From 32a4eb04d59ae8d5bb5baa5a8528e31094ae8e84 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 10 Jun 2021 13:12:34 +0200 Subject: drm/fourcc: Add macros to determine the modifier vendor When working with framebuffer modifiers, it can be useful to extract the vendor identifier or check a modifier against a given vendor identifier. Add one macro that extracts the vendor identifier and a helper to check a modifier against a given vendor identifier. Reviewed-by: Daniel Vetter Acked-by: Daniel Stone Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20210610111236.3814211-1-thierry.reding@gmail.com --- include/uapi/drm/drm_fourcc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 9f4bb4a6f358..45a914850be0 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -373,6 +373,12 @@ extern "C" { #define DRM_FORMAT_RESERVED ((1ULL << 56) - 1) +#define fourcc_mod_get_vendor(modifier) \ + (((modifier) >> 56) & 0xff) + +#define fourcc_mod_is_vendor(modifier, vendor) \ + (fourcc_mod_get_vendor(modifier) == DRM_FORMAT_MOD_VENDOR_## vendor) + #define fourcc_mod_code(vendor, val) \ ((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | ((val) & 0x00ffffffffffffffULL)) -- cgit v1.2.3 From 353be7c2328ccba0add424d015ef51ddf423e202 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 3 Sep 2021 13:00:16 +0000 Subject: drm: document drm_mode_create_lease object requirements validate_lease expects one CRTC, one connector and one plane. Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Pekka Paalanen Cc: Keith Packard Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210903130000.1590-1-contact@emersion.fr --- include/uapi/drm/drm_mode.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 90c55383f1ee..e4a2570a6058 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -1110,6 +1110,9 @@ struct drm_mode_destroy_blob { * struct drm_mode_create_lease - Create lease * * Lease mode resources, creating another drm_master. + * + * The @object_ids array must reference at least one CRTC, one connector and + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. */ struct drm_mode_create_lease { /** @object_ids: Pointer to array of object ids (__u32) */ -- cgit v1.2.3 From 90f7d7a0d0d68623b5f7df5621a8d54d9518fcc4 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 10 Sep 2021 15:36:29 -0400 Subject: locks: remove LOCK_MAND flock lock support As best I can tell, the logic for these has been broken for a long time (at least before the move to git), such that they never conflict with anything. Also, nothing checks for these flags and prevented opens or read/write behavior on the files. They don't seem to do anything. Given that, we can rip these symbols out of the kernel, and just make flock(2) return 0 when LOCK_MAND is set in order to preserve existing behavior. Cc: Matthew Wilcox Cc: Stephen Rothwell Signed-off-by: Jeff Layton --- fs/ceph/locks.c | 3 --- fs/gfs2/file.c | 2 -- fs/locks.c | 47 +++++++++++++++++++--------------------- fs/nfs/file.c | 9 -------- include/uapi/asm-generic/fcntl.h | 4 ++++ 5 files changed, 26 insertions(+), 39 deletions(-) (limited to 'include/uapi') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index bdeb271f47d9..d8c31069fbf2 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -302,9 +302,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; - /* No mandatory locks */ - if (fl->fl_type & LOCK_MAND) - return -EOPNOTSUPP; dout("ceph_flock, fl_file: %p\n", fl->fl_file); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index c559827cb6f9..078ef29e31bc 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1338,8 +1338,6 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) { if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; - if (fl->fl_type & LOCK_MAND) - return -EOPNOTSUPP; if (fl->fl_type == F_UNLCK) { do_unflock(file, fl); diff --git a/fs/locks.c b/fs/locks.c index 3d6fb4ae847b..d397394633be 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -461,8 +461,6 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) } static inline int flock_translate_cmd(int cmd) { - if (cmd & LOCK_MAND) - return cmd & (LOCK_MAND | LOCK_RW); switch (cmd) { case LOCK_SH: return F_RDLCK; @@ -942,8 +940,6 @@ static bool flock_locks_conflict(struct file_lock *caller_fl, */ if (caller_fl->fl_file == sys_fl->fl_file) return false; - if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND)) - return false; return locks_conflict(caller_fl, sys_fl); } @@ -2116,11 +2112,9 @@ EXPORT_SYMBOL(locks_lock_inode_wait); * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. - * - %LOCK_MAND -- a 'mandatory' flock. - * This exists to emulate Windows Share Modes. + * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED) * - * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other - * processes read and write access respectively. + * %LOCK_MAND support has been removed from the kernel. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { @@ -2137,9 +2131,22 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) cmd &= ~LOCK_NB; unlock = (cmd == LOCK_UN); - if (!unlock && !(cmd & LOCK_MAND) && - !(f.file->f_mode & (FMODE_READ|FMODE_WRITE))) + if (!unlock && !(f.file->f_mode & (FMODE_READ|FMODE_WRITE))) + goto out_putf; + + /* + * LOCK_MAND locks were broken for a long time in that they never + * conflicted with one another and didn't prevent any sort of open, + * read or write activity. + * + * Just ignore these requests now, to preserve legacy behavior, but + * throw a warning to let people know that they don't actually work. + */ + if (cmd & LOCK_MAND) { + pr_warn_once("Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n"); + error = 0; goto out_putf; + } lock = flock_make_lock(f.file, cmd, NULL); if (IS_ERR(lock)) { @@ -2718,6 +2725,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, struct inode *inode = NULL; unsigned int fl_pid; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); + int type; fl_pid = locks_translate_pid(fl, proc_pidns); /* @@ -2745,11 +2753,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : "ADVISORY "); } else if (IS_FLOCK(fl)) { - if (fl->fl_type & LOCK_MAND) { - seq_puts(f, "FLOCK MSNFS "); - } else { - seq_puts(f, "FLOCK ADVISORY "); - } + seq_puts(f, "FLOCK ADVISORY "); } else if (IS_LEASE(fl)) { if (fl->fl_flags & FL_DELEG) seq_puts(f, "DELEG "); @@ -2765,17 +2769,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, } else { seq_puts(f, "UNKNOWN UNKNOWN "); } - if (fl->fl_type & LOCK_MAND) { - seq_printf(f, "%s ", - (fl->fl_type & LOCK_READ) - ? (fl->fl_type & LOCK_WRITE) ? "RW " : "READ " - : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE "); - } else { - int type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type; + type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type; - seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : - (type == F_RDLCK) ? "READ" : "UNLCK"); - } + seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : + (type == F_RDLCK) ? "READ" : "UNLCK"); if (inode) { /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%lu ", fl_pid, diff --git a/fs/nfs/file.c b/fs/nfs/file.c index aa353fd58240..24e7dccce355 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -843,15 +843,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; - /* - * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of - * any standard. In principle we might be able to support LOCK_MAND - * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the - * NFS code is not set up for it. - */ - if (fl->fl_type & LOCK_MAND) - return -EINVAL; - if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK) is_local = 1; diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 9dc0bf0c5a6e..ecd0f5bdfc1d 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -181,6 +181,10 @@ struct f_owner_ex { blocking */ #define LOCK_UN 8 /* remove lock */ +/* + * LOCK_MAND support has been removed from the kernel. We leave the symbols + * here to not break legacy builds, but these should not be used in new code. + */ #define LOCK_MAND 32 /* This is a mandatory flock ... */ #define LOCK_READ 64 /* which allows concurrent read operations */ #define LOCK_WRITE 128 /* which allows concurrent write operations */ -- cgit v1.2.3 From f64c4acea51fbe2c08c0b0f48b7f5d1657d7a5e4 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Fri, 10 Sep 2021 01:04:08 +0300 Subject: bpf: Add hardware timestamp field to __sk_buff BPF programs may want to know hardware timestamps if NIC supports such timestamping. Expose this data as hwtstamp field of __sk_buff the same way as gso_segs/gso_size. This field could be accessed from the same programs as tstamp field, but it's read-only field. Explicit test to deny access to padding data is added to bpf_skb_is_valid_access. Also update BPF_PROG_TEST_RUN tests of the feature. Signed-off-by: Vadim Fedorenko Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210909220409.8804-2-vfedorenko@novek.ru --- include/uapi/linux/bpf.h | 2 ++ net/core/filter.c | 21 +++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 2 ++ 3 files changed, 25 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 791f31dd0abe..51cfd91cc387 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5284,6 +5284,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { diff --git a/net/core/filter.c b/net/core/filter.c index 2e32cee2c469..4bace37a6a44 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7765,6 +7765,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; + case bpf_ctx_range(struct __sk_buff, hwtstamp): + if (type == BPF_WRITE || size != sizeof(__u64)) + return false; + break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; @@ -7774,6 +7778,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; + case offsetofend(struct __sk_buff, gso_size) ... offsetof(struct __sk_buff, hwtstamp) - 1: + /* Explicitly prohibit access to padding in __sk_buff. */ + return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { @@ -7802,6 +7809,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -7872,6 +7880,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -8373,6 +8382,7 @@ static bool sk_skb_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -8884,6 +8894,17 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; + case offsetof(struct __sk_buff, hwtstamp): + BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); + BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); + + insn = bpf_convert_shinfo_access(si, insn); + *insn++ = BPF_LDX_MEM(BPF_DW, + si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + hwtstamps, 8, + target_size)); + break; } return insn - insn_buf; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 791f31dd0abe..51cfd91cc387 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5284,6 +5284,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { -- cgit v1.2.3 From 856c02dbce4f8d6a5644083db22c11750aa11481 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 10 Sep 2021 11:33:51 -0700 Subject: bpf: Introduce helper bpf_get_branch_snapshot Introduce bpf_get_branch_snapshot(), which allows tracing pogram to get branch trace from hardware (e.g. Intel LBR). To use the feature, the user need to create perf_event with proper branch_record filtering on each cpu, and then calls bpf_get_branch_snapshot in the bpf function. On Intel CPUs, VLBR event (raw event 0x1b00) can be use for this. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210910183352.3151445-3-songliubraving@fb.com --- include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++ kernel/bpf/trampoline.c | 3 ++- kernel/trace/bpf_trace.c | 30 ++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++ 4 files changed, 76 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 51cfd91cc387..d21326558d42 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4877,6 +4877,27 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5076,7 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index fe1e857324e6..39eaaff81953 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -10,6 +10,7 @@ #include #include #include +#include /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -526,7 +527,7 @@ out: } #define NO_START_TIME 1 -static u64 notrace bpf_prog_start_time(void) +static __always_inline u64 notrace bpf_prog_start_time(void) { u64 start = NO_START_TIME; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8e2eb950aa82..067e88c3d2ee 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1017,6 +1017,34 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) +{ +#ifndef CONFIG_X86 + return -ENOENT; +#else + static const u32 br_entry_size = sizeof(struct perf_branch_entry); + u32 entry_cnt = size / br_entry_size; + + entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt); + + if (unlikely(flags)) + return -EINVAL; + + if (!entry_cnt) + return -ENOENT; + + return entry_cnt * br_entry_size; +#endif +} + +static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { + .func = bpf_get_branch_snapshot, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1132,6 +1160,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_snprintf_proto; case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_tracing; + case BPF_FUNC_get_branch_snapshot: + return &bpf_get_branch_snapshot_proto; default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 51cfd91cc387..d21326558d42 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4877,6 +4877,27 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5076,7 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 059ebe4fe332c5d1c25124166527cdf9fe43a3ce Mon Sep 17 00:00:00 2001 From: Andra Paraschiv Date: Fri, 27 Aug 2021 18:49:29 +0300 Subject: nitro_enclaves: Add fixes for checkpatch spell check reports Fix the typos in the words spelling as per the checkpatch script reports. Reviewed-by: George-Aurelian Popescu Signed-off-by: Andra Paraschiv Link: https://lore.kernel.org/r/20210827154930.40608-7-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/nitro_enclaves.h | 10 +++++----- samples/nitro_enclaves/ne_ioctl_sample.c | 4 ++-- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nitro_enclaves.h b/include/uapi/linux/nitro_enclaves.h index b945073fe544..e808f5ba124d 100644 --- a/include/uapi/linux/nitro_enclaves.h +++ b/include/uapi/linux/nitro_enclaves.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. */ #ifndef _UAPI_LINUX_NITRO_ENCLAVES_H_ @@ -60,7 +60,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() / copy_to_user() failure. @@ -95,7 +95,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() / copy_to_user() failure. @@ -118,7 +118,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() failure. @@ -161,7 +161,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() / copy_to_user() failure. diff --git a/samples/nitro_enclaves/ne_ioctl_sample.c b/samples/nitro_enclaves/ne_ioctl_sample.c index 480b763142b3..6a60990b2e20 100644 --- a/samples/nitro_enclaves/ne_ioctl_sample.c +++ b/samples/nitro_enclaves/ne_ioctl_sample.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. */ /** @@ -638,7 +638,7 @@ static int ne_start_enclave(int enclave_fd, struct ne_enclave_start_info *encla } /** - * ne_start_enclave_check_booted() - Start the enclave and wait for a hearbeat + * ne_start_enclave_check_booted() - Start the enclave and wait for a heartbeat * from it, on a newly created vsock channel, * to check it has booted. * @enclave_fd : The file descriptor associated with the enclave. -- cgit v1.2.3 From fa0866625543b4d8b3d026e4e0ef5ec25a453920 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Tue, 14 Sep 2021 10:35:05 +0200 Subject: net/smc: add support for user defined EIDs SMC-Dv2 allows users to define EIDs which allows to create separate name spaces enabling users to cluster their SMC-Dv2 connections. Add support for user defined EIDs and extent the generic netlink interface so users can add, remove and dump EIDs. Signed-off-by: Karsten Graul Reviewed-by: Guvenc Gulce Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 15 +++ net/smc/af_smc.c | 34 +++--- net/smc/smc.h | 3 - net/smc/smc_clc.c | 263 ++++++++++++++++++++++++++++++++++++++++++++--- net/smc/smc_clc.h | 16 ++- net/smc/smc_core.h | 1 + net/smc/smc_netlink.c | 32 +++++- net/smc/smc_netlink.h | 2 + 8 files changed, 335 insertions(+), 31 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 0f7f87c70baf..e3728af2832b 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -38,6 +38,9 @@ enum { /* SMC PNET Table commands */ #define SMC_GENL_FAMILY_VERSION 1 #define SMC_PCI_ID_STR_LEN 16 /* Max length of pci id string */ +#define SMC_MAX_HOSTNAME_LEN 32 /* Max length of the hostname */ +#define SMC_MAX_UEID 4 /* Max number of user EIDs */ +#define SMC_MAX_EID_LEN 32 /* Max length of an EID */ /* SMC_GENL_FAMILY commands */ enum { @@ -49,6 +52,10 @@ enum { SMC_NETLINK_GET_DEV_SMCR, SMC_NETLINK_GET_STATS, SMC_NETLINK_GET_FBACK_STATS, + SMC_NETLINK_DUMP_UEID, + SMC_NETLINK_ADD_UEID, + SMC_NETLINK_REMOVE_UEID, + SMC_NETLINK_FLUSH_UEID, }; /* SMC_GENL_FAMILY top level attributes */ @@ -242,4 +249,12 @@ enum { __SMC_NLA_FBACK_STATS_MAX, SMC_NLA_FBACK_STATS_MAX = __SMC_NLA_FBACK_STATS_MAX - 1 }; + +/* SMC_NETLINK_UEID attributes */ +enum { + SMC_NLA_EID_TABLE_UNSPEC, + SMC_NLA_EID_TABLE_ENTRY, /* string */ + __SMC_NLA_EID_TABLE_MAX, + SMC_NLA_EID_TABLE_MAX = __SMC_NLA_EID_TABLE_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c038efc23ce3..e5d62acbe401 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -829,7 +829,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_rmb_sync_sg_for_device(&smc->conn); reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, - SMC_V1); + SMC_V1, NULL); if (reason_code) goto connect_abort; @@ -883,6 +883,7 @@ static int smc_connect_ism(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { + u8 *eid = NULL; int rc = 0; ini->is_smcd = true; @@ -918,8 +919,15 @@ static int smc_connect_ism(struct smc_sock *smc, smc_rx_init(smc); smc_tx_init(smc); + if (aclc->hdr.version > SMC_V1) { + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + + eid = clc_v2->eid; + } + rc = smc_clc_send_confirm(smc, ini->first_contact_local, - aclc->hdr.version); + aclc->hdr.version, eid); if (rc) goto connect_abort; mutex_unlock(&smc_server_lgr_pending); @@ -1533,9 +1541,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); - if (!smcd_v2_ext || - !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */ - smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini); + if (!smcd_v2_ext) { + smc_find_ism_store_rc(SMC_CLC_DECL_NOV2DEXT, ini); goto not_found; } @@ -1555,13 +1562,13 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } mutex_unlock(&smcd_dev_list.mutex); - if (ini->ism_dev[0]) { - smc_ism_get_system_eid(ini->ism_dev[0], &eid); - if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN)) - goto not_found; - } else { + if (!ini->ism_dev[0]) + goto not_found; + + smc_ism_get_system_eid(ini->ism_dev[0], &eid); + if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, + smcd_v2_ext->system_eid, eid)) goto not_found; - } /* separate - outside the smcd_dev_list.lock */ smcd_version = ini->smcd_version; @@ -1579,6 +1586,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } /* no V2 ISM device could be initialized */ ini->smcd_version = smcd_version; /* restore original value */ + ini->negotiated_eid[0] = 0; not_found: ini->smcd_version &= ~SMC_V2; @@ -1788,7 +1796,8 @@ static void smc_listen_work(struct work_struct *work) /* send SMC Accept CLC message */ rc = smc_clc_send_accept(new_smc, ini->first_contact_local, - ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1); + ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1, + ini->negotiated_eid); if (rc) goto out_unlock; @@ -2662,6 +2671,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); + smc_clc_exit(); unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); diff --git a/net/smc/smc.h b/net/smc/smc.h index d65e15f0c944..5e7def3ab730 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -29,9 +29,6 @@ * devices */ -#define SMC_MAX_HOSTNAME_LEN 32 -#define SMC_MAX_EID_LEN 32 - extern struct proto smc_proto; extern struct proto smc_proto6; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index e286dafd6e88..a3d99f894f52 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -26,6 +26,7 @@ #include "smc_clc.h" #include "smc_ib.h" #include "smc_ism.h" +#include "smc_netlink.h" #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 @@ -39,6 +40,223 @@ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN]; +struct smc_clc_eid_table { + rwlock_t lock; + struct list_head list; + u8 ueid_cnt; + u8 seid_enabled; +}; + +static struct smc_clc_eid_table smc_clc_eid_table; + +struct smc_clc_eid_entry { + struct list_head list; + u8 eid[SMC_MAX_EID_LEN]; +}; + +/* The size of a user EID is 32 characters. + * Valid characters should be (single-byte character set) A-Z, 0-9, '.' and '-'. + * Blanks should only be used to pad to the expected size. + * First character must be alphanumeric. + */ +static bool smc_clc_ueid_valid(char *ueid) +{ + char *end = ueid + SMC_MAX_EID_LEN; + + while (--end >= ueid && isspace(*end)) + ; + if (end < ueid) + return false; + if (!isalnum(*ueid) || islower(*ueid)) + return false; + while (ueid <= end) { + if ((!isalnum(*ueid) || islower(*ueid)) && *ueid != '.' && + *ueid != '-') + return false; + ueid++; + } + return true; +} + +static int smc_clc_ueid_add(char *ueid) +{ + struct smc_clc_eid_entry *new_ueid, *tmp_ueid; + int rc; + + if (!smc_clc_ueid_valid(ueid)) + return -EINVAL; + + /* add a new ueid entry to the ueid table if there isn't one */ + new_ueid = kzalloc(sizeof(*new_ueid), GFP_KERNEL); + if (!new_ueid) + return -ENOMEM; + memcpy(new_ueid->eid, ueid, SMC_MAX_EID_LEN); + + write_lock(&smc_clc_eid_table.lock); + if (smc_clc_eid_table.ueid_cnt >= SMC_MAX_UEID) { + rc = -ERANGE; + goto err_out; + } + list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { + if (!memcmp(tmp_ueid->eid, ueid, SMC_MAX_EID_LEN)) { + rc = -EEXIST; + goto err_out; + } + } + list_add_tail(&new_ueid->list, &smc_clc_eid_table.list); + smc_clc_eid_table.ueid_cnt++; + write_unlock(&smc_clc_eid_table.lock); + return 0; + +err_out: + write_unlock(&smc_clc_eid_table.lock); + kfree(new_ueid); + return rc; +} + +int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; + char *ueid; + + if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) + return -EINVAL; + ueid = (char *)nla_data(nla_ueid); + + return smc_clc_ueid_add(ueid); +} + +/* remove one or all ueid entries from the table */ +static int smc_clc_ueid_remove(char *ueid) +{ + struct smc_clc_eid_entry *lst_ueid, *tmp_ueid; + int rc = -ENOENT; + + /* remove table entry */ + write_lock(&smc_clc_eid_table.lock); + list_for_each_entry_safe(lst_ueid, tmp_ueid, &smc_clc_eid_table.list, + list) { + if (!ueid || !memcmp(lst_ueid->eid, ueid, SMC_MAX_EID_LEN)) { + list_del(&lst_ueid->list); + smc_clc_eid_table.ueid_cnt--; + kfree(lst_ueid); + rc = 0; + } + } + write_unlock(&smc_clc_eid_table.lock); + return rc; +} + +int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; + char *ueid; + + if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) + return -EINVAL; + ueid = (char *)nla_data(nla_ueid); + + return smc_clc_ueid_remove(ueid); +} + +int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info) +{ + smc_clc_ueid_remove(NULL); + return 0; +} + +static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, + u32 flags, char *ueid) +{ + char ueid_str[SMC_MAX_EID_LEN + 1]; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &smc_gen_nl_family, + flags, SMC_NETLINK_DUMP_UEID); + if (!hdr) + return -ENOMEM; + snprintf(ueid_str, sizeof(ueid_str), "%s", ueid); + if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; + } + genlmsg_end(skb, hdr); + return 0; +} + +static int _smc_nl_ueid_dump(struct sk_buff *skb, u32 portid, u32 seq, + int start_idx) +{ + struct smc_clc_eid_entry *lst_ueid; + int idx = 0; + + read_lock(&smc_clc_eid_table.lock); + list_for_each_entry(lst_ueid, &smc_clc_eid_table.list, list) { + if (idx++ < start_idx) + continue; + if (smc_nl_ueid_dumpinfo(skb, portid, seq, NLM_F_MULTI, + lst_ueid->eid)) { + --idx; + break; + } + } + read_unlock(&smc_clc_eid_table.lock); + return idx; +} + +int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + int idx; + + idx = _smc_nl_ueid_dump(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, cb_ctx->pos[0]); + + cb_ctx->pos[0] = idx; + return skb->len; +} + +static bool _smc_clc_match_ueid(u8 *peer_ueid) +{ + struct smc_clc_eid_entry *tmp_ueid; + + list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { + if (!memcmp(tmp_ueid->eid, peer_ueid, SMC_MAX_EID_LEN)) + return true; + } + return false; +} + +bool smc_clc_match_eid(u8 *negotiated_eid, + struct smc_clc_v2_extension *smc_v2_ext, + u8 *peer_eid, u8 *local_eid) +{ + bool match = false; + int i; + + negotiated_eid[0] = 0; + read_lock(&smc_clc_eid_table.lock); + if (smc_clc_eid_table.seid_enabled && + smc_v2_ext->hdr.flag.seid && + !