type = 0x02; - } else { - continue; - } + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) + rp->entry[count].type = 0x01; + else + rp->entry[count].type = 0x00; rp->entry[count].bus = d->bus; rp->entry[count++].index = cpu_to_le16(d->id); @@ -9331,23 +9319,14 @@ void mgmt_index_added(struct hci_dev *hdev) if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - switch (hdev->dev_type) { - case HCI_PRIMARY: - if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { - mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, - NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS); - ev.type = 0x01; - } else { - mgmt_index_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, - HCI_MGMT_INDEX_EVENTS); - ev.type = 0x00; - } - break; - case HCI_AMP: - ev.type = 0x02; - break; - default: - return; + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { + mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, NULL, 0, + HCI_MGMT_UNCONF_INDEX_EVENTS); + ev.type = 0x01; + } else { + mgmt_index_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, + HCI_MGMT_INDEX_EVENTS); + ev.type = 0x00; } ev.bus = hdev->bus; @@ -9364,25 +9343,16 @@ void mgmt_index_removed(struct hci_dev *hdev) if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - switch (hdev->dev_type) { - case HCI_PRIMARY: - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); + mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); - if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { - mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, - NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS); - ev.type = 0x01; - } else { - mgmt_index_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, - HCI_MGMT_INDEX_EVENTS); - ev.type = 0x00; - } - break; - case HCI_AMP: - ev.type = 0x02; - break; - default: - return; + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { + mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0, + HCI_MGMT_UNCONF_INDEX_EVENTS); + ev.type = 0x01; + } else { + mgmt_index_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, + HCI_MGMT_INDEX_EVENTS); + ev.type = 0x00; } ev.bus = hdev->bus; -- cgit v1.2.3 From e4544c550eb1857845bb7114bac53edd04dc078f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 18 Mar 2024 13:06:45 +0100 Subject: virtio-mem: support suspend+resume With virtio-mem, primarily hibernation is problematic: as the machine shuts down, the virtio-mem device loses its state. Powering the machine back up is like losing a bunch of DIMMs. While there would be ways to add limited support, suspend+resume is more commonly used for VMs and "easier" to support cleanly. s2idle can be supported without any device dependencies. Similarly, one would expect suspend-to-ram (i.e., S3) to work out of the box. However, QEMU currently unplugs all device memory when resuming the VM, using a cold reset on the "wakeup" path. In order to support S3, we need a feature flag for the device to tell us if memory remains plugged when waking up. In the future, QEMU will implement this feature. So let's always support s2idle and support S3 with plugged memory only if the device indicates support. Block hibernation early using the PM notifier. Trying to hibernate now fails early: # echo disk > /sys/power/state [ 26.455369] PM: hibernation: hibernation entry [ 26.458271] virtio_mem virtio0: hibernation is not supported. [ 26.462498] PM: hibernation: hibernation exit -bash: echo: write error: Operation not permitted s2idle works even without the new feature bit: # echo s2idle > /sys/power/mem_sleep # echo mem > /sys/power/state [ 52.083725] PM: suspend entry (s2idle) [ 52.095950] Filesystems sync: 0.010 seconds [ 52.101493] Freezing user space processes [ 52.104213] Freezing user space processes completed (elapsed 0.001 seconds) [ 52.106520] OOM killer disabled. [ 52.107655] Freezing remaining freezable tasks [ 52.110880] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 52.113296] printk: Suspending console(s) (use no_console_suspend to debug) S3 does not work without the feature bit when memory is plugged: # echo deep > /sys/power/mem_sleep # echo mem > /sys/power/state [ 32.788281] PM: suspend entry (deep) [ 32.816630] Filesystems sync: 0.027 seconds [ 32.820029] Freezing user space processes [ 32.823870] Freezing user space processes completed (elapsed 0.001 seconds) [ 32.827756] OOM killer disabled. [ 32.829608] Freezing remaining freezable tasks [ 32.833842] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 32.837953] printk: Suspending console(s) (use no_console_suspend to debug) [ 32.916172] virtio_mem virtio0: suspend+resume with plugged memory is not supported [ 32.916181] virtio-pci 0000:00:02.0: PM: pci_pm_suspend(): virtio_pci_freeze+0x0/0x50 returns -1 [ 32.916197] virtio-pci 0000:00:02.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x170 returns -1 [ 32.916210] virtio-pci 0000:00:02.0: PM: failed to suspend async: error -1 But S3 works with the new feature bit when memory is plugged (patched QEMU): # echo deep > /sys/power/mem_sleep # echo mem > /sys/power/state [ 33.983694] PM: suspend entry (deep) [ 34.009828] Filesystems sync: 0.024 seconds [ 34.013589] Freezing user space processes [ 34.016722] Freezing user space processes completed (elapsed 0.001 seconds) [ 34.019092] OOM killer disabled. [ 34.020291] Freezing remaining freezable tasks [ 34.023549] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 34.026090] printk: Suspending console(s) (use no_console_suspend to debug) Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Xuan Zhuo Signed-off-by: David Hildenbrand Message-Id: <20240318120645.105664-1-david@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_mem.c | 68 +++++++++++++++++++++++++++++++++++++---- include/uapi/linux/virtio_mem.h | 2 ++ 2 files changed, 64 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 8e3223294442..51088d02de32 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -21,6 +21,7 @@ #include #include #include +#include #include @@ -252,6 +253,9 @@ struct virtio_mem { /* Memory notifier (online/offline events). */ struct notifier_block memory_notifier; + /* Notifier to block hibernation image storing/reloading. */ + struct notifier_block pm_notifier; + #ifdef CONFIG_PROC_VMCORE /* vmcore callback for /proc/vmcore handling in kdump mode */ struct vmcore_cb vmcore_cb; @@ -1111,6 +1115,25 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb, return rc; } +static int virtio_mem_pm_notifier_cb(struct notifier_block *nb, + unsigned long action, void *arg) +{ + struct virtio_mem *vm = container_of(nb, struct virtio_mem, + pm_notifier); + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + /* + * When restarting the VM, all memory is unplugged. Don't + * allow to hibernate and restore from an image. + */ + dev_err(&vm->vdev->dev, "hibernation is not supported.\n"); + return NOTIFY_BAD; + default: + return NOTIFY_OK; + } +} + /* * Set a range of pages PG_offline. Remember pages that were never onlined * (via generic_online_page()) using PageDirty(). @@ -2615,11 +2638,19 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm) rc = register_memory_notifier(&vm->memory_notifier); if (rc) goto out_unreg_group; - rc = register_virtio_mem_device(vm); + /* Block hibernation as early as possible. */ + vm->pm_notifier.priority = INT_MAX; + vm->pm_notifier.notifier_call = virtio_mem_pm_notifier_cb; + rc = register_pm_notifier(&vm->pm_notifier); if (rc) goto out_unreg_mem; + rc = register_virtio_mem_device(vm); + if (rc) + goto out_unreg_pm; return 0; +out_unreg_pm: + unregister_pm_notifier(&vm->pm_notifier); out_unreg_mem: unregister_memory_notifier(&vm->memory_notifier); out_unreg_group: @@ -2897,6 +2928,7 @@ static void virtio_mem_deinit_hotplug(struct virtio_mem *vm) /* unregister callbacks */ unregister_virtio_mem_device(vm); + unregister_pm_notifier(&vm->pm_notifier); unregister_memory_notifier(&vm->memory_notifier); /* @@ -2960,17 +2992,40 @@ static void virtio_mem_config_changed(struct virtio_device *vdev) #ifdef CONFIG_PM_SLEEP static int virtio_mem_freeze(struct virtio_device *vdev) { + struct virtio_mem *vm = vdev->priv; + /* - * When restarting the VM, all memory is usually unplugged. Don't - * allow to suspend/hibernate. + * We block hibernation using the PM notifier completely. The workqueue + * is already frozen by the PM core at this point, so we simply + * reset the device and cleanup the queues. */ - dev_err(&vdev->dev, "save/restore not supported.\n"); - return -EPERM; + if (pm_suspend_target_state != PM_SUSPEND_TO_IDLE && + vm->plugged_size && + !virtio_has_feature(vm->vdev, VIRTIO_MEM_F_PERSISTENT_SUSPEND)) { + dev_err(&vm->vdev->dev, + "suspending with plugged memory is not supported\n"); + return -EPERM; + } + + virtio_reset_device(vdev); + vdev->config->del_vqs(vdev); + vm->vq = NULL; + return 0; } static int virtio_mem_restore(struct virtio_device *vdev) { - return -EPERM; + struct virtio_mem *vm = vdev->priv; + int ret; + + ret = virtio_mem_init_vq(vm); + if (ret) + return ret; + virtio_device_ready(vdev); + + /* Let's check if anything changed. */ + virtio_mem_config_changed(vdev); + return 0; } #endif @@ -2979,6 +3034,7 @@ static unsigned int virtio_mem_features[] = { VIRTIO_MEM_F_ACPI_PXM, #endif VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, + VIRTIO_MEM_F_PERSISTENT_SUSPEND, }; static const struct virtio_device_id virtio_mem_id_table[] = { diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index e9122f1d0e0c..6e4b2cf6b7f1 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -90,6 +90,8 @@ #define VIRTIO_MEM_F_ACPI_PXM 0 /* unplugged memory must not be accessed */ #define VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE 1 +/* plugged memory will remain plugged when suspending+resuming */ +#define VIRTIO_MEM_F_PERSISTENT_SUSPEND 2 /* --- virtio-mem: guest -> host requests --- */ -- cgit v1.2.3 From 1693c5db6ab8262e6f5263f9d211855959aa5acd Mon Sep 17 00:00:00 2001 From: Abhishek Chauhan Date: Thu, 9 May 2024 14:18:33 -0700 Subject: net: Add additional bit to support clockid_t timestamp type tstamp_type is now set based on actual clockid_t compressed into 2 bits. To make the design scalable for future needs this commit bring in the change to extend the tstamp_type:1 to tstamp_type:2 to support other clockid_t timestamp. We now support CLOCK_TAI as part of tstamp_type as part of this commit with existing support CLOCK_MONOTONIC and CLOCK_REALTIME. Signed-off-by: Abhishek Chauhan Reviewed-by: Willem de Bruijn Reviewed-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20240509211834.3235191-3-quic_abchauha@quicinc.com Signed-off-by: Martin KaFai Lau --- include/linux/skbuff.h | 18 +++++++++++------ include/uapi/linux/bpf.h | 15 +++++++++----- net/core/filter.c | 46 ++++++++++++++++++++++++------------------ net/ipv4/ip_output.c | 5 ++++- net/ipv4/raw.c | 2 +- net/ipv4/tcp_ipv4.c | 2 ++ net/ipv6/ip6_output.c | 5 ++++- net/ipv6/raw.c | 2 +- net/ipv6/tcp_ipv6.c | 10 +++++++-- net/packet/af_packet.c | 7 +++---- tools/include/uapi/linux/bpf.h | 15 +++++++++----- 11 files changed, 81 insertions(+), 46 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3a721cc3b644..1e5c97daaa37 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -709,6 +709,8 @@ typedef unsigned char *sk_buff_data_t; enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, + SKB_CLOCK_TAI, + __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** @@ -957,7 +959,7 @@ struct sk_buff { /* private: */ __u8 __mono_tc_offset[0]; /* public: */ - __u8 tstamp_type:1; /* See skb_tstamp_type */ + __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; @@ -1087,15 +1089,16 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move tc_at_ingress or mono_delivery_time +/* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) -#define TC_AT_INGRESS_MASK (1 << 6) +#define SKB_TSTAMP_TYPE_MASK (3 << 6) +#define SKB_TSTAMP_TYPE_RSHIFT (6) +#define TC_AT_INGRESS_MASK (1 << 5) #else -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) -#define TC_AT_INGRESS_MASK (1 << 1) +#define SKB_TSTAMP_TYPE_MASK (3) +#define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) @@ -4216,6 +4219,9 @@ static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; + case CLOCK_TAI: + tstamp_type = SKB_CLOCK_TAI; + break; default: WARN_ON_ONCE(1); kt = 0; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 90706a47f6ff..25ea393cf084 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6207,12 +6207,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; diff --git a/net/core/filter.c b/net/core/filter.c index a3781a796da4..c6edfe9f41bc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7726,17 +7726,21 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, return -EOPNOTSUPP; switch (tstamp_type) { - case BPF_SKB_TSTAMP_DELIVERY_MONO: + case BPF_SKB_CLOCK_REALTIME: + skb->tstamp = tstamp; + skb->tstamp_type = SKB_CLOCK_REALTIME; + break; + case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; - case BPF_SKB_TSTAMP_UNSPEC: - if (tstamp) + case BPF_SKB_CLOCK_TAI: + if (!tstamp) return -EINVAL; - skb->tstamp = 0; - skb->tstamp_type = SKB_CLOCK_REALTIME; + skb->tstamp = tstamp; + skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; @@ -9387,16 +9391,17 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; - /* AX is needed because src_reg and dst_reg could be the same */ - __u8 tmp_reg = BPF_REG_AX; - - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, - SKB_BF_MONO_TC_OFFSET); - *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, - SKB_MONO_DELIVERY_TIME_MASK, 2); - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); - *insn++ = BPF_JMP_A(1); - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO); + BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); + BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); + BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); + BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); + *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); +#ifdef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); +#else + BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); +#endif return insn; } @@ -9439,10 +9444,11 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, - TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg, - TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2); + /* check if ingress mask bits is set */ + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); + *insn++ = BPF_JMP_A(4); + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); + *insn++ = BPF_JMP_A(2); /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ @@ -9479,7 +9485,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, /* goto */ *insn++ = BPF_JMP_A(2); /* : skb->tstamp_type */ - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index fe86cadfa85b..b90d0f78ac80 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1457,7 +1457,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; - skb->tstamp = cork->transmit_time; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid); /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4cb43401e0e0..1a0953650356 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -360,7 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 30ef0c8f5e92..8f70b8d1d1e5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3625,6 +3625,8 @@ void __init tcp_v4_init(void) */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + sk->sk_clockid = CLOCK_MONOTONIC; + per_cpu(ipv4_tcp_sk, cpu) = sk; } if (register_pernet_subsys(&tcp_sk_ops)) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1ab0f23d37bf..e7a19df3125e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1924,7 +1924,10 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; - skb->tstamp = cork->base.transmit_time; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid); ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 2eedf255600b..f838366e8256 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->protocol = htons(ETH_P_IPV6); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_put(skb, length); skb_reset_network_header(skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8333005c5c2e..750aa681779c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2387,8 +2387,14 @@ static struct inet_protosw tcpv6_protosw = { static int __net_init tcpv6_net_init(struct net *net) { - return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, - SOCK_RAW, IPPROTO_TCP, net); + int res; + + res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, + SOCK_RAW, IPPROTO_TCP, net); + if (!res) + net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC; + + return res; } static void __net_exit tcpv6_net_exit(struct net *net) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ea3ebc160e25..fce390887591 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2056,8 +2056,7 @@ retry: skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); - skb->tstamp = sockc.transmit_time; - + skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2584,7 +2583,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3062,7 +3061,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; - skb->tstamp = sockc.transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 90706a47f6ff..25ea393cf084 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6207,12 +6207,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; -- cgit v1.2.3 From 06e785aeb9ea8a43d0a3967c1ba6e69d758e82d4 Mon Sep 17 00:00:00 2001 From: Matt Jan Date: Tue, 14 May 2024 12:10:46 +0800 Subject: connector: Fix invalid conversion in cn_proc.h The implicit conversion from unsigned int to enum proc_cn_event is invalid, so explicitly cast it for compilation in a C++ compiler. /usr/include/linux/cn_proc.h: In function 'proc_cn_event valid_event(proc_cn_event)': /usr/include/linux/cn_proc.h:72:17: error: invalid conversion from 'unsigned int' to 'proc_cn_event' [-fpermissive] 72 | ev_type &= PROC_EVENT_ALL; | ^ | | | unsigned int Signed-off-by: Matt Jan Signed-off-by: David S. Miller --- include/uapi/linux/cn_proc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index f2afb7cc4926..18e3745b86cd 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -69,8 +69,7 @@ struct proc_input { static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type) { - ev_type &= PROC_EVENT_ALL; - return ev_type; + return (enum proc_cn_event)(ev_type & PROC_EVENT_ALL); } /* -- cgit v1.2.3 From ed7ee6a69f9289337af4835a908aa782263d4852 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 29 May 2024 10:39:01 +0200 Subject: statx: Update offset commentary for struct statx In commit 2a82bb02941f ("statx: stx_subvol"), a new member was added to struct statx, but the offset comment was not correct. Update it. Signed-off-by: John Garry Link: https://lore.kernel.org/r/20240529081725.3769290-1-john.g.garry@oracle.com Signed-off-by: Christian Brauner --- include/uapi/linux/stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 67626d535316..95770941ee2c 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,8 +126,8 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ + __u64 stx_subvol; /* Subvolume identifier */ __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; -- cgit v1.2.3 From 13c7c941e72908b8cce5a84b45a7b5e485ca12ed Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 29 May 2024 09:35:47 -0700 Subject: netdev: add qstat for csum complete Recent commit 0cfe71f45f42 ("netdev: add queue stats") added a lot of useful stats, but only those immediately needed by virtio. Presumably virtio does not support CHECKSUM_COMPLETE, so statistic for that form of checksumming wasn't included. Other drivers will definitely need it, in fact we expect it to be needed in net-next soon (mlx5). So let's add the definition of the counter for CHECKSUM_COMPLETE to uAPI in net already, so that the counters are in a more natural order (all subsequent counters have not been present in any released kernel, yet). Signed-off-by: Jakub Kicinski Reviewed-by: Joe Damato Fixes: 0cfe71f45f42 ("netdev: add queue stats") Link: https://lore.kernel.org/r/20240529163547.3693194-1-kuba@kernel.org Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 4 ++++ include/uapi/linux/netdev.h | 1 + tools/include/uapi/linux/netdev.h | 1 + 3 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 11a32373365a..959755be4d7f 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -349,6 +349,10 @@ attribute-sets: Number of packets dropped due to transient lack of resources, such as buffer space, host descriptors etc. type: uint + - + name: rx-csum-complete + doc: Number of packets that were marked as CHECKSUM_COMPLETE. + type: uint - name: rx-csum-unnecessary doc: Number of packets that were marked as CHECKSUM_UNNECESSARY. diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index a8188202413e..43742ac5b00d 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -148,6 +148,7 @@ enum { NETDEV_A_QSTATS_RX_ALLOC_FAIL, NETDEV_A_QSTATS_RX_HW_DROPS, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, NETDEV_A_QSTATS_RX_CSUM_NONE, NETDEV_A_QSTATS_RX_CSUM_BAD, diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index a8188202413e..43742ac5b00d 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -148,6 +148,7 @@ enum { NETDEV_A_QSTATS_RX_ALLOC_FAIL, NETDEV_A_QSTATS_RX_HW_DROPS, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, NETDEV_A_QSTATS_RX_CSUM_NONE, NETDEV_A_QSTATS_RX_CSUM_BAD, -- cgit v1.2.3 From 7bc4244c882a7d7d79f4afefc50893244eb11d07 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 1 Jun 2024 07:28:21 +0200 Subject: Revert "VT: Use macros to define ioctls" This reverts commit 8c467f3300591a206fa8dcc6988d768910799872. Turns out this breaks many architectures as the vt ioctls do not all match up everywhere due to historical reasons, so the original commit is invalid for many values. Reported-by: Nick Bowler Reported-by: Arnd Bergmann Reported-by: Jiri Slaby Reported-by: Christian Zigotzky Reported-by: Michael Ellerman Cc: Al Viro Cc: Alexey Gladkov Link: https://lore.kernel.org/r/ad4e561c-1d49-4f25-882c-7a36c6b1b5c0@draconx.ca Link: https://lore.kernel.org/r/0da9785e-ba44-4718-9d08-4e96c1ba7ab2@kernel.org Link: https://lore.kernel.org/all/34d848f4-670b-4493-bf21-130ef862521b@xenosoft.de/ Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/kd.h | 96 ++++++++++++++++++++++++------------------------- 1 file changed, 47 insertions(+), 49 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h index 8ddb2219a84b..6b384065c013 100644 --- a/include/uapi/linux/kd.h +++ b/include/uapi/linux/kd.h @@ -5,61 +5,60 @@ #include /* 0x4B is 'K', to avoid collision with termios and vt */ -#define KD_IOCTL_BASE 'K' -#define GIO_FONT _IO(KD_IOCTL_BASE, 0x60) /* gets font in expanded form */ -#define PIO_FONT _IO(KD_IOCTL_BASE, 0x61) /* use font in expanded form */ +#define GIO_FONT 0x4B60 /* gets font in expanded form */ +#define PIO_FONT 0x4B61 /* use font in expanded form */ -#define GIO_FONTX _IO(KD_IOCTL_BASE, 0x6B) /* get font using struct consolefontdesc */ -#define PIO_FONTX _IO(KD_IOCTL_BASE, 0x6C) /* set font using struct consolefontdesc */ +#define GIO_FONTX 0x4B6B /* get font using struct consolefontdesc */ +#define PIO_FONTX 0x4B6C /* set font using struct consolefontdesc */ struct consolefontdesc { unsigned short charcount; /* characters in font (256 or 512) */ unsigned short charheight; /* scan lines per character (1-32) */ char __user *chardata; /* font data in expanded form */ }; -#define PIO_FONTRESET _IO(KD_IOCTL_BASE, 0x6D) /* reset to default font */ +#define PIO_FONTRESET 0x4B6D /* reset to default font */ -#define GIO_CMAP _IO(KD_IOCTL_BASE, 0x70) /* gets colour palette on VGA+ */ -#define PIO_CMAP _IO(KD_IOCTL_BASE, 0x71) /* sets colour palette on VGA+ */ +#define GIO_CMAP 0x4B70 /* gets colour palette on VGA+ */ +#define PIO_CMAP 0x4B71 /* sets colour palette on VGA+ */ -#define KIOCSOUND _IO(KD_IOCTL_BASE, 0x2F) /* start sound generation (0 for off) */ -#define KDMKTONE _IO(KD_IOCTL_BASE, 0x30) /* generate tone */ +#define KIOCSOUND 0x4B2F /* start sound generation (0 for off) */ +#define KDMKTONE 0x4B30 /* generate tone */ -#define KDGETLED _IO(KD_IOCTL_BASE, 0x31) /* return current led state */ -#define KDSETLED _IO(KD_IOCTL_BASE, 0x32) /* set led state [lights, not flags] */ +#define KDGETLED 0x4B31 /* return current led state */ +#define KDSETLED 0x4B32 /* set led state [lights, not flags] */ #define LED_SCR 0x01 /* scroll lock led */ #define LED_NUM 0x02 /* num lock led */ #define LED_CAP 0x04 /* caps lock led */ -#define KDGKBTYPE _IO(KD_IOCTL_BASE, 0x33) /* get keyboard type */ +#define KDGKBTYPE 0x4B33 /* get keyboard type */ #define KB_84 0x01 #define KB_101 0x02 /* this is what we always answer */ #define KB_OTHER 0x03 -#define KDADDIO _IO(KD_IOCTL_BASE, 0x34) /* add i/o port as valid */ -#define KDDELIO _IO(KD_IOCTL_BASE, 0x35) /* del i/o port as valid */ -#define KDENABIO _IO(KD_IOCTL_BASE, 0x36) /* enable i/o to video board */ -#define KDDISABIO _IO(KD_IOCTL_BASE, 0x37) /* disable i/o to video board */ +#define KDADDIO 0x4B34 /* add i/o port as valid */ +#define KDDELIO 0x4B35 /* del i/o port as valid */ +#define KDENABIO 0x4B36 /* enable i/o to video board */ +#define KDDISABIO 0x4B37 /* disable i/o to video board */ -#define KDSETMODE _IO(KD_IOCTL_BASE, 0x3A) /* set text/graphics mode */ +#define KDSETMODE 0x4B3A /* set text/graphics mode */ #define KD_TEXT 0x00 #define KD_GRAPHICS 0x01 #define KD_TEXT0 0x02 /* obsolete */ #define KD_TEXT1 0x03 /* obsolete */ -#define KDGETMODE _IO(KD_IOCTL_BASE, 0x3B) /* get current mode */ +#define KDGETMODE 0x4B3B /* get current mode */ -#define KDMAPDISP _IO(KD_IOCTL_BASE, 0x3C) /* map display into address space */ -#define KDUNMAPDISP _IO(KD_IOCTL_BASE, 0x3D) /* unmap display from address space */ +#define KDMAPDISP 0x4B3C /* map display into address space */ +#define KDUNMAPDISP 0x4B3D /* unmap display from address space */ typedef char scrnmap_t; #define E_TABSZ 256 -#define GIO_SCRNMAP _IO(KD_IOCTL_BASE, 0x40) /* get screen mapping from kernel */ -#define PIO_SCRNMAP _IO(KD_IOCTL_BASE, 0x41) /* put screen mapping table in kernel */ -#define GIO_UNISCRNMAP _IO(KD_IOCTL_BASE, 0x69) /* get full Unicode screen mapping */ -#define PIO_UNISCRNMAP _IO(KD_IOCTL_BASE, 0x6A) /* set full Unicode screen mapping */ +#define GIO_SCRNMAP 0x4B40 /* get screen mapping from kernel */ +#define PIO_SCRNMAP 0x4B41 /* put screen mapping table in kernel */ +#define GIO_UNISCRNMAP 0x4B69 /* get full Unicode screen mapping */ +#define PIO_UNISCRNMAP 0x4B6A /* set full Unicode screen mapping */ -#define GIO_UNIMAP _IO(KD_IOCTL_BASE, 0x66) /* get unicode-to-font mapping from kernel */ +#define GIO_UNIMAP 0x4B66 /* get unicode-to-font mapping from kernel */ struct unipair { unsigned short unicode; unsigned short fontpos; @@ -68,8 +67,8 @@ struct unimapdesc { unsigned short entry_ct; struct unipair __user *entries; }; -#define PIO_UNIMAP _IO(KD_IOCTL_BASE, 0x67) /* put unicode-to-font mapping in kernel */ -#define PIO_UNIMAPCLR _IO(KD_IOCTL_BASE, 0x68) /* clear table, possibly advise hash algorithm */ +#define PIO_UNIMAP 0x4B67 /* put unicode-to-font mapping in kernel */ +#define PIO_UNIMAPCLR 0x4B68 /* clear table, possibly advise hash algorithm */ struct unimapinit { unsigned short advised_hashsize; /* 0 if no opinion */ unsigned short advised_hashstep; /* 0 if no opinion */ @@ -84,19 +83,19 @@ struct unimapinit { #define K_MEDIUMRAW 0x02 #define K_UNICODE 0x03 #define K_OFF 0x04 -#define KDGKBMODE _IO(KD_IOCTL_BASE, 0x44) /* gets current keyboard mode */ -#define KDSKBMODE _IO(KD_IOCTL_BASE, 0x45) /* sets current keyboard mode */ +#define KDGKBMODE 0x4B44 /* gets current keyboard mode */ +#define KDSKBMODE 0x4B45 /* sets current keyboard mode */ #define K_METABIT 0x03 #define K_ESCPREFIX 0x04 -#define KDGKBMETA _IO(KD_IOCTL_BASE, 0x62) /* gets meta key handling mode */ -#define KDSKBMETA _IO(KD_IOCTL_BASE, 0x63) /* sets meta key handling mode */ +#define KDGKBMETA 0x4B62 /* gets meta key handling mode */ +#define KDSKBMETA 0x4B63 /* sets meta key handling mode */ #define K_SCROLLLOCK 0x01 #define K_NUMLOCK 0x02 #define K_CAPSLOCK 0x04 -#define KDGKBLED _IO(KD_IOCTL_BASE, 0x64) /* get led flags (not lights) */ -#define KDSKBLED _IO(KD_IOCTL_BASE, 0x65) /* set led flags (not lights) */ +#define KDGKBLED 0x4B64 /* get led flags (not lights) */ +#define KDSKBLED 0x4B65 /* set led flags (not lights) */ struct kbentry { unsigned char kb_table; @@ -108,15 +107,15 @@ struct kbentry { #define K_ALTTAB 0x02 #define K_ALTSHIFTTAB 0x03 -#define KDGKBENT _IO(KD_IOCTL_BASE, 0x46) /* gets one entry in translation table */ -#define KDSKBENT _IO(KD_IOCTL_BASE, 0x47) /* sets one entry in translation table */ +#define KDGKBENT 0x4B46 /* gets one entry in translation table */ +#define KDSKBENT 0x4B47 /* sets one entry in translation table */ struct kbsentry { unsigned char kb_func; unsigned char kb_string[512]; }; -#define KDGKBSENT _IO(KD_IOCTL_BASE, 0x48) /* gets one function key string entry */ -#define KDSKBSENT _IO(KD_IOCTL_BASE, 0x49) /* sets one function key string entry */ +#define KDGKBSENT 0x4B48 /* gets one function key string entry */ +#define KDSKBSENT 0x4B49 /* sets one function key string entry */ struct kbdiacr { unsigned char diacr, base, result; @@ -125,8 +124,8 @@ struct kbdiacrs { unsigned int kb_cnt; /* number of entries in following array */ struct kbdiacr kbdiacr[256]; /* MAX_DIACR from keyboard.h */ }; -#define KDGKBDIACR _IO(KD_IOCTL_BASE, 0x4A) /* read kernel accent table */ -#define KDSKBDIACR _IO(KD_IOCTL_BASE, 0x4B) /* write kernel accent table */ +#define KDGKBDIACR 0x4B4A /* read kernel accent table */ +#define KDSKBDIACR 0x4B4B /* write kernel accent table */ struct kbdiacruc { unsigned int diacr, base, result; @@ -135,16 +134,16 @@ struct kbdiacrsuc { unsigned int kb_cnt; /* number of entries in following array */ struct kbdiacruc kbdiacruc[256]; /* MAX_DIACR from keyboard.h */ }; -#define KDGKBDIACRUC _IO(KD_IOCTL_BASE, 0xFA) /* read kernel accent table - UCS */ -#define KDSKBDIACRUC _IO(KD_IOCTL_BASE, 0xFB) /* write kernel accent table - UCS */ +#define KDGKBDIACRUC 0x4BFA /* read kernel accent table - UCS */ +#define KDSKBDIACRUC 0x4BFB /* write kernel accent table - UCS */ struct kbkeycode { unsigned int scancode, keycode; }; -#define KDGETKEYCODE _IO(KD_IOCTL_BASE, 0x4C) /* read kernel keycode table entry */ -#define KDSETKEYCODE _IO(KD_IOCTL_BASE, 0x4D) /* write kernel keycode table entry */ +#define KDGETKEYCODE 0x4B4C /* read kernel keycode table entry */ +#define KDSETKEYCODE 0x4B4D /* write kernel keycode table entry */ -#define KDSIGACCEPT _IO(KD_IOCTL_BASE, 0x4E) /* accept kbd generated signals */ +#define KDSIGACCEPT 0x4B4E /* accept kbd generated signals */ struct kbd_repeat { int delay; /* in msec; <= 0: don't change */ @@ -152,11 +151,10 @@ struct kbd_repeat { /* earlier this field was misnamed "rate" */ }; -#define KDKBDREP _IO(KD_IOCTL_BASE, 0x52) /* set keyboard delay/repeat rate; - * actually used values are returned - */ +#define KDKBDREP 0x4B52 /* set keyboard delay/repeat rate; + * actually used values are returned */ -#define KDFONTOP _IO(KD_IOCTL_BASE, 0x72) /* font operations */ +#define KDFONTOP 0x4B72 /* font operations */ struct console_font_op { unsigned int op; /* operation code KD_FONT_OP_* */ -- cgit v1.2.3 From 1d8491d3e726984343dd8c3cdbe2f2b47cfdd928 Mon Sep 17 00:00:00 2001 From: Paolo Pisati Date: Sat, 1 Jun 2024 17:32:54 +0200 Subject: m68k: amiga: Turn off Warp1260 interrupts during boot On an Amiga 1200 equipped with a Warp1260 accelerator, an interrupt storm coming from the accelerator board causes the machine to crash in local_irq_enable() or auto_irq_enable(). Disabling interrupts for the Warp1260 in amiga_parse_bootinfo() fixes the problem. Link: https://lore.kernel.org/r/ZkjwzVwYeQtyAPrL@amaterasu.local Cc: stable Signed-off-by: Paolo Pisati Reviewed-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20240601153254.186225-1-p.pisati@gmail.com Signed-off-by: Geert Uytterhoeven --- arch/m68k/amiga/config.c | 9 +++++++++ include/uapi/linux/zorro_ids.h | 3 +++ 2 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index d4b170c861bf..0147130dc34e 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -180,6 +180,15 @@ int __init amiga_parse_bootinfo(const struct bi_record *record) dev->slotsize = be16_to_cpu(cd->cd_SlotSize); dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr); dev->boardsize = be32_to_cpu(cd->cd_BoardSize); + + /* CS-LAB Warp 1260 workaround */ + if (be16_to_cpu(dev->rom.er_Manufacturer) == ZORRO_MANUF(ZORRO_PROD_CSLAB_WARP_1260) && + dev->rom.er_Product == ZORRO_PROD(ZORRO_PROD_CSLAB_WARP_1260)) { + + /* turn off all interrupts */ + pr_info("Warp 1260 card detected: applying interrupt storm workaround\n"); + *(uint32_t *)(dev->boardaddr + 0x1000) = 0xfff; + } } else pr_warn("amiga_parse_bootinfo: too many AutoConfig devices\n"); #endif /* CONFIG_ZORRO */ diff --git a/include/uapi/linux/zorro_ids.h b/include/uapi/linux/zorro_ids.h index 6e574d7b7d79..393f2ee9c042 100644 --- a/include/uapi/linux/zorro_ids.h +++ b/include/uapi/linux/zorro_ids.h @@ -449,6 +449,9 @@ #define ZORRO_PROD_VMC_ISDN_BLASTER_Z2 ZORRO_ID(VMC, 0x01, 0) #define ZORRO_PROD_VMC_HYPERCOM_4 ZORRO_ID(VMC, 0x02, 0) +#define ZORRO_MANUF_CSLAB 0x1400 +#define ZORRO_PROD_CSLAB_WARP_1260 ZORRO_ID(CSLAB, 0x65, 0) + #define ZORRO_MANUF_INFORMATION 0x157C #define ZORRO_PROD_INFORMATION_ISDN_ENGINE_I ZORRO_ID(INFORMATION, 0x64, 0) -- cgit v1.2.3 From 1d17568e74dedbcb54d36af0662a15128297d681 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 30 May 2024 19:08:35 +0200 Subject: net/sched: cls_flower: add support for matching tunnel control flags extend cls_flower to match TUNNEL_FLAGS_PRESENT bits in tunnel metadata. Suggested-by: Ilya Maximets Acked-by: Jamal Hadi Salim Signed-off-by: Davide Caratti Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- include/uapi/linux/pkt_cls.h | 3 +++ net/sched/cls_flower.c | 56 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 58 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 229fc925ec3a..b6d38f5fd7c0 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -554,6 +554,9 @@ enum { TCA_FLOWER_KEY_SPI, /* be32 */ TCA_FLOWER_KEY_SPI_MASK, /* be32 */ + TCA_FLOWER_KEY_ENC_FLAGS, /* u32 */ + TCA_FLOWER_KEY_ENC_FLAGS_MASK, /* u32 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index fd9a6f20b60b..eef570c577ac 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -41,6 +41,12 @@ #define TCA_FLOWER_KEY_CT_FLAGS_MASK \ (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) +#define TUNNEL_FLAGS_PRESENT (\ + _BITUL(IP_TUNNEL_CSUM_BIT) | \ + _BITUL(IP_TUNNEL_DONT_FRAGMENT_BIT) | \ + _BITUL(IP_TUNNEL_OAM_BIT) | \ + _BITUL(IP_TUNNEL_CRIT_OPT_BIT)) + struct fl_flow_key { struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; @@ -75,6 +81,7 @@ struct fl_flow_key { struct flow_dissector_key_l2tpv3 l2tpv3; struct flow_dissector_key_ipsec ipsec; struct flow_dissector_key_cfm cfm; + struct flow_dissector_key_enc_flags enc_flags; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -732,6 +739,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_U32, + TUNNEL_FLAGS_PRESENT), + [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_U32, + TUNNEL_FLAGS_PRESENT), }; static const struct nla_policy @@ -1825,6 +1836,21 @@ static int fl_set_key_cfm(struct nlattr **tb, return 0; } +static int fl_set_key_enc_flags(struct nlattr **tb, u32 *flags_key, + u32 *flags_mask, struct netlink_ext_ack *extack) +{ + /* mask is mandatory for flags */ + if (NL_REQ_ATTR_CHECK(extack, NULL, tb, TCA_FLOWER_KEY_ENC_FLAGS_MASK)) { + NL_SET_ERR_MSG(extack, "missing enc_flags mask"); + return -EINVAL; + } + + *flags_key = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS]); + *flags_mask = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS_MASK]); + + return 0; +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -2059,9 +2085,16 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (ret) return ret; - if (tb[TCA_FLOWER_KEY_FLAGS]) + if (tb[TCA_FLOWER_KEY_FLAGS]) { ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags, extack); + if (ret) + return ret; + } + + if (tb[TCA_FLOWER_KEY_ENC_FLAGS]) + ret = fl_set_key_enc_flags(tb, &key->enc_flags.flags, + &mask->enc_flags.flags, extack); return ret; } @@ -2175,6 +2208,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPSEC, ipsec); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_CFM, cfm); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_FLAGS, enc_flags); skb_flow_dissector_init(dissector, keys, cnt); } @@ -3291,6 +3326,22 @@ err_cfm_opts: return err; } +static int fl_dump_key_enc_flags(struct sk_buff *skb, + struct flow_dissector_key_enc_flags *key, + struct flow_dissector_key_enc_flags *mask) +{ + if (!memchr_inv(mask, 0, sizeof(*mask))) + return 0; + + if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS, key->flags)) + return -EMSGSIZE; + + if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS_MASK, mask->flags)) + return -EMSGSIZE; + + return 0; +} + static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, struct flow_dissector_key_enc_opts *enc_opts) { @@ -3592,6 +3643,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) goto nla_put_failure; + if (fl_dump_key_enc_flags(skb, &key->enc_flags, &mask->enc_flags)) + goto nla_put_failure; + return 0; nla_put_failure: -- cgit v1.2.3 From 310ec03841a36e3f45fb528f0dfdfe5b9e84b037 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Wed, 5 Jun 2024 13:26:05 +1200 Subject: dma-buf: align fd_flags and heap_flags with dma_heap_allocation_data dma_heap_allocation_data defines the UAPI as follows: struct dma_heap_allocation_data { __u64 len; __u32 fd; __u32 fd_flags; __u64 heap_flags; }; However, dma_heap_buffer_alloc() casts both fd_flags and heap_flags into unsigned int. We're inconsistent with types in the non UAPI arguments. This patch fixes it. Signed-off-by: Barry Song Acked-by: John Stultz Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20240605012605.5341-1-21cnbao@gmail.com --- drivers/dma-buf/dma-heap.c | 4 ++-- include/uapi/linux/dma-heap.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 84ae708fafe7..2298ca5e112e 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -50,8 +50,8 @@ static struct class *dma_heap_class; static DEFINE_XARRAY_ALLOC(dma_heap_minors); static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, - unsigned int fd_flags, - unsigned int heap_flags) + u32 fd_flags, + u64 heap_flags) { struct dma_buf *dmabuf; int fd; diff --git a/include/uapi/linux/dma-heap.h b/include/uapi/linux/dma-heap.h index 6f84fa08e074..a4cf716a49fa 100644 --- a/include/uapi/linux/dma-heap.h +++ b/include/uapi/linux/dma-heap.h @@ -19,7 +19,7 @@ #define DMA_HEAP_VALID_FD_FLAGS (O_CLOEXEC | O_ACCMODE) /* Currently no heap flags */ -#define DMA_HEAP_VALID_HEAP_FLAGS (0) +#define DMA_HEAP_VALID_HEAP_FLAGS (0ULL) /** * struct dma_heap_allocation_data - metadata passed from userspace for -- cgit v1.2.3 From 6fef518594bcb7e374f809717281bd02894929f8 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 25 Apr 2024 15:07:01 -0700 Subject: KVM: x86: Add a capability to configure bus frequency for APIC timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add KVM_CAP_X86_APIC_BUS_CYCLES_NS capability to configure the APIC bus clock frequency for APIC timer emulation. Allow KVM_ENABLE_CAPABILITY(KVM_CAP_X86_APIC_BUS_CYCLES_NS) to set the frequency in nanoseconds. When using this capability, the user space VMM should configure CPUID leaf 0x15 to advertise the frequency. Vishal reported that the TDX guest kernel expects a 25MHz APIC bus frequency but ends up getting interrupts at a significantly higher rate. The TDX architecture hard-codes the core crystal clock frequency to 25MHz and mandates exposing it via CPUID leaf 0x15. The TDX architecture does not allow the VMM to override the value. In addition, per Intel SDM: "The APIC timer frequency will be the processor’s bus clock or core crystal clock frequency (when TSC/core crystal clock ratio is enumerated in CPUID leaf 0x15) divided by the value specified in the divide configuration register." The resulting 25MHz APIC bus frequency conflicts with the KVM hardcoded APIC bus frequency of 1GHz. The KVM doesn't enumerate CPUID leaf 0x15 to the guest unless the user space VMM sets it using KVM_SET_CPUID. If the CPUID leaf 0x15 is enumerated, the guest kernel uses it as the APIC bus frequency. If not, the guest kernel measures the frequency based on other known timers like the ACPI timer or the legacy PIT. As reported by Vishal the TDX guest kernel expects a 25MHz timer frequency but gets timer interrupt more frequently due to the 1GHz frequency used by KVM. To ensure that the guest doesn't have a conflicting view of the APIC bus frequency, allow the userspace to tell KVM to use the same frequency that TDX mandates instead of the default 1Ghz. Reported-by: Vishal Annapurve Closes: https://lore.kernel.org/lkml/20231006011255.4163884-1-vannapurve@google.com Signed-off-by: Isaku Yamahata Reviewed-by: Rick Edgecombe Co-developed-by: Reinette Chatre Signed-off-by: Reinette Chatre Reviewed-by: Xiaoyao Li Reviewed-by: Yuan Yao Link: https://lore.kernel.org/r/6748a4c12269e756f0c48680da8ccc5367c31ce7.1714081726.git.reinette.chatre@intel.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 17 +++++++++++++++++ arch/x86/kvm/x86.c | 27 +++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 3 files changed, 45 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index a71d91978d9e..cb31ae071cba 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8070,6 +8070,23 @@ error/annotated fault. See KVM_EXIT_MEMORY_FAULT for more information. +7.35 KVM_CAP_X86_APIC_BUS_CYCLES_NS +----------------------------------- + +:Architectures: x86 +:Target: VM +:Parameters: args[0] is the desired APIC bus clock rate, in nanoseconds +:Returns: 0 on success, -EINVAL if args[0] contains an invalid value for the + frequency or if any vCPUs have been created, -ENXIO if a virtual + local APIC has not been created using KVM_CREATE_IRQCHIP. + +This capability sets the VM's APIC bus clock frequency, used by KVM's in-kernel +virtual APIC when emulating APIC timers. KVM's default value can be retrieved +by KVM_CHECK_EXTENSION. + +Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the +core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. + 8. Other capabilities. ====================== diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9bdc841d5928..09e3460bcbc5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4706,6 +4706,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: + r = APIC_BUS_CYCLE_NS_DEFAULT; + break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; @@ -6746,6 +6749,30 @@ split_irqchip_unlock: } mutex_unlock(&kvm->lock); break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: { + u64 bus_cycle_ns = cap->args[0]; + u64 unused; + + /* + * Guard against overflow in tmict_to_ns(). 128 is the highest + * divide value that can be programmed in APIC_TDCR. + */ + r = -EINVAL; + if (!bus_cycle_ns || + check_mul_overflow((u64)U32_MAX * 128, bus_cycle_ns, &unused)) + break; + + r = 0; + mutex_lock(&kvm->lock); + if (!irqchip_in_kernel(kvm)) + r = -ENXIO; + else if (kvm->created_vcpus) + r = -EINVAL; + else + kvm->arch.apic_bus_cycle_ns = bus_cycle_ns; + mutex_unlock(&kvm->lock); + break; + } default: r = -EINVAL; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d03842abae57..ec998e6b6555 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -917,6 +917,7 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 236 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From 0c7dd00de018ff70b3452c424901816e26366a8a Mon Sep 17 00:00:00 2001 From: Aseda Aboagye Date: Tue, 4 Jun 2024 23:10:47 +0000 Subject: input: Add event code for accessibility key HUTRR116 added support for a new usage titled "System Accessibility Binding" which toggles a system-wide bound accessibility UI or command. This commit simply adds a new event code for the usage. Signed-off-by: Aseda Aboagye Acked-by: Dmitry Torokhov Link: https://lore.kernel.org/r/Zl-e97O9nvudco5z@google.com Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-debug.c | 1 + drivers/hid/hid-input.c | 1 + include/uapi/linux/input-event-codes.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 87a961cae775..322ed63a98ab 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -3366,6 +3366,7 @@ static const char *keys[KEY_MAX + 1] = { [KEY_CAMERA_ACCESS_ENABLE] = "CameraAccessEnable", [KEY_CAMERA_ACCESS_DISABLE] = "CameraAccessDisable", [KEY_CAMERA_ACCESS_TOGGLE] = "CameraAccessToggle", + [KEY_ACCESSIBILITY] = "Accessibility", [KEY_DICTATE] = "Dictate", [KEY_MICMUTE] = "MicrophoneMute", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index e03d300d2bac..d5a6e89c3086 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -836,6 +836,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel if ((usage->hid & 0xf0) == 0xa0) { /* SystemControl */ switch (usage->hid & 0xf) { case 0x9: map_key_clear(KEY_MICMUTE); break; + case 0xa: map_key_clear(KEY_ACCESSIBILITY); break; default: goto ignore; } break; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 03edf2ccdf6c..39f11ec676fa 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -618,6 +618,7 @@ #define KEY_CAMERA_ACCESS_ENABLE 0x24b /* Enables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_DISABLE 0x24c /* Disables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_TOGGLE 0x24d /* Toggles the current state of the camera access control. (HUTRR72) */ +#define KEY_ACCESSIBILITY 0x24e /* Toggles the system bound accessibility UI/command (HUTRR116) */ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ -- cgit v1.2.3 From 22d6d060ac77955291deb43efc2f3f4f9632c6cb Mon Sep 17 00:00:00 2001 From: Aseda Aboagye Date: Tue, 4 Jun 2024 23:16:32 +0000 Subject: input: Add support for "Do Not Disturb" HUTRR94 added support for a new usage titled "System Do Not Disturb" which toggles a system-wide Do Not Disturb setting. This commit simply adds a new event code for the usage. Signed-off-by: Aseda Aboagye Acked-by: Dmitry Torokhov Link: https://lore.kernel.org/r/Zl-gUHE70s7wCAoB@google.com Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-debug.c | 1 + drivers/hid/hid-input.c | 8 ++++++++ include/uapi/linux/input-event-codes.h | 1 + 3 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 322ed63a98ab..d5abfe652fb5 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -3367,6 +3367,7 @@ static const char *keys[KEY_MAX + 1] = { [KEY_CAMERA_ACCESS_DISABLE] = "CameraAccessDisable", [KEY_CAMERA_ACCESS_TOGGLE] = "CameraAccessToggle", [KEY_ACCESSIBILITY] = "Accessibility", + [KEY_DO_NOT_DISTURB] = "DoNotDisturb", [KEY_DICTATE] = "Dictate", [KEY_MICMUTE] = "MicrophoneMute", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index d5a6e89c3086..8bb16e9b94aa 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -833,6 +833,14 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel break; } + if ((usage->hid & 0xf0) == 0x90) { /* SystemControl*/ + switch (usage->hid & 0xf) { + case 0xb: map_key_clear(KEY_DO_NOT_DISTURB); break; + default: goto ignore; + } + break; + } + if ((usage->hid & 0xf0) == 0xa0) { /* SystemControl */ switch (usage->hid & 0xf) { case 0x9: map_key_clear(KEY_MICMUTE); break; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 39f11ec676fa..a4206723f503 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -619,6 +619,7 @@ #define KEY_CAMERA_ACCESS_DISABLE 0x24c /* Disables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_TOGGLE 0x24d /* Toggles the current state of the camera access control. (HUTRR72) */ #define KEY_ACCESSIBILITY 0x24e /* Toggles the system bound accessibility UI/command (HUTRR116) */ +#define KEY_DO_NOT_DISTURB 0x24f /* Toggles the system-wide "Do Not Disturb" control (HUTRR94)*/ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ -- cgit v1.2.3 From 62096c48394b49e326056a62780fb67b60edde91 Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Mon, 6 May 2024 17:49:16 +0900 Subject: media: v4l2-ctrls: Add average QP control Add a control V4L2_CID_MPEG_VIDEO_AVERAGE_QP to report the average QP value of the current encoded frame. The value applies to the last dequeued capture buffer. Signed-off-by: Ming Qian Reviewed-by: Hans Verkuil Signed-off-by: Sebastian Fricke Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 14 ++++++++++++++ drivers/media/v4l2-core/v4l2-ctrls-defs.c | 5 +++++ include/uapi/linux/v4l2-controls.h | 2 ++ 3 files changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 2a165ae063fb..4a379bd9e3fb 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -1653,6 +1653,20 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - Quantization parameter for a P frame for FWHT. Valid range: from 1 to 31. +``V4L2_CID_MPEG_VIDEO_AVERAGE_QP (integer)`` + This read-only control returns the average QP value of the currently + encoded frame. The value applies to the last dequeued capture buffer + (VIDIOC_DQBUF). Its valid range depends on the encoding format and parameters. + For H264, its valid range is from 0 to 51. + For HEVC, its valid range is from 0 to 51 for 8 bit and + from 0 to 63 for 10 bit. + For H263 and MPEG4, its valid range is from 1 to 31. + For VP8, its valid range is from 0 to 127. + For VP9, its valid range is from 0 to 255. + If the codec's MIN_QP and MAX_QP are set, then the QP will meet both requirements. + Codecs need to always use the specified range, rather then a HW custom range. + Applicable to encoders + .. raw:: latex \normalsize diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 8696eb1cdd61..1ea52011247a 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -970,6 +970,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_LTR_COUNT: return "LTR Count"; case V4L2_CID_MPEG_VIDEO_FRAME_LTR_INDEX: return "Frame LTR Index"; case V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES: return "Use LTR Frames"; + case V4L2_CID_MPEG_VIDEO_AVERAGE_QP: return "Average QP Value"; case V4L2_CID_FWHT_I_FRAME_QP: return "FWHT I-Frame QP Value"; case V4L2_CID_FWHT_P_FRAME_QP: return "FWHT P-Frame QP Value"; @@ -1507,6 +1508,10 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, *max = 0xffffffffffffLL; *step = 1; break; + case V4L2_CID_MPEG_VIDEO_AVERAGE_QP: + *type = V4L2_CTRL_TYPE_INTEGER; + *flags |= V4L2_CTRL_FLAG_READ_ONLY; + break; case V4L2_CID_PIXEL_RATE: *type = V4L2_CTRL_TYPE_INTEGER64; *flags |= V4L2_CTRL_FLAG_READ_ONLY; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 99c3f5e99da7..974fd254e573 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -898,6 +898,8 @@ enum v4l2_mpeg_video_av1_level { V4L2_MPEG_VIDEO_AV1_LEVEL_7_3 = 23 }; +#define V4L2_CID_MPEG_VIDEO_AVERAGE_QP (V4L2_CID_CODEC_BASE + 657) + /* MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */ #define V4L2_CID_CODEC_CX2341X_BASE (V4L2_CTRL_CLASS_CODEC | 0x1000) #define V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE (V4L2_CID_CODEC_CX2341X_BASE+0) -- cgit v1.2.3 From 85542adb65ecd7cc0e442e8befef74f2ed07f5f6 Mon Sep 17 00:00:00 2001 From: Thomas Prescher Date: Wed, 8 May 2024 15:25:01 +0200 Subject: KVM: x86: Add KVM_RUN_X86_GUEST_MODE kvm_run flag When a vCPU is interrupted by a signal while running a nested guest, KVM will exit to userspace with L2 state. However, userspace has no way to know whether it sees L1 or L2 state (besides calling KVM_GET_STATS_FD, which does not have a stable ABI). This causes multiple problems: The simplest one is L2 state corruption when userspace marks the sregs as dirty. See this mailing list thread [1] for a complete discussion. Another problem is that if userspace decides to continue by emulating instructions, it will unknowingly emulate with L2 state as if L1 doesn't exist, which can be considered a weird guest escape. Introduce a new flag, KVM_RUN_X86_GUEST_MODE, in the kvm_run data structure, which is set when the vCPU exited while running a nested guest. Also introduce a new capability, KVM_CAP_X86_GUEST_MODE, to advertise the functionality to userspace. [1] https://lore.kernel.org/kvm/20240416123558.212040-1-julian.stecklina@cyberus-technology.de/T/#m280aadcb2e10ae02c191a7dc4ed4b711a74b1f55 Signed-off-by: Thomas Prescher Signed-off-by: Julian Stecklina Link: https://lore.kernel.org/r/20240508132502.184428-1-julian.stecklina@cyberus-technology.de Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 17 +++++++++++++++++ arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/x86.c | 3 +++ include/uapi/linux/kvm.h | 1 + 4 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 67edb84317ef..42d1d9518bf2 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6419,6 +6419,9 @@ affect the device's behavior. Current defined flags:: #define KVM_RUN_X86_SMM (1 << 0) /* x86, set if bus lock detected in VM */ #define KVM_RUN_X86_BUS_LOCK (1 << 1) + /* x86, set if the VCPU is executing a nested (L2) guest */ + #define KVM_RUN_X86_GUEST_MODE (1 << 2) + /* arm64, set for KVM_EXIT_DEBUG */ #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) @@ -8089,6 +8092,20 @@ by KVM_CHECK_EXTENSION. Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. +7.36 KVM_CAP_X86_GUEST_MODE +------------------------------ + +:Architectures: x86 +:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP. + +The presence of this capability indicates that KVM_RUN will update the +KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the +vCPU was executing nested guest code when it exited. + +KVM exits with the register state of either the L1 or L2 guest +depending on which executed at the time of an exit. Userspace must +take care to differentiate between these cases. + 8. Other capabilities. ====================== diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 9fae1b73b529..b85671d9c8aa 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ struct kvm_ioapic_state { #define KVM_RUN_X86_SMM (1 << 0) #define KVM_RUN_X86_BUS_LOCK (1 << 1) +#define KVM_RUN_X86_GUEST_MODE (1 << 2) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bfe3dba56e24..33e41103fcde 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4704,6 +4704,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_MEMORY_FAULT_INFO: + case KVM_CAP_X86_GUEST_MODE: r = 1; break; case KVM_CAP_X86_APIC_BUS_CYCLES_NS: @@ -10277,6 +10278,8 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; + if (is_guest_mode(vcpu)) + kvm_run->flags |= KVM_RUN_X86_GUEST_MODE; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ec998e6b6555..a6ac00ec77ad 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -918,6 +918,7 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 236 +#define KVM_CAP_X86_GUEST_MODE 237 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From f328a26eeb5380bc74e58cb9c3280a4908452df7 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 3 Jun 2024 17:55:55 -0400 Subject: dlm: introduce DLM_LSFL_SOFTIRQ_SAFE Introduce a new external lockspace flag DLM_LSFL_SOFTIRQ_SAFE. A lockspace user will set this flag if it can handle dlm running the callback functions from softirq context. When not set, dlm will continue to run callback functions from the dlm_callback workqueue. The new lockspace flag cannot be used for user space lockspaces, so a uapi placeholder definition is used for the new flag value. Signed-off-by: Alexander Aring Signed-off-by: David Teigland --- fs/dlm/lockspace.c | 3 +++ include/linux/dlm.h | 17 ++++++++++++++++- include/uapi/linux/dlm.h | 2 ++ 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 8a4351ee9a42..a7ac0fcb4ef3 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -629,6 +629,9 @@ int dlm_new_user_lockspace(const char *name, const char *cluster, void *ops_arg, int *ops_result, dlm_lockspace_t **lockspace) { + if (flags & DLM_LSFL_SOFTIRQ) + return -EINVAL; + return __dlm_new_lockspace(name, cluster, flags, lvblen, ops, ops_arg, ops_result, lockspace); } diff --git a/include/linux/dlm.h b/include/linux/dlm.h index c58c4f790c04..bacda9898f2b 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -35,6 +35,9 @@ struct dlm_lockspace_ops { int num_slots, int our_slot, uint32_t generation); }; +/* only relevant for kernel lockspaces, will be removed in future */ +#define DLM_LSFL_SOFTIRQ __DLM_LSFL_RESERVED0 + /* * dlm_new_lockspace * @@ -55,6 +58,11 @@ struct dlm_lockspace_ops { * used to select the directory node. Must be the same on all nodes. * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. + * DLM_LSFL_SOFTIRQ + * dlm request callbacks (ast, bast) are softirq safe. Flag should be + * preferred by users. Will be default in some future. If set the + * strongest context for ast, bast callback is softirq as it avoids + * an additional context switch. * * lvblen: length of lvb in bytes. Must be multiple of 8. * dlm_new_lockspace() returns an error if this does not match @@ -121,7 +129,14 @@ int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); * call. * * AST routines should not block (at least not for long), but may make - * any locking calls they please. + * any locking calls they please. If DLM_LSFL_SOFTIRQ for kernel + * users of dlm_new_lockspace() is passed the ast and bast callbacks + * can be processed in softirq context. Also some of the callback + * contexts are in the same context as the DLM lock request API, users + * must not hold locks while calling dlm lock request API and trying + * to acquire this lock in the callback again, this will end in a + * lock recursion. For newer implementation the DLM_LSFL_SOFTIRQ + * should be used. */ int dlm_lock(dlm_lockspace_t *lockspace, diff --git a/include/uapi/linux/dlm.h b/include/uapi/linux/dlm.h index e7e905fb0bb2..4eaf835780b0 100644 --- a/include/uapi/linux/dlm.h +++ b/include/uapi/linux/dlm.h @@ -71,6 +71,8 @@ struct dlm_lksb { /* DLM_LSFL_TIMEWARN is deprecated and reserved. DO NOT USE! */ #define DLM_LSFL_TIMEWARN 0x00000002 #define DLM_LSFL_NEWEXCL 0x00000008 +/* currently reserved due in-kernel use */ +#define __DLM_LSFL_RESERVED0 0x00000010 #endif /* _UAPI__DLM_DOT_H__ */ -- cgit v1.2.3 From c1d8bd8d777d55f6708ca6e47c54dbe9f66f9bbb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 May 2024 12:09:49 +0200 Subject: wifi: cfg80211: add regulatory flag to allow VLP AP operation Add a regulatory flag to allow VLP AP operation even on channels otherwise marked NO_IR, which may be possible in some regulatory domains/countries. Note that this requires checking also when the beacon is changed, since that may change the regulatory power type. Reviewed-by: Miriam Rachel Korenblit Signed-off-by: Johannes Berg Link: https://msgid.link/20240523120945.63792ce19790.Ie2a02750d283b78fbf3c686b10565fb0388889e2@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/chan.c | 37 ++++++++++++++++++++++++++----------- net/wireless/nl80211.c | 27 +++++++++++++++++++++++++-- net/wireless/reg.c | 2 ++ net/wireless/trace.h | 15 +++++++++------ 6 files changed, 74 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 45ffeb110d36..6f992aff74ae 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -125,6 +125,8 @@ struct wiphy; * @IEEE80211_CHAN_CAN_MONITOR: This channel can be used for monitor * mode even in the presence of other (regulatory) restrictions, * even if it is otherwise disabled. + * @IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP: Allow using this channel for AP operation + * with very low power (VLP), even if otherwise set to NO_IR. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = BIT(0), @@ -152,6 +154,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = BIT(22), IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = BIT(23), IEEE80211_CHAN_CAN_MONITOR = BIT(24), + IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP = BIT(25), }; #define IEEE80211_CHAN_NO_HT40 \ @@ -8806,9 +8809,12 @@ static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy, * @relax: allow IR-relaxation conditions to apply (e.g. another * interface connected already on the same channel) * NOTE: If this is set, wiphy mutex must be held. + * @reg_power: &enum ieee80211_ap_reg_power value indicating the + * advertised/used 6 GHz regulatory power setting */ struct cfg80211_beaconing_check_config { enum nl80211_iftype iftype; + enum ieee80211_ap_reg_power reg_power; bool relax; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f917bc6c9b6f..6ae3997061b6 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4277,6 +4277,8 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_CAN_MONITOR: This channel can be used in monitor * mode despite other (regulatory) restrictions, even if the channel is * otherwise completely disabled. + * @NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP: This channel can be used for a + * very low power (VLP) AP, despite being NO_IR. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4320,6 +4322,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT, NL80211_FREQUENCY_ATTR_CAN_MONITOR, + NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4529,6 +4532,8 @@ enum nl80211_sched_scan_match_attr { * Should be used together with %NL80211_RRF_DFS only. * @NL80211_RRF_NO_6GHZ_VLP_CLIENT: Client connection to VLP AP not allowed * @NL80211_RRF_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP not allowed + * @NL80211_RRF_ALLOW_6GHZ_VLP_AP: Very low power (VLP) AP can be permitted + * despite NO_IR configuration. */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4553,6 +4558,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_DFS_CONCURRENT = 1<<21, NL80211_RRF_NO_6GHZ_VLP_CLIENT = 1<<22, NL80211_RRF_NO_6GHZ_AFC_CLIENT = 1<<23, + NL80211_RRF_ALLOW_6GHZ_VLP_AP = 1<<24, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 8b1796130b28..bf2fdcd42019 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -1523,28 +1523,38 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype, - bool check_no_ir) + u32 prohibited_flags, + u32 permitting_flags) { - bool res; - u32 prohibited_flags = IEEE80211_CHAN_DISABLED; + bool res, check_radar; int dfs_required; - trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir); + trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, + prohibited_flags, + permitting_flags); - if (check_no_ir) - prohibited_flags |= IEEE80211_CHAN_NO_IR; + if (!_cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_DISABLED, 0)) + return false; dfs_required = cfg80211_chandef_dfs_required(wiphy, chandef, iftype); - if (dfs_required != 0) - prohibited_flags |= IEEE80211_CHAN_RADAR; + check_radar = dfs_required != 0; if (dfs_required > 0 && cfg80211_chandef_dfs_available(wiphy, chandef)) { /* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */ - prohibited_flags = IEEE80211_CHAN_DISABLED; + prohibited_flags &= ~IEEE80211_CHAN_NO_IR; + check_radar = false; } - res = _cfg80211_chandef_usable(wiphy, chandef, prohibited_flags, 0); + if (check_radar && + !_cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_RADAR, 0)) + return false; + + res = _cfg80211_chandef_usable(wiphy, chandef, + prohibited_flags, + permitting_flags); trace_cfg80211_return_bool(res); return res; @@ -1555,6 +1565,7 @@ bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, struct cfg80211_beaconing_check_config *cfg) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + u32 permitting_flags = 0; bool check_no_ir = true; /* @@ -1569,8 +1580,12 @@ bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, chandef->chan); } + if (cfg->reg_power == IEEE80211_REG_VLP_AP) + permitting_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP; + return _cfg80211_reg_can_beacon(wiphy, chandef, cfg->iftype, - check_no_ir); + check_no_ir ? IEEE80211_CHAN_NO_IR : 0, + permitting_flags); } EXPORT_SYMBOL(cfg80211_reg_check_beaconing); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4628280abf1d..a94e73c133f7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1207,6 +1207,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_CAN_MONITOR) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_CAN_MONITOR)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -5954,6 +5957,7 @@ static int nl80211_validate_ap_phy_operation(struct cfg80211_ap_settings *params static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beaconing_check_config beacon_check = {}; unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -6103,8 +6107,13 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms->chandef, - wdev->iftype)) { + beacon_check.iftype = wdev->iftype; + beacon_check.relax = true; + beacon_check.reg_power = + cfg80211_get_6ghz_power_type(params->beacon.tail, + params->beacon.tail_len); + if (!cfg80211_reg_check_beaconing(&rdev->wiphy, ¶ms->chandef, + &beacon_check)) { err = -EINVAL; goto out; } @@ -6261,6 +6270,7 @@ out: static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beaconing_check_config beacon_check = {}; unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -6287,6 +6297,19 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) if (err) goto out; + /* recheck beaconing is permitted with possibly changed power type */ + beacon_check.iftype = wdev->iftype; + beacon_check.relax = true; + beacon_check.reg_power = + cfg80211_get_6ghz_power_type(params->beacon.tail, + params->beacon.tail_len); + if (!cfg80211_reg_check_beaconing(&rdev->wiphy, + &wdev->links[link_id].ap.chandef, + &beacon_check)) { + err = -EINVAL; + goto out; + } + attr = info->attrs[NL80211_ATTR_FILS_DISCOVERY]; if (attr) { err = nl80211_parse_fils_discovery(rdev, attr, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3cef0021a3db..4a27f3823e25 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1600,6 +1600,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; + if (rd_flags & NL80211_RRF_ALLOW_6GHZ_VLP_AP) + channel_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP; return channel_flags; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 6ef9294747e3..5c26f065bd68 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3389,23 +3389,26 @@ TRACE_EVENT(cfg80211_cqm_rssi_notify, TRACE_EVENT(cfg80211_reg_can_beacon, TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype, bool check_no_ir), - TP_ARGS(wiphy, chandef, iftype, check_no_ir), + enum nl80211_iftype iftype, u32 prohibited_flags, + u32 permitting_flags), + TP_ARGS(wiphy, chandef, iftype, prohibited_flags, permitting_flags), TP_STRUCT__entry( WIPHY_ENTRY CHAN_DEF_ENTRY __field(enum nl80211_iftype, iftype) - __field(bool, check_no_ir) + __field(u32, prohibited_flags) + __field(u32, permitting_flags) ), TP_fast_assign( WIPHY_ASSIGN; CHAN_DEF_ASSIGN(chandef); __entry->iftype = iftype; - __entry->check_no_ir = check_no_ir; + __entry->prohibited_flags = prohibited_flags; + __entry->permitting_flags = permitting_flags; ), - TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d check_no_ir=%s", + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d prohibited_flags=0x%x permitting_flags=0x%x", WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype, - BOOL_TO_STR(__entry->check_no_ir)) + __entry->prohibited_flags, __entry->permitting_flags) ); TRACE_EVENT(cfg80211_chandef_dfs_required, -- cgit v1.2.3 From a3cfe84cca28f205761a0450016593b0d728165e Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Thu, 6 Jun 2024 07:58:50 -0700 Subject: bpf: Add CHECKSUM_COMPLETE to bpf test progs Add special flag to validate that TC BPF program properly updates checksum information in skb. Signed-off-by: Vadim Fedorenko Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Kicinski Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240606145851.229116-1-vadfed@meta.com --- include/uapi/linux/bpf.h | 2 ++ net/bpf/test_run.c | 28 +++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 2 ++ 3 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 25ea393cf084..35bcf52dbc65 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1425,6 +1425,8 @@ enum { #define BPF_F_TEST_RUN_ON_CPU (1U << 0) /* If set, XDP frames will be transmitted after processing */ #define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) +/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */ +#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 36ae54f57bf5..3c965e32fc33 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -983,7 +983,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; - if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) + if ((kattr->test.flags & ~BPF_F_TEST_SKB_CHECKSUM_COMPLETE) || + kattr->test.cpu || kattr->test.batch_size) return -EINVAL; data = bpf_test_init(kattr, kattr->test.data_size_in, @@ -1031,6 +1032,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); + if (ctx && ctx->ifindex > 1) { dev = dev_get_by_index(net, ctx->ifindex); if (!dev) { @@ -1066,9 +1068,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); + ret = convert___skb_to_skb(skb, ctx); if (ret) goto out; + + if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) { + const int off = skb_network_offset(skb); + int len = skb->len - off; + + skb->csum = skb_checksum(skb, off, len, 0); + skb->ip_summed = CHECKSUM_COMPLETE; + } + ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false); if (ret) goto out; @@ -1083,6 +1095,20 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, } memset(__skb_push(skb, hh_len), 0, hh_len); } + + if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) { + const int off = skb_network_offset(skb); + int len = skb->len - off; + __wsum csum; + + csum = skb_checksum(skb, off, len, 0); + + if (csum_fold(skb->csum) != csum_fold(csum)) { + ret = -EBADMSG; + goto out; + } + } + convert_skb_to___skb(skb, ctx); size = skb->len; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 25ea393cf084..35bcf52dbc65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1425,6 +1425,8 @@ enum { #define BPF_F_TEST_RUN_ON_CPU (1U << 0) /* If set, XDP frames will be transmitted after processing */ #define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) +/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */ +#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { -- cgit v1.2.3 From d25a92ccae6bed02327b63d138e12e7806830f78 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Fri, 14 Jun 2024 02:00:30 +0800 Subject: net/smc: Introduce IPPROTO_SMC This patch allows to create smc socket via AF_INET, similar to the following code, /* create v4 smc sock */ v4 = socket(AF_INET, SOCK_STREAM, IPPROTO_SMC); /* create v6 smc sock */ v6 = socket(AF_INET6, SOCK_STREAM, IPPROTO_SMC); There are several reasons why we believe it is appropriate here: 1. For smc sockets, it actually use IPv4 (AF-INET) or IPv6 (AF-INET6) address. There is no AF_SMC address at all. 2. Create smc socket in the AF_INET(6) path, which allows us to reuse the infrastructure of AF_INET(6) path, such as common ebpf hooks. Otherwise, smc have to implement it again in AF_SMC path. Signed-off-by: D. Wythe Reviewed-by: Wenjia Zhang Reviewed-by: Dust Li Tested-by: Niklas Schnelle Tested-by: Wenjia Zhang Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 2 + net/smc/Makefile | 2 +- net/smc/af_smc.c | 16 ++++- net/smc/smc_inet.c | 159 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_inet.h | 22 +++++++ 5 files changed, 198 insertions(+), 3 deletions(-) create mode 100644 net/smc/smc_inet.c create mode 100644 net/smc/smc_inet.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX diff --git a/net/smc/Makefile b/net/smc/Makefile index 2c510d543058..60f1c87d5212 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o -smc-y += smc_tracepoint.o +smc-y += smc_tracepoint.o smc_inet.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o smc-$(CONFIG_SMC_LO) += smc_loopback.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 7ee6f37813d6..73a875573e7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -54,6 +54,7 @@ #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_loopback.h" +#include "smc_inet.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -3575,10 +3576,15 @@ static int __init smc_init(void) pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); goto out_lo; } - + rc = smc_inet_init(); + if (rc) { + pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); + goto out_ulp; + } static_branch_enable(&tcp_have_smc); return 0; - +out_ulp: + tcp_unregister_ulp(&smc_ulp_ops); out_lo: smc_loopback_exit(); out_ib: @@ -3615,6 +3621,7 @@ out_pernet_subsys: static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); + smc_inet_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); @@ -3642,4 +3649,9 @@ MODULE_DESCRIPTION("smc socket address family"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_SMC); MODULE_ALIAS_TCP_ULP("smc"); +/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1); +#if IS_ENABLED(CONFIG_IPV6) +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1); +#endif /* CONFIG_IPV6 */ MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME); diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c new file mode 100644 index 000000000000..bece346dd8e9 --- /dev/null +++ b/net/smc/smc_inet.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + * + * Copyright IBM Corp. 2016, 2018 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe + */ + +#include +#include + +#include "smc_inet.h" +#include "smc.h" + +static int smc_inet_init_sock(struct sock *sk); + +static struct proto smc_inet_prot = { + .name = "INET_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v4_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet_stream_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet_prot, + .ops = &smc_inet_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static struct proto smc_inet6_prot = { + .name = "INET6_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v6_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet6_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet6_prot, + .ops = &smc_inet6_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; +#endif /* CONFIG_IPV6 */ + +static int smc_inet_init_sock(struct sock *sk) +{ + struct net *net = sock_net(sk); + + /* init common smc sock */ + smc_sk_init(net, sk, IPPROTO_SMC); + /* create clcsock */ + return smc_create_clcsk(net, sk, sk->sk_family); +} + +int __init smc_inet_init(void) +{ + int rc; + + rc = proto_register(&smc_inet_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet_prot fails with %d\n", + __func__, rc); + return rc; + } + /* no return value */ + inet_register_protosw(&smc_inet_protosw); + +#if IS_ENABLED(CONFIG_IPV6) + rc = proto_register(&smc_inet6_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet6_prot fails with %d\n", + __func__, rc); + goto out_inet6_prot; + } + rc = inet6_register_protosw(&smc_inet6_protosw); + if (rc) { + pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n", + __func__, rc); + goto out_inet6_protosw; + } + return rc; +out_inet6_protosw: + proto_unregister(&smc_inet6_prot); +out_inet6_prot: + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +#endif /* CONFIG_IPV6 */ + return rc; +} + +void smc_inet_exit(void) +{ +#if IS_ENABLED(CONFIG_IPV6) + inet6_unregister_protosw(&smc_inet6_protosw); + proto_unregister(&smc_inet6_prot); +#endif /* CONFIG_IPV6 */ + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +} diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h new file mode 100644 index 000000000000..a489c8a2b8ef --- /dev/null +++ b/net/smc/smc_inet.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + + * Copyright IBM Corp. 2016 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe + */ +#ifndef __INET_SMC +#define __INET_SMC + +/* Initialize protocol registration on IPPROTO_SMC, + * @return 0 on success + */ +int smc_inet_init(void); + +void smc_inet_exit(void); + +#endif /* __INET_SMC */ -- cgit v1.2.3 From 4b23e0c199b20fa6fe9655b3d0e12d6c6f18c27f Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 3 May 2024 11:17:33 -0700 Subject: KVM: Ensure new code that references immediate_exit gets extra scrutiny Ensure that any new KVM code that references immediate_exit gets extra scrutiny by renaming it to immediate_exit__unsafe in kernel code. All fields in struct kvm_run are subject to TOCTOU races since they are mapped into userspace, which may be malicious or buggy. To protect KVM, introduces a new macro that appends __unsafe to select field names in struct kvm_run, hinting to developers and reviewers that accessing such fields must be done carefully. Apply the new macro to immediate_exit, since userspace can make immediate_exit inconsistent with vcpu->wants_to_run, i.e. accessing immediate_exit directly could lead to unexpected bugs in the future. Signed-off-by: David Matlack Link: https://lore.kernel.org/r/20240503181734.1467938-3-dmatlack@google.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- include/uapi/linux/kvm.h | 15 ++++++++++++++- virt/kvm/kvm_main.c | 2 +- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d03842abae57..795773f5db63 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -192,11 +192,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from to __unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 66bfdfa11805..2fed9a9b8bd6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4435,7 +4435,7 @@ static long kvm_vcpu_ioctl(struct file *filp, synchronize_rcu(); put_pid(oldpid); } - vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit); + vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe); r = kvm_arch_vcpu_ioctl_run(vcpu); vcpu->wants_to_run = false; -- cgit v1.2.3 From 7481fd93fa0a851740e26026485f56a1305454ce Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 14 Jun 2024 12:30:46 -0400 Subject: io_uring: Introduce IORING_OP_BIND IORING_OP_BIND provides the semantic of bind(2) via io_uring. While this is an essentially synchronous system call, the main point is to enable a network path to execute fully with io_uring registered and descriptorless files. Signed-off-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20240614163047.31581-3-krisman@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 36 ++++++++++++++++++++++++++++++++++++ io_uring/net.h | 3 +++ io_uring/opdef.c | 13 +++++++++++++ 4 files changed, 53 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 994bf7af0efe..4ef153d95c87 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -257,6 +257,7 @@ enum io_uring_op { IORING_OP_FUTEX_WAITV, IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, + IORING_OP_BIND, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index 7c98c4d50946..8cc4cfc2fef3 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -51,6 +51,11 @@ struct io_connect { bool seen_econnaborted; }; +struct io_bind { + struct file *file; + int addr_len; +}; + struct io_sr_msg { struct file *file; union { @@ -1715,6 +1720,37 @@ out: return IOU_OK; } +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); + struct sockaddr __user *uaddr; + struct io_async_msghdr *io; + + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + bind->addr_len = READ_ONCE(sqe->addr2); + + io = io_msg_alloc_async(req); + if (unlikely(!io)) + return -ENOMEM; + return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); +} + +int io_bind(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); + struct io_async_msghdr *io = req->async_data; + int ret; + + ret = __sys_bind_socket(sock_from_file(req->file), &io->addr, bind->addr_len); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return 0; +} + void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; diff --git a/io_uring/net.h b/io_uring/net.h index 0eb1c1920fc9..49f9a7bc1113 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -49,6 +49,9 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags); int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); void io_send_zc_cleanup(struct io_kiocb *req); +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_bind(struct io_kiocb *req, unsigned int issue_flags); + void io_netmsg_cache_free(const void *entry); #else static inline void io_netmsg_cache_free(const void *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 2e3b7b16effb..1424c2d9e9ef 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -495,6 +495,16 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_ftruncate_prep, .issue = io_ftruncate, }, + [IORING_OP_BIND] = { +#if defined(CONFIG_NET) + .needs_file = 1, + .prep = io_bind_prep, + .issue = io_bind, + .async_size = sizeof(struct io_async_msghdr), +#else + .prep = io_eopnotsupp_prep, +#endif + }, }; const struct io_cold_def io_cold_defs[] = { @@ -716,6 +726,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FTRUNCATE] = { .name = "FTRUNCATE", }, + [IORING_OP_BIND] = { + .name = "BIND", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit v1.2.3 From ff140cc8628abfb1755691d16cfa8788d8820ef7 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 14 Jun 2024 12:30:47 -0400 Subject: io_uring: Introduce IORING_OP_LISTEN IORING_OP_LISTEN provides the semantic of listen(2) via io_uring. While this is an essentially synchronous system call, the main point is to enable a network path to execute fully with io_uring registered and descriptorless files. Signed-off-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20240614163047.31581-4-krisman@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 28 ++++++++++++++++++++++++++++ io_uring/net.h | 3 +++ io_uring/opdef.c | 13 +++++++++++++ 4 files changed, 45 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4ef153d95c87..2aaf7ee256ac 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -258,6 +258,7 @@ enum io_uring_op { IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, IORING_OP_BIND, + IORING_OP_LISTEN, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index 8cc4cfc2fef3..db4a4a03ce3a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -56,6 +56,11 @@ struct io_bind { int addr_len; }; +struct io_listen { + struct file *file; + int backlog; +}; + struct io_sr_msg { struct file *file; union { @@ -1751,6 +1756,29 @@ int io_bind(struct io_kiocb *req, unsigned int issue_flags) return 0; } +int io_listen_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_listen *listen = io_kiocb_to_cmd(req, struct io_listen); + + if (sqe->addr || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in || sqe->addr2) + return -EINVAL; + + listen->backlog = READ_ONCE(sqe->len); + return 0; +} + +int io_listen(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_listen *listen = io_kiocb_to_cmd(req, struct io_listen); + int ret; + + ret = __sys_listen_socket(sock_from_file(req->file), listen->backlog); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return 0; +} + void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; diff --git a/io_uring/net.h b/io_uring/net.h index 49f9a7bc1113..52bfee05f06a 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -52,6 +52,9 @@ void io_send_zc_cleanup(struct io_kiocb *req); int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_bind(struct io_kiocb *req, unsigned int issue_flags); +int io_listen_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_listen(struct io_kiocb *req, unsigned int issue_flags); + void io_netmsg_cache_free(const void *entry); #else static inline void io_netmsg_cache_free(const void *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 1424c2d9e9ef..2dd49cf22f64 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -503,6 +503,16 @@ const struct io_issue_def io_issue_defs[] = { .async_size = sizeof(struct io_async_msghdr), #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_LISTEN] = { +#if defined(CONFIG_NET) + .needs_file = 1, + .prep = io_listen_prep, + .issue = io_listen, + .async_size = sizeof(struct io_async_msghdr), +#else + .prep = io_eopnotsupp_prep, #endif }, }; @@ -729,6 +739,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_BIND] = { .name = "BIND", }, + [IORING_OP_LISTEN] = { + .name = "LISTEN", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit v1.2.3 From ba63a7e08523be3496cc1b7e5f77d306144a3a40 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 20 Apr 2024 21:47:46 +0200 Subject: can: isotp: remove ISO 15675-2 specification version where possible With the new ISO 15765-2:2024 release the former documentation and comments have to be reworked. This patch removes the ISO specification version/date where possible. Signed-off-by: Oliver Hartkopp Acked-by: Vincent Mailhol Acked-by: Francesco Valla Link: https://lore.kernel.org/all/20240420194746.4885-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 2 +- net/can/Kconfig | 11 +++++------ net/can/isotp.c | 11 ++++++----- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 6cde62371b6f..bd990917f7c4 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -2,7 +2,7 @@ /* * linux/can/isotp.h * - * Definitions for isotp CAN sockets (ISO 15765-2:2016) + * Definitions for ISO 15765-2 CAN transport protocol sockets * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. diff --git a/net/can/Kconfig b/net/can/Kconfig index cb56be8e3862..af64a6f76458 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -56,18 +56,17 @@ config CAN_GW source "net/can/j1939/Kconfig" config CAN_ISOTP - tristate "ISO 15765-2:2016 CAN transport protocol" + tristate "ISO 15765-2 CAN transport protocol" help CAN Transport Protocols offer support for segmented Point-to-Point communication between CAN nodes via two defined CAN Identifiers. + This protocol driver implements segmented data transfers for CAN CC + (aka Classical CAN, CAN 2.0B) and CAN FD frame types which were + introduced with ISO 15765-2:2016. As CAN frames can only transport a small amount of data bytes - (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this + (max. 8 bytes for CAN CC and max. 64 bytes for CAN FD) this segmentation is needed to transport longer Protocol Data Units (PDU) as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. - This protocol driver implements data transfers according to - ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. - If you want to perform automotive vehicle diagnostic services (UDS), - say 'y'. endif diff --git a/net/can/isotp.c b/net/can/isotp.c index 25bac0fafc83..16046931542a 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -72,7 +72,7 @@ #include #include -MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol"); +MODULE_DESCRIPTION("PF_CAN ISO 15765-2 transport protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp "); MODULE_ALIAS("can-proto-6"); @@ -83,10 +83,11 @@ MODULE_ALIAS("can-proto-6"); (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can - * take full 32 bit values (4 Gbyte). We would need some good concept to handle - * this between user space and kernel space. For now set the static buffer to - * something about 8 kbyte to be able to test this new functionality. +/* Since ISO 15765-2:2016 the CAN isotp protocol supports more than 4095 + * byte per ISO PDU as the FF_DL can take full 32 bit values (4 Gbyte). + * We would need some good concept to handle this between user space and + * kernel space. For now set the static buffer to something about 8 kbyte + * to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 -- cgit v1.2.3 From c34fc6f26ab86d03a2d47446f42b6cd492dfdc56 Mon Sep 17 00:00:00 2001 From: Prasad Singamsetty Date: Thu, 20 Jun 2024 12:53:52 +0000 Subject: fs: Initial atomic write support An atomic write is a write issued with torn-write protection, meaning that for a power failure or any other hardware failure, all or none of the data from the write will be stored, but never a mix of old and new data. Userspace may add flag RWF_ATOMIC to pwritev2() to indicate that the write is to be issued with torn-write prevention, according to special alignment and length rules. For any syscall interface utilizing struct iocb, add IOCB_ATOMIC for iocb->ki_flags field to indicate the same. A call to statx will give the relevant atomic write info for a file: - atomic_write_unit_min - atomic_write_unit_max - atomic_write_segments_max Both min and max values must be a power-of-2. Applications can avail of atomic write feature by ensuring that the total length of a write is a power-of-2 in size and also sized between atomic_write_unit_min and atomic_write_unit_max, inclusive. Applications must ensure that the write is at a naturally-aligned offset in the file wrt the total write length. The value in atomic_write_segments_max indicates the upper limit for IOV_ITER iovcnt. Add file mode flag FMODE_CAN_ATOMIC_WRITE, so files which do not have the flag set will have RWF_ATOMIC rejected and not just ignored. Add a type argument to kiocb_set_rw_flags() to allows reads which have RWF_ATOMIC set to be rejected. Helper function generic_atomic_write_valid() can be used by FSes to verify compliant writes. There we check for iov_iter type is for ubuf, which implies iovcnt==1 for pwritev2(), which is an initial restriction for atomic_write_segments_max. Initially the only user will be bdev file operations write handler. We will rely on the block BIO submission path to ensure write sizes are compliant for the bdev, so we don't need to check atomic writes sizes yet. Signed-off-by: Prasad Singamsetty jpg: merge into single patch and much rewrite Acked-by: Darrick J. Wong Reviewed-by: Martin K. Petersen Signed-off-by: John Garry Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20240620125359.2684798-4-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- fs/aio.c | 8 ++++---- fs/btrfs/ioctl.c | 2 +- fs/read_write.c | 18 +++++++++++++++++- include/linux/fs.h | 17 +++++++++++++++-- include/uapi/linux/fs.h | 5 ++++- io_uring/rw.c | 9 ++++----- 6 files changed, 45 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/aio.c b/fs/aio.c index 57c9f7c077e6..93ef59d358b3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1516,7 +1516,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res) iocb_put(iocb); } -static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) +static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret; @@ -1542,7 +1542,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) } else req->ki_ioprio = get_current_ioprio(); - ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); + ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret; @@ -1594,7 +1594,7 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; @@ -1621,7 +1621,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index efd5d6e9589e..6ad524b894fc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4627,7 +4627,7 @@ static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool goto out_iov; init_sync_kiocb(&kiocb, file); - ret = kiocb_set_rw_flags(&kiocb, 0); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); if (ret) goto out_iov; kiocb.ki_pos = pos; diff --git a/fs/read_write.c b/fs/read_write.c index ef6339391351..90e283b31ca1 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -730,7 +730,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, ssize_t ret; init_sync_kiocb(&kiocb, filp); - ret = kiocb_set_rw_flags(&kiocb, flags); + ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); @@ -1736,3 +1736,19 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out) return 0; } + +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos) +{ + size_t len = iov_iter_count(iter); + + if (!iter_is_ubuf(iter)) + return false; + + if (!is_power_of_2(len)) + return false; + + if (!IS_ALIGNED(pos, len)) + return false; + + return true; +} diff --git a/include/linux/fs.h b/include/linux/fs.h index 0283cf366c2a..e049414bef7d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -125,8 +125,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) -/* FMODE_* bits 7 to 8 */ +/* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) @@ -317,6 +319,7 @@ struct readahead_control; #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -351,6 +354,7 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -3403,7 +3407,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3422,6 +3427,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3613,4 +3624,6 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); + #endif /* _LINUX_FS_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 45e4e64fd664..191a7e88a8ab 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -329,9 +329,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO negation of O_APPEND */ #define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/io_uring/rw.c b/io_uring/rw.c index 1a2128459cb4..c004d21e2f12 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -772,7 +772,7 @@ static bool need_complete_io(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } -static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); struct kiocb *kiocb = &rw->kiocb; @@ -787,7 +787,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) req->flags |= io_file_get_flags(file); kiocb->ki_flags = file->f_iocb_flags; - ret = kiocb_set_rw_flags(kiocb, rw->flags); + ret = kiocb_set_rw_flags(kiocb, rw->flags, rw_type); if (unlikely(ret)) return ret; kiocb->ki_flags |= IOCB_ALLOC_CACHE; @@ -832,8 +832,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(ret < 0)) return ret; } - - ret = io_rw_init_file(req, FMODE_READ); + ret = io_rw_init_file(req, FMODE_READ, READ); if (unlikely(ret)) return ret; req->cqe.res = iov_iter_count(&io->iter); @@ -1013,7 +1012,7 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) ssize_t ret, ret2; loff_t *ppos; - ret = io_rw_init_file(req, FMODE_WRITE); + ret = io_rw_init_file(req, FMODE_WRITE, WRITE); if (unlikely(ret)) return ret; req->cqe.res = iov_iter_count(&io->iter); -- cgit v1.2.3 From 0f9ca80fa4f9670ba09721e4e36b8baf086a500c Mon Sep 17 00:00:00 2001 From: Prasad Singamsetty Date: Thu, 20 Jun 2024 12:53:53 +0000 Subject: fs: Add initial atomic write support info to statx Extend statx system call to return additional info for atomic write support support for a file. Helper function generic_fill_statx_atomic_writes() can be used by FSes to fill in the relevant statx fields. For now atomic_write_segments_max will always be 1, otherwise some rules would need to be imposed on iovec length and alignment, which we don't want now. Signed-off-by: Prasad Singamsetty jpg: relocate bdev support to another patch Reviewed-by: Darrick J. Wong Reviewed-by: Martin K. Petersen Signed-off-by: John Garry Acked-by: Darrick J. Wong Link: https://lore.kernel.org/r/20240620125359.2684798-5-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- fs/stat.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/fs.h | 3 +++ include/linux/stat.h | 3 +++ include/uapi/linux/stat.h | 12 ++++++++++-- 4 files changed, 50 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/stat.c b/fs/stat.c index 70bd3e888cfa..72d0e6357b91 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) } EXPORT_SYMBOL(generic_fill_statx_attr); +/** + * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes + * @stat: Where to fill in the attribute flags + * @unit_min: Minimum supported atomic write length in bytes + * @unit_max: Maximum supported atomic write length in bytes + * + * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from + * atomic write unit_min and unit_max values. + */ +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max) +{ + /* Confirm that the request type is known */ + stat->result_mask |= STATX_WRITE_ATOMIC; + + /* Confirm that the file attribute type is known */ + stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC; + + if (unit_min) { + stat->atomic_write_unit_min = unit_min; + stat->atomic_write_unit_max = unit_max; + /* Initially only allow 1x segment */ + stat->atomic_write_segments_max = 1; + + /* Confirm atomic writes are actually supported */ + stat->attributes |= STATX_ATTR_WRITE_ATOMIC; + } +} +EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes); + /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from @@ -659,6 +690,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; tmp.stx_subvol = stat->subvol; + tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; + tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; + tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index e049414bef7d..db26b4a70c62 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3235,6 +3235,9 @@ extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); diff --git a/include/linux/stat.h b/include/linux/stat.h index bf92441dbad2..3d900c86981c 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -54,6 +54,9 @@ struct kstat { u32 dio_offset_align; u64 change_cookie; u64 subvol; + u32 atomic_write_unit_min; + u32 atomic_write_unit_max; + u32 atomic_write_segments_max; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3 From ca567df74a28a9fb368c6b2d93e864113f73f5c2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sun, 7 Jun 2020 22:47:08 +0200 Subject: nsfs: add pid translation ioctls Add ioctl()s to translate pids between pid namespaces. LXCFS is a tiny fuse filesystem used to virtualize various aspects of procfs. LXCFS is run on the host. The files and directories it creates can be bind-mounted by e.g. a container at startup and mounted over the various procfs files the container wishes to have virtualized. When e.g. a read request for uptime is received, LXCFS will receive the pid of the reader. In order to virtualize the corresponding read, LXCFS needs to know the pid of the init process of the reader's pid namespace. In order to do this, LXCFS first needs to fork() two helper processes. The first helper process setns() to the readers pid namespace. The second helper process is needed to create a process that is a proper member of the pid namespace. The second helper process then creates a ucred message with ucred.pid set to 1 and sends it back to LXCFS. The kernel will translate the ucred.pid field to the corresponding pid number in LXCFS's pid namespace. This way LXCFS can learn the init pid number of the reader's pid namespace and can go on to virtualize. Since these two forks() are costly LXCFS maintains an init pid cache that caches a given pid for a fixed amount of time. The cache is pruned during new read requests. However, even with the cache the hit of the two forks() is singificant when a very large number of containers are running. With this simple patch we add an ns ioctl that let's a caller retrieve the init pid nr of a pid namespace through its pid namespace fd. This significantly improves performance with a very simple change. Support translation of pids and tgids. Other concepts can be added but there are no obvious users for this right now. To protect against races pidfds can be used to check whether the process is still valid. If needed, this can also be extended to work on pidfds directly. Link: https://lore.kernel.org/r/20240619-work-ns_ioctl-v1-1-7c0097e6bb6b@kernel.org Reviewed-by: Alexander Mikhalitsyn Signed-off-by: Christian Brauner --- fs/nsfs.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/nsfs.h | 8 +++++++ 2 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 07e22a15ef02..a23c827a0299 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -123,9 +124,12 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct user_namespace *user_ns; + struct pid_namespace *pid_ns; + struct task_struct *tsk; struct ns_common *ns = get_proc_ns(file_inode(filp)); uid_t __user *argp; uid_t uid; + int ret; switch (ioctl) { case NS_GET_USERNS: @@ -143,9 +147,56 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, argp = (uid_t __user *) arg; uid = from_kuid_munged(current_user_ns(), user_ns->owner); return put_user(uid, argp); + case NS_GET_PID_FROM_PIDNS: + fallthrough; + case NS_GET_TGID_FROM_PIDNS: + fallthrough; + case NS_GET_PID_IN_PIDNS: + fallthrough; + case NS_GET_TGID_IN_PIDNS: + if (ns->ops->type != CLONE_NEWPID) + return -EINVAL; + + ret = -ESRCH; + pid_ns = container_of(ns, struct pid_namespace, ns); + + rcu_read_lock(); + + if (ioctl == NS_GET_PID_IN_PIDNS || + ioctl == NS_GET_TGID_IN_PIDNS) + tsk = find_task_by_vpid(arg); + else + tsk = find_task_by_pid_ns(arg, pid_ns); + if (!tsk) + break; + + switch (ioctl) { + case NS_GET_PID_FROM_PIDNS: + ret = task_pid_vnr(tsk); + break; + case NS_GET_TGID_FROM_PIDNS: + ret = task_tgid_vnr(tsk); + break; + case NS_GET_PID_IN_PIDNS: + ret = task_pid_nr_ns(tsk, pid_ns); + break; + case NS_GET_TGID_IN_PIDNS: + ret = task_tgid_nr_ns(tsk, pid_ns); + break; + default: + ret = 0; + break; + } + rcu_read_unlock(); + + if (!ret) + ret = -ESRCH; + break; default: - return -ENOTTY; + ret = -ENOTTY; } + + return ret; } int ns_get_name(char *buf, size_t size, struct task_struct *task, diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index a0c8552b64ee..faeb9195da08 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -15,5 +15,13 @@ #define NS_GET_NSTYPE _IO(NSIO, 0x3) /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) +/* Translate pid from target pid namespace into the caller's pid namespace. */ +#define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x5, int) +/* Return thread-group leader id of pid in the callers pid namespace. */ +#define NS_GET_TGID_FROM_PIDNS _IOR(NSIO, 0x7, int) +/* Translate pid from caller's pid namespace into a target pid namespace. */ +#define NS_GET_PID_IN_PIDNS _IOR(NSIO, 0x6, int) +/* Return thread-group leader id of pid in the target pid namespace. */ +#define NS_GET_TGID_IN_PIDNS _IOR(NSIO, 0x8, int) #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From e29630247be24c3987e2b048f8e152771b32d38b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 3 Jun 2024 20:16:59 +0200 Subject: netfilter: nf_tables: rise cap on SELinux secmark context secmark context is artificially limited 256 bytes, rise it to 4Kbytes. Fixes: fb961945457f ("netfilter: nf_tables: add SECMARK support") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index aa4094ca2444..639894ed1b97 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1376,7 +1376,7 @@ enum nft_secmark_attributes { #define NFTA_SECMARK_MAX (__NFTA_SECMARK_MAX - 1) /* Max security context length */ -#define NFT_SECMARK_CTX_MAXLEN 256 +#define NFT_SECMARK_CTX_MAXLEN 4096 /** * enum nft_reject_types - nf_tables reject expression reject types -- cgit v1.2.3 From f750dfe825b904164688adeb147950e0e0c4d262 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:51 +0800 Subject: ethtool: provide customized dim profile management The NetDIM library, currently leveraged by an array of NICs, delivers excellent acceleration benefits. Nevertheless, NICs vary significantly in their dim profile list prerequisites. Specifically, virtio-net backends may present diverse sw or hw device implementation, making a one-size-fits-all parameter list impractical. On Alibaba Cloud, the virtio DPU's performance under the default DIM profile falls short of expectations, partly due to a mismatch in parameter configuration. I also noticed that ice/idpf/ena and other NICs have customized profilelist or placed some restrictions on dim capabilities. Motivated by this, I tried adding new params for "ethtool -C" that provides a per-device control to modify and access a device's interrupt parameters. Usage ======== The target NIC is named ethx. Assume that ethx only declares support for rx profile setting (with DIM_PROFILE_RX flag set in profile_flags) and supports modification of usec and pkt fields. 1. Query the currently customized list of the device $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 256, .comps = n/a,}, {.usec = 8, .pkts = 256, .comps = n/a,}, {.usec = 64, .pkts = 256, .comps = n/a,}, {.usec = 128, .pkts = 256, .comps = n/a,}, {.usec = 256, .pkts = 256, .comps = n/a,} tx-profile: n/a 2. Tune $ ethtool -C ethx rx-profile 1,1,n_2,n,n_3,3,n_4,4,n_n,5,n "n" means do not modify this field. $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 1, .comps = n/a,}, {.usec = 2, .pkts = 256, .comps = n/a,}, {.usec = 3, .pkts = 3, .comps = n/a,}, {.usec = 4, .pkts = 4, .comps = n/a,}, {.usec = 256, .pkts = 5, .comps = n/a,} tx-profile: n/a 3. Hint If the device does not support some type of customized dim profiles, the corresponding "n/a" will display. If the "n/a" field is being modified, -EOPNOTSUPP will be reported. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-4-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 31 +++ Documentation/networking/ethtool-netlink.rst | 8 + Documentation/networking/net_dim.rst | 42 +++++ include/linux/dim.h | 58 ++++++ include/linux/ethtool.h | 4 +- include/linux/netdevice.h | 3 + include/uapi/linux/ethtool_netlink.h | 22 +++ lib/dim/net_dim.c | 70 +++++++ net/Kconfig | 1 + net/ethtool/coalesce.c | 273 ++++++++++++++++++++++++++- 10 files changed, 509 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 00dc61358be8..6c2ab3d1c22f 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -414,6 +414,26 @@ attribute-sets: name: combined-count type: u32 + - + name: irq-moderation + attributes: + - + name: usec + type: u32 + - + name: pkts + type: u32 + - + name: comps + type: u32 + - + name: profile + attributes: + - + name: irq-moderation + type: nest + multi-attr: true + nested-attributes: irq-moderation - name: coalesce attributes: @@ -502,6 +522,15 @@ attribute-sets: - name: tx-aggr-time-usecs type: u32 + - + name: rx-profile + type: nest + nested-attributes: profile + - + name: tx-profile + type: nest + nested-attributes: profile + - name: pause-stat attributes: @@ -1325,6 +1354,8 @@ operations: - tx-aggr-max-bytes - tx-aggr-max-frames - tx-aggr-time-usecs + - rx-profile + - tx-profile dump: *coalesce-get-op - name: coalesce-set diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 160bfb0ae8ba..7ec08e903bab 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1033,6 +1033,8 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1062,6 +1064,10 @@ block should be sent. This feature is mainly of interest for specific USB devices which does not cope well with frequent small-sized URBs transmissions. +``ETHTOOL_A_COALESCE_RX_PROFILE`` and ``ETHTOOL_A_COALESCE_TX_PROFILE`` refer +to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM) +`_. + COALESCE_SET ============ @@ -1098,6 +1104,8 @@ Request contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/Documentation/networking/net_dim.rst b/Documentation/networking/net_dim.rst index 3bed9fd95336..8908fd7b0a8d 100644 --- a/Documentation/networking/net_dim.rst +++ b/Documentation/networking/net_dim.rst @@ -169,6 +169,48 @@ usage is not complete but it should make the outline of the usage clear. ... } + +Tuning DIM +========== + +Net DIM serves a range of network devices and delivers excellent acceleration +benefits. Yet, it has been observed that some preset configurations of DIM may +not align seamlessly with the varying specifications of network devices, and +this discrepancy has been identified as a factor to the suboptimal performance +outcomes of DIM-enabled network devices, related to a mismatch in profiles. + +To address this issue, Net DIM introduces a per-device control to modify and +access a device's ``rx-profile`` and ``tx-profile`` parameters: +Assume that the target network device is named ethx, and ethx only declares +support for RX profile setting and supports modification of ``usec`` field +and ``pkts`` field (See the data structure: +:c:type:`struct dim_cq_moder `). + +You can use ethtool to modify the current RX DIM profile where all +values are 64:: + + $ ethtool -C ethx rx-profile 1,1,n_2,2,n_3,n,n_n,4,n_n,n,n + +``n`` means do not modify this field, and ``_`` separates structure +elements of the profile array. + +Querying the current profiles using:: + + $ ethtool -c ethx + ... + rx-profile: + {.usec = 1, .pkts = 1, .comps = n/a,}, + {.usec = 2, .pkts = 2, .comps = n/a,}, + {.usec = 3, .pkts = 64, .comps = n/a,}, + {.usec = 64, .pkts = 4, .comps = n/a,}, + {.usec = 64, .pkts = 64, .comps = n/a,} + tx-profile: n/a + +If the network device does not support specific fields of DIM profiles, +the corresponding ``n/a`` will display. If the ``n/a`` field is being +modified, error messages will be reported. + + Dynamic Interrupt Moderation (DIM) library API ============================================== diff --git a/include/linux/dim.h b/include/linux/dim.h index 43398f5eade2..e0f39bd85432 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,8 @@ #include #include +struct net_device; + /* Number of DIM profiles and period mode. */ #define NET_DIM_PARAMS_NUM_PROFILES 5 #define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 @@ -45,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -198,6 +233,29 @@ enum dim_step_result { DIM_ON_EDGE, }; +/** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + /** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6fd9107d3cc0..959196af7f5a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -284,7 +284,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4e81660b4462..cc18acd3c58b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2402,6 +2402,9 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b49b804b9495..d15856c7e001 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -415,12 +415,34 @@ enum { ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_RX_PROFILE, + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_TX_PROFILE, /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) }; +enum { + ETHTOOL_A_PROFILE_UNSPEC, + /* nest, _A_IRQ_MODERATION_* */ + ETHTOOL_A_PROFILE_IRQ_MODERATION, + __ETHTOOL_A_PROFILE_CNT, + ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) +}; + +enum { + ETHTOOL_A_IRQ_MODERATION_UNSPEC, + ETHTOOL_A_IRQ_MODERATION_USEC, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_PKTS, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_COMPS, /* u32 */ + + __ETHTOOL_A_IRQ_MODERATION_CNT, + ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) +}; + /* PAUSE */ enum { diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 67d5beb34dc3..0cd41277c7a3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -4,6 +4,7 @@ */ #include +#include /* * Net DIM profiles: @@ -95,6 +96,75 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) } EXPORT_SYMBOL(net_dim_get_def_tx_moderation); +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)) +{ + struct dim_cq_moder *rxp = NULL, *txp; + struct dim_irq_moder *moder; + int len; + + dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL); + if (!dev->irq_moder) + return -ENOMEM; + + moder = dev->irq_moder; + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile); + + moder->coal_flags = coal_flags; + moder->profile_flags = profile_flags; + + if (profile_flags & DIM_PROFILE_RX) { + moder->rx_dim_work = rx_dim_work; + moder->dim_rx_mode = rx_mode; + rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL); + if (!rxp) + goto free_moder; + + rcu_assign_pointer(moder->rx_profile, rxp); + } + + if (profile_flags & DIM_PROFILE_TX) { + moder->tx_dim_work = tx_dim_work; + moder->dim_tx_mode = tx_mode; + txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL); + if (!txp) + goto free_rxp; + + rcu_assign_pointer(moder->tx_profile, txp); + } + + return 0; + +free_rxp: + kfree(rxp); +free_moder: + kfree(moder); + return -ENOMEM; +} +EXPORT_SYMBOL(net_dim_init_irq_moder); + +/* RTNL lock is held. */ +void net_dim_free_irq_moder(struct net_device *dev) +{ + struct dim_cq_moder *rxp, *txp; + + if (!dev->irq_moder) + return; + + rxp = rtnl_dereference(dev->irq_moder->rx_profile); + txp = rtnl_dereference(dev->irq_moder->tx_profile); + + rcu_assign_pointer(dev->irq_moder->rx_profile, NULL); + rcu_assign_pointer(dev->irq_moder->tx_profile, NULL); + + kfree_rcu(rxp, rcu); + kfree_rcu(txp, rcu); + kfree(dev->irq_moder); +} +EXPORT_SYMBOL(net_dim_free_irq_moder); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) diff --git a/net/Kconfig b/net/Kconfig index 9fe65fa26e48..d27d0deac0bf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -508,6 +508,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" + select DIMLIB default y help An alternative userspace interface for ethtool based on generic diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 83112c1a71ae..759b16e3d134 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include "netlink.h" #include "common.h" @@ -82,6 +83,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { + int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ + nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ + + int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ + modersz * NET_DIM_PARAMS_NUM_PROFILES; + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ @@ -108,7 +117,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ - nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ + total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -127,14 +137,84 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, return nla_put_u8(skb, attr_type, !!val); } +/** + * coalesce_put_profile - fill reply with a nla nest with four child nla nests. + * @skb: socket buffer the message is stored in + * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE + * @profile: data passed to userspace + * @coal_flags: modifiable parameters supported by the driver + * + * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. + * + * Return: 0 on success or a negative error code. + */ +static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, + const struct dim_cq_moder *profile, + u8 coal_flags) +{ + struct nlattr *profile_attr, *moder_attr; + int i, ret; + + if (!profile || !coal_flags) + return 0; + + profile_attr = nla_nest_start(skb, attr_type); + if (!profile_attr) + return -EMSGSIZE; + + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { + moder_attr = nla_nest_start(skb, + ETHTOOL_A_PROFILE_IRQ_MODERATION); + if (!moder_attr) { + ret = -EMSGSIZE; + goto cancel_profile; + } + + if (coal_flags & DIM_COALESCE_USEC) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, + profile[i].usec); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_PKTS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, + profile[i].pkts); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_COMPS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, + profile[i].comps); + if (ret) + goto cancel_moder; + } + + nla_nest_end(skb, moder_attr); + } + + nla_nest_end(skb, profile_attr); + + return 0; + +cancel_moder: + nla_nest_cancel(skb, moder_attr); +cancel_profile: + nla_nest_cancel(skb, profile_attr); + return ret; +} + static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; + struct dim_irq_moder *moder = req_base->dev->irq_moder; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; + int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || @@ -192,11 +272,41 @@ static int coalesce_fill_reply(struct sk_buff *skb, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; - return 0; + if (!moder) + return 0; + + rcu_read_lock(); + if (moder->profile_flags & DIM_PROFILE_RX) { + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, + rcu_dereference(moder->rx_profile), + moder->coal_flags); + if (ret) + goto out; + } + + if (moder->profile_flags & DIM_PROFILE_TX) + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, + rcu_dereference(moder->tx_profile), + moder->coal_flags); + +out: + rcu_read_unlock(); + return ret; } /* COALESCE_SET */ +static const struct nla_policy coalesce_irq_moderation_policy[] = { + [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy coalesce_profile_policy[] = { + [ETHTOOL_A_PROFILE_IRQ_MODERATION] = + NLA_POLICY_NESTED(coalesce_irq_moderation_policy), +}; + const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -227,6 +337,10 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), + [ETHTOOL_A_COALESCE_TX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), }; static int @@ -234,6 +348,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; @@ -243,6 +358,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) + supported_params |= ETHTOOL_COALESCE_RX_PROFILE; + + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) + supported_params |= ETHTOOL_COALESCE_TX_PROFILE; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], @@ -253,6 +374,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, return 1; } +/** + * ethnl_update_irq_moder - update a specific field in the given profile + * @irq_moder: place that collects dim related information + * @irq_field: field in profile to modify + * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* + * @tb: netlink attribute with new values or null + * @coal_bit: DIM_COALESCE_* bit from coal_flags + * @mod: pointer to bool for modification tracking + * @extack: netlink extended ack + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, + u16 *irq_field, u16 attr_type, + struct nlattr **tb, + u8 coal_bit, bool *mod, + struct netlink_ext_ack *extack) +{ + int ret = 0; + u32 val; + + if (!tb[attr_type]) + return 0; + + if (irq_moder->coal_flags & coal_bit) { + val = nla_get_u32(tb[attr_type]); + if (*irq_field == val) + return 0; + + *irq_field = val; + *mod = true; + } else { + NL_SET_BAD_ATTR(extack, tb[attr_type]); + ret = -EOPNOTSUPP; + } + + return ret; +} + +/** + * ethnl_update_profile - get a profile nest with child nests from userspace. + * @dev: netdevice to update the profile + * @dst: profile get from the driver and modified by ethnl_update_profile. + * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. + * @mod: pointer to bool for modification tracking + * @extack: Netlink extended ack + * + * Layout of nests: + * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * ... + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_profile(struct net_device *dev, + struct dim_cq_moder __rcu **dst, + const struct nlattr *nests, + bool *mod, + struct netlink_ext_ack *extack) +{ + int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); + struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; + struct dim_irq_moder *irq_moder = dev->irq_moder; + struct dim_cq_moder *new_profile, *old_profile; + int ret, rem, i = 0, len; + struct nlattr *nest; + + if (!nests) + return 0; + + if (!