From a0af74f30bb62143593c6f895ed439059d19675e Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Thu, 1 Dec 2022 09:42:46 +0100 Subject: media: uapi: add MEDIA_BUS_FMT_RGB565_1X24_CPADHI Add the MEDIA_BUS_FMT_RGB565_1X24_CPADHI format used by the Geekworm MZP280 panel for the Raspberry Pi. Signed-off-by: Chris Morgan Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20221013-rpi-dpi-improvements-v3-1-eb76e26a772d@cerno.tech Signed-off-by: Maxime Ripard --- include/uapi/linux/media-bus-format.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index ec3323dbb927..8e159e6b4d21 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -34,7 +34,7 @@ #define MEDIA_BUS_FMT_FIXED 0x0001 -/* RGB - next is 0x1022 */ +/* RGB - next is 0x1023 */ #define MEDIA_BUS_FMT_RGB444_1X12 0x1016 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE 0x1001 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE 0x1002 @@ -48,6 +48,7 @@ #define MEDIA_BUS_FMT_RGB666_1X18 0x1009 #define MEDIA_BUS_FMT_RBG888_1X24 0x100e #define MEDIA_BUS_FMT_RGB666_1X24_CPADHI 0x1015 +#define MEDIA_BUS_FMT_RGB565_1X24_CPADHI 0x1022 #define MEDIA_BUS_FMT_RGB666_1X7X3_SPWG 0x1010 #define MEDIA_BUS_FMT_BGR888_1X24 0x1013 #define MEDIA_BUS_FMT_BGR888_3X8 0x101b -- cgit v1.2.3 From 2468e0195c09706896712a29030132e7f1bd0bcc Mon Sep 17 00:00:00 2001 From: Joerg Quinten Date: Thu, 1 Dec 2022 09:42:47 +0100 Subject: media: uapi: add MEDIA_BUS_FMT_BGR666_1X18 Add the BGR666 format MEDIA_BUS_FMT_BGR666_1X18 supported by the RaspberryPi. Signed-off-by: Joerg Quinten Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20221013-rpi-dpi-improvements-v3-2-eb76e26a772d@cerno.tech Signed-off-by: Maxime Ripard --- .../userspace-api/media/v4l/subdev-formats.rst | 37 ++++++++++++++++++++++ include/uapi/linux/media-bus-format.h | 3 +- 2 files changed, 39 insertions(+), 1 deletion(-) (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 aa549c42e798..6605c056cc7c 100644 --- a/Documentation/userspace-api/media/v4l/subdev-formats.rst +++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst @@ -949,6 +949,43 @@ The following tables list existing packed RGB formats. - b\ :sub:`2` - b\ :sub:`1` - b\ :sub:`0` + * .. _MEDIA-BUS-FMT-BGR666-1X18: + + - MEDIA_BUS_FMT_BGR666_1X18 + - 0x1023 + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - b\ :sub:`5` + - b\ :sub:`4` + - b\ :sub:`3` + - b\ :sub:`2` + - b\ :sub:`1` + - b\ :sub:`0` + - g\ :sub:`5` + - g\ :sub:`4` + - g\ :sub:`3` + - g\ :sub:`2` + - g\ :sub:`1` + - g\ :sub:`0` + - r\ :sub:`5` + - r\ :sub:`4` + - r\ :sub:`3` + - r\ :sub:`2` + - r\ :sub:`1` + - r\ :sub:`0` * .. _MEDIA-BUS-FMT-RBG888-1X24: - MEDIA_BUS_FMT_RBG888_1X24 diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index 8e159e6b4d21..6ce56a984112 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -34,7 +34,7 @@ #define MEDIA_BUS_FMT_FIXED 0x0001 -/* RGB - next is 0x1023 */ +/* RGB - next is 0x1024 */ #define MEDIA_BUS_FMT_RGB444_1X12 0x1016 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE 0x1001 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE 0x1002 @@ -46,6 +46,7 @@ #define MEDIA_BUS_FMT_RGB565_2X8_BE 0x1007 #define MEDIA_BUS_FMT_RGB565_2X8_LE 0x1008 #define MEDIA_BUS_FMT_RGB666_1X18 0x1009 +#define MEDIA_BUS_FMT_BGR666_1X18 0x1023 #define MEDIA_BUS_FMT_RBG888_1X24 0x100e #define MEDIA_BUS_FMT_RGB666_1X24_CPADHI 0x1015 #define MEDIA_BUS_FMT_RGB565_1X24_CPADHI 0x1022 -- cgit v1.2.3 From 1113f644c488225212eebd3966360326579e2d3d Mon Sep 17 00:00:00 2001 From: Joerg Quinten Date: Thu, 1 Dec 2022 09:42:48 +0100 Subject: media: uapi: add MEDIA_BUS_FMT_BGR666_1X24_CPADHI Add the BGR666 format MEDIA_BUS_FMT_BGR666_1X24_CPADHI supported by the RaspberryPi. Signed-off-by: Joerg Quinten Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20221013-rpi-dpi-improvements-v3-3-eb76e26a772d@cerno.tech Signed-off-by: Maxime Ripard --- .../userspace-api/media/v4l/subdev-formats.rst | 37 ++++++++++++++++++++++ include/uapi/linux/media-bus-format.h | 3 +- 2 files changed, 39 insertions(+), 1 deletion(-) (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 6605c056cc7c..5f2ce6eada71 100644 --- a/Documentation/userspace-api/media/v4l/subdev-formats.rst +++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst @@ -1060,6 +1060,43 @@ The following tables list existing packed RGB formats. - b\ :sub:`2` - b\ :sub:`1` - b\ :sub:`0` + * .. _MEDIA-BUS-FMT-BGR666-1X24_CPADHI: + + - MEDIA_BUS_FMT_BGR666_1X24_CPADHI + - 0x1024 + - + - + - + - + - + - + - + - + - + - 0 + - 0 + - b\ :sub:`5` + - b\ :sub:`4` + - b\ :sub:`3` + - b\ :sub:`2` + - b\ :sub:`1` + - b\ :sub:`0` + - 0 + - 0 + - g\ :sub:`5` + - g\ :sub:`4` + - g\ :sub:`3` + - g\ :sub:`2` + - g\ :sub:`1` + - g\ :sub:`0` + - 0 + - 0 + - r\ :sub:`5` + - r\ :sub:`4` + - r\ :sub:`3` + - r\ :sub:`2` + - r\ :sub:`1` + - r\ :sub:`0` * .. _MEDIA-BUS-FMT-RGB565-1X24_CPADHI: - MEDIA_BUS_FMT_RGB565_1X24_CPADHI diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index 6ce56a984112..f3b0b8091a2c 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -34,7 +34,7 @@ #define MEDIA_BUS_FMT_FIXED 0x0001 -/* RGB - next is 0x1024 */ +/* RGB - next is 0x1025 */ #define MEDIA_BUS_FMT_RGB444_1X12 0x1016 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE 0x1001 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE 0x1002 @@ -49,6 +49,7 @@ #define MEDIA_BUS_FMT_BGR666_1X18 0x1023 #define MEDIA_BUS_FMT_RBG888_1X24 0x100e #define MEDIA_BUS_FMT_RGB666_1X24_CPADHI 0x1015 +#define MEDIA_BUS_FMT_BGR666_1X24_CPADHI 0x1024 #define MEDIA_BUS_FMT_RGB565_1X24_CPADHI 0x1022 #define MEDIA_BUS_FMT_RGB666_1X7X3_SPWG 0x1010 #define MEDIA_BUS_FMT_BGR888_1X24 0x1013 -- cgit v1.2.3 From e26aa600ba6a62fe84659f1df497a381bab6d07e Mon Sep 17 00:00:00 2001 From: Christian Ehrig Date: Sun, 18 Dec 2022 06:17:31 +0100 Subject: bpf: Add flag BPF_F_NO_TUNNEL_KEY to bpf_skb_set_tunnel_key() This patch allows to remove TUNNEL_KEY from the tunnel flags bitmap when using bpf_skb_set_tunnel_key by providing a BPF_F_NO_TUNNEL_KEY flag. On egress, the resulting tunnel header will not contain a tunnel key if the protocol and implementation supports it. At the moment bpf_tunnel_key wants a user to specify a numeric tunnel key. This will wrap the inner packet into a tunnel header with the key bit and value set accordingly. This is problematic when using a tunnel protocol that supports optional tunnel keys and a receiving tunnel device that is not expecting packets with the key bit set. The receiver won't decapsulate and drop the packet. RFC 2890 and RFC 2784 GRE tunnels are examples where this flag is useful. It allows for generating packets, that can be decapsulated by a GRE tunnel device not operating in collect metadata mode or not expecting the key bit set. Signed-off-by: Christian Ehrig Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20221218051734.31411-1-cehrig@cloudflare.com --- include/uapi/linux/bpf.h | 4 ++++ net/core/filter.c | 5 ++++- tools/include/uapi/linux/bpf.h | 4 ++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 464ca3f01fe7..bc1a3d232ae4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2001,6 +2001,9 @@ union bpf_attr { * sending the packet. This flag was added for GRE * encapsulation, but might be used with other protocols * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. * * Here is a typical usage on the transmit path: * @@ -5764,6 +5767,7 @@ enum { BPF_F_ZERO_CSUM_TX = (1ULL << 1), BPF_F_DONT_FRAGMENT = (1ULL << 2), BPF_F_SEQ_NUMBER = (1ULL << 3), + BPF_F_NO_TUNNEL_KEY = (1ULL << 4), }; /* BPF_FUNC_skb_get_tunnel_key flags. */ diff --git a/net/core/filter.c b/net/core/filter.c index 929358677183..c746e4d77214 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4615,7 +4615,8 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | - BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER))) + BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER | + BPF_F_NO_TUNNEL_KEY))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { @@ -4653,6 +4654,8 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, 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; info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 464ca3f01fe7..bc1a3d232ae4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2001,6 +2001,9 @@ union bpf_attr { * sending the packet. This flag was added for GRE * encapsulation, but might be used with other protocols * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. * * Here is a typical usage on the transmit path: * @@ -5764,6 +5767,7 @@ enum { BPF_F_ZERO_CSUM_TX = (1ULL << 1), BPF_F_DONT_FRAGMENT = (1ULL << 2), BPF_F_SEQ_NUMBER = (1ULL << 3), + BPF_F_NO_TUNNEL_KEY = (1ULL << 4), }; /* BPF_FUNC_skb_get_tunnel_key flags. */ -- cgit v1.2.3 From 317c8194e6aeb8b3b573ad139fc2a0635856498e Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 22 Nov 2022 15:39:04 -0500 Subject: rseq: Introduce feature size and alignment ELF auxiliary vector entries Export the rseq feature size supported by the kernel as well as the required allocation alignment for the rseq per-thread area to user-space through ELF auxiliary vector entries. This is part of the extensible rseq ABI. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20221122203932.231377-3-mathieu.desnoyers@efficios.com --- fs/binfmt_elf.c | 5 +++++ include/uapi/linux/auxvec.h | 2 ++ include/uapi/linux/rseq.h | 5 +++++ 3 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index de63572a9404..0ba86f0b1477 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include @@ -288,6 +289,10 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, if (bprm->have_execfd) { NEW_AUX_ENT(AT_EXECFD, bprm->execfd); } +#ifdef CONFIG_RSEQ + NEW_AUX_ENT(AT_RSEQ_FEATURE_SIZE, offsetof(struct rseq, end)); + NEW_AUX_ENT(AT_RSEQ_ALIGN, __alignof__(struct rseq)); +#endif #undef NEW_AUX_ENT /* AT_NULL is zero; clear the rest too */ memset(elf_info, 0, (char *)mm->saved_auxv + diff --git a/include/uapi/linux/auxvec.h b/include/uapi/linux/auxvec.h index c7e502bf5a6f..6991c4b8ab18 100644 --- a/include/uapi/linux/auxvec.h +++ b/include/uapi/linux/auxvec.h @@ -30,6 +30,8 @@ * differ from AT_PLATFORM. */ #define AT_RANDOM 25 /* address of 16 random bytes */ #define AT_HWCAP2 26 /* extension of AT_HWCAP */ +#define AT_RSEQ_FEATURE_SIZE 27 /* rseq supported feature size */ +#define AT_RSEQ_ALIGN 28 /* rseq allocation alignment */ #define AT_EXECFN 31 /* filename of program */ diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 77ee207623a9..05d3c4cdeb40 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -130,6 +130,11 @@ struct rseq { * this thread. */ __u32 flags; + + /* + * Flexible array member at end of structure, after last feature field. + */ + char end[]; } __attribute__((aligned(4 * sizeof(__u64)))); #endif /* _UAPI_LINUX_RSEQ_H */ -- cgit v1.2.3 From cbae6bac29a8c5cf2f1cb5c6bce35af00cec164b Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 22 Nov 2022 15:39:06 -0500 Subject: rseq: Extend struct rseq with numa node id Adding the NUMA node id to struct rseq is a straightforward thing to do, and a good way to figure out if anything in the user-space ecosystem prevents extending struct rseq. This NUMA node id field allows memory allocators such as tcmalloc to take advantage of fast access to the current NUMA node id to perform NUMA-aware memory allocation. It can also be useful for implementing fast-paths for NUMA-aware user-space mutexes. It also allows implementing getcpu(2) purely in user-space. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20221122203932.231377-5-mathieu.desnoyers@efficios.com --- include/trace/events/rseq.h | 4 +++- include/uapi/linux/rseq.h | 8 ++++++++ kernel/rseq.c | 19 +++++++++++++------ 3 files changed, 24 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/trace/events/rseq.h b/include/trace/events/rseq.h index a04a64bc1a00..dde7a359b4ef 100644 --- a/include/trace/events/rseq.h +++ b/include/trace/events/rseq.h @@ -16,13 +16,15 @@ TRACE_EVENT(rseq_update, TP_STRUCT__entry( __field(s32, cpu_id) + __field(s32, node_id) ), TP_fast_assign( __entry->cpu_id = raw_smp_processor_id(); + __entry->node_id = cpu_to_node(__entry->cpu_id); ), - TP_printk("cpu_id=%d", __entry->cpu_id) + TP_printk("cpu_id=%d node_id=%d", __entry->cpu_id, __entry->node_id) ); TRACE_EVENT(rseq_ip_fixup, diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 05d3c4cdeb40..1cb90a435c5c 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -131,6 +131,14 @@ struct rseq { */ __u32 flags; + /* + * Restartable sequences node_id field. Updated by the kernel. Read by + * user-space with single-copy atomicity semantics. This field should + * only be read by the thread which registered this data structure. + * Aligned on 32-bit. Contains the current NUMA node ID. + */ + __u32 node_id; + /* * Flexible array member at end of structure, after last feature field. */ diff --git a/kernel/rseq.c b/kernel/rseq.c index 7962738455c9..193cfcc94ddc 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -85,15 +85,17 @@ * F1. */ -static int rseq_update_cpu_id(struct task_struct *t) +static int rseq_update_cpu_node_id(struct task_struct *t) { - u32 cpu_id = raw_smp_processor_id(); struct rseq __user *rseq = t->rseq; + u32 cpu_id = raw_smp_processor_id(); + u32 node_id = cpu_to_node(cpu_id); if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end); unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end); + unsafe_put_user(node_id, &rseq->node_id, efault_end); /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally updated only if @@ -109,9 +111,9 @@ efault: return -EFAULT; } -static int rseq_reset_rseq_cpu_id(struct task_struct *t) +static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) { - u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED; + u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0; /* * Reset cpu_id_start to its initial state (0). @@ -125,6 +127,11 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t) */ if (put_user(cpu_id, &t->rseq->cpu_id)) return -EFAULT; + /* + * Reset node_id to its initial state (0). + */ + if (put_user(node_id, &t->rseq->node_id)) + return -EFAULT; /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally reset only if @@ -314,7 +321,7 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) if (unlikely(ret < 0)) goto error; } - if (unlikely(rseq_update_cpu_id(t))) + if (unlikely(rseq_update_cpu_node_id(t))) goto error; return; @@ -361,7 +368,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, return -EINVAL; if (current->rseq_sig != sig) return -EPERM; - ret = rseq_reset_rseq_cpu_id(current); + ret = rseq_reset_rseq_cpu_node_id(current); if (ret) return ret; current->rseq = NULL; -- cgit v1.2.3 From f7b01bb0b57f994a44ea6368536b59062b796381 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 22 Nov 2022 15:39:10 -0500 Subject: rseq: Extend struct rseq with per-memory-map concurrency ID If a memory map has fewer threads than there are cores on the system, or is limited to run on few cores concurrently through sched affinity or cgroup cpusets, the concurrency IDs will be values close to 0, thus allowing efficient use of user-space memory for per-cpu data structures. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20221122203932.231377-9-mathieu.desnoyers@efficios.com --- include/uapi/linux/rseq.h | 9 +++++++++ kernel/rseq.c | 11 ++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 1cb90a435c5c..c233aae5eac9 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -139,6 +139,15 @@ struct rseq { */ __u32 node_id; + /* + * Restartable sequences mm_cid field. Updated by the kernel. Read by + * user-space with single-copy atomicity semantics. This field should + * only be read by the thread which registered this data structure. + * Aligned on 32-bit. Contains the current thread's concurrency ID + * (allocated uniquely within a memory map). + */ + __u32 mm_cid; + /* * Flexible array member at end of structure, after last feature field. */ diff --git a/kernel/rseq.c b/kernel/rseq.c index 193cfcc94ddc..9de6e35fe679 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -90,12 +90,15 @@ static int rseq_update_cpu_node_id(struct task_struct *t) struct rseq __user *rseq = t->rseq; u32 cpu_id = raw_smp_processor_id(); u32 node_id = cpu_to_node(cpu_id); + u32 mm_cid = task_mm_cid(t); + WARN_ON_ONCE((int) mm_cid < 0); if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end); unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end); unsafe_put_user(node_id, &rseq->node_id, efault_end); + unsafe_put_user(mm_cid, &rseq->mm_cid, efault_end); /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally updated only if @@ -113,7 +116,8 @@ efault: static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) { - u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0; + u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0, + mm_cid = 0; /* * Reset cpu_id_start to its initial state (0). @@ -132,6 +136,11 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) */ if (put_user(node_id, &t->rseq->node_id)) return -EFAULT; + /* + * Reset mm_cid to its initial state (0). + */ + if (put_user(mm_cid, &t->rseq->mm_cid)) + return -EFAULT; /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally reset only if -- cgit v1.2.3 From f3dc61cde80d48751999c4cb46daf3b2185e6895 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 25 Nov 2022 10:18:26 +0000 Subject: firmware/psci: Fix MEM_PROTECT_RANGE function numbers PSCI v1.1 offers 32-bit and 64-bit variants of the MEM_PROTECT_RANGE call using function identifier 20. Fix the incorrect definitions of the MEM_PROTECT_CHECK_RANGE calls in the PSCI UAPI header. Cc: Dmitry Baryshkov Cc: Lorenzo Pieralisi Cc: Arnd Bergmann Fixes: 3137f2e60098 ("firmware/psci: Add debugfs support to ease debugging") Acked-by: Marc Zyngier Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20221125101826.22404-1-will@kernel.org Signed-off-by: Will Deacon --- include/uapi/linux/psci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 3511095c2702..42a40ad3fb62 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -58,7 +58,7 @@ #define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18) #define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19) -#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(19) +#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(20) #define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12) #define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13) @@ -67,7 +67,7 @@ #define PSCI_1_0_FN64_STAT_COUNT PSCI_0_2_FN64(17) #define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18) -#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(19) +#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(20) /* PSCI v0.2 power state encoding for CPU_SUSPEND function */ #define PSCI_0_2_POWER_STATE_ID_MASK 0xffff -- cgit v1.2.3 From 0b5dfa35da03277287d6c5fcd2b56a77f1c61f62 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 14:21:16 -0800 Subject: ipv6: ioam: Replace 0-length array with flexible array Zero-length arrays are deprecated[1]. Replace struct ioam6_trace_hdr's "data" 0-length array with a flexible array. Detected with GCC 13, using -fstrict-flex-arrays=3: net/ipv6/ioam6_iptunnel.c: In function 'ioam6_build_state': net/ipv6/ioam6_iptunnel.c:194:37: warning: array subscript is outside array bounds of '__u8[0]' {aka 'unsigned char[]'} [-Warray-bounds=] 194 | tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN; | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~ In file included from include/linux/ioam6.h:11, from net/ipv6/ioam6_iptunnel.c:13: include/uapi/linux/ioam6.h:130:17: note: while referencing 'data' 130 | __u8 data[0]; | ^~~~ [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Justin Iurman Tested-by: Justin Iurman Link: https://lore.kernel.org/r/20230105222115.never.661-kees@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/ioam6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h index ac4de376f0ce..8f72b24fefb3 100644 --- a/include/uapi/linux/ioam6.h +++ b/include/uapi/linux/ioam6.h @@ -127,7 +127,7 @@ struct ioam6_trace_hdr { #endif #define IOAM6_TRACE_DATA_SIZE_MAX 244 - __u8 data[0]; + __u8 data[]; } __attribute__((packed)); #endif /* _UAPI_LINUX_IOAM6_H */ -- cgit v1.2.3 From e8d283b6cf0e83d5fcb5345e037956eb3e9b2483 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 14:15:37 -0800 Subject: net: ipv6: rpl_iptunnel: Replace 0-length arrays with flexible arrays Zero-length arrays are deprecated[1]. Replace struct ipv6_rpl_sr_hdr's "segments" union of 0-length arrays with flexible arrays. Detected with GCC 13, using -fstrict-flex-arrays=3: In function 'rpl_validate_srh', inlined from 'rpl_build_state' at ../net/ipv6/rpl_iptunnel.c:96:7: ../net/ipv6/rpl_iptunnel.c:60:28: warning: array subscript is outside array bounds of 'struct in6_addr[0]' [-Warray-bounds=] 60 | if (ipv6_addr_type(&srh->rpl_segaddr[srh->segments_left - 1]) & | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from ../include/net/rpl.h:12, from ../net/ipv6/rpl_iptunnel.c:13: ../include/uapi/linux/rpl.h: In function 'rpl_build_state': ../include/uapi/linux/rpl.h:40:33: note: while referencing 'addr' 40 | struct in6_addr addr[0]; | ^~~~ [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Cc: Hideaki YOSHIFUJI Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230105221533.never.711-kees@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/rpl.h | 4 ++-- net/ipv6/rpl_iptunnel.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rpl.h b/include/uapi/linux/rpl.h index 708adddf9f13..7c8970e5b84b 100644 --- a/include/uapi/linux/rpl.h +++ b/include/uapi/linux/rpl.h @@ -37,8 +37,8 @@ struct ipv6_rpl_sr_hdr { #endif union { - struct in6_addr addr[0]; - __u8 data[0]; + __DECLARE_FLEX_ARRAY(struct in6_addr, addr); + __DECLARE_FLEX_ARRAY(__u8, data); } segments; } __attribute__((packed)); diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index ff691d9f4a04..b1c028df686e 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -13,7 +13,7 @@ #include struct rpl_iptunnel_encap { - struct ipv6_rpl_sr_hdr srh[0]; + DECLARE_FLEX_ARRAY(struct ipv6_rpl_sr_hdr, srh); }; struct rpl_lwt { -- cgit v1.2.3 From b466a25c930f2b7f1ed21c9eeaa553017ae78d1c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 20:28:48 -0800 Subject: ethtool: Replace 0-length array with flexible array Zero-length arrays are deprecated[1]. Replace struct ethtool_rxnfc's "rule_locs" 0-length array with a flexible array. Detected with GCC 13, using -fstrict-flex-arrays=3: net/ethtool/common.c: In function 'ethtool_get_max_rxnfc_channel': net/ethtool/common.c:558:55: warning: array subscript i is outside array bounds of '__u32[0]' {aka 'unsigned int[]'} [-Warray-bounds=] 558 | .fs.location = info->rule_locs[i], | ~~~~~~~~~~~~~~~^~~ In file included from include/linux/ethtool.h:19, from include/uapi/linux/ethtool_netlink.h:12, from include/linux/ethtool_netlink.h:6, from net/ethtool/common.c:3: include/uapi/linux/ethtool.h:1186:41: note: while referencing 'rule_locs' 1186 | __u32 rule_locs[0]; | ^~~~~~~~~ [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Cc: Andrew Lunn Cc: kernel test robot Cc: Oleksij Rempel Cc: Sean Anderson Cc: Alexandru Tachici Cc: Amit Cohen Signed-off-by: Kees Cook Reviewed-by: Vincent Mailhol Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20230106042844.give.885-kees@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 58e587ba0450..3135fa0ba9a4 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1183,7 +1183,7 @@ struct ethtool_rxnfc { __u32 rule_cnt; __u32 rss_context; }; - __u32 rule_locs[0]; + __u32 rule_locs[]; }; -- cgit v1.2.3 From 544a4f2ecd45f9d6ed78d207583f39130ad40349 Mon Sep 17 00:00:00 2001 From: Michal Clapinski Date: Wed, 7 Dec 2022 17:43:37 +0100 Subject: sched/membarrier: Introduce MEMBARRIER_CMD_GET_REGISTRATIONS Provide a method to query previously issued registrations. Signed-off-by: Michal Clapinski Signed-off-by: Ingo Molnar Acked-by: Mathieu Desnoyers Acked-by: Paul E. McKenney Link: https://lore.kernel.org/r/20221207164338.1535591-2-mclapinski@google.com --- include/uapi/linux/membarrier.h | 4 ++++ kernel/sched/membarrier.c | 39 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 737605897f36..5f3ad6d5be6f 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -137,6 +137,9 @@ * @MEMBARRIER_CMD_SHARED: * Alias to MEMBARRIER_CMD_GLOBAL. Provided for * header backward compatibility. + * @MEMBARRIER_CMD_GET_REGISTRATIONS: + * Returns a bitmask of previously issued + * registration commands. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to @@ -153,6 +156,7 @@ enum membarrier_cmd { MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 6), MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ = (1 << 7), MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ = (1 << 8), + MEMBARRIER_CMD_GET_REGISTRATIONS = (1 << 9), /* Alias for header backward compatibility. */ MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL, diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 0c5be7ebb1dc..2ad881d07752 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -159,7 +159,8 @@ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ - | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) + | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ + | MEMBARRIER_CMD_GET_REGISTRATIONS) static void ipi_mb(void *info) { @@ -540,6 +541,40 @@ static int membarrier_register_private_expedited(int flags) return 0; } +static int membarrier_get_registrations(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + int registrations_mask = 0, membarrier_state, i; + static const int states[] = { + MEMBARRIER_STATE_GLOBAL_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY, + MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE | + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY, + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ | + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY + }; + static const int registration_cmds[] = { + MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED, + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED, + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE, + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ + }; + BUILD_BUG_ON(ARRAY_SIZE(states) != ARRAY_SIZE(registration_cmds)); + + membarrier_state = atomic_read(&mm->membarrier_state); + for (i = 0; i < ARRAY_SIZE(states); ++i) { + if (membarrier_state & states[i]) { + registrations_mask |= registration_cmds[i]; + membarrier_state &= ~states[i]; + } + } + WARN_ON_ONCE(membarrier_state != 0); + return registrations_mask; +} + /** * sys_membarrier - issue memory barriers on a set of threads * @cmd: Takes command values defined in enum membarrier_cmd. @@ -623,6 +658,8 @@ SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id) return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id); case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ: return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ); + case MEMBARRIER_CMD_GET_REGISTRATIONS: + return membarrier_get_registrations(); default: return -EINVAL; } -- cgit v1.2.3 From 8580e16c28f3f1a1bee87de115157161577334b4 Mon Sep 17 00:00:00 2001 From: Piergiorgio Beruto Date: Mon, 9 Jan 2023 17:59:39 +0100 Subject: net/ethtool: add netlink interface for the PLCA RS Add support for configuring the PLCA Reconciliation Sublayer on multi-drop PHYs that support IEEE802.3cg-2019 Clause 148 (e.g., 10BASE-T1S). This patch adds the appropriate netlink interface to ethtool. Signed-off-by: Piergiorgio Beruto Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 138 +++++++++++++ MAINTAINERS | 6 + include/linux/ethtool.h | 12 ++ include/linux/phy.h | 57 ++++++ include/uapi/linux/ethtool_netlink.h | 25 +++ net/ethtool/Makefile | 2 +- net/ethtool/netlink.c | 29 +++ net/ethtool/netlink.h | 6 + net/ethtool/plca.c | 277 +++++++++++++++++++++++++++ 9 files changed, 551 insertions(+), 1 deletion(-) create mode 100644 net/ethtool/plca.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index f10f8eb44255..c59b542eb693 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1716,6 +1716,141 @@ being used. Current supported options are toeplitz, xor or crc32. ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte indicates queue number. +PLCA_GET_CFG +============ + +Gets the IEEE 802.3cg-2019 Clause 148 Physical Layer Collision Avoidance +(PLCA) Reconciliation Sublayer (RS) attributes. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PLCA_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ============================= + ``ETHTOOL_A_PLCA_HEADER`` nested reply header + ``ETHTOOL_A_PLCA_VERSION`` u16 Supported PLCA management + interface standard/version + ``ETHTOOL_A_PLCA_ENABLED`` u8 PLCA Admin State + ``ETHTOOL_A_PLCA_NODE_ID`` u32 PLCA unique local node ID + ``ETHTOOL_A_PLCA_NODE_CNT`` u32 Number of PLCA nodes on the + network, including the + coordinator + ``ETHTOOL_A_PLCA_TO_TMR`` u32 Transmit Opportunity Timer + value in bit-times (BT) + ``ETHTOOL_A_PLCA_BURST_CNT`` u32 Number of additional packets + the node is allowed to send + within a single TO + ``ETHTOOL_A_PLCA_BURST_TMR`` u32 Time to wait for the MAC to + transmit a new frame before + terminating the burst + ====================================== ====== ============================= + +When set, the optional ``ETHTOOL_A_PLCA_VERSION`` attribute indicates which +standard and version the PLCA management interface complies to. When not set, +the interface is vendor-specific and (possibly) supplied by the driver. +The OPEN Alliance SIG specifies a standard register map for 10BASE-T1S PHYs +embedding the PLCA Reconcialiation Sublayer. See "10BASE-T1S PLCA Management +Registers" at https://www.opensig.org/about/specifications/. + +When set, the optional ``ETHTOOL_A_PLCA_ENABLED`` attribute indicates the +administrative state of the PLCA RS. When not set, the node operates in "plain" +CSMA/CD mode. This option is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.1 +aPLCAAdminState / 30.16.1.2.1 acPLCAAdminControl. + +When set, the optional ``ETHTOOL_A_PLCA_NODE_ID`` attribute indicates the +configured local node ID of the PHY. This ID determines which transmit +opportunity (TO) is reserved for the node to transmit into. This option is +corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.4 aPLCALocalNodeID. The valid +range for this attribute is [0 .. 255] where 255 means "not configured". + +When set, the optional ``ETHTOOL_A_PLCA_NODE_CNT`` attribute indicates the +configured maximum number of PLCA nodes on the mixing-segment. This number +determines the total number of transmit opportunities generated during a +PLCA cycle. This attribute is relevant only for the PLCA coordinator, which is +the node with aPLCALocalNodeID set to 0. Follower nodes ignore this setting. +This option is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.3 +aPLCANodeCount. The valid range for this attribute is [1 .. 255]. + +When set, the optional ``ETHTOOL_A_PLCA_TO_TMR`` attribute indicates the +configured value of the transmit opportunity timer in bit-times. This value +must be set equal across all nodes sharing the medium for PLCA to work +correctly. This option is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.5 +aPLCATransmitOpportunityTimer. The valid range for this attribute is +[0 .. 255]. + +When set, the optional ``ETHTOOL_A_PLCA_BURST_CNT`` attribute indicates the +configured number of extra packets that the node is allowed to send during a +single transmit opportunity. By default, this attribute is 0, meaning that +the node can only send a sigle frame per TO. When greater than 0, the PLCA RS +keeps the TO after any transmission, waiting for the MAC to send a new frame +for up to aPLCABurstTimer BTs. This can only happen a number of times per PLCA +cycle up to the value of this parameter. After that, the burst is over and the +normal counting of TOs resumes. This option is corresponding to +``IEEE 802.3cg-2019`` 30.16.1.1.6 aPLCAMaxBurstCount. The valid range for this +attribute is [0 .. 255]. + +When set, the optional ``ETHTOOL_A_PLCA_BURST_TMR`` attribute indicates how +many bit-times the PLCA RS waits for the MAC to initiate a new transmission +when aPLCAMaxBurstCount is greater than 0. If the MAC fails to send a new +frame within this time, the burst ends and the counting of TOs resumes. +Otherwise, the new frame is sent as part of the current burst. This option +is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.7 aPLCABurstTimer. The +valid range for this attribute is [0 .. 255]. Although, the value should be +set greater than the Inter-Frame-Gap (IFG) time of the MAC (plus some margin) +for PLCA burst mode to work as intended. + +PLCA_SET_CFG +============ + +Sets PLCA RS parameters. + +Request contents: + + ====================================== ====== ============================= + ``ETHTOOL_A_PLCA_HEADER`` nested request header + ``ETHTOOL_A_PLCA_ENABLED`` u8 PLCA Admin State + ``ETHTOOL_A_PLCA_NODE_ID`` u8 PLCA unique local node ID + ``ETHTOOL_A_PLCA_NODE_CNT`` u8 Number of PLCA nodes on the + netkork, including the + coordinator + ``ETHTOOL_A_PLCA_TO_TMR`` u8 Transmit Opportunity Timer + value in bit-times (BT) + ``ETHTOOL_A_PLCA_BURST_CNT`` u8 Number of additional packets + the node is allowed to send + within a single TO + ``ETHTOOL_A_PLCA_BURST_TMR`` u8 Time to wait for the MAC to + transmit a new frame before + terminating the burst + ====================================== ====== ============================= + +For a description of each attribute, see ``PLCA_GET_CFG``. + +PLCA_GET_STATUS +=============== + +Gets PLCA RS status information. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PLCA_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ============================= + ``ETHTOOL_A_PLCA_HEADER`` nested reply header + ``ETHTOOL_A_PLCA_STATUS`` u8 PLCA RS operational status + ====================================== ====== ============================= + +When set, the ``ETHTOOL_A_PLCA_STATUS`` attribute indicates whether the node is +detecting the presence of the BEACON on the network. This flag is +corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.2 aPLCAStatus. + Request translation =================== @@ -1817,4 +1952,7 @@ are netlink only. n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` n/a ``ETHTOOL_MSG_MODULE_GET`` n/a ``ETHTOOL_MSG_MODULE_SET`` + n/a ``ETHTOOL_MSG_PLCA_GET_CFG`` + n/a ``ETHTOOL_MSG_PLCA_SET_CFG`` + n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` =================================== ===================================== diff --git a/MAINTAINERS b/MAINTAINERS index 0f61b5d64716..7b6e602b90d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16616,6 +16616,12 @@ S: Maintained F: Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml F: drivers/iio/chemical/pms7003.c +PLCA RECONCILIATION SUBLAYER (IEEE802.3 Clause 148) +M: Piergiorgio Beruto +L: netdev@vger.kernel.org +S: Maintained +F: net/ethtool/plca.c + PLDMFW LIBRARY M: Jacob Keller S: Maintained diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9e0a76fc7de9..d0da303f6634 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -802,12 +802,17 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, struct phy_device; struct phy_tdr_config; +struct phy_plca_cfg; +struct phy_plca_status; /** * struct ethtool_phy_ops - Optional PHY device options * @get_sset_count: Get number of strings that @get_strings will write. * @get_strings: Return a set of strings that describe the requested objects * @get_stats: Return extended statistics about the PHY device. + * @get_plca_cfg: Return PLCA configuration. + * @set_plca_cfg: Set PLCA configuration. + * @get_plca_status: Get PLCA configuration. * @start_cable_test: Start a cable test * @start_cable_test_tdr: Start a Time Domain Reflectometry cable test * @@ -819,6 +824,13 @@ struct ethtool_phy_ops { int (*get_strings)(struct phy_device *dev, u8 *data); int (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); + int (*get_plca_cfg)(struct phy_device *dev, + struct phy_plca_cfg *plca_cfg); + int (*set_plca_cfg)(struct phy_device *dev, + const struct phy_plca_cfg *plca_cfg, + struct netlink_ext_ack *extack); + int (*get_plca_status)(struct phy_device *dev, + struct phy_plca_status *plca_st); int (*start_cable_test)(struct phy_device *phydev, struct netlink_ext_ack *extack); int (*start_cable_test_tdr)(struct phy_device *phydev, diff --git a/include/linux/phy.h b/include/linux/phy.h index 89b43cda5bda..b82fdb0d82ed 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -773,6 +773,63 @@ struct phy_tdr_config { }; #define PHY_PAIR_ALL -1 +/** + * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision + * Avoidance) Reconciliation Sublayer. + * + * @version: read-only PLCA register map version. -1 = not available. Ignored + * when setting the configuration. Format is the same as reported by the PLCA + * IDVER register (31.CA00). -1 = not available. + * @enabled: PLCA configured mode (enabled/disabled). -1 = not available / don't + * set. 0 = disabled, anything else = enabled. + * @node_id: the PLCA local node identifier. -1 = not available / don't set. + * Allowed values [0 .. 254]. 255 = node disabled. + * @node_cnt: the PLCA node count (maximum number of nodes having a TO). Only + * meaningful for the coordinator (node_id = 0). -1 = not available / don't + * set. Allowed values [1 .. 255]. + * @to_tmr: The value of the PLCA to_timer in bit-times, which determines the + * PLCA transmit opportunity window opening. See IEEE802.3 Clause 148 for + * more details. The to_timer shall be set equal over all nodes. + * -1 = not available / don't set. Allowed values [0 .. 255]. + * @burst_cnt: controls how many additional frames a node is allowed to send in + * single transmit opportunity (TO). The default value of 0 means that the + * node is allowed exactly one frame per TO. A value of 1 allows two frames + * per TO, and so on. -1 = not available / don't set. + * Allowed values [0 .. 255]. + * @burst_tmr: controls how many bit times to wait for the MAC to send a new + * frame before interrupting the burst. This value should be set to a value + * greater than the MAC inter-packet gap (which is typically 96 bits). + * -1 = not available / don't set. Allowed values [0 .. 255]. + * + * A structure containing configuration parameters for setting/getting the PLCA + * RS configuration. The driver does not need to implement all the parameters, + * but should report what is actually used. + */ +struct phy_plca_cfg { + int version; + int enabled; + int node_id; + int node_cnt; + int to_tmr; + int burst_cnt; + int burst_tmr; +}; + +/** + * struct phy_plca_status - Status of the PLCA (Physical Layer Collision + * Avoidance) Reconciliation Sublayer. + * + * @pst: The PLCA status as reported by the PST bit in the PLCA STATUS + * register(31.CA03), indicating BEACON activity. + * + * A structure containing status information of the PLCA RS configuration. + * The driver does not need to implement all the parameters, but should report + * what is actually used. + */ +struct phy_plca_status { + bool pst; +}; + /** * struct phy_driver - Driver structure for a particular PHY type * diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5799a9db034e..75b3d6d476ff 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -52,6 +52,9 @@ enum { ETHTOOL_MSG_PSE_GET, ETHTOOL_MSG_PSE_SET, ETHTOOL_MSG_RSS_GET, + ETHTOOL_MSG_PLCA_GET_CFG, + ETHTOOL_MSG_PLCA_SET_CFG, + ETHTOOL_MSG_PLCA_GET_STATUS, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -99,6 +102,9 @@ enum { ETHTOOL_MSG_MODULE_NTF, ETHTOOL_MSG_PSE_GET_REPLY, ETHTOOL_MSG_RSS_GET_REPLY, + ETHTOOL_MSG_PLCA_GET_CFG_REPLY, + ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, + ETHTOOL_MSG_PLCA_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -894,6 +900,25 @@ enum { ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), }; +/* PLCA */ + +enum { + ETHTOOL_A_PLCA_UNSPEC, + ETHTOOL_A_PLCA_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PLCA_VERSION, /* u16 */ + ETHTOOL_A_PLCA_ENABLED, /* u8 */ + ETHTOOL_A_PLCA_STATUS, /* u8 */ + ETHTOOL_A_PLCA_NODE_CNT, /* u32 */ + ETHTOOL_A_PLCA_NODE_ID, /* u32 */ + ETHTOOL_A_PLCA_TO_TMR, /* u32 */ + ETHTOOL_A_PLCA_BURST_CNT, /* u32 */ + ETHTOOL_A_PLCA_BURST_TMR, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_PLCA_CNT, + ETHTOOL_A_PLCA_MAX = (__ETHTOOL_A_PLCA_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 228f13df2e18..563864c1bf5a 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o \ - pse-pd.o + pse-pd.o plca.o diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index aee98be6237f..9f924875bba9 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -288,6 +288,8 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, + [ETHTOOL_MSG_PLCA_GET_CFG] = ðnl_plca_cfg_request_ops, + [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -603,6 +605,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, + [ETHTOOL_MSG_PLCA_NTF] = ðnl_plca_cfg_request_ops, }; /* default notification handler */ @@ -696,6 +699,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_PLCA_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -1047,6 +1051,31 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PLCA_GET_CFG, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_plca_get_cfg_policy, + .maxattr = ARRAY_SIZE(ethnl_plca_get_cfg_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_PLCA_SET_CFG, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_plca_cfg, + .policy = ethnl_plca_set_cfg_policy, + .maxattr = ARRAY_SIZE(ethnl_plca_set_cfg_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_PLCA_GET_STATUS, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_plca_get_status_policy, + .maxattr = ARRAY_SIZE(ethnl_plca_get_status_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3753787ba233..f271266f6e28 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -347,6 +347,8 @@ extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct ethnl_request_ops ethnl_module_request_ops; extern const struct ethnl_request_ops ethnl_pse_request_ops; 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 nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -388,6 +390,9 @@ extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MO extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; +extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; +extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; +extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); @@ -408,6 +413,7 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_set_fec(struct sk_buff *skb, struct genl_info *info); int ethnl_set_module(struct sk_buff *skb, struct genl_info *info); int ethnl_set_pse(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_plca_cfg(struct sk_buff *skb, struct genl_info *info); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c new file mode 100644 index 000000000000..d9bb13ffc654 --- /dev/null +++ b/net/ethtool/plca.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include "netlink.h" +#include "common.h" + +struct plca_req_info { + struct ethnl_req_info base; +}; + +struct plca_reply_data { + struct ethnl_reply_data base; + struct phy_plca_cfg plca_cfg; + struct phy_plca_status plca_st; +}; + +// Helpers ------------------------------------------------------------------ // + +#define PLCA_REPDATA(__reply_base) \ + container_of(__reply_base, struct plca_reply_data, base) + +static void plca_update_sint(int *dst, const struct nlattr *attr, + bool *mod) +{ + if (!attr) + return; + + *dst = nla_get_u32(attr); + *mod = true; +} + +// PLCA get configuration message ------------------------------------------- // + +const struct nla_policy ethnl_plca_get_cfg_policy[] = { + [ETHTOOL_A_PLCA_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct plca_reply_data *data = PLCA_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_phy_ops *ops; + int ret; + + // check that the PHY device is available and connected + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out; + } + + // note: rtnl_lock is held already by ethnl_default_doit + ops = ethtool_phy_ops; + if (!ops || !ops->get_plca_cfg) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = ethnl_ops_begin(dev); + if (!ret) + goto out; + + memset(&data->plca_cfg, 0xff, + sizeof_field(struct plca_reply_data, plca_cfg)); + + ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg); + ethnl_ops_complete(dev); + +out: + return ret; +} + +static int plca_get_cfg_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u16)) + /* _VERSION */ + nla_total_size(sizeof(u8)) + /* _ENABLED */ + nla_total_size(sizeof(u32)) + /* _NODE_CNT */ + nla_total_size(sizeof(u32)) + /* _NODE_ID */ + nla_total_size(sizeof(u32)) + /* _TO_TIMER */ + nla_total_size(sizeof(u32)) + /* _BURST_COUNT */ + nla_total_size(sizeof(u32)); /* _BURST_TIMER */ +} + +static int plca_get_cfg_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct plca_reply_data *data = PLCA_REPDATA(reply_base); + const struct phy_plca_cfg *plca = &data->plca_cfg; + + if ((plca->version >= 0 && + nla_put_u16(skb, ETHTOOL_A_PLCA_VERSION, plca->version)) || + (plca->enabled >= 0 && + nla_put_u8(skb, ETHTOOL_A_PLCA_ENABLED, !!plca->enabled)) || + (plca->node_id >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_ID, plca->node_id)) || + (plca->node_cnt >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_CNT, plca->node_cnt)) || + (plca->to_tmr >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_TO_TMR, plca->to_tmr)) || + (plca->burst_cnt >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_CNT, plca->burst_cnt)) || + (plca->burst_tmr >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_TMR, plca->burst_tmr))) + return -EMSGSIZE; + + return 0; +}; + +const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { + .request_cmd = ETHTOOL_MSG_PLCA_GET_CFG, + .reply_cmd = ETHTOOL_MSG_PLCA_GET_CFG_REPLY, + .hdr_attr = ETHTOOL_A_PLCA_HEADER, + .req_info_size = sizeof(struct plca_req_info), + .reply_data_size = sizeof(struct plca_reply_data), + + .prepare_data = plca_get_cfg_prepare_data, + .reply_size = plca_get_cfg_reply_size, + .fill_reply = plca_get_cfg_fill_reply, +}; + +// PLCA set configuration message ------------------------------------------- // + +const struct nla_policy ethnl_plca_set_cfg_policy[] = { + [ETHTOOL_A_PLCA_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), + [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), + [ETHTOOL_A_PLCA_TO_TMR] = NLA_POLICY_MAX(NLA_U32, 255), + [ETHTOOL_A_PLCA_BURST_CNT] = NLA_POLICY_MAX(NLA_U32, 255), + [ETHTOOL_A_PLCA_BURST_TMR] = NLA_POLICY_MAX(NLA_U32, 255), +}; + +int ethnl_set_plca_cfg(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + const struct ethtool_phy_ops *ops; + struct phy_plca_cfg plca_cfg; + struct net_device *dev; + bool mod = false; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_PLCA_HEADER], + genl_info_net(info), info->extack, + true); + if (!ret) + return ret; + + dev = req_info.dev; + + rtnl_lock(); + + // check that the PHY device is available and connected + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + + ops = ethtool_phy_ops; + if (!ops || !ops->set_plca_cfg) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + + ret = ethnl_ops_begin(dev); + if (!ret) + goto out_rtnl; + + memset(&plca_cfg, 0xff, sizeof(plca_cfg)); + plca_update_sint(&plca_cfg.enabled, tb[ETHTOOL_A_PLCA_ENABLED], &mod); + plca_update_sint(&plca_cfg.node_id, tb[ETHTOOL_A_PLCA_NODE_ID], &mod); + plca_update_sint(&plca_cfg.node_cnt, tb[ETHTOOL_A_PLCA_NODE_CNT], &mod); + plca_update_sint(&plca_cfg.to_tmr, tb[ETHTOOL_A_PLCA_TO_TMR], &mod); + plca_update_sint(&plca_cfg.burst_cnt, tb[ETHTOOL_A_PLCA_BURST_CNT], + &mod); + plca_update_sint(&plca_cfg.burst_tmr, tb[ETHTOOL_A_PLCA_BURST_TMR], + &mod); + + ret = 0; + if (!mod) + goto out_ops; + + ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack); + if (!ret) + goto out_ops; + + ethtool_notify(dev, ETHTOOL_MSG_PLCA_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info); + + return ret; +} + +// PLCA get status message -------------------------------------------------- // + +const struct nla_policy ethnl_plca_get_status_policy[] = { + [ETHTOOL_A_PLCA_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct plca_reply_data *data = PLCA_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_phy_ops *ops; + int ret; + + // check that the PHY device is available and connected + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out; + } + + // note: rtnl_lock is held already by ethnl_default_doit + ops = ethtool_phy_ops; + if (!ops || !ops->get_plca_status) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = ethnl_ops_begin(dev); + if (!ret) + goto out; + + memset(&data->plca_st, 0xff, + sizeof_field(struct plca_reply_data, plca_st)); + + ret = ops->get_plca_status(dev->phydev, &data->plca_st); + ethnl_ops_complete(dev); +out: + return ret; +} + +static int plca_get_status_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u8)); /* _STATUS */ +} + +static int plca_get_status_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct plca_reply_data *data = PLCA_REPDATA(reply_base); + const u8 status = data->plca_st.pst; + + if (nla_put_u8(skb, ETHTOOL_A_PLCA_STATUS, !!status)) + return -EMSGSIZE; + + return 0; +}; + +const struct ethnl_request_ops ethnl_plca_status_request_ops = { + .request_cmd = ETHTOOL_MSG_PLCA_GET_STATUS, + .reply_cmd = ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, + .hdr_attr = ETHTOOL_A_PLCA_HEADER, + .req_info_size = sizeof(struct plca_req_info), + .reply_data_size = sizeof(struct plca_reply_data), + + .prepare_data = plca_get_status_prepare_data, + .reply_size = plca_get_status_reply_size, + .fill_reply = plca_get_status_fill_reply, +}; -- cgit v1.2.3 From 16178c8ef53dc9734302c4c07633696454579ee3 Mon Sep 17 00:00:00 2001 From: Piergiorgio Beruto Date: Mon, 9 Jan 2023 17:59:58 +0100 Subject: drivers/net/phy: add the link modes for the 10BASE-T1S Ethernet PHY This patch adds the link modes for the IEEE 802.3cg Clause 147 10BASE-T1S Ethernet PHY. According to the specifications, the 10BASE-T1S supports Point-To-Point Full-Duplex, Point-To-Point Half-Duplex and/or Point-To-Multipoint (AKA Multi-Drop) Half-Duplex operations. Signed-off-by: Piergiorgio Beruto Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy-core.c | 5 ++++- drivers/net/phy/phy_device.c | 14 ++++++++++++++ drivers/net/phy/phylink.c | 6 +++++- include/linux/phy.h | 14 ++++++++++++++ include/uapi/linux/ethtool.h | 3 +++ net/ethtool/common.c | 8 ++++++++ 6 files changed, 48 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 5d08c627a516..a64186dc53f8 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 != 99, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 102, "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"); @@ -260,6 +260,9 @@ static const struct phy_setting settings[] = { PHY_SETTING( 10, FULL, 10baseT_Full ), PHY_SETTING( 10, HALF, 10baseT_Half ), PHY_SETTING( 10, FULL, 10baseT1L_Full ), + PHY_SETTING( 10, FULL, 10baseT1S_Full ), + PHY_SETTING( 10, HALF, 10baseT1S_Half ), + PHY_SETTING( 10, HALF, 10baseT1S_P2MP_Half ), }; #undef PHY_SETTING diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index e4562859ac00..1cde41d39196 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -45,6 +45,9 @@ EXPORT_SYMBOL_GPL(phy_basic_features); __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_basic_t1_features); +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_basic_t1s_p2mp_features); + __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_gbit_features); @@ -98,6 +101,12 @@ const int phy_basic_t1_features_array[3] = { }; EXPORT_SYMBOL_GPL(phy_basic_t1_features_array); +const int phy_basic_t1s_p2mp_features_array[2] = { + ETHTOOL_LINK_MODE_TP_BIT, + ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, +}; +EXPORT_SYMBOL_GPL(phy_basic_t1s_p2mp_features_array); + const int phy_gbit_features_array[2] = { ETHTOOL_LINK_MODE_1000baseT_Half_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT, @@ -138,6 +147,11 @@ static void features_init(void) ARRAY_SIZE(phy_basic_t1_features_array), phy_basic_t1_features); + /* 10 half, P2MP, TP */ + linkmode_set_bit_array(phy_basic_t1s_p2mp_features_array, + ARRAY_SIZE(phy_basic_t1s_p2mp_features_array), + phy_basic_t1s_p2mp_features); + /* 10/100 half/full + 1000 half/full */ linkmode_set_bit_array(phy_basic_ports_array, ARRAY_SIZE(phy_basic_ports_array), diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 09cc65c0da93..319790221d7f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -241,12 +241,16 @@ void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps) if (caps & MAC_ASYM_PAUSE) __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, linkmodes); - if (caps & MAC_10HD) + if (caps & MAC_10HD) { __set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10baseT1S_Half_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, linkmodes); + } if (caps & MAC_10FD) { __set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, linkmodes); __set_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10baseT1S_Full_BIT, linkmodes); } if (caps & MAC_100HD) { diff --git a/include/linux/phy.h b/include/linux/phy.h index b82fdb0d82ed..63b199f574f7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -45,6 +45,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; @@ -54,6 +55,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) +#define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) @@ -66,6 +68,7 @@ extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; +extern const int phy_basic_t1s_p2mp_features_array[2]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; @@ -1041,6 +1044,17 @@ struct phy_driver { int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); + + /* PLCA RS interface */ + /** @get_plca_cfg: Return the current PLCA configuration */ + int (*get_plca_cfg)(struct phy_device *dev, + struct phy_plca_cfg *plca_cfg); + /** @set_plca_cfg: Set the PLCA configuration */ + int (*set_plca_cfg)(struct phy_device *dev, + const struct phy_plca_cfg *plca_cfg); + /** @get_plca_status: Return the current PLCA status info */ + int (*get_plca_status)(struct phy_device *dev, + struct phy_plca_status *plca_st); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 3135fa0ba9a4..6389953c32cf 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1741,6 +1741,9 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT = 96, ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT = 97, ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT = 98, + ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, + ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, + ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6f399afc2ff2..5fb19050991e 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -208,6 +208,9 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(800000, DR8_2, Full), __DEFINE_LINK_MODE_NAME(800000, SR8, Full), __DEFINE_LINK_MODE_NAME(800000, VR8, Full), + __DEFINE_LINK_MODE_NAME(10, T1S, Full), + __DEFINE_LINK_MODE_NAME(10, T1S, Half), + __DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -244,6 +247,8 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_X 1 #define __LINK_MODE_LANES_FX 1 #define __LINK_MODE_LANES_T1L 1 +#define __LINK_MODE_LANES_T1S 1 +#define __LINK_MODE_LANES_T1S_P2MP 1 #define __LINK_MODE_LANES_VR8 8 #define __LINK_MODE_LANES_DR8_2 8 @@ -366,6 +371,9 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full), __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full), __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full), + __DEFINE_LINK_MODE_PARAMS(10, T1S, Full), + __DEFINE_LINK_MODE_PARAMS(10, T1S, Half), + __DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); -- cgit v1.2.3 From 31de2842399ae68c4b2887ffeaedebb7934f343e Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Wed, 11 Jan 2023 14:05:18 +0100 Subject: ethtool: add tx aggregation parameters Add the following ethtool tx aggregation parameters: ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES Maximum size in bytes of a tx aggregated block of frames. ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES Maximum number of frames that can be aggregated into a block. ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS Time in usecs after the first packet arrival in an aggregated block for the block to be sent. Signed-off-by: Daniele Palmas Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 17 +++++++++++++++++ include/linux/ethtool.h | 12 +++++++++++- include/uapi/linux/ethtool_netlink.h | 3 +++ net/ethtool/coalesce.c | 22 ++++++++++++++++++++-- 4 files changed, 51 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index c59b542eb693..d345f5df248e 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1004,6 +1004,9 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval ``ETHTOOL_A_COALESCE_USE_CQE_TX`` bool timer reset mode, Tx ``ETHTOOL_A_COALESCE_USE_CQE_RX`` bool timer reset mode, Rx + ``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 =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1022,6 +1025,17 @@ each packet event resets the timer. In this mode timer is used to force the interrupt if queue goes idle, while busy queues depend on the packet limit to trigger interrupts. +Tx aggregation consists of copying frames into a contiguous buffer so that they +can be submitted as a single IO operation. ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` +describes the maximum size in bytes for the submitted buffer. +``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` describes the maximum number of frames +that can be aggregated into a single buffer. +``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` describes the amount of time in usecs, +counted since the first packet arrival in an aggregated block, after which the +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. + COALESCE_SET ============ @@ -1055,6 +1069,9 @@ Request contents: ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval ``ETHTOOL_A_COALESCE_USE_CQE_TX`` bool timer reset mode, Tx ``ETHTOOL_A_COALESCE_USE_CQE_RX`` bool timer reset mode, Rx + ``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 =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index d0da303f6634..20d197693d34 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -217,6 +217,9 @@ __ethtool_get_link_ksettings(struct net_device *dev, struct kernel_ethtool_coalesce { u8 use_cqe_mode_tx; u8 use_cqe_mode_rx; + u32 tx_aggr_max_bytes; + u32 tx_aggr_max_frames; + u32 tx_aggr_time_usecs; }; /** @@ -260,7 +263,10 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL BIT(21) #define ETHTOOL_COALESCE_USE_CQE_RX BIT(22) #define ETHTOOL_COALESCE_USE_CQE_TX BIT(23) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(23, 0) +#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_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) @@ -288,6 +294,10 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL) #define ETHTOOL_COALESCE_USE_CQE \ (ETHTOOL_COALESCE_USE_CQE_RX | ETHTOOL_COALESCE_USE_CQE_TX) +#define ETHTOOL_COALESCE_TX_AGGR \ + (ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES | \ + ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES | \ + ETHTOOL_COALESCE_TX_AGGR_TIME_USECS) #define ETHTOOL_STAT_NOT_SET (~0ULL) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 75b3d6d476ff..83557cae0b87 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -406,6 +406,9 @@ enum { ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, /* u32 */ ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, /* u8 */ ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, /* u8 */ + ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ + ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ + ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 487bdf345541..e405b47f7eed 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -105,7 +105,10 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _RATE_SAMPLE_INTERVAL */ nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_TX */ - nla_total_size(sizeof(u8)); /* _USE_CQE_MODE_RX */ + 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 */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -180,7 +183,13 @@ static int coalesce_fill_reply(struct sk_buff *skb, coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, kcoal->use_cqe_mode_tx, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, - kcoal->use_cqe_mode_rx, supported)) + kcoal->use_cqe_mode_rx, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, + kcoal->tx_aggr_max_bytes, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, + kcoal->tx_aggr_max_frames, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, + kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; return 0; @@ -227,6 +236,9 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = NLA_POLICY_MAX(NLA_U8, 1), + [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 }, }; int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) @@ -321,6 +333,12 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX], &mod); ethnl_update_u8(&kernel_coalesce.use_cqe_mode_rx, tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX], &mod); + ethnl_update_u32(&kernel_coalesce.tx_aggr_max_bytes, + tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES], &mod); + ethnl_update_u32(&kernel_coalesce.tx_aggr_max_frames, + tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES], &mod); + ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, + tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); ret = 0; if (!mod) goto out_ops; -- cgit v1.2.3 From d219df60a70ed0739aa5dd34b477763311fc5a7b Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Fri, 13 Jan 2023 17:24:51 +0800 Subject: bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust_room() Add ipip6 and ip6ip decap support for bpf_skb_adjust_room(). Main use case is for using cls_bpf on ingress hook to decapsulate IPv4 over IPv6 and IPv6 over IPv4 tunnel packets. Add two new flags BPF_F_ADJ_ROOM_DECAP_L3_IPV{4,6} to indicate the new IP header version after decapsulating the outer IP header. Suggested-by: Willem de Bruijn Signed-off-by: Ziyang Xuan Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/b268ec7f0ff9431f4f43b1b40ab856ebb28cb4e1.1673574419.git.william.xuanziyang@huawei.com Signed-off-by: Martin KaFai Lau --- include/uapi/linux/bpf.h | 7 +++++++ net/core/filter.c | 31 ++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 7 +++++++ 3 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bc1a3d232ae4..adae5b168f9d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2647,6 +2647,11 @@ union bpf_attr { * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the * L2 type as Ethernet. * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the outer + * IP header. Used when the inner and outer IP versions are different. + * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -5807,6 +5812,8 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { diff --git a/net/core/filter.c b/net/core/filter.c index d9befa6ba04e..b4547a2c02f4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3381,13 +3381,17 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb) #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) +#define BPF_F_ADJ_ROOM_DECAP_L3_MASK (BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \ + BPF_F_ADJ_ROOM_DECAP_L3_IPV6) + #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ - BPF_ADJ_ROOM_ENCAP_L2_MASK)) + BPF_ADJ_ROOM_ENCAP_L2_MASK) | \ + BPF_F_ADJ_ROOM_DECAP_L3_MASK) static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) @@ -3501,6 +3505,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | + BPF_F_ADJ_ROOM_DECAP_L3_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; @@ -3519,6 +3524,14 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, if (unlikely(ret < 0)) return ret; + /* Match skb->protocol to new outer l3 protocol */ + if (skb->protocol == htons(ETH_P_IP) && + flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) + skb->protocol = htons(ETH_P_IPV6); + else if (skb->protocol == htons(ETH_P_IPV6) && + flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) + skb->protocol = htons(ETH_P_IP); + if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); @@ -3608,6 +3621,22 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, return -ENOTSUPP; } + if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { + if (!shrink) + return -EINVAL; + + switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { + case BPF_F_ADJ_ROOM_DECAP_L3_IPV4: + len_min = sizeof(struct iphdr); + break; + case BPF_F_ADJ_ROOM_DECAP_L3_IPV6: + len_min = sizeof(struct ipv6hdr); + break; + default: + return -EINVAL; + } + } + len_cur = skb->len - skb_network_offset(skb); if ((shrink && (len_diff_abs >= len_cur || len_cur - len_diff_abs < len_min)) || diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bc1a3d232ae4..142b81bcbb2e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2647,6 +2647,11 @@ union bpf_attr { * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the * L2 type as Ethernet. * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the outer + * IP header. Used when the inner and outer IP versions are different. + * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -5807,6 +5812,8 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { -- cgit v1.2.3 From 716c330433e3ad6074d057092b98c09a989e17d8 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Thu, 5 Jan 2023 14:52:58 +0100 Subject: media: uvcvideo: Use standard names for menus Instead of duplicating the menu info, use the one from the core. Also, do not use extra memory for 1:1 mappings. Suggested-by: Laurent Pinchart Signed-off-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart --- drivers/media/usb/uvc/uvc_ctrl.c | 129 ++++++++++++++++++++++++++++----------- drivers/media/usb/uvc/uvc_v4l2.c | 105 +++++++++++++++++++++++-------- drivers/media/usb/uvc/uvcvideo.h | 3 +- include/uapi/linux/uvcvideo.h | 4 +- 4 files changed, 176 insertions(+), 65 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 6354efffe9b0..ee58f0db2763 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -364,19 +364,45 @@ static const u32 uvc_control_classes[] = { V4L2_CID_USER_CLASS, }; -static const struct uvc_menu_info power_line_frequency_controls[] = { - { 0, "Disabled" }, - { 1, "50 Hz" }, - { 2, "60 Hz" }, - { 3, "Auto" }, -}; +static const int exposure_auto_mapping[] = { 2, 1, 4, 8 }; -static const struct uvc_menu_info exposure_auto_controls[] = { - { 2, "Auto Mode" }, - { 1, "Manual Mode" }, - { 4, "Shutter Priority Mode" }, - { 8, "Aperture Priority Mode" }, -}; +/* + * This function translates the V4L2 menu index @idx, as exposed to userspace as + * the V4L2 control value, to the corresponding UVC control value used by the + * device. The custom menu_mapping in the control @mapping is used when + * available, otherwise the function assumes that the V4L2 and UVC values are + * identical. + * + * For controls of type UVC_CTRL_DATA_TYPE_BITMASK, the UVC control value is + * expressed as a bitmask and is thus guaranteed to have a single bit set. + * + * The function returns -EINVAL if the V4L2 menu index @idx isn't valid for the + * control, which includes all controls whose type isn't UVC_CTRL_DATA_TYPE_ENUM + * or UVC_CTRL_DATA_TYPE_BITMASK. + */ +static int uvc_mapping_get_menu_value(const struct uvc_control_mapping *mapping, + u32 idx) +{ + if (!test_bit(idx, &mapping->menu_mask)) + return -EINVAL; + + if (mapping->menu_mapping) + return mapping->menu_mapping[idx]; + + return idx; +} + +static const char * +uvc_mapping_get_menu_name(const struct uvc_control_mapping *mapping, u32 idx) +{ + if (!test_bit(idx, &mapping->menu_mask)) + return NULL; + + if (mapping->menu_names) + return mapping->menu_names[idx]; + + return v4l2_ctrl_get_menu(mapping->id)[idx]; +} static s32 uvc_ctrl_get_zoom(struct uvc_control_mapping *mapping, u8 query, const u8 *data) @@ -525,7 +551,7 @@ static const struct uvc_control_mapping uvc_ctrl_mappings[] = { .offset = 0, .v4l2_type = V4L2_CTRL_TYPE_MENU, .data_type = UVC_CTRL_DATA_TYPE_BITMASK, - .menu_info = exposure_auto_controls, + .menu_mapping = exposure_auto_mapping, .menu_mask = GENMASK(V4L2_EXPOSURE_APERTURE_PRIORITY, V4L2_EXPOSURE_AUTO), .slave_ids = { V4L2_CID_EXPOSURE_ABSOLUTE, }, @@ -731,7 +757,6 @@ const struct uvc_control_mapping uvc_ctrl_power_line_mapping_limited = { .offset = 0, .v4l2_type = V4L2_CTRL_TYPE_MENU, .data_type = UVC_CTRL_DATA_TYPE_ENUM, - .menu_info = power_line_frequency_controls, .menu_mask = GENMASK(V4L2_CID_POWER_LINE_FREQUENCY_60HZ, V4L2_CID_POWER_LINE_FREQUENCY_50HZ), }; @@ -744,7 +769,6 @@ const struct uvc_control_mapping uvc_ctrl_power_line_mapping_uvc11 = { .offset = 0, .v4l2_type = V4L2_CTRL_TYPE_MENU, .data_type = UVC_CTRL_DATA_TYPE_ENUM, - .menu_info = power_line_frequency_controls, .menu_mask = GENMASK(V4L2_CID_POWER_LINE_FREQUENCY_60HZ, V4L2_CID_POWER_LINE_FREQUENCY_DISABLED), }; @@ -762,7 +786,6 @@ static const struct uvc_control_mapping uvc_ctrl_power_line_mapping_uvc15 = { .offset = 0, .v4l2_type = V4L2_CTRL_TYPE_MENU, .data_type = UVC_CTRL_DATA_TYPE_ENUM, - .menu_info = power_line_frequency_controls, .menu_mask = GENMASK(V4L2_CID_POWER_LINE_FREQUENCY_AUTO, V4L2_CID_POWER_LINE_FREQUENCY_DISABLED), }; @@ -995,13 +1018,17 @@ static s32 __uvc_ctrl_get_value(struct uvc_control_mapping *mapping, s32 value = mapping->get(mapping, UVC_GET_CUR, data); if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) { - const struct uvc_menu_info *menu = mapping->menu_info; unsigned int i; - for (i = 0; BIT(i) <= mapping->menu_mask; ++i, ++menu) { + for (i = 0; BIT(i) <= mapping->menu_mask; ++i) { + u32 menu_value; + if (!test_bit(i, &mapping->menu_mask)) continue; - if (menu->value == value) { + + menu_value = uvc_mapping_get_menu_value(mapping, i); + + if (menu_value == value) { value = i; break; } @@ -1212,7 +1239,6 @@ static int __uvc_query_v4l2_ctrl(struct uvc_video_chain *chain, { struct uvc_control_mapping *master_map = NULL; struct uvc_control *master_ctrl = NULL; - const struct uvc_menu_info *menu; unsigned int i; memset(v4l2_ctrl, 0, sizeof(*v4l2_ctrl)); @@ -1257,11 +1283,15 @@ static int __uvc_query_v4l2_ctrl(struct uvc_video_chain *chain, v4l2_ctrl->maximum = fls(mapping->menu_mask) - 1; v4l2_ctrl->step = 1; - menu = mapping->menu_info; - for (i = 0; BIT(i) <= mapping->menu_mask; ++i, ++menu) { + for (i = 0; BIT(i) <= mapping->menu_mask; ++i) { + u32 menu_value; + if (!test_bit(i, &mapping->menu_mask)) continue; - if (menu->value == v4l2_ctrl->default_value) { + + menu_value = uvc_mapping_get_menu_value(mapping, i); + + if (menu_value == v4l2_ctrl->default_value) { v4l2_ctrl->default_value = i; break; } @@ -1360,11 +1390,11 @@ done: int uvc_query_v4l2_menu(struct uvc_video_chain *chain, struct v4l2_querymenu *query_menu) { - const struct uvc_menu_info *menu_info; struct uvc_control_mapping *mapping; struct uvc_control *ctrl; u32 index = query_menu->index; u32 id = query_menu->id; + const char *name; int ret; memset(query_menu, 0, sizeof(*query_menu)); @@ -1386,22 +1416,34 @@ int uvc_query_v4l2_menu(struct uvc_video_chain *chain, goto done; } - menu_info = &mapping->menu_info[query_menu->index]; - if (mapping->data_type == UVC_CTRL_DATA_TYPE_BITMASK) { + int mask; + if (!ctrl->cached) { ret = uvc_ctrl_populate_cache(chain, ctrl); if (ret < 0) goto done; } - if (!(uvc_get_ctrl_bitmap(ctrl, mapping) & menu_info->value)) { + mask = uvc_mapping_get_menu_value(mapping, query_menu->index); + if (mask < 0) { + ret = mask; + goto done; + } + + if (!(uvc_get_ctrl_bitmap(ctrl, mapping) & mask)) { ret = -EINVAL; goto done; } } - strscpy(query_menu->name, menu_info->name, sizeof(query_menu->name)); + name = uvc_mapping_get_menu_name(mapping, query_menu->index); + if (!name) { + ret = -EINVAL; + goto done; + } + + strscpy(query_menu->name, name, sizeof(query_menu->name)); done: mutex_unlock(&chain->ctrl_mutex); @@ -1902,7 +1944,7 @@ int uvc_ctrl_set(struct uvc_fh *handle, if (!test_bit(xctrl->value, &mapping->menu_mask)) return -EINVAL; - value = mapping->menu_info[xctrl->value].value; + value = uvc_mapping_get_menu_value(mapping, xctrl->value); /* * Valid menu indices are reported by the GET_RES request for @@ -2327,7 +2369,8 @@ static int __uvc_ctrl_add_mapping(struct uvc_video_chain *chain, return -ENOMEM; map->name = NULL; - map->menu_info = NULL; + map->menu_names = NULL; + map->menu_mapping = NULL; /* For UVCIOC_CTRL_MAP custom control */ if (mapping->name) { @@ -2338,10 +2381,22 @@ static int __uvc_ctrl_add_mapping(struct uvc_video_chain *chain, INIT_LIST_HEAD(&map->ev_subs); - size = sizeof(*mapping->menu_info) * fls(mapping->menu_mask); - map->menu_info = kmemdup(mapping->menu_info, size, GFP_KERNEL); - if (!map->menu_info) - goto err_nomem; + if (mapping->menu_mapping && mapping->menu_mask) { + size = sizeof(mapping->menu_mapping[0]) + * fls(mapping->menu_mask); + map->menu_mapping = kmemdup(mapping->menu_mapping, size, + GFP_KERNEL); + if (!map->menu_mapping) + goto err_nomem; + } + if (mapping->menu_names && mapping->menu_mask) { + size = sizeof(mapping->menu_names[0]) + * fls(mapping->menu_mask); + map->menu_names = kmemdup(mapping->menu_names, size, + GFP_KERNEL); + if (!map->menu_names) + goto err_nomem; + } if (map->get == NULL) map->get = uvc_get_le_value; @@ -2364,7 +2419,8 @@ static int __uvc_ctrl_add_mapping(struct uvc_video_chain *chain, return 0; err_nomem: - kfree(map->menu_info); + kfree(map->menu_names); + kfree(map->menu_mapping); kfree(map->name); kfree(map); return -ENOMEM; @@ -2689,7 +2745,8 @@ static void uvc_ctrl_cleanup_mappings(struct uvc_device *dev, list_for_each_entry_safe(mapping, nm, &ctrl->info.mappings, list) { list_del(&mapping->list); - kfree(mapping->menu_info); + kfree(mapping->menu_names); + kfree(mapping->menu_mapping); kfree(mapping->name); kfree(mapping); } diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index 950b42d78a10..35453f81c1d9 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -26,14 +26,84 @@ #include "uvcvideo.h" +static int uvc_control_add_xu_mapping(struct uvc_video_chain *chain, + struct uvc_control_mapping *map, + const struct uvc_xu_control_mapping *xmap) +{ + unsigned int i; + size_t size; + int ret; + + /* + * Prevent excessive memory consumption, as well as integer + * overflows. + */ + if (xmap->menu_count == 0 || + xmap->menu_count > UVC_MAX_CONTROL_MENU_ENTRIES) + return -EINVAL; + + map->menu_names = NULL; + map->menu_mapping = NULL; + + map->menu_mask = BIT_MASK(xmap->menu_count); + + size = xmap->menu_count * sizeof(*map->menu_mapping); + map->menu_mapping = kzalloc(size, GFP_KERNEL); + if (!map->menu_mapping) { + ret = -ENOMEM; + goto done; + } + + for (i = 0; i < xmap->menu_count ; i++) { + if (copy_from_user((u32 *)&map->menu_mapping[i], + &xmap->menu_info[i].value, + sizeof(map->menu_mapping[i]))) { + ret = -EACCES; + goto done; + } + } + + /* + * Always use the standard naming if available, otherwise copy the + * names supplied by userspace. + */ + if (!v4l2_ctrl_get_menu(map->id)) { + size = xmap->menu_count * sizeof(map->menu_names[0]); + map->menu_names = kzalloc(size, GFP_KERNEL); + if (!map->menu_names) { + ret = -ENOMEM; + goto done; + } + + for (i = 0; i < xmap->menu_count ; i++) { + /* sizeof(names[i]) - 1: to take care of \0 */ + if (copy_from_user((char *)map->menu_names[i], + xmap->menu_info[i].name, + sizeof(map->menu_names[i]) - 1)) { + ret = -EACCES; + goto done; + } + } + } + + ret = uvc_ctrl_add_mapping(chain, map); + +done: + kfree(map->menu_names); + map->menu_names = NULL; + kfree(map->menu_mapping); + map->menu_mapping = NULL; + + return ret; +} + /* ------------------------------------------------------------------------ * UVC ioctls */ -static int uvc_ioctl_ctrl_map(struct uvc_video_chain *chain, - struct uvc_xu_control_mapping *xmap) +static int uvc_ioctl_xu_ctrl_map(struct uvc_video_chain *chain, + struct uvc_xu_control_mapping *xmap) { struct uvc_control_mapping *map; - unsigned int size; int ret; map = kzalloc(sizeof(*map), GFP_KERNEL); @@ -61,39 +131,20 @@ static int uvc_ioctl_ctrl_map(struct uvc_video_chain *chain, case V4L2_CTRL_TYPE_INTEGER: case V4L2_CTRL_TYPE_BOOLEAN: case V4L2_CTRL_TYPE_BUTTON: + ret = uvc_ctrl_add_mapping(chain, map); break; case V4L2_CTRL_TYPE_MENU: - /* - * Prevent excessive memory consumption, as well as integer - * overflows. - */ - if (xmap->menu_count == 0 || - xmap->menu_count > UVC_MAX_CONTROL_MENU_ENTRIES) { - ret = -EINVAL; - goto free_map; - } - - size = xmap->menu_count * sizeof(*map->menu_info); - map->menu_info = memdup_user(xmap->menu_info, size); - if (IS_ERR(map->menu_info)) { - ret = PTR_ERR(map->menu_info); - goto free_map; - } - - map->menu_mask = GENMASK(xmap->menu_count - 1, 0); + ret = uvc_control_add_xu_mapping(chain, map, xmap); break; default: uvc_dbg(chain->dev, CONTROL, "Unsupported V4L2 control type %u\n", xmap->v4l2_type); ret = -ENOTTY; - goto free_map; + break; } - ret = uvc_ctrl_add_mapping(chain, map); - - kfree(map->menu_info); free_map: kfree(map); @@ -1314,7 +1365,7 @@ static long uvc_ioctl_default(struct file *file, void *fh, bool valid_prio, switch (cmd) { /* Dynamic controls. */ case UVCIOC_CTRL_MAP: - return uvc_ioctl_ctrl_map(chain, arg); + return uvc_ioctl_xu_ctrl_map(chain, arg); case UVCIOC_CTRL_QUERY: return uvc_xu_ctrl_query(chain, arg); @@ -1427,7 +1478,7 @@ static long uvc_v4l2_compat_ioctl32(struct file *file, ret = uvc_v4l2_get_xu_mapping(&karg.xmap, up); if (ret) return ret; - ret = uvc_ioctl_ctrl_map(handle->chain, &karg.xmap); + ret = uvc_ioctl_xu_ctrl_map(handle->chain, &karg.xmap); if (ret) return ret; ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up); diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 178729467967..e85df8deb965 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -114,7 +114,8 @@ struct uvc_control_mapping { enum v4l2_ctrl_type v4l2_type; u32 data_type; - const struct uvc_menu_info *menu_info; + const u32 *menu_mapping; + const char (*menu_names)[UVC_MENU_NAME_LEN]; unsigned long menu_mask; u32 master_id; diff --git a/include/uapi/linux/uvcvideo.h b/include/uapi/linux/uvcvideo.h index 8288137387c0..d45d0c2ea252 100644 --- a/include/uapi/linux/uvcvideo.h +++ b/include/uapi/linux/uvcvideo.h @@ -36,9 +36,11 @@ UVC_CTRL_FLAG_GET_MAX | UVC_CTRL_FLAG_GET_RES | \ UVC_CTRL_FLAG_GET_DEF) +#define UVC_MENU_NAME_LEN 32 + struct uvc_menu_info { __u32 value; - __u8 name[32]; + __u8 name[UVC_MENU_NAME_LEN]; }; struct uvc_xu_control_mapping { -- cgit v1.2.3 From b839212988575c701aab4d3d9ca15e44c87e383c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 22:17:04 -0800 Subject: media: uvcvideo: Silence memcpy() run-time false positive warnings The memcpy() in uvc_video_decode_meta() intentionally copies across the length and flags members and into the trailing buf flexible array. Split the copy so that the compiler can better reason about (the lack of) buffer overflows here. Avoid the run-time false positive warning: memcpy: detected field-spanning write (size 12) of single field "&meta->length" at drivers/media/usb/uvc/uvc_video.c:1355 (size 1) Additionally fix a typo in the documentation for struct uvc_meta_buf. Reported-by: ionut_n2001@yahoo.