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) { + memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN); + match = true; + goto out; + } + + for (i = 0; i < smc_v2_ext->hdr.eid_cnt; i++) { + if (_smc_clc_match_ueid(smc_v2_ext->user_eids[i])) { + memcpy(negotiated_eid, smc_v2_ext->user_eids[i], + SMC_MAX_EID_LEN); + match = true; + goto out; + } + } +out: + read_unlock(&smc_clc_eid_table.lock); + return match; +} + /* check arriving CLC proposal */ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) { @@ -550,6 +768,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) if (ini->smc_type_v2 == SMC_TYPE_N) { pclc_smcd->v2_ext_offset = 0; } else { + struct smc_clc_eid_entry *ueident; u16 v2_ext_offset; u8 *eid = NULL; @@ -560,10 +779,19 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); pclc_smcd->v2_ext_offset = htons(v2_ext_offset); - v2_ext->hdr.eid_cnt = 0; + + read_lock(&smc_clc_eid_table.lock); + v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; + plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN; + i = 0; + list_for_each_entry(ueident, &smc_clc_eid_table.list, list) { + memcpy(v2_ext->user_eids[i++], ueident->eid, + sizeof(ueident->eid)); + } + v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; + read_unlock(&smc_clc_eid_table.lock); v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; v2_ext->hdr.flag.release = SMC_RELEASE; - v2_ext->hdr.flag.seid = 1; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + @@ -572,7 +800,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) smc_ism_get_system_eid(ini->ism_dev[0], &eid); else smc_ism_get_system_eid(ini->ism_dev[1], &eid); - if (eid) + if (eid && v2_ext->hdr.flag.seid) memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { @@ -607,7 +835,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) } if (ini->smc_type_v2 != SMC_TYPE_N) { vec[i].iov_base = v2_ext; - vec[i++].iov_len = sizeof(*v2_ext); + vec[i++].iov_len = sizeof(*v2_ext) + + (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); vec[i].iov_base = smcd_v2_ext; vec[i++].iov_len = sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { @@ -635,7 +864,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) /* build and send CLC CONFIRM / ACCEPT message */ static int smc_clc_send_confirm_accept(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2, - int first_contact, u8 version) + int first_contact, u8 version, + u8 *eid) { struct smc_connection *conn = &smc->conn; struct smc_clc_msg_accept_confirm *clc; @@ -663,11 +893,8 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - u8 *eid = NULL; - clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd)); - smc_ism_get_system_eid(conn->lgr->smcd, &eid); - if (eid) + if (eid[0]) memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) @@ -732,7 +959,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, /* send CLC CONFIRM message across internal TCP socket */ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version) + u8 version, u8 *eid) { struct smc_clc_msg_accept_confirm_v2 cclc_v2; int reason_code = 0; @@ -742,7 +969,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, memset(&cclc_v2, 0, sizeof(cclc_v2)); cclc_v2.hdr.type = SMC_CLC_CONFIRM; len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, - version); + version, eid); if (len < ntohs(cclc_v2.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; @@ -757,7 +984,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, /* send CLC ACCEPT message across internal TCP socket */ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, - u8 version) + u8 version, u8 *negotiated_eid) { struct smc_clc_msg_accept_confirm_v2 aclc_v2; int len; @@ -765,7 +992,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, memset(&aclc_v2, 0, sizeof(aclc_v2)); aclc_v2.hdr.type = SMC_CLC_ACCEPT; len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, - version); + version, negotiated_eid); if (len < ntohs(aclc_v2.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; @@ -785,4 +1012,14 @@ void __init smc_clc_init(void) u = utsname(); memcpy(smc_hostname, u->nodename, min_t(size_t, strlen(u->nodename), sizeof(smc_hostname))); + + INIT_LIST_HEAD(&smc_clc_eid_table.list); + rwlock_init(&smc_clc_eid_table.lock); + smc_clc_eid_table.ueid_cnt = 0; + smc_clc_eid_table.seid_enabled = 1; +} + +void smc_clc_exit(void) +{ + smc_clc_ueid_remove(NULL); } diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 32d37f7b70f2..0699e0cee308 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -14,8 +14,10 @@ #define _SMC_CLC_H #include +#include #include "smc.h" +#include "smc_netlink.h" #define SMC_CLC_PROPOSAL 0x01 #define SMC_CLC_ACCEPT 0x02 @@ -158,6 +160,7 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ } __aligned(4); #define SMC_CLC_MAX_V6_PREFIX 8 +#define SMC_CLC_MAX_UEID 8 struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal pclc_base; @@ -165,6 +168,7 @@ struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal_prefix pclc_prfx; struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX]; struct smc_clc_v2_extension pclc_v2_ext; + u8 user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN]; struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext; struct smc_clc_smcd_gid_chid pclc_gidchids[SMC_MAX_ISM_DEVS]; struct smc_clc_msg_trail pclc_trl; @@ -330,10 +334,18 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version); int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini); int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version); + u8 version, u8 *eid); int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, - u8 version); + u8 version, u8 *negotiated_eid); void smc_clc_init(void) __init; +void smc_clc_exit(void); void smc_clc_get_hostname(u8 **host); +bool smc_clc_match_eid(u8 *negotiated_eid, + struct smc_clc_v2_extension *smc_v2_ext, + u8 *peer_eid, u8 *local_eid); +int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c043ecdca5c4..83d30b06016f 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -310,6 +310,7 @@ struct smc_init_info { u8 first_contact_local; unsigned short vlan_id; u32 rc; + u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 6fb6f96c1d17..4548ff2df245 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -19,11 +19,19 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_ib.h" +#include "smc_clc.h" #include "smc_stats.h" #include "smc_netlink.h" -#define SMC_CMD_MAX_ATTR 1 +const struct nla_policy +smc_gen_ueid_policy[SMC_NLA_EID_TABLE_MAX + 1] = { + [SMC_NLA_EID_TABLE_UNSPEC] = { .type = NLA_UNSPEC }, + [SMC_NLA_EID_TABLE_ENTRY] = { .type = NLA_STRING, + .len = SMC_MAX_EID_LEN, + }, +}; +#define SMC_CMD_MAX_ATTR 1 /* SMC_GENL generic netlink operation definition */ static const struct genl_ops smc_gen_nl_ops[] = { { @@ -66,6 +74,28 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smc_nl_get_fback_stats, }, + { + .cmd = SMC_NETLINK_DUMP_UEID, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_ueid, + }, + { + .cmd = SMC_NETLINK_ADD_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_add_ueid, + .policy = smc_gen_ueid_policy, + }, + { + .cmd = SMC_NETLINK_REMOVE_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_remove_ueid, + .policy = smc_gen_ueid_policy, + }, + { + .cmd = SMC_NETLINK_FLUSH_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_flush_ueid, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 5ce2c0a89ccd..e8c6c3f0e98c 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -17,6 +17,8 @@ extern struct genl_family smc_gen_nl_family; +extern const struct nla_policy smc_gen_ueid_policy[]; + struct smc_nl_dmp_ctx { int pos[3]; }; -- cgit v1.2.3 From 3c572145c24e21c24e1cd0fd168011eaba85da8e Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Tue, 14 Sep 2021 10:35:07 +0200 Subject: net/smc: add generic netlink support for system EID With SMC-Dv2 users can configure if the static system EID should be used during CLC handshake, or if only user EIDs are allowed. Add generic netlink support to enable and disable the system EID, and to retrieve the system EID and its current enabled state. Signed-off-by: Karsten Graul Reviewed-by: Guvenc Gulce Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 12 ++++++++++ net/smc/smc_clc.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_clc.h | 3 +++ net/smc/smc_netlink.c | 15 ++++++++++++ 4 files changed, 92 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index e3728af2832b..b175bd0165a1 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -56,6 +56,9 @@ enum { SMC_NETLINK_ADD_UEID, SMC_NETLINK_REMOVE_UEID, SMC_NETLINK_FLUSH_UEID, + SMC_NETLINK_DUMP_SEID, + SMC_NETLINK_ENABLE_SEID, + SMC_NETLINK_DISABLE_SEID, }; /* SMC_GENL_FAMILY top level attributes */ @@ -257,4 +260,13 @@ enum { __SMC_NLA_EID_TABLE_MAX, SMC_NLA_EID_TABLE_MAX = __SMC_NLA_EID_TABLE_MAX - 1 }; + +/* SMC_NETLINK_SEID attributes */ +enum { + SMC_NLA_SEID_UNSPEC, + SMC_NLA_SEID_ENTRY, /* string */ + SMC_NLA_SEID_ENABLED, /* u8 */ + __SMC_NLA_SEID_TABLE_MAX, + SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 5a5ebf752860..4afd9e71e5c2 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -143,6 +143,10 @@ static int smc_clc_ueid_remove(char *ueid) rc = 0; } } + if (!rc && !smc_clc_eid_table.ueid_cnt) { + smc_clc_eid_table.seid_enabled = 1; + rc = -EAGAIN; /* indicate success and enabling of seid */ + } write_unlock(&smc_clc_eid_table.lock); return rc; } @@ -216,6 +220,64 @@ int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + char seid_str[SMC_MAX_EID_LEN + 1]; + u8 seid_enabled; + void *hdr; + u8 *seid; + + if (cb_ctx->pos[0]) + return skb->len; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_DUMP_SEID); + if (!hdr) + return -ENOMEM; + if (!smc_ism_is_v2_capable()) + goto end; + + smc_ism_get_system_eid(&seid); + snprintf(seid_str, sizeof(seid_str), "%s", seid); + if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) + goto err; + read_lock(&smc_clc_eid_table.lock); + seid_enabled = smc_clc_eid_table.seid_enabled; + read_unlock(&smc_clc_eid_table.lock); + if (nla_put_u8(skb, SMC_NLA_SEID_ENABLED, seid_enabled)) + goto err; +end: + genlmsg_end(skb, hdr); + cb_ctx->pos[0]++; + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) +{ + write_lock(&smc_clc_eid_table.lock); + smc_clc_eid_table.seid_enabled = 1; + write_unlock(&smc_clc_eid_table.lock); + return 0; +} + +int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) +{ + int rc = 0; + + write_lock(&smc_clc_eid_table.lock); + if (!smc_clc_eid_table.ueid_cnt) + rc = -ENOENT; + else + smc_clc_eid_table.seid_enabled = 0; + write_unlock(&smc_clc_eid_table.lock); + return rc; +} + static bool _smc_clc_match_ueid(u8 *peer_ueid) { struct smc_clc_eid_entry *tmp_ueid; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 0699e0cee308..974d01d16bb5 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -347,5 +347,8 @@ int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 4548ff2df245..f13ab0661ed5 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -96,6 +96,21 @@ static const struct genl_ops smc_gen_nl_ops[] = { .flags = GENL_ADMIN_PERM, .doit = smc_nl_flush_ueid, }, + { + .cmd = SMC_NETLINK_DUMP_SEID, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_seid, + }, + { + .cmd = SMC_NETLINK_ENABLE_SEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_enable_seid, + }, + { + .cmd = SMC_NETLINK_DISABLE_SEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_disable_seid, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.2.3 From 41ced4cd88020c9d4b71ff7c50d020f081efa4a0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 14 Sep 2021 15:30:09 -0700 Subject: btf: Change BTF_KIND_* macros to enums Change BTF_KIND_* macros to enums so they are encoded in dwarf and appear in vmlinux.h. This will make it easier for bpf programs to use these constants without macro definitions. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210914223009.245307-1-yhs@fb.com --- include/uapi/linux/btf.h | 41 ++++++++++++++++++++++------------------- tools/include/uapi/linux/btf.h | 41 ++++++++++++++++++++++------------------- 2 files changed, 44 insertions(+), 38 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index d27b1708efe9..10e401073dd1 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -56,25 +56,28 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index d27b1708efe9..10e401073dd1 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -56,25 +56,28 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. -- cgit v1.2.3 From b5ea834dde6b6e7f75e51d5f66dac8cd7c97b5ef Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 14 Sep 2021 15:30:15 -0700 Subject: bpf: Support for new btf kind BTF_KIND_TAG LLVM14 added support for a new C attribute ([1]) __attribute__((btf_tag("arbitrary_str"))) This attribute will be emitted to dwarf ([2]) and pahole will convert it to BTF. Or for bpf target, this attribute will be emitted to BTF directly ([3], [4]). The attribute is intended to provide additional information for - struct/union type or struct/union member - static/global variables - static/global function or function parameter. For linux kernel, the btf_tag can be applied in various places to specify user pointer, function pre- or post- condition, function allow/deny in certain context, etc. Such information will be encoded in vmlinux BTF and can be used by verifier. The btf_tag can also be applied to bpf programs to help global verifiable functions, e.g., specifying preconditions, etc. This patch added basic parsing and checking support in kernel for new BTF_KIND_TAG kind. [1] https://reviews.llvm.org/D106614 [2] https://reviews.llvm.org/D106621 [3] https://reviews.llvm.org/D106622 [4] https://reviews.llvm.org/D109560 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210914223015.245546-1-yhs@fb.com --- include/uapi/linux/btf.h | 14 ++++- kernel/bpf/btf.c | 128 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/btf.h | 14 ++++- 3 files changed, 154 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 10e401073dd1..642b6ecb37d7 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -74,6 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -173,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dfe61df4f974..c3d605b22473 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,6 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -459,6 +460,17 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } +static bool btf_type_is_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TAG; +} + +static bool btf_type_is_tag_target(const struct btf_type *t) +{ + return btf_type_is_func(t) || btf_type_is_struct(t) || + btf_type_is_var(t); +} + u32 btf_nr_types(const struct btf *btf) { u32 total = 0; @@ -537,6 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || + btf_type_is_tag(t) || btf_type_is_datasec(t); } @@ -563,6 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || + btf_type_is_tag(t) || btf_type_is_datasec(t); } @@ -616,6 +630,11 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } +static const struct btf_tag *btf_type_tag(const struct btf_type *t) +{ + return (const struct btf_tag *)(t + 1); +} + static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; @@ -3801,6 +3820,110 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; +static s32 btf_tag_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_tag *tag; + u32 meta_needed = sizeof(*tag); + s32 component_idx; + const char *value; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid value"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + component_idx = btf_type_tag(t)->component_idx; + if (component_idx < -1) { + btf_verifier_log_type(env, t, "Invalid component_idx"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_tag_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + s32 component_idx; + u32 vlen; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type || !btf_type_is_tag_target(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + component_idx = btf_type_tag(t)->component_idx; + if (component_idx != -1) { + if (btf_type_is_var(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + + if (btf_type_is_struct(next_type)) { + vlen = btf_type_vlen(next_type); + } else { + /* next_type should be a function */ + next_type = btf_type_by_id(btf, next_type->type); + vlen = btf_type_vlen(next_type); + } + + if ((u32)component_idx >= vlen) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + } + + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +{ + btf_verifier_log(env, "type=%u component_idx=%d", t->type, + btf_type_tag(t)->component_idx); +} + +static const struct btf_kind_operations tag_ops = { + .check_meta = btf_tag_check_meta, + .resolve = btf_tag_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_tag_log, + .show = btf_df_show, +}; + static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { @@ -3935,6 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, + [BTF_KIND_TAG] = &tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4019,6 +4143,10 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); + if (btf_type_is_tag(t)) + return btf_resolved_type_id(btf, type_id) && + !btf_resolved_type_size(btf, type_id); + if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 10e401073dd1..642b6ecb37d7 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -74,6 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -173,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ -- cgit v1.2.3 From 67f1e027c27054e641584655020a417eaac9cb3a Mon Sep 17 00:00:00 2001 From: Lukas Prediger Date: Tue, 14 Sep 2021 00:09:42 +0100 Subject: drivers/cdrom: improved ioctl for media change detection The current implementation of the CDROM_MEDIA_CHANGED ioctl relies on global state, meaning that only one process can detect a disc change while the ioctl call will return 0 for other calling processes afterwards (see bug 213267). This introduces a new cdrom ioctl, CDROM_TIMED_MEDIA_CHANGE, that works by maintaining a timestamp of the last detected disc change instead of a boolean flag: Processes calling this ioctl command can provide a timestamp of the last disc change known to them and receive an indication whether the disc was changed since then and the updated timestamp. I considered fixing the buggy behavior in the original CDROM_MEDIA_CHANGED ioctl but that would require maintaining state for each calling process in the kernel, which seems like a worse solution than introducing this new ioctl. Signed-off-by: Lukas Prediger Link: https://lore.kernel.org/all/20210912191207.74449-1-lumip@lumip.de Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20210913230942.1188-1-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- Documentation/cdrom/cdrom-standard.rst | 11 ++++++ Documentation/userspace-api/ioctl/cdrom.rst | 3 ++ drivers/cdrom/cdrom.c | 59 +++++++++++++++++++++++++++-- include/linux/cdrom.h | 1 + include/uapi/linux/cdrom.h | 19 ++++++++++ 5 files changed, 89 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 5845960ca382..52ea7b6b2fe8 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -907,6 +907,17 @@ commands can be identified by the underscores in their names. specifies the slot for which the information is given. The special value *CDSL_CURRENT* requests that information about the currently selected slot be returned. +`CDROM_TIMED_MEDIA_CHANGE` + Checks whether the disc has been changed since a user supplied time + and returns the time of the last disc change. + + *arg* is a pointer to a *cdrom_timed_media_change_info* struct. + *arg->last_media_change* may be set by calling code to signal + the timestamp of the last known media change (by the caller). + Upon successful return, this ioctl call will set + *arg->last_media_change* to the latest media change timestamp (in ms) + known by the kernel/driver and set *arg->has_changed* to 1 if + that timestamp is more recent than the timestamp set by the caller. `CDROM_DRIVE_STATUS` Returns the status of the drive by a call to *drive_status()*. Return values are defined in cdrom_drive_status_. diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst index 3b4c0506de46..bac5bbf93ca0 100644 --- a/Documentation/userspace-api/ioctl/cdrom.rst +++ b/Documentation/userspace-api/ioctl/cdrom.rst @@ -54,6 +54,9 @@ are as follows: CDROM_SELECT_SPEED Set the CD-ROM speed CDROM_SELECT_DISC Select disc (for juke-boxes) CDROM_MEDIA_CHANGED Check is media changed + CDROM_TIMED_MEDIA_CHANGE Check if media changed + since given time + (struct cdrom_timed_media_change_info) CDROM_DRIVE_STATUS Get tray position, etc. CDROM_DISC_STATUS Get disc type, etc. CDROM_CHANGER_NSLOTS Get number of slots diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index bd2e5b1560f5..89a68457820a 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -344,6 +344,12 @@ static void cdrom_sysctl_register(void); static LIST_HEAD(cdrom_list); +static void signal_media_change(struct cdrom_device_info *cdi) +{ + cdi->mc_flags = 0x3; /* set media changed bits, on both queues */ + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); +} + int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi, struct packet_command *cgc) { @@ -616,6 +622,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) ENSURE(cdo, generic_packet, CDC_GENERIC_PACKET); cdi->mc_flags = 0; cdi->options = CDO_USE_FFLAGS; + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); if (autoclose == 1 && CDROM_CAN(CDC_CLOSE_TRAY)) cdi->options |= (int) CDO_AUTO_CLOSE; @@ -1421,8 +1428,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) cdi->ops->check_events(cdi, 0, slot); if (slot == CDSL_NONE) { - /* set media changed bits, on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); return cdrom_load_unload(cdi, -1); } @@ -1455,7 +1461,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) slot = curslot; /* set media changed bits on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); if ((ret = cdrom_load_unload(cdi, slot))) return ret; @@ -1521,7 +1527,7 @@ int media_changed(struct cdrom_device_info *cdi, int queue) cdi->ioctl_events = 0; if (changed) { - cdi->mc_flags = 0x3; /* set bit on both queues */ + signal_media_change(cdi); ret |= 1; cdi->media_written = 0; } @@ -2336,6 +2342,49 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, return ret; } +/* + * Media change detection with timing information. + * + * arg is a pointer to a cdrom_timed_media_change_info struct. + * arg->last_media_change may be set by calling code to signal + * the timestamp (in ms) of the last known media change (by the caller). + * Upon successful return, ioctl call will set arg->last_media_change + * to the latest media change timestamp known by the kernel/driver + * and set arg->has_changed to 1 if that timestamp is more recent + * than the timestamp set by the caller. + */ +static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi, + unsigned long arg) +{ + int ret; + struct cdrom_timed_media_change_info __user *info; + struct cdrom_timed_media_change_info tmp_info; + + if (!CDROM_CAN(CDC_MEDIA_CHANGED)) + return -ENOSYS; + + info = (struct cdrom_timed_media_change_info __user *)arg; + cd_dbg(CD_DO_IOCTL, "entering CDROM_TIMED_MEDIA_CHANGE\n"); + + ret = cdrom_ioctl_media_changed(cdi, CDSL_CURRENT); + if (ret < 0) + return ret; + + if (copy_from_user(&tmp_info, info, sizeof(tmp_info)) != 0) + return -EFAULT; + + tmp_info.media_flags = 0; + if (tmp_info.last_media_change - cdi->last_media_change_ms < 0) + tmp_info.media_flags |= MEDIA_CHANGED_FLAG; + + tmp_info.last_media_change = cdi->last_media_change_ms; + + if (copy_to_user(info, &tmp_info, sizeof(*info)) != 0) + return -EFAULT; + + return 0; +} + static int cdrom_ioctl_set_options(struct cdrom_device_info *cdi, unsigned long arg) { @@ -3313,6 +3362,8 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, return cdrom_ioctl_eject_sw(cdi, arg); case CDROM_MEDIA_CHANGED: return cdrom_ioctl_media_changed(cdi, arg); + case CDROM_TIMED_MEDIA_CHANGE: + return cdrom_ioctl_timed_media_change(cdi, arg); case CDROM_SET_OPTIONS: return cdrom_ioctl_set_options(cdi, arg); case CDROM_CLEAR_OPTIONS: diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index c4fef00abdf3..0a89f111e00e 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -64,6 +64,7 @@ struct cdrom_device_info { int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + __s64 last_media_change_ms; }; struct cdrom_device_ops { diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 6c34f6e2f1f7..804ff8d98f71 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -147,6 +147,8 @@ #define CDROM_NEXT_WRITABLE 0x5394 /* get next writable block */ #define CDROM_LAST_WRITTEN 0x5395 /* get last block written on disc */ +#define CDROM_TIMED_MEDIA_CHANGE 0x5396 /* get the timestamp of the last media change */ + /******************************************************* * CDROM IOCTL structures *******************************************************/ @@ -295,6 +297,23 @@ struct cdrom_generic_command }; }; +/* This struct is used by CDROM_TIMED_MEDIA_CHANGE */ +struct cdrom_timed_media_change_info { + __s64 last_media_change; /* Timestamp of the last detected media + * change in ms. May be set by caller, + * updated upon successful return of + * ioctl. + */ + __u64 media_flags; /* Flags returned by ioctl to indicate + * media status. + */ +}; +#define MEDIA_CHANGED_FLAG 0x1 /* Last detected media change was more + * recent than last_media_change set by + * caller. + */ +/* other bits of media_flags available for future use */ + /* * A CD-ROM physical sector size is 2048, 2052, 2056, 2324, 2332, 2336, * 2340, or 2352 bytes long. -- cgit v1.2.3 From 336562752acc1a723f9a24b5b8129ae22e0478c6 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Wed, 15 Sep 2021 01:54:00 +0200 Subject: bpf: Update bpf_get_smp_processor_id() documentation BPF programs run with migration disabled regardless of preemption, as they are protected by migrate_disable(). Update the uapi documentation accordingly. Signed-off-by: Matteo Croce Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210914235400.59427-1-mcroce@linux.microsoft.com --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d21326558d42..3e9785f1064a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d21326558d42..3e9785f1064a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return -- cgit v1.2.3 From 227b9644ab16d2ecd98d593edbe15c32c0c9620a Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 16 Sep 2021 11:37:38 +0800 Subject: net/tls: support SM4 GCM/CCM algorithm The RFC8998 specification defines the use of the ShangMi algorithm cipher suites in TLS 1.3, and also supports the GCM/CCM mode using the SM4 algorithm. Signed-off-by: Tianjia Zhang Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/tls.h | 30 ++++++++++++++++++++++++++++++ net/tls/tls_main.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ net/tls/tls_sw.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index 0d54baea1d8d..5f38be0ec0f3 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -84,6 +84,20 @@ #define TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE 16 #define TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE 8 +#define TLS_CIPHER_SM4_GCM 55 +#define TLS_CIPHER_SM4_GCM_IV_SIZE 8 +#define TLS_CIPHER_SM4_GCM_KEY_SIZE 16 +#define TLS_CIPHER_SM4_GCM_SALT_SIZE 4 +#define TLS_CIPHER_SM4_GCM_TAG_SIZE 16 +#define TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE 8 + +#define TLS_CIPHER_SM4_CCM 56 +#define TLS_CIPHER_SM4_CCM_IV_SIZE 8 +#define TLS_CIPHER_SM4_CCM_KEY_SIZE 16 +#define TLS_CIPHER_SM4_CCM_SALT_SIZE 4 +#define TLS_CIPHER_SM4_CCM_TAG_SIZE 16 +#define TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE 8 + #define TLS_SET_RECORD_TYPE 1 #define TLS_GET_RECORD_TYPE 2 @@ -124,6 +138,22 @@ struct tls12_crypto_info_chacha20_poly1305 { unsigned char rec_seq[TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE]; }; +struct tls12_crypto_info_sm4_gcm { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_SM4_GCM_IV_SIZE]; + unsigned char key[TLS_CIPHER_SM4_GCM_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_SM4_GCM_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE]; +}; + +struct tls12_crypto_info_sm4_ccm { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_SM4_CCM_IV_SIZE]; + unsigned char key[TLS_CIPHER_SM4_CCM_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_SM4_CCM_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE]; +}; + enum { TLS_INFO_UNSPEC, TLS_INFO_VERSION, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index fde56ff49163..d44399efeac6 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -421,6 +421,46 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EFAULT; break; } + case TLS_CIPHER_SM4_GCM: { + struct tls12_crypto_info_sm4_gcm *sm4_gcm_info = + container_of(crypto_info, + struct tls12_crypto_info_sm4_gcm, info); + + if (len != sizeof(*sm4_gcm_info)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(sm4_gcm_info->iv, + cctx->iv + TLS_CIPHER_SM4_GCM_SALT_SIZE, + TLS_CIPHER_SM4_GCM_IV_SIZE); + memcpy(sm4_gcm_info->rec_seq, cctx->rec_seq, + TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, sm4_gcm_info, sizeof(*sm4_gcm_info))) + rc = -EFAULT; + break; + } + case TLS_CIPHER_SM4_CCM: { + struct tls12_crypto_info_sm4_ccm *sm4_ccm_info = + container_of(crypto_info, + struct tls12_crypto_info_sm4_ccm, info); + + if (len != sizeof(*sm4_ccm_info)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(sm4_ccm_info->iv, + cctx->iv + TLS_CIPHER_SM4_CCM_SALT_SIZE, + TLS_CIPHER_SM4_CCM_IV_SIZE); + memcpy(sm4_ccm_info->rec_seq, cctx->rec_seq, + TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, sm4_ccm_info, sizeof(*sm4_ccm_info))) + rc = -EFAULT; + break; + } default: rc = -EINVAL; } @@ -524,6 +564,12 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, case TLS_CIPHER_CHACHA20_POLY1305: optsize = sizeof(struct tls12_crypto_info_chacha20_poly1305); break; + case TLS_CIPHER_SM4_GCM: + optsize = sizeof(struct tls12_crypto_info_sm4_gcm); + break; + case TLS_CIPHER_SM4_CCM: + optsize = sizeof(struct tls12_crypto_info_sm4_ccm); + break; default: rc = -EINVAL; goto err_crypto_info; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4feb95e34b64..989d1423a245 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2424,6 +2424,40 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cipher_name = "rfc7539(chacha20,poly1305)"; break; } + case TLS_CIPHER_SM4_GCM: { + struct tls12_crypto_info_sm4_gcm *sm4_gcm_info; + + sm4_gcm_info = (void *)crypto_info; + nonce_size = TLS_CIPHER_SM4_GCM_IV_SIZE; + tag_size = TLS_CIPHER_SM4_GCM_TAG_SIZE; + iv_size = TLS_CIPHER_SM4_GCM_IV_SIZE; + iv = sm4_gcm_info->iv; + rec_seq_size = TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE; + rec_seq = sm4_gcm_info->rec_seq; + keysize = TLS_CIPHER_SM4_GCM_KEY_SIZE; + key = sm4_gcm_info->key; + salt = sm4_gcm_info->salt; + salt_size = TLS_CIPHER_SM4_GCM_SALT_SIZE; + cipher_name = "gcm(sm4)"; + break; + } + case TLS_CIPHER_SM4_CCM: { + struct tls12_crypto_info_sm4_ccm *sm4_ccm_info; + + sm4_ccm_info = (void *)crypto_info; + nonce_size = TLS_CIPHER_SM4_CCM_IV_SIZE; + tag_size = TLS_CIPHER_SM4_CCM_TAG_SIZE; + iv_size = TLS_CIPHER_SM4_CCM_IV_SIZE; + iv = sm4_ccm_info->iv; + rec_seq_size = TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE; + rec_seq = sm4_ccm_info->rec_seq; + keysize = TLS_CIPHER_SM4_CCM_KEY_SIZE; + key = sm4_ccm_info->key; + salt = sm4_ccm_info->salt; + salt_size = TLS_CIPHER_SM4_CCM_SALT_SIZE; + cipher_name = "ccm(sm4)"; + break; + } default: rc = -EINVAL; goto free_priv; -- cgit v1.2.3 From 10aceb629e198429c849d5e995c3bb1ba7a9aaa3 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:05 -0700 Subject: bpf: Add bpf_trace_vprintk helper This helper is meant to be "bpf_trace_printk, but with proper vararg support". Follow bpf_snprintf's example and take a u64 pseudo-vararg array. Write to /sys/kernel/debug/tracing/trace_pipe using the same mechanism as bpf_trace_printk. The functionality of this helper was requested in the libbpf issue tracker [0]. [0] Closes: https://github.com/libbpf/libbpf/issues/315 Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-4-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++ kernel/bpf/core.c | 5 ++++ kernel/bpf/helpers.c | 2 ++ kernel/trace/bpf_trace.c | 52 +++++++++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 11 +++++++++ 6 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be8d57e6e78a..b6c45a6cbbba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1088,6 +1088,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..6fddc13fe67f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2357,6 +2357,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8f9f392c1322..2c604ff8c7fb 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1435,6 +1435,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return NULL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4ec779fa0c1d..6b3153841a33 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -398,7 +398,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .arg2_type = ARG_CONST_SIZE, }; -const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +static void __set_printk_clr_event(void) { /* * This program might be calling bpf_trace_printk, @@ -410,10 +410,58 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); +} +const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +{ + __set_printk_clr_event(); return &bpf_trace_printk_proto; } +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, + u32, data_len) +{ + static char buf[BPF_TRACE_PRINTK_SIZE]; + unsigned long flags; + int ret, num_args; + u32 *bin_args; + + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || + (data_len && !data)) + return -EINVAL; + num_args = data_len / 8; + + ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + if (ret < 0) + return ret; + + raw_spin_lock_irqsave(&trace_printk_lock, flags); + ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + + trace_bpf_trace_printk(buf); + raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + + bpf_bprintf_cleanup(); + + return ret; +} + +static const struct bpf_func_proto bpf_trace_vprintk_proto = { + .func = bpf_trace_vprintk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) +{ + __set_printk_clr_event(); + return &bpf_trace_vprintk_proto; +} + BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) { @@ -1160,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From a42effb0b24fcaf49513c2d7d77ef6daa9e32a6f Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:11 -0700 Subject: bpf: Clarify data_len param in bpf_snprintf and bpf_seq_printf comments Since the data_len in these two functions is a byte len of the preceding u64 *data array, it must always be a multiple of 8. If this isn't the case both helpers error out, so let's make the requirement explicit so users don't need to infer it. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-10-davemarchevsky@fb.com --- include/uapi/linux/bpf.h | 5 +++-- tools/include/uapi/linux/bpf.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 98ca79a67937..6fc59d61937a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 98ca79a67937..6fc59d61937a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid -- cgit v1.2.3 From 55c42fa7fa331f98062c32799456420930b8bf8c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:19 -0700 Subject: mptcp: add MPTCP_INFO getsockopt Its not compatible with multipath-tcp.org kernel one. 1. The out-of-tree implementation defines a different 'struct mptcp_info', with embedded __user addresses for additional data such as endpoint addresses. 2. Mat Martineau points out that embedded __user addresses doesn't work with BPF_CGROUP_RUN_PROG_GETSOCKOPT() which assumes that copying in optsize bytes from optval provides all data that got copied to userspace. This provides mptcp_info data for the given mptcp socket. Userspace sets optlen to the size of the structure it expects. The kernel updates it to contain the number of bytes that it copied. This allows to append more information to the structure later. Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/uapi/linux/mptcp.h | 3 +++ net/mptcp/sockopt.c | 40 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/linux/socket.h b/include/linux/socket.h index 041d6032a348..7612d760b6a9 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -364,6 +364,7 @@ struct ucred { #define SOL_KCM 281 #define SOL_TLS 282 #define SOL_XDP 283 +#define SOL_MPTCP 284 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index f66038b9551f..3e9caeddda7e 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -193,4 +193,7 @@ enum mptcp_event_attr { #define MPTCP_RST_EBADPERF 5 #define MPTCP_RST_EMIDDLEBOX 6 +/* MPTCP socket options */ +#define MPTCP_INFO 1 + #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 54f0d521a399..f7683c22911f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -673,10 +673,14 @@ out: void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) { struct sock *sk = &msk->sk.icsk_inet.sk; - bool slow = lock_sock_fast(sk); u32 flags = 0; + bool slow; u8 val; + memset(info, 0, sizeof(*info)); + + slow = lock_sock_fast(sk); + info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); @@ -702,6 +706,27 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); +static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen) +{ + struct mptcp_info m_info; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(struct mptcp_info)); + + mptcp_diag_fill_info(msk, &m_info); + + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &m_info, len)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -716,6 +741,17 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return -EOPNOTSUPP; } +static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, + char __user *optval, int __user *optlen) +{ + switch (optname) { + case MPTCP_INFO: + return mptcp_getsockopt_info(msk, optval, optlen); + } + + return -EOPNOTSUPP; +} + int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { @@ -738,6 +774,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, if (level == SOL_TCP) return mptcp_getsockopt_sol_tcp(msk, optname, optval, option); + if (level == SOL_MPTCP) + return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option); return -EOPNOTSUPP; } -- cgit v1.2.3 From 06f15cee369535a383c9c82ed37a25f0a413f6f1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:20 -0700 Subject: mptcp: add MPTCP_TCPINFO getsockopt support Allow users to retrieve TCP_INFO data of all subflows. Users need to pre-initialize a meta header that has to be prepended to the data buffer that will be filled with the tcp info data. The meta header looks like this: struct mptcp_subflow_data { __u32 size_subflow_data;/* size of this structure in userspace */ __u32 num_subflows; /* must be 0, set by kernel */ __u32 size_kernel; /* must be 0, set by kernel */ __u32 size_user; /* size of one element in data[] */ } __attribute__((aligned(8))); size_subflow_data has to be set to 'sizeof(struct mptcp_subflow_data)'. This allows to extend mptcp_subflow_data structure later on without breaking backwards compatibility. If the structure is extended later on, kernel knows where the userspace-provided meta header ends, even if userspace uses an older (smaller) version of the structure. num_subflows must be set to 0. If the getsockopt request succeeds (return value is 0), it will be updated to contain the number of active subflows for the given logical connection. size_kernel must be set to 0. If the getsockopt request is successful, it will contain the size of the 'struct tcp_info' as known by the kernel. This is informational only. size_user must be set to 'sizeof(struct tcp_info)'. This allows the kernel to only fill in the space reserved/expected by userspace. Example: struct my_tcp_info { struct mptcp_subflow_data d; struct tcp_info ti[2]; }; struct my_tcp_info ti; socklen_t olen; memset(&ti, 0, sizeof(ti)); ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data); ti.d.size_user = sizeof(struct tcp_info); olen = sizeof(ti); ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen); if (ret < 0) die_perror("getsockopt MPTCP_TCPINFO"); mptcp_subflow_data.num_subflows is populated with the number of subflows that exist on the kernel side for the logical mptcp connection. This allows userspace to re-try with a larger tcp_info array if the number of subflows was larger than the available space in the ti[] array. olen has to be set to the number of bytes that userspace has allocated to receive the kernel data. It will be updated to contain the real number bytes that have been copied to by the kernel. In the above example, if the number if subflows was 1, olen is equal to 'sizeof(struct mptcp_subflow_data) + sizeof(struct tcp_info). For 2 or more subflows olen is equal to 'sizeof(struct my_tcp_info)'. If there was more data that could not be copied due to lack of space in the option buffer, userspace can detect this by checking mptcp_subflow_data->num_subflows. Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 10 +++- net/mptcp/sockopt.c | 115 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 124 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3e9caeddda7e..3f013a513770 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -193,7 +193,15 @@ enum mptcp_event_attr { #define MPTCP_RST_EBADPERF 5 #define MPTCP_RST_EMIDDLEBOX 6 +struct mptcp_subflow_data { + __u32 size_subflow_data; /* size of this structure in userspace */ + __u32 num_subflows; /* must be 0, set by kernel */ + __u32 size_kernel; /* must be 0, set by kernel */ + __u32 size_user; /* size of one element in data[] */ +} __attribute__((aligned(8))); + /* MPTCP socket options */ -#define MPTCP_INFO 1 +#define MPTCP_INFO 1 +#define MPTCP_TCPINFO 2 #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index f7683c22911f..eb2905bfa089 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -14,6 +14,8 @@ #include #include "protocol.h" +#define MIN_INFO_OPTLEN_SIZE 16 + static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { sock_owned_by_me((const struct sock *)msk); @@ -727,6 +729,117 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in return 0; } +static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd, + char __user *optval, + u32 copied, + int __user *optlen) +{ + u32 copylen = min_t(u32, sfd->size_subflow_data, sizeof(*sfd)); + + if (copied) + copied += sfd->size_subflow_data; + else + copied = copylen; + + if (put_user(copied, optlen)) + return -EFAULT; + + if (copy_to_user(optval, sfd, copylen)) + return -EFAULT; + + return 0; +} + +static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd, + char __user *optval, int __user *optlen) +{ + int len, copylen; + + if (get_user(len, optlen)) + return -EFAULT; + + /* if mptcp_subflow_data size is changed, need to adjust + * this function to deal with programs using old version. + */ + BUILD_BUG_ON(sizeof(*sfd) != MIN_INFO_OPTLEN_SIZE); + + if (len < MIN_INFO_OPTLEN_SIZE) + return -EINVAL; + + memset(sfd, 0, sizeof(*sfd)); + + copylen = min_t(unsigned int, len, sizeof(*sfd)); + if (copy_from_user(sfd, optval, copylen)) + return -EFAULT; + + /* size_subflow_data is u32, but len is signed */ + if (sfd->size_subflow_data > INT_MAX || + sfd->size_user > INT_MAX) + return -EINVAL; + + if (sfd->size_subflow_data < MIN_INFO_OPTLEN_SIZE || + sfd->size_subflow_data > len) + return -EINVAL; + + if (sfd->num_subflows || sfd->size_kernel) + return -EINVAL; + + return len - sfd->size_subflow_data; +} + +static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = &msk->sk.icsk_inet.sk; + unsigned int sfcount = 0, copied = 0; + struct mptcp_subflow_data sfd; + char __user *infoptr; + int len; + + len = mptcp_get_subflow_data(&sfd, optval, optlen); + if (len < 0) + return len; + + sfd.size_kernel = sizeof(struct tcp_info); + sfd.size_user = min_t(unsigned int, sfd.size_user, + sizeof(struct tcp_info)); + + infoptr = optval + sfd.size_subflow_data; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ++sfcount; + + if (len && len >= sfd.size_user) { + struct tcp_info info; + + tcp_get_info(ssk, &info); + + if (copy_to_user(infoptr, &info, sfd.size_user)) { + release_sock(sk); + return -EFAULT; + } + + infoptr += sfd.size_user; + copied += sfd.size_user; + len -= sfd.size_user; + } + } + + release_sock(sk); + + sfd.num_subflows = sfcount; + + if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -747,6 +860,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, switch (optname) { case MPTCP_INFO: return mptcp_getsockopt_info(msk, optval, optlen); + case MPTCP_TCPINFO: + return mptcp_getsockopt_tcpinfo(msk, optval, optlen); } return -EOPNOTSUPP; -- cgit v1.2.3 From c11c5906bc0aba62a78da69035f6b30c6da6d13b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:21 -0700 Subject: mptcp: add MPTCP_SUBFLOW_ADDRS getsockopt support This retrieves the address pairs of all subflows currently active for a given mptcp connection. It re-uses the same meta-header as for MPTCP_TCPINFO. A new structure is provided to hold the subflow address data: struct mptcp_subflow_addrs { union { __kernel_sa_family_t sa_family; struct sockaddr sa_local; struct sockaddr_in sin_local; struct sockaddr_in6 sin6_local; struct sockaddr_storage ss_local; }; union { struct sockaddr sa_remote; struct sockaddr_in sin_remote; struct sockaddr_in6 sin6_remote; struct sockaddr_storage ss_remote; }; }; Usage of the new getsockopt is very similar to MPTCP_TCPINFO one. Userspace allocates a 'struct mptcp_subflow_data', followed by one or more 'struct mptcp_subflow_addrs', then inits the mptcp_subflow_data structure as follows: struct mptcp_subflow_addrs *sf_addr; struct mptcp_subflow_data *addr; socklen_t olen = sizeof(*addr) + (8 * sizeof(*sf_addr)); addr = malloc(olen); addr->size_subflow_data = sizeof(*addr); addr->num_subflows = 0; addr->size_kernel = 0; addr->size_user = sizeof(struct mptcp_subflow_addrs); sf_addr = (struct mptcp_subflow_addrs *)(addr + 1); and then retrieves the endpoint addresses via: ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, addr, &olen); If the call succeeds, kernel will have added up to 8 endpoint addresses after the 'mptcp_subflow_data' header. Userspace needs to re-check 'olen' value to detect how many bytes have been filled in by the kernel. Userspace can check addr->num_subflows to discover when there were more subflows that available data space. Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 24 ++++++++++++ net/mptcp/sockopt.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3f013a513770..c8cc46f80a16 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -4,6 +4,13 @@ #include #include +#include /* for sockaddr_in */ +#include /* for sockaddr_in6 */ +#include /* for sockaddr_storage and sa_family */ + +#ifndef __KERNEL__ +#include /* for struct sockaddr */ +#endif #define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0) #define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1) @@ -200,8 +207,25 @@ struct mptcp_subflow_data { __u32 size_user; /* size of one element in data[] */ } __attribute__((aligned(8))); +struct mptcp_subflow_addrs { + union { + __kernel_sa_family_t sa_family; + struct sockaddr sa_local; + struct sockaddr_in sin_local; + struct sockaddr_in6 sin6_local; + struct __kernel_sockaddr_storage ss_local; + }; + union { + struct sockaddr sa_remote; + struct sockaddr_in sin_remote; + struct sockaddr_in6 sin6_remote; + struct __kernel_sockaddr_storage ss_remote; + }; +}; + /* MPTCP socket options */ #define MPTCP_INFO 1 #define MPTCP_TCPINFO 2 +#define MPTCP_SUBFLOW_ADDRS 3 #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index eb2905bfa089..8137cc3a4296 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -840,6 +840,95 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, return 0; } +static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a) +{ + struct inet_sock *inet = inet_sk(sk); + + memset(a, 0, sizeof(*a)); + + if (sk->sk_family == AF_INET) { + a->sin_local.sin_family = AF_INET; + a->sin_local.sin_port = inet->inet_sport; + a->sin_local.sin_addr.s_addr = inet->inet_rcv_saddr; + + if (!a->sin_local.sin_addr.s_addr) + a->sin_local.sin_addr.s_addr = inet->inet_saddr; + + a->sin_remote.sin_family = AF_INET; + a->sin_remote.sin_port = inet->inet_dport; + a->sin_remote.sin_addr.s_addr = inet->inet_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_family == AF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + + a->sin6_local.sin6_family = AF_INET6; + a->sin6_local.sin6_port = inet->inet_sport; + + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + a->sin6_local.sin6_addr = np->saddr; + else + a->sin6_local.sin6_addr = sk->sk_v6_rcv_saddr; + + a->sin6_remote.sin6_family = AF_INET6; + a->sin6_remote.sin6_port = inet->inet_dport; + a->sin6_remote.sin6_addr = sk->sk_v6_daddr; +#endif + } +} + +static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + struct sock *sk = &msk->sk.icsk_inet.sk; + struct mptcp_subflow_context *subflow; + unsigned int sfcount = 0, copied = 0; + struct mptcp_subflow_data sfd; + char __user *addrptr; + int len; + + len = mptcp_get_subflow_data(&sfd, optval, optlen); + if (len < 0) + return len; + + sfd.size_kernel = sizeof(struct mptcp_subflow_addrs); + sfd.size_user = min_t(unsigned int, sfd.size_user, + sizeof(struct mptcp_subflow_addrs)); + + addrptr = optval + sfd.size_subflow_data; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ++sfcount; + + if (len && len >= sfd.size_user) { + struct mptcp_subflow_addrs a; + + mptcp_get_sub_addrs(ssk, &a); + + if (copy_to_user(addrptr, &a, sfd.size_user)) { + release_sock(sk); + return -EFAULT; + } + + addrptr += sfd.size_user; + copied += sfd.size_user; + len -= sfd.size_user; + } + } + + release_sock(sk); + + sfd.num_subflows = sfcount; + + if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -862,6 +951,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, return mptcp_getsockopt_info(msk, optval, optlen); case MPTCP_TCPINFO: return mptcp_getsockopt_tcpinfo(msk, optval, optlen); + case MPTCP_SUBFLOW_ADDRS: + return mptcp_getsockopt_subflow_addrs(msk, optval, optlen); } return -EOPNOTSUPP; -- cgit v1.2.3 From 5bd2182d58e9d9c6279b7a8a2f9b41add0e7f9cb Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 16 Feb 2021 19:46:48 -0500 Subject: audit,io_uring,io-wq: add some basic audit support to io_uring This patch adds basic auditing to io_uring operations, regardless of their context. This is accomplished by allocating audit_context structures for the io-wq worker and io_uring SQPOLL kernel threads as well as explicitly auditing the io_uring operations in io_issue_sqe(). Individual io_uring operations can bypass auditing through the "audit_skip" field in the struct io_op_def definition for the operation; although great care must be taken so that security relevant io_uring operations do not bypass auditing; please contact the audit mailing list (see the MAINTAINERS file) with any questions. The io_uring operations are audited using a new AUDIT_URINGOP record, an example is shown below: type=UNKNOWN[1336] msg=audit(1631800225.981:37289): uring_op=19 success=yes exit=0 items=0 ppid=15454 pid=15681 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) Thanks to Richard Guy Briggs for review and feedback. Signed-off-by: Paul Moore --- fs/io-wq.c | 4 ++ fs/io_uring.c | 55 +++++++++++++-- include/linux/audit.h | 26 +++++++ include/uapi/linux/audit.h | 1 + kernel/audit.h | 2 + kernel/auditsc.c | 166 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 248 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/fs/io-wq.c b/fs/io-wq.c index 6c55362c1f99..dac5c5961c9d 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "io-wq.h" @@ -562,6 +563,8 @@ static int io_wqe_worker(void *data) snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); + audit_alloc_kernel(current); + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { long ret; @@ -601,6 +604,7 @@ loop: io_worker_handle_work(worker); } + audit_free(current); io_worker_exit(worker); return 0; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 16fb7436043c..388754b24785 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -79,6 +79,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -917,6 +918,8 @@ struct io_op_def { unsigned needs_async_setup : 1; /* should block plug */ unsigned plug : 1; + /* skip auditing */ + unsigned audit_skip : 1; /* size of async data needed, if any */ unsigned short async_size; }; @@ -930,6 +933,7 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .needs_async_setup = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITEV] = { @@ -939,16 +943,19 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .needs_async_setup = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FSYNC] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE_FIXED] = { @@ -957,15 +964,20 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_POLL_ADD] = { .needs_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, + }, + [IORING_OP_POLL_REMOVE] = { + .audit_skip = 1, }, - [IORING_OP_POLL_REMOVE] = {}, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_SENDMSG] = { .needs_file = 1, @@ -983,18 +995,23 @@ static const struct io_op_def io_op_defs[] = { .async_size = sizeof(struct io_async_msghdr), }, [IORING_OP_TIMEOUT] = { + .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_TIMEOUT_REMOVE] = { /* used by timeout updates' prep() */ + .audit_skip = 1, }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, }, - [IORING_OP_ASYNC_CANCEL] = {}, + [IORING_OP_ASYNC_CANCEL] = { + .audit_skip = 1, + }, [IORING_OP_LINK_TIMEOUT] = { + .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_CONNECT] = { @@ -1009,14 +1026,19 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_OPENAT] = {}, [IORING_OP_CLOSE] = {}, - [IORING_OP_FILES_UPDATE] = {}, - [IORING_OP_STATX] = {}, + [IORING_OP_FILES_UPDATE] = { + .audit_skip = 1, + }, + [IORING_OP_STATX] = { + .audit_skip = 1, + }, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE] = { @@ -1025,39 +1047,50 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FADVISE] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_MADVISE] = {}, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .audit_skip = 1, }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, + .audit_skip = 1, }, [IORING_OP_OPENAT2] = { }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, + .audit_skip = 1, }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, + }, + [IORING_OP_PROVIDE_BUFFERS] = { + .audit_skip = 1, + }, + [IORING_OP_REMOVE_BUFFERS] = { + .audit_skip = 1, }, - [IORING_OP_PROVIDE_BUFFERS] = {}, - [IORING_OP_REMOVE_BUFFERS] = {}, [IORING_OP_TEE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, }, [IORING_OP_SHUTDOWN] = { .needs_file = 1, @@ -6591,6 +6624,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) creds = override_creds(req->creds); + if (!io_op_defs[req->opcode].audit_skip) + audit_uring_entry(req->opcode); + switch (req->opcode) { case IORING_OP_NOP: ret = io_nop(req, issue_flags); @@ -6706,6 +6742,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) break; } + if (!io_op_defs[req->opcode].audit_skip) + audit_uring_exit(!ret, ret); + if (creds) revert_creds(creds); if (ret) @@ -7360,6 +7399,8 @@ static int io_sq_thread(void *data) set_cpus_allowed_ptr(current, cpu_online_mask); current->flags |= PF_NO_SETAFFINITY; + audit_alloc_kernel(current); + mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; @@ -7425,6 +7466,8 @@ static int io_sq_thread(void *data) io_run_task_work(); mutex_unlock(&sqd->lock); + audit_free(current); + complete(&sqd->exited); do_exit(0); } diff --git a/include/linux/audit.h b/include/linux/audit.h index 82b7c1116a85..d656a06dd909 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -286,7 +286,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t) /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); +extern int audit_alloc_kernel(struct task_struct *task); extern void __audit_free(struct task_struct *task); +extern void __audit_uring_entry(u8 op); +extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); @@ -323,6 +326,21 @@ static inline void audit_free(struct task_struct *task) if (unlikely(task->audit_context)) __audit_free(task); } +static inline void audit_uring_entry(u8 op) +{ + /* + * We intentionally check audit_context() before audit_enabled as most + * Linux systems (as of ~2021) rely on systemd which forces audit to + * be enabled regardless of the user's audit configuration. + */ + if (unlikely(audit_context() && audit_enabled)) + __audit_uring_entry(op); +} +static inline void audit_uring_exit(int success, long code) +{ + if (unlikely(!audit_dummy_context())) + __audit_uring_exit(success, code); +} static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) @@ -554,8 +572,16 @@ static inline int audit_alloc(struct task_struct *task) { return 0; } +static inline int audit_alloc_kernel(struct task_struct *task) +{ + return 0; +} static inline void audit_free(struct task_struct *task) { } +static inline void audit_uring_entry(u8 op) +{ } +static inline void audit_uring_exit(int success, long code) +{ } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..a1997697c8b1 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,7 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_URINGOP 1336 /* io_uring operation */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.h b/kernel/audit.h index 13abc48de0bd..d1161e3b83e2 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -103,10 +103,12 @@ struct audit_context { enum { AUDIT_CTX_UNUSED, /* audit_context is currently unused */ AUDIT_CTX_SYSCALL, /* in use by syscall */ + AUDIT_CTX_URING, /* in use by io_uring */ } context; enum audit_state state, current_state; unsigned int serial; /* serial number for record */ int major; /* syscall number */ + int uring_op; /* uring operation */ struct timespec64 ctime; /* time of syscall entry */ unsigned long argv[4]; /* syscall arguments */ long return_code;/* syscall return code */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f3d309b05c2d..6dda448fb826 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -959,6 +959,7 @@ static void audit_reset_context(struct audit_context *ctx) ctx->current_state = ctx->state; ctx->serial = 0; ctx->major = 0; + ctx->uring_op = 0; ctx->ctime = (struct timespec64){ .tv_sec = 0, .tv_nsec = 0 }; memset(ctx->argv, 0, sizeof(ctx->argv)); ctx->return_code = 0; @@ -1044,6 +1045,31 @@ int audit_alloc(struct task_struct *tsk) return 0; } +/** + * audit_alloc_kernel - allocate an audit_context for a kernel task + * @tsk: the kernel task + * + * Similar to the audit_alloc() function, but intended for kernel private + * threads. Returns zero on success, negative values on failure. + */ +int audit_alloc_kernel(struct task_struct *tsk) +{ + /* + * At the moment we are just going to call into audit_alloc() to + * simplify the code, but there two things to keep in mind with this + * approach: + * + * 1. Filtering internal kernel tasks is a bit laughable in almost all + * cases, but there is at least one case where there is a benefit: + * the '-a task,never' case allows the admin to effectively disable + * task auditing at runtime. + * + * 2. The {set,clear}_task_syscall_work() ops likely have zero effect + * on these internal kernel tasks, but they probably don't hurt either. + */ + return audit_alloc(tsk); +} + static inline void audit_free_context(struct audit_context *context) { /* resetting is extra work, but it is likely just noise */ @@ -1546,6 +1572,44 @@ out: audit_log_end(ab); } +/** + * audit_log_uring - generate a AUDIT_URINGOP record + * @ctx: the audit context + */ +static void audit_log_uring(struct audit_context *ctx) +{ + struct audit_buffer *ab; + const struct cred *cred; + + ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_URINGOP); + if (!ab) + return; + cred = current_cred(); + audit_log_format(ab, "uring_op=%d", ctx->uring_op); + if (ctx->return_valid != AUDITSC_INVALID) + audit_log_format(ab, " success=%s exit=%ld", + (ctx->return_valid == AUDITSC_SUCCESS ? + "yes" : "no"), + ctx->return_code); + audit_log_format(ab, + " items=%d" + " ppid=%d pid=%d uid=%u gid=%u euid=%u suid=%u" + " fsuid=%u egid=%u sgid=%u fsgid=%u", + ctx->name_count, + task_ppid_nr(current), task_tgid_nr(current), + from_kuid(&init_user_ns, cred->uid), + from_kgid(&init_user_ns, cred->gid), + from_kuid(&init_user_ns, cred->euid), + from_kuid(&init_user_ns, cred->suid), + from_kuid(&init_user_ns, cred->fsuid), + from_kgid(&init_user_ns, cred->egid), + from_kgid(&init_user_ns, cred->sgid), + from_kgid(&init_user_ns, cred->fsgid)); + audit_log_task_context(ab); + audit_log_key(ab, ctx->filterkey); + audit_log_end(ab); +} + static void audit_log_exit(void) { int i, call_panic = 0; @@ -1581,6 +1645,9 @@ static void audit_log_exit(void) audit_log_key(ab, context->filterkey); audit_log_end(ab); break; + case AUDIT_CTX_URING: + audit_log_uring(context); + break; default: BUG(); break; @@ -1751,6 +1818,105 @@ static void audit_return_fixup(struct audit_context *ctx, ctx->return_valid = (success ? AUDITSC_SUCCESS : AUDITSC_FAILURE); } +/** + * __audit_uring_entry - prepare the kernel task's audit context for io_uring + * @op: the io_uring opcode + * + * This is similar to audit_syscall_entry() but is intended for use by io_uring + * operations. This function should only ever be called from + * audit_uring_entry() as we rely on the audit context checking present in that + * function. + */ +void __audit_uring_entry(u8 op) +{ + struct audit_context *ctx = audit_context(); + + if (ctx->state == AUDIT_STATE_DISABLED) + return; + + /* + * NOTE: It's possible that we can be called from the process' context + * before it returns to userspace, and before audit_syscall_exit() + * is called. In this case there is not much to do, just record + * the io_uring details and return. + */ + ctx->uring_op = op; + if (ctx->context == AUDIT_CTX_SYSCALL) + return; + + ctx->dummy = !audit_n_rules; + if (!ctx->dummy && ctx->state == AUDIT_STATE_BUILD) + ctx->prio = 0; + + ctx->context = AUDIT_CTX_URING; + ctx->current_state = ctx->state; + ktime_get_coarse_real_ts64(&ctx->ctime); +} + +/** + * __audit_uring_exit - wrap up the kernel task's audit context after io_uring + * @success: true/false value to indicate if the operation succeeded or not + * @code: operation return code + * + * This is similar to audit_syscall_exit() but is intended for use by io_uring + * operations. This function should only ever be called from + * audit_uring_exit() as we rely on the audit context checking present in that + * function. + */ +void __audit_uring_exit(int success, long code) +{ + struct audit_context *ctx = audit_context(); + + /* + * TODO: At some point we will likely want to filter on io_uring ops + * and other things similar to what we do for syscalls, but that + * is something for another day; just record what we can here. + */ + + if (ctx->context == AUDIT_CTX_SYSCALL) { + /* + * NOTE: See the note in __audit_uring_entry() about the case + * where we may be called from process context before we + * return to userspace via audit_syscall_exit(). In this + * case we simply emit a URINGOP record and bail, the + * normal syscall exit handling will take care of + * everything else. + * It is also worth mentioning that when we are called, + * the current process creds may differ from the creds + * used during the normal syscall processing; keep that + * in mind if/when we move the record generation code. + */ + + /* + * We need to filter on the syscall info here to decide if we + * should emit a URINGOP record. I know it seems odd but this + * solves the problem where users have a filter to block *all* + * syscall records in the "exit" filter; we want to preserve + * the behavior here. + */ + audit_filter_syscall(current, ctx); + audit_filter_inodes(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + return; + + audit_log_uring(ctx); + return; + } + + /* this may generate CONFIG_CHANGE records */ + if (!list_empty(&ctx->killed_trees)) + audit_kill_trees(ctx); + + audit_filter_inodes(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + goto out; + audit_return_fixup(ctx, success, code); + audit_log_exit(); + +out: + audit_reset_context(ctx); +} + /** * __audit_syscall_entry - fill in an audit record at syscall entry * @major: major syscall type (function) -- cgit v1.2.3 From 67daf270cebcf7aab4b3292b36f9adf357b23ddc Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Sun, 18 Apr 2021 21:54:47 -0400 Subject: audit: add filtering for io_uring records This patch adds basic audit io_uring filtering, using as much of the existing audit filtering infrastructure as possible. In order to do this we reuse the audit filter rule's syscall mask for the io_uring operation and we create a new filter for io_uring operations as AUDIT_FILTER_URING_EXIT/audit_filter_list[7]. Thanks to Richard Guy Briggs for his review, feedback, and work on the corresponding audit userspace changes. Acked-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 3 ++- kernel/audit_tree.c | 3 ++- kernel/audit_watch.c | 3 ++- kernel/auditfilter.c | 15 +++++++++--- kernel/auditsc.c | 60 +++++++++++++++++++++++++++++++++++----------- 5 files changed, 64 insertions(+), 20 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index a1997697c8b1..ecf1edd2affa 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -167,8 +167,9 @@ #define AUDIT_FILTER_EXCLUDE 0x05 /* Apply rule before record creation */ #define AUDIT_FILTER_TYPE AUDIT_FILTER_EXCLUDE /* obsolete misleading naming */ #define AUDIT_FILTER_FS 0x06 /* Apply rule at __audit_inode_child */ +#define AUDIT_FILTER_URING_EXIT 0x07 /* Apply rule at io_uring op exit */ -#define AUDIT_NR_FILTERS 7 +#define AUDIT_NR_FILTERS 8 #define AUDIT_FILTER_PREPEND 0x10 /* Prepend to front of list */ diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 2cd7b5694422..338c53a961c5 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -726,7 +726,8 @@ int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) { if (pathname[0] != '/' || - rule->listnr != AUDIT_FILTER_EXIT || + (rule->listnr != AUDIT_FILTER_EXIT && + rule->listnr != AUDIT_FILTER_URING_EXIT) || op != Audit_equal || rule->inode_f || rule->watch || rule->tree) return -EINVAL; diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2acf7ca49154..698b62b4a2ec 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -183,7 +183,8 @@ int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op) return -EOPNOTSUPP; if (path[0] != '/' || path[len-1] == '/' || - krule->listnr != AUDIT_FILTER_EXIT || + (krule->listnr != AUDIT_FILTER_EXIT && + krule->listnr != AUDIT_FILTER_URING_EXIT) || op != Audit_equal || krule->inode_f || krule->watch || krule->tree) return -EINVAL; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index db2c6b59dfc3..d75acb014ccd 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -44,7 +44,8 @@ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), -#if AUDIT_NR_FILTERS != 7 + LIST_HEAD_INIT(audit_filter_list[7]), +#if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; @@ -56,6 +57,7 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), + LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); @@ -151,7 +153,8 @@ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { - if (krule->listnr != AUDIT_FILTER_EXIT || + if ((krule->listnr != AUDIT_FILTER_EXIT && + krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; @@ -248,6 +251,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data * pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: + case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: @@ -332,6 +336,10 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; + case AUDIT_PERM: + if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) + return -EINVAL; + break; } switch (entry->rule.listnr) { @@ -980,7 +988,8 @@ static inline int audit_add_rule(struct audit_entry *entry) } entry->rule.prio = ~0ULL; - if (entry->rule.listnr == AUDIT_FILTER_EXIT) { + if (entry->rule.listnr == AUDIT_FILTER_EXIT || + entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 6dda448fb826..3c9fb842a8f0 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -805,6 +805,34 @@ static int audit_in_mask(const struct audit_krule *rule, unsigned long val) return rule->mask[word] & bit; } +/** + * audit_filter_uring - apply filters to an io_uring operation + * @tsk: associated task + * @ctx: audit context + */ +static void audit_filter_uring(struct task_struct *tsk, + struct audit_context *ctx) +{ + struct audit_entry *e; + enum audit_state state; + + if (auditd_test_task(tsk)) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_URING_EXIT], + list) { + if (audit_in_mask(&e->rule, ctx->uring_op) && + audit_filter_rules(tsk, &e->rule, ctx, NULL, &state, + false)) { + rcu_read_unlock(); + ctx->current_state = state; + return; + } + } + rcu_read_unlock(); +} + /* At syscall exit time, this filter is called if the audit_state is * not low enough that auditing cannot take place, but is also not * high enough that we already know we have to write an audit record @@ -1757,7 +1785,7 @@ static void audit_log_exit(void) * __audit_free - free a per-task audit context * @tsk: task whose audit context block to free * - * Called from copy_process and do_exit + * Called from copy_process, do_exit, and the io_uring code */ void __audit_free(struct task_struct *tsk) { @@ -1775,15 +1803,21 @@ void __audit_free(struct task_struct *tsk) * random task_struct that doesn't doesn't have any meaningful data we * need to log via audit_log_exit(). */ - if (tsk == current && !context->dummy && - context->context == AUDIT_CTX_SYSCALL) { + if (tsk == current && !context->dummy) { context->return_valid = AUDITSC_INVALID; context->return_code = 0; - - audit_filter_syscall(tsk, context); - audit_filter_inodes(tsk, context); - if (context->current_state == AUDIT_STATE_RECORD) - audit_log_exit(); + if (context->context == AUDIT_CTX_SYSCALL) { + audit_filter_syscall(tsk, context); + audit_filter_inodes(tsk, context); + if (context->current_state == AUDIT_STATE_RECORD) + audit_log_exit(); + } else if (context->context == AUDIT_CTX_URING) { + /* TODO: verify this case is real and valid */ + audit_filter_uring(tsk, context); + audit_filter_inodes(tsk, context); + if (context->current_state == AUDIT_STATE_RECORD) + audit_log_uring(context); + } } audit_set_context(tsk, NULL); @@ -1867,12 +1901,6 @@ void __audit_uring_exit(int success, long code) { struct audit_context *ctx = audit_context(); - /* - * TODO: At some point we will likely want to filter on io_uring ops - * and other things similar to what we do for syscalls, but that - * is something for another day; just record what we can here. - */ - if (ctx->context == AUDIT_CTX_SYSCALL) { /* * NOTE: See the note in __audit_uring_entry() about