*dst) + return -EOPNOTSUPP; + + old_profile = rtnl_dereference(*dst); + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); + new_profile = kmemdup(old_profile, len, GFP_KERNEL); + if (!new_profile) + return -ENOMEM; + + nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, + nests, rem) { + ret = nla_parse_nested(tb, len_irq_moder - 1, nest, + coalesce_irq_moderation_policy, + extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, + ETHTOOL_A_IRQ_MODERATION_USEC, + tb, DIM_COALESCE_USEC, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, + ETHTOOL_A_IRQ_MODERATION_PKTS, + tb, DIM_COALESCE_PKTS, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, + ETHTOOL_A_IRQ_MODERATION_COMPS, + tb, DIM_COALESCE_COMPS, + mod, extack); + if (ret) + goto err_out; + + i++; + } + + /* After the profile is modified, dim itself is a dynamic + * mechanism and will quickly fit to the appropriate + * coalescing parameters according to the new profile. + */ + rcu_assign_pointer(*dst, new_profile); + kfree_rcu(old_profile, rcu); + + return 0; + +err_out: + kfree(new_profile); + return ret; +} + static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) @@ -317,6 +570,22 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, + tb[ETHTOOL_A_COALESCE_RX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, + tb[ETHTOOL_A_COALESCE_TX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); -- cgit v1.2.3 From f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Mon, 27 May 2024 20:29:14 -0700 Subject: xfrm: support sending NAT keepalives in ESP in UDP states Add the ability to send out RFC-3948 NAT keepalives from the xfrm stack. To use, Userspace sets an XFRM_NAT_KEEPALIVE_INTERVAL integer property when creating XFRM outbound states which denotes the number of seconds between keepalive messages. Keepalive messages are sent from a per net delayed work which iterates over the xfrm states. The logic is guarded by the xfrm state spinlock due to the xfrm state walk iterator. Possible future enhancements: - Adding counters to keep track of sent keepalives. - deduplicate NAT keepalives between states sharing the same nat keepalive parameters. - provisioning hardware offloads for devices capable of implementing this. - revise xfrm state list to use an rcu list in order to avoid running this under spinlock. Suggested-by: Paul Wouters Tested-by: Paul Wouters Tested-by: Antony Antony Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/ipv6_stubs.h | 3 + include/net/netns/xfrm.h | 1 + include/net/xfrm.h | 10 ++ include/uapi/linux/xfrm.h | 1 + net/ipv6/af_inet6.c | 1 + net/ipv6/xfrm6_policy.c | 7 + net/xfrm/Makefile | 3 +- net/xfrm/xfrm_compat.c | 6 +- net/xfrm/xfrm_nat_keepalive.c | 292 ++++++++++++++++++++++++++++++++++++++++++ net/xfrm/xfrm_policy.c | 8 ++ net/xfrm/xfrm_state.c | 17 +++ net/xfrm/xfrm_user.c | 15 +++ 12 files changed, 361 insertions(+), 3 deletions(-) create mode 100644 net/xfrm/xfrm_nat_keepalive.c (limited to 'include/uapi/linux') diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 485c39a89866..11cefd50704d 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -9,6 +9,7 @@ #include #include #include +#include /* structs from net/ip6_fib.h */ struct fib6_info; @@ -72,6 +73,8 @@ struct ipv6_stub { int (*output)(struct net *, struct sock *, struct sk_buff *)); struct net_device *(*ipv6_dev_find)(struct net *net, const struct in6_addr *addr, struct net_device *dev); + int (*ip6_xmit)(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, + __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 423b52eca908..d489d9250bff 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -83,6 +83,7 @@ struct netns_xfrm { spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; + struct delayed_work nat_keepalive_work; }; #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 77ebf5bcf0b9..46a214a76081 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -229,6 +229,10 @@ struct xfrm_state { struct xfrm_encap_tmpl *encap; struct sock __rcu *encap_sk; + /* NAT keepalive */ + u32 nat_keepalive_interval; /* seconds */ + time64_t nat_keepalive_expiration; + /* Data for care-of address */ xfrm_address_t *coaddr; @@ -2203,4 +2207,10 @@ static inline int register_xfrm_state_bpf(void) } #endif +int xfrm_nat_keepalive_init(unsigned short family); +void xfrm_nat_keepalive_fini(unsigned short family); +int xfrm_nat_keepalive_net_init(struct net *net); +int xfrm_nat_keepalive_net_fini(struct net *net); +void xfrm_nat_keepalive_state_updated(struct xfrm_state *x); + #endif /* _NET_XFRM_H */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index d950d02ab791..f28701500714 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -321,6 +321,7 @@ enum xfrm_attr_type_t { XFRMA_IF_ID, /* __u32 */ XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ XFRMA_SA_DIR, /* __u8 */ + XFRMA_NAT_KEEPALIVE_INTERVAL, /* __u32 in seconds for NAT keepalive */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8041dc181bd4..2b893858b9a9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1060,6 +1060,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .nd_tbl = &nd_tbl, .ipv6_fragment = ip6_fragment, .ipv6_dev_find = ipv6_dev_find, + .ip6_xmit = ip6_xmit, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index cc885d3aa9e5..6837ff05f11a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -284,8 +284,14 @@ int __init xfrm6_init(void) ret = register_pernet_subsys(&xfrm6_net_ops); if (ret) goto out_protocol; + + ret = xfrm_nat_keepalive_init(AF_INET6); + if (ret) + goto out_nat_keepalive; out: return ret; +out_nat_keepalive: + unregister_pernet_subsys(&xfrm6_net_ops); out_protocol: xfrm6_protocol_fini(); out_state: @@ -297,6 +303,7 @@ out_policy: void xfrm6_fini(void) { + xfrm_nat_keepalive_fini(AF_INET6); unregister_pernet_subsys(&xfrm6_net_ops); xfrm6_protocol_fini(); xfrm6_policy_fini(); diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 547cec77ba03..512e0b2f8514 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -13,7 +13,8 @@ endif obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ - xfrm_sysctl.o xfrm_replay.o xfrm_device.o + xfrm_sysctl.o xfrm_replay.o xfrm_device.o \ + xfrm_nat_keepalive.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 703d4172c7d7..91357ccaf4af 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -131,6 +131,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), + [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -280,9 +281,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: case XFRMA_SA_DIR: + case XFRMA_NAT_KEEPALIVE_INTERVAL: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -437,7 +439,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c new file mode 100644 index 000000000000..82f0a301683f --- /dev/null +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * xfrm_nat_keepalive.c + * + * (c) 2024 Eyal Birger + */ + +#include +#include +#include + +static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv4); +#if IS_ENABLED(CONFIG_IPV6) +static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv6); +#endif + +struct nat_keepalive { + struct net *net; + u16 family; + xfrm_address_t saddr; + xfrm_address_t daddr; + __be16 encap_sport; + __be16 encap_dport; + __u32 smark; +}; + +static void nat_keepalive_init(struct nat_keepalive *ka, struct xfrm_state *x) +{ + ka->net = xs_net(x); + ka->family = x->props.family; + ka->saddr = x->props.saddr; + ka->daddr = x->id.daddr; + ka->encap_sport = x->encap->encap_sport; + ka->encap_dport = x->encap->encap_dport; + ka->smark = xfrm_smark_get(0, x); +} + +static int nat_keepalive_send_ipv4(struct sk_buff *skb, + struct nat_keepalive *ka) +{ + struct net *net = ka->net; + struct flowi4 fl4; + struct rtable *rt; + struct sock *sk; + __u8 tos = 0; + int err; + + flowi4_init_output(&fl4, 0 /* oif */, skb->mark, tos, + RT_SCOPE_UNIVERSE, IPPROTO_UDP, 0, + ka->daddr.a4, ka->saddr.a4, ka->encap_dport, + ka->encap_sport, sock_net_uid(net, NULL)); + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + skb_dst_set(skb, &rt->dst); + + sk = *this_cpu_ptr(&nat_keepalive_sk_ipv4); + sock_net_set(sk, net); + err = ip_build_and_send_pkt(skb, sk, fl4.saddr, fl4.daddr, NULL, tos); + sock_net_set(sk, &init_net); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int nat_keepalive_send_ipv6(struct sk_buff *skb, + struct nat_keepalive *ka, + struct udphdr *uh) +{ + struct net *net = ka->net; + struct dst_entry *dst; + struct flowi6 fl6; + struct sock *sk; + __wsum csum; + int err; + + csum = skb_checksum(skb, 0, skb->len, 0); + uh->check = csum_ipv6_magic(&ka->saddr.in6, &ka->daddr.in6, + skb->len, IPPROTO_UDP, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.saddr = ka->saddr.in6; + fl6.daddr = ka->daddr.in6; + fl6.flowi6_proto = IPPROTO_UDP; + fl6.fl6_sport = ka->encap_sport; + fl6.fl6_dport = ka->encap_dport; + + sk = *this_cpu_ptr(&nat_keepalive_sk_ipv6); + sock_net_set(sk, net); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, &fl6, NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + skb_dst_set(skb, dst); + err = ipv6_stub->ip6_xmit(sk, skb, &fl6, skb->mark, NULL, 0, 0); + sock_net_set(sk, &init_net); + return err; +} +#endif + +static void nat_keepalive_send(struct nat_keepalive *ka) +{ + const int nat_ka_hdrs_len = max(sizeof(struct iphdr), + sizeof(struct ipv6hdr)) + + sizeof(struct udphdr); + const u8 nat_ka_payload = 0xFF; + int err = -EAFNOSUPPORT; + struct sk_buff *skb; + struct udphdr *uh; + + skb = alloc_skb(nat_ka_hdrs_len + sizeof(nat_ka_payload), GFP_ATOMIC); + if (unlikely(!skb)) + return; + + skb_reserve(skb, nat_ka_hdrs_len); + + skb_put_u8(skb, nat_ka_payload); + + uh = skb_push(skb, sizeof(*uh)); + uh->source = ka->encap_sport; + uh->dest = ka->encap_dport; + uh->len = htons(skb->len); + uh->check = 0; + + skb->mark = ka->smark; + + switch (ka->family) { + case AF_INET: + err = nat_keepalive_send_ipv4(skb, ka); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + err = nat_keepalive_send_ipv6(skb, ka, uh); + break; +#endif + } + if (err) + kfree_skb(skb); +} + +struct nat_keepalive_work_ctx { + time64_t next_run; + time64_t now; +}; + +static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr) +{ + struct nat_keepalive_work_ctx *ctx = ptr; + bool send_keepalive = false; + struct nat_keepalive ka; + time64_t next_run; + u32 interval; + int delta; + + interval = x->nat_keepalive_interval; + if (!interval) + return 0; + + spin_lock(&x->lock); + + delta = (int)(ctx->now - x->lastused); + if (delta < interval) { + x->nat_keepalive_expiration = ctx->now + interval - delta; + next_run = x->nat_keepalive_expiration; + } else if (x->nat_keepalive_expiration > ctx->now) { + next_run = x->nat_keepalive_expiration; + } else { + next_run = ctx->now + interval; + nat_keepalive_init(&ka, x); + send_keepalive = true; + } + + spin_unlock(&x->lock); + + if (send_keepalive) + nat_keepalive_send(&ka); + + if (!ctx->next_run || next_run < ctx->next_run) + ctx->next_run = next_run; + return 0; +} + +static void nat_keepalive_work(struct work_struct *work) +{ + struct nat_keepalive_work_ctx ctx; + struct xfrm_state_walk walk; + struct net *net; + + ctx.next_run = 0; + ctx.now = ktime_get_real_seconds(); + + net = container_of(work, struct net, xfrm.nat_keepalive_work.work); + xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL); + xfrm_state_walk(net, &walk, nat_keepalive_work_single, &ctx); + xfrm_state_walk_done(&walk, net); + if (ctx.next_run) + schedule_delayed_work(&net->xfrm.nat_keepalive_work, + (ctx.next_run - ctx.now) * HZ); +} + +static int nat_keepalive_sk_init(struct sock * __percpu *socks, + unsigned short family) +{ + struct sock *sk; + int err, i; + + for_each_possible_cpu(i) { + err = inet_ctl_sock_create(&sk, family, SOCK_RAW, IPPROTO_UDP, + &init_net); + if (err < 0) + goto err; + + *per_cpu_ptr(socks, i) = sk; + } + + return 0; +err: + for_each_possible_cpu(i) + inet_ctl_sock_destroy(*per_cpu_ptr(socks, i)); + return err; +} + +static void nat_keepalive_sk_fini(struct sock * __percpu *socks) +{ + int i; + + for_each_possible_cpu(i) + inet_ctl_sock_destroy(*per_cpu_ptr(socks, i)); +} + +void xfrm_nat_keepalive_state_updated(struct xfrm_state *x) +{ + struct net *net; + + if (!x->nat_keepalive_interval) + return; + + net = xs_net(x); + schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0); +} + +int __net_init xfrm_nat_keepalive_net_init(struct net *net) +{ + INIT_DELAYED_WORK(&net->xfrm.nat_keepalive_work, nat_keepalive_work); + return 0; +} + +int xfrm_nat_keepalive_net_fini(struct net *net) +{ + cancel_delayed_work_sync(&net->xfrm.nat_keepalive_work); + return 0; +} + +int xfrm_nat_keepalive_init(unsigned short family) +{ + int err = -EAFNOSUPPORT; + + switch (family) { + case AF_INET: + err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv4, PF_INET); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv6, PF_INET6); + break; +#endif + } + + if (err) + pr_err("xfrm nat keepalive init: failed to init err:%d\n", err); + return err; +} +EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_init); + +void xfrm_nat_keepalive_fini(unsigned short family) +{ + switch (family) { + case AF_INET: + nat_keepalive_sk_fini(&nat_keepalive_sk_ipv4); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + nat_keepalive_sk_fini(&nat_keepalive_sk_ipv6); + break; +#endif + } +} +EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_fini); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 475b904fe68b..6603d3bd171f 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4289,8 +4289,14 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out_sysctl; + rv = xfrm_nat_keepalive_net_init(net); + if (rv < 0) + goto out_nat_keepalive; + return 0; +out_nat_keepalive: + xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: @@ -4303,6 +4309,7 @@ out_statistics: static void __net_exit xfrm_net_exit(struct net *net) { + xfrm_nat_keepalive_net_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); @@ -4364,6 +4371,7 @@ void __init xfrm_init(void) #endif register_xfrm_state_bpf(); + xfrm_nat_keepalive_init(AF_INET); } #ifdef CONFIG_AUDITSYSCALL diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 649bb739df0d..abadc857cd45 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -715,6 +715,7 @@ int __xfrm_state_delete(struct xfrm_state *x) if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; + xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); if (x->encap_sk) @@ -1453,6 +1454,7 @@ static void __xfrm_state_insert(struct xfrm_state *x) net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); + xfrm_nat_keepalive_state_updated(x); } /* net->xfrm.xfrm_state_lock is held */ @@ -2871,6 +2873,21 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, goto error; } + if (x->nat_keepalive_interval) { + if (x->dir != XFRM_SA_DIR_OUT) { + NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs"); + err = -EINVAL; + goto error; + } + + if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) { + NL_SET_ERR_MSG(extack, + "NAT keepalive is only supported for UDP encapsulation"); + err = -EINVAL; + goto error; + } + } + error: return err; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e83c687bd64e..a552cfa623ea 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -833,6 +833,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_DIR]) x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + if (attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]) + x->nat_keepalive_interval = + nla_get_u32(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack); if (err) goto error; @@ -1288,6 +1292,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, } if (x->dir) ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + + if (x->nat_keepalive_interval) { + ret = nla_put_u32(skb, XFRMA_NAT_KEEPALIVE_INTERVAL, + x->nat_keepalive_interval); + if (ret) + goto out; + } out: return ret; } @@ -3165,6 +3176,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), + [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); @@ -3474,6 +3486,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->dir) l += nla_total_size(sizeof(x->dir)); + if (x->nat_keepalive_interval) + l += nla_total_size(sizeof(x->nat_keepalive_interval)); + return l; } -- cgit v1.2.3 From d1741141d03f8f5535adaf5a2d5000da3be9fe90 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:32 +0200 Subject: media: uapi: Add a pixel format for BGR48 and RGB48 Add BGR48 and RGB48 16-bit per component image formats. Signed-off-by: Jacopo Mondi Reviewed-by: Kieran Bingham Reviewed-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-rgb.rst | 54 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-common.c | 2 + drivers/media/v4l2-core/v4l2-ioctl.c | 2 + include/uapi/linux/videodev2.h | 2 + 4 files changed, 60 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst b/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst index b71b80d634d6..5ed4d62df909 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst @@ -996,6 +996,60 @@ arranged in little endian order. \normalsize +16 Bits Per Component +===================== + +These formats store an RGB triplet in six bytes, with 16 bits per component +stored in memory in little endian byte order. They are named based on the order +of the RGB components as stored in memory. For instance, RGB48 stores R\ +:sub:`7:0` and R\ :sub:`15:8` in bytes 0 and 1 respectively. This differs from +the DRM format nomenclature that instead uses the order of components as seen in +the 48-bits little endian word. + +.. raw:: latex + + \small + +.. flat-table:: RGB Formats With 16 Bits Per Component + :header-rows: 1 + + * - Identifier + - Code + - Byte 0 + - Byte 1 + - Byte 2 + - Byte 3 + - Byte 4 + - Byte 5 + + * .. _V4L2-PIX-FMT-BGR48: + + - ``V4L2_PIX_FMT_BGR48`` + - 'BGR6' + + - B\ :sub:`7-0` + - B\ :sub:`15-8` + - G\ :sub:`7-0` + - G\ :sub:`15-8` + - R\ :sub:`7-0` + - R\ :sub:`15-8` + + * .. _V4L2-PIX-FMT-RGB48: + + - ``V4L2_PIX_FMT_RGB48`` + - 'RGB6' + + - R\ :sub:`7-0` + - R\ :sub:`15-8` + - G\ :sub:`7-0` + - G\ :sub:`15-8` + - B\ :sub:`7-0` + - B\ :sub:`15-8` + +.. raw:: latex + + \normalsize + Deprecated RGB Formats ====================== diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 4165c815faef..0a2f4f0d0a07 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -253,6 +253,8 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) { .format = V4L2_PIX_FMT_RGB555, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_BGR666, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_BGR48_12, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 6, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, + { .format = V4L2_PIX_FMT_BGR48, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 6, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, + { .format = V4L2_PIX_FMT_RGB48, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 6, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_ABGR64_12, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 8, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_RGBA1010102, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_RGBX1010102, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 4c76d17b4629..ee97643ff3a7 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1307,6 +1307,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_RGBX1010102: descr = "32-bit RGBX 10-10-10-2"; break; case V4L2_PIX_FMT_RGBA1010102: descr = "32-bit RGBA 10-10-10-2"; break; case V4L2_PIX_FMT_ARGB2101010: descr = "32-bit ARGB 2-10-10-10"; break; + case V4L2_PIX_FMT_BGR48: descr = "48-bit BGR 16-16-16"; break; + case V4L2_PIX_FMT_RGB48: descr = "48-bit RGB 16-16-16"; break; case V4L2_PIX_FMT_BGR48_12: descr = "12-bit Depth BGR"; break; case V4L2_PIX_FMT_ABGR64_12: descr = "12-bit Depth BGRA"; break; case V4L2_PIX_FMT_GREY: descr = "8-bit Greyscale"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index fe6b67e83751..dd6876380fe3 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -582,6 +582,8 @@ struct v4l2_pix_format { /* RGB formats (6 or 8 bytes per pixel) */ #define V4L2_PIX_FMT_BGR48_12 v4l2_fourcc('B', '3', '1', '2') /* 48 BGR 12-bit per component */ +#define V4L2_PIX_FMT_BGR48 v4l2_fourcc('B', 'G', 'R', '6') /* 48 BGR 16-bit per component */ +#define V4L2_PIX_FMT_RGB48 v4l2_fourcc('R', 'G', 'B', '6') /* 48 RGB 16-bit per component */ #define V4L2_PIX_FMT_ABGR64_12 v4l2_fourcc('B', '4', '1', '2') /* 64 BGRA 12-bit per component */ /* Grey formats */ -- cgit v1.2.3 From c6c49bac8770ef95518faf20083e8b3e6150f45f Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:33 +0200 Subject: media: uapi: Add Raspberry Pi PiSP Back End uAPI Add the Raspberry Pi PiSP Back End uAPI header. The header defines the data type used to configure the PiSP Back End ISP. The detailed description of the types and of the ISP configuration procedure is available at https://datasheets.raspberrypi.com/camera/raspberry-pi-image-signal-processor-specification.pdf Signed-off-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- MAINTAINERS | 7 + .../uapi/linux/media/raspberrypi/pisp_be_config.h | 927 +++++++++++++++++++++ include/uapi/linux/media/raspberrypi/pisp_common.h | 199 +++++ 3 files changed, 1133 insertions(+) create mode 100644 include/uapi/linux/media/raspberrypi/pisp_be_config.h create mode 100644 include/uapi/linux/media/raspberrypi/pisp_common.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index ad1ecb2c4aed..861ee24cc1f7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18805,6 +18805,13 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/ras/amd/fmpm.c +RASPBERRY PI PISP BACK END +M: Jacopo Mondi +L: Raspberry Pi Kernel Maintenance +L: linux-media@vger.kernel.org +S: Maintained +F: include/uapi/linux/media/raspberrypi/ + RC-CORE / LIRC FRAMEWORK M: Sean Young L: linux-media@vger.kernel.org diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h new file mode 100644 index 000000000000..1684ae068d4f --- /dev/null +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -0,0 +1,927 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * PiSP Back End configuration definitions. + * + * Copyright (C) 2021 - Raspberry Pi Ltd + * + */ +#ifndef _UAPI_PISP_BE_CONFIG_H_ +#define _UAPI_PISP_BE_CONFIG_H_ + +#include + +#include "pisp_common.h" + +/* byte alignment for inputs */ +#define PISP_BACK_END_INPUT_ALIGN 4u +/* alignment for compressed inputs */ +#define PISP_BACK_END_COMPRESSED_ALIGN 8u +/* minimum required byte alignment for outputs */ +#define PISP_BACK_END_OUTPUT_MIN_ALIGN 16u +/* preferred byte alignment for outputs */ +#define PISP_BACK_END_OUTPUT_MAX_ALIGN 64u + +/* minimum allowed tile width anywhere in the pipeline */ +#define PISP_BACK_END_MIN_TILE_WIDTH 16u +/* minimum allowed tile width anywhere in the pipeline */ +#define PISP_BACK_END_MIN_TILE_HEIGHT 16u + +#define PISP_BACK_END_NUM_OUTPUTS 2 +#define PISP_BACK_END_HOG_OUTPUT 1 + +#define PISP_BACK_END_NUM_TILES 64 + +enum pisp_be_bayer_enable { + PISP_BE_BAYER_ENABLE_INPUT = 0x000001, + PISP_BE_BAYER_ENABLE_DECOMPRESS = 0x000002, + PISP_BE_BAYER_ENABLE_DPC = 0x000004, + PISP_BE_BAYER_ENABLE_GEQ = 0x000008, + PISP_BE_BAYER_ENABLE_TDN_INPUT = 0x000010, + PISP_BE_BAYER_ENABLE_TDN_DECOMPRESS = 0x000020, + PISP_BE_BAYER_ENABLE_TDN = 0x000040, + PISP_BE_BAYER_ENABLE_TDN_COMPRESS = 0x000080, + PISP_BE_BAYER_ENABLE_TDN_OUTPUT = 0x000100, + PISP_BE_BAYER_ENABLE_SDN = 0x000200, + PISP_BE_BAYER_ENABLE_BLC = 0x000400, + PISP_BE_BAYER_ENABLE_STITCH_INPUT = 0x000800, + PISP_BE_BAYER_ENABLE_STITCH_DECOMPRESS = 0x001000, + PISP_BE_BAYER_ENABLE_STITCH = 0x002000, + PISP_BE_BAYER_ENABLE_STITCH_COMPRESS = 0x004000, + PISP_BE_BAYER_ENABLE_STITCH_OUTPUT = 0x008000, + PISP_BE_BAYER_ENABLE_WBG = 0x010000, + PISP_BE_BAYER_ENABLE_CDN = 0x020000, + PISP_BE_BAYER_ENABLE_LSC = 0x040000, + PISP_BE_BAYER_ENABLE_TONEMAP = 0x080000, + PISP_BE_BAYER_ENABLE_CAC = 0x100000, + PISP_BE_BAYER_ENABLE_DEBIN = 0x200000, + PISP_BE_BAYER_ENABLE_DEMOSAIC = 0x400000, +}; + +enum pisp_be_rgb_enable { + PISP_BE_RGB_ENABLE_INPUT = 0x000001, + PISP_BE_RGB_ENABLE_CCM = 0x000002, + PISP_BE_RGB_ENABLE_SAT_CONTROL = 0x000004, + PISP_BE_RGB_ENABLE_YCBCR = 0x000008, + PISP_BE_RGB_ENABLE_FALSE_COLOUR = 0x000010, + PISP_BE_RGB_ENABLE_SHARPEN = 0x000020, + /* Preferred colours would occupy 0x000040 */ + PISP_BE_RGB_ENABLE_YCBCR_INVERSE = 0x000080, + PISP_BE_RGB_ENABLE_GAMMA = 0x000100, + PISP_BE_RGB_ENABLE_CSC0 = 0x000200, + PISP_BE_RGB_ENABLE_CSC1 = 0x000400, + PISP_BE_RGB_ENABLE_DOWNSCALE0 = 0x001000, + PISP_BE_RGB_ENABLE_DOWNSCALE1 = 0x002000, + PISP_BE_RGB_ENABLE_RESAMPLE0 = 0x008000, + PISP_BE_RGB_ENABLE_RESAMPLE1 = 0x010000, + PISP_BE_RGB_ENABLE_OUTPUT0 = 0x040000, + PISP_BE_RGB_ENABLE_OUTPUT1 = 0x080000, + PISP_BE_RGB_ENABLE_HOG = 0x200000 +}; + +#define PISP_BE_RGB_ENABLE_CSC(i) (PISP_BE_RGB_ENABLE_CSC0 << (i)) +#define PISP_BE_RGB_ENABLE_DOWNSCALE(i) (PISP_BE_RGB_ENABLE_DOWNSCALE0 << (i)) +#define PISP_BE_RGB_ENABLE_RESAMPLE(i) (PISP_BE_RGB_ENABLE_RESAMPLE0 << (i)) +#define PISP_BE_RGB_ENABLE_OUTPUT(i) (PISP_BE_RGB_ENABLE_OUTPUT0 << (i)) + +/* + * We use the enable flags to show when blocks are "dirty", but we need some + * extra ones too. + */ +enum pisp_be_dirty { + PISP_BE_DIRTY_GLOBAL = 0x0001, + PISP_BE_DIRTY_SH_FC_COMBINE = 0x0002, + PISP_BE_DIRTY_CROP = 0x0004 +}; + +/** + * struct pisp_be_global_config - PiSP global enable bitmaps + * @bayer_enables: Bayer input enable flags + * @rgb_enables: RGB output enable flags + * @bayer_order: Bayer input format ordering + * @pad: Padding bytes + */ +struct pisp_be_global_config { + __u32 bayer_enables; + __u32 rgb_enables; + __u8 bayer_order; + __u8 pad[3]; +} __attribute__((packed)); + +/** + * struct pisp_be_input_buffer_config - PiSP Back End input buffer + * @addr: Input buffer address + */ +struct pisp_be_input_buffer_config { + /* low 32 bits followed by high 32 bits (for each of up to 3 planes) */ + __u32 addr[3][2]; +} __attribute__((packed)); + +/** + * struct pisp_be_dpc_config - PiSP Back End DPC config + * + * Defective Pixel Correction configuration + * + * @coeff_level: Coefficient for the darkest neighbouring pixel value + * @coeff_range: Coefficient for the range of pixels for this Bayer channel + * @pad: Padding byte + * @flags: DPC configuration flags + */ +struct pisp_be_dpc_config { + __u8 coeff_level; + __u8 coeff_range; + __u8 pad; +#define PISP_BE_DPC_FLAG_FOLDBACK 1 + __u8 flags; +} __attribute__((packed)); + +/** + * struct pisp_be_geq_config - PiSP Back End GEQ config + * + * Green Equalisation configuration + * + * @offset: Offset value for threshold calculation + * @slope_sharper: Slope/Sharper configuration + * @min: Minimum value the threshold may have + * @max: Maximum value the threshold may have + */ +struct pisp_be_geq_config { + __u16 offset; +#define PISP_BE_GEQ_SHARPER BIT(15) +#define PISP_BE_GEQ_SLOPE ((1 << 10) - 1) + /* top bit is the "sharper" flag, slope value is bottom 10 bits */ + __u16 slope_sharper; + __u16 min; + __u16 max; +} __attribute__((packed)); + +/** + * struct pisp_be_tdn_input_buffer_config - PiSP Back End TDN input buffer + * @addr: TDN input buffer address + */ +struct pisp_be_tdn_input_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_tdn_config - PiSP Back End TDN config + * + * Temporal Denoise configuration + * + * @black_level: Black level value subtracted from pixels + * @ratio: Multiplier for the LTA input frame + * @noise_constant: Constant offset value used in noise estimation + * @noise_slope: Noise estimation multiplier + * @threshold: Threshold for TDN operations + * @reset: Disable TDN operations + * @pad: Padding byte + */ +struct pisp_be_tdn_config { + __u16 black_level; + __u16 ratio; + __u16 noise_constant; + __u16 noise_slope; + __u16 threshold; + __u8 reset; + __u8 pad; +} __attribute__((packed)); + +/** + * struct pisp_be_tdn_output_buffer_config - PiSP Back End TDN output buffer + * @addr: TDN output buffer address + */ +struct pisp_be_tdn_output_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_sdn_config - PiSP Back End SDN config + * + * Spatial Denoise configuration + * + * @black_level: Black level subtracted from pixel for noise estimation + * @leakage: Proportion of the original undenoised value to mix in + * denoised output + * @pad: Padding byte + * @noise_constant: Noise constant used for noise estimation + * @noise_slope: Noise slope value used for noise estimation + * @noise_constant2: Second noise constant used for noise estimation + * @noise_slope2: Second slope value used for noise estimation + */ +struct pisp_be_sdn_config { + __u16 black_level; + __u8 leakage; + __u8 pad; + __u16 noise_constant; + __u16 noise_slope; + __u16 noise_constant2; + __u16 noise_slope2; +} __attribute__((packed)); + +/** + * struct pisp_be_stitch_input_buffer_config - PiSP Back End Stitch input + * @addr: Stitch input buffer address + */ +struct pisp_be_stitch_input_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +#define PISP_BE_STITCH_STREAMING_LONG 0x8000 +#define PISP_BE_STITCH_EXPOSURE_RATIO_MASK 0x7fff + +/** + * struct pisp_be_stitch_config - PiSP Back End Stitch config + * + * Stitch block configuration + * + * @threshold_lo: Low threshold value + * @threshold_diff_power: Low and high threshold difference + * @pad: Padding bytes + * @exposure_ratio: Multiplier to convert long exposure pixels into + * short exposure pixels + * @motion_threshold_256: Motion threshold above which short exposure + * pixels are used + * @motion_threshold_recip: Reciprocal of motion_threshold_256 value + */ +struct pisp_be_stitch_config { + __u16 threshold_lo; + __u8 threshold_diff_power; + __u8 pad; + + /* top bit indicates whether streaming input is the long exposure */ + __u16 exposure_ratio; + + __u8 motion_threshold_256; + __u8 motion_threshold_recip; +} __attribute__((packed)); + +/** + * struct pisp_be_stitch_output_buffer_config - PiSP Back End Stitch output + * @addr: Stitch input buffer address + */ +struct pisp_be_stitch_output_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_cdn_config - PiSP Back End CDN config + * + * Colour Denoise configuration + * + * @thresh: Constant for noise estimation + * @iir_strength: Relative strength of the IIR part of the filter + * @g_adjust: Proportion of the change assigned to the G channel + */ +struct pisp_be_cdn_config { + __u16 thresh; + __u8 iir_strength; + __u8 g_adjust; +} __attribute__((packed)); + +#define PISP_BE_LSC_LOG_GRID_SIZE 5 +#define PISP_BE_LSC_GRID_SIZE (1 << PISP_BE_LSC_LOG_GRID_SIZE) +#define PISP_BE_LSC_STEP_PRECISION 18 + +/** + * struct pisp_be_lsc_config - PiSP Back End LSC config + * + * Lens Shading Correction configuration + * + * @grid_step_x: Reciprocal of cell size width + * @grid_step_y: Reciprocal of cell size height + * @lut_packed: Jointly-coded RGB gains for each LSC grid + */ +struct pisp_be_lsc_config { + /* (1<<18) / grid_cell_width */ + __u16 grid_step_x; + /* (1<<18) / grid_cell_height */ + __u16 grid_step_y; + /* RGB gains jointly encoded in 32 bits */ +#define PISP_BE_LSC_LUT_SIZE (PISP_BE_LSC_GRID_SIZE + 1) + __u32 lut_packed[PISP_BE_LSC_LUT_SIZE][PISP_BE_LSC_LUT_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_lsc_extra - PiSP Back End LSC Extra config + * @offset_x: Horizontal offset into the LSC table of this tile + * @offset_y: Vertical offset into the LSC table of this tile + */ +struct pisp_be_lsc_extra { + __u16 offset_x; + __u16 offset_y; +} __attribute__((packed)); + +#define PISP_BE_CAC_LOG_GRID_SIZE 3 +#define PISP_BE_CAC_GRID_SIZE (1 << PISP_BE_CAC_LOG_GRID_SIZE) +#define PISP_BE_CAC_STEP_PRECISION 20 + +/** + * struct pisp_be_cac_config - PiSP Back End CAC config + * + * Chromatic Aberration Correction config + * + * @grid_step_x: Reciprocal of cell size width + * @grid_step_y: Reciprocal of cell size height + * @lut: Pixel shift for the CAC grid + */ +struct pisp_be_cac_config { + /* (1<<20) / grid_cell_width */ + __u16 grid_step_x; + /* (1<<20) / grid_cell_height */ + __u16 grid_step_y; + /* [gridy][gridx][rb][xy] */ +#define PISP_BE_CAC_LUT_SIZE (PISP_BE_CAC_GRID_SIZE + 1) + __s8 lut[PISP_BE_CAC_LUT_SIZE][PISP_BE_CAC_LUT_SIZE][2][2]; +} __attribute__((packed)); + +/** + * struct pisp_be_cac_extra - PiSP Back End CAC extra config + * @offset_x: Horizontal offset into the CAC table of this tile + * @offset_y: Horizontal offset into the CAC table of this tile + */ +struct pisp_be_cac_extra { + __u16 offset_x; + __u16 offset_y; +} __attribute__((packed)); + +#define PISP_BE_DEBIN_NUM_COEFFS 4 + +/** + * struct pisp_be_debin_config - PiSP Back End Debin config + * + * Debinning configuration + * + * @coeffs: Filter coefficients for debinning + * @h_enable: Horizontal debinning enable + * @v_enable: Vertical debinning enable + * @pad: Padding bytes + */ +struct pisp_be_debin_config { + __s8 coeffs[PISP_BE_DEBIN_NUM_COEFFS]; + __s8 h_enable; + __s8 v_enable; + __s8 pad[2]; +} __attribute__((packed)); + +#define PISP_BE_TONEMAP_LUT_SIZE 64 + +/** + * struct pisp_be_tonemap_config - PiSP Back End Tonemap config + * + * Tonemapping configuration + * + * @detail_constant: Constant value for threshold calculation + * @detail_slope: Slope value for threshold calculation + * @iir_strength: Relative strength of the IIR fiter + * @strength: Strength factor + * @lut: Look-up table for tonemap curve + */ +struct pisp_be_tonemap_config { + __u16 detail_constant; + __u16 detail_slope; + __u16 iir_strength; + __u16 strength; + __u32 lut[PISP_BE_TONEMAP_LUT_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_demosaic_config - PiSP Back End Demosaic config + * + * Demosaic configuration + * + * @sharper: Use other Bayer channels to increase sharpness + * @fc_mode: Built-in false colour suppression mode + * @pad: Padding bytes + */ +struct pisp_be_demosaic_config { + __u8 sharper; + __u8 fc_mode; + __u8 pad[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_ccm_config - PiSP Back End CCM config + * + * Colour Correction Matrix configuration + * + * @coeffs: Matrix coefficients + * @pad: Padding bytes + * @offsets: Offsets triplet + */ +struct pisp_be_ccm_config { + __s16 coeffs[9]; + __u8 pad[2]; + __s32 offsets[3]; +} __attribute__((packed)); + +/** + * struct pisp_be_sat_control_config - PiSP Back End SAT config + * + * Saturation Control configuration + * + * @shift_r: Left shift for Red colour channel + * @shift_g: Left shift for Green colour channel + * @shift_b: Left shift for Blue colour channel + * @pad: Padding byte + */ +struct pisp_be_sat_control_config { + __u8 shift_r; + __u8 shift_g; + __u8 shift_b; + __u8 pad; +} __attribute__((packed)); + +/** + * struct pisp_be_false_colour_config - PiSP Back End False Colour config + * + * False Colour configuration + * + * @distance: Distance of neighbouring pixels, either 1 or 2 + * @pad: Padding bytes + */ +struct pisp_be_false_colour_config { + __u8 distance; + __u8 pad[3]; +} __attribute__((packed)); + +#define PISP_BE_SHARPEN_SIZE 5 +#define PISP_BE_SHARPEN_FUNC_NUM_POINTS 9 + +/** + * struct pisp_be_sharpen_config - PiSP Back End Sharpening config + * + * Sharpening configuration + * + * @kernel0: Coefficient for filter 0 + * @pad0: Padding byte + * @kernel1: Coefficient for filter 1 + * @pad1: Padding byte + * @kernel2: Coefficient for filter 2 + * @pad2: Padding byte + * @kernel3: Coefficient for filter 3 + * @pad3: Padding byte + * @kernel4: Coefficient for filter 4 + * @pad4: Padding byte + * @threshold_offset0: Offset for filter 0 response calculation + * @threshold_slope0: Slope multiplier for the filter 0 response calculation + * @scale0: Scale factor for filter 0 response calculation + * @pad5: Padding byte + * @threshold_offset1: Offset for filter 0 response calculation + * @threshold_slope1: Slope multiplier for the filter 0 response calculation + * @scale1: Scale factor for filter 0 response calculation + * @pad6: Padding byte + * @threshold_offset2: Offset for filter 0 response calculation + * @threshold_slope2: Slope multiplier for the filter 0 response calculation + * @scale2: Scale factor for filter 0 response calculation + * @pad7: Padding byte + * @threshold_offset3: Offset for filter 0 response calculation + * @threshold_slope3: Slope multiplier for the filter 0 response calculation + * @scale3: Scale factor for filter 0 response calculation + * @pad8: Padding byte + * @threshold_offset4: Offset for filter 0 response calculation + * @threshold_slope4: Slope multiplier for the filter 0 response calculation + * @scale4: Scale factor for filter 0 response calculation + * @pad9: Padding byte + * @positive_strength: Factor to scale the positive sharpening strength + * @positive_pre_limit: Maximum allowed possible positive sharpening value + * @positive_func: Gain factor applied to positive sharpening response + * @positive_limit: Final gain factor applied to positive sharpening + * @negative_strength: Factor to scale the negative sharpening strength + * @negative_pre_limit: Maximum allowed possible negative sharpening value + * @negative_func: Gain factor applied to negative sharpening response + * @negative_limit: Final gain factor applied to negative sharpening + * @enables: Filter enable mask + * @white: White output pixel filter mask + * @black: Black output pixel filter mask + * @grey: Grey output pixel filter mask + */ +struct pisp_be_sharpen_config { + __s8 kernel0[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad0[3]; + __s8 kernel1[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad1[3]; + __s8 kernel2[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad2[3]; + __s8 kernel3[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad3[3]; + __s8 kernel4[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad4[3]; + __u16 threshold_offset0; + __u16 threshold_slope0; + __u16 scale0; + __u16 pad5; + __u16 threshold_offset1; + __u16 threshold_slope1; + __u16 scale1; + __u16 pad6; + __u16 threshold_offset2; + __u16 threshold_slope2; + __u16 scale2; + __u16 pad7; + __u16 threshold_offset3; + __u16 threshold_slope3; + __u16 scale3; + __u16 pad8; + __u16 threshold_offset4; + __u16 threshold_slope4; + __u16 scale4; + __u16 pad9; + __u16 positive_strength; + __u16 positive_pre_limit; + __u16 positive_func[PISP_BE_SHARPEN_FUNC_NUM_POINTS]; + __u16 positive_limit; + __u16 negative_strength; + __u16 negative_pre_limit; + __u16 negative_func[PISP_BE_SHARPEN_FUNC_NUM_POINTS]; + __u16 negative_limit; + __u8 enables; + __u8 white; + __u8 black; + __u8 grey; +} __attribute__((packed)); + +/** + * struct pisp_be_sh_fc_combine_config - PiSP Back End Sharpening and + * False Colour config + * + * Sharpening and False Colour configuration + * + * @y_factor: Control amount of desaturation of pixels being darkened + * @c1_factor: Control amount of brightening of a pixel for the Cb + * channel + * @c2_factor: Control amount of brightening of a pixel for the Cr + * channel + * @pad: Padding byte + */ +struct pisp_be_sh_fc_combine_config { + __u8 y_factor; + __u8 c1_factor; + __u8 c2_factor; + __u8 pad; +} __attribute__((packed)); + +#define PISP_BE_GAMMA_LUT_SIZE 64 + +/** + * struct pisp_be_gamma_config - PiSP Back End Gamma configuration + * @lut: Gamma curve look-up table + */ +struct pisp_be_gamma_config { + __u32 lut[PISP_BE_GAMMA_LUT_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_crop_config - PiSP Back End Crop config + * + * Crop configuration + * + * @offset_x: Number of pixels cropped from the left of the tile + * @offset_y: Number of pixels cropped from the top of the tile + * @width: Width of the cropped tile output + * @height: Height of the cropped tile output + */ +struct pisp_be_crop_config { + __u16 offset_x, offset_y; + __u16 width, height; +} __attribute__((packed)); + +#define PISP_BE_RESAMPLE_FILTER_SIZE 96 + +/** + * struct pisp_be_resample_config - PiSP Back End Resampling config + * + * Resample configuration + * + * @scale_factor_h: Horizontal scale factor + * @scale_factor_v: Vertical scale factor + * @coef: Resample coefficients + */ +struct pisp_be_resample_config { + __u16 scale_factor_h, scale_factor_v; + __s16 coef[PISP_BE_RESAMPLE_FILTER_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_resample_extra - PiSP Back End Resample config + * + * Resample configuration + * + * @scaled_width: Width in pixels of the scaled output + * @scaled_height: Height in pixels of the scaled output + * @initial_phase_h: Initial horizontal phase + * @initial_phase_v: Initial vertical phase + */ +struct pisp_be_resample_extra { + __u16 scaled_width; + __u16 scaled_height; + __s16 initial_phase_h[3]; + __s16 initial_phase_v[3]; +} __attribute__((packed)); + +/** + * struct pisp_be_downscale_config - PiSP Back End Downscale config + * + * Downscale configuration + * + * @scale_factor_h: Horizontal scale factor + * @scale_factor_v: Vertical scale factor + * @scale_recip_h: Horizontal reciprocal factor + * @scale_recip_v: Vertical reciprocal factor + */ +struct pisp_be_downscale_config { + __u16 scale_factor_h; + __u16 scale_factor_v; + __u16 scale_recip_h; + __u16 scale_recip_v; +} __attribute__((packed)); + +/** + * struct pisp_be_downscale_extra - PiSP Back End Downscale Extra config + * @scaled_width: Scaled image width + * @scaled_height: Scaled image height + */ +struct pisp_be_downscale_extra { + __u16 scaled_width; + __u16 scaled_height; +} __attribute__((packed)); + +/** + * struct pisp_be_hog_config - PiSP Back End HOG config + * + * Histogram of Oriented Gradients configuration + * + * @compute_signed: Set 0 for unsigned gradients, 1 for signed + * @channel_mix: Channels proportions to use + * @stride: Stride in bytes between blocks directly below + */ +struct pisp_be_hog_config { + __u8 compute_signed; + __u8 channel_mix[3]; + __u32 stride; +} __attribute__((packed)); + +struct pisp_be_axi_config { + __u8 r_qos; /* Read QoS */ + __u8 r_cache_prot; /* Read { prot[2:0], cache[3:0] } */ + __u8 w_qos; /* Write QoS */ + __u8 w_cache_prot; /* Write { prot[2:0], cache[3:0] } */ +} __attribute__((packed)); + +/** + * enum pisp_be_transform - PiSP Back End Transform flags + * @PISP_BE_TRANSFORM_NONE: No transform + * @PISP_BE_TRANSFORM_HFLIP: Horizontal flip + * @PISP_BE_TRANSFORM_VFLIP: Vertical flip + * @PISP_BE_TRANSFORM_ROT180: 180 degress rotation + */ +enum pisp_be_transform { + PISP_BE_TRANSFORM_NONE = 0x0, + PISP_BE_TRANSFORM_HFLIP = 0x1, + PISP_BE_TRANSFORM_VFLIP = 0x2, + PISP_BE_TRANSFORM_ROT180 = + (PISP_BE_TRANSFORM_HFLIP | PISP_BE_TRANSFORM_VFLIP) +}; + +struct pisp_be_output_format_config { + struct pisp_image_format_config image; + __u8 transform; + __u8 pad[3]; + __u16 lo; + __u16 hi; + __u16 lo2; + __u16 hi2; +} __attribute__((packed)); + +/** + * struct pisp_be_output_buffer_config - PiSP Back End Output buffer + * @addr: Output buffer address + */ +struct pisp_be_output_buffer_config { + /* low 32 bits followed by high 32 bits (for each of 3 planes) */ + __u32 addr[3][2]; +} __attribute__((packed)); + +/** + * struct pisp_be_hog_buffer_config - PiSP Back End HOG buffer + * @addr: HOG buffer address + */ +struct pisp_be_hog_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_config - RaspberryPi PiSP Back End Processing configuration + * + * @global: Global PiSP configuration + * @input_format: Input image format + * @decompress: Decompress configuration + * @dpc: Defective Pixel Correction configuration + * @geq: Green Equalisation configuration + * @tdn_input_format: Temporal Denoise input format + * @tdn_decompress: Temporal Denoise decompress configuration + * @tdn: Temporal Denoise configuration + * @tdn_compress: Temporal Denoise compress configuration + * @tdn_output_format: Temporal Denoise output format + * @sdn: Spatial Denoise configuration + * @blc: Black Level Correction configuration + * @stitch_compress: Stitch compress configuration + * @stitch_output_format: Stitch output format + * @stitch_input_format: Stitch input format + * @stitch_decompress: Stitch decompress configuration + * @stitch: Stitch configuration + * @lsc: Lens Shading Correction configuration + * @wbg: White Balance Gain configuration + * @cdn: Colour Denoise configuration + * @cac: Colour Aberration Correction configuration + * @debin: Debinning configuration + * @tonemap: Tonemapping configuration + * @demosaic: Demosaicing configuration + * @ccm: Colour Correction Matrix configuration + * @sat_control: Saturation Control configuration + * @ycbcr: YCbCr colour correction configuration + * @sharpen: Sharpening configuration + * @false_colour: False colour correction + * @sh_fc_combine: Sharpening and False Colour correction + * @ycbcr_inverse: Inverse YCbCr colour correction + * @gamma: Gamma curve configuration + * @csc: Color Space Conversion configuration + * @downscale: Downscale configuration + * @resample: Resampling configuration + * @output_format: Output format configuration + * @hog: HOG configuration + */ +struct pisp_be_config { + struct pisp_be_global_config global; + struct pisp_image_format_config input_format; + struct pisp_decompress_config decompress; + struct pisp_be_dpc_config dpc; + struct pisp_be_geq_config geq; + struct pisp_image_format_config tdn_input_format; + struct pisp_decompress_config tdn_decompress; + struct pisp_be_tdn_config tdn; + struct pisp_compress_config tdn_compress; + struct pisp_image_format_config tdn_output_format; + struct pisp_be_sdn_config sdn; + struct pisp_bla_config blc; + struct pisp_compress_config stitch_compress; + struct pisp_image_format_config stitch_output_format; + struct pisp_image_format_config stitch_input_format; + struct pisp_decompress_config stitch_decompress; + struct pisp_be_stitch_config stitch; + struct pisp_be_lsc_config lsc; + struct pisp_wbg_config wbg; + struct pisp_be_cdn_config cdn; + struct pisp_be_cac_config cac; + struct pisp_be_debin_config debin; + struct pisp_be_tonemap_config tonemap; + struct pisp_be_demosaic_config demosaic; + struct pisp_be_ccm_config ccm; + struct pisp_be_sat_control_config sat_control; + struct pisp_be_ccm_config ycbcr; + struct pisp_be_sharpen_config sharpen; + struct pisp_be_false_colour_config false_colour; + struct pisp_be_sh_fc_combine_config sh_fc_combine; + struct pisp_be_ccm_config ycbcr_inverse; + struct pisp_be_gamma_config gamma; + struct pisp_be_ccm_config csc[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_downscale_config downscale[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_resample_config resample[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_output_format_config + output_format[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_hog_config hog; +} __attribute__((packed)); + +/** + * enum pisp_tile_edge - PiSP Back End Tile position + * @PISP_LEFT_EDGE: Left edge tile + * @PISP_RIGHT_EDGE: Right edge tile + * @PISP_TOP_EDGE: Top edge tile + * @PISP_BOTTOM_EDGE: Bottom edge tile + */ +enum pisp_tile_edge { + PISP_LEFT_EDGE = (1 << 0), + PISP_RIGHT_EDGE = (1 << 1), + PISP_TOP_EDGE = (1 << 2), + PISP_BOTTOM_EDGE = (1 << 3) +}; + +/** + * struct pisp_tile - Raspberry Pi PiSP Back End tile configuration + * + * Tile parameters: each set of tile parameters is a 160-bytes block of data + * which contains the tile processing parameters. + * + * @edge: Edge tile flag + * @pad0: Padding bytes + * @input_addr_offset: Top-left pixel offset, in bytes + * @input_addr_offset2: Top-left pixel offset, in bytes for the second/ + * third image planes + * @input_offset_x: Horizontal offset in pixels of this tile in the + * input image + * @input_offset_y: Vertical offset in pixels of this tile in the + * input image + * @input_width: Width in pixels of this tile + * @input_height: Height in pixels of the this tile + * @tdn_input_addr_offset: TDN input image offset, in bytes + * @tdn_output_addr_offset: TDN output image offset, in bytes + * @stitch_input_addr_offset: Stitch input image offset, in bytes + * @stitch_output_addr_offset: Stitch output image offset, in bytes + * @lsc_grid_offset_x: Horizontal offset in the LSC table for this tile + * @lsc_grid_offset_y: Vertical offset in the LSC table for this tile + * @cac_grid_offset_x: Horizontal offset in the CAC table for this tile + * @cac_grid_offset_y: Horizontal offset in the CAC table for this tile + * @crop_x_start: Number of pixels cropped from the left of the + * tile + * @crop_x_end: Number of pixels cropped from the right of the + * tile + * @crop_y_start: Number of pixels cropped from the top of the + * tile + * @crop_y_end: Number of pixels cropped from the bottom of the + * tile + * @downscale_phase_x: Initial horizontal phase in pixels + * @downscale_phase_y: Initial vertical phase in pixels + * @resample_in_width: Width in pixels of the tile entering the + * Resample block + * @resample_in_height: Height in pixels of the tile entering the + * Resample block + * @resample_phase_x: Initial horizontal phase for the Resample block + * @resample_phase_y: Initial vertical phase for the Resample block + * @output_offset_x: Horizontal offset in pixels where the tile will + * be written into the output image + * @output_offset_y: Vertical offset in pixels where the tile will be + * written into the output image + * @output_width: Width in pixels in the output image of this tile + * @output_height: Height in pixels in the output image of this tile + * @output_addr_offset: Offset in bytes into the output buffer + * @output_addr_offset2: Offset in bytes into the output buffer for the + * second and third plane + * @output_hog_addr_offset: Offset in bytes into the HOG buffer where + * results of this tile are to be written + */ +struct pisp_tile { + __u8 edge; /* enum pisp_tile_edge */ + __u8 pad0[3]; + /* 4 bytes */ + __u32 input_addr_offset; + __u32 input_addr_offset2; + __u16 input_offset_x; + __u16 input_offset_y; + __u16 input_width; + __u16 input_height; + /* 20 bytes */ + __u32 tdn_input_addr_offset; + __u32 tdn_output_addr_offset; + __u32 stitch_input_addr_offset; + __u32 stitch_output_addr_offset; + /* 36 bytes */ + __u32 lsc_grid_offset_x; + __u32 lsc_grid_offset_y; + /* 44 bytes */ + __u32 cac_grid_offset_x; + __u32 cac_grid_offset_y; + /* 52 bytes */ + __u16 crop_x_start[PISP_BACK_END_NUM_OUTPUTS]; + __u16 crop_x_end[PISP_BACK_END_NUM_OUTPUTS]; + __u16 crop_y_start[PISP_BACK_END_NUM_OUTPUTS]; + __u16 crop_y_end[PISP_BACK_END_NUM_OUTPUTS]; + /* 68 bytes */ + /* Ordering is planes then branches */ + __u16 downscale_phase_x[3 * PISP_BACK_END_NUM_OUTPUTS]; + __u16 downscale_phase_y[3 * PISP_BACK_END_NUM_OUTPUTS]; + /* 92 bytes */ + __u16 resample_in_width[PISP_BACK_END_NUM_OUTPUTS]; + __u16 resample_in_height[PISP_BACK_END_NUM_OUTPUTS]; + /* 100 bytes */ + /* Ordering is planes then branches */ + __u16 resample_phase_x[3 * PISP_BACK_END_NUM_OUTPUTS]; + __u16 resample_phase_y[3 * PISP_BACK_END_NUM_OUTPUTS]; + /* 124 bytes */ + __u16 output_offset_x[PISP_BACK_END_NUM_OUTPUTS]; + __u16 output_offset_y[PISP_BACK_END_NUM_OUTPUTS]; + __u16 output_width[PISP_BACK_END_NUM_OUTPUTS]; + __u16 output_height[PISP_BACK_END_NUM_OUTPUTS]; + /* 140 bytes */ + __u32 output_addr_offset[PISP_BACK_END_NUM_OUTPUTS]; + __u32 output_addr_offset2[PISP_BACK_END_NUM_OUTPUTS]; + /* 156 bytes */ + __u32 output_hog_addr_offset; + /* 160 bytes */ +} __attribute__((packed)); + +/** + * struct pisp_be_tiles_config - Raspberry Pi PiSP Back End configuration + * @tiles: Tile descriptors + * @num_tiles: Number of tiles + * @config: PiSP Back End configuration + */ +struct pisp_be_tiles_config { + struct pisp_tile tiles[PISP_BACK_END_NUM_TILES]; + __u32 num_tiles; + struct pisp_be_config config; +} __attribute__((packed)); + +#endif /* _UAPI_PISP_BE_CONFIG_H_ */ diff --git a/include/uapi/linux/media/raspberrypi/pisp_common.h b/include/uapi/linux/media/raspberrypi/pisp_common.h new file mode 100644 index 000000000000..b2522e29c976 --- /dev/null +++ b/include/uapi/linux/media/raspberrypi/pisp_common.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * RP1 PiSP common definitions. + * + * Copyright (C) 2021 - Raspberry Pi Ltd. + * + */ +#ifndef _UAPI_PISP_COMMON_H_ +#define _UAPI_PISP_COMMON_H_ + +#include + +struct pisp_image_format_config { + /* size in pixels */ + __u16 width; + __u16 height; + /* must match struct pisp_image_format below */ + __u32 format; + __s32 stride; + /* some planar image formats will need a second stride */ + __s32 stride2; +} __attribute__((packed)); + +enum pisp_bayer_order { + /* + * Note how bayer_order&1 tells you if G is on the even pixels of the + * checkerboard or not, and bayer_order&2 tells you if R is on the even + * rows or is swapped with B. Note that if the top (of the 8) bits is + * set, this denotes a monochrome or greyscale image, and the lower bits + * should all be ignored. + */ + PISP_BAYER_ORDER_RGGB = 0, + PISP_BAYER_ORDER_GBRG = 1, + PISP_BAYER_ORDER_BGGR = 2, + PISP_BAYER_ORDER_GRBG = 3, + PISP_BAYER_ORDER_GREYSCALE = 128 +}; + +enum pisp_image_format { + /* + * Precise values are mostly tbd. Generally these will be portmanteau + * values comprising bit fields and flags. This format must be shared + * throughout the PiSP. + */ + PISP_IMAGE_FORMAT_BPS_8 = 0x00000000, + PISP_IMAGE_FORMAT_BPS_10 = 0x00000001, + PISP_IMAGE_FORMAT_BPS_12 = 0x00000002, + PISP_IMAGE_FORMAT_BPS_16 = 0x00000003, + PISP_IMAGE_FORMAT_BPS_MASK = 0x00000003, + + PISP_IMAGE_FORMAT_PLANARITY_INTERLEAVED = 0x00000000, + PISP_IMAGE_FORMAT_PLANARITY_SEMI_PLANAR = 0x00000010, + PISP_IMAGE_FORMAT_PLANARITY_PLANAR = 0x00000020, + PISP_IMAGE_FORMAT_PLANARITY_MASK = 0x00000030, + + PISP_IMAGE_FORMAT_SAMPLING_444 = 0x00000000, + PISP_IMAGE_FORMAT_SAMPLING_422 = 0x00000100, + PISP_IMAGE_FORMAT_SAMPLING_420 = 0x00000200, + PISP_IMAGE_FORMAT_SAMPLING_MASK = 0x00000300, + + PISP_IMAGE_FORMAT_ORDER_NORMAL = 0x00000000, + PISP_IMAGE_FORMAT_ORDER_SWAPPED = 0x00001000, + + PISP_IMAGE_FORMAT_SHIFT_0 = 0x00000000, + PISP_IMAGE_FORMAT_SHIFT_1 = 0x00010000, + PISP_IMAGE_FORMAT_SHIFT_2 = 0x00020000, + PISP_IMAGE_FORMAT_SHIFT_3 = 0x00030000, + PISP_IMAGE_FORMAT_SHIFT_4 = 0x00040000, + PISP_IMAGE_FORMAT_SHIFT_5 = 0x00050000, + PISP_IMAGE_FORMAT_SHIFT_6 = 0x00060000, + PISP_IMAGE_FORMAT_SHIFT_7 = 0x00070000, + PISP_IMAGE_FORMAT_SHIFT_8 = 0x00080000, + PISP_IMAGE_FORMAT_SHIFT_MASK = 0x000f0000, + + PISP_IMAGE_FORMAT_UNCOMPRESSED = 0x00000000, + PISP_IMAGE_FORMAT_COMPRESSION_MODE_1 = 0x01000000, + PISP_IMAGE_FORMAT_COMPRESSION_MODE_2 = 0x02000000, + PISP_IMAGE_FORMAT_COMPRESSION_MODE_3 = 0x03000000, + PISP_IMAGE_FORMAT_COMPRESSION_MASK = 0x03000000, + + PISP_IMAGE_FORMAT_HOG_SIGNED = 0x04000000, + PISP_IMAGE_FORMAT_HOG_UNSIGNED = 0x08000000, + PISP_IMAGE_FORMAT_INTEGRAL_IMAGE = 0x10000000, + PISP_IMAGE_FORMAT_WALLPAPER_ROLL = 0x20000000, + PISP_IMAGE_FORMAT_THREE_CHANNEL = 0x40000000, + + /* Lastly a few specific instantiations of the above. */ + PISP_IMAGE_FORMAT_SINGLE_16 = PISP_IMAGE_FORMAT_BPS_16, + PISP_IMAGE_FORMAT_THREE_16 = PISP_IMAGE_FORMAT_BPS_16 | + PISP_IMAGE_FORMAT_THREE_CHANNEL +}; + +#define PISP_IMAGE_FORMAT_bps_8(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_8) +#define PISP_IMAGE_FORMAT_bps_10(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_10) +#define PISP_IMAGE_FORMAT_bps_12(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_12) +#define PISP_IMAGE_FORMAT_bps_16(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_16) +#define PISP_IMAGE_FORMAT_bps(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) ? \ + 8 + (2 << (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) - 1)) : 8) +#define PISP_IMAGE_FORMAT_shift(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SHIFT_MASK) / PISP_IMAGE_FORMAT_SHIFT_1) +#define PISP_IMAGE_FORMAT_three_channel(fmt) \ + ((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL) +#define PISP_IMAGE_FORMAT_single_channel(fmt) \ + (!((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL)) +#define PISP_IMAGE_FORMAT_compressed(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_COMPRESSION_MASK) != \ + PISP_IMAGE_FORMAT_UNCOMPRESSED) +#define PISP_IMAGE_FORMAT_sampling_444(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ + PISP_IMAGE_FORMAT_SAMPLING_444) +#define PISP_IMAGE_FORMAT_sampling_422(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ + PISP_IMAGE_FORMAT_SAMPLING_422) +#define PISP_IMAGE_FORMAT_sampling_420(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ + PISP_IMAGE_FORMAT_SAMPLING_420) +#define PISP_IMAGE_FORMAT_order_normal(fmt) \ + (!((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED)) +#define PISP_IMAGE_FORMAT_order_swapped(fmt) \ + ((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED) +#define PISP_IMAGE_FORMAT_interleaved(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ + PISP_IMAGE_FORMAT_PLANARITY_INTERLEAVED) +#define PISP_IMAGE_FORMAT_semiplanar(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ + PISP_IMAGE_FORMAT_PLANARITY_SEMI_PLANAR) +#define PISP_IMAGE_FORMAT_planar(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ + PISP_IMAGE_FORMAT_PLANARITY_PLANAR) +#define PISP_IMAGE_FORMAT_wallpaper(fmt) \ + ((fmt) & PISP_IMAGE_FORMAT_WALLPAPER_ROLL) +#define PISP_IMAGE_FORMAT_HOG(fmt) \ + ((fmt) & \ + (PISP_IMAGE_FORMAT_HOG_SIGNED | PISP_IMAGE_FORMAT_HOG_UNSIGNED)) + +#define PISP_WALLPAPER_WIDTH 128 /* in bytes */ + +struct pisp_bla_config { + __u16 black_level_r; + __u16 black_level_gr; + __u16 black_level_gb; + __u16 black_level_b; + __u16 output_black_level; + __u8 pad[2]; +} __attribute__((packed)); + +struct pisp_wbg_config { + __u16 gain_r; + __u16 gain_g; + __u16 gain_b; + __u8 pad[2]; +} __attribute__((packed)); + +struct pisp_compress_config { + /* value subtracted from incoming data */ + __u16 offset; + __u8 pad; + /* 1 => Companding; 2 => Delta (recommended); 3 => Combined (for HDR) */ + __u8 mode; +} __attribute__((packed)); + +struct pisp_decompress_config { + /* value added to reconstructed data */ + __u16 offset; + __u8 pad; + /* 1 => Companding; 2 => Delta (recommended); 3 => Combined (for HDR) */ + __u8 mode; +} __attribute__((packed)); + +enum pisp_axi_flags { + /* + * round down bursts to end at a 32-byte boundary, to align following + * bursts + */ + PISP_AXI_FLAG_ALIGN = 128, + /* for FE writer: force WSTRB high, to pad output to 16-byte boundary */ + PISP_AXI_FLAG_PAD = 64, + /* for FE writer: Use Output FIFO level to trigger "panic" */ + PISP_AXI_FLAG_PANIC = 32, +}; + +struct pisp_axi_config { + /* + * burst length minus one, which must be in the range 0:15; OR'd with + * flags + */ + __u8 maxlen_flags; + /* { prot[2:0], cache[3:0] } fields, echoed on AXI bus */ + __u8 cache_prot; + /* QoS field(s) (4x4 bits for FE writer; 4 bits for other masters) */ + __u16 qos; +} __attribute__((packed)); + +#endif /* _UAPI_PISP_COMMON_H_ */ -- cgit v1.2.3 From 8f6c2202222faffa0959929d8cd9090254a60831 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:34 +0200 Subject: media: uapi: Add meta pixel format for PiSP BE config Add format description for the PiSP Back End configuration parameter buffer. Signed-off-by: Jacopo Mondi Reviewed-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/meta-formats.rst | 1 + .../userspace-api/media/v4l/metafmt-pisp-be.rst | 56 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 3 ++ 4 files changed, 61 insertions(+) create mode 100644 Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/meta-formats.rst b/Documentation/userspace-api/media/v4l/meta-formats.rst index c23aac823d2c..c6e56b5888bc 100644 --- a/Documentation/userspace-api/media/v4l/meta-formats.rst +++ b/Documentation/userspace-api/media/v4l/meta-formats.rst @@ -15,6 +15,7 @@ These formats are used for the :ref:`metadata` interface only. metafmt-d4xx metafmt-generic metafmt-intel-ipu3 + metafmt-pisp-be metafmt-rkisp1 metafmt-uvc metafmt-vivid diff --git a/Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst b/Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst new file mode 100644 index 000000000000..3281fe366c86 --- /dev/null +++ b/Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst @@ -0,0 +1,56 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _v4l2-meta-fmt-rpi-be-cfg: + +************************ +V4L2_META_FMT_RPI_BE_CFG +************************ + +Raspberry Pi PiSP Back End configuration format +=============================================== + +The Raspberry Pi PiSP Back End memory-to-memory image signal processor is +configured by userspace by providing a buffer of configuration parameters +to the `pispbe-config` output video device node using the +:c:type:`v4l2_meta_format` interface. + +The PiSP Back End processes images in tiles, and its configuration requires +specifying two different sets of parameters by populating the members of +:c:type:`pisp_be_tiles_config` defined in the ``pisp_be_config.h`` header file. + +The `Raspberry Pi PiSP technical specification +`_ +provide detailed description of the ISP back end configuration and programming +model. + +Global configuration data +------------------------- + +The global configuration data describe how the pixels in a particular image are +to be processed and is therefore shared across all the tiles of the image. So +for example, LSC (Lens Shading Correction) or Denoise parameters would be common +across all tiles from the same frame. + +Global configuration data are passed to the ISP by populating the member of +:c:type:`pisp_be_config`. + +Tile parameters +--------------- + +As the ISP processes images in tiles, each set of tiles parameters describe how +a single tile in an image is going to be processed. A single set of tile +parameters consist of 160 bytes of data and to process a batch of tiles several +sets of tiles parameters are required. + +Tiles parameters are passed to the ISP by populating the member of +``pisp_tile`` and the ``num_tiles`` fields of :c:type:`pisp_be_tiles_config`. + +Raspberry Pi PiSP Back End uAPI data types +========================================== + +This section describes the data types exposed to userspace by the Raspberry Pi +PiSP Back End. The section is informative only, for a detailed description of +each field refer to the `Raspberry Pi PiSP technical specification +`_. + +.. kernel-doc:: include/uapi/linux/media/raspberrypi/pisp_be_config.h diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ee97643ff3a7..7c684788997c 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1465,6 +1465,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y210: descr = "10-bit YUYV Packed"; break; case V4L2_PIX_FMT_Y212: descr = "12-bit YUYV Packed"; break; case V4L2_PIX_FMT_Y216: descr = "16-bit YUYV Packed"; break; + case V4L2_META_FMT_RPI_BE_CFG: descr = "RPi PiSP BE Config format"; break; case V4L2_META_FMT_GENERIC_8: descr = "8-bit Generic Metadata"; break; case V4L2_META_FMT_GENERIC_CSI2_10: descr = "8-bit Generic Meta, 10b CSI-2"; break; case V4L2_META_FMT_GENERIC_CSI2_12: descr = "8-bit Generic Meta, 12b CSI-2"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index dd6876380fe3..96fc0456081e 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -843,6 +843,9 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_PARAMS v4l2_fourcc('R', 'K', '1', 'P') /* Rockchip ISP1 3A Parameters */ #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ +/* Vendor specific - used for RaspberryPi PiSP */ +#define V4L2_META_FMT_RPI_BE_CFG v4l2_fourcc('R', 'P', 'B', 'C') /* PiSP BE configuration */ + #ifdef __KERNEL__ /* * Line-based metadata formats. Remember to update v4l_fill_fmtdesc() when -- cgit v1.2.3 From d260c1224786c870edbae09ef6ecf5f35361821e Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:35 +0200 Subject: media: uapi: Add PiSP Compressed RAW Bayer formats Add Raspberry Pi compressed RAW Bayer formats. The compression algorithm description is provided by Nick Hollinghurst from Raspberry Pi. Signed-off-by: Jacopo Mondi Reviewed-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-bayer.rst | 1 + .../media/v4l/pixfmt-srggb8-pisp-comp.rst | 74 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 10 +++ include/uapi/linux/videodev2.h | 12 ++++ 4 files changed, 97 insertions(+) create mode 100644 Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst b/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst index 2500413e5f43..ed3eb432967d 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst @@ -20,6 +20,7 @@ orders. See also `the Wikipedia article on Bayer filter :maxdepth: 1 pixfmt-srggb8 + pixfmt-srggb8-pisp-comp pixfmt-srggb10 pixfmt-srggb10p pixfmt-srggb10alaw8 diff --git a/Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst b/Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst new file mode 100644 index 000000000000..5a82a15559d6 --- /dev/null +++ b/Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst @@ -0,0 +1,74 @@ +.. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later + +.. _v4l2-pix-fmt-pisp-comp1-rggb: +.. _v4l2-pix-fmt-pisp-comp1-grbg: +.. _v4l2-pix-fmt-pisp-comp1-gbrg: +.. _v4l2-pix-fmt-pisp-comp1-bggr: +.. _v4l2-pix-fmt-pisp-comp1-mono: +.. _v4l2-pix-fmt-pisp-comp2-rggb: +.. _v4l2-pix-fmt-pisp-comp2-grbg: +.. _v4l2-pix-fmt-pisp-comp2-gbrg: +.. _v4l2-pix-fmt-pisp-comp2-bggr: +.. _v4l2-pix-fmt-pisp-comp2-mono: + +************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************** +V4L2_PIX_FMT_PISP_COMP1_RGGB ('PC1R'), V4L2_PIX_FMT_PISP_COMP1_GRBG ('PC1G'), V4L2_PIX_FMT_PISP_COMP1_GBRG ('PC1g'), V4L2_PIX_FMT_PISP_COMP1_BGGR ('PC1B), V4L2_PIX_FMT_PISP_COMP1_MONO ('PC1M'), V4L2_PIX_FMT_PISP_COMP2_RGGB ('PC2R'), V4L2_PIX_FMT_PISP_COMP2_GRBG ('PC2G'), V4L2_PIX_FMT_PISP_COMP2_GBRG ('PC2g'), V4L2_PIX_FMT_PISP_COMP2_BGGR ('PC2B), V4L2_PIX_FMT_PISP_COMP2_MONO ('PC2M') +************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************** + +================================================ +Raspberry Pi PiSP compressed 8-bit Bayer formats +================================================ + +Description +=========== + +The Raspberry Pi ISP (PiSP) uses a family of three fixed-rate compressed Bayer +formats. A black-level offset may be subtracted to improve compression +efficiency; the nominal black level and amount of offset must be signalled out +of band. Each scanline is padded to a multiple of 8 pixels wide, and each block +of 8 horizontally-contiguous pixels is coded using 8 bytes. + +Mode 1 uses a quantization and delta-based coding scheme which preserves up to +12 significant bits. Mode 2 is a simple sqrt-like companding scheme with 6 PWL +chords, preserving up to 12 significant bits. Mode 3 combines both companding +(with 4 chords) and the delta scheme, preserving up to 14 significant bits. + +The remainder of this description applies to Modes 1 and 3. + +Each block of 8 pixels is separated into even and odd phases of 4 pixels, +coded independently by 32-bit words at successive locations in memory. +The two LS bits of each 32-bit word give its "quantization mode". + +In quantization mode 0, the lowest 321 quantization levels are multiples of +FSD/4096 and the remaining levels are successive multiples of FSD/2048. +Quantization modes 1 and 2 use linear quantization with step sizes of +FSD/1024 and FSD/512 respectively. Each of the four pixels is quantized +independently, with rounding to the nearest level. +In quantization mode 2 where the middle two samples have quantized values +(q1,q2) both in the range [384..511], they are coded using 9 bits for q1 +followed by 7 bits for (q2 & 127). Otherwise, for quantization modes +0, 1 and 2: a 9-bit field encodes MIN(q1,q2) which must be in the range +[0..511] and a 7-bit field encodes (q2-q1+64) which must be in [0..127]. + +Each of the outer samples (q0,q3) is encoded using a 7-bit field based +on its inner neighbour q1 or q2. In quantization mode 2 where the inner +sample has a quantized value in the range [448..511], the field value is +(q0-384). Otherwise for quantization modes 0, 1 and 2: The outer sample +is encoded as (q0-MAX(0,q1-64)). q3 is likewise coded based on q2. +Each of these values must be in the range [0..127]. All these fields +of 2, 9, 7, 7, 7 bits respectively are packed in little-endian order +to give a 32-bit word with LE byte order. + +Quantization mode 3 has a "7.5-bit" escape, used when none of the above +encodings will fit. Each pixel value is quantized to the nearest of 176 +levels, where the lowest 95 levels are multiples of FSD/256 and the +remaining levels are multiples of FSD/128 (level 175 represents values +very close to FSD and may require saturating arithmetic to decode). + +Each pair of quantized pixels (q0,q1) or (q2,q3) is jointly coded +by a 15-bit field: 2816*(q0>>4) + 16*q1 + (q0&15). +Three fields of 2, 15, 15 bits are packed in LE order {15,15,2}. + +An implementation of a software decoder of compressed formats is available +in `Raspberry Pi camera applications code base +`_. diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 7c684788997c..5eb4d797d259 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1532,6 +1532,16 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_MT2110T: descr = "Mediatek 10bit Tile Mode"; break; case V4L2_PIX_FMT_MT2110R: descr = "Mediatek 10bit Raster Mode"; break; case V4L2_PIX_FMT_HEXTILE: descr = "Hextile Compressed Format"; break; + case V4L2_PIX_FMT_PISP_COMP1_RGGB: descr = "PiSP 8b RGRG/GBGB mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_GRBG: descr = "PiSP 8b GRGR/BGBG mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_GBRG: descr = "PiSP 8b GBGB/RGRG mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_BGGR: descr = "PiSP 8b BGBG/GRGR mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_MONO: descr = "PiSP 8b monochrome mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_RGGB: descr = "PiSP 8b RGRG/GBGB mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_GRBG: descr = "PiSP 8b GRGR/BGBG mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_GBRG: descr = "PiSP 8b GBGB/RGRG mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_BGGR: descr = "PiSP 8b BGBG/GRGR mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_MONO: descr = "PiSP 8b monochrome mode2 compr"; break; default: if (fmt->description[0]) return; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 96fc0456081e..4e91362da6da 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -816,6 +816,18 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_IPU3_SGRBG10 v4l2_fourcc('i', 'p', '3', 'G') /* IPU3 packed 10-bit GRBG bayer */ #define V4L2_PIX_FMT_IPU3_SRGGB10 v4l2_fourcc('i', 'p', '3', 'r') /* IPU3 packed 10-bit RGGB bayer */ +/* Raspberry Pi PiSP compressed formats. */ +#define V4L2_PIX_FMT_PISP_COMP1_RGGB v4l2_fourcc('P', 'C', '1', 'R') /* PiSP 8-bit mode 1 compressed RGGB bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_GRBG v4l2_fourcc('P', 'C', '1', 'G') /* PiSP 8-bit mode 1 compressed GRBG bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_GBRG v4l2_fourcc('P', 'C', '1', 'g') /* PiSP 8-bit mode 1 compressed GBRG bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_BGGR v4l2_fourcc('P', 'C', '1', 'B') /* PiSP 8-bit mode 1 compressed BGGR bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_MONO v4l2_fourcc('P', 'C', '1', 'M') /* PiSP 8-bit mode 1 compressed monochrome */ +#define V4L2_PIX_FMT_PISP_COMP2_RGGB v4l2_fourcc('P', 'C', '2', 'R') /* PiSP 8-bit mode 2 compressed RGGB bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_GRBG v4l2_fourcc('P', 'C', '2', 'G') /* PiSP 8-bit mode 2 compressed GRBG bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_GBRG v4l2_fourcc('P', 'C', '2', 'g') /* PiSP 8-bit mode 2 compressed GBRG bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_BGGR v4l2_fourcc('P', 'C', '2', 'B') /* PiSP 8-bit mode 2 compressed BGGR bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_MONO v4l2_fourcc('P', 'C', '2', 'M') /* PiSP 8-bit mode 2 compressed monochrome */ + /* SDR formats - used only for Software Defined Radio devices */ #define V4L2_SDR_FMT_CU8 v4l2_fourcc('C', 'U', '0', '8') /* IQ u8 */ #define V4L2_SDR_FMT_CU16LE v4l2_fourcc('C', 'U', '1', '6') /* IQ u16le */ -- cgit v1.2.3 From d04bccd8c19d601232ed3e3c9e248c0040167d47 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 7 Jun 2024 16:55:37 +0200 Subject: listmount: allow listing in reverse order util-linux is about to implement listmount() and statmount() support. Karel requested the ability to scan the mount table in backwards order because that's what libmount currently does in order to get the latest mount first. We currently don't support this in listmount(). Add a new LISTMOUNT_REVERSE flag to allow listing mounts in reverse order. For example, listing all child mounts of /sys without LISTMOUNT_REVERSE gives: /sys/kernel/security @ mnt_id: 4294968369 /sys/fs/cgroup @ mnt_id: 4294968370 /sys/firmware/efi/efivars @ mnt_id: 4294968371 /sys/fs/bpf @ mnt_id: 4294968372 /sys/kernel/tracing @ mnt_id: 4294968373 /sys/kernel/debug @ mnt_id: 4294968374 /sys/fs/fuse/connections @ mnt_id: 4294968375 /sys/kernel/config @ mnt_id: 4294968376 whereas with LISTMOUNT_REVERSE it gives: /sys/kernel/config @ mnt_id: 4294968376 /sys/fs/fuse/connections @ mnt_id: 4294968375 /sys/kernel/debug @ mnt_id: 4294968374 /sys/kernel/tracing @ mnt_id: 4294968373 /sys/fs/bpf @ mnt_id: 4294968372 /sys/firmware/efi/efivars @ mnt_id: 4294968371 /sys/fs/cgroup @ mnt_id: 4294968370 /sys/kernel/security @ mnt_id: 4294968369 Link: https://lore.kernel.org/r/20240607-vfs-listmount-reverse-v1-4-7877a2bfa5e5@kernel.org Reviewed-by: Josef Bacik Signed-off-by: Christian Brauner --- fs/namespace.c | 59 ++++++++++++++++++++++++++++++++++++++-------- include/uapi/linux/mount.h | 1 + 2 files changed, 50 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 98671cd89511..02a697287da5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1448,6 +1448,30 @@ static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) return ret; } +/* + * Returns the mount which either has the specified mnt_id, or has the next + * greater id before the specified one. + */ +static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id) +{ + struct rb_node *node = ns->mounts.rb_node; + struct mount *ret = NULL; + + while (node) { + struct mount *m = node_to_mount(node); + + if (mnt_id >= m->mnt_id_unique) { + ret = node_to_mount(node); + if (mnt_id == m->mnt_id_unique) + break; + node = node->rb_right; + } else { + node = node->rb_left; + } + } + return ret; +} + #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ @@ -5042,13 +5066,20 @@ retry: return ret; } -static struct mount *listmnt_next(struct mount *curr) +static struct mount *listmnt_next(struct mount *curr, bool reverse) { - return node_to_mount(rb_next(&curr->mnt_node)); + struct rb_node *node; + + if (reverse) + node = rb_prev(&curr->mnt_node); + else + node = rb_next(&curr->mnt_node); + + return node_to_mount(node); } static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, - size_t nr_mnt_ids) + size_t nr_mnt_ids, bool reverse) { struct path root __free(path_put) = {}; struct mnt_namespace *ns = current->nsproxy->mnt_ns; @@ -5080,12 +5111,19 @@ static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, if (ret) return ret; - if (!last_mnt_id) - first = node_to_mount(rb_first(&ns->mounts)); - else - first = mnt_find_id_at(ns, last_mnt_id + 1); + if (!last_mnt_id) { + if (reverse) + first = node_to_mount(rb_last(&ns->mounts)); + else + first = node_to_mount(rb_first(&ns->mounts)); + } else { + if (reverse) + first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); + else + first = mnt_find_id_at(ns, last_mnt_id + 1); + } - for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) { + for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r, reverse)) { if (r->mnt_id_unique == mnt_parent_id) continue; if (!is_path_reachable(r, r->mnt.mnt_root, &orig)) @@ -5106,7 +5144,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, struct mnt_id_req kreq; ssize_t ret; - if (flags) + if (flags & ~LISTMOUNT_REVERSE) return -EINVAL; /* @@ -5130,7 +5168,8 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, return -ENOMEM; scoped_guard(rwsem_read, &namespace_sem) - ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, nr_mnt_ids); + ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, + nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids))) return -EFAULT; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index ad5478dbad00..88d78de1519f 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -207,5 +207,6 @@ struct mnt_id_req { * Special @mnt_id values that can be passed to listmount */ #define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ #endif /* _UAPI_LINUX_MOUNT_H */ -- cgit v1.2.3 From 09b31295f833031c88419550172703d45c5401e3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 24 Jun 2024 11:49:47 -0400 Subject: fs: export the mount ns id via statmount In order to allow users to iterate through children mount namespaces via listmount we need a way for them to know what the ns id for the mount. Add a new field to statmount called mnt_ns_id which will carry the ns id for the given mount entry. Co-developed-by: Christian Brauner Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/6dabf437331fb7415d886f7c64b21cb2a50b1c66.1719243756.git.josef@toxicpanda.com Signed-off-by: Christian Brauner --- fs/namespace.c | 11 +++++++++++ include/uapi/linux/mount.h | 4 +++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index eebe9d912a71..ed2d9353e4be 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4974,6 +4974,14 @@ static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) return 0; } +static void statmount_mnt_ns_id(struct kstatmount *s) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + + s->sm.mask |= STATMOUNT_MNT_NS_ID; + s->sm.mnt_ns_id = ns->seq; +} + static int statmount_string(struct kstatmount *s, u64 flag) { int ret; @@ -5070,6 +5078,9 @@ static int do_statmount(struct kstatmount *s) if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); + if (!err && s->mask & STATMOUNT_MNT_NS_ID) + statmount_mnt_ns_id(s); + if (err) return err; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 88d78de1519f..a07508aee518 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -172,7 +172,8 @@ struct statmount { __u64 propagate_from; /* Propagation from in current namespace */ __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ - __u64 __spare2[50]; + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u64 __spare2[49]; char str[]; /* Variable size part containing strings */ }; @@ -202,6 +203,7 @@ struct mnt_id_req { #define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ /* * Special @mnt_id values that can be passed to listmount -- cgit v1.2.3 From 0a3deb11858ae8a0b3849b5fda45512ad383f0e1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 24 Jun 2024 11:49:48 -0400 Subject: fs: Allow listmount() in foreign mount namespace Expand struct mnt_id_req to add an optional mnt_ns_id field. When this field is populated, listmount() will be performed on the specified mount namespace, provided the currently application has CAP_SYS_ADMIN in its user namespace and the mount namespace is a child of the current namespace. Co-developed-by: Josef Bacik Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/49930bdce29a8367a213eb14c1e68e7e49284f86.1719243756.git.josef@toxicpanda.com Signed-off-by: Christian Brauner --- fs/namespace.c | 88 ++++++++++++++++++++++++++++++++++++---------- include/uapi/linux/mount.h | 2 ++ 2 files changed, 72 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index ed2d9353e4be..a54d68f822a8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5122,7 +5122,7 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, int ret; size_t usize; - BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0); + BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER1); ret = get_user(usize, &req->size); if (ret) @@ -5140,6 +5140,58 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, return 0; } +static struct mount *listmnt_next(struct mount *curr, bool reverse) +{ + struct rb_node *node; + + if (reverse) + node = rb_prev(&curr->mnt_node); + else + node = rb_next(&curr->mnt_node); + + return node_to_mount(node); +} + +static int grab_requested_root(struct mnt_namespace *ns, struct path *root) +{ + struct mount *first; + + rwsem_assert_held(&namespace_sem); + + /* We're looking at our own ns, just use get_fs_root. */ + if (ns == current->nsproxy->mnt_ns) { + get_fs_root(current->fs, root); + return 0; + } + + /* + * We have to find the first mount in our ns and use that, however it + * may not exist, so handle that properly. + */ + if (RB_EMPTY_ROOT(&ns->mounts)) + return -ENOENT; + + first = listmnt_next(ns->root, false); + if (!first) + return -ENOENT; + root->mnt = mntget(&first->mnt); + root->dentry = dget(root->mnt->mnt_root); + return 0; +} + +/* + * If the user requested a specific mount namespace id, look that up and return + * that, or if not simply grab a passive reference on our mount namespace and + * return that. + */ +static struct mnt_namespace *grab_requested_mnt_ns(u64 mnt_ns_id) +{ + if (mnt_ns_id) + return lookup_mnt_ns(mnt_ns_id); + refcount_inc(¤t->nsproxy->mnt_ns->passive); + return current->nsproxy->mnt_ns; +} + SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) @@ -5185,30 +5237,21 @@ retry: return ret; } -static struct mount *listmnt_next(struct mount *curr, bool reverse) -{ - struct rb_node *node; - - if (reverse) - node = rb_prev(&curr->mnt_node); - else - node = rb_next(&curr->mnt_node); - - return node_to_mount(node); -} - -static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, - size_t nr_mnt_ids, bool reverse) +static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id, + u64 last_mnt_id, u64 *mnt_ids, size_t nr_mnt_ids, + bool reverse) { struct path root __free(path_put) = {}; - struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct path orig; struct mount *r, *first; ssize_t ret; rwsem_assert_held(&namespace_sem); - get_fs_root(current->fs, &root); + ret = grab_requested_root(ns, &root); + if (ret) + return ret; + if (mnt_parent_id == LSMT_ROOT) { orig = root; } else { @@ -5260,6 +5303,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, { u64 *kmnt_ids __free(kvfree) = NULL; const size_t maxcount = 1000000; + struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct mnt_id_req kreq; ssize_t ret; @@ -5286,8 +5330,16 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, if (!kmnt_ids) return -ENOMEM; + ns = grab_requested_mnt_ns(kreq.mnt_ns_id); + if (!ns) + return -ENOENT; + + if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && + !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) + return -ENOENT; + scoped_guard(rwsem_read, &namespace_sem) - ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, + ret = do_listmount(ns, kreq.mnt_id, kreq.param, kmnt_ids, nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids))) diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index a07508aee518..ee1559cd6764 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -189,10 +189,12 @@ struct mnt_id_req { __u32 spare; __u64 mnt_id; __u64 param; + __u64 mnt_ns_id; }; /* List of all mnt_id_req versions. */ #define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ /* * @mask bits for statmount(2) -- cgit v1.2.3 From e8e43a1fcc5c07575f37e40f8a2cd78aee46f9a0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 24 Jun 2024 11:49:50 -0400 Subject: fs: add an ioctl to get the mnt ns id from nsfs In order to utilize the listmount() and statmount() extensions that allow us to call them on different namespaces we need a way to get the mnt namespace id from user space. Add an ioctl to nsfs that will allow us to extract the mnt namespace id in order to make these new extensions usable. Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/180449959d5a756af7306d6bda55f41b9d53e3cb.1719243756.git.josef@toxicpanda.com Signed-off-by: Christian Brauner --- fs/nsfs.c | 14 ++++++++++++++ include/uapi/linux/nsfs.h | 2 ++ 2 files changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 07e22a15ef02..af352dadffe1 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -12,6 +12,7 @@ #include #include +#include "mount.h" #include "internal.h" static struct vfsmount *nsfs_mnt; @@ -143,6 +144,19 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, argp = (uid_t __user *) arg; uid = from_kuid_munged(current_user_ns(), user_ns->owner); return put_user(uid, argp); + case NS_GET_MNTNS_ID: { + struct mnt_namespace *mnt_ns; + __u64 __user *idp; + __u64 id; + + if (ns->ops->type != CLONE_NEWNS) + return -EINVAL; + + mnt_ns = container_of(ns, struct mnt_namespace, ns); + idp = (__u64 __user *)arg; + id = mnt_ns->seq; + return put_user(id, idp); + } default: return -ENOTTY; } diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index a0c8552b64ee..56e8b1639b98 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -15,5 +15,7 @@ #define NS_GET_NSTYPE _IO(NSIO, 0x3) /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) +/* Get the id for a mount namespace */ +#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From 5b08bd408534bfb3a7cf5778da5b27d4e4fffe12 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 27 Jun 2024 16:11:42 +0200 Subject: pidfs: allow retrieval of namespace file descriptors For users that hold a reference to a pidfd procfs might not even be available nor is it desirable to parse through procfs just for the sake of getting namespace file descriptors for a process. Make it possible to directly retrieve namespace file descriptors from a pidfd. Pidfds already can be used with setns() to change a set of namespaces atomically. Link: https://lore.kernel.org/r/20240627-work-pidfs-v1-4-7e9ab6cc3bb1@kernel.org Reviewed-by: Jeff Layton Reviewed-by: Josef Bacik Reviewed-by: Alexander Mikhalitsyn Signed-off-by: Christian Brauner --- fs/pidfs.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pidfd.h | 14 ++++++++ 2 files changed, 104 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/pidfs.c b/fs/pidfs.c index dbb9d854d1c5..c9cb14181def 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -11,10 +11,16 @@ #include #include #include +#include #include #include +#include +#include +#include +#include #include "internal.h" +#include "mount.h" #ifdef CONFIG_PROC_FS /** @@ -108,11 +114,95 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) return poll_flags; } +static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct task_struct *task __free(put_task) = NULL; + struct nsproxy *nsp __free(put_nsproxy) = NULL; + struct pid *pid = pidfd_pid(file); + struct ns_common *ns_common; + + if (arg) + return -EINVAL; + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) + return -ESRCH; + + scoped_guard(task_lock, task) { + nsp = task->nsproxy; + if (nsp) + get_nsproxy(nsp); + } + if (!nsp) + return -ESRCH; /* just pretend it didn't exist */ + + /* + * We're trying to open a file descriptor to the namespace so perform a + * filesystem cred ptrace check. Also, we mirror nsfs behavior. + */ + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + return -EACCES; + + switch (cmd) { + /* Namespaces that hang of nsproxy. */ + case PIDFD_GET_CGROUP_NAMESPACE: + get_cgroup_ns(nsp->cgroup_ns); + ns_common = to_ns_common(nsp->cgroup_ns); + break; + case PIDFD_GET_IPC_NAMESPACE: + get_ipc_ns(nsp->ipc_ns); + ns_common = to_ns_common(nsp->ipc_ns); + break; + case PIDFD_GET_MNT_NAMESPACE: + get_mnt_ns(nsp->mnt_ns); + ns_common = to_ns_common(nsp->mnt_ns); + break; + case PIDFD_GET_NET_NAMESPACE: + ns_common = to_ns_common(nsp->net_ns); + get_net_ns(ns_common); + break; + case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: + get_pid_ns(nsp->pid_ns_for_children); + ns_common = to_ns_common(nsp->pid_ns_for_children); + break; + case PIDFD_GET_TIME_NAMESPACE: + get_time_ns(nsp->time_ns); + ns_common = to_ns_common(nsp->time_ns); + break; + case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: + get_time_ns(nsp->time_ns_for_children); + ns_common = to_ns_common(nsp->time_ns_for_children); + break; + case PIDFD_GET_UTS_NAMESPACE: + get_uts_ns(nsp->uts_ns); + ns_common = to_ns_common(nsp->uts_ns); + break; + /* Namespaces that don't hang of nsproxy. */ + case PIDFD_GET_USER_NAMESPACE: + rcu_read_lock(); + ns_common = to_ns_common(get_user_ns(task_cred_xxx(task, user_ns))); + rcu_read_unlock(); + break; + case PIDFD_GET_PID_NAMESPACE: + rcu_read_lock(); + ns_common = to_ns_common(get_pid_ns(task_active_pid_ns(task))); + rcu_read_unlock(); + break; + default: + return -ENOIOCTLCMD; + } + + /* open_namespace() unconditionally consumes the reference */ + return open_namespace(ns_common); +} + static const struct file_operations pidfs_file_operations = { .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif + .unlocked_ioctl = pidfd_ioctl, + .compat_ioctl = compat_ptr_ioctl, }; struct pid *pidfd_pid(const struct file *file) diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 72ec000a97cd..565fc0629fff 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -5,6 +5,7 @@ #include #include +#include /* Flags for pidfd_open(). */ #define PIDFD_NONBLOCK O_NONBLOCK @@ -15,4 +16,17 @@ #define PIDFD_SIGNAL_THREAD_GROUP (1UL << 1) #define PIDFD_SIGNAL_PROCESS_GROUP (1UL << 2) +#define PIDFS_IOCTL_MAGIC 0xFF + +#define PIDFD_GET_CGROUP_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 1) +#define PIDFD_GET_IPC_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 2) +#define PIDFD_GET_MNT_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 3) +#define PIDFD_GET_NET_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 4) +#define PIDFD_GET_PID_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 5) +#define PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 6) +#define PIDFD_GET_TIME_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 7) +#define PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 8) +#define PIDFD_GET_USER_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 9) +#define PIDFD_GET_UTS_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 10) + #endif /* _UAPI_LINUX_PIDFD_H */ -- cgit v1.2.3 From 46fb3ba95b93d1887e6dfa02a535e0526062de95 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 27 Jun 2024 17:08:50 +0300 Subject: ethtool: Add an interface for flashing transceiver modules' firmware CMIS compliant modules such as QSFP-DD might be running a firmware that can be updated in a vendor-neutral way by exchanging messages between the host and the module as described in section 7.3.1 of revision 5.2 of the CMIS standard. Add a pair of new ethtool messages that allow: * User space to trigger firmware update of transceiver modules * The kernel to notify user space about the progress of the process The user interface is designed to be asynchronous in order to avoid RTNL being held for too long and to allow several modules to be updated simultaneously. The interface is designed with CMIS compliant modules in mind, but kept generic enough to accommodate future use cases, if these arise. Signed-off-by: Danielle Ratson Reviewed-by: Petr Machata Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 55 ++++++++++++++++++++++ Documentation/networking/ethtool-netlink.rst | 70 ++++++++++++++++++++++++++++ include/uapi/linux/ethtool.h | 18 +++++++ include/uapi/linux/ethtool_netlink.h | 19 ++++++++ tools/net/ynl/Makefile.deps | 3 +- 5 files changed, 164 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 683f5c3f30ad..949e2722505d 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -20,6 +20,10 @@ definitions: name: header-flags type: flags entries: [ compact-bitsets, omit-reply, stats ] + - + name: module-fw-flash-status + type: enum + entries: [ started, in_progress, completed, error ] attribute-sets: - @@ -1004,6 +1008,32 @@ attribute-sets: - name: burst-tmr type: u32 + - + name: module-fw-flash + attributes: + - + name: header + type: nest + nested-attributes: header + - + name: file-name + type: string + - + name: password + type: u32 + - + name: status + type: u32 + enum: module-fw-flash-status + - + name: status-msg + type: string + - + name: done + type: uint + - + name: total + type: uint operations: enum-model: directional @@ -1764,3 +1794,28 @@ operations: name: mm-ntf doc: Notification for change in MAC Merge configuration. notify: mm-get + - + name: module-fw-flash-act + doc: Flash transceiver module firmware. + + attribute-set: module-fw-flash + + do: + request: + attributes: + - header + - file-name + - password + - + name: module-fw-flash-ntf + doc: Notification for firmware flashing progress and status. + + attribute-set: module-fw-flash + + event: + attributes: + - header + - status + - status-msg + - done + - total diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 7ec08e903bab..bfe2eda8580d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -228,6 +228,7 @@ Userspace to kernel: ``ETHTOOL_MSG_PLCA_GET_STATUS`` get PLCA RS status ``ETHTOOL_MSG_MM_GET`` get MAC merge layer state ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters + ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` flash transceiver module firmware ===================================== ================================= Kernel to userspace: @@ -274,6 +275,7 @@ Kernel to userspace: ``ETHTOOL_MSG_PLCA_GET_STATUS_REPLY`` PLCA RS status ``ETHTOOL_MSG_PLCA_NTF`` PLCA RS parameters ``ETHTOOL_MSG_MM_GET_REPLY`` MAC merge layer status + ``ETHTOOL_MSG_MODULE_FW_FLASH_NTF`` transceiver module flash updates ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -2041,6 +2043,73 @@ The attributes are propagated to the driver through the following structure: .. kernel-doc:: include/linux/ethtool.h :identifiers: ethtool_mm_cfg +MODULE_FW_FLASH_ACT +=================== + +Flashes transceiver module firmware. + +Request contents: + + ======================================= ====== =========================== + ``ETHTOOL_A_MODULE_FW_FLASH_HEADER`` nested request header + ``ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME`` string firmware image file name + ``ETHTOOL_A_MODULE_FW_FLASH_PASSWORD`` u32 transceiver module password + ======================================= ====== =========================== + +The firmware update process consists of three logical steps: + +1. Downloading a firmware image to the transceiver module and validating it. +2. Running the firmware image. +3. Committing the firmware image so that it is run upon reset. + +When flash command is given, those three steps are taken in that order. + +This message merely schedules the update process and returns immediately +without blocking. The process then runs asynchronously. +Since it can take several minutes to complete, during the update process +notifications are emitted from the kernel to user space updating it about +the status and progress. + +The ``ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME`` attribute encodes the firmware +image file name. The firmware image is downloaded to the transceiver module, +validated, run and committed. + +The optional ``ETHTOOL_A_MODULE_FW_FLASH_PASSWORD`` attribute encodes a password +that might be required as part of the transceiver module firmware update +process. + +The firmware update process can take several minutes to complete. Therefore, +during the update process notifications are emitted from the kernel to user +space updating it about the status and progress. + + + +Notification contents: + + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_HEADER`` | nested | reply header | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_STATUS`` | u32 | status | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG`` | string | status message | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` | uint | progress | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL`` | uint | total | + +---------------------------------------------------+--------+----------------+ + +The ``ETHTOOL_A_MODULE_FW_FLASH_STATUS`` attribute encodes the current status +of the firmware update process. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_fw_flash_status + +The ``ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG`` attribute encodes a status message +string. + +The ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` and ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL`` +attributes encode the completed and total amount of work, respectively. + Request translation =================== @@ -2147,4 +2216,5 @@ are netlink only. n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` + n/a ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8733a3117902..e011384c915c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -877,6 +877,24 @@ enum ethtool_mm_verify_status { ETHTOOL_MM_VERIFY_STATUS_DISABLED, }; +/** + * enum ethtool_module_fw_flash_status - plug-in module firmware flashing status + * @ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED: The firmware flashing process has + * started. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS: The firmware flashing process + * is in progress. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED: The firmware flashing process was + * completed successfully. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR: The firmware flashing process was + * stopped due to an error. + */ +enum ethtool_module_fw_flash_status { + ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED = 1, + ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS, + ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED, + ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR, +}; + /** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index d15856c7e001..840dabdc9d88 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -57,6 +57,7 @@ enum { ETHTOOL_MSG_PLCA_GET_STATUS, ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, + ETHTOOL_MSG_MODULE_FW_FLASH_ACT, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -109,6 +110,7 @@ enum { ETHTOOL_MSG_PLCA_NTF, ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, + ETHTOOL_MSG_MODULE_FW_FLASH_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -1018,6 +1020,23 @@ enum { ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) }; +/* MODULE_FW_FLASH */ + +enum { + ETHTOOL_A_MODULE_FW_FLASH_UNSPEC, + ETHTOOL_A_MODULE_FW_FLASH_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME, /* string */ + ETHTOOL_A_MODULE_FW_FLASH_PASSWORD, /* u32 */ + ETHTOOL_A_MODULE_FW_FLASH_STATUS, /* u32 */ + ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG, /* string */ + ETHTOOL_A_MODULE_FW_FLASH_DONE, /* uint */ + ETHTOOL_A_MODULE_FW_FLASH_TOTAL, /* uint */ + + /* add new constants above here */ + __ETHTOOL_A_MODULE_FW_FLASH_CNT, + ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index f4e8eb79c1b8..dbdca32a1c61 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -16,7 +16,8 @@ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) -CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) +CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ + $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h) CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) -- cgit v1.2.3 From f9af549d1fd31487bbbc666b5b158cfc940ccc17 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 24 Jun 2024 15:40:52 -0400 Subject: fs: export mount options via statmount() statmount() can export arbitrary strings, so utilize the __spare1 slot for a mnt_opts string pointer, and then support asking for and setting the mount options during statmount(). This calls into the helper for showing mount options, which already uses a seq_file, so fits in nicely with our existing mechanism for exporting strings via statmount(). Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/3aa6bf8bd5d0a21df9ebd63813af8ab532c18276.1719257716.git.josef@toxicpanda.com Reviewed-by: Jeff Layton [brauner: only call sb->s_op->show_options()] Signed-off-by: Christian Brauner --- fs/namespace.c | 37 ++++++++++++++++++++++++++++++++++++- include/uapi/linux/mount.h | 3 ++- 2 files changed, 38 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index a989e89b0a10..c53a0ee748c6 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4980,6 +4980,34 @@ static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns) s->sm.mnt_ns_id = ns->seq; } +static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) +{ + struct vfsmount *mnt = s->mnt; + struct super_block *sb = mnt->mnt_sb; + int err; + + if (sb->s_op->show_options) { + size_t start = seq->count; + + err = sb->s_op->show_options(seq, mnt->mnt_root); + if (err) + return err; + + if (unlikely(seq_has_overflowed(seq))) + return -EAGAIN; + + if (seq->count == start) + return 0; + + /* skip leading comma */ + memmove(seq->buf + start, seq->buf + start + 1, + seq->count - start - 1); + seq->count--; + } + + return 0; +} + static int statmount_string(struct kstatmount *s, u64 flag) { int ret; @@ -5000,6 +5028,10 @@ static int statmount_string(struct kstatmount *s, u64 flag) sm->mnt_point = seq->count; ret = statmount_mnt_point(s, seq); break; + case STATMOUNT_MNT_OPTS: + sm->mnt_opts = seq->count; + ret = statmount_mnt_opts(s, seq); + break; default: WARN_ON_ONCE(true); return -EINVAL; @@ -5130,6 +5162,9 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); + if (!err && s->mask & STATMOUNT_MNT_OPTS) + err = statmount_string(s, STATMOUNT_MNT_OPTS); + if (!err && s->mask & STATMOUNT_MNT_NS_ID) statmount_mnt_ns_id(s, ns); @@ -5151,7 +5186,7 @@ static inline bool retry_statmount(const long ret, size_t *seq_size) } #define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \ - STATMOUNT_FS_TYPE) + STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS) static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, struct statmount __user *buf, size_t bufsize, diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index ee1559cd6764..225bc366ffcb 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 __spare1; + __u32 mnt_opts; /* [str] Mount options of the mount */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -206,6 +206,7 @@ struct mnt_id_req { #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ #define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ /* * Special @mnt_id values that can be passed to listmount -- cgit v1.2.3 From 3e26d9f08fbe0b73e951a5e810fdb7a332b7e37f Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 20 Jun 2024 14:27:22 +0200 Subject: iio: core: Add new DMABUF interface infrastructure Add the necessary infrastructure to the IIO core to support a new optional DMABUF based interface. With this new interface, DMABUF objects (externally created) can be attached to a IIO buffer, and subsequently used for data transfer. A userspace application can then use this interface to share DMABUF objects between several interfaces, allowing it to transfer data in a zero-copy fashion, for instance between IIO and the USB stack. The userspace application can also memory-map the DMABUF objects, and access the sample data directly. The advantage of doing this vs. the read() interface is that it avoids an extra copy of the data between the kernel and userspace. This is particularly userful for high-speed devices which produce several megabytes or even gigabytes of data per second. As part of the interface, 3 new IOCTLs have been added: IIO_BUFFER_DMABUF_ATTACH_IOCTL(int fd): Attach the DMABUF object identified by the given file descriptor to the buffer. IIO_BUFFER_DMABUF_DETACH_IOCTL(int fd): Detach the DMABUF object identified by the given file descriptor from the buffer. Note that closing the IIO buffer's file descriptor will automatically detach all previously attached DMABUF objects. IIO_BUFFER_DMABUF_ENQUEUE_IOCTL(struct iio_dmabuf *): Request a data transfer to/from the given DMABUF object. Its file descriptor, as well as the transfer size and flags are provided in the "iio_dmabuf" structure. These three IOCTLs have to be performed on the IIO buffer's file descriptor, obtained using the IIO_BUFFER_GET_FD_IOCTL() ioctl. Signed-off-by: Paul Cercueil Co-developed-by: Nuno Sa Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240620122726.41232-4-paul@crapouillou.net Signed-off-by: Jonathan Cameron --- drivers/iio/Kconfig | 1 + drivers/iio/industrialio-buffer.c | 459 ++++++++++++++++++++++++++++++++++++++ include/linux/iio/buffer_impl.h | 33 +++ include/uapi/linux/iio/buffer.h | 22 ++ 4 files changed, 515 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig index 9c351ffc7bed..661127aed2f9 100644 --- a/drivers/iio/Kconfig +++ b/drivers/iio/Kconfig @@ -14,6 +14,7 @@ if IIO config IIO_BUFFER bool "Enable buffer support within IIO" + select DMA_SHARED_BUFFER help Provide core support for various buffer based data acquisition methods. diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 0138b21b244f..d6fe105d2f40 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -9,15 +9,20 @@ * - Better memory allocation techniques? * - Alternative access techniques? */ +#include #include #include #include #include #include +#include +#include +#include #include #include #include #include +#include #include #include @@ -29,6 +34,34 @@ #include #include +#define DMABUF_ENQUEUE_TIMEOUT_MS 5000 + +MODULE_IMPORT_NS(DMA_BUF); + +struct iio_dmabuf_priv { + struct list_head entry; + struct kref ref; + + struct iio_buffer *buffer; + struct iio_dma_buffer_block *block; + + u64 context; + + /* Spinlock used for locking the dma_fence */ + spinlock_t lock; + + struct dma_buf_attachment *attach; + struct sg_table *sgt; + enum dma_data_direction dir; + atomic_t seqno; +}; + +struct iio_dma_fence { + struct dma_fence base; + struct iio_dmabuf_priv *priv; + struct work_struct work; +}; + static const char * const iio_endian_prefix[] = { [IIO_BE] = "be", [IIO_LE] = "le", @@ -333,6 +366,8 @@ void iio_buffer_init(struct iio_buffer *buffer) { INIT_LIST_HEAD(&buffer->demux_list); INIT_LIST_HEAD(&buffer->buffer_list); + INIT_LIST_HEAD(&buffer->dmabufs); + mutex_init(&buffer->dmabufs_mutex); init_waitqueue_head(&buffer->pollq); kref_init(&buffer->ref); if (!buffer->watermark) @@ -1526,14 +1561,55 @@ static void iio_buffer_unregister_legacy_sysfs_groups(struct iio_dev *indio_dev) kfree(iio_dev_opaque->legacy_scan_el_group.attrs); } +static void iio_buffer_dmabuf_release(struct kref *ref) +{ + struct iio_dmabuf_priv *priv = container_of(ref, struct iio_dmabuf_priv, ref); + struct dma_buf_attachment *attach = priv->attach; + struct iio_buffer *buffer = priv->buffer; + struct dma_buf *dmabuf = attach->dmabuf; + + dma_resv_lock(dmabuf->resv, NULL); + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir); + dma_resv_unlock(dmabuf->resv); + + buffer->access->detach_dmabuf(buffer, priv->block); + + dma_buf_detach(attach->dmabuf, attach); + dma_buf_put(dmabuf); + kfree(priv); +} + +static void iio_buffer_dmabuf_get(struct dma_buf_attachment *attach) +{ + struct iio_dmabuf_priv *priv = attach->importer_priv; + + kref_get(&priv->ref); +} + +static void iio_buffer_dmabuf_put(struct dma_buf_attachment *attach) +{ + struct iio_dmabuf_priv *priv = attach->importer_priv; + + kref_put(&priv->ref, iio_buffer_dmabuf_release); +} + static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep) { struct iio_dev_buffer_pair *ib = filep->private_data; struct iio_dev *indio_dev = ib->indio_dev; struct iio_buffer *buffer = ib->buffer; + struct iio_dmabuf_priv *priv, *tmp; wake_up(&buffer->pollq); + guard(mutex)(&buffer->dmabufs_mutex); + + /* Close all attached DMABUFs */ + list_for_each_entry_safe(priv, tmp, &buffer->dmabufs, entry) { + list_del_init(&priv->entry); + iio_buffer_dmabuf_put(priv->attach); + } + kfree(ib); clear_bit(IIO_BUSY_BIT_POS, &buffer->flags); iio_device_put(indio_dev); @@ -1541,11 +1617,393 @@ static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep) return 0; } +static int iio_dma_resv_lock(struct dma_buf *dmabuf, bool nonblock) +{ + if (!nonblock) + return dma_resv_lock_interruptible(dmabuf->resv, NULL); + + if (!dma_resv_trylock(dmabuf->resv)) + return -EBUSY; + + return 0; +} + +static struct dma_buf_attachment * +iio_buffer_find_attachment(struct iio_dev_buffer_pair *ib, + struct dma_buf *dmabuf, bool nonblock) +{ + struct device *dev = ib->indio_dev->dev.parent; + struct iio_buffer *buffer = ib->buffer; + struct dma_buf_attachment *attach = NULL; + struct iio_dmabuf_priv *priv; + + guard(mutex)(&buffer->dmabufs_mutex); + + list_for_each_entry(priv, &buffer->dmabufs, entry) { + if (priv->attach->dev == dev + && priv->attach->dmabuf == dmabuf) { + attach = priv->attach; + break; + } + } + + if (attach) + iio_buffer_dmabuf_get(attach); + + return attach ?: ERR_PTR(-EPERM); +} + +static int iio_buffer_attach_dmabuf(struct iio_dev_buffer_pair *ib, + int __user *user_fd, bool nonblock) +{ + struct iio_dev *indio_dev = ib->indio_dev; + struct iio_buffer *buffer = ib->buffer; + struct dma_buf_attachment *attach; + struct iio_dmabuf_priv *priv, *each; + struct dma_buf *dmabuf; + int err, fd; + + if (!buffer->access->attach_dmabuf + || !buffer->access->detach_dmabuf + || !buffer->access->enqueue_dmabuf) + return -EPERM; + + if (copy_from_user(&fd, user_fd, sizeof(fd))) + return -EFAULT; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->lock); + priv->context = dma_fence_context_alloc(1); + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) { + err = PTR_ERR(dmabuf); + goto err_free_priv; + } + + attach = dma_buf_attach(dmabuf, indio_dev->dev.parent); + if (IS_ERR(attach)) { + err = PTR_ERR(attach); + goto err_dmabuf_put; + } + + err = iio_dma_resv_lock(dmabuf, nonblock); + if (err) + goto err_dmabuf_detach; + + priv->dir = buffer->direction == IIO_BUFFER_DIRECTION_IN + ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + + priv->sgt = dma_buf_map_attachment(attach, priv->dir); + if (IS_ERR(priv->sgt)) { + err = PTR_ERR(priv->sgt); + dev_err(&indio_dev->dev, "Unable to map attachment: %d\n", err); + goto err_resv_unlock; + } + + kref_init(&priv->ref); + priv->buffer = buffer; + priv->attach = attach; + attach->importer_priv = priv; + + priv->block = buffer->access->attach_dmabuf(buffer, attach); + if (IS_ERR(priv->block)) { + err = PTR_ERR(priv->block); + goto err_dmabuf_unmap_attachment; + } + + dma_resv_unlock(dmabuf->resv); + + mutex_lock(&buffer->dmabufs_mutex); + + /* + * Check whether we already have an attachment for this driver/DMABUF + * combo. If we do, refuse to attach. + */ + list_for_each_entry(each, &buffer->dmabufs, entry) { + if (each->attach->dev == indio_dev->dev.parent + && each->attach->dmabuf == dmabuf) { + /* + * We unlocked the reservation object, so going through + * the cleanup code would mean re-locking it first. + * At this stage it is simpler to free the attachment + * using iio_buffer_dma_put(). + */ + mutex_unlock(&buffer->dmabufs_mutex); + iio_buffer_dmabuf_put(attach); + return -EBUSY; + } + } + + /* Otherwise, add the new attachment to our dmabufs list. */ + list_add(&priv->entry, &buffer->dmabufs); + mutex_unlock(&buffer->dmabufs_mutex); + + return 0; + +err_dmabuf_unmap_attachment: + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir); +err_resv_unlock: + dma_resv_unlock(dmabuf->resv); +err_dmabuf_detach: + dma_buf_detach(dmabuf, attach); +err_dmabuf_put: + dma_buf_put(dmabuf); +err_free_priv: + kfree(priv); + + return err; +} + +static int iio_buffer_detach_dmabuf(struct iio_dev_buffer_pair *ib, + int __user *user_req, bool nonblock) +{ + struct iio_buffer *buffer = ib->buffer; + struct iio_dev *indio_dev = ib->indio_dev; + struct iio_dmabuf_priv *priv; + struct dma_buf *dmabuf; + int dmabuf_fd, ret = -EPERM; + + if (copy_from_user(&dmabuf_fd, user_req, sizeof(dmabuf_fd))) + return -EFAULT; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + guard(mutex)(&buffer->dmabufs_mutex); + + list_for_each_entry(priv, &buffer->dmabufs, entry) { + if (priv->attach->dev == indio_dev->dev.parent + && priv->attach->dmabuf == dmabuf) { + list_del(&priv->entry); + + /* Unref the reference from iio_buffer_attach_dmabuf() */ + iio_buffer_dmabuf_put(priv->attach); + ret = 0; + break; + } + } + + dma_buf_put(dmabuf); + + return ret; +} + +static const char * +iio_buffer_dma_fence_get_driver_name(struct dma_fence *fence) +{ + return "iio"; +} + +static void iio_buffer_dma_fence_release(struct dma_fence *fence) +{ + struct iio_dma_fence *iio_fence = + container_of(fence, struct iio_dma_fence, base); + + kfree(iio_fence); +} + +static const struct dma_fence_ops iio_buffer_dma_fence_ops = { + .get_driver_name = iio_buffer_dma_fence_get_driver_name, + .get_timeline_name = iio_buffer_dma_fence_get_driver_name, + .release = iio_buffer_dma_fence_release, +}; + +static int iio_buffer_enqueue_dmabuf(struct iio_dev_buffer_pair *ib, + struct iio_dmabuf __user *iio_dmabuf_req, + bool nonblock) +{ + struct iio_buffer *buffer = ib->buffer; + struct iio_dmabuf iio_dmabuf; + struct dma_buf_attachment *attach; + struct iio_dmabuf_priv *priv; + struct iio_dma_fence *fence; + struct dma_buf *dmabuf; + unsigned long timeout; + bool cookie, cyclic, dma_to_ram; + long retl; + u32 seqno; + int ret; + + if (copy_from_user(&iio_dmabuf, iio_dmabuf_req, sizeof(iio_dmabuf))) + return -EFAULT; + + if (iio_dmabuf.flags & ~IIO_BUFFER_DMABUF_SUPPORTED_FLAGS) + return -EINVAL; + + cyclic = iio_dmabuf.flags & IIO_BUFFER_DMABUF_CYCLIC; + + /* Cyclic flag is only supported on output buffers */ + if (cyclic && buffer->direction != IIO_BUFFER_DIRECTION_OUT) + return -EINVAL; + + dmabuf = dma_buf_get(iio_dmabuf.fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + if (!iio_dmabuf.bytes_used || iio_dmabuf.bytes_used > dmabuf->size) { + ret = -EINVAL; + goto err_dmabuf_put; + } + + attach = iio_buffer_find_attachment(ib, dmabuf, nonblock); + if (IS_ERR(attach)) { + ret = PTR_ERR(attach); + goto err_dmabuf_put; + } + + priv = attach->importer_priv; + + fence = kmalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) { + ret = -ENOMEM; + goto err_attachment_put; + } + + fence->priv = priv; + + seqno = atomic_add_return(1, &priv->seqno); + + /* + * The transfers are guaranteed to be processed in the order they are + * enqueued, so we can use a simple incrementing sequence number for + * the dma_fence. + */ + dma_fence_init(&fence->base, &iio_buffer_dma_fence_ops, + &priv->lock, priv->context, seqno); + + ret = iio_dma_resv_lock(dmabuf, nonblock); + if (ret) + goto err_fence_put; + + timeout = nonblock ? 0 : msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS); + dma_to_ram = buffer->direction == IIO_BUFFER_DIRECTION_IN; + + /* Make sure we don't have writers */ + retl = dma_resv_wait_timeout(dmabuf->resv, + dma_resv_usage_rw(dma_to_ram), + true, timeout); + if (retl == 0) + retl = -EBUSY; + if (retl < 0) { + ret = (int)retl; + goto err_resv_unlock; + } + + if (buffer->access->lock_queue) + buffer->access->lock_queue(buffer); + + ret = dma_resv_reserve_fences(dmabuf->resv, 1); + if (ret) + goto err_queue_unlock; + + dma_resv_add_fence(dmabuf->resv, &fence->base, + dma_to_ram ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); + dma_resv_unlock(dmabuf->resv); + + cookie = dma_fence_begin_signalling(); + + ret = buffer->access->enqueue_dmabuf(buffer, priv->block, &fence->base, + priv->sgt, iio_dmabuf.bytes_used, + cyclic); + if (ret) { + /* + * DMABUF enqueue failed, but we already added the fence. + * Signal the error through the fence completion mechanism. + */ + iio_buffer_signal_dmabuf_done(&fence->base, ret); + } + + if (buffer->access->unlock_queue) + buffer->access->unlock_queue(buffer); + + dma_fence_end_signalling(cookie); + dma_buf_put(dmabuf); + + return ret; + +err_queue_unlock: + if (buffer->access->unlock_queue) + buffer->access->unlock_queue(buffer); +err_resv_unlock: + dma_resv_unlock(dmabuf->resv); +err_fence_put: + dma_fence_put(&fence->base); +err_attachment_put: + iio_buffer_dmabuf_put(attach); +err_dmabuf_put: + dma_buf_put(dmabuf); + + return ret; +} + +static void iio_buffer_cleanup(struct work_struct *work) +{ + struct iio_dma_fence *fence = + container_of(work, struct iio_dma_fence, work); + struct iio_dmabuf_priv *priv = fence->priv; + struct dma_buf_attachment *attach = priv->attach; + + dma_fence_put(&fence->base); + iio_buffer_dmabuf_put(attach); +} + +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret) +{ + struct iio_dma_fence *iio_fence = + container_of(fence, struct iio_dma_fence, base); + bool cookie = dma_fence_begin_signalling(); + + /* + * Get a reference to the fence, so that it's not freed as soon as + * it's signaled. + */ + dma_fence_get(fence); + + fence->error = ret; + dma_fence_signal(fence); + dma_fence_end_signalling(cookie); + + /* + * The fence will be unref'd in iio_buffer_cleanup. + * It can't be done here, as the unref functions might try to lock the + * resv object, which can deadlock. + */ + INIT_WORK(&iio_fence->work, iio_buffer_cleanup); + schedule_work(&iio_fence->work); +} +EXPORT_SYMBOL_GPL(iio_buffer_signal_dmabuf_done); + +static long iio_buffer_chrdev_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct iio_dev_buffer_pair *ib = filp->private_data; + void __user *_arg = (void __user *)arg; + bool nonblock = filp->f_flags & O_NONBLOCK; + + switch (cmd) { + case IIO_BUFFER_DMABUF_ATTACH_IOCTL: + return iio_buffer_attach_dmabuf(ib, _arg, nonblock); + case IIO_BUFFER_DMABUF_DETACH_IOCTL: + return iio_buffer_detach_dmabuf(ib, _arg, nonblock); + case IIO_BUFFER_DMABUF_ENQUEUE_IOCTL: + return iio_buffer_enqueue_dmabuf(ib, _arg, nonblock); + default: + return -EINVAL; + } +} + static const struct file_operations iio_buffer_chrdev_fileops = { .owner = THIS_MODULE, .llseek = noop_llseek, .read = iio_buffer_read, .write = iio_buffer_write, + .unlocked_ioctl = iio_buffer_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, .poll = iio_buffer_poll, .release = iio_buffer_chrdev_release, }; @@ -1994,6 +2452,7 @@ static void iio_buffer_release(struct kref *ref) { struct iio_buffer *buffer = container_of(ref, struct iio_buffer, ref); + mutex_destroy(&buffer->dmabufs_mutex); buffer->access->release(buffer); } diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 89c3fd7c29ca..e72552e026f3 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -9,8 +9,12 @@ #include #include +struct dma_buf_attachment; +struct dma_fence; struct iio_dev; +struct iio_dma_buffer_block; struct iio_buffer; +struct sg_table; /** * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be @@ -39,6 +43,16 @@ struct iio_buffer; * device stops sampling. Calles are balanced with @enable. * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. + * @attach_dmabuf: called from userspace via ioctl to attach one external + * DMABUF. + * @detach_dmabuf: called from userspace via ioctl to detach one previously + * attached DMABUF. + * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF + * object to this buffer. Requires a valid DMABUF fd, that + * was previouly attached to this buffer. + * @lock_queue: called when the core needs to lock the buffer queue; + * it is used when enqueueing DMABUF objects. + * @unlock_queue: used to unlock a previously locked buffer queue * @modes: Supported operating modes by this buffer type * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* * @@ -68,6 +82,17 @@ struct iio_buffer_access_funcs { void (*release)(struct iio_buffer *buffer); + struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer, + struct dma_buf_attachment *attach); + void (*detach_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block); + int (*enqueue_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block, + struct dma_fence *fence, struct sg_table *sgt, + size_t size, bool cyclic); + void (*lock_queue)(struct iio_buffer *buffer); + void (*unlock_queue)(struct iio_buffer *buffer); + unsigned int modes; unsigned int flags; }; @@ -136,6 +161,12 @@ struct iio_buffer { /* @ref: Reference count of the buffer. */ struct kref ref; + + /* @dmabufs: List of DMABUF attachments */ + struct list_head dmabufs; /* P: dmabufs_mutex */ + + /* @dmabufs_mutex: Protects dmabufs */ + struct mutex dmabufs_mutex; }; /** @@ -159,6 +190,8 @@ void iio_buffer_init(struct iio_buffer *buffer); struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer); void iio_buffer_put(struct iio_buffer *buffer); +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret); + #else /* CONFIG_IIO_BUFFER */ static inline void iio_buffer_get(struct iio_buffer *buffer) {} diff --git a/include/uapi/linux/iio/buffer.h b/include/uapi/linux/iio/buffer.h index 13939032b3f6..c666aa95e532 100644 --- a/include/uapi/linux/iio/buffer.h +++ b/include/uapi/linux/iio/buffer.h @@ -5,6 +5,28 @@ #ifndef _UAPI_IIO_BUFFER_H_ #define _UAPI_IIO_BUFFER_H_ +#include + +/* Flags for iio_dmabuf.flags */ +#define IIO_BUFFER_DMABUF_CYCLIC (1 << 0) +#define IIO_BUFFER_DMABUF_SUPPORTED_FLAGS 0x00000001 + +/** + * struct iio_dmabuf - Descriptor for a single IIO DMABUF object + * @fd: file descriptor of the DMABUF object + * @flags: one or more IIO_BUFFER_DMABUF_* flags + * @bytes_used: number of bytes used in this DMABUF for the data transfer. + * Should generally be set to the DMABUF's size. + */ +struct iio_dmabuf { + __u32 fd; + __u32 flags; + __u64 bytes_used; +}; + #define IIO_BUFFER_GET_FD_IOCTL _IOWR('i', 0x91, int) +#define IIO_BUFFER_DMABUF_ATTACH_IOCTL _IOW('i', 0x92, int) +#define IIO_BUFFER_DMABUF_DETACH_IOCTL _IOW('i', 0x93, int) +#define IIO_BUFFER_DMABUF_ENQUEUE_IOCTL _IOW('i', 0x94, struct iio_dmabuf) #endif /* _UAPI_IIO_BUFFER_H_ */ -- cgit v1.2.3 From 7c8110057b1bb9ab9f47ac0efc554d5c3a53b693 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jun 2024 14:35:50 -0700 Subject: tcp_metrics: add UAPI to the header guard tcp_metrics' header lacks the customary _UAPI in the header guard. This makes YNL build rules work less seamlessly. We can easily fix that on YNL side, but this could also be problematic if we ever needed to create a kernel-only tcp_metrics.h. Signed-off-by: Jakub Kicinski Reviewed-by: Donald Hunter Signed-off-by: David S. Miller --- include/uapi/linux/tcp_metrics.