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=216810 Signed-off-by: Kees Cook Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart --- drivers/media/usb/uvc/uvc_video.c | 4 +++- include/uapi/linux/uvcvideo.h | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 98d34d20afe3..d4b023d4de7c 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -1356,7 +1356,9 @@ static void uvc_video_decode_meta(struct uvc_streaming *stream, if (has_scr) memcpy(stream->clock.last_scr, scr, 6); - memcpy(&meta->length, mem, length); + meta->length = mem[0]; + meta->flags = mem[1]; + memcpy(meta->buf, &mem[2], length - 2); meta_buf->bytesused += length + sizeof(meta->ns) + sizeof(meta->sof); uvc_dbg(stream->dev, FRAME, diff --git a/include/uapi/linux/uvcvideo.h b/include/uapi/linux/uvcvideo.h index d45d0c2ea252..f86185456dc5 100644 --- a/include/uapi/linux/uvcvideo.h +++ b/include/uapi/linux/uvcvideo.h @@ -88,7 +88,7 @@ struct uvc_xu_control_query { * struct. The first two fields are added by the driver, they can be used for * clock synchronisation. The rest is an exact copy of a UVC payload header. * Only complete objects with complete buffers are included. Therefore it's - * always sizeof(meta->ts) + sizeof(meta->sof) + meta->length bytes large. + * always sizeof(meta->ns) + sizeof(meta->sof) + meta->length bytes large. */ struct uvc_meta_buf { __u64 ns; -- cgit v1.2.3 From 0349b8779cc949ad9e6aced32672ee48cf79b497 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 13 Jan 2023 11:43:53 +0800 Subject: sched: add new attr TCA_EXT_WARN_MSG to report tc extact message We will report extack message if there is an error via netlink_ack(). But if the rule is not to be exclusively executed by the hardware, extack is not passed along and offloading failures don't get logged. In commit 81c7288b170a ("sched: cls: enable verbose logging") Marcelo made cls could log verbose info for offloading failures, which helps improving Open vSwitch debuggability when using flower offloading. It would also be helpful if userspace monitor tools, like "tc monitor", could log this kind of message, as it doesn't require vswitchd log level adjusment. Let's add a new tc attributes to report the extack message so the monitor program could receive the failures. e.g. # tc monitor added chain dev enp3s0f1np1 parent ffff: chain 0 added filter dev enp3s0f1np1 ingress protocol all pref 49152 flower chain 0 handle 0x1 ct_state +trk+new not_in_hw action order 1: gact action drop random type none pass val 0 index 1 ref 1 bind 1 Warning: mlx5_core: matching on ct_state +new isn't supported. In this patch I only report the extack message on add/del operations. It doesn't look like we need to report the extack message on get/dump operations. Note this message not only reporte to multicast groups, it could also be reported unicast, which may affect the current usersapce tool's behaivor. Suggested-by: Marcelo Ricardo Leitner Signed-off-by: Hangbin Liu Acked-by: Jakub Kicinski Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230113034353.2766735-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni --- include/uapi/linux/rtnetlink.h | 1 + net/sched/act_api.c | 15 ++++++---- net/sched/cls_api.c | 62 ++++++++++++++++++++++++++---------------- net/sched/sch_api.c | 55 +++++++++++++++++++++++-------------- 4 files changed, 84 insertions(+), 49 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index eb2747d58a81..25a0af57dd5e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -635,6 +635,7 @@ enum { TCA_INGRESS_BLOCK, TCA_EGRESS_BLOCK, TCA_DUMP_FLAGS, + TCA_EXT_WARN_MSG, __TCA_MAX }; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 5b3c0ac495be..cd09ef49df22 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1582,7 +1582,7 @@ errout: static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], u32 portid, u32 seq, u16 flags, int event, int bind, - int ref) + int ref, struct netlink_ext_ack *extack) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -1606,7 +1606,12 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], nla_nest_end(skb, nest); + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1625,7 +1630,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, - 0, 1) <= 0) { + 0, 1, NULL) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; @@ -1799,7 +1804,7 @@ tcf_reoffload_del_notify(struct net *net, struct tc_action *action) if (!skb) return -ENOBUFS; - if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1) <= 0) { + if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1, NULL) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1886,7 +1891,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, - 0, 2) <= 0) { + 0, 2, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); return -EINVAL; @@ -1965,7 +1970,7 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, - RTM_NEWACTION, 0, 0) <= 0) { + RTM_NEWACTION, 0, 0, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 668130f08903..5b4a95e8a1ee 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -488,7 +488,8 @@ static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block, #endif static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, - u32 seq, u16 flags, int event, bool unicast); + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack); static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create, @@ -521,7 +522,7 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, */ if (is_first_reference && !by_act) tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + RTM_NEWCHAIN, false, NULL); return chain; @@ -1817,7 +1818,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, u32 portid, u32 seq, u16 flags, int event, - bool terse_dump, bool rtnl_held) + bool terse_dump, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1857,7 +1859,13 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) goto nla_put_failure; } + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto nla_put_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1871,7 +1879,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, int event, bool unicast, - bool rtnl_held) + bool rtnl_held, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1883,7 +1891,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event, - false, rtnl_held) <= 0) { + false, rtnl_held, extack) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1912,7 +1920,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER, - false, rtnl_held) <= 0) { + false, rtnl_held, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); kfree_skb(skb); return -EINVAL; @@ -1938,14 +1946,15 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct tcf_block *block, struct Qdisc *q, u32 parent, struct nlmsghdr *n, - struct tcf_chain *chain, int event) + struct tcf_chain *chain, int event, + struct netlink_ext_ack *extack) { struct tcf_proto *tp; for (tp = tcf_get_next_proto(chain, NULL); tp; tp = tcf_get_next_proto(chain, tp)) - tfilter_notify(net, oskb, n, tp, block, - q, parent, NULL, event, false, true); + tfilter_notify(net, oskb, n, tp, block, q, parent, NULL, + event, false, true, extack); } static void tfilter_put(struct tcf_proto *tp, void *fh) @@ -2156,7 +2165,7 @@ replay: flags, extack); if (err == 0) { tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_NEWTFILTER, false, rtnl_held); + RTM_NEWTFILTER, false, rtnl_held, extack); tfilter_put(tp, fh); /* q pointer is NULL for shared blocks */ if (q) @@ -2284,7 +2293,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (prio == 0) { tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, extack); tcf_chain_flush(chain, rtnl_held); err = 0; goto errout; @@ -2308,7 +2317,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, tcf_proto_put(tp, rtnl_held, NULL); tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_DELTFILTER, false, rtnl_held); + RTM_DELTFILTER, false, rtnl_held, extack); err = 0; goto errout; } @@ -2452,7 +2461,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -ENOENT; } else { err = tfilter_notify(net, skb, n, tp, block, q, parent, - fh, RTM_NEWTFILTER, true, rtnl_held); + fh, RTM_NEWTFILTER, true, rtnl_held, NULL); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); } @@ -2490,7 +2499,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER, a->terse_dump, true); + RTM_NEWTFILTER, a->terse_dump, true, NULL); } static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, @@ -2524,7 +2533,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER, false, true) <= 0) + RTM_NEWTFILTER, false, true, NULL) <= 0) goto errout; cb->args[1] = 1; } @@ -2667,7 +2676,8 @@ static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, void *tmplt_priv, u32 chain_index, struct net *net, struct sk_buff *skb, struct tcf_block *block, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) { unsigned char *b = skb_tail_pointer(skb); const struct tcf_proto_ops *ops; @@ -2704,7 +2714,12 @@ static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, goto nla_put_failure; } + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -2714,7 +2729,8 @@ nla_put_failure: } static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, - u32 seq, u16 flags, int event, bool unicast) + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct tcf_block *block = chain->block; @@ -2728,7 +2744,7 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, chain->index, net, skb, block, portid, - seq, flags, event) <= 0) { + seq, flags, event, extack) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -2756,7 +2772,7 @@ static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, return -ENOBUFS; if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb, - block, portid, seq, flags, RTM_DELCHAIN) <= 0) { + block, portid, seq, flags, RTM_DELCHAIN, NULL) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -2908,11 +2924,11 @@ replay: } tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + RTM_NEWCHAIN, false, extack); break; case RTM_DELCHAIN: tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, extack); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain, true); /* In case the chain was successfully deleted, put a reference @@ -2922,7 +2938,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_flags, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true, extack); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; @@ -3022,7 +3038,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) chain->index, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWCHAIN); + RTM_NEWCHAIN, NULL); if (err <= 0) break; index++; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 72d2c204d5f3..c14018a8052c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -902,7 +902,8 @@ static void qdisc_offload_graft_root(struct net_device *dev, } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) { struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; @@ -970,7 +971,12 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -991,7 +997,8 @@ static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) static int qdisc_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new) + struct Qdisc *old, struct Qdisc *new, + struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1002,12 +1009,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, - 0, RTM_DELQDISC) < 0) + 0, RTM_DELQDISC, extack) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, - old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) + old ? NLM_F_REPLACE : 0, RTM_NEWQDISC, extack) < 0) goto err_out; } @@ -1022,10 +1029,11 @@ err_out: static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new) + struct Qdisc *old, struct Qdisc *new, + struct netlink_ext_ack *extack) { if (new || old) - qdisc_notify(net, skb, n, clid, old, new); + qdisc_notify(net, skb, n, clid, old, new, extack); if (old) qdisc_put(old); @@ -1105,12 +1113,12 @@ skip: qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); - notify_and_destroy(net, skb, n, classid, old, new); + notify_and_destroy(net, skb, n, classid, old, new, extack); if (new && new->ops->attach) new->ops->attach(new); } else { - notify_and_destroy(net, skb, n, classid, old, new); + notify_and_destroy(net, skb, n, classid, old, new, extack); } if (dev->flags & IFF_UP) @@ -1141,7 +1149,7 @@ skip: err = cops->graft(parent, cl, new, &old, extack); if (err) return err; - notify_and_destroy(net, skb, n, classid, old, new); + notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; } @@ -1509,7 +1517,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, if (err != 0) return err; } else { - qdisc_notify(net, skb, n, clid, NULL, q); + qdisc_notify(net, skb, n, clid, NULL, q, NULL); } return 0; } @@ -1648,7 +1656,7 @@ replay: } err = qdisc_change(q, tca, extack); if (err == 0) - qdisc_notify(net, skb, n, clid, NULL, q); + qdisc_notify(net, skb, n, clid, NULL, q, extack); return err; create_n_graft: @@ -1715,7 +1723,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWQDISC) <= 0) + RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } @@ -1737,7 +1745,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWQDISC) <= 0) + RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } @@ -1810,8 +1818,8 @@ done: ************************************************/ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, - unsigned long cl, - u32 portid, u32 seq, u16 flags, int event) + unsigned long cl, u32 portid, u32 seq, u16 flags, + int event, struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1846,7 +1854,12 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1857,7 +1870,7 @@ nla_put_failure: static int tclass_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, - unsigned long cl, int event) + unsigned long cl, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1866,7 +1879,7 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) { + if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event, extack) < 0) { kfree_skb(skb); return -EINVAL; } @@ -1893,7 +1906,7 @@ static int tclass_del_notify(struct net *net, return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, - RTM_DELTCLASS) < 0) { + RTM_DELTCLASS, extack) < 0) { kfree_skb(skb); return -EINVAL; } @@ -2100,7 +2113,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, tc_bind_tclass(q, portid, clid, 0); goto out; case RTM_GETTCLASS: - err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS); + err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS, extack); goto out; default: err = -EINVAL; @@ -2118,7 +2131,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, if (cops->change) err = cops->change(q, clid, portid, tca, &new_cl, extack); if (err == 0) { - tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS); + tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS, extack); /* We just create a new class, need to do reverse binding. */ if (cl != new_cl) tc_bind_tclass(q, portid, clid, new_cl); @@ -2140,7 +2153,7 @@ static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTCLASS); + RTM_NEWTCLASS, NULL); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, -- cgit v1.2.3 From f80a612dd77c4585171e44a06b490466bdeec1ae Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Mon, 2 Jan 2023 15:42:34 +0100 Subject: netfilter: nf_tables: add support to destroy operation Introduce NFT_MSG_DESTROY* message type. The destroy operation performs a delete operation but ignoring the ENOENT errors. This is useful for the transaction semantics, where failing to delete an object which does not exist results in aborting the transaction. This new command allows the transaction to proceed in case the object does not exist. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter/nf_tables.h | 14 ++++ net/netfilter/nf_tables_api.c | 111 ++++++++++++++++++++++++++++--- 2 files changed, 117 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index cfa844da1ce6..ff677f3a6cad 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -98,6 +98,13 @@ enum nft_verdicts { * @NFT_MSG_GETFLOWTABLE: get flow table (enum nft_flowtable_attributes) * @NFT_MSG_DELFLOWTABLE: delete flow table (enum nft_flowtable_attributes) * @NFT_MSG_GETRULE_RESET: get rules and reset stateful expressions (enum nft_obj_attributes) + * @NFT_MSG_DESTROYTABLE: destroy a table (enum nft_table_attributes) + * @NFT_MSG_DESTROYCHAIN: destroy a chain (enum nft_chain_attributes) + * @NFT_MSG_DESTROYRULE: destroy a rule (enum nft_rule_attributes) + * @NFT_MSG_DESTROYSET: destroy a set (enum nft_set_attributes) + * @NFT_MSG_DESTROYSETELEM: destroy a set element (enum nft_set_elem_attributes) + * @NFT_MSG_DESTROYOBJ: destroy a stateful object (enum nft_object_attributes) + * @NFT_MSG_DESTROYFLOWTABLE: destroy flow table (enum nft_flowtable_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -126,6 +133,13 @@ enum nf_tables_msg_types { NFT_MSG_GETFLOWTABLE, NFT_MSG_DELFLOWTABLE, NFT_MSG_GETRULE_RESET, + NFT_MSG_DESTROYTABLE, + NFT_MSG_DESTROYCHAIN, + NFT_MSG_DESTROYRULE, + NFT_MSG_DESTROYSET, + NFT_MSG_DESTROYSETELEM, + NFT_MSG_DESTROYOBJ, + NFT_MSG_DESTROYFLOWTABLE, NFT_MSG_MAX, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8c09e4d12ac1..974b95dece1d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1401,6 +1401,10 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, } if (IS_ERR(table)) { + if (PTR_ERR(table) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYTABLE) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(table); } @@ -2639,6 +2643,10 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, chain = nft_chain_lookup(net, table, attr, genmask); } if (IS_ERR(chain)) { + if (PTR_ERR(chain) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); } @@ -3716,6 +3724,10 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { + if (PTR_ERR(rule) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) + return 0; + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } @@ -3729,6 +3741,10 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_RULE_HANDLE]) { rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { + if (PTR_ERR(rule) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) + return 0; + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); } @@ -4808,6 +4824,10 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, } if (IS_ERR(set)) { + if (PTR_ERR(set) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSET) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(set); } @@ -6690,6 +6710,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); + if (err == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM) + continue; + if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; @@ -7334,6 +7358,10 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, } if (IS_ERR(obj)) { + if (PTR_ERR(obj) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYOBJ) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(obj); } @@ -7964,6 +7992,10 @@ static int nf_tables_delflowtable(struct sk_buff *skb, } if (IS_ERR(flowtable)) { + if (PTR_ERR(flowtable) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYFLOWTABLE) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(flowtable); } @@ -8373,6 +8405,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, + [NFT_MSG_DESTROYTABLE] = { + .call = nf_tables_deltable, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_TABLE_MAX, + .policy = nft_table_policy, + }, [NFT_MSG_NEWCHAIN] = { .call = nf_tables_newchain, .type = NFNL_CB_BATCH, @@ -8391,6 +8429,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, + [NFT_MSG_DESTROYCHAIN] = { + .call = nf_tables_delchain, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_CHAIN_MAX, + .policy = nft_chain_policy, + }, [NFT_MSG_NEWRULE] = { .call = nf_tables_newrule, .type = NFNL_CB_BATCH, @@ -8415,6 +8459,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, + [NFT_MSG_DESTROYRULE] = { + .call = nf_tables_delrule, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_RULE_MAX, + .policy = nft_rule_policy, + }, [NFT_MSG_NEWSET] = { .call = nf_tables_newset, .type = NFNL_CB_BATCH, @@ -8433,6 +8483,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, + [NFT_MSG_DESTROYSET] = { + .call = nf_tables_delset, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_SET_MAX, + .policy = nft_set_policy, + }, [NFT_MSG_NEWSETELEM] = { .call = nf_tables_newsetelem, .type = NFNL_CB_BATCH, @@ -8451,6 +8507,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, + [NFT_MSG_DESTROYSETELEM] = { + .call = nf_tables_delsetelem, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_SET_ELEM_LIST_MAX, + .policy = nft_set_elem_list_policy, + }, [NFT_MSG_GETGEN] = { .call = nf_tables_getgen, .type = NFNL_CB_RCU, @@ -8473,6 +8535,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, + [NFT_MSG_DESTROYOBJ] = { + .call = nf_tables_delobj, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_OBJ_MAX, + .policy = nft_obj_policy, + }, [NFT_MSG_GETOBJ_RESET] = { .call = nf_tables_getobj, .type = NFNL_CB_RCU, @@ -8497,6 +8565,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, + [NFT_MSG_DESTROYFLOWTABLE] = { + .call = nf_tables_delflowtable, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_FLOWTABLE_MAX, + .policy = nft_flowtable_policy, + }, }; static int nf_tables_validate(struct net *net) @@ -8590,6 +8664,7 @@ static void nft_commit_release(struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_DELTABLE: + case NFT_MSG_DESTROYTABLE: nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: @@ -8597,23 +8672,29 @@ static void nft_commit_release(struct nft_trans *trans) kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: + case NFT_MSG_DESTROYSET: nft_set_destroy(&trans->ctx, nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: + case NFT_MSG_DESTROYSETELEM: nf_tables_set_elem_destroy(&trans->ctx, nft_trans_elem_set(trans), nft_trans_elem(trans).priv); break; case NFT_MSG_DELOBJ: + case NFT_MSG_DESTROYOBJ: nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: + case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else @@ -9065,8 +9146,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELTABLE: + case NFT_MSG_DESTROYTABLE: list_del_rcu(&trans->ctx.table->list); - nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); + nf_tables_table_notify(&trans->ctx, trans->msg_type); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { @@ -9081,8 +9163,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } break; case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: nft_chain_del(trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN); + nf_tables_chain_notify(&trans->ctx, trans->msg_type); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, trans->ctx.chain); @@ -9098,10 +9181,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: list_del_rcu(&nft_trans_rule(trans)->list); nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), - NFT_MSG_DELRULE); + trans->msg_type); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); @@ -9129,9 +9213,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSET: + case NFT_MSG_DESTROYSET: list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), - NFT_MSG_DELSET, GFP_KERNEL); + trans->msg_type, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; @@ -9143,11 +9228,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: + case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_DELSETELEM); + trans->msg_type); nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) { atomic_dec(&te->set->nelems); @@ -9169,9 +9255,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } break; case NFT_MSG_DELOBJ: + case NFT_MSG_DESTROYOBJ: nft_obj_del(nft_trans_obj(trans)); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), - NFT_MSG_DELOBJ); + trans->msg_type); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { @@ -9193,11 +9280,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELFLOWTABLE: + case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), - NFT_MSG_DELFLOWTABLE); + trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { @@ -9205,7 +9293,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list, - NFT_MSG_DELFLOWTABLE); + trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); } @@ -9301,6 +9389,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELTABLE: + case NFT_MSG_DESTROYTABLE: nft_clear(trans->ctx.net, trans->ctx.table); nft_trans_destroy(trans); break; @@ -9322,6 +9411,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: trans->ctx.table->use++; nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); @@ -9336,6 +9426,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); @@ -9357,6 +9448,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: + case NFT_MSG_DESTROYSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); nft_trans_destroy(trans); @@ -9372,6 +9464,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) atomic_dec(&te->set->nelems); break; case NFT_MSG_DELSETELEM: + case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; nft_setelem_data_activate(net, te->set, &te->elem); @@ -9391,6 +9484,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELOBJ: + case NFT_MSG_DESTROYOBJ: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); @@ -9407,6 +9501,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELFLOWTABLE: + case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); -- cgit v1.2.3 From 648fba791cb0f5ef6166449d056f82e6639fe268 Mon Sep 17 00:00:00 2001 From: Shivani Baranwal Date: Tue, 6 Dec 2022 20:07:15 +0530 Subject: wifi: cfg80211: Support 32 bytes KCK key in GTK rekey offload Currently, maximum KCK key length supported for GTK rekey offload is 24 bytes but with some newer AKMs the KCK key length can be 32 bytes. e.g., 00-0F-AC:24 AKM suite with SAE finite cyclic group 21. Add support to allow 32 bytes KCK keys in GTK rekey offload. Signed-off-by: Shivani Baranwal Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20221206143715.1802987-3-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 ++- include/uapi/linux/nl80211.h | 1 + net/wireless/nl80211.c | 6 ++++-- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1f8f827290a2..f96db7ad64f1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4682,6 +4682,7 @@ struct cfg80211_ops { * in order to not have them reachable in normal drivers, until we have * complete feature/interface combinations/etc. advertisement. No driver * should set this flag for now. + * @WIPHY_FLAG_SUPPORTS_EXT_KCK_32: The device supports 32-byte KCK keys. */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), @@ -4694,7 +4695,7 @@ enum wiphy_flags { WIPHY_FLAG_CONTROL_PORT_PROTOCOL = BIT(7), WIPHY_FLAG_IBSS_RSN = BIT(8), WIPHY_FLAG_MESH_AUTH = BIT(10), - /* use hole at 11 */ + WIPHY_FLAG_SUPPORTS_EXT_KCK_32 = BIT(11), /* use hole at 12 */ WIPHY_FLAG_SUPPORTS_FW_ROAM = BIT(13), WIPHY_FLAG_AP_UAPSD = BIT(14), diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c14a91bbca7c..429bdc399962 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5869,6 +5869,7 @@ enum plink_actions { #define NL80211_KEK_LEN 16 #define NL80211_KCK_EXT_LEN 24 #define NL80211_KEK_EXT_LEN 32 +#define NL80211_KCK_EXT_LEN_32 32 #define NL80211_REPLAY_CTR_LEN 8 /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 02b9a0280896..64cf6110ce9d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -883,7 +883,7 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { }, [NL80211_REKEY_DATA_KCK] = { .type = NLA_BINARY, - .len = NL80211_KCK_EXT_LEN + .len = NL80211_KCK_EXT_LEN_32 }, [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN(NL80211_REPLAY_CTR_LEN), [NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 }, @@ -13809,7 +13809,9 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) return -ERANGE; if (nla_len(tb[NL80211_REKEY_DATA_KCK]) != NL80211_KCK_LEN && !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && - nla_len(tb[NL80211_REKEY_DATA_KCK]) == NL80211_KCK_EXT_LEN)) + nla_len(tb[NL80211_REKEY_DATA_KCK]) == NL80211_KCK_EXT_LEN) && + !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KCK_32 && + nla_len(tb[NL80211_REKEY_DATA_KCK]) == NL80211_KCK_EXT_LEN_32)) return -ERANGE; rekey_data.kek = nla_data(tb[NL80211_REKEY_DATA_KEK]); -- cgit v1.2.3 From bfc551679cd63ca3a4b3e7f338aa2bb06ce43e25 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Tue, 6 Dec 2022 13:32:26 +0530 Subject: wifi: cfg80211: Use MLD address to indicate MLD STA disconnection We use station's MLD address to report disconnection of MLD station. Update the documentation in multiple places to indicate this. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20221206080226.1702646-4-quic_vjakkam@quicinc.com [update commit message] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++-- include/uapi/linux/nl80211.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f96db7ad64f1..54a77d906b2d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7775,7 +7775,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, /** * cfg80211_del_sta_sinfo - notify userspace about deletion of a station * @dev: the netdev - * @mac_addr: the station's address + * @mac_addr: the station's address. For MLD station, MLD address is used. * @sinfo: the station information/statistics * @gfp: allocation flags */ @@ -7786,7 +7786,7 @@ void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr, * cfg80211_del_sta - notify userspace about deletion of a station * * @dev: the netdev - * @mac_addr: the station's address + * @mac_addr: the station's address. For MLD station, MLD address is used. * @gfp: allocation flags */ static inline void cfg80211_del_sta(struct net_device *dev, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 429bdc399962..8ecb0fbee721 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -424,7 +424,8 @@ * interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_DEL_STATION: Remove a station identified by %NL80211_ATTR_MAC * or, if no MAC address given, all stations, on the interface identified - * by %NL80211_ATTR_IFINDEX. %NL80211_ATTR_MGMT_SUBTYPE and + * by %NL80211_ATTR_IFINDEX. For MLD station, MLD address is used in + * %NL80211_ATTR_MAC. %NL80211_ATTR_MGMT_SUBTYPE and * %NL80211_ATTR_REASON_CODE can optionally be used to specify which type * of disconnection indication should be sent to the station * (Deauthentication or Disassociation frame and reason code for that -- cgit v1.2.3 From 6fd7353829cafc4067aad9eea0dc95da67e7df16 Mon Sep 17 00:00:00 2001 From: Daniel Verkamp Date: Thu, 15 Dec 2022 00:12:01 +0000 Subject: mm/memfd: add F_SEAL_EXEC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm/memfd: introduce MFD_NOEXEC_SEAL and MFD_EXEC", v8. Since Linux introduced the memfd feature, memfd have always had their execute bit set, and the memfd_create() syscall doesn't allow setting it differently. However, in a secure by default system, such as ChromeOS, (where all executables should come from the rootfs, which is protected by Verified boot), this executable nature of memfd opens a door for NoExec bypass and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm process created a memfd to share the content with an external process, however the memfd is overwritten and used for executing arbitrary code and root escalation. [2] lists more VRP in this kind. On the other hand, executable memfd has its legit use, runc uses memfd’s seal and executable feature to copy the contents of the binary then execute them, for such system, we need a solution to differentiate runc's use of executable memfds and an attacker's [3]. To address those above, this set of patches add following: 1> Let memfd_create() set X bit at creation time. 2> Let memfd to be sealed for modifying X bit. 3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of X bit.For example, if a container has vm.memfd_noexec=2, then memfd_create() without MFD_NOEXEC_SEAL will be rejected. 4> A new security hook in memfd_create(). This make it possible to a new LSM, which rejects or allows executable memfd based on its security policy. This patch (of 5): The new F_SEAL_EXEC flag will prevent modification of the exec bits: written as traditional octal mask, 0111, or as named flags, S_IXUSR | S_IXGRP | S_IXOTH. Any chmod(2) or similar call that attempts to modify any of these bits after the seal is applied will fail with errno EPERM. This will preserve the execute bits as they are at the time of sealing, so the memfd will become either permanently executable or permanently un-executable. Link: https://lkml.kernel.org/r/20221215001205.51969-1-jeffxu@google.com Link: https://lkml.kernel.org/r/20221215001205.51969-2-jeffxu@google.com Signed-off-by: Daniel Verkamp Co-developed-by: Jeff Xu Signed-off-by: Jeff Xu Reviewed-by: Kees Cook Cc: Dmitry Torokhov Cc: Hugh Dickins Cc: Jann Horn Cc: Jorge Lucangeli Obes Cc: Shuah Khan Cc: David Herrmann Cc: kernel test robot Signed-off-by: Andrew Morton --- include/uapi/linux/fcntl.h | 1 + mm/memfd.c | 2 ++ mm/shmem.c | 6 ++++++ 3 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 2f86b2ad6d7e..e8c07da58c9f 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -43,6 +43,7 @@ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ #define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */ +#define F_SEAL_EXEC 0x0020 /* prevent chmod modifying exec bits */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/mm/memfd.c b/mm/memfd.c index 08f5f8304746..4ebeab94aa74 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -147,6 +147,7 @@ static unsigned int *memfd_file_seals_ptr(struct file *file) } #define F_ALL_SEALS (F_SEAL_SEAL | \ + F_SEAL_EXEC | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ F_SEAL_WRITE | \ @@ -175,6 +176,7 @@ static int memfd_add_seals(struct file *file, unsigned int seals) * SEAL_SHRINK: Prevent the file from shrinking * SEAL_GROW: Prevent the file from growing * SEAL_WRITE: Prevent write access to the file + * SEAL_EXEC: Prevent modification of the exec bits in the file mode * * As we don't require any trust relationship between two parties, we * must prevent seals from being removed. Therefore, sealing a file diff --git a/mm/shmem.c b/mm/shmem.c index 0005ab2c29af..d3f0c94f6836 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1093,6 +1093,12 @@ static int shmem_setattr(struct user_namespace *mnt_userns, if (error) return error; + if ((info->seals & F_SEAL_EXEC) && (attr->ia_valid & ATTR_MODE)) { + if ((inode->i_mode ^ attr->ia_mode) & 0111) { + return -EPERM; + } + } + if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; -- cgit v1.2.3 From 105ff5339f498af74e60d7662c8f1c4d21f1342d Mon Sep 17 00:00:00 2001 From: Jeff Xu Date: Thu, 15 Dec 2022 00:12:03 +0000 Subject: mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC The new MFD_NOEXEC_SEAL and MFD_EXEC flags allows application to set executable bit at creation time (memfd_create). When MFD_NOEXEC_SEAL is set, memfd is created without executable bit (mode:0666), and sealed with F_SEAL_EXEC, so it can't be chmod to be executable (mode: 0777) after creation. when MFD_EXEC flag is set, memfd is created with executable bit (mode:0777), this is the same as the old behavior of memfd_create. The new pid namespaced sysctl vm.memfd_noexec has 3 values: 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like MFD_EXEC was set. 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like MFD_NOEXEC_SEAL was set. 2: memfd_create() without MFD_NOEXEC_SEAL will be rejected. The sysctl allows finer control of memfd_create for old-software that doesn't set the executable bit, for example, a container with vm.memfd_noexec=1 means the old-software will create non-executable memfd by default. Also, the value of memfd_noexec is passed to child namespace at creation time. For example, if the init namespace has vm.memfd_noexec=2, all its children namespaces will be created with 2. [akpm@linux-foundation.org: add stub functions to fix build] [akpm@linux-foundation.org: remove unneeded register_pid_ns_ctl_table_vm() stub, per Jeff] [akpm@linux-foundation.org: s/pr_warn_ratelimited/pr_warn_once/, per review] [akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warning] Link: https://lkml.kernel.org/r/20221215001205.51969-4-jeffxu@google.com Signed-off-by: Jeff Xu Co-developed-by: Daniel Verkamp Signed-off-by: Daniel Verkamp Reported-by: kernel test robot Reviewed-by: Kees Cook Cc: David Herrmann Cc: Dmitry Torokhov Cc: Hugh Dickins Cc: Jann Horn Cc: Jorge Lucangeli Obes Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/pid_namespace.h | 19 ++++++++++++++ include/uapi/linux/memfd.h | 4 +++ kernel/pid_namespace.c | 5 ++++ kernel/pid_sysctl.h | 60 +++++++++++++++++++++++++++++++++++++++++++ mm/memfd.c | 48 ++++++++++++++++++++++++++++++++-- 5 files changed, 134 insertions(+), 2 deletions(-) create mode 100644 kernel/pid_sysctl.h (limited to 'include/uapi/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 07481bb87d4e..c758809d5bcf 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -16,6 +16,21 @@ struct fs_pin; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +/* + * sysctl for vm.memfd_noexec + * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL + * acts like MFD_EXEC was set. + * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL + * acts like MFD_NOEXEC_SEAL was set. + * 2: memfd_create() without MFD_NOEXEC_SEAL will be + * rejected. + */ +#define MEMFD_NOEXEC_SCOPE_EXEC 0 +#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 +#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 +#endif + struct pid_namespace { struct idr idr; struct rcu_head rcu; @@ -31,6 +46,10 @@ struct pid_namespace { struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) + /* sysctl for vm.memfd_noexec */ + int memfd_noexec_scope; +#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 7a8a26751c23..273a4e15dfcf 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -8,6 +8,10 @@ #define MFD_CLOEXEC 0x0001U #define MFD_ALLOW_SEALING 0x0002U #define MFD_HUGETLB 0x0004U +/* not executable and sealed to prevent changing to executable. */ +#define MFD_NOEXEC_SEAL 0x0008U +/* executable */ +#define MFD_EXEC 0x0010U /* * Huge page size encoding when MFD_HUGETLB is specified, and a huge page diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index f4f8cb0435b4..8a98b1af9376 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -23,6 +23,7 @@ #include #include #include +#include "pid_sysctl.h" static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; @@ -110,6 +111,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; + initialize_memfd_noexec_scope(ns); + return ns; out_free_idr: @@ -455,6 +458,8 @@ static __init int pid_namespaces_init(void) #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_paths(kern_path, pid_ns_ctl_table); #endif + + register_pid_ns_sysctl_table_vm(); return 0; } diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h new file mode 100644 index 000000000000..e22d072e1e24 --- /dev/null +++ b/kernel/pid_sysctl.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_PID_SYSCTL_H +#define LINUX_PID_SYSCTL_H + +#include + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) +{ + ns->memfd_noexec_scope = + task_active_pid_ns(current)->memfd_noexec_scope; +} + +static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table, + int write, void *buf, size_t *lenp, loff_t *ppos) +{ + struct pid_namespace *ns = task_active_pid_ns(current); + struct ctl_table table_copy; + + if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + table_copy = *table; + if (ns != &init_pid_ns) + table_copy.data = &ns->memfd_noexec_scope; + + /* + * set minimum to current value, the effect is only bigger + * value is accepted. + */ + if (*(int *)table_copy.data > *(int *)table_copy.extra1) + table_copy.extra1 = table_copy.data; + + return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos); +} + +static struct ctl_table pid_ns_ctl_table_vm[] = { + { + .procname = "memfd_noexec", + .data = &init_pid_ns.memfd_noexec_scope, + .maxlen = sizeof(init_pid_ns.memfd_noexec_scope), + .mode = 0644, + .proc_handler = pid_mfd_noexec_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; +static struct ctl_path vm_path[] = { { .procname = "vm", }, { } }; +static inline void register_pid_ns_sysctl_table_vm(void) +{ + register_sysctl_paths(vm_path, pid_ns_ctl_table_vm); +} +#else +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void register_pid_ns_sysctl_table_vm(void) {} +#endif + +#endif /* LINUX_PID_SYSCTL_H */ diff --git a/mm/memfd.c b/mm/memfd.c index 4ebeab94aa74..bc214390e28d 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -263,12 +264,13 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg) #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) -#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC) SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags) { + char comm[TASK_COMM_LEN]; unsigned int *file_seals; struct file *file; int fd, error; @@ -285,6 +287,40 @@ SYSCALL_DEFINE2(memfd_create, return -EINVAL; } + /* Invalid if both EXEC and NOEXEC_SEAL are set.*/ + if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) + return -EINVAL; + + if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { +#ifdef CONFIG_SYSCTL + int sysctl = MEMFD_NOEXEC_SCOPE_EXEC; + struct pid_namespace *ns; + + ns = task_active_pid_ns(current); + if (ns) + sysctl = ns->memfd_noexec_scope; + + switch (sysctl) { + case MEMFD_NOEXEC_SCOPE_EXEC: + flags |= MFD_EXEC; + break; + case MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL: + flags |= MFD_NOEXEC_SEAL; + break; + default: + pr_warn_once( + "memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n", + task_pid_nr(current), get_task_comm(comm, current)); + return -EINVAL; + } +#else + flags |= MFD_EXEC; +#endif + pr_warn_once( + "memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL, pid=%d '%s'\n", + task_pid_nr(current), get_task_comm(comm, current)); + } + /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); if (len <= 0) @@ -328,7 +364,15 @@ SYSCALL_DEFINE2(memfd_create, file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; - if (flags & MFD_ALLOW_SEALING) { + if (flags & MFD_NOEXEC_SEAL) { + struct inode *inode = file_inode(file); + + inode->i_mode &= ~0111; + file_seals = memfd_file_seals_ptr(file); + *file_seals &= ~F_SEAL_SEAL; + *file_seals |= F_SEAL_EXEC; + } else if (flags & MFD_ALLOW_SEALING) { + /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); *file_seals &= ~F_SEAL_SEAL; } -- cgit v1.2.3 From 93c473948c588978cd55d9a3adad8b3e8057aa21 Mon Sep 17 00:00:00 2001 From: Jó Ágila Bitsch Date: Fri, 13 Jan 2023 01:53:19 +0100 Subject: usb: gadget: add WebUSB landing page support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a custom (non-USB IF) extension to the USB standard: https://wicg.github.io/webusb/ This specification is published under the W3C Community Contributor Agreement, which in particular allows to implement the specification without any royalties. The specification allows USB gadgets to announce an URL to landing page and describes a Javascript interface for websites to interact with the USB gadget, if the user allows it. It is currently supported by Chromium-based browsers, such as Chrome, Edge and Opera on all major operating systems including Linux. This patch adds optional support for Linux-based USB gadgets wishing to expose such a landing page. During device enumeration, a host recognizes that the announced USB version is at least 2.01, which means, that there are BOS descriptors available. The device than announces WebUSB support using a platform device capability. This includes a vendor code under which the landing page URL can be retrieved using a vendor-specific request. Previously, the BOS descriptors would unconditionally include an LPM related descriptor, as BOS descriptors were only ever sent when the device was LPM capable. As this is no longer the case, this patch puts this descriptor behind a lpm_capable condition. Usage is modeled after os_desc descriptors: echo 1 > webusb/use echo "https://www.kernel.org" > webusb/landingPage lsusb will report the device with the following lines: Platform Device Capability: bLength 24 bDescriptorType 16 bDevCapabilityType 5 bReserved 0 PlatformCapabilityUUID {3408b638-09a9-47a0-8bfd-a0768815b665} WebUSB: bcdVersion 1.00 bVendorCode 0 iLandingPage 1 https://www.kernel.org Signed-off-by: Jó Ágila Bitsch Link: https://lore.kernel.org/r/Y8Crf8P2qAWuuk/F@jo-einhundert Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/configfs-usb-gadget | 13 ++ drivers/usb/gadget/composite.c | 102 ++++++++++++++-- drivers/usb/gadget/configfs.c | 166 ++++++++++++++++++++++++++ include/linux/usb/composite.h | 7 ++ include/linux/usb/webusb.h | 83 +++++++++++++ include/uapi/linux/usb/ch9.h | 16 +++ 6 files changed, 377 insertions(+), 10 deletions(-) create mode 100644 include/linux/usb/webusb.h (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/configfs-usb-gadget b/Documentation/ABI/testing/configfs-usb-gadget index b7943aa7e997..a8bb896def54 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget +++ b/Documentation/ABI/testing/configfs-usb-gadget @@ -143,3 +143,16 @@ Description: qw_sign an identifier to be reported as "OS String" proper ============= =============================================== + +What: /config/usb-gadget/gadget/webusb +Date: Dec 2022 +KernelVersion: 6.3 +Description: + This group contains "WebUSB" extension handling attributes. + + ============= =============================================== + use flag turning "WebUSB" support on/off + bcdVersion bcd WebUSB specification version number + bVendorCode one-byte value used for custom per-device + landingPage UTF-8 encoded URL of the device's landing page + ============= =============================================== diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 403563c06477..8e2603688016 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -14,9 +14,11 @@ #include #include #include +#include #include #include +#include #include #include "u_os_desc.h" @@ -713,14 +715,16 @@ static int bos_desc(struct usb_composite_dev *cdev) * A SuperSpeed device shall include the USB2.0 extension descriptor * and shall support LPM when operating in USB2.0 HS mode. */ - usb_ext = cdev->req->buf + le16_to_cpu(bos->wTotalLength); - bos->bNumDeviceCaps++; - le16_add_cpu(&bos->wTotalLength, USB_DT_USB_EXT_CAP_SIZE); - usb_ext->bLength = USB_DT_USB_EXT_CAP_SIZE; - usb_ext->bDescriptorType = USB_DT_DEVICE_CAPABILITY; - usb_ext->bDevCapabilityType = USB_CAP_TYPE_EXT; - usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT | - USB_BESL_SUPPORT | besl); + if (cdev->gadget->lpm_capable) { + usb_ext = cdev->req->buf + le16_to_cpu(bos->wTotalLength); + bos->bNumDeviceCaps++; + le16_add_cpu(&bos->wTotalLength, USB_DT_USB_EXT_CAP_SIZE); + usb_ext->bLength = USB_DT_USB_EXT_CAP_SIZE; + usb_ext->bDescriptorType = USB_DT_DEVICE_CAPABILITY; + usb_ext->bDevCapabilityType = USB_CAP_TYPE_EXT; + usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT | + USB_BESL_SUPPORT | besl); + } /* * The Superspeed USB Capability descriptor shall be implemented by all @@ -821,6 +825,37 @@ static int bos_desc(struct usb_composite_dev *cdev) } } + /* The WebUSB Platform Capability descriptor */ + if (cdev->use_webusb) { + struct usb_plat_dev_cap_descriptor *webusb_cap; + struct usb_webusb_cap_data *webusb_cap_data; + uuid_t webusb_uuid = WEBUSB_UUID; + + webusb_cap = cdev->req->buf + le16_to_cpu(bos->wTotalLength); + webusb_cap_data = (struct usb_webusb_cap_data *) webusb_cap->CapabilityData; + bos->bNumDeviceCaps++; + le16_add_cpu(&bos->wTotalLength, + USB_DT_USB_PLAT_DEV_CAP_SIZE(USB_WEBUSB_CAP_DATA_SIZE)); + + webusb_cap->bLength = USB_DT_USB_PLAT_DEV_CAP_SIZE(USB_WEBUSB_CAP_DATA_SIZE); + webusb_cap->bDescriptorType = USB_DT_DEVICE_CAPABILITY; + webusb_cap->bDevCapabilityType = USB_PLAT_DEV_CAP_TYPE; + webusb_cap->bReserved = 0; + export_uuid(webusb_cap->UUID, &webusb_uuid); + + if (cdev->bcd_webusb_version != 0) + webusb_cap_data->bcdVersion = cpu_to_le16(cdev->bcd_webusb_version); + else + webusb_cap_data->bcdVersion = WEBUSB_VERSION_1_00; + + webusb_cap_data->bVendorCode = cdev->b_webusb_vendor_code; + + if (strnlen(cdev->landing_page, sizeof(cdev->landing_page)) > 0) + webusb_cap_data->iLandingPage = WEBUSB_LANDING_PAGE_PRESENT; + else + webusb_cap_data->iLandingPage = WEBUSB_LANDING_PAGE_NOT_PRESENT; + } + return le16_to_cpu(bos->wTotalLength); } @@ -1744,7 +1779,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) cdev->desc.bcdUSB = cpu_to_le16(0x0210); } } else { - if (gadget->lpm_capable) + if (gadget->lpm_capable || cdev->use_webusb) cdev->desc.bcdUSB = cpu_to_le16(0x0201); else cdev->desc.bcdUSB = cpu_to_le16(0x0200); @@ -1779,7 +1814,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) break; case USB_DT_BOS: if (gadget_is_superspeed(gadget) || - gadget->lpm_capable) { + gadget->lpm_capable || cdev->use_webusb) { value = bos_desc(cdev); value = min(w_length, (u16) value); } @@ -2013,6 +2048,53 @@ unknown: goto check_value; } + /* + * WebUSB URL descriptor handling, following: + * https://wicg.github.io/webusb/#device-requests + */ + if (cdev->use_webusb && + ctrl->bRequestType == (USB_DIR_IN | USB_TYPE_VENDOR) && + w_index == WEBUSB_GET_URL && + w_value == WEBUSB_LANDING_PAGE_PRESENT && + ctrl->bRequest == cdev->b_webusb_vendor_code) { + unsigned int landing_page_length; + unsigned int landing_page_offset; + struct webusb_url_descriptor *url_descriptor = + (struct webusb_url_descriptor *)cdev->req->buf; + + url_descriptor->bDescriptorType = WEBUSB_URL_DESCRIPTOR_TYPE; + + if (strncasecmp(cdev->landing_page, "https://", 8) == 0) { + landing_page_offset = 8; + url_descriptor->bScheme = WEBUSB_URL_SCHEME_HTTPS; + } else if (strncasecmp(cdev->landing_page, "http://", 7) == 0) { + landing_page_offset = 7; + url_descriptor->bScheme = WEBUSB_URL_SCHEME_HTTP; + } else { + landing_page_offset = 0; + url_descriptor->bScheme = WEBUSB_URL_SCHEME_NONE; + } + + landing_page_length = strnlen(cdev->landing_page, + sizeof(url_descriptor->URL) + - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + landing_page_offset); + + if (ctrl->wLength < WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + + landing_page_length) + landing_page_length = ctrl->wLength + - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + landing_page_offset; + + memcpy(url_descriptor->URL, + cdev->landing_page + landing_page_offset, + landing_page_length - landing_page_offset); + url_descriptor->bLength = landing_page_length + - landing_page_offset + WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH; + + value = url_descriptor->bLength; + + goto check_value; + } + VDBG(cdev, "non-core control req%02x.%02x v%04x i%04x l%d\n", ctrl->bRequestType, ctrl->bRequest, diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 96121d1c8df4..4a1236063c19 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "configfs.h" #include "u_f.h" #include "u_os_desc.h" @@ -39,6 +40,7 @@ struct gadget_info { struct config_group configs_group; struct config_group strings_group; struct config_group os_desc_group; + struct config_group webusb_group; struct mutex lock; struct usb_gadget_strings *gstrings[MAX_USB_STRING_LANGS + 1]; @@ -50,6 +52,11 @@ struct gadget_info { bool use_os_desc; char b_vendor_code; char qw_sign[OS_STRING_QW_SIGN_LEN]; + bool use_webusb; + u16 bcd_webusb_version; + u8 b_webusb_vendor_code; + char landing_page[WEBUSB_URL_RAW_MAX_LENGTH]; + spinlock_t spinlock; bool unbind; }; @@ -780,6 +787,154 @@ static void gadget_strings_attr_release(struct config_item *item) USB_CONFIG_STRING_RW_OPS(gadget_strings); USB_CONFIG_STRINGS_LANG(gadget_strings, gadget_info); +static inline struct gadget_info *webusb_item_to_gadget_info( + struct config_item *item) +{ + return container_of(to_config_group(item), + struct gadget_info, webusb_group); +} + +static ssize_t webusb_use_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "%d\n", + webusb_item_to_gadget_info(item)->use_webusb); +} + +static ssize_t webusb_use_store(struct config_item *item, const char *page, + size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + int ret; + bool use; + + mutex_lock(&gi->lock); + ret = kstrtobool(page, &use); + if (!ret) { + gi->use_webusb = use; + ret = len; + } + mutex_unlock(&gi->lock); + + return ret; +} + +static ssize_t webusb_bcdVersion_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "0x%04x\n", + webusb_item_to_gadget_info(item)->bcd_webusb_version); +} + +static ssize_t webusb_bcdVersion_store(struct config_item *item, + const char *page, size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + u16 bcdVersion; + int ret; + + mutex_lock(&gi->lock); + ret = kstrtou16(page, 0, &bcdVersion); + if (ret) + goto out; + ret = is_valid_bcd(bcdVersion); + if (ret) + goto out; + + gi->bcd_webusb_version = bcdVersion; + ret = len; + +out: + mutex_unlock(&gi->lock); + + return ret; +} + +static ssize_t webusb_bVendorCode_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "0x%02x\n", + webusb_item_to_gadget_info(item)->b_webusb_vendor_code); +} + +static ssize_t webusb_bVendorCode_store(struct config_item *item, + const char *page, size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + int ret; + u8 b_vendor_code; + + mutex_lock(&gi->lock); + ret = kstrtou8(page, 0, &b_vendor_code); + if (!ret) { + gi->b_webusb_vendor_code = b_vendor_code; + ret = len; + } + mutex_unlock(&gi->lock); + + return ret; +} + +static ssize_t webusb_landingPage_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "%s\n", webusb_item_to_gadget_info(item)->landing_page); +} + +static ssize_t webusb_landingPage_store(struct config_item *item, const char *page, + size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + unsigned int bytes_to_strip = 0; + int l = len; + + if (page[l - 1] == '\n') { + --l; + ++bytes_to_strip; + } + + if (l > sizeof(gi->landing_page)) { + pr_err("webusb: landingPage URL too long\n"); + return -EINVAL; + } + + // validation + if (strncasecmp(page, "https://", 8) == 0) + bytes_to_strip = 8; + else if (strncasecmp(page, "http://", 7) == 0) + bytes_to_strip = 7; + else + bytes_to_strip = 0; + + if (l > U8_MAX - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + bytes_to_strip) { + pr_err("webusb: landingPage URL %d bytes too long for given URL scheme\n", + l - U8_MAX + WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH - bytes_to_strip); + return -EINVAL; + } + + mutex_lock(&gi->lock); + // ensure 0 bytes are set, in case the new landing page is shorter then the old one. + memset(gi->landing_page, 0, sizeof(gi->landing_page)); + memcpy(gi->landing_page, page, l); + mutex_unlock(&gi->lock); + + return len; +} + +CONFIGFS_ATTR(webusb_, use); +CONFIGFS_ATTR(webusb_, bVendorCode); +CONFIGFS_ATTR(webusb_, bcdVersion); +CONFIGFS_ATTR(webusb_, landingPage); + +static struct configfs_attribute *webusb_attrs[] = { + &webusb_attr_use, + &webusb_attr_bcdVersion, + &webusb_attr_bVendorCode, + &webusb_attr_landingPage, + NULL, +}; + +static struct config_item_type webusb_type = { + .ct_attrs = webusb_attrs, + .ct_owner = THIS_MODULE, +}; + static inline struct gadget_info *os_desc_item_to_gadget_info( struct config_item *item) { @@ -1341,6 +1496,13 @@ static int configfs_composite_bind(struct usb_gadget *gadget, gi->cdev.desc.iSerialNumber = s[USB_GADGET_SERIAL_IDX].id; } + if (gi->use_webusb) { + cdev->use_webusb = true; + cdev->bcd_webusb_version = gi->bcd_webusb_version; + cdev->b_webusb_vendor_code = gi->b_webusb_vendor_code; + memcpy(cdev->landing_page, gi->landing_page, WEBUSB_URL_RAW_MAX_LENGTH); + } + if (gi->use_os_desc) { cdev->use_os_string = true; cdev->b_vendor_code = gi->b_vendor_code; @@ -1605,6 +1767,10 @@ static struct config_group *gadgets_make( &os_desc_type); configfs_add_default_group(&gi->os_desc_group, &gi->group); + config_group_init_type_name(&gi->webusb_group, "webusb", + &webusb_type); + configfs_add_default_group(&gi->webusb_group, &gi->group); + gi->composite.bind = configfs_do_nothing; gi->composite.unbind = configfs_do_nothing; gi->composite.suspend = NULL; diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 43ac3fa760db..91d22c3ed458 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -474,6 +475,12 @@ struct usb_composite_dev { struct usb_configuration *os_desc_config; unsigned int use_os_string:1; + /* WebUSB */ + u16 bcd_webusb_version; + u8 b_webusb_vendor_code; + char landing_page[WEBUSB_URL_RAW_MAX_LENGTH]; + unsigned int use_webusb:1; + /* private: */ /* internals */ unsigned int suspended:1; diff --git a/include/linux/usb/webusb.h b/include/linux/usb/webusb.h new file mode 100644 index 000000000000..b430d84357f3 --- /dev/null +++ b/include/linux/usb/webusb.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * WebUSB descriptors and constants + * + * Copyright (C) 2023 Jó Ágila Bitsch + */ + +#ifndef __LINUX_USB_WEBUSB_H +#define __LINUX_USB_WEBUSB_H + +#include "uapi/linux/usb/ch9.h" + +/* + * little endian PlatformCapablityUUID for WebUSB + * 3408b638-09a9-47a0-8bfd-a0768815b665 + * to identify Platform Device Capability descriptors as referring to WebUSB + * + * the UUID above MUST be sent over the wire as the byte sequence: + * {0x38, 0xB6, 0x08, 0x34, 0xA9, 0x09, 0xA0, 0x47, 0x8B, 0xFD, 0xA0, 0x76, 0x88, 0x15, 0xB6, 0x65}. + */ +#define WEBUSB_UUID \ + UUID_INIT(0x38b60834, 0xa909, 0xa047, 0x8b, 0xfd, 0xa0, 0x76, 0x88, 0x15, 0xb6, 0x65) + +/* + * WebUSB Platform Capability data + * + * A device announces support for the + * WebUSB command set by including the following Platform Descriptor Data in its + * Binary Object Store associated with the WebUSB_UUID above. + * See: https://wicg.github.io/webusb/#webusb-platform-capability-descriptor + */ +struct usb_webusb_cap_data { + __le16 bcdVersion; +#define WEBUSB_VERSION_1_00 cpu_to_le16(0x0100) /* currently only version 1.00 is defined */ + u8 bVendorCode; + u8 iLandingPage; +#define WEBUSB_LANDING_PAGE_NOT_PRESENT 0 +#define WEBUSB_LANDING_PAGE_PRESENT 1 /* we chose the fixed index 1 for the URL descriptor */ +} __packed; + +#define USB_WEBUSB_CAP_DATA_SIZE 4 + +/* + * Get URL Request + * + * The request to fetch an URL is defined in https://wicg.github.io/webusb/#get-url as: + * bmRequestType: (USB_DIR_IN | USB_TYPE_VENDOR) = 11000000B + * bRequest: bVendorCode + * wValue: iLandingPage + * wIndex: GET_URL = 2 + * wLength: Descriptor Length (typically U8_MAX = 255) + * Data: URL Descriptor + */ +#define WEBUSB_GET_URL 2 + +/* + * This descriptor contains a single URL and is returned by the Get URL request. + * + * See: https://wicg.github.io/webusb/#url-descriptor + */ +struct webusb_url_descriptor { + u8 bLength; +#define WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH 3 + u8 bDescriptorType; +#define WEBUSB_URL_DESCRIPTOR_TYPE 3 + u8 bScheme; +#define WEBUSB_URL_SCHEME_HTTP 0 +#define WEBUSB_URL_SCHEME_HTTPS 1 +#define WEBUSB_URL_SCHEME_NONE 255 + u8 URL[U8_MAX - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH]; +} __packed; + +/* + * Buffer size to hold the longest URL that can be in an URL descriptor + * + * The descriptor can be U8_MAX bytes long. + * WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH bytes are used for a header. + * Since the longest prefix that might be stripped is "https://", we may accommodate an additional + * 8 bytes. + */ +#define WEBUSB_URL_RAW_MAX_LENGTH (U8_MAX - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + 8) + +#endif /* __LINUX_USB_USBNET_H */ diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 31fcfa084e63..b17e3a21b15f 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -947,6 +947,22 @@ struct usb_ss_container_id_descriptor { #define USB_DT_USB_SS_CONTN_ID_SIZE 20 +/* + * Platform Device Capability descriptor: Defines platform specific device + * capabilities + */ +#define USB_PLAT_DEV_CAP_TYPE 5 +struct usb_plat_dev_cap_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDevCapabilityType; + __u8 bReserved; + __u8 UUID[16]; + __u8 CapabilityData[]; +} __attribute__((packed)); + +#define USB_DT_USB_PLAT_DEV_CAP_SIZE(capability_data_size) (20 + capability_data_size) + /* * SuperSpeed Plus USB Capability descriptor: Defines the set of * SuperSpeed Plus USB specific device level capabilities -- cgit v1.2.3 From 3398cc4f2b1592148a2ebabc5a2df3e303d4e77c Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 25 Nov 2022 15:05:07 +0200 Subject: serial: 8250: Add IIR FIFOs enabled field properly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Don't use magic literals & comments but define a real field instead for UART_IIR_FIFO_ENABLED and name also the values. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20221125130509.8482-5-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 17 +++++++---------- include/uapi/linux/serial_reg.h | 4 ++++ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index e79bf2afd9be..a47ce3e974a2 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1293,22 +1293,19 @@ static void autoconfig(struct uart_8250_port *up) serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); - /* Assign this as it is to truncate any bits above 7. */ - scratch = serial_in(up, UART_IIR); - - switch (scratch >> 6) { - case 0: + switch (serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED) { + case UART_IIR_FIFO_ENABLED_8250: autoconfig_8250(up); break; - case 1: - port->type = PORT_UNKNOWN; - break; - case 2: + case UART_IIR_FIFO_ENABLED_16550: port->type = PORT_16550; break; - case 3: + case UART_IIR_FIFO_ENABLED_16550A: autoconfig_16550a(up); break; + default: + port->type = PORT_UNKNOWN; + break; } #ifdef CONFIG_SERIAL_8250_RSA diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index bab3b39266cc..19aef5b0b049 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -44,6 +44,10 @@ #define UART_IIR_RX_TIMEOUT 0x0c /* OMAP RX Timeout interrupt */ #define UART_IIR_XOFF 0x10 /* OMAP XOFF/Special Character */ #define UART_IIR_CTS_RTS_DSR 0x20 /* OMAP CTS/RTS/DSR Change */ +#define UART_IIR_FIFO_ENABLED 0xc0 /* FIFOs enabled / port type identification */ +#define UART_IIR_FIFO_ENABLED_8250 0x00 /* 8250: no FIFO */ +#define UART_IIR_FIFO_ENABLED_16550 0x80 /* 16550: (broken/unusable) FIFO */ +#define UART_IIR_FIFO_ENABLED_16550A 0xc0 /* 16550A: FIFO enabled */ #define UART_FCR 2 /* Out: FIFO Control Register */ #define UART_FCR_ENABLE_FIFO 0x01 /* Enable the FIFO */ -- cgit v1.2.3 From afd216ca17b1fd24f6b73a1490752c22ab42598c Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 25 Nov 2022 15:05:08 +0200 Subject: serial: 8250: Define IIR 64 byte bit & cleanup related code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 16750 indicates 64 bytes FIFO with a IIR bit. Add define for it and make related code more obvious. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20221125130509.8482-6-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 14 +++++++++----- include/uapi/linux/serial_reg.h | 1 + 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index a47ce3e974a2..33be7aad11ef 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1050,11 +1050,12 @@ static void autoconfig_16550a(struct uart_8250_port *up) serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); - status1 = serial_in(up, UART_IIR) >> 5; + status1 = serial_in(up, UART_IIR) & (UART_IIR_64BYTE_FIFO | + UART_IIR_FIFO_ENABLED); serial_out(up, UART_FCR, 0); serial_out(up, UART_LCR, 0); - if (status1 == 7) + if (status1 == (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED)) up->port.type = PORT_16550A_FSL64; else DEBUG_AUTOCONF("Motorola 8xxx DUART "); @@ -1122,17 +1123,20 @@ static void autoconfig_16550a(struct uart_8250_port *up) */ serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); - status1 = serial_in(up, UART_IIR) >> 5; + status1 = serial_in(up, UART_IIR) & (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); - status2 = serial_in(up, UART_IIR) >> 5; + status2 = serial_in(up, UART_IIR) & (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); + serial_out(up, UART_LCR, 0); DEBUG_AUTOCONF("iir1=%d iir2=%d ", status1, status2); - if (status1 == 6 && status2 == 7) { + if (status1 == UART_IIR_FIFO_ENABLED_16550A && + status2 == (UART_IIR_64BYTE_FIFO | UART_IIR_FIFO_ENABLED_16550A)) { up->port.type = PORT_16750; up->capabilities |= UART_CAP_AFE | UART_CAP_SLEEP; return; diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index 19aef5b0b049..08b3527e1b93 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -44,6 +44,7 @@ #define UART_IIR_RX_TIMEOUT 0x0c /* OMAP RX Timeout interrupt */ #define UART_IIR_XOFF 0x10 /* OMAP XOFF/Special Character */ #define UART_IIR_CTS_RTS_DSR 0x20 /* OMAP CTS/RTS/DSR Change */ +#define UART_IIR_64BYTE_FIFO 0x20 /* 16750 64 bytes FIFO */ #define UART_IIR_FIFO_ENABLED 0xc0 /* FIFOs enabled / port type identification */ #define UART_IIR_FIFO_ENABLED_8250 0x00 /* 8250: no FIFO */ #define UART_IIR_FIFO_ENABLED_16550 0x80 /* 16550: (broken/unusable) FIFO */ -- cgit v1.2.3 From 24d69384bcd34b9dcaf5dab744bf7096e84d1abd Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Thu, 19 Jan 2023 16:19:16 +0100 Subject: VT: Add KD_FONT_OP_SET/GET_TALL operations The KD_FONT_OP_SET/GET operations hardcode vpitch to be 32 pixels, which only dates from the old VGA hardware which as asserting this. Drivers such as fbcon however do not have such limitation, so this introduces KD_FONT_OP_SET/GET_TALL operations, which userland can try to use to avoid this limitation, thus opening the patch to >32 pixels font height. Signed-off-by: Samuel Thibault Link: https://lore.kernel.org/r/20230119151935.013597162@ens-lyon.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 14 ++++++++++---- include/uapi/linux/kd.h | 10 ++++++++-- 2 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 268d0f57fdd4..8da7ab34b8fd 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4540,6 +4540,7 @@ static int con_font_get(struct vc_data *vc, struct console_font_op *op) struct console_font font; int rc = -EINVAL; int c; + unsigned int vpitch = op->op == KD_FONT_OP_GET_TALL ? op->height : 32; if (op->data) { font.data = kmalloc(max_font_size, GFP_KERNEL); @@ -4552,7 +4553,7 @@ static int con_font_get(struct vc_data *vc, struct console_font_op *op) if (vc->vc_mode != KD_TEXT) rc = -EINVAL; else if (vc->vc_sw->con_font_get) - rc = vc->vc_sw->con_font_get(vc, &font, 32); + rc = vc->vc_sw->con_font_get(vc, &font, vpitch); else rc = -ENOSYS; console_unlock(); @@ -4560,7 +4561,7 @@ static int con_font_get(struct vc_data *vc, struct console_font_op *op) if (rc) goto out; - c = (font.width+7)/8 * 32 * font.charcount; + c = (font.width+7)/8 * vpitch * font.charcount; if (op->data && font.charcount > op->charcount) rc = -ENOSPC; @@ -4586,6 +4587,7 @@ static int con_font_set(struct vc_data *vc, struct console_font_op *op) struct console_font font; int rc = -EINVAL; int size; + unsigned int vpitch = op->op == KD_FONT_OP_SET_TALL ? op->height : 32; if (vc->vc_mode != KD_TEXT) return -EINVAL; @@ -4595,7 +4597,9 @@ static int con_font_set(struct vc_data *vc, struct console_font_op *op) return -EINVAL; if (op->width <= 0 || op->width > 32 || !op->height || op->height > 32) return -EINVAL; - size = (op->width+7)/8 * 32 * op->charcount; + if (vpitch < op->height) + return -EINVAL; + size = (op->width+7)/8 * vpitch * op->charcount; if (size > max_font_size) return -ENOSPC; @@ -4613,7 +4617,7 @@ static int con_font_set(struct vc_data *vc, struct console_font_op *op) else if (vc->vc_sw->con_font_set) { if (vc_is_sel(vc)) clear_selection(); - rc = vc->vc_sw->con_font_set(vc, &font, 32, op->flags); + rc = vc->vc_sw->con_font_set(vc, &font, vpitch, op->flags); } else rc = -ENOSYS; console_unlock(); @@ -4659,8 +4663,10 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op) { switch (op->op) { case KD_FONT_OP_SET: + case KD_FONT_OP_SET_TALL: return con_font_set(vc, op); case KD_FONT_OP_GET: + case KD_FONT_OP_GET_TALL: return con_font_get(vc, op); case KD_FONT_OP_SET_DEFAULT: return con_font_default(vc, op); diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h index ee929ece4112..6b384065c013 100644 --- a/include/uapi/linux/kd.h +++ b/include/uapi/linux/kd.h @@ -161,19 +161,25 @@ struct console_font_op { unsigned int flags; /* KD_FONT_FLAG_* */ unsigned int width, height; /* font size */ unsigned int charcount; - unsigned char __user *data; /* font data with height fixed to 32 */ + unsigned char __user *data; /* font data with vpitch fixed to 32 for + * KD_FONT_OP_SET/GET + */ }; struct console_font { unsigned int width, height; /* font size */ unsigned int charcount; - unsigned char *data; /* font data with height fixed to 32 */ + unsigned char *data; /* font data with vpitch fixed to 32 for + * KD_FONT_OP_SET/GET + */ }; #define KD_FONT_OP_SET 0 /* Set font */ #define KD_FONT_OP_GET 1 /* Get font */ #define KD_FONT_OP_SET_DEFAULT 2 /* Set font to default, data points to name / NULL */ #define KD_FONT_OP_COPY 3 /* Obsolete, do not use */ +#define KD_FONT_OP_SET_TALL 4 /* Set font with vpitch = height */ +#define KD_FONT_OP_GET_TALL 5 /* Get font with vpitch = height */ #define KD_FONT_FLAG_DONT_RECALC 1 /* Don't recalculate hw charcell size [compat] */ -- cgit v1.2.3 From 0567461a7a6ecb12692e3bbb97e86ff9d39a2837 Mon Sep 17 00:00:00 2001 From: Li Li Date: Wed, 23 Nov 2022 12:16:54 -0800 Subject: binder: return pending info for frozen async txns An async transaction to a frozen process will still be successfully put in the queue. But this pending async transaction won't be processed until the target process is unfrozen at an unspecified time in the future. Pass this important information back to the user space caller by returning BR_TRANSACTION_PENDING_FROZEN. Signed-off-by: Li Li Acked-by: Carlos Llamas Link: https://lore.kernel.org/r/20221123201654.589322-2-dualli@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 32 ++++++++++++++++++++++++++------ drivers/android/binder_internal.h | 3 ++- include/uapi/linux/android/binder.h | 7 ++++++- 3 files changed, 34 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 48e5a3531282..a73df6b6c127 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2728,7 +2728,10 @@ binder_find_outdated_transaction_ilocked(struct binder_transaction *t, * * Return: 0 if the transaction was successfully queued * BR_DEAD_REPLY if the target process or thread is dead - * BR_FROZEN_REPLY if the target process or thread is frozen + * BR_FROZEN_REPLY if the target process or thread is frozen and + * the sync transaction was rejected + * BR_TRANSACTION_PENDING_FROZEN if the target process is frozen + * and the async transaction was successfully queued */ static int binder_proc_transaction(struct binder_transaction *t, struct binder_proc *proc, @@ -2738,6 +2741,7 @@ static int binder_proc_transaction(struct binder_transaction *t, bool oneway = !!