the case @@ -1895,6 +1923,8 @@ void __audit_uring_exit(int success, long code) * the behavior here. */ audit_filter_syscall(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + audit_filter_uring(current, ctx); audit_filter_inodes(current, ctx); if (ctx->current_state != AUDIT_STATE_RECORD) return; @@ -1907,6 +1937,8 @@ void __audit_uring_exit(int success, long code) if (!list_empty(&ctx->killed_trees)) audit_kill_trees(ctx); + /* run through both filters to ensure we set the filterkey properly */ + audit_filter_uring(current, ctx); audit_filter_inodes(current, ctx); if (ctx->current_state != AUDIT_STATE_RECORD) goto out; -- cgit v1.2.3 From 50d7bd38c3aafc4749e05e8d7fcb616979143602 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 17 May 2021 20:01:15 -0700 Subject: stddef: Introduce struct_group() helper macro Kernel code has a regular need to describe groups of members within a structure usually when they need to be copied or initialized separately from the rest of the surrounding structure. The generally accepted design pattern in C is to use a named sub-struct: struct foo { int one; struct { int two; int three, four; } thing; int five; }; This would allow for traditional references and sizing: memcpy(&dst.thing, &src.thing, sizeof(dst.thing)); However, doing this would mean that referencing struct members enclosed by such named structs would always require including the sub-struct name in identifiers: do_something(dst.thing.three); This has tended to be quite inflexible, especially when such groupings need to be added to established code which causes huge naming churn. Three workarounds exist in the kernel for this problem, and each have other negative properties. To avoid the naming churn, there is a design pattern of adding macro aliases for the named struct: #define f_three thing.three This ends up polluting the global namespace, and makes it difficult to search for identifiers. Another common work-around in kernel code avoids the pollution by avoiding the named struct entirely, instead identifying the group's boundaries using either a pair of empty anonymous structs of a pair of zero-element arrays: struct foo { int one; struct { } start; int two; int three, four; struct { } finish; int five; }; struct foo { int one; int start[0]; int two; int three, four; int finish[0]; int five; }; This allows code to avoid needing to use a sub-struct named for member references within the surrounding structure, but loses the benefits of being able to actually use such a struct, making it rather fragile. Using these requires open-coded calculation of sizes and offsets. The efforts made to avoid common mistakes include lots of comments, or adding various BUILD_BUG_ON()s. Such code is left with no way for the compiler to reason about the boundaries (e.g. the "start" object looks like it's 0 bytes in length), making bounds checking depend on open-coded calculations: if (length > offsetof(struct foo, finish) - offsetof(struct foo, start)) return -EINVAL; memcpy(&dst.start, &src.start, offsetof(struct foo, finish) - offsetof(struct foo, start)); However, the vast majority of places in the kernel that operate on groups of members do so without any identification of the grouping, relying either on comments or implicit knowledge of the struct contents, which is even harder for the compiler to reason about, and results in even more fragile manual sizing, usually depending on member locations outside of the region (e.g. to copy "two" and "three", use the start of "four" to find the size): BUILD_BUG_ON((offsetof(struct foo, four) < offsetof(struct foo, two)) || (offsetof(struct foo, four) < offsetof(struct foo, three)); if (length > offsetof(struct foo, four) - offsetof(struct foo, two)) return -EINVAL; memcpy(&dst.two, &src.two, length); In order to have a regular programmatic way to describe a struct region that can be used for references and sizing, can be examined for bounds checking, avoids forcing the use of intermediate identifiers, and avoids polluting the global namespace, introduce the struct_group() macro. This macro wraps the member declarations to create an anonymous union of an anonymous struct (no intermediate name) and a named struct (for references and sizing): struct foo { int one; struct_group(thing, int two; int three, four; ); int five; }; if (length > sizeof(src.thing)) return -EINVAL; memcpy(&dst.thing, &src.thing, length); do_something(dst.three); There are some rare cases where the resulting struct_group() needs attributes added, so struct_group_attr() is also introduced to allow for specifying struct attributes (e.g. __align(x) or __packed). Additionally, there are places where such declarations would like to have the struct be tagged, so struct_group_tagged() is added. Given there is a need for a handful of UAPI uses too, the underlying __struct_group() macro has been defined in UAPI so it can be used there too. To avoid confusing scripts/kernel-doc, hide the macro from its struct parsing. Co-developed-by: Keith Packard Signed-off-by: Keith Packard Acked-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/20210728023217.GC35706@embeddedor Enhanced-by: Rasmus Villemoes Link: https://lore.kernel.org/lkml/41183a98-bdb9-4ad6-7eab-5a7292a6df84@rasmusvillemoes.dk Enhanced-by: Dan Williams Link: https://lore.kernel.org/lkml/1d9a2e6df2a9a35b2cdd50a9a68cac5991e7e5f0.camel@intel.com Enhanced-by: Daniel Vetter Link: https://lore.kernel.org/lkml/YQKa76A6XuFqgM03@phenom.ffwll.local Acked-by: Dan Williams Signed-off-by: Kees Cook --- include/linux/stddef.h | 48 +++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/stddef.h | 21 ++++++++++++++++++++ scripts/kernel-doc | 7 +++++++ 3 files changed, 76 insertions(+) (limited to 'include/uapi') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 8553b33143d1..8b103a53b000 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -36,4 +36,52 @@ enum { #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +/** + * struct_group() - Wrap a set of declarations in a mirrored struct + * + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. + */ +#define struct_group(NAME, MEMBERS...) \ + __struct_group(/* no tag */, NAME, /* no attrs */, MEMBERS) + +/** + * struct_group_attr() - Create a struct_group() with trailing attributes + * + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes to apply + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes structure attributes argument. + */ +#define struct_group_attr(NAME, ATTRS, MEMBERS...) \ + __struct_group(/* no tag */, NAME, ATTRS, MEMBERS) + +/** + * struct_group_tagged() - Create a struct_group with a reusable tag + * + * @TAG: The tag name for the named sub-struct + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes struct tag argument for the named copy, + * so the specified layout can be reused later. + */ +#define struct_group_tagged(TAG, NAME, MEMBERS...) \ + __struct_group(TAG, NAME, /* no attrs */, MEMBERS) + #endif diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index ee8220f8dcf5..610204f7c275 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -4,3 +4,24 @@ #ifndef __always_inline #define __always_inline inline #endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse, as well + * as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct TAG { MEMBERS } ATTRS NAME; \ + } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index cfcb60737957..38aa799a776c 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1245,6 +1245,13 @@ sub dump_struct($$) { $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; $members =~ s/\s*____cacheline_aligned/ /gos; + # unwrap struct_group(): + # - first eat non-declaration parameters and rewrite for final match + # - then remove macro, outer parens, and trailing semicolon + $members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos; + $members =~ s/\bstruct_group_(attr|tagged)\s*\(([^,]*,){2}/STRUCT_GROUP(/gos; + $members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos; + $members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos; my $args = qr{([^,)]+)}; # replace DECLARE_BITMAP -- cgit v1.2.3 From 10579b75e02362809e8db610f3160f520607b395 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 May 2021 23:55:11 -0700 Subject: drm/mga/mga_ioc32: Use struct_group() for memcpy() region In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use struct_group() in struct drm32_mga_init around members chipset, sgram, maccess, fb_cpp, front_offset, front_pitch, back_offset, back_pitch, depth_cpp, depth_offset, depth_pitch, texture_offset, and texture_size, so they can be referenced together. This will allow memcpy() and sizeof() to more easily reason about sizes, improve readability, and avoid future warnings about writing beyond the end of chipset. "pahole" shows no size nor member offset changes to struct drm32_mga_init. "objdump -d" shows no meaningful object code changes (i.e. only source line number induced differences and optimizations). Note that since this is a UAPI header, __struct_group() is used directly. Cc: David Airlie Cc: Lee Jones Cc: dri-devel@lists.freedesktop.org Signed-off-by: Kees Cook Acked-by: Daniel Vetter Link: https://lore.kernel.org/lkml/YQKa76A6XuFqgM03@phenom.ffwll.local --- drivers/gpu/drm/mga/mga_ioc32.c | 27 ++++++++++++++------------- include/uapi/drm/mga_drm.h | 22 ++++++++++++---------- 2 files changed, 26 insertions(+), 23 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/mga/mga_ioc32.c b/drivers/gpu/drm/mga/mga_ioc32.c index 4fd4de16cd32..894472921c30 100644 --- a/drivers/gpu/drm/mga/mga_ioc32.c +++ b/drivers/gpu/drm/mga/mga_ioc32.c @@ -38,16 +38,18 @@ typedef struct drm32_mga_init { int func; u32 sarea_priv_offset; - int chipset; - int sgram; - unsigned int maccess; - unsigned int fb_cpp; - unsigned int front_offset, front_pitch; - unsigned int back_offset, back_pitch; - unsigned int depth_cpp; - unsigned int depth_offset, depth_pitch; - unsigned int texture_offset[MGA_NR_TEX_HEAPS]; - unsigned int texture_size[MGA_NR_TEX_HEAPS]; + struct_group(always32bit, + int chipset; + int sgram; + unsigned int maccess; + unsigned int fb_cpp; + unsigned int front_offset, front_pitch; + unsigned int back_offset, back_pitch; + unsigned int depth_cpp; + unsigned int depth_offset, depth_pitch; + unsigned int texture_offset[MGA_NR_TEX_HEAPS]; + unsigned int texture_size[MGA_NR_TEX_HEAPS]; + ); u32 fb_offset; u32 mmio_offset; u32 status_offset; @@ -67,9 +69,8 @@ static int compat_mga_init(struct file *file, unsigned int cmd, init.func = init32.func; init.sarea_priv_offset = init32.sarea_priv_offset; - memcpy(&init.chipset, &init32.chipset, - offsetof(drm_mga_init_t, fb_offset) - - offsetof(drm_mga_init_t, chipset)); + memcpy(&init.always32bit, &init32.always32bit, + sizeof(init32.always32bit)); init.fb_offset = init32.fb_offset; init.mmio_offset = init32.mmio_offset; init.status_offset = init32.status_offset; diff --git a/include/uapi/drm/mga_drm.h b/include/uapi/drm/mga_drm.h index 8c4337548ab5..bb31567e66c0 100644 --- a/include/uapi/drm/mga_drm.h +++ b/include/uapi/drm/mga_drm.h @@ -279,20 +279,22 @@ typedef struct drm_mga_init { unsigned long sarea_priv_offset; - int chipset; - int sgram; + __struct_group(/* no tag */, always32bit, /* no attrs */, + int chipset; + int sgram; - unsigned int maccess; + unsigned int maccess; - unsigned int fb_cpp; - unsigned int front_offset, front_pitch; - unsigned int back_offset, back_pitch; + unsigned int fb_cpp; + unsigned int front_offset, front_pitch; + unsigned int back_offset, back_pitch; - unsigned int depth_cpp; - unsigned int depth_offset, depth_pitch; + unsigned int depth_cpp; + unsigned int depth_offset, depth_pitch; - unsigned int texture_offset[MGA_NR_TEX_HEAPS]; - unsigned int texture_size[MGA_NR_TEX_HEAPS]; + unsigned int texture_offset[MGA_NR_TEX_HEAPS]; + unsigned int texture_size[MGA_NR_TEX_HEAPS]; + ); unsigned long fb_offset; unsigned long mmio_offset; -- cgit v1.2.3 From e306784a8de08868d0ecbf78dd42a0051d0e14ce Mon Sep 17 00:00:00 2001 From: Subrat Mishra Date: Wed, 15 Sep 2021 11:22:23 +0530 Subject: cfg80211: AP mode driver offload for FILS association crypto Add a driver FILS crypto offload extended capability flag to indicate that the driver running in AP mode is capable of handling encryption and decryption of (Re)Association request and response frames. Add a command to set FILS AAD data to driver. This feature is supported on drivers running in AP mode only. This extended capability is exchanged with hostapd during cfg80211 init. If the driver indicates this capability, then before sending the Authentication response frame, hostapd sets FILS AAD data to the driver. This allows the driver to decrypt (Re)Association Request frame and encrypt (Re)Association Response frame. FILS Key derivation will still be done in hostapd. Signed-off-by: Subrat Mishra Link: https://lore.kernel.org/r/1631685143-13530-1-git-send-email-subratm@codeaurora.org [fix whitespace] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 22 ++++++++++++++++++++++ include/uapi/linux/nl80211.h | 37 +++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.c | 30 ++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 14 ++++++++++++++ net/wireless/trace.h | 31 +++++++++++++++++++++++++++++++ 5 files changed, 134 insertions(+) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 62dd8422e0dc..125f563d66a1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -739,6 +739,22 @@ struct cfg80211_tid_config { struct cfg80211_tid_cfg tid_conf[]; }; +/** + * struct cfg80211_fils_aad - FILS AAD data + * @macaddr: STA MAC address + * @kek: FILS KEK + * @kek_len: FILS KEK length + * @snonce: STA Nonce + * @anonce: AP Nonce + */ +struct cfg80211_fils_aad { + const u8 *macaddr; + const u8 *kek; + u8 kek_len; + const u8 *snonce; + const u8 *anonce; +}; + /** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition @@ -4018,6 +4034,10 @@ struct mgmt_frame_regs { * @set_sar_specs: Update the SAR (TX power) settings. * * @color_change: Initiate a color change. + * + * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use + * those to decrypt (Re)Association Request and encrypt (Re)Association + * Response frame. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4348,6 +4368,8 @@ struct cfg80211_ops { int (*color_change)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params); + int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_fils_aad *fils_aad); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c2efea98e060..e89bbf856228 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -300,6 +300,29 @@ * the interface goes down. */ +/** + * DOC: FILS shared key crypto offload + * + * This feature is applicable to drivers running in AP mode. + * + * FILS shared key crypto offload can be advertised by drivers by setting + * @NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD flag. The drivers that support + * FILS shared key crypto offload should be able to encrypt and decrypt + * association frames for FILS shared key authentication as per IEEE 802.11ai. + * With this capability, for FILS key derivation, drivers depend on userspace. + * + * After FILS key derivation, userspace shares the FILS AAD details with the + * driver and the driver stores the same to use in decryption of association + * request and in encryption of association response. The below parameters + * should be given to the driver in %NL80211_CMD_SET_FILS_AAD. + * %NL80211_ATTR_MAC - STA MAC address, used for storing FILS AAD per STA + * %NL80211_ATTR_FILS_KEK - Used for encryption or decryption + * %NL80211_ATTR_FILS_NONCES - Used for encryption or decryption + * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) + * + * Once the association is done, the driver cleans the FILS AAD data. + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -1200,6 +1223,12 @@ * @NL80211_CMD_COLOR_CHANGE_COMPLETED: Notify userland that the color change * has completed * + * @NL80211_CMD_SET_FILS_AAD: Set FILS AAD data to the driver using - + * &NL80211_ATTR_MAC - for STA MAC address + * &NL80211_ATTR_FILS_KEK - for KEK + * &NL80211_ATTR_FILS_NONCES - for FILS Nonces + * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1440,6 +1469,8 @@ enum nl80211_commands { NL80211_CMD_COLOR_CHANGE_ABORTED, NL80211_CMD_COLOR_CHANGE_COMPLETED, + NL80211_CMD_SET_FILS_AAD, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -5995,6 +6026,11 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_BSS_COLOR: The driver supports BSS color collision * detection and change announcemnts. * + * @NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD: Driver running in AP mode supports + * FILS encryption and decryption for (Re)Association Request and Response + * frames. Userspace has to share FILS AAD details to the driver by using + * @NL80211_CMD_SET_FILS_AAD. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6060,6 +6096,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SECURE_RTT, NL80211_EXT_FEATURE_PROT_RANGE_NEGO_AND_MEASURE, NL80211_EXT_FEATURE_BSS_COLOR, + NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0b4f29d689d2..d7c03f6145f0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14936,6 +14936,29 @@ out: return err; } +static int nl80211_set_fils_aad(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_fils_aad fils_aad = {}; + u8 *nonces; + + if (!info->attrs[NL80211_ATTR_MAC] || + !info->attrs[NL80211_ATTR_FILS_KEK] || + !info->attrs[NL80211_ATTR_FILS_NONCES]) + return -EINVAL; + + fils_aad.macaddr = nla_data(info->attrs[NL80211_ATTR_MAC]); + fils_aad.kek_len = nla_len(info->attrs[NL80211_ATTR_FILS_KEK]); + fils_aad.kek = nla_data(info->attrs[NL80211_ATTR_FILS_KEK]); + nonces = nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]); + fils_aad.snonce = nonces; + fils_aad.anonce = nonces + FILS_NONCE_LEN; + + return rdev_set_fils_aad(rdev, dev, &fils_aad); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -15937,6 +15960,13 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_FILS_AAD, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = nl80211_set_fils_aad, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index ce6bf218a1a3..cc1efec4b27b 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1381,4 +1381,18 @@ static inline int rdev_color_change(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_fils_aad(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct cfg80211_fils_aad *fils_aad) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_set_fils_aad(&rdev->wiphy, dev, fils_aad); + if (rdev->ops->set_fils_aad) + ret = rdev->ops->set_fils_aad(&rdev->wiphy, dev, fils_aad); + trace_rdev_return_int(&rdev->wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 19b78d472283..ad6c16a06bcb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -167,6 +167,19 @@ __entry->center_freq1, __entry->freq1_offset, \ __entry->center_freq2 +#define FILS_AAD_ASSIGN(fa) \ + do { \ + if (fa) { \ + ether_addr_copy(__entry->macaddr, fa->macaddr); \ + __entry->kek_len = fa->kek_len; \ + } else { \ + eth_zero_addr(__entry->macaddr); \ + __entry->kek_len = 0; \ + } \ + } while (0) +#define FILS_AAD_PR_FMT \ + "macaddr: %pM, kek_len: %d" + #define SINFO_ENTRY __field(int, generation) \ __field(u32, connected_time) \ __field(u32, inactive_time) \ @@ -2614,6 +2627,24 @@ DEFINE_EVENT(wiphy_wdev_cookie_evt, rdev_abort_pmsr, TP_ARGS(wiphy, wdev, cookie) ); +TRACE_EVENT(rdev_set_fils_aad, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_fils_aad *fils_aad), + TP_ARGS(wiphy, netdev, fils_aad), + TP_STRUCT__entry(WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, macaddr, ETH_ALEN) + __field(u8, kek_len) + ), + TP_fast_assign(WIPHY_ASSIGN; + NETDEV_ASSIGN; + FILS_AAD_ASSIGN(fils_aad); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " FILS_AAD_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr, + __entry->kek_len) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ -- cgit v1.2.3 From dc1e3cb8da8b414b37208b2fb6755fef8122504b Mon Sep 17 00:00:00 2001 From: John Crispin Date: Wed, 15 Sep 2021 19:54:34 -0700 Subject: nl80211: MBSSID and EMA support in AP mode Add new attributes to configure support for multiple BSSID and advanced multi-BSSID advertisements (EMA) in AP mode. - NL80211_ATTR_MBSSID_CONFIG used for per interface configuration. - NL80211_ATTR_MBSSID_ELEMS used to MBSSID elements for beacons. Memory for the elements is allocated dynamically. This change frees the memory in existing functions which call nl80211_parse_beacon(), a comment is added to indicate the new references to do the same. Signed-off-by: John Crispin Co-developed-by: Aloka Dixit Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/20210916025437.29138-2-alokad@codeaurora.org [don't leave ERR_PTR hanging around] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 44 +++++++++++ include/uapi/linux/nl80211.h | 76 +++++++++++++++++- net/wireless/nl80211.c | 178 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 293 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 125f563d66a1..e9e313aa991f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1056,6 +1056,36 @@ struct cfg80211_crypto_settings { enum nl80211_sae_pwe_mechanism sae_pwe; }; +/** + * struct cfg80211_mbssid_config - AP settings for multi bssid + * + * @tx_wdev: pointer to the transmitted interface in the MBSSID set + * @index: index of this AP in the multi bssid group. + * @ema: set to true if the beacons should be sent out in EMA mode. + */ +struct cfg80211_mbssid_config { + struct wireless_dev *tx_wdev; + u8 index; + bool ema; +}; + +/** + * struct cfg80211_mbssid_elems - Multiple BSSID elements + * + * @cnt: Number of elements in array %elems. + * + * @elem: Array of multiple BSSID element(s) to be added into Beacon frames. + * @elem.data: Data for multiple BSSID elements. + * @elem.len: Length of data. + */ +struct cfg80211_mbssid_elems { + u8 cnt; + struct { + const u8 *data; + size_t len; + } elem[]; +}; + /** * struct cfg80211_beacon_data - beacon data * @head: head portion of beacon (before TIM IE) @@ -1074,6 +1104,7 @@ struct cfg80211_crypto_settings { * @assocresp_ies_len: length of assocresp_ies in octets * @probe_resp_len: length of probe response template (@probe_resp) * @probe_resp: probe response template (AP mode only) + * @mbssid_ies: multiple BSSID elements * @ftm_responder: enable FTM responder functionality; -1 for no change * (which also implies no change in LCI/civic location data) * @lci: Measurement Report element content, starting with Measurement Token @@ -1091,6 +1122,7 @@ struct cfg80211_beacon_data { const u8 *probe_resp; const u8 *lci; const u8 *civicloc; + struct cfg80211_mbssid_elems *mbssid_ies; s8 ftm_responder; size_t head_len, tail_len; @@ -1205,6 +1237,7 @@ enum cfg80211_ap_settings_flags { * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters + * @mbssid_config: AP settings for multiple bssid */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1237,6 +1270,7 @@ struct cfg80211_ap_settings { struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; + struct cfg80211_mbssid_config mbssid_config; }; /** @@ -5003,6 +5037,13 @@ struct wiphy_iftype_akm_suites { * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities * @rfkill: a pointer to the rfkill structure + * + * @mbssid_max_interfaces: maximum number of interfaces supported by the driver + * in a multiple BSSID set. This field must be set to a non-zero value + * by the driver to advertise MBSSID support. + * @mbssid_max_ema_profile_periodicity: maximum profile periodicity supported by + * the driver. Setting this field to a non-zero value indicates that the + * driver supports enhanced multi-BSSID advertisements (EMA AP). */ struct wiphy { struct mutex mtx; @@ -5147,6 +5188,9 @@ struct wiphy { struct rfkill *rfkill; + u8 mbssid_max_interfaces; + u8 ema_max_profile_periodicity; + char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e89bbf856228..eda608b1eb09 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -360,7 +360,10 @@ * @NL80211_CMD_DEL_INTERFACE: Virtual interface was deleted, has attributes * %NL80211_ATTR_IFINDEX and %NL80211_ATTR_WIPHY. Can also be sent from * userspace to request deletion of a virtual interface, then requires - * attribute %NL80211_ATTR_IFINDEX. + * attribute %NL80211_ATTR_IFINDEX. If multiple BSSID advertisements are + * enabled using %NL80211_ATTR_MBSSID_CONFIG, %NL80211_ATTR_MBSSID_ELEMS, + * and if this command is used for the transmitting interface, then all + * the non-transmitting interfaces are deleted as well. * * @NL80211_CMD_GET_KEY: Get sequence counter information for a key specified * by %NL80211_ATTR_KEY_IDX and/or %NL80211_ATTR_MAC. @@ -2624,6 +2627,18 @@ enum nl80211_commands { * @NL80211_ATTR_COLOR_CHANGE_ELEMS: Nested set of attributes containing the IE * information for the time while performing a color switch. * + * @NL80211_ATTR_MBSSID_CONFIG: Nested attribute for multiple BSSID + * advertisements (MBSSID) parameters in AP mode. + * Kernel uses this attribute to indicate the driver's support for MBSSID + * and enhanced multi-BSSID advertisements (EMA AP) to the userspace. + * Userspace should use this attribute to configure per interface MBSSID + * parameters. + * See &enum nl80211_mbssid_config_attributes for details. + * + * @NL80211_ATTR_MBSSID_ELEMS: Nested parameter to pass multiple BSSID elements. + * Mandatory parameter for the transmitting interface to enable MBSSID. + * Optional for the non-transmitting interfaces. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3127,6 +3142,9 @@ enum nl80211_attrs { NL80211_ATTR_COLOR_CHANGE_COLOR, NL80211_ATTR_COLOR_CHANGE_ELEMS, + NL80211_ATTR_MBSSID_CONFIG, + NL80211_ATTR_MBSSID_ELEMS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -7386,4 +7404,60 @@ enum nl80211_sar_specs_attrs { NL80211_SAR_ATTR_SPECS_MAX = __NL80211_SAR_ATTR_SPECS_LAST - 1, }; +/** + * enum nl80211_mbssid_config_attributes - multiple BSSID (MBSSID) and enhanced + * multi-BSSID advertisements (EMA) in AP mode. + * Kernel uses some of these attributes to advertise driver's support for + * MBSSID and EMA. + * Remaining attributes should be used by the userspace to configure the + * features. + * + * @__NL80211_MBSSID_CONFIG_ATTR_INVALID: Invalid + * + * @NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES: Used by the kernel to advertise + * the maximum number of MBSSID interfaces supported by the driver. + * Driver should indicate MBSSID support by setting + * wiphy->mbssid_max_interfaces to a value more than or equal to 2. + * + * @NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY: Used by the kernel + * to advertise the maximum profile periodicity supported by the driver + * if EMA is enabled. Driver should indicate EMA support to the userspace + * by setting wiphy->mbssid_max_ema_profile_periodicity to + * a non-zero value. + * + * @NL80211_MBSSID_CONFIG_ATTR_INDEX: Mandatory parameter to pass the index of + * this BSS (u8) in the multiple BSSID set. + * Value must be set to 0 for the transmitting interface and non-zero for + * all non-transmitting interfaces. The userspace will be responsible + * for using unique indices for the interfaces. + * Range: 0 to wiphy->mbssid_max_interfaces-1. + * + * @NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX: Mandatory parameter for + * a non-transmitted profile which provides the interface index (u32) of + * the transmitted profile. The value must match one of the interface + * indices advertised by the kernel. Optional if the interface being set up + * is the transmitting one, however, if provided then the value must match + * the interface index of the same. + * + * @NL80211_MBSSID_CONFIG_ATTR_EMA: Flag used to enable EMA AP feature. + * Setting this flag is permitted only if the driver advertises EMA support + * by setting wiphy->mbssid_max_ema_profile_periodicity to non-zero. + * + * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal + * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute + */ +enum nl80211_mbssid_config_attributes { + __NL80211_MBSSID_CONFIG_ATTR_INVALID, + + NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES, + NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY, + NL80211_MBSSID_CONFIG_ATTR_INDEX, + NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX, + NL80211_MBSSID_CONFIG_ATTR_EMA, + + /* keep last */ + __NL80211_MBSSID_CONFIG_ATTR_LAST, + NL80211_MBSSID_CONFIG_ATTR_MAX = __NL80211_MBSSID_CONFIG_ATTR_LAST - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0f728de36f33..3f37e4d5c5d2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -437,6 +437,16 @@ sar_policy[NL80211_SAR_ATTR_MAX + 1] = { [NL80211_SAR_ATTR_SPECS] = NLA_POLICY_NESTED_ARRAY(sar_specs_policy), }; +static const struct nla_policy +nl80211_mbssid_config_policy[NL80211_MBSSID_CONFIG_ATTR_MAX + 1] = { + [NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES] = NLA_POLICY_MIN(NLA_U8, 2), + [NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY] = + NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_MBSSID_CONFIG_ATTR_INDEX] = { .type = NLA_U8 }, + [NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX] = { .type = NLA_U32 }, + [NL80211_MBSSID_CONFIG_ATTR_EMA] = { .type = NLA_FLAG }, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -763,6 +773,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_COLOR_CHANGE_COUNT] = { .type = NLA_U8 }, [NL80211_ATTR_COLOR_CHANGE_COLOR] = { .type = NLA_U8 }, [NL80211_ATTR_COLOR_CHANGE_ELEMS] = NLA_POLICY_NESTED(nl80211_policy), + [NL80211_ATTR_MBSSID_CONFIG] = + NLA_POLICY_NESTED(nl80211_mbssid_config_policy), + [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -2207,6 +2220,35 @@ fail: return -ENOBUFS; } +static int nl80211_put_mbssid_support(struct wiphy *wiphy, struct sk_buff *msg) +{ + struct nlattr *config; + + if (!wiphy->mbssid_max_interfaces) + return 0; + + config = nla_nest_start(msg, NL80211_ATTR_MBSSID_CONFIG); + if (!config) + return -ENOBUFS; + + if (nla_put_u8(msg, NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES, + wiphy->mbssid_max_interfaces)) + goto fail; + + if (wiphy->ema_max_profile_periodicity && + nla_put_u8(msg, + NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY, + wiphy->ema_max_profile_periodicity)) + goto fail; + + nla_nest_end(msg, config); + return 0; + +fail: + nla_nest_cancel(msg, config); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2792,6 +2834,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_put_sar_specs(rdev, msg)) goto nla_put_failure; + if (nl80211_put_mbssid_support(&rdev->wiphy, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -4981,6 +5026,96 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, return 0; } +static int nl80211_parse_mbssid_config(struct wiphy *wiphy, + struct net_device *dev, + struct nlattr *attrs, + struct cfg80211_mbssid_config *config, + u8 num_elems) +{ + struct nlattr *tb[NL80211_MBSSID_CONFIG_ATTR_MAX + 1]; + + if (!wiphy->mbssid_max_interfaces) + return -EOPNOTSUPP; + + if (nla_parse_nested(tb, NL80211_MBSSID_CONFIG_ATTR_MAX, attrs, NULL, + NULL) || + !tb[NL80211_MBSSID_CONFIG_ATTR_INDEX]) + return -EINVAL; + + config->ema = nla_get_flag(tb[NL80211_MBSSID_CONFIG_ATTR_EMA]); + if (config->ema) { + if (!wiphy->ema_max_profile_periodicity) + return -EOPNOTSUPP; + + if (num_elems > wiphy->ema_max_profile_periodicity) + return -EINVAL; + } + + config->index = nla_get_u8(tb[NL80211_MBSSID_CONFIG_ATTR_INDEX]); + if (config->index >= wiphy->mbssid_max_interfaces || + (!config->index && !num_elems)) + return -EINVAL; + + if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]) { + u32 tx_ifindex = + nla_get_u32(tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]); + + if ((!config->index && tx_ifindex != dev->ifindex) || + (config->index && tx_ifindex == dev->ifindex)) + return -EINVAL; + + if (tx_ifindex != dev->ifindex) { + struct net_device *tx_netdev = + dev_get_by_index(wiphy_net(wiphy), tx_ifindex); + + if (!tx_netdev || !tx_netdev->ieee80211_ptr || + tx_netdev->ieee80211_ptr->wiphy != wiphy || + tx_netdev->ieee80211_ptr->iftype != + NL80211_IFTYPE_AP) { + dev_put(tx_netdev); + return -EINVAL; + } + + config->tx_wdev = tx_netdev->ieee80211_ptr; + } else { + config->tx_wdev = dev->ieee80211_ptr; + } + } else if (!config->index) { + config->tx_wdev = dev->ieee80211_ptr; + } else { + return -EINVAL; + } + + return 0; +} + +static struct cfg80211_mbssid_elems * +nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) +{ + struct nlattr *nl_elems; + struct cfg80211_mbssid_elems *elems; + int rem_elems; + u8 i = 0, num_elems = 0; + + if (!wiphy->mbssid_max_interfaces) + return ERR_PTR(-EINVAL); + + nla_for_each_nested(nl_elems, attrs, rem_elems) + num_elems++; + + elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); + if (!elems) + return ERR_PTR(-ENOMEM); + + nla_for_each_nested(nl_elems, attrs, rem_elems) { + elems->elem[i].data = nla_data(nl_elems); + elems->elem[i].len = nla_len(nl_elems); + i++; + } + elems->cnt = num_elems; + return elems; +} + static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, struct nlattr *attrs[], struct cfg80211_beacon_data *bcn) @@ -5061,6 +5196,17 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, bcn->ftm_responder = -1; } + if (attrs[NL80211_ATTR_MBSSID_ELEMS]) { + struct cfg80211_mbssid_elems *mbssid = + nl80211_parse_mbssid_elems(&rdev->wiphy, + attrs[NL80211_ATTR_MBSSID_ELEMS]); + + if (IS_ERR(mbssid)) + return PTR_ERR(mbssid); + + bcn->mbssid_ies = mbssid; + } + return 0; } @@ -5547,6 +5693,17 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } + if (info->attrs[NL80211_ATTR_MBSSID_CONFIG]) { + err = nl80211_parse_mbssid_config(&rdev->wiphy, dev, + info->attrs[NL80211_ATTR_MBSSID_CONFIG], + ¶ms->mbssid_config, + params->beacon.mbssid_ies ? + params->beacon.mbssid_ies->cnt : + 0); + if (err) + goto out; + } + nl80211_calculate_ap_params(params); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -5568,6 +5725,11 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) out: kfree(params->acl); + kfree(params->beacon.mbssid_ies); + if (params->mbssid_config.tx_wdev && + params->mbssid_config.tx_wdev->netdev && + params->mbssid_config.tx_wdev->netdev != dev) + dev_put(params->mbssid_config.tx_wdev->netdev); kfree(params); return err; @@ -5593,12 +5755,14 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_beacon(rdev, info->attrs, ¶ms); if (err) - return err; + goto out; wdev_lock(wdev); err = rdev_change_beacon(rdev, dev, ¶ms); wdev_unlock(wdev); +out: + kfree(params.mbssid_ies); return err; } @@ -9275,12 +9439,14 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_beacon(rdev, info->attrs, ¶ms.beacon_after); if (err) - return err; + goto free; csa_attrs = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*csa_attrs), GFP_KERNEL); - if (!csa_attrs) - return -ENOMEM; + if (!csa_attrs) { + err = -ENOMEM; + goto free; + } err = nla_parse_nested_deprecated(csa_attrs, NL80211_ATTR_MAX, info->attrs[NL80211_ATTR_CSA_IES], @@ -9398,6 +9564,8 @@ skip_beacons: wdev_unlock(wdev); free: + kfree(params.beacon_after.mbssid_ies); + kfree(params.beacon_csa.mbssid_ies); kfree(csa_attrs); return err; } @@ -14933,6 +15101,8 @@ static int nl80211_color_change(struct sk_buff *skb, struct genl_info *info) wdev_unlock(wdev); out: + kfree(params.beacon_next.mbssid_ies); + kfree(params.beacon_color_change.mbssid_ies); kfree(tb); return err; } -- cgit v1.2.3 From 34268c9dde4cbae0b701b66c44497da068f418ee Mon Sep 17 00:00:00 2001 From: Gurchetan Singh Date: Tue, 21 Sep 2021 16:20:13 -0700 Subject: virtio-gpu api: multiple context types with explicit initialization This feature allows for each virtio-gpu 3D context to be created with a "context_init" variable. This variable can specify: - the type of protocol used by the context via the capset id. This is useful for differentiating virgl, gfxstream, and venus protocols by host userspace. - other things in the future, such as the version of the context. In addition, each different context needs one or more timelines, so for example a virgl context's waiting can be independent on a gfxstream context's waiting. VIRTIO_GPU_FLAG_INFO_RING_IDX is introduced to specific to tell the host which per-context command ring (or "hardware queue", distinct from the virtio-queue) the fence should be associated with. The new capability sets (gfxstream, venus etc.) are only defined in the virtio-gpu spec and not defined in the header. Signed-off-by: Gurchetan Singh Acked-by: Lingfeng Yang Link: http://patchwork.freedesktop.org/patch/msgid/20210921232024.817-2-gurchetansingh@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/linux/virtio_gpu.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 97523a95781d..f556fde07b76 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -59,6 +59,11 @@ * VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB */ #define VIRTIO_GPU_F_RESOURCE_BLOB 3 +/* + * VIRTIO_GPU_CMD_CREATE_CONTEXT with + * context_init and multiple timelines + */ +#define VIRTIO_GPU_F_CONTEXT_INIT 4 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -122,14 +127,20 @@ enum virtio_gpu_shm_id { VIRTIO_GPU_SHM_ID_HOST_VISIBLE = 1 }; -#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +/* + * If the following flag is set, then ring_idx contains the index + * of the command ring that needs to used when creating the fence + */ +#define VIRTIO_GPU_FLAG_INFO_RING_IDX (1 << 1) struct virtio_gpu_ctrl_hdr { __le32 type; __le32 flags; __le64 fence_id; __le32 ctx_id; - __le32 padding; + __u8 ring_idx; + __u8 padding[3]; }; /* data passed in the cursor vq */ @@ -269,10 +280,11 @@ struct virtio_gpu_resource_create_3d { }; /* VIRTIO_GPU_CMD_CTX_CREATE */ +#define VIRTIO_GPU_CONTEXT_INIT_CAPSET_ID_MASK 0x000000ff struct virtio_gpu_ctx_create { struct virtio_gpu_ctrl_hdr hdr; __le32 nlen; - __le32 padding; + __le32 context_init; char debug_name[64]; }; -- cgit v1.2.3 From b10790434cf2a40017bd796a99d5c4a6e949d616 Mon Sep 17 00:00:00 2001 From: Gurchetan Singh Date: Tue, 21 Sep 2021 16:20:14 -0700 Subject: drm/virtgpu api: create context init feature This change allows creating contexts of depending on set of context parameters. The meaning of each of the parameters is listed below: 1) VIRTGPU_CONTEXT_PARAM_CAPSET_ID This determines the type of a context based on the capability set ID. For example, the current capsets: VIRTIO_GPU_CAPSET_VIRGL VIRTIO_GPU_CAPSET_VIRGL2 define a Gallium, TGSI based "virgl" context. We only need 1 capset ID per context type, though virgl has two due a bug that has since been fixed. The use case is the "gfxstream" rendering library and "venus" renderer. gfxstream doesn't do Gallium/TGSI translation and mostly relies on auto-generated API streaming. Certain users prefer gfxstream over virgl for GLES on GLES emulation. {gfxstream vk}/{venus} are also required for Vulkan emulation. The maximum capset ID is 63. The goal is for guest userspace to choose the optimal context type depending on the situation/hardware. 2) VIRTGPU_CONTEXT_PARAM_NUM_RINGS This tells the number of independent command rings that the context will use. This value may be zero and is inferred to be zero if VIRTGPU_CONTEXT_PARAM_NUM_RINGS is not passed in. This is for backwards compatibility for virgl, which has one big giant command ring for all commands. The maxiumum number of rings is 64. In practice, multi-queue or multi-ring submission is used for powerful dGPUs and virtio-gpu may not be the best option in that case (see PCI passthrough or rendernode forwarding). 3) VIRTGPU_CONTEXT_PARAM_POLL_RING_IDX_MASK This is a mask of ring indices for which the DRM fd is pollable. For example, if VIRTGPU_CONTEXT_PARAM_NUM_RINGS is 2, then the mask may be: [ring idx] | [1 << ring_idx] | final mask ------------------------------------------- 0 1 1 1 2 3 The "Sommelier" guest Wayland proxy uses this to poll for events from the host compositor. Signed-off-by: Gurchetan Singh Acked-by: Lingfeng Yang Acked-by: Nicholas Verne Link: http://patchwork.freedesktop.org/patch/msgid/20210921232024.817-3-gurchetansingh@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/drm/virtgpu_drm.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index b9ec26e9c646..a13e20cc66b4 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -47,12 +47,15 @@ extern "C" { #define DRM_VIRTGPU_WAIT 0x08 #define DRM_VIRTGPU_GET_CAPS 0x09 #define DRM_VIRTGPU_RESOURCE_CREATE_BLOB 0x0a +#define DRM_VIRTGPU_CONTEXT_INIT 0x0b #define VIRTGPU_EXECBUF_FENCE_FD_IN 0x01 #define VIRTGPU_EXECBUF_FENCE_FD_OUT 0x02 +#define VIRTGPU_EXECBUF_RING_IDX 0x04 #define VIRTGPU_EXECBUF_FLAGS (\ VIRTGPU_EXECBUF_FENCE_FD_IN |\ VIRTGPU_EXECBUF_FENCE_FD_OUT |\ + VIRTGPU_EXECBUF_RING_IDX |\ 0) struct drm_virtgpu_map { @@ -68,6 +71,8 @@ struct drm_virtgpu_execbuffer { __u64 bo_handles; __u32 num_bo_handles; __s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */ + __u32 ring_idx; /* command ring index (see VIRTGPU_EXECBUF_RING_IDX) */ + __u32 pad; }; #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */ @@ -75,6 +80,8 @@ struct drm_virtgpu_execbuffer { #define VIRTGPU_PARAM_RESOURCE_BLOB 3 /* DRM_VIRTGPU_RESOURCE_CREATE_BLOB */ #define VIRTGPU_PARAM_HOST_VISIBLE 4 /* Host blob resources are mappable */ #define VIRTGPU_PARAM_CROSS_DEVICE 5 /* Cross virtio-device resource sharing */ +#define VIRTGPU_PARAM_CONTEXT_INIT 6 /* DRM_VIRTGPU_CONTEXT_INIT */ +#define VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs 7 /* Bitmask of supported capability set ids */ struct drm_virtgpu_getparam { __u64 param; @@ -173,6 +180,22 @@ struct drm_virtgpu_resource_create_blob { __u64 blob_id; }; +#define VIRTGPU_CONTEXT_PARAM_CAPSET_ID 0x0001 +#define VIRTGPU_CONTEXT_PARAM_NUM_RINGS 0x0002 +#define VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK 0x0003 +struct drm_virtgpu_context_set_param { + __u64 param; + __u64 value; +}; + +struct drm_virtgpu_context_init { + __u32 num_params; + __u32 pad; + + /* pointer to drm_virtgpu_context_set_param array */ + __u64 ctx_set_params; +}; + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) @@ -212,6 +235,10 @@ struct drm_virtgpu_resource_create_blob { DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_CREATE_BLOB, \ struct drm_virtgpu_resource_create_blob) +#define DRM_IOCTL_VIRTGPU_CONTEXT_INIT \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_CONTEXT_INIT, \ + struct drm_virtgpu_context_init) + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From 61bc346ce64a3864ac55f5d18bdc1572cda4fb18 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Wed, 25 Aug 2021 19:06:13 +0200 Subject: uapi/linux/prctl: provide macro definitions for the PR_SCHED_CORE type argument Commit 7ac592aa35a684ff ("sched: prctl() core-scheduling interface") made use of enum pid_type in prctl's arg4; this type and the associated enumeration definitions are not exposed to userspace. Christian has suggested to provide additional macro definitions that convey the meaning of the type argument more in alignment with its actual usage, and this patch does exactly that. Link: https://lore.kernel.org/r/20210825170613.GA3884@asgard.redhat.com Suggested-by: Christian Brauner Acked-by: Christian Brauner Signed-off-by: Eugene Syromiatnikov Complements: 7ac592aa35a684ff ("sched: prctl() core-scheduling interface") Signed-off-by: Christian Brauner --- Documentation/admin-guide/hw-vuln/core-scheduling.rst | 5 +++-- include/uapi/linux/prctl.h | 3 +++ kernel/sched/core_sched.c | 4 ++++ 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index 0febe458597c..cf1eeefdfc32 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -61,8 +61,9 @@ arg3: ``pid`` of the task for which the operation applies. arg4: - ``pid_type`` for which the operation applies. It is of type ``enum pid_type``. - For example, if arg4 is ``PIDTYPE_TGID``, then the operation of this command + ``pid_type`` for which the operation applies. It is one of + ``PR_SCHED_CORE_SCOPE_``-prefixed macro constants. For example, if arg4 + is ``PR_SCHED_CORE_SCOPE_THREAD_GROUP``, then the operation of this command will be performed for all tasks in the task group of ``pid``. arg5: diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 43bd7f713c39..b2e4dc1449b9 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -268,5 +268,8 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ # define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ # define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 9a80e9a474c0..20f640949450 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -134,6 +134,10 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, if (!static_branch_likely(&sched_smt_present)) return -ENODEV; + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD != PIDTYPE_PID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD_GROUP != PIDTYPE_TGID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_PROCESS_GROUP != PIDTYPE_PGID); + if (type > PIDTYPE_PGID || cmd >= PR_SCHED_CORE_MAX || pid < 0 || (cmd != PR_SCHED_CORE_GET && uaddr)) return -EINVAL; -- cgit v1.2.3 From b84f60a307f09debe30cc171b0f0a5c36797cf67 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:49 +0200 Subject: media: Rename V4L2_PIX_FMT_SUNXI_TILED_NV12 to V4L2_PIX_FMT_NV12_32L32 The V4L2_PIX_FMT_SUNXI_TILED_NV12 format is actually a fairly common NV12 tiled format, with 32x32 linear tiles. Rename the format and move its documentation together with the other tiled NV12 formats. Keep V4L2_PIX_FMT_SUNXI_TILED_NV12 for application compatibility. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 14 -------------- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 13 ++++++++++--- .../userspace-api/media/videodev2.h.rst.exceptions | 1 + drivers/media/v4l2-core/v4l2-ioctl.c | 2 +- drivers/staging/media/sunxi/cedrus/cedrus.c | 2 +- drivers/staging/media/sunxi/cedrus/cedrus_hw.c | 2 +- drivers/staging/media/sunxi/cedrus/cedrus_video.c | 4 ++-- include/uapi/linux/videodev2.h | 9 ++++++++- 8 files changed, 24 insertions(+), 23 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index 0b879c0da713..e762f911737a 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -246,20 +246,6 @@ please make a proposal on the linux-media mailing list. It is an opaque intermediate format and the MDP hardware must be used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``, ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``. - * .. _V4L2-PIX-FMT-SUNXI-TILED-NV12: - - - ``V4L2_PIX_FMT_SUNXI_TILED_NV12`` - - 'ST12' - - Two-planar NV12-based format used by the video engine found on Allwinner - (codenamed sunxi) platforms, with 32x32 tiles for the luminance plane - and 32x64 tiles for the chrominance plane. The data in each tile is - stored in linear order, within the tile bounds. Each tile follows the - previous one linearly in memory (from left to right, top to bottom). - - The associated buffer dimensions are aligned to match an integer number - of tiles, resulting in 32-aligned resolutions for the luminance plane - and 16-aligned resolutions for the chrominance plane (with 2x2 - subsampling). .. raw:: latex diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 090c091affd2..edeaf7628b28 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -254,14 +254,16 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: +.. _V4L2-PIX-FMT-NV12-32L32: -NV12MT and MV12MT_16X16 ------------------------ +Tiled NV12 +---------- Semi-planar YUV 4:2:0 formats, using macroblock tiling. The chroma plane is subsampled by 2 in each direction. Chroma lines contain half the number of pixels and the same number of bytes as luma lines, and the chroma plane -contains half the number of lines of the luma plane. +contains half the number of lines of the luma plane. Each tile follows the +previous one linearly in memory (from left to right, top to bottom). ``V4L2_PIX_FMT_NV12MT_16X16`` stores pixel in 2D 16x16 macroblocks, and stores macroblocks linearly in memory. The line stride and image height must be @@ -276,6 +278,11 @@ If the vertical resolution is an odd number of macroblocks, the last row of macroblocks is stored in linear order. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_32L32`` stores pixel in 32x32 tiles, and stores +tiles linearly in memory. The line stride and image height must be +aligned to a multiple of 32. The layouts of the luma and chroma planes are +identical. + .. _nv12mt: .. kernel-figure:: nv12mt.svg diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 2217b56c2686..982675a2342e 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -187,6 +187,7 @@ replace define V4L2_CAP_IO_MC device-capabilities # V4L2 pix flags replace define V4L2_PIX_FMT_PRIV_MAGIC :c:type:`v4l2_pix_format` replace define V4L2_PIX_FMT_FLAG_PREMUL_ALPHA format-flags +replace define V4L2_PIX_FMT_SUNXI_TILED_NV12 :c:type:`v4l2_pix_format` # V4L2 format flags replace define V4L2_FMT_FLAG_COMPRESSED fmtdesc-flags diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 05d5db3d85e5..ed194e9da7b0 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1282,6 +1282,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV21M: descr = "Y/CrCb 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV16M: descr = "Y/CbCr 4:2:2 (N-C)"; break; @@ -1415,7 +1416,6 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SE401: descr = "GSPCA SE401"; break; case V4L2_PIX_FMT_S5C_UYVY_JPG: descr = "S5C73MX interleaved UYVY/JPEG"; break; case V4L2_PIX_FMT_MT21C: descr = "Mediatek Compressed Format"; break; - case V4L2_PIX_FMT_SUNXI_TILED_NV12: descr = "Sunxi Tiled NV12 Format"; break; default: if (fmt->description[0]) return; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index 8114e2167013..144286920749 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -288,7 +288,7 @@ static int cedrus_open(struct file *file) ret = PTR_ERR(ctx->fh.m2m_ctx); goto err_ctrls; } - ctx->dst_fmt.pixelformat = V4L2_PIX_FMT_SUNXI_TILED_NV12; + ctx->dst_fmt.pixelformat = V4L2_PIX_FMT_NV12_32L32; cedrus_prepare_format(&ctx->dst_fmt); ctx->src_fmt.pixelformat = V4L2_PIX_FMT_MPEG2_SLICE; /* diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c index e2f2ff609c7e..2d7663726467 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c @@ -99,7 +99,7 @@ void cedrus_dst_format_set(struct cedrus_dev *dev, cedrus_write(dev, VE_PRIMARY_FB_LINE_STRIDE, reg); break; - case V4L2_PIX_FMT_SUNXI_TILED_NV12: + case V4L2_PIX_FMT_NV12_32L32: default: reg = VE_PRIMARY_OUT_FMT_TILED_32_NV12; cedrus_write(dev, VE_PRIMARY_OUT_FMT, reg); diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_video.c b/drivers/staging/media/sunxi/cedrus/cedrus_video.c index f3cd452575d4..ee7353086641 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_video.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_video.c @@ -56,7 +56,7 @@ static struct cedrus_format cedrus_formats[] = { .capabilities = CEDRUS_CAPABILITY_VP8_DEC, }, { - .pixelformat = V4L2_PIX_FMT_SUNXI_TILED_NV12, + .pixelformat = V4L2_PIX_FMT_NV12_32L32, .directions = CEDRUS_DECODE_DST, }, { @@ -124,7 +124,7 @@ void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt) sizeimage = max_t(u32, SZ_1K, sizeimage); break; - case V4L2_PIX_FMT_SUNXI_TILED_NV12: + case V4L2_PIX_FMT_NV12_32L32: /* 32-aligned stride. */ bytesperline = ALIGN(width, 32); diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9260791b8438..0188cd39468f 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -627,6 +627,9 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YUV444M v4l2_fourcc('Y', 'M', '2', '4') /* 24 YUV444 planar */ #define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24 YVU444 planar */ +/* Tiled YUV formats */ +#define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ + /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G', 'B', 'R', 'G') /* 8 GBGB.. RGRG.. */ @@ -734,7 +737,6 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Z16 v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */ #define V4L2_PIX_FMT_MT21C v4l2_fourcc('M', 'T', '2', '1') /* Mediatek compressed block mode */ #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ -#define V4L2_PIX_FMT_SUNXI_TILED_NV12 v4l2_fourcc('S', 'T', '1', '2') /* Sunxi Tiled NV12 Format */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ @@ -2615,4 +2617,9 @@ struct v4l2_create_buffers { #define BASE_VIDIOC_PRIVATE 192 /* 192-255 are private */ +/* Deprecated definitions kept for backwards compatibility */ +#ifndef __KERNEL__ +#define V4L2_PIX_FMT_SUNXI_TILED_NV12 V4L2_PIX_FMT_NV12_32L32 +#endif + #endif /* _UAPI__LINUX_VIDEODEV2_H */ -- cgit v1.2.3 From 78eee7b5f110c9884c8ffd1dfcdd9c29296f3e43 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:50 +0200 Subject: media: Rename V4L2_PIX_FMT_HM12 to V4L2_PIX_FMT_NV12_16L16 The V4L2_PIX_FMT_HM12 format is actually a simple NV12 tiled format, with 16x16 linear tiles. Rename the format and move its documentation together with the other tiled NV12 formats. Keep V4L2_PIX_FMT_HM12 for application compatibility. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/media/ivtv.rst | 2 +- Documentation/userspace-api/media/drivers/cx2341x-uapi.rst | 8 +++----- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 8 -------- Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst | 6 ++++++ Documentation/userspace-api/media/videodev2.h.rst.exceptions | 1 + drivers/media/pci/cx18/cx18-ioctl.c | 4 ++-- drivers/media/pci/cx18/cx18-streams.c | 8 ++++---- drivers/media/pci/ivtv/ivtv-ioctl.c | 8 ++++---- drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c | 10 +++++----- drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h | 2 +- drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c | 2 +- drivers/media/v4l2-core/v4l2-ioctl.c | 2 +- include/uapi/linux/videodev2.h | 3 ++- 13 files changed, 31 insertions(+), 33 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/admin-guide/media/ivtv.rst b/Documentation/admin-guide/media/ivtv.rst index 7b8775d20214..101f16d0263e 100644 --- a/Documentation/admin-guide/media/ivtv.rst +++ b/Documentation/admin-guide/media/ivtv.rst @@ -159,7 +159,7 @@ whatever). Otherwise the device numbers can get confusing. The ivtv Read-only The raw YUV video output from the current video input. The YUV format - is non-standard (V4L2_PIX_FMT_HM12). + is a 16x16 linear tiled NV12 format (V4L2_PIX_FMT_NV12_16L16) Note that the YUV and PCM streams are not synchronized, so they are of limited use. diff --git a/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst b/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst index 8a7977af79d5..debde65fb8cd 100644 --- a/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst +++ b/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst @@ -7,9 +7,7 @@ Non-compressed file format -------------------------- The cx23416 can produce (and the cx23415 can also read) raw YUV output. The -format of a YUV frame is specific to this chip and is called HM12. 'HM' stands -for 'Hauppauge Macroblock', which is a misnomer as 'Conexant Macroblock' would -be more accurate. +format of a YUV frame is 16x16 linear tiled NV12 (V4L2_PIX_FMT_NV12_16L16). The format is YUV 4:2:0 which uses 1 Y byte per pixel and 1 U and V byte per four pixels. @@ -34,8 +32,8 @@ second line of 8 UV pairs of the top-left block, etc. After transmitting this block the first line of the block on the right to the first block is transmitted, etc. -The code below is given as an example on how to convert HM12 to separate -Y, U and V planes. This code assumes frames of 720x576 (PAL) pixels. +The code below is given as an example on how to convert V4L2_PIX_FMT_NV12_16L16 +to separate Y, U and V planes. This code assumes frames of 720x576 (PAL) pixels. The width of a frame is always 720 pixels, regardless of the actual specified width. diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index e762f911737a..adcad9454175 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -48,14 +48,6 @@ please make a proposal on the linux-media mailing list. - ``V4L2_PIX_FMT_HI240`` - 'HI24' - 8 bit RGB format used by the BTTV driver. - * .. _V4L2-PIX-FMT-HM12: - - - ``V4L2_PIX_FMT_HM12`` - - 'HM12' - - YUV 4:2:0 format used by the IVTV driver. - - The format is documented in the kernel sources in the file - ``Documentation/userspace-api/media/drivers/cx2341x-uapi.rst`` * .. _V4L2-PIX-FMT-CPIA1: - ``V4L2_PIX_FMT_CPIA1`` diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index edeaf7628b28..884828f2272c 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -254,6 +254,7 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: +.. _V4L2-PIX-FMT-NV12-16L16: .. _V4L2-PIX-FMT-NV12-32L32: Tiled NV12 @@ -278,6 +279,11 @@ If the vertical resolution is an odd number of macroblocks, the last row of macroblocks is stored in linear order. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_16L16`` stores pixel in 16x16 tiles, and stores +tiles linearly in memory. The line stride and image height must be +aligned to a multiple of 16. The layouts of the luma and chroma planes are +identical. + ``V4L2_PIX_FMT_NV12_32L32`` stores pixel in 32x32 tiles, and stores tiles linearly in memory. The line stride and image height must be aligned to a multiple of 32. The layouts of the luma and chroma planes are diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 982675a2342e..eb0b1cd37abd 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -187,6 +187,7 @@ replace define V4L2_CAP_IO_MC device-capabilities # V4L2 pix flags replace define V4L2_PIX_FMT_PRIV_MAGIC :c:type:`v4l2_pix_format` replace define V4L2_PIX_FMT_FLAG_PREMUL_ALPHA format-flags +replace define V4L2_PIX_FMT_HM12 :c:type:`v4l2_pix_format` replace define V4L2_PIX_FMT_SUNXI_TILED_NV12 :c:type:`v4l2_pix_format` # V4L2 format flags diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c index 4864def20676..ce3f0141f94e 100644 --- a/drivers/media/pci/cx18/cx18-ioctl.c +++ b/drivers/media/pci/cx18/cx18-ioctl.c @@ -276,7 +276,7 @@ static int cx18_s_fmt_vid_cap(struct file *file, void *fh, s->pixelformat = fmt->fmt.pix.pixelformat; /* HM12 YUV size is (Y=(h*720) + UV=(h*(720/2))) UYUV YUV size is (Y=(h*720) + UV=(h*(720))) */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) { + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) { s->vb_bytes_per_frame = h * 720 * 3 / 2; s->vb_bytes_per_line = 720; /* First plane */ } else { @@ -470,7 +470,7 @@ static int cx18_enum_fmt_vid_cap(struct file *file, void *fh, .index = 0, .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .description = "HM12 (YUV 4:1:1)", - .pixelformat = V4L2_PIX_FMT_HM12, + .pixelformat = V4L2_PIX_FMT_NV12_16L16, }, { .index = 1, diff --git a/drivers/media/pci/cx18/cx18-streams.c b/drivers/media/pci/cx18/cx18-streams.c index c41bae118415..16d37ab48906 100644 --- a/drivers/media/pci/cx18/cx18-streams.c +++ b/drivers/media/pci/cx18/cx18-streams.c @@ -133,7 +133,7 @@ static int cx18_prepare_buffer(struct videobuf_queue *q, /* HM12 YUV size is (Y=(h*720) + UV=(h*(720/2))) UYUV YUV size is (Y=(h*720) + UV=(h*(720))) */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) s->vb_bytes_per_frame = height * 720 * 3 / 2; else s->vb_bytes_per_frame = height * 720 * 2; @@ -155,7 +155,7 @@ static int cx18_prepare_buffer(struct videobuf_queue *q, /* HM12 YUV size is (Y=(h*720) + UV=(h*(720/2))) UYUV YUV size is (Y=(h*720) + UV=(h*(720))) */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) s->vb_bytes_per_frame = height * 720 * 3 / 2; else s->vb_bytes_per_frame = height * 720 * 2; @@ -287,7 +287,7 @@ static void cx18_stream_init(struct cx18 *cx, int type) s, &cx->serialize_lock); /* Assume the previous pixel default */ - s->pixelformat = V4L2_PIX_FMT_HM12; + s->pixelformat = V4L2_PIX_FMT_NV12_16L16; s->vb_bytes_per_frame = cx->cxhdl.height * 720 * 3 / 2; s->vb_bytes_per_line = 720; } @@ -733,7 +733,7 @@ static void cx18_stream_configure_mdls(struct cx18_stream *s) * Set the MDL size to the exact size needed for one frame. * Use enough buffers per MDL to cover the MDL size */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) s->mdl_size = 720 * s->cx->cxhdl.height * 3 / 2; else s->mdl_size = 720 * s->cx->cxhdl.height * 2; diff --git a/drivers/media/pci/ivtv/ivtv-ioctl.c b/drivers/media/pci/ivtv/ivtv-ioctl.c index da19b2e95e6c..0cdf6b3210c2 100644 --- a/drivers/media/pci/ivtv/ivtv-ioctl.c +++ b/drivers/media/pci/ivtv/ivtv-ioctl.c @@ -339,7 +339,7 @@ static int ivtv_g_fmt_vid_cap(struct file *file, void *fh, struct v4l2_format *f pixfmt->colorspace = V4L2_COLORSPACE_SMPTE170M; pixfmt->field = V4L2_FIELD_INTERLACED; if (id->type == IVTV_ENC_STREAM_TYPE_YUV) { - pixfmt->pixelformat = V4L2_PIX_FMT_HM12; + pixfmt->pixelformat = V4L2_PIX_FMT_NV12_16L16; /* YUV size is (Y=(h*720) + UV=(h*(720/2))) */ pixfmt->sizeimage = pixfmt->height * 720 * 3 / 2; pixfmt->bytesperline = 720; @@ -417,7 +417,7 @@ static int ivtv_g_fmt_vid_out(struct file *file, void *fh, struct v4l2_format *f pixfmt->field = V4L2_FIELD_ANY; break; } - pixfmt->pixelformat = V4L2_PIX_FMT_HM12; + pixfmt->pixelformat = V4L2_PIX_FMT_NV12_16L16; pixfmt->bytesperline = 720; pixfmt->width = itv->yuv_info.v4l2_src_w; pixfmt->height = itv->yuv_info.v4l2_src_h; @@ -917,7 +917,7 @@ static int ivtv_enum_fmt_vid_cap(struct file *file, void *fh, struct v4l2_fmtdes static const struct v4l2_fmtdesc hm12 = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .description = "HM12 (YUV 4:2:0)", - .pixelformat = V4L2_PIX_FMT_HM12, + .pixelformat = V4L2_PIX_FMT_NV12_16L16, }; static const struct v4l2_fmtdesc mpeg = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, @@ -944,7 +944,7 @@ static int ivtv_enum_fmt_vid_out(struct file *file, void *fh, struct v4l2_fmtdes static const struct v4l2_fmtdesc hm12 = { .type = V4L2_BUF_TYPE_VIDEO_OUTPUT, .description = "HM12 (YUV 4:2:0)", - .pixelformat = V4L2_PIX_FMT_HM12, + .pixelformat = V4L2_PIX_FMT_NV12_16L16, }; static const struct v4l2_fmtdesc mpeg = { .type = V4L2_BUF_TYPE_VIDEO_OUTPUT, diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c index 08df0c833423..4b8d66fec3cf 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c @@ -61,7 +61,7 @@ bool sun6i_csi_is_format_supported(struct sun6i_csi *csi, || sdev->csi.v4l2_ep.bus_type == V4L2_MBUS_BT656) && sdev->csi.v4l2_ep.bus.parallel.bus_width == 16) { switch (pixformat) { - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_NV16: @@ -124,7 +124,7 @@ bool sun6i_csi_is_format_supported(struct sun6i_csi *csi, case V4L2_PIX_FMT_VYUY: return (mbus_code == MEDIA_BUS_FMT_VYUY8_2X8); - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_NV16: @@ -269,7 +269,7 @@ static enum csi_output_fmt get_csi_output_format(struct sun6i_csi_dev *sdev, case V4L2_PIX_FMT_VYUY: return buf_interlaced ? CSI_FRAME_RAW_8 : CSI_FIELD_RAW_8; - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: return buf_interlaced ? CSI_FRAME_MB_YUV420 : CSI_FIELD_MB_YUV420; case V4L2_PIX_FMT_NV12: @@ -311,7 +311,7 @@ static enum csi_input_seq get_csi_input_seq(struct sun6i_csi_dev *sdev, return 0; switch (pixformat) { - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV16: case V4L2_PIX_FMT_YUV420: @@ -526,7 +526,7 @@ static void sun6i_csi_set_window(struct sun6i_csi_dev *sdev) planar_offset[0] = 0; switch (config->pixelformat) { - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_NV16: diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h index c626821aaedb..3a38d107ae3f 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h @@ -105,7 +105,7 @@ static inline int sun6i_csi_get_bpp(unsigned int pixformat) case V4L2_PIX_FMT_SGBRG12: case V4L2_PIX_FMT_SGRBG12: case V4L2_PIX_FMT_SRGGB12: - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_YUV420: diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c index 07b2161392d2..33459892c1a9 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c @@ -48,7 +48,7 @@ static const u32 supported_pixformats[] = { V4L2_PIX_FMT_YVYU, V4L2_PIX_FMT_UYVY, V4L2_PIX_FMT_VYUY, - V4L2_PIX_FMT_HM12, + V4L2_PIX_FMT_NV12_16L16, V4L2_PIX_FMT_NV12, V4L2_PIX_FMT_NV21, V4L2_PIX_FMT_YUV420, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ed194e9da7b0..8731d65ad39e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1274,7 +1274,6 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_YUV410: descr = "Planar YUV 4:1:0"; break; case V4L2_PIX_FMT_YUV420: descr = "Planar YUV 4:2:0"; break; case V4L2_PIX_FMT_HI240: descr = "8-bit Dithered RGB (BTTV)"; break; - case V4L2_PIX_FMT_HM12: descr = "YUV 4:2:0 (16x16 Macroblocks)"; break; case V4L2_PIX_FMT_M420: descr = "YUV 4:2:0 (M420)"; break; case V4L2_PIX_FMT_NV12: descr = "Y/CbCr 4:2:0"; break; case V4L2_PIX_FMT_NV21: descr = "Y/CrCb 4:2:0"; break; @@ -1282,6 +1281,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_NV12_16L16: descr = "Y/CbCr 4:2:0 (16x16 Linear)"; break; case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV21M: descr = "Y/CrCb 4:2:0 (N-C)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 0188cd39468f..40fec00ce73a 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -601,7 +601,6 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV61 v4l2_fourcc('N', 'V', '6', '1') /* 16 Y/CrCb 4:2:2 */ #define V4L2_PIX_FMT_NV24 v4l2_fourcc('N', 'V', '2', '4') /* 24 Y/CbCr 4:4:4 */ #define V4L2_PIX_FMT_NV42 v4l2_fourcc('N', 'V', '4', '2') /* 24 Y/CrCb 4:4:4 */ -#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ /* two non contiguous planes - one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12M v4l2_fourcc('N', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 */ @@ -628,6 +627,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24 YVU444 planar */ /* Tiled YUV formats */ +#define V4L2_PIX_FMT_NV12_16L16 v4l2_fourcc('H', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ #define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ @@ -2619,6 +2619,7 @@ struct v4l2_create_buffers { /* Deprecated definitions kept for backwards compatibility */ #ifndef __KERNEL__ +#define V4L2_PIX_FMT_HM12 V4L2_PIX_FMT_NV12_16L16 #define V4L2_PIX_FMT_SUNXI_TILED_NV12 V4L2_PIX_FMT_NV12_32L32 #endif -- cgit v1.2.3 From 683f71ebb35d9223b4a22488e2eaffac30af104d Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:51 +0200 Subject: media: Add NV12_4L4 tiled format This format is produced by VeriSilicon Hantro G2 and VC8000D cores. It is a simple 4x4 tiling layout in a linear way. The pixel format was introduced by GStreamer using FourCC VT12, so let's stick to it. Link: https://gstreamer.freedesktop.org/documentation/video/video-format.html Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst | 6 ++++++ drivers/media/v4l2-core/v4l2-common.c | 3 +++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 4 files changed, 11 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 884828f2272c..0fc74351605a 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -254,6 +254,7 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: +.. _V4L2-PIX-FMT-NV12-4L4: .. _V4L2-PIX-FMT-NV12-16L16: .. _V4L2-PIX-FMT-NV12-32L32: @@ -279,6 +280,11 @@ If the vertical resolution is an odd number of macroblocks, the last row of macroblocks is stored in linear order. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_4L4`` stores pixel in 4x4 tiles, and stores +tiles linearly in memory. The line stride and image height must be +aligned to a multiple of 4. The layouts of the luma and chroma planes are +identical. + ``V4L2_PIX_FMT_NV12_16L16`` stores pixel in 16x16 tiles, and stores tiles linearly in memory. The line stride and image height must be aligned to a multiple of 16. The layouts of the luma and chroma planes are diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 04af03285a20..df34b2a283bc 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -275,6 +275,9 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) { .format = V4L2_PIX_FMT_YUV422P, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 }, { .format = V4L2_PIX_FMT_GREY, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 }, + /* Tiled YUV formats */ + { .format = V4L2_PIX_FMT_NV12_4L4, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 }, + /* YUV planar formats, non contiguous variant */ { .format = V4L2_PIX_FMT_YUV420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 }, { .format = V4L2_PIX_FMT_YVU420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 8731d65ad39e..ec6fc1ef291e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1281,6 +1281,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_NV12_4L4: descr = "Y/CbCr 4:2:0 (4x4 Linear)"; break; case V4L2_PIX_FMT_NV12_16L16: descr = "Y/CbCr 4:2:0 (16x16 Linear)"; break; case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 40fec00ce73a..56003a5467fc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -627,6 +627,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24 YVU444 planar */ /* Tiled YUV formats */ +#define V4L2_PIX_FMT_NV12_4L4 v4l2_fourcc('V', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 4x4 tiles */ #define V4L2_PIX_FMT_NV12_16L16 v4l2_fourcc('H', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ #define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ -- cgit v1.2.3 From 75b8f8f2646ccaf085a87983329be8e47bd8b6bc Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:52 +0200 Subject: media: Clean V4L2_PIX_FMT_NV12MT documentation Add more information about V4L2_PIX_FMT_NV12MT and V4L2_PIX_FMT_NV12M_16X16, so it's clearer for driver authors and users. Also, group the two pixel formats with the other tiled formats, for clarity. Unlike the recently introduced tiled formats (V4L2_PIX_FMT_NV12_4L4, etc) these formats have remained Samsung-specific until now. Therefore, and although the NV12MT and NV12MT_16X16 nomenclatures are less clear, we are keeping them as-is. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 25 +++++++++++----------- include/uapi/linux/videodev2.h | 6 ++++-- 2 files changed, 17 insertions(+), 14 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 0fc74351605a..3a09d93d405b 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -99,7 +99,7 @@ All components are stored with the same number of bits per component. - 4:2:0 - Cb, Cr - No - - 64x32 macroblocks + - 64x32 tiles Horizontal Z order * - V4L2_PIX_FMT_NV12MT_16X16 @@ -108,7 +108,7 @@ All components are stored with the same number of bits per component. - 4:2:2 - Cb, Cr - No - - 16x16 macroblocks + - 16x16 tiles * - V4L2_PIX_FMT_NV16 - 'NV16' - 8 @@ -267,17 +267,18 @@ pixels and the same number of bytes as luma lines, and the chroma plane contains half the number of lines of the luma plane. Each tile follows the previous one linearly in memory (from left to right, top to bottom). -``V4L2_PIX_FMT_NV12MT_16X16`` stores pixel in 2D 16x16 macroblocks, and stores -macroblocks linearly in memory. The line stride and image height must be -aligned to a multiple of 16. The layouts of the luma and chroma planes are -identical. +``V4L2_PIX_FMT_NV12MT_16X16`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores +pixels in 2D 16x16 tiles, and stores tiles linearly in memory. +The line stride and image height must be aligned to a multiple of 16. +The layouts of the luma and chroma planes are identical. -``V4L2_PIX_FMT_NV12MT`` stores pixels in 2D 64x32 macroblocks, and stores 2x2 -groups of macroblocks in Z-order in memory, alternating Z and mirrored Z shapes -horizontally. The line stride must be a multiple of 128 pixels to ensure an +``V4L2_PIX_FMT_NV12MT`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores +pixels in 2D 64x32 tiles, and stores 2x2 groups of tiles in +Z-order in memory, alternating Z and mirrored Z shapes horizontally. +The line stride must be a multiple of 128 pixels to ensure an integer number of Z shapes. The image height must be a multiple of 32 pixels. -If the vertical resolution is an odd number of macroblocks, the last row of -macroblocks is stored in linear order. The layouts of the luma and chroma +If the vertical resolution is an odd number of tiles, the last row of +tiles is stored in linear order. The layouts of the luma and chroma planes are identical. ``V4L2_PIX_FMT_NV12_4L4`` stores pixel in 4x4 tiles, and stores @@ -309,7 +310,7 @@ identical. :alt: nv12mt_example.svg :align: center - Example V4L2_PIX_FMT_NV12MT memory layout of macroblocks + Example V4L2_PIX_FMT_NV12MT memory layout of tiles .. _V4L2-PIX-FMT-NV16: diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 56003a5467fc..58392dcd3bf5 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -607,8 +607,6 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV21M v4l2_fourcc('N', 'M', '2', '1') /* 21 Y/CrCb 4:2:0 */ #define V4L2_PIX_FMT_NV16M v4l2_fourcc('N', 'M', '1', '6') /* 16 Y/CbCr 4:2:2 */ #define V4L2_PIX_FMT_NV61M v4l2_fourcc('N', 'M', '6', '1') /* 16 Y/CrCb 4:2:2 */ -#define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 macroblocks */ -#define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 macroblocks */ /* three planes - Y Cb, Cr */ #define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ @@ -631,6 +629,10 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV12_16L16 v4l2_fourcc('H', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ #define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ +/* Tiled YUV formats, non contiguous planes */ +#define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 tiles */ +#define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ + /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G', 'B', 'R', 'G') /* 8 GBGB.. RGRG.. */ -- cgit v1.2.3 From ffe5350c016a0de8ac77d32d9d4ea378cc9ff402 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Aug 2021 06:15:25 +0200 Subject: media: add Mediatek's MM21 format Add Mediatek's non-compressed 8 bit block video mode. This format is produced by the MT8183 codec and can be converted to a non-proprietary format by the MDP3 component. Signed-off-by: Alexandre Courbot Signed-off-by: Tzung-Bi Shih Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 7 +++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 9 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index adcad9454175..2f2133b4cd9c 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -238,6 +238,13 @@ please make a proposal on the linux-media mailing list. It is an opaque intermediate format and the MDP hardware must be used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``, ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``. + * .. _V4L2-PIX-FMT-MM21: + + - ``V4L2_PIX_FMT_MM21`` + - 'MM21' + - Non-compressed, tiled two-planar format used by Mediatek MT8183. + This is an opaque intermediate format and the MDP3 hardware can be + used to convert it to other formats. .. raw:: latex diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ec6fc1ef291e..d4f97ab1b237 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1348,6 +1348,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_TM6000: descr = "A/V + VBI Mux Packet"; break; case V4L2_PIX_FMT_CIT_YYVYUY: descr = "GSPCA CIT YYVYUY"; break; case V4L2_PIX_FMT_KONICA420: descr = "GSPCA KONICA420"; break; + case V4L2_PIX_FMT_MM21: descr = "Mediatek 8-bit Block Format"; break; case V4L2_PIX_FMT_HSV24: descr = "24-bit HSV 8-8-8"; break; case V4L2_PIX_FMT_HSV32: descr = "32-bit XHSV 8-8-8-8"; break; case V4L2_SDR_FMT_CU8: descr = "Complex U8"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 58392dcd3bf5..5cc9545feb40 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -739,6 +739,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Y12I v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */ #define V4L2_PIX_FMT_Z16 v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */ #define V4L2_PIX_FMT_MT21C v4l2_fourcc('M', 'T', '2', '1') /* Mediatek compressed block mode */ +#define V4L2_PIX_FMT_MM21 v4l2_fourcc('M', 'M', '2', '1') /* Mediatek 8-bit block mode, two non-contiguous planes */ #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ -- cgit v1.2.3 From a9c80593ff80ddb7c6496624e5384e1ea3460a72 Mon Sep 17 00:00:00 2001 From: David Plowman Date: Mon, 16 Aug 2021 13:39:08 +0200 Subject: media: v4l2-ctrls: Add V4L2_CID_NOTIFY_GAINS control We add a new control V4L2_CID_NOTIFY_GAINS which allows the sensor to be notified what gains will be applied to the different colour channels by subsequent processing (such as by an ISP), even though the sensor will not apply any of these gains itself. For Bayer sensors this will be an array control taking 4 values which are the 4 gains arranged in the fixed order B, Gb, Gr and R, irrespective of the exact Bayer order of the sensor itself. The use of an array makes it straightforward to extend this control to non-Bayer sensors (for example, sensors with an RGBW pattern) in future. The units are in all cases linear with the default value indicating a gain of exactly 1.0. For example, if the default value were reported as 128 then the value 192 would represent a gain of exactly 1.5. Signed-off-by: David Plowman Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls-defs.c | 1 + include/uapi/linux/v4l2-controls.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index eae300c58274..ebe82b6ba6e6 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -1108,6 +1108,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_TEST_PATTERN_GREENR: return "Green (Red) Pixel Value"; case V4L2_CID_TEST_PATTERN_BLUE: return "Blue Pixel Value"; case V4L2_CID_TEST_PATTERN_GREENB: return "Green (Blue) Pixel Value"; + case V4L2_CID_NOTIFY_GAINS: return "Notify Gains"; /* Image processing controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 5532b5f68493..133e20444939 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1118,6 +1118,7 @@ enum v4l2_jpeg_chroma_subsampling { #define V4L2_CID_TEST_PATTERN_BLUE (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 6) #define V4L2_CID_TEST_PATTERN_GREENB (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 7) #define V4L2_CID_UNIT_CELL_SIZE (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 8) +#define V4L2_CID_NOTIFY_GAINS (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 9) /* Image processing controls */ -- cgit v1.2.3 From 965c1e0bfeb66888fb000540c1fc4e8b55533d9c Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 9 Sep 2021 13:24:27 +0200 Subject: media: videobuf2: add V4L2_MEMORY_FLAG_NON_COHERENT flag By setting or clearing the V4L2_MEMORY_FLAG_NON_COHERENT flag user-space should be able to hint vb2 that either non-coherent (if supported) or coherent memory should be used for the buffer allocation. Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/buffer.rst | 40 ++++++++++++++++++++-- .../userspace-api/media/v4l/vidioc-reqbufs.rst | 5 +-- include/uapi/linux/videodev2.h | 2 ++ 3 files changed, 43 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst index e991ba73d873..4638ec64db00 100644 --- a/Documentation/userspace-api/media/v4l/buffer.rst +++ b/Documentation/userspace-api/media/v4l/buffer.rst @@ -676,8 +676,6 @@ Buffer Flags \normalsize -.. _memory-flags: - enum v4l2_memory ================ @@ -701,6 +699,44 @@ enum v4l2_memory - 4 - The buffer is used for :ref:`DMA shared buffer ` I/O. +.. _memory-flags: + +Memory Consistency Flags +------------------------ + +.. raw:: latex + + \small + +.. tabularcolumns:: |p{7.0cm}|p{2.1cm}|p{8.4cm}| + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 3 1 4 + + * .. _`V4L2-MEMORY-FLAG-NON-COHERENT`: + + - ``V4L2_MEMORY_FLAG_NON_COHERENT`` + - 0x00000001 + - A buffer is allocated either in coherent (it will be automatically + coherent between the CPU and the bus) or non-coherent memory. The + latter can provide performance gains, for instance the CPU cache + sync/flush operations can be avoided if the buffer is accessed by the + corresponding device only and the CPU does not read/write to/from that + buffer. However, this requires extra care from the driver -- it must + guarantee memory consistency by issuing a cache flush/sync when + consistency is needed. If this flag is set V4L2 will attempt to + allocate the buffer in non-coherent memory. The flag takes effect + only if the buffer is used for :ref:`memory mapping ` I/O and the + queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS + ` capability. + +.. raw:: latex + + \normalsize Timecodes ========= diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index 50ea72043bb0..e59306aba2b0 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -158,8 +158,9 @@ aborting or finishing any DMA in progress, an implicit - This capability is set by the driver to indicate that the queue supports cache and memory management hints. However, it's only valid when the queue is used for :ref:`memory mapping ` streaming I/O. See - :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE ` and - :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN `. + :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE `, + :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN ` and + :ref:`V4L2_MEMORY_FLAG_NON_COHERENT `. .. raw:: latex diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 5cc9545feb40..9b7032abb2c7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -962,6 +962,8 @@ struct v4l2_requestbuffers { __u32 reserved[1]; }; +#define V4L2_MEMORY_FLAG_NON_COHERENT (1 << 0) + /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */ #define V4L2_BUF_CAP_SUPPORTS_MMAP (1 << 0) #define V4L2_BUF_CAP_SUPPORTS_USERPTR (1 << 1) -- cgit v1.2.3 From c0acf9cfeee061f041fab778dbdcb34b6ca5e2e7 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 9 Sep 2021 13:24:29 +0200 Subject: media: videobuf2: handle V4L2_MEMORY_FLAG_NON_COHERENT flag This patch lets user-space request a non-coherent memory allocation during CREATE_BUFS and REQBUFS ioctl calls. = CREATE_BUFS struct v4l2_create_buffers has seven 4-byte reserved areas, so reserved[0] is renamed to ->flags. The struct, thus, now has six reserved 4-byte regions. = CREATE_BUFS32 struct v4l2_create_buffers32 has seven 4-byte reserved areas, so reserved[0] is renamed to ->flags. The struct, thus, now has six reserved 4-byte regions. = REQBUFS We use one byte of a 4 byte ->reserved[1] member of struct v4l2_requestbuffers. The struct, thus, now has reserved 3 bytes. Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/vidioc-create-bufs.rst | 7 ++++- .../userspace-api/media/v4l/vidioc-reqbufs.rst | 11 +++++--- drivers/media/common/videobuf2/videobuf2-core.c | 4 +-- drivers/media/common/videobuf2/videobuf2-v4l2.c | 31 +++++++++++++++++++--- drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 9 ++++++- drivers/media/v4l2-core/v4l2-ioctl.c | 4 +-- include/uapi/linux/videodev2.h | 9 +++++-- 7 files changed, 60 insertions(+), 15 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst index f98f18c9e91c..a048a9f6b7b6 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst @@ -113,7 +113,12 @@ than the number requested. ``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type. * - __u32 - - ``reserved``\ [7] + - ``flags`` + - Specifies additional buffer management attributes. + See :ref:`memory-flags`. + + * - __u32 + - ``reserved``\ [6] - A place holder for future extensions. Drivers and applications must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index e59306aba2b0..099fa6695167 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -104,10 +104,13 @@ aborting or finishing any DMA in progress, an implicit ``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will free any previously allocated buffers, so this is typically something that will be done at the start of the application. - * - __u32 - - ``reserved``\ [1] - - A place holder for future extensions. Drivers and applications - must set the array to zero. + * - __u8 + - ``flags`` + - Specifies additional buffer management attributes. + See :ref:`memory-flags`. + * - __u8 + - ``reserved``\ [3] + - Reserved for future extensions. .. _v4l2-buf-capabilities: .. _V4L2-BUF-CAP-SUPPORTS-MMAP: diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 60fb43b8f134..2266bbd239ab 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -761,7 +761,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, { unsigned int num_buffers, allocated_buffers, num_planes = 0; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool non_coherent_mem = false; + bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; unsigned int i; int ret; @@ -905,7 +905,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, { unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool non_coherent_mem = false; + bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; int ret; if (q->num_buffers == VB2_MAX_FRAME) { diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index b4f70ddb09b0..6edf4508c636 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -692,12 +692,32 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps) #endif } +static void validate_memory_flags(struct vb2_queue *q, + int memory, + u32 *flags) +{ + if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) { + /* + * This needs to clear V4L2_MEMORY_FLAG_NON_COHERENT only, + * but in order to avoid bugs we zero out all bits. + */ + *flags = 0; + } else { + /* Clear all unknown flags. */ + *flags &= V4L2_MEMORY_FLAG_NON_COHERENT; + } +} + int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) { int ret = vb2_verify_memory_type(q, req->memory, req->type); + u32 flags = req->flags; fill_buf_caps(q, &req->capabilities); - return ret ? ret : vb2_core_reqbufs(q, req->memory, 0, &req->count); + validate_memory_flags(q, req->memory, &flags); + req->flags = flags; + return ret ? ret : vb2_core_reqbufs(q, req->memory, + req->flags, &req->count); } EXPORT_SYMBOL_GPL(vb2_reqbufs); @@ -729,6 +749,7 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) unsigned i; fill_buf_caps(q, &create->capabilities); + validate_memory_flags(q, create->memory, &create->flags); create->index = q->num_buffers; if (create->count == 0) return ret != -EBUSY ? ret : 0; @@ -772,7 +793,7 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) if (requested_sizes[i] == 0) return -EINVAL; return ret ? ret : vb2_core_create_bufs(q, create->memory, - 0, + create->flags, &create->count, requested_planes, requested_sizes); @@ -969,13 +990,16 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv, { struct video_device *vdev = video_devdata(file); int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type); + u32 flags = p->flags; fill_buf_caps(vdev->queue, &p->capabilities); + validate_memory_flags(vdev->queue, p->memory, &flags); + p->flags = flags; if (res) return res; if (vb2_queue_is_busy(vdev, file)) return -EBUSY; - res = vb2_core_reqbufs(vdev->queue, p->memory, 0, &p->count); + res = vb2_core_reqbufs(vdev->queue, p->memory, p->flags, &p->count); /* If count == 0, then the owner has released all buffers and he is no longer owner of the queue. Otherwise we have a new owner. */ if (res == 0) @@ -993,6 +1017,7 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv, p->index = vdev->queue->num_buffers; fill_buf_caps(vdev->queue, &p->capabilities); + validate_memory_flags(vdev->queue, p->memory, &p->flags); /* * If count == 0, then just check if memory and type are valid. * Any -EBUSY result from vb2_verify_memory_type can be mapped to 0. diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 47aff3b19742..8176769a89fa 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -126,6 +126,9 @@ struct v4l2_format32 { * @memory: buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. + * @flags: additional buffer management attributes (ignored unless the + * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and + * configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers32 { @@ -134,7 +137,8 @@ struct v4l2_create_buffers32 { __u32 memory; /* enum v4l2_memory */ struct v4l2_format32 format; __u32 capabilities; - __u32 reserved[7]; + __u32 flags; + __u32 reserved[6]; }; static int get_v4l2_format32(struct v4l2_format *p64, @@ -182,6 +186,8 @@ static int get_v4l2_create32(struct v4l2_create_buffers *p64, if (copy_from_user(p64, p32, offsetof(struct v4l2_create_buffers32, format))) return -EFAULT; + if (copy_from_user(&p64->flags, &p32->flags, sizeof(p32->flags))) + return -EFAULT; return get_v4l2_format32(&p64->format, &p32->format); } @@ -227,6 +233,7 @@ static int put_v4l2_create32(struct v4l2_create_buffers *p64, if (copy_to_user(p32, p64, offsetof(struct v4l2_create_buffers32, format)) || put_user(p64->capabilities, &p32->capabilities) || + put_user(p64->flags, &p32->flags) || copy_to_user(p32->reserved, p64->reserved, sizeof(p64->reserved))) return -EFAULT; return put_v4l2_format32(&p64->format, &p32->format); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index bc83d23ce25d..31d0109ce5a8 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2024,7 +2024,7 @@ static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; - CLEAR_AFTER_FIELD(p, capabilities); + CLEAR_AFTER_FIELD(p, flags); return ops->vidioc_reqbufs(file, fh, p); } @@ -2065,7 +2065,7 @@ static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; - CLEAR_AFTER_FIELD(create, capabilities); + CLEAR_AFTER_FIELD(create, flags); v4l_sanitize_format(&create->format); diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9b7032abb2c7..f118fe7a9f58 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -959,7 +959,8 @@ struct v4l2_requestbuffers { __u32 type; /* enum v4l2_buf_type */ __u32 memory; /* enum v4l2_memory */ __u32 capabilities; - __u32 reserved[1]; + __u8 flags; + __u8 reserved[3]; }; #define V4L2_MEMORY_FLAG_NON_COHERENT (1 << 0) @@ -2507,6 +2508,9 @@ struct v4l2_dbg_chip_info { * @memory: enum v4l2_memory; buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. + * @flags: additional buffer management attributes (ignored unless the + * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability + * and configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2515,7 +2519,8 @@ struct v4l2_create_buffers { __u32 memory; struct v4l2_format format; __u32 capabilities; - __u32 reserved[7]; + __u32 flags; + __u32 reserved[6]; }; /* -- cgit v1.2.3 From 2bb2f5fb21b0486ff69b7b4a1fe03a760527d133 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 29 Sep 2021 10:25:11 -0700 Subject: net: add new socket option SO_RESERVE_MEM This socket option provides a mechanism for users to reserve a certain amount of memory for the socket to use. When this option is set, kernel charges the user specified amount of memory to memcg, as well as sk_forward_alloc. This amount of memory is not reclaimable and is available in sk_forward_alloc for this socket. With this socket option set, the networking stack spends less cycles doing forward alloc and reclaim, which should lead to better system performance, with the cost of an amount of pre-allocated and unreclaimable memory, even under memory pressure. Note: This socket option is only available when memory cgroup is enabled and we require this reserved memory to be charged to the user's memcg. We hope this could avoid mis-behaving users to abused this feature to reserve a large amount on certain sockets and cause unfairness for others. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 44 ++++++++++++++++++++++--- include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 69 +++++++++++++++++++++++++++++++++++++++ net/core/stream.c | 2 +- net/ipv4/af_inet.c | 2 +- 5 files changed, 112 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/net/sock.h b/include/net/sock.h index 879980de3dcd..447fddb384a4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -269,6 +269,7 @@ struct bpf_local_storage; * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward + * @sk_reserved_mem: space reserved and non-reclaimable for the socket * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode @@ -409,6 +410,7 @@ struct sock { #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; + u32 sk_reserved_mem; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; /* ===== mostly read cache line ===== */ @@ -1511,20 +1513,49 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) skb_pfmemalloc(skb); } +static inline int sk_unused_reserved_mem(const struct sock *sk) +{ + int unused_mem; + + if (likely(!sk->sk_reserved_mem)) + return 0; + + unused_mem = sk->sk_reserved_mem - sk->sk_wmem_queued - + atomic_read(&sk->sk_rmem_alloc); + + return unused_mem > 0 ? unused_mem : 0; +} + static inline void sk_mem_reclaim(struct sock *sk) { + int reclaimable; + if (!sk_has_account(sk)) return; - if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, sk->sk_forward_alloc); + + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); + + if (reclaimable >= SK_MEM_QUANTUM) + __sk_mem_reclaim(sk, reclaimable); +} + +static inline void sk_mem_reclaim_final(struct sock *sk) +{ + sk->sk_reserved_mem = 0; + sk_mem_reclaim(sk); } static inline void sk_mem_reclaim_partial(struct sock *sk) { + int reclaimable; + if (!sk_has_account(sk)) return; - if (sk->sk_forward_alloc > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1); + + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); + + if (reclaimable > SK_MEM_QUANTUM) + __sk_mem_reclaim(sk, reclaimable - 1); } static inline void sk_mem_charge(struct sock *sk, int size) @@ -1536,9 +1567,12 @@ static inline void sk_mem_charge(struct sock *sk, int size) static inline void sk_mem_uncharge(struct sock *sk, int size) { + int reclaimable; + if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; + reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); /* Avoid a possible overflow. * TCP send queues can make this happen, if sk_mem_reclaim() @@ -1547,7 +1581,7 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) * If we reach 2 MBytes, reclaim 1 MBytes right now, there is * no need to hold that much forward allocation anyway. */ - if (unlikely(sk->sk_forward_alloc >= 1 << 21)) + if (unlikely(reclaimable >= 1 << 21)) __sk_mem_reclaim(sk, 1 << 20); } diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 1f0a2b4864e4..c77a1313b3b0 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -126,6 +126,8 @@ #define SO_BUF_LOCK 72 +#define SO_RESERVE_MEM 73 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/core/sock.c b/net/core/sock.c index 512e629f9780..0ecb8590e043 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -947,6 +947,53 @@ void sock_set_mark(struct sock *sk, u32 val) } EXPORT_SYMBOL(sock_set_mark); +static void sock_release_reserved_memory(struct sock *sk, int bytes) +{ + /* Round down bytes to multiple of pages */ + bytes &= ~(SK_MEM_QUANTUM - 1); + + WARN_ON(bytes > sk->sk_reserved_mem); + sk->sk_reserved_mem -= bytes; + sk_mem_reclaim(sk); +} + +static int sock_reserve_memory(struct sock *sk, int bytes) +{ + long allocated; + bool charged; + int pages; + + if (!mem_cgroup_sockets_enabled || !sk->sk_memcg) + return -EOPNOTSUPP; + + if (!bytes) + return 0; + + pages = sk_mem_pages(bytes); + + /* pre-charge to memcg */ + charged = mem_cgroup_charge_skmem(sk->sk_memcg, pages, + GFP_KERNEL | __GFP_RETRY_MAYFAIL); + if (!charged) + return -ENOMEM; + + /* pre-charge to forward_alloc */ + allocated = sk_memory_allocated_add(sk, pages); + /* If the system goes into memory pressure with this + * precharge, give up and return error. + */ + if (allocated > sk_prot_mem_limits(sk, 1)) { + sk_memory_allocated_sub(sk, pages); + mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); + return -ENOMEM; + } + sk->sk_forward_alloc += pages << SK_MEM_QUANTUM_SHIFT; + + sk->sk_reserved_mem += pages << SK_MEM_QUANTUM_SHIFT; + + return 0; +} + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. @@ -1367,6 +1414,23 @@ set_sndbuf: ~SOCK_BUF_LOCK_MASK); break; + case SO_RESERVE_MEM: + { + int delta; + + if (val < 0) { + ret = -EINVAL; + break; + } + + delta = val - sk->sk_reserved_mem; + if (delta < 0) + sock_release_reserved_memory(sk, -delta); + else + ret = sock_reserve_memory(sk, delta); + break; + } + default: ret