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index 7cb4a172feed..c48841076998 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* tcp_metrics.h - TCP Metrics Interface */ -#ifndef _LINUX_TCP_METRICS_H -#define _LINUX_TCP_METRICS_H +#ifndef _UAPI_LINUX_TCP_METRICS_H +#define _UAPI_LINUX_TCP_METRICS_H #include @@ -58,4 +58,4 @@ enum { #define TCP_METRICS_CMD_MAX (__TCP_METRICS_CMD_MAX - 1) -#endif /* _LINUX_TCP_METRICS_H */ +#endif /* _UAPI_LINUX_TCP_METRICS_H */ -- cgit v1.2.3 From 85674625e0bc25be4dbaa165a556ef6037328379 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jun 2024 14:35:51 -0700 Subject: tcp_metrics: add netlink protocol spec in YAML Add a protocol spec for tcp_metrics, so that it's accessible via YNL. Useful at the very least for testing fixes. In this episode of "10,000 ways to complicate netlink" the metric nest has defines which are off by 1. iproute2 does: struct rtattr *m[TCP_METRIC_MAX + 1 + 1]; parse_rtattr_nested(m, TCP_METRIC_MAX + 1, a); for (i = 0; i < TCP_METRIC_MAX + 1; i++) { // ... attr = m[i + 1]; This is too weird to support in YNL, add a new set of defines with _correct_ values to the official kernel header. Signed-off-by: Jakub Kicinski Reviewed-by: Donald Hunter Signed-off-by: David S. Miller --- Documentation/netlink/specs/tcp_metrics.yaml | 169 +++++++++++++++++++++++++++ include/uapi/linux/tcp_metrics.h | 16 +++ tools/net/ynl/Makefile.deps | 1 + 3 files changed, 186 insertions(+) create mode 100644 Documentation/netlink/specs/tcp_metrics.yaml (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/tcp_metrics.yaml b/Documentation/netlink/specs/tcp_metrics.yaml new file mode 100644 index 000000000000..1bd94f43e526 --- /dev/null +++ b/Documentation/netlink/specs/tcp_metrics.yaml @@ -0,0 +1,169 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: tcp_metrics + +protocol: genetlink-legacy + +doc: | + Management interface for TCP metrics. + +c-family-name: tcp-metrics-genl-name +c-version-name: tcp-metrics-genl-version +max-by-define: true +kernel-policy: global + +definitions: + - + name: tcp-fastopen-cookie-max + type: const + value: 16 + +attribute-sets: + - + name: tcp-metrics + name-prefix: tcp-metrics-attr- + attributes: + - + name: addr-ipv4 + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: addr-ipv6 + type: binary + checks: + min-len: 16 + byte-order: big-endian + display-hint: ipv6 + - + name: age + type: u64 + - + name: tw-tsval + type: u32 + doc: unused + - + name: tw-ts-stamp + type: s32 + doc: unused + - + name: vals + type: nest + nested-attributes: metrics + - + name: fopen-mss + type: u16 + - + name: fopen-syn-drops + type: u16 + - + name: fopen-syn-drop-ts + type: u64 + - + name: fopen-cookie + type: binary + checks: + min-len: tcp-fastopen-cookie-max + - + name: saddr-ipv4 + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: saddr-ipv6 + type: binary + checks: + min-len: 16 + byte-order: big-endian + display-hint: ipv6 + - + name: pad + type: pad + + - + name: metrics + # Intentionally don't define the name-prefix, see below. + doc: | + Attributes with metrics. Note that the values here do not match + the TCP_METRIC_* defines in the kernel, because kernel defines + are off-by one (e.g. rtt is defined as enum 0, while netlink carries + attribute type 1). + attributes: + - + name: rtt + type: u32 + doc: | + Round Trip Time (RTT), in msecs with 3 bits fractional + (left-shift by 3 to get the msec value). + - + name: rttvar + type: u32 + doc: | + Round Trip Time VARiance (RTT), in msecs with 2 bits fractional + (left-shift by 2 to get the msec value). + - + name: ssthresh + type: u32 + doc: Slow Start THRESHold. + - + name: cwnd + type: u32 + doc: Congestion Window. + - + name: reodering + type: u32 + doc: Reodering metric. + - + name: rtt-us + type: u32 + doc: | + Round Trip Time (RTT), in usecs, with 3 bits fractional + (left-shift by 3 to get the msec value). + - + name: rttvar-us + type: u32 + doc: | + Round Trip Time (RTT), in usecs, with 2 bits fractional + (left-shift by 3 to get the msec value). + +operations: + list: + - + name: get + doc: Retrieve metrics. + attribute-set: tcp-metrics + + dont-validate: [ strict, dump ] + + do: + request: &sel_attrs + attributes: + - addr-ipv4 + - addr-ipv6 + - saddr-ipv4 + - saddr-ipv6 + reply: &all_attrs + attributes: + - addr-ipv4 + - addr-ipv6 + - saddr-ipv4 + - saddr-ipv6 + - age + - vals + - fopen-mss + - fopen-syn-drops + - fopen-syn-drop-ts + - fopen-cookie + dump: + reply: *all_attrs + + - + name: del + doc: Delete metrics. + attribute-set: tcp-metrics + + dont-validate: [ strict, dump ] + flags: [ admin-perm ] + + do: + request: *sel_attrs diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index c48841076998..927c735a5b0e 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -27,6 +27,22 @@ enum tcp_metric_index { #define TCP_METRIC_MAX (__TCP_METRIC_MAX - 1) +/* Re-define enum tcp_metric_index, again, using the values carried + * as netlink attribute types. + */ +enum { + TCP_METRICS_A_METRICS_RTT = 1, + TCP_METRICS_A_METRICS_RTTVAR, + TCP_METRICS_A_METRICS_SSTHRESH, + TCP_METRICS_A_METRICS_CWND, + TCP_METRICS_A_METRICS_REODERING, + TCP_METRICS_A_METRICS_RTT_US, + TCP_METRICS_A_METRICS_RTTVAR_US, + + __TCP_METRICS_A_METRICS_MAX +}; +#define TCP_METRICS_A_METRICS_MAX (__TCP_METRICS_A_METRICS_MAX - 1) + enum { TCP_METRICS_ATTR_UNSPEC, TCP_METRICS_ATTR_ADDR_IPV4, /* u32 */ diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index dbdca32a1c61..0712b5e82eb7 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -26,3 +26,4 @@ CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h) CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) CFLAGS_ovs_flow:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) CFLAGS_ovs_vport:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) +CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h) -- cgit v1.2.3 From 6555acdefc758a4dae7038c3f2301f311e287218 Mon Sep 17 00:00:00 2001 From: Mordechay Goodstein Date: Tue, 2 Jul 2024 19:21:18 +0200 Subject: um: time-travel: support time-travel protocol broadcast messages Add a message type to the time-travel protocol to broadcast a small (64-bit) value to all participants in a simulation. The main use case is to have an identical message come to all participants in a simulation, e.g. to separate out logs for different tests running in a single simulation. Down in the guts of time_travel_handle_message() we can't use printk() and not even printk_deferred(), so just store the message and print it at the start of the userspace() function. Unfortunately this means that other prints in the kernel can actually bypass the message, but in most cases where this is used, for example to separate test logs, userspace will be involved. Also, even if we could use printk_deferred(), we'd still need to flush it out in the userspace() function since otherwise userspace messages might cross it. As a result, this is a reasonable compromise, there's no need to have any core changes and it solves the main use case we have for it. Signed-off-by: Mordechay Goodstein Link: https://patch.msgid.link/20240702192118.c4093bc5b15e.I2ca8d006b67feeb866ac2017af7b741c9e06445a@changeid Signed-off-by: Johannes Berg --- arch/um/include/shared/timetravel.h | 9 ++++++ arch/um/kernel/time.c | 59 +++++++++++++++++++++++++++++++++++++ arch/um/os-Linux/skas/process.c | 3 ++ include/uapi/linux/um_timetravel.h | 11 +++++++ 4 files changed, 82 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/um/include/shared/timetravel.h b/arch/um/include/shared/timetravel.h index e5c3d69f1b69..c8db2f213dba 100644 --- a/arch/um/include/shared/timetravel.h +++ b/arch/um/include/shared/timetravel.h @@ -15,8 +15,17 @@ enum time_travel_mode { #if defined(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT) || \ defined(CONFIG_UML_TIME_TRAVEL_SUPPORT) extern enum time_travel_mode time_travel_mode; +extern int time_travel_should_print_bc_msg; #else #define time_travel_mode TT_MODE_OFF +#define time_travel_should_print_bc_msg 0 #endif /* (UML_)CONFIG_UML_TIME_TRAVEL_SUPPORT */ +void _time_travel_print_bc_msg(void); +static inline void time_travel_print_bc_msg(void) +{ + if (time_travel_should_print_bc_msg) + _time_travel_print_bc_msg(); +} + #endif /* _UM_TIME_TRAVEL_H_ */ diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 5b5fd8f68d9c..2339edc22f7c 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -60,6 +60,15 @@ enum time_travel_message_handling { TTMH_READ, }; +static u64 bc_message; +int time_travel_should_print_bc_msg; + +void _time_travel_print_bc_msg(void) +{ + time_travel_should_print_bc_msg = 0; + printk(KERN_INFO "time-travel: received broadcast 0x%llx\n", bc_message); +} + static void time_travel_handle_message(struct um_timetravel_msg *msg, enum time_travel_message_handling mode) { @@ -101,6 +110,10 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, time_travel_ext_free_until_valid = true; time_travel_ext_free_until = msg->time; break; + case UM_TIMETRAVEL_BROADCAST: + bc_message = msg->time; + time_travel_should_print_bc_msg = 1; + break; } resp.seq = msg->seq; @@ -880,4 +893,50 @@ __uml_help(setup_time_travel_start, "time-travel-start=\n" "Configure the UML instance's wall clock to start at this value rather than\n" "the host's wall clock at the time of UML boot.\n"); +static struct kobject *bc_time_kobject; + +static ssize_t bc_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "0x%llx", bc_message); +} + +static ssize_t bc_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret; + u64 user_bc_message; + + ret = kstrtou64(buf, 0, &user_bc_message); + if (ret) + return ret; + + bc_message = user_bc_message; + + time_travel_ext_req(UM_TIMETRAVEL_BROADCAST, bc_message); + pr_info("um: time: sent broadcast message: 0x%llx\n", bc_message); + return count; +} + +static struct kobj_attribute bc_attribute = __ATTR(bc-message, 0660, bc_show, bc_store); + +static int __init um_bc_start(void) +{ + if (time_travel_mode != TT_MODE_EXTERNAL) + return 0; + + bc_time_kobject = kobject_create_and_add("um-ext-time", kernel_kobj); + if (!bc_time_kobject) + return 0; + + if (sysfs_create_file(bc_time_kobject, &bc_attribute.attr)) + pr_debug("failed to create the bc file in /sys/kernel/um_time"); + + return 0; +} + +void __exit time_exit(void) +{ + kobject_put(bc_time_kobject); +} + +late_initcall(um_bc_start); #endif diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 41a288dcfc34..45885deb6cae 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "../internal.h" int is_skas_winch(int pid, int fd, void *data) @@ -345,6 +346,8 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) interrupt_end(); while (1) { + time_travel_print_bc_msg(); + if (kill_userspace_mm[0]) fatal_sigsegv(); diff --git a/include/uapi/linux/um_timetravel.h b/include/uapi/linux/um_timetravel.h index ca3238222b6d..078ea401aa2a 100644 --- a/include/uapi/linux/um_timetravel.h +++ b/include/uapi/linux/um_timetravel.h @@ -123,6 +123,17 @@ enum um_timetravel_ops { * the simulation. */ UM_TIMETRAVEL_GET_TOD = 8, + + /** + * @UM_TIMETRAVEL_BROADCAST: Send/Receive a broadcast message. + * This message can be used to sync all components in the system + * with a single message, if the calender gets the message, the + * calender broadcast the message to all components, and if a + * component receives it it should act based on it e.g print a + * message to it's log system. + * (calendar <-> host) + */ + UM_TIMETRAVEL_BROADCAST = 9, }; #endif /* _UAPI_LINUX_UM_TIMETRAVEL_H */ -- cgit v1.2.3 From bfb80d8bc92fa70f5b44a57ed2b24d57685fe188 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 2 Jul 2024 19:21:21 +0200 Subject: um: add shared memory optimisation for time-travel=ext With external time travel, a LOT of message can end up being exchanged on the socket, taking a significant amount of time just to do that. Add a new shared memory optimisation to that, where a number of changes are made: - the controller sends a client ID and a shared memory FD (and a logging FD we don't use) in the ACK message to the initial START - the shared memory holds the current time and the free_until value, so that there's no need to exchange messages for that - if the client that's running has shared memory support, any client (the running one included) can request the next time it wants to run inside the shared memory, rather than sending a message, by also updating the free_until value - when shared memory is enabled, RUN/WAIT messages no longer have an ACK, further cutting down on messages Together, this can reduce the number of messages very significantly, and reduce overall test/simulation run time. Co-developed-by: Mordechay Goodstein Signed-off-by: Mordechay Goodstein Link: https://patch.msgid.link/20240702192118.6ad0a083f574.Ie41206c8ce4507fe26b991937f47e86c24ca7a31@changeid Signed-off-by: Johannes Berg --- arch/um/kernel/time.c | 130 ++++++++++++++++++++++++--- include/uapi/linux/um_timetravel.h | 179 ++++++++++++++++++++++++++++++++++--- 2 files changed, 283 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 2339edc22f7c..d44eaad53d9d 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -31,6 +31,7 @@ EXPORT_SYMBOL_GPL(time_travel_mode); static bool time_travel_start_set; static unsigned long long time_travel_start; static unsigned long long time_travel_time; +static unsigned long long time_travel_shm_offset; static LIST_HEAD(time_travel_events); static LIST_HEAD(time_travel_irqs); static unsigned long long time_travel_timer_interval; @@ -40,8 +41,11 @@ static int time_travel_ext_fd = -1; static unsigned int time_travel_ext_waiting; static bool time_travel_ext_prev_request_valid; static unsigned long long time_travel_ext_prev_request; -static bool time_travel_ext_free_until_valid; -static unsigned long long time_travel_ext_free_until; +static unsigned long long *time_travel_ext_free_until; +static unsigned long long _time_travel_ext_free_until; +static u16 time_travel_shm_id; +static struct um_timetravel_schedshm *time_travel_shm; +static union um_timetravel_schedshm_client *time_travel_shm_client; static void time_travel_set_time(unsigned long long ns) { @@ -58,6 +62,7 @@ enum time_travel_message_handling { TTMH_IDLE, TTMH_POLL, TTMH_READ, + TTMH_READ_START_ACK, }; static u64 bc_message; @@ -69,6 +74,40 @@ void _time_travel_print_bc_msg(void) printk(KERN_INFO "time-travel: received broadcast 0x%llx\n", bc_message); } +static void time_travel_setup_shm(int fd, u16 id) +{ + u32 len; + + time_travel_shm = os_mmap_rw_shared(fd, sizeof(*time_travel_shm)); + + if (!time_travel_shm) + goto out; + + len = time_travel_shm->len; + + if (time_travel_shm->version != UM_TIMETRAVEL_SCHEDSHM_VERSION || + len < struct_size(time_travel_shm, clients, id + 1)) { + os_unmap_memory(time_travel_shm, sizeof(*time_travel_shm)); + time_travel_shm = NULL; + goto out; + } + + time_travel_shm = os_mremap_rw_shared(time_travel_shm, + sizeof(*time_travel_shm), + len); + if (!time_travel_shm) + goto out; + + time_travel_shm_offset = time_travel_shm->current_time; + time_travel_shm_client = &time_travel_shm->clients[id]; + time_travel_shm_client->capa |= UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE; + time_travel_shm_id = id; + /* always look at that free_until from now on */ + time_travel_ext_free_until = &time_travel_shm->free_until; +out: + os_close_file(fd); +} + static void time_travel_handle_message(struct um_timetravel_msg *msg, enum time_travel_message_handling mode) { @@ -89,7 +128,20 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, } } - ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); + if (unlikely(mode == TTMH_READ_START_ACK)) { + int fd[UM_TIMETRAVEL_SHARED_MAX_FDS]; + + ret = os_rcv_fd_msg(time_travel_ext_fd, fd, + ARRAY_SIZE(fd), msg, sizeof(*msg)); + if (ret == sizeof(*msg)) { + time_travel_setup_shm(fd[UM_TIMETRAVEL_SHARED_MEMFD], + msg->time & UM_TIMETRAVEL_START_ACK_ID); + /* we don't use the logging for now */ + os_close_file(fd[UM_TIMETRAVEL_SHARED_LOGFD]); + } + } else { + ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); + } if (ret == 0) panic("time-travel external link is broken\n"); @@ -105,10 +157,20 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, return; case UM_TIMETRAVEL_RUN: time_travel_set_time(msg->time); + if (time_travel_shm) { + /* no request right now since we're running */ + time_travel_shm_client->flags &= + ~UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN; + /* no ack for shared memory RUN */ + return; + } break; case UM_TIMETRAVEL_FREE_UNTIL: - time_travel_ext_free_until_valid = true; - time_travel_ext_free_until = msg->time; + /* not supposed to get this with shm, but ignore it */ + if (time_travel_shm) + break; + time_travel_ext_free_until = &_time_travel_ext_free_until; + _time_travel_ext_free_until = msg->time; break; case UM_TIMETRAVEL_BROADCAST: bc_message = msg->time; @@ -149,8 +211,15 @@ static u64 time_travel_ext_req(u32 op, u64 time) block_signals_hard(); os_write_file(time_travel_ext_fd, &msg, sizeof(msg)); + /* no ACK expected for WAIT in shared memory mode */ + if (msg.op == UM_TIMETRAVEL_WAIT && time_travel_shm) + goto done; + while (msg.op != UM_TIMETRAVEL_ACK) - time_travel_handle_message(&msg, TTMH_READ); + time_travel_handle_message(&msg, + op == UM_TIMETRAVEL_START ? + TTMH_READ_START_ACK : + TTMH_READ); if (msg.seq != mseq) panic("time-travel: ACK message has different seqno! op=%d, seq=%d != %d time=%lld\n", @@ -158,6 +227,7 @@ static u64 time_travel_ext_req(u32 op, u64 time) if (op == UM_TIMETRAVEL_GET) time_travel_set_time(msg.time); +done: unblock_signals_hard(); return msg.time; @@ -193,13 +263,33 @@ static void time_travel_ext_update_request(unsigned long long time) /* * if we're running and are allowed to run past the request * then we don't need to update it either + * + * Note for shm we ignore FREE_UNTIL messages and leave the pointer + * to shared memory, and for non-shm the offset is 0. */ - if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && - time < time_travel_ext_free_until) + if (!time_travel_ext_waiting && time_travel_ext_free_until && + time < (*time_travel_ext_free_until - time_travel_shm_offset)) return; time_travel_ext_prev_request = time; time_travel_ext_prev_request_valid = true; + + if (time_travel_shm) { + union um_timetravel_schedshm_client *running; + + running = &time_travel_shm->clients[time_travel_shm->running_id]; + + if (running->capa & UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE) { + time_travel_shm_client->flags |= + UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN; + time += time_travel_shm_offset; + time_travel_shm_client->req_time = time; + if (time < time_travel_shm->free_until) + time_travel_shm->free_until = time; + return; + } + } + time_travel_ext_req(UM_TIMETRAVEL_REQUEST, time); } @@ -207,6 +297,14 @@ void __time_travel_propagate_time(void) { static unsigned long long last_propagated; + if (time_travel_shm) { + if (time_travel_shm->running_id != time_travel_shm_id) + panic("time-travel: setting time while not running\n"); + time_travel_shm->current_time = time_travel_time + + time_travel_shm_offset; + return; + } + if (last_propagated == time_travel_time) return; @@ -222,9 +320,12 @@ static bool time_travel_ext_request(unsigned long long time) * If we received an external sync point ("free until") then we * don't have to request/wait for anything until then, unless * we're already waiting. + * + * Note for shm we ignore FREE_UNTIL messages and leave the pointer + * to shared memory, and for non-shm the offset is 0. */ - if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && - time < time_travel_ext_free_until) + if (!time_travel_ext_waiting && time_travel_ext_free_until && + time < (*time_travel_ext_free_until - time_travel_shm_offset)) return false; time_travel_ext_update_request(time); @@ -238,7 +339,8 @@ static void time_travel_ext_wait(bool idle) }; time_travel_ext_prev_request_valid = false; - time_travel_ext_free_until_valid = false; + if (!time_travel_shm) + time_travel_ext_free_until = NULL; time_travel_ext_waiting++; time_travel_ext_req(UM_TIMETRAVEL_WAIT, -1); @@ -261,7 +363,11 @@ static void time_travel_ext_wait(bool idle) static void time_travel_ext_get_time(void) { - time_travel_ext_req(UM_TIMETRAVEL_GET, -1); + if (time_travel_shm) + time_travel_set_time(time_travel_shm->current_time - + time_travel_shm_offset); + else + time_travel_ext_req(UM_TIMETRAVEL_GET, -1); } static void __time_travel_update_time(unsigned long long ns, bool idle) diff --git a/include/uapi/linux/um_timetravel.h b/include/uapi/linux/um_timetravel.h index 078ea401aa2a..546a690b0346 100644 --- a/include/uapi/linux/um_timetravel.h +++ b/include/uapi/linux/um_timetravel.h @@ -1,17 +1,6 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ /* - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - * - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019 - 2023 Intel Corporation */ #ifndef _UAPI_LINUX_UM_TIMETRAVEL_H #define _UAPI_LINUX_UM_TIMETRAVEL_H @@ -50,6 +39,36 @@ struct um_timetravel_msg { __u64 time; }; +/* max number of file descriptors that can be sent/received in a message */ +#define UM_TIMETRAVEL_MAX_FDS 2 + +/** + * enum um_timetravel_shared_mem_fds - fds sent in ACK message for START message + */ +enum um_timetravel_shared_mem_fds { + /** + * @UM_TIMETRAVEL_SHARED_MEMFD: Index of the shared memory file + * descriptor in the control message + */ + UM_TIMETRAVEL_SHARED_MEMFD, + /** + * @UM_TIMETRAVEL_SHARED_LOGFD: Index of the logging file descriptor + * in the control message + */ + UM_TIMETRAVEL_SHARED_LOGFD, + UM_TIMETRAVEL_SHARED_MAX_FDS, +}; + +/** + * enum um_timetravel_start_ack - ack-time mask for start message + */ +enum um_timetravel_start_ack { + /** + * @UM_TIMETRAVEL_START_ACK_ID: client ID that controller allocated. + */ + UM_TIMETRAVEL_START_ACK_ID = 0xffff, +}; + /** * enum um_timetravel_ops - Operation codes */ @@ -57,7 +76,9 @@ enum um_timetravel_ops { /** * @UM_TIMETRAVEL_ACK: response (ACK) to any previous message, * this usually doesn't carry any data in the 'time' field - * unless otherwise specified below + * unless otherwise specified below, note: while using shared + * memory no ACK for WAIT and RUN messages, for more info see + * &struct um_timetravel_schedshm. */ UM_TIMETRAVEL_ACK = 0, @@ -136,4 +157,134 @@ enum um_timetravel_ops { UM_TIMETRAVEL_BROADCAST = 9, }; +/* version of struct um_timetravel_schedshm */ +#define UM_TIMETRAVEL_SCHEDSHM_VERSION 2 + +/** + * enum um_timetravel_schedshm_cap - time travel capabilities of every client + * + * These flags must be set immediately after processing the ACK to + * the START message, before sending any message to the controller. + */ +enum um_timetravel_schedshm_cap { + /** + * @UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE: client can read current time + * update internal time request to shared memory and read + * free until and send no Ack on RUN and doesn't expect ACK on + * WAIT. + */ + UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE = 0x1, +}; + +/** + * enum um_timetravel_schedshm_flags - time travel flags of every client + */ +enum um_timetravel_schedshm_flags { + /** + * @UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN: client has a request to run. + * It's set by client when it has a request to run, if (and only + * if) the @running_id points to a client that is able to use + * shared memory, i.e. has %UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE + * (this includes the client itself). Otherwise, a message must + * be used. + */ + UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN = 0x1, +}; + +/** + * DOC: Time travel shared memory overview + * + * The main purpose of the shared memory is to avoid all time travel message + * that don't need any action, for example current time can be held in shared + * memory without the need of any client to send a message UM_TIMETRAVEL_GET + * in order to know what's the time. + * + * Since this is shared memory with all clients and controller and controller + * creates the shared memory space, all time values are absolute to controller + * time. So first time client connects to shared memory mode it should take the + * current_time value in shared memory and keep it internally as a diff to + * shared memory times, and once shared memory is initialized, any interaction + * with the controller must happen in the controller time domain, including any + * messages (for clients that are not using shared memory, the controller will + * handle an offset and make the clients think they start at time zero.) + * + * Along with the shared memory file descriptor is sent to the client a logging + * file descriptor, to have all logs related to shared memory, + * logged into one place. note: to have all logs synced into log file at write, + * file should be flushed (fflush) after writing to it. + * + * To avoid memory corruption, we define below for each field who can write to + * it at what time, defined in the structure fields. + * + * To avoid having to pack this struct, all fields in it must be naturally aligned + * (i.e. aligned to their size). + */ + +/** + * union um_timetravel_schedshm_client - UM time travel client struct + * + * Every entity using the shared memory including the controller has a place in + * the um_timetravel_schedshm clients array, that holds info related to the client + * using the shared memory, and can be set only by the client after it gets the + * fd memory. + * + * @capa: bit fields with client capabilities see + * &enum um_timetravel_schedshm_cap, set by client once after getting the + * shared memory file descriptor. + * @flags: bit fields for flags see &enum um_timetravel_schedshm_flags for doc. + * @req_time: request time to run, set by client on every request it needs. + * @name: unique id sent to the controller by client with START message. + */ +union um_timetravel_schedshm_client { + struct { + __u32 capa; + __u32 flags; + __u64 req_time; + __u64 name; + }; + char reserve[128]; /* reserved for future usage */ +}; + +/** + * struct um_timetravel_schedshm - UM time travel shared memory struct + * + * @hdr: header fields: + * @version: Current version struct UM_TIMETRAVEL_SCHEDSHM_VERSION, + * set by controller once at init, clients must check this after mapping + * and work without shared memory if they cannot handle the indicated + * version. + * @len: Length of all the memory including header (@hdr), clients should once + * per connection first mmap the header and take the length (@len) to remap the entire size. + * This is done in order to support dynamic struct size letting number of + * clients be dynamic based on controller support. + * @free_until: Stores the next request to run by any client, in order for the + * current client to know how long it can still run. A client needs to (at + * least) reload this value immediately after communicating with any other + * client, since the controller will update this field when a new request + * is made by any client. Clients also must update this value when they + * insert/update an own request into the shared memory while not running + * themselves, and the new request is before than the current value. + * current_time: Current time, can only be set by the client in running state + * (indicated by @running_id), though that client may only run until @free_until, + * so it must remain smaller than @free_until. + * @running_id: The current client in state running, set before a client is + * notified that it's now running. + * @max_clients: size of @clients array, set once at init by the controller. + * @clients: clients array see &union um_timetravel_schedshm_client for doc, + * set only by client. + */ +struct um_timetravel_schedshm { + union { + struct { + __u32 version; + __u32 len; + __u64 free_until; + __u64 current_time; + __u16 running_id; + __u16 max_clients; + }; + char hdr[4096]; /* align to 4K page size */ + }; + union um_timetravel_schedshm_client clients[]; +}; #endif /* _UAPI_LINUX_UM_TIMETRAVEL_H */ -- cgit v1.2.3 From 4ecaf7e98a3ae0c843d67c76649ecc694232834b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 2 Jul 2024 15:33:54 -0400 Subject: tracing: Have memmapped ring buffer use ioctl of "R" range 0x20-2F To prevent conflicts with other ioctl numbers to allow strace to have an idea of what is happening, add the range of ioctls for the trace buffer mapping from _IO("T", 0x1) to the range of "R" 0x20 - 0x2F. Link: https://lore.kernel.org/linux-trace-kernel/20240630105322.GA17573@altlinux.org/ Link: https://lore.kernel.org/linux-trace-kernel/20240630213626.GA23566@altlinux.org/ Cc: Jonathan Corbet Fixes: cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer") Link: https://lore.kernel.org/20240702153354.367861db@rorschach.local.home Reported-by: "Dmitry V. Levin" Reviewed-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + include/uapi/linux/trace_mmap.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a141e8e65c5d..9a97030c6c8d 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -186,6 +186,7 @@ Code Seq# Include File Comments 'Q' all linux/soundcard.h 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! +'R' 20-2F linux/trace_mmap.h 'R' C0-DF net/bluetooth/rfcomm.h 'R' E0 uapi/linux/fsl_mc.h 'S' all linux/cdrom.h conflict! diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h index bd1066754220..c102ef35d11e 100644 --- a/include/uapi/linux/trace_mmap.h +++ b/include/uapi/linux/trace_mmap.h @@ -43,6 +43,6 @@ struct trace_buffer_meta { __u64 Reserved2; }; -#define TRACE_MMAP_IOCTL_GET_READER _IO('T', 0x1) +#define TRACE_MMAP_IOCTL_GET_READER _IO('R', 0x20) #endif /* _TRACE_MMAP_H_ */ -- cgit v1.2.3 From 608f6976c309793ceea37292c54b057dab091944 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 26 Jun 2024 07:35:37 -0700 Subject: perf/x86/intel: Support new data source for Lunar Lake A new PEBS data source format is introduced for the p-core of Lunar Lake. The data source field is extended to 8 bits with new encodings. A new layout is introduced into the union intel_x86_pebs_dse. Introduce the lnl_latency_data() to parse the new format. Enlarge the pebs_data_source[] accordingly to include new encodings. Only the mem load and the mem store events can generate the data source. Introduce INTEL_HYBRID_LDLAT_CONSTRAINT and INTEL_HYBRID_STLAT_CONSTRAINT to mark them. Add two new bits for the new cache-related data src, L2_MHB and MSC. The L2_MHB is short for L2 Miss Handling Buffer, which is similar to LFB (Line Fill Buffer), but to track the L2 Cache misses. The MSC stands for the memory-side cache. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andi Kleen Reviewed-by: Ian Rogers Link: https://lkml.kernel.org/r/20240626143545.480761-6-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 2 + arch/x86/events/intel/ds.c | 94 ++++++++++++++++++++++++++++++++++++++++- arch/x86/events/perf_event.h | 16 ++++++- include/uapi/linux/perf_event.h | 6 ++- 4 files changed, 113 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 35f2d52281cc..6a6f1f4b9205 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6960,6 +6960,7 @@ __init int intel_pmu_init(void) case INTEL_ARROWLAKE: intel_pmu_init_hybrid(hybrid_big_small); + x86_pmu.pebs_latency_data = lnl_latency_data; x86_pmu.get_event_constraints = mtl_get_event_constraints; x86_pmu.hw_config = adl_hw_config; @@ -6977,6 +6978,7 @@ __init int intel_pmu_init(void) pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; intel_pmu_init_skt(&pmu->pmu); + intel_pmu_pebs_data_source_lnl(); pr_cont("Lunarlake Hybrid events, "); name = "lunarlake_hybrid"; break; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 3581c2715b21..b9cc520b2942 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -63,6 +63,15 @@ union intel_x86_pebs_dse { unsigned int mtl_fwd_blk:1; unsigned int ld_reserved4:24; }; + struct { + unsigned int lnc_dse:8; + unsigned int ld_reserved5:2; + unsigned int lnc_stlb_miss:1; + unsigned int lnc_locked:1; + unsigned int lnc_data_blk:1; + unsigned int lnc_addr_blk:1; + unsigned int ld_reserved6:18; + }; }; @@ -77,7 +86,7 @@ union intel_x86_pebs_dse { #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) /* Version for Sandy Bridge and later */ -static u64 pebs_data_source[] = { +static u64 pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = { P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -173,6 +182,40 @@ void __init intel_pmu_pebs_data_source_cmt(void) __intel_pmu_pebs_data_source_cmt(pebs_data_source); } +/* Version for Lion Cove and later */ +static u64 lnc_pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* 0x00: ukn L3 */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 hit */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x02: L1 hit */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x03: LFB/L1 Miss Handling Buffer hit */ + 0, /* 0x04: Reserved */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x05: L2 Hit */ + OP_LH | LEVEL(L2_MHB) | P(SNOOP, NONE), /* 0x06: L2 Miss Handling Buffer Hit */ + 0, /* 0x07: Reserved */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x08: L3 Hit */ + 0, /* 0x09: Reserved */ + 0, /* 0x0a: Reserved */ + 0, /* 0x0b: Reserved */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* 0x0c: L3 Hit Snoop Fwd */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0d: L3 Hit Snoop HitM */ + 0, /* 0x0e: Reserved */ + P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0f: L3 Miss Snoop HitM */ + OP_LH | LEVEL(MSC) | P(SNOOP, NONE), /* 0x10: Memory-side Cache Hit */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* 0x11: Local Memory Hit */ +}; + +void __init intel_pmu_pebs_data_source_lnl(void) +{ + u64 *data_source; + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source; + memcpy(data_source, lnc_pebs_data_source, sizeof(lnc_pebs_data_source)); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_cmt(data_source); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -264,7 +307,7 @@ static u64 __grt_latency_data(struct perf_event *event, u64 status, WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big); - dse &= PERF_PEBS_DATA_SOURCE_MASK; + dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK; val = hybrid_var(event->pmu, pebs_data_source)[dse]; pebs_set_tlb_lock(&val, tlb, lock); @@ -300,6 +343,51 @@ u64 cmt_latency_data(struct perf_event *event, u64 status) dse.mtl_fwd_blk); } +static u64 lnc_latency_data(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + union perf_mem_data_src src; + u64 val; + + dse.val = status; + + /* LNC core latency data */ + val = hybrid_var(event->pmu, pebs_data_source)[status & PERF_PEBS_DATA_SOURCE_MASK]; + if (!val) + val = P(OP, LOAD) | LEVEL(NA) | P(SNOOP, NA); + + if (dse.lnc_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + if (dse.lnc_locked) + val |= P(LOCK, LOCKED); + + if (dse.lnc_data_blk) + val |= P(BLK, DATA); + if (dse.lnc_addr_blk) + val |= P(BLK, ADDR); + if (!dse.lnc_data_blk && !dse.lnc_addr_blk) + val |= P(BLK, NA); + + src.val = val; + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + src.mem_op = P(OP, STORE); + + return src.val; +} + +u64 lnl_latency_data(struct perf_event *event, u64 status) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->pmu_type == hybrid_small) + return cmt_latency_data(event, status); + + return lnc_latency_data(event, status); +} + static u64 load_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; @@ -1090,6 +1178,8 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), + INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff), + INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fc2561959fed..493bc9f70ffe 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -476,6 +476,14 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID) +#define INTEL_HYBRID_LDLAT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_LD_HSW) + +#define INTEL_HYBRID_STLAT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_ST_HSW) + /* Event constraint, but match on all event flags too. */ #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS) @@ -655,8 +663,10 @@ enum { x86_lbr_exclusive_max, }; -#define PERF_PEBS_DATA_SOURCE_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_MAX 0x100 #define PERF_PEBS_DATA_SOURCE_MASK (PERF_PEBS_DATA_SOURCE_MAX - 1) +#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1) enum hybrid_cpu_type { HYBRID_INTEL_NONE, @@ -1552,6 +1562,8 @@ u64 grt_latency_data(struct perf_event *event, u64 status); u64 cmt_latency_data(struct perf_event *event, u64 status); +u64 lnl_latency_data(struct perf_event *event, u64 status); + extern struct event_constraint intel_core2_pebs_event_constraints[]; extern struct event_constraint intel_atom_pebs_event_constraints[]; @@ -1673,6 +1685,8 @@ void intel_pmu_pebs_data_source_mtl(void); void intel_pmu_pebs_data_source_cmt(void); +void intel_pmu_pebs_data_source_lnl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 3a64499b0f5d..4842c36fdf80 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1349,12 +1349,14 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ +/* 0x7 available */ #define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ #define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ #define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ -- cgit v1.2.3 From 093b0f366567aa3fed85c316f832607069202b23 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:52 +0200 Subject: net: psample: add user cookie Add a user cookie to the sample metadata so that sample emitters can provide more contextual information to samples. If present, send the user cookie in a new attribute: PSAMPLE_ATTR_USER_COOKIE. Reviewed-by: Michal Kubiak Acked-by: Eelco Chaudron Reviewed-by: Simon Horman Reviewed-by: Ido Schimmel Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-2-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- include/net/psample.h | 2 ++ include/uapi/linux/psample.h | 1 + net/psample/psample.c | 9 ++++++++- 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/psample.h b/include/net/psample.h index 0509d2d6be67..2ac71260a546 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -25,6 +25,8 @@ struct psample_metadata { out_tc_occ_valid:1, latency_valid:1, unused:5; + const u8 *user_cookie; + u32 user_cookie_len; }; struct psample_group *psample_group_get(struct net *net, u32 group_num); diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index e585db5bf2d2..e80637e1d97b 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -19,6 +19,7 @@ enum { PSAMPLE_ATTR_LATENCY, /* u64, nanoseconds */ PSAMPLE_ATTR_TIMESTAMP, /* u64, nanoseconds */ PSAMPLE_ATTR_PROTO, /* u16 */ + PSAMPLE_ATTR_USER_COOKIE, /* binary, user provided data */ __PSAMPLE_ATTR_MAX }; diff --git a/net/psample/psample.c b/net/psample/psample.c index a5d9b8446f77..b37488f426bc 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -386,7 +386,9 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, nla_total_size(sizeof(u32)) + /* group_num */ nla_total_size(sizeof(u32)) + /* seq */ nla_total_size_64bit(sizeof(u64)) + /* timestamp */ - nla_total_size(sizeof(u16)); /* protocol */ + nla_total_size(sizeof(u16)) + /* protocol */ + (md->user_cookie_len ? + nla_total_size(md->user_cookie_len) : 0); /* user cookie */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -486,6 +488,11 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, } #endif + if (md->user_cookie && md->user_cookie_len && + nla_put(nl_skb, PSAMPLE_ATTR_USER_COOKIE, md->user_cookie_len, + md->user_cookie)) + goto error; + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); -- cgit v1.2.3 From 7b1b2b60c63f070e0dfbe072ccaae13168b38d01 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:55 +0200 Subject: net: psample: allow using rate as probability Although not explicitly documented in the psample module itself, the definition of PSAMPLE_ATTR_SAMPLE_RATE seems inherited from act_sample. Quoting tc-sample(8): "RATE of 100 will lead to an average of one sampled packet out of every 100 observed." With this semantics, the rates that we can express with an unsigned 32-bits number are very unevenly distributed and concentrated towards "sampling few packets". For example, we can express a probability of 2.32E-8% but we cannot express anything between 100% and 50%. For sampling applications that are capable of sampling a decent amount of packets, this sampling rate semantics is not very useful. Add a new flag to the uAPI that indicates that the sampling rate is expressed in scaled probability, this is: - 0 is 0% probability, no packets get sampled. - U32_MAX is 100% probability, all packets get sampled. Reviewed-by: Aaron Conole Acked-by: Eelco Chaudron Reviewed-by: Ido Schimmel Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-5-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- include/net/psample.h | 3 ++- include/uapi/linux/psample.h | 10 +++++++++- net/psample/psample.c | 3 +++ 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/psample.h b/include/net/psample.h index 2ac71260a546..c52e9ebd88dd 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -24,7 +24,8 @@ struct psample_metadata { u8 out_tc_valid:1, out_tc_occ_valid:1, latency_valid:1, - unused:5; + rate_as_probability:1, + unused:4; const u8 *user_cookie; u32 user_cookie_len; }; diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index e80637e1d97b..b765f0e81f20 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -8,7 +8,11 @@ enum { PSAMPLE_ATTR_ORIGSIZE, PSAMPLE_ATTR_SAMPLE_GROUP, PSAMPLE_ATTR_GROUP_SEQ, - PSAMPLE_ATTR_SAMPLE_RATE, + PSAMPLE_ATTR_SAMPLE_RATE, /* u32, ratio between observed and + * sampled packets or scaled probability + * if PSAMPLE_ATTR_SAMPLE_PROBABILITY + * is set. + */ PSAMPLE_ATTR_DATA, PSAMPLE_ATTR_GROUP_REFCOUNT, PSAMPLE_ATTR_TUNNEL, @@ -20,6 +24,10 @@ enum { PSAMPLE_ATTR_TIMESTAMP, /* u64, nanoseconds */ PSAMPLE_ATTR_PROTO, /* u16 */ PSAMPLE_ATTR_USER_COOKIE, /* binary, user provided data */ + PSAMPLE_ATTR_SAMPLE_PROBABILITY,/* no argument, interpret rate in + * PSAMPLE_ATTR_SAMPLE_RATE as a + * probability scaled 0 - U32_MAX. + */ __PSAMPLE_ATTR_MAX }; diff --git a/net/psample/psample.c b/net/psample/psample.c index 1c76f3e48dcd..f48b5b9cd409 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -497,6 +497,9 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, md->user_cookie)) goto error; + if (md->rate_as_probability) + nla_put_flag(skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); -- cgit v1.2.3 From aae0b82b46cb5004bdf82a000c004d69a0885c33 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:56 +0200 Subject: net: openvswitch: add psample action Add support for a new action: psample. This action accepts a u32 group id and a variable-length cookie and uses the psample multicast group to make the packet available for observability. The maximum length of the user-defined cookie is set to 16, same as tc_cookie, to discourage using cookies that will not be offloadable. Reviewed-by: Michal Kubiak Reviewed-by: Aaron Conole Reviewed-by: Ilya Maximets Acked-by: Eelco Chaudron Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-6-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ovs_flow.yaml | 17 +++++++++++ include/uapi/linux/openvswitch.h | 28 ++++++++++++++++++ net/openvswitch/Kconfig | 1 + net/openvswitch/actions.c | 48 +++++++++++++++++++++++++++++++ net/openvswitch/flow_netlink.c | 32 ++++++++++++++++++++- 5 files changed, 125 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml index 4fdfc6b5cae9..46f5d1cd8a5f 100644 --- a/Documentation/netlink/specs/ovs_flow.yaml +++ b/Documentation/netlink/specs/ovs_flow.yaml @@ -727,6 +727,12 @@ attribute-sets: name: dec-ttl type: nest nested-attributes: dec-ttl-attrs + - + name: psample + type: nest + nested-attributes: psample-attrs + doc: | + Sends a packet sample to psample for external observation. - name: tunnel-key-attrs enum-name: ovs-tunnel-key-attr @@ -938,6 +944,17 @@ attribute-sets: - name: gbp type: u32 + - + name: psample-attrs + enum-name: ovs-psample-attr + name-prefix: ovs-psample-attr- + attributes: + - + name: group + type: u32 + - + name: cookie + type: binary operations: name-prefix: ovs-flow-cmd- diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index efc82c318fa2..3dd653748725 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -914,6 +914,31 @@ struct check_pkt_len_arg { }; #endif +#define OVS_PSAMPLE_COOKIE_MAX_SIZE 16 +/** + * enum ovs_psample_attr - Attributes for %OVS_ACTION_ATTR_PSAMPLE + * action. + * + * @OVS_PSAMPLE_ATTR_GROUP: 32-bit number to identify the source of the + * sample. + * @OVS_PSAMPLE_ATTR_COOKIE: An optional variable-length binary cookie that + * contains user-defined metadata. The maximum length is + * OVS_PSAMPLE_COOKIE_MAX_SIZE bytes. + * + * Sends the packet to the psample multicast group with the specified group and + * cookie. It is possible to combine this action with the + * %OVS_ACTION_ATTR_TRUNC action to limit the size of the sample. + */ +enum ovs_psample_attr { + OVS_PSAMPLE_ATTR_GROUP = 1, /* u32 number. */ + OVS_PSAMPLE_ATTR_COOKIE, /* Optional, user specified cookie. */ + + /* private: */ + __OVS_PSAMPLE_ATTR_MAX +}; + +#define OVS_PSAMPLE_ATTR_MAX (__OVS_PSAMPLE_ATTR_MAX - 1) + /** * enum ovs_action_attr - Action types. * @@ -966,6 +991,8 @@ struct check_pkt_len_arg { * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS * argument. * @OVS_ACTION_ATTR_DROP: Explicit drop action. + * @OVS_ACTION_ATTR_PSAMPLE: Send a sample of the packet to external observers + * via psample. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -1004,6 +1031,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_ADD_MPLS, /* struct ovs_action_add_mpls. */ OVS_ACTION_ATTR_DEC_TTL, /* Nested OVS_DEC_TTL_ATTR_*. */ OVS_ACTION_ATTR_DROP, /* u32 error code. */ + OVS_ACTION_ATTR_PSAMPLE, /* Nested OVS_PSAMPLE_ATTR_*. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 29a7081858cd..2535f3f9f462 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -10,6 +10,7 @@ config OPENVSWITCH (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ (!NF_NAT || NF_NAT) && \ (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT))) + depends on PSAMPLE || !PSAMPLE select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 964225580824..892d7e48fc5b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -24,6 +24,11 @@ #include #include #include + +#if IS_ENABLED(CONFIG_PSAMPLE) +#include +#endif + #include #include "datapath.h" @@ -1299,6 +1304,40 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key) return 0; } +#if IS_ENABLED(CONFIG_PSAMPLE) +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{ + struct psample_group psample_group = {}; + struct psample_metadata md = {}; + const struct nlattr *a; + int rem; + + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_PSAMPLE_ATTR_GROUP: + psample_group.group_num = nla_get_u32(a); + break; + + case OVS_PSAMPLE_ATTR_COOKIE: + md.user_cookie = nla_data(a); + md.user_cookie_len = nla_len(a); + break; + } + } + + psample_group.net = ovs_dp_get_net(dp); + md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; + md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + + psample_sample_packet(&psample_group, skb, 0, &md); +} +#else +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{} +#endif + /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, @@ -1502,6 +1541,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, ovs_kfree_skb_reason(skb, reason); return 0; } + + case OVS_ACTION_ATTR_PSAMPLE: + execute_psample(dp, skb, a); + OVS_CB(skb)->cutlen = 0; + if (nla_is_last(a, rem)) { + consume_skb(skb); + return 0; + } + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index f224d9bcea5e..c92bdc4dfe19 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -64,6 +64,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: case OVS_ACTION_ATTR_DROP: + case OVS_ACTION_ATTR_PSAMPLE: break; case OVS_ACTION_ATTR_CT: @@ -2409,7 +2410,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) /* Whenever new actions are added, the need to update this * function should be considered. */ - BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24); + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 25); if (!actions) return; @@ -3157,6 +3158,28 @@ static int validate_and_copy_check_pkt_len(struct net *net, return 0; } +static int validate_psample(const struct nlattr *attr) +{ + static const struct nla_policy policy[OVS_PSAMPLE_ATTR_MAX + 1] = { + [OVS_PSAMPLE_ATTR_GROUP] = { .type = NLA_U32 }, + [OVS_PSAMPLE_ATTR_COOKIE] = { + .type = NLA_BINARY, + .len = OVS_PSAMPLE_COOKIE_MAX_SIZE, + }, + }; + struct nlattr *a[OVS_PSAMPLE_ATTR_MAX + 1]; + int err; + + if (!IS_ENABLED(CONFIG_PSAMPLE)) + return -EOPNOTSUPP; + + err = nla_parse_nested(a, OVS_PSAMPLE_ATTR_MAX, attr, policy, NULL); + if (err) + return err; + + return a[OVS_PSAMPLE_ATTR_GROUP] ? 0 : -EINVAL; +} + static int copy_action(const struct nlattr *from, struct sw_flow_actions **sfa, bool log) { @@ -3212,6 +3235,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, [OVS_ACTION_ATTR_DROP] = sizeof(u32), + [OVS_ACTION_ATTR_PSAMPLE] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3490,6 +3514,12 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; break; + case OVS_ACTION_ATTR_PSAMPLE: + err = validate_psample(a); + if (err) + return err; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; -- cgit v1.2.3 From 71763d8a8203c28178d7be7f18af73d4dddb36ba Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:57 +0200 Subject: net: openvswitch: store sampling probability in cb. When a packet sample is observed, the sampling rate that was used is important to estimate the real frequency of such event. Store the probability of the parent sample action in the skb's cb area and use it in psample action to pass it down to psample module. Reviewed-by: Aaron Conole Acked-by: Eelco Chaudron Reviewed-by: Ilya Maximets Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-7-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/openvswitch.h | 3 ++- net/openvswitch/actions.c | 20 +++++++++++++++++--- net/openvswitch/datapath.h | 3 +++ net/openvswitch/vport.c | 1 + 4 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 3dd653748725..3a701bd1f31b 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -649,7 +649,8 @@ enum ovs_flow_attr { * Actions are passed as nested attributes. * * Executes the specified actions with the given probability on a per-packet - * basis. + * basis. Nested actions will be able to access the probability value of the + * parent @OVS_ACTION_ATTR_SAMPLE. */ enum ovs_sample_attr { OVS_SAMPLE_ATTR_UNSPEC, diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 892d7e48fc5b..101f9a23792c 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1048,12 +1048,15 @@ static int sample(struct datapath *dp, struct sk_buff *skb, struct nlattr *sample_arg; int rem = nla_len(attr); const struct sample_arg *arg; + u32 init_probability; bool clone_flow_key; + int err; /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */ sample_arg = nla_data(attr); arg = nla_data(sample_arg); actions = nla_next(sample_arg, &rem); + init_probability = OVS_CB(skb)->probability; if ((arg->probability != U32_MAX) && (!arg->probability || get_random_u32() > arg->probability)) { @@ -1062,9 +1065,16 @@ static int sample(struct datapath *dp, struct sk_buff *skb, return 0; } + OVS_CB(skb)->probability = arg->probability; + clone_flow_key = !arg->exec; - return clone_execute(dp, skb, key, 0, actions, rem, last, - clone_flow_key); + err = clone_execute(dp, skb, key, 0, actions, rem, last, + clone_flow_key); + + if (!last) + OVS_CB(skb)->probability = init_probability; + + return err; } /* When 'last' is true, clone() should always consume the 'skb'. @@ -1311,6 +1321,7 @@ static void execute_psample(struct datapath *dp, struct sk_buff *skb, struct psample_group psample_group = {}; struct psample_metadata md = {}; const struct nlattr *a; + u32 rate; int rem; nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { @@ -1329,8 +1340,11 @@ static void execute_psample(struct datapath *dp, struct sk_buff *skb, psample_group.net = ovs_dp_get_net(dp); md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + md.rate_as_probability = 1; + + rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX; - psample_sample_packet(&psample_group, skb, 0, &md); + psample_sample_packet(&psample_group, skb, rate, &md); } #else static void execute_psample(struct datapath *dp, struct sk_buff *skb, diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 0cd29971a907..9ca6231ea647 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -115,12 +115,15 @@ struct datapath { * fragmented. * @acts_origlen: The netlink size of the flow actions applied to this skb. * @cutlen: The number of bytes from the packet end to be removed. + * @probability: The sampling probability that was applied to this skb; 0 means + * no sampling has occurred; U32_MAX means 100% probability. */ struct ovs_skb_cb { struct vport *input_vport; u16 mru; u16 acts_origlen; u32 cutlen; + u32 probability; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 972ae01a70f7..8732f6e51ae5 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -500,6 +500,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->probability = 0; if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { u32 mark; -- cgit v1.2.3 From e46296002113b4556baffd5dc68c4f9e22dae13a Mon Sep 17 00:00:00 2001 From: "Kory Maincent (Dent Project)" Date: Thu, 4 Jul 2024 10:11:56 +0200 Subject: net: ethtool: pse-pd: Expand C33 PSE status with class, power and extended state This update expands the status information provided by ethtool for PSE c33. It includes details such as the detected class, current power delivered, and extended state information. Reviewed-by: Oleksij Rempel Signed-off-by: Kory Maincent Link: https://patch.msgid.link/20240704-feature_poe_power_cap-v6-1-320003204264@bootlin.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 37 ++++++ include/linux/ethtool.h | 15 +++ include/linux/pse-pd/pse.h | 8 ++ include/uapi/linux/ethtool.h | 191 +++++++++++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 4 + net/ethtool/pse-pd.c | 32 ++++- 6 files changed, 286 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index bfe2eda8580d..0656ad4be000 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1740,6 +1740,13 @@ Kernel response contents: PSE functions. ``ETHTOOL_A_C33_PSE_PW_D_STATUS`` u32 power detection status of the PoE PSE. + ``ETHTOOL_A_C33_PSE_PW_CLASS`` u32 power class of the PoE PSE. + ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` u32 actual power drawn on the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_STATE`` u32 power extended state of the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` u32 power extended substatus of + the PoE PSE. ====================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies @@ -1772,6 +1779,36 @@ The same goes for ``ETHTOOL_A_C33_PSE_ADMIN_PW_D_STATUS`` implementing .. kernel-doc:: include/uapi/linux/ethtool.h :identifiers: ethtool_c33_pse_pw_d_status +When set, the optional ``ETHTOOL_A_C33_PSE_PW_CLASS`` attribute identifies +the power class of the C33 PSE. It depends on the class negotiated between +the PSE and the PD. This option is corresponding to ``IEEE 802.3-2022`` +30.9.1.1.8 aPSEPowerClassification. + +When set, the optional ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` attribute identifies +This option is corresponding to ``IEEE 802.3-2022`` 30.9.1.1.23 aPSEActualPower. +Actual power is reported in mW. + +When set, the optional ``ETHTOOL_A_C33_PSE_EXT_STATE`` attribute identifies +the extended error state of the C33 PSE. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_c33_pse_ext_state + +When set, the optional ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` attribute identifies +the extended error state of the C33 PSE. Possible values are: +Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_c33_pse_ext_substate_class_num_events + ethtool_c33_pse_ext_substate_error_condition + ethtool_c33_pse_ext_substate_mr_pse_enable + ethtool_c33_pse_ext_substate_option_detect_ted + ethtool_c33_pse_ext_substate_option_vport_lim + ethtool_c33_pse_ext_substate_ovld_detected + ethtool_c33_pse_ext_substate_pd_dll_power_type + ethtool_c33_pse_ext_substate_power_not_available + ethtool_c33_pse_ext_substate_short_detected + PSE_SET ======= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 3a99238ef895..3e70f5d9e0bb 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1273,4 +1273,19 @@ struct ethtool_forced_speed_map { void ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); + +/* C33 PSE extended state and substate. */ +struct ethtool_c33_pse_ext_state_info { + enum ethtool_c33_pse_ext_state c33_pse_ext_state; + union { + enum ethtool_c33_pse_ext_substate_error_condition error_condition; + enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; + enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; + enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; + enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; + enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; + enum ethtool_c33_pse_ext_substate_short_detected short_detected; + u32 __c33_pse_ext_substate; + }; +}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 6eec24ffa866..38b9308e5e7a 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -36,12 +36,20 @@ struct pse_control_config { * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState * @c33_pw_status: power detection status of the PSE. * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: + * @c33_pw_class: detected class of a powered PD + * IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification + * @c33_actual_pw: power currently delivered by the PSE in mW + * IEEE 802.3-2022 30.9.1.1.23 aPSEActualPower + * @c33_ext_state_info: extended state information of the PSE */ struct pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; enum ethtool_c33_pse_admin_state c33_admin_state; enum ethtool_c33_pse_pw_d_status c33_pw_status; + u32 c33_pw_class; + u32 c33_actual_pw; + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; }; /** diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index e011384c915c..230110b97029 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -752,6 +752,197 @@ enum ethtool_module_power_mode { ETHTOOL_MODULE_POWER_MODE_HIGH, }; +/** + * enum ethtool_c33_pse_ext_state - groups of PSE extended states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_STATE_ERROR_CONDITION: Group of error_condition states + * @ETHTOOL_C33_PSE_EXT_STATE_MR_MPS_VALID: Group of mr_mps_valid states + * @ETHTOOL_C33_PSE_EXT_STATE_MR_PSE_ENABLE: Group of mr_pse_enable states + * @ETHTOOL_C33_PSE_EXT_STATE_OPTION_DETECT_TED: Group of option_detect_ted + * states + * @ETHTOOL_C33_PSE_EXT_STATE_OPTION_VPORT_LIM: Group of option_vport_lim states + * @ETHTOOL_C33_PSE_EXT_STATE_OVLD_DETECTED: Group of ovld_detected states + * @ETHTOOL_C33_PSE_EXT_STATE_PD_DLL_POWER_TYPE: Group of pd_dll_power_type + * states + * @ETHTOOL_C33_PSE_EXT_STATE_POWER_NOT_AVAILABLE: Group of power_not_available + * states + * @ETHTOOL_C33_PSE_EXT_STATE_SHORT_DETECTED: Group of short_detected states + */ +enum ethtool_c33_pse_ext_state { + ETHTOOL_C33_PSE_EXT_STATE_ERROR_CONDITION = 1, + ETHTOOL_C33_PSE_EXT_STATE_MR_MPS_VALID, + ETHTOOL_C33_PSE_EXT_STATE_MR_PSE_ENABLE, + ETHTOOL_C33_PSE_EXT_STATE_OPTION_DETECT_TED, + ETHTOOL_C33_PSE_EXT_STATE_OPTION_VPORT_LIM, + ETHTOOL_C33_PSE_EXT_STATE_OVLD_DETECTED, + ETHTOOL_C33_PSE_EXT_STATE_PD_DLL_POWER_TYPE, + ETHTOOL_C33_PSE_EXT_STATE_POWER_NOT_AVAILABLE, + ETHTOOL_C33_PSE_EXT_STATE_SHORT_DETECTED, +}; + +/** + * enum ethtool_c33_pse_ext_substate_mr_mps_valid - mr_mps_valid states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_DETECTED_UNDERLOAD: Underload + * state + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_CONNECTION_OPEN: Port is not + * connected + * + * The PSE monitors either the DC or AC Maintain Power Signature + * (MPS, see 33.2.9.1). This variable indicates the presence or absence of + * a valid MPS. + */ +enum ethtool_c33_pse_ext_substate_mr_mps_valid { + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_DETECTED_UNDERLOAD = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_CONNECTION_OPEN, +}; + +/** + * enum ethtool_c33_pse_ext_substate_error_condition - error_condition states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_NON_EXISTING_PORT: Non-existing + * port number + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNDEFINED_PORT: Undefined port + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_INTERNAL_HW_FAULT: Internal + * hardware fault + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_COMM_ERROR_AFTER_FORCE_ON: + * Communication error after force on + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNKNOWN_PORT_STATUS: Unknown + * port status + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_TURN_OFF: Host + * crash turn off + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_FORCE_SHUTDOWN: + * Host crash force shutdown + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_CONFIG_CHANGE: Configuration + * change + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_DETECTED_OVER_TEMP: Over + * temperature detected + * + * error_condition is a variable indicating the status of + * implementation-specific fault conditions or optionally other system faults + * that prevent the PSE from meeting the specifications in Table 33–11 and that + * require the PSE not to source power. These error conditions are different + * from those monitored by the state diagrams in Figure 33–10. + */ +enum ethtool_c33_pse_ext_substate_error_condition { + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_NON_EXISTING_PORT = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNDEFINED_PORT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_INTERNAL_HW_FAULT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_COMM_ERROR_AFTER_FORCE_ON, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNKNOWN_PORT_STATUS, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_TURN_OFF, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_FORCE_SHUTDOWN, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_CONFIG_CHANGE, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_DETECTED_OVER_TEMP, +}; + +/** + * enum ethtool_c33_pse_ext_substate_mr_pse_enable - mr_pse_enable states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_PSE_ENABLE_DISABLE_PIN_ACTIVE: Disable + * pin active + * + * mr_pse_enable is control variable that selects PSE operation and test + * functions. + */ +enum ethtool_c33_pse_ext_substate_mr_pse_enable { + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_PSE_ENABLE_DISABLE_PIN_ACTIVE = 1, +}; + +/** + * enum ethtool_c33_pse_ext_substate_option_detect_ted - option_detect_ted + * states functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_DET_IN_PROCESS: Detection + * in process + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_CONNECTION_CHECK_ERROR: + * Connection check error + * + * option_detect_ted is a variable indicating if detection can be performed + * by the PSE during the ted_timer interval. + */ +enum ethtool_c33_pse_ext_substate_option_detect_ted { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_DET_IN_PROCESS = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_CONNECTION_CHECK_ERROR, +}; + +/** + * enum ethtool_c33_pse_ext_substate_option_vport_lim - option_vport_lim states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_HIGH_VOLTAGE: Main supply + * voltage is high + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_LOW_VOLTAGE: Main supply + * voltage is low + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_VOLTAGE_INJECTION: Voltage + * injection into the port + * + * option_vport_lim is an optional variable indicates if VPSE is out of the + * operating range during normal operating state. + */ +enum ethtool_c33_pse_ext_substate_option_vport_lim { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_HIGH_VOLTAGE = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_LOW_VOLTAGE, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_VOLTAGE_INJECTION, +}; + +/** + * enum ethtool_c33_pse_ext_substate_ovld_detected - ovld_detected states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OVLD_DETECTED_OVERLOAD: Overload state + * + * ovld_detected is a variable indicating if the PSE output current has been + * in an overload condition (see 33.2.7.6) for at least TCUT of a one-second + * sliding time. + */ +enum ethtool_c33_pse_ext_substate_ovld_detected { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OVLD_DETECTED_OVERLOAD = 1, +}; + +/** + * enum ethtool_c33_pse_ext_substate_power_not_available - power_not_available + * states functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_BUDGET_EXCEEDED: Power + * budget exceeded for the controller + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PORT_PW_LIMIT_EXCEEDS_CONTROLLER_BUDGET: + * Configured port power limit exceeded controller power budget + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PD_REQUEST_EXCEEDS_PORT_LIMIT: + * Power request from PD exceeds port limit + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_HW_PW_LIMIT: Power + * denied due to Hardware power limit + * + * power_not_available is a variable that is asserted in an + * implementation-dependent manner when the PSE is no longer capable of + * sourcing sufficient power to support the attached PD. Sufficient power + * is defined by classification; see 33.2.6. + */ +enum ethtool_c33_pse_ext_substate_power_not_available { + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_BUDGET_EXCEEDED = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PORT_PW_LIMIT_EXCEEDS_CONTROLLER_BUDGET, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PD_REQUEST_EXCEEDS_PORT_LIMIT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_HW_PW_LIMIT, +}; + +/** + * enum ethtool_c33_pse_ext_substate_short_detected - short_detected states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_SHORT_DETECTED_SHORT_CONDITION: Short + * condition was detected + * + * short_detected is a variable indicating if the PSE output current has been + * in a short circuit condition for TLIM within a sliding window (see 33.2.7.7). + */ +enum ethtool_c33_pse_ext_substate_short_detected { + ETHTOOL_C33_PSE_EXT_SUBSTATE_SHORT_DETECTED_SHORT_CONDITION = 1, +}; + /** * enum ethtool_pse_types - Types of PSE controller. * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 840dabdc9d88..b8895da001bc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -939,6 +939,10 @@ enum { ETHTOOL_A_C33_PSE_ADMIN_STATE, /* u32 */ ETHTOOL_A_C33_PSE_ADMIN_CONTROL, /* u32 */ ETHTOOL_A_C33_PSE_PW_D_STATUS, /* u32 */ + ETHTOOL_A_C33_PSE_PW_CLASS, /* u32 */ + ETHTOOL_A_C33_PSE_ACTUAL_PW, /* u32 */ + ETHTOOL_A_C33_PSE_EXT_STATE, /* u32 */ + ETHTOOL_A_C33_PSE_EXT_SUBSTATE, /* u32 */ /* add new constants above here */ __ETHTOOL_A_PSE_CNT, diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 2c981d443f27..d2a1c14d789f 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -86,7 +86,16 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, len += nla_total_size(sizeof(u32)); /* _C33_PSE_ADMIN_STATE */ if (st->c33_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_D_STATUS */ - + if (st->c33_pw_class > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_CLASS */ + if (st->c33_actual_pw > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_ACTUAL_PW */ + if (st->c33_ext_state_info.c33_pse_ext_state > 0) { + len += nla_total_size(sizeof(u32)); /* _C33_PSE_EXT_STATE */ + if (st->c33_ext_state_info.__c33_pse_ext_substate > 0) + /* _C33_PSE_EXT_SUBSTATE */ + len += nla_total_size(sizeof(u32)); + } return len; } @@ -117,6 +126,27 @@ static int pse_fill_reply(struct sk_buff *skb, st->c33_pw_status)) return -EMSGSIZE; + if (st->c33_pw_class > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_CLASS, + st->c33_pw_class)) + return -EMSGSIZE; + + if (st->c33_actual_pw > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_ACTUAL_PW, + st->c33_actual_pw)) + return -EMSGSIZE; + + if (st->c33_ext_state_info.c33_pse_ext_state > 0) { + if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_STATE, + st->c33_ext_state_info.c33_pse_ext_state)) + return -EMSGSIZE; + + if (st->c33_ext_state_info.__c33_pse_ext_substate > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_SUBSTATE, + st->c33_ext_state_info.__c33_pse_ext_substate)) + return -EMSGSIZE; + } + return 0; } -- cgit v1.2.3 From 30d7b6727724ce3729f2cb5b8be985d2d1931d2b Mon Sep 17 00:00:00 2001 From: "Kory Maincent (Dent Project)" Date: Thu, 4 Jul 2024 10:12:00 +0200 Subject: net: ethtool: Add new power limit get and set features This patch expands the status information provided by ethtool for PSE c33 with available power limit and available power limit ranges. It also adds a call to pse_ethtool_set_pw_limit() to configure the PSE control power limit. Reviewed-by: Oleksij Rempel Signed-off-by: Kory Maincent Link: https://patch.msgid.link/20240704-feature_poe_power_cap-v6-5-320003204264@bootlin.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 64 ++++++++++++++------ include/linux/ethtool.h | 5 ++ include/uapi/linux/ethtool_netlink.h | 8 +++ net/ethtool/pse-pd.c | 89 +++++++++++++++++++++++++--- 4 files changed, 141 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 0656ad4be000..3ab423b80e91 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1730,24 +1730,28 @@ Request contents: Kernel response contents: - ====================================== ====== ============================= - ``ETHTOOL_A_PSE_HEADER`` nested reply header - ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` u32 Operational state of the PoDL - PSE functions - ``ETHTOOL_A_PODL_PSE_PW_D_STATUS`` u32 power detection status of the - PoDL PSE. - ``ETHTOOL_A_C33_PSE_ADMIN_STATE`` u32 Operational state of the PoE - PSE functions. - ``ETHTOOL_A_C33_PSE_PW_D_STATUS`` u32 power detection status of the - PoE PSE. - ``ETHTOOL_A_C33_PSE_PW_CLASS`` u32 power class of the PoE PSE. - ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` u32 actual power drawn on the - PoE PSE. - ``ETHTOOL_A_C33_PSE_EXT_STATE`` u32 power extended state of the - PoE PSE. - ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` u32 power extended substatus of - the PoE PSE. - ====================================== ====== ============================= + ========================================== ====== ============================= + ``ETHTOOL_A_PSE_HEADER`` nested reply header + ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` u32 Operational state of the PoDL + PSE functions + ``ETHTOOL_A_PODL_PSE_PW_D_STATUS`` u32 power detection status of the + PoDL PSE. + ``ETHTOOL_A_C33_PSE_ADMIN_STATE`` u32 Operational state of the PoE + PSE functions. + ``ETHTOOL_A_C33_PSE_PW_D_STATUS`` u32 power detection status of the + PoE PSE. + ``ETHTOOL_A_C33_PSE_PW_CLASS`` u32 power class of the PoE PSE. + ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` u32 actual power drawn on the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_STATE`` u32 power extended state of the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` u32 power extended substatus of + the PoE PSE. + ``ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT`` u32 currently configured power + limit of the PoE PSE. + ``ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES`` nested Supported power limit + configuration ranges. + ========================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies the operational state of the PoDL PSE functions. The operational state of the @@ -1809,6 +1813,16 @@ Possible values are: ethtool_c33_pse_ext_substate_power_not_available ethtool_c33_pse_ext_substate_short_detected +When set, the optional ``ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT`` attribute +identifies the C33 PSE power limit in mW. + +When set the optional ``ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES`` nested attribute +identifies the C33 PSE power limit ranges through +``ETHTOOL_A_C33_PSE_PWR_VAL_LIMIT_RANGE_MIN`` and +``ETHTOOL_A_C33_PSE_PWR_VAL_LIMIT_RANGE_MAX``. +If the controller works with fixed classes, the min and max values will be +equal. + PSE_SET ======= @@ -1820,6 +1834,8 @@ Request contents: ``ETHTOOL_A_PSE_HEADER`` nested request header ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL`` u32 Control PoDL PSE Admin state ``ETHTOOL_A_C33_PSE_ADMIN_CONTROL`` u32 Control PSE Admin state + ``ETHTOOL_A_C33_PSE_AVAIL_PWR_LIMIT`` u32 Control PoE PSE available + power limit ====================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL`` attribute is used @@ -1830,6 +1846,18 @@ to control PoDL PSE Admin functions. This option is implementing The same goes for ``ETHTOOL_A_C33_PSE_ADMIN_CONTROL`` implementing ``IEEE 802.3-2022`` 30.9.1.2.1 acPSEAdminControl. +When set, the optional ``ETHTOOL_A_C33_PSE_AVAIL_PWR_LIMIT`` attribute is +used to control the available power value limit for C33 PSE in milliwatts. +This attribute corresponds to the `pse_available_power` variable described in +``IEEE 802.3-2022`` 33.2.4.4 Variables and `pse_avail_pwr` in 145.2.5.4 +Variables, which are described in power classes. + +It was decided to use milliwatts for this interface to unify it with other +power monitoring interfaces, which also use milliwatts, and to align with +various existing products that document power consumption in watts rather than +classes. If power limit configuration based on classes is needed, the +conversion can be done in user space, for example by ethtool. + RSS_GET ======= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 3e70f5d9e0bb..e213b5508da6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1288,4 +1288,9 @@ struct ethtool_c33_pse_ext_state_info { u32 __c33_pse_ext_substate; }; }; + +struct ethtool_c33_pse_pw_limit_range { + u32 min; + u32 max; +}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b8895da001bc..6d5bdcc67631 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -930,6 +930,12 @@ enum { }; /* Power Sourcing Equipment */ +enum { + ETHTOOL_A_C33_PSE_PW_LIMIT_UNSPEC, + ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, /* u32 */ + ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, /* u32 */ +}; + enum { ETHTOOL_A_PSE_UNSPEC, ETHTOOL_A_PSE_HEADER, /* nest - _A_HEADER_* */ @@ -943,6 +949,8 @@ enum { ETHTOOL_A_C33_PSE_ACTUAL_PW, /* u32 */ ETHTOOL_A_C33_PSE_EXT_STATE, /* u32 */ ETHTOOL_A_C33_PSE_EXT_SUBSTATE, /* u32 */ + ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, /* u32 */ + ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES, /* nest - _C33_PSE_PW_LIMIT_* */ /* add new constants above here */ __ETHTOOL_A_PSE_CNT, diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index d2a1c14d789f..ba46c9c8b12d 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -96,9 +96,46 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, /* _C33_PSE_EXT_SUBSTATE */ len += nla_total_size(sizeof(u32)); } + if (st->c33_avail_pw_limit > 0) + /* _C33_AVAIL_PSE_PW_LIMIT */ + len += nla_total_size(sizeof(u32)); + if (st->c33_pw_limit_nb_ranges > 0) + /* _C33_PSE_PW_LIMIT_RANGES */ + len += st->c33_pw_limit_nb_ranges * + (nla_total_size(0) + + nla_total_size(sizeof(u32)) * 2); + return len; } +static int pse_put_pw_limit_ranges(struct sk_buff *skb, + const struct pse_control_status *st) +{ + const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; + int i; + + pw_limit_ranges = st->c33_pw_limit_ranges; + for (i = 0; i < st->c33_pw_limit_nb_ranges; i++) { + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, + pw_limit_ranges->min) || + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, + pw_limit_ranges->max)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + nla_nest_end(skb, nest); + pw_limit_ranges++; + } + + return 0; +} + static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) @@ -147,9 +184,25 @@ static int pse_fill_reply(struct sk_buff *skb, return -EMSGSIZE; } + if (st->c33_avail_pw_limit > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, + st->c33_avail_pw_limit)) + return -EMSGSIZE; + + if (st->c33_pw_limit_nb_ranges > 0 && + pse_put_pw_limit_ranges(skb, st)) + return -EMSGSIZE; + return 0; } +static void pse_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct pse_reply_data *data = PSE_REPDATA(reply_base); + + kfree(data->status.c33_pw_limit_ranges); +} + /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { @@ -160,6 +213,7 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { [ETHTOOL_A_C33_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), + [ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT] = { .type = NLA_U32 }, }; static int @@ -202,19 +256,39 @@ static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; - struct pse_control_config config = {}; struct nlattr **tb = info->attrs; struct phy_device *phydev; + int ret = 0; phydev = dev->phydev; + + if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { + unsigned int pw_limit; + + pw_limit = nla_get_u32(tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]); + ret = pse_ethtool_set_pw_limit(phydev->psec, info->extack, + pw_limit); + if (ret) + return ret; + } + /* These values are already validated by the ethnl_pse_set_policy */ - if (pse_has_podl(phydev->psec)) - config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); - if (pse_has_c33(phydev->psec)) - config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] || + tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) { + struct pse_control_config config = {}; + + if (pse_has_podl(phydev->psec)) + config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); + if (pse_has_c33(phydev->psec)) + config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + + ret = pse_ethtool_set_config(phydev->psec, info->extack, + &config); + if (ret) + return ret; + } - /* Return errno directly - PSE has no notification */ - return pse_ethtool_set_config(phydev->psec, info->extack, &config); + return ret; } const struct ethnl_request_ops ethnl_pse_request_ops = { @@ -227,6 +301,7 @@ const struct ethnl_request_ops ethnl_pse_request_ops = { .prepare_data = pse_prepare_data, .reply_size = pse_reply_size, .fill_reply = pse_fill_reply, + .cleanup_data = pse_cleanup_data, .set_validate = ethnl_set_pse_validate, .set = ethnl_set_pse, -- cgit v1.2.3 From 6a68aed602d7b770552c7f890d0c30c53725c7b8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Jun 2024 21:21:21 -0400 Subject: NFSv4: Add new attribute delegation definitions Add the attribute delegation XDR definitions from the spec. Signed-off-by: Tom Haynes Signed-off-by: Trond Myklebust Signed-off-by: Lance Shelton Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 2 +- include/linux/nfs4.h | 9 +++++++++ include/uapi/linux/nfs4.h | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7f294085e887..90df37f3866a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3852,7 +3852,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL) #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) -#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_XATTR_SUPPORT - 1UL) +#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_TIME_DELEG_MODIFY - 1UL) static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 0d896ce296ce..c074e0ac390f 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -367,6 +367,8 @@ enum open_delegation_type4 { NFS4_OPEN_DELEGATE_READ = 1, NFS4_OPEN_DELEGATE_WRITE = 2, NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */ + NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5, }; enum why_no_delegation4 { /* new to v4.1 */ @@ -507,6 +509,11 @@ enum { FATTR4_XATTR_SUPPORT = 82, }; +enum { + FATTR4_TIME_DELEG_ACCESS = 84, + FATTR4_TIME_DELEG_MODIFY = 85, +}; + /* * The following internal definitions enable processing the above * attribute bits within 32-bit word boundaries. @@ -586,6 +593,8 @@ enum { #define FATTR4_WORD2_SECURITY_LABEL BIT(FATTR4_SEC_LABEL - 64) #define FATTR4_WORD2_MODE_UMASK BIT(FATTR4_MODE_UMASK - 64) #define FATTR4_WORD2_XATTR_SUPPORT BIT(FATTR4_XATTR_SUPPORT - 64) +#define FATTR4_WORD2_TIME_DELEG_ACCESS BIT(FATTR4_TIME_DELEG_ACCESS - 64) +#define FATTR4_WORD2_TIME_DELEG_MODIFY BIT(FATTR4_TIME_DELEG_MODIFY - 64) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 1d2043708bf1..afd7e32906c3 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -69,6 +69,8 @@ #define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL 0x10000 #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 +#define NFS4_SHARE_WANT_DELEG_TIMESTAMPS 0x100000 + #define NFS4_CDFC4_FORE 0x1 #define NFS4_CDFC4_BACK 0x2 #define NFS4_CDFC4_BOTH 0x3 -- cgit v1.2.3 From d2a00cceb93a4df2afaceb836297628d0aeec7ad Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Jun 2024 21:21:33 -0400 Subject: NFSv4: Detect support for OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION If the server supports the NFSv4.2 protocol extension to optimise away returning a stateid when it returns a delegation, then we cache that information in another capability flag. Signed-off-by: Trond Myklebust Signed-off-by: Lance Shelton Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 4 ++++ include/linux/nfs_fs_sb.h | 1 + include/uapi/linux/nfs4.h | 2 ++ 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ae91492e9521..adf4fc8610f6 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3990,6 +3990,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f sizeof(server->attr_bitmask)); server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (res.open_caps.oa_share_access_want[0] & + NFS4_SHARE_WANT_OPEN_XOR_DELEGATION) + server->caps |= NFS_CAP_OPEN_XOR; + memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask)); server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE; server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 5a76a87cd924..fe5b1a8bd723 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -278,6 +278,7 @@ struct nfs_server { #define NFS_CAP_LGOPEN (1U << 5) #define NFS_CAP_CASE_INSENSITIVE (1U << 6) #define NFS_CAP_CASE_PRESERVING (1U << 7) +#define NFS_CAP_OPEN_XOR (1U << 12) #define NFS_CAP_DELEGTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index afd7e32906c3..caf4db2fcbb9 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -46,6 +46,7 @@ #define NFS4_OPEN_RESULT_CONFIRM 0x0002 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 #define NFS4_OPEN_RESULT_PRESERVE_UNLINKED 0x0008 +#define NFS4_OPEN_RESULT_NO_OPEN_STATEID 0x0010 #define NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK 0x0020 #define NFS4_SHARE_ACCESS_MASK 0x000F @@ -70,6 +71,7 @@ #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 #define NFS4_SHARE_WANT_DELEG_TIMESTAMPS 0x100000 +#define NFS4_SHARE_WANT_OPEN_XOR_DELEGATION 0x200000 #define NFS4_CDFC4_FORE 0x1 #define NFS4_CDFC4_BACK 0x2 -- cgit v1.2.3 From 00506072d70829196849e835ee4ef0b350b61fb9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 14 Jun 2024 08:59:10 -0400 Subject: nfsd: new netlink ops to get/set server pool_mode Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 27 +++++++++++++++++ fs/nfsd/netlink.c | 17 +++++++++++ fs/nfsd/netlink.h | 2 ++ fs/nfsd/nfsctl.c | 57 +++++++++++++++++++++++++++++++++++ include/uapi/linux/nfsd_netlink.h | 10 ++++++ 5 files changed, 113 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 6bda7a467301..c87658114852 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -115,6 +115,15 @@ attribute-sets: type: nest nested-attributes: sock multi-attr: true + - + name: pool-mode + attributes: + - + name: mode + type: string + - + name: npools + type: u32 operations: list: @@ -195,3 +204,21 @@ operations: reply: attributes: - addr + - + name: pool-mode-set + doc: set the current server pool-mode + attribute-set: pool-mode + flags: [ admin-perm ] + do: + request: + attributes: + - mode + - + name: pool-mode-get + doc: get info about server pool-mode + attribute-set: pool-mode + do: + reply: + attributes: + - mode + - npools diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 529a75ecf22e..ca54aa583530 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -40,6 +40,11 @@ static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_AD [NFSD_A_SERVER_SOCK_ADDR] = NLA_POLICY_NESTED(nfsd_sock_nl_policy), }; +/* NFSD_CMD_POOL_MODE_SET - do */ +static const struct nla_policy nfsd_pool_mode_set_nl_policy[NFSD_A_POOL_MODE_MODE + 1] = { + [NFSD_A_POOL_MODE_MODE] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -83,6 +88,18 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .doit = nfsd_nl_listener_get_doit, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_POOL_MODE_SET, + .doit = nfsd_nl_pool_mode_set_doit, + .policy = nfsd_pool_mode_set_nl_policy, + .maxattr = NFSD_A_POOL_MODE_MODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_POOL_MODE_GET, + .doit = nfsd_nl_pool_mode_get_doit, + .flags = GENL_CMD_CAP_DO, + }, }; struct genl_family nfsd_nl_family __ro_after_init = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 2e132ef328f8..8eb903f24c41 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -23,6 +23,8 @@ int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info); extern struct genl_family nfsd_nl_family; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3da7e4b3e2c3..9e0ea6fc2aa3 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2156,6 +2156,63 @@ err_free_msg: return err; } +/** + * nfsd_nl_pool_mode_set_doit - set the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + const struct nlattr *attr; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_POOL_MODE_MODE)) + return -EINVAL; + + attr = info->attrs[NFSD_A_POOL_MODE_MODE]; + return sunrpc_set_pool_mode(nla_data(attr)); +} + +/** + * nfsd_nl_pool_mode_get_doit - get info about pool_mode + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + char buf[16]; + void *hdr; + int err; + + if (sunrpc_get_pool_mode(buf, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) + return -ERANGE; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_iput(skb, info); + if (!hdr) + goto err_free_msg; + + err = nla_put_string(skb, NFSD_A_POOL_MODE_MODE, buf) | + nla_put_u32(skb, NFSD_A_POOL_MODE_NPOOLS, nfsd_nrpools(net)); + if (err) + goto err_free_msg; + + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, info); + +err_free_msg: + nlmsg_free(skb); + return err; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 24c86dbc7ed5..887cbd12b695 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -70,6 +70,14 @@ enum { NFSD_A_SERVER_SOCK_MAX = (__NFSD_A_SERVER_SOCK_MAX - 1) }; +enum { + NFSD_A_POOL_MODE_MODE = 1, + NFSD_A_POOL_MODE_NPOOLS, + + __NFSD_A_POOL_MODE_MAX, + NFSD_A_POOL_MODE_MAX = (__NFSD_A_POOL_MODE_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -78,6 +86,8 @@ enum { NFSD_CMD_VERSION_GET, NFSD_CMD_LISTENER_SET, NFSD_CMD_LISTENER_GET, + NFSD_CMD_POOL_MODE_SET, + NFSD_CMD_POOL_MODE_GET, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.2.3 From e6c06ca8f21d1cdb444c708e385d86a54bc5fc60 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 9 Jul 2024 10:38:30 +0200 Subject: wifi: cfg80211: add support for advertising multiple radios belonging to a wiphy The prerequisite for MLO support in cfg80211/mac80211 is that all the links participating in MLO must be from the same wiphy/ieee80211_hw. To meet this expectation, some drivers may need to group multiple discrete hardware each acting as a link in MLO under single wiphy. With this change, supported frequencies and interface combinations of each individual radio are reported to user space. This allows user space to figure out the limitations of what combination of channels can be used concurrently. Even for non-MLO devices, this improves support for devices capable of running on multiple channels at the same time. Signed-off-by: Felix Fietkau Link: https://patch.msgid.link/18a88f9ce82b1c9f7c12f1672430eaf2bb0be295.1720514221.git-series.nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 42 +++++++++++++++- include/uapi/linux/nl80211.h | 65 +++++++++++++++++++++++++ net/wireless/nl80211.c | 113 ++++++++++++++++++++++++++++++++++++++----- 3 files changed, 208 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6f992aff74ae..a00cf80e61dc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5046,7 +5046,9 @@ struct ieee80211_iface_limit { * struct ieee80211_iface_combination - possible interface combination * * With this structure the driver can describe which interface - * combinations it supports concurrently. + * combinations it supports concurrently. When set in a struct wiphy_radio, + * the combinations refer to combinations of interfaces currently active on + * that radio. * * Examples: * @@ -5406,6 +5408,38 @@ struct wiphy_iftype_akm_suites { int n_akm_suites; }; +/** + * struct wiphy_radio_freq_range - wiphy frequency range + * @start_freq: start range edge frequency (kHz) + * @end_freq: end range edge frequency (kHz) + */ +struct wiphy_radio_freq_range { + u32 start_freq; + u32 end_freq; +}; + + +/** + * struct wiphy_radio - physical radio of a wiphy + * This structure describes a physical radio belonging to a wiphy. + * It is used to describe concurrent-channel capabilities. Only one channel + * can be active on the radio described by struct wiphy_radio. + * + * @freq_range: frequency range that the radio can operate on. + * @n_freq_range: number of elements in @freq_range + * + * @iface_combinations: Valid interface combinations array, should not + * list single interface types. + * @n_iface_combinations: number of entries in @iface_combinations array. + */ +struct wiphy_radio { + const struct wiphy_radio_freq_range *freq_range; + int n_freq_range; + + const struct ieee80211_iface_combination *iface_combinations; + int n_iface_combinations; +}; + #define CFG80211_HW_TIMESTAMP_ALL_PEERS 0xffff /** @@ -5624,6 +5658,9 @@ struct wiphy_iftype_akm_suites { * A value of %CFG80211_HW_TIMESTAMP_ALL_PEERS indicates the driver * supports enabling HW timestamping for all peers (i.e. no need to * specify a mac address). + * + * @radio: radios belonging to this wiphy + * @n_radio: number of radios */ struct wiphy { struct mutex mtx; @@ -5774,6 +5811,9 @@ struct wiphy { u16 hw_timestamp_max_peers; + int n_radio; + const struct wiphy_radio *radio; + char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6ae3997061b6..f97f5adc8d51 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2052,6 +2052,10 @@ enum nl80211_commands { * @NL80211_ATTR_INTERFACE_COMBINATIONS: Nested attribute listing the supported * interface combinations. In each nested item, it contains attributes * defined in &enum nl80211_if_combination_attrs. + * If the wiphy uses multiple radios (@NL80211_ATTR_WIPHY_RADIOS is set), + * this attribute contains the interface combinations of the first radio. + * See @NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS for the global wiphy + * combinations for the sum of all radios. * @NL80211_ATTR_SOFTWARE_IFTYPES: Nested attribute (just like * %NL80211_ATTR_SUPPORTED_IFTYPES) containing the interface types that * are managed in software: interfaces of these types aren't subject to @@ -2856,6 +2860,14 @@ enum nl80211_commands { * %NL80211_CMD_ASSOCIATE indicating the SPP A-MSDUs * are used on this connection * + * @NL80211_ATTR_WIPHY_RADIOS: Nested attribute describing physical radios + * belonging to this wiphy. See &enum nl80211_wiphy_radio_attrs. + * + * @NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS: Nested attribute listing the + * supported interface combinations for all radios combined. In each + * nested item, it contains attributes defined in + * &enum nl80211_if_combination_attrs. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3401,6 +3413,9 @@ enum nl80211_attrs { NL80211_ATTR_ASSOC_SPP_AMSDU, + NL80211_ATTR_WIPHY_RADIOS, + NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -8005,4 +8020,54 @@ enum nl80211_ap_settings_flags { NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT = 1 << 1, }; +/** + * enum nl80211_wiphy_radio_attrs - wiphy radio attributes + * + * @__NL80211_WIPHY_RADIO_ATTR_INVALID: Invalid + * + * @NL80211_WIPHY_RADIO_ATTR_INDEX: Index of this radio (u32) + * @NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE: Frequency range supported by this + * radio. Attribute may be present multiple times. + * @NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION: Supported interface + * combination for this radio. Attribute may be present multiple times + * and contains attributes defined in &enum nl80211_if_combination_attrs. + * + * @__NL80211_WIPHY_RADIO_ATTR_LAST: Internal + * @NL80211_WIPHY_RADIO_ATTR_MAX: Highest attribute + */ +enum nl80211_wiphy_radio_attrs { + __NL80211_WIPHY_RADIO_ATTR_INVALID, + + NL80211_WIPHY_RADIO_ATTR_INDEX, + NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE, + NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION, + + /* keep last */ + __NL80211_WIPHY_RADIO_ATTR_LAST, + NL80211_WIPHY_RADIO_ATTR_MAX = __NL80211_WIPHY_RADIO_ATTR_LAST - 1, +}; + +/** + * enum nl80211_wiphy_radio_freq_range - wiphy radio frequency range + * + * @__NL80211_WIPHY_RADIO_FREQ_ATTR_INVALID: Invalid + * + * @NL80211_WIPHY_RADIO_FREQ_ATTR_START: Frequency range start (u32). + * The unit is kHz. + * @NL80211_WIPHY_RADIO_FREQ_ATTR_END: Frequency range end (u32). + * The unit is kHz. + * + * @__NL80211_WIPHY_RADIO_FREQ_ATTR_LAST: Internal + * @NL80211_WIPHY_RADIO_FREQ_ATTR_MAX: Highest attribute + */ +enum nl80211_wiphy_radio_freq_range { + __NL80211_WIPHY_RADIO_FREQ_ATTR_INVALID, + + NL80211_WIPHY_RADIO_FREQ_ATTR_START, + NL80211_WIPHY_RADIO_FREQ_ATTR_END, + + __NL80211_WIPHY_RADIO_FREQ_ATTR_LAST, + NL80211_WIPHY_RADIO_FREQ_ATTR_MAX = __NL80211_WIPHY_RADIO_FREQ_ATTR_LAST - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index deacd5f3f256..7397a372c78e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1632,16 +1632,18 @@ nla_put_failure: } static int nl80211_put_ifcomb_data(struct sk_buff *msg, bool large, int idx, - const struct ieee80211_iface_combination *c) + const struct ieee80211_iface_combination *c, + u16 nested) { struct nlattr *nl_combi, *nl_limits; int i; - nl_combi = nla_nest_start_noflag(msg, idx); + nl_combi = nla_nest_start_noflag(msg, idx | nested); if (!nl_combi) goto nla_put_failure; - nl_limits = nla_nest_start_noflag(msg, NL80211_IFACE_COMB_LIMITS); + nl_limits = nla_nest_start_noflag(msg, NL80211_IFACE_COMB_LIMITS | + nested); if (!nl_limits) goto nla_put_failure; @@ -1689,19 +1691,26 @@ nla_put_failure: static int nl80211_put_iface_combinations(struct wiphy *wiphy, struct sk_buff *msg, - bool large) + int attr, int radio, + bool large, u16 nested) { + const struct ieee80211_iface_combination *c; struct nlattr *nl_combis; - int i; + int i, n; - nl_combis = nla_nest_start_noflag(msg, - NL80211_ATTR_INTERFACE_COMBINATIONS); + nl_combis = nla_nest_start_noflag(msg, attr | nested); if (!nl_combis) goto nla_put_failure; - for (i = 0; i < wiphy->n_iface_combinations; i++) - if (nl80211_put_ifcomb_data(msg, large, i + 1, - &wiphy->iface_combinations[i])) + if (radio >= 0) { + c = wiphy->radio[0].iface_combinations; + n = wiphy->radio[0].n_iface_combinations; + } else { + c = wiphy->iface_combinations; + n = wiphy->n_iface_combinations; + } + for (i = 0; i < n; i++) + if (nl80211_put_ifcomb_data(msg, large, i + 1, &c[i], nested)) goto nla_put_failure; nla_nest_end(msg, nl_combis); @@ -2408,6 +2417,80 @@ fail: return -ENOBUFS; } +static int nl80211_put_radio(struct wiphy *wiphy, struct sk_buff *msg, int idx) +{ + const struct wiphy_radio *r = &wiphy->radio[idx]; + struct nlattr *radio, *freq; + int i; + + radio = nla_nest_start(msg, idx); + if (!radio) + return -ENOBUFS; + + if (nla_put_u32(msg, NL80211_WIPHY_RADIO_ATTR_INDEX, idx)) + goto nla_put_failure; + + for (i = 0; i < r->n_freq_range; i++) { + const struct wiphy_radio_freq_range *range = &r->freq_range[i]; + + freq = nla_nest_start(msg, NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE); + if (!freq) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_WIPHY_RADIO_FREQ_ATTR_START, + range->start_freq) || + nla_put_u32(msg, NL80211_WIPHY_RADIO_FREQ_ATTR_END, + range->end_freq)) + goto nla_put_failure; + + nla_nest_end(msg, freq); + } + + for (i = 0; i < r->n_iface_combinations; i++) + if (nl80211_put_ifcomb_data(msg, true, + NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION, + &r->iface_combinations[i], + NLA_F_NESTED)) + goto nla_put_failure; + + nla_nest_end(msg, radio); + + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +static int nl80211_put_radios(struct wiphy *wiphy, struct sk_buff *msg) +{ + struct nlattr *radios; + int i; + + if (!wiphy->n_radio) + return 0; + + radios = nla_nest_start(msg, NL80211_ATTR_WIPHY_RADIOS); + if (!radios) + return -ENOBUFS; + + for (i = 0; i < wiphy->n_radio; i++) + if (nl80211_put_radio(wiphy, msg, i)) + goto fail; + + nla_nest_end(msg, radios); + + if (nl80211_put_iface_combinations(wiphy, msg, + NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS, + -1, true, NLA_F_NESTED)) + return -ENOBUFS; + + return 0; + +fail: + nla_nest_cancel(msg, radios); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2703,7 +2786,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; if (nl80211_put_iface_combinations(&rdev->wiphy, msg, - state->split)) + NL80211_ATTR_INTERFACE_COMBINATIONS, + rdev->wiphy.n_radio ? 0 : -1, + state->split, 0)) goto nla_put_failure; state->split_start++; @@ -3017,6 +3102,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.hw_timestamp_max_peers)) goto nla_put_failure; + state->split_start++; + break; + case 17: + if (nl80211_put_radios(&rdev->wiphy, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; -- cgit v1.2.3 From c714f15860fcca02fe0fd7c3f1f1fc35b1768ac1 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 2 Jul 2024 14:34:39 +0800 Subject: iommufd: Add fault and response message definitions iommu_hwpt_pgfaults represent fault messages that the userspace can retrieve. Multiple iommu_hwpt_pgfaults might be put in an iopf group, with the IOMMU_PGFAULT_FLAGS_LAST_PAGE flag set only for the last iommu_hwpt_pgfault. An iommu_hwpt_page_response is a response message that the userspace should send to the kernel after finishing handling a group of fault messages. The @dev_id, @pasid, and @grpid fields in the message identify an outstanding iopf group for a device. The @cookie field, which matches the cookie field of the last fault in the group, will be used by the kernel to look up the pending message. Link: https://lore.kernel.org/r/20240702063444.105814-6-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 83 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 1dfeaa2e649e..4d89ed97b533 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -692,4 +692,87 @@ struct iommu_hwpt_invalidate { __u32 __reserved; }; #define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE) + +/** + * enum iommu_hwpt_pgfault_flags - flags for struct iommu_hwpt_pgfault + * @IOMMU_PGFAULT_FLAGS_PASID_VALID: The pasid field of the fault data is + * valid. + * @IOMMU_PGFAULT_FLAGS_LAST_PAGE: It's the last fault of a fault group. + */ +enum iommu_hwpt_pgfault_flags { + IOMMU_PGFAULT_FLAGS_PASID_VALID = (1 << 0), + IOMMU_PGFAULT_FLAGS_LAST_PAGE = (1 << 1), +}; + +/** + * enum iommu_hwpt_pgfault_perm - perm bits for struct iommu_hwpt_pgfault + * @IOMMU_PGFAULT_PERM_READ: request for read permission + * @IOMMU_PGFAULT_PERM_WRITE: request for write permission + * @IOMMU_PGFAULT_PERM_EXEC: (PCIE 10.4.1) request with a PASID that has the + * Execute Requested bit set in PASID TLP Prefix. + * @IOMMU_PGFAULT_PERM_PRIV: (PCIE 10.4.1) request with a PASID that has the + * Privileged Mode Requested bit set in PASID TLP + * Prefix. + */ +enum iommu_hwpt_pgfault_perm { + IOMMU_PGFAULT_PERM_READ = (1 << 0), + IOMMU_PGFAULT_PERM_WRITE = (1 << 1), + IOMMU_PGFAULT_PERM_EXEC = (1 << 2), + IOMMU_PGFAULT_PERM_PRIV = (1 << 3), +}; + +/** + * struct iommu_hwpt_pgfault - iommu page fault data + * @flags: Combination of enum iommu_hwpt_pgfault_flags + * @dev_id: id of the originated device + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @perm: Combination of enum iommu_hwpt_pgfault_perm + * @addr: Fault address + * @length: a hint of how much data the requestor is expecting to fetch. For + * example, if the PRI initiator knows it is going to do a 10MB + * transfer, it could fill in 10MB and the OS could pre-fault in + * 10MB of IOVA. It's default to 0 if there's no such hint. + * @cookie: kernel-managed cookie identifying a group of fault messages. The + * cookie number encoded in the last page fault of the group should + * be echoed back in the response message. + */ +struct iommu_hwpt_pgfault { + __u32 flags; + __u32 dev_id; + __u32 pasid; + __u32 grpid; + __u32 perm; + __u64 addr; + __u32 length; + __u32 cookie; +}; + +/** + * enum iommufd_page_response_code - Return status of fault handlers + * @IOMMUFD_PAGE_RESP_SUCCESS: Fault has been handled and the page tables + * populated, retry the access. This is the + * "Success" defined in PCI 10.4.2.1. + * @IOMMUFD_PAGE_RESP_INVALID: Could not handle this fault, don't retry the + * access. This is the "Invalid Request" in PCI + * 10.4.2.1. + * @IOMMUFD_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from + * this device if possible. This is the "Response + * Failure" in PCI 10.4.2.1. + */ +enum iommufd_page_response_code { + IOMMUFD_PAGE_RESP_SUCCESS = 0, + IOMMUFD_PAGE_RESP_INVALID, + IOMMUFD_PAGE_RESP_FAILURE, +}; + +/** + * struct iommu_hwpt_page_response - IOMMU page fault response + * @cookie: The kernel-managed cookie reported in the fault message. + * @code: One of response code in enum iommufd_page_response_code. + */ +struct iommu_hwpt_page_response { + __u32 cookie; + __u32 code; +}; #endif -- cgit v1.2.3 From 07838f7fd529c8a6de44b601d4b7057e6c8d36ed Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 2 Jul 2024 14:34:40 +0800 Subject: iommufd: Add iommufd fault object An iommufd fault object provides an interface for delivering I/O page faults to user space. These objects are created and destroyed by user space, and they can be associated with or dissociated from hardware page table objects during page table allocation or destruction. User space interacts with the fault object through a file interface. This interface offers a straightforward and efficient way for user space to handle page faults. It allows user space to read fault messages sequentially and respond to them by writing to the same file. The file interface supports reading messages in poll mode, so it's recommended that user space applications use io_uring to enhance read and write efficiency. A fault object can be associated with any iopf-capable iommufd_hw_pgtable during the pgtable's allocation. All I/O page faults triggered by devices when accessing the I/O addresses of an iommufd_hw_pgtable are routed through the fault object to user space. Similarly, user space's responses to these page faults are routed back to the iommu device driver through the same fault object. Link: https://lore.kernel.org/r/20240702063444.105814-7-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/io-pgfault.c | 2 + drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/fault.c | 226 ++++++++++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 30 +++++ drivers/iommu/iommufd/main.c | 6 + include/linux/iommu.h | 4 + include/uapi/linux/iommufd.h | 18 +++ 7 files changed, 287 insertions(+) create mode 100644 drivers/iommu/iommufd/fault.c (limited to 'include/uapi/linux') diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 7c9011992d3f..cd679c13752e 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -110,6 +110,8 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, list_add(&group->pending_node, &iopf_param->faults); mutex_unlock(&iopf_param->lock); + group->fault_count = list_count_nodes(&group->faults); + return group; } diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index 34b446146961..cf4605962bea 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ device.o \ + fault.o \ hw_pagetable.o \ io_pagetable.o \ ioas.o \ diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c new file mode 100644 index 000000000000..68ff94671d48 --- /dev/null +++ b/drivers/iommu/iommufd/fault.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024 Intel Corporation + */ +#define pr_fmt(fmt) "iommufd: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../iommu-priv.h" +#include "iommufd_private.h" + +void iommufd_fault_destroy(struct iommufd_object *obj) +{ + struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj); + struct iopf_group *group, *next; + + /* + * The iommufd object's reference count is zero at this point. + * We can be confident that no other threads are currently + * accessing this pointer. Therefore, acquiring the mutex here + * is unnecessary. + */ + list_for_each_entry_safe(group, next, &fault->deliver, node) { + list_del(&group->node); + iopf_group_response(group, IOMMU_PAGE_RESP_INVALID); + iopf_free_group(group); + } +} + +static void iommufd_compose_fault_message(struct iommu_fault *fault, + struct iommu_hwpt_pgfault *hwpt_fault, + struct iommufd_device *idev, + u32 cookie) +{ + hwpt_fault->flags = fault->prm.flags; + hwpt_fault->dev_id = idev->obj.id; + hwpt_fault->pasid = fault->prm.pasid; + hwpt_fault->grpid = fault->prm.grpid; + hwpt_fault->perm = fault->prm.perm; + hwpt_fault->addr = fault->prm.addr; + hwpt_fault->length = 0; + hwpt_fault->cookie = cookie; +} + +static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf, + size_t count, loff_t *ppos) +{ + size_t fault_size = sizeof(struct iommu_hwpt_pgfault); + struct iommufd_fault *fault = filep->private_data; + struct iommu_hwpt_pgfault data; + struct iommufd_device *idev; + struct iopf_group *group; + struct iopf_fault *iopf; + size_t done = 0; + int rc = 0; + + if (*ppos || count % fault_size) + return -ESPIPE; + + mutex_lock(&fault->mutex); + while (!list_empty(&fault->deliver) && count > done) { + group = list_first_entry(&fault->deliver, + struct iopf_group, node); + + if (group->fault_count * fault_size > count - done) + break; + + rc = xa_alloc(&fault->response, &group->cookie, group, + xa_limit_32b, GFP_KERNEL); + if (rc) + break; + + idev = to_iommufd_handle(group->attach_handle)->idev; + list_for_each_entry(iopf, &group->faults, list) { + iommufd_compose_fault_message(&iopf->fault, + &data, idev, + group->cookie); + if (copy_to_user(buf + done, &data, fault_size)) { + xa_erase(&fault->response, group->cookie); + rc = -EFAULT; + break; + } + done += fault_size; + } + + list_del(&group->node); + } + mutex_unlock(&fault->mutex); + + return done == 0 ? rc : done; +} + +static ssize_t iommufd_fault_fops_write(struct file *filep, const char __user *buf, + size_t count, loff_t *ppos) +{ + size_t response_size = sizeof(struct iommu_hwpt_page_response); + struct iommufd_fault *fault = filep->private_data; + struct iommu_hwpt_page_response response; + struct iopf_group *group; + size_t done = 0; + int rc = 0; + + if (*ppos || count % response_size) + return -ESPIPE; + + mutex_lock(&fault->mutex); + while (count > done) { + rc = copy_from_user(&response, buf + done, response_size); + if (rc) + break; + + group = xa_erase(&fault->response, response.cookie); + if (!group) { + rc = -EINVAL; + break; + } + + iopf_group_response(group, response.code); + iopf_free_group(group); + done += response_size; + } + mutex_unlock(&fault->mutex); + + return done == 0 ? rc : done; +} + +static __poll_t iommufd_fault_fops_poll(struct file *filep, + struct poll_table_struct *wait) +{ + struct iommufd_fault *fault = filep->private_data; + __poll_t pollflags = EPOLLOUT; + + poll_wait(filep, &fault->wait_queue, wait); + mutex_lock(&fault->mutex); + if (!list_empty(&fault->deliver)) + pollflags |= EPOLLIN | EPOLLRDNORM; + mutex_unlock(&fault->mutex); + + return pollflags; +} + +static int iommufd_fault_fops_release(struct inode *inode, struct file *filep) +{ + struct iommufd_fault *fault = filep->private_data; + + refcount_dec(&fault->obj.users); + iommufd_ctx_put(fault->ictx); + return 0; +} + +static const struct file_operations iommufd_fault_fops = { + .owner = THIS_MODULE, + .open = nonseekable_open, + .read = iommufd_fault_fops_read, + .write = iommufd_fault_fops_write, + .poll = iommufd_fault_fops_poll, + .release = iommufd_fault_fops_release, + .llseek = no_llseek, +}; + +int iommufd_fault_alloc(struct iommufd_ucmd *ucmd) +{ + struct iommu_fault_alloc *cmd = ucmd->cmd; + struct iommufd_fault *fault; + struct file *filep; + int fdno; + int rc; + + if (cmd->flags) + return -EOPNOTSUPP; + + fault = iommufd_object_alloc(ucmd->ictx, fault, IOMMUFD_OBJ_FAULT); + if (IS_ERR(fault)) + return PTR_ERR(fault); + + fault->ictx = ucmd->ictx; + INIT_LIST_HEAD(&fault->deliver); + xa_init_flags(&fault->response, XA_FLAGS_ALLOC1); + mutex_init(&fault->mutex); + init_waitqueue_head(&fault->wait_queue); + + filep = anon_inode_getfile("[iommufd-pgfault]", &iommufd_fault_fops, + fault, O_RDWR); + if (IS_ERR(filep)) { + rc = PTR_ERR(filep); + goto out_abort; + } + + refcount_inc(&fault->obj.users); + iommufd_ctx_get(fault->ictx); + fault->filep = filep; + + fdno = get_unused_fd_flags(O_CLOEXEC); + if (fdno < 0) { + rc = fdno; + goto out_fput; + } + + cmd->out_fault_id = fault->obj.id; + cmd->out_fault_fd = fdno; + + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_put_fdno; + iommufd_object_finalize(ucmd->ictx, &fault->obj); + + fd_install(fdno, fault->filep); + + return 0; +out_put_fdno: + put_unused_fd(fdno); +out_fput: + fput(filep); + refcount_dec(&fault->obj.users); + iommufd_ctx_put(fault->ictx); +out_abort: + iommufd_object_abort_and_destroy(ucmd->ictx, &fault->obj); + + return rc; +} diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 991f864d1f9b..c8a4519f1405 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -128,6 +128,7 @@ enum iommufd_object_type { IOMMUFD_OBJ_HWPT_NESTED, IOMMUFD_OBJ_IOAS, IOMMUFD_OBJ_ACCESS, + IOMMUFD_OBJ_FAULT, #ifdef CONFIG_IOMMUFD_TEST IOMMUFD_OBJ_SELFTEST, #endif @@ -426,6 +427,35 @@ void iopt_remove_access(struct io_pagetable *iopt, u32 iopt_access_list_id); void iommufd_access_destroy_object(struct iommufd_object *obj); +/* + * An iommufd_fault object represents an interface to deliver I/O page faults + * to the user space. These objects are created/destroyed by the user space and + * associated with hardware page table objects during page-table allocation. + */ +struct iommufd_fault { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct file *filep; + + /* The lists of outstanding faults protected by below mutex. */ + struct mutex mutex; + struct list_head deliver; + struct xarray response; + + struct wait_queue_head wait_queue; +}; + +struct iommufd_attach_handle { + struct iommu_attach_handle handle; + struct iommufd_device *idev; +}; + +/* Convert an iommu attach handle to iommufd handle. */ +#define to_iommufd_handle(hdl) container_of(hdl, struct iommufd_attach_handle, handle) + +int iommufd_fault_alloc(struct iommufd_ucmd *ucmd); +void iommufd_fault_destroy(struct iommufd_object *obj); + #ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); void iommufd_selftest_destroy(struct iommufd_object *obj); diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 39b32932c61e..83bbd7c5d160 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -319,6 +319,7 @@ static int iommufd_option(struct iommufd_ucmd *ucmd) union ucmd_buffer { struct iommu_destroy destroy; + struct iommu_fault_alloc fault; struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; @@ -355,6 +356,8 @@ struct iommufd_ioctl_op { } static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id), + IOCTL_OP(IOMMU_FAULT_QUEUE_ALLOC, iommufd_fault_alloc, struct iommu_fault_alloc, + out_fault_fd), IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info, __reserved), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, @@ -513,6 +516,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { .destroy = iommufd_hwpt_nested_destroy, .abort = iommufd_hwpt_nested_abort, }, + [IOMMUFD_OBJ_FAULT] = { + .destroy = iommufd_fault_destroy, + }, #ifdef CONFIG_IOMMUFD_TEST [IOMMUFD_OBJ_SELFTEST] = { .destroy = iommufd_selftest_destroy, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 910aec80886e..73bc3aee95a1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -124,12 +124,16 @@ struct iopf_fault { struct iopf_group { struct iopf_fault last_fault; struct list_head faults; + size_t fault_count; /* list node for iommu_fault_param::faults */ struct list_head pending_node; struct work_struct work; struct iommu_attach_handle *attach_handle; /* The device's fault data parameter. */ struct iommu_fault_param *fault_param; + /* Used by handler provider to hook the group on its own lists. */ + struct list_head node; + u32 cookie; }; /** diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 4d89ed97b533..70b8a38fcd46 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -50,6 +50,7 @@ enum { IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, IOMMUFD_CMD_HWPT_INVALIDATE, + IOMMUFD_CMD_FAULT_QUEUE_ALLOC, }; /** @@ -775,4 +776,21 @@ struct iommu_hwpt_page_response { __u32 cookie; __u32 code; }; + +/** + * struct iommu_fault_alloc - ioctl(IOMMU_FAULT_QUEUE_ALLOC) + * @size: sizeof(struct iommu_fault_alloc) + * @flags: Must be 0 + * @out_fault_id: The ID of the new FAULT + * @out_fault_fd: The fd of the new FAULT + * + * Explicitly allocate a fault handling object. + */ +struct iommu_fault_alloc { + __u32 size; + __u32 flags; + __u32 out_fault_id; + __u32 out_fault_fd; +}; +#define IOMMU_FAULT_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_FAULT_QUEUE_ALLOC) #endif -- cgit v1.2.3 From 34765cbc679c59ea5d952d738d2d16bf4aadc497 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 2 Jul 2024 14:34:42 +0800 Subject: iommufd: Associate fault object with iommufd_hw_pgtable When allocating a user iommufd_hw_pagetable, the user space is allowed to associate a fault object with the hw_pagetable by specifying the fault object ID in the page table allocation data and setting the IOMMU_HWPT_FAULT_ID_VALID flag bit. On a successful return of hwpt allocation, the user can retrieve and respond to page faults by reading and writing the file interface of the fault object. Once a fault object has been associated with a hwpt, the hwpt is iopf-capable, indicated by hwpt->fault is non NULL. Attaching, detaching, or replacing an iopf-capable hwpt to an RID or PASID will differ from those that are not iopf-capable. Link: https://lore.kernel.org/r/20240702063444.105814-9-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/fault.c | 17 +++++++++++++++ drivers/iommu/iommufd/hw_pagetable.c | 38 ++++++++++++++++++++++++++------- drivers/iommu/iommufd/iommufd_private.h | 9 ++++++++ include/uapi/linux/iommufd.h | 8 +++++++ 4 files changed, 64 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index 4934ae572638..54d6cd20a673 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -414,3 +414,20 @@ out_abort: return rc; } + +int iommufd_fault_iopf_handler(struct iopf_group *group) +{ + struct iommufd_hw_pagetable *hwpt; + struct iommufd_fault *fault; + + hwpt = group->attach_handle->domain->fault_data; + fault = hwpt->fault; + + mutex_lock(&fault->mutex); + list_add_tail(&group->node, &fault->deliver); + mutex_unlock(&fault->mutex); + + wake_up_interruptible(&fault->wait_queue); + + return 0; +} diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 33d142f8057d..e63f80f087d1 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -8,6 +8,15 @@ #include "../iommu-priv.h" #include "iommufd_private.h" +static void __iommufd_hwpt_destroy(struct iommufd_hw_pagetable *hwpt) +{ + if (hwpt->domain) + iommu_domain_free(hwpt->domain); + + if (hwpt->fault) + refcount_dec(&hwpt->fault->obj.users); +} + void iommufd_hwpt_paging_destroy(struct iommufd_object *obj) { struct iommufd_hwpt_paging *hwpt_paging = @@ -22,9 +31,7 @@ void iommufd_hwpt_paging_destroy(struct iommufd_object *obj) hwpt_paging->common.domain); } - if (hwpt_paging->common.domain) - iommu_domain_free(hwpt_paging->common.domain); - + __iommufd_hwpt_destroy(&hwpt_paging->common); refcount_dec(&hwpt_paging->ioas->obj.users); } @@ -49,9 +56,7 @@ void iommufd_hwpt_nested_destroy(struct iommufd_object *obj) struct iommufd_hwpt_nested *hwpt_nested = container_of(obj, struct iommufd_hwpt_nested, common.obj); - if (hwpt_nested->common.domain) - iommu_domain_free(hwpt_nested->common.domain); - + __iommufd_hwpt_destroy(&hwpt_nested->common); refcount_dec(&hwpt_nested->parent->common.obj.users); } @@ -213,7 +218,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, struct iommufd_hw_pagetable *hwpt; int rc; - if (flags || !user_data->len || !ops->domain_alloc_user) + if ((flags & ~IOMMU_HWPT_FAULT_ID_VALID) || + !user_data->len || !ops->domain_alloc_user) return ERR_PTR(-EOPNOTSUPP); if (parent->auto_domain || !parent->nest_parent) return ERR_PTR(-EINVAL); @@ -227,7 +233,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, refcount_inc(&parent->common.obj.users); hwpt_nested->parent = parent; - hwpt->domain = ops->domain_alloc_user(idev->dev, flags, + hwpt->domain = ops->domain_alloc_user(idev->dev, + flags & ~IOMMU_HWPT_FAULT_ID_VALID, parent->common.domain, user_data); if (IS_ERR(hwpt->domain)) { rc = PTR_ERR(hwpt->domain); @@ -308,6 +315,21 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) goto out_put_pt; } + if (cmd->flags & IOMMU_HWPT_FAULT_ID_VALID) { + struct iommufd_fault *fault; + + fault = iommufd_get_fault(ucmd, cmd->fault_id); + if (IS_ERR(fault)) { + rc = PTR_ERR(fault); + goto out_hwpt; + } + hwpt->fault = fault; + hwpt->domain->iopf_handler = iommufd_fault_iopf_handler; + hwpt->domain->fault_data = hwpt; + refcount_inc(&fault->obj.users); + iommufd_put_object(ucmd->ictx, &fault->obj); + } + cmd->out_hwpt_id = hwpt->obj.id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index aa4c26c87cb9..92efe30a8f0d 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -458,8 +458,17 @@ struct iommufd_attach_handle { /* Convert an iommu attach handle to iommufd handle. */ #define to_iommufd_handle(hdl) container_of(hdl, struct iommufd_attach_handle, handle) +static inline struct iommufd_fault * +iommufd_get_fault(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_FAULT), + struct iommufd_fault, obj); +} + int iommufd_fault_alloc(struct iommufd_ucmd *ucmd); void iommufd_fault_destroy(struct iommufd_object *obj); +int iommufd_fault_iopf_handler(struct iopf_group *group); int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt, struct iommufd_device *idev); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 70b8a38fcd46..ede2b464a761 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -357,10 +357,13 @@ struct iommu_vfio_ioas { * the parent HWPT in a nesting configuration. * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is * enforced on device attachment + * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is + * valid. */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, + IOMMU_HWPT_FAULT_ID_VALID = 1 << 2, }; /** @@ -412,6 +415,9 @@ enum iommu_hwpt_data_type { * @data_type: One of enum iommu_hwpt_data_type * @data_len: Length of the type specific data * @data_uptr: User pointer to the type specific data + * @fault_id: The ID of IOMMUFD_FAULT object. Valid only if flags field of + * IOMMU_HWPT_FAULT_ID_VALID is set. + * @__reserved2: Padding to 64-bit alignment. Must be 0. * * Explicitly allocate a hardware page table object. This is the same object * type that is returned by iommufd_device_attach() and represents the @@ -442,6 +448,8 @@ struct iommu_hwpt_alloc { __u32 data_type; __u32 data_len; __aligned_u64 data_uptr; + __u32 fault_id; + __u32 __reserved2; }; #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) -- cgit v1.2.3 From 87128f520a6b7573f8086f2c89b9381ee7e85e51 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 10 Jun 2024 06:22:56 +0930 Subject: btrfs: uapi: record temporary super flags used by btrfstune [BUG] There is a bug report that a canceled checksum conversion (still experimental feature) results in unexpected super block flags: csum_type 0 (crc32c) csum_size 4 csum 0x14973811 [match] bytenr 65536 flags 0x1000000001 ( WRITTEN | CHANGING_FSID_V2 ) magic _BHRfS_M [match] While for a filesystem with ongoing checksum conversion it should have either CHANGING_DATA_CSUM or CHANGING_META_CSUM. [CAUSE] It turns out that, due to btrfs-progs keeps its own extra flags inside its own ctree.h headers, not the shared uapi headers, we have conflicting super flags: kernel-shared/uapi/btrfs_tree.h:#define BTRFS_SUPER_FLAG_METADUMP_V2 (1ULL << 34) kernel-shared/uapi/btrfs_tree.h:#define BTRFS_SUPER_FLAG_CHANGING_FSID (1ULL << 35) kernel-shared/uapi/btrfs_tree.h:#define BTRFS_SUPER_FLAG_CHANGING_FSID_V2 (1ULL << 36) kernel-shared/ctree.h:#define BTRFS_SUPER_FLAG_CHANGING_DATA_CSUM (1ULL << 36) kernel-shared/ctree.h:#define BTRFS_SUPER_FLAG_CHANGING_META_CSUM (1ULL << 37) Note that CHANGING_FSID_V2 is conflicting with CHANGING_DATA_CSUM. [FIX] The proper fix would be done inside btrfs-progs, but to keep everything properly recorded, we should have everything inside the same uapi header. Copy all the new flags into uapi header, and change the value for CHANGING_DATA_CSUM and CHANGING_META_CSUM, while keep the value of CHANGING_BG_TREE untouched. Thankfully checksum change is still only experimental and all those CHANGING_* flags are transient (only for btrfs-progs to resume the conversion, and kernel will reject them all), the damage is still minor. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index d24e8e121507..c7636331e566 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -777,6 +777,14 @@ struct btrfs_stripe_extent { #define BTRFS_SUPER_FLAG_CHANGING_FSID (1ULL << 35) #define BTRFS_SUPER_FLAG_CHANGING_FSID_V2 (1ULL << 36) +/* + * Those are temporaray flags utilized by btrfs-progs to do offline conversion. + * They are rejected by kernel. + * But still keep them all here to avoid conflicts. + */ +#define BTRFS_SUPER_FLAG_CHANGING_BG_TREE (1ULL << 38) +#define BTRFS_SUPER_FLAG_CHANGING_DATA_CSUM (1ULL << 39) +#define BTRFS_SUPER_FLAG_CHANGING_META_CSUM (1ULL << 40) /* * items in the extent btree are used to record the objectid of the -- cgit v1.2.3 From 2422547e99f99f952d1a37f26b63289f749d5fcd Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Mon, 13 May 2024 18:01:43 +0200 Subject: btrfs: remove raid-stripe-tree encoding field from stripe_extent Remove the encoding field from 'struct btrfs_stripe_extent'. It was originally intended to encode the RAID type as well as if we're a data or a parity stripe. But the RAID type can be inferred form the block-group and the data vs. parity differentiation can be done easier with adding a new key type for parity stripes in the RAID stripe tree. Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 3 --- fs/btrfs/print-tree.c | 5 ----- fs/btrfs/raid-stripe-tree.c | 13 ------------- fs/btrfs/raid-stripe-tree.h | 3 +-- fs/btrfs/tree-checker.c | 19 ------------------- include/uapi/linux/btrfs_tree.h | 14 +------------- 6 files changed, 2 insertions(+), 55 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index 6c3deaa3e878..b2eb9cde2c5d 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -315,11 +315,8 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32); BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64); BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32); -BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8); BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64); BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64); -BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding, - struct btrfs_stripe_extent, encoding, 8); BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64); BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 453cd8358760..32dcea662da3 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -208,11 +208,6 @@ static void print_raid_stripe_key(const struct extent_buffer *eb, u32 item_size, struct btrfs_stripe_extent *stripe) { const int num_stripes = btrfs_num_raid_stripes(item_size); - const u8 encoding = btrfs_stripe_extent_encoding(eb, stripe); - - pr_info("\t\t\tencoding: %s\n", - (encoding && encoding < BTRFS_NR_RAID_TYPES) ? - btrfs_raid_array[encoding].raid_name : "unknown"); for (int i = 0; i < num_stripes; i++) pr_info("\t\t\tstride %d devid %llu physical %llu\n", diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 6af6b4b9a32e..e6f7a234b8f6 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -80,7 +80,6 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_key stripe_key; struct btrfs_root *stripe_root = fs_info->stripe_root; const int num_stripes = btrfs_bg_type_to_factor(bioc->map_type); - u8 encoding = btrfs_bg_flags_to_raid_index(bioc->map_type); struct btrfs_stripe_extent *stripe_extent; const size_t item_size = struct_size(stripe_extent, strides, num_stripes); int ret; @@ -94,7 +93,6 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, trace_btrfs_insert_one_raid_extent(fs_info, bioc->logical, bioc->size, num_stripes); - btrfs_set_stack_stripe_extent_encoding(stripe_extent, encoding); for (int i = 0; i < num_stripes; i++) { u64 devid = bioc->stripes[i].dev->devid; u64 physical = bioc->stripes[i].physical; @@ -159,7 +157,6 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf; const u64 end = logical + *length; int num_stripes; - u8 encoding; u64 offset; u64 found_logical; u64 found_length; @@ -222,16 +219,6 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, num_stripes = btrfs_num_raid_stripes(btrfs_item_size(leaf, slot)); stripe_extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent); - encoding = btrfs_stripe_extent_encoding(leaf, stripe_extent); - - if (encoding != btrfs_bg_flags_to_raid_index(map_type)) { - ret = -EUCLEAN; - btrfs_handle_fs_error(fs_info, ret, - "on-disk stripe encoding %d doesn't match RAID index %d", - encoding, - btrfs_bg_flags_to_raid_index(map_type)); - goto out; - } for (int i = 0; i < num_stripes; i++) { struct btrfs_raid_stride *stride = &stripe_extent->strides[i]; diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h index c9c258f84903..1ac1c21aac2f 100644 --- a/fs/btrfs/raid-stripe-tree.h +++ b/fs/btrfs/raid-stripe-tree.h @@ -48,8 +48,7 @@ static inline bool btrfs_need_stripe_tree_update(struct btrfs_fs_info *fs_info, static inline int btrfs_num_raid_stripes(u32 item_size) { - return (item_size - offsetof(struct btrfs_stripe_extent, strides)) / - sizeof(struct btrfs_raid_stride); + return item_size / sizeof(struct btrfs_raid_stride); } #endif diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a2c3651a3d8f..1e140f6dabc6 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1682,9 +1682,6 @@ static int check_inode_ref(struct extent_buffer *leaf, static int check_raid_stripe_extent(const struct extent_buffer *leaf, const struct btrfs_key *key, int slot) { - struct btrfs_stripe_extent *stripe_extent = - btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent); - if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) { generic_err(leaf, slot, "invalid key objectid for raid stripe extent, have %llu expect aligned to %u", @@ -1698,22 +1695,6 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf, return -EUCLEAN; } - switch (btrfs_stripe_extent_encoding(leaf, stripe_extent)) { - case BTRFS_STRIPE_RAID0: - case BTRFS_STRIPE_RAID1: - case BTRFS_STRIPE_DUP: - case BTRFS_STRIPE_RAID10: - case BTRFS_STRIPE_RAID5: - case BTRFS_STRIPE_RAID6: - case BTRFS_STRIPE_RAID1C3: - case BTRFS_STRIPE_RAID1C4: - break; - default: - generic_err(leaf, slot, "invalid raid stripe encoding %u", - btrfs_stripe_extent_encoding(leaf, stripe_extent)); - return -EUCLEAN; - } - return 0; } diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index c7636331e566..fc29d273845d 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -747,21 +747,9 @@ struct btrfs_raid_stride { __le64 physical; } __attribute__ ((__packed__)); -/* The stripe_extent::encoding, 1:1 mapping of enum btrfs_raid_types. */ -#define BTRFS_STRIPE_RAID0 1 -#define BTRFS_STRIPE_RAID1 2 -#define BTRFS_STRIPE_DUP 3 -#define BTRFS_STRIPE_RAID10 4 -#define BTRFS_STRIPE_RAID5 5 -#define BTRFS_STRIPE_RAID6 6 -#define BTRFS_STRIPE_RAID1C3 7 -#define BTRFS_STRIPE_RAID1C4 8 - struct btrfs_stripe_extent { - __u8 encoding; - __u8 reserved[7]; /* An array of raid strides this stripe is composed of. */ - struct btrfs_raid_stride strides[]; + __DECLARE_FLEX_ARRAY(struct btrfs_raid_stride, strides); } __attribute__ ((__packed__)); #define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) -- cgit v1.2.3 From 861f96a785149a0062cce6578e0fa7cb95435a7e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 10 Jul 2024 16:33:39 +0800 Subject: iommufd: Remove IOMMUFD_PAGE_RESP_FAILURE The response code of IOMMUFD_PAGE_RESP_FAILURE was defined to be equivalent to the "Response Failure" in PCI spec, section 10.4.2.1. This response code indicates that one or more pages within the associated request group have encountered or caused an unrecoverable error. Therefore, this response disables the PRI at the function. Modern I/O virtualization technologies, like SR-IOV, share PRI among the assignable device units. Therefore, a response failure on one unit might cause I/O failure on other units. Remove this response code so that user space can only respond with SUCCESS or INVALID. The VMM is recommended to emulate a failure response as a PRI reset, or PRI disable and changing to a non-PRI domain. Fixes: c714f15860fc ("iommufd: Add fault and response message definitions") Link: https://lore.kernel.org/r/20240710083341.44617-2-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index ede2b464a761..e31385b75d0b 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -765,14 +765,10 @@ struct iommu_hwpt_pgfault { * @IOMMUFD_PAGE_RESP_INVALID: Could not handle this fault, don't retry the * access. This is the "Invalid Request" in PCI * 10.4.2.1. - * @IOMMUFD_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from - * this device if possible. This is the "Response - * Failure" in PCI 10.4.2.1. */ enum iommufd_page_response_code { IOMMUFD_PAGE_RESP_SUCCESS = 0, IOMMUFD_PAGE_RESP_INVALID, - IOMMUFD_PAGE_RESP_FAILURE, }; /** -- cgit v1.2.3 From 79cf9c6ee44e0af7e1383365d29c64eece6665bb Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:42 +0200 Subject: media: uapi: pisp_be_config: Drop BIT() from uAPI The pisp_be_config.h uAPI header file contains a bit-field definition that uses the BIT() helper macro. As the BIT() identifier is not defined in userspace, drop it from the uAPI header. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Reviewed-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_be_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h index 1684ae068d4f..27d0cc417d6b 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_be_config.h +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -146,7 +146,7 @@ struct pisp_be_dpc_config { */ struct pisp_be_geq_config { __u16 offset; -#define PISP_BE_GEQ_SHARPER BIT(15) +#define PISP_BE_GEQ_SHARPER (1U << 15) #define PISP_BE_GEQ_SLOPE ((1 << 10) - 1) /* top bit is the "sharper" flag, slope value is bottom 10 bits */ __u16 slope_sharper; -- cgit v1.2.3 From 1991a09e6d7c1dff5efea65b5b31082332f2e64e Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:43 +0200 Subject: media: uapi: pisp_common: Add 32 bpp format test Add definition and test for 32-bits image formats to the pisp_common.h uAPI header. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Acked-by: David Plowman Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_common.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_common.h b/include/uapi/linux/media/raspberrypi/pisp_common.h index b2522e29c976..74d096188233 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_common.h +++ b/include/uapi/linux/media/raspberrypi/pisp_common.h @@ -72,6 +72,8 @@ enum pisp_image_format { PISP_IMAGE_FORMAT_SHIFT_8 = 0x00080000, PISP_IMAGE_FORMAT_SHIFT_MASK = 0x000f0000, + PISP_IMAGE_FORMAT_BPP_32 = 0x00100000, + PISP_IMAGE_FORMAT_UNCOMPRESSED = 0x00000000, PISP_IMAGE_FORMAT_COMPRESSION_MODE_1 = 0x01000000, PISP_IMAGE_FORMAT_COMPRESSION_MODE_2 = 0x02000000, @@ -134,6 +136,7 @@ enum pisp_image_format { PISP_IMAGE_FORMAT_PLANARITY_PLANAR) #define PISP_IMAGE_FORMAT_wallpaper(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_WALLPAPER_ROLL) +#define PISP_IMAGE_FORMAT_bpp_32(fmt) ((fmt) & PISP_IMAGE_FORMAT_BPP_32) #define PISP_IMAGE_FORMAT_HOG(fmt) \ ((fmt) & \ (PISP_IMAGE_FORMAT_HOG_SIGNED | PISP_IMAGE_FORMAT_HOG_UNSIGNED)) -- cgit v1.2.3 From f5cee94f2dfe5b7625452b831f7629369ce68a7b Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:44 +0200 Subject: media: uapi: pisp_common: Capitalize all macros The macro used to inspect an image format characteristic use a mixture of capitalized and non-capitalized letters, which is rather unusual for the Linux kernel style. Capitalize all identifiers. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_common.h | 38 +++++++++++----------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_common.h b/include/uapi/linux/media/raspberrypi/pisp_common.h index 74d096188233..cbdccfed1261 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_common.h +++ b/include/uapi/linux/media/raspberrypi/pisp_common.h @@ -92,51 +92,51 @@ enum pisp_image_format { PISP_IMAGE_FORMAT_THREE_CHANNEL }; -#define PISP_IMAGE_FORMAT_bps_8(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_8(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_8) -#define PISP_IMAGE_FORMAT_bps_10(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_10(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_10) -#define PISP_IMAGE_FORMAT_bps_12(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_12(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_12) -#define PISP_IMAGE_FORMAT_bps_16(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_16(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_16) -#define PISP_IMAGE_FORMAT_bps(fmt) \ +#define PISP_IMAGE_FORMAT_BPS(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) ? \ 8 + (2 << (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) - 1)) : 8) -#define PISP_IMAGE_FORMAT_shift(fmt) \ +#define PISP_IMAGE_FORMAT_SHIFT(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SHIFT_MASK) / PISP_IMAGE_FORMAT_SHIFT_1) -#define PISP_IMAGE_FORMAT_three_channel(fmt) \ +#define PISP_IMAGE_FORMAT_THREE_CHANNEL(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL) -#define PISP_IMAGE_FORMAT_single_channel(fmt) \ +#define PISP_IMAGE_FORMAT_SINGLE_CHANNEL(fmt) \ (!((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL)) -#define PISP_IMAGE_FORMAT_compressed(fmt) \ +#define PISP_IMAGE_FORMAT_COMPRESSED(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_COMPRESSION_MASK) != \ PISP_IMAGE_FORMAT_UNCOMPRESSED) -#define PISP_IMAGE_FORMAT_sampling_444(fmt) \ +#define PISP_IMAGE_FORMAT_SAMPLING_444(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ PISP_IMAGE_FORMAT_SAMPLING_444) -#define PISP_IMAGE_FORMAT_sampling_422(fmt) \ +#define PISP_IMAGE_FORMAT_SAMPLING_422(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ PISP_IMAGE_FORMAT_SAMPLING_422) -#define PISP_IMAGE_FORMAT_sampling_420(fmt) \ +#define PISP_IMAGE_FORMAT_SAMPLING_420(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ PISP_IMAGE_FORMAT_SAMPLING_420) -#define PISP_IMAGE_FORMAT_order_normal(fmt) \ +#define PISP_IMAGE_FORMAT_ORDER_NORMAL(fmt) \ (!((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED)) -#define PISP_IMAGE_FORMAT_order_swapped(fmt) \ +#define PISP_IMAGE_FORMAT_ORDER_SWAPPED(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED) -#define PISP_IMAGE_FORMAT_interleaved(fmt) \ +#define PISP_IMAGE_FORMAT_INTERLEAVED(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ PISP_IMAGE_FORMAT_PLANARITY_INTERLEAVED) -#define PISP_IMAGE_FORMAT_semiplanar(fmt) \ +#define PISP_IMAGE_FORMAT_SEMIPLANAR(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ PISP_IMAGE_FORMAT_PLANARITY_SEMI_PLANAR) -#define PISP_IMAGE_FORMAT_planar(fmt) \ +#define PISP_IMAGE_FORMAT_PLANAR(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ PISP_IMAGE_FORMAT_PLANARITY_PLANAR) -#define PISP_IMAGE_FORMAT_wallpaper(fmt) \ +#define PISP_IMAGE_FORMAT_WALLPAPER(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_WALLPAPER_ROLL) -#define PISP_IMAGE_FORMAT_bpp_32(fmt) ((fmt) & PISP_IMAGE_FORMAT_BPP_32) +#define PISP_IMAGE_FORMAT_BPP_32(fmt) ((fmt) & PISP_IMAGE_FORMAT_BPP_32) #define PISP_IMAGE_FORMAT_HOG(fmt) \ ((fmt) & \ (PISP_IMAGE_FORMAT_HOG_SIGNED | PISP_IMAGE_FORMAT_HOG_UNSIGNED)) -- cgit v1.2.3 From 639065c621df9bad9d94373084e1c568f81d34e0 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:45 +0200 Subject: media: uapi: pisp_be_config: Re-sort pisp_be_tiles_config The order of the members of pisp_be_tiles_config is relevant as the driver logic assumes 'config' to be at offset 0. Re-sort the member to match the driver's expectations. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Acked-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_be_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h index 27d0cc417d6b..f8650ca92bf8 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_be_config.h +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -919,9 +919,9 @@ struct pisp_tile { * @config: PiSP Back End configuration */ struct pisp_be_tiles_config { + struct pisp_be_config config; struct pisp_tile tiles[PISP_BACK_END_NUM_TILES]; __u32 num_tiles; - struct pisp_be_config config; } __attribute__((packed)); #endif /* _UAPI_PISP_BE_CONFIG_H_ */ -- cgit v1.2.3 From 1c2c57bd439ecaffc728139a0a00701bee886d0a Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:46 +0200 Subject: media: uapi: pisp_be_config: Add extra config fields Complete the pisp_be_config strcture by adding fields that even if not written to the HW are relevant to complete the uAPI and put it in par with the BSP driver. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../uapi/linux/media/raspberrypi/pisp_be_config.h | 41 ++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h index f8650ca92bf8..cbeb714f4d61 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_be_config.h +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -716,6 +716,13 @@ struct pisp_be_hog_buffer_config { /** * struct pisp_be_config - RaspberryPi PiSP Back End Processing configuration * + * @input_buffer: Input buffer addresses + * @tdn_input_buffer: TDN input buffer addresses + * @stitch_input_buffer: Stitch input buffer addresses + * @tdn_output_buffer: TDN output buffer addresses + * @stitch_output_buffer: Stitch output buffer addresses + * @output_buffer: Output buffers addresses + * @hog_buffer: HOG buffer addresses * @global: Global PiSP configuration * @input_format: Input image format * @decompress: Decompress configuration @@ -753,8 +760,30 @@ struct pisp_be_hog_buffer_config { * @resample: Resampling configuration * @output_format: Output format configuration * @hog: HOG configuration + * @axi: AXI bus configuration + * @lsc_extra: LSC extra info + * @cac_extra: CAC extra info + * @downscale_extra: Downscaler extra info + * @resample_extra: Resample extra info + * @crop: Crop configuration + * @hog_format: HOG format info + * @dirty_flags_bayer: Bayer enable dirty flags + * (:c:type:`pisp_be_bayer_enable`) + * @dirty_flags_rgb: RGB enable dirty flags + * (:c:type:`pisp_be_rgb_enable`) + * @dirty_flags_extra: Extra dirty flags */ struct pisp_be_config { + /* I/O configuration: */ + struct pisp_be_input_buffer_config input_buffer; + struct pisp_be_tdn_input_buffer_config tdn_input_buffer; + struct pisp_be_stitch_input_buffer_config stitch_input_buffer; + struct pisp_be_tdn_output_buffer_config tdn_output_buffer; + struct pisp_be_stitch_output_buffer_config stitch_output_buffer; + struct pisp_be_output_buffer_config + output_buffer[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_hog_buffer_config hog_buffer; + /* Processing configuration: */ struct pisp_be_global_config global; struct pisp_image_format_config input_format; struct pisp_decompress_config decompress; @@ -793,6 +822,18 @@ struct pisp_be_config { struct pisp_be_output_format_config output_format[PISP_BACK_END_NUM_OUTPUTS]; struct pisp_be_hog_config hog; + struct pisp_be_axi_config axi; + /* Non-register fields: */ + struct pisp_be_lsc_extra lsc_extra; + struct pisp_be_cac_extra cac_extra; + struct pisp_be_downscale_extra + downscale_extra[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_resample_extra resample_extra[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_crop_config crop; + struct pisp_image_format_config hog_format; + __u32 dirty_flags_bayer; /* these use pisp_be_bayer_enable */ + __u32 dirty_flags_rgb; /* use pisp_be_rgb_enable */ + __u32 dirty_flags_extra; /* these use pisp_be_dirty_t */ } __attribute__((packed)); /** -- cgit v1.2.3 From bc1a5cd002116552db4c3541e91f8a5b1b0cf65d Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 10 Apr 2024 15:07:28 -0700 Subject: KVM: Add KVM_PRE_FAULT_MEMORY vcpu ioctl to pre-populate guest memory Add a new ioctl KVM_PRE_FAULT_MEMORY in the KVM common code. It iterates on the memory range and calls the arch-specific function. The implementation is optional and enabled by a Kconfig symbol. Suggested-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Rick Edgecombe Message-ID: <819322b8f25971f2b9933bfa4506e618508ad782.1712785629.git.isaku.yamahata@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 ++++ include/uapi/linux/kvm.h | 10 ++++++++ virt/kvm/Kconfig | 3 +++ virt/kvm/kvm_main.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 78 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7b57878c8c18..c3c922bf077f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2477,4 +2477,9 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d03842abae57..e5af8c692dc0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -917,6 +917,7 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_PRE_FAULT_MEMORY 236 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1548,4 +1549,13 @@ struct kvm_create_guest_memfd { __u64 reserved[6]; }; +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 754c6c923427..b14e14cdbfb9 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -67,6 +67,9 @@ config HAVE_KVM_INVALID_WAKEUPS config KVM_GENERIC_DIRTYLOG_READ_PROTECT bool +config KVM_GENERIC_PRE_FAULT_MEMORY + bool + config KVM_COMPAT def_bool y depends on KVM && COMPAT && !(S390 || ARM64 || RISCV) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8e422c2c9450..f817ec66c85f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4373,6 +4373,52 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) return fd; } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + int idx; + long r; + u64 full_size; + + if (range->flags) + return -EINVAL; + + if (!PAGE_ALIGNED(range->gpa) || + !PAGE_ALIGNED(range->size) || + range->gpa + range->size <= range->gpa) + return -EINVAL; + + vcpu_load(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + + full_size = range->size; + do { + if (signal_pending(current)) { + r = -EINTR; + break; + } + + r = kvm_arch_vcpu_pre_fault_memory(vcpu, range); + if (WARN_ON_ONCE(r == 0 || r == -EIO)) + break; + + if (r < 0) + break; + + range->size -= r; + range->gpa += r; + cond_resched(); + } while (range->size); + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + vcpu_put(vcpu); + + /* Return success if at least one page was mapped successfully. */ + return full_size == range->size ? r : 0; +} +#endif + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4573,6 +4619,20 @@ out_free1: r = kvm_vcpu_ioctl_get_stats_fd(vcpu); break; } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY + case KVM_PRE_FAULT_MEMORY: { + struct kvm_pre_fault_memory range; + + r = -EFAULT; + if (copy_from_user(&range, argp, sizeof(range))) + break; + r = kvm_vcpu_pre_fault_memory(vcpu, &range); + /* Pass back leftover range. */ + if (copy_to_user(argp, &range, sizeof(range))) + r = -EFAULT; + break; + } +#endif default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } -- cgit v1.2.3 From ed5d583a88a9207b866c14ba834984c6f3c51d23 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 27 Jun 2024 10:08:54 -0700 Subject: fs/procfs: implement efficient VMA querying API for /proc//maps /proc//maps file is extremely useful in practice for various tasks involving figuring out process memory layout, what files are backing any given memory range, etc. One important class of applications that absolutely rely on this are profilers/stack symbolizers (perf tool being one of them). Patterns of use differ, but they generally would fall into two categories. In on-demand pattern, a profiler/symbolizer would normally capture stack trace containing absolute memory addresses of some functions, and would then use /proc//maps file to find corresponding backing ELF files (normally, only executable VMAs are of interest), file offsets within them, and then continue from there to get yet more information (ELF symbols, DWARF information) to get human-readable symbolic information. This pattern is used by Meta's fleet-wide profiler, as one example. In preprocessing pattern, application doesn't know the set of addresses of interest, so it has to fetch all relevant VMAs (again, probably only executable ones), store or cache them, then proceed with profiling and stack trace capture. Once done, it would do symbolization based on stored VMA information. This can happen at much later point in time. This patterns is used by perf tool, as an example. In either case, there are both performance and correctness requirement involved. This address to VMA information translation has to be done as efficiently as possible, but also not miss any VMA (especially in the case of loading/unloading shared libraries). In practice, correctness can't be guaranteed (due to process dying before VMA data can be captured, or shared library being unloaded, etc), but any effort to maximize the chance of finding the VMA is appreciated. Unfortunately, for all the /proc//maps file universality and usefulness, it doesn't fit the above use cases 100%. First, it's main purpose is to emit all VMAs sequentially, but in practice captured addresses would fall only into a smaller subset of all process' VMAs, mainly containing executable text. Yet, library would need to parse most or all of the contents to find needed VMAs, as there is no way to skip VMAs that are of no use. Efficient library can do the linear pass and it is still relatively efficient, but it's definitely an overhead that can be avoided, if there was a way to do more targeted querying of the relevant VMA information. Second, it's a text based interface, which makes its programmatic use from applications and libraries more cumbersome and inefficient due to the need to handle text parsing to get necessary pieces of information. The overhead is actually payed both by kernel, formatting originally binary VMA data into text, and then by user space application, parsing it back into binary data for further use. For the on-demand pattern of usage, described above, another problem when writing generic stack trace symbolization library is an unfortunate performance-vs-correctness tradeoff that needs to be made. Library has to make a decision to either cache parsed contents of /proc//maps (after initial processing) to service future requests (if application requests to symbolize another set of addresses (for the same process), captured at some later time, which is typical for periodic/continuous profiling cases) to avoid higher costs of re-parsing this file. Or it has to choose to cache the contents in memory to speed up future requests. In the former case, more memory is used for the cache and there is a risk of getting stale data if application loads or unloads shared libraries, or otherwise changed its set of VMAs somehow, e.g., through additional mmap() calls. In the latter case, it's the performance hit that comes from re-opening the file and re-parsing its contents all over again. This patch aims to solve this problem by providing a new API built on top of /proc//maps. It's meant to address both non-selectiveness and text nature of /proc//maps, by giving user more control of what sort of VMA(s) needs to be queried, and being binary-based interface eliminates the overhead of text formatting (on kernel side) and parsing (on user space side). It's also designed to be extensible and forward/backward compatible by including required struct size field, which user has to provide. We use established copy_struct_from_user() approach to handle extensibility. User has a choice to pick either getting VMA that covers provided address or -ENOENT if none is found (exact, least surprising, case). Or, with an extra query flag (PROCMAP_QUERY_COVERING_OR_NEXT_VMA), they can get either VMA that covers the address (if there is one), or the closest next VMA (i.e., VMA with the smallest vm_start > addr). The latter allows more efficient use, but, given it could be a surprising behavior, requires an explicit opt-in. There is another query flag that is useful for some use cases. PROCMAP_QUERY_FILE_BACKED_VMA instructs this API to only return file-backed VMAs. Combining this with PROCMAP_QUERY_COVERING_OR_NEXT_VMA makes it possible to efficiently iterate only file-backed VMAs of the process, which is what profilers/symbolizers are normally interested in. All the above querying flags can be combined with (also optional) set of desired VMA permissions flags. This allows to, for example, iterate only an executable subset of VMAs, which is what preprocessing pattern, used by perf tool, would benefit from, as the assumption is that captured stack traces would have addresses of executable code. This saves time by skipping non-executable VMAs altogether efficienty. All these querying flags (modifiers) are orthogonal and can be combined in a semantically meaningful and natural way. Basing this ioctl()-based API on top of /proc//maps's FD makes sense given it's querying the same set of VMA data. It's also benefitial because permission checks for /proc//maps is performed at open time once, and the actual data read of text contents of /proc//maps is done without further permission checks. We piggyback on this pattern with ioctl()-based API as well, as that's a desired property. Both for performance reasons, but also for security and flexibility reasons. Allowing application to open an FD for /proc/self/maps without any extra capabilities, and then passing it to some sort of profiling agent through Unix-domain socket, would allow such profiling agent to not require some of the capabilities that are otherwise expected when opening /proc//maps file for *another* process. This is a desirable property for some more restricted setups. This new ioctl-based implementation doesn't interfere with seq_file-based implementation of /proc//maps textual interface, and so could be used together or independently without paying any price for that. Note also, that fetching VMA name (e.g., backing file path, or special hard-coded or user-provided names) is optional just like build ID. If user sets vma_name_size to zero, kernel code won't attempt to retrieve it, saving resources. Earlier versions of this patch set were adding per-VMA locking, which is why we have a code structure that is ready for abstracting mmap_lock vs vm_lock differences (query_vma_setup(), query_vma_teardown(), and query_vma_find_by_addr()), but given anon_vma_name() is not yet compatible with per-VMA locking, initial implementation sticks to using only mmap_lock for now. It will be easy to add back per-VMA locking once all the pieces are ready later on. Which is why we keep existing code structure with setup/teardown/query helper functions. [andrii@kernel.org: improve PROCMAP_QUERY's compat mode handling] Link: https://lkml.kernel.org/r/20240701174805.1897344-2-andrii@kernel.org Link: https://lkml.kernel.org/r/20240627170900.1672542-3-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Liam R. Howlett Cc: Alexey Dobriyan Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Mike Rapoport (IBM) Cc: Suren Baghdasaryan Cc: Andi Kleen Cc: Arnd Bergmann Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 235 ++++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fs.h | 130 ++++++++++++++++++++++++++- 2 files changed, 364 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 507b7dc7c4c8..75679b5de549 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -375,11 +375,246 @@ static int pid_maps_open(struct inode *inode, struct file *file) return do_maps_open(inode, file, &proc_pid_maps_op); } +#define PROCMAP_QUERY_VMA_FLAGS ( \ + PROCMAP_QUERY_VMA_READABLE | \ + PROCMAP_QUERY_VMA_WRITABLE | \ + PROCMAP_QUERY_VMA_EXECUTABLE | \ + PROCMAP_QUERY_VMA_SHARED \ +) + +#define PROCMAP_QUERY_VALID_FLAGS_MASK ( \ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA | \ + PROCMAP_QUERY_FILE_BACKED_VMA | \ + PROCMAP_QUERY_VMA_FLAGS \ +) + +static int query_vma_setup(struct mm_struct *mm) +{ + return mmap_read_lock_killable(mm); +} + +static void query_vma_teardown(struct mm_struct *mm, struct vm_area_struct *vma) +{ + mmap_read_unlock(mm); +} + +static struct vm_area_struct *query_vma_find_by_addr(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +static struct vm_area_struct *query_matching_vma(struct mm_struct *mm, + unsigned long addr, u32 flags) +{ + struct vm_area_struct *vma; + +next_vma: + vma = query_vma_find_by_addr(mm, addr); + if (!vma) + goto no_vma; + + /* user requested only file-backed VMA, keep iterating */ + if ((flags & PROCMAP_QUERY_FILE_BACKED_VMA) && !vma->vm_file) + goto skip_vma; + + /* VMA permissions should satisfy query flags */ + if (flags & PROCMAP_QUERY_VMA_FLAGS) { + u32 perm = 0; + + if (flags & PROCMAP_QUERY_VMA_READABLE) + perm |= VM_READ; + if (flags & PROCMAP_QUERY_VMA_WRITABLE) + perm |= VM_WRITE; + if (flags & PROCMAP_QUERY_VMA_EXECUTABLE) + perm |= VM_EXEC; + if (flags & PROCMAP_QUERY_VMA_SHARED) + perm |= VM_MAYSHARE; + + if ((vma->vm_flags & perm) != perm) + goto skip_vma; + } + + /* found covering VMA or user is OK with the matching next VMA */ + if ((flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) || vma->vm_start <= addr) + return vma; + +skip_vma: + /* + * If the user needs closest matching VMA, keep iterating. + */ + addr = vma->vm_end; + if (flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) + goto next_vma; +no_vma: + return ERR_PTR(-ENOENT); +} + +static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) +{ + struct procmap_query karg; + struct vm_area_struct *vma; + struct mm_struct *mm; + const char *name = NULL; + char *name_buf = NULL; + __u64 usize; + int err; + + if (copy_from_user(&usize, (void __user *)uarg, sizeof(usize))) + return -EFAULT; + /* argument struct can never be that large, reject abuse */ + if (usize > PAGE_SIZE) + return -E2BIG; + /* argument struct should have at least query_flags and query_addr fields */ + if (usize < offsetofend(struct procmap_query, query_addr)) + return -EINVAL; + err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + if (err) + return err; + + /* reject unknown flags */ + if (karg.query_flags & ~PROCMAP_QUERY_VALID_FLAGS_MASK) + return -EINVAL; + /* either both buffer address and size are set, or both should be zero */ + if (!!karg.vma_name_size != !!karg.vma_name_addr) + return -EINVAL; + + mm = priv->mm; + if (!mm || !mmget_not_zero(mm)) + return -ESRCH; + + err = query_vma_setup(mm); + if (err) { + mmput(mm); + return err; + } + + vma = query_matching_vma(mm, karg.query_addr, karg.query_flags); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + vma = NULL; + goto out; + } + + karg.vma_start = vma->vm_start; + karg.vma_end = vma->vm_end; + + karg.vma_flags = 0; + if (vma->vm_flags & VM_READ) + karg.vma_flags |= PROCMAP_QUERY_VMA_READABLE; + if (vma->vm_flags & VM_WRITE) + karg.vma_flags |= PROCMAP_QUERY_VMA_WRITABLE; + if (vma->vm_flags & VM_EXEC) + karg.vma_flags |= PROCMAP_QUERY_VMA_EXECUTABLE; + if (vma->vm_flags & VM_MAYSHARE) + karg.vma_flags |= PROCMAP_QUERY_VMA_SHARED; + + karg.vma_page_size = vma_kernel_pagesize(vma); + + if (vma->vm_file) { + const struct inode *inode = file_user_inode(vma->vm_file); + + karg.vma_offset = ((__u64)vma->vm_pgoff) << PAGE_SHIFT; + karg.dev_major = MAJOR(inode->i_sb->s_dev); + karg.dev_minor = MINOR(inode->i_sb->s_dev); + karg.inode = inode->i_ino; + } else { + karg.vma_offset = 0; + karg.dev_major = 0; + karg.dev_minor = 0; + karg.inode = 0; + } + + if (karg.build_id_size) { + __u32 build_id_sz; + + err = build_id_parse(vma, build_id_buf, &build_id_sz); + if (err) { + karg.build_id_size = 0; + } else { + if (karg.build_id_size < build_id_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.build_id_size = build_id_sz; + } + } + + if (karg.vma_name_size) { + size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size); + const struct path *path; + const char *name_fmt; + size_t name_sz = 0; + + get_vma_name(vma, &path, &name, &name_fmt); + + if (path || name_fmt || name) { + name_buf = kmalloc(name_buf_sz, GFP_KERNEL); + if (!name_buf) { + err = -ENOMEM; + goto out; + } + } + if (path) { + name = d_path(path, name_buf, name_buf_sz); + if (IS_ERR(name)) { + err = PTR_ERR(name); + goto out; + } + name_sz = name_buf + name_buf_sz - name; + } else if (name || name_fmt) { + name_sz = 1 + snprintf(name_buf, name_buf_sz, name_fmt ?: "%s", name); + name = name_buf; + } + if (name_sz > name_buf_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.vma_name_size = name_sz; + } + + /* unlock vma or mmap_lock, and put mm_struct before copying data to user */ + query_vma_teardown(mm, vma); + mmput(mm); + + if (karg.vma_name_size && copy_to_user((void __user *)karg.vma_name_addr, + name, karg.vma_name_size)) { + kfree(name_buf); + return -EFAULT; + } + kfree(name_buf); + + if (copy_to_user(uarg, &karg, min_t(size_t, sizeof(karg), usize))) + return -EFAULT; + + return 0; + +out: + query_vma_teardown(mm, vma); + mmput(mm); + kfree(name_buf); + return err; +} + +static long procfs_procmap_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct seq_file *seq = file->private_data; + struct proc_maps_private *priv = seq->private; + + switch (cmd) { + case PROCMAP_QUERY: + return do_procmap_query(priv, (void __user *)arg); + default: + return -ENOIOCTLCMD; + } +} + const struct file_operations proc_pid_maps_operations = { .open = pid_maps_open, .read = seq_read, .llseek = seq_lseek, .release = proc_map_release, + .unlocked_ioctl = procfs_procmap_ioctl, + .compat_ioctl = compat_ptr_ioctl, }; /* diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 45e4e64fd664..5d440f9b5d92 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -333,8 +333,10 @@ typedef int __bitwise __kernel_rwf_t; #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND | RWF_NOAPPEND) +#define PROCFS_IOCTL_MAGIC 'f' + /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -393,4 +395,130 @@ struct pm_scan_arg { __u64 return_mask; }; +/* /proc//maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc//maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ +}; + #endif /* _UAPI_LINUX_FS_H */ -- cgit v1.2.3 From bfc69fd05ef9b6416f4811aafafb7f2b34daa000 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 27 Jun 2024 10:08:55 -0700 Subject: fs/procfs: add build ID fetching to PROCMAP_QUERY API The need to get ELF build ID reliably is an important aspect when dealing with profiling and stack trace symbolization, and /proc//maps textual representation doesn't help with this. To get backing file's ELF build ID, application has to first resolve VMA, then use it's start/end address range to follow a special /proc//map_files/- symlink to open the ELF file (this is necessary because backing file might have been removed from the disk or was already replaced with another binary in the same file path. Such approach, beyond just adding complexity of having to do a bunch of extra work, has extra security implications. Because application opens underlying ELF file and needs read access to its entire contents (as far as kernel is concerned), kernel puts additional capable() checks on following /proc//map_files/- symlink. And that makes sense in general. But in the case of build ID, profiler/symbolizer doesn't need the contents of ELF file, per se. It's only build ID that is of interest, and ELF build ID itself doesn't provide any sensitive information. So this patch adds a way to request backing file's ELF build ID along the rest of VMA information in the same API. User has control over whether this piece of information is requested or not by either setting build_id_size field to zero or non-zero maximum buffer size they provided through build_id_addr field (which encodes user pointer as __u64 field). This is a completely optional piece of information, and so has no performance implications for user cases that don't care about build ID, while improving performance and simplifying the setup for those application that do need it. Kernel already implements build ID fetching, which is used from BPF subsystem. We are reusing this code here, but plan a follow up changes to make it work better under more relaxed assumption (compared to what existing code assumes) of being called from user process context, in which page faults are allowed. BPF-specific implementation currently bails out if necessary part of ELF file is not paged in, all due to extra BPF-specific restrictions (like the need to fetch build ID in restrictive contexts such as NMI handler). [andrii@kernel.org: fix integer to pointer cast warning in do_procmap_query()] Link: https://lkml.kernel.org/r/20240701174805.1897344-1-andrii@kernel.org Link: https://lkml.kernel.org/r/20240627170900.1672542-4-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Liam R. Howlett Cc: Alexey Dobriyan Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Mike Rapoport (IBM) Cc: Suren Baghdasaryan Cc: Andi Kleen Cc: Arnd Bergmann Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 27 +++++++++++++++++++++++++-- include/uapi/linux/fs.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 75679b5de549..728693ed00e6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -445,6 +446,7 @@ skip_vma: addr = vma->vm_end; if (flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) goto next_vma; + no_vma: return ERR_PTR(-ENOENT); } @@ -455,7 +457,7 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) struct vm_area_struct *vma; struct mm_struct *mm; const char *name = NULL; - char *name_buf = NULL; + char build_id_buf[BUILD_ID_SIZE_MAX], *name_buf = NULL; __u64 usize; int err; @@ -477,6 +479,8 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) /* either both buffer address and size are set, or both should be zero */ if (!!karg.vma_name_size != !!karg.vma_name_addr) return -EINVAL; + if (!!karg.build_id_size != !!karg.build_id_addr) + return -EINVAL; mm = priv->mm; if (!mm || !mmget_not_zero(mm)) @@ -539,6 +543,21 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) } } + if (karg.build_id_size) { + __u32 build_id_sz; + + err = build_id_parse(vma, build_id_buf, &build_id_sz); + if (err) { + karg.build_id_size = 0; + } else { + if (karg.build_id_size < build_id_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.build_id_size = build_id_sz; + } + } + if (karg.vma_name_size) { size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size); const struct path *path; @@ -576,13 +595,17 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) query_vma_teardown(mm, vma); mmput(mm); - if (karg.vma_name_size && copy_to_user((void __user *)karg.vma_name_addr, + if (karg.vma_name_size && copy_to_user(u64_to_user_ptr(karg.vma_name_addr), name, karg.vma_name_size)) { kfree(name_buf); return -EFAULT; } kfree(name_buf); + if (karg.build_id_size && copy_to_user(u64_to_user_ptr(karg.build_id_addr), + build_id_buf, karg.build_id_size)) + return -EFAULT; + if (copy_to_user(uarg, &karg, min_t(size_t, sizeof(karg), usize))) return -EFAULT; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 5d440f9b5d92..2a4a5f50c98e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -511,6 +511,26 @@ struct procmap_query { * If set to zero, vma_name_addr should be set to zero as well */ __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ /* * User-supplied address of a buffer of at least vma_name_size bytes * for kernel to fill with matched VMA's name (see vma_name_size field @@ -519,6 +539,14 @@ struct procmap_query { * Should be set to zero if VMA name should not be returned. */ __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ }; #endif /* _UAPI_LINUX_FS_H */ -- cgit v1.2.3 From 2c1583290b08c5aa9005178a573be8f329de2976 Mon Sep 17 00:00:00 2001 From: "Kamil Horák (2N)" Date: Fri, 12 Jul 2024 17:07:06 +0200 Subject: net: phy: bcm54811: New link mode for BroadR-Reach MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new link mode necessary for 10 MBit single-pair connection in BroadR-Reach mode on bcm5481x PHY by Broadcom. This new link mode, 10baseT1BRR, is known as 1BR10 in the Broadcom terminology. Another link mode to be used is 1BR100 and it is already present as 100baseT1, because Broadcom's 1BR100 became 100baseT1 (IEEE 802.3bw). Signed-off-by: Kamil Horák (2N) Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240712150709.3134474-2-kamilh@axis.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy-core.c | 3 ++- include/uapi/linux/ethtool.h | 1 + net/ethtool/common.c | 3 +++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index a235ea2264a7..1f98b6a96c15 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -13,7 +13,7 @@ */ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 102, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 103, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -266,6 +266,7 @@ static const struct phy_setting settings[] = { PHY_SETTING( 10, FULL, 10baseT1S_Full ), PHY_SETTING( 10, HALF, 10baseT1S_Half ), PHY_SETTING( 10, HALF, 10baseT1S_P2MP_Half ), + PHY_SETTING( 10, FULL, 10baseT1BRR_Full ), }; #undef PHY_SETTING diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 230110b97029..4a0a6e703483 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2054,6 +2054,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, + ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT = 102, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 67d06cd002a5..5f99a32e4fe5 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -211,6 +211,7 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(10, T1S, Full), __DEFINE_LINK_MODE_NAME(10, T1S, Half), __DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half), + __DEFINE_LINK_MODE_NAME(10, T1BRR, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -251,6 +252,7 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_T1S_P2MP 1 #define __LINK_MODE_LANES_VR8 8 #define __LINK_MODE_LANES_DR8_2 8 +#define __LINK_MODE_LANES_T1BRR 1 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ @@ -374,6 +376,7 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(10, T1S, Full), __DEFINE_LINK_MODE_PARAMS(10, T1S, Half), __DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half), + __DEFINE_LINK_MODE_PARAMS(10, T1BRR, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); -- cgit v1.2.3 From 136a8066676e593cd29627219467fc222c8f3b04 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 11 Jul 2024 21:11:03 -0300 Subject: iommufd: Put constants for all the uAPI enums Relying on position in the enum makes it subtly harder when doing merge resolutions or backporting as it is easy to grab a patch and not notice it is a uAPI change with a differently ordered enum. This may become a bigger problem in next cycles when iommu_hwpt_invalidate_data_type and other per-driver enums have patches flowing through different trees. So lets start including constants for all the uAPI enums to make this safer. No functional change. Link: https://lore.kernel.org/r/0-v1-2c06ec044924+133-iommufd_uapi_const_jgg@nvidia.com Reviewed-by: Kevin Tian Reviewed-by: Yi Liu Tested-by: Yi Liu Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index e31385b75d0b..4dde745cfb7e 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -37,20 +37,20 @@ enum { IOMMUFD_CMD_BASE = 0x80, IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, - IOMMUFD_CMD_IOAS_ALLOC, - IOMMUFD_CMD_IOAS_ALLOW_IOVAS, - IOMMUFD_CMD_IOAS_COPY, - IOMMUFD_CMD_IOAS_IOVA_RANGES, - IOMMUFD_CMD_IOAS_MAP, - IOMMUFD_CMD_IOAS_UNMAP, - IOMMUFD_CMD_OPTION, - IOMMUFD_CMD_VFIO_IOAS, - IOMMUFD_CMD_HWPT_ALLOC, - IOMMUFD_CMD_GET_HW_INFO, - IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, - IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, - IOMMUFD_CMD_HWPT_INVALIDATE, - IOMMUFD_CMD_FAULT_QUEUE_ALLOC, + IOMMUFD_CMD_IOAS_ALLOC = 0x81, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS = 0x82, + IOMMUFD_CMD_IOAS_COPY = 0x83, + IOMMUFD_CMD_IOAS_IOVA_RANGES = 0x84, + IOMMUFD_CMD_IOAS_MAP = 0x85, + IOMMUFD_CMD_IOAS_UNMAP = 0x86, + IOMMUFD_CMD_OPTION = 0x87, + IOMMUFD_CMD_VFIO_IOAS = 0x88, + IOMMUFD_CMD_HWPT_ALLOC = 0x89, + IOMMUFD_CMD_GET_HW_INFO = 0x8a, + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING = 0x8b, + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP = 0x8c, + IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d, + IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e, }; /** @@ -400,8 +400,8 @@ struct iommu_hwpt_vtd_s1 { * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table */ enum iommu_hwpt_data_type { - IOMMU_HWPT_DATA_NONE, - IOMMU_HWPT_DATA_VTD_S1, + IOMMU_HWPT_DATA_NONE = 0, + IOMMU_HWPT_DATA_VTD_S1 = 1, }; /** @@ -491,8 +491,8 @@ struct iommu_hw_info_vtd { * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type */ enum iommu_hw_info_type { - IOMMU_HW_INFO_TYPE_NONE, - IOMMU_HW_INFO_TYPE_INTEL_VTD, + IOMMU_HW_INFO_TYPE_NONE = 0, + IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, }; /** @@ -629,7 +629,7 @@ struct iommu_hwpt_get_dirty_bitmap { * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 */ enum iommu_hwpt_invalidate_data_type { - IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, + IOMMU_HWPT_INVALIDATE_DATA_VTD_S1 = 0, }; /** @@ -768,7 +768,7 @@ struct iommu_hwpt_pgfault { */ enum iommufd_page_response_code { IOMMUFD_PAGE_RESP_SUCCESS = 0, - IOMMUFD_PAGE_RESP_INVALID, + IOMMUFD_PAGE_RESP_INVALID = 1, }; /** -- cgit v1.2.3 From 6e5c85c003e47fd49b72ca052b9181644e04a520 Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sat, 13 Jul 2024 02:18:58 +0000 Subject: net/sched: flower: refactor control flag definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Redefine the flower control flags as an enum, so they are included in BTF info. Make the kernel-side enum a more explicit superset of TCA_FLOWER_KEY_FLAGS_*, new flags still need to be added to both enums, but at least the bit position only has to be defined once. FLOW_DIS_ENCAPSULATION is never set for mask, so it can't be exposed to userspace in an unsupported flags mask error message, so it will be placed one bit position above the last uAPI flag. Suggested-by: Alexander Lobakin Suggested-by: Jakub Kicinski Signed-off-by: Asbjørn Sloth Tønnesen Reviewed-by: Davide Caratti Link: https://patch.msgid.link/20240713021911.1631517-2-ast@fiberby.net Signed-off-by: Jakub Kicinski --- include/net/flow_dissector.h | 14 +++++++++++--- include/uapi/linux/pkt_cls.h | 3 +++ 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 3e47e123934d..c3fce070b912 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -7,6 +7,7 @@ #include #include #include +#include struct bpf_prog; struct net; @@ -24,9 +25,16 @@ struct flow_dissector_key_control { u32 flags; }; -#define FLOW_DIS_IS_FRAGMENT BIT(0) -#define FLOW_DIS_FIRST_FRAG BIT(1) -#define FLOW_DIS_ENCAPSULATION BIT(2) +/* The control flags are kept in sync with TCA_FLOWER_KEY_FLAGS_*, as those + * flags are exposed to userspace in some error paths, ie. unsupported flags. + */ +enum flow_dissector_ctrl_flags { + FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, + FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + + /* These flags are internal to the kernel */ + FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), +}; enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index b6d38f5fd7c0..12db276f0c11 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -677,8 +677,11 @@ enum { enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), + __TCA_FLOWER_KEY_FLAGS_MAX, }; +#define TCA_FLOWER_KEY_FLAGS_MAX (__TCA_FLOWER_KEY_FLAGS_MAX - 1) + enum { TCA_FLOWER_KEY_CFM_OPT_UNSPEC, TCA_FLOWER_KEY_CFM_MD_LEVEL, -- cgit v1.2.3 From bfda5a63137bc83c344c4d995f404c8e701ff0fa Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sat, 13 Jul 2024 02:19:00 +0000 Subject: net/sched: flower: define new tunnel flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define new TCA_FLOWER_KEY_FLAGS_* flags for use in struct flow_dissector_key_control, covering the same flags as currently exposed through TCA_FLOWER_KEY_ENC_FLAGS. Put the new flags under FLOW_DIS_F_*. The idea is that we can later, move the existing flags under FLOW_DIS_F_* as well. The ynl flag names have been taken from the RFC iproute2 patch. Signed-off-by: Asbjørn Sloth Tønnesen Reviewed-by: Donald Hunter Link: https://patch.msgid.link/20240713021911.1631517-4-ast@fiberby.net Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/tc.yaml | 4 ++++ include/net/flow_dissector.h | 7 ++++++- include/uapi/linux/pkt_cls.h | 4 ++++ 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index fbbc928647fa..aa574e3827ab 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -47,6 +47,10 @@ definitions: entries: - frag - firstfrag + - tuncsum + - tundf + - tunoam + - tuncrit - name: tc-stats type: struct diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index c3fce070b912..460ea65b9e59 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -17,7 +17,8 @@ struct sk_buff; * struct flow_dissector_key_control: * @thoff: Transport header offset * @addr_type: Type of key. One of FLOW_DISSECTOR_KEY_* - * @flags: Key flags. Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAGENCAPSULATION) + * @flags: Key flags. + * Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAG|ENCAPSULATION|F_*) */ struct flow_dissector_key_control { u16 thoff; @@ -31,6 +32,10 @@ struct flow_dissector_key_control { enum flow_dissector_ctrl_flags { FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + FLOW_DIS_F_TUNNEL_CSUM = TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT = TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_OAM = TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, + FLOW_DIS_F_TUNNEL_CRIT_OPT = TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, /* These flags are internal to the kernel */ FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 12db276f0c11..3dc4388e944c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -677,6 +677,10 @@ enum { enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), + TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM = (1 << 2), + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT = (1 << 3), + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM = (1 << 4), + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT = (1 << 5), __TCA_FLOWER_KEY_FLAGS_MAX, }; -- cgit v1.2.3 From 11036bd7a0b3b05c5e1f43d107ddb02abf83adb9 Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sat, 13 Jul 2024 02:19:06 +0000 Subject: net/sched: cls_flower: rework TCA_FLOWER_KEY_ENC_FLAGS usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch changes how TCA_FLOWER_KEY_ENC_FLAGS is used, so that it is used with TCA_FLOWER_KEY_FLAGS_* flags, in the same way as TCA_FLOWER_KEY_FLAGS is currently used. Where TCA_FLOWER_KEY_FLAGS uses {key,mask}->control.flags, then TCA_FLOWER_KEY_ENC_FLAGS now uses {key,mask}->enc_control.flags, therefore {key,mask}->enc_flags is now unused. As the generic fl_set_key_flags/fl_dump_key_flags() is used with encap set to true, then fl_{set,dump}_key_enc_flags() is removed. This breaks unreleased userspace API (net-next since 2024-06-04). Signed-off-by: Asbjørn Sloth Tønnesen Tested-by: Davide Caratti Reviewed-by: Davide Caratti Link: https://patch.msgid.link/20240713021911.1631517-10-ast@fiberby.net Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 4 ++-- net/sched/cls_flower.c | 56 ++++++++++---------------------------------- 2 files changed, 15 insertions(+), 45 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 3dc4388e944c..d36d9cdf0c00 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -554,8 +554,8 @@ enum { TCA_FLOWER_KEY_SPI, /* be32 */ TCA_FLOWER_KEY_SPI_MASK, /* be32 */ - TCA_FLOWER_KEY_ENC_FLAGS, /* u32 */ - TCA_FLOWER_KEY_ENC_FLAGS_MASK, /* u32 */ + TCA_FLOWER_KEY_ENC_FLAGS, /* be32 */ + TCA_FLOWER_KEY_ENC_FLAGS_MASK, /* be32 */ __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2a440f11fe1f..e2239ab01355 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -45,11 +45,11 @@ (TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT | \ TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST) -#define TUNNEL_FLAGS_PRESENT (\ - _BITUL(IP_TUNNEL_CSUM_BIT) | \ - _BITUL(IP_TUNNEL_DONT_FRAGMENT_BIT) | \ - _BITUL(IP_TUNNEL_OAM_BIT) | \ - _BITUL(IP_TUNNEL_CRIT_OPT_BIT)) +#define TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK \ + (TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT) struct fl_flow_key { struct flow_dissector_key_meta meta; @@ -745,10 +745,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, - [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_U32, - TUNNEL_FLAGS_PRESENT), - [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_U32, - TUNNEL_FLAGS_PRESENT), + [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), + [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), }; static const struct nla_policy @@ -1866,21 +1866,6 @@ static int fl_set_key_cfm(struct nlattr **tb, return 0; } -static int fl_set_key_enc_flags(struct nlattr **tb, u32 *flags_key, - u32 *flags_mask, struct netlink_ext_ack *extack) -{ - /* mask is mandatory for flags */ - if (NL_REQ_ATTR_CHECK(extack, NULL, tb, TCA_FLOWER_KEY_ENC_FLAGS_MASK)) { - NL_SET_ERR_MSG(extack, "missing enc_flags mask"); - return -EINVAL; - } - - *flags_key = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS]); - *flags_mask = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS_MASK]); - - return 0; -} - static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -2123,8 +2108,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb, } if (tb[TCA_FLOWER_KEY_ENC_FLAGS]) - ret = fl_set_key_enc_flags(tb, &key->enc_flags.flags, - &mask->enc_flags.flags, extack); + ret = fl_set_key_flags(tb, true, &key->enc_control.flags, + &mask->enc_control.flags, extack); return ret; } @@ -3381,22 +3366,6 @@ err_cfm_opts: return err; } -static int fl_dump_key_enc_flags(struct sk_buff *skb, - struct flow_dissector_key_enc_flags *key, - struct flow_dissector_key_enc_flags *mask) -{ - if (!memchr_inv(mask, 0, sizeof(*mask))) - return 0; - - if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS, key->flags)) - return -EMSGSIZE; - - if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS_MASK, mask->flags)) - return -EMSGSIZE; - - return 0; -} - static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, struct flow_dissector_key_enc_opts *enc_opts) { @@ -3699,7 +3668,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) goto nla_put_failure; - if (fl_dump_key_enc_flags(skb, &key->enc_flags, &mask->enc_flags)) + if (fl_dump_key_flags(skb, true, key->enc_control.flags, + mask->enc_control.flags)) goto nla_put_failure; return 0; -- cgit v1.2.3 From 33c97e7c0338d921c2ae0c2e54bf17121007fb94 Mon Sep 17 00:00:00 2001 From: Günther Noack Date: Thu, 11 Jul 2024 16:54:57 +0000 Subject: landlock: Clarify documentation for struct landlock_ruleset_attr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The explanation for @handled_access_fs and @handled_access_net has significant overlap and is better explained together. * Explain the commonalities in structure-level documentation. * Clarify some wording and break up longer sentences. * Put emphasis on the word "handled" to make it clearer that "handled" is a term with special meaning in the context of Landlock. I'd like to transfer this wording into the man pages as well. Signed-off-by: Günther Noack Cc: Alejandro Colomar Cc: Konstantin Meskhidze Cc: linux-security-module@vger.kernel.org Link: https://lore.kernel.org/r/20240711165456.2148590-2-gnoack@google.com [mic: Format commit message] Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 39 +++++++++++++++++++++++---------------- 1 file changed, 23 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 68625e728f43..e76186da3260 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -12,29 +12,36 @@ #include /** - * struct landlock_ruleset_attr - Ruleset definition + * struct landlock_ruleset_attr - Ruleset definition. * - * Argument of sys_landlock_create_ruleset(). This structure can grow in - * future versions. + * Argument of sys_landlock_create_ruleset(). + * + * This structure defines a set of *handled access rights*, a set of actions on + * different object types, which should be denied by default when the ruleset is + * enacted. Vice versa, access rights that are not specifically listed here are + * not going to be denied by this ruleset when it is enacted. + * + * For historical reasons, the %LANDLOCK_ACCESS_FS_REFER right is always denied + * by default, even when its bit is not set in @handled_access_fs. In order to + * add new rules with this access right, the bit must still be set explicitly + * (cf. `Filesystem flags`_). + * + * The explicit listing of *handled access rights* is required for backwards + * compatibility reasons. In most use cases, processes that use Landlock will + * *handle* a wide range or all access rights that they know about at build time + * (and that they have tested with a kernel that supported them all). + * + * This structure can grow in future Landlock versions. */ struct landlock_ruleset_attr { /** - * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_) - * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them: it is a deny-by-default list that should - * contain as much Landlock access rights as possible. Indeed, all - * Landlock filesystem access rights that are not part of - * handled_access_fs are allowed. This is needed for backward - * compatibility reasons. One exception is the - * %LANDLOCK_ACCESS_FS_REFER access right, which is always implicitly - * handled, but must still be explicitly handled to add new rules with - * this access right. + * @handled_access_fs: Bitmask of handled filesystem actions + * (cf. `Filesystem flags`_). */ __u64 handled_access_fs; /** - * @handled_access_net: Bitmask of actions (cf. `Network flags`_) - * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them. + * @handled_access_net: Bitmask of handled network actions (cf. `Network + * flags`_). */ __u64 handled_access_net; }; -- cgit v1.2.3 From 88caf544c9305313e1c48ac1a437faa5df8fff06 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 1 Jul 2024 17:31:46 -0500 Subject: KVM: SEV: Provide support for SNP_GUEST_REQUEST NAE event Version 2 of GHCB specification added support for the SNP Guest Request Message NAE event. The event allows for an SEV-SNP guest to make requests to the SEV-SNP firmware through the hypervisor using the SNP_GUEST_REQUEST API defined in the SEV-SNP firmware specification. This is used by guests primarily to request attestation reports from firmware. There are other request types are available as well, but the specifics of what guest requests are being made generally does not affect how they are handled by the hypervisor, which only serves as a proxy for the guest requests and firmware responses. Implement handling for these events. When an SNP Guest Request is issued, the guest will provide its own request/response pages, which could in theory be passed along directly to firmware. However, these pages would need special care: - Both pages are from shared guest memory, so they need to be protected from migration/etc. occurring while firmware reads/writes to them. At a minimum, this requires elevating the ref counts and potentially needing an explicit pinning of the memory. This places additional restrictions on what type of memory backends userspace can use for shared guest memory since there would be some reliance on using refcounted pages. - The response page needs to be switched to Firmware-owned state before the firmware can write to it, which can lead to potential host RMP #PFs if the guest is misbehaved and hands the host a guest page that KVM is writing to for other reasons (e.g. virtio buffers). Both of these issues can be avoided completely by using separately-allocated bounce pages for both the request/response pages and passing those to firmware instead. So that's the approach taken here. Signed-off-by: Brijesh Singh Co-developed-by: Alexey Kardashevskiy Signed-off-by: Alexey Kardashevskiy Co-developed-by: Ashish Kalra Signed-off-by: Ashish Kalra Reviewed-by: Tom Lendacky Reviewed-by: Liam Merwick [mdr: ensure FW command failures are indicated to guest, drop extended request handling to be re-written as separate patch, massage commit] Signed-off-by: Michael Roth Message-ID: <20240701223148.3798365-2-michael.roth@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 134 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.h | 3 + include/uapi/linux/sev-guest.h | 3 + 3 files changed, 140 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 20b92f4b0906..fdf3ba7dda07 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -326,6 +327,78 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_decommission(handle); } +/* + * This sets up bounce buffers/firmware pages to handle SNP Guest Request + * messages (e.g. attestation requests). See "SNP Guest Request" in the GHCB + * 2.0 specification for more details. + * + * Technically, when an SNP Guest Request is issued, the guest will provide its + * own request/response pages, which could in theory be passed along directly + * to firmware rather than using bounce pages. However, these pages would need + * special care: + * + * - Both pages are from shared guest memory, so they need to be protected + * from migration/etc. occurring while firmware reads/writes to them. At a + * minimum, this requires elevating the ref counts and potentially needing + * an explicit pinning of the memory. This places additional restrictions + * on what type of memory backends userspace can use for shared guest + * memory since there is some reliance on using refcounted pages. + * + * - The response page needs to be switched to Firmware-owned[1] state + * before the firmware can write to it, which can lead to potential + * host RMP #PFs if the guest is misbehaved and hands the host a + * guest page that KVM might write to for other reasons (e.g. virtio + * buffers/etc.). + * + * Both of these issues can be avoided completely by using separately-allocated + * bounce pages for both the request/response pages and passing those to + * firmware instead. So that's what is being set up here. + * + * Guest requests rely on message sequence numbers to ensure requests are + * issued to firmware in the order the guest issues them, so concurrent guest + * requests generally shouldn't happen. But a misbehaved guest could issue + * concurrent guest requests in theory, so a mutex is used to serialize + * access to the bounce buffers. + * + * [1] See the "Page States" section of the SEV-SNP Firmware ABI for more + * details on Firmware-owned pages, along with "RMP and VMPL Access Checks" + * in the APM for details on the related RMP restrictions. + */ +static int snp_guest_req_init(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct page *req_page; + + req_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!req_page) + return -ENOMEM; + + sev->guest_resp_buf = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!sev->guest_resp_buf) { + __free_page(req_page); + return -EIO; + } + + sev->guest_req_buf = page_address(req_page); + mutex_init(&sev->guest_req_mutex); + + return 0; +} + +static void snp_guest_req_cleanup(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + + if (sev->guest_resp_buf) + snp_free_firmware_page(sev->guest_resp_buf); + + if (sev->guest_req_buf) + __free_page(virt_to_page(sev->guest_req_buf)); + + sev->guest_req_buf = NULL; + sev->guest_resp_buf = NULL; +} + static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, struct kvm_sev_init *data, unsigned long vm_type) @@ -376,6 +449,10 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, if (ret) goto e_free; + /* This needs to happen after SEV/SNP firmware initialization. */ + if (vm_type == KVM_X86_SNP_VM && snp_guest_req_init(kvm)) + goto e_free; + INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); sev->need_init = false; @@ -2834,6 +2911,8 @@ void sev_vm_destroy(struct kvm *kvm) } if (sev_snp_guest(kvm)) { + snp_guest_req_cleanup(kvm); + /* * Decomission handles unbinding of the ASID. If it fails for * some unexpected reason, just leak the ASID. @@ -3299,6 +3378,13 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; + case SVM_VMGEXIT_GUEST_REQUEST: + if (!sev_snp_guest(vcpu->kvm) || + !PAGE_ALIGNED(control->exit_info_1) || + !PAGE_ALIGNED(control->exit_info_2) || + control->exit_info_1 == control->exit_info_2) + goto vmgexit_err; + break; default: reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; @@ -3917,6 +4003,51 @@ out: return ret; } +static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa) +{ + struct sev_data_snp_guest_request data = {0}; + struct kvm *kvm = svm->vcpu.kvm; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + sev_ret_code fw_err = 0; + int ret; + + if (!sev_snp_guest(kvm)) + return -EINVAL; + + mutex_lock(&sev->guest_req_mutex); + + if (kvm_read_guest(kvm, req_gpa, sev->guest_req_buf, PAGE_SIZE)) { + ret = -EIO; + goto out_unlock; + } + + data.gctx_paddr = __psp_pa(sev->snp_context); + data.req_paddr = __psp_pa(sev->guest_req_buf); + data.res_paddr = __psp_pa(sev->guest_resp_buf); + + /* + * Firmware failures are propagated on to guest, but any other failure + * condition along the way should be reported to userspace. E.g. if + * the PSP is dead and commands are timing out. + */ + ret = sev_issue_cmd(kvm, SEV_CMD_SNP_GUEST_REQUEST, &data, &fw_err); + if (ret && !fw_err) + goto out_unlock; + + if (kvm_write_guest(kvm, resp_gpa, sev->guest_resp_buf, PAGE_SIZE)) { + ret = -EIO; + goto out_unlock; + } + + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, SNP_GUEST_ERR(0, fw_err)); + + ret = 1; /* resume guest */ + +out_unlock: + mutex_unlock(&sev->guest_req_mutex); + return ret; +} + static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -4191,6 +4322,9 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = 1; break; + case SVM_VMGEXIT_GUEST_REQUEST: + ret = snp_handle_guest_req(svm, control->exit_info_1, control->exit_info_2); + break; case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f0ab0d93cd20..8528f40efffc 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -94,6 +94,9 @@ struct kvm_sev_info { struct misc_cg *misc_cg; /* For misc cgroup accounting */ atomic_t migration_in_progress; void *snp_context; /* SNP guest context page */ + void *guest_req_buf; /* Bounce buffer for SNP Guest Request input */ + void *guest_resp_buf; /* Bounce buffer for SNP Guest Request output */ + struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */ }; struct kvm_svm { diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 154a87a1eca9..fcdfea767fca 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -89,6 +89,9 @@ struct snp_ext_report_req { #define SNP_GUEST_FW_ERR_MASK GENMASK_ULL(31, 0) #define SNP_GUEST_VMM_ERR_SHIFT 32 #define SNP_GUEST_VMM_ERR(x) (((u64)x) << SNP_GUEST_VMM_ERR_SHIFT) +#define SNP_GUEST_FW_ERR(x) ((x) & SNP_GUEST_FW_ERR_MASK) +#define SNP_GUEST_ERR(vmm_err, fw_err) (SNP_GUEST_VMM_ERR(vmm_err) | \ + SNP_GUEST_FW_ERR(fw_err)) #define SNP_GUEST_VMM_ERR_INVALID_LEN 1 #define SNP_GUEST_VMM_ERR_BUSY 2 -- cgit v1.2.3 From 332d2c1d713e232e163386c35a3ba0c1b90df83f Mon Sep 17 00:00:00 2001 From: Michael Roth Date: Wed, 1 May 2024 03:52:10 -0500 Subject: crypto: ccp: Add the SNP_VLEK_LOAD command When requesting an attestation report a guest is able to specify whether it wants SNP firmware to sign the report using either a Versioned Chip Endorsement Key (VCEK), which is derived from chip-unique secrets, or a Versioned Loaded Endorsement Key (VLEK) which is obtained from an AMD Key Derivation Service (KDS) and derived from seeds allocated to enrolled cloud service providers (CSPs). For VLEK keys, an SNP_VLEK_LOAD SNP firmware command is used to load them into the system after obtaining them from the KDS. Add a corresponding userspace interface so to allow the loading of VLEK keys into the system. See SEV-SNP Firmware ABI 1.54, SNP_VLEK_LOAD for more details. Reviewed-by: Tom Lendacky Signed-off-by: Michael Roth Message-ID: <20240501085210.2213060-21-michael.roth@amd.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/coco/sev-guest.rst | 19 ++++++++++++++++++ drivers/crypto/ccp/sev-dev.c | 36 +++++++++++++++++++++++++++++++++++ include/uapi/linux/psp-sev.h | 27 ++++++++++++++++++++++++++ 3 files changed, 82 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index e1eaf6a830ce..de68d3a4b540 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -176,6 +176,25 @@ to SNP_CONFIG command defined in the SEV-SNP spec. The current values of the firmware parameters affected by this command can be queried via SNP_PLATFORM_STATUS. +2.7 SNP_VLEK_LOAD +----------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (in): struct sev_user_data_snp_vlek_load +:Returns (out): 0 on success, -negative on error + +When requesting an attestation report a guest is able to specify whether +it wants SNP firmware to sign the report using either a Versioned Chip +Endorsement Key (VCEK), which is derived from chip-unique secrets, or a +Versioned Loaded Endorsement Key (VLEK) which is obtained from an AMD +Key Derivation Service (KDS) and derived from seeds allocated to +enrolled cloud service providers. + +In the case of VLEK keys, the SNP_VLEK_LOAD SNP command is used to load +them into the system after obtaining them from the KDS, and corresponds +closely to the SNP_VLEK_LOAD firmware command specified in the SEV-SNP +spec. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 2102377f727b..97a7959406ee 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -2027,6 +2027,39 @@ static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); } +static int sev_ioctl_do_snp_vlek_load(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_vlek_load input; + void *blob; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&input, u64_to_user_ptr(argp->data), sizeof(input))) + return -EFAULT; + + if (input.len != sizeof(input) || input.vlek_wrapped_version != 0) + return -EINVAL; + + blob = psp_copy_user_blob(input.vlek_wrapped_address, + sizeof(struct sev_user_data_snp_wrapped_vlek_hashstick)); + if (IS_ERR(blob)) + return PTR_ERR(blob); + + input.vlek_wrapped_address = __psp_pa(blob); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_VLEK_LOAD, &input, &argp->error); + + kfree(blob); + + return ret; +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -2087,6 +2120,9 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SNP_SET_CONFIG: ret = sev_ioctl_do_snp_set_config(&input, writable); break; + case SNP_VLEK_LOAD: + ret = sev_ioctl_do_snp_vlek_load(&input, writable); + break; default: ret = -EINVAL; goto out; diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index b7a2c2ee35b7..2289b7c76c59 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -31,6 +31,7 @@ enum { SNP_PLATFORM_STATUS, SNP_COMMIT, SNP_SET_CONFIG, + SNP_VLEK_LOAD, SEV_MAX, }; @@ -214,6 +215,32 @@ struct sev_user_data_snp_config { __u8 rsvd1[52]; } __packed; +/** + * struct sev_data_snp_vlek_load - SNP_VLEK_LOAD structure + * + * @len: length of the command buffer read by the PSP + * @vlek_wrapped_version: version of wrapped VLEK hashstick (Must be 0h) + * @rsvd: reserved + * @vlek_wrapped_address: address of a wrapped VLEK hashstick + * (struct sev_user_data_snp_wrapped_vlek_hashstick) + */ +struct sev_user_data_snp_vlek_load { + __u32 len; /* In */ + __u8 vlek_wrapped_version; /* In */ + __u8 rsvd[3]; /* In */ + __u64 vlek_wrapped_address; /* In */ +} __packed; + +/** + * struct sev_user_data_snp_vlek_wrapped_vlek_hashstick - Wrapped VLEK data + * + * @data: Opaque data provided by AMD KDS (as described in SEV-SNP Firmware ABI + * 1.54, SNP_VLEK_LOAD) + */ +struct sev_user_data_snp_wrapped_vlek_hashstick { + __u8 data[432]; /* In */ +} __packed; + /** * struct sev_issue_cmd - SEV ioctl parameters * -- cgit v1.2.3 From f4b89d8ce5a835afa51404977ee7e3889c2b9722 Mon Sep 17 00:00:00 2001 From: Günther Noack Date: Mon, 15 Jul 2024 16:03:29 +0000 Subject: landlock: Various documentation improvements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Fix some typos, incomplete or confusing phrases. * Split paragraphs where appropriate. * List the same error code multiple times, if it has multiple possible causes. * Bring wording closer to the man page wording, which has undergone more thorough review (esp. for LANDLOCK_ACCESS_FS_WRITE_FILE). * Small semantic clarifications * Call the ephemeral port range "ephemeral" * Clarify reasons for EFAULT in landlock_add_rule() * Clarify @rule_type doc for landlock_add_rule() This is a collection of small fixes which I collected when preparing the corresponding man pages [1]. Cc: Alejandro Colomar Cc: Konstantin Meskhidze Link: https://lore.kernel.org/r/20240715155554.2791018-1-gnoack@google.com [1] Signed-off-by: Günther Noack Link: https://lore.kernel.org/r/20240715160328.2792835-2-gnoack@google.com [mic: Add label to link, fix formatting spotted by make htmldocs, synchronize userspace-api documentation's date] Signed-off-by: Mickaël Salaün --- Documentation/userspace-api/landlock.rst | 2 +- include/uapi/linux/landlock.h | 27 ++++++++++++++------------- security/landlock/syscalls.c | 17 +++++++++-------- 3 files changed, 24 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst index 07b63aec56fa..37dafce8038b 100644 --- a/Documentation/userspace-api/landlock.rst +++ b/Documentation/userspace-api/landlock.rst @@ -8,7 +8,7 @@ Landlock: unprivileged access control ===================================== :Author: Mickaël Salaün -:Date: April 2024 +:Date: July 2024 The goal of Landlock is to enable to restrict ambient rights (e.g. global filesystem or network access) for a set of processes. Because Landlock diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index e76186da3260..2c8dbc74b955 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -104,20 +104,21 @@ struct landlock_path_beneath_attr { */ struct landlock_net_port_attr { /** - * @allowed_access: Bitmask of allowed access network for a port + * @allowed_access: Bitmask of allowed network actions for a port * (cf. `Network flags`_). */ __u64 allowed_access; /** * @port: Network port in host endianness. * - * It should be noted that port 0 passed to :manpage:`bind(2)` will - * bind to an available port from a specific port range. This can be - * configured thanks to the ``/proc/sys/net/ipv4/ip_local_port_range`` - * sysctl (also used for IPv6). A Landlock rule with port 0 and the - * ``LANDLOCK_ACCESS_NET_BIND_TCP`` right means that requesting to bind - * on port 0 is allowed and it will automatically translate to binding - * on the related port range. + * It should be noted that port 0 passed to :manpage:`bind(2)` will bind + * to an available port from the ephemeral port range. This can be + * configured with the ``/proc/sys/net/ipv4/ip_local_port_range`` sysctl + * (also used for IPv6). + * + * A Landlock rule with port 0 and the ``LANDLOCK_ACCESS_NET_BIND_TCP`` + * right means that requesting to bind on port 0 is allowed and it will + * automatically translate to binding on the related port range. */ __u64 port; }; @@ -138,10 +139,10 @@ struct landlock_net_port_attr { * The following access rights apply only to files: * * - %LANDLOCK_ACCESS_FS_EXECUTE: Execute a file. - * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. Note that - * you might additionally need the %LANDLOCK_ACCESS_FS_TRUNCATE right in order - * to overwrite files with :manpage:`open(2)` using ``O_TRUNC`` or - * :manpage:`creat(2)`. + * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. When + * opening files for writing, you will often additionally need the + * %LANDLOCK_ACCESS_FS_TRUNCATE right. In many cases, these system calls + * truncate existing files when overwriting them (e.g., :manpage:`creat(2)`). * - %LANDLOCK_ACCESS_FS_READ_FILE: Open a file with read access. * - %LANDLOCK_ACCESS_FS_TRUNCATE: Truncate a file with :manpage:`truncate(2)`, * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with @@ -263,7 +264,7 @@ struct landlock_net_port_attr { * These flags enable to restrict a sandboxed process to a set of network * actions. This is supported since the Landlock ABI version 4. * - * TCP sockets with allowed actions: + * The following access rights apply to TCP port numbers: * * - %LANDLOCK_ACCESS_NET_BIND_TCP: Bind a TCP socket to a local port. * - %LANDLOCK_ACCESS_NET_CONNECT_TCP: Connect an active TCP socket to diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 03b470f5a85a..ccc8bc6c1584 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -378,8 +378,7 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, * with the new rule. * @rule_type: Identify the structure type pointed to by @rule_attr: * %LANDLOCK_RULE_PATH_BENEATH or %LANDLOCK_RULE_NET_PORT. - * @rule_attr: Pointer to a rule (only of type &struct - * landlock_path_beneath_attr for now). + * @rule_attr: Pointer to a rule (matching the @rule_type). * @flags: Must be 0. * * This system call enables to define a new rule and add it to an existing @@ -390,18 +389,20 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EAFNOSUPPORT: @rule_type is %LANDLOCK_RULE_NET_PORT but TCP/IP is not * supported by the running kernel; - * - %EINVAL: @flags is not 0, or inconsistent access in the rule (i.e. + * - %EINVAL: @flags is not 0; + * - %EINVAL: The rule accesses are inconsistent (i.e. * &landlock_path_beneath_attr.allowed_access or - * &landlock_net_port_attr.allowed_access is not a subset of the - * ruleset handled accesses), or &landlock_net_port_attr.port is - * greater than 65535; - * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access); + * &landlock_net_port_attr.allowed_access is not a subset of the ruleset + * handled accesses) + * - %EINVAL: &landlock_net_port_attr.port is greater than 65535; + * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access is + * 0); * - %EBADF: @ruleset_fd is not a file descriptor for the current thread, or a * member of @rule_attr is not a file descriptor as expected; * - %EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of * @rule_attr is not the expected file descriptor type; * - %EPERM: @ruleset_fd has no write access to the underlying ruleset; - * - %EFAULT: @rule_attr inconsistency. + * - %EFAULT: @rule_attr was not a valid address. */ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, const enum landlock_rule_type, rule_type, -- cgit v1.2.3 From 9651fcedf7b92d3f7f1ab179e8ab55b85ee10fc1 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 8 Dec 2022 17:55:04 +0100 Subject: mm: add MAP_DROPPABLE for designating always lazily freeable mappings The vDSO getrandom() implementation works with a buffer allocated with a new system call that has certain requirements: - It shouldn't be written to core dumps. * Easy: VM_DONTDUMP. - It should be zeroed on fork. * Easy: VM_WIPEONFORK. - It shouldn't be written to swap. * Uh-oh: mlock is rlimited. * Uh-oh: mlock isn't inherited by forks. - It shouldn't reserve actual memory, but it also shouldn't crash when page faulting in memory if none is available * Uh-oh: VM_NORESERVE means segfaults. It turns out that the vDSO getrandom() function has three really nice characteristics that we can exploit to solve this problem: 1) Due to being wiped during fork(), the vDSO code is already robust to having the contents of the pages it reads zeroed out midway through the function's execution. 2) In the absolute worst case of whatever contingency we're coding for, we have the option to fallback to the getrandom() syscall, and everything is fine. 3) The buffers the function uses are only ever useful for a maximum of 60 seconds -- a sort of cache, rather than a long term allocation. These characteristics mean that we can introduce VM_DROPPABLE, which has the following semantics: a) It never is written out to swap. b) Under memory pressure, mm can just drop the pages (so that they're zero when read back again). c) It is inherited by fork. d) It doesn't count against the mlock budget, since nothing is locked. e) If there's not enough memory to service a page fault, it's not fatal, and no signal is sent. This way, allocations used by vDSO getrandom() can use: VM_DROPPABLE | VM_DONTDUMP | VM_WIPEONFORK | VM_NORESERVE And there will be no problem with OOMing, crashing on overcommitment, using memory when not in use, not wiping on fork(), coredumps, or writing out to swap. In order to let vDSO getrandom() use this, expose these via mmap(2) as MAP_DROPPABLE. Note that this involves removing the MADV_FREE special case from sort_folio(), which according to Yu Zhao is unnecessary and will simply result in an extra call to shrink_folio_list() in the worst case. The chunk removed reenables the swapbacked flag, which we don't want for VM_DROPPABLE, and we can't conditionalize it here because there isn't a vma reference available. Finally, the provided self test ensures that this is working as desired. Cc: linux-mm@kvack.org Acked-by: David Hildenbrand Signed-off-by: Jason A. Donenfeld --- fs/proc/task_mmu.c | 1 + include/linux/mm.h | 7 +++++ include/linux/userfaultfd_k.h | 3 ++ include/trace/events/mmflags.h | 7 +++++ include/uapi/linux/mman.h | 1 + mm/ksm.c | 2 +- mm/madvise.c | 5 +++- mm/memory.c | 13 +++++++++ mm/mempolicy.c | 3 ++ mm/mlock.c | 2 +- mm/mmap.c | 30 +++++++++++++++++++ mm/rmap.c | 22 ++++++++++++-- mm/vmscan.c | 9 ------ tools/include/uapi/linux/mman.h | 1 + tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/droppable.c | 53 ++++++++++++++++++++++++++++++++++ 17 files changed, 146 insertions(+), 15 deletions(-) create mode 100644 tools/testing/selftests/mm/droppable.c (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 71e5039d940d..46f0b0fe9ee3 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -708,6 +708,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_SHADOW_STACK)] = "ss", #endif #ifdef CONFIG_64BIT + [ilog2(VM_DROPPABLE)] = "dp", [ilog2(VM_SEALED)] = "sl", #endif }; diff --git a/include/linux/mm.h b/include/linux/mm.h index eb7c96d24ac0..e078c2890bf8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -406,6 +406,13 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif +#ifdef CONFIG_64BIT +#define VM_DROPPABLE_BIT 40 +#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#else +#define VM_DROPPABLE VM_NONE +#endif + #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 05d59f74fc88..a12bcf042551 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, { vm_flags &= __VM_UFFD_FLAGS; + if (vm_flags & VM_DROPPABLE) + return false; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index e46d6e82765e..b63d211bd141 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -165,6 +165,12 @@ IF_HAVE_PG_ARCH_X(arch_3) # define IF_HAVE_UFFD_MINOR(flag, name) #endif +#ifdef CONFIG_64BIT +# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name}, +#else +# define IF_HAVE_VM_DROPPABLE(flag, name) +#endif + #define __def_vmaflag_names \ {VM_READ, "read" }, \ {VM_WRITE, "write" }, \ @@ -197,6 +203,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \ {VM_MIXEDMAP, "mixedmap" }, \ {VM_HUGEPAGE, "hugepage" }, \ {VM_NOHUGEPAGE, "nohugepage" }, \ +IF_HAVE_VM_DROPPABLE(VM_DROPPABLE, "droppable" ) \ {VM_MERGEABLE, "mergeable" } \ #define show_vma_flags(flags) \ diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index a246e11988d5..e89d00528f2f 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/mm/ksm.c b/mm/ksm.c index 34c4820e0d3d..8778eb7c40f8 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -717,7 +717,7 @@ static bool vma_ksm_compatible(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | VM_HUGETLB | - VM_MIXEDMAP)) + VM_MIXEDMAP| VM_DROPPABLE)) return false; /* just ignore the advice */ if (vma_is_dax(vma)) diff --git a/mm/madvise.c b/mm/madvise.c index a77893462b92..cba5bc652fc4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1068,13 +1068,16 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: + if (vma->vm_flags & VM_DROPPABLE) + return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: - if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) + if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) || + (vma->vm_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; diff --git a/mm/memory.c b/mm/memory.c index d10e616d7389..98d9a4485d24 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5660,6 +5660,7 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, /* If the fault handler drops the mmap_lock, vma may be freed */ struct mm_struct *mm = vma->vm_mm; vm_fault_t ret; + bool is_droppable; __set_current_state(TASK_RUNNING); @@ -5674,6 +5675,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, goto out; } + is_droppable = !!(vma->vm_flags & VM_DROPPABLE); + /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. @@ -5688,8 +5691,18 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, else ret = __handle_mm_fault(vma, address, flags); + /* + * Warning: It is no longer safe to dereference vma-> after this point, + * because mmap_lock might have been dropped by __handle_mm_fault(), so + * vma might be destroyed from underneath us. + */ + lru_gen_exit_fault(); + /* If the mapping is droppable, then errors due to OOM aren't fatal. */ + if (is_droppable) + ret &= ~VM_FAULT_OOM; + if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* diff --git a/mm/mempolicy.c b/mm/mempolicy.c index aec756ae5637..32291ab25960 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2300,6 +2300,9 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct pgoff_t ilx; struct page *page; + if (vma->vm_flags & VM_DROPPABLE) + gfp |= __GFP_NOWARN; + pol = get_vma_policy(vma, addr, order, &ilx); page = alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, pol, ilx, numa_node_id()); diff --git a/mm/mlock.c b/mm/mlock.c index 30b51cdea89d..b87b3d8cc9cc 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -485,7 +485,7 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || - vma_is_dax(vma) || vma_is_secretmem(vma)) + vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; diff --git a/mm/mmap.c b/mm/mmap.c index 83b4682ec85c..8aeedeb784c2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1369,6 +1369,36 @@ unsigned long do_mmap(struct file *file, unsigned long addr, pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; + case MAP_DROPPABLE: + if (VM_DROPPABLE == VM_NONE) + return -ENOTSUPP; + /* + * A locked or stack area makes no sense to be droppable. + * + * Also, since droppable pages can just go away at any time + * it makes no sense to copy them on fork or dump them. + * + * And don't attempt to combine with hugetlb for now. + */ + if (flags & (MAP_LOCKED | MAP_HUGETLB)) + return -EINVAL; + if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP)) + return -EINVAL; + + vm_flags |= VM_DROPPABLE; + + /* + * If the pages can be dropped, then it doesn't make + * sense to reserve them. + */ + vm_flags |= VM_NORESERVE; + + /* + * Likewise, they're volatile enough that they + * shouldn't survive forks or coredumps. + */ + vm_flags |= VM_WIPEONFORK | VM_DONTDUMP; + fallthrough; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. diff --git a/mm/rmap.c b/mm/rmap.c index e8fc5ecb59b2..1f9b5a9cb121 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1397,7 +1397,12 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); - __folio_set_swapbacked(folio); + /* + * VM_DROPPABLE mappings don't swap; instead they're just dropped when + * under memory pressure. + */ + if (!(vma->vm_flags & VM_DROPPABLE)) + __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, true); if (likely(!folio_test_large(folio))) { @@ -1841,7 +1846,13 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && - !folio_test_dirty(folio)) { + (!folio_test_dirty(folio) || + /* + * Unlike MADV_FREE mappings, VM_DROPPABLE + * ones can be dropped even if they've + * been dirtied. + */ + (vma->vm_flags & VM_DROPPABLE))) { dec_mm_counter(mm, MM_ANONPAGES); goto discard; } @@ -1851,7 +1862,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); - folio_set_swapbacked(folio); + /* + * Unlike MADV_FREE mappings, VM_DROPPABLE ones + * never get swap backed on failure to drop. + */ + if (!(vma->vm_flags & VM_DROPPABLE)) + folio_set_swapbacked(folio); ret = false; page_vma_mapped_walk_done(&pvmw); break; diff --git a/mm/vmscan.c b/mm/vmscan.c index 2e34de9cd0d4..5ef0ee4610d6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4265,15 +4265,6 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c return true; } - /* dirty lazyfree */ - if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) { - success = lru_gen_del_folio(lruvec, folio, true); - VM_WARN_ON_ONCE_FOLIO(!success, folio); - folio_set_swapbacked(folio); - lruvec_add_folio_tail(lruvec, folio); - return true; - } - /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index a246e11988d5..e89d00528f2f 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 0b9ab987601c..a8beeb43c2b5 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -49,3 +49,4 @@ hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test seal_elf +droppable diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 3b49bc3d0a3b..e3e5740e13e1 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -73,6 +73,7 @@ TEST_GEN_FILES += ksm_functional_tests TEST_GEN_FILES += mdwe_test TEST_GEN_FILES += hugetlb_fault_after_madv TEST_GEN_FILES += hugetlb_madv_vs_map +TEST_GEN_FILES += droppable ifneq ($(ARCH),arm64) TEST_GEN_FILES += soft-dirty diff --git a/tools/testing/selftests/mm/droppable.c b/tools/testing/selftests/mm/droppable.c new file mode 100644 index 000000000000..f3d9ecf96890 --- /dev/null +++ b/tools/testing/selftests/mm/droppable.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" + +int main(int argc, char *argv[]) +{ + size_t alloc_size = 134217728; + size_t page_size = getpagesize(); + void *alloc; + pid_t child; + + ksft_print_header(); + ksft_set_plan(1); + + alloc = mmap(0, alloc_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_DROPPABLE, -1, 0); + assert(alloc != MAP_FAILED); + memset(alloc, 'A', alloc_size); + for (size_t i = 0; i < alloc_size; i += page_size) + assert(*(uint8_t *)(alloc + i)); + + child = fork(); + assert(child >= 0); + if (!child) { + for (;;) + *(char *)malloc(page_size) = 'B'; + } + + for (bool done = false; !done;) { + for (size_t i = 0; i < alloc_size; i += page_size) { + if (!*(uint8_t *)(alloc + i)) { + done = true; + break; + } + } + } + kill(child, SIGTERM); + + ksft_test_result_pass("MAP_DROPPABLE: PASS\n"); + exit(KSFT_PASS); +} -- cgit v1.2.3 From 4ad10a5f5f78a5b3e525a63bd075a4eb1139dde1 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 18 Nov 2022 17:23:34 +0100 Subject: random: introduce generic vDSO getrandom() implementation Provide a generic C vDSO getrandom() implementation, which operates on an opaque state returned by vgetrandom_alloc() and produces random bytes the same way as getrandom(). This has the following API signature: ssize_t vgetrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len); The return value and the first three arguments are the same as ordinary getrandom(), while the last two arguments are a pointer to the opaque allocated state and its size. Were all five arguments passed to the getrandom() syscall, nothing different would happen, and the functions would have the exact same behavior. The actual vDSO RNG algorithm implemented is the same one implemented by drivers/char/random.c, using the same fast-erasure techniques as that. Should the in-kernel implementation change, so too will the vDSO one. It requires an implementation of ChaCha20 that does not use any stack, in order to maintain forward secrecy if a multi-threaded program forks (though this does not account for a similar issue with SA_SIGINFO copying registers to the stack), so this is left as an architecture-specific fill-in. Stack-less ChaCha20 is an easy algorithm to implement on a variety of architectures, so this shouldn't be too onerous. Initially, the state is keyless, and so the first call makes a getrandom() syscall to generate that key, and then uses it for subsequent calls. By keeping track of a generation counter, it knows when its key is invalidated and it should fetch a new one using the syscall. Later, more than just a generation counter might be used. Since MADV_WIPEONFORK is set on the opaque state, the key and related state is wiped during a fork(), so secrets don't roll over into new processes, and the same state doesn't accidentally generate the same random stream. The generation counter, as well, is always >0, so that the 0 counter is a useful indication of a fork() or otherwise uninitialized state. If the kernel RNG is not yet initialized, then the vDSO always calls the syscall, because that behavior cannot be emulated in userspace, but fortunately that state is short lived and only during early boot. If it has been initialized, then there is no need to inspect the `flags` argument, because the behavior does not change post-initialization regardless of the `flags` value. Since the opaque state passed to it is mutated, vDSO getrandom() is not reentrant, when used with the same opaque state, which libc should be mindful of. The function works over an opaque per-thread state of a particular size, which must be marked VM_WIPEONFORK, VM_DONTDUMP, VM_NORESERVE, and VM_DROPPABLE for proper operation. Over time, the nuances of these allocations may change or grow or even differ based on architectural features. The opaque state passed to vDSO getrandom() must be allocated using the mmap_flags and mmap_prot parameters provided by the vgetrandom_opaque_params struct, which also contains the size of each state. That struct can be obtained with a call to vgetrandom(NULL, 0, 0, ¶ms, ~0UL). Then, libc can call mmap(2) and slice up the returned array into a state per each thread, while ensuring that no single state straddles a page boundary. Libc is expected to allocate a chunk of these on first use, and then dole them out to threads as they're created, allocating more when needed. vDSO getrandom() provides the ability for userspace to generate random bytes quickly and safely, and is intended to be integrated into libc's thread management. As an illustrative example, the introduced code in the vdso_test_getrandom self test later in this series might be used to do the same outside of libc. In a libc the various pthread-isms are expected to be elided into libc internals. Reviewed-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld --- MAINTAINERS | 2 + drivers/char/random.c | 18 +++- include/uapi/linux/random.h | 15 +++ include/vdso/datapage.h | 11 ++ include/vdso/getrandom.h | 46 ++++++++ lib/vdso/Kconfig | 5 + lib/vdso/getrandom.c | 251 ++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 347 insertions(+), 1 deletion(-) create mode 100644 include/vdso/getrandom.h create mode 100644 lib/vdso/getrandom.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 2a4d4b3a9b40..7edb30b4abf0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18745,6 +18745,8 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git F: Documentation/devicetree/bindings/rng/microsoft,vmgenid.yaml F: drivers/char/random.c F: drivers/virt/vmgenid.c +F: include/vdso/getrandom.h +F: lib/vdso/getrandom.c RAPIDIO SUBSYSTEM M: Matt Porter diff --git a/drivers/char/random.c b/drivers/char/random.c index 2597cb43f438..b02a12436750 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* - * Copyright (C) 2017-2022 Jason A. Donenfeld . All Rights Reserved. + * Copyright (C) 2017-2024 Jason A. Donenfeld . All Rights Reserved. * Copyright Matt Mackall , 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * @@ -56,6 +56,10 @@ #include #include #include +#ifdef CONFIG_VDSO_GETRANDOM +#include +#include +#endif #include #include #include @@ -271,6 +275,15 @@ static void crng_reseed(struct work_struct *work) if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); +#ifdef CONFIG_VDSO_GETRANDOM + /* base_crng.generation's invalid value is ULONG_MAX, while + * _vdso_rng_data.generation's invalid value is 0, so add one to the + * former to arrive at the latter. Use smp_store_release so that this + * is ordered with the write above to base_crng.generation. Pairs with + * the smp_rmb() before the syscall in the vDSO code. + */ + smp_store_release(&_vdso_rng_data.generation, next_gen + 1); +#endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); @@ -721,6 +734,9 @@ static void __cold _credit_init_bits(size_t bits) if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); +#ifdef CONFIG_VDSO_GETRANDOM + WRITE_ONCE(_vdso_rng_data.is_ready, true); +#endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index e744c23582eb..2a3fe4c2cdc9 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -55,4 +55,19 @@ struct rand_pool_info { #define GRND_RANDOM 0x0002 #define GRND_INSECURE 0x0004 +/** + * struct vgetrandom_opaque_params - arguments for allocating memory for vgetrandom + * + * @size_per_opaque_state: Size of each state that is to be passed to vgetrandom(). + * @mmap_prot: Value of the prot argument in mmap(2). + * @mmap_flags: Value of the flags argument in mmap(2). + * @reserved: Reserved for future use. + */ +struct vgetrandom_opaque_params { + __u32 size_of_opaque_state; + __u32 mmap_prot; + __u32 mmap_flags; + __u32 reserved[13]; +}; + #endif /* _UAPI_LINUX_RANDOM_H */ diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index d04d394db064..05e5787beb73 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -113,6 +113,16 @@ struct vdso_data { struct arch_vdso_data arch_data; }; +/** + * struct vdso_rng_data - vdso RNG state information + * @generation: counter representing the number of RNG reseeds + * @is_ready: boolean signaling whether the RNG is initialized + */ +struct vdso_rng_data { + u64 generation; + u8 is_ready; +}; + /* * We use the hidden visibility to prevent the compiler from generating a GOT * relocation. Not only is going through a GOT useless (the entry couldn't and @@ -124,6 +134,7 @@ struct vdso_data { */ extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden"))); +extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden"))); /** * union vdso_data_store - Generic vDSO data page diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h new file mode 100644 index 000000000000..a8b7c14b0ae0 --- /dev/null +++ b/include/vdso/getrandom.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#ifndef _VDSO_GETRANDOM_H +#define _VDSO_GETRANDOM_H + +#include + +#define CHACHA_KEY_SIZE 32 +#define CHACHA_BLOCK_SIZE 64 + +/** + * struct vgetrandom_state - State used by vDSO getrandom(). + * + * @batch: One and a half ChaCha20 blocks of buffered RNG output. + * + * @key: Key to be used for generating next batch. + * + * @batch_key: Union of the prior two members, which is exactly two full + * ChaCha20 blocks in size, so that @batch and @key can be filled + * together. + * + * @generation: Snapshot of @rng_info->generation in the vDSO data page at + * the time @key was generated. + * + * @pos: Offset into @batch of the next available random byte. + * + * @in_use: Reentrancy guard for reusing a state within the same thread + * due to signal handlers. + */ +struct vgetrandom_state { + union { + struct { + u8 batch[CHACHA_BLOCK_SIZE * 3 / 2]; + u32 key[CHACHA_KEY_SIZE / sizeof(u32)]; + }; + u8 batch_key[CHACHA_BLOCK_SIZE * 2]; + }; + u64 generation; + u8 pos; + bool in_use; +}; + +#endif /* _VDSO_GETRANDOM_H */ diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index c46c2300517c..82fe827af542 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -38,3 +38,8 @@ config GENERIC_VDSO_OVERFLOW_PROTECT in the hotpath. endif + +config VDSO_GETRANDOM + bool + help + Selected by architectures that support vDSO getrandom(). diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c new file mode 100644 index 000000000000..b230f0b10832 --- /dev/null +++ b/lib/vdso/getrandom.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do { \ + while (len >= sizeof(type)) { \ + __put_unaligned_t(type, __get_unaligned_t(type, src), dst); \ + __put_unaligned_t(type, 0, src); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } \ +} while (0) + +static void memcpy_and_zero_src(void *dst, void *src, size_t len) +{ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + if (IS_ENABLED(CONFIG_64BIT)) + MEMCPY_AND_ZERO_SRC(u64, dst, src, len); + MEMCPY_AND_ZERO_SRC(u32, dst, src, len); + MEMCPY_AND_ZERO_SRC(u16, dst, src, len); + } + MEMCPY_AND_ZERO_SRC(u8, dst, src, len); +} + +/** + * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall. + * @rng_info: Describes state of kernel RNG, memory shared with kernel. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * @opaque_state: Pointer to an opaque state area. + * @opaque_len: Length of opaque state area. + * + * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's + * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same + * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always + * calls into the syscall. + * + * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated + * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0, + * this function should not be used. + * + * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields + * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external + * locking is used, one state must be allocated per thread, as it is not safe to call this function + * concurrently with the same @opaque_state. However, it is safe to call this using the same + * @opaque_state that is shared between main code and signal handling code, within the same thread. + * + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t +__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len, + unsigned int flags, void *opaque_state, size_t opaque_len) +{ + ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len); + struct vgetrandom_state *state = opaque_state; + size_t batch_len, nblocks, orig_len = len; + bool in_use, have_retried = false; + unsigned long current_generation; + void *orig_buffer = buffer; + u32 counter[2] = { 0 }; + + if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) { + *(struct vgetrandom_opaque_params *)opaque_state = (struct vgetrandom_opaque_params) { + .size_of_opaque_state = sizeof(*state), + .mmap_prot = PROT_READ | PROT_WRITE, + .mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS + }; + return 0; + } + + /* The state must not straddle a page, since pages can be zeroed at any time. */ + if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE)) + return -EFAULT; + + /* If the caller passes the wrong size, which might happen due to CRIU, fallback. */ + if (unlikely(opaque_len != sizeof(*state))) + goto fallback_syscall; + + /* + * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from + * userspace, because A) the various @flags require this to block, or not, depending on + * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is + * ready is to reseed from the entropy pool at every invocation. + */ + if (unlikely(!READ_ONCE(rng_info->is_ready))) + goto fallback_syscall; + + /* + * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is + * initialized, the @flags parameter may require this to block or return an error, even when + * len is zero. + */ + if (unlikely(!len)) + return 0; + + /* + * @state->in_use is basic reentrancy protection against this running in a signal handler + * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one + * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before + * writing @state->in_use, there is still no race, because the signal handler will run to + * its completion before returning execution. + */ + in_use = READ_ONCE(state->in_use); + if (unlikely(in_use)) + /* The syscall simply fills the buffer and does not touch @state, so fallback. */ + goto fallback_syscall; + WRITE_ONCE(state->in_use, true); + +retry_generation: + /* + * @rng_info->generation must always be read here, as it serializes @state->key with the + * kernel's RNG reseeding schedule. + */ + current_generation = READ_ONCE(rng_info->generation); + + /* + * If @state->generation doesn't match the kernel RNG's generation, then it means the + * kernel's RNG has reseeded, and so @state->key is reseeded as well. + */ + if (unlikely(state->generation != current_generation)) { + /* + * Write the generation before filling the key, in case of fork. If there is a fork + * just after this line, the parent and child will get different random bytes from + * the syscall, which is good. However, were this line to occur after the getrandom + * syscall, then both child and parent could have the same bytes and the same + * generation counter, so the fork would not be detected. Therefore, write + * @state->generation before the call to the getrandom syscall. + */ + WRITE_ONCE(state->generation, current_generation); + + /* + * Prevent the syscall from being reordered wrt current_generation. Pairs with the + * smp_store_release(&_vdso_rng_data.generation) in random.c. + */ + smp_rmb(); + + /* Reseed @state->key using fresh bytes from the kernel. */ + if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) { + /* + * If the syscall failed to refresh the key, then @state->key is now + * invalid, so invalidate the generation so that it is not used again, and + * fallback to using the syscall entirely. + */ + WRITE_ONCE(state->generation, 0); + + /* + * Set @state->in_use to false only after the last write to @state in the + * line above. + */ + WRITE_ONCE(state->in_use, false); + + goto fallback_syscall; + } + + /* + * Set @state->pos to beyond the end of the batch, so that the batch is refilled + * using the new key. + */ + state->pos = sizeof(state->batch); + } + + /* Set len to the total amount of bytes that this function is allowed to read, ret. */ + len = ret; +more_batch: + /* + * First use bytes out of @state->batch, which may have been filled by the last call to this + * function. + */ + batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len); + if (batch_len) { + /* Zeroing at the same time as memcpying helps preserve forward secrecy. */ + memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len); + state->pos += batch_len; + buffer += batch_len; + len -= batch_len; + } + + if (!len) { + /* Prevent the loop from being reordered wrt ->generation. */ + barrier(); + + /* + * Since @rng_info->generation will never be 0, re-read @state->generation, rather + * than using the local current_generation variable, to learn whether a fork + * occurred or if @state was zeroed due to memory pressure. Primarily, though, this + * indicates whether the kernel's RNG has reseeded, in which case generate a new key + * and start over. + */ + if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) { + /* + * Prevent this from looping forever in case of low memory or racing with a + * user force-reseeding the kernel's RNG using the ioctl. + */ + if (have_retried) { + WRITE_ONCE(state->in_use, false); + goto fallback_syscall; + } + + have_retried = true; + buffer = orig_buffer; + goto retry_generation; + } + + /* + * Set @state->in_use to false only when there will be no more reads or writes of + * @state. + */ + WRITE_ONCE(state->in_use, false); + return ret; + } + + /* Generate blocks of RNG output directly into @buffer while there's enough room left. */ + nblocks = len / CHACHA_BLOCK_SIZE; + if (nblocks) { + __arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks); + buffer += nblocks * CHACHA_BLOCK_SIZE; + len -= nblocks * CHACHA_BLOCK_SIZE; + } + + BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0); + + /* Refill the batch and overwrite the key, in order to preserve forward secrecy. */ + __arch_chacha20_blocks_nostack(state->batch_key, state->key, counter, + sizeof(state->batch_key) / CHACHA_BLOCK_SIZE); + + /* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */ + state->pos = 0; + goto more_batch; + +fallback_syscall: + return getrandom_syscall(orig_buffer, orig_len, flags); +} + +static __always_inline ssize_t +__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len); +} -- cgit v1.2.3 From 13f75d9ecf3d8efcf597dfcd8f7be7460cdaa11a Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 15 Jul 2024 04:50:07 +0200 Subject: random: note that RNDGETPOOL was removed in 2.6.9-rc2 RNDGETPOOL was thankfully removed twenty years ago, but it's stuck around in headers. Probably removing it from uapi headers isn't great in case there are some weird users out there, but we should at least mark this as having been removed, to save future readers the same goose chase I just went on. Link: https://lore.kernel.org/all/E1By1St-0001TS-Qj@thunk.org/ Link: https://lore.kernel.org/all/Pine.LNX.4.58.0409130937050.4094@ppc970.osdl.org/ Signed-off-by: Jason A. Donenfeld --- include/uapi/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index 2a3fe4c2cdc9..1dd047ec98a1 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -20,7 +20,7 @@ /* Add to (or subtract from) the entropy count. (Superuser only.) */ #define RNDADDTOENTCNT _IOW( 'R', 0x01, int ) -/* Get the contents of the entropy pool. (Superuser only.) */ +/* Get the contents of the entropy pool. (Superuser only.) (Removed in 2.6.9-rc2.) */ #define RNDGETPOOL _IOR( 'R', 0x02, int [2] ) /* -- cgit v1.2.3 From d5e726d9143c5624135f5dc9e4069799adeef734 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 12 Jul 2024 18:52:51 -0700 Subject: xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len Julian reports that commit 341ac980eab9 ("xsk: Support tx_metadata_len") can break existing use cases which don't zero-initialize xdp_umem_reg padding. Introduce new XDP_UMEM_TX_METADATA_LEN to make sure we interpret the padding as tx_metadata_len only when being explicitly asked. Fixes: 341ac980eab9 ("xsk: Support tx_metadata_len") Reported-by: Julian Schindel Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Reviewed-by: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20240713015253.121248-2-sdf@fomichev.me --- Documentation/networking/xsk-tx-metadata.rst | 16 ++++++++++------ include/uapi/linux/if_xdp.h | 4 ++++ net/xdp/xdp_umem.c | 9 ++++++--- 3 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst index bd033fe95cca..e76b0cfc32f7 100644 --- a/Documentation/networking/xsk-tx-metadata.rst +++ b/Documentation/networking/xsk-tx-metadata.rst @@ -11,12 +11,16 @@ metadata on the receive side. General Design ============== -The headroom for the metadata is reserved via ``tx_metadata_len`` in -``struct xdp_umem_reg``. The metadata length is therefore the same for -every socket that shares the same umem. The metadata layout is a fixed UAPI, -refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``. -Thus, generally, the ``tx_metadata_len`` field above should contain -``sizeof(union xsk_tx_metadata)``. +The headroom for the metadata is reserved via ``tx_metadata_len`` and +``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata +length is therefore the same for every socket that shares the same umem. +The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in +``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len`` +field above should contain ``sizeof(union xsk_tx_metadata)``. + +Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN`` +flag was not required. Applications might attempt to create a umem +with a flag first and if it fails, do another attempt without a flag. The headroom and the metadata itself should be located right before ``xdp_desc->addr`` in the umem frame. Within a frame, the metadata diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index d31698410410..42ec5ddaab8d 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -41,6 +41,10 @@ */ #define XDP_UMEM_TX_SW_CSUM (1 << 1) +/* Request to reserve tx_metadata_len bytes of per-chunk metadata. + */ +#define XDP_UMEM_TX_METADATA_LEN (1 << 2) + struct sockaddr_xdp { __u16 sxdp_family; __u16 sxdp_flags; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index caa340134b0e..9f76ca591d54 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) #define XDP_UMEM_FLAGS_VALID ( \ XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ XDP_UMEM_TX_SW_CSUM | \ + XDP_UMEM_TX_METADATA_LEN | \ 0) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) @@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; - if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) - return -EINVAL; + if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { + if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) + return -EINVAL; + umem->tx_metadata_len = mr->tx_metadata_len; + } umem->size = size; umem->headroom = headroom; @@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - umem->tx_metadata_len = mr->tx_metadata_len; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); -- cgit v1.2.3 From 42b0f8da3acc87953161baeb24f756936eb4d4b2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 31 Jul 2024 07:47:27 +0200 Subject: nsfs: fix ioctl declaration The kernel is writing an object of type __u64, so the ioctl has to be defined to _IOR(NSIO, 0x5, __u64) instead of _IO(NSIO, 0x5). Reported-by: Dmitry V. Levin Link: https://lore.kernel.org/r/20240730164554.GA18486@altlinux.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index b133211331f6..5fad3d0fcd70 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -3,6 +3,7 @@ #define __LINUX_NSFS_H #include +#include #define NSIO 0xb7 @@ -16,7 +17,7 @@ /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) /* Get the id for a mount namespace */ -#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) +#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64) /* Translate pid from target pid namespace into the caller's pid namespace. */ #define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) /* Return thread-group leader id of pid in the callers pid namespace. */ -- cgit v1.2.3 From 1c0e5881691a787a9399a99bff4d56ead6e75e91 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Wed, 14 Aug 2024 10:31:13 +0200 Subject: KVM: SEV: uapi: fix typo in SEV_RET_INVALID_CONFIG "INVALID" is misspelt in "SEV_RET_INAVLID_CONFIG". Since this is part of the UAPI, keep the current definition and add a new one with the fix. Fix-suggested-by: Marc Zyngier Signed-off-by: Amit Shah Message-ID: <20240814083113.21622-1-amit@kernel.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/psp-sev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 2289b7c76c59..832c15d9155b 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -51,6 +51,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, + SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, -- cgit v1.2.3 From 1fc2ac428ef7d2ab9e8e19efe7ec3e58aea51bf3 Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Fri, 16 Aug 2024 12:15:23 -0600 Subject: io_uring: fix user_data field name in comment io_uring_cqe's user_data field refers to `sqe->data`, but io_uring_sqe does not have a data field. Fix the comment to say `sqe->user_data`. Signed-off-by: Caleb Sander Mateos Link: https://github.com/axboe/liburing/pull/1206 Link: https://lore.kernel.org/r/20240816181526.3642732-1-csander@purestorage.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 2aaf7ee256ac..adc2524fd8e3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -421,7 +421,7 @@ enum io_uring_msg_ring_flags { * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { - __u64 user_data; /* sqe->data submission passed back */ + __u64 user_data; /* sqe->user_data value passed back */ __s32 res; /* result code for this event */ __u32 flags; -- cgit v1.2.3