(t->flags & TF_ONE_WAY); bool pending_async = false; struct binder_transaction *t_outdated = NULL; + bool frozen = false; BUG_ON(!node); binder_node_lock(node); @@ -2751,15 +2755,16 @@ static int binder_proc_transaction(struct binder_transaction *t, binder_inner_proc_lock(proc); if (proc->is_frozen) { + frozen = true; proc->sync_recv |= !oneway; proc->async_recv |= oneway; } - if ((proc->is_frozen && !oneway) || proc->is_dead || + if ((frozen && !oneway) || proc->is_dead || (thread && thread->is_dead)) { binder_inner_proc_unlock(proc); binder_node_unlock(node); - return proc->is_frozen ? BR_FROZEN_REPLY : BR_DEAD_REPLY; + return frozen ? BR_FROZEN_REPLY : BR_DEAD_REPLY; } if (!thread && !pending_async) @@ -2770,7 +2775,7 @@ static int binder_proc_transaction(struct binder_transaction *t, } else if (!pending_async) { binder_enqueue_work_ilocked(&t->work, &proc->todo); } else { - if ((t->flags & TF_UPDATE_TXN) && proc->is_frozen) { + if ((t->flags & TF_UPDATE_TXN) && frozen) { t_outdated = binder_find_outdated_transaction_ilocked(t, &node->async_todo); if (t_outdated) { @@ -2807,6 +2812,9 @@ static int binder_proc_transaction(struct binder_transaction *t, binder_stats_deleted(BINDER_STAT_TRANSACTION); } + if (oneway && frozen) + return BR_TRANSACTION_PENDING_FROZEN; + return 0; } @@ -3607,9 +3615,17 @@ static void binder_transaction(struct binder_proc *proc, } else { BUG_ON(target_node == NULL); BUG_ON(t->buffer->async_transaction != 1); - binder_enqueue_thread_work(thread, tcomplete); return_error = binder_proc_transaction(t, target_proc, NULL); - if (return_error) + /* + * Let the caller know when async transaction reaches a frozen + * process and is put in a pending queue, waiting for the target + * process to be unfrozen. + */ + if (return_error == BR_TRANSACTION_PENDING_FROZEN) + tcomplete->type = BINDER_WORK_TRANSACTION_PENDING; + binder_enqueue_thread_work(thread, tcomplete); + if (return_error && + return_error != BR_TRANSACTION_PENDING_FROZEN) goto err_dead_proc_or_thread; } if (target_thread) @@ -4440,10 +4456,13 @@ retry: binder_stat_br(proc, thread, cmd); } break; case BINDER_WORK_TRANSACTION_COMPLETE: + case BINDER_WORK_TRANSACTION_PENDING: case BINDER_WORK_TRANSACTION_ONEWAY_SPAM_SUSPECT: { if (proc->oneway_spam_detection_enabled && w->type == BINDER_WORK_TRANSACTION_ONEWAY_SPAM_SUSPECT) cmd = BR_ONEWAY_SPAM_SUSPECT; + else if (w->type == BINDER_WORK_TRANSACTION_PENDING) + cmd = BR_TRANSACTION_PENDING_FROZEN; else cmd = BR_TRANSACTION_COMPLETE; binder_inner_proc_unlock(proc); @@ -6159,6 +6178,7 @@ static const char * const binder_return_strings[] = { "BR_FAILED_REPLY", "BR_FROZEN_REPLY", "BR_ONEWAY_SPAM_SUSPECT", + "BR_TRANSACTION_PENDING_FROZEN" }; static const char * const binder_command_strings[] = { diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index abe19d88c6ec..28ef5b3704b1 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -133,7 +133,7 @@ enum binder_stat_types { }; struct binder_stats { - atomic_t br[_IOC_NR(BR_ONEWAY_SPAM_SUSPECT) + 1]; + atomic_t br[_IOC_NR(BR_TRANSACTION_PENDING_FROZEN) + 1]; atomic_t bc[_IOC_NR(BC_REPLY_SG) + 1]; atomic_t obj_created[BINDER_STAT_COUNT]; atomic_t obj_deleted[BINDER_STAT_COUNT]; @@ -152,6 +152,7 @@ struct binder_work { enum binder_work_type { BINDER_WORK_TRANSACTION = 1, BINDER_WORK_TRANSACTION_COMPLETE, + BINDER_WORK_TRANSACTION_PENDING, BINDER_WORK_TRANSACTION_ONEWAY_SPAM_SUSPECT, BINDER_WORK_RETURN_ERROR, BINDER_WORK_NODE, diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index e72e4de8f452..5f636b5afcd7 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -450,7 +450,7 @@ enum binder_driver_return_protocol { BR_FROZEN_REPLY = _IO('r', 18), /* - * The target of the last transaction (either a bcTRANSACTION or + * The target of the last sync transaction (either a bcTRANSACTION or * a bcATTEMPT_ACQUIRE) is frozen. No parameters. */ @@ -460,6 +460,11 @@ enum binder_driver_return_protocol { * asynchronous transaction makes the allocated async buffer size exceed * detection threshold. No parameters. */ + + BR_TRANSACTION_PENDING_FROZEN = _IO('r', 20), + /* + * The target of the last async transaction is frozen. No parameters. + */ }; enum binder_driver_command_protocol { -- cgit v1.2.3 From 622f1b2fae2eea28a80b04f130e3bb54227699f8 Mon Sep 17 00:00:00 2001 From: Daniel Machon Date: Wed, 18 Jan 2023 22:08:27 +0100 Subject: net: dcb: add new rewrite table Add new rewrite table and all the required functions, offload hooks and bookkeeping for maintaining it. The rewrite table reuses the app struct, and the entire set of app selectors. As such, some bookeeping code can be shared between the rewrite- and the APP table. New functions for getting, setting and deleting entries has been added. Apart from operating on the rewrite list, these functions do not emit a DCB_APP_EVENT when the list os modified. The new dcb_getrewr does a lookup based on selector and priority and returns the protocol, so that mappings from priority to protocol, for a given selector and ifindex is obtained. Also, a new nested attribute has been added, that encapsulates one or more app structs. This attribute is used to distinguish the two tables. The dcb_lock used for the APP table is reused for the rewrite table. Signed-off-by: Daniel Machon Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/dcbnl.h | 8 ++++ include/uapi/linux/dcbnl.h | 2 + net/dcb/dcbnl.c | 113 ++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 122 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 8841ab6c2de7..fe7dfb8bcb5b 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -19,6 +19,10 @@ struct dcb_app_type { u8 dcbx; }; +u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app); +int dcb_setrewr(struct net_device *dev, struct dcb_app *app); +int dcb_delrewr(struct net_device *dev, struct dcb_app *app); + int dcb_setapp(struct net_device *, struct dcb_app *); u8 dcb_getapp(struct net_device *, struct dcb_app *); int dcb_ieee_setapp(struct net_device *, struct dcb_app *); @@ -113,6 +117,10 @@ struct dcbnl_rtnl_ops { /* apptrust */ int (*dcbnl_setapptrust)(struct net_device *, u8 *, int); int (*dcbnl_getapptrust)(struct net_device *, u8 *, int *); + + /* rewrite */ + int (*dcbnl_setrewr)(struct net_device *dev, struct dcb_app *app); + int (*dcbnl_delrewr)(struct net_device *dev, struct dcb_app *app); }; #endif /* __NET_DCBNL_H__ */ diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 99047223ab26..7e15214aa5dd 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -411,6 +411,7 @@ enum dcbnl_attrs { * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only * @DCB_ATTR_DCB_APP_TRUST_TABLE: selector trust table + * @DCB_ATTR_DCB_REWR_TABLE: rewrite configuration */ enum ieee_attrs { DCB_ATTR_IEEE_UNSPEC, @@ -425,6 +426,7 @@ enum ieee_attrs { DCB_ATTR_IEEE_QCN_STATS, DCB_ATTR_DCB_BUFFER, DCB_ATTR_DCB_APP_TRUST_TABLE, + DCB_ATTR_DCB_REWR_TABLE, __DCB_ATTR_IEEE_MAX }; #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index cb5319c6afe6..2ca7fffcf069 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -178,6 +178,7 @@ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { }; static LIST_HEAD(dcb_app_list); +static LIST_HEAD(dcb_rewr_list); static DEFINE_SPINLOCK(dcb_lock); static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) @@ -1138,7 +1139,7 @@ static int dcbnl_app_table_setdel(struct nlattr *attr, static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; - struct nlattr *ieee, *app; + struct nlattr *ieee, *app, *rewr; struct dcb_app_type *itr; int dcbx; int err; @@ -1241,6 +1242,27 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); + rewr = nla_nest_start(skb, DCB_ATTR_DCB_REWR_TABLE); + if (!rewr) + return -EMSGSIZE; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == netdev->ifindex) { + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); + if (err) { + spin_unlock_bh(&dcb_lock); + nla_nest_cancel(skb, rewr); + return -EMSGSIZE; + } + } + } + + spin_unlock_bh(&dcb_lock); + nla_nest_end(skb, rewr); + if (ops->dcbnl_getapptrust) { err = dcbnl_getapptrust(netdev, skb); if (err) @@ -1602,6 +1624,14 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, goto err; } + if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], + netdev, + ops->dcbnl_setrewr ?: dcb_setrewr); + if (err) + goto err; + } + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], netdev, ops->ieee_setapp ?: @@ -1701,6 +1731,14 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, goto err; } + if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], + netdev, + ops->dcbnl_delrewr ?: dcb_delrewr); + if (err) + goto err; + } + err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0); @@ -1929,6 +1967,22 @@ out: return ret; } +static struct dcb_app_type *dcb_rewr_lookup(const struct dcb_app *app, + int ifindex, int proto) +{ + struct dcb_app_type *itr; + + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->app.selector == app->selector && + itr->app.priority == app->priority && + itr->ifindex == ifindex && + ((proto == -1) || itr->app.protocol == proto)) + return itr; + } + + return NULL; +} + static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, int ifindex, int prio) { @@ -2052,6 +2106,63 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) } EXPORT_SYMBOL(dcb_ieee_getapp_mask); +/* Get protocol value from rewrite entry. */ +u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u16 proto = 0; + + spin_lock_bh(&dcb_lock); + itr = dcb_rewr_lookup(app, dev->ifindex, -1); + if (itr) + proto = itr->app.protocol; + spin_unlock_bh(&dcb_lock); + + return proto; +} +EXPORT_SYMBOL(dcb_getrewr); + + /* Add rewrite entry to the rewrite list. */ +int dcb_setrewr(struct net_device *dev, struct dcb_app *new) +{ + int err; + + spin_lock_bh(&dcb_lock); + /* Search for existing match and abort if found. */ + if (dcb_rewr_lookup(new, dev->ifindex, new->protocol)) { + err = -EEXIST; + goto out; + } + + err = dcb_app_add(&dcb_rewr_list, new, dev->ifindex); +out: + spin_unlock_bh(&dcb_lock); + + return err; +} +EXPORT_SYMBOL(dcb_setrewr); + +/* Delete rewrite entry from the rewrite list. */ +int dcb_delrewr(struct net_device *dev, struct dcb_app *del) +{ + struct dcb_app_type *itr; + int err = -ENOENT; + + spin_lock_bh(&dcb_lock); + /* Search for existing match and remove it. */ + itr = dcb_rewr_lookup(del, dev->ifindex, del->protocol); + if (itr) { + list_del(&itr->list); + kfree(itr); + err = 0; + } + + spin_unlock_bh(&dcb_lock); + + return err; +} +EXPORT_SYMBOL(dcb_delrewr); + /** * dcb_ieee_setapp - add IEEE dcb application data to app list * @dev: network interface -- cgit v1.2.3 From f90b529bcbe57c66da2b6a0d3c7c81e8567af63d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 16 Jan 2023 16:04:47 +0000 Subject: arm64/sme: Implement ZT0 ptrace support Implement support for a new note type NT_ARM64_ZT providing access to ZT0 when implemented. Since ZT0 is a register with constant size this is much simpler than for other SME state. As ZT0 is only accessible when PSTATE.ZA is set writes to ZT0 cause PSTATE.ZA to be set, the main alternative would be to return -EBUSY in this case but this seemed more constructive. Practical users are also going to be working with ZA anyway and have some understanding of the state. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20221208-arm64-sme2-v4-12-f2fa0aef982f@kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/kernel/ptrace.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 55 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 67256e7772e4..38be7ca202af 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1138,6 +1138,51 @@ out: return ret; } +static int zt_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme2()) + return -EINVAL; + + /* + * If PSTATE.ZA is not set then ZT will be zeroed when it is + * enabled so report the current register value as zero. + */ + if (thread_za_enabled(&target->thread)) + membuf_write(&to, thread_zt_state(&target->thread), + ZT_SIG_REG_BYTES); + else + membuf_zero(&to, ZT_SIG_REG_BYTES); + + return 0; +} + +static int zt_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!system_supports_sme2()) + return -EINVAL; + + if (!thread_za_enabled(&target->thread)) { + sme_alloc(target); + if (!target->thread.sme_state) + return -ENOMEM; + } + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + thread_zt_state(&target->thread), + 0, ZT_SIG_REG_BYTES); + if (ret == 0) + target->thread.svcr |= SVCR_ZA_MASK; + + return ret; +} + #endif /* CONFIG_ARM64_SME */ #ifdef CONFIG_ARM64_PTR_AUTH @@ -1360,6 +1405,7 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SSVE, REGSET_ZA, + REGSET_ZT, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, @@ -1467,6 +1513,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = za_get, .set = za_set, }, + [REGSET_ZT] = { /* SME ZT */ + .core_note_type = NT_ARM_ZT, + .n = 1, + .size = ZT_SIG_REG_BYTES, + .align = sizeof(u64), + .regset_get = zt_get, + .set = zt_set, + }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 4c6a8fa5e7ed..68de6f4c4eee 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -434,6 +434,7 @@ typedef struct elf64_shdr { #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ +#define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From 8d0e3fc61abdf56a403b316e03fa8f89a3108caa Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 21 Dec 2022 11:24:42 +0200 Subject: media: Add 2-10-10-10 RGB formats Add RGBX1010102, RGBA1010102 and ARGB2101010 formats. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Acked-by: Mauro Carvalho Chehab Acked-by: Hans Verkuil Signed-off-by: Laurent Pinchart --- .../userspace-api/media/v4l/pixfmt-rgb.rst | 194 +++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 3 + include/uapi/linux/videodev2.h | 3 + 3 files changed, 200 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 30f51cd33f99..d330aeb4d3eb 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst @@ -763,6 +763,200 @@ nomenclature that instead use the order of components as seen in a 24- or \normalsize +10 Bits Per Component +===================== + +These formats store a 30-bit RGB triplet with an optional 2 bit alpha in four +bytes. They are named based on the order of the RGB components as seen in a +32-bit word, which is then stored in memory in little endian byte order +(unless otherwise noted by the presence of bit 31 in the 4CC value), and on the +number of bits for each component. + +.. raw:: latex + + \begingroup + \tiny + \setlength{\tabcolsep}{2pt} + +.. tabularcolumns:: |p{2.8cm}|p{2.0cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}|p{0.22cm}| + + +.. flat-table:: RGB Formats 10 Bits Per Color Component + :header-rows: 2 + :stub-columns: 0 + + * - Identifier + - Code + - :cspan:`7` Byte 0 in memory + - :cspan:`7` Byte 1 + - :cspan:`7` Byte 2 + - :cspan:`7` Byte 3 + * - + - + - 7 + - 6 + - 5 + - 4 + - 3 + - 2 + - 1 + - 0 + + - 7 + - 6 + - 5 + - 4 + - 3 + - 2 + - 1 + - 0 + + - 7 + - 6 + - 5 + - 4 + - 3 + - 2 + - 1 + - 0 + + - 7 + - 6 + - 5 + - 4 + - 3 + - 2 + - 1 + - 0 + * .. _V4L2-PIX-FMT-RGBX1010102: + + - ``V4L2_PIX_FMT_RGBX1010102`` + - 'RX30' + + - b\ :sub:`5` + - b\ :sub:`4` + - b\ :sub:`3` + - b\ :sub:`2` + - b\ :sub:`1` + - b\ :sub:`0` + - x + - x + + - g\ :sub:`3` + - g\ :sub:`2` + - g\ :sub:`1` + - g\ :sub:`0` + - b\ :sub:`9` + - b\ :sub:`8` + - b\ :sub:`7` + - b\ :sub:`6` + + - r\ :sub:`1` + - r\ :sub:`0` + - g\ :sub:`9` + - g\ :sub:`8` + - g\ :sub:`7` + - g\ :sub:`6` + - g\ :sub:`5` + - g\ :sub:`4` + + - r\ :sub:`9` + - r\ :sub:`8` + - r\ :sub:`7` + - r\ :sub:`6` + - r\ :sub:`5` + - r\ :sub:`4` + - r\ :sub:`3` + - r\ :sub:`2` + - + * .. _V4L2-PIX-FMT-RGBA1010102: + + - ``V4L2_PIX_FMT_RGBA1010102`` + - 'RA30' + + - b\ :sub:`5` + - b\ :sub:`4` + - b\ :sub:`3` + - b\ :sub:`2` + - b\ :sub:`1` + - b\ :sub:`0` + - a\ :sub:`1` + - a\ :sub:`0` + + - g\ :sub:`3` + - g\ :sub:`2` + - g\ :sub:`1` + - g\ :sub:`0` + - b\ :sub:`9` + - b\ :sub:`8` + - b\ :sub:`7` + - b\ :sub:`6` + + - r\ :sub:`1` + - r\ :sub:`0` + - g\ :sub:`9` + - g\ :sub:`8` + - g\ :sub:`7` + - g\ :sub:`6` + - g\ :sub:`5` + - g\ :sub:`4` + + - r\ :sub:`9` + - r\ :sub:`8` + - r\ :sub:`7` + - r\ :sub:`6` + - r\ :sub:`5` + - r\ :sub:`4` + - r\ :sub:`3` + - r\ :sub:`2` + - + * .. _V4L2-PIX-FMT-ARGB2101010: + + - ``V4L2_PIX_FMT_ARGB2101010`` + - 'AR30' + + - b\ :sub:`7` + - b\ :sub:`6` + - b\ :sub:`5` + - b\ :sub:`4` + - b\ :sub:`3` + - b\ :sub:`2` + - b\ :sub:`1` + - b\ :sub:`0` + + - g\ :sub:`5` + - g\ :sub:`4` + - g\ :sub:`3` + - g\ :sub:`2` + - g\ :sub:`1` + - g\ :sub:`0` + - b\ :sub:`9` + - b\ :sub:`8` + + - r\ :sub:`3` + - r\ :sub:`2` + - r\ :sub:`1` + - r\ :sub:`0` + - g\ :sub:`9` + - g\ :sub:`8` + - g\ :sub:`7` + - g\ :sub:`6` + + - a\ :sub:`1` + - a\ :sub:`0` + - r\ :sub:`9` + - r\ :sub:`8` + - r\ :sub:`7` + - r\ :sub:`6` + - r\ :sub:`5` + - r\ :sub:`4` + - + +.. raw:: latex + + \endgroup + + Deprecated RGB Formats ====================== diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 8e0a0ff62a70..b58615bab790 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1298,6 +1298,9 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_BGRX32: descr = "32-bit XBGR 8-8-8-8"; break; case V4L2_PIX_FMT_RGBA32: descr = "32-bit RGBA 8-8-8-8"; break; case V4L2_PIX_FMT_RGBX32: descr = "32-bit RGBX 8-8-8-8"; break; + 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_GREY: descr = "8-bit Greyscale"; break; case V4L2_PIX_FMT_Y4: descr = "4-bit Greyscale"; break; case V4L2_PIX_FMT_Y6: descr = "6-bit Greyscale"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 1befd181a4cc..a573aea5acbd 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -576,6 +576,9 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_RGBX32 v4l2_fourcc('X', 'B', '2', '4') /* 32 RGBX-8-8-8-8 */ #define V4L2_PIX_FMT_ARGB32 v4l2_fourcc('B', 'A', '2', '4') /* 32 ARGB-8-8-8-8 */ #define V4L2_PIX_FMT_XRGB32 v4l2_fourcc('B', 'X', '2', '4') /* 32 XRGB-8-8-8-8 */ +#define V4L2_PIX_FMT_RGBX1010102 v4l2_fourcc('R', 'X', '3', '0') /* 32 RGBX-10-10-10-2 */ +#define V4L2_PIX_FMT_RGBA1010102 v4l2_fourcc('R', 'A', '3', '0') /* 32 RGBA-10-10-10-2 */ +#define V4L2_PIX_FMT_ARGB2101010 v4l2_fourcc('A', 'R', '3', '0') /* 32 ARGB-2-10-10-10 */ /* Grey formats */ #define V4L2_PIX_FMT_GREY v4l2_fourcc('G', 'R', 'E', 'Y') /* 8 Greyscale */ -- cgit v1.2.3 From 0dc1d7a79a8d13e316d3b168e9fc57e376099c7a Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 21 Dec 2022 11:24:43 +0200 Subject: media: Add Y210, Y212 and Y216 formats Add Y210, Y212 and Y216 formats. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Acked-by: Mauro Carvalho Chehab Acked-by: Hans Verkuil Signed-off-by: Laurent Pinchart --- .../userspace-api/media/v4l/pixfmt-packed-yuv.rst | 49 +++++++++++++++++++++- drivers/media/v4l2-core/v4l2-ioctl.c | 3 ++ include/uapi/linux/videodev2.h | 8 ++++ 3 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst b/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst index bf283a1b5581..24a771542059 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst @@ -262,7 +262,12 @@ the second byte and Y'\ :sub:`7-0` in the third byte. ================= These formats, commonly referred to as YUYV or YUY2, subsample the chroma -components horizontally by 2, storing 2 pixels in 4 bytes. +components horizontally by 2, storing 2 pixels in a container. The container +is 32-bits for 8-bit formats, and 64-bits for 10+-bit formats. + +The packed YUYV formats with more than 8 bits per component are stored as four +16-bit little-endian words. Each word's most significant bits contain one +component, and the least significant bits are zero padding. .. raw:: latex @@ -270,7 +275,7 @@ components horizontally by 2, storing 2 pixels in 4 bytes. .. tabularcolumns:: |p{3.4cm}|p{1.2cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}| -.. flat-table:: Packed YUV 4:2:2 Formats +.. flat-table:: Packed YUV 4:2:2 Formats in 32-bit container :header-rows: 1 :stub-columns: 0 @@ -337,6 +342,46 @@ components horizontally by 2, storing 2 pixels in 4 bytes. - Y'\ :sub:`3` - Cb\ :sub:`2` +.. tabularcolumns:: |p{3.4cm}|p{1.2cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}|p{0.8cm}| + +.. flat-table:: Packed YUV 4:2:2 Formats in 64-bit container + :header-rows: 1 + :stub-columns: 0 + + * - Identifier + - Code + - Word 0 + - Word 1 + - Word 2 + - Word 3 + * .. _V4L2-PIX-FMT-Y210: + + - ``V4L2_PIX_FMT_Y210`` + - 'Y210' + + - Y'\ :sub:`0` (bits 15-6) + - Cb\ :sub:`0` (bits 15-6) + - Y'\ :sub:`1` (bits 15-6) + - Cr\ :sub:`0` (bits 15-6) + * .. _V4L2-PIX-FMT-Y212: + + - ``V4L2_PIX_FMT_Y212`` + - 'Y212' + + - Y'\ :sub:`0` (bits 15-4) + - Cb\ :sub:`0` (bits 15-4) + - Y'\ :sub:`1` (bits 15-4) + - Cr\ :sub:`0` (bits 15-4) + * .. _V4L2-PIX-FMT-Y216: + + - ``V4L2_PIX_FMT_Y216`` + - 'Y216' + + - Y'\ :sub:`0` (bits 15-0) + - Cb\ :sub:`0` (bits 15-0) + - Y'\ :sub:`1` (bits 15-0) + - Cr\ :sub:`0` (bits 15-0) + .. raw:: latex \normalsize diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index b58615bab790..2a0139c72d29 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1445,6 +1445,9 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV12M_8L128: descr = "NV12M (8x128 Linear)"; break; case V4L2_PIX_FMT_NV12_10BE_8L128: descr = "10-bit NV12 (8x128 Linear, BE)"; break; case V4L2_PIX_FMT_NV12M_10BE_8L128: descr = "10-bit NV12M (8x128 Linear, BE)"; break; + 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; default: /* Compressed formats */ diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index a573aea5acbd..17a9b975177a 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -621,6 +621,14 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YUVX32 v4l2_fourcc('Y', 'U', 'V', 'X') /* 32 YUVX-8-8-8-8 */ #define V4L2_PIX_FMT_M420 v4l2_fourcc('M', '4', '2', '0') /* 12 YUV 4:2:0 2 lines y, 1 line uv interleaved */ +/* + * YCbCr packed format. For each Y2xx format, xx bits of valid data occupy the MSBs + * of the 16 bit components, and 16-xx bits of zero padding occupy the LSBs. + */ +#define V4L2_PIX_FMT_Y210 v4l2_fourcc('Y', '2', '1', '0') /* 32 YUYV 4:2:2 */ +#define V4L2_PIX_FMT_Y212 v4l2_fourcc('Y', '2', '1', '2') /* 32 YUYV 4:2:2 */ +#define V4L2_PIX_FMT_Y216 v4l2_fourcc('Y', '2', '1', '6') /* 32 YUYV 4:2:2 */ + /* two planes -- one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12 v4l2_fourcc('N', 'V', '1', '2') /* 12 Y/CbCr 4:2:0 */ #define V4L2_PIX_FMT_NV21 v4l2_fourcc('N', 'V', '2', '1') /* 12 Y/CrCb 4:2:0 */ -- cgit v1.2.3 From 0c4061c0d0e2c381ffe4d8b7c62ea69ad8132071 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Tue, 27 Dec 2022 20:34:06 +0100 Subject: batman-adv: tvlv: prepare for tvlv enabled multicast packet type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prepare TVLV infrastructure for more packet types, in particular the upcoming batman-adv multicast packet type. For that swap the OGM vs. unicast-tvlv packet boolean indicator to an explicit unsigned integer packet type variable. And provide the skb to a call to batadv_tvlv_containers_process(), as later the multicast packet's TVLV handler will need to have access not only to the TVLV but the full skb for forwarding. Forwarding will be invoked from the multicast packet's TVLVs' contents later. Signed-off-by: Linus Lüssing Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 2 + net/batman-adv/bat_v_ogm.c | 4 +- net/batman-adv/distributed-arp-table.c | 2 +- net/batman-adv/gateway_common.c | 2 +- net/batman-adv/multicast.c | 2 +- net/batman-adv/network-coding.c | 2 +- net/batman-adv/routing.c | 7 ++-- net/batman-adv/translation-table.c | 4 +- net/batman-adv/tvlv.c | 71 +++++++++++++++++++++++----------- net/batman-adv/tvlv.h | 9 +++-- net/batman-adv/types.h | 6 +++ 11 files changed, 74 insertions(+), 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index ea4692c339ce..9204e4494b25 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -26,6 +26,7 @@ * @BATADV_CODED: network coded packets * @BATADV_ELP: echo location packets for B.A.T.M.A.N. V * @BATADV_OGM2: originator messages for B.A.T.M.A.N. V + * @BATADV_MCAST: multicast packet with multiple destination addresses * * @BATADV_UNICAST: unicast packets carrying unicast payload traffic * @BATADV_UNICAST_FRAG: unicast packets carrying a fragment of the original @@ -42,6 +43,7 @@ enum batadv_packettype { BATADV_CODED = 0x02, BATADV_ELP = 0x03, BATADV_OGM2 = 0x04, + BATADV_MCAST = 0x05, /* 0x40 - 0x7f: unicast */ #define BATADV_UNICAST_MIN 0x40 BATADV_UNICAST = 0x40, diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 96e027364ddd..e710e9afe78f 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -799,8 +799,8 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, /* only unknown & newer OGMs contain TVLVs we are interested in */ if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT) - batadv_tvlv_containers_process(bat_priv, true, orig_node, - NULL, NULL, + batadv_tvlv_containers_process(bat_priv, BATADV_OGM2, orig_node, + NULL, (unsigned char *)(ogm2 + 1), ntohs(ogm2->tvlv_len)); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fefb51a5f606..6968e55eb971 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -822,7 +822,7 @@ int batadv_dat_init(struct batadv_priv *bat_priv) batadv_dat_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_dat_tvlv_ogm_handler_v1, - NULL, BATADV_TVLV_DAT, 1, + NULL, NULL, BATADV_TVLV_DAT, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_dat_tvlv_container_update(bat_priv); return 0; diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 9349c76f30c5..6a964a773f57 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -259,7 +259,7 @@ void batadv_gw_init(struct batadv_priv *bat_priv) atomic_set(&bat_priv->gw.sel_class, 1); batadv_tvlv_handler_register(bat_priv, batadv_gw_tvlv_ogm_handler_v1, - NULL, BATADV_TVLV_GW, 1, + NULL, NULL, BATADV_TVLV_GW, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 7e2822c01e00..315394f12c55 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1818,7 +1818,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, void batadv_mcast_init(struct batadv_priv *bat_priv) { batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler, - NULL, BATADV_TVLV_MCAST, 2, + NULL, NULL, BATADV_TVLV_MCAST, 2, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index ecd871abda34..71ebd0284f95 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -160,7 +160,7 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) batadv_nc_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_nc_tvlv_ogm_handler_v1, - NULL, BATADV_TVLV_NC, 1, + NULL, NULL, BATADV_TVLV_NC, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_nc_tvlv_container_update(bat_priv); return 0; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 83f31494ea4d..163cd43c4821 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1073,10 +1073,9 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, if (tvlv_buff_len > skb->len - hdr_size) goto free_skb; - ret = batadv_tvlv_containers_process(bat_priv, false, NULL, - unicast_tvlv_packet->src, - unicast_tvlv_packet->dst, - tvlv_buff, tvlv_buff_len); + ret = batadv_tvlv_containers_process(bat_priv, BATADV_UNICAST_TVLV, + NULL, skb, tvlv_buff, + tvlv_buff_len); if (ret != NET_RX_SUCCESS) { ret = batadv_route_unicast_packet(skb, recv_if); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 01d30c1e412c..36ca31252a73 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -4168,11 +4168,11 @@ int batadv_tt_init(struct batadv_priv *bat_priv) } batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1, - batadv_tt_tvlv_unicast_handler_v1, + batadv_tt_tvlv_unicast_handler_v1, NULL, BATADV_TVLV_TT, 1, BATADV_NO_FLAGS); batadv_tvlv_handler_register(bat_priv, NULL, - batadv_roam_tvlv_unicast_handler_v1, + batadv_roam_tvlv_unicast_handler_v1, NULL, BATADV_TVLV_ROAM, 1, BATADV_NO_FLAGS); INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 7ec2e2343884..2a583215d439 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -352,10 +352,9 @@ end: * appropriate handlers * @bat_priv: the bat priv with all the soft interface information * @tvlv_handler: tvlv callback function handling the tvlv content - * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet + * @packet_type: indicates for which packet type the TVLV handler is called * @orig_node: orig node emitting the ogm packet - * @src: source mac address of the unicast packet - * @dst: destination mac address of the unicast packet + * @skb: the skb the TVLV handler is called for * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length * @@ -364,15 +363,20 @@ end: */ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, struct batadv_tvlv_handler *tvlv_handler, - bool ogm_source, + u8 packet_type, struct batadv_orig_node *orig_node, - u8 *src, u8 *dst, - void *tvlv_value, u16 tvlv_value_len) + struct sk_buff *skb, void *tvlv_value, + u16 tvlv_value_len) { + unsigned int tvlv_offset; + u8 *src, *dst; + if (!tvlv_handler) return NET_RX_SUCCESS; - if (ogm_source) { + switch (packet_type) { + case BATADV_IV_OGM: + case BATADV_OGM2: if (!tvlv_handler->ogm_handler) return NET_RX_SUCCESS; @@ -383,19 +387,32 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, BATADV_NO_FLAGS, tvlv_value, tvlv_value_len); tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED; - } else { - if (!src) - return NET_RX_SUCCESS; - - if (!dst) + break; + case BATADV_UNICAST_TVLV: + if (!skb) return NET_RX_SUCCESS; if (!tvlv_handler->unicast_handler) return NET_RX_SUCCESS; + src = ((struct batadv_unicast_tvlv_packet *)skb->data)->src; + dst = ((struct batadv_unicast_tvlv_packet *)skb->data)->dst; + return tvlv_handler->unicast_handler(bat_priv, src, dst, tvlv_value, tvlv_value_len); + case BATADV_MCAST: + if (!skb) + return NET_RX_SUCCESS; + + if (!tvlv_handler->mcast_handler) + return NET_RX_SUCCESS; + + tvlv_offset = (unsigned char *)tvlv_value - skb->data; + skb_set_network_header(skb, tvlv_offset); + skb_set_transport_header(skb, tvlv_offset + tvlv_value_len); + + return tvlv_handler->mcast_handler(bat_priv, skb); } return NET_RX_SUCCESS; @@ -405,10 +422,9 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, * batadv_tvlv_containers_process() - parse the given tvlv buffer to call the * appropriate handlers * @bat_priv: the bat priv with all the soft interface information - * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet + * @packet_type: indicates for which packet type the TVLV handler is called * @orig_node: orig node emitting the ogm packet - * @src: source mac address of the unicast packet - * @dst: destination mac address of the unicast packet + * @skb: the skb the TVLV handler is called for * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length * @@ -416,10 +432,10 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, * handler callbacks. */ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, - bool ogm_source, + u8 packet_type, struct batadv_orig_node *orig_node, - u8 *src, u8 *dst, - void *tvlv_value, u16 tvlv_value_len) + struct sk_buff *skb, void *tvlv_value, + u16 tvlv_value_len) { struct batadv_tvlv_handler *tvlv_handler; struct batadv_tvlv_hdr *tvlv_hdr; @@ -441,20 +457,24 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, tvlv_hdr->version); ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler, - ogm_source, orig_node, - src, dst, tvlv_value, + packet_type, orig_node, skb, + tvlv_value, tvlv_value_cont_len); batadv_tvlv_handler_put(tvlv_handler); tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; tvlv_value_len -= tvlv_value_cont_len; } - if (!ogm_source) + if (packet_type != BATADV_IV_OGM && + packet_type != BATADV_OGM2) return ret; rcu_read_lock(); hlist_for_each_entry_rcu(tvlv_handler, &bat_priv->tvlv.handler_list, list) { + if (!tvlv_handler->ogm_handler) + continue; + if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) && !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED)) tvlv_handler->ogm_handler(bat_priv, orig_node, @@ -490,7 +510,7 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, tvlv_value = batadv_ogm_packet + 1; - batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL, + batadv_tvlv_containers_process(bat_priv, BATADV_IV_OGM, orig_node, NULL, tvlv_value, tvlv_value_len); } @@ -504,6 +524,10 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, * @uptr: unicast tvlv handler callback function. This function receives the * source & destination of the unicast packet as well as the tvlv content * to process. + * @mptr: multicast packet tvlv handler callback function. This function + * receives the full skb to process, with the skb network header pointing + * to the current tvlv and the skb transport header pointing to the first + * byte after the current tvlv. * @type: tvlv handler type to be registered * @version: tvlv handler version to be registered * @flags: flags to enable or disable TVLV API behavior @@ -518,6 +542,8 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len), + int (*mptr)(struct batadv_priv *bat_priv, + struct sk_buff *skb), u8 type, u8 version, u8 flags) { struct batadv_tvlv_handler *tvlv_handler; @@ -539,6 +565,7 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, tvlv_handler->ogm_handler = optr; tvlv_handler->unicast_handler = uptr; + tvlv_handler->mcast_handler = mptr; tvlv_handler->type = type; tvlv_handler->version = version; tvlv_handler->flags = flags; diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index 4cf8af00fc11..e5697230d991 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -9,6 +9,7 @@ #include "main.h" +#include #include #include @@ -34,14 +35,16 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len), + int (*mptr)(struct batadv_priv *bat_priv, + struct sk_buff *skb), u8 type, u8 version, u8 flags); void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, u8 type, u8 version); int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, - bool ogm_source, + u8 packet_type, struct batadv_orig_node *orig_node, - u8 *src, u8 *dst, - void *tvlv_buff, u16 tvlv_buff_len); + struct sk_buff *skb, void *tvlv_buff, + u16 tvlv_buff_len); void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, const u8 *src, const u8 *dst, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 758cd797a063..ca9449ec9836 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -2335,6 +2335,12 @@ struct batadv_tvlv_handler { u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len); + /** + * @mcast_handler: handler callback which is given the tvlv payload to + * process on incoming mcast packet + */ + int (*mcast_handler)(struct batadv_priv *bat_priv, struct sk_buff *skb); + /** @type: tvlv type this handler feels responsible for */ u8 type; -- cgit v1.2.3 From 9a6b5bf4c1bba341eeb010f3ea8b5b48651f65f8 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Mon, 22 Nov 2021 16:18:23 +0100 Subject: media: add V4L2_SUBDEV_CAP_STREAMS Add a subdev capability flag to expose to userspace if a subdev supports multiplexed streams. Signed-off-by: Tomi Valkeinen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-subdev.c | 5 ++++- include/uapi/linux/v4l2-subdev.h | 3 +++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 24acb4aa0895..3adb186bb742 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -446,6 +446,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, struct v4l2_subdev *sd = vdev_to_v4l2_subdev(vdev); struct v4l2_fh *vfh = file->private_data; bool ro_subdev = test_bit(V4L2_FL_SUBDEV_RO_DEVNODE, &vdev->flags); + bool streams_subdev = sd->flags & V4L2_SUBDEV_FL_STREAMS; int rval; switch (cmd) { @@ -454,7 +455,9 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, memset(cap->reserved, 0, sizeof(cap->reserved)); cap->version = LINUX_VERSION_CODE; - cap->capabilities = ro_subdev ? V4L2_SUBDEV_CAP_RO_SUBDEV : 0; + cap->capabilities = + (ro_subdev ? V4L2_SUBDEV_CAP_RO_SUBDEV : 0) | + (streams_subdev ? V4L2_SUBDEV_CAP_STREAMS : 0); return 0; } diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index ecce4c79f5c5..ffed9047e0be 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -175,6 +175,9 @@ struct v4l2_subdev_capability { /* The v4l2 sub-device video device node is registered in read-only mode. */ #define V4L2_SUBDEV_CAP_RO_SUBDEV 0x00000001 +/* The v4l2 sub-device supports routing and multiplexed streams. */ +#define V4L2_SUBDEV_CAP_STREAMS 0x00000002 + /* Backwards compatibility define --- to be removed */ #define v4l2_subdev_edid v4l2_edid -- cgit v1.2.3 From a418bb3f30d9ac570d51ff3f700851b78da2a8a9 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 23 Apr 2021 09:15:54 +0200 Subject: media: subdev: Add [GS]_ROUTING subdev ioctls and operations Add support for subdev internal routing. A route is defined as a single stream from a sink pad to a source pad. The userspace can configure the routing via two new ioctls, VIDIOC_SUBDEV_G_ROUTING and VIDIOC_SUBDEV_S_ROUTING, and subdevs can implement the functionality with v4l2_subdev_pad_ops.set_routing(). - Add sink and source streams for multiplexed links - Copy the argument back in case of an error. This is needed to let the caller know the number of routes. - Expand and refine documentation. - Make the 'routes' pointer a __u64 __user pointer so that a compat32 version of the ioctl is not required. - Add struct v4l2_subdev_krouting to be used for subdevice operations. - Fix typecasing warnings - Check sink & source pad types - Add 'which' field - Routing to subdev state - Dropped get_routing subdev op Signed-off-by: Laurent Pinchart Signed-off-by: Michal Simek Signed-off-by: Sakari Ailus Signed-off-by: Jacopo Mondi Signed-off-by: Tomi Valkeinen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ioctl.c | 25 ++++++++++- drivers/media/v4l2-core/v4l2-subdev.c | 84 +++++++++++++++++++++++++++++++++++ include/media/v4l2-subdev.h | 22 +++++++++ include/uapi/linux/v4l2-subdev.h | 43 ++++++++++++++++++ 4 files changed, 173 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 8e0a0ff62a70..b26da2650289 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -16,6 +16,7 @@ #include #include +#include #include #include /* for media_set_bus_info() */ @@ -3148,6 +3149,21 @@ static int check_array_args(unsigned int cmd, void *parg, size_t *array_size, ret = 1; break; } + + case VIDIOC_SUBDEV_G_ROUTING: + case VIDIOC_SUBDEV_S_ROUTING: { + struct v4l2_subdev_routing *routing = parg; + + if (routing->num_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; + ret = 1; + break; + } } return ret; @@ -3394,8 +3410,15 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg, /* * Some ioctls can return an error, but still have valid * results that must be returned. + * + * FIXME: subdev IOCTLS are partially handled here and partially in + * v4l2-subdev.c and the 'always_copy' flag can only be set for IOCTLS + * defined here as part of the 'v4l2_ioctls' array. As + * VIDIOC_SUBDEV_G_ROUTING needs to return results to applications even + * in case of failure, but it is not defined here as part of the + * 'v4l2_ioctls' array, insert an ad-hoc check to address that. */ - if (err < 0 && !always_copy) + if (err < 0 && !always_copy && cmd != VIDIOC_SUBDEV_G_ROUTING) goto out; if (has_array_args) { diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 3adb186bb742..f047ac1bf5ef 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -23,6 +23,16 @@ #include #include +/* + * Maximum stream ID is 63 for now, as we use u64 bitmask to represent a set + * of streams. + * + * Note that V4L2_FRAME_DESC_ENTRY_MAX is related: V4L2_FRAME_DESC_ENTRY_MAX + * restricts the total number of streams in a pad, although the stream ID is + * not restricted. + */ +#define V4L2_SUBDEV_MAX_STREAM_ID 63 + #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) static int subdev_fh_init(struct v4l2_subdev_fh *fh, struct v4l2_subdev *sd) { @@ -432,6 +442,10 @@ subdev_ioctl_get_state(struct v4l2_subdev *sd, struct v4l2_subdev_fh *subdev_fh, case VIDIOC_SUBDEV_S_SELECTION: which = ((struct v4l2_subdev_selection *)arg)->which; break; + case VIDIOC_SUBDEV_G_ROUTING: + case VIDIOC_SUBDEV_S_ROUTING: + which = ((struct v4l2_subdev_routing *)arg)->which; + break; } return which == V4L2_SUBDEV_FORMAT_TRY ? @@ -748,6 +762,75 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, case VIDIOC_SUBDEV_QUERYSTD: return v4l2_subdev_call(sd, video, querystd, arg); + case VIDIOC_SUBDEV_G_ROUTING: { + struct v4l2_subdev_routing *routing = arg; + struct v4l2_subdev_krouting *krouting; + + if (!(sd->flags & V4L2_SUBDEV_FL_STREAMS)) + return -ENOIOCTLCMD; + + memset(routing->reserved, 0, sizeof(routing->reserved)); + + 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)); + routing->num_routes = krouting->num_routes; + + return 0; + } + + case VIDIOC_SUBDEV_S_ROUTING: { + struct v4l2_subdev_routing *routing = arg; + struct v4l2_subdev_route *routes = + (struct v4l2_subdev_route *)(uintptr_t)routing->routes; + struct v4l2_subdev_krouting krouting = {}; + unsigned int i; + + if (!(sd->flags & V4L2_SUBDEV_FL_STREAMS)) + return -ENOIOCTLCMD; + + if (routing->which != V4L2_SUBDEV_FORMAT_TRY && ro_subdev) + return -EPERM; + + memset(routing->reserved, 0, sizeof(routing->reserved)); + + for (i = 0; i < routing->num_routes; ++i) { + const struct v4l2_subdev_route *route = &routes[i]; + const struct media_pad *pads = sd->entity.pads; + + if (route->sink_stream > V4L2_SUBDEV_MAX_STREAM_ID || + route->source_stream > V4L2_SUBDEV_MAX_STREAM_ID) + return -EINVAL; + + if (route->sink_pad >= sd->entity.num_pads) + return -EINVAL; + + if (!(pads[route->sink_pad].flags & + MEDIA_PAD_FL_SINK)) + return -EINVAL; + + if (route->source_pad >= sd->entity.num_pads) + return -EINVAL; + + if (!(pads[route->source_pad].flags & + MEDIA_PAD_FL_SOURCE)) + return -EINVAL; + } + + krouting.num_routes = routing->num_routes; + krouting.routes = routes; + + return v4l2_subdev_call(sd, pad, set_routing, state, + routing->which, &krouting); + } + default: return v4l2_subdev_call(sd, core, ioctl, cmd, arg); } @@ -1031,6 +1114,7 @@ void __v4l2_subdev_state_free(struct v4l2_subdev_state *state) mutex_destroy(&state->_lock); + kfree(state->routing.routes); kvfree(state->pads); kfree(state); } diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 95361b541087..67e55758f037 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -700,12 +700,26 @@ struct v4l2_subdev_pad_config { struct v4l2_rect try_compose; }; +/** + * struct v4l2_subdev_krouting - subdev routing table + * + * @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 num_routes; + struct v4l2_subdev_route *routes; +}; + /** * struct v4l2_subdev_state - Used for storing subdev state information. * * @_lock: default for 'lock' * @lock: mutex for the state. May be replaced by the user. * @pads: &struct v4l2_subdev_pad_config array + * @routing: routing table for the subdev * * This structure only needs to be passed to the pad op if the 'which' field * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For @@ -716,6 +730,7 @@ struct v4l2_subdev_state { struct mutex _lock; struct mutex *lock; struct v4l2_subdev_pad_config *pads; + struct v4l2_subdev_krouting routing; }; /** @@ -768,6 +783,9 @@ struct v4l2_subdev_state { * this operation as close as possible to stream on time. The * operation shall fail if the pad index it has been called on * is not valid or in case of unrecoverable failures. + * + * @set_routing: enable or disable data connection routes described in the + * subdevice routing table. */ struct v4l2_subdev_pad_ops { int (*init_cfg)(struct v4l2_subdev *sd, @@ -810,6 +828,10 @@ struct v4l2_subdev_pad_ops { struct v4l2_mbus_frame_desc *fd); int (*get_mbus_config)(struct v4l2_subdev *sd, unsigned int pad, struct v4l2_mbus_config *config); + int (*set_routing)(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + enum v4l2_subdev_format_whence which, + struct v4l2_subdev_krouting *route); }; /** diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index ffed9047e0be..284ae8c95960 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -11,6 +11,7 @@ #ifndef __LINUX_V4L2_SUBDEV_H #define __LINUX_V4L2_SUBDEV_H +#include #include #include #include @@ -178,6 +179,46 @@ struct v4l2_subdev_capability { /* The v4l2 sub-device supports routing and multiplexed streams. */ #define V4L2_SUBDEV_CAP_STREAMS 0x00000002 +/* + * Is the route active? An active route will start when streaming is enabled + * on a video node. + */ +#define V4L2_SUBDEV_ROUTE_FL_ACTIVE (1U << 0) + +/** + * struct v4l2_subdev_route - A route inside a subdev + * + * @sink_pad: the sink pad index + * @sink_stream: the sink stream identifier + * @source_pad: the source pad index + * @source_stream: the source stream identifier + * @flags: route flags V4L2_SUBDEV_ROUTE_FL_* + * @reserved: drivers and applications must zero this array + */ +struct v4l2_subdev_route { + __u32 sink_pad; + __u32 sink_stream; + __u32 source_pad; + __u32 source_stream; + __u32 flags; + __u32 reserved[5]; +}; + +/** + * 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 + * @routes: pointer to the routes array + * @reserved: drivers and applications must zero this array + */ +struct v4l2_subdev_routing { + __u32 which; + __u32 num_routes; + __u64 routes; + __u32 reserved[6]; +}; + /* Backwards compatibility define --- to be removed */ #define v4l2_subdev_edid v4l2_edid @@ -193,6 +234,8 @@ struct v4l2_subdev_capability { #define VIDIOC_SUBDEV_S_CROP _IOWR('V', 60, struct v4l2_subdev_crop) #define VIDIOC_SUBDEV_G_SELECTION _IOWR('V', 61, struct v4l2_subdev_selection) #define VIDIOC_SUBDEV_S_SELECTION _IOWR('V', 62, struct v4l2_subdev_selection) +#define VIDIOC_SUBDEV_G_ROUTING _IOWR('V', 38, struct v4l2_subdev_routing) +#define VIDIOC_SUBDEV_S_ROUTING _IOWR('V', 39, struct v4l2_subdev_routing) /* The following ioctls are identical to the ioctls in videodev2.h */ #define VIDIOC_SUBDEV_G_STD _IOR('V', 23, v4l2_std_id) #define VIDIOC_SUBDEV_S_STD _IOW('V', 24, v4l2_std_id) -- cgit v1.2.3 From 2f91e10ee6fd4c0c4abba4d36c013a93560cf514 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 21 Dec 2021 11:20:53 +0100 Subject: media: subdev: add stream based configuration Add support to manage configurations (format, crop, compose) per stream, instead of per pad. This is accomplished with data structures that hold an array of all subdev's stream configurations. The number of streams can vary at runtime based on routing. Every time the routing is changed, the stream configurations need to be re-initialized. Signed-off-by: Tomi Valkeinen Signed-off-by: Mauro Carvalho Chehab --- .../v4l/vidioc-subdev-enum-frame-interval.rst | 5 +- .../media/v4l/vidioc-subdev-enum-frame-size.rst | 5 +- .../media/v4l/vidioc-subdev-enum-mbus-code.rst | 5 +- .../media/v4l/vidioc-subdev-g-crop.rst | 5 +- .../media/v4l/vidioc-subdev-g-fmt.rst | 5 +- .../media/v4l/vidioc-subdev-g-frame-interval.rst | 5 +- .../media/v4l/vidioc-subdev-g-selection.rst | 5 +- drivers/media/v4l2-core/v4l2-subdev.c | 150 ++++++++++++++++++++- include/media/v4l2-subdev.h | 79 +++++++++++ include/uapi/linux/v4l2-subdev.h | 28 +++- 10 files changed, 271 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-interval.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-interval.rst index 3703943b412f..8def4c05d3da 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-interval.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-interval.rst @@ -92,7 +92,10 @@ multiple pads of the same sub-device is not defined. - Frame intervals to be enumerated, from enum :ref:`v4l2_subdev_format_whence `. * - __u32 - - ``reserved``\ [8] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [7] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-size.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-size.rst index c25a9896df0e..3ef361c0dca7 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-size.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-frame-size.rst @@ -97,7 +97,10 @@ information about try formats. - Frame sizes to be enumerated, from enum :ref:`v4l2_subdev_format_whence `. * - __u32 - - ``reserved``\ [8] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [7] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst index 417f1a19bcc4..248f6f9ee7c5 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst @@ -73,7 +73,10 @@ information about the try formats. - ``flags`` - See :ref:`v4l2-subdev-mbus-code-flags` * - __u32 - - ``reserved``\ [7] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [6] - Reserved for future extensions. Applications and drivers must set the array to zero. 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 bd15c0a5a66b..1d267f7e7991 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-crop.rst @@ -96,7 +96,10 @@ modified format should be as close as possible to the original request. - ``rect`` - Crop rectangle boundaries, in pixels. * - __u32 - - ``reserved``\ [8] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [7] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-fmt.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-fmt.rst index 7acdbb939d89..ed253a1e44b7 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-fmt.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-fmt.rst @@ -102,7 +102,10 @@ should be as close as possible to the original request. - Definition of an image format, see :c:type:`v4l2_mbus_framefmt` for details. * - __u32 - - ``reserved``\ [8] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [7] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst index d7fe7543c506..842f962d2aea 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst @@ -90,7 +90,10 @@ the same sub-device is not defined. - ``interval`` - Period, in seconds, between consecutive video frames. * - __u32 - - ``reserved``\ [9] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [8] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-selection.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-selection.rst index f9172a42f036..6b629c19168c 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-selection.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-selection.rst @@ -94,7 +94,10 @@ Selection targets and flags are documented in - ``r`` - Selection rectangle, in pixels. * - __u32 - - ``reserved``\ [8] + - ``stream`` + - Stream identifier. + * - __u32 + - ``reserved``\ [7] - Reserved for future extensions. Applications and drivers must set the array to zero. diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 730c31eaa35e..a3e412c73715 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -168,8 +168,22 @@ static inline int check_pad(struct v4l2_subdev *sd, u32 pad) return 0; } -static int check_state_pads(u32 which, struct v4l2_subdev_state *state) +static int check_state(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, + u32 which, u32 pad, u32 stream) { + if (sd->flags & V4L2_SUBDEV_FL_STREAMS) { +#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) + if (!v4l2_subdev_state_get_stream_format(state, pad, stream)) + return -EINVAL; + return 0; +#else + return -EINVAL; +#endif + } + + if (stream != 0) + return -EINVAL; + if (which == V4L2_SUBDEV_FORMAT_TRY && (!state || !state->pads)) return -EINVAL; @@ -184,7 +198,7 @@ static inline int check_format(struct v4l2_subdev *sd, return -EINVAL; return check_which(format->which) ? : check_pad(sd, format->pad) ? : - check_state_pads(format->which, state); + check_state(sd, state, format->which, format->pad, format->stream); } static int call_get_fmt(struct v4l2_subdev *sd, @@ -211,7 +225,7 @@ static int call_enum_mbus_code(struct v4l2_subdev *sd, return -EINVAL; return check_which(code->which) ? : check_pad(sd, code->pad) ? : - check_state_pads(code->which, state) ? : + check_state(sd, state, code->which, code->pad, code->stream) ? : sd->ops->pad->enum_mbus_code(sd, state, code); } @@ -223,7 +237,7 @@ static int call_enum_frame_size(struct v4l2_subdev *sd, return -EINVAL; return check_which(fse->which) ? : check_pad(sd, fse->pad) ? : - check_state_pads(fse->which, state) ? : + check_state(sd, state, fse->which, fse->pad, fse->stream) ? : sd->ops->pad->enum_frame_size(sd, state, fse); } @@ -258,7 +272,7 @@ static int call_enum_frame_interval(struct v4l2_subdev *sd, return -EINVAL; return check_which(fie->which) ? : check_pad(sd, fie->pad) ? : - check_state_pads(fie->which, state) ? : + check_state(sd, state, fie->which, fie->pad, fie->stream) ? : sd->ops->pad->enum_frame_interval(sd, state, fie); } @@ -270,7 +284,7 @@ static inline int check_selection(struct v4l2_subdev *sd, return -EINVAL; return check_which(sel->which) ? : check_pad(sd, sel->pad) ? : - check_state_pads(sel->which, state); + check_state(sd, state, sel->which, sel->pad, sel->stream); } static int call_get_selection(struct v4l2_subdev *sd, @@ -1122,7 +1136,8 @@ __v4l2_subdev_state_alloc(struct v4l2_subdev *sd, const char *lock_name, else state->lock = &state->_lock; - if (sd->entity.num_pads) { + /* Drivers that support streams do not need the legacy pad config */ + if (!(sd->flags & V4L2_SUBDEV_FL_STREAMS) && sd->entity.num_pads) { state->pads = kvcalloc(sd->entity.num_pads, sizeof(*state->pads), GFP_KERNEL); if (!state->pads) { @@ -1162,6 +1177,7 @@ void __v4l2_subdev_state_free(struct v4l2_subdev_state *state) mutex_destroy(&state->_lock); kfree(state->routing.routes); + kvfree(state->stream_configs.configs); kvfree(state->pads); kfree(state); } @@ -1191,6 +1207,55 @@ EXPORT_SYMBOL_GPL(v4l2_subdev_cleanup); #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) +static int +v4l2_subdev_init_stream_configs(struct v4l2_subdev_stream_configs *stream_configs, + const struct v4l2_subdev_krouting *routing) +{ + struct v4l2_subdev_stream_configs new_configs = { 0 }; + struct v4l2_subdev_route *route; + u32 idx; + + /* Count number of formats needed */ + for_each_active_route(routing, route) { + /* + * Each route needs a format on both ends of the route. + */ + new_configs.num_configs += 2; + } + + if (new_configs.num_configs) { + new_configs.configs = kvcalloc(new_configs.num_configs, + sizeof(*new_configs.configs), + GFP_KERNEL); + + if (!new_configs.configs) + return -ENOMEM; + } + + /* + * Fill in the 'pad' and stream' value for each item in the array from + * the routing table + */ + idx = 0; + + for_each_active_route(routing, route) { + new_configs.configs[idx].pad = route->sink_pad; + new_configs.configs[idx].stream = route->sink_stream; + + idx++; + + new_configs.configs[idx].pad = route->source_pad; + new_configs.configs[idx].stream = route->source_stream; + + idx++; + } + + kvfree(stream_configs->configs); + *stream_configs = new_configs; + + return 0; +} + int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, struct v4l2_subdev_format *format) { @@ -1217,6 +1282,7 @@ int v4l2_subdev_set_routing(struct v4l2_subdev *sd, const struct v4l2_subdev_krouting *src = routing; struct v4l2_subdev_krouting new_routing = { 0 }; size_t bytes; + int r; if (unlikely(check_mul_overflow((size_t)src->num_routes, sizeof(*src->routes), &bytes))) @@ -1232,6 +1298,13 @@ int v4l2_subdev_set_routing(struct v4l2_subdev *sd, new_routing.num_routes = src->num_routes; + r = v4l2_subdev_init_stream_configs(&state->stream_configs, + &new_routing); + if (r) { + kfree(new_routing.routes); + return r; + } + kfree(dst->routes); *dst = new_routing; @@ -1259,6 +1332,69 @@ __v4l2_subdev_next_active_route(const struct v4l2_subdev_krouting *routing, } EXPORT_SYMBOL_GPL(__v4l2_subdev_next_active_route); +struct v4l2_mbus_framefmt * +v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state, + unsigned int pad, u32 stream) +{ + struct v4l2_subdev_stream_configs *stream_configs; + unsigned int i; + + lockdep_assert_held(state->lock); + + stream_configs = &state->stream_configs; + + for (i = 0; i < stream_configs->num_configs; ++i) { + if (stream_configs->configs[i].pad == pad && + stream_configs->configs[i].stream == stream) + return &stream_configs->configs[i].fmt; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_stream_format); + +struct v4l2_rect * +v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state, + unsigned int pad, u32 stream) +{ + struct v4l2_subdev_stream_configs *stream_configs; + unsigned int i; + + lockdep_assert_held(state->lock); + + stream_configs = &state->stream_configs; + + for (i = 0; i < stream_configs->num_configs; ++i) { + if (stream_configs->configs[i].pad == pad && + stream_configs->configs[i].stream == stream) + return &stream_configs->configs[i].crop; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_stream_crop); + +struct v4l2_rect * +v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state, + unsigned int pad, u32 stream) +{ + struct v4l2_subdev_stream_configs *stream_configs; + unsigned int i; + + lockdep_assert_held(state->lock); + + stream_configs = &state->stream_configs; + + for (i = 0; i < stream_configs->num_configs; ++i) { + if (stream_configs->configs[i].pad == pad && + stream_configs->configs[i].stream == stream) + return &stream_configs->configs[i].compose; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_stream_compose); + #endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ #endif /* CONFIG_MEDIA_CONTROLLER */ diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 9e34c70b8d73..643cdcd69ac6 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -700,6 +700,37 @@ struct v4l2_subdev_pad_config { struct v4l2_rect try_compose; }; +/** + * struct v4l2_subdev_stream_config - Used for storing stream configuration. + * + * @pad: pad number + * @stream: stream number + * @fmt: &struct v4l2_mbus_framefmt + * @crop: &struct v4l2_rect to be used for crop + * @compose: &struct v4l2_rect to be used for compose + * + * This structure stores configuration for a stream. + */ +struct v4l2_subdev_stream_config { + u32 pad; + u32 stream; + + struct v4l2_mbus_framefmt fmt; + struct v4l2_rect crop; + struct v4l2_rect compose; +}; + +/** + * struct v4l2_subdev_stream_configs - A collection of stream configs. + * + * @num_configs: number of entries in @config. + * @configs: an array of &struct v4l2_subdev_stream_configs. + */ +struct v4l2_subdev_stream_configs { + u32 num_configs; + struct v4l2_subdev_stream_config *configs; +}; + /** * struct v4l2_subdev_krouting - subdev routing table * @@ -720,6 +751,7 @@ struct v4l2_subdev_krouting { * @lock: mutex for the state. May be replaced by the user. * @pads: &struct v4l2_subdev_pad_config array * @routing: routing table for the subdev + * @stream_configs: stream configurations (only for V4L2_SUBDEV_FL_STREAMS) * * This structure only needs to be passed to the pad op if the 'which' field * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For @@ -731,6 +763,7 @@ struct v4l2_subdev_state { struct mutex *lock; struct v4l2_subdev_pad_config *pads; struct v4l2_subdev_krouting routing; + struct v4l2_subdev_stream_configs stream_configs; }; /** @@ -1453,6 +1486,52 @@ __v4l2_subdev_next_active_route(const struct v4l2_subdev_krouting *routing, for ((route) = NULL; \ ((route) = __v4l2_subdev_next_active_route((routing), (route)));) +/** + * v4l2_subdev_state_get_stream_format() - Get pointer to a stream format + * @state: subdevice state + * @pad: pad id + * @stream: stream id + * + * This returns a pointer to &struct v4l2_mbus_framefmt for the given pad + + * stream in the subdev state. + * + * If the state does not contain the given pad + stream, NULL is returned. + */ +struct v4l2_mbus_framefmt * +v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state, + unsigned int pad, u32 stream); + +/** + * v4l2_subdev_state_get_stream_crop() - Get pointer to a stream crop rectangle + * @state: subdevice state + * @pad: pad id + * @stream: stream id + * + * This returns a pointer to crop rectangle for the given pad + stream in the + * subdev state. + * + * If the state does not contain the given pad + stream, NULL is returned. + */ +struct v4l2_rect * +v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state, + unsigned int pad, u32 stream); + +/** + * v4l2_subdev_state_get_stream_compose() - Get pointer to a stream compose + * rectangle + * @state: subdevice state + * @pad: pad id + * @stream: stream id + * + * This returns a pointer to compose rectangle for the given pad + stream in the + * subdev state. + * + * If the state does not contain the given pad + stream, NULL is returned. + */ +struct v4l2_rect * +v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state, + unsigned int pad, u32 stream); + #endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ #endif /* CONFIG_MEDIA_CONTROLLER */ diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 284ae8c95960..654d659de835 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -32,13 +32,15 @@ enum v4l2_subdev_format_whence { * @which: format type (from enum v4l2_subdev_format_whence) * @pad: pad number, as reported by the media API * @format: media bus format (format code and frame size) + * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_format { __u32 which; __u32 pad; struct v4l2_mbus_framefmt format; - __u32 reserved[8]; + __u32 stream; + __u32 reserved[7]; }; /** @@ -46,13 +48,15 @@ struct v4l2_subdev_format { * @which: format type (from enum v4l2_subdev_format_whence) * @pad: pad number, as reported by the media API * @rect: pad crop rectangle boundaries + * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_crop { __u32 which; __u32 pad; struct v4l2_rect rect; - __u32 reserved[8]; + __u32 stream; + __u32 reserved[7]; }; #define V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE 0x00000001 @@ -68,6 +72,7 @@ struct v4l2_subdev_crop { * @code: format code (MEDIA_BUS_FMT_ definitions) * @which: format type (from enum v4l2_subdev_format_whence) * @flags: flags set by the driver, (V4L2_SUBDEV_MBUS_CODE_*) + * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_mbus_code_enum { @@ -76,7 +81,8 @@ struct v4l2_subdev_mbus_code_enum { __u32 code; __u32 which; __u32 flags; - __u32 reserved[7]; + __u32 stream; + __u32 reserved[6]; }; /** @@ -89,6 +95,7 @@ struct v4l2_subdev_mbus_code_enum { * @min_height: minimum frame height, in pixels * @max_height: maximum frame height, in pixels * @which: format type (from enum v4l2_subdev_format_whence) + * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_frame_size_enum { @@ -100,19 +107,22 @@ struct v4l2_subdev_frame_size_enum { __u32 min_height; __u32 max_height; __u32 which; - __u32 reserved[8]; + __u32 stream; + __u32 reserved[7]; }; /** * struct v4l2_subdev_frame_interval - Pad-level frame rate * @pad: pad number, as reported by the media API * @interval: frame interval in seconds + * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_frame_interval { __u32 pad; struct v4l2_fract interval; - __u32 reserved[9]; + __u32 stream; + __u32 reserved[8]; }; /** @@ -124,6 +134,7 @@ struct v4l2_subdev_frame_interval { * @height: frame height in pixels * @interval: frame interval in seconds * @which: format type (from enum v4l2_subdev_format_whence) + * @stream: stream number, defined in subdev routing * @reserved: drivers and applications must zero this array */ struct v4l2_subdev_frame_interval_enum { @@ -134,7 +145,8 @@ struct v4l2_subdev_frame_interval_enum { __u32 height; struct v4l2_fract interval; __u32 which; - __u32 reserved[8]; + __u32 stream; + __u32 reserved[7]; }; /** @@ -146,6 +158,7 @@ struct v4l2_subdev_frame_interval_enum { * defined in v4l2-common.h; V4L2_SEL_TGT_* . * @flags: constraint flags, defined in v4l2-common.h; V4L2_SEL_FLAG_*. * @r: coordinates of the selection window + * @stream: stream number, defined in subdev routing * @reserved: for future use, set to zero for now * * Hardware may use multiple helper windows to process a video stream. @@ -158,7 +171,8 @@ struct v4l2_subdev_selection { __u32 target; __u32 flags; struct v4l2_rect r; - __u32 reserved[8]; + __u32 stream; + __u32 reserved[7]; }; /** -- cgit v1.2.3 From ba47652ba65523ccadac3f8d50dc0e0d560477b2 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 10 Jan 2023 10:26:19 +0100 Subject: media: meye: remove this deprecated driver The meye driver does not use the vb2 framework for streaming video, instead it implements this in the driver. This is error prone, and nobody stepped in to convert this driver to that framework. The hardware is very old, so the decision was made to remove it altogether. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/media/meye.rst | 93 - Documentation/admin-guide/media/pci-cardlist.rst | 1 - Documentation/admin-guide/media/v4l-drivers.rst | 1 - .../userspace-api/media/drivers/index.rst | 1 - .../userspace-api/media/drivers/meye-uapi.rst | 53 - MAINTAINERS | 8 - drivers/staging/media/Kconfig | 1 - drivers/staging/media/Makefile | 1 - drivers/staging/media/deprecated/meye/Kconfig | 19 - drivers/staging/media/deprecated/meye/Makefile | 2 - drivers/staging/media/deprecated/meye/TODO | 6 - drivers/staging/media/deprecated/meye/meye.c | 1814 -------------------- drivers/staging/media/deprecated/meye/meye.h | 311 ---- include/uapi/linux/meye.h | 65 - include/uapi/linux/v4l2-controls.h | 8 +- 15 files changed, 6 insertions(+), 2378 deletions(-) delete mode 100644 Documentation/admin-guide/media/meye.rst delete mode 100644 Documentation/userspace-api/media/drivers/meye-uapi.rst delete mode 100644 drivers/staging/media/deprecated/meye/Kconfig delete mode 100644 drivers/staging/media/deprecated/meye/Makefile delete mode 100644 drivers/staging/media/deprecated/meye/TODO delete mode 100644 drivers/staging/media/deprecated/meye/meye.c delete mode 100644 drivers/staging/media/deprecated/meye/meye.h delete mode 100644 include/uapi/linux/meye.h (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/media/meye.rst b/Documentation/admin-guide/media/meye.rst deleted file mode 100644 index 9098a1e65f8b..000000000000 --- a/Documentation/admin-guide/media/meye.rst +++ /dev/null @@ -1,93 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -.. include:: - -Vaio Picturebook Motion Eye Camera Driver -========================================= - -Copyright |copy| 2001-2004 Stelian Pop - -Copyright |copy| 2001-2002 Alcôve - -Copyright |copy| 2000 Andrew Tridgell - -This driver enable the use of video4linux compatible applications with the -Motion Eye camera. This driver requires the "Sony Laptop Extras" driver (which -can be found in the "Misc devices" section of the kernel configuration utility) -to be compiled and installed (using its "camera=1" parameter). - -It can do at maximum 30 fps @ 320x240 or 15 fps @ 640x480. - -Grabbing is supported in packed YUV colorspace only. - -MJPEG hardware grabbing is supported via a private API (see below). - -Hardware supported ------------------- - -This driver supports the 'second' version of the MotionEye camera :) - -The first version was connected directly on the video bus of the Neomagic -video card and is unsupported. - -The second one, made by Kawasaki Steel is fully supported by this -driver (PCI vendor/device is 0x136b/0xff01) - -The third one, present in recent (more or less last year) Picturebooks -(C1M* models), is not supported. The manufacturer has given the specs -to the developers under a NDA (which allows the development of a GPL -driver however), but things are not moving very fast (see -http://r-engine.sourceforge.net/) (PCI vendor/device is 0x10cf/0x2011). - -There is a forth model connected on the USB bus in TR1* Vaio laptops. -This camera is not supported at all by the current driver, in fact -little information if any is available for this camera -(USB vendor/device is 0x054c/0x0107). - -Driver options --------------- - -Several options can be passed to the meye driver using the standard -module argument syntax (= when passing the option to the -module or meye.= on the kernel boot line when meye is -statically linked into the kernel). Those options are: - -.. code-block:: none - - gbuffers: number of capture buffers, default is 2 (32 max) - - gbufsize: size of each capture buffer, default is 614400 - - video_nr: video device to register (0 = /dev/video0, etc) - -Module use ----------- - -In order to automatically load the meye module on use, you can put those lines -in your /etc/modprobe.d/meye.conf file: - -.. code-block:: none - - alias char-major-81 videodev - alias char-major-81-0 meye - options meye gbuffers=32 - -Usage: ------- - -.. code-block:: none - - xawtv >= 3.49 () - for display and uncompressed video capture: - - xawtv -c /dev/video0 -geometry 640x480 - or - xawtv -c /dev/video0 -geometry 320x240 - - motioneye () - for getting ppm or jpg snapshots, mjpeg video - -Bugs / Todo ------------ - -- 'motioneye' still uses the meye private v4l1 API extensions. diff --git a/Documentation/admin-guide/media/pci-cardlist.rst b/Documentation/admin-guide/media/pci-cardlist.rst index f4d670e632f8..42528795d4da 100644 --- a/Documentation/admin-guide/media/pci-cardlist.rst +++ b/Documentation/admin-guide/media/pci-cardlist.rst @@ -77,7 +77,6 @@ ipu3-cio2 Intel ipu3-cio2 driver ivtv Conexant cx23416/cx23415 MPEG encoder/decoder ivtvfb Conexant cx23415 framebuffer mantis MANTIS based cards -meye Sony Vaio Picturebook Motion Eye mxb Siemens-Nixdorf 'Multimedia eXtension Board' netup-unidvb NetUP Universal DVB card ngene Micronas nGene diff --git a/Documentation/admin-guide/media/v4l-drivers.rst b/Documentation/admin-guide/media/v4l-drivers.rst index 90a026ee05c6..adb5240d0407 100644 --- a/Documentation/admin-guide/media/v4l-drivers.rst +++ b/Documentation/admin-guide/media/v4l-drivers.rst @@ -19,7 +19,6 @@ Video4Linux (V4L) driver-specific documentation imx7 ipu3 ivtv - meye omap3isp omap4_camera philips diff --git a/Documentation/userspace-api/media/drivers/index.rst b/Documentation/userspace-api/media/drivers/index.rst index 915dbf0f4db5..6708d649afd7 100644 --- a/Documentation/userspace-api/media/drivers/index.rst +++ b/Documentation/userspace-api/media/drivers/index.rst @@ -37,7 +37,6 @@ For more details see the file COPYING in the source distribution of Linux. dw100 imx-uapi max2175 - meye-uapi omap3isp-uapi st-vgxy61 uvcvideo diff --git a/Documentation/userspace-api/media/drivers/meye-uapi.rst b/Documentation/userspace-api/media/drivers/meye-uapi.rst deleted file mode 100644 index 66b1c142f920..000000000000 --- a/Documentation/userspace-api/media/drivers/meye-uapi.rst +++ /dev/null @@ -1,53 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -.. include:: - -Vaio Picturebook Motion Eye Camera Driver -========================================= - -Copyright |copy| 2001-2004 Stelian Pop - -Copyright |copy| 2001-2002 Alcôve - -Copyright |copy| 2000 Andrew Tridgell - -Private API ------------ - -The driver supports frame grabbing with the video4linux API, -so all video4linux tools (like xawtv) should work with this driver. - -Besides the video4linux interface, the driver has a private interface -for accessing the Motion Eye extended parameters (camera sharpness, -agc, video framerate), the snapshot and the MJPEG capture facilities. - -This interface consists of several ioctls (prototypes and structures -can be found in include/linux/meye.h): - -MEYEIOC_G_PARAMS and MEYEIOC_S_PARAMS - Get and set the extended parameters of the motion eye camera. - The user should always query the current parameters with - MEYEIOC_G_PARAMS, change what he likes and then issue the - MEYEIOC_S_PARAMS call (checking for -EINVAL). The extended - parameters are described by the meye_params structure. - - -MEYEIOC_QBUF_CAPT - Queue a buffer for capture (the buffers must have been - obtained with a VIDIOCGMBUF call and mmap'ed by the - application). The argument to MEYEIOC_QBUF_CAPT is the - buffer number to queue (or -1 to end capture). The first - call to MEYEIOC_QBUF_CAPT starts the streaming capture. - -MEYEIOC_SYNC - Takes as an argument the buffer number you want to sync. - This ioctl blocks until the buffer is filled and ready - for the application to use. It returns the buffer size. - -MEYEIOC_STILLCAPT and MEYEIOC_STILLJCAPT - Takes a snapshot in an uncompressed or compressed jpeg format. - This ioctl blocks until the snapshot is done and returns (for - jpeg snapshot) the size of the image. The image data is - available from the first mmap'ed buffer. - -Look at the 'motioneye' application code for an actual example. diff --git a/MAINTAINERS b/MAINTAINERS index f61eb221415b..f814ab594ea4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13071,7 +13071,6 @@ F: include/media/ F: include/uapi/linux/dvb/ F: include/uapi/linux/ivtv* F: include/uapi/linux/media.h -F: include/uapi/linux/meye.h F: include/uapi/linux/uvcvideo.h F: include/uapi/linux/v4l2-* F: include/uapi/linux/videodev2.h @@ -14150,13 +14149,6 @@ F: drivers/regulator/mpq7920.c F: drivers/regulator/mpq7920.h F: include/linux/mfd/mp2629.h -MOTION EYE VAIO PICTUREBOOK CAMERA DRIVER -S: Orphan -W: http://popies.net/meye/ -F: Documentation/userspace-api/media/drivers/meye* -F: drivers/staging/media/deprecated/meye/ -F: include/uapi/linux/meye.h - MOTORCOMM PHY DRIVER M: Peter Geis M: Frank diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig index b79f93684c4f..c312fe741a30 100644 --- a/drivers/staging/media/Kconfig +++ b/drivers/staging/media/Kconfig @@ -54,7 +54,6 @@ if STAGING_MEDIA_DEPRECATED source "drivers/staging/media/deprecated/atmel/Kconfig" source "drivers/staging/media/deprecated/cpia2/Kconfig" source "drivers/staging/media/deprecated/fsl-viu/Kconfig" -source "drivers/staging/media/deprecated/meye/Kconfig" source "drivers/staging/media/deprecated/saa7146/Kconfig" source "drivers/staging/media/deprecated/stkwebcam/Kconfig" source "drivers/staging/media/deprecated/tm6000/Kconfig" diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile index 54bbdd4b0d08..f61ab43625b3 100644 --- a/drivers/staging/media/Makefile +++ b/drivers/staging/media/Makefile @@ -5,7 +5,6 @@ obj-$(CONFIG_VIDEO_CPIA2) += deprecated/cpia2/ obj-$(CONFIG_VIDEO_IMX_MEDIA) += imx/ obj-$(CONFIG_VIDEO_MAX96712) += max96712/ obj-$(CONFIG_VIDEO_MESON_VDEC) += meson/vdec/ -obj-$(CONFIG_VIDEO_MEYE) += deprecated/meye/ obj-$(CONFIG_VIDEO_OMAP4) += omap4iss/ obj-$(CONFIG_VIDEO_ROCKCHIP_VDEC) += rkvdec/ obj-$(CONFIG_VIDEO_STKWEBCAM) += deprecated/stkwebcam/ diff --git a/drivers/staging/media/deprecated/meye/Kconfig b/drivers/staging/media/deprecated/meye/Kconfig deleted file mode 100644 index f135f8568c85..000000000000 --- a/drivers/staging/media/deprecated/meye/Kconfig +++ /dev/null @@ -1,19 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -config VIDEO_MEYE - tristate "Sony Vaio Picturebook Motion Eye Video For Linux (DEPRECATED)" - depends on PCI && VIDEO_DEV - depends on SONY_LAPTOP - depends on X86 || COMPILE_TEST - help - This is the video4linux driver for the Motion Eye camera found - in the Vaio Picturebook laptops. Please read the material in - for more information. - - If you say Y or M here, you need to say Y or M to "Sony Laptop - Extras" in the misc device section. - - This driver is deprecated and is scheduled for removal by - the beginning of 2023. See the TODO file for more information. - - To compile this driver as a module, choose M here: the - module will be called meye. diff --git a/drivers/staging/media/deprecated/meye/Makefile b/drivers/staging/media/deprecated/meye/Makefile deleted file mode 100644 index 36f1f86f0d58..000000000000 --- a/drivers/staging/media/deprecated/meye/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_VIDEO_MEYE) += meye.o diff --git a/drivers/staging/media/deprecated/meye/TODO b/drivers/staging/media/deprecated/meye/TODO deleted file mode 100644 index 6d1d1433d5a0..000000000000 --- a/drivers/staging/media/deprecated/meye/TODO +++ /dev/null @@ -1,6 +0,0 @@ -The meye driver does not use the vb2 framework for streaming -video, instead it implements this in the driver. - -To prevent removal of this driver early 2023 it has to be -converted to use vb2. Contact the linux-media@vger.kernel.org -mailing list if you want to do this. diff --git a/drivers/staging/media/deprecated/meye/meye.c b/drivers/staging/media/deprecated/meye/meye.c deleted file mode 100644 index 5d87efd9b95c..000000000000 --- a/drivers/staging/media/deprecated/meye/meye.c +++ /dev/null @@ -1,1814 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Motion Eye video4linux driver for Sony Vaio PictureBook - * - * Copyright (C) 2001-2004 Stelian Pop - * - * Copyright (C) 2001-2002 Alcôve - * - * Copyright (C) 2000 Andrew Tridgell - * - * Earlier work by Werner Almesberger, Paul `Rusty' Russell and Paul Mackerras. - * - * Some parts borrowed from various video4linux drivers, especially - * bttv-driver.c and zoran.c, see original files for credits. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "meye.h" -#include - -MODULE_AUTHOR("Stelian Pop "); -MODULE_DESCRIPTION("v4l2 driver for the MotionEye camera"); -MODULE_LICENSE("GPL"); -MODULE_VERSION(MEYE_DRIVER_VERSION); - -/* number of grab buffers */ -static unsigned int gbuffers = 2; -module_param(gbuffers, int, 0444); -MODULE_PARM_DESC(gbuffers, "number of capture buffers, default is 2 (32 max)"); - -/* size of a grab buffer */ -static unsigned int gbufsize = MEYE_MAX_BUFSIZE; -module_param(gbufsize, int, 0444); -MODULE_PARM_DESC(gbufsize, "size of the capture buffers, default is 614400 (will be rounded up to a page multiple)"); - -/* /dev/videoX registration number */ -static int video_nr = -1; -module_param(video_nr, int, 0444); -MODULE_PARM_DESC(video_nr, "video device to register (0=/dev/video0, etc)"); - -/* driver structure - only one possible */ -static struct meye meye; - -/****************************************************************************/ -/* Memory allocation routines (stolen from bttv-driver.c) */ -/****************************************************************************/ -static void *rvmalloc(unsigned long size) -{ - void *mem; - unsigned long adr; - - size = PAGE_ALIGN(size); - mem = vmalloc_32(size); - if (mem) { - memset(mem, 0, size); - adr = (unsigned long) mem; - while (size > 0) { - SetPageReserved(vmalloc_to_page((void *)adr)); - adr += PAGE_SIZE; - size -= PAGE_SIZE; - } - } - return mem; -} - -static void rvfree(void * mem, unsigned long size) -{ - unsigned long adr; - - if (mem) { - adr = (unsigned long) mem; - while ((long) size > 0) { - ClearPageReserved(vmalloc_to_page((void *)adr)); - adr += PAGE_SIZE; - size -= PAGE_SIZE; - } - vfree(mem); - } -} - -/* - * return a page table pointing to N pages of locked memory - * - * NOTE: The meye device expects DMA addresses on 32 bits, we build - * a table of 1024 entries = 4 bytes * 1024 = 4096 bytes. - */ -static int ptable_alloc(void) -{ - u32 *pt; - int i; - - memset(meye.mchip_ptable, 0, sizeof(meye.mchip_ptable)); - - /* give only 32 bit DMA addresses */ - if (dma_set_mask(&meye.mchip_dev->dev, DMA_BIT_MASK(32))) - return -1; - - meye.mchip_ptable_toc = dma_alloc_coherent(&meye.mchip_dev->dev, - PAGE_SIZE, - &meye.mchip_dmahandle, - GFP_KERNEL); - if (!meye.mchip_ptable_toc) { - meye.mchip_dmahandle = 0; - return -1; - } - - pt = meye.mchip_ptable_toc; - for (i = 0; i < MCHIP_NB_PAGES; i++) { - dma_addr_t dma; - meye.mchip_ptable[i] = dma_alloc_coherent(&meye.mchip_dev->dev, - PAGE_SIZE, - &dma, - GFP_KERNEL); - if (!meye.mchip_ptable[i]) { - int j; - pt = meye.mchip_ptable_toc; - for (j = 0; j < i; ++j) { - dma = (dma_addr_t) *pt; - dma_free_coherent(&meye.mchip_dev->dev, - PAGE_SIZE, - meye.mchip_ptable[j], dma); - pt++; - } - dma_free_coherent(&meye.mchip_dev->dev, - PAGE_SIZE, - meye.mchip_ptable_toc, - meye.mchip_dmahandle); - meye.mchip_ptable_toc = NULL; - meye.mchip_dmahandle = 0; - return -1; - } - *pt = (u32) dma; - pt++; - } - return 0; -} - -static void ptable_free(void) -{ - u32 *pt; - int i; - - pt = meye.mchip_ptable_toc; - for (i = 0; i < MCHIP_NB_PAGES; i++) { - dma_addr_t dma = (dma_addr_t) *pt; - if (meye.mchip_ptable[i]) - dma_free_coherent(&meye.mchip_dev->dev, - PAGE_SIZE, - meye.mchip_ptable[i], dma); - pt++; - } - - if (meye.mchip_ptable_toc) - dma_free_coherent(&meye.mchip_dev->dev, - PAGE_SIZE, - meye.mchip_ptable_toc, - meye.mchip_dmahandle); - - memset(meye.mchip_ptable, 0, sizeof(meye.mchip_ptable)); - meye.mchip_ptable_toc = NULL; - meye.mchip_dmahandle = 0; -} - -/* copy data from ptable into buf */ -static void ptable_copy(u8 *buf, int start, int size, int pt_pages) -{ - int i; - - for (i = 0; i < (size / PAGE_SIZE) * PAGE_SIZE; i += PAGE_SIZE) { - memcpy(buf + i, meye.mchip_ptable[start++], PAGE_SIZE); - if (start >= pt_pages) - start = 0; - } - memcpy(buf + i, meye.mchip_ptable[start], size % PAGE_SIZE); -} - -/****************************************************************************/ -/* JPEG tables at different qualities to load into the VRJ chip */ -/****************************************************************************/ - -/* return a set of quantisation tables based on a quality from 1 to 10 */ -static u16 *jpeg_quantisation_tables(int *length, int quality) -{ - static u16 jpeg_tables[][70] = { { - 0xdbff, 0x4300, 0xff00, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, - 0xdbff, 0x4300, 0xff01, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, - }, - { - 0xdbff, 0x4300, 0x5000, 0x3c37, 0x3c46, 0x5032, 0x4146, 0x5a46, - 0x5055, 0x785f, 0x82c8, 0x6e78, 0x786e, 0xaff5, 0x91b9, 0xffc8, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, - 0xdbff, 0x4300, 0x5501, 0x5a5a, 0x6978, 0xeb78, 0x8282, 0xffeb, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, - 0xffff, 0xffff, 0xffff, - }, - { - 0xdbff, 0x4300, 0x2800, 0x1e1c, 0x1e23, 0x2819, 0x2123, 0x2d23, - 0x282b, 0x3c30, 0x4164, 0x373c, 0x3c37, 0x587b, 0x495d, 0x9164, - 0x9980, 0x8f96, 0x8c80, 0xa08a, 0xe6b4, 0xa0c3, 0xdaaa, 0x8aad, - 0xc88c, 0xcbff, 0xeeda, 0xfff5, 0xffff, 0xc19b, 0xffff, 0xfaff, - 0xe6ff, 0xfffd, 0xfff8, - 0xdbff, 0x4300, 0x2b01, 0x2d2d, 0x353c, 0x763c, 0x4141, 0xf876, - 0x8ca5, 0xf8a5, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, - 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, - 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, 0xf8f8, - 0xf8f8, 0xf8f8, 0xfff8, - }, - { - 0xdbff, 0x4300, 0x1b00, 0x1412, 0x1417, 0x1b11, 0x1617, 0x1e17, - 0x1b1c, 0x2820, 0x2b42, 0x2528, 0x2825, 0x3a51, 0x303d, 0x6042, - 0x6555, 0x5f64, 0x5d55, 0x6a5b, 0x9978, 0x6a81, 0x9071, 0x5b73, - 0x855d, 0x86b5, 0x9e90, 0xaba3, 0xabad, 0x8067, 0xc9bc, 0xa6ba, - 0x99c7, 0xaba8, 0xffa4, - 0xdbff, 0x4300, 0x1c01, 0x1e1e, 0x2328, 0x4e28, 0x2b2b, 0xa44e, - 0x5d6e, 0xa46e, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, - 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, - 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, 0xa4a4, - 0xa4a4, 0xa4a4, 0xffa4, - }, - { - 0xdbff, 0x4300, 0x1400, 0x0f0e, 0x0f12, 0x140d, 0x1012, 0x1712, - 0x1415, 0x1e18, 0x2132, 0x1c1e, 0x1e1c, 0x2c3d, 0x242e, 0x4932, - 0x4c40, 0x474b, 0x4640, 0x5045, 0x735a, 0x5062, 0x6d55, 0x4556, - 0x6446, 0x6588, 0x776d, 0x817b, 0x8182, 0x604e, 0x978d, 0x7d8c, - 0x7396, 0x817e, 0xff7c, - 0xdbff, 0x4300, 0x1501, 0x1717, 0x1a1e, 0x3b1e, 0x2121, 0x7c3b, - 0x4653, 0x7c53, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, - 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, - 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, 0x7c7c, - 0x7c7c, 0x7c7c, 0xff7c, - }, - { - 0xdbff, 0x4300, 0x1000, 0x0c0b, 0x0c0e, 0x100a, 0x0d0e, 0x120e, - 0x1011, 0x1813, 0x1a28, 0x1618, 0x1816, 0x2331, 0x1d25, 0x3a28, - 0x3d33, 0x393c, 0x3833, 0x4037, 0x5c48, 0x404e, 0x5744, 0x3745, - 0x5038, 0x516d, 0x5f57, 0x6762, 0x6768, 0x4d3e, 0x7971, 0x6470, - 0x5c78, 0x6765, 0xff63, - 0xdbff, 0x4300, 0x1101, 0x1212, 0x1518, 0x2f18, 0x1a1a, 0x632f, - 0x3842, 0x6342, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, - 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, - 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, 0x6363, - 0x6363, 0x6363, 0xff63, - }, - { - 0xdbff, 0x4300, 0x0d00, 0x0a09, 0x0a0b, 0x0d08, 0x0a0b, 0x0e0b, - 0x0d0e, 0x130f, 0x1520, 0x1213, 0x1312, 0x1c27, 0x171e, 0x2e20, - 0x3129, 0x2e30, 0x2d29, 0x332c, 0x4a3a, 0x333e, 0x4636, 0x2c37, - 0x402d, 0x4157, 0x4c46, 0x524e, 0x5253, 0x3e32, 0x615a, 0x505a, - 0x4a60, 0x5251, 0xff4f, - 0xdbff, 0x4300, 0x0e01, 0x0e0e, 0x1113, 0x2613, 0x1515, 0x4f26, - 0x2d35, 0x4f35, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, - 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, - 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, 0x4f4f, - 0x4f4f, 0x4f4f, 0xff4f, - }, - { - 0xdbff, 0x4300, 0x0a00, 0x0707, 0x0708, 0x0a06, 0x0808, 0x0b08, - 0x0a0a, 0x0e0b, 0x1018, 0x0d0e, 0x0e0d, 0x151d, 0x1116, 0x2318, - 0x251f, 0x2224, 0x221f, 0x2621, 0x372b, 0x262f, 0x3429, 0x2129, - 0x3022, 0x3141, 0x3934, 0x3e3b, 0x3e3e, 0x2e25, 0x4944, 0x3c43, - 0x3748, 0x3e3d, 0xff3b, - 0xdbff, 0x4300, 0x0a01, 0x0b0b, 0x0d0e, 0x1c0e, 0x1010, 0x3b1c, - 0x2228, 0x3b28, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, - 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, - 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, 0x3b3b, - 0x3b3b, 0x3b3b, 0xff3b, - }, - { - 0xdbff, 0x4300, 0x0600, 0x0504, 0x0506, 0x0604, 0x0506, 0x0706, - 0x0607, 0x0a08, 0x0a10, 0x090a, 0x0a09, 0x0e14, 0x0c0f, 0x1710, - 0x1814, 0x1718, 0x1614, 0x1a16, 0x251d, 0x1a1f, 0x231b, 0x161c, - 0x2016, 0x202c, 0x2623, 0x2927, 0x292a, 0x1f19, 0x302d, 0x282d, - 0x2530, 0x2928, 0xff28, - 0xdbff, 0x4300, 0x0701, 0x0707, 0x080a, 0x130a, 0x0a0a, 0x2813, - 0x161a, 0x281a, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, - 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, - 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, 0x2828, - 0x2828, 0x2828, 0xff28, - }, - { - 0xdbff, 0x4300, 0x0300, 0x0202, 0x0203, 0x0302, 0x0303, 0x0403, - 0x0303, 0x0504, 0x0508, 0x0405, 0x0504, 0x070a, 0x0607, 0x0c08, - 0x0c0a, 0x0b0c, 0x0b0a, 0x0d0b, 0x120e, 0x0d10, 0x110e, 0x0b0e, - 0x100b, 0x1016, 0x1311, 0x1514, 0x1515, 0x0f0c, 0x1817, 0x1416, - 0x1218, 0x1514, 0xff14, - 0xdbff, 0x4300, 0x0301, 0x0404, 0x0405, 0x0905, 0x0505, 0x1409, - 0x0b0d, 0x140d, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, - 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, - 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, 0x1414, - 0x1414, 0x1414, 0xff14, - }, - { - 0xdbff, 0x4300, 0x0100, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0xff01, - 0xdbff, 0x4300, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0101, 0x0101, 0xff01, - } }; - - if (quality < 0 || quality > 10) { - printk(KERN_WARNING - "meye: invalid quality level %d - using 8\n", quality); - quality = 8; - } - - *length = ARRAY_SIZE(jpeg_tables[quality]); - return jpeg_tables[quality]; -} - -/* return a generic set of huffman tables */ -static u16 *jpeg_huffman_tables(int *length) -{ - static u16 tables[] = { - 0xC4FF, 0xB500, 0x0010, 0x0102, 0x0303, 0x0402, 0x0503, 0x0405, - 0x0004, 0x0100, 0x017D, 0x0302, 0x0400, 0x0511, 0x2112, 0x4131, - 0x1306, 0x6151, 0x2207, 0x1471, 0x8132, 0xA191, 0x2308, 0xB142, - 0x15C1, 0xD152, 0x24F0, 0x6233, 0x8272, 0x0A09, 0x1716, 0x1918, - 0x251A, 0x2726, 0x2928, 0x342A, 0x3635, 0x3837, 0x3A39, 0x4443, - 0x4645, 0x4847, 0x4A49, 0x5453, 0x5655, 0x5857, 0x5A59, 0x6463, - 0x6665, 0x6867, 0x6A69, 0x7473, 0x7675, 0x7877, 0x7A79, 0x8483, - 0x8685, 0x8887, 0x8A89, 0x9392, 0x9594, 0x9796, 0x9998, 0xA29A, - 0xA4A3, 0xA6A5, 0xA8A7, 0xAAA9, 0xB3B2, 0xB5B4, 0xB7B6, 0xB9B8, - 0xC2BA, 0xC4C3, 0xC6C5, 0xC8C7, 0xCAC9, 0xD3D2, 0xD5D4, 0xD7D6, - 0xD9D8, 0xE1DA, 0xE3E2, 0xE5E4, 0xE7E6, 0xE9E8, 0xF1EA, 0xF3F2, - 0xF5F4, 0xF7F6, 0xF9F8, 0xFFFA, - 0xC4FF, 0xB500, 0x0011, 0x0102, 0x0402, 0x0304, 0x0704, 0x0405, - 0x0004, 0x0201, 0x0077, 0x0201, 0x1103, 0x0504, 0x3121, 0x1206, - 0x5141, 0x6107, 0x1371, 0x3222, 0x0881, 0x4214, 0xA191, 0xC1B1, - 0x2309, 0x5233, 0x15F0, 0x7262, 0x0AD1, 0x2416, 0xE134, 0xF125, - 0x1817, 0x1A19, 0x2726, 0x2928, 0x352A, 0x3736, 0x3938, 0x433A, - 0x4544, 0x4746, 0x4948, 0x534A, 0x5554, 0x5756, 0x5958, 0x635A, - 0x6564, 0x6766, 0x6968, 0x736A, 0x7574, 0x7776, 0x7978, 0x827A, - 0x8483, 0x8685, 0x8887, 0x8A89, 0x9392, 0x9594, 0x9796, 0x9998, - 0xA29A, 0xA4A3, 0xA6A5, 0xA8A7, 0xAAA9, 0xB3B2, 0xB5B4, 0xB7B6, - 0xB9B8, 0xC2BA, 0xC4C3, 0xC6C5, 0xC8C7, 0xCAC9, 0xD3D2, 0xD5D4, - 0xD7D6, 0xD9D8, 0xE2DA, 0xE4E3, 0xE6E5, 0xE8E7, 0xEAE9, 0xF3F2, - 0xF5F4, 0xF7F6, 0xF9F8, 0xFFFA, - 0xC4FF, 0x1F00, 0x0000, 0x0501, 0x0101, 0x0101, 0x0101, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0201, 0x0403, 0x0605, 0x0807, 0x0A09, - 0xFF0B, - 0xC4FF, 0x1F00, 0x0001, 0x0103, 0x0101, 0x0101, 0x0101, 0x0101, - 0x0000, 0x0000, 0x0000, 0x0201, 0x0403, 0x0605, 0x0807, 0x0A09, - 0xFF0B - }; - - *length = ARRAY_SIZE(tables); - return tables; -} - -/****************************************************************************/ -/* MCHIP low-level functions */ -/****************************************************************************/ - -/* returns the horizontal capture size */ -static inline int mchip_hsize(void) -{ - return meye.params.subsample ? 320 : 640; -} - -/* returns the vertical capture size */ -static inline int mchip_vsize(void) -{ - return meye.params.subsample ? 240 : 480; -} - -/* waits for a register to be available */ -static void mchip_sync(int reg) -{ - u32 status; - int i; - - if (reg == MCHIP_MM_FIFO_DATA) { - for (i = 0; i < MCHIP_REG_TIMEOUT; i++) { - status = readl(meye.mchip_mmregs + - MCHIP_MM_FIFO_STATUS); - if (!(status & MCHIP_MM_FIFO_WAIT)) { - printk(KERN_WARNING "meye: fifo not ready\n"); - return; - } - if (status & MCHIP_MM_FIFO_READY) - return; - udelay(1); - } - } else if (reg > 0x80) { - u32 mask = (reg < 0x100) ? MCHIP_HIC_STATUS_MCC_RDY - : MCHIP_HIC_STATUS_VRJ_RDY; - for (i = 0; i < MCHIP_REG_TIMEOUT; i++) { - status = readl(meye.mchip_mmregs + MCHIP_HIC_STATUS); - if (status & mask) - return; - udelay(1); - } - } else - return; - printk(KERN_WARNING - "meye: mchip_sync() timeout on reg 0x%x status=0x%x\n", - reg, status); -} - -/* sets a value into the register */ -static inline void mchip_set(int reg, u32 v) -{ - mchip_sync(reg); - writel(v, meye.mchip_mmregs + reg); -} - -/* get the register value */ -static inline u32 mchip_read(int reg) -{ - mchip_sync(reg); - return readl(meye.mchip_mmregs + reg); -} - -/* wait for a register to become a particular value */ -static inline int mchip_delay(u32 reg, u32 v) -{ - int n = 10; - while (--n && mchip_read(reg) != v) - udelay(1); - return n; -} - -/* setup subsampling */ -static void mchip_subsample(void) -{ - mchip_set(MCHIP_MCC_R_SAMPLING, meye.params.subsample); - mchip_set(MCHIP_MCC_R_XRANGE, mchip_hsize()); - mchip_set(MCHIP_MCC_R_YRANGE, mchip_vsize()); - mchip_set(MCHIP_MCC_B_XRANGE, mchip_hsize()); - mchip_set(MCHIP_MCC_B_YRANGE, mchip_vsize()); - mchip_delay(MCHIP_HIC_STATUS, MCHIP_HIC_STATUS_IDLE); -} - -/* set the framerate into the mchip */ -static void mchip_set_framerate(void) -{ - mchip_set(MCHIP_HIC_S_RATE, meye.params.framerate); -} - -/* load some huffman and quantisation tables into the VRJ chip ready - for JPEG compression */ -static void mchip_load_tables(void) -{ - int i; - int length; - u16 *tables; - - tables = jpeg_huffman_tables(&length); - for (i = 0; i < length; i++) - writel(tables[i], meye.mchip_mmregs + MCHIP_VRJ_TABLE_DATA); - - tables = jpeg_quantisation_tables(&length, meye.params.quality); - for (i = 0; i < length; i++) - writel(tables[i], meye.mchip_mmregs + MCHIP_VRJ_TABLE_DATA); -} - -/* setup the VRJ parameters in the chip */ -static void mchip_vrj_setup(u8 mode) -{ - mchip_set(MCHIP_VRJ_BUS_MODE, 5); - mchip_set(MCHIP_VRJ_SIGNAL_ACTIVE_LEVEL, 0x1f); - mchip_set(MCHIP_VRJ_PDAT_USE, 1); - mchip_set(MCHIP_VRJ_IRQ_FLAG, 0xa0); - mchip_set(MCHIP_VRJ_MODE_SPECIFY, mode); - mchip_set(MCHIP_VRJ_NUM_LINES, mchip_vsize()); - mchip_set(MCHIP_VRJ_NUM_PIXELS, mchip_hsize()); - mchip_set(MCHIP_VRJ_NUM_COMPONENTS, 0x1b); - mchip_set(MCHIP_VRJ_LIMIT_COMPRESSED_LO, 0xFFFF); - mchip_set(MCHIP_VRJ_LIMIT_COMPRESSED_HI, 0xFFFF); - mchip_set(MCHIP_VRJ_COMP_DATA_FORMAT, 0xC); - mchip_set(MCHIP_VRJ_RESTART_INTERVAL, 0); - mchip_set(MCHIP_VRJ_SOF1, 0x601); - mchip_set(MCHIP_VRJ_SOF2, 0x1502); - mchip_set(MCHIP_VRJ_SOF3, 0x1503); - mchip_set(MCHIP_VRJ_SOF4, 0x1596); - mchip_set(MCHIP_VRJ_SOS, 0x0ed0); - - mchip_load_tables(); -} - -/* sets the DMA parameters into the chip */ -static void mchip_dma_setup(dma_addr_t dma_addr) -{ - int i; - - mchip_set(MCHIP_MM_PT_ADDR, (u32)dma_addr); - for (i = 0; i < 4; i++) - mchip_set(MCHIP_MM_FIR(i), 0); - meye.mchip_fnum = 0; -} - -/* setup for DMA transfers - also zeros the framebuffer */ -static int mchip_dma_alloc(void) -{ - if (!meye.mchip_dmahandle) - if (ptable_alloc()) - return -1; - return 0; -} - -/* frees the DMA buffer */ -static void mchip_dma_free(void) -{ - if (meye.mchip_dmahandle) { - mchip_dma_setup(0); - ptable_free(); - } -} - -/* stop any existing HIC action and wait for any dma to complete then - reset the dma engine */ -static void mchip_hic_stop(void) -{ - int i, j; - - meye.mchip_mode = MCHIP_HIC_MODE_NOOP; - if (!(mchip_read(MCHIP_HIC_STATUS) & MCHIP_HIC_STATUS_BUSY)) - return; - for (i = 0; i < 20; ++i) { - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_STOP); - mchip_delay(MCHIP_HIC_CMD, 0); - for (j = 0; j < 100; ++j) { - if (mchip_delay(MCHIP_HIC_STATUS, - MCHIP_HIC_STATUS_IDLE)) - return; - msleep(1); - } - printk(KERN_ERR "meye: need to reset HIC!\n"); - - mchip_set(MCHIP_HIC_CTL, MCHIP_HIC_CTL_SOFT_RESET); - msleep(250); - } - printk(KERN_ERR "meye: resetting HIC hanged!\n"); -} - -/****************************************************************************/ -/* MCHIP frame processing functions */ -/****************************************************************************/ - -/* get the next ready frame from the dma engine */ -static u32 mchip_get_frame(void) -{ - return mchip_read(MCHIP_MM_FIR(meye.mchip_fnum)); -} - -/* frees the current frame from the dma engine */ -static void mchip_free_frame(void) -{ - mchip_set(MCHIP_MM_FIR(meye.mchip_fnum), 0); - meye.mchip_fnum++; - meye.mchip_fnum %= 4; -} - -/* read one frame from the framebuffer assuming it was captured using - a uncompressed transfer */ -static void mchip_cont_read_frame(u32 v, u8 *buf, int size) -{ - int pt_id; - - pt_id = (v >> 17) & 0x3FF; - - ptable_copy(buf, pt_id, size, MCHIP_NB_PAGES); -} - -/* read a compressed frame from the framebuffer */ -static int mchip_comp_read_frame(u32 v, u8 *buf, int size) -{ - int pt_start, pt_end, trailer; - int fsize; - int i; - - pt_start = (v >> 19) & 0xFF; - pt_end = (v >> 11) & 0xFF; - trailer = (v >> 1) & 0x3FF; - - if (pt_end < pt_start) - fsize = (MCHIP_NB_PAGES_MJPEG - pt_start) * PAGE_SIZE + - pt_end * PAGE_SIZE + trailer * 4; - else - fsize = (pt_end - pt_start) * PAGE_SIZE + trailer * 4; - - if (fsize > size) { - printk(KERN_WARNING "meye: oversized compressed frame %d\n", - fsize); - return -1; - } - - ptable_copy(buf, pt_start, fsize, MCHIP_NB_PAGES_MJPEG); - -#ifdef MEYE_JPEG_CORRECTION - - /* Some mchip generated jpeg frames are incorrect. In most - * (all ?) of those cases, the final EOI (0xff 0xd9) marker - * is not present at the end of the frame. - * - * Since adding the final marker is not enough to restore - * the jpeg integrity, we drop the frame. - */ - - for (i = fsize - 1; i > 0 && buf[i] == 0xff; i--) ; - - if (i < 2 || buf[i - 1] != 0xff || buf[i] != 0xd9) - return -1; - -#endif - - return fsize; -} - -/* take a picture into SDRAM */ -static void mchip_take_picture(void) -{ - int i; - - mchip_hic_stop(); - mchip_subsample(); - mchip_dma_setup(meye.mchip_dmahandle); - - mchip_set(MCHIP_HIC_MODE, MCHIP_HIC_MODE_STILL_CAP); - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_START); - - mchip_delay(MCHIP_HIC_CMD, 0); - - for (i = 0; i < 100; ++i) { - if (mchip_delay(MCHIP_HIC_STATUS, MCHIP_HIC_STATUS_IDLE)) - break; - msleep(1); - } -} - -/* dma a previously taken picture into a buffer */ -static void mchip_get_picture(u8 *buf, int bufsize) -{ - u32 v; - int i; - - mchip_set(MCHIP_HIC_MODE, MCHIP_HIC_MODE_STILL_OUT); - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_START); - - mchip_delay(MCHIP_HIC_CMD, 0); - for (i = 0; i < 100; ++i) { - if (mchip_delay(MCHIP_HIC_STATUS, MCHIP_HIC_STATUS_IDLE)) - break; - msleep(1); - } - for (i = 0; i < 4; ++i) { - v = mchip_get_frame(); - if (v & MCHIP_MM_FIR_RDY) { - mchip_cont_read_frame(v, buf, bufsize); - break; - } - mchip_free_frame(); - } -} - -/* start continuous dma capture */ -static void mchip_continuous_start(void) -{ - mchip_hic_stop(); - mchip_subsample(); - mchip_set_framerate(); - mchip_dma_setup(meye.mchip_dmahandle); - - meye.mchip_mode = MCHIP_HIC_MODE_CONT_OUT; - - mchip_set(MCHIP_HIC_MODE, MCHIP_HIC_MODE_CONT_OUT); - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_START); - - mchip_delay(MCHIP_HIC_CMD, 0); -} - -/* compress one frame into a buffer */ -static int mchip_compress_frame(u8 *buf, int bufsize) -{ - u32 v; - int len = -1, i; - - mchip_vrj_setup(0x3f); - udelay(50); - - mchip_set(MCHIP_HIC_MODE, MCHIP_HIC_MODE_STILL_COMP); - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_START); - - mchip_delay(MCHIP_HIC_CMD, 0); - for (i = 0; i < 100; ++i) { - if (mchip_delay(MCHIP_HIC_STATUS, MCHIP_HIC_STATUS_IDLE)) - break; - msleep(1); - } - - for (i = 0; i < 4; ++i) { - v = mchip_get_frame(); - if (v & MCHIP_MM_FIR_RDY) { - len = mchip_comp_read_frame(v, buf, bufsize); - break; - } - mchip_free_frame(); - } - return len; -} - -#if 0 -/* uncompress one image into a buffer */ -static int mchip_uncompress_frame(u8 *img, int imgsize, u8 *buf, int bufsize) -{ - mchip_vrj_setup(0x3f); - udelay(50); - - mchip_set(MCHIP_HIC_MODE, MCHIP_HIC_MODE_STILL_DECOMP); - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_START); - - mchip_delay(MCHIP_HIC_CMD, 0); - - return mchip_comp_read_frame(buf, bufsize); -} -#endif - -/* start continuous compressed capture */ -static void mchip_cont_compression_start(void) -{ - mchip_hic_stop(); - mchip_vrj_setup(0x3f); - mchip_subsample(); - mchip_set_framerate(); - mchip_dma_setup(meye.mchip_dmahandle); - - meye.mchip_mode = MCHIP_HIC_MODE_CONT_COMP; - - mchip_set(MCHIP_HIC_MODE, MCHIP_HIC_MODE_CONT_COMP); - mchip_set(MCHIP_HIC_CMD, MCHIP_HIC_CMD_START); - - mchip_delay(MCHIP_HIC_CMD, 0); -} - -/****************************************************************************/ -/* Interrupt handling */ -/****************************************************************************/ - -static irqreturn_t meye_irq(int irq, void *dev_id) -{ - u32 v; - int reqnr; - static int sequence; - - v = mchip_read(MCHIP_MM_INTA); - - if (meye.mchip_mode != MCHIP_HIC_MODE_CONT_OUT && - meye.mchip_mode != MCHIP_HIC_MODE_CONT_COMP) - return IRQ_NONE; - -again: - v = mchip_get_frame(); - if (!(v & MCHIP_MM_FIR_RDY)) - return IRQ_HANDLED; - - if (meye.mchip_mode == MCHIP_HIC_MODE_CONT_OUT) { - if (kfifo_out_locked(&meye.grabq, (unsigned char *)&reqnr, - sizeof(int), &meye.grabq_lock) != sizeof(int)) { - mchip_free_frame(); - return IRQ_HANDLED; - } - mchip_cont_read_frame(v, meye.grab_fbuffer + gbufsize * reqnr, - mchip_hsize() * mchip_vsize() * 2); - meye.grab_buffer[reqnr].size = mchip_hsize() * mchip_vsize() * 2; - meye.grab_buffer[reqnr].state = MEYE_BUF_DONE; - meye.grab_buffer[reqnr].ts = ktime_get_ns(); - meye.grab_buffer[reqnr].sequence = sequence++; - kfifo_in_locked(&meye.doneq, (unsigned char *)&reqnr, - sizeof(int), &meye.doneq_lock); - wake_up_interruptible(&meye.proc_list); - } else { - int size; - size = mchip_comp_read_frame(v, meye.grab_temp, gbufsize); - if (size == -1) { - mchip_free_frame(); - goto again; - } - if (kfifo_out_locked(&meye.grabq, (unsigned char *)&reqnr, - sizeof(int), &meye.grabq_lock) != sizeof(int)) { - mchip_free_frame(); - goto again; - } - memcpy(meye.grab_fbuffer + gbufsize * reqnr, meye.grab_temp, - size); - meye.grab_buffer[reqnr].size = size; - meye.grab_buffer[reqnr].state = MEYE_BUF_DONE; - meye.grab_buffer[reqnr].ts = ktime_get_ns(); - meye.grab_buffer[reqnr].sequence = sequence++; - kfifo_in_locked(&meye.doneq, (unsigned char *)&reqnr, - sizeof(int), &meye.doneq_lock); - wake_up_interruptible(&meye.proc_list); - } - mchip_free_frame(); - goto again; -} - -/****************************************************************************/ -/* video4linux integration */ -/****************************************************************************/ - -static int meye_open(struct file *file) -{ - int i; - - if (test_and_set_bit(0, &meye.in_use)) - return -EBUSY; - - mchip_hic_stop(); - - if (mchip_dma_alloc()) { - printk(KERN_ERR "meye: mchip framebuffer allocation failed\n"); - clear_bit(0, &meye.in_use); - return -ENOBUFS; - } - - for (i = 0; i < MEYE_MAX_BUFNBRS; i++) - meye.grab_buffer[i].state = MEYE_BUF_UNUSED; - kfifo_reset(&meye.grabq); - kfifo_reset(&meye.doneq); - return v4l2_fh_open(file); -} - -static int meye_release(struct file *file) -{ - mchip_hic_stop(); - mchip_dma_free(); - clear_bit(0, &meye.in_use); - return v4l2_fh_release(file); -} - -static int meyeioc_g_params(struct meye_params *p) -{ - *p = meye.params; - return 0; -} - -static int meyeioc_s_params(struct meye_params *jp) -{ - if (jp->subsample > 1) - return -EINVAL; - - if (jp->quality > 10) - return -EINVAL; - - if (jp->sharpness > 63 || jp->agc > 63 || jp->picture > 63) - return -EINVAL; - - if (jp->framerate > 31) - return -EINVAL; - - mutex_lock(&meye.lock); - - if (meye.params.subsample != jp->subsample || - meye.params.quality != jp->quality) - mchip_hic_stop(); /* need restart */ - - meye.params = *jp; - sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERASHARPNESS, - meye.params.sharpness); - sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERAAGC, - meye.params.agc); - sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERAPICTURE, - meye.params.picture); - mutex_unlock(&meye.lock); - - return 0; -} - -static int meyeioc_qbuf_capt(int *nb) -{ - if (!meye.grab_fbuffer) - return -EINVAL; - - if (*nb >= gbuffers) - return -EINVAL; - - if (*nb < 0) { - /* stop capture */ - mchip_hic_stop(); - return 0; - } - - if (meye.grab_buffer[*nb].state != MEYE_BUF_UNUSED) - return -EBUSY; - - mutex_lock(&meye.lock); - - if (meye.mchip_mode != MCHIP_HIC_MODE_CONT_COMP) - mchip_cont_compression_start(); - - meye.grab_buffer[*nb].state = MEYE_BUF_USING; - kfifo_in_locked(&meye.grabq, (unsigned char *)nb, sizeof(int), - &meye.grabq_lock); - mutex_unlock(&meye.lock); - - return 0; -} - -static int meyeioc_sync(struct file *file, void *fh, int *i) -{ - int unused; - - if (*i < 0 || *i >= gbuffers) - return -EINVAL; - - mutex_lock(&meye.lock); - switch (meye.grab_buffer[*i].state) { - - case MEYE_BUF_UNUSED: - mutex_unlock(&meye.lock); - return -EINVAL; - case MEYE_BUF_USING: - if (file->f_flags & O_NONBLOCK) { - mutex_unlock(&meye.lock); - return -EAGAIN; - } - if (wait_event_interruptible(meye.proc_list, - (meye.grab_buffer[*i].state != MEYE_BUF_USING))) { - mutex_unlock(&meye.lock); - return -EINTR; - } - fallthrough; - case MEYE_BUF_DONE: - meye.grab_buffer[*i].state = MEYE_BUF_UNUSED; - if (kfifo_out_locked(&meye.doneq, (unsigned char *)&unused, - sizeof(int), &meye.doneq_lock) != sizeof(int)) - break; - } - *i = meye.grab_buffer[*i].size; - mutex_unlock(&meye.lock); - return 0; -} - -static int meyeioc_stillcapt(void) -{ - if (!meye.grab_fbuffer) - return -EINVAL; - - if (meye.grab_buffer[0].state != MEYE_BUF_UNUSED) - return -EBUSY; - - mutex_lock(&meye.lock); - meye.grab_buffer[0].state = MEYE_BUF_USING; - mchip_take_picture(); - - mchip_get_picture(meye.grab_fbuffer, - mchip_hsize() * mchip_vsize() * 2); - - meye.grab_buffer[0].state = MEYE_BUF_DONE; - mutex_unlock(&meye.lock); - - return 0; -} - -static int meyeioc_stilljcapt(int *len) -{ - if (!meye.grab_fbuffer) - return -EINVAL; - - if (meye.grab_buffer[0].state != MEYE_BUF_UNUSED) - return -EBUSY; - - mutex_lock(&meye.lock); - meye.grab_buffer[0].state = MEYE_BUF_USING; - *len = -1; - - while (*len == -1) { - mchip_take_picture(); - *len = mchip_compress_frame(meye.grab_fbuffer, gbufsize); - } - - meye.grab_buffer[0].state = MEYE_BUF_DONE; - mutex_unlock(&meye.lock); - return 0; -} - -static int vidioc_querycap(struct file *file, void *fh, - struct v4l2_capability *cap) -{ - strscpy(cap->driver, "meye", sizeof(cap->driver)); - strscpy(cap->card, "meye", sizeof(cap->card)); - return 0; -} - -static int vidioc_enum_input(struct file *file, void *fh, struct v4l2_input *i) -{ - if (i->index != 0) - return -EINVAL; - - strscpy(i->name, "Camera", sizeof(i->name)); - i->type = V4L2_INPUT_TYPE_CAMERA; - - return 0; -} - -static int vidioc_g_input(struct file *file, void *fh, unsigned int *i) -{ - *i = 0; - return 0; -} - -static int vidioc_s_input(struct file *file, void *fh, unsigned int i) -{ - if (i != 0) - return -EINVAL; - - return 0; -} - -static int meye_s_ctrl(struct v4l2_ctrl *ctrl) -{ - mutex_lock(&meye.lock); - switch (ctrl->id) { - case V4L2_CID_BRIGHTNESS: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERABRIGHTNESS, ctrl->val); - meye.brightness = ctrl->val << 10; - break; - case V4L2_CID_HUE: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERAHUE, ctrl->val); - meye.hue = ctrl->val << 10; - break; - case V4L2_CID_CONTRAST: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERACONTRAST, ctrl->val); - meye.contrast = ctrl->val << 10; - break; - case V4L2_CID_SATURATION: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERACOLOR, ctrl->val); - meye.colour = ctrl->val << 10; - break; - case V4L2_CID_MEYE_AGC: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERAAGC, ctrl->val); - meye.params.agc = ctrl->val; - break; - case V4L2_CID_SHARPNESS: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERASHARPNESS, ctrl->val); - meye.params.sharpness = ctrl->val; - break; - case V4L2_CID_MEYE_PICTURE: - sony_pic_camera_command( - SONY_PIC_COMMAND_SETCAMERAPICTURE, ctrl->val); - meye.params.picture = ctrl->val; - break; - case V4L2_CID_JPEG_COMPRESSION_QUALITY: - meye.params.quality = ctrl->val; - break; - case V4L2_CID_MEYE_FRAMERATE: - meye.params.framerate = ctrl->val; - break; - default: - mutex_unlock(&meye.lock); - return -EINVAL; - } - mutex_unlock(&meye.lock); - - return 0; -} - -static int vidioc_enum_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_fmtdesc *f) -{ - if (f->index > 1) - return -EINVAL; - - if (f->index == 0) { - /* standard YUV 422 capture */ - f->flags = 0; - f->pixelformat = V4L2_PIX_FMT_YUYV; - } else { - /* compressed MJPEG capture */ - f->pixelformat = V4L2_PIX_FMT_MJPEG; - } - - return 0; -} - -static int vidioc_try_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_format *f) -{ - if (f->fmt.pix.pixelformat != V4L2_PIX_FMT_YUYV && - f->fmt.pix.pixelformat != V4L2_PIX_FMT_MJPEG) - return -EINVAL; - - if (f->fmt.pix.field != V4L2_FIELD_ANY && - f->fmt.pix.field != V4L2_FIELD_NONE) - return -EINVAL; - - f->fmt.pix.field = V4L2_FIELD_NONE; - - if (f->fmt.pix.width <= 320) { - f->fmt.pix.width = 320; - f->fmt.pix.height = 240; - } else { - f->fmt.pix.width = 640; - f->fmt.pix.height = 480; - } - - f->fmt.pix.bytesperline = f->fmt.pix.width * 2; - f->fmt.pix.sizeimage = f->fmt.pix.height * - f->fmt.pix.bytesperline; - f->fmt.pix.colorspace = 0; - - return 0; -} - -static int vidioc_g_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_format *f) -{ - switch (meye.mchip_mode) { - case MCHIP_HIC_MODE_CONT_OUT: - default: - f->fmt.pix.pixelformat = V4L2_PIX_FMT_YUYV; - break; - case MCHIP_HIC_MODE_CONT_COMP: - f->fmt.pix.pixelformat = V4L2_PIX_FMT_MJPEG; - break; - } - - f->fmt.pix.field = V4L2_FIELD_NONE; - f->fmt.pix.width = mchip_hsize(); - f->fmt.pix.height = mchip_vsize(); - f->fmt.pix.bytesperline = f->fmt.pix.width * 2; - f->fmt.pix.sizeimage = f->fmt.pix.height * - f->fmt.pix.bytesperline; - - return 0; -} - -static int vidioc_s_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_format *f) -{ - if (f->fmt.pix.pixelformat != V4L2_PIX_FMT_YUYV && - f->fmt.pix.pixelformat != V4L2_PIX_FMT_MJPEG) - return -EINVAL; - - if (f->fmt.pix.field != V4L2_FIELD_ANY && - f->fmt.pix.field != V4L2_FIELD_NONE) - return -EINVAL; - - f->fmt.pix.field = V4L2_FIELD_NONE; - mutex_lock(&meye.lock); - - if (f->fmt.pix.width <= 320) { - f->fmt.pix.width = 320; - f->fmt.pix.height = 240; - meye.params.subsample = 1; - } else { - f->fmt.pix.width = 640; - f->fmt.pix.height = 480; - meye.params.subsample = 0; - } - - switch (f->fmt.pix.pixelformat) { - case V4L2_PIX_FMT_YUYV: - meye.mchip_mode = MCHIP_HIC_MODE_CONT_OUT; - break; - case V4L2_PIX_FMT_MJPEG: - meye.mchip_mode = MCHIP_HIC_MODE_CONT_COMP; - break; - } - - mutex_unlock(&meye.lock); - f->fmt.pix.bytesperline = f->fmt.pix.width * 2; - f->fmt.pix.sizeimage = f->fmt.pix.height * - f->fmt.pix.bytesperline; - f->fmt.pix.colorspace = 0; - - return 0; -} - -static int vidioc_reqbufs(struct file *file, void *fh, - struct v4l2_requestbuffers *req) -{ - int i; - - if (req->memory != V4L2_MEMORY_MMAP) - return -EINVAL; - - if (meye.grab_fbuffer && req->count == gbuffers) { - /* already allocated, no modifications */ - return 0; - } - - mutex_lock(&meye.lock); - if (meye.grab_fbuffer) { - for (i = 0; i < gbuffers; i++) - if (meye.vma_use_count[i]) { - mutex_unlock(&meye.lock); - return -EINVAL; - } - rvfree(meye.grab_fbuffer, gbuffers * gbufsize); - meye.grab_fbuffer = NULL; - } - - gbuffers = max(2, min((int)req->count, MEYE_MAX_BUFNBRS)); - req->count = gbuffers; - meye.grab_fbuffer = rvmalloc(gbuffers * gbufsize); - - if (!meye.grab_fbuffer) { - printk(KERN_ERR "meye: v4l framebuffer allocation failed\n"); - mutex_unlock(&meye.lock); - return -ENOMEM; - } - - for (i = 0; i < gbuffers; i++) - meye.vma_use_count[i] = 0; - - mutex_unlock(&meye.lock); - - return 0; -} - -static int vidioc_querybuf(struct file *file, void *fh, struct v4l2_buffer *buf) -{ - unsigned int index = buf->index; - - if (index >= gbuffers) - return -EINVAL; - - buf->bytesused = meye.grab_buffer[index].size; - buf->flags = V4L2_BUF_FLAG_MAPPED | V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - - if (meye.grab_buffer[index].state == MEYE_BUF_USING) - buf->flags |= V4L2_BUF_FLAG_QUEUED; - - if (meye.grab_buffer[index].state == MEYE_BUF_DONE) - buf->flags |= V4L2_BUF_FLAG_DONE; - - buf->field = V4L2_FIELD_NONE; - v4l2_buffer_set_timestamp(buf, meye.grab_buffer[index].ts); - buf->sequence = meye.grab_buffer[index].sequence; - buf->memory = V4L2_MEMORY_MMAP; - buf->m.offset = index * gbufsize; - buf->length = gbufsize; - - return 0; -} - -static int vidioc_qbuf(struct file *file, void *fh, struct v4l2_buffer *buf) -{ - if (buf->memory != V4L2_MEMORY_MMAP) - return -EINVAL; - - if (buf->index >= gbuffers) - return -EINVAL; - - if (meye.grab_buffer[buf->index].state != MEYE_BUF_UNUSED) - return -EINVAL; - - mutex_lock(&meye.lock); - buf->flags |= V4L2_BUF_FLAG_QUEUED; - buf->flags &= ~V4L2_BUF_FLAG_DONE; - meye.grab_buffer[buf->index].state = MEYE_BUF_USING; - kfifo_in_locked(&meye.grabq, (unsigned char *)&buf->index, - sizeof(int), &meye.grabq_lock); - mutex_unlock(&meye.lock); - - return 0; -} - -static int vidioc_dqbuf(struct file *file, void *fh, struct v4l2_buffer *buf) -{ - int reqnr; - - if (buf->memory != V4L2_MEMORY_MMAP) - return -EINVAL; - - mutex_lock(&meye.lock); - - if (kfifo_len(&meye.doneq) == 0 && file->f_flags & O_NONBLOCK) { - mutex_unlock(&meye.lock); - return -EAGAIN; - } - - if (wait_event_interruptible(meye.proc_list, - kfifo_len(&meye.doneq) != 0) < 0) { - mutex_unlock(&meye.lock); - return -EINTR; - } - - if (!kfifo_out_locked(&meye.doneq, (unsigned char *)&reqnr, - sizeof(int), &meye.doneq_lock)) { - mutex_unlock(&meye.lock); - return -EBUSY; - } - - if (meye.grab_buffer[reqnr].state != MEYE_BUF_DONE) { - mutex_unlock(&meye.lock); - return -EINVAL; - } - - buf->index = reqnr; - buf->bytesused = meye.grab_buffer[reqnr].size; - buf->flags = V4L2_BUF_FLAG_MAPPED | V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - buf->field = V4L2_FIELD_NONE; - v4l2_buffer_set_timestamp(buf, meye.grab_buffer[reqnr].ts); - buf->sequence = meye.grab_buffer[reqnr].sequence; - buf->memory = V4L2_MEMORY_MMAP; - buf->m.offset = reqnr * gbufsize; - buf->length = gbufsize; - meye.grab_buffer[reqnr].state = MEYE_BUF_UNUSED; - mutex_unlock(&meye.lock); - - return 0; -} - -static int vidioc_streamon(struct file *file, void *fh, enum v4l2_buf_type i) -{ - mutex_lock(&meye.lock); - - switch (meye.mchip_mode) { - case MCHIP_HIC_MODE_CONT_OUT: - mchip_continuous_start(); - break; - case MCHIP_HIC_MODE_CONT_COMP: - mchip_cont_compression_start(); - break; - default: - mutex_unlock(&meye.lock); - return -EINVAL; - } - - mutex_unlock(&meye.lock); - - return 0; -} - -static int vidioc_streamoff(struct file *file, void *fh, enum v4l2_buf_type i) -{ - mutex_lock(&meye.lock); - mchip_hic_stop(); - kfifo_reset(&meye.grabq); - kfifo_reset(&meye.doneq); - - for (i = 0; i < MEYE_MAX_BUFNBRS; i++) - meye.grab_buffer[i].state = MEYE_BUF_UNUSED; - - mutex_unlock(&meye.lock); - return 0; -} - -static long vidioc_default(struct file *file, void *fh, bool valid_prio, - unsigned int cmd, void *arg) -{ - switch (cmd) { - case MEYEIOC_G_PARAMS: - return meyeioc_g_params((struct meye_params *) arg); - - case MEYEIOC_S_PARAMS: - return meyeioc_s_params((struct meye_params *) arg); - - case MEYEIOC_QBUF_CAPT: - return meyeioc_qbuf_capt((int *) arg); - - case MEYEIOC_SYNC: - return meyeioc_sync(file, fh, (int *) arg); - - case MEYEIOC_STILLCAPT: - return meyeioc_stillcapt(); - - case MEYEIOC_STILLJCAPT: - return meyeioc_stilljcapt((int *) arg); - - default: - return -ENOTTY; - } - -} - -static __poll_t meye_poll(struct file *file, poll_table *wait) -{ - __poll_t res = v4l2_ctrl_poll(file, wait); - - mutex_lock(&meye.lock); - poll_wait(file, &meye.proc_list, wait); - if (kfifo_len(&meye.doneq)) - res |= EPOLLIN | EPOLLRDNORM; - mutex_unlock(&meye.lock); - return res; -} - -static void meye_vm_open(struct vm_area_struct *vma) -{ - long idx = (long)vma->vm_private_data; - meye.vma_use_count[idx]++; -} - -static void meye_vm_close(struct vm_area_struct *vma) -{ - long idx = (long)vma->vm_private_data; - meye.vma_use_count[idx]--; -} - -static const struct vm_operations_struct meye_vm_ops = { - .open = meye_vm_open, - .close = meye_vm_close, -}; - -static int meye_mmap(struct file *file, struct vm_area_struct *vma) -{ - unsigned long start = vma->vm_start; - unsigned long size = vma->vm_end - vma->vm_start; - unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; - unsigned long page, pos; - - mutex_lock(&meye.lock); - if (size > gbuffers * gbufsize || offset > gbuffers * gbufsize - size) { - mutex_unlock(&meye.lock); - return -EINVAL; - } - if (!meye.grab_fbuffer) { - int i; - - /* lazy allocation */ - meye.grab_fbuffer = rvmalloc(gbuffers*gbufsize); - if (!meye.grab_fbuffer) { - printk(KERN_ERR "meye: v4l framebuffer allocation failed\n"); - mutex_unlock(&meye.lock); - return -ENOMEM; - } - for (i = 0; i < gbuffers; i++) - meye.vma_use_count[i] = 0; - } - pos = (unsigned long)meye.grab_fbuffer + offset; - - while (size > 0) { - page = vmalloc_to_pfn((void *)pos); - if (remap_pfn_range(vma, start, page, PAGE_SIZE, PAGE_SHARED)) { - mutex_unlock(&meye.lock); - return -EAGAIN; - } - start += PAGE_SIZE; - pos += PAGE_SIZE; - if (size > PAGE_SIZE) - size -= PAGE_SIZE; - else - size = 0; - } - - vma->vm_ops = &meye_vm_ops; - vma->vm_flags &= ~VM_IO; /* not I/O memory */ - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; - vma->vm_private_data = (void *) (offset / gbufsize); - meye_vm_open(vma); - - mutex_unlock(&meye.lock); - return 0; -} - -static const struct v4l2_file_operations meye_fops = { - .owner = THIS_MODULE, - .open = meye_open, - .release = meye_release, - .mmap = meye_mmap, - .unlocked_ioctl = video_ioctl2, - .poll = meye_poll, -}; - -static const struct v4l2_ioctl_ops meye_ioctl_ops = { - .vidioc_querycap = vidioc_querycap, - .vidioc_enum_input = vidioc_enum_input, - .vidioc_g_input = vidioc_g_input, - .vidioc_s_input = vidioc_s_input, - .vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap, - .vidioc_try_fmt_vid_cap = vidioc_try_fmt_vid_cap, - .vidioc_g_fmt_vid_cap = vidioc_g_fmt_vid_cap, - .vidioc_s_fmt_vid_cap = vidioc_s_fmt_vid_cap, - .vidioc_reqbufs = vidioc_reqbufs, - .vidioc_querybuf = vidioc_querybuf, - .vidioc_qbuf = vidioc_qbuf, - .vidioc_dqbuf = vidioc_dqbuf, - .vidioc_streamon = vidioc_streamon, - .vidioc_streamoff = vidioc_streamoff, - .vidioc_log_status = v4l2_ctrl_log_status, - .vidioc_subscribe_event = v4l2_ctrl_subscribe_event, - .vidioc_unsubscribe_event = v4l2_event_unsubscribe, - .vidioc_default = vidioc_default, -}; - -static const struct video_device meye_template = { - .name = "meye", - .fops = &meye_fops, - .ioctl_ops = &meye_ioctl_ops, - .release = video_device_release_empty, - .device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING, -}; - -static const struct v4l2_ctrl_ops meye_ctrl_ops = { - .s_ctrl = meye_s_ctrl, -}; - -static int __maybe_unused meye_suspend(struct device *dev) -{ - meye.pm_mchip_mode = meye.mchip_mode; - mchip_hic_stop(); - mchip_set(MCHIP_MM_INTA, 0x0); - return 0; -} - -static int __maybe_unused meye_resume(struct device *dev) -{ - pci_write_config_word(meye.mchip_dev, MCHIP_PCI_SOFTRESET_SET, 1); - - mchip_delay(MCHIP_HIC_CMD, 0); - mchip_delay(MCHIP_HIC_STATUS, MCHIP_HIC_STATUS_IDLE); - msleep(1); - mchip_set(MCHIP_VRJ_SOFT_RESET, 1); - msleep(1); - mchip_set(MCHIP_MM_PCI_MODE, 5); - msleep(1); - mchip_set(MCHIP_MM_INTA, MCHIP_MM_INTA_HIC_1_MASK); - - switch (meye.pm_mchip_mode) { - case MCHIP_HIC_MODE_CONT_OUT: - mchip_continuous_start(); - break; - case MCHIP_HIC_MODE_CONT_COMP: - mchip_cont_compression_start(); - break; - } - return 0; -} - -static int meye_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) -{ - static const struct v4l2_ctrl_config ctrl_agc = { - .id = V4L2_CID_MEYE_AGC, - .type = V4L2_CTRL_TYPE_INTEGER, - .ops = &meye_ctrl_ops, - .name = "AGC", - .max = 63, - .step = 1, - .def = 48, - .flags = V4L2_CTRL_FLAG_SLIDER, - }; - static const struct v4l2_ctrl_config ctrl_picture = { - .id = V4L2_CID_MEYE_PICTURE, - .type = V4L2_CTRL_TYPE_INTEGER, - .ops = &meye_ctrl_ops, - .name = "Picture", - .max = 63, - .step = 1, - }; - static const struct v4l2_ctrl_config ctrl_framerate = { - .id = V4L2_CID_MEYE_FRAMERATE, - .type = V4L2_CTRL_TYPE_INTEGER, - .ops = &meye_ctrl_ops, - .name = "Framerate", - .max = 31, - .step = 1, - }; - struct v4l2_device *v4l2_dev = &meye.v4l2_dev; - int ret = -EBUSY; - unsigned long mchip_adr; - - if (meye.mchip_dev != NULL) { - printk(KERN_ERR "meye: only one device allowed!\n"); - return ret; - } - - ret = v4l2_device_register(&pcidev->dev, v4l2_dev); - if (ret < 0) { - v4l2_err(v4l2_dev, "Could not register v4l2_device\n"); - return ret; - } - ret = -ENOMEM; - meye.mchip_dev = pcidev; - - meye.grab_temp = vmalloc(array_size(PAGE_SIZE, MCHIP_NB_PAGES_MJPEG)); - if (!meye.grab_temp) - goto outvmalloc; - - spin_lock_init(&meye.grabq_lock); - if (kfifo_alloc(&meye.grabq, sizeof(int) * MEYE_MAX_BUFNBRS, - GFP_KERNEL)) - goto outkfifoalloc1; - - spin_lock_init(&meye.doneq_lock); - if (kfifo_alloc(&meye.doneq, sizeof(int) * MEYE_MAX_BUFNBRS, - GFP_KERNEL)) - goto outkfifoalloc2; - - meye.vdev = meye_template; - meye.vdev.v4l2_dev = &meye.v4l2_dev; - - ret = sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERA, 1); - if (ret) { - v4l2_err(v4l2_dev, "meye: unable to power on the camera\n"); - v4l2_err(v4l2_dev, "meye: did you enable the camera in sonypi using the module options ?\n"); - goto outsonypienable; - } - - ret = pci_enable_device(meye.mchip_dev); - if (ret) { - v4l2_err(v4l2_dev, "meye: pci_enable_device failed\n"); - goto outenabledev; - } - - ret = -EIO; - mchip_adr = pci_resource_start(meye.mchip_dev,0); - if (!mchip_adr) { - v4l2_err(v4l2_dev, "meye: mchip has no device base address\n"); - goto outregions; - } - if (!request_mem_region(pci_resource_start(meye.mchip_dev, 0), - pci_resource_len(meye.mchip_dev, 0), - "meye")) { - v4l2_err(v4l2_dev, "meye: request_mem_region failed\n"); - goto outregions; - } - meye.mchip_mmregs = ioremap(mchip_adr, MCHIP_MM_REGS); - if (!meye.mchip_mmregs) { - v4l2_err(v4l2_dev, "meye: ioremap failed\n"); - goto outremap; - } - - meye.mchip_irq = pcidev->irq; - if (request_irq(meye.mchip_irq, meye_irq, - IRQF_SHARED, "meye", meye_irq)) { - v4l2_err(v4l2_dev, "request_irq failed\n"); - goto outreqirq; - } - - pci_write_config_byte(meye.mchip_dev, PCI_CACHE_LINE_SIZE, 8); - pci_write_config_byte(meye.mchip_dev, PCI_LATENCY_TIMER, 64); - - pci_set_master(meye.mchip_dev); - - /* Ask the camera to perform a soft reset. */ - pci_write_config_word(meye.mchip_dev, MCHIP_PCI_SOFTRESET_SET, 1); - - mchip_delay(MCHIP_HIC_CMD, 0); - mchip_delay(MCHIP_HIC_STATUS, MCHIP_HIC_STATUS_IDLE); - - msleep(1); - mchip_set(MCHIP_VRJ_SOFT_RESET, 1); - - msleep(1); - mchip_set(MCHIP_MM_PCI_MODE, 5); - - msleep(1); - mchip_set(MCHIP_MM_INTA, MCHIP_MM_INTA_HIC_1_MASK); - - mutex_init(&meye.lock); - init_waitqueue_head(&meye.proc_list); - - v4l2_ctrl_handler_init(&meye.hdl, 3); - v4l2_ctrl_new_std(&meye.hdl, &meye_ctrl_ops, - V4L2_CID_BRIGHTNESS, 0, 63, 1, 32); - v4l2_ctrl_new_std(&meye.hdl, &meye_ctrl_ops, - V4L2_CID_HUE, 0, 63, 1, 32); - v4l2_ctrl_new_std(&meye.hdl, &meye_ctrl_ops, - V4L2_CID_CONTRAST, 0, 63, 1, 32); - v4l2_ctrl_new_std(&meye.hdl, &meye_ctrl_ops, - V4L2_CID_SATURATION, 0, 63, 1, 32); - v4l2_ctrl_new_custom(&meye.hdl, &ctrl_agc, NULL); - v4l2_ctrl_new_std(&meye.hdl, &meye_ctrl_ops, - V4L2_CID_SHARPNESS, 0, 63, 1, 32); - v4l2_ctrl_new_custom(&meye.hdl, &ctrl_picture, NULL); - v4l2_ctrl_new_std(&meye.hdl, &meye_ctrl_ops, - V4L2_CID_JPEG_COMPRESSION_QUALITY, 0, 10, 1, 8); - v4l2_ctrl_new_custom(&meye.hdl, &ctrl_framerate, NULL); - if (meye.hdl.error) { - v4l2_err(v4l2_dev, "couldn't register controls\n"); - goto outvideoreg; - } - - v4l2_ctrl_handler_setup(&meye.hdl); - meye.vdev.ctrl_handler = &meye.hdl; - - if (video_register_device(&meye.vdev, VFL_TYPE_VIDEO, - video_nr) < 0) { - v4l2_err(v4l2_dev, "video_register_device failed\n"); - goto outvideoreg; - } - - v4l2_info(v4l2_dev, "Motion Eye Camera Driver v%s.\n", - MEYE_DRIVER_VERSION); - v4l2_info(v4l2_dev, "mchip KL5A72002 rev. %d, base %lx, irq %d\n", - meye.mchip_dev->revision, mchip_adr, meye.mchip_irq); - - return 0; - -outvideoreg: - v4l2_ctrl_handler_free(&meye.hdl); - free_irq(meye.mchip_irq, meye_irq); -outreqirq: - iounmap(meye.mchip_mmregs); -outremap: - release_mem_region(pci_resource_start(meye.mchip_dev, 0), - pci_resource_len(meye.mchip_dev, 0)); -outregions: - pci_disable_device(meye.mchip_dev); -outenabledev: - sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERA, 0); -outsonypienable: - kfifo_free(&meye.doneq); -outkfifoalloc2: - kfifo_free(&meye.grabq); -outkfifoalloc1: - vfree(meye.grab_temp); -outvmalloc: - return ret; -} - -static void meye_remove(struct pci_dev *pcidev) -{ - video_unregister_device(&meye.vdev); - - mchip_hic_stop(); - - mchip_dma_free(); - - /* disable interrupts */ - mchip_set(MCHIP_MM_INTA, 0x0); - - free_irq(meye.mchip_irq, meye_irq); - - iounmap(meye.mchip_mmregs); - - release_mem_region(pci_resource_start(meye.mchip_dev, 0), - pci_resource_len(meye.mchip_dev, 0)); - - pci_disable_device(meye.mchip_dev); - - sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERA, 0); - - kfifo_free(&meye.doneq); - kfifo_free(&meye.grabq); - - vfree(meye.grab_temp); - - if (meye.grab_fbuffer) { - rvfree(meye.grab_fbuffer, gbuffers*gbufsize); - meye.grab_fbuffer = NULL; - } - - printk(KERN_INFO "meye: removed\n"); -} - -static const struct pci_device_id meye_pci_tbl[] = { - { PCI_VDEVICE(KAWASAKI, PCI_DEVICE_ID_MCHIP_KL5A72002), 0 }, - { } -}; - -MODULE_DEVICE_TABLE(pci, meye_pci_tbl); - -static SIMPLE_DEV_PM_OPS(meye_pm_ops, meye_suspend, meye_resume); - -static struct pci_driver meye_driver = { - .name = "meye", - .id_table = meye_pci_tbl, - .probe = meye_probe, - .remove = meye_remove, - .driver.pm = &meye_pm_ops, -}; - -static int __init meye_init(void) -{ - gbuffers = max(2, min((int)gbuffers, MEYE_MAX_BUFNBRS)); - if (gbufsize > MEYE_MAX_BUFSIZE) - gbufsize = MEYE_MAX_BUFSIZE; - gbufsize = PAGE_ALIGN(gbufsize); - printk(KERN_INFO "meye: using %d buffers with %dk (%dk total) for capture\n", - gbuffers, - gbufsize / 1024, gbuffers * gbufsize / 1024); - return pci_register_driver(&meye_driver); -} - -static void __exit meye_exit(void) -{ - pci_unregister_driver(&meye_driver); -} - -module_init(meye_init); -module_exit(meye_exit); diff --git a/drivers/staging/media/deprecated/meye/meye.h b/drivers/staging/media/deprecated/meye/meye.h deleted file mode 100644 index 5fa6552cf93d..000000000000 --- a/drivers/staging/media/deprecated/meye/meye.h +++ /dev/null @@ -1,311 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Motion Eye video4linux driver for Sony Vaio PictureBook - * - * Copyright (C) 2001-2004 Stelian Pop - * - * Copyright (C) 2001-2002 Alcôve - * - * Copyright (C) 2000 Andrew Tridgell - * - * Earlier work by Werner Almesberger, Paul `Rusty' Russell and Paul Mackerras. - * - * Some parts borrowed from various video4linux drivers, especially - * bttv-driver.c and zoran.c, see original files for credits. - */ - -#ifndef _MEYE_PRIV_H_ -#define _MEYE_PRIV_H_ - -#define MEYE_DRIVER_MAJORVERSION 1 -#define MEYE_DRIVER_MINORVERSION 14 - -#define MEYE_DRIVER_VERSION __stringify(MEYE_DRIVER_MAJORVERSION) "." \ - __stringify(MEYE_DRIVER_MINORVERSION) - -#include -#include -#include -#include - -/****************************************************************************/ -/* Motion JPEG chip registers */ -/****************************************************************************/ - -/* Motion JPEG chip PCI configuration registers */ -#define MCHIP_PCI_POWER_CSR 0x54 -#define MCHIP_PCI_MCORE_STATUS 0x60 /* see HIC_STATUS */ -#define MCHIP_PCI_HOSTUSEREQ_SET 0x64 -#define MCHIP_PCI_HOSTUSEREQ_CLR 0x68 -#define MCHIP_PCI_LOWPOWER_SET 0x6c -#define MCHIP_PCI_LOWPOWER_CLR 0x70 -#define MCHIP_PCI_SOFTRESET_SET 0x74 - -/* Motion JPEG chip memory mapped registers */ -#define MCHIP_MM_REGS 0x200 /* 512 bytes */ -#define MCHIP_REG_TIMEOUT 1000 /* reg access, ~us */ -#define MCHIP_MCC_VRJ_TIMEOUT 1000 /* MCC & VRJ access */ - -#define MCHIP_MM_PCI_MODE 0x00 /* PCI access mode */ -#define MCHIP_MM_PCI_MODE_RETRY 0x00000001 /* retry mode */ -#define MCHIP_MM_PCI_MODE_MASTER 0x00000002 /* master access */ -#define MCHIP_MM_PCI_MODE_READ_LINE 0x00000004 /* read line */ - -#define MCHIP_MM_INTA 0x04 /* Int status/mask */ -#define MCHIP_MM_INTA_MCC 0x00000001 /* MCC interrupt */ -#define MCHIP_MM_INTA_VRJ 0x00000002 /* VRJ interrupt */ -#define MCHIP_MM_INTA_HIC_1 0x00000004 /* one frame done */ -#define MCHIP_MM_INTA_HIC_1_MASK 0x00000400 /* 1: enable */ -#define MCHIP_MM_INTA_HIC_END 0x00000008 /* all frames done */ -#define MCHIP_MM_INTA_HIC_END_MASK 0x00000800 -#define MCHIP_MM_INTA_JPEG 0x00000010 /* decompress. error */ -#define MCHIP_MM_INTA_JPEG_MASK 0x00001000 -#define MCHIP_MM_INTA_CAPTURE 0x00000020 /* capture end */ -#define MCHIP_MM_INTA_PCI_ERR 0x00000040 /* PCI error */ -#define MCHIP_MM_INTA_PCI_ERR_MASK 0x00004000 - -#define MCHIP_MM_PT_ADDR 0x08 /* page table address*/ - /* n*4kB */ -#define MCHIP_NB_PAGES 1024 /* pages for display */ -#define MCHIP_NB_PAGES_MJPEG 256 /* pages for mjpeg */ - -#define MCHIP_MM_FIR(n) (0x0c+(n)*4) /* Frame info 0-3 */ -#define MCHIP_MM_FIR_RDY 0x00000001 /* frame ready */ -#define MCHIP_MM_FIR_FAILFR_MASK 0xf8000000 /* # of failed frames */ -#define MCHIP_MM_FIR_FAILFR_SHIFT 27 - - /* continuous comp/decomp mode */ -#define MCHIP_MM_FIR_C_ENDL_MASK 0x000007fe /* end DW [10] */ -#define MCHIP_MM_FIR_C_ENDL_SHIFT 1 -#define MCHIP_MM_FIR_C_ENDP_MASK 0x0007f800 /* end page [8] */ -#define MCHIP_MM_FIR_C_ENDP_SHIFT 11 -#define MCHIP_MM_FIR_C_STARTP_MASK 0x07f80000 /* start page [8] */ -#define MCHIP_MM_FIR_C_STARTP_SHIFT 19 - - /* continuous picture output mode */ -#define MCHIP_MM_FIR_O_STARTP_MASK 0x7ffe0000 /* start page [10] */ -#define MCHIP_MM_FIR_O_STARTP_SHIFT 17 - -#define MCHIP_MM_FIFO_DATA 0x1c /* PCI TGT FIFO data */ -#define MCHIP_MM_FIFO_STATUS 0x20 /* PCI TGT FIFO stat */ -#define MCHIP_MM_FIFO_MASK 0x00000003 -#define MCHIP_MM_FIFO_WAIT_OR_READY 0x00000002 /* Bits common to WAIT & READY*/ -#define MCHIP_MM_FIFO_IDLE 0x0 /* HIC idle */ -#define MCHIP_MM_FIFO_IDLE1 0x1 /* idem ??? */ -#define MCHIP_MM_FIFO_WAIT 0x2 /* wait request */ -#define MCHIP_MM_FIFO_READY 0x3 /* data ready */ - -#define MCHIP_HIC_HOST_USEREQ 0x40 /* host uses MCORE */ - -#define MCHIP_HIC_TP_BUSY 0x44 /* taking picture */ - -#define MCHIP_HIC_PIC_SAVED 0x48 /* pic in SDRAM */ - -#define MCHIP_HIC_LOWPOWER 0x4c /* clock stopped */ - -#define MCHIP_HIC_CTL 0x50 /* HIC control */ -#define MCHIP_HIC_CTL_SOFT_RESET 0x00000001 /* MCORE reset */ -#define MCHIP_HIC_CTL_MCORE_RDY 0x00000002 /* MCORE ready */ - -#define MCHIP_HIC_CMD 0x54 /* HIC command */ -#define MCHIP_HIC_CMD_BITS 0x00000003 /* cmd width=[1:0]*/ -#define MCHIP_HIC_CMD_NOOP 0x0 -#define MCHIP_HIC_CMD_START 0x1 -#define MCHIP_HIC_CMD_STOP 0x2 - -#define MCHIP_HIC_MODE 0x58 -#define MCHIP_HIC_MODE_NOOP 0x0 -#define MCHIP_HIC_MODE_STILL_CAP 0x1 /* still pic capt */ -#define MCHIP_HIC_MODE_DISPLAY 0x2 /* display */ -#define MCHIP_HIC_MODE_STILL_COMP 0x3 /* still pic comp. */ -#define MCHIP_HIC_MODE_STILL_DECOMP 0x4 /* still pic decomp. */ -#define MCHIP_HIC_MODE_CONT_COMP 0x5 /* cont capt+comp */ -#define MCHIP_HIC_MODE_CONT_DECOMP 0x6 /* cont decomp+disp */ -#define MCHIP_HIC_MODE_STILL_OUT 0x7 /* still pic output */ -#define MCHIP_HIC_MODE_CONT_OUT 0x8 /* cont output */ - -#define MCHIP_HIC_STATUS 0x5c -#define MCHIP_HIC_STATUS_MCC_RDY 0x00000001 /* MCC reg acc ok */ -#define MCHIP_HIC_STATUS_VRJ_RDY 0x00000002 /* VRJ reg acc ok */ -#define MCHIP_HIC_STATUS_IDLE 0x00000003 -#define MCHIP_HIC_STATUS_CAPDIS 0x00000004 /* cap/disp in prog */ -#define MCHIP_HIC_STATUS_COMPDEC 0x00000008 /* (de)comp in prog */ -#define MCHIP_HIC_STATUS_BUSY 0x00000010 /* HIC busy */ - -#define MCHIP_HIC_S_RATE 0x60 /* MJPEG # frames */ - -#define MCHIP_HIC_PCI_VFMT 0x64 /* video format */ -#define MCHIP_HIC_PCI_VFMT_YVYU 0x00000001 /* 0: V Y' U Y */ - /* 1: Y' V Y U */ - -#define MCHIP_MCC_CMD 0x80 /* MCC commands */ -#define MCHIP_MCC_CMD_INITIAL 0x0 /* idle ? */ -#define MCHIP_MCC_CMD_IIC_START_SET 0x1 -#define MCHIP_MCC_CMD_IIC_END_SET 0x2 -#define MCHIP_MCC_CMD_FM_WRITE 0x3 /* frame memory */ -#define MCHIP_MCC_CMD_FM_READ 0x4 -#define MCHIP_MCC_CMD_FM_STOP 0x5 -#define MCHIP_MCC_CMD_CAPTURE 0x6 -#define MCHIP_MCC_CMD_DISPLAY 0x7 -#define MCHIP_MCC_CMD_END_DISP 0x8 -#define MCHIP_MCC_CMD_STILL_COMP 0x9 -#define MCHIP_MCC_CMD_STILL_DECOMP 0xa -#define MCHIP_MCC_CMD_STILL_OUTPUT 0xb -#define MCHIP_MCC_CMD_CONT_OUTPUT 0xc -#define MCHIP_MCC_CMD_CONT_COMP 0xd -#define MCHIP_MCC_CMD_CONT_DECOMP 0xe -#define MCHIP_MCC_CMD_RESET 0xf /* MCC reset */ - -#define MCHIP_MCC_IIC_WR 0x84 - -#define MCHIP_MCC_MCC_WR 0x88 - -#define MCHIP_MCC_MCC_RD 0x8c - -#define MCHIP_MCC_STATUS 0x90 -#define MCHIP_MCC_STATUS_CAPT 0x00000001 /* capturing */ -#define MCHIP_MCC_STATUS_DISP 0x00000002 /* displaying */ -#define MCHIP_MCC_STATUS_COMP 0x00000004 /* compressing */ -#define MCHIP_MCC_STATUS_DECOMP 0x00000008 /* decompressing */ -#define MCHIP_MCC_STATUS_MCC_WR 0x00000010 /* register ready */ -#define MCHIP_MCC_STATUS_MCC_RD 0x00000020 /* register ready */ -#define MCHIP_MCC_STATUS_IIC_WR 0x00000040 /* register ready */ -#define MCHIP_MCC_STATUS_OUTPUT 0x00000080 /* output in prog */ - -#define MCHIP_MCC_SIG_POLARITY 0x94 -#define MCHIP_MCC_SIG_POL_VS_H 0x00000001 /* VS active-high */ -#define MCHIP_MCC_SIG_POL_HS_H 0x00000002 /* HS active-high */ -#define MCHIP_MCC_SIG_POL_DOE_H 0x00000004 /* DOE active-high */ - -#define MCHIP_MCC_IRQ 0x98 -#define MCHIP_MCC_IRQ_CAPDIS_STRT 0x00000001 /* cap/disp started */ -#define MCHIP_MCC_IRQ_CAPDIS_STRT_MASK 0x00000010 -#define MCHIP_MCC_IRQ_CAPDIS_END 0x00000002 /* cap/disp ended */ -#define MCHIP_MCC_IRQ_CAPDIS_END_MASK 0x00000020 -#define MCHIP_MCC_IRQ_COMPDEC_STRT 0x00000004 /* (de)comp started */ -#define MCHIP_MCC_IRQ_COMPDEC_STRT_MASK 0x00000040 -#define MCHIP_MCC_IRQ_COMPDEC_END 0x00000008 /* (de)comp ended */ -#define MCHIP_MCC_IRQ_COMPDEC_END_MASK 0x00000080 - -#define MCHIP_MCC_HSTART 0x9c /* video in */ -#define MCHIP_MCC_VSTART 0xa0 -#define MCHIP_MCC_HCOUNT 0xa4 -#define MCHIP_MCC_VCOUNT 0xa8 -#define MCHIP_MCC_R_XBASE 0xac /* capt/disp */ -#define MCHIP_MCC_R_YBASE 0xb0 -#define MCHIP_MCC_R_XRANGE 0xb4 -#define MCHIP_MCC_R_YRANGE 0xb8 -#define MCHIP_MCC_B_XBASE 0xbc /* comp/decomp */ -#define MCHIP_MCC_B_YBASE 0xc0 -#define MCHIP_MCC_B_XRANGE 0xc4 -#define MCHIP_MCC_B_YRANGE 0xc8 - -#define MCHIP_MCC_R_SAMPLING 0xcc /* 1: 1:4 */ - -#define MCHIP_VRJ_CMD 0x100 /* VRJ commands */ - -/* VRJ registers (see table 12.2.4) */ -#define MCHIP_VRJ_COMPRESSED_DATA 0x1b0 -#define MCHIP_VRJ_PIXEL_DATA 0x1b8 - -#define MCHIP_VRJ_BUS_MODE 0x100 -#define MCHIP_VRJ_SIGNAL_ACTIVE_LEVEL 0x108 -#define MCHIP_VRJ_PDAT_USE 0x110 -#define MCHIP_VRJ_MODE_SPECIFY 0x118 -#define MCHIP_VRJ_LIMIT_COMPRESSED_LO 0x120 -#define MCHIP_VRJ_LIMIT_COMPRESSED_HI 0x124 -#define MCHIP_VRJ_COMP_DATA_FORMAT 0x128 -#define MCHIP_VRJ_TABLE_DATA 0x140 -#define MCHIP_VRJ_RESTART_INTERVAL 0x148 -#define MCHIP_VRJ_NUM_LINES 0x150 -#define MCHIP_VRJ_NUM_PIXELS 0x158 -#define MCHIP_VRJ_NUM_COMPONENTS 0x160 -#define MCHIP_VRJ_SOF1 0x168 -#define MCHIP_VRJ_SOF2 0x170 -#define MCHIP_VRJ_SOF3 0x178 -#define MCHIP_VRJ_SOF4 0x180 -#define MCHIP_VRJ_SOS 0x188 -#define MCHIP_VRJ_SOFT_RESET 0x190 - -#define MCHIP_VRJ_STATUS 0x1c0 -#define MCHIP_VRJ_STATUS_BUSY 0x00001 -#define MCHIP_VRJ_STATUS_COMP_ACCESS 0x00002 -#define MCHIP_VRJ_STATUS_PIXEL_ACCESS 0x00004 -#define MCHIP_VRJ_STATUS_ERROR 0x00008 - -#define MCHIP_VRJ_IRQ_FLAG 0x1c8 -#define MCHIP_VRJ_ERROR_REPORT 0x1d8 - -#define MCHIP_VRJ_START_COMMAND 0x1a0 - -/****************************************************************************/ -/* Driver definitions. */ -/****************************************************************************/ - -/* Sony Programmable I/O Controller for accessing the camera commands */ -#include - -/* private API definitions */ -#include -#include - - -/* Enable jpg software correction */ -#define MEYE_JPEG_CORRECTION 1 - -/* Maximum size of a buffer */ -#define MEYE_MAX_BUFSIZE 614400 /* 640 * 480 * 2 */ - -/* Maximum number of buffers */ -#define MEYE_MAX_BUFNBRS 32 - -/* State of a buffer */ -#define MEYE_BUF_UNUSED 0 /* not used */ -#define MEYE_BUF_USING 1 /* currently grabbing / playing */ -#define MEYE_BUF_DONE 2 /* done */ - -/* grab buffer */ -struct meye_grab_buffer { - int state; /* state of buffer */ - unsigned long size; /* size of jpg frame */ - u64 ts; /* timestamp */ - unsigned long sequence; /* sequence number */ -}; - -/* size of kfifos containing buffer indices */ -#define MEYE_QUEUE_SIZE MEYE_MAX_BUFNBRS - -/* Motion Eye device structure */ -struct meye { - struct v4l2_device v4l2_dev; /* Main v4l2_device struct */ - struct v4l2_ctrl_handler hdl; - struct pci_dev *mchip_dev; /* pci device */ - u8 mchip_irq; /* irq */ - u8 mchip_mode; /* actual mchip mode: HIC_MODE... */ - u8 mchip_fnum; /* current mchip frame number */ - unsigned char __iomem *mchip_mmregs;/* mchip: memory mapped registers */ - u8 *mchip_ptable[MCHIP_NB_PAGES];/* mchip: ptable */ - void *mchip_ptable_toc; /* mchip: ptable toc */ - dma_addr_t mchip_dmahandle; /* mchip: dma handle to ptable toc */ - unsigned char *grab_fbuffer; /* capture framebuffer */ - unsigned char *grab_temp; /* temporary buffer */ - /* list of buffers */ - struct meye_grab_buffer grab_buffer[MEYE_MAX_BUFNBRS]; - int vma_use_count[MEYE_MAX_BUFNBRS]; /* mmap count */ - struct mutex lock; /* mutex for open/mmap... */ - struct kfifo grabq; /* queue for buffers to be grabbed */ - spinlock_t grabq_lock; /* lock protecting the queue */ - struct kfifo doneq; /* queue for grabbed buffers */ - spinlock_t doneq_lock; /* lock protecting the queue */ - wait_queue_head_t proc_list; /* wait queue */ - struct video_device vdev; /* video device parameters */ - u16 brightness; - u16 hue; - u16 contrast; - u16 colour; - struct meye_params params; /* additional parameters */ - unsigned long in_use; /* set to 1 if the device is in use */ - u8 pm_mchip_mode; /* old mchip mode */ -}; - -#endif diff --git a/include/uapi/linux/meye.h b/include/uapi/linux/meye.h deleted file mode 100644 index de9e3a954f3d..000000000000 --- a/include/uapi/linux/meye.h +++ /dev/null @@ -1,65 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* - * Motion Eye video4linux driver for Sony Vaio PictureBook - * - * Copyright (C) 2001-2003 Stelian Pop - * - * Copyright (C) 2001-2002 Alcôve - * - * Copyright (C) 2000 Andrew Tridgell - * - * Earlier work by Werner Almesberger, Paul `Rusty' Russell and Paul Mackerras. - * - * Some parts borrowed from various video4linux drivers, especially - * bttv-driver.c and zoran.c, see original files for credits. - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef _MEYE_H_ -#define _MEYE_H_ - -/****************************************************************************/ -/* Private API for handling mjpeg capture / playback. */ -/****************************************************************************/ - -struct meye_params { - unsigned char subsample; - unsigned char quality; - unsigned char sharpness; - unsigned char agc; - unsigned char picture; - unsigned char framerate; -}; - -/* query the extended parameters */ -#define MEYEIOC_G_PARAMS _IOR ('v', BASE_VIDIOC_PRIVATE+0, struct meye_params) -/* set the extended parameters */ -#define MEYEIOC_S_PARAMS _IOW ('v', BASE_VIDIOC_PRIVATE+1, struct meye_params) -/* queue a buffer for mjpeg capture */ -#define MEYEIOC_QBUF_CAPT _IOW ('v', BASE_VIDIOC_PRIVATE+2, int) -/* sync a previously queued mjpeg buffer */ -#define MEYEIOC_SYNC _IOWR('v', BASE_VIDIOC_PRIVATE+3, int) -/* get a still uncompressed snapshot */ -#define MEYEIOC_STILLCAPT _IO ('v', BASE_VIDIOC_PRIVATE+4) -/* get a jpeg compressed snapshot */ -#define MEYEIOC_STILLJCAPT _IOR ('v', BASE_VIDIOC_PRIVATE+5, int) - -/* V4L2 private controls */ -#define V4L2_CID_MEYE_AGC (V4L2_CID_USER_MEYE_BASE + 0) -#define V4L2_CID_MEYE_PICTURE (V4L2_CID_USER_MEYE_BASE + 1) -#define V4L2_CID_MEYE_FRAMERATE (V4L2_CID_USER_MEYE_BASE + 2) - -#endif diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index b73a8ba7df6c..5e80daa4ffe0 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -115,9 +115,13 @@ enum v4l2_colorfx { /* USER-class private control IDs */ -/* The base for the meye driver controls. See linux/meye.h for the list - * of controls. We reserve 16 controls for this driver. */ +#ifndef __KERNEL__ +/* + * The base for the meye driver controls. This driver was removed, but + * we keep this define in case any software still uses it. + */ #define V4L2_CID_USER_MEYE_BASE (V4L2_CID_USER_BASE + 0x1000) +#endif /* The base for the bttv driver controls. * We reserve 32 controls for this driver. */ -- cgit v1.2.3 From 2b30f8291a30305eeedcd787b4d0e352410f7268 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 19 Jan 2023 14:26:54 +0200 Subject: net: ethtool: add support for MAC Merge layer The MAC merge sublayer (IEEE 802.3-2018 clause 99) is one of 2 specifications (the other being Frame Preemption; IEEE 802.1Q-2018 clause 6.7.2), which work together to minimize latency caused by frame interference at TX. The overall goal of TSN is for normal traffic and traffic with a bounded deadline to be able to cohabitate on the same L2 network and not bother each other too much. The standards achieve this (partly) by introducing the concept of preemptible traffic, i.e. Ethernet frames that have a custom value for the Start-of-Frame-Delimiter (SFD), and these frames can be fragmented and reassembled at L2 on a link-local basis. The non-preemptible frames are called express traffic, they are transmitted using a normal SFD, and they can preempt preemptible frames, therefore having lower latency, which can matter at lower (100 Mbps) link speeds, or at high MTUs (jumbo frames around 9K). Preemption is not recursive, i.e. a P frame cannot preempt another P frame. Preemption also does not depend upon priority, or otherwise said, an E frame with prio 0 will still preempt a P frame with prio 7. In terms of implementation, the standards talk about the presence of an express MAC (eMAC) which handles express traffic, and a preemptible MAC (pMAC) which handles preemptible traffic, and these MACs are multiplexed on the same MII by a MAC merge layer. To support frame preemption, the definition of the SFD was generalized to SMD (Start-of-mPacket-Delimiter), where an mPacket is essentially an Ethernet frame fragment, or a complete frame. Stations unaware of an SMD value different from the standard SFD will treat P frames as error frames. To prevent that from happening, a negotiation process is defined. On RX, packets are dispatched to the eMAC or pMAC after being filtered by their SMD. On TX, the eMAC/pMAC classification decision is taken by the 802.1Q spec, based on packet priority (each of the 8 user priority values may have an admin-status of preemptible or express). The MAC Merge layer and the Frame Preemption parameters have some degree of independence in terms of how software stacks are supposed to deal with them. The activation of the MM layer is supposed to be controlled by an LLDP daemon (after it has been communicated that the link partner also supports it), after which a (hardware-based or not) verification handshake takes place, before actually enabling the feature. So the process is intended to be relatively plug-and-play. Whereas FP settings are supposed to be coordinated across a network using something approximating NETCONF. The support contained here is exclusively for the 802.3 (MAC Merge) portions and not for the 802.1Q (Frame Preemption) parts. This API is sufficient for an LLDP daemon to do its job. The FP adminStatus variable from 802.1Q is outside the scope of an LLDP daemon. I have taken a few creative licenses and augmented the Linux kernel UAPI compared to the standard managed objects recommended by IEEE 802.3. These are: - ETHTOOL_A_MM_PMAC_ENABLED: According to Figure 99-6: Receive Processing state diagram, a MAC Merge layer is always supposed to be able to receive P frames. However, this implies keeping the pMAC powered on, which will consume needless power in applications where FP will never be used. If LLDP is used, the reception of an Additional Ethernet Capabilities TLV from the link partner is sufficient indication that the pMAC should be enabled. So my proposal is that in Linux, we keep the pMAC turned off by default and that user space turns it on when needed. - ETHTOOL_A_MM_VERIFY_ENABLED: The IEEE managed object is called aMACMergeVerifyDisableTx. I opted for consistency (positive logic) in the boolean netlink attributes offered, so this is also positive here. Other than the meaning being reversed, they correspond to the same thing. - ETHTOOL_A_MM_MAX_VERIFY_TIME: I found it most reasonable for a LLDP daemon to maximize the verifyTime variable (delay between SMD-V transmissions), to maximize its chances that the LP replies. IEEE says that the verifyTime can range between 1 and 128 ms, but the NXP ENETC stupidly keeps this variable in a 7 bit register, so the maximum supported value is 127 ms. I could have chosen to hardcode this in the LLDP daemon to a lower value, but why not let the kernel expose its supported range directly. - ETHTOOL_A_MM_TX_MIN_FRAG_SIZE: the standard managed object is called aMACMergeAddFragSize, and expresses the "additional" fragment size (on top of ETH_ZLEN), whereas this expresses the absolute value of the fragment size. - ETHTOOL_A_MM_RX_MIN_FRAG_SIZE: there doesn't appear to exist a managed object mandated by the standard, but user space clearly needs to know what is the minimum supported fragment size of our local receiver, since LLDP must advertise a value no lower than that. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/ethtool.h | 99 ++++++++++++++ include/uapi/linux/ethtool.h | 25 ++++ include/uapi/linux/ethtool_netlink.h | 47 +++++++ net/ethtool/Makefile | 4 +- net/ethtool/mm.c | 255 +++++++++++++++++++++++++++++++++++ net/ethtool/netlink.c | 19 +++ net/ethtool/netlink.h | 4 + 7 files changed, 451 insertions(+), 2 deletions(-) create mode 100644 net/ethtool/mm.c (limited to 'include/uapi/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 20d197693d34..37eba38da502 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -477,6 +477,98 @@ struct ethtool_module_power_mode_params { enum ethtool_module_power_mode mode; }; +/** + * struct ethtool_mm_state - 802.3 MAC merge layer state + * @verify_time: + * wait time between verification attempts in ms (according to clause + * 30.14.1.6 aMACMergeVerifyTime) + * @max_verify_time: + * maximum accepted value for the @verify_time variable in set requests + * @verify_status: + * state of the verification state machine of the MM layer (according to + * clause 30.14.1.2 aMACMergeStatusVerify) + * @tx_enabled: + * set if the MM layer is administratively enabled in the TX direction + * (according to clause 30.14.1.3 aMACMergeEnableTx) + * @tx_active: + * set if the MM layer is enabled in the TX direction, which makes FP + * possible (according to 30.14.1.5 aMACMergeStatusTx). This should be + * true if MM is enabled, and the verification status is either verified, + * or disabled. + * @pmac_enabled: + * set if the preemptible MAC is powered on and is able to receive + * preemptible packets and respond to verification frames. + * @verify_enabled: + * set if the Verify function of the MM layer (which sends SMD-V + * verification requests) is administratively enabled (regardless of + * whether it is currently in the ETHTOOL_MM_VERIFY_STATUS_DISABLED state + * or not), according to clause 30.14.1.4 aMACMergeVerifyDisableTx (but + * using positive rather than negative logic). The device should always + * respond to received SMD-V requests as long as @pmac_enabled is set. + * @tx_min_frag_size: + * the minimum size of non-final mPacket fragments that the link partner + * supports receiving, expressed in octets. Compared to the definition + * from clause 30.14.1.7 aMACMergeAddFragSize which is expressed in the + * range 0 to 3 (requiring a translation to the size in octets according + * to the formula 64 * (1 + addFragSize) - 4), a value in a continuous and + * unbounded range can be specified here. + * @rx_min_frag_size: + * the minimum size of non-final mPacket fragments that this device + * supports receiving, expressed in octets. + */ +struct ethtool_mm_state { + u32 verify_time; + u32 max_verify_time; + enum ethtool_mm_verify_status verify_status; + bool tx_enabled; + bool tx_active; + bool pmac_enabled; + bool verify_enabled; + u32 tx_min_frag_size; + u32 rx_min_frag_size; +}; + +/** + * struct ethtool_mm_cfg - 802.3 MAC merge layer configuration + * @verify_time: see struct ethtool_mm_state + * @verify_enabled: see struct ethtool_mm_state + * @tx_enabled: see struct ethtool_mm_state + * @pmac_enabled: see struct ethtool_mm_state + * @tx_min_frag_size: see struct ethtool_mm_state + */ +struct ethtool_mm_cfg { + u32 verify_time; + bool verify_enabled; + bool tx_enabled; + bool pmac_enabled; + u32 tx_min_frag_size; +}; + +/** + * struct ethtool_mm_stats - 802.3 MAC merge layer statistics + * @MACMergeFrameAssErrorCount: + * received MAC frames with reassembly errors + * @MACMergeFrameSmdErrorCount: + * received MAC frames/fragments rejected due to unknown or incorrect SMD + * @MACMergeFrameAssOkCount: + * received MAC frames that were successfully reassembled and passed up + * @MACMergeFragCountRx: + * number of additional correct SMD-C mPackets received due to preemption + * @MACMergeFragCountTx: + * number of additional mPackets sent due to preemption + * @MACMergeHoldCount: + * number of times the MM layer entered the HOLD state, which blocks + * transmission of preemptible traffic + */ +struct ethtool_mm_stats { + u64 MACMergeFrameAssErrorCount; + u64 MACMergeFrameSmdErrorCount; + u64 MACMergeFrameAssOkCount; + u64 MACMergeFragCountRx; + u64 MACMergeFragCountTx; + u64 MACMergeHoldCount; +}; + /** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes @@ -649,6 +741,9 @@ struct ethtool_module_power_mode_params { * plugged-in. * @set_module_power_mode: Set the power mode policy for the plug-in module * used by the network device. + * @get_mm: Query the 802.3 MAC Merge layer state. + * @set_mm: Set the 802.3 MAC Merge layer parameters. + * @get_mm_stats: Query the 802.3 MAC Merge layer statistics. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -787,6 +882,10 @@ struct ethtool_ops { int (*set_module_power_mode)(struct net_device *dev, const struct ethtool_module_power_mode_params *params, struct netlink_ext_ack *extack); + int (*get_mm)(struct net_device *dev, struct ethtool_mm_state *state); + int (*set_mm)(struct net_device *dev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack); + void (*get_mm_stats)(struct net_device *dev, struct ethtool_mm_stats *stats); }; int ethtool_check_ops(const struct ethtool_ops *ops); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 6389953c32cf..529a93696ab6 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -779,6 +779,31 @@ enum ethtool_podl_pse_pw_d_status { ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR, }; +/** + * enum ethtool_mm_verify_status - status of MAC Merge Verify function + * @ETHTOOL_MM_VERIFY_STATUS_UNKNOWN: + * verification status is unknown + * @ETHTOOL_MM_VERIFY_STATUS_INITIAL: + * the 802.3 Verify State diagram is in the state INIT_VERIFICATION + * @ETHTOOL_MM_VERIFY_STATUS_VERIFYING: + * the Verify State diagram is in the state VERIFICATION_IDLE, + * SEND_VERIFY or WAIT_FOR_RESPONSE + * @ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED: + * indicates that the Verify State diagram is in the state VERIFIED + * @ETHTOOL_MM_VERIFY_STATUS_FAILED: + * the Verify State diagram is in the state VERIFY_FAIL + * @ETHTOOL_MM_VERIFY_STATUS_DISABLED: + * verification of preemption operation is disabled + */ +enum ethtool_mm_verify_status { + ETHTOOL_MM_VERIFY_STATUS_UNKNOWN, + ETHTOOL_MM_VERIFY_STATUS_INITIAL, + ETHTOOL_MM_VERIFY_STATUS_VERIFYING, + ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED, + ETHTOOL_MM_VERIFY_STATUS_FAILED, + ETHTOOL_MM_VERIFY_STATUS_DISABLED, +}; + /** * 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 83557cae0b87..58af390823b0 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -55,6 +55,8 @@ enum { ETHTOOL_MSG_PLCA_GET_CFG, ETHTOOL_MSG_PLCA_SET_CFG, ETHTOOL_MSG_PLCA_GET_STATUS, + ETHTOOL_MSG_MM_GET, + ETHTOOL_MSG_MM_SET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -105,6 +107,8 @@ enum { ETHTOOL_MSG_PLCA_GET_CFG_REPLY, ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, ETHTOOL_MSG_PLCA_NTF, + ETHTOOL_MSG_MM_GET_REPLY, + ETHTOOL_MSG_MM_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -922,6 +926,49 @@ enum { ETHTOOL_A_PLCA_MAX = (__ETHTOOL_A_PLCA_CNT - 1) }; +/* MAC Merge (802.3) */ + +enum { + ETHTOOL_A_MM_STAT_UNSPEC, + ETHTOOL_A_MM_STAT_PAD, + + /* aMACMergeFrameAssErrorCount */ + ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS, /* u64 */ + /* aMACMergeFrameSmdErrorCount */ + ETHTOOL_A_MM_STAT_SMD_ERRORS, /* u64 */ + /* aMACMergeFrameAssOkCount */ + ETHTOOL_A_MM_STAT_REASSEMBLY_OK, /* u64 */ + /* aMACMergeFragCountRx */ + ETHTOOL_A_MM_STAT_RX_FRAG_COUNT, /* u64 */ + /* aMACMergeFragCountTx */ + ETHTOOL_A_MM_STAT_TX_FRAG_COUNT, /* u64 */ + /* aMACMergeHoldCount */ + ETHTOOL_A_MM_STAT_HOLD_COUNT, /* u64 */ + + /* add new constants above here */ + __ETHTOOL_A_MM_STAT_CNT, + ETHTOOL_A_MM_STAT_MAX = (__ETHTOOL_A_MM_STAT_CNT - 1) +}; + +enum { + ETHTOOL_A_MM_UNSPEC, + ETHTOOL_A_MM_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_MM_PMAC_ENABLED, /* u8 */ + ETHTOOL_A_MM_TX_ENABLED, /* u8 */ + ETHTOOL_A_MM_TX_ACTIVE, /* u8 */ + ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, /* u32 */ + ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, /* u32 */ + ETHTOOL_A_MM_VERIFY_ENABLED, /* u8 */ + ETHTOOL_A_MM_VERIFY_STATUS, /* u8 */ + ETHTOOL_A_MM_VERIFY_TIME, /* u32 */ + ETHTOOL_A_MM_MAX_VERIFY_TIME, /* u32 */ + ETHTOOL_A_MM_STATS, /* nest - _A_MM_STAT_* */ + + /* add new constants above here */ + __ETHTOOL_A_MM_CNT, + ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 563864c1bf5a..504f954a1b28 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,5 +7,5 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ - tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o \ - pse-pd.o plca.o + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ + module.o pse-pd.o plca.o mm.o diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c new file mode 100644 index 000000000000..76b209ad53d2 --- /dev/null +++ b/net/ethtool/mm.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022-2023 NXP + */ +#include "common.h" +#include "netlink.h" + +struct mm_req_info { + struct ethnl_req_info base; +}; + +struct mm_reply_data { + struct ethnl_reply_data base; + struct ethtool_mm_state state; + struct ethtool_mm_stats stats; +}; + +#define MM_REPDATA(__reply_base) \ + container_of(__reply_base, struct mm_reply_data, base) + +#define ETHTOOL_MM_STAT_CNT \ + (__ETHTOOL_A_MM_STAT_CNT - (ETHTOOL_A_MM_STAT_PAD + 1)) + +const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1] = { + [ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), +}; + +static int mm_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct mm_reply_data *data = MM_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops; + int ret; + + ops = dev->ethtool_ops; + + if (!ops->get_mm) + return -EOPNOTSUPP; + + ethtool_stats_init((u64 *)&data->stats, + sizeof(data->stats) / sizeof(u64)); + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = ops->get_mm(dev, &data->state); + if (ret) + goto out_complete; + + if (ops->get_mm_stats && (req_base->flags & ETHTOOL_FLAG_STATS)) + ops->get_mm_stats(dev, &data->stats); + +out_complete: + ethnl_ops_complete(dev); + + return 0; +} + +static int mm_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + int len = 0; + + len += nla_total_size(sizeof(u8)); /* _MM_PMAC_ENABLED */ + len += nla_total_size(sizeof(u8)); /* _MM_TX_ENABLED */ + len += nla_total_size(sizeof(u8)); /* _MM_TX_ACTIVE */ + len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_ENABLED */ + len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_STATUS */ + len += nla_total_size(sizeof(u32)); /* _MM_VERIFY_TIME */ + len += nla_total_size(sizeof(u32)); /* _MM_MAX_VERIFY_TIME */ + len += nla_total_size(sizeof(u32)); /* _MM_TX_MIN_FRAG_SIZE */ + len += nla_total_size(sizeof(u32)); /* _MM_RX_MIN_FRAG_SIZE */ + + if (req_base->flags & ETHTOOL_FLAG_STATS) + len += nla_total_size(0) + /* _MM_STATS */ + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_MM_STAT_CNT; + + return len; +} + +static int mm_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) +{ + if (val == ETHTOOL_STAT_NOT_SET) + return 0; + if (nla_put_u64_64bit(skb, attrtype, val, ETHTOOL_A_MM_STAT_PAD)) + return -EMSGSIZE; + return 0; +} + +static int mm_put_stats(struct sk_buff *skb, + const struct ethtool_mm_stats *stats) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_MM_STATS); + if (!nest) + return -EMSGSIZE; + + if (mm_put_stat(skb, stats->MACMergeFrameAssErrorCount, + ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS) || + mm_put_stat(skb, stats->MACMergeFrameSmdErrorCount, + ETHTOOL_A_MM_STAT_SMD_ERRORS) || + mm_put_stat(skb, stats->MACMergeFrameAssOkCount, + ETHTOOL_A_MM_STAT_REASSEMBLY_OK) || + mm_put_stat(skb, stats->MACMergeFragCountRx, + ETHTOOL_A_MM_STAT_RX_FRAG_COUNT) || + mm_put_stat(skb, stats->MACMergeFragCountTx, + ETHTOOL_A_MM_STAT_TX_FRAG_COUNT) || + mm_put_stat(skb, stats->MACMergeHoldCount, + ETHTOOL_A_MM_STAT_HOLD_COUNT)) + goto err_cancel; + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int mm_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct mm_reply_data *data = MM_REPDATA(reply_base); + const struct ethtool_mm_state *state = &data->state; + + if (nla_put_u8(skb, ETHTOOL_A_MM_TX_ENABLED, state->tx_enabled) || + nla_put_u8(skb, ETHTOOL_A_MM_TX_ACTIVE, state->tx_active) || + nla_put_u8(skb, ETHTOOL_A_MM_PMAC_ENABLED, state->pmac_enabled) || + nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_ENABLED, state->verify_enabled) || + nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_STATUS, state->verify_status) || + nla_put_u32(skb, ETHTOOL_A_MM_VERIFY_TIME, state->verify_time) || + nla_put_u32(skb, ETHTOOL_A_MM_MAX_VERIFY_TIME, state->max_verify_time) || + nla_put_u32(skb, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, state->tx_min_frag_size) || + nla_put_u32(skb, ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, state->rx_min_frag_size)) + return -EMSGSIZE; + + if (req_base->flags & ETHTOOL_FLAG_STATS && + mm_put_stats(skb, &data->stats)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_mm_request_ops = { + .request_cmd = ETHTOOL_MSG_MM_GET, + .reply_cmd = ETHTOOL_MSG_MM_GET_REPLY, + .hdr_attr = ETHTOOL_A_MM_HEADER, + .req_info_size = sizeof(struct mm_req_info), + .reply_data_size = sizeof(struct mm_reply_data), + + .prepare_data = mm_prepare_data, + .reply_size = mm_reply_size, + .fill_reply = mm_fill_reply, +}; + +const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1] = { + [ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_MM_VERIFY_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_MM_VERIFY_TIME] = NLA_POLICY_RANGE(NLA_U32, 1, 128), + [ETHTOOL_A_MM_TX_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_MM_PMAC_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_MM_TX_MIN_FRAG_SIZE] = NLA_POLICY_RANGE(NLA_U32, 60, 252), +}; + +static void mm_state_to_cfg(const struct ethtool_mm_state *state, + struct ethtool_mm_cfg *cfg) +{ + /* We could also compare state->verify_status against + * ETHTOOL_MM_VERIFY_STATUS_DISABLED, but state->verify_enabled + * is more like an administrative state which should be seen in + * ETHTOOL_MSG_MM_GET replies. For example, a port with verification + * disabled might be in the ETHTOOL_MM_VERIFY_STATUS_INITIAL + * if it's down. + */ + cfg->verify_enabled = state->verify_enabled; + cfg->verify_time = state->verify_time; + cfg->tx_enabled = state->tx_enabled; + cfg->pmac_enabled = state->pmac_enabled; + cfg->tx_min_frag_size = state->tx_min_frag_size; +} + +int ethnl_set_mm(struct sk_buff *skb, struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct ethnl_req_info req_info = {}; + struct ethtool_mm_state state = {}; + struct nlattr **tb = info->attrs; + struct ethtool_mm_cfg cfg = {}; + const struct ethtool_ops *ops; + struct net_device *dev; + bool mod = false; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MM_HEADER], + genl_info_net(info), extack, true); + if (ret) + return ret; + + dev = req_info.dev; + ops = dev->ethtool_ops; + + if (!ops->get_mm || !ops->set_mm) { + ret = -EOPNOTSUPP; + goto out_dev_put; + } + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl_unlock; + + ret = ops->get_mm(dev, &state); + if (ret) + goto out_complete; + + mm_state_to_cfg(&state, &cfg); + + ethnl_update_bool(&cfg.verify_enabled, tb[ETHTOOL_A_MM_VERIFY_ENABLED], + &mod); + ethnl_update_u32(&cfg.verify_time, tb[ETHTOOL_A_MM_VERIFY_TIME], &mod); + ethnl_update_bool(&cfg.tx_enabled, tb[ETHTOOL_A_MM_TX_ENABLED], &mod); + ethnl_update_bool(&cfg.pmac_enabled, tb[ETHTOOL_A_MM_PMAC_ENABLED], + &mod); + ethnl_update_u32(&cfg.tx_min_frag_size, + tb[ETHTOOL_A_MM_TX_MIN_FRAG_SIZE], &mod); + + if (!mod) + goto out_complete; + + if (cfg.verify_time > state.max_verify_time) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MM_VERIFY_TIME], + "verifyTime exceeds device maximum"); + ret = -ERANGE; + goto out_complete; + } + + ret = ops->set_mm(dev, &cfg, extack); + if (ret) + goto out_complete; + + ethtool_notify(dev, ETHTOOL_MSG_MM_NTF, NULL); + +out_complete: + ethnl_ops_complete(dev); +out_rtnl_unlock: + rtnl_unlock(); +out_dev_put: + ethnl_parse_header_dev_put(&req_info); + return ret; +} diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 9f924875bba9..6412c4dc663d 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -290,6 +290,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, [ETHTOOL_MSG_PLCA_GET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, + [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -606,6 +607,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, [ETHTOOL_MSG_PLCA_NTF] = ðnl_plca_cfg_request_ops, + [ETHTOOL_MSG_MM_NTF] = ðnl_mm_request_ops, }; /* default notification handler */ @@ -700,6 +702,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PLCA_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_MM_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -1076,6 +1079,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_plca_get_status_policy, .maxattr = ARRAY_SIZE(ethnl_plca_get_status_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_MM_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_mm_get_policy, + .maxattr = ARRAY_SIZE(ethnl_mm_get_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_MM_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_mm, + .policy = ethnl_mm_set_policy, + .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index f271266f6e28..657b0c80620c 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -349,6 +349,7 @@ extern const struct ethnl_request_ops ethnl_pse_request_ops; 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 nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -393,6 +394,8 @@ extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; +extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; +extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); @@ -414,6 +417,7 @@ int ethnl_set_fec(struct sk_buff *skb, struct genl_info *info); int ethnl_set_module(struct sk_buff *skb, struct genl_info *info); int ethnl_set_pse(struct sk_buff *skb, struct genl_info *info); int ethnl_set_plca_cfg(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_mm(struct sk_buff *skb, struct genl_info *info); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; -- cgit v1.2.3 From 04692c9020b76939715d6f2b4ff84d832246e0fc Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 19 Jan 2023 14:26:56 +0200 Subject: net: ethtool: netlink: retrieve stats from multiple sources (eMAC, pMAC) IEEE 802.3-2018 clause 99 defines a MAC Merge sublayer which contains an Express MAC and a Preemptible MAC. Both MACs are hidden to higher and lower layers and visible as a single MAC (packet classification to eMAC or pMAC on TX is done based on priority; classification on RX is done based on SFD). For devices which support a MAC Merge sublayer, it is desirable to retrieve individual packet counters from the eMAC and the pMAC, as well as aggregate statistics (their sum). Introduce a new ETHTOOL_A_STATS_SRC attribute which is part of the policy of ETHTOOL_MSG_STATS_GET and, and an ETHTOOL_A_PAUSE_STATS_SRC which is part of the policy of ETHTOOL_MSG_PAUSE_GET (accepted when ETHTOOL_FLAG_STATS is set in the common ethtool header). Both of these take values from enum ethtool_mac_stats_src, defaulting to "aggregate" in the absence of the attribute. Existing drivers do not need to pay attention to this enum which was added to all driver-facing structures, just the ones which report the MAC merge layer as supported. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/ethtool.h | 9 +++++++ include/uapi/linux/ethtool.h | 18 ++++++++++++++ include/uapi/linux/ethtool_netlink.h | 3 +++ net/ethtool/common.h | 2 ++ net/ethtool/mm.c | 16 ++++++++++++ net/ethtool/netlink.h | 4 +-- net/ethtool/pause.c | 48 ++++++++++++++++++++++++++++++++++++ net/ethtool/stats.c | 32 +++++++++++++++++++++++- 8 files changed, 129 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 37eba38da502..0ccba6612190 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -311,6 +311,7 @@ static inline void ethtool_stats_init(u64 *stats, unsigned int n) * via a more targeted API. */ struct ethtool_eth_mac_stats { + enum ethtool_mac_stats_src src; u64 FramesTransmittedOK; u64 SingleCollisionFrames; u64 MultipleCollisionFrames; @@ -339,6 +340,7 @@ struct ethtool_eth_mac_stats { * via a more targeted API. */ struct ethtool_eth_phy_stats { + enum ethtool_mac_stats_src src; u64 SymbolErrorDuringCarrier; }; @@ -346,6 +348,7 @@ struct ethtool_eth_phy_stats { * via a more targeted API. */ struct ethtool_eth_ctrl_stats { + enum ethtool_mac_stats_src src; u64 MACControlFramesTransmitted; u64 MACControlFramesReceived; u64 UnsupportedOpcodesReceived; @@ -353,6 +356,8 @@ struct ethtool_eth_ctrl_stats { /** * struct ethtool_pause_stats - statistics for IEEE 802.3x pause frames + * @src: input field denoting whether stats should be queried from the eMAC or + * pMAC (if the MM layer is supported). To be ignored otherwise. * @tx_pause_frames: transmitted pause frame count. Reported to user space * as %ETHTOOL_A_PAUSE_STAT_TX_FRAMES. * @@ -366,6 +371,7 @@ struct ethtool_eth_ctrl_stats { * from the standard. */ struct ethtool_pause_stats { + enum ethtool_mac_stats_src src; u64 tx_pause_frames; u64 rx_pause_frames; }; @@ -417,6 +423,8 @@ struct ethtool_rmon_hist_range { /** * struct ethtool_rmon_stats - selected RMON (RFC 2819) statistics + * @src: input field denoting whether stats should be queried from the eMAC or + * pMAC (if the MM layer is supported). To be ignored otherwise. * @undersize_pkts: Equivalent to `etherStatsUndersizePkts` from the RFC. * @oversize_pkts: Equivalent to `etherStatsOversizePkts` from the RFC. * @fragments: Equivalent to `etherStatsFragments` from the RFC. @@ -432,6 +440,7 @@ struct ethtool_rmon_hist_range { * ranges is left to the driver. */ struct ethtool_rmon_stats { + enum ethtool_mac_stats_src src; u64 undersize_pkts; u64 oversize_pkts; u64 fragments; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 529a93696ab6..f7fba0dc87e5 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -711,6 +711,24 @@ enum ethtool_stringset { ETH_SS_COUNT }; +/** + * enum ethtool_mac_stats_src - source of ethtool MAC statistics + * @ETHTOOL_MAC_STATS_SRC_AGGREGATE: + * if device supports a MAC merge layer, this retrieves the aggregate + * statistics of the eMAC and pMAC. Otherwise, it retrieves just the + * statistics of the single (express) MAC. + * @ETHTOOL_MAC_STATS_SRC_EMAC: + * if device supports a MM layer, this retrieves the eMAC statistics. + * Otherwise, it retrieves the statistics of the single (express) MAC. + * @ETHTOOL_MAC_STATS_SRC_PMAC: + * if device supports a MM layer, this retrieves the pMAC statistics. + */ +enum ethtool_mac_stats_src { + ETHTOOL_MAC_STATS_SRC_AGGREGATE, + ETHTOOL_MAC_STATS_SRC_EMAC, + ETHTOOL_MAC_STATS_SRC_PMAC, +}; + /** * enum ethtool_module_power_mode_policy - plug-in module power mode policy * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 58af390823b0..ffb073c0dbb4 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -428,6 +428,7 @@ enum { ETHTOOL_A_PAUSE_RX, /* u8 */ ETHTOOL_A_PAUSE_TX, /* u8 */ ETHTOOL_A_PAUSE_STATS, /* nest - _PAUSE_STAT_* */ + ETHTOOL_A_PAUSE_STATS_SRC, /* u32 */ /* add new constants above here */ __ETHTOOL_A_PAUSE_CNT, @@ -744,6 +745,8 @@ enum { ETHTOOL_A_STATS_GRP, /* nest - _A_STATS_GRP_* */ + ETHTOOL_A_STATS_SRC, /* u32 */ + /* add new constants above here */ __ETHTOOL_A_STATS_CNT, ETHTOOL_A_STATS_MAX = (__ETHTOOL_A_STATS_CNT - 1) diff --git a/net/ethtool/common.h b/net/ethtool/common.h index b1b9db810eca..28b8aaaf9bcb 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -54,4 +54,6 @@ int ethtool_get_module_info_call(struct net_device *dev, int ethtool_get_module_eeprom_call(struct net_device *dev, struct ethtool_eeprom *ee, u8 *data); +bool __ethtool_dev_mm_supported(struct net_device *dev); + #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c index 76b209ad53d2..809d196665c6 100644 --- a/net/ethtool/mm.c +++ b/net/ethtool/mm.c @@ -253,3 +253,19 @@ out_dev_put: ethnl_parse_header_dev_put(&req_info); return ret; } + +/* Returns whether a given device supports the MAC merge layer + * (has an eMAC and a pMAC). Must be called under rtnl_lock() and + * ethnl_ops_begin(). + */ +bool __ethtool_dev_mm_supported(struct net_device *dev) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_mm_state state = {}; + int ret = -EOPNOTSUPP; + + if (ops && ops->get_mm) + ret = ops->get_mm(dev, &state); + + return !!ret; +} diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 657b0c80620c..deb057c4ea62 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -373,7 +373,7 @@ extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEAD extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1]; -extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_HEADER + 1]; +extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_STATS_SRC + 1]; extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; @@ -384,7 +384,7 @@ extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INF extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; -extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; +extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1]; extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1]; extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index a8c113d244db..e2be9e89c9d9 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -5,8 +5,12 @@ struct pause_req_info { struct ethnl_req_info base; + enum ethtool_mac_stats_src src; }; +#define PAUSE_REQINFO(__req_base) \ + container_of(__req_base, struct pause_req_info, base) + struct pause_reply_data { struct ethnl_reply_data base; struct ethtool_pauseparam pauseparam; @@ -19,13 +23,40 @@ struct pause_reply_data { const struct nla_policy ethnl_pause_get_policy[] = { [ETHTOOL_A_PAUSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), + [ETHTOOL_A_PAUSE_STATS_SRC] = + NLA_POLICY_MAX(NLA_U32, ETHTOOL_MAC_STATS_SRC_PMAC), }; +static int pause_parse_request(struct ethnl_req_info *req_base, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + enum ethtool_mac_stats_src src = ETHTOOL_MAC_STATS_SRC_AGGREGATE; + struct pause_req_info *req_info = PAUSE_REQINFO(req_base); + + if (tb[ETHTOOL_A_PAUSE_STATS_SRC]) { + if (!(req_base->flags & ETHTOOL_FLAG_STATS)) { + NL_SET_ERR_MSG_MOD(extack, + "ETHTOOL_FLAG_STATS must be set when requesting a source of stats"); + return -EINVAL; + } + + src = nla_get_u32(tb[ETHTOOL_A_PAUSE_STATS_SRC]); + } + + req_info->src = src; + + return 0; +} + static int pause_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) { + const struct pause_req_info *req_info = PAUSE_REQINFO(req_base); struct pause_reply_data *data = PAUSE_REPDATA(reply_base); + enum ethtool_mac_stats_src src = req_info->src; + struct netlink_ext_ack *extack = info->extack; struct net_device *dev = reply_base->dev; int ret; @@ -34,14 +65,26 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base, ethtool_stats_init((u64 *)&data->pausestat, sizeof(data->pausestat) / 8); + data->pausestat.src = src; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; + + if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || + src == ETHTOOL_MAC_STATS_SRC_PMAC) && + !__ethtool_dev_mm_supported(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Device does not support MAC merge layer"); + ethnl_ops_complete(dev); + return -EOPNOTSUPP; + } + dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam); if (req_base->flags & ETHTOOL_FLAG_STATS && dev->ethtool_ops->get_pause_stats) dev->ethtool_ops->get_pause_stats(dev, &data->pausestat); + ethnl_ops_complete(dev); return 0; @@ -56,6 +99,7 @@ static int pause_reply_size(const struct ethnl_req_info *req_base, if (req_base->flags & ETHTOOL_FLAG_STATS) n += nla_total_size(0) + /* _PAUSE_STATS */ + nla_total_size(sizeof(u32)) + /* _PAUSE_STATS_SRC */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } @@ -77,6 +121,9 @@ static int pause_put_stats(struct sk_buff *skb, const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD; struct nlattr *nest; + if (nla_put_u32(skb, ETHTOOL_A_PAUSE_STATS_SRC, pause_stats->src)) + return -EMSGSIZE; + nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS); if (!nest) return -EMSGSIZE; @@ -121,6 +168,7 @@ const struct ethnl_request_ops ethnl_pause_request_ops = { .req_info_size = sizeof(struct pause_req_info), .reply_data_size = sizeof(struct pause_reply_data), + .parse_request = pause_parse_request, .prepare_data = pause_prepare_data, .reply_size = pause_reply_size, .fill_reply = pause_fill_reply, diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index a20e0a24ff61..26a70320e01d 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -7,6 +7,7 @@ struct stats_req_info { struct ethnl_req_info base; DECLARE_BITMAP(stat_mask, __ETHTOOL_STATS_CNT); + enum ethtool_mac_stats_src src; }; #define STATS_REQINFO(__req_base) \ @@ -75,16 +76,19 @@ const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_RMON_JABBER] = "etherStatsJabbers", }; -const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1] = { +const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1] = { [ETHTOOL_A_STATS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_STATS_GROUPS] = { .type = NLA_NESTED }, + [ETHTOOL_A_STATS_SRC] = + NLA_POLICY_MAX(NLA_U32, ETHTOOL_MAC_STATS_SRC_PMAC), }; static int stats_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, struct netlink_ext_ack *extack) { + enum ethtool_mac_stats_src src = ETHTOOL_MAC_STATS_SRC_AGGREGATE; struct stats_req_info *req_info = STATS_REQINFO(req_base); bool mod = false; int err; @@ -100,6 +104,11 @@ static int stats_parse_request(struct ethnl_req_info *req_base, return -EINVAL; } + if (tb[ETHTOOL_A_STATS_SRC]) + src = nla_get_u32(tb[ETHTOOL_A_STATS_SRC]); + + req_info->src = src; + return 0; } @@ -109,6 +118,8 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, { const struct stats_req_info *req_info = STATS_REQINFO(req_base); struct stats_reply_data *data = STATS_REPDATA(reply_base); + enum ethtool_mac_stats_src src = req_info->src; + struct netlink_ext_ack *extack = info->extack; struct net_device *dev = reply_base->dev; int ret; @@ -116,11 +127,25 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; + if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || + src == ETHTOOL_MAC_STATS_SRC_PMAC) && + !__ethtool_dev_mm_supported(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Device does not support MAC merge layer"); + ethnl_ops_complete(dev); + return -EOPNOTSUPP; + } + /* Mark all stats as unset (see ETHTOOL_STAT_NOT_SET) to prevent them * from being reported to user space in case driver did not set them. */ memset(&data->stats, 0xff, sizeof(data->stats)); + data->phy_stats.src = src; + data->mac_stats.src = src; + data->ctrl_stats.src = src; + data->rmon_stats.src = src; + if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && dev->ethtool_ops->get_eth_phy_stats) dev->ethtool_ops->get_eth_phy_stats(dev, &data->phy_stats); @@ -146,6 +171,8 @@ static int stats_reply_size(const struct ethnl_req_info *req_base, unsigned int n_grps = 0, n_stats = 0; int len = 0; + len += nla_total_size(sizeof(u32)); /* _STATS_SRC */ + if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_phy_stats) / sizeof(u64); n_grps++; @@ -379,6 +406,9 @@ static int stats_fill_reply(struct sk_buff *skb, const struct stats_reply_data *data = STATS_REPDATA(reply_base); int ret = 0; + if (nla_put_u32(skb, ETHTOOL_A_STATS_SRC, req_info->src)) + return -EMSGSIZE; + if (!ret && test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_PHY, ETH_SS_STATS_ETH_PHY, -- cgit v1.2.3 From 2b3486bc2d237ec345b3942b7be5deabf8c8fed1 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 19 Jan 2023 14:15:24 -0800 Subject: bpf: Introduce device-bound XDP programs New flag BPF_F_XDP_DEV_BOUND_ONLY plus all the infra to have a way to associate a netdev with a BPF program at load time. netdevsim checks are dropped in favor of generic check in dev_xdp_attach. Cc: John Fastabend Cc: David Ahern Cc: Martin KaFai Lau Cc: Jakub Kicinski Cc: Willem de Bruijn Cc: Jesper Dangaard Brouer Cc: Anatoly Burakov Cc: Alexander Lobakin Cc: Magnus Karlsson Cc: Maryam Tahhan Cc: xdp-hints@xdp-project.net Cc: netdev@vger.kernel.org Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20230119221536.3349901-6-sdf@google.com Signed-off-by: Martin KaFai Lau --- drivers/net/netdevsim/bpf.c | 4 -- include/linux/bpf.h | 24 +++++++++-- include/uapi/linux/bpf.h | 5 +++ kernel/bpf/core.c | 4 +- kernel/bpf/offload.c | 95 +++++++++++++++++++++++++++++++----------- kernel/bpf/syscall.c | 9 ++-- net/core/dev.c | 5 +++ tools/include/uapi/linux/bpf.h | 5 +++ 8 files changed, 113 insertions(+), 38 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 50854265864d..f60eb97e3a62 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -315,10 +315,6 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf) NSIM_EA(bpf->extack, "xdpoffload of non-bound program"); return -EINVAL; } - if (!bpf_offload_dev_match(bpf->prog, ns->netdev)) { - NSIM_EA(bpf->extack, "program bound to different dev"); - return -EINVAL; - } state = bpf->prog->aux->offload->dev_priv; if (WARN_ON(strcmp(state->state, "xlated"))) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1bb525c0130e..b97a05bb47be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1261,7 +1261,8 @@ struct bpf_prog_aux { enum bpf_prog_type saved_dst_prog_type; enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ - bool offload_requested; + bool dev_bound; /* Program is bound to the netdev. */ + bool offload_requested; /* Program is bound and offloaded to the netdev. */ bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; bool sleepable; @@ -2451,7 +2452,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); -void bpf_prog_offload_destroy(struct bpf_prog *prog); +void bpf_prog_dev_bound_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); @@ -2479,7 +2480,13 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); void unpriv_ebpf_notify(int new_state); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) -int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); +int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr); +void bpf_dev_bound_netdev_unregister(struct net_device *dev); + +static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) +{ + return aux->dev_bound; +} static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux) { @@ -2507,12 +2514,21 @@ void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else -static inline int bpf_prog_offload_init(struct bpf_prog *prog, +static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } +static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev) +{ +} + +static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) +{ + return false; +} + static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux) { return false; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index adae5b168f9d..ba0f0cfb5e42 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1156,6 +1156,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded + * program becomes device-bound but can access XDP metadata. + */ +#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 515f4f08591c..1cf19da3c128 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2553,8 +2553,8 @@ static void bpf_prog_free_deferred(struct work_struct *work) #endif bpf_free_used_maps(aux); bpf_free_used_btfs(aux); - if (bpf_prog_is_offloaded(aux)) - bpf_prog_offload_destroy(aux->prog); + if (bpf_prog_is_dev_bound(aux)) + bpf_prog_dev_bound_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index deb06498da0b..f767455ed732 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -41,7 +41,7 @@ struct bpf_offload_dev { struct bpf_offload_netdev { struct rhash_head l; struct net_device *netdev; - struct bpf_offload_dev *offdev; + struct bpf_offload_dev *offdev; /* NULL when bound-only */ struct list_head progs; struct list_head maps; struct list_head offdev_netdevs; @@ -89,19 +89,17 @@ static int __bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, INIT_LIST_HEAD(&ondev->progs); INIT_LIST_HEAD(&ondev->maps); - down_write(&bpf_devs_lock); err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); if (err) { netdev_warn(netdev, "failed to register for BPF offload\n"); - goto err_unlock_free; + goto err_free; } - list_add(&ondev->offdev_netdevs, &offdev->netdevs); - up_write(&bpf_devs_lock); + if (offdev) + list_add(&ondev->offdev_netdevs, &offdev->netdevs); return 0; -err_unlock_free: - up_write(&bpf_devs_lock); +err_free: kfree(ondev); return err; } @@ -149,24 +147,26 @@ static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev) { - struct bpf_offload_netdev *ondev, *altdev; + struct bpf_offload_netdev *ondev, *altdev = NULL; struct bpf_offloaded_map *offmap, *mtmp; struct bpf_prog_offload *offload, *ptmp; ASSERT_RTNL(); - down_write(&bpf_devs_lock); ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); if (WARN_ON(!ondev)) - goto unlock; + return; WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); - list_del(&ondev->offdev_netdevs); /* Try to move the objects to another netdev of the device */ - altdev = list_first_entry_or_null(&offdev->netdevs, - struct bpf_offload_netdev, - offdev_netdevs); + if (offdev) { + list_del(&ondev->offdev_netdevs); + altdev = list_first_entry_or_null(&offdev->netdevs, + struct bpf_offload_netdev, + offdev_netdevs); + } + if (altdev) { list_for_each_entry(offload, &ondev->progs, offloads) offload->netdev = altdev->netdev; @@ -185,11 +185,9 @@ static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, WARN_ON(!list_empty(&ondev->progs)); WARN_ON(!list_empty(&ondev->maps)); kfree(ondev); -unlock: - up_write(&bpf_devs_lock); } -int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { struct bpf_offload_netdev *ondev; struct bpf_prog_offload *offload; @@ -199,7 +197,11 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) attr->prog_type != BPF_PROG_TYPE_XDP) return -EINVAL; - if (attr->prog_flags) + if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY) + return -EINVAL; + + if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS && + attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY) return -EINVAL; offload = kzalloc(sizeof(*offload), GFP_USER); @@ -214,11 +216,23 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) if (err) goto err_maybe_put; + prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY); + down_write(&bpf_devs_lock); ondev = bpf_offload_find_netdev(offload->netdev); if (!ondev) { - err = -EINVAL; - goto err_unlock; + if (bpf_prog_is_offloaded(prog->aux)) { + err = -EINVAL; + goto err_unlock; + } + + /* When only binding to the device, explicitly + * create an entry in the hashtable. + */ + err = __bpf_offload_dev_netdev_register(NULL, offload->netdev); + if (err) + goto err_unlock; + ondev = bpf_offload_find_netdev(offload->netdev); } offload->offdev = ondev->offdev; prog->aux->offload = offload; @@ -321,12 +335,25 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) up_read(&bpf_devs_lock); } -void bpf_prog_offload_destroy(struct bpf_prog *prog) +void bpf_prog_dev_bound_destroy(struct bpf_prog *prog) { + struct bpf_offload_netdev *ondev; + struct net_device *netdev; + + rtnl_lock(); down_write(&bpf_devs_lock); - if (prog->aux->offload) + if (prog->aux->offload) { + list_del_init(&prog->aux->offload->offloads); + + netdev = prog->aux->offload->netdev; __bpf_prog_offload_destroy(prog); + + ondev = bpf_offload_find_netdev(netdev); + if (!ondev->offdev && list_empty(&ondev->progs)) + __bpf_offload_dev_netdev_unregister(NULL, netdev); + } up_write(&bpf_devs_lock); + rtnl_unlock(); } static int bpf_prog_offload_translate(struct bpf_prog *prog) @@ -621,7 +648,7 @@ static bool __bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_offload_netdev *ondev1, *ondev2; struct bpf_prog_offload *offload; - if (!bpf_prog_is_offloaded(prog->aux)) + if (!bpf_prog_is_dev_bound(prog->aux)) return false; offload = prog->aux->offload; @@ -667,14 +694,21 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev) { - return __bpf_offload_dev_netdev_register(offdev, netdev); + int err; + + down_write(&bpf_devs_lock); + err = __bpf_offload_dev_netdev_register(offdev, netdev); + up_write(&bpf_devs_lock); + return err; } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev) { + down_write(&bpf_devs_lock); __bpf_offload_dev_netdev_unregister(offdev, netdev); + up_write(&bpf_devs_lock); } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); @@ -708,6 +742,19 @@ void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev) } EXPORT_SYMBOL_GPL(bpf_offload_dev_priv); +void bpf_dev_bound_netdev_unregister(struct net_device *dev) +{ + struct bpf_offload_netdev *ondev; + + ASSERT_RTNL(); + + down_write(&bpf_devs_lock); + ondev = bpf_offload_find_netdev(dev); + if (ondev && !ondev->offdev) + __bpf_offload_dev_netdev_unregister(NULL, ondev->netdev); + up_write(&bpf_devs_lock); +} + static int __init bpf_offload_init(void) { return rhashtable_init(&offdevs, &offdevs_params); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5e90b697f908..fdf4ff3d5a7f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2491,7 +2491,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | - BPF_F_XDP_HAS_FRAGS)) + BPF_F_XDP_HAS_FRAGS | + BPF_F_XDP_DEV_BOUND_ONLY)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2575,7 +2576,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; - prog->aux->offload_requested = !!attr->prog_ifindex; + prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; @@ -2598,8 +2599,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) atomic64_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; - if (bpf_prog_is_offloaded(prog->aux)) { - err = bpf_prog_offload_init(prog, attr); + if (bpf_prog_is_dev_bound(prog->aux)) { + err = bpf_prog_dev_bound_init(prog, attr); if (err) goto free_prog_sec; } diff --git a/net/core/dev.c b/net/core/dev.c index a37829de6529..e66da626df84 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9228,6 +9228,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported"); return -EINVAL; } + if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) { + NL_SET_ERR_MSG(extack, "Program bound to different device"); + return -EINVAL; + } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; @@ -10830,6 +10834,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev_shutdown(dev); dev_xdp_uninstall(dev); + bpf_dev_bound_netdev_unregister(dev); netdev_offload_xstats_disable_all(dev); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 142b81bcbb2e..7f024ac22edd 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1156,6 +1156,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded + * program becomes device-bound but can access XDP metadata. + */ +#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ -- cgit v1.2.3 From 13bd9b31a969b03c8ec1d4eb0f2b9aebd30ebfd8 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Tue, 24 Jan 2023 02:47:20 +0100 Subject: Revert "netfilter: conntrack: add sctp DATA_SENT state" This reverts commit (bff3d0534804: "netfilter: conntrack: add sctp DATA_SENT state") Using DATA/SACK to detect a new connection on secondary/alternate paths works only on new connections, while a HEARTBEAT is required on connection re-use. It is probably consistent to wait for HEARTBEAT to create a secondary connection in conntrack. Signed-off-by: Sriram Yagnaraman Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_sctp.h | 1 - include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 1 - net/netfilter/nf_conntrack_proto_sctp.c | 102 +++++++++------------ net/netfilter/nf_conntrack_standalone.c | 8 -- 4 files changed, 42 insertions(+), 70 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index c742469afe21..edc6ddab0de6 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -16,7 +16,6 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, SCTP_CONNTRACK_HEARTBEAT_ACKED, - SCTP_CONNTRACK_DATA_SENT, SCTP_CONNTRACK_MAX }; diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index 94e74034706d..6b20fb22717b 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -95,7 +95,6 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, - CTA_TIMEOUT_SCTP_DATA_SENT, __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c561c1213704..01cf3e06f042 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -60,7 +60,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, - [SCTP_CONNTRACK_DATA_SENT] = 30 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -75,7 +74,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT #define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED -#define sDS SCTP_CONNTRACK_DATA_SENT #define sIV SCTP_CONNTRACK_MAX /* @@ -98,10 +96,9 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction - opposite to that of the HEARTBEAT/DATA chunk. Secondary connection - is established. -DATA_SENT - We have seen a DATA/SACK in a new flow. +HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to + that of the HEARTBEAT chunk. Secondary connection is + established. */ /* TODO @@ -115,38 +112,36 @@ cookie echoed to closed. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, -/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, -/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} } }; @@ -258,11 +253,6 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; - case SCTP_CID_DATA: - case SCTP_CID_SACK: - pr_debug("SCTP_CID_DATA/SACK"); - i = 11; - break; default: /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", @@ -316,9 +306,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ih->init_tag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; - } else if (sch->type == SCTP_CID_HEARTBEAT || - sch->type == SCTP_CID_DATA || - sch->type == SCTP_CID_SACK) { + } else if (sch->type == SCTP_CID_HEARTBEAT) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; @@ -404,19 +392,19 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!sctp_new(ct, skb, sh, dataoff)) return -NF_ACCEPT; - } else { - /* Check the verification tag (Sec 8.5) */ - if (!test_bit(SCTP_CID_INIT, map) && - !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && - !test_bit(SCTP_CID_COOKIE_ECHO, map) && - !test_bit(SCTP_CID_ABORT, map) && - !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && - !test_bit(SCTP_CID_HEARTBEAT, map) && - !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && - sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out; - } + } + + /* Check the verification tag (Sec 8.5) */ + if (!test_bit(SCTP_CID_INIT, map) && + !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && + !test_bit(SCTP_CID_COOKIE_ECHO, map) && + !test_bit(SCTP_CID_ABORT, map) && + !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && + sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out; } old_state = new_state = SCTP_CONNTRACK_NONE; @@ -483,11 +471,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } - } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) { - if (ct->proto.sctp.vtag[dir] == 0) { - pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); - ct->proto.sctp.vtag[dir] = sh->vtag; - } } old_state = ct->proto.sctp.state; @@ -708,7 +691,6 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, - [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0250725e38a4..bca839ab1ae8 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -602,7 +602,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -893,12 +892,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = { - .procname = "nf_conntrack_sctp_timeout_data_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -1043,7 +1036,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); XASSIGN(HEARTBEAT_ACKED, sn); - XASSIGN(DATA_SENT, sn); #undef XASSIGN #endif } -- cgit v1.2.3 From a44b7651489f26271ac784b70895e8a85d0cebf4 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Tue, 24 Jan 2023 02:47:21 +0100 Subject: netfilter: conntrack: unify established states for SCTP paths An SCTP endpoint can start an association through a path and tear it down over another one. That means the initial path will not see the shutdown sequence, and the conntrack entry will remain in ESTABLISHED state for 5 days. By merging the HEARTBEAT_ACKED and ESTABLISHED states into one ESTABLISHED state, there remains no difference between a primary or secondary path. The timeout for the merged ESTABLISHED state is set to 210 seconds (hb_interval * max_path_retrans + rto_max). So, even if a path doesn't see the shutdown sequence, it will expire in a reasonable amount of time. With this change in place, there is now more than one state from which we can transition to ESTABLISHED, COOKIE_ECHOED and HEARTBEAT_SENT, so handle the setting of ASSURED bit whenever a state change has happened and the new state is ESTABLISHED. Removed the check for dir==REPLY since the transition to ESTABLISHED can happen only in the reply direction. Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Sriram Yagnaraman Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/nf_conntrack-sysctl.rst | 10 +-- include/uapi/linux/netfilter/nf_conntrack_sctp.h | 2 +- include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 2 +- net/netfilter/nf_conntrack_proto_sctp.c | 93 +++++++++------------- net/netfilter/nf_conntrack_standalone.c | 8 -- 5 files changed, 44 insertions(+), 71 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 49db1d11d7c4..8b1045c3b59e 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -173,7 +173,9 @@ nf_conntrack_sctp_timeout_cookie_echoed - INTEGER (seconds) default 3 nf_conntrack_sctp_timeout_established - INTEGER (seconds) - default 432000 (5 days) + default 210 + + Default is set to (hb_interval * path_max_retrans + rto_max) nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds) default 0.3 @@ -190,12 +192,6 @@ nf_conntrack_sctp_timeout_heartbeat_sent - INTEGER (seconds) This timeout is used to setup conntrack entry on secondary paths. Default is set to hb_interval. -nf_conntrack_sctp_timeout_heartbeat_acked - INTEGER (seconds) - default 210 - - This timeout is used to setup conntrack entry on secondary paths. - Default is set to (hb_interval * path_max_retrans + rto_max) - nf_conntrack_udp_timeout - INTEGER (seconds) default 30 diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index edc6ddab0de6..2d6f80d75ae7 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -15,7 +15,7 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_RECD, SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, - SCTP_CONNTRACK_HEARTBEAT_ACKED, + SCTP_CONNTRACK_HEARTBEAT_ACKED, /* no longer used */ SCTP_CONNTRACK_MAX }; diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index 6b20fb22717b..aa805e6d4e28 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -94,7 +94,7 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_RECD, CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, - CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, + CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, /* no longer used */ __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 01cf3e06f042..945dd40e7077 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -27,22 +27,16 @@ #include #include -/* FIXME: Examine ipfilter's timeouts and conntrack transitions more - closely. They're more complex. --RR - - And so for me for SCTP :D -Kiran */ - static const char *const sctp_conntrack_names[] = { - "NONE", - "CLOSED", - "COOKIE_WAIT", - "COOKIE_ECHOED", - "ESTABLISHED", - "SHUTDOWN_SENT", - "SHUTDOWN_RECD", - "SHUTDOWN_ACK_SENT", - "HEARTBEAT_SENT", - "HEARTBEAT_ACKED", + [SCTP_CONNTRACK_NONE] = "NONE", + [SCTP_CONNTRACK_CLOSED] = "CLOSED", + [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT", + [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED", + [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED", + [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT", + [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD", + [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT", + [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", }; #define SECS * HZ @@ -54,12 +48,11 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_CLOSED] = 10 SECS, [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, - [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS, + [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, - [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -73,7 +66,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT -#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED #define sIV SCTP_CONNTRACK_MAX /* @@ -96,9 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to - that of the HEARTBEAT chunk. Secondary connection is - established. */ /* TODO @@ -115,33 +104,33 @@ cookie echoed to closed. static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES}, } }; @@ -508,8 +497,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } ct->proto.sctp.state = new_state; - if (old_state != new_state) + if (old_state != new_state) { nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + if (new_state == SCTP_CONNTRACK_ESTABLISHED && + !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); + } } spin_unlock_bh(&ct->lock); @@ -523,14 +516,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); - if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && - dir == IP_CT_DIR_REPLY && - new_state == SCTP_CONNTRACK_ESTABLISHED) { - pr_debug("Setting assured bit\n"); - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); - } - return NF_ACCEPT; out_unlock: diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index bca839ab1ae8..460294bd4b60 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -601,7 +601,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -886,12 +885,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -1035,7 +1028,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); - XASSIGN(HEARTBEAT_ACKED, sn); #undef XASSIGN #endif } -- cgit v1.2.3 From 3a330496baa87f334159fdf2388e44f42f619ab5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 20 Jan 2023 09:50:38 -0800 Subject: net: fou: regenerate the uAPI from the spec Regenerate the FOU uAPI header from the YAML spec. The flags now come before attributes which use them, and the comments for type disappear (coders should look at the spec instead). Acked-by: Stanislav Fomichev Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- include/uapi/linux/fou.h | 54 +++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index 87c2c9f08803..19ebbef41a63 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -1,32 +1,37 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* fou.h - FOU Interface */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN uapi header */ #ifndef _UAPI_LINUX_FOU_H #define _UAPI_LINUX_FOU_H -/* NETLINK_GENERIC related info - */ #define FOU_GENL_NAME "fou" -#define FOU_GENL_VERSION 0x1 +#define FOU_GENL_VERSION 1 enum { - FOU_ATTR_UNSPEC, - FOU_ATTR_PORT, /* u16 */ - FOU_ATTR_AF, /* u8 */ - FOU_ATTR_IPPROTO, /* u8 */ - FOU_ATTR_TYPE, /* u8 */ - FOU_ATTR_REMCSUM_NOPARTIAL, /* flag */ - FOU_ATTR_LOCAL_V4, /* u32 */ - FOU_ATTR_LOCAL_V6, /* in6_addr */ - FOU_ATTR_PEER_V4, /* u32 */ - FOU_ATTR_PEER_V6, /* in6_addr */ - FOU_ATTR_PEER_PORT, /* u16 */ - FOU_ATTR_IFINDEX, /* s32 */ - - __FOU_ATTR_MAX, + FOU_ENCAP_UNSPEC, + FOU_ENCAP_DIRECT, + FOU_ENCAP_GUE, }; -#define FOU_ATTR_MAX (__FOU_ATTR_MAX - 1) +enum { + FOU_ATTR_UNSPEC, + FOU_ATTR_PORT, + FOU_ATTR_AF, + FOU_ATTR_IPPROTO, + FOU_ATTR_TYPE, + FOU_ATTR_REMCSUM_NOPARTIAL, + FOU_ATTR_LOCAL_V4, + FOU_ATTR_LOCAL_V6, + FOU_ATTR_PEER_V4, + FOU_ATTR_PEER_V6, + FOU_ATTR_PEER_PORT, + FOU_ATTR_IFINDEX, + + __FOU_ATTR_MAX +}; +#define FOU_ATTR_MAX (__FOU_ATTR_MAX - 1) enum { FOU_CMD_UNSPEC, @@ -34,15 +39,8 @@ enum { FOU_CMD_DEL, FOU_CMD_GET, - __FOU_CMD_MAX, + __FOU_CMD_MAX }; - -enum { - FOU_ENCAP_UNSPEC, - FOU_ENCAP_DIRECT, - FOU_ENCAP_GUE, -}; - -#define FOU_CMD_MAX (__FOU_CMD_MAX - 1) +#define FOU_CMD_MAX (__FOU_CMD_MAX - 1) #endif /* _UAPI_LINUX_FOU_H */ -- cgit v1.2.3 From 14329b825ffb7f2710c13fdcc37fc2e7c67b6781 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 20 Dec 2022 16:12:33 +0000 Subject: KVM: x86/pmu: Introduce masked events to the pmu event filter When building a list of filter events, it can sometimes be a challenge to fit all the events needed to adequately restrict the guest into the limited space available in the pmu event filter. This stems from the fact that the pmu event filter requires each event (i.e. event select + unit mask) be listed, when the intention might be to restrict the event select all together, regardless of it's unit mask. Instead of increasing the number of filter events in the pmu event filter, add a new encoding that is able to do a more generalized match on the unit mask. Introduce masked events as another encoding the pmu event filter understands. Masked events has the fields: mask, match, and exclude. When filtering based on these events, the mask is applied to the guest's unit mask to see if it matches the match value (i.e. umask & mask == match). The exclude bit can then be used to exclude events from that match. E.g. for a given event select, if it's easier to say which unit mask values shouldn't be filtered, a masked event can be set up to match all possible unit mask values, then another masked event can be set up to match the unit mask values that shouldn't be filtered. Userspace can query to see if this feature exists by looking for the capability, KVM_CAP_PMU_EVENT_MASKED_EVENTS. This feature is enabled by setting the flags field in the pmu event filter to KVM_PMU_EVENT_FLAG_MASKED_EVENTS. Events can be encoded by using KVM_PMU_ENCODE_MASKED_ENTRY(). It is an error to have a bit set outside the valid bits for a masked event, and calls to KVM_SET_PMU_EVENT_FILTER will return -EINVAL in such cases, including the high bits of the event select (35:32) if called on Intel. With these updates the filter matching code has been updated to match on a common event. Masked events were flexible enough to handle both event types, so they were used as the common event. This changes how guest events get filtered because regardless of the type of event used in the uAPI, they will be converted to masked events. Because of this there could be a slight performance hit because instead of matching the filter event with a lookup on event select + unit mask, it does a lookup on event select then walks the unit masks to find the match. This shouldn't be a big problem because I would expect the set of common event selects to be small, and if they aren't the set can likely be reduced by using masked events to generalize the unit mask. Using one type of event when filtering guest events allows for a common code path to be used. Signed-off-by: Aaron Lewis Link: https://lore.kernel.org/r/20221220161236.555143-5-aaronlewis@google.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 78 ++++++++++++++-- arch/x86/include/asm/kvm_host.h | 14 ++- arch/x86/include/uapi/asm/kvm.h | 29 ++++++ arch/x86/kvm/pmu.c | 197 ++++++++++++++++++++++++++++++++++------ arch/x86/kvm/x86.c | 1 + include/uapi/linux/kvm.h | 1 + 6 files changed, 282 insertions(+), 38 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9807b05a1b57..83e3acc9e321 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5005,6 +5005,15 @@ using this ioctl. :Parameters: struct kvm_pmu_event_filter (in) :Returns: 0 on success, -1 on error +Errors: + + ====== ============================================================ + EFAULT args[0] cannot be accessed + EINVAL args[0] contains invalid data in the filter or filter events + E2BIG nevents is too large + EBUSY not enough memory to allocate the filter + ====== ============================================================ + :: struct kvm_pmu_event_filter { @@ -5016,14 +5025,69 @@ using this ioctl. __u64 events[0]; }; -This ioctl restricts the set of PMU events that the guest can program. -The argument holds a list of events which will be allowed or denied. -The eventsel+umask of each event the guest attempts to program is compared -against the events field to determine whether the guest should have access. -The events field only controls general purpose counters; fixed purpose -counters are controlled by the fixed_counter_bitmap. +This ioctl restricts the set of PMU events the guest can program by limiting +which event select and unit mask combinations are permitted. + +The argument holds a list of filter events which will be allowed or denied. + +Filter events only control general purpose counters; fixed purpose counters +are controlled by the fixed_counter_bitmap. + +Valid values for 'flags':: + +``0`` + +To use this mode, clear the 'flags' field. + +In this mode each event will contain an event select + unit mask. + +When the guest attempts to program the PMU the guest's event select + +unit mask is compared against the filter events to determine whether the +guest should have access. + +``KVM_PMU_EVENT_FLAG_MASKED_EVENTS`` +:Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS + +In this mode each filter event will contain an event select, mask, match, and +exclude value. To encode a masked event use:: + + KVM_PMU_ENCODE_MASKED_ENTRY() + +An encoded event will follow this layout:: + + Bits Description + ---- ----------- + 7:0 event select (low bits) + 15:8 umask match + 31:16 unused + 35:32 event select (high bits) + 36:54 unused + 55 exclude bit + 63:56 umask mask + +When the guest attempts to program the PMU, these steps are followed in +determining if the guest should have access: + + 1. Match the event select from the guest against the filter events. + 2. If a match is found, match the guest's unit mask to the mask and match + values of the included filter events. + I.e. (unit mask & mask) == match && !exclude. + 3. If a match is found, match the guest's unit mask to the mask and match + values of the excluded filter events. + I.e. (unit mask & mask) == match && exclude. + 4. + a. If an included match is found and an excluded match is not found, filter + the event. + b. For everything else, do not filter the event. + 5. + a. If the event is filtered and it's an allow list, allow the guest to + program the event. + b. If the event is filtered and it's a deny list, do not allow the guest to + program the event. -No flags are defined yet, the field must be zero. +When setting a new pmu event filter, -EINVAL will be returned if any of the +unused fields are set or if any of the high bits (35:32) in the event +select are set when called on Intel. Valid values for 'action':: diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4d2bc08794e4..cd0151e6af62 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1145,6 +1145,18 @@ struct kvm_x86_msr_filter { struct msr_bitmap_range ranges[16]; }; +struct kvm_x86_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 nr_includes; + __u32 nr_excludes; + __u64 *includes; + __u64 *excludes; + __u64 events[]; +}; + enum kvm_apicv_inhibit { /********************************************************************/ @@ -1363,7 +1375,7 @@ struct kvm_arch { /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; - struct kvm_pmu_event_filter __rcu *pmu_event_filter; + struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index e48deab8901d..f142f3ebf4e4 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -525,6 +525,35 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 8a734f4343bb..3264f8e0e8ef 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -255,30 +255,99 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *pa, const void *pb) +static int filter_cmp(const void *pa, const void *pb, u64 mask) { - u64 a = *(u64 *)pa; - u64 b = *(u64 *)pb; + u64 a = *(u64 *)pa & mask; + u64 b = *(u64 *)pb & mask; return (a > b) - (a < b); } -static u64 *find_filter_entry(struct kvm_pmu_event_filter *filter, u64 key) + +static int filter_sort_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT | + KVM_PMU_MASKED_ENTRY_EXCLUDE)); +} + +/* + * For the event filter, searching is done on the 'includes' list and + * 'excludes' list separately rather than on the 'events' list (which + * has both). As a result the exclude bit can be ignored. + */ +static int filter_event_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT)); +} + +static int find_filter_index(u64 *events, u64 nevents, u64 key) +{ + u64 *fe = bsearch(&key, events, nevents, sizeof(events[0]), + filter_event_cmp); + + if (!fe) + return -1; + + return fe - events; +} + +static bool is_filter_entry_match(u64 filter_event, u64 umask) +{ + u64 mask = filter_event >> (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8); + u64 match = filter_event & KVM_PMU_MASKED_ENTRY_UMASK_MATCH; + + BUILD_BUG_ON((KVM_PMU_ENCODE_MASKED_ENTRY(0, 0xff, 0, false) >> + (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8)) != + ARCH_PERFMON_EVENTSEL_UMASK); + + return (umask & mask) == match; +} + +static bool filter_contains_match(u64 *events, u64 nevents, u64 eventsel) { - return bsearch(&key, filter->events, filter->nevents, - sizeof(filter->events[0]), cmp_u64); + u64 event_select = eventsel & kvm_pmu_ops.EVENTSEL_EVENT; + u64 umask = eventsel & ARCH_PERFMON_EVENTSEL_UMASK; + int i, index; + + index = find_filter_index(events, nevents, event_select); + if (index < 0) + return false; + + /* + * Entries are sorted by the event select. Walk the list in both + * directions to process all entries with the targeted event select. + */ + for (i = index; i < nevents; i++) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + for (i = index - 1; i >= 0; i--) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + return false; } -static bool is_gp_event_allowed(struct kvm_pmu_event_filter *filter, u64 eventsel) +static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f, + u64 eventsel) { - if (find_filter_entry(filter, eventsel & (kvm_pmu_ops.EVENTSEL_EVENT | - ARCH_PERFMON_EVENTSEL_UMASK))) - return filter->action == KVM_PMU_EVENT_ALLOW; + if (filter_contains_match(f->includes, f->nr_includes, eventsel) && + !filter_contains_match(f->excludes, f->nr_excludes, eventsel)) + return f->action == KVM_PMU_EVENT_ALLOW; - return filter->action == KVM_PMU_EVENT_DENY; + return f->action == KVM_PMU_EVENT_DENY; } -static bool is_fixed_event_allowed(struct kvm_pmu_event_filter *filter, int idx) +static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter, + int idx) { int fixed_idx = idx - INTEL_PMC_IDX_FIXED; @@ -294,7 +363,7 @@ static bool is_fixed_event_allowed(struct kvm_pmu_event_filter *filter, int idx) static bool check_pmu_event_filter(struct kvm_pmc *pmc) { - struct kvm_pmu_event_filter *filter; + struct kvm_x86_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; if (!static_call(kvm_x86_pmu_hw_event_available)(pmc)) @@ -604,60 +673,128 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) } EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); -static void remove_impossible_events(struct kvm_pmu_event_filter *filter) +static bool is_masked_filter_valid(const struct kvm_x86_pmu_event_filter *filter) +{ + u64 mask = kvm_pmu_ops.EVENTSEL_EVENT | + KVM_PMU_MASKED_ENTRY_UMASK_MASK | + KVM_PMU_MASKED_ENTRY_UMASK_MATCH | + KVM_PMU_MASKED_ENTRY_EXCLUDE; + int i; + + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & ~mask) + return false; + } + + return true; +} + +static void convert_to_masked_filter(struct kvm_x86_pmu_event_filter *filter) { int i, j; for (i = 0, j = 0; i < filter->nevents; i++) { + /* + * Skip events that are impossible to match against a guest + * event. When filtering, only the event select + unit mask + * of the guest event is used. To maintain backwards + * compatibility, impossible filters can't be rejected :-( + */ if (filter->events[i] & ~(kvm_pmu_ops.EVENTSEL_EVENT | ARCH_PERFMON_EVENTSEL_UMASK)) continue; - - filter->events[j++] = filter->events[i]; + /* + * Convert userspace events to a common in-kernel event so + * only one code path is needed to support both events. For + * the in-kernel events use masked events because they are + * flexible enough to handle both cases. To convert to masked + * events all that's needed is to add an "all ones" umask_mask, + * (unmasked filter events don't support EXCLUDE). + */ + filter->events[j++] = filter->events[i] | + (0xFFULL << KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT); } filter->nevents = j; } +static int prepare_filter_lists(struct kvm_x86_pmu_event_filter *filter) +{ + int i; + + if (!(filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS)) + convert_to_masked_filter(filter); + else if (!is_masked_filter_valid(filter)) + return -EINVAL; + + /* + * Sort entries by event select and includes vs. excludes so that all + * entries for a given event select can be processed efficiently during + * filtering. The EXCLUDE flag uses a more significant bit than the + * event select, and so the sorted list is also effectively split into + * includes and excludes sub-lists. + */ + sort(&filter->events, filter->nevents, sizeof(filter->events[0]), + filter_sort_cmp, NULL); + + i = filter->nevents; + /* Find the first EXCLUDE event (only supported for masked events). */ + if (filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS) { + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & KVM_PMU_MASKED_ENTRY_EXCLUDE) + break; + } + } + + filter->nr_includes = i; + filter->nr_excludes = filter->nevents - filter->nr_includes; + filter->includes = filter->events; + filter->excludes = filter->events + filter->nr_includes; + + return 0; +} + int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { - struct kvm_pmu_event_filter tmp, *filter; + struct kvm_pmu_event_filter __user *user_filter = argp; + struct kvm_x86_pmu_event_filter *filter; + struct kvm_pmu_event_filter tmp; struct kvm_vcpu *vcpu; unsigned long i; size_t size; int r; - if (copy_from_user(&tmp, argp, sizeof(tmp))) + if (copy_from_user(&tmp, user_filter, sizeof(tmp))) return -EFAULT; if (tmp.action != KVM_PMU_EVENT_ALLOW && tmp.action != KVM_PMU_EVENT_DENY) return -EINVAL; - if (tmp.flags != 0) + if (tmp.flags & ~KVM_PMU_EVENT_FLAGS_VALID_MASK) return -EINVAL; if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS) return -E2BIG; size = struct_size(filter, events, tmp.nevents); - filter = kmalloc(size, GFP_KERNEL_ACCOUNT); + filter = kzalloc(size, GFP_KERNEL_ACCOUNT); if (!filter) return -ENOMEM; + filter->action = tmp.action; + filter->nevents = tmp.nevents; + filter->fixed_counter_bitmap = tmp.fixed_counter_bitmap; + filter->flags = tmp.flags; + r = -EFAULT; - if (copy_from_user(filter, argp, size)) + if (copy_from_user(filter->events, user_filter->events, + sizeof(filter->events[0]) * filter->nevents)) goto cleanup; - /* Restore the verified state to guard against TOCTOU attacks. */ - *filter = tmp; - - remove_impossible_events(filter); - - /* - * Sort the in-kernel list so that we can search it with bsearch. - */ - sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL); + r = prepare_filter_lists(filter); + if (r) + goto cleanup; mutex_lock(&kvm->lock); filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 508074e47bc0..da02a08e21b5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4406,6 +4406,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_PMU_EVENT_FILTER: + case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 55155e262646..76156e372f9c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1175,6 +1175,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 +#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 91d0b78c5177f3e42a4d8738af8ac19c3a90d002 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Tue, 24 Jan 2023 14:36:43 +0100 Subject: inet: Add IP_LOCAL_PORT_RANGE socket option Users who want to share a single public IP address for outgoing connections between several hosts traditionally reach for SNAT. However, SNAT requires state keeping on the node(s) performing the NAT. A stateless alternative exists, where a single IP address used for egress can be shared between several hosts by partitioning the available ephemeral port range. In such a setup: 1. Each host gets assigned a disjoint range of ephemeral ports. 2. Applications open connections from the host-assigned port range. 3. Return traffic gets routed to the host based on both, the destination IP and the destination port. An application which wants to open an outgoing connection (connect) from a given port range today can choose between two solutions: 1. Manually pick the source port by bind()'ing to it before connect()'ing the socket. This approach has a couple of downsides: a) Search for a free port has to be implemented in the user-space. If the chosen 4-tuple happens to be busy, the application needs to retry from a different local port number. Detecting if 4-tuple is busy can be either easy (TCP) or hard (UDP). In TCP case, the application simply has to check if connect() returned an error (EADDRNOTAVAIL). That is assuming that the local port sharing was enabled (REUSEADDR) by all the sockets. # Assume desired local port range is 60_000-60_511 s = socket(AF_INET, SOCK_STREAM) s.setsockopt(SOL_SOCKET, SO_REUSEADDR, 1) s.bind(("192.0.2.1", 60_000)) s.connect(("1.1.1.1", 53)) # Fails only if 192.0.2.1:60000 -> 1.1.1.1:53 is busy # Application must retry with another local port In case of UDP, the network stack allows binding more than one socket to the same 4-tuple, when local port sharing is enabled (REUSEADDR). Hence detecting the conflict is much harder and involves querying sock_diag and toggling the REUSEADDR flag [1]. b) For TCP, bind()-ing to a port within the ephemeral port range means that no connecting sockets, that is those which leave it to the network stack to find a free local port at connect() time, can use the this port. IOW, the bind hash bucket tb->fastreuse will be 0 or 1, and the port will be skipped during the free port search at connect() time. 2. Isolate the app in a dedicated netns and use the use the per-netns ip_local_port_range sysctl to adjust the ephemeral port range bounds. The per-netns setting affects all sockets, so this approach can be used only if: - there is just one egress IP address, or - the desired egress port range is the same for all egress IP addresses used by the application. For TCP, this approach avoids the downsides of (1). Free port search and 4-tuple conflict detection is done by the network stack: system("sysctl -w net.ipv4.ip_local_port_range='60000 60511'") s = socket(AF_INET, SOCK_STREAM) s.setsockopt(SOL_IP, IP_BIND_ADDRESS_NO_PORT, 1) s.bind(("192.0.2.1", 0)) s.connect(("1.1.1.1", 53)) # Fails if all 4-tuples 192.0.2.1:60000-60511 -> 1.1.1.1:53 are busy For UDP this approach has limited applicability. Setting the IP_BIND_ADDRESS_NO_PORT socket option does not result in local source port being shared with other connected UDP sockets. Hence relying on the network stack to find a free source port, limits the number of outgoing UDP flows from a single IP address down to the number of available ephemeral ports. To put it another way, partitioning the ephemeral port range between hosts using the existing Linux networking API is cumbersome. To address this use case, add a new socket option at the SOL_IP level, named IP_LOCAL_PORT_RANGE. The new option can be used to clamp down the ephemeral port range for each socket individually. The option can be used only to narrow down the per-netns local port range. If the per-socket range lies outside of the per-netns range, the latter takes precedence. UAPI-wise, the low and high range bounds are passed to the kernel as a pair of u16 values in host byte order packed into a u32. This avoids pointer passing. PORT_LO = 40_000 PORT_HI = 40_511 s = socket(AF_INET, SOCK_STREAM) v = struct.pack("I", PORT_HI << 16 | PORT_LO) s.setsockopt(SOL_IP, IP_LOCAL_PORT_RANGE, v) s.bind(("127.0.0.1", 0)) s.getsockname() # Local address between ("127.0.0.1", 40_000) and ("127.0.0.1", 40_511), # if there is a free port. EADDRINUSE otherwise. [1] https://github.com/cloudflare/cloudflare-blog/blob/232b432c1d57/2022-02-connectx/connectx.py#L116 Reviewed-by: Marek Majkowski Reviewed-by: Kuniyuki Iwashima Signed-off-by: Jakub Sitnicki Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_sock.h | 4 ++++ include/net/ip.h | 3 ++- include/uapi/linux/in.h | 1 + net/ipv4/inet_connection_sock.c | 25 +++++++++++++++++++++++-- net/ipv4/inet_hashtables.c | 2 +- net/ipv4/ip_sockglue.c | 18 ++++++++++++++++++ net/ipv4/udp.c | 2 +- net/sctp/socket.c | 2 +- 8 files changed, 51 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index bf5654ce711e..51857117ac09 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -249,6 +249,10 @@ struct inet_sock { __be32 mc_addr; struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; + struct { + __u16 lo; + __u16 hi; + } local_port_range; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ diff --git a/include/net/ip.h b/include/net/ip.h index 144bdfbb25af..c3fffaa92d6e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -340,7 +340,8 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o } \ } -void inet_get_local_port_range(struct net *net, int *low, int *high); +void inet_get_local_port_range(const struct net *net, int *low, int *high); +void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 07a4cb149305..4b7f2df66b99 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -162,6 +162,7 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d1f837579398..6ed7e65de494 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -117,7 +117,7 @@ bool inet_rcv_saddr_any(const struct sock *sk) return !sk->sk_rcv_saddr; } -void inet_get_local_port_range(struct net *net, int *low, int *high) +void inet_get_local_port_range(const struct net *net, int *low, int *high) { unsigned int seq; @@ -130,6 +130,27 @@ void inet_get_local_port_range(struct net *net, int *low, int *high) } EXPORT_SYMBOL(inet_get_local_port_range); +void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct net *net = sock_net(sk); + int lo, hi, sk_lo, sk_hi; + + inet_get_local_port_range(net, &lo, &hi); + + sk_lo = inet->local_port_range.lo; + sk_hi = inet->local_port_range.hi; + + if (unlikely(lo <= sk_lo && sk_lo <= hi)) + lo = sk_lo; + if (unlikely(lo <= sk_hi && sk_hi <= hi)) + hi = sk_hi; + + *low = lo; + *high = hi; +} +EXPORT_SYMBOL(inet_sk_get_local_port_range); + static bool inet_use_bhash2_on_bind(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) @@ -316,7 +337,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret, ports_exhausted: attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0; other_half_scan: - inet_get_local_port_range(net, &low, &high); + inet_sk_get_local_port_range(sk, &low, &high); high++; /* [32768, 60999] -> [32768, 61000[ */ if (high - low < 4) attempt_half = 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7a13dd7f546b..e41fdc38ce19 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1016,7 +1016,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, l3mdev = inet_sk_bound_l3mdev(sk); - inet_get_local_port_range(net, &low, &high); + inet_sk_get_local_port_range(sk, &low, &high); high++; /* [32768, 60999] -> [32768, 61000[ */ remaining = high - low; if (likely(remaining > 1)) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 9f92ae35bb01..b511ff0adc0a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -923,6 +923,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, case IP_CHECKSUM: case IP_RECVFRAGSIZE: case IP_RECVERR_RFC4884: + case IP_LOCAL_PORT_RANGE: if (optlen >= sizeof(int)) { if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; @@ -1365,6 +1366,20 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, WRITE_ONCE(inet->min_ttl, val); break; + case IP_LOCAL_PORT_RANGE: + { + const __u16 lo = val; + const __u16 hi = val >> 16; + + if (optlen != sizeof(__u32)) + goto e_inval; + if (lo != 0 && hi != 0 && lo > hi) + goto e_inval; + + inet->local_port_range.lo = lo; + inet->local_port_range.hi = hi; + break; + } default: err = -ENOPROTOOPT; break; @@ -1743,6 +1758,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MINTTL: val = inet->min_ttl; break; + case IP_LOCAL_PORT_RANGE: + val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9592fe3e444a..c605d171eb2d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -248,7 +248,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, int low, high, remaining; unsigned int rand; - inet_get_local_port_range(net, &low, &high); + inet_sk_get_local_port_range(sk, &low, &high); remaining = (high - low) + 1; rand = get_random_u32(); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a98511b676cd..b91616f819de 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8322,7 +8322,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) int low, high, remaining, index; unsigned int rover; - inet_get_local_port_range(net, &low, &high); + inet_sk_get_local_port_range(sk, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_below(remaining) + low; -- cgit v1.2.3 From d0941130c93515411c8d66fc22bdae407b509a6d Mon Sep 17 00:00:00 2001 From: Jamie Bainbridge Date: Wed, 25 Jan 2023 11:16:52 +1100 Subject: icmp: Add counters for rate limits There are multiple ICMP rate limiting mechanisms: * Global limits: net.ipv4.icmp_msgs_burst/icmp_msgs_per_sec * v4 per-host limits: net.ipv4.icmp_ratelimit/ratemask * v6 per-host limits: net.ipv6.icmp_ratelimit/ratemask However, when ICMP output is limited, there is no way to tell which limit has been hit or even if the limits are responsible for the lack of ICMP output. Add counters for each of the cases above. As we are within local_bh_disable(), use the __INC stats variant. Example output: # nstat -sz "*RateLimit*" IcmpOutRateLimitGlobal 134 0.0 IcmpOutRateLimitHost 770 0.0 Icmp6OutRateLimitHost 84 0.0 Signed-off-by: Jamie Bainbridge Suggested-by: Abhishek Rawal Link: https://lore.kernel.org/r/273b32241e6b7fdc5c609e6f5ebc68caf3994342.1674605770.git.jamie.bainbridge@gmail.com Signed-off-by: Paolo Abeni --- include/uapi/linux/snmp.h | 3 +++ net/ipv4/icmp.c | 3 +++ net/ipv4/proc.c | 8 +++++--- net/ipv6/icmp.c | 4 ++++ net/ipv6/proc.c | 1 + 5 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 6600cb0164c2..26f33a4c253d 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -95,6 +95,8 @@ enum ICMP_MIB_OUTADDRMASKS, /* OutAddrMasks */ ICMP_MIB_OUTADDRMASKREPS, /* OutAddrMaskReps */ ICMP_MIB_CSUMERRORS, /* InCsumErrors */ + ICMP_MIB_RATELIMITGLOBAL, /* OutRateLimitGlobal */ + ICMP_MIB_RATELIMITHOST, /* OutRateLimitHost */ __ICMP_MIB_MAX }; @@ -112,6 +114,7 @@ enum ICMP6_MIB_OUTMSGS, /* OutMsgs */ ICMP6_MIB_OUTERRORS, /* OutErrors */ ICMP6_MIB_CSUMERRORS, /* InCsumErrors */ + ICMP6_MIB_RATELIMITHOST, /* OutRateLimitHost */ __ICMP6_MIB_MAX }; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 46aa2d65e40a..8cebb476b3ab 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -296,6 +296,7 @@ static bool icmpv4_global_allow(struct net *net, int type, int code) if (icmp_global_allow()) return true; + __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } @@ -325,6 +326,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, if (peer) inet_putpeer(peer); out: + if (!rc) + __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); return rc; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f88daace9de3..eaf1d3113b62 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -353,7 +353,7 @@ static void icmp_put(struct seq_file *seq) seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors"); for (i = 0; icmpmibmap[i].name; i++) seq_printf(seq, " In%s", icmpmibmap[i].name); - seq_puts(seq, " OutMsgs OutErrors"); + seq_puts(seq, " OutMsgs OutErrors OutRateLimitGlobal OutRateLimitHost"); for (i = 0; icmpmibmap[i].name; i++) seq_printf(seq, " Out%s", icmpmibmap[i].name); seq_printf(seq, "\nIcmp: %lu %lu %lu", @@ -363,9 +363,11 @@ static void icmp_put(struct seq_file *seq) for (i = 0; icmpmibmap[i].name; i++) seq_printf(seq, " %lu", atomic_long_read(ptr + icmpmibmap[i].index)); - seq_printf(seq, " %lu %lu", + seq_printf(seq, " %lu %lu %lu %lu", snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), - snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS), + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_RATELIMITGLOBAL), + snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_RATELIMITHOST)); for (i = 0; icmpmibmap[i].name; i++) seq_printf(seq, " %lu", atomic_long_read(ptr + (icmpmibmap[i].index | 0x100))); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 9d92d51c4757..79c769c0d113 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -183,6 +183,7 @@ static bool icmpv6_global_allow(struct net *net, int type) if (icmp_global_allow()) return true; + __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } @@ -224,6 +225,9 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, if (peer) inet_putpeer(peer); } + if (!res) + __ICMP6_INC_STATS(net, ip6_dst_idev(dst), + ICMP6_MIB_RATELIMITHOST); dst_release(dst); return res; } diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index d6306aa46bb1..e20b3705c2d2 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -94,6 +94,7 @@ static const struct snmp_mib snmp6_icmp6_list[] = { SNMP_MIB_ITEM("Icmp6OutMsgs", ICMP6_MIB_OUTMSGS), SNMP_MIB_ITEM("Icmp6OutErrors", ICMP6_MIB_OUTERRORS), SNMP_MIB_ITEM("Icmp6InCsumErrors", ICMP6_MIB_CSUMERRORS), + SNMP_MIB_ITEM("Icmp6OutRateLimitHost", ICMP6_MIB_RATELIMITHOST), SNMP_MIB_SENTINEL }; -- cgit v1.2.3 From 15d937d7ca8c55d2b0ce9116e20c780fdd0b67cc Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 10 Nov 2022 15:46:33 +0100 Subject: fuse: add request extension Will need to add supplementary groups to create messages, so add the general concept of a request extension. A request extension is appended to the end of the main request. It has a header indicating the size and type of the extension. The create security context (fuse_secctx_*) is similar to the generic request extension, so include that as well in a backward compatible manner. Add the total extension length to the request header. The offset of the extension block within the request can be calculated by: inh->len - inh->total_extlen * 8 Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 2 ++ fs/fuse/dir.c | 66 +++++++++++++++++++++++++++-------------------- fs/fuse/fuse_i.h | 6 +++-- include/uapi/linux/fuse.h | 28 +++++++++++++++++++- 4 files changed, 71 insertions(+), 31 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e8b60ce72c9a..9f349f834977 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -476,6 +476,8 @@ static void fuse_args_to_req(struct fuse_req *req, struct fuse_args *args) req->in.h.opcode = args->opcode; req->in.h.nodeid = args->nodeid; req->args = args; + if (args->is_ext) + req->in.h.total_extlen = args->in_args[args->ext_idx].size / 8; if (args->end) __set_bit(FR_ASYNC, &req->flags); } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index cd1a071b625a..fa6381f199b3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -466,7 +466,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, } static int get_security_context(struct dentry *entry, umode_t mode, - void **security_ctx, u32 *security_ctxlen) + struct fuse_in_arg *ext) { struct fuse_secctx *fctx; struct fuse_secctx_header *header; @@ -513,14 +513,42 @@ static int get_security_context(struct dentry *entry, umode_t mode, memcpy(ptr, ctx, ctxlen); } - *security_ctxlen = total_len; - *security_ctx = header; + ext->size = total_len; + ext->value = header; err = 0; out_err: kfree(ctx); return err; } +static int get_create_ext(struct fuse_args *args, struct dentry *dentry, + umode_t mode) +{ + struct fuse_conn *fc = get_fuse_conn_super(dentry->d_sb); + struct fuse_in_arg ext = { .size = 0, .value = NULL }; + int err = 0; + + if (fc->init_security) + err = get_security_context(dentry, mode, &ext); + + if (!err && ext.size) { + WARN_ON(args->in_numargs >= ARRAY_SIZE(args->in_args)); + args->is_ext = true; + args->ext_idx = args->in_numargs++; + args->in_args[args->ext_idx] = ext; + } else { + kfree(ext.value); + } + + return err; +} + +static void free_ext_value(struct fuse_args *args) +{ + if (args->is_ext) + kfree(args->in_args[args->ext_idx].value); +} + /* * Atomic create+open operation * @@ -541,8 +569,6 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_entry_out outentry; struct fuse_inode *fi; struct fuse_file *ff; - void *security_ctx = NULL; - u32 security_ctxlen; bool trunc = flags & O_TRUNC; /* Userspace expects S_IFREG in create mode */ @@ -586,19 +612,12 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, args.out_args[1].size = sizeof(outopen); args.out_args[1].value = &outopen; - if (fm->fc->init_security) { - err = get_security_context(entry, mode, &security_ctx, - &security_ctxlen); - if (err) - goto out_put_forget_req; - - args.in_numargs = 3; - args.in_args[2].size = security_ctxlen; - args.in_args[2].value = security_ctx; - } + err = get_create_ext(&args, entry, mode); + if (err) + goto out_put_forget_req; err = fuse_simple_request(fm, &args); - kfree(security_ctx); + free_ext_value(&args); if (err) goto out_free_ff; @@ -705,8 +724,6 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, struct dentry *d; int err; struct fuse_forget_link *forget; - void *security_ctx = NULL; - u32 security_ctxlen; if (fuse_is_bad(dir)) return -EIO; @@ -721,21 +738,14 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, args->out_args[0].size = sizeof(outarg); args->out_args[0].value = &outarg; - if (fm->fc->init_security && args->opcode != FUSE_LINK) { - err = get_security_context(entry, mode, &security_ctx, - &security_ctxlen); + if (args->opcode != FUSE_LINK) { + err = get_create_ext(args, entry, mode); if (err) goto out_put_forget_req; - - BUG_ON(args->in_numargs != 2); - - args->in_numargs = 3; - args->in_args[2].size = security_ctxlen; - args->in_args[2].value = security_ctx; } err = fuse_simple_request(fm, args); - kfree(security_ctx); + free_ext_value(args); if (err) goto out_put_forget_req; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index c673faefdcb9..ac300f14aa2d 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -249,8 +249,9 @@ struct fuse_page_desc { struct fuse_args { uint64_t nodeid; uint32_t opcode; - unsigned short in_numargs; - unsigned short out_numargs; + uint8_t in_numargs; + uint8_t out_numargs; + uint8_t ext_idx; bool force:1; bool noreply:1; bool nocreds:1; @@ -261,6 +262,7 @@ struct fuse_args { bool page_zeroing:1; bool page_replace:1; bool may_block:1; + bool is_ext:1; struct fuse_in_arg in_args[3]; struct fuse_arg out_args[2]; void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index e3c54109bae9..c71f12429e3d 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -201,6 +201,9 @@ * 7.38 * - add FUSE_EXPIRE_ONLY flag to fuse_notify_inval_entry * - add FOPEN_PARALLEL_DIRECT_WRITES + * - add total_extlen to fuse_in_header + * - add FUSE_MAX_NR_SECCTX + * - add extension header */ #ifndef _LINUX_FUSE_H @@ -503,6 +506,15 @@ struct fuse_file_lock { */ #define FUSE_EXPIRE_ONLY (1 << 0) +/** + * extension type + * FUSE_MAX_NR_SECCTX: maximum value of &fuse_secctx_header.nr_secctx + */ +enum fuse_ext_type { + /* Types 0..31 are reserved for fuse_secctx_header */ + FUSE_MAX_NR_SECCTX = 31, +}; + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -886,7 +898,8 @@ struct fuse_in_header { uint32_t uid; uint32_t gid; uint32_t pid; - uint32_t padding; + uint16_t total_extlen; /* length of extensions in 8byte units */ + uint16_t padding; }; struct fuse_out_header { @@ -1047,4 +1060,17 @@ struct fuse_secctx_header { uint32_t nr_secctx; }; +/** + * struct fuse_ext_header - extension header + * @size: total size of this extension including this header + * @type: type of extension + * + * This is made compatible with fuse_secctx_header by using type values > + * FUSE_MAX_NR_SECCTX + */ +struct fuse_ext_header { + uint32_t size; + uint32_t type; +}; + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From 8ed7cb3f279fe67a93f407ee2ec3ea661a483a65 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 10 Nov 2022 15:46:33 +0100 Subject: fuse: optional supplementary group in create requests Permission to create an object (create, mkdir, symlink, mknod) needs to take supplementary groups into account. Add a supplementary group request extension. This can contain an arbitrary number of group IDs and can be added to any request. This extension is not added to any request by default. Add FUSE_CREATE_SUPP_GROUP init flag to enable supplementary group info in creation requests. This adds just a single supplementary group that matches the parent group in the case described above. In other cases the extension is not added. Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 64 ++++++++++++++++++++++++++++++++++++++++++++--- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 4 ++- include/uapi/linux/fuse.h | 17 +++++++++++++ 4 files changed, 84 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index fa6381f199b3..0c1d7e387f0d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -521,7 +521,63 @@ out_err: return err; } -static int get_create_ext(struct fuse_args *args, struct dentry *dentry, +static void *extend_arg(struct fuse_in_arg *buf, u32 bytes) +{ + void *p; + u32 newlen = buf->size + bytes; + + p = krealloc(buf->value, newlen, GFP_KERNEL); + if (!p) { + kfree(buf->value); + buf->size = 0; + buf->value = NULL; + return NULL; + } + + memset(p + buf->size, 0, bytes); + buf->value = p; + buf->size = newlen; + + return p + newlen - bytes; +} + +static u32 fuse_ext_size(size_t size) +{ + return FUSE_REC_ALIGN(sizeof(struct fuse_ext_header) + size); +} + +/* + * This adds just a single supplementary group that matches the parent's group. + */ +static int get_create_supp_group(struct inode *dir, struct fuse_in_arg *ext) +{ + struct fuse_conn *fc = get_fuse_conn(dir); + struct fuse_ext_header *xh; + struct fuse_supp_groups *sg; + kgid_t kgid = dir->i_gid; + gid_t parent_gid = from_kgid(fc->user_ns, kgid); + u32 sg_len = fuse_ext_size(sizeof(*sg) + sizeof(sg->groups[0])); + + if (parent_gid == (gid_t) -1 || gid_eq(kgid, current_fsgid()) || + !in_group_p(kgid)) + return 0; + + xh = extend_arg(ext, sg_len); + if (!xh) + return -ENOMEM; + + xh->size = sg_len; + xh->type = FUSE_EXT_GROUPS; + + sg = (struct fuse_supp_groups *) &xh[1]; + sg->nr_groups = 1; + sg->groups[0] = parent_gid; + + return 0; +} + +static int get_create_ext(struct fuse_args *args, + struct inode *dir, struct dentry *dentry, umode_t mode) { struct fuse_conn *fc = get_fuse_conn_super(dentry->d_sb); @@ -530,6 +586,8 @@ static int get_create_ext(struct fuse_args *args, struct dentry *dentry, if (fc->init_security) err = get_security_context(dentry, mode, &ext); + if (!err && fc->create_supp_group) + err = get_create_supp_group(dir, &ext); if (!err && ext.size) { WARN_ON(args->in_numargs >= ARRAY_SIZE(args->in_args)); @@ -612,7 +670,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, args.out_args[1].size = sizeof(outopen); args.out_args[1].value = &outopen; - err = get_create_ext(&args, entry, mode); + err = get_create_ext(&args, dir, entry, mode); if (err) goto out_put_forget_req; @@ -739,7 +797,7 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, args->out_args[0].value = &outarg; if (args->opcode != FUSE_LINK) { - err = get_create_ext(args, entry, mode); + err = get_create_ext(args, dir, entry, mode); if (err) goto out_put_forget_req; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ac300f14aa2d..e13a8eff2e3d 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -783,6 +783,9 @@ struct fuse_conn { /* Initialize security xattrs when creating a new inode */ unsigned int init_security:1; + /* Add supplementary group info when creating a new inode */ + unsigned int create_supp_group:1; + /* Does the filesystem support per inode DAX? */ unsigned int inode_dax:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 6b3beda16c1b..114bdb3f7ccb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1201,6 +1201,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->setxattr_ext = 1; if (flags & FUSE_SECURITY_CTX) fc->init_security = 1; + if (flags & FUSE_CREATE_SUPP_GROUP) + fc->create_supp_group = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1246,7 +1248,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | - FUSE_SECURITY_CTX; + FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index c71f12429e3d..1b9d0dfae72d 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -204,6 +204,8 @@ * - add total_extlen to fuse_in_header * - add FUSE_MAX_NR_SECCTX * - add extension header + * - add FUSE_EXT_GROUPS + * - add FUSE_CREATE_SUPP_GROUP */ #ifndef _LINUX_FUSE_H @@ -365,6 +367,8 @@ struct fuse_file_lock { * FUSE_SECURITY_CTX: add security context to create, mkdir, symlink, and * mknod * FUSE_HAS_INODE_DAX: use per inode DAX + * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, + * symlink and mknod (single group that matches parent) */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -401,6 +405,7 @@ struct fuse_file_lock { /* bits 32..63 get shifted down 32 bits into the flags2 field */ #define FUSE_SECURITY_CTX (1ULL << 32) #define FUSE_HAS_INODE_DAX (1ULL << 33) +#define FUSE_CREATE_SUPP_GROUP (1ULL << 34) /** * CUSE INIT request/reply flags @@ -509,10 +514,12 @@ struct fuse_file_lock { /** * extension type * FUSE_MAX_NR_SECCTX: maximum value of &fuse_secctx_header.nr_secctx + * FUSE_EXT_GROUPS: &fuse_supp_groups extension */ enum fuse_ext_type { /* Types 0..31 are reserved for fuse_secctx_header */ FUSE_MAX_NR_SECCTX = 31, + FUSE_EXT_GROUPS = 32, }; enum fuse_opcode { @@ -1073,4 +1080,14 @@ struct fuse_ext_header { uint32_t type; }; +/** + * struct fuse_supp_groups - Supplementary group extension + * @nr_groups: number of supplementary groups + * @groups: flexible array of group IDs + */ +struct fuse_supp_groups { + uint32_t nr_groups; + uint32_t groups[]; +}; + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From 36632d062975a9ff4410c90dd6d37922b68d0920 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 11:05:11 -0800 Subject: io_uring: Replace 0-length array with flexible array Zero-length arrays are deprecated[1]. Replace struct io_uring_buf_ring's "bufs" with a flexible array member. (How is the size of this array verified?) Detected with GCC 13, using -fstrict-flex-arrays=3: In function 'io_ring_buffer_select', inlined from 'io_buffer_select' at io_uring/kbuf.c:183:10: io_uring/kbuf.c:141:23: warning: array subscript 255 is outside the bounds of an interior zero-length array 'struct io_uring_buf[0]' [-Wzero-length-bounds] 141 | buf = &br->bufs[head]; | ^~~~~~~~~~~~~~~ In file included from include/linux/io_uring.h:7, from io_uring/kbuf.c:10: include/uapi/linux/io_uring.h: In function 'io_buffer_select': include/uapi/linux/io_uring.h:628:41: note: while referencing 'bufs' 628 | struct io_uring_buf bufs[0]; | ^~~~ [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Fixes: c7fb19428d67 ("io_uring: add support for ring mapped supplied buffers") Cc: Jens Axboe Cc: Pavel Begunkov Cc: "Gustavo A. R. Silva" Cc: stable@vger.kernel.org Cc: io-uring@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20230105190507.gonna.131-kees@kernel.org --- 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 2780bce62faf..434f62e0fb72 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -625,7 +625,7 @@ struct io_uring_buf_ring { __u16 resv3; __u16 tail; }; - struct io_uring_buf bufs[0]; + __DECLARE_FLEX_ARRAY(struct io_uring_buf, bufs); }; }; -- cgit v1.2.3 From cbeb47a7b5f003429ded32b1fb3a7108ce5c1b54 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 3 Jan 2023 08:05:07 -0800 Subject: io_uring/msg_ring: Pass custom flags to the cqe This patch adds a new flag (IORING_MSG_RING_FLAGS_PASS) in the message ring operations (IORING_OP_MSG_RING). This new flag enables the sender to specify custom flags, which will be copied over to cqe->flags in the receiving ring. These custom flags should be specified using the sqe->file_index field. This mechanism provides additional flexibility when sending messages between rings. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20230103160507.617416-1-leitao@debian.org Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ io_uring/msg_ring.c | 24 +++++++++++++++++++----- 2 files changed, 21 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 2780bce62faf..636a4c2c1294 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -347,6 +347,8 @@ enum { * applicable for IORING_MSG_DATA, obviously. */ #define IORING_MSG_RING_CQE_SKIP (1U << 0) +/* Pass through the flags from sqe->file_index to cqe->flags */ +#define IORING_MSG_RING_FLAGS_PASS (1U << 1) /* * IO completion data structure (Completion Queue Entry) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 15602a136821..27992bda1ffa 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -13,6 +13,11 @@ #include "filetable.h" #include "msg_ring.h" + +/* All valid masks for MSG_RING */ +#define IORING_MSG_RING_MASK (IORING_MSG_RING_CQE_SKIP | \ + IORING_MSG_RING_FLAGS_PASS) + struct io_msg { struct file *file; struct file *src_file; @@ -21,7 +26,10 @@ struct io_msg { u32 len; u32 cmd; u32 src_fd; - u32 dst_fd; + union { + u32 dst_fd; + u32 cqe_flags; + }; u32 flags; }; @@ -114,9 +122,12 @@ static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + u32 flags = 0; int ret; - if (msg->src_fd || msg->dst_fd || msg->flags) + if (msg->src_fd || msg->flags & ~IORING_MSG_RING_FLAGS_PASS) + return -EINVAL; + if (!(msg->flags & IORING_MSG_RING_FLAGS_PASS) && msg->dst_fd) return -EINVAL; if (target_ctx->flags & IORING_SETUP_R_DISABLED) return -EBADFD; @@ -124,15 +135,18 @@ static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) if (io_msg_need_remote(target_ctx)) return io_msg_exec_remote(req, io_msg_tw_complete); + if (msg->flags & IORING_MSG_RING_FLAGS_PASS) + flags = msg->cqe_flags; + ret = -EOVERFLOW; if (target_ctx->flags & IORING_SETUP_IOPOLL) { if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) return -EAGAIN; - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, flags)) ret = 0; io_double_unlock_ctx(target_ctx); } else { - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, flags)) ret = 0; } return ret; @@ -241,7 +255,7 @@ int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) msg->src_fd = READ_ONCE(sqe->addr3); msg->dst_fd = READ_ONCE(sqe->file_index); msg->flags = READ_ONCE(sqe->msg_ring_flags); - if (msg->flags & ~IORING_MSG_RING_CQE_SKIP) + if (msg->flags & ~IORING_MSG_RING_MASK) return -EINVAL; return 0; -- cgit v1.2.3 From abb864d380854b5427b6b070beb2ebc291ce4d1e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 6 Jan 2023 12:17:09 +0800 Subject: ublk_drv: add device parameter UBLK_PARAM_TYPE_DEVT Userspace side only knows device ID, but the associated path of ublkc* and ublkb* could be changed by udev, and that depends on userspace's policy, so add parameter of UBLK_PARAM_TYPE_DEVT for retrieving major/minor of the ublkc* and ublkb*, then user may figure out major/minor of the ublk disks he/she owns. With major/minor, it is easy to find the device node path. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230106041711.914434-5-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 24 +++++++++++++++++++++++- include/uapi/linux/ublk_cmd.h | 13 +++++++++++++ 2 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index b015e46b59bb..75033304b900 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -54,7 +54,8 @@ | UBLK_F_USER_RECOVERY_REISSUE) /* All UBLK_PARAM_TYPE_* should be included here */ -#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) +#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ + UBLK_PARAM_TYPE_DISCARD | UBLK_PARAM_TYPE_DEVT) struct ublk_rq_data { struct llist_node node; @@ -255,6 +256,10 @@ static int ublk_validate_params(const struct ublk_device *ub) return -EINVAL; } + /* dev_t is read-only */ + if (ub->params.types & UBLK_PARAM_TYPE_DEVT) + return -EINVAL; + return 0; } @@ -1777,6 +1782,22 @@ static int ublk_ctrl_get_dev_info(struct ublk_device *ub, return 0; } +/* TYPE_DEVT is readonly, so fill it up before returning to userspace */ +static void ublk_ctrl_fill_params_devt(struct ublk_device *ub) +{ + ub->params.devt.char_major = MAJOR(ub->cdev_dev.devt); + ub->params.devt.char_minor = MINOR(ub->cdev_dev.devt); + + if (ub->ub_disk) { + ub->params.devt.disk_major = MAJOR(disk_devt(ub->ub_disk)); + ub->params.devt.disk_minor = MINOR(disk_devt(ub->ub_disk)); + } else { + ub->params.devt.disk_major = 0; + ub->params.devt.disk_minor = 0; + } + ub->params.types |= UBLK_PARAM_TYPE_DEVT; +} + static int ublk_ctrl_get_params(struct ublk_device *ub, struct io_uring_cmd *cmd) { @@ -1798,6 +1819,7 @@ static int ublk_ctrl_get_params(struct ublk_device *ub, ph.len = sizeof(struct ublk_params); mutex_lock(&ub->mutex); + ublk_ctrl_fill_params_devt(ub); if (copy_to_user(argp, &ub->params, ph.len)) ret = -EFAULT; else diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 8f88e3a29998..4e38b9aa0293 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -214,6 +214,17 @@ struct ublk_param_discard { __u16 reserved0; }; +/* + * read-only, can't set via UBLK_CMD_SET_PARAMS, disk_devt is available + * after device is started + */ +struct ublk_param_devt { + __u32 char_major; + __u32 char_minor; + __u32 disk_major; + __u32 disk_minor; +}; + struct ublk_params { /* * Total length of parameters, userspace has to set 'len' for both @@ -224,10 +235,12 @@ struct ublk_params { __u32 len; #define UBLK_PARAM_TYPE_BASIC (1 << 0) #define UBLK_PARAM_TYPE_DISCARD (1 << 1) +#define UBLK_PARAM_TYPE_DEVT (1 << 2) __u32 types; /* types of parameter included */ struct ublk_param_basic basic; struct ublk_param_discard discard; + struct ublk_param_devt devt; }; #endif -- cgit v1.2.3 From 4093cb5a06343ea3936ae46664d132c82576b153 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 6 Jan 2023 12:17:11 +0800 Subject: ublk_drv: add mechanism for supporting unprivileged ublk device unprivileged ublk device is helpful for container use case, such as: ublk device created in one unprivileged container can be controlled and accessed by this container only. Implement this feature by adding flag of UBLK_F_UNPRIVILEGED_DEV, and if this flag isn't set, any control command has been run from privileged user. Otherwise, any control command can be sent from any unprivileged user, but the user has to be permitted to access the ublk char device to be controlled. In case of UBLK_F_UNPRIVILEGED_DEV: 1) for command UBLK_CMD_ADD_DEV, it is always allowed, and user needs to provide owner's uid/gid in this command, so that udev can set correct ownership for the created ublk device, since the device owner uid/gid can be queried via command of UBLK_CMD_GET_DEV_INFO. 2) for other control commands, they can only be run successfully if the current user is allowed to access the specified ublk char device, for running the permission check, path of the ublk char device has to be provided by these commands. Also add one control of command UBLK_CMD_GET_DEV_INFO2 which always include the char dev path in payload since userspace may not have knowledge if this device is created in unprivileged mode. For applying this mechanism, system administrator needs to take the following policies: 1) chmod 0666 /dev/ublk-control 2) change ownership of ublkcN & ublkbN - chown owner_uid:owner_gid /dev/ublkcN - chown owner_uid:owner_gid /dev/ublkbN Both can be done via one simple udev rule. Userspace: https://github.com/ming1/ubdsrv/tree/unprivileged-ublk 'ublk add -t $TYPE --un_privileged=1' is for creating one un-privileged ublk device if the user is un-privileged. Link: https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/ Suggested-by: Stefan Hajnoczi Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230106041711.914434-7-ming.lei@redhat.com Signed-off-by: Jens Axboe --- Documentation/block/ublk.rst | 49 +++++++++++--- drivers/block/ublk_drv.c | 152 ++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/ublk_cmd.h | 36 +++++++++- 3 files changed, 220 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst index ba45c46cc0da..2916fcf3ab44 100644 --- a/Documentation/block/ublk.rst +++ b/Documentation/block/ublk.rst @@ -144,6 +144,37 @@ managing and controlling ublk devices with help of several control commands: For retrieving device info via ``ublksrv_ctrl_dev_info``. It is the server's responsibility to save IO target specific info in userspace. +- ``UBLK_CMD_GET_DEV_INFO2`` + Same purpose with ``UBLK_CMD_GET_DEV_INFO``, but ublk server has to + provide path of the char device of ``/dev/ublkc*`` for kernel to run + permission check, and this command is added for supporting unprivileged + ublk device, and introduced with ``UBLK_F_UNPRIVILEGED_DEV`` together. + Only the user owning the requested device can retrieve the device info. + + How to deal with userspace/kernel compatibility: + + 1) if kernel is capable of handling ``UBLK_F_UNPRIVILEGED_DEV`` + If ublk server supports ``UBLK_F_UNPRIVILEGED_DEV``: + ublk server should send ``UBLK_CMD_GET_DEV_INFO2``, given anytime + unprivileged application needs to query devices the current user owns, + when the application has no idea if ``UBLK_F_UNPRIVILEGED_DEV`` is set + given the capability info is stateless, and application should always + retrieve it via ``UBLK_CMD_GET_DEV_INFO2`` + + If ublk server doesn't support ``UBLK_F_UNPRIVILEGED_DEV``: + ``UBLK_CMD_GET_DEV_INFO`` is always sent to kernel, and the feature of + UBLK_F_UNPRIVILEGED_DEV isn't available for user + + 2) if kernel isn't capable of handling ``UBLK_F_UNPRIVILEGED_DEV`` + If ublk server supports ``UBLK_F_UNPRIVILEGED_DEV``: + ``UBLK_CMD_GET_DEV_INFO2`` is tried first, and will be failed, then + ``UBLK_CMD_GET_DEV_INFO`` needs to be retried given + ``UBLK_F_UNPRIVILEGED_DEV`` can't be set + + If ublk server doesn't support ``UBLK_F_UNPRIVILEGED_DEV``: + ``UBLK_CMD_GET_DEV_INFO`` is always sent to kernel, and the feature of + ``UBLK_F_UNPRIVILEGED_DEV`` isn't available for user + - ``UBLK_CMD_START_USER_RECOVERY`` This command is valid if ``UBLK_F_USER_RECOVERY`` feature is enabled. This @@ -180,6 +211,15 @@ managing and controlling ublk devices with help of several control commands: double-write since the driver may issue the same I/O request twice. It might be useful to a read-only FS or a VM backend. +Unprivileged ublk device is supported by passing ``UBLK_F_UNPRIVILEGED_DEV``. +Once the flag is set, all control commands can be sent by unprivileged +user. Except for command of ``UBLK_CMD_ADD_DEV``, permission check on +the specified char device(``/dev/ublkc*``) is done for all other control +commands by ublk driver, for doing that, path of the char device has to +be provided in these commands' payload from ublk server. With this way, +ublk device becomes container-ware, and device created in one container +can be controlled/accessed just inside this container. + Data plane ---------- @@ -254,15 +294,6 @@ with specified IO tag in the command data: Future development ================== -Container-aware ublk deivice ----------------------------- - -ublk driver doesn't handle any IO logic. Its function is well defined -for now and very limited userspace interfaces are needed, which is also -well defined too. It is possible to make ublk devices container-aware block -devices in future as Stefan Hajnoczi suggested [#stefan]_, by removing -ADMIN privilege. - Zero copy --------- diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 883f7974d105..a725a236a38f 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #define UBLK_MINORS (1U << MINORBITS) @@ -51,7 +52,8 @@ | UBLK_F_URING_CMD_COMP_IN_TASK \ | UBLK_F_NEED_GET_DATA \ | UBLK_F_USER_RECOVERY \ - | UBLK_F_USER_RECOVERY_REISSUE) + | UBLK_F_USER_RECOVERY_REISSUE \ + | UBLK_F_UNPRIVILEGED_DEV) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ @@ -1618,6 +1620,17 @@ out_free_cpumask: return ret; } +static void ublk_store_owner_uid_gid(struct ublksrv_ctrl_dev_info *info) +{ + kuid_t uid; + kgid_t gid; + + current_uid_gid(&uid, &gid); + + info->owner_uid = from_kuid(&init_user_ns, uid); + info->owner_gid = from_kgid(&init_user_ns, gid); +} + static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) { pr_devel("%s: dev id %d flags %llx\n", __func__, @@ -1641,15 +1654,26 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) __func__, header->queue_id); return -EINVAL; } + if (copy_from_user(&info, argp, sizeof(info))) return -EFAULT; - ublk_dump_dev_info(&info); + + if (capable(CAP_SYS_ADMIN)) + info.flags &= ~UBLK_F_UNPRIVILEGED_DEV; + else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV)) + return -EPERM; + + /* the created device is always owned by current user */ + ublk_store_owner_uid_gid(&info); + if (header->dev_id != info.dev_id) { pr_warn("%s: dev id not match %u %u\n", __func__, header->dev_id, info.dev_id); return -EINVAL; } + ublk_dump_dev_info(&info); + ret = mutex_lock_killable(&ublk_ctl_mutex); if (ret) return ret; @@ -1982,6 +2006,115 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, return ret; } +/* + * All control commands are sent via /dev/ublk-control, so we have to check + * the destination device's permission + */ +static int ublk_char_dev_permission(struct ublk_device *ub, + const char *dev_path, int mask) +{ + int err; + struct path path; + struct kstat stat; + + err = kern_path(dev_path, LOOKUP_FOLLOW, &path); + if (err) + return err; + + err = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT); + if (err) + goto exit; + + err = -EPERM; + if (stat.rdev != ub->cdev_dev.devt || !S_ISCHR(stat.mode)) + goto exit; + + err = inode_permission(&init_user_ns, + d_backing_inode(path.dentry), mask); +exit: + path_put(&path); + return err; +} + +static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, + struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + bool unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV; + void __user *argp = (void __user *)(unsigned long)header->addr; + char *dev_path = NULL; + int ret = 0; + int mask; + + if (!unprivileged) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* + * The new added command of UBLK_CMD_GET_DEV_INFO2 includes + * char_dev_path in payload too, since userspace may not + * know if the specified device is created as unprivileged + * mode. + */ + if (cmd->cmd_op != UBLK_CMD_GET_DEV_INFO2) + return 0; + } + + /* + * User has to provide the char device path for unprivileged ublk + * + * header->addr always points to the dev path buffer, and + * header->dev_path_len records length of dev path buffer. + */ + if (!header->dev_path_len || header->dev_path_len > PATH_MAX) + return -EINVAL; + + if (header->len < header->dev_path_len) + return -EINVAL; + + dev_path = kmalloc(header->dev_path_len + 1, GFP_KERNEL); + if (!dev_path) + return -ENOMEM; + + ret = -EFAULT; + if (copy_from_user(dev_path, argp, header->dev_path_len)) + goto exit; + dev_path[header->dev_path_len] = 0; + + ret = -EINVAL; + switch (cmd->cmd_op) { + case UBLK_CMD_GET_DEV_INFO: + case UBLK_CMD_GET_DEV_INFO2: + case UBLK_CMD_GET_QUEUE_AFFINITY: + case UBLK_CMD_GET_PARAMS: + mask = MAY_READ; + break; + case UBLK_CMD_START_DEV: + case UBLK_CMD_STOP_DEV: + case UBLK_CMD_ADD_DEV: + case UBLK_CMD_DEL_DEV: + case UBLK_CMD_SET_PARAMS: + case UBLK_CMD_START_USER_RECOVERY: + case UBLK_CMD_END_USER_RECOVERY: + mask = MAY_READ | MAY_WRITE; + break; + default: + goto exit; + } + + ret = ublk_char_dev_permission(ub, dev_path, mask); + if (!ret) { + header->len -= header->dev_path_len; + header->addr += header->dev_path_len; + } + pr_devel("%s: dev id %d cmd_op %x uid %d gid %d path %s ret %d\n", + __func__, ub->ub_number, cmd->cmd_op, + ub->dev_info.owner_uid, ub->dev_info.owner_gid, + dev_path, ret); +exit: + kfree(dev_path); + return ret; +} + static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -1997,17 +2130,21 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (!(issue_flags & IO_URING_F_SQE128)) goto out; - ret = -EPERM; - if (!capable(CAP_SYS_ADMIN)) - goto out; - if (cmd->cmd_op != UBLK_CMD_ADD_DEV) { ret = -ENODEV; ub = ublk_get_device_from_id(header->dev_id); if (!ub) goto out; + + ret = ublk_ctrl_uring_cmd_permission(ub, cmd); + } else { + /* ADD_DEV permission check is done in command handler */ + ret = 0; } + if (ret) + goto put_dev; + switch (cmd->cmd_op) { case UBLK_CMD_START_DEV: ret = ublk_ctrl_start_dev(ub, cmd); @@ -2016,6 +2153,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = ublk_ctrl_stop_dev(ub); break; case UBLK_CMD_GET_DEV_INFO: + case UBLK_CMD_GET_DEV_INFO2: ret = ublk_ctrl_get_dev_info(ub, cmd); break; case UBLK_CMD_ADD_DEV: @@ -2043,6 +2181,8 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = -ENOTSUPP; break; } + + put_dev: if (ub) ublk_put_device(ub); out: diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 4e38b9aa0293..f6238ccc7800 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -19,6 +19,8 @@ #define UBLK_CMD_GET_PARAMS 0x09 #define UBLK_CMD_START_USER_RECOVERY 0x10 #define UBLK_CMD_END_USER_RECOVERY 0x11 +#define UBLK_CMD_GET_DEV_INFO2 0x12 + /* * IO commands, issued by ublk server, and handled by ublk driver. * @@ -79,6 +81,27 @@ #define UBLK_F_USER_RECOVERY_REISSUE (1UL << 4) +/* + * Unprivileged user can create /dev/ublkcN and /dev/ublkbN. + * + * /dev/ublk-control needs to be available for unprivileged user, and it + * can be done via udev rule to make all control commands available to + * unprivileged user. Except for the command of UBLK_CMD_ADD_DEV, all + * other commands are only allowed for the owner of the specified device. + * + * When userspace sends UBLK_CMD_ADD_DEV, the device pair's owner_uid and + * owner_gid are stored to ublksrv_ctrl_dev_info by kernel, so far only + * the current user's uid/gid is stored, that said owner of the created + * device is always the current user. + * + * We still need udev rule to apply OWNER/GROUP with the stored owner_uid + * and owner_gid. + * + * Then ublk server can be run as unprivileged user, and /dev/ublkbN can + * be accessed and managed by its owner represented by owner_uid/owner_gid. + */ +#define UBLK_F_UNPRIVILEGED_DEV (1UL << 5) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -98,7 +121,15 @@ struct ublksrv_ctrl_cmd { __u64 addr; /* inline data */ - __u64 data[2]; + __u64 data[1]; + + /* + * Used for UBLK_F_UNPRIVILEGED_DEV and UBLK_CMD_GET_DEV_INFO2 + * only, include null char + */ + __u16 dev_path_len; + __u16 pad; + __u32 reserved; }; struct ublksrv_ctrl_dev_info { @@ -118,7 +149,8 @@ struct ublksrv_ctrl_dev_info { /* For ublksrv internal use, invisible to ublk driver */ __u64 ublksrv_flags; - __u64 reserved0; + __u32 owner_uid; /* store by kernel */ + __u32 owner_gid; /* store by kernel */ __u64 reserved1; __u64 reserved2; }; -- cgit v1.2.3 From 5e6a51787fef20b849682d8c49ec9c2beed5c373 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 24 Jan 2023 15:38:38 +0200 Subject: uuid: Decouple guid_t and uuid_le types and respective macros The guid_t type and respective macros are being used internally only. The uuid_le has its user outside the kernel. Decouple these types and macros, and make guid_t completely internal type to the kernel. Signed-off-by: Andy Shevchenko Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230124133838.22645-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 +- include/linux/uuid.h | 20 ++++++++++++++++---- include/uapi/linux/uuid.h | 12 ++++-------- 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 1397e8db4cf1..1f61dc5c7847 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10566,6 +10566,7 @@ F: drivers/watchdog/mei_wdt.c F: include/linux/mei_aux.h F: include/linux/mei_cl_bus.h F: include/uapi/linux/mei.h +F: include/uapi/linux/uuid.h F: samples/mei/* INTEL MAX 10 BMC MFD DRIVER @@ -21829,7 +21830,6 @@ L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.infradead.org/users/hch/uuid.git F: include/linux/uuid.h -F: include/uapi/linux/uuid.h F: lib/test_uuid.c F: lib/uuid.c diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 8cdc0d3567cd..5be158a49e11 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -8,15 +8,25 @@ #ifndef _LINUX_UUID_H_ #define _LINUX_UUID_H_ -#include #include #define UUID_SIZE 16 +typedef struct { + __u8 b[UUID_SIZE]; +} guid_t; + typedef struct { __u8 b[UUID_SIZE]; } uuid_t; +#define GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((guid_t) \ +{{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) + #define UUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ ((uuid_t) \ {{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ @@ -97,10 +107,12 @@ extern const u8 uuid_index[16]; int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); -/* backwards compatibility, don't use in new code */ -static inline int uuid_le_cmp(const guid_t u1, const guid_t u2) +/* MEI UUID type, don't use anywhere else */ +#include + +static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) { - return memcmp(&u1, &u2, sizeof(guid_t)); + return memcmp(&u1, &u2, sizeof(uuid_le)); } #endif diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index c0f4bd9b040e..96ac684a4b2f 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* DO NOT USE in new code! This is solely for MEI due to legacy reasons */ /* - * UUID/GUID definition + * MEI UUID definition * * Copyright (C) 2010, Intel Corp. * Huang Ying @@ -14,19 +14,15 @@ typedef struct { __u8 b[16]; -} guid_t; +} uuid_le; -#define GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ -((guid_t) \ +#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_le) \ {{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ (b) & 0xff, ((b) >> 8) & 0xff, \ (c) & 0xff, ((c) >> 8) & 0xff, \ (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) -/* backwards compatibility, don't use in new code */ -typedef guid_t uuid_le; -#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ - GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) #define NULL_UUID_LE \ UUID_LE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ 0x00, 0x00, 0x00, 0x00) -- cgit v1.2.3 From 8e08bb75b60f7f9ed319185cef80188b87d9b43a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 28 Jan 2023 10:58:37 -0500 Subject: packet: add TP_STATUS_GSO_TCP for tp_status Introduce TP_STATUS_GSO_TCP tp_status flag to tell the af_packet user that this is a TCP GSO packet. When parsing IPv4 BIG TCP packets in tcpdump/libpcap, it can use tp_len as the IPv4 packet len when this flag is set, as iph tot_len is set to 0 for IPv4 BIG TCP packets. Signed-off-by: Xin Long Reviewed-by: David Ahern Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_packet.h | 1 + net/packet/af_packet.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index a8516b3594a4..78c981d6a9d4 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -115,6 +115,7 @@ struct tpacket_auxdata { #define TP_STATUS_BLK_TMO (1 << 5) #define TP_STATUS_VLAN_TPID_VALID (1 << 6) /* auxdata has valid tp_vlan_tpid */ #define TP_STATUS_CSUM_VALID (1 << 7) +#define TP_STATUS_GSO_TCP (1 << 8) /* Tx ring - header status */ #define TP_STATUS_AVAILABLE 0 diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b5ab98ca2511..8ffb19c643ab 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2296,6 +2296,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; + if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) + status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; @@ -3522,6 +3524,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; + if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) + aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; -- cgit v1.2.3 From 9eefedd58ae1daece2ba907849a44db2941fb4b0 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 28 Jan 2023 10:58:38 -0500 Subject: net: add gso_ipv4_max_size and gro_ipv4_max_size per device This patch introduces gso_ipv4_max_size and gro_ipv4_max_size per device and adds netlink attributes for them, so that IPV4 BIG TCP can be guarded by a separate tunable in the next patch. To not break the old application using "gso/gro_max_size" for IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size" in netif_set_gso/gro_max_size() if the new size isn't greater than GSO_LEGACY_MAX_SIZE, so that nothing will change even if userspace doesn't realize the new netlink attributes. Signed-off-by: Xin Long Reviewed-by: David Ahern Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 ++++++ include/uapi/linux/if_link.h | 3 +++ net/core/dev.c | 4 ++++ net/core/dev.h | 18 ++++++++++++++++++ net/core/rtnetlink.c | 33 +++++++++++++++++++++++++++++++++ 5 files changed, 64 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2466afa25078..d5ef4c1fedd2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1964,6 +1964,8 @@ enum netdev_ml_priv_type { * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO * @tso_max_segs: Device (as in HW) limit on the max TSO segment count + * @gso_ipv4_max_size: Maximum size of generic segmentation offload, + * for IPv4. * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -2004,6 +2006,8 @@ enum netdev_ml_priv_type { * keep a list of interfaces to be deleted. * @gro_max_size: Maximum size of aggregated packet in generic * receive offload (GRO) + * @gro_ipv4_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO), for IPv4. * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. @@ -2207,6 +2211,7 @@ struct net_device { */ #define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; + unsigned int gro_ipv4_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -2330,6 +2335,7 @@ struct net_device { u16 gso_max_segs; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; + unsigned int gso_ipv4_max_size; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1021a7e47a86..02b87e4c65be 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -374,6 +374,9 @@ enum { IFLA_DEVLINK_PORT, + IFLA_GSO_IPV4_MAX_SIZE, + IFLA_GRO_IPV4_MAX_SIZE, + __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index f72f5c4ee7e2..bb42150a38ec 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3001,6 +3001,8 @@ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); + if (size < READ_ONCE(dev->gso_ipv4_max_size)) + netif_set_gso_ipv4_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); @@ -10614,6 +10616,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; + dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; + dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; diff --git a/net/core/dev.h b/net/core/dev.h index 814ed5b7b960..a065b7571441 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -100,6 +100,8 @@ static inline void netif_set_gso_max_size(struct net_device *dev, { /* dev->gso_max_size is read locklessly from sk_setup_caps() */ WRITE_ONCE(dev->gso_max_size, size); + if (size <= GSO_LEGACY_MAX_SIZE) + WRITE_ONCE(dev->gso_ipv4_max_size, size); } static inline void netif_set_gso_max_segs(struct net_device *dev, @@ -114,6 +116,22 @@ static inline void netif_set_gro_max_size(struct net_device *dev, { /* This pairs with the READ_ONCE() in skb_gro_receive() */ WRITE_ONCE(dev->gro_max_size, size); + if (size <= GRO_LEGACY_MAX_SIZE) + WRITE_ONCE(dev->gro_ipv4_max_size, size); +} + +static inline void netif_set_gso_ipv4_max_size(struct net_device *dev, + unsigned int size) +{ + /* dev->gso_ipv4_max_size is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_ipv4_max_size, size); +} + +static inline void netif_set_gro_ipv4_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_ipv4_max_size, size); } #endif diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 64289bc98887..b9f584955b77 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1074,6 +1074,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */ + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */ + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */ + + nla_total_size(4) /* IFLA_GSO_IPV4_MAX_SIZE */ + + nla_total_size(4) /* IFLA_GRO_IPV4_MAX_SIZE */ + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */ + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */ + nla_total_size(1) /* IFLA_OPERSTATE */ @@ -1807,6 +1809,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) || + nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, dev->gso_ipv4_max_size) || + nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, dev->gro_ipv4_max_size) || nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) || nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) || #ifdef CONFIG_RPS @@ -1968,6 +1972,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT }, [IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT }, [IFLA_ALLMULTI] = { .type = NLA_REJECT }, + [IFLA_GSO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2883,6 +2889,29 @@ static int do_setlink(const struct sk_buff *skb, } } + if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { + u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); + + if (max_size > dev->tso_max_size) { + err = -EINVAL; + goto errout; + } + + if (dev->gso_ipv4_max_size ^ max_size) { + netif_set_gso_ipv4_max_size(dev, max_size); + status |= DO_SETLINK_MODIFIED; + } + } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE]) { + u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]); + + if (dev->gro_ipv4_max_size ^ gro_max_size) { + netif_set_gro_ipv4_max_size(dev, gro_max_size); + status |= DO_SETLINK_MODIFIED; + } + } + if (tb[IFLA_OPERSTATE]) set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); @@ -3325,6 +3354,10 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS])); if (tb[IFLA_GRO_MAX_SIZE]) netif_set_gro_max_size(dev, nla_get_u32(tb[IFLA_GRO_MAX_SIZE])); + if (tb[IFLA_GSO_IPV4_MAX_SIZE]) + netif_set_gso_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE])); + if (tb[IFLA_GRO_IPV4_MAX_SIZE]) + netif_set_gro_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE])); return dev; } -- cgit v1.2.3 From d3d854fd6a1d97157f790604e07f6386e8df8fe4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 1 Feb 2023 11:24:17 +0100 Subject: netdev-genl: create a simple family for netdev stuff Add a Netlink spec-compatible family for netdevs. This is a very simple implementation without much thought going into it. It allows us to reap all the benefits of Netlink specs, one can use the generic client to issue the commands: $ ./cli.py --spec netdev.yaml --dump dev_get [{'ifindex': 1, 'xdp-features': set()}, {'ifindex': 2, 'xdp-features': {'basic', 'ndo-xmit', 'redirect'}}, {'ifindex': 3, 'xdp-features': {'rx-sg'}}] the generic python library does not have flags-by-name support, yet, but we also don't have to carry strings in the messages, as user space can get the names from the spec. Acked-by: Jesper Dangaard Brouer Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Co-developed-by: Kumar Kartikeya Dwivedi Signed-off-by: Kumar Kartikeya Dwivedi Co-developed-by: Marek Majtyka Signed-off-by: Marek Majtyka Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/327ad9c9868becbe1e601b580c962549c8cd81f2.1675245258.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- Documentation/netlink/specs/netdev.yaml | 100 ++++++++++++++++++ include/linux/netdevice.h | 3 + include/net/xdp.h | 3 + include/uapi/linux/netdev.h | 59 +++++++++++ net/core/Makefile | 3 +- net/core/dev.c | 1 + net/core/netdev-genl-gen.c | 48 +++++++++ net/core/netdev-genl-gen.h | 23 ++++ net/core/netdev-genl.c | 179 ++++++++++++++++++++++++++++++++ tools/include/uapi/linux/netdev.h | 59 +++++++++++ 10 files changed, 477 insertions(+), 1 deletion(-) create mode 100644 Documentation/netlink/specs/netdev.yaml create mode 100644 include/uapi/linux/netdev.h create mode 100644 net/core/netdev-genl-gen.c create mode 100644 net/core/netdev-genl-gen.h create mode 100644 net/core/netdev-genl.c create mode 100644 tools/include/uapi/linux/netdev.h (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml new file mode 100644 index 000000000000..b4dcdae54ffd --- /dev/null +++ b/Documentation/netlink/specs/netdev.yaml @@ -0,0 +1,100 @@ +name: netdev + +doc: + netdev configuration over generic netlink. + +definitions: + - + type: flags + name: xdp-act + entries: + - + name: basic + doc: + XDP feautues set supported by all drivers + (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + - + name: redirect + doc: + The netdev supports XDP_REDIRECT + - + name: ndo-xmit + doc: + This feature informs if netdev implements ndo_xdp_xmit callback. + - + name: xsk-zerocopy + doc: + This feature informs if netdev supports AF_XDP in zero copy mode. + - + name: hw-offload + doc: + This feature informs if netdev supports XDP hw oflloading. + - + name: rx-sg + doc: + This feature informs if netdev implements non-linear XDP buffer + support in the driver napi callback. + - + name: ndo-xmit-sg + doc: + This feature informs if netdev implements non-linear XDP buffer + support in ndo_xdp_xmit callback. + +attribute-sets: + - + name: dev + attributes: + - + name: ifindex + doc: netdev ifindex + type: u32 + value: 1 + checks: + min: 1 + - + name: pad + type: pad + - + name: xdp-features + doc: Bitmask of enabled xdp-features. + type: u64 + enum: xdp-act + enum-as-flags: true + +operations: + list: + - + name: dev-get + doc: Get / dump information about a netdev. + value: 1 + attribute-set: dev + do: + request: + attributes: + - ifindex + reply: &dev-all + attributes: + - ifindex + - xdp-features + dump: + reply: *dev-all + - + name: dev-add-ntf + doc: Notification about device appearing. + notify: dev-get + mcgrp: mgmt + - + name: dev-del-ntf + doc: Notification about device disappearing. + notify: dev-get + mcgrp: mgmt + - + name: dev-change-ntf + doc: Notification about device configuration being changed. + notify: dev-get + mcgrp: mgmt + +mcast-groups: + list: + - + name: mgmt diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2466afa25078..0f7967591288 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include @@ -2055,6 +2056,7 @@ struct net_device { /* Read-mostly cache-line for fast-path access */ unsigned int flags; + xdp_features_t xdp_features; unsigned long long priv_flags; const struct net_device_ops *netdev_ops; const struct xdp_metadata_ops *xdp_metadata_ops; @@ -2839,6 +2841,7 @@ enum netdev_cmd { NETDEV_OFFLOAD_XSTATS_DISABLE, NETDEV_OFFLOAD_XSTATS_REPORT_USED, NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, + NETDEV_XDP_FEAT_CHANGE, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); diff --git a/include/net/xdp.h b/include/net/xdp.h index 91292aa13bc0..8d1c86914f4c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -7,6 +7,7 @@ #define __LINUX_NET_XDP_H__ #include /* skb_shared_info */ +#include /** * DOC: XDP RX-queue information @@ -43,6 +44,8 @@ enum xdp_mem_type { MEM_TYPE_MAX, }; +typedef u32 xdp_features_t; + /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h new file mode 100644 index 000000000000..9ee459872600 --- /dev/null +++ b/include/uapi/linux/netdev.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * oflloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" + +#endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/net/core/Makefile b/net/core/Makefile index 10edd66a8a37..8f367813bc68 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -12,7 +12,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o flow_offload.o gro.o + fib_notifier.o xdp.o flow_offload.o gro.o \ + netdev-genl.o netdev-genl-gen.o obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o diff --git a/net/core/dev.c b/net/core/dev.c index f72f5c4ee7e2..9ac0eeb2c8cd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1614,6 +1614,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) + N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c new file mode 100644 index 000000000000..48812ec843f5 --- /dev/null +++ b/net/core/netdev-genl-gen.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN kernel source */ + +#include +#include + +#include "netdev-genl-gen.h" + +#include + +/* NETDEV_CMD_DEV_GET - do */ +static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { + [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +/* Ops table for netdev */ +static const struct genl_split_ops netdev_nl_ops[2] = { + { + .cmd = NETDEV_CMD_DEV_GET, + .doit = netdev_nl_dev_get_doit, + .policy = netdev_dev_get_nl_policy, + .maxattr = NETDEV_A_DEV_IFINDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_DEV_GET, + .dumpit = netdev_nl_dev_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +}; + +static const struct genl_multicast_group netdev_nl_mcgrps[] = { + [NETDEV_NLGRP_MGMT] = { "mgmt", }, +}; + +struct genl_family netdev_nl_family __ro_after_init = { + .name = NETDEV_FAMILY_NAME, + .version = NETDEV_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = netdev_nl_ops, + .n_split_ops = ARRAY_SIZE(netdev_nl_ops), + .mcgrps = netdev_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), +}; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h new file mode 100644 index 000000000000..b16dc7e026bb --- /dev/null +++ b/net/core/netdev-genl-gen.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_NETDEV_GEN_H +#define _LINUX_NETDEV_GEN_H + +#include +#include + +#include + +int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); + +enum { + NETDEV_NLGRP_MGMT, +}; + +extern struct genl_family netdev_nl_family; + +#endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c new file mode 100644 index 000000000000..a4270fafdf11 --- /dev/null +++ b/net/core/netdev-genl.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include + +#include "netdev-genl-gen.h" + +static int +netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, + u32 portid, u32 seq, int flags, u32 cmd) +{ + void *hdr; + + hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, + netdev->xdp_features, NETDEV_A_DEV_PAD)) { + genlmsg_cancel(rsp, hdr); + return -EINVAL; + } + + genlmsg_end(rsp, hdr); + + return 0; +} + +static void +netdev_genl_dev_notify(struct net_device *netdev, int cmd) +{ + struct sk_buff *ntf; + + if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev), + NETDEV_NLGRP_MGMT)) + return; + + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!ntf) + return; + + if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) { + nlmsg_free(ntf); + return; + } + + genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf, + 0, NETDEV_NLGRP_MGMT, GFP_KERNEL); +} + +int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *netdev; + struct sk_buff *rsp; + u32 ifindex; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (netdev) + err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid, + info->snd_seq, 0, info->genlhdr->cmd); + else + err = -ENODEV; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + int idx = 0, s_idx; + int h, s_h; + int err; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rtnl_lock(); + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + struct hlist_head *head; + + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry(netdev, head, index_hlist) { + if (idx < s_idx) + goto cont; + err = netdev_nl_dev_fill(netdev, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NETDEV_CMD_DEV_GET); + if (err < 0) + break; +cont: + idx++; + } + } + + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + cb->args[1] = idx; + cb->args[0] = h; + cb->seq = net->dev_base_seq; + + return skb->len; +} + +static int netdev_genl_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_REGISTER: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF); + break; + case NETDEV_UNREGISTER: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF); + break; + case NETDEV_XDP_FEAT_CHANGE: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block netdev_genl_nb = { + .notifier_call = netdev_genl_netdevice_event, +}; + +static int __init netdev_genl_init(void) +{ + int err; + + err = register_netdevice_notifier(&netdev_genl_nb); + if (err) + return err; + + err = genl_register_family(&netdev_nl_family); + if (err) + goto err_unreg_ntf; + + return 0; + +err_unreg_ntf: + unregister_netdevice_notifier(&netdev_genl_nb); + return err; +} + +subsys_initcall(netdev_genl_init); diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h new file mode 100644 index 000000000000..9ee459872600 --- /dev/null +++ b/tools/include/uapi/linux/netdev.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * oflloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" + +#endif /* _UAPI_LINUX_NETDEV_H */ -- cgit v1.2.3 From b507808ebce23561d4ff8c2aa1fb949fe402bc61 Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Thu, 19 Jan 2023 16:03:43 +0000 Subject: mm: implement memory-deny-write-execute as a prctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm: In-kernel support for memory-deny-write-execute (MDWE)", v2. The background to this is that systemd has a configuration option called MemoryDenyWriteExecute [2], implemented as a SECCOMP BPF filter. Its aim is to prevent a user task from inadvertently creating an executable mapping that is (or was) writeable. Since such BPF filter is stateless, it cannot detect mappings that were previously writeable but subsequently changed to read-only. Therefore the filter simply rejects any mprotect(PROT_EXEC). The side-effect is that on arm64 with BTI support (Branch Target Identification), the dynamic loader cannot change an ELF section from PROT_EXEC to PROT_EXEC|PROT_BTI using mprotect(). For libraries, it can resort to unmapping and re-mapping but for the main executable it does not have a file descriptor. The original bug report in the Red Hat bugzilla - [3] - and subsequent glibc workaround for libraries - [4]. This series adds in-kernel support for this feature as a prctl PR_SET_MDWE, that is inherited on fork(). The prctl denies PROT_WRITE | PROT_EXEC mappings. Like the systemd BPF filter it also denies adding PROT_EXEC to mappings. However unlike the BPF filter it only denies it if the mapping didn't previous have PROT_EXEC. This allows to PROT_EXEC -> PROT_EXEC | PROT_BTI with mprotect(), which is a problem with the BPF filter. This patch (of 2): The aim of such policy is to prevent a user task from creating an executable mapping that is also writeable. An example of mmap() returning -EACCESS if the policy is enabled: mmap(0, size, PROT_READ | PROT_WRITE | PROT_EXEC, flags, 0, 0); Similarly, mprotect() would return -EACCESS below: addr = mmap(0, size, PROT_READ | PROT_EXEC, flags, 0, 0); mprotect(addr, size, PROT_READ | PROT_WRITE | PROT_EXEC); The BPF filter that systemd MDWE uses is stateless, and disallows mprotect() with PROT_EXEC completely. This new prctl allows PROT_EXEC to be enabled if it was already PROT_EXEC, which allows the following case: addr = mmap(0, size, PROT_READ | PROT_EXEC, flags, 0, 0); mprotect(addr, size, PROT_READ | PROT_EXEC | PROT_BTI); where PROT_BTI enables branch tracking identification on arm64. Link: https://lkml.kernel.org/r/20230119160344.54358-1-joey.gouly@arm.com Link: https://lkml.kernel.org/r/20230119160344.54358-2-joey.gouly@arm.com Signed-off-by: Joey Gouly Co-developed-by: Catalin Marinas Signed-off-by: Catalin Marinas Cc: Alexander Viro Cc: Jeremy Linton Cc: Kees Cook Cc: Lennart Poettering Cc: Mark Brown Cc: nd Cc: Shuah Khan Cc: Szabolcs Nagy Cc: Topi Miettinen Cc: Zbigniew Jędrzejewski-Szmek Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/mman.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/sched/coredump.h | 6 +++++- include/uapi/linux/prctl.h | 6 ++++++ kernel/sys.c | 33 +++++++++++++++++++++++++++++++++ mm/mmap.c | 10 ++++++++++ mm/mprotect.c | 5 +++++ 6 files changed, 93 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 58b3abd457a3..cee1e4b566d8 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -156,4 +156,38 @@ calc_vm_flag_bits(unsigned long flags) } unsigned long vm_commit_limit(void); + +/* + * Denies creating a writable executable mapping or gaining executable permissions. + * + * This denies the following: + * + * a) mmap(PROT_WRITE | PROT_EXEC) + * + * b) mmap(PROT_WRITE) + * mprotect(PROT_EXEC) + * + * c) mmap(PROT_WRITE) + * mprotect(PROT_READ) + * mprotect(PROT_EXEC) + * + * But allows the following: + * + * d) mmap(PROT_READ | PROT_EXEC) + * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + */ +static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +{ + if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return false; + + if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + return true; + + if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + return true; + + return false; +} + #endif /* _LINUX_MMAN_H */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 8270ad7ae14c..0e17ae7fbfd3 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -81,9 +81,13 @@ static inline int get_dumpable(struct mm_struct *mm) * lifecycle of this mm, just for simplicity. */ #define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ + +#define MMF_HAS_MDWE 28 +#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) + #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK) + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a5e06dcbba13..1312a137f7fb 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -281,6 +281,12 @@ struct prctl_mm_map { # define PR_SME_VL_LEN_MASK 0xffff # define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN 1 + +#define PR_GET_MDWE 66 + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/kernel/sys.c b/kernel/sys.c index 5fd54bf0e886..b3cab94545ed 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2348,6 +2348,33 @@ static int prctl_set_vma(unsigned long opt, unsigned long start, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + if (arg3 || arg4 || arg5) + return -EINVAL; + + if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN)) + return -EINVAL; + + if (bits & PR_MDWE_REFUSE_EXEC_GAIN) + set_bit(MMF_HAS_MDWE, ¤t->mm->flags); + else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return -EPERM; /* Cannot unset the flag */ + + return 0; +} + +static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + + return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ? + PR_MDWE_REFUSE_EXEC_GAIN : 0; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2623,6 +2650,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_MDWE: + error = prctl_set_mdwe(arg2, arg3, arg4, arg5); + break; + case PR_GET_MDWE: + error = prctl_get_mdwe(arg2, arg3, arg4, arg5); + break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; diff --git a/mm/mmap.c b/mm/mmap.c index 335ba3df9898..ffc0815cd7fb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2669,6 +2669,16 @@ cannot_expand: vma_set_anonymous(vma); } + if (map_deny_write_exec(vma, vma->vm_flags)) { + error = -EACCES; + if (file) + goto close_and_free_vma; + else if (vma->vm_file) + goto unmap_and_free_vma; + else + goto free_vma; + } + /* Allow architectures to sanity-check the vm_flags */ if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; diff --git a/mm/mprotect.c b/mm/mprotect.c index 6ecdf0671b81..6a22f3ad9b84 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -799,6 +799,11 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } + if (map_deny_write_exec(vma, newflags)) { + error = -EACCES; + goto out; + } + /* Allow architectures to sanity-check the new flags */ if (!arch_validate_flags(newflags)) { error = -EINVAL; -- cgit v1.2.3 From 17c9b4e1a7d14719378c3eedefc2960018f5a7bb Mon Sep 17 00:00:00 2001 From: Florian Lehner Date: Fri, 3 Feb 2023 13:14:39 +0100 Subject: bpf: fix typo in header for bpf_perf_prog_read_value Fix a simple typo in the documentation for bpf_perf_prog_read_value. Signed-off-by: Florian Lehner Acked-by: John Fastabend Link: https://lore.kernel.org/r/20230203121439.25884-1-dev@der-flo.net Signed-off-by: Martin KaFai Lau --- 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 ba0f0cfb5e42..17afd2b35ee5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2801,7 +2801,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ba0f0cfb5e42..17afd2b35ee5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2801,7 +2801,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see -- cgit v1.2.3 From a1aee20d5db29dc73331067b6a338eb650f0b5f1 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 2 Feb 2023 18:59:26 +0100 Subject: net: bridge: Add netlink knobs for number / maximum MDB entries The previous patch added accounting for number of MDB entries per port and per port-VLAN, and the logic to verify that these values stay within configured bounds. However it didn't provide means to actually configure those bounds or read the occupancy. This patch does that. Two new netlink attributes are added for the MDB occupancy: IFLA_BRPORT_MCAST_N_GROUPS for the per-port occupancy and BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS for the per-port-VLAN occupancy. And another two for the maximum number of MDB entries: IFLA_BRPORT_MCAST_MAX_GROUPS for the per-port maximum, and BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS for the per-port-VLAN one. Note that the two new IFLA_BRPORT_ attributes prompt bumping of RTNL_SLAVE_MAX_TYPE to size the slave attribute tables large enough. The new attributes are used like this: # ip link add name br up type bridge vlan_filtering 1 mcast_snooping 1 \ mcast_vlan_snooping 1 mcast_querier 1 # ip link set dev v1 master br # bridge vlan add dev v1 vid 2 # bridge vlan set dev v1 vid 1 mcast_max_groups 1 # bridge mdb add dev br port v1 grp 230.1.2.3 temp vid 1 # bridge mdb add dev br port v1 grp 230.1.2.4 temp vid 1 Error: bridge: Port-VLAN is already in 1 groups, and mcast_max_groups=1. # bridge link set dev v1 mcast_max_groups 1 # bridge mdb add dev br port v1 grp 230.1.2.3 temp vid 2 Error: bridge: Port is already in 1 groups, and mcast_max_groups=1. # bridge -d link show 5: v1@v2: mtu 1500 master br [...] [...] mcast_n_groups 1 mcast_max_groups 1 # bridge -d vlan show port vlan-id br 1 PVID Egress Untagged state forwarding mcast_router 1 v1 1 PVID Egress Untagged [...] mcast_n_groups 1 mcast_max_groups 1 2 [...] mcast_n_groups 0 mcast_max_groups 0 Signed-off-by: Petr Machata Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 2 ++ include/uapi/linux/if_link.h | 2 ++ net/bridge/br_multicast.c | 15 +++++++++++++++ net/bridge/br_netlink.c | 17 ++++++++++++++++- net/bridge/br_private.h | 6 +++++- net/bridge/br_vlan.c | 11 +++++++---- net/bridge/br_vlan_options.c | 27 ++++++++++++++++++++++++++- net/core/rtnetlink.c | 2 +- 8 files changed, 74 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index d9de241d90f9..d60c456710b3 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -523,6 +523,8 @@ enum { BRIDGE_VLANDB_ENTRY_TUNNEL_INFO, BRIDGE_VLANDB_ENTRY_STATS, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, + BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, __BRIDGE_VLANDB_ENTRY_MAX, }; #define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 02b87e4c65be..57ceb788250f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -567,6 +567,8 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, IFLA_BRPORT_MAB, + IFLA_BRPORT_MCAST_N_GROUPS, + IFLA_BRPORT_MCAST_MAX_GROUPS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b6aa0bad5817..96d1fc78dd39 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -772,6 +772,21 @@ static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) br_multicast_port_ngroups_dec_one(&port->multicast_ctx); } +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_n_entries); +} + +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) +{ + WRITE_ONCE(pmctx->mdb_max_entries, max); +} + +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_max_entries); +} + static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a6133d469885..9173e52b89e2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -202,6 +202,8 @@ static inline size_t br_port_info_size(void) + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ @@ -298,7 +300,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, - p->multicast_eht_hosts_cnt)) + p->multicast_eht_hosts_cnt) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, + br_multicast_ngroups_get(&p->multicast_ctx)) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif @@ -883,6 +889,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, + [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -1017,6 +1025,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { + u32 max_groups; + + max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 49f411a0a1f1..cef5f6ea850c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -978,6 +978,9 @@ void br_multicast_uninit_stats(struct net_bridge *br); void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest); +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx); +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max); +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx); void br_mdb_init(void); void br_mdb_uninit(void); void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1761,7 +1764,8 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v); +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p); size_t br_vlan_opts_nl_size(void); int br_vlan_process_options(const struct net_bridge *br, const struct net_bridge_port *p, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bc75fa1e4666..8a3dbc09ba38 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1816,6 +1816,7 @@ out_err: /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, + const struct net_bridge_port *p, u16 flags, bool dump_stats) { @@ -1842,7 +1843,7 @@ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, goto out_err; if (v_opts) { - if (!br_vlan_opts_fill(skb, v_opts)) + if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) @@ -1925,7 +1926,7 @@ void br_vlan_notify(const struct net_bridge *br, goto out_kfree; } - if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false)) + if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); @@ -2030,7 +2031,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - vlan_flags, dump_stats)) { + p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } @@ -2056,7 +2057,7 @@ update_end: else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - br_vlan_flags(range_start, pvid), + p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } @@ -2131,6 +2132,8 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index a2724d03278c..e378c2f3a9e2 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -48,7 +48,8 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, curr_mc_rtr == range_mc_rtr; } -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p) { if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) || !__vlan_tun_put(skb, v)) @@ -58,6 +59,12 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, br_vlan_multicast_router(v))) return false; + if (p && !br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx) && + (nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + br_multicast_ngroups_get(&v->port_mcast_ctx)) || + nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&v->port_mcast_ctx)))) + return false; #endif return true; @@ -70,6 +77,8 @@ size_t br_vlan_opts_nl_size(void) + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */ #endif + 0; } @@ -212,6 +221,22 @@ static int br_vlan_process_one_opts(const struct net_bridge *br, return err; *changed = true; } + if (tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]) { + u32 val; + + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Can't set mcast_max_groups for non-port vlans"); + return -EINVAL; + } + if (br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx)) { + NL_SET_ERR_MSG_MOD(extack, "Multicast snooping disabled on this VLAN"); + return -EINVAL; + } + + val = nla_get_u32(tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&v->port_mcast_ctx, val); + *changed = true; + } #endif return 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b9f584955b77..5d8eb57867a9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -58,7 +58,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 40 +#define RTNL_SLAVE_MAX_TYPE 42 struct rtnl_link { rtnl_doit_func doit; -- cgit v1.2.3 From 03702d4d29be4e2510ec80b248dbbde4e57030d9 Mon Sep 17 00:00:00 2001 From: "Herton R. Krzesinski" Date: Fri, 3 Feb 2023 13:04:48 -0300 Subject: uapi: add missing ip/ipv6 header dependencies for linux/stddef.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 58e0be1ef6118 ("net: use struct_group to copy ip/ipv6 header addresses"), ip and ipv6 headers started to use the __struct_group definition, which is defined at include/uapi/linux/stddef.h. However, linux/stddef.h isn't explicitly included in include/uapi/linux/{ip,ipv6}.h, which breaks build of xskxceiver bpf selftest if you install the uapi headers in the system: $ make V=1 xskxceiver -C tools/testing/selftests/bpf ... make: Entering directory '(...)/tools/testing/selftests/bpf' gcc -g -O0 -rdynamic -Wall -Werror (...) In file included from xskxceiver.c:79: /usr/include/linux/ip.h:103:9: error: expected specifier-qualifier-list before ‘__struct_group’ 103 | __struct_group(/* no tag */, addrs, /* no attrs */, | ^~~~~~~~~~~~~~ ... Include the missing dependency in ip.h and do the same for the ipv6.h header. Fixes: 58e0be1ef611 ("net: use struct_group to copy ip/ipv6 header addresses") Signed-off-by: Herton R. Krzesinski Reviewed-by: Carlos O'Donell Tested-by: Carlos O'Donell Signed-off-by: David S. Miller --- include/uapi/linux/ip.h | 1 + include/uapi/linux/ipv6.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 874a92349bf5..283dec7e3645 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -18,6 +18,7 @@ #ifndef _UAPI_LINUX_IP_H #define _UAPI_LINUX_IP_H #include +#include #include #define IPTOS_TOS_MASK 0x1E diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 81f4243bebb1..53326dfc59ec 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -4,6 +4,7 @@ #include #include +#include #include #include -- cgit v1.2.3 From e16cab9c1596e251761d2bfb5e1467950d616963 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 2 Feb 2023 11:41:37 +0000 Subject: usb: uvc: Enumerate valid values for color matching The color matching descriptors defined in the UVC Specification contain 3 fields with discrete numeric values representing particular settings. Enumerate those values so that later code setting them can be more readable. Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20230202114142.300858-2-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/video.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/video.h b/include/uapi/linux/usb/video.h index 6e8e572c2980..2ff0e8a3a683 100644 --- a/include/uapi/linux/usb/video.h +++ b/include/uapi/linux/usb/video.h @@ -179,6 +179,36 @@ #define UVC_CONTROL_CAP_AUTOUPDATE (1 << 3) #define UVC_CONTROL_CAP_ASYNCHRONOUS (1 << 4) +/* 3.9.2.6 Color Matching Descriptor Values */ +enum uvc_color_primaries_values { + UVC_COLOR_PRIMARIES_UNSPECIFIED, + UVC_COLOR_PRIMARIES_BT_709_SRGB, + UVC_COLOR_PRIMARIES_BT_470_2_M, + UVC_COLOR_PRIMARIES_BT_470_2_B_G, + UVC_COLOR_PRIMARIES_SMPTE_170M, + UVC_COLOR_PRIMARIES_SMPTE_240M, +}; + +enum uvc_transfer_characteristics_values { + UVC_TRANSFER_CHARACTERISTICS_UNSPECIFIED, + UVC_TRANSFER_CHARACTERISTICS_BT_709, + UVC_TRANSFER_CHARACTERISTICS_BT_470_2_M, + UVC_TRANSFER_CHARACTERISTICS_BT_470_2_B_G, + UVC_TRANSFER_CHARACTERISTICS_SMPTE_170M, + UVC_TRANSFER_CHARACTERISTICS_SMPTE_240M, + UVC_TRANSFER_CHARACTERISTICS_LINEAR, + UVC_TRANSFER_CHARACTERISTICS_SRGB, +}; + +enum uvc_matrix_coefficients { + UVC_MATRIX_COEFFICIENTS_UNSPECIFIED, + UVC_MATRIX_COEFFICIENTS_BT_709, + UVC_MATRIX_COEFFICIENTS_FCC, + UVC_MATRIX_COEFFICIENTS_BT_470_2_B_G, + UVC_MATRIX_COEFFICIENTS_SMPTE_170M, + UVC_MATRIX_COEFFICIENTS_SMPTE_240M, +}; + /* ------------------------------------------------------------------------ * UVC structures */ -- cgit v1.2.3 From 09519ec3b19e4144b5f6e269c54fbb9c294a9fcb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 9 Jan 2023 13:26:23 -0600 Subject: perf: Add perf_event_attr::config3 Arm SPEv1.2 adds another 64-bits of event filtering control. As the existing perf_event_attr::configN fields are all used up for SPE PMU, an additional field is needed. Add a new 'config3' field. Tested-by: James Clark Signed-off-by: Rob Herring Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220825-arm-spe-v8-7-v4-7-327f860daf28@kernel.org Signed-off-by: Will Deacon --- include/uapi/linux/perf_event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index ccb7f5dad59b..37675437b768 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -374,6 +374,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ #define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -515,6 +516,8 @@ struct perf_event_attr { * truncated accordingly on 32 bit architectures. */ __u64 sig_data; + + __u64 config3; /* extension of config2 */ }; /* -- cgit v1.2.3 From 70529a199574c15a40f46b14256633b02ba10ca2 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 3 Feb 2023 16:35:15 -0500 Subject: fanotify: define struct members to hold response decision context This patch adds a flag, FAN_INFO and an extensible buffer to provide additional information about response decisions. The buffer contains one or more headers defining the information type and the length of the following information. The patch defines one additional information type, FAN_RESPONSE_INFO_AUDIT_RULE, to audit a rule number. This will allow for the creation of other information types in the future if other users of the API identify different needs. The kernel can be tested if it supports a given info type by supplying the complete info extension but setting fd to FAN_NOFD. It will return the expected size but not issue an audit record. Suggested-by: Steve Grubb Link: https://lore.kernel.org/r/2745105.e9J7NaK4W3@x2 Suggested-by: Jan Kara Link: https://lore.kernel.org/r/20201001101219.GE17860@quack2.suse.cz Tested-by: Steve Grubb Acked-by: Steve Grubb Signed-off-by: Richard Guy Briggs Signed-off-by: Jan Kara Message-Id: <10177cfcae5480926b7176321a28d9da6835b667.1675373475.git.rgb@redhat.com> --- fs/notify/fanotify/fanotify.c | 5 ++- fs/notify/fanotify/fanotify.h | 4 ++ fs/notify/fanotify/fanotify_user.c | 86 ++++++++++++++++++++++++++++---------- include/linux/fanotify.h | 5 +++ include/uapi/linux/fanotify.h | 30 ++++++++++++- 5 files changed, 107 insertions(+), 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index a2a15bc4df28..24ec1d66d5a8 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -262,7 +262,7 @@ static int fanotify_get_response(struct fsnotify_group *group, } /* userspace responded, convert to something usable */ - switch (event->response & ~FAN_AUDIT) { + switch (event->response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: ret = 0; break; @@ -563,6 +563,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH_PERM; pevent->response = 0; + pevent->hdr.type = FAN_RESPONSE_INFO_NONE; + pevent->hdr.pad = 0; + pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; path_get(path); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index f899d610bc08..e8a3c28c5d12 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -428,6 +428,10 @@ struct fanotify_perm_event { u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ + union { + struct fanotify_response_info_header hdr; + struct fanotify_response_info_audit_rule audit_rule; + }; }; static inline struct fanotify_perm_event * diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index caa1211bac8c..8f430bfad487 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -283,19 +283,42 @@ static int create_fd(struct fsnotify_group *group, const struct path *path, return client_fd; } +static int process_access_response_info(const char __user *info, + size_t info_len, + struct fanotify_response_info_audit_rule *friar) +{ + if (info_len != sizeof(*friar)) + return -EINVAL; + + if (copy_from_user(friar, info, sizeof(*friar))) + return -EFAULT; + + if (friar->hdr.type != FAN_RESPONSE_INFO_AUDIT_RULE) + return -EINVAL; + if (friar->hdr.pad != 0) + return -EINVAL; + if (friar->hdr.len != sizeof(*friar)) + return -EINVAL; + + return info_len; +} + /* * Finish processing of permission event by setting it to ANSWERED state and * drop group->notification_lock. */ static void finish_permission_event(struct fsnotify_group *group, - struct fanotify_perm_event *event, - u32 response) + struct fanotify_perm_event *event, u32 response, + struct fanotify_response_info_audit_rule *friar) __releases(&group->notification_lock) { bool destroy = false; assert_spin_locked(&group->notification_lock); - event->response = response; + event->response = response & ~FAN_INFO; + if (response & FAN_INFO) + memcpy(&event->audit_rule, friar, sizeof(*friar)); + if (event->state == FAN_EVENT_CANCELED) destroy = true; else @@ -306,20 +329,27 @@ static void finish_permission_event(struct fsnotify_group *group, } static int process_access_response(struct fsnotify_group *group, - struct fanotify_response *response_struct) + struct fanotify_response *response_struct, + const char __user *info, + size_t info_len) { struct fanotify_perm_event *event; int fd = response_struct->fd; u32 response = response_struct->response; + int ret = info_len; + struct fanotify_response_info_audit_rule friar; - pr_debug("%s: group=%p fd=%d response=%u\n", __func__, group, - fd, response); + pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__, + group, fd, response, info, info_len); /* * make sure the response is valid, if invalid we do nothing and either * userspace can send a valid response or we will clean it up after the * timeout */ - switch (response & ~FAN_AUDIT) { + if (response & ~FANOTIFY_RESPONSE_VALID_MASK) + return -EINVAL; + + switch (response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: case FAN_DENY: break; @@ -327,10 +357,20 @@ static int process_access_response(struct fsnotify_group *group, return -EINVAL; } - if (fd < 0) + if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) return -EINVAL; - if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) + if (response & FAN_INFO) { + ret = process_access_response_info(info, info_len, &friar); + if (ret < 0) + return ret; + if (fd == FAN_NOFD) + return ret; + } else { + ret = 0; + } + + if (fd < 0) return -EINVAL; spin_lock(&group->notification_lock); @@ -340,9 +380,9 @@ static int process_access_response(struct fsnotify_group *group, continue; list_del_init(&event->fae.fse.list); - finish_permission_event(group, event, response); + finish_permission_event(group, event, response, &friar); wake_up(&group->fanotify_data.access_waitq); - return 0; + return ret; } spin_unlock(&group->notification_lock); @@ -804,7 +844,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, if (ret <= 0) { spin_lock(&group->notification_lock); finish_permission_event(group, - FANOTIFY_PERM(event), FAN_DENY); + FANOTIFY_PERM(event), FAN_DENY, NULL); wake_up(&group->fanotify_data.access_waitq); } else { spin_lock(&group->notification_lock); @@ -827,28 +867,32 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct fanotify_response response = { .fd = -1, .response = -1 }; + struct fanotify_response response; struct fsnotify_group *group; int ret; + const char __user *info_buf = buf + sizeof(struct fanotify_response); + size_t info_len; if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) return -EINVAL; group = file->private_data; + pr_debug("%s: group=%p count=%zu\n", __func__, group, count); + if (count < sizeof(response)) return -EINVAL; - count = sizeof(response); - - pr_debug("%s: group=%p count=%zu\n", __func__, group, count); - - if (copy_from_user(&response, buf, count)) + if (copy_from_user(&response, buf, sizeof(response))) return -EFAULT; - ret = process_access_response(group, &response); + info_len = count - sizeof(response); + + ret = process_access_response(group, &response, info_buf, info_len); if (ret < 0) count = ret; + else + count = sizeof(response) + ret; return count; } @@ -876,7 +920,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) event = list_first_entry(&group->fanotify_data.access_list, struct fanotify_perm_event, fae.fse.list); list_del_init(&event->fae.fse.list); - finish_permission_event(group, event, FAN_ALLOW); + finish_permission_event(group, event, FAN_ALLOW, NULL); spin_lock(&group->notification_lock); } @@ -893,7 +937,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) fsnotify_destroy_event(group, fsn_event); } else { finish_permission_event(group, FANOTIFY_PERM(event), - FAN_ALLOW); + FAN_ALLOW, NULL); } spin_lock(&group->notification_lock); } diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 8ad743def6f3..4f1c4f603118 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -122,6 +122,11 @@ #define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ FANOTIFY_EVENT_FLAGS) +/* These masks check for invalid bits in permission responses. */ +#define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY) +#define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO) +#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS) + /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS #undef FAN_ALL_INIT_FLAGS diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 436258214bb0..cd14c94e9a1e 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -188,15 +188,43 @@ struct fanotify_event_info_error { __u32 error_count; }; +/* + * User space may need to record additional information about its decision. + * The extra information type records what kind of information is included. + * The default is none. We also define an extra information buffer whose + * size is determined by the extra information type. + * + * If the information type is Audit Rule, then the information following + * is the rule number that triggered the user space decision that + * requires auditing. + */ + +#define FAN_RESPONSE_INFO_NONE 0 +#define FAN_RESPONSE_INFO_AUDIT_RULE 1 + struct fanotify_response { __s32 fd; __u32 response; }; +struct fanotify_response_info_header { + __u8 type; + __u8 pad; + __u16 len; +}; + +struct fanotify_response_info_audit_rule { + struct fanotify_response_info_header hdr; + __u32 rule_number; + __u32 subj_trust; + __u32 obj_trust; +}; + /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 -#define FAN_AUDIT 0x10 /* Bit mask to create audit record for result */ +#define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ +#define FAN_INFO 0x20 /* Bitmask to indicate additional information */ /* No fd set in event */ #define FAN_NOFD -1 -- cgit v1.2.3 From 3fd49805d19d1c566e92358d2e3d9fadb3b5ec16 Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Mon, 6 Feb 2023 17:46:00 +0100 Subject: KVM: s390: Extend MEM_OP ioctl by storage key checked cmpxchg User space can use the MEM_OP ioctl to make storage key checked reads and writes to the guest, however, it has no way of performing atomic, key checked, accesses to the guest. Extend the MEM_OP ioctl in order to allow for this, by adding a cmpxchg op. For now, support this op for absolute accesses only. This op can be used, for example, to set the device-state-change indicator and the adapter-local-summary indicator atomically. Signed-off-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20230206164602.138068-13-scgl@linux.ibm.com Message-Id: <20230206164602.138068-13-scgl@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kvm/gaccess.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/gaccess.h | 3 ++ arch/s390/kvm/kvm-s390.c | 56 +++++++++++++++++++++++- include/uapi/linux/kvm.h | 8 ++++ 4 files changed, 175 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 0243b6e38d36..3eb85f254881 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1161,6 +1161,115 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, return rc; } +/** + * cmpxchg_guest_abs_with_key() - Perform cmpxchg on guest absolute address. + * @kvm: Virtual machine instance. + * @gpa: Absolute guest address of the location to be changed. + * @len: Operand length of the cmpxchg, required: 1 <= len <= 16. Providing a + * non power of two will result in failure. + * @old_addr: Pointer to old value. If the location at @gpa contains this value, + * the exchange will succeed. After calling cmpxchg_guest_abs_with_key() + * *@old_addr contains the value at @gpa before the attempt to + * exchange the value. + * @new: The value to place at @gpa. + * @access_key: The access key to use for the guest access. + * @success: output value indicating if an exchange occurred. + * + * Atomically exchange the value at @gpa by @new, if it contains *@old. + * Honors storage keys. + * + * Return: * 0: successful exchange + * * >0: a program interruption code indicating the reason cmpxchg could + * not be attempted + * * -EINVAL: address misaligned or len not power of two + * * -EAGAIN: transient failure (len 1 or 2) + * * -EOPNOTSUPP: read-only memslot (should never occur) + */ +int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len, + __uint128_t *old_addr, __uint128_t new, + u8 access_key, bool *success) +{ + gfn_t gfn = gpa_to_gfn(gpa); + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + bool writable; + hva_t hva; + int ret; + + if (!IS_ALIGNED(gpa, len)) + return -EINVAL; + + hva = gfn_to_hva_memslot_prot(slot, gfn, &writable); + if (kvm_is_error_hva(hva)) + return PGM_ADDRESSING; + /* + * Check if it's a read-only memslot, even though that cannot occur + * since those are unsupported. + * Don't try to actually handle that case. + */ + if (!writable) + return -EOPNOTSUPP; + + hva += offset_in_page(gpa); + /* + * The cmpxchg_user_key macro depends on the type of "old", so we need + * a case for each valid length and get some code duplication as long + * as we don't introduce a new macro. + */ + switch (len) { + case 1: { + u8 old; + + ret = cmpxchg_user_key((u8 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 2: { + u16 old; + + ret = cmpxchg_user_key((u16 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 4: { + u32 old; + + ret = cmpxchg_user_key((u32 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 8: { + u64 old; + + ret = cmpxchg_user_key((u64 __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + case 16: { + __uint128_t old; + + ret = cmpxchg_user_key((__uint128_t __user *)hva, &old, *old_addr, new, access_key); + *success = !ret && old == *old_addr; + *old_addr = old; + break; + } + default: + return -EINVAL; + } + if (*success) + mark_page_dirty_in_slot(kvm, slot, gfn); + /* + * Assume that the fault is caused by protection, either key protection + * or user page write protection. + */ + if (ret == -EFAULT) + ret = PGM_PROTECTION; + return ret; +} + /** * guest_translate_address_with_key - translate guest logical into guest absolute address * @vcpu: virtual cpu diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 9408d6cc8e2c..b320d12aa049 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -206,6 +206,9 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, unsigned long len, enum gacc_mode mode); +int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len, __uint128_t *old, + __uint128_t new, u8 access_key, bool *success); + /** * write_guest_with_key - copy data from kernel space to guest space * @vcpu: virtual cpu diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 17368d118653..8dfda720f60d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -584,7 +584,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_VCPU_RESETS: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_S390_DIAG318: - case KVM_CAP_S390_MEM_OP_EXTENSION: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -598,6 +597,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break; + case KVM_CAP_S390_MEM_OP_EXTENSION: + /* + * Flag bits indicating which extensions are supported. + * If r > 0, the base extension must also be supported/indicated, + * in order to maintain backwards compatibility. + */ + r = KVM_S390_MEMOP_EXTENSION_CAP_BASE | + KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG; + break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: @@ -2832,6 +2840,50 @@ out_unlock: return r; } +static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void __user *old_addr = (void __user *)mop->old_addr; + union { + __uint128_t quad; + char raw[sizeof(__uint128_t)]; + } old = { .quad = 0}, new = { .quad = 0 }; + unsigned int off_in_quad = sizeof(new) - mop->size; + int r, srcu_idx; + bool success; + + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION); + if (r) + return r; + /* + * This validates off_in_quad. Checking that size is a power + * of two is not necessary, as cmpxchg_guest_abs_with_key + * takes care of that + */ + if (mop->size > sizeof(new)) + return -EINVAL; + if (copy_from_user(&new.raw[off_in_quad], uaddr, mop->size)) + return -EFAULT; + if (copy_from_user(&old.raw[off_in_quad], old_addr, mop->size)) + return -EFAULT; + + srcu_idx = srcu_read_lock(&kvm->srcu); + + if (kvm_is_error_gpa(kvm, mop->gaddr)) { + r = PGM_ADDRESSING; + goto out_unlock; + } + + r = cmpxchg_guest_abs_with_key(kvm, mop->gaddr, mop->size, &old.quad, + new.quad, mop->key, &success); + if (!success && copy_to_user(old_addr, &old.raw[off_in_quad], mop->size)) + r = -EFAULT; + +out_unlock: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return r; +} + static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) { /* @@ -2850,6 +2902,8 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) case KVM_S390_MEMOP_ABSOLUTE_READ: case KVM_S390_MEMOP_ABSOLUTE_WRITE: return kvm_s390_vm_mem_op_abs(kvm, mop); + case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG: + return kvm_s390_vm_mem_op_cmpxchg(kvm, mop); default: return -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 55155e262646..d2f30463c133 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -583,6 +583,8 @@ struct kvm_s390_mem_op { struct { __u8 ar; /* the access register number */ __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ }; __u32 sida_offset; /* offset into the sida */ __u8 reserved[32]; /* ignored */ @@ -595,11 +597,17 @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_SIDA_WRITE 3 #define KVM_S390_MEMOP_ABSOLUTE_READ 4 #define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) #define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ -- cgit v1.2.3 From 32bb477fa7bf386ce87837691c4672854a5231e4 Mon Sep 17 00:00:00 2001 From: Kumaravel Thiagarajan Date: Tue, 7 Feb 2023 22:18:12 +0530 Subject: serial: 8250_pci1xxxx: Add driver for quad-uart support pci1xxxx is a PCIe switch with a multi-function endpoint on one of its downstream ports. Quad-uart is one of the functions in the multi-function endpoint. This driver loads for the quad-uart and enumerates single or multiple instances of uart based on the PCIe subsystem device ID. Co-developed-by: Tharun Kumar P Signed-off-by: Tharun Kumar P Signed-off-by: Kumaravel Thiagarajan Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230207164814.3104605-3-kumaravel.thiagarajan@microchip.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 7 + drivers/tty/serial/8250/8250_pci1xxxx.c | 329 ++++++++++++++++++++++++++++++++ drivers/tty/serial/8250/8250_port.c | 8 + drivers/tty/serial/8250/Kconfig | 11 ++ drivers/tty/serial/8250/Makefile | 1 + include/uapi/linux/serial_core.h | 3 + 6 files changed, 359 insertions(+) create mode 100644 drivers/tty/serial/8250/8250_pci1xxxx.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index fb1471cb5ed3..91437fe072af 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13799,6 +13799,13 @@ L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-mchp-pci1xxxx.c +MICROCHIP PCIe UART DRIVER +M: Kumaravel Thiagarajan +M: Tharun Kumar P +L: linux-serial@vger.kernel.org +S: Maintained +F: drivers/tty/serial/8250/8250_pci1xxxx.c + MICROCHIP PWM DRIVER M: Claudiu Beznea L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c new file mode 100644 index 000000000000..ea04c014edb9 --- /dev/null +++ b/drivers/tty/serial/8250/8250_pci1xxxx.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Probe module for 8250/16550-type MCHP PCI serial ports. + * + * Based on drivers/tty/serial/8250/8250_pci.c, + * + * Copyright (C) 2022 Microchip Technology Inc., All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "8250.h" +#include "8250_pcilib.h" + +#define PCI_DEVICE_ID_EFAR_PCI12000 0xa002 +#define PCI_DEVICE_ID_EFAR_PCI11010 0xa012 +#define PCI_DEVICE_ID_EFAR_PCI11101 0xa022 +#define PCI_DEVICE_ID_EFAR_PCI11400 0xa032 +#define PCI_DEVICE_ID_EFAR_PCI11414 0xa042 + +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_4p 0x0001 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p012 0x0002 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p013 0x0003 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p023 0x0004 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p123 0x0005 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p01 0x0006 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p02 0x0007 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p03 0x0008 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p12 0x0009 +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p13 0x000a +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p23 0x000b +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p0 0x000c +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p1 0x000d +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p2 0x000e +#define PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p3 0x000f + +#define PCI_SUBDEVICE_ID_EFAR_PCI12000 PCI_DEVICE_ID_EFAR_PCI12000 +#define PCI_SUBDEVICE_ID_EFAR_PCI11010 PCI_DEVICE_ID_EFAR_PCI11010 +#define PCI_SUBDEVICE_ID_EFAR_PCI11101 PCI_DEVICE_ID_EFAR_PCI11101 +#define PCI_SUBDEVICE_ID_EFAR_PCI11400 PCI_DEVICE_ID_EFAR_PCI11400 +#define PCI_SUBDEVICE_ID_EFAR_PCI11414 PCI_DEVICE_ID_EFAR_PCI11414 + +#define UART_ACTV_REG 0x11 +#define UART_BLOCK_SET_ACTIVE BIT(0) + +#define UART_PCI_CTRL_REG 0x80 +#define UART_PCI_CTRL_SET_MULTIPLE_MSI BIT(4) +#define UART_PCI_CTRL_D3_CLK_ENABLE BIT(0) + +#define ADCL_CFG_REG 0x40 +#define ADCL_CFG_POL_SEL BIT(2) +#define ADCL_CFG_PIN_SEL BIT(1) +#define ADCL_CFG_EN BIT(0) + +#define UART_BIT_SAMPLE_CNT 16 +#define BAUD_CLOCK_DIV_INT_MSK GENMASK(31, 8) +#define ADCL_CFG_RTS_DELAY_MASK GENMASK(11, 8) +#define UART_CLOCK_DEFAULT (62500 * HZ_PER_KHZ) + +#define UART_WAKE_REG 0x8C +#define UART_WAKE_MASK_REG 0x90 +#define UART_WAKE_N_PIN BIT(2) +#define UART_WAKE_NCTS BIT(1) +#define UART_WAKE_INT BIT(0) +#define UART_WAKE_SRCS \ + (UART_WAKE_N_PIN | UART_WAKE_NCTS | UART_WAKE_INT) + +#define UART_BAUD_CLK_DIVISOR_REG 0x54 + +#define UART_RESET_REG 0x94 +#define UART_RESET_D3_RESET_DISABLE BIT(16) + +#define MAX_PORTS 4 +#define PORT_OFFSET 0x100 + +static const int logical_to_physical_port_idx[][MAX_PORTS] = { + {0, 1, 2, 3}, /* PCI12000, PCI11010, PCI11101, PCI11400, PCI11414 */ + {0, 1, 2, 3}, /* PCI4p */ + {0, 1, 2, -1}, /* PCI3p012 */ + {0, 1, 3, -1}, /* PCI3p013 */ + {0, 2, 3, -1}, /* PCI3p023 */ + {1, 2, 3, -1}, /* PCI3p123 */ + {0, 1, -1, -1}, /* PCI2p01 */ + {0, 2, -1, -1}, /* PCI2p02 */ + {0, 3, -1, -1}, /* PCI2p03 */ + {1, 2, -1, -1}, /* PCI2p12 */ + {1, 3, -1, -1}, /* PCI2p13 */ + {2, 3, -1, -1}, /* PCI2p23 */ + {0, -1, -1, -1}, /* PCI1p0 */ + {1, -1, -1, -1}, /* PCI1p1 */ + {2, -1, -1, -1}, /* PCI1p2 */ + {3, -1, -1, -1}, /* PCI1p3 */ +}; + +struct pci1xxxx_8250 { + unsigned int nr; + void __iomem *membase; + int line[]; +}; + +static int pci1xxxx_get_num_ports(struct pci_dev *dev) +{ + switch (dev->subsystem_device) { + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p0: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p1: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p2: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p3: + case PCI_SUBDEVICE_ID_EFAR_PCI12000: + case PCI_SUBDEVICE_ID_EFAR_PCI11010: + case PCI_SUBDEVICE_ID_EFAR_PCI11101: + case PCI_SUBDEVICE_ID_EFAR_PCI11400: + default: + return 1; + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p01: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p02: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p03: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p12: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p13: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_2p23: + return 2; + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p012: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p123: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p013: + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_3p023: + return 3; + case PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_4p: + case PCI_SUBDEVICE_ID_EFAR_PCI11414: + return 4; + } +} + +static unsigned int pci1xxxx_get_divisor(struct uart_port *port, + unsigned int baud, unsigned int *frac) +{ + unsigned int quot; + + /* + * Calculate baud rate sampling period in nanoseconds. + * Fractional part x denotes x/255 parts of a nanosecond. + */ + quot = NSEC_PER_SEC / (baud * UART_BIT_SAMPLE_CNT); + *frac = (NSEC_PER_SEC - quot * baud * UART_BIT_SAMPLE_CNT) * + 255 / UART_BIT_SAMPLE_CNT / baud; + + return quot; +} + +static void pci1xxxx_set_divisor(struct uart_port *port, unsigned int baud, + unsigned int quot, unsigned int frac) +{ + writel(FIELD_PREP(BAUD_CLOCK_DIV_INT_MSK, quot) | frac, + port->membase + UART_BAUD_CLK_DIVISOR_REG); +} + +static int pci1xxxx_setup(struct pci_dev *pdev, + struct uart_8250_port *port, int port_idx) +{ + int ret; + + port->port.flags |= UPF_FIXED_TYPE | UPF_SKIP_TEST; + port->port.type = PORT_MCHP16550A; + port->port.set_termios = serial8250_do_set_termios; + port->port.get_divisor = pci1xxxx_get_divisor; + port->port.set_divisor = pci1xxxx_set_divisor; + + ret = serial8250_pci_setup_port(pdev, port, 0, PORT_OFFSET * port_idx, 0); + if (ret < 0) + return ret; + + writeb(UART_BLOCK_SET_ACTIVE, port->port.membase + UART_ACTV_REG); + writeb(UART_WAKE_SRCS, port->port.membase + UART_WAKE_REG); + writeb(UART_WAKE_N_PIN, port->port.membase + UART_WAKE_MASK_REG); + + return 0; +} + +static unsigned int pci1xxxx_get_max_port(int subsys_dev) +{ + unsigned int i = MAX_PORTS; + + if (subsys_dev < ARRAY_SIZE(logical_to_physical_port_idx)) + while (i--) { + if (logical_to_physical_port_idx[subsys_dev][i] != -1) + return logical_to_physical_port_idx[subsys_dev][i] + 1; + } + + if (subsys_dev == PCI_SUBDEVICE_ID_EFAR_PCI11414) + return 4; + + return 1; +} + +static int pci1xxxx_logical_to_physical_port_translate(int subsys_dev, int port) +{ + if (subsys_dev < ARRAY_SIZE(logical_to_physical_port_idx)) + return logical_to_physical_port_idx[subsys_dev][port]; + + return logical_to_physical_port_idx[0][port]; +} + +static int pci1xxxx_serial_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct pci1xxxx_8250 *priv; + struct uart_8250_port uart; + unsigned int max_vec_reqd; + unsigned int nr_ports, i; + int num_vectors; + int subsys_dev; + int port_idx; + int rc; + + rc = pcim_enable_device(pdev); + if (rc) + return rc; + + nr_ports = pci1xxxx_get_num_ports(pdev); + + priv = devm_kzalloc(dev, struct_size(priv, line, nr_ports), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->membase = pci_ioremap_bar(pdev, 0); + if (!priv->membase) + return -ENOMEM; + + pci_set_master(pdev); + + priv->nr = nr_ports; + + subsys_dev = pdev->subsystem_device; + max_vec_reqd = pci1xxxx_get_max_port(subsys_dev); + + num_vectors = pci_alloc_irq_vectors(pdev, 1, max_vec_reqd, PCI_IRQ_ALL_TYPES); + if (num_vectors < 0) { + pci_iounmap(pdev, priv->membase); + return num_vectors; + } + + memset(&uart, 0, sizeof(uart)); + uart.port.flags = UPF_SHARE_IRQ | UPF_FIXED_PORT; + uart.port.uartclk = UART_CLOCK_DEFAULT; + uart.port.dev = dev; + + if (num_vectors == max_vec_reqd) + writeb(UART_PCI_CTRL_SET_MULTIPLE_MSI, priv->membase + UART_PCI_CTRL_REG); + + for (i = 0; i < nr_ports; i++) { + priv->line[i] = -ENODEV; + + port_idx = pci1xxxx_logical_to_physical_port_translate(subsys_dev, i); + + if (num_vectors == max_vec_reqd) + uart.port.irq = pci_irq_vector(pdev, port_idx); + else + uart.port.irq = pci_irq_vector(pdev, 0); + + rc = pci1xxxx_setup(pdev, &uart, port_idx); + if (rc) { + dev_warn(dev, "Failed to setup port %u\n", i); + continue; + } + + priv->line[i] = serial8250_register_8250_port(&uart); + if (priv->line[i] < 0) { + dev_warn(dev, + "Couldn't register serial port %lx, irq %d, type %d, error %d\n", + uart.port.iobase, uart.port.irq, uart.port.iotype, + priv->line[i]); + } + } + + pci_set_drvdata(pdev, priv); + + return 0; +} + +static void pci1xxxx_serial_remove(struct pci_dev *dev) +{ + struct pci1xxxx_8250 *priv = pci_get_drvdata(dev); + unsigned int i; + + for (i = 0; i < priv->nr; i++) { + if (priv->line[i] >= 0) + serial8250_unregister_port(priv->line[i]); + } + + pci_free_irq_vectors(dev); + pci_iounmap(dev, priv->membase); +} + +static const struct pci_device_id pci1xxxx_pci_tbl[] = { + { PCI_VDEVICE(EFAR, PCI_DEVICE_ID_EFAR_PCI11010) }, + { PCI_VDEVICE(EFAR, PCI_DEVICE_ID_EFAR_PCI11101) }, + { PCI_VDEVICE(EFAR, PCI_DEVICE_ID_EFAR_PCI11400) }, + { PCI_VDEVICE(EFAR, PCI_DEVICE_ID_EFAR_PCI11414) }, + { PCI_VDEVICE(EFAR, PCI_DEVICE_ID_EFAR_PCI12000) }, + {} +}; +MODULE_DEVICE_TABLE(pci, pci1xxxx_pci_tbl); + +static struct pci_driver pci1xxxx_pci_driver = { + .name = "pci1xxxx serial", + .probe = pci1xxxx_serial_probe, + .remove = pci1xxxx_serial_remove, + .id_table = pci1xxxx_pci_tbl, +}; +module_pci_driver(pci1xxxx_pci_driver); + +static_assert((ARRAY_SIZE(logical_to_physical_port_idx) == PCI_SUBDEVICE_ID_EFAR_PCI1XXXX_1p3 + 1)); + +MODULE_IMPORT_NS(SERIAL_8250_PCI); +MODULE_DESCRIPTION("Microchip Technology Inc. PCIe to UART module"); +MODULE_AUTHOR("Kumaravel Thiagarajan "); +MODULE_AUTHOR("Tharun Kumar P "); +MODULE_LICENSE("GPL"); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index e61753c295d5..fa43df05342b 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -313,6 +313,14 @@ static const struct serial8250_config uart_config[] = { .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, + [PORT_MCHP16550A] = { + .name = "MCHP16550A", + .fifo_size = 256, + .tx_loadsz = 256, + .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, + .rxtrig_bytes = {2, 66, 130, 194}, + .flags = UART_CAP_FIFO, + }, }; /* Uart divisor latch read */ diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index 9b3ba28cc562..978dc196c29b 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -295,6 +295,17 @@ config SERIAL_8250_HUB6 To compile this driver as a module, choose M here: the module will be called 8250_hub6. +config SERIAL_8250_PCI1XXXX + tristate "Microchip 8250 based serial port" + depends on SERIAL_8250 && PCI + select SERIAL_8250_PCILIB + default SERIAL_8250 + help + Select this option if you have a setup with Microchip PCIe + Switch with serial port enabled and wish to enable 8250 + serial driver for the serial interface. This driver support + will ensure to support baud rates upto 1.5Mpbs. + # # Misc. options/drivers. # diff --git a/drivers/tty/serial/8250/Makefile b/drivers/tty/serial/8250/Makefile index ce63a250da3b..4fc2fc1f41b6 100644 --- a/drivers/tty/serial/8250/Makefile +++ b/drivers/tty/serial/8250/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_SERIAL_8250_ACCENT) += 8250_accent.o obj-$(CONFIG_SERIAL_8250_BOCA) += 8250_boca.o obj-$(CONFIG_SERIAL_8250_EXAR_ST16C554) += 8250_exar_st16c554.o obj-$(CONFIG_SERIAL_8250_HUB6) += 8250_hub6.o +obj-$(CONFIG_SERIAL_8250_PCI1XXXX) += 8250_pci1xxxx.o obj-$(CONFIG_SERIAL_8250_FSL) += 8250_fsl.o obj-$(CONFIG_SERIAL_8250_MEN_MCB) += 8250_men_mcb.o obj-$(CONFIG_SERIAL_8250_DFL) += 8250_dfl.o diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 3ba34d8378bd..281fa286555c 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -207,6 +207,9 @@ /* Atheros AR933X SoC */ #define PORT_AR933X 99 +/* MCHP 16550A UART with 256 byte FIFOs */ +#define PORT_MCHP16550A 100 + /* ARC (Synopsys) on-chip UART */ #define PORT_ARC 101 -- cgit v1.2.3 From 9bd6dcb8ccb1a7d18534a88ff0d11e466a3a98a4 Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Mon, 6 Feb 2023 12:46:03 +0100 Subject: tty: n_gsm: mark unusable ioctl structure fields accordingly gsm_config and gsm_netconfig includes unused fields that have been included to allow future extension without changing the structure size. Unfortunately, no checks have been included for these field. The actual value set by old user space code remains undefined. This means that future extensions can not use these fields without breaking old user space code which may set unexpected values. Mark these fields accordingly to avoid breaking code changes. Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230206114606.2133-1-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/gsmmux.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gsmmux.h b/include/uapi/linux/gsmmux.h index cb8693b39cb7..785d6b253f6d 100644 --- a/include/uapi/linux/gsmmux.h +++ b/include/uapi/linux/gsmmux.h @@ -19,8 +19,7 @@ struct gsm_config unsigned int mtu; unsigned int k; unsigned int i; - unsigned int unused[8]; /* Padding for expansion without - breaking stuff */ + unsigned int unused[8]; /* Can not be used */ }; #define GSMIOC_GETCONF _IOR('G', 0, struct gsm_config) @@ -29,9 +28,9 @@ struct gsm_config struct gsm_netconfig { unsigned int adaption; /* Adaption to use in network mode */ unsigned short protocol;/* Protocol to use - only ETH_P_IP supported */ - unsigned short unused2; + unsigned short unused2; /* Can not be used */ char if_name[IFNAMSIZ]; /* interface name format string */ - __u8 unused[28]; /* For future use */ + __u8 unused[28]; /* Can not be used */ }; #define GSMIOC_ENABLE_NET _IOW('G', 2, struct gsm_netconfig) -- cgit v1.2.3 From ef3a3f6a294ba65fd906a291553935881796f8a5 Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Tue, 31 Jan 2023 08:58:03 -0800 Subject: vfio/type1: exclude mdevs from VFIO_UPDATE_VADDR Disable the VFIO_UPDATE_VADDR capability if mediated devices are present. Their kernel threads could be blocked indefinitely by a misbehaving userland while trying to pin/unpin pages while vaddrs are being updated. Do not allow groups to be added to the container while vaddr's are invalid, so we never need to block user threads from pinning, and can delete the vaddr-waiting code in a subsequent patch. Fixes: c3cbab24db38 ("vfio/type1: implement interfaces to update vaddr") Cc: stable@vger.kernel.org Signed-off-by: Steve Sistare Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1675184289-267876-2-git-send-email-steven.sistare@oracle.com Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 44 +++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/vfio.h | 15 ++++++++------ 2 files changed, 51 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 23c24fe98c00..144f5bb20fb8 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -861,6 +861,12 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, mutex_lock(&iommu->lock); + if (WARN_ONCE(iommu->vaddr_invalid_count, + "vfio_pin_pages not allowed with VFIO_UPDATE_VADDR\n")) { + ret = -EBUSY; + goto pin_done; + } + /* * Wait for all necessary vaddr's to be valid so they can be used in * the main loop without dropping the lock, to avoid racing vs unmap. @@ -1343,6 +1349,12 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu, mutex_lock(&iommu->lock); + /* Cannot update vaddr if mdev is present. */ + if (invalidate_vaddr && !list_empty(&iommu->emulated_iommu_groups)) { + ret = -EBUSY; + goto unlock; + } + pgshift = __ffs(iommu->pgsize_bitmap); pgsize = (size_t)1 << pgshift; @@ -2185,11 +2197,16 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, struct iommu_domain_geometry *geo; LIST_HEAD(iova_copy); LIST_HEAD(group_resv_regions); - int ret = -EINVAL; + int ret = -EBUSY; mutex_lock(&iommu->lock); + /* Attach could require pinning, so disallow while vaddr is invalid. */ + if (iommu->vaddr_invalid_count) + goto out_unlock; + /* Check for duplicates */ + ret = -EINVAL; if (vfio_iommu_find_iommu_group(iommu, iommu_group)) goto out_unlock; @@ -2660,6 +2677,16 @@ static int vfio_domains_have_enforce_cache_coherency(struct vfio_iommu *iommu) return ret; } +static bool vfio_iommu_has_emulated(struct vfio_iommu *iommu) +{ + bool ret; + + mutex_lock(&iommu->lock); + ret = !list_empty(&iommu->emulated_iommu_groups); + mutex_unlock(&iommu->lock); + return ret; +} + static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu, unsigned long arg) { @@ -2668,8 +2695,13 @@ static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu, case VFIO_TYPE1v2_IOMMU: case VFIO_TYPE1_NESTING_IOMMU: case VFIO_UNMAP_ALL: - case VFIO_UPDATE_VADDR: return 1; + case VFIO_UPDATE_VADDR: + /* + * Disable this feature if mdevs are present. They cannot + * safely pin/unpin/rw while vaddrs are being updated. + */ + return iommu && !vfio_iommu_has_emulated(iommu); case VFIO_DMA_CC_IOMMU: if (!iommu) return 0; @@ -3138,6 +3170,13 @@ static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t user_iova, size_t done; mutex_lock(&iommu->lock); + + if (WARN_ONCE(iommu->vaddr_invalid_count, + "vfio_dma_rw not allowed with VFIO_UPDATE_VADDR\n")) { + ret = -EBUSY; + goto out; + } + while (count > 0) { ret = vfio_iommu_type1_dma_rw_chunk(iommu, user_iova, data, count, write, &done); @@ -3149,6 +3188,7 @@ static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t user_iova, user_iova += done; } +out: mutex_unlock(&iommu->lock); return ret; } diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 23105eb036fa..0552e8dcf0cb 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -49,7 +49,11 @@ /* Supports VFIO_DMA_UNMAP_FLAG_ALL */ #define VFIO_UNMAP_ALL 9 -/* Supports the vaddr flag for DMA map and unmap */ +/* + * Supports the vaddr flag for DMA map and unmap. Not supported for mediated + * devices, so this capability is subject to change as groups are added or + * removed. + */ #define VFIO_UPDATE_VADDR 10 /* @@ -1343,8 +1347,7 @@ struct vfio_iommu_type1_info_dma_avail { * Map process virtual addresses to IO virtual addresses using the * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. * - * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova, and - * unblock translation of host virtual addresses in the iova range. The vaddr + * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova. The vaddr * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR. To * maintain memory consistency within the user application, the updated vaddr * must address the same memory object as originally mapped. Failure to do so @@ -1395,9 +1398,9 @@ struct vfio_bitmap { * must be 0. This cannot be combined with the get-dirty-bitmap flag. * * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host - * virtual addresses in the iova range. Tasks that attempt to translate an - * iova's vaddr will block. DMA to already-mapped pages continues. This - * cannot be combined with the get-dirty-bitmap flag. + * virtual addresses in the iova range. DMA to already-mapped pages continues. + * Groups may not be added to the container while any addresses are invalid. + * This cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; -- cgit v1.2.3 From 11ef026e467b05eac0a2ceb981d351ddc4b12216 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 2 Feb 2023 17:04:25 -0800 Subject: cxl/uapi: Add warning on CXL command enum The CXL command enum is exported to user space and must maintain backwards compatibility. Add comment that new defines must be added to the end of the list. Suggested-by: Dan Williams Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20221222-cxl-misc-v4-2-62f701c1cdd1@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/cxl_mem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index c71021a2a9ed..459a3f7f764b 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -19,6 +19,10 @@ #define CXL_MEM_QUERY_COMMANDS _IOR(0xCE, 1, struct cxl_mem_query_commands) #define CXL_MEM_SEND_COMMAND _IOWR(0xCE, 2, struct cxl_send_command) +/* + * NOTE: New defines must be added to the end of the list to preserve + * compatibility because this enum is exported to user space. + */ #define CXL_CMDS \ ___C(INVALID, "Invalid Command"), \ ___C(IDENTIFY, "Identify Command"), \ -- cgit v1.2.3 From 814a15f3b4131d3205bd47e23b50ccc6c666ce1d Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 2 Feb 2023 17:04:26 -0800 Subject: cxl/uapi: Tag commands from cxl_query_cmd() It was pointed out that commands not supported by the device or excluded by the kernel were being returned in cxl_query_cmd().[1] While libcxl correctly handles failing commands, it is more efficient to not issue an invalid command in the first place. This can't be done without additional information being returned from cxl_query_cmd(). In addition, information about the availability of commands can be useful for debugging. Add flags to struct cxl_command_info which reflect if a command is enabled and/or exclusive to the kernel. [1] https://lore.kernel.org/all/63b4ec4e37cc1_5178e2941d@dwillia2-xfh.jf.intel.com.notmuch/ Suggested-by: Dan Williams Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20221222-cxl-misc-v4-3-62f701c1cdd1@intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 9 +++++++-- include/uapi/linux/cxl_mem.h | 19 +++++++++++++++++-- 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 202d49dd9911..fd3b13b0fb7f 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -451,9 +451,14 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd, * structures. */ cxl_for_each_cmd(cmd) { - const struct cxl_command_info *info = &cmd->info; + struct cxl_command_info info = cmd->info; - if (copy_to_user(&q->commands[j++], info, sizeof(*info))) + if (test_bit(info.id, cxlmd->cxlds->enabled_cmds)) + info.flags |= CXL_MEM_COMMAND_FLAG_ENABLED; + if (test_bit(info.id, cxlmd->cxlds->exclusive_cmds)) + info.flags |= CXL_MEM_COMMAND_FLAG_EXCLUSIVE; + + if (copy_to_user(&q->commands[j++], &info, sizeof(info))) return -EFAULT; if (j == n_commands) diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 459a3f7f764b..9fe832afee37 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -72,6 +72,19 @@ static const struct { * struct cxl_command_info - Command information returned from a query. * @id: ID number for the command. * @flags: Flags that specify command behavior. + * + * CXL_MEM_COMMAND_FLAG_USER_ENABLED + * + * The given command id is supported by the driver and is supported by + * a related opcode on the device. + * + * CXL_MEM_COMMAND_FLAG_EXCLUSIVE + * + * Requests with the given command id will terminate with EBUSY as the + * kernel actively owns management of the given resource. For example, + * the label-storage-area can not be written while the kernel is + * actively managing that space. + * * @size_in: Expected input size, or ~0 if variable length. * @size_out: Expected output size, or ~0 if variable length. * @@ -81,7 +94,7 @@ static const struct { * bytes of output. * * - @id = 10 - * - @flags = 0 + * - @flags = CXL_MEM_COMMAND_FLAG_ENABLED * - @size_in = ~0 * - @size_out = 0 * @@ -91,7 +104,9 @@ struct cxl_command_info { __u32 id; __u32 flags; -#define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0) +#define CXL_MEM_COMMAND_FLAG_MASK GENMASK(1, 0) +#define CXL_MEM_COMMAND_FLAG_ENABLED BIT(0) +#define CXL_MEM_COMMAND_FLAG_EXCLUSIVE BIT(1) __u32 size_in; __u32 size_out; -- cgit v1.2.3 From af73370dcbe584f44168872b0bacac899f3c48f2 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 2 Feb 2023 17:04:27 -0800 Subject: cxl/mem: Fix UAPI command comment The command comment had grammatical errors. In an attempt to fix those it was noted that the comment and the query command were not in sync. Now that the query command returns excluded and device unsupported command information. Update the kdoc and fix the grammatical errors. [1] https://lore.kernel.org/all/63b4ec4e37cc1_5178e2941d@dwillia2-xfh.jf.intel.com.notmuch/ Reviewed-by: Jonathan Cameron Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20221222-cxl-misc-v4-4-62f701c1cdd1@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/cxl_mem.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 9fe832afee37..86bbacf2a315 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -11,9 +11,10 @@ /** * DOC: UAPI * - * Not all of all commands that the driver supports are always available for use - * by userspace. Userspace must check the results from the QUERY command in - * order to determine the live set of commands. + * Not all of the commands that the driver supports are available for use by + * userspace at all times. Userspace can check the result of the QUERY command + * to determine the live set of commands. Alternatively, it can issue the + * command and check for failure. */ #define CXL_MEM_QUERY_COMMANDS _IOR(0xCE, 1, struct cxl_mem_query_commands) -- cgit v1.2.3 From 5b4e9a7a71ab912d150cb2276cb23af51c863150 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 10 Feb 2023 16:50:16 -0800 Subject: net: ethtool: extend ringparam set/get APIs for rx_push Similar to what was done for TX_PUSH, add an RX_PUSH concept to the ethtool interfaces. Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 6 ++++-- include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 17 +++++++++++++++-- 5 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d144e890961d..e1bc6186d7ea 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -874,6 +874,7 @@ Kernel response contents: ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ``ETHTOOL_A_RINGS_TX_PUSH`` u8 flag of TX Push mode + ``ETHTOOL_A_RINGS_RX_PUSH`` u8 flag of RX Push mode ==================================== ====== =========================== ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with @@ -883,8 +884,8 @@ separate buffers. The device configuration must make it possible to receive full memory pages of data, for example because MTU is high enough or through HW-GRO. -``ETHTOOL_A_RINGS_TX_PUSH`` flag is used to enable descriptor fast -path to send packets. In ordinary path, driver fills descriptors in DRAM and +``ETHTOOL_A_RINGS_[RX|TX]_PUSH`` flag is used to enable descriptor fast +path to send or receive packets. In ordinary path, driver fills descriptors in DRAM and notifies NIC hardware. In fast path, driver pushes descriptors to the device through MMIO writes, thus reducing the latency. However, enabling this feature may increase the CPU cost. Drivers may enforce additional per-packet @@ -906,6 +907,7 @@ Request contents: ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ``ETHTOOL_A_RINGS_TX_PUSH`` u8 flag of TX Push mode + ``ETHTOOL_A_RINGS_RX_PUSH`` u8 flag of RX Push mode ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 515c78d8eb7c..2792185dda22 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -73,12 +73,14 @@ enum { * @rx_buf_len: Current length of buffers on the rx ring. * @tcp_data_split: Scatter packet headers and data to separate buffers * @tx_push: The flag of tx push mode + * @rx_push: The flag of rx push mode * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; u8 tcp_data_split; u8 tx_push; + u8 rx_push; u32 cqe_size; }; @@ -87,11 +89,13 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push + * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), ETHTOOL_RING_USE_CQE_SIZE = BIT(1), ETHTOOL_RING_USE_TX_PUSH = BIT(2), + ETHTOOL_RING_USE_RX_PUSH = BIT(3), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index ffb073c0dbb4..d39ce21381c5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -356,6 +356,7 @@ enum { ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ ETHTOOL_A_RINGS_TX_PUSH, /* u8 */ + ETHTOOL_A_RINGS_RX_PUSH, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index ae0732460e88..f7b189ed96b2 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -413,7 +413,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; -extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX_PUSH + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_RX_PUSH + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 2a2d3539630c..f358cd57d094 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -56,7 +56,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX_BUF_LEN */ nla_total_size(sizeof(u8)) + /* _RINGS_TCP_DATA_SPLIT */ nla_total_size(sizeof(u32) + /* _RINGS_CQE_SIZE */ - nla_total_size(sizeof(u8))); /* _RINGS_TX_PUSH */ + nla_total_size(sizeof(u8)) + /* _RINGS_TX_PUSH */ + nla_total_size(sizeof(u8))); /* _RINGS_RX_PUSH */ } static int rings_fill_reply(struct sk_buff *skb, @@ -96,7 +97,8 @@ static int rings_fill_reply(struct sk_buff *skb, kr->tcp_data_split))) || (kr->cqe_size && (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size))) || - nla_put_u8(skb, ETHTOOL_A_RINGS_TX_PUSH, !!kr->tx_push)) + nla_put_u8(skb, ETHTOOL_A_RINGS_TX_PUSH, !!kr->tx_push) || + nla_put_u8(skb, ETHTOOL_A_RINGS_RX_PUSH, !!kr->rx_push)) return -EMSGSIZE; return 0; @@ -114,6 +116,7 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_RX_BUF_LEN] = NLA_POLICY_MIN(NLA_U32, 1), [ETHTOOL_A_RINGS_CQE_SIZE] = NLA_POLICY_MIN(NLA_U32, 1), [ETHTOOL_A_RINGS_TX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_RINGS_RX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), }; static int @@ -147,6 +150,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info, return -EOPNOTSUPP; } + if (tb[ETHTOOL_A_RINGS_RX_PUSH] && + !(ops->supported_ring_params & ETHTOOL_RING_USE_RX_PUSH)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_RX_PUSH], + "setting rx push not supported"); + return -EOPNOTSUPP; + } + return ops->get_ringparam && ops->set_ringparam ? 1 : -EOPNOTSUPP; } @@ -176,6 +187,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod); ethnl_update_u8(&kernel_ringparam.tx_push, tb[ETHTOOL_A_RINGS_TX_PUSH], &mod); + ethnl_update_u8(&kernel_ringparam.rx_push, + tb[ETHTOOL_A_RINGS_RX_PUSH], &mod); if (!mod) return 0; -- cgit v1.2.3 From 022c3f87f88e2d68e90be7687d981c9cb893a3b1 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Sat, 11 Feb 2023 08:41:09 +0100 Subject: net: phy: add genphy_c45_ethtool_get/set_eee() support Add replacement for phy_ethtool_get/set_eee() functions. Current phy_ethtool_get/set_eee() implementation is great and it is possible to make it even better: - this functionality is for devices implementing parts of IEEE 802.3 specification beyond Clause 22. The better place for this code is phy-c45.c - currently it is able to do read/write operations on PHYs with different abilities to not existing registers. It is better to use stored supported_eee abilities to avoid false read/write operations. - the eee_active detection will provide wrong results on not supported link modes. It is better to validate speed/duplex properties against supported EEE link modes. - it is able to support only limited amount of link modes. We have more EEE link modes... By refactoring this code I address most of this point except of the last one. Adding additional EEE link modes will need more work. Signed-off-by: Oleksij Rempel Signed-off-by: David S. Miller --- drivers/net/phy/phy-c45.c | 238 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mdio.h | 58 +++++++++++ include/linux/phy.h | 7 ++ include/uapi/linux/mdio.h | 8 ++ 4 files changed, 311 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 2d10d22e7684..b4910c4c21d7 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -661,6 +661,129 @@ int genphy_c45_read_mdix(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); +/** + * genphy_c45_write_eee_adv - write advertised EEE link modes + * @phydev: target phy_device struct + * @adv: the linkmode advertisement settings + */ +int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv) +{ + int val, changed; + + if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) { + val = linkmode_to_mii_eee_cap1_t(adv); + + /* In eee_broken_modes are stored MDIO_AN_EEE_ADV specific raw + * register values. + */ + val &= ~phydev->eee_broken_modes; + + /* IEEE 802.3-2018 45.2.7.13 EEE advertisement 1 + * (Register 7.60) + */ + val = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, + MDIO_AN_EEE_ADV, + MDIO_EEE_100TX | MDIO_EEE_1000T | + MDIO_EEE_10GT | MDIO_EEE_1000KX | + MDIO_EEE_10GKX4 | MDIO_EEE_10GKR, + val); + if (val < 0) + return val; + if (val > 0) + changed = 1; + } + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + phydev->supported_eee)) { + val = linkmode_adv_to_mii_10base_t1_t(adv); + /* IEEE 802.3cg-2019 45.2.7.25 10BASE-T1 AN control register + * (Register 7.526) + */ + val = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, + MDIO_AN_10BT1_AN_CTRL, + MDIO_AN_10BT1_AN_CTRL_ADV_EEE_T1L, + val); + if (val < 0) + return val; + if (val > 0) + changed = 1; + } + + return changed; +} + +/** + * genphy_c45_read_eee_adv - read advertised EEE link modes + * @phydev: target phy_device struct + * @adv: the linkmode advertisement status + */ +static int genphy_c45_read_eee_adv(struct phy_device *phydev, + unsigned long *adv) +{ + int val; + + if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) { + /* IEEE 802.3-2018 45.2.7.13 EEE advertisement 1 + * (Register 7.60) + */ + val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV); + if (val < 0) + return val; + + mii_eee_cap1_mod_linkmode_t(adv, val); + } + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + phydev->supported_eee)) { + /* IEEE 802.3cg-2019 45.2.7.25 10BASE-T1 AN control register + * (Register 7.526) + */ + val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10BT1_AN_CTRL); + if (val < 0) + return val; + + mii_10base_t1_adv_mod_linkmode_t(adv, val); + } + + return 0; +} + +/** + * genphy_c45_read_eee_lpa - read advertised LP EEE link modes + * @phydev: target phy_device struct + * @lpa: the linkmode LP advertisement status + */ +static int genphy_c45_read_eee_lpa(struct phy_device *phydev, + unsigned long *lpa) +{ + int val; + + if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) { + /* IEEE 802.3-2018 45.2.7.14 EEE link partner ability 1 + * (Register 7.61) + */ + val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE); + if (val < 0) + return val; + + mii_eee_cap1_mod_linkmode_t(lpa, val); + } + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + phydev->supported_eee)) { + /* IEEE 802.3cg-2019 45.2.7.26 10BASE-T1 AN status register + * (Register 7.527) + */ + val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10BT1_AN_STAT); + if (val < 0) + return val; + + mii_10base_t1_adv_mod_linkmode_t(lpa, val); + } + + return 0; +} + /** * genphy_c45_read_eee_cap1 - read supported EEE link modes from register 3.20 * @phydev: target phy_device struct @@ -1194,6 +1317,121 @@ int genphy_c45_plca_get_status(struct phy_device *phydev, } EXPORT_SYMBOL_GPL(genphy_c45_plca_get_status); +/** + * genphy_c45_eee_is_active - get EEE status + * @phydev: target phy_device struct + * @adv: variable to store advertised linkmodes + * @lp: variable to store LP advertised linkmodes + * @is_enabled: variable to store EEE enabled/disabled configuration value + * + * Description: this function will read local and link partner PHY + * advertisements. Compare them return current EEE state. + */ +int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, + unsigned long *lp, bool *is_enabled) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_adv) = {}; + __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_lp) = {}; + __ETHTOOL_DECLARE_LINK_MODE_MASK(common); + bool eee_enabled, eee_active; + int ret; + + ret = genphy_c45_read_eee_adv(phydev, tmp_adv); + if (ret) + return ret; + + ret = genphy_c45_read_eee_lpa(phydev, tmp_lp); + if (ret) + return ret; + + eee_enabled = !linkmode_empty(tmp_adv); + linkmode_and(common, tmp_adv, tmp_lp); + if (eee_enabled && !linkmode_empty(common)) + eee_active = phy_check_valid(phydev->speed, phydev->duplex, + common); + else + eee_active = false; + + if (adv) + linkmode_copy(adv, tmp_adv); + if (lp) + linkmode_copy(lp, tmp_lp); + if (is_enabled) + *is_enabled = eee_enabled; + + return eee_active; +} +EXPORT_SYMBOL(genphy_c45_eee_is_active); + +/** + * genphy_c45_ethtool_get_eee - get EEE supported and status + * @phydev: target phy_device struct + * @data: ethtool_eee data + * + * Description: it reports the Supported/Advertisement/LP Advertisement + * capabilities. + */ +int genphy_c45_ethtool_get_eee(struct phy_device *phydev, + struct ethtool_eee *data) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp) = {}; + bool overflow = false, is_enabled; + int ret; + + ret = genphy_c45_eee_is_active(phydev, adv, lp, &is_enabled); + if (ret < 0) + return ret; + + data->eee_enabled = is_enabled; + data->eee_active = ret; + + if (!ethtool_convert_link_mode_to_legacy_u32(&data->supported, + phydev->supported_eee)) + overflow = true; + if (!ethtool_convert_link_mode_to_legacy_u32(&data->advertised, adv)) + overflow = true; + if (!ethtool_convert_link_mode_to_legacy_u32(&data->lp_advertised, lp)) + overflow = true; + + if (overflow) + phydev_warn(phydev, "Not all supported or advertised EEE link modes were passed to the user space\n"); + + return 0; +} +EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); + +/** + * genphy_c45_ethtool_set_eee - get EEE supported and status + * @phydev: target phy_device struct + * @data: ethtool_eee data + * + * Description: it reportes the Supported/Advertisement/LP Advertisement + * capabilities. + */ +int genphy_c45_ethtool_set_eee(struct phy_device *phydev, + struct ethtool_eee *data) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; + int ret; + + if (data->eee_enabled) { + if (data->advertised) + adv[0] = data->advertised; + else + linkmode_copy(adv, phydev->supported_eee); + } + + ret = genphy_c45_write_eee_adv(phydev, adv); + if (ret < 0) + return ret; + if (ret > 0) + return phy_restart_aneg(phydev); + + return 0; +} +EXPORT_SYMBOL(genphy_c45_ethtool_set_eee); + struct phy_driver genphy_c45_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, diff --git a/include/linux/mdio.h b/include/linux/mdio.h index e75583f5d967..27013d6bf24a 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -428,6 +428,64 @@ static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val) adv, val & MDIO_EEE_10GKR); } +/** + * linkmode_to_mii_eee_cap1_t() + * @adv: the linkmode advertisement settings + * + * A function that translates linkmode to value for IEEE 802.3-2018 45.2.7.13 + * "EEE advertisement 1" register (7.60) + */ +static inline u32 linkmode_to_mii_eee_cap1_t(unsigned long *adv) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, adv)) + result |= MDIO_EEE_100TX; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, adv)) + result |= MDIO_EEE_1000T; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, adv)) + result |= MDIO_EEE_10GT; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, adv)) + result |= MDIO_EEE_1000KX; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, adv)) + result |= MDIO_EEE_10GKX4; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, adv)) + result |= MDIO_EEE_10GKR; + + return result; +} + +/** + * mii_10base_t1_adv_mod_linkmode_t() + * @adv: linkmode advertisement settings + * @val: register value + * + * A function that translates IEEE 802.3cg-2019 45.2.7.26 "10BASE-T1 AN status" + * register (7.527) value to the linkmode. + */ +static inline void mii_10base_t1_adv_mod_linkmode_t(unsigned long *adv, u16 val) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + adv, val & MDIO_AN_10BT1_AN_CTRL_ADV_EEE_T1L); +} + +/** + * linkmode_adv_to_mii_10base_t1_t() + * @adv: linkmode advertisement settings + * + * A function that translates the linkmode to IEEE 802.3cg-2019 45.2.7.25 + * "10BASE-T1 AN control" register (7.526) value. + */ +static inline u32 linkmode_adv_to_mii_10base_t1_t(unsigned long *adv) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, adv)) + result |= MDIO_AN_10BT1_AN_CTRL_ADV_EEE_T1L; + + return result; +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, diff --git a/include/linux/phy.h b/include/linux/phy.h index 7a8e541de3f3..727bff531a14 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1758,6 +1758,13 @@ int genphy_c45_plca_set_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); +int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, + unsigned long *lp, bool *is_enabled); +int genphy_c45_ethtool_get_eee(struct phy_device *phydev, + struct ethtool_eee *data); +int genphy_c45_ethtool_set_eee(struct phy_device *phydev, + struct ethtool_eee *data); +int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 75b7257a51e1..256b463e47a6 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -79,6 +79,8 @@ #define MDIO_AN_T1_LP_L 517 /* BASE-T1 AN LP Base Page ability register [15:0] */ #define MDIO_AN_T1_LP_M 518 /* BASE-T1 AN LP Base Page ability register [31:16] */ #define MDIO_AN_T1_LP_H 519 /* BASE-T1 AN LP Base Page ability register [47:32] */ +#define MDIO_AN_10BT1_AN_CTRL 526 /* 10BASE-T1 AN control register */ +#define MDIO_AN_10BT1_AN_STAT 527 /* 10BASE-T1 AN status register */ #define MDIO_PMA_PMD_BT1_CTRL 2100 /* BASE-T1 PMA/PMD control register */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ @@ -340,6 +342,12 @@ #define MDIO_AN_T1_LP_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level LP Transmit Request */ #define MDIO_AN_T1_LP_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level LP Transmit Ability */ +/* 10BASE-T1 AN control register */ +#define MDIO_AN_10BT1_AN_CTRL_ADV_EEE_T1L 0x4000 /* 10BASE-T1L EEE ability advertisement */ + +/* 10BASE-T1 AN status register */ +#define MDIO_AN_10BT1_AN_STAT_LPA_EEE_T1L 0x4000 /* 10BASE-T1L LP EEE ability advertisement */ + /* BASE-T1 PMA/PMD control register */ #define MDIO_PMA_PMD_BT1_CTRL_CFG_MST 0x4000 /* MASTER-SLAVE config value */ -- cgit v1.2.3 From 9c395c1b99bd23f74bc628fa000480c49593d17f Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Mon, 13 Feb 2023 16:40:10 -0800 Subject: bpf: Add basic bpf_rb_{root,node} support This patch adds special BPF_RB_{ROOT,NODE} btf_field_types similar to BPF_LIST_{HEAD,NODE}, adds the necessary plumbing to detect the new types, and adds bpf_rb_root_free function for freeing bpf_rb_root in map_values. structs bpf_rb_root and bpf_rb_node are opaque types meant to obscure structs rb_root_cached rb_node, respectively. btf_struct_access will prevent BPF programs from touching these special fields automatically now that they're recognized. btf_check_and_fixup_fields now groups list_head and rb_root together as "graph root" fields and {list,rb}_node as "graph node", and does same ownership cycle checking as before. Note that this function does _not_ prevent ownership type mixups (e.g. rb_root owning list_node) - that's handled by btf_parse_graph_root. After this patch, a bpf program can have a struct bpf_rb_root in a map_value, but not add anything to nor do anything useful with it. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230214004017.2534011-2-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 20 ++- include/uapi/linux/bpf.h | 11 ++ kernel/bpf/btf.c | 162 ++++++++++++++------- kernel/bpf/helpers.c | 40 +++++ kernel/bpf/syscall.c | 28 ++-- kernel/bpf/verifier.c | 5 +- tools/include/uapi/linux/bpf.h | 11 ++ .../testing/selftests/bpf/prog_tests/linked_list.c | 12 +- 8 files changed, 216 insertions(+), 73 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8b5d0b4c4ada..be34f7deb6c3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -181,7 +181,10 @@ enum btf_field_type { BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, BPF_LIST_HEAD = (1 << 4), BPF_LIST_NODE = (1 << 5), - BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD, + BPF_RB_ROOT = (1 << 6), + BPF_RB_NODE = (1 << 7), + BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | + BPF_RB_NODE | BPF_RB_ROOT, }; struct btf_field_kptr { @@ -285,6 +288,10 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; + case BPF_RB_ROOT: + return "bpf_rb_root"; + case BPF_RB_NODE: + return "bpf_rb_node"; default: WARN_ON_ONCE(1); return "unknown"; @@ -305,6 +312,10 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); + case BPF_RB_ROOT: + return sizeof(struct bpf_rb_root); + case BPF_RB_NODE: + return sizeof(struct bpf_rb_node); default: WARN_ON_ONCE(1); return 0; @@ -325,6 +336,10 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); + case BPF_RB_ROOT: + return __alignof__(struct bpf_rb_root); + case BPF_RB_NODE: + return __alignof__(struct bpf_rb_node); default: WARN_ON_ONCE(1); return 0; @@ -435,6 +450,9 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, void bpf_timer_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); +void bpf_rb_root_free(const struct btf_field *field, void *rb_root, + struct bpf_spin_lock *spin_lock); + int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 17afd2b35ee5..1503f61336b6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6917,6 +6917,17 @@ struct bpf_list_node { __u64 :64; } __attribute__((aligned(8))); +struct bpf_rb_root { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_node { + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 740bdb045b14..b9d1f5c4e316 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3324,12 +3324,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf, return NULL; } -static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, - const struct btf_type *t, int comp_idx, - u32 off, int sz, struct btf_field_info *info) +static int +btf_find_graph_root(const struct btf *btf, const struct btf_type *pt, + const struct btf_type *t, int comp_idx, u32 off, + int sz, struct btf_field_info *info, + enum btf_field_type head_type) { + const char *node_field_name; const char *value_type; - const char *list_node; s32 id; if (!__btf_type_is_struct(t)) @@ -3339,26 +3341,32 @@ static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); if (!value_type) return -EINVAL; - list_node = strstr(value_type, ":"); - if (!list_node) + node_field_name = strstr(value_type, ":"); + if (!node_field_name) return -EINVAL; - value_type = kstrndup(value_type, list_node - value_type, GFP_KERNEL | __GFP_NOWARN); + value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL | __GFP_NOWARN); if (!value_type) return -ENOMEM; id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT); kfree(value_type); if (id < 0) return id; - list_node++; - if (str_is_empty(list_node)) + node_field_name++; + if (str_is_empty(node_field_name)) return -EINVAL; - info->type = BPF_LIST_HEAD; + info->type = head_type; info->off = off; info->graph_root.value_btf_id = id; - info->graph_root.node_name = list_node; + info->graph_root.node_name = node_field_name; return BTF_FIELD_FOUND; } +#define field_mask_test_name(field_type, field_type_str) \ + if (field_mask & field_type && !strcmp(name, field_type_str)) { \ + type = field_type; \ + goto end; \ + } + static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, int *align, int *sz) { @@ -3382,18 +3390,11 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } - if (field_mask & BPF_LIST_HEAD) { - if (!strcmp(name, "bpf_list_head")) { - type = BPF_LIST_HEAD; - goto end; - } - } - if (field_mask & BPF_LIST_NODE) { - if (!strcmp(name, "bpf_list_node")) { - type = BPF_LIST_NODE; - 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"); + field_mask_test_name(BPF_RB_NODE, "bpf_rb_node"); + /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3406,6 +3407,8 @@ end: return type; } +#undef field_mask_test_name + static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt) @@ -3438,6 +3441,7 @@ static int btf_find_struct_field(const struct btf *btf, case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_LIST_NODE: + case BPF_RB_NODE: ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3451,8 +3455,11 @@ static int btf_find_struct_field(const struct btf *btf, return ret; break; case BPF_LIST_HEAD: - ret = btf_find_list_head(btf, t, member_type, i, off, sz, - idx < info_cnt ? &info[idx] : &tmp); + case BPF_RB_ROOT: + ret = btf_find_graph_root(btf, t, member_type, + i, off, sz, + idx < info_cnt ? &info[idx] : &tmp, + field_type); if (ret < 0) return ret; break; @@ -3499,6 +3506,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_LIST_NODE: + case BPF_RB_NODE: ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3512,8 +3520,11 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, return ret; break; case BPF_LIST_HEAD: - ret = btf_find_list_head(btf, var, var_type, -1, off, sz, - idx < info_cnt ? &info[idx] : &tmp); + case BPF_RB_ROOT: + ret = btf_find_graph_root(btf, var, var_type, + -1, off, sz, + idx < info_cnt ? &info[idx] : &tmp, + field_type); if (ret < 0) return ret; break; @@ -3615,8 +3626,11 @@ end_btf: return ret; } -static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, - struct btf_field_info *info) +static int btf_parse_graph_root(const struct btf *btf, + struct btf_field *field, + struct btf_field_info *info, + const char *node_type_name, + size_t node_type_align) { const struct btf_type *t, *n = NULL; const struct btf_member *member; @@ -3638,13 +3652,13 @@ static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, n = btf_type_by_id(btf, member->type); if (!__btf_type_is_struct(n)) return -EINVAL; - if (strcmp("bpf_list_node", __btf_name_by_offset(btf, n->name_off))) + if (strcmp(node_type_name, __btf_name_by_offset(btf, n->name_off))) return -EINVAL; offset = __btf_member_bit_offset(n, member); if (offset % 8) return -EINVAL; offset /= 8; - if (offset % __alignof__(struct bpf_list_node)) + if (offset % node_type_align) return -EINVAL; field->graph_root.btf = (struct btf *)btf; @@ -3656,6 +3670,20 @@ static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, return 0; } +static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + return btf_parse_graph_root(btf, field, info, "bpf_list_node", + __alignof__(struct bpf_list_node)); +} + +static int btf_parse_rb_root(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + return btf_parse_graph_root(btf, field, info, "bpf_rb_node", + __alignof__(struct bpf_rb_node)); +} + struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size) { @@ -3718,7 +3746,13 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_RB_ROOT: + ret = btf_parse_rb_root(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; case BPF_LIST_NODE: + case BPF_RB_NODE: break; default: ret = -EFAULT; @@ -3727,8 +3761,9 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec->cnt++; } - /* bpf_list_head requires bpf_spin_lock */ - if (btf_record_has_field(rec, BPF_LIST_HEAD) && rec->spin_lock_off < 0) { + /* bpf_{list_head, rb_node} require bpf_spin_lock */ + if ((btf_record_has_field(rec, BPF_LIST_HEAD) || + btf_record_has_field(rec, BPF_RB_ROOT)) && rec->spin_lock_off < 0) { ret = -EINVAL; goto end; } @@ -3739,22 +3774,28 @@ end: return ERR_PTR(ret); } +#define GRAPH_ROOT_MASK (BPF_LIST_HEAD | BPF_RB_ROOT) +#define GRAPH_NODE_MASK (BPF_LIST_NODE | BPF_RB_NODE) + int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) { int i; - /* There are two owning types, kptr_ref and bpf_list_head. The former - * only supports storing kernel types, which can never store references - * to program allocated local types, atleast not yet. Hence we only need - * to ensure that bpf_list_head ownership does not form cycles. + /* There are three types that signify ownership of some other type: + * kptr_ref, bpf_list_head, bpf_rb_root. + * kptr_ref only supports storing kernel types, which can't store + * references to program allocated local types. + * + * Hence we only need to ensure that bpf_{list_head,rb_root} ownership + * does not form cycles. */ - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & GRAPH_ROOT_MASK)) return 0; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *meta; u32 btf_id; - if (!(rec->fields[i].type & BPF_LIST_HEAD)) + if (!(rec->fields[i].type & GRAPH_ROOT_MASK)) continue; btf_id = rec->fields[i].graph_root.value_btf_id; meta = btf_find_struct_meta(btf, btf_id); @@ -3762,39 +3803,47 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) return -EFAULT; rec->fields[i].graph_root.value_rec = meta->record; - if (!(rec->field_mask & BPF_LIST_NODE)) + /* We need to set value_rec for all root types, but no need + * to check ownership cycle for a type unless it's also a + * node type. + */ + if (!(rec->field_mask & GRAPH_NODE_MASK)) continue; /* We need to ensure ownership acyclicity among all types. The * proper way to do it would be to topologically sort all BTF * IDs based on the ownership edges, since there can be multiple - * bpf_list_head in a type. Instead, we use the following - * reasoning: + * bpf_{list_head,rb_node} in a type. Instead, we use the + * following resaoning: * * - A type can only be owned by another type in user BTF if it - * has a bpf_list_node. + * has a bpf_{list,rb}_node. Let's call these node types. * - A type can only _own_ another type in user BTF if it has a - * bpf_list_head. + * bpf_{list_head,rb_root}. Let's call these root types. * - * We ensure that if a type has both bpf_list_head and - * bpf_list_node, its element types cannot be owning types. + * We ensure that if a type is both a root and node, its + * element types cannot be root types. * * To ensure acyclicity: * - * When A only has bpf_list_head, ownership chain can be: + * When A is an root type but not a node, its ownership + * chain can be: * A -> B -> C * Where: - * - B has both bpf_list_head and bpf_list_node. - * - C only has bpf_list_node. + * - A is an root, e.g. has bpf_rb_root. + * - B is both a root and node, e.g. has bpf_rb_node and + * bpf_list_head. + * - C is only an root, e.g. has bpf_list_node * - * When A has both bpf_list_head and bpf_list_node, some other - * type already owns it in the BTF domain, hence it can not own - * another owning type through any of the bpf_list_head edges. + * When A is both a root and node, some other type already + * owns it in the BTF domain, hence it can not own + * another root type through any of the ownership edges. * A -> B * Where: - * - B only has bpf_list_node. + * - A is both an root and node. + * - B is only an node. */ - if (meta->record->field_mask & BPF_LIST_HEAD) + if (meta->record->field_mask & GRAPH_ROOT_MASK) return -ELOOP; } return 0; @@ -5256,6 +5305,8 @@ static const char *alloc_obj_fields[] = { "bpf_spin_lock", "bpf_list_head", "bpf_list_node", + "bpf_rb_root", + "bpf_rb_node", }; static struct btf_struct_metas * @@ -5329,7 +5380,8 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) type = &tab->types[tab->cnt]; type->btf_id = i; - record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size); + record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE | + BPF_RB_ROOT | BPF_RB_NODE, t->size); /* The record cannot be unset, treat it as an error if so */ if (IS_ERR_OR_NULL(record)) { ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 2dae44581922..192184b5156e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1772,6 +1772,46 @@ unlock: } } +/* Like rbtree_postorder_for_each_entry_safe, but 'pos' and 'n' are + * 'rb_node *', so field name of rb_node within containing struct is not + * needed. + * + * Since bpf_rb_tree's node type has a corresponding struct btf_field with + * graph_root.node_offset, it's not necessary to know field name + * or type of node struct + */ +#define bpf_rbtree_postorder_for_each_entry_safe(pos, n, root) \ + for (pos = rb_first_postorder(root); \ + pos && ({ n = rb_next_postorder(pos); 1; }); \ + pos = n) + +void bpf_rb_root_free(const struct btf_field *field, void *rb_root, + struct bpf_spin_lock *spin_lock) +{ + struct rb_root_cached orig_root, *root = rb_root; + struct rb_node *pos, *n; + void *obj; + + BUILD_BUG_ON(sizeof(struct rb_root_cached) > sizeof(struct bpf_rb_root)); + BUILD_BUG_ON(__alignof__(struct rb_root_cached) > __alignof__(struct bpf_rb_root)); + + __bpf_spin_lock_irqsave(spin_lock); + orig_root = *root; + *root = RB_ROOT_CACHED; + __bpf_spin_unlock_irqrestore(spin_lock); + + bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) { + obj = pos; + obj -= field->graph_root.node_offset; + + bpf_obj_free_fields(field->graph_root.value_rec, obj); + + migrate_disable(); + bpf_mem_free(&bpf_global_ma, obj); + migrate_enable(); + } +} + __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cda8d00f3762..e3fcdc9836a6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -537,9 +537,6 @@ void btf_record_free(struct btf_record *rec) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (rec->fields[i].kptr.module) @@ -548,7 +545,11 @@ void btf_record_free(struct btf_record *rec) break; case BPF_LIST_HEAD: case BPF_LIST_NODE: - /* Nothing to release for bpf_list_head */ + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_TIMER: + /* Nothing to release */ break; default: WARN_ON_ONCE(1); @@ -581,9 +582,6 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: btf_get(fields[i].kptr.btf); @@ -594,7 +592,11 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) break; case BPF_LIST_HEAD: case BPF_LIST_NODE: - /* Nothing to acquire for bpf_list_head */ + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_TIMER: + /* Nothing to acquire */ break; default: ret = -EFAULT; @@ -674,7 +676,13 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; + case BPF_RB_ROOT: + if (WARN_ON_ONCE(rec->spin_lock_off < 0)) + continue; + bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); + break; case BPF_LIST_NODE: + case BPF_RB_NODE: break; default: WARN_ON_ONCE(1); @@ -1010,7 +1018,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EINVAL; map->record = btf_parse_fields(btf, value_type, - BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD, + BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | + BPF_RB_ROOT, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1058,6 +1067,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } break; case BPF_LIST_HEAD: + case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f176bc15c879..4fd098851f43 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14703,9 +14703,10 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); - if (btf_record_has_field(map->record, BPF_LIST_HEAD)) { + if (btf_record_has_field(map->record, BPF_LIST_HEAD) || + btf_record_has_field(map->record, BPF_RB_ROOT)) { if (is_tracing_prog_type(prog_type)) { - verbose(env, "tracing progs cannot use bpf_list_head yet\n"); + verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n"); return -EINVAL; } } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 17afd2b35ee5..1503f61336b6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6917,6 +6917,17 @@ struct bpf_list_node { __u64 :64; } __attribute__((aligned(8))); +struct bpf_rb_root { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_node { + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 2592b8aa5e41..c456b34a823a 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -58,12 +58,12 @@ static struct { TEST(inner_map, pop_front) TEST(inner_map, pop_back) #undef TEST - { "map_compat_kprobe", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_kretprobe", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_tp", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_perf", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_raw_tp", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_raw_tp_w", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_kprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_kretprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_perf", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_raw_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_raw_tp_w", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, { "obj_type_id_oor", "local type ID argument must be in range [0, U32_MAX]" }, { "obj_new_no_composite", "bpf_obj_new type ID argument must be of a struct" }, { "obj_new_no_struct", "bpf_obj_new type ID argument must be of a struct" }, -- cgit v1.2.3 From 9a47c1ef5a95d1fd229ee5e375985f809a9d8177 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Mon, 16 Jan 2023 18:20:58 +0530 Subject: wifi: cfg80211: Authentication offload to user space for MLO connection in STA mode Currently authentication request event interface doesn't have support to indicate the user space whether it should enable MLO or not during the authentication with the specified AP. But driver needs such capability since the connection is MLO or not decided by the driver in case of SME offload to the driver. Add support for driver to indicate MLD address of the AP in authentication offload request to inform user space to enable MLO during authentication process. Driver shall look at NL80211_ATTR_MLO_SUPPORT flag capability in NL80211_CMD_CONNECT to know whether the user space supports enabling MLO during the authentication offload. User space should enable MLO during the authentication only when it receives the AP MLD address in authentication offload request. User space shouldn't enable MLO if the authentication offload request doesn't indicate the AP MLD address even if the AP is MLO capable. When MLO is enabled, user space should use the MAC address of the interface (on which driver sent request) as self MLD address. User space and driver to use MLD addresses in RA, TA and BSSID fields of the frames between them, and driver translates the MLD addresses to/from link addresses based on the link chosen for the authentication. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20230116125058.1604843-1-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 ++++++++++++ include/uapi/linux/nl80211.h | 17 +++++++++++++++++ net/wireless/nl80211.c | 4 +++- net/wireless/trace.h | 7 +++++-- 4 files changed, 37 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 54a77d906b2d..bcde215475c6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3600,6 +3600,17 @@ struct cfg80211_pmk_conf { * the real status code for failures. Used only for the authentication * response command interface (user space to driver). * @pmkid: The identifier to refer a PMKSA. + * @mld_addr: MLD address of the peer. Used by the authentication request event + * interface. Driver indicates this to enable MLO during the authentication + * offload to user space. Driver shall look at %NL80211_ATTR_MLO_SUPPORT + * flag capability in NL80211_CMD_CONNECT to know whether the user space + * supports enabling MLO during the authentication offload. + * User space should use the address of the interface (on which the + * authentication request event reported) as self MLD address. User space + * and driver should use MLD addresses in RA, TA and BSSID fields of + * authentication frames sent or received via cfg80211. The driver + * translates the MLD addresses to/from link addresses based on the link + * chosen for the authentication. */ struct cfg80211_external_auth_params { enum nl80211_external_auth_action action; @@ -3608,6 +3619,7 @@ struct cfg80211_external_auth_params { unsigned int key_mgmt_suite; u16 status; const u8 *pmkid; + u8 mld_addr[ETH_ALEN] __aligned(2); }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8ecb0fbee721..a984c6c4cf02 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1167,6 +1167,23 @@ * %NL80211_ATTR_STATUS_CODE attribute in %NL80211_CMD_EXTERNAL_AUTH * command interface. * + * Host driver sends MLD address of the AP with %NL80211_ATTR_MLD_ADDR in + * %NL80211_CMD_EXTERNAL_AUTH event to indicate user space to enable MLO + * during the authentication offload in STA mode while connecting to MLD + * APs. Host driver should check %NL80211_ATTR_MLO_SUPPORT flag capability + * in %NL80211_CMD_CONNECT to know whether the user space supports enabling + * MLO during the authentication offload or not. + * User space should enable MLO during the authentication only when it + * receives the AP MLD address in authentication offload request. User + * space shouldn't enable MLO when the authentication offload request + * doesn't indicate the AP MLD address even if the AP is MLO capable. + * User space should use %NL80211_ATTR_MLD_ADDR as peer's MLD address and + * interface address identified by %NL80211_ATTR_IFINDEX as self MLD + * address. User space and host driver to use MLD addresses in RA, TA and + * BSSID fields of the frames between them, and host driver translates the + * MLD addresses to/from link addresses based on the link chosen for the + * authentication. + * * Host driver reports this status on an authentication failure to the * user space through the connect result as the user space would have * initiated the connection through the connect request. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 64cf6110ce9d..a0858d747e45 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -19720,7 +19720,9 @@ int cfg80211_external_auth_request(struct net_device *dev, params->action) || nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, params->bssid) || nla_put(msg, NL80211_ATTR_SSID, params->ssid.ssid_len, - params->ssid.ssid)) + params->ssid.ssid) || + (!is_zero_ether_addr(params->mld_addr) && + nla_put(msg, NL80211_ATTR_MLD_ADDR, ETH_ALEN, params->mld_addr))) goto nla_put_failure; genlmsg_end(msg, hdr); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 9660fd94cd92..044b3c5a88ef 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2524,6 +2524,7 @@ TRACE_EVENT(rdev_external_auth, MAC_ENTRY(bssid) __array(u8, ssid, IEEE80211_MAX_SSID_LEN + 1) __field(u16, status) + MAC_ENTRY(mld_addr) ), TP_fast_assign(WIPHY_ASSIGN; NETDEV_ASSIGN; @@ -2532,10 +2533,12 @@ TRACE_EVENT(rdev_external_auth, memcpy(__entry->ssid, params->ssid.ssid, params->ssid.ssid_len); __entry->status = params->status; + MAC_ASSIGN(mld_addr, params->mld_addr); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: %pM" - ", ssid: %s, status: %u", WIPHY_PR_ARG, NETDEV_PR_ARG, - __entry->bssid, __entry->ssid, __entry->status) + ", ssid: %s, status: %u, mld_addr: %pM", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->bssid, + __entry->ssid, __entry->status, __entry->mld_addr) ); TRACE_EVENT(rdev_start_radar_detection, -- cgit v1.2.3 From d7c1a9a0ed180d8884798ce97afe7283622a484f Mon Sep 17 00:00:00 2001 From: Aloka Dixit Date: Mon, 30 Jan 2023 16:12:25 -0800 Subject: wifi: nl80211: validate and configure puncturing bitmap - New feature flag, NL80211_EXT_FEATURE_PUNCT, to advertise driver support for preamble puncturing in AP mode. - New attribute, NL80211_ATTR_PUNCT_BITMAP, to receive a puncturing bitmap from the userspace during AP bring up (NL80211_CMD_START_AP) and channel switch (NL80211_CMD_CHANNEL_SWITCH) operations. Each bit corresponds to a 20 MHz channel in the operating bandwidth, lowest bit for the lowest channel. Bit set to 1 indicates that the channel is punctured. Higher 16 bits are reserved. - New members added to structures cfg80211_ap_settings and cfg80211_csa_settings to propagate the bitmap to the driver after validation. Signed-off-by: Aloka Dixit Signed-off-by: Muna Sinada Link: https://lore.kernel.org/r/20230131001227.25014-3-quic_alokad@quicinc.com [move validation against 0xffff into policy] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 8 ++++++++ include/uapi/linux/nl80211.h | 11 +++++++++++ net/wireless/nl80211.c | 32 ++++++++++++++++++++++++++++++++ 3 files changed, 51 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 191603f32b37..fb8b79e6ac36 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1316,6 +1316,9 @@ struct cfg80211_unsol_bcast_probe_resp { * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters * @mbssid_config: AP settings for multiple bssid + * @punct_bitmap: Preamble puncturing bitmap. Each bit represents + * a 20 MHz channel, lowest bit corresponding to the lowest channel. + * Bit set to 1 indicates that the channel is punctured. */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1350,6 +1353,7 @@ struct cfg80211_ap_settings { struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; struct cfg80211_mbssid_config mbssid_config; + u16 punct_bitmap; }; /** @@ -1367,6 +1371,9 @@ struct cfg80211_ap_settings { * @radar_required: whether radar detection is required on the new channel * @block_tx: whether transmissions should be blocked while changing * @count: number of beacons until switch + * @punct_bitmap: Preamble puncturing bitmap. Each bit represents + * a 20 MHz channel, lowest bit corresponding to the lowest channel. + * Bit set to 1 indicates that the channel is punctured. */ struct cfg80211_csa_settings { struct cfg80211_chan_def chandef; @@ -1379,6 +1386,7 @@ struct cfg80211_csa_settings { bool radar_required; bool block_tx; u8 count; + u16 punct_bitmap; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a984c6c4cf02..831660956ab2 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2769,6 +2769,12 @@ enum nl80211_commands { * the incoming frame RX timestamp. * @NL80211_ATTR_TD_BITMAP: Transition Disable bitmap, for subsequent * (re)associations. + * + * @NL80211_ATTR_PUNCT_BITMAP: (u32) Preamble puncturing bitmap, lowest + * bit corresponds to the lowest 20 MHz channel. Each bit set to 1 + * indicates that the sub-channel is punctured. Higher 16 bits are + * reserved. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3298,6 +3304,8 @@ enum nl80211_attrs { NL80211_ATTR_RX_HW_TIMESTAMP, NL80211_ATTR_TD_BITMAP, + NL80211_ATTR_PUNCT_BITMAP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -6313,6 +6321,8 @@ enum nl80211_feature_flags { * might apply, e.g. no scans in progress, no offchannel operations * in progress, and no active connections. * + * @NL80211_EXT_FEATURE_PUNCT: Driver supports preamble puncturing in AP mode. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6381,6 +6391,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, NL80211_EXT_FEATURE_RADAR_BACKGROUND, NL80211_EXT_FEATURE_POWERED_ADDR_CHANGE, + NL80211_EXT_FEATURE_PUNCT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c82c66c32faa..683adeb3c9e3 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -805,6 +805,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), [NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_MAX_NUM_AKM_SUITES] = { .type = NLA_REJECT }, + [NL80211_ATTR_PUNCT_BITMAP] = NLA_POLICY_RANGE(NLA_U8, 0, 0xffff), }; /* policy for the key attributes */ @@ -3173,6 +3174,21 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) wdev->iftype == NL80211_IFTYPE_P2P_GO; } +static int nl80211_parse_punct_bitmap(struct cfg80211_registered_device *rdev, + struct genl_info *info, + const struct cfg80211_chan_def *chandef, + u16 *punct_bitmap) +{ + if (!wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_PUNCT)) + return -EINVAL; + + *punct_bitmap = nla_get_u32(info->attrs[NL80211_ATTR_PUNCT_BITMAP]); + if (!cfg80211_valid_disable_subchannel_bitmap(punct_bitmap, chandef)) + return -EINVAL; + + return 0; +} + int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct genl_info *info, struct cfg80211_chan_def *chandef) @@ -5957,6 +5973,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } + if (info->attrs[NL80211_ATTR_PUNCT_BITMAP]) { + err = nl80211_parse_punct_bitmap(rdev, info, + ¶ms->chandef, + ¶ms->punct_bitmap); + if (err) + goto out; + } + if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms->chandef, wdev->iftype)) { err = -EINVAL; @@ -10114,6 +10138,14 @@ skip_beacons: if (info->attrs[NL80211_ATTR_CH_SWITCH_BLOCK_TX]) params.block_tx = true; + if (info->attrs[NL80211_ATTR_PUNCT_BITMAP]) { + err = nl80211_parse_punct_bitmap(rdev, info, + ¶ms.chandef, + ¶ms.punct_bitmap); + if (err) + goto free; + } + wdev_lock(wdev); err = rdev_channel_switch(rdev, dev, ¶ms); wdev_unlock(wdev); -- cgit v1.2.3 From 9b89495e479c5fedbf3f2eca4f1c4e9dd481265e Mon Sep 17 00:00:00 2001 From: Vinay Gannevaram Date: Sat, 4 Feb 2023 19:29:39 +0530 Subject: wifi: nl80211: Allow authentication frames and set keys on NAN interface Wi-Fi Aware R4 specification defines NAN Pairing which uses PASN handshake to authenticate the peer and generate keys. Hence allow to register and transmit the PASN authentication frames on NAN interface and set the keys to driver or underlying modules on NAN interface. The driver needs to configure the feature flag NL80211_EXT_FEATURE_SECURE_NAN, which also helps userspace modules to know if the driver supports secure NAN. Signed-off-by: Vinay Gannevaram Link: https://lore.kernel.org/r/1675519179-24174-1-git-send-email-quic_vganneva@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 ++++ net/wireless/nl80211.c | 18 +++++++++++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 831660956ab2..f14621a954e1 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -6323,6 +6323,9 @@ enum nl80211_feature_flags { * * @NL80211_EXT_FEATURE_PUNCT: Driver supports preamble puncturing in AP mode. * + * @NL80211_EXT_FEATURE_SECURE_NAN: Device supports NAN Pairing which enables + * authentication, data encryption and message integrity. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6392,6 +6395,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_RADAR_BACKGROUND, NL80211_EXT_FEATURE_POWERED_ADDR_CHANGE, NL80211_EXT_FEATURE_PUNCT, + NL80211_EXT_FEATURE_SECURE_NAN, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 22e6bc9a44cb..4f112d75ac9c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1549,10 +1549,14 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) if (wdev->connected) return 0; return -ENOLINK; + case NL80211_IFTYPE_NAN: + if (wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_NAN)) + return 0; + return -EINVAL; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_WDS: case NUM_NL80211_IFTYPES: @@ -12342,6 +12346,10 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_P2P_DEVICE: break; case NL80211_IFTYPE_NAN: + if (!wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_NAN)) + return -EOPNOTSUPP; + break; default: return -EOPNOTSUPP; } @@ -12399,6 +12407,10 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_P2P_GO: break; case NL80211_IFTYPE_NAN: + if (!wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_NAN)) + return -EOPNOTSUPP; + break; default: return -EOPNOTSUPP; } @@ -12536,6 +12548,10 @@ static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *in case NL80211_IFTYPE_P2P_DEVICE: break; case NL80211_IFTYPE_NAN: + if (!wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_NAN)) + return -EOPNOTSUPP; + break; default: return -EOPNOTSUPP; } -- cgit v1.2.3 From 248529edc86f8d7d390a15a86bd1904951311665 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 14 Feb 2023 10:00:24 -0700 Subject: cxl: add RAS status unmasking for CXL By default the CXL RAS mask registers bits are defaulted to 1's and suppress all error reporting. If the kernel has negotiated ownership of error handling for CXL then unmask the mask registers by writing 0s. PCI_EXP_DEVCTL capability is checked to see uncorrectable or correctable errors bits are set before unmasking the respective errors. Acked-by: Bjorn Helgaas # pci_regs.h Reviewed-by: Jonathan Cameron Signed-off-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/167639402301.778884.12556849214955646539.stgit@djiang5-mobl3.local Signed-off-by: Dan Williams --- drivers/cxl/cxl.h | 1 + drivers/cxl/pci.c | 65 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pci_regs.h | 1 + 3 files changed, 67 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index aa3af3bb73b2..197ecffce4d0 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -130,6 +130,7 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw) #define CXL_RAS_UNCORRECTABLE_STATUS_MASK (GENMASK(16, 14) | GENMASK(11, 0)) #define CXL_RAS_UNCORRECTABLE_MASK_OFFSET 0x4 #define CXL_RAS_UNCORRECTABLE_MASK_MASK (GENMASK(16, 14) | GENMASK(11, 0)) +#define CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK BIT(8) #define CXL_RAS_UNCORRECTABLE_SEVERITY_OFFSET 0x8 #define CXL_RAS_UNCORRECTABLE_SEVERITY_MASK (GENMASK(16, 14) | GENMASK(11, 0)) #define CXL_RAS_CORRECTABLE_STATUS_OFFSET 0xC diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index cc8b5a766a82..a509640994d7 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -412,6 +412,67 @@ static bool is_cxl_restricted(struct pci_dev *pdev) return pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END; } +/* + * CXL v3.0 6.2.3 Table 6-4 + * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits + * mode, otherwise it's 68B flits mode. + */ +static bool cxl_pci_flit_256(struct pci_dev *pdev) +{ + u16 lnksta2; + + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2); + return lnksta2 & PCI_EXP_LNKSTA2_FLIT; +} + +static int cxl_pci_ras_unmask(struct pci_dev *pdev) +{ + struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus); + struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); + void __iomem *addr; + u32 orig_val, val, mask; + u16 cap; + int rc; + + if (!cxlds->regs.ras) { + dev_dbg(&pdev->dev, "No RAS registers.\n"); + return 0; + } + + /* BIOS has CXL error control */ + if (!host_bridge->native_cxl_error) + return -ENXIO; + + rc = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &cap); + if (rc) + return rc; + + if (cap & PCI_EXP_DEVCTL_URRE) { + addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_MASK_OFFSET; + orig_val = readl(addr); + + mask = CXL_RAS_UNCORRECTABLE_MASK_MASK; + if (!cxl_pci_flit_256(pdev)) + mask &= ~CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK; + val = orig_val & ~mask; + writel(val, addr); + dev_dbg(&pdev->dev, + "Uncorrectable RAS Errors Mask: %#x -> %#x\n", + orig_val, val); + } + + if (cap & PCI_EXP_DEVCTL_CERE) { + addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_MASK_OFFSET; + orig_val = readl(addr); + val = orig_val & ~CXL_RAS_CORRECTABLE_MASK_MASK; + writel(val, addr); + dev_dbg(&pdev->dev, "Correctable RAS Errors Mask: %#x -> %#x\n", + orig_val, val); + } + + return 0; +} + static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct cxl_register_map map; @@ -489,6 +550,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); + rc = cxl_pci_ras_unmask(pdev); + if (rc) + dev_dbg(&pdev->dev, "No RAS reporting unmasked\n"); + pci_save_state(pdev); return rc; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 85ab1278811e..dc2000e0fe3a 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -693,6 +693,7 @@ #define PCI_EXP_LNKCTL2_TX_MARGIN 0x0380 /* Transmit Margin */ #define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ #define PCI_EXP_LNKSTA2 0x32 /* Link Status 2 */ +#define PCI_EXP_LNKSTA2_FLIT 0x0400 /* Flit Mode Status */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32 /* end of v2 EPs w/ link */ #define PCI_EXP_SLTCAP2 0x34 /* Slot Capabilities 2 */ #define PCI_EXP_SLTCAP2_IBPD 0x00000001 /* In-band PD Disable Supported */ -- cgit v1.2.3 From 95bfec41bd3d39b7659cba65b72080420bf5691e Mon Sep 17 00:00:00 2001 From: Dmitry Fomichev Date: Sat, 15 Oct 2022 23:41:27 -0400 Subject: virtio-blk: add support for zoned block devices This patch adds support for Zoned Block Devices (ZBDs) to the kernel virtio-blk driver. The patch accompanies the virtio-blk ZBD support draft that is now being proposed for standardization. The latest version of the draft is linked at https://github.com/oasis-tcs/virtio-spec/issues/143 . The QEMU zoned device code that implements these protocol extensions has been developed by Sam Li and it is currently in review at the QEMU mailing list. A number of virtblk request structure changes has been introduced to accommodate the functionality that is specific to zoned block devices and, most importantly, make room for carrying the Zoned Append sector value from the device back to the driver along with the request status. The zone-specific code in the patch is heavily influenced by NVMe ZNS code in drivers/nvme/host/zns.c, but it is simpler because the proposed virtio ZBD draft only covers the zoned device features that are relevant to the zoned functionality provided by Linux block layer. includes the following fixup: virtio-blk: fix probe without CONFIG_BLK_DEV_ZONED When building without CONFIG_BLK_DEV_ZONED, VIRTIO_BLK_F_ZONED is excluded from array of driver features. As a result virtio_has_feature panics in virtio_check_driver_offered_feature since that by design verifies that a feature we are checking for is listed in the feature array. To fix, replace the call to virtio_has_feature with a stub. Message-Id: <20221016034127.330942-3-dmitry.fomichev@wdc.com> Co-developed-by: Stefan Hajnoczi Signed-off-by: Stefan Hajnoczi Signed-off-by: Dmitry Fomichev Message-Id: <20221220112340.518841-1-mst@redhat.com> Reported-by: Linux Kernel Functional Testing Tested-by: Linux Kernel Functional Testing Reported-by: Xuan Zhuo Debugged-by: Xuan Zhuo Tested-by: Anders Roxell Tested-by: Marek Szyprowski Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/block/virtio_blk.c | 387 ++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/virtio_blk.h | 105 +++++++++++ 2 files changed, 474 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6a77fa917428..71e1e4bd8439 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #define PART_BITS 4 @@ -80,22 +81,51 @@ struct virtio_blk { int num_vqs; int io_queues[HCTX_MAX_TYPES]; struct virtio_blk_vq *vqs; + + /* For zoned device */ + unsigned int zone_sectors; }; struct virtblk_req { + /* Out header */ struct virtio_blk_outhdr out_hdr; - u8 status; + + /* In header */ + union { + u8 status; + + /* + * The zone append command has an extended in header. + * The status field in zone_append_in_hdr must have + * the same offset in virtblk_req as the non-zoned + * status field above. + */ + struct { + u8 status; + u8 reserved[7]; + u64 append_sector; + } zone_append_in_hdr; + }; + + size_t in_hdr_len; + struct sg_table sg_table; struct scatterlist sg[]; }; -static inline blk_status_t virtblk_result(struct virtblk_req *vbr) +static inline blk_status_t virtblk_result(u8 status) { - switch (vbr->status) { + switch (status) { case VIRTIO_BLK_S_OK: return BLK_STS_OK; case VIRTIO_BLK_S_UNSUPP: return BLK_STS_NOTSUPP; + case VIRTIO_BLK_S_ZONE_OPEN_RESOURCE: + return BLK_STS_ZONE_OPEN_RESOURCE; + case VIRTIO_BLK_S_ZONE_ACTIVE_RESOURCE: + return BLK_STS_ZONE_ACTIVE_RESOURCE; + case VIRTIO_BLK_S_IOERR: + case VIRTIO_BLK_S_ZONE_UNALIGNED_WP: default: return BLK_STS_IOERR; } @@ -111,11 +141,11 @@ static inline struct virtio_blk_vq *get_virtio_blk_vq(struct blk_mq_hw_ctx *hctx static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr) { - struct scatterlist hdr, status, *sgs[3]; + struct scatterlist out_hdr, in_hdr, *sgs[3]; unsigned int num_out = 0, num_in = 0; - sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr)); - sgs[num_out++] = &hdr; + sg_init_one(&out_hdr, &vbr->out_hdr, sizeof(vbr->out_hdr)); + sgs[num_out++] = &out_hdr; if (vbr->sg_table.nents) { if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT)) @@ -124,8 +154,8 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr) sgs[num_out + num_in++] = vbr->sg_table.sgl; } - sg_init_one(&status, &vbr->status, sizeof(vbr->status)); - sgs[num_out + num_in++] = &status; + sg_init_one(&in_hdr, &vbr->status, vbr->in_hdr_len); + sgs[num_out + num_in++] = &in_hdr; return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); } @@ -214,21 +244,22 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, struct request *req, struct virtblk_req *vbr) { + size_t in_hdr_len = sizeof(vbr->status); bool unmap = false; u32 type; + u64 sector = 0; - vbr->out_hdr.sector = 0; + /* Set fields for all request types */ + vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req)); switch (req_op(req)) { case REQ_OP_READ: type = VIRTIO_BLK_T_IN; - vbr->out_hdr.sector = cpu_to_virtio64(vdev, - blk_rq_pos(req)); + sector = blk_rq_pos(req); break; case REQ_OP_WRITE: type = VIRTIO_BLK_T_OUT; - vbr->out_hdr.sector = cpu_to_virtio64(vdev, - blk_rq_pos(req)); + sector = blk_rq_pos(req); break; case REQ_OP_FLUSH: type = VIRTIO_BLK_T_FLUSH; @@ -243,16 +274,42 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, case REQ_OP_SECURE_ERASE: type = VIRTIO_BLK_T_SECURE_ERASE; break; - case REQ_OP_DRV_IN: - type = VIRTIO_BLK_T_GET_ID; + case REQ_OP_ZONE_OPEN: + type = VIRTIO_BLK_T_ZONE_OPEN; + sector = blk_rq_pos(req); + break; + case REQ_OP_ZONE_CLOSE: + type = VIRTIO_BLK_T_ZONE_CLOSE; + sector = blk_rq_pos(req); + break; + case REQ_OP_ZONE_FINISH: + type = VIRTIO_BLK_T_ZONE_FINISH; + sector = blk_rq_pos(req); + break; + case REQ_OP_ZONE_APPEND: + type = VIRTIO_BLK_T_ZONE_APPEND; + sector = blk_rq_pos(req); + in_hdr_len = sizeof(vbr->zone_append_in_hdr); break; + case REQ_OP_ZONE_RESET: + type = VIRTIO_BLK_T_ZONE_RESET; + sector = blk_rq_pos(req); + break; + case REQ_OP_ZONE_RESET_ALL: + type = VIRTIO_BLK_T_ZONE_RESET_ALL; + break; + case REQ_OP_DRV_IN: + /* Out header already filled in, nothing to do */ + return 0; default: WARN_ON_ONCE(1); return BLK_STS_IOERR; } + /* Set fields for non-REQ_OP_DRV_IN request types */ + vbr->in_hdr_len = in_hdr_len; vbr->out_hdr.type = cpu_to_virtio32(vdev, type); - vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req)); + vbr->out_hdr.sector = cpu_to_virtio64(vdev, sector); if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES || type == VIRTIO_BLK_T_SECURE_ERASE) { @@ -266,10 +323,15 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, static inline void virtblk_request_done(struct request *req) { struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); + int status = virtblk_result(vbr->status); virtblk_unmap_data(req, vbr); virtblk_cleanup_cmd(req); - blk_mq_end_request(req, virtblk_result(vbr)); + + if (req_op(req) == REQ_OP_ZONE_APPEND) + req->__sector = le64_to_cpu(vbr->zone_append_in_hdr.append_sector); + + blk_mq_end_request(req, status); } static void virtblk_done(struct virtqueue *vq) @@ -457,6 +519,275 @@ static void virtio_queue_rqs(struct request **rqlist) *rqlist = requeue_list; } +#ifdef CONFIG_BLK_DEV_ZONED +static void *virtblk_alloc_report_buffer(struct virtio_blk *vblk, + unsigned int nr_zones, + unsigned int zone_sectors, + size_t *buflen) +{ + struct request_queue *q = vblk->disk->queue; + size_t bufsize; + void *buf; + + nr_zones = min_t(unsigned int, nr_zones, + get_capacity(vblk->disk) >> ilog2(zone_sectors)); + + bufsize = sizeof(struct virtio_blk_zone_report) + + nr_zones * sizeof(struct virtio_blk_zone_descriptor); + bufsize = min_t(size_t, bufsize, + queue_max_hw_sectors(q) << SECTOR_SHIFT); + bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); + + while (bufsize >= sizeof(struct virtio_blk_zone_report)) { + buf = __vmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY); + if (buf) { + *buflen = bufsize; + return buf; + } + bufsize >>= 1; + } + + return NULL; +} + +static int virtblk_submit_zone_report(struct virtio_blk *vblk, + char *report_buf, size_t report_len, + sector_t sector) +{ + struct request_queue *q = vblk->disk->queue; + struct request *req; + struct virtblk_req *vbr; + int err; + + req = blk_mq_alloc_request(q, REQ_OP_DRV_IN, 0); + if (IS_ERR(req)) + return PTR_ERR(req); + + vbr = blk_mq_rq_to_pdu(req); + vbr->in_hdr_len = sizeof(vbr->status); + vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_ZONE_REPORT); + vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, sector); + + err = blk_rq_map_kern(q, req, report_buf, report_len, GFP_KERNEL); + if (err) + goto out; + + blk_execute_rq(req, false); + err = blk_status_to_errno(virtblk_result(vbr->status)); +out: + blk_mq_free_request(req); + return err; +} + +static int virtblk_parse_zone(struct virtio_blk *vblk, + struct virtio_blk_zone_descriptor *entry, + unsigned int idx, unsigned int zone_sectors, + report_zones_cb cb, void *data) +{ + struct blk_zone zone = { }; + + if (entry->z_type != VIRTIO_BLK_ZT_SWR && + entry->z_type != VIRTIO_BLK_ZT_SWP && + entry->z_type != VIRTIO_BLK_ZT_CONV) { + dev_err(&vblk->vdev->dev, "invalid zone type %#x\n", + entry->z_type); + return -EINVAL; + } + + zone.type = entry->z_type; + zone.cond = entry->z_state; + zone.len = zone_sectors; + zone.capacity = le64_to_cpu(entry->z_cap); + zone.start = le64_to_cpu(entry->z_start); + if (zone.cond == BLK_ZONE_COND_FULL) + zone.wp = zone.start + zone.len; + else + zone.wp = le64_to_cpu(entry->z_wp); + + return cb(&zone, idx, data); +} + +static int virtblk_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, + void *data) +{ + struct virtio_blk *vblk = disk->private_data; + struct virtio_blk_zone_report *report; + unsigned int zone_sectors = vblk->zone_sectors; + unsigned int nz, i; + int ret, zone_idx = 0; + size_t buflen; + + if (WARN_ON_ONCE(!vblk->zone_sectors)) + return -EOPNOTSUPP; + + report = virtblk_alloc_report_buffer(vblk, nr_zones, + zone_sectors, &buflen); + if (!report) + return -ENOMEM; + + while (zone_idx < nr_zones && sector < get_capacity(vblk->disk)) { + memset(report, 0, buflen); + + ret = virtblk_submit_zone_report(vblk, (char *)report, + buflen, sector); + if (ret) { + if (ret > 0) + ret = -EIO; + goto out_free; + } + nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones); + if (!nz) + break; + + for (i = 0; i < nz && zone_idx < nr_zones; i++) { + ret = virtblk_parse_zone(vblk, &report->zones[i], + zone_idx, zone_sectors, cb, data); + if (ret) + goto out_free; + sector = le64_to_cpu(report->zones[i].z_start) + zone_sectors; + zone_idx++; + } + } + + if (zone_idx > 0) + ret = zone_idx; + else + ret = -EINVAL; +out_free: + kvfree(report); + return ret; +} + +static void virtblk_revalidate_zones(struct virtio_blk *vblk) +{ + u8 model; + + if (!vblk->zone_sectors) + return; + + virtio_cread(vblk->vdev, struct virtio_blk_config, + zoned.model, &model); + if (!blk_revalidate_disk_zones(vblk->disk, NULL)) + set_capacity_and_notify(vblk->disk, 0); +} + +static int virtblk_probe_zoned_device(struct virtio_device *vdev, + struct virtio_blk *vblk, + struct request_queue *q) +{ + u32 v; + u8 model; + int ret; + + virtio_cread(vdev, struct virtio_blk_config, + zoned.model, &model); + + switch (model) { + case VIRTIO_BLK_Z_NONE: + return 0; + case VIRTIO_BLK_Z_HM: + break; + case VIRTIO_BLK_Z_HA: + /* + * Present the host-aware device as a regular drive. + * TODO It is possible to add an option to make it appear + * in the system as a zoned drive. + */ + return 0; + default: + dev_err(&vdev->dev, "unsupported zone model %d\n", model); + return -EINVAL; + } + + dev_dbg(&vdev->dev, "probing host-managed zoned device\n"); + + disk_set_zoned(vblk->disk, BLK_ZONED_HM); + blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); + + virtio_cread(vdev, struct virtio_blk_config, + zoned.max_open_zones, &v); + disk_set_max_open_zones(vblk->disk, le32_to_cpu(v)); + + dev_dbg(&vdev->dev, "max open zones = %u\n", le32_to_cpu(v)); + + virtio_cread(vdev, struct virtio_blk_config, + zoned.max_active_zones, &v); + disk_set_max_active_zones(vblk->disk, le32_to_cpu(v)); + dev_dbg(&vdev->dev, "max active zones = %u\n", le32_to_cpu(v)); + + virtio_cread(vdev, struct virtio_blk_config, + zoned.write_granularity, &v); + if (!v) { + dev_warn(&vdev->dev, "zero write granularity reported\n"); + return -ENODEV; + } + blk_queue_physical_block_size(q, le32_to_cpu(v)); + blk_queue_io_min(q, le32_to_cpu(v)); + + dev_dbg(&vdev->dev, "write granularity = %u\n", le32_to_cpu(v)); + + /* + * virtio ZBD specification doesn't require zones to be a power of + * two sectors in size, but the code in this driver expects that. + */ + virtio_cread(vdev, struct virtio_blk_config, zoned.zone_sectors, &v); + vblk->zone_sectors = le32_to_cpu(v); + if (vblk->zone_sectors == 0 || !is_power_of_2(vblk->zone_sectors)) { + dev_err(&vdev->dev, + "zoned device with non power of two zone size %u\n", + vblk->zone_sectors); + return -ENODEV; + } + dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors); + + if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { + dev_warn(&vblk->vdev->dev, + "ignoring negotiated F_DISCARD for zoned device\n"); + blk_queue_max_discard_sectors(q, 0); + } + + ret = blk_revalidate_disk_zones(vblk->disk, NULL); + if (!ret) { + virtio_cread(vdev, struct virtio_blk_config, + zoned.max_append_sectors, &v); + if (!v) { + dev_warn(&vdev->dev, "zero max_append_sectors reported\n"); + return -ENODEV; + } + blk_queue_max_zone_append_sectors(q, le32_to_cpu(v)); + dev_dbg(&vdev->dev, "max append sectors = %u\n", le32_to_cpu(v)); + } + + return ret; +} + +static inline bool virtblk_has_zoned_feature(struct virtio_device *vdev) +{ + return virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED); +} +#else + +/* + * Zoned block device support is not configured in this kernel. + * We only need to define a few symbols to avoid compilation errors. + */ +#define virtblk_report_zones NULL +static inline void virtblk_revalidate_zones(struct virtio_blk *vblk) +{ +} +static inline int virtblk_probe_zoned_device(struct virtio_device *vdev, + struct virtio_blk *vblk, struct request_queue *q) +{ + return -EOPNOTSUPP; +} + +static inline bool virtblk_has_zoned_feature(struct virtio_device *vdev) +{ + return false; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + /* return id (s/n) string for *disk to *id_str */ static int virtblk_get_id(struct gendisk *disk, char *id_str) @@ -464,18 +795,24 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) struct virtio_blk *vblk = disk->private_data; struct request_queue *q = vblk->disk->queue; struct request *req; + struct virtblk_req *vbr; int err; req = blk_mq_alloc_request(q, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) return PTR_ERR(req); + vbr = blk_mq_rq_to_pdu(req); + vbr->in_hdr_len = sizeof(vbr->status); + vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID); + vbr->out_hdr.sector = 0; + err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL); if (err) goto out; blk_execute_rq(req, false); - err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req))); + err = blk_status_to_errno(virtblk_result(vbr->status)); out: blk_mq_free_request(req); return err; @@ -526,6 +863,7 @@ static const struct block_device_operations virtblk_fops = { .owner = THIS_MODULE, .getgeo = virtblk_getgeo, .free_disk = virtblk_free_disk, + .report_zones = virtblk_report_zones, }; static int index_to_minor(int index) @@ -596,6 +934,7 @@ static void virtblk_config_changed_work(struct work_struct *work) struct virtio_blk *vblk = container_of(work, struct virtio_blk, config_work); + virtblk_revalidate_zones(vblk); virtblk_update_capacity(vblk, true); } @@ -1152,6 +1491,15 @@ static int virtblk_probe(struct virtio_device *vdev) virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); + if (virtblk_has_zoned_feature(vdev)) { + err = virtblk_probe_zoned_device(vdev, vblk, q); + if (err) + goto out_cleanup_disk; + } + + dev_info(&vdev->dev, "blk config size: %zu\n", + sizeof(struct virtio_blk_config)); + err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); if (err) goto out_cleanup_disk; @@ -1253,6 +1601,9 @@ static unsigned int features[] = { VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, VIRTIO_BLK_F_SECURE_ERASE, +#ifdef CONFIG_BLK_DEV_ZONED + VIRTIO_BLK_F_ZONED, +#endif /* CONFIG_BLK_DEV_ZONED */ }; static struct virtio_driver virtio_blk = { diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 58e70b24b504..3744e4da1b2a 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -41,6 +41,7 @@ #define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */ #define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */ #define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */ +#define VIRTIO_BLK_F_ZONED 17 /* Zoned block device */ /* Legacy feature bits */ #ifndef VIRTIO_BLK_NO_LEGACY @@ -137,6 +138,16 @@ struct virtio_blk_config { /* Secure erase commands must be aligned to this number of sectors. */ __virtio32 secure_erase_sector_alignment; + /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ + struct virtio_blk_zoned_characteristics { + __virtio32 zone_sectors; + __virtio32 max_open_zones; + __virtio32 max_active_zones; + __virtio32 max_append_sectors; + __virtio32 write_granularity; + __u8 model; + __u8 unused2[3]; + } zoned; } __attribute__((packed)); /* @@ -174,6 +185,27 @@ struct virtio_blk_config { /* Secure erase command */ #define VIRTIO_BLK_T_SECURE_ERASE 14 +/* Zone append command */ +#define VIRTIO_BLK_T_ZONE_APPEND 15 + +/* Report zones command */ +#define VIRTIO_BLK_T_ZONE_REPORT 16 + +/* Open zone command */ +#define VIRTIO_BLK_T_ZONE_OPEN 18 + +/* Close zone command */ +#define VIRTIO_BLK_T_ZONE_CLOSE 20 + +/* Finish zone command */ +#define VIRTIO_BLK_T_ZONE_FINISH 22 + +/* Reset zone command */ +#define VIRTIO_BLK_T_ZONE_RESET 24 + +/* Reset All zones command */ +#define VIRTIO_BLK_T_ZONE_RESET_ALL 26 + #ifndef VIRTIO_BLK_NO_LEGACY /* Barrier before this op. */ #define VIRTIO_BLK_T_BARRIER 0x80000000 @@ -193,6 +225,72 @@ struct virtio_blk_outhdr { __virtio64 sector; }; +/* + * Supported zoned device models. + */ + +/* Regular block device */ +#define VIRTIO_BLK_Z_NONE 0 +/* Host-managed zoned device */ +#define VIRTIO_BLK_Z_HM 1 +/* Host-aware zoned device */ +#define VIRTIO_BLK_Z_HA 2 + +/* + * Zone descriptor. A part of VIRTIO_BLK_T_ZONE_REPORT command reply. + */ +struct virtio_blk_zone_descriptor { + /* Zone capacity */ + __virtio64 z_cap; + /* The starting sector of the zone */ + __virtio64 z_start; + /* Zone write pointer position in sectors */ + __virtio64 z_wp; + /* Zone type */ + __u8 z_type; + /* Zone state */ + __u8 z_state; + __u8 reserved[38]; +}; + +struct virtio_blk_zone_report { + __virtio64 nr_zones; + __u8 reserved[56]; + struct virtio_blk_zone_descriptor zones[]; +}; + +/* + * Supported zone types. + */ + +/* Conventional zone */ +#define VIRTIO_BLK_ZT_CONV 1 +/* Sequential Write Required zone */ +#define VIRTIO_BLK_ZT_SWR 2 +/* Sequential Write Preferred zone */ +#define VIRTIO_BLK_ZT_SWP 3 + +/* + * Zone states that are available for zones of all types. + */ + +/* Not a write pointer (conventional zones only) */ +#define VIRTIO_BLK_ZS_NOT_WP 0 +/* Empty */ +#define VIRTIO_BLK_ZS_EMPTY 1 +/* Implicitly Open */ +#define VIRTIO_BLK_ZS_IOPEN 2 +/* Explicitly Open */ +#define VIRTIO_BLK_ZS_EOPEN 3 +/* Closed */ +#define VIRTIO_BLK_ZS_CLOSED 4 +/* Read-Only */ +#define VIRTIO_BLK_ZS_RDONLY 13 +/* Full */ +#define VIRTIO_BLK_ZS_FULL 14 +/* Offline */ +#define VIRTIO_BLK_ZS_OFFLINE 15 + /* Unmap this range (only valid for write zeroes command) */ #define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001 @@ -219,4 +317,11 @@ struct virtio_scsi_inhdr { #define VIRTIO_BLK_S_OK 0 #define VIRTIO_BLK_S_IOERR 1 #define VIRTIO_BLK_S_UNSUPP 2 + +/* Error codes that are specific to zoned block devices */ +#define VIRTIO_BLK_S_ZONE_INVALID_CMD 3 +#define VIRTIO_BLK_S_ZONE_UNALIGNED_WP 4 +#define VIRTIO_BLK_S_ZONE_OPEN_RESOURCE 5 +#define VIRTIO_BLK_S_ZONE_ACTIVE_RESOURCE 6 + #endif /* _LINUX_VIRTIO_BLK_H */ -- cgit v1.2.3 From b16a1756c716235891e298beabd68f3cd6bb5952 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 22 Dec 2022 14:30:13 -0500 Subject: virtio_blk: mark all zone fields LE zone is a virtio 1.x feature so all fields are LE, they are handled as such, but have mistakenly been labeled __virtioXX in the header. This results in a bunch of sparse warnings. Use the __leXX tags to make sparse happy. Message-Id: <20221222193214.55146-1-mst@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_blk.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 3744e4da1b2a..5af2a0300bb9 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -140,11 +140,11 @@ struct virtio_blk_config { /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ struct virtio_blk_zoned_characteristics { - __virtio32 zone_sectors; - __virtio32 max_open_zones; - __virtio32 max_active_zones; - __virtio32 max_append_sectors; - __virtio32 write_granularity; + __le32 zone_sectors; + __le32 max_open_zones; + __le32 max_active_zones; + __le32 max_append_sectors; + __le32 write_granularity; __u8 model; __u8 unused2[3]; } zoned; @@ -241,11 +241,11 @@ struct virtio_blk_outhdr { */ struct virtio_blk_zone_descriptor { /* Zone capacity */ - __virtio64 z_cap; + __le64 z_cap; /* The starting sector of the zone */ - __virtio64 z_start; + __le64 z_start; /* Zone write pointer position in sectors */ - __virtio64 z_wp; + __le64 z_wp; /* Zone type */ __u8 z_type; /* Zone state */ @@ -254,7 +254,7 @@ struct virtio_blk_zone_descriptor { }; struct virtio_blk_zone_report { - __virtio64 nr_zones; + __le64 nr_zones; __u8 reserved[56]; struct virtio_blk_zone_descriptor zones[]; }; -- cgit v1.2.3 From 72206cc730b5c9208e9a99ace1c619f542035312 Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Tue, 14 Feb 2023 13:27:37 +0100 Subject: tty: n_gsm: add keep alive support n_gsm is based on the 3GPP 07.010 and its newer version is the 3GPP 27.010. See https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=1516 The changes from 07.010 to 27.010 are non-functional. Therefore, I refer to the newer 27.010 here. Chapters 5.4.6.3.4 and 5.1.8.1.3 describe the test command which can be used to test the mux connection between both sides. Currently, no algorithm is implemented to make use of this command. This requires that each multiplexed upper layer protocol supervises the underlying muxer connection to handle possible connection losses. Introduce ioctl commands and functions to optionally enable keep alive handling via the test command as described in chapter 5.4.6.3.4. A single incrementing octet "ka_num" is being used for unique identification of each single keep alive packet. Retries will use the same "ka_num" value as the original packet. Retry count and interval are taken from the general parameters N2 and T2. Add usage description and basic example for the new ioctl to the n_gsm documentation. Note that support for the test command is mandatory and already present in the muxer implementation since the very first version. Also note that the previous ioctl structure gsm_config cannot be extended due to missing checks against zero of the field "unused". Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230214122737.1976-1-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/tty/n_gsm.rst | 19 ++++++ drivers/tty/n_gsm.c | 106 ++++++++++++++++++++++++++++++++- include/uapi/linux/gsmmux.h | 10 ++++ 3 files changed, 133 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/driver-api/tty/n_gsm.rst b/Documentation/driver-api/tty/n_gsm.rst index 35d7381515b0..9447b8a3b8e2 100644 --- a/Documentation/driver-api/tty/n_gsm.rst +++ b/Documentation/driver-api/tty/n_gsm.rst @@ -25,6 +25,8 @@ Config Initiator #. Switch the serial line to using the n_gsm line discipline by using ``TIOCSETD`` ioctl. +#. Configure the mux using ``GSMIOC_GETCONF_EXT``/``GSMIOC_SETCONF_EXT`` ioctl if needed. + #. Configure the mux using ``GSMIOC_GETCONF``/``GSMIOC_SETCONF`` ioctl. #. Obtain base gsmtty number for the used serial port. @@ -42,6 +44,7 @@ Config Initiator int ldisc = N_GSM0710; struct gsm_config c; + struct gsm_config_ext ce; struct termios configuration; uint32_t first; @@ -62,6 +65,12 @@ Config Initiator /* use n_gsm line discipline */ ioctl(fd, TIOCSETD, &ldisc); + /* get n_gsm extended configuration */ + ioctl(fd, GSMIOC_GETCONF_EXT, &ce); + /* use keep-alive once every 5s for modem connection supervision */ + ce.keep_alive = 500; + /* set the new extended configuration */ + ioctl(fd, GSMIOC_SETCONF_EXT, &ce); /* get n_gsm configuration */ ioctl(fd, GSMIOC_GETCONF, &c); /* we are initiator and need encoding 0 (basic) */ @@ -106,6 +115,9 @@ Config Requester #. Switch the serial line to using the *n_gsm* line discipline by using ``TIOCSETD`` ioctl. +#. Configure the mux using ``GSMIOC_GETCONF_EXT``/``GSMIOC_SETCONF_EXT`` + ioctl if needed. + #. Configure the mux using ``GSMIOC_GETCONF``/``GSMIOC_SETCONF`` ioctl. #. Obtain base gsmtty number for the used serial port:: @@ -119,6 +131,7 @@ Config Requester int ldisc = N_GSM0710; struct gsm_config c; + struct gsm_config_ext ce; struct termios configuration; uint32_t first; @@ -132,6 +145,12 @@ Config Requester /* use n_gsm line discipline */ ioctl(fd, TIOCSETD, &ldisc); + /* get n_gsm extended configuration */ + ioctl(fd, GSMIOC_GETCONF_EXT, &ce); + /* use keep-alive once every 5s for peer connection supervision */ + ce.keep_alive = 500; + /* set the new extended configuration */ + ioctl(fd, GSMIOC_SETCONF_EXT, &ce); /* get n_gsm configuration */ ioctl(fd, GSMIOC_GETCONF, &c); /* we are requester and need encoding 0 (basic) */ diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 58ea30fd6576..7aa05ebed8e1 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -318,6 +318,11 @@ struct gsm_mux { struct gsm_control *pending_cmd;/* Our current pending command */ spinlock_t control_lock; /* Protects the pending command */ + /* Keep-alive */ + struct timer_list ka_timer; /* Keep-alive response timer */ + u8 ka_num; /* Keep-alive match pattern */ + signed int ka_retries; /* Keep-alive retry counter, -1 if not yet initialized */ + /* Configuration */ int adaption; /* 1 or 2 supported */ u8 ftype; /* UI or UIH */ @@ -325,6 +330,7 @@ struct gsm_mux { unsigned int t3; /* Power wake-up timer in seconds. */ int n2; /* Retry count */ u8 k; /* Window size */ + u32 keep_alive; /* Control channel keep-alive in 10ms */ /* Statistics (not currently exposed) */ unsigned long bad_fcs; @@ -1903,11 +1909,13 @@ static void gsm_control_response(struct gsm_mux *gsm, unsigned int command, const u8 *data, int clen) { struct gsm_control *ctrl; + struct gsm_dlci *dlci; unsigned long flags; spin_lock_irqsave(&gsm->control_lock, flags); ctrl = gsm->pending_cmd; + dlci = gsm->dlci[0]; command |= 1; /* Does the reply match our command */ if (ctrl != NULL && (command == ctrl->cmd || command == CMD_NSC)) { @@ -1922,6 +1930,53 @@ static void gsm_control_response(struct gsm_mux *gsm, unsigned int command, /* Or did we receive the PN response to our PN command */ } else if (command == CMD_PN) { gsm_control_negotiation(gsm, 0, data, clen); + /* Or did we receive the TEST response to our TEST command */ + } else if (command == CMD_TEST && clen == 1 && *data == gsm->ka_num) { + gsm->ka_retries = -1; /* trigger new keep-alive message */ + if (dlci && !dlci->dead) + mod_timer(&gsm->ka_timer, jiffies + gsm->keep_alive * HZ / 100); + } + spin_unlock_irqrestore(&gsm->control_lock, flags); +} + +/** + * gsm_control_keep_alive - check timeout or start keep-alive + * @t: timer contained in our gsm object + * + * Called off the keep-alive timer expiry signaling that our link + * partner is not responding anymore. Link will be closed. + * This is also called to startup our timer. + */ + +static void gsm_control_keep_alive(struct timer_list *t) +{ + struct gsm_mux *gsm = from_timer(gsm, t, ka_timer); + unsigned long flags; + + spin_lock_irqsave(&gsm->control_lock, flags); + if (gsm->ka_num && gsm->ka_retries == 0) { + /* Keep-alive expired -> close the link */ + if (debug & DBG_ERRORS) + pr_debug("%s keep-alive timed out\n", __func__); + spin_unlock_irqrestore(&gsm->control_lock, flags); + if (gsm->dlci[0]) + gsm_dlci_begin_close(gsm->dlci[0]); + return; + } else if (gsm->keep_alive && gsm->dlci[0] && !gsm->dlci[0]->dead) { + if (gsm->ka_retries > 0) { + /* T2 expired for keep-alive -> resend */ + gsm->ka_retries--; + } else { + /* Start keep-alive timer */ + gsm->ka_num++; + if (!gsm->ka_num) + gsm->ka_num++; + gsm->ka_retries = (signed int)gsm->n2; + } + gsm_control_command(gsm, CMD_TEST, &gsm->ka_num, + sizeof(gsm->ka_num)); + mod_timer(&gsm->ka_timer, + jiffies + gsm->t2 * HZ / 100); } spin_unlock_irqrestore(&gsm->control_lock, flags); } @@ -2067,8 +2122,10 @@ static void gsm_dlci_close(struct gsm_dlci *dlci) /* Ensure that gsmtty_open() can return. */ tty_port_set_initialized(&dlci->port, false); wake_up_interruptible(&dlci->port.open_wait); - } else + } else { + del_timer(&dlci->gsm->ka_timer); dlci->gsm->dead = true; + } /* A DLCI 0 close is a MUX termination so we need to kick that back to userspace somehow */ gsm_dlci_data_kick(dlci); @@ -2084,6 +2141,8 @@ static void gsm_dlci_close(struct gsm_dlci *dlci) static void gsm_dlci_open(struct gsm_dlci *dlci) { + struct gsm_mux *gsm = dlci->gsm; + /* Note that SABM UA .. SABM UA first UA lost can mean that we go open -> open */ del_timer(&dlci->t1); @@ -2093,8 +2152,15 @@ static void gsm_dlci_open(struct gsm_dlci *dlci) if (debug & DBG_ERRORS) pr_debug("DLCI %d goes open.\n", dlci->addr); /* Send current modem state */ - if (dlci->addr) + if (dlci->addr) { gsm_modem_update(dlci, 0); + } else { + /* Start keep-alive control */ + gsm->ka_num = 0; + gsm->ka_retries = -1; + mod_timer(&gsm->ka_timer, + jiffies + gsm->keep_alive * HZ / 100); + } gsm_dlci_data_kick(dlci); wake_up(&dlci->gsm->event); } @@ -2847,6 +2913,7 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) /* Finish outstanding timers, making sure they are done */ del_timer_sync(&gsm->kick_timer); del_timer_sync(&gsm->t2_timer); + del_timer_sync(&gsm->ka_timer); /* Finish writing to ldisc */ flush_work(&gsm->tx_work); @@ -2994,6 +3061,7 @@ static struct gsm_mux *gsm_alloc_mux(void) INIT_LIST_HEAD(&gsm->tx_data_list); timer_setup(&gsm->kick_timer, gsm_kick_timer, 0); timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0); + timer_setup(&gsm->ka_timer, gsm_control_keep_alive, 0); INIT_WORK(&gsm->tx_work, gsmld_write_task); init_waitqueue_head(&gsm->event); spin_lock_init(&gsm->control_lock); @@ -3010,6 +3078,7 @@ static struct gsm_mux *gsm_alloc_mux(void) gsm->mru = 64; /* Default to encoding 1 so these should be 64 */ gsm->mtu = 64; gsm->dead = true; /* Avoid early tty opens */ + gsm->keep_alive = 0; /* Disabled */ /* Store the instance to the mux array or abort if no space is * available. @@ -3145,6 +3214,29 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) return 0; } +static void gsm_copy_config_ext_values(struct gsm_mux *gsm, + struct gsm_config_ext *ce) +{ + memset(ce, 0, sizeof(*ce)); + ce->keep_alive = gsm->keep_alive; +} + +static int gsm_config_ext(struct gsm_mux *gsm, struct gsm_config_ext *ce) +{ + unsigned int i; + + /* + * Check that userspace doesn't put stuff in here to prevent breakages + * in the future. + */ + for (i = 0; i < ARRAY_SIZE(ce->reserved); i++) + if (ce->reserved[i]) + return -EINVAL; + + gsm->keep_alive = ce->keep_alive; + return 0; +} + /** * gsmld_output - write to link * @gsm: our mux @@ -3463,6 +3555,7 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct gsm_config c; + struct gsm_config_ext ce; struct gsm_mux *gsm = tty->disc_data; unsigned int base; @@ -3479,6 +3572,15 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, case GSMIOC_GETFIRST: base = mux_num_to_base(gsm); return put_user(base + 1, (__u32 __user *)arg); + case GSMIOC_GETCONF_EXT: + gsm_copy_config_ext_values(gsm, &ce); + if (copy_to_user((void __user *)arg, &ce, sizeof(ce))) + return -EFAULT; + return 0; + case GSMIOC_SETCONF_EXT: + if (copy_from_user(&ce, (void __user *)arg, sizeof(ce))) + return -EFAULT; + return gsm_config_ext(gsm, &ce); default: return n_tty_ioctl_helper(tty, cmd, arg); } diff --git a/include/uapi/linux/gsmmux.h b/include/uapi/linux/gsmmux.h index 785d6b253f6d..a703780aa095 100644 --- a/include/uapi/linux/gsmmux.h +++ b/include/uapi/linux/gsmmux.h @@ -39,4 +39,14 @@ struct gsm_netconfig { /* get the base tty number for a configured gsmmux tty */ #define GSMIOC_GETFIRST _IOR('G', 4, __u32) +struct gsm_config_ext { + __u32 keep_alive; /* Control channel keep-alive in 1/100th of a + * second (0 to disable) + */ + __u32 reserved[7]; /* For future use, must be initialized to zero */ +}; + +#define GSMIOC_GETCONF_EXT _IOR('G', 5, struct gsm_config_ext) +#define GSMIOC_SETCONF_EXT _IOW('G', 6, struct gsm_config_ext) + #endif -- cgit v1.2.3 From 7d3fd88d61a41016da01889f076fd1c60c7298fc Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Tue, 14 Feb 2023 16:42:22 -0800 Subject: io_uring: Support calling io_uring_register with a registered ring fd Add a new flag IORING_REGISTER_USE_REGISTERED_RING (set via the high bit of the opcode) to treat the fd as a registered index rather than a file descriptor. This makes it possible for a library to open an io_uring, register the ring fd, close the ring fd, and subsequently use the ring entirely via registered index. Signed-off-by: Josh Triplett Link: https://lore.kernel.org/r/f2396369e638284586b069dbddffb8c992afba95.1676419314.git.josh@joshtriplett.org [axboe: remove extra high bit clear] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 +++++- io_uring/io_uring.c | 33 ++++++++++++++++++++++++++------- 2 files changed, 31 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 636a4c2c1294..97661a60b28c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -472,6 +472,7 @@ struct io_uring_params { #define IORING_FEAT_RSRC_TAGS (1U << 10) #define IORING_FEAT_CQE_SKIP (1U << 11) #define IORING_FEAT_LINKED_FILE (1U << 12) +#define IORING_FEAT_REG_REG_RING (1U << 13) /* * io_uring_register(2) opcodes and arguments @@ -519,7 +520,10 @@ enum { IORING_REGISTER_FILE_ALLOC_RANGE = 25, /* this goes last */ - IORING_REGISTER_LAST + IORING_REGISTER_LAST, + + /* flag added to the opcode to use a registered ring fd */ + IORING_REGISTER_USE_REGISTERED_RING = 1U << 31 }; /* io-wq worker categories */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0e42160a3051..3b915deb4d08 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3785,7 +3785,7 @@ 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_LINKED_FILE | IORING_FEAT_REG_REG_RING; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -4306,17 +4306,36 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, struct io_ring_ctx *ctx; long ret = -EBADF; struct fd f; + bool use_registered_ring; + + use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING); + opcode &= ~IORING_REGISTER_USE_REGISTERED_RING; if (opcode >= IORING_REGISTER_LAST) return -EINVAL; - f = fdget(fd); - if (!f.file) - return -EBADF; + if (use_registered_ring) { + /* + * Ring fd has been registered via IORING_REGISTER_RING_FDS, we + * need only dereference our task private array to find it. + */ + struct io_uring_task *tctx = current->io_uring; - ret = -EOPNOTSUPP; - if (!io_is_uring_fops(f.file)) - goto out_fput; + if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX)) + return -EINVAL; + fd = array_index_nospec(fd, IO_RINGFD_REG_MAX); + f.file = tctx->registered_rings[fd]; + f.flags = 0; + if (unlikely(!f.file)) + return -EBADF; + } else { + f = fdget(fd); + if (unlikely(!f.file)) + return -EBADF; + ret = -EOPNOTSUPP; + if (!io_is_uring_fops(f.file)) + goto out_fput; + } ctx = f.file->private_data; -- cgit v1.2.3 From 9ec041ea40dbc6425c0ee6ae15786e5ab1d6aad6 Mon Sep 17 00:00:00 2001 From: Luca Boccassi Date: Fri, 10 Feb 2023 01:06:12 +0000 Subject: sed-opal: add support flag for SUM in status ioctl Not every OPAL drive supports SUM (Single User Mode), so report this information to userspace via the get-status ioctl so that we can adjust the formatting options accordingly. Tested on a kingston drive (which supports it) and a samsung one (which does not). Signed-off-by: Luca Boccassi Link: https://lore.kernel.org/r/20230210010612.28729-1-luca.boccassi@gmail.com Signed-off-by: Jens Axboe --- block/sed-opal.c | 2 ++ include/uapi/linux/sed-opal.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/block/sed-opal.c b/block/sed-opal.c index 463873f61e01..c320093c14f1 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -487,6 +487,8 @@ static int opal_discovery0_end(struct opal_dev *dev) break; case FC_SINGLEUSER: single_user = check_sum(body->features); + if (single_user) + dev->flags |= OPAL_FL_SUM_SUPPORTED; break; case FC_GEOMETRY: check_geometry(dev, body); diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index 1fed3c9294fc..d7a1524023db 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -144,6 +144,7 @@ struct opal_read_write_table { #define OPAL_FL_LOCKED 0x00000008 #define OPAL_FL_MBR_ENABLED 0x00000010 #define OPAL_FL_MBR_DONE 0x00000020 +#define OPAL_FL_SUM_SUPPORTED 0x00000040 struct opal_status { __u32 flags; -- cgit v1.2.3 From 31de4105f00d64570139bc5494a201b0bd57349f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 17 Feb 2023 12:55:14 -0800 Subject: bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup The bpf_fib_lookup() also looks up the neigh table. This was done before bpf_redirect_neigh() was added. In the use case that does not manage the neigh table and requires bpf_fib_lookup() to lookup a fib to decide if it needs to redirect or not, the bpf prog can depend only on using bpf_redirect_neigh() to lookup the neigh. It also keeps the neigh entries fresh and connected. This patch adds a bpf_fib_lookup flag, SKIP_NEIGH, to avoid the double neigh lookup when the bpf prog always call bpf_redirect_neigh() to do the neigh lookup. The params->smac output is skipped together when SKIP_NEIGH is set because bpf_redirect_neigh() will figure out the smac also. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230217205515.3583372-1-martin.lau@linux.dev --- include/uapi/linux/bpf.h | 6 ++++++ net/core/filter.c | 39 ++++++++++++++++++++++++++------------- tools/include/uapi/linux/bpf.h | 6 ++++++ 3 files changed, 38 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1503f61336b6..62ce1f5d1b1d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3134,6 +3134,11 @@ union bpf_attr { * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6750,6 +6755,7 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), }; enum { diff --git a/net/core/filter.c b/net/core/filter.c index 8daaaf76ab15..1d6f165923bf 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5722,12 +5722,8 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) -static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, - const struct neighbour *neigh, - const struct net_device *dev, u32 mtu) +static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) { - memcpy(params->dmac, neigh->ha, ETH_ALEN); - memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; if (mtu) @@ -5838,21 +5834,29 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; - - neigh = __ipv4_neigh_lookup_noref(dev, - (__force u32)params->ipv4_dst); } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; - neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) + goto set_fwd_params; + + if (likely(nhc->nhc_gw_family != AF_INET6)) + neigh = __ipv4_neigh_lookup_noref(dev, + (__force u32)params->ipv4_dst); + else + neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst); + if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; + memcpy(params->dmac, neigh->ha, ETH_ALEN); + memcpy(params->smac, dev->dev_addr, ETH_ALEN); - return bpf_fib_set_fwd_params(params, neigh, dev, mtu); +set_fwd_params: + return bpf_fib_set_fwd_params(params, mtu); } #endif @@ -5960,24 +5964,33 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) + goto set_fwd_params; + /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; + memcpy(params->dmac, neigh->ha, ETH_ALEN); + memcpy(params->smac, dev->dev_addr, ETH_ALEN); - return bpf_fib_set_fwd_params(params, neigh, dev, mtu); +set_fwd_params: + return bpf_fib_set_fwd_params(params, mtu); } #endif +#define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ + BPF_FIB_LOOKUP_SKIP_NEIGH) + BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; - if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) + if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; switch (params->family) { @@ -6015,7 +6028,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, if (plen < sizeof(*params)) return -EINVAL; - if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) + if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; if (params->tot_len) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1503f61336b6..62ce1f5d1b1d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3134,6 +3134,11 @@ union bpf_attr { * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6750,6 +6755,7 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), }; enum { -- cgit v1.2.3 From 69106b6fb3d73bd4252daa48ae96e600c9701147 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Tue, 3 Jan 2023 11:51:06 +0100 Subject: vhost-vdpa: Introduce RESUME backend feature bit Userspace knows if the device can be resumed or not by checking this feature bit. It's only exposed if the vdpa driver backend implements the resume() operation callback. Userspace trying to negotiate this feature when it hasn't been exposed will result in an error. Acked-by: Jason Wang Signed-off-by: Sebastien Boeuf Message-Id: Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- drivers/vhost/vdpa.c | 16 +++++++++++++++- include/uapi/linux/vhost_types.h | 2 ++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ec32f785dfde..abbe397b8509 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -359,6 +359,14 @@ static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v) return ops->suspend; } +static bool vhost_vdpa_can_resume(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->resume; +} + static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; @@ -606,11 +614,15 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; if (features & ~(VHOST_VDPA_BACKEND_FEATURES | - BIT_ULL(VHOST_BACKEND_F_SUSPEND))) + BIT_ULL(VHOST_BACKEND_F_SUSPEND) | + BIT_ULL(VHOST_BACKEND_F_RESUME))) return -EOPNOTSUPP; if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) && !vhost_vdpa_can_suspend(v)) return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_RESUME)) && + !vhost_vdpa_can_resume(v)) + return -EOPNOTSUPP; vhost_set_backend_features(&v->vdev, features); return 0; } @@ -662,6 +674,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, features = VHOST_VDPA_BACKEND_FEATURES; if (vhost_vdpa_can_suspend(v)) features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND); + if (vhost_vdpa_can_resume(v)) + features |= BIT_ULL(VHOST_BACKEND_F_RESUME); if (copy_to_user(featurep, &features, sizeof(features))) r = -EFAULT; break; diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 53601ce2c20a..c5690a8992d8 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -163,5 +163,7 @@ struct vhost_vdpa_iova_range { #define VHOST_BACKEND_F_IOTLB_ASID 0x3 /* Device can be suspended */ #define VHOST_BACKEND_F_SUSPEND 0x4 +/* Device can be resumed */ +#define VHOST_BACKEND_F_RESUME 0x5 #endif -- cgit v1.2.3 From 3b688d7a086d0438649ea37990c6e811954fc780 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Tue, 3 Jan 2023 11:51:07 +0100 Subject: vhost-vdpa: uAPI to resume the device This new ioctl adds support for resuming the device from userspace. This is required when trying to restore the device in a functioning state after it's been suspended. It is already possible to reset a suspended device, but that means the device must be reconfigured and all the IOMMU/IOTLB mappings must be recreated. This new operation allows the device to be resumed without going through a full reset. This is particularly useful when trying to perform offline migration of a virtual machine (also known as snapshot/restore) as it allows the VMM to resume the virtual machine back to a running state after the snapshot is performed. Acked-by: Jason Wang Signed-off-by: Sebastien Boeuf Message-Id: <73b75fb87d25cff59768b4955a81fe7ffe5b4770.1672742878.git.sebastien.boeuf@intel.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- drivers/vhost/vdpa.c | 18 ++++++++++++++++++ include/uapi/linux/vhost.h | 8 ++++++++ 2 files changed, 26 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index abbe397b8509..23db92388393 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -506,6 +506,21 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v) return ops->suspend(vdpa); } +/* After a successful return of this ioctl the device resumes processing + * virtqueue descriptors. The device becomes fully operational the same way it + * was before it was suspended. + */ +static long vhost_vdpa_resume(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!ops->resume) + return -EOPNOTSUPP; + + return ops->resume(vdpa); +} + static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -691,6 +706,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_SUSPEND: r = vhost_vdpa_suspend(v); break; + case VHOST_VDPA_RESUME: + r = vhost_vdpa_resume(v); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index f9f115a7c75b..92e1b700b51c 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -180,4 +180,12 @@ */ #define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) +/* Resume a device so it can resume processing virtqueue requests + * + * After the return of this ioctl the device will have restored all the + * necessary states and it is fully operational to continue processing the + * virtqueue descriptors. + */ +#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) + #endif -- cgit v1.2.3 From 1862de92c81c2a74ff05819aca20b0b83192c83b Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 23 Feb 2023 09:26:56 +0200 Subject: netdev-genl: fix repeated typo oflloading -> offloading Fix a repeated copy/paste typo. Fixes: d3d854fd6a1d ("netdev-genl: create a simple family for netdev stuff") Signed-off-by: Tariq Toukan Acked-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- Documentation/netlink/specs/netdev.yaml | 2 +- include/uapi/linux/netdev.h | 2 +- tools/include/uapi/linux/netdev.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index b4dcdae54ffd..cffef09729f1 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -28,7 +28,7 @@ definitions: - name: hw-offload doc: - This feature informs if netdev supports XDP hw oflloading. + This feature informs if netdev supports XDP hw offloading. - name: rx-sg doc: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 9ee459872600..588391447bfb 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -19,7 +19,7 @@ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP * in zero copy mode. * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw - * oflloading. + * offloading. * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear * XDP buffer support in the driver napi callback. * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 9ee459872600..588391447bfb 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -19,7 +19,7 @@ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP * in zero copy mode. * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw - * oflloading. + * offloading. * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear * XDP buffer support in the driver napi callback. * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements -- cgit v1.2.3 From 1a69f7a161a78aead07cd4b811d796950e892fa4 Mon Sep 17 00:00:00 2001 From: Qing Zhang Date: Sat, 25 Feb 2023 15:52:57 +0800 Subject: LoongArch: ptrace: Expose hardware breakpoints to debuggers Implement the regset-based ptrace interface that exposes hardware breakpoints to user-space debuggers to query and set instruction and data breakpoints. Signed-off-by: Qing Zhang Signed-off-by: Huacai Chen --- arch/loongarch/include/uapi/asm/ptrace.h | 9 + arch/loongarch/kernel/ptrace.c | 402 +++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 2 + 3 files changed, 413 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index 083193f4a5d5..cc48ed262021 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -46,6 +46,15 @@ struct user_fp_state { uint32_t fcsr; }; +struct user_watch_state { + uint16_t dbg_info; + struct { + uint64_t addr; + uint64_t mask; + uint32_t ctrl; + } dbg_regs[8]; +}; + #define PTRACE_SYSEMU 0x1f #define PTRACE_SYSEMU_SINGLESTEP 0x20 diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index dc2b82ea894c..11b491395636 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -20,7 +20,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -246,6 +248,384 @@ static int cfg_set(struct task_struct *target, return 0; } +#ifdef CONFIG_HAVE_HW_BREAKPOINT + +/* + * Handle hitting a HW-breakpoint. + */ +static void ptrace_hbptriggered(struct perf_event *bp, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + int i; + struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); + + for (i = 0; i < LOONGARCH_MAX_BRP; ++i) + if (current->thread.hbp_break[i] == bp) + break; + + for (i = 0; i < LOONGARCH_MAX_WRP; ++i) + if (current->thread.hbp_watch[i] == bp) + break; + + force_sig_ptrace_errno_trap(i, (void __user *)bkpt->address); +} + +static struct perf_event *ptrace_hbp_get_event(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + struct perf_event *bp; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if (idx >= LOONGARCH_MAX_BRP) + return ERR_PTR(-EINVAL); + idx = array_index_nospec(idx, LOONGARCH_MAX_BRP); + bp = tsk->thread.hbp_break[idx]; + break; + case NT_LOONGARCH_HW_WATCH: + if (idx >= LOONGARCH_MAX_WRP) + return ERR_PTR(-EINVAL); + idx = array_index_nospec(idx, LOONGARCH_MAX_WRP); + bp = tsk->thread.hbp_watch[idx]; + break; + } + + return bp; +} + +static int ptrace_hbp_set_event(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, + struct perf_event *bp) +{ + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if (idx >= LOONGARCH_MAX_BRP) + return -EINVAL; + idx = array_index_nospec(idx, LOONGARCH_MAX_BRP); + tsk->thread.hbp_break[idx] = bp; + break; + case NT_LOONGARCH_HW_WATCH: + if (idx >= LOONGARCH_MAX_WRP) + return -EINVAL; + idx = array_index_nospec(idx, LOONGARCH_MAX_WRP); + tsk->thread.hbp_watch[idx] = bp; + break; + } + + return 0; +} + +static struct perf_event *ptrace_hbp_create(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + int err, type; + struct perf_event *bp; + struct perf_event_attr attr; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + type = HW_BREAKPOINT_X; + break; + case NT_LOONGARCH_HW_WATCH: + type = HW_BREAKPOINT_RW; + break; + default: + return ERR_PTR(-EINVAL); + } + + ptrace_breakpoint_init(&attr); + + /* + * Initialise fields to sane defaults + * (i.e. values that will pass validation). + */ + attr.bp_addr = 0; + attr.bp_len = HW_BREAKPOINT_LEN_4; + attr.bp_type = type; + attr.disabled = 1; + + bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk); + if (IS_ERR(bp)) + return bp; + + err = ptrace_hbp_set_event(note_type, tsk, idx, bp); + if (err) + return ERR_PTR(err); + + return bp; +} + +static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, + struct arch_hw_breakpoint_ctrl ctrl, + struct perf_event_attr *attr) +{ + int err, len, type, offset; + + err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + if (err) + return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if ((type & HW_BREAKPOINT_X) != type) + return -EINVAL; + break; + case NT_LOONGARCH_HW_WATCH: + if ((type & HW_BREAKPOINT_RW) != type) + return -EINVAL; + break; + default: + return -EINVAL; + } + + attr->bp_len = len; + attr->bp_type = type; + attr->bp_addr += offset; + + return 0; +} + +static int ptrace_hbp_get_resource_info(unsigned int note_type, u16 *info) +{ + u8 num; + u16 reg = 0; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + num = hw_breakpoint_slots(TYPE_INST); + break; + case NT_LOONGARCH_HW_WATCH: + num = hw_breakpoint_slots(TYPE_DATA); + break; + default: + return -EINVAL; + } + + *info = reg | num; + + return 0; +} + +static struct perf_event *ptrace_hbp_get_initialised_bp(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (!bp) + bp = ptrace_hbp_create(note_type, tsk, idx); + + return bp; +} + +static int ptrace_hbp_get_ctrl(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u32 *ctrl) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *ctrl = bp ? encode_ctrl_reg(counter_arch_bp(bp)->ctrl) : 0; + + return 0; +} + +static int ptrace_hbp_get_mask(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 *mask) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *mask = bp ? counter_arch_bp(bp)->mask : 0; + + return 0; +} + +static int ptrace_hbp_get_addr(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 *addr) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *addr = bp ? counter_arch_bp(bp)->address : 0; + + return 0; +} + +static int ptrace_hbp_set_ctrl(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u32 uctrl) +{ + int err; + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint_ctrl ctrl; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + decode_ctrl_reg(uctrl, &ctrl); + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + + return modify_user_hw_breakpoint(bp, &attr); +} + +static int ptrace_hbp_set_mask(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 mask) +{ + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint *info; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + info = counter_arch_bp(bp); + info->mask = mask; + + return modify_user_hw_breakpoint(bp, &attr); +} + +static int ptrace_hbp_set_addr(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 addr) +{ + struct perf_event *bp; + struct perf_event_attr attr; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + attr.bp_addr = addr; + + return modify_user_hw_breakpoint(bp, &attr); +} + +#define PTRACE_HBP_CTRL_SZ sizeof(u32) +#define PTRACE_HBP_ADDR_SZ sizeof(u64) +#define PTRACE_HBP_MASK_SZ sizeof(u64) + +static int hw_break_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + u16 info; + u32 ctrl; + u64 addr, mask; + int ret, idx = 0; + unsigned int note_type = regset->core_note_type; + + /* Resource info */ + ret = ptrace_hbp_get_resource_info(note_type, &info); + if (ret) + return ret; + + membuf_write(&to, &info, sizeof(info)); + + /* (address, ctrl) registers */ + while (to.left) { + ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); + if (ret) + return ret; + + ret = ptrace_hbp_get_mask(note_type, target, idx, &mask); + if (ret) + return ret; + + ret = ptrace_hbp_get_ctrl(note_type, target, idx, &ctrl); + if (ret) + return ret; + + membuf_store(&to, addr); + membuf_store(&to, mask); + membuf_store(&to, ctrl); + idx++; + } + + return 0; +} + +static int hw_break_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u32 ctrl; + u64 addr, mask; + int ret, idx = 0, offset, limit; + unsigned int note_type = regset->core_note_type; + + /* Resource info */ + offset = offsetof(struct user_watch_state, dbg_regs); + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); + + /* (address, ctrl) registers */ + limit = regset->n * regset->size; + while (count && offset < limit) { + if (count < PTRACE_HBP_ADDR_SZ) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, + offset, offset + PTRACE_HBP_ADDR_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_addr(note_type, target, idx, addr); + if (ret) + return ret; + offset += PTRACE_HBP_ADDR_SZ; + + if (!count) + break; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, + offset, offset + PTRACE_HBP_ADDR_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_mask(note_type, target, idx, mask); + if (ret) + return ret; + offset += PTRACE_HBP_MASK_SZ; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, + offset, offset + PTRACE_HBP_MASK_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_ctrl(note_type, target, idx, ctrl); + if (ret) + return ret; + offset += PTRACE_HBP_CTRL_SZ; + idx++; + } + + return 0; +} + +#endif + struct pt_regs_offset { const char *name; int offset; @@ -319,6 +699,10 @@ enum loongarch_regset { REGSET_GPR, REGSET_FPR, REGSET_CPUCFG, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + REGSET_HW_BREAK, + REGSET_HW_WATCH, +#endif }; static const struct user_regset loongarch64_regsets[] = { @@ -346,6 +730,24 @@ static const struct user_regset loongarch64_regsets[] = { .regset_get = cfg_get, .set = cfg_set, }, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + [REGSET_HW_BREAK] = { + .core_note_type = NT_LOONGARCH_HW_BREAK, + .n = sizeof(struct user_watch_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = hw_break_get, + .set = hw_break_set, + }, + [REGSET_HW_WATCH] = { + .core_note_type = NT_LOONGARCH_HW_WATCH, + .n = sizeof(struct user_watch_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = hw_break_get, + .set = hw_break_set, + }, +#endif }; static const struct user_regset_view user_loongarch64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 4c6a8fa5e7ed..9db473d9405d 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -444,6 +444,8 @@ typedef struct elf64_shdr { #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ #define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ #define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ +#define NT_LOONGARCH_HW_BREAK 0xa05 /* LoongArch hardware breakpoint registers */ +#define NT_LOONGARCH_HW_WATCH 0xa06 /* LoongArch hardware watchpoint registers */ /* Note types with note name "GNU" */ #define NT_GNU_PROPERTY_TYPE_0 5 -- cgit v1.2.3 From 2943868a909f1d526da363dc077fd7b578643f4b Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sat, 11 Feb 2023 19:53:05 +0800 Subject: btrfs: ioctl: return device fsid from DEV_INFO ioctl Currently user space utilizes dev info ioctl to grab the info of a certain devid, this includes its device uuid. But the returned info is not enough to determine if a device is a seed. Commit a26d60dedf9a ("btrfs: sysfs: add devinfo/fsid to retrieve actual fsid from the device") exports the same value in sysfs so this is for parity with ioctl. Add a new member, fsid, into btrfs_ioctl_dev_info_args, and populate the member with fsid value. This should not cause any compatibility problem, following the combinations: - Old user space, old kernel - Old user space, new kernel User space tool won't even check the new member. - New user space, old kernel The kernel won't touch the new member, and user space tool should zero out its argument, thus the new member is all zero. User space tool can then know the kernel doesn't support this fsid reporting, and falls back to whatever they can. - New user space, new kernel Go as planned. Would find the fsid member is no longer zero, and trust its value. Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 1 + include/uapi/linux/btrfs.h | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8ea557e22252..439a5bf5ebc6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2859,6 +2859,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, di_args->bytes_used = btrfs_device_get_bytes_used(dev); di_args->total_bytes = btrfs_device_get_total_bytes(dev); memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); + memcpy(di_args->fsid, dev->fs_devices->fsid, BTRFS_UUID_SIZE); if (dev->name) strscpy(di_args->path, btrfs_dev_name(dev), sizeof(di_args->path)); else diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index b4f0f9531119..ada0a489bf2b 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -245,7 +245,17 @@ struct btrfs_ioctl_dev_info_args { __u8 uuid[BTRFS_UUID_SIZE]; /* in/out */ __u64 bytes_used; /* out */ __u64 total_bytes; /* out */ - __u64 unused[379]; /* pad to 4k */ + /* + * Optional, out. + * + * Showing the fsid of the device, allowing user space to check if this + * device is a seeding one. + * + * Introduced in v6.3, thus user space still needs to check if kernel + * changed this value. Older kernel will not touch the values here. + */ + __u8 fsid[BTRFS_UUID_SIZE]; + __u64 unused[377]; /* pad to 4k */ __u8 path[BTRFS_DEVICE_PATH_NAME_MAX]; /* out */ }; -- cgit v1.2.3 From 37d9df224d1eec1b434fe9ffa40104c756478c29 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 6 Mar 2023 12:04:57 -0800 Subject: ynl: re-license uniformly under GPL-2.0 OR BSD-3-Clause I was intending to make all the Netlink Spec code BSD-3-Clause to ease the adoption but it appears that: - I fumbled the uAPI and used "GPL WITH uAPI note" there - it gives people pause as they expect GPL in the kernel As suggested by Chuck re-license under dual. This gives us benefit of full BSD freedom while fulfilling the broad "kernel is under GPL" expectations. Link: https://lore.kernel.org/all/20230304120108.05dd44c5@kernel.org/ Link: https://lore.kernel.org/r/20230306200457.3903854-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/genetlink-c.yaml | 2 +- Documentation/netlink/genetlink-legacy.yaml | 2 +- Documentation/netlink/genetlink.yaml | 2 +- Documentation/netlink/specs/ethtool.yaml | 2 ++ Documentation/netlink/specs/fou.yaml | 2 ++ Documentation/netlink/specs/netdev.yaml | 2 ++ Documentation/userspace-api/netlink/specs.rst | 3 +++ include/uapi/linux/fou.h | 2 +- include/uapi/linux/netdev.h | 2 +- net/core/netdev-genl-gen.c | 2 +- net/core/netdev-genl-gen.h | 2 +- net/ipv4/fou_nl.c | 2 +- net/ipv4/fou_nl.h | 2 +- tools/include/uapi/linux/netdev.h | 2 +- tools/net/ynl/cli.py | 2 +- tools/net/ynl/lib/__init__.py | 2 +- tools/net/ynl/lib/nlspec.py | 2 +- tools/net/ynl/lib/ynl.py | 2 +- tools/net/ynl/ynl-gen-c.py | 7 ++++--- tools/net/ynl/ynl-regen.sh | 2 +- 20 files changed, 28 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index bbcfa2472b04..f082a5ad7cf1 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause %YAML 1.2 --- $id: http://kernel.org/schemas/netlink/genetlink-c.yaml# diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 5642925c4ceb..c6b8c77f7d12 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause %YAML 1.2 --- $id: http://kernel.org/schemas/netlink/genetlink-legacy.yaml# diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index 62a922755ce2..b2d56ab9e615 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause %YAML 1.2 --- $id: http://kernel.org/schemas/netlink/genetlink-legacy.yaml# diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 35c462bce56f..18ecb7d90cbe 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + name: ethtool protocol: genetlink-legacy diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml index cca4cf98f03a..cff104288723 100644 --- a/Documentation/netlink/specs/fou.yaml +++ b/Documentation/netlink/specs/fou.yaml @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + name: fou protocol: genetlink-legacy diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index ba9ee13cf729..24de747b5344 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + name: netdev doc: diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst index 32e53328d113..2122e0c4a399 100644 --- a/Documentation/userspace-api/netlink/specs.rst +++ b/Documentation/userspace-api/netlink/specs.rst @@ -24,6 +24,9 @@ YAML specifications can be found under ``Documentation/netlink/specs/`` This document describes details of the schema. See :doc:`intro-specs` for a practical starting guide. +All specs must be licensed under ``GPL-2.0-only OR BSD-3-Clause`` +to allow for easy adoption in user space code. + Compatibility levels ==================== diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index 19ebbef41a63..5041c3598493 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN uapi header */ diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 588391447bfb..8c4e3e536c04 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 48812ec843f5..9e10802587fc 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: BSD-3-Clause +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel source */ diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index b16dc7e026bb..2c5fc7d1e8a7 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: BSD-3-Clause */ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel header */ diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 6c3820f41dd5..5c14fe030eda 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: BSD-3-Clause +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel source */ diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h index b7a68121ce6f..58b1e1ed4b3b 100644 --- a/net/ipv4/fou_nl.h +++ b/net/ipv4/fou_nl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: BSD-3-Clause */ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel header */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 588391447bfb..8c4e3e536c04 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py index db410b74d539..ffaa8038aa8c 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/cli.py @@ -1,5 +1,5 @@ #!/usr/bin/env python3 -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import argparse import json diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py index 3c73f59eabab..a2cb8b16d6f1 100644 --- a/tools/net/ynl/lib/__init__.py +++ b/tools/net/ynl/lib/__init__.py @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause from .nlspec import SpecAttr, SpecAttrSet, SpecFamily, SpecOperation from .ynl import YnlFamily diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index 9d394e50de23..0a2cfb5862aa 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import collections import importlib diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 1c7411ee04dc..a842adc8e87e 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import functools import os diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 62f8f2c3c56c..c940ca834d3f 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import argparse import collections @@ -2127,12 +2128,12 @@ def main(): _, spec_kernel = find_kernel_root(args.spec) if args.mode == 'uapi': - cw.p('/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */') + cw.p('/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */') else: if args.header: - cw.p('/* SPDX-License-Identifier: BSD-3-Clause */') + cw.p('/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */') else: - cw.p('// SPDX-License-Identifier: BSD-3-Clause') + cw.p('// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause') cw.p("/* Do not edit directly, auto-generated from: */") cw.p(f"/*\t{spec_kernel} */") cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 43989ae48ed0..74f5de1c2399 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -1,5 +1,5 @@ #!/bin/bash -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause TOOL=$(dirname $(realpath $0))/ynl-gen-c.py -- cgit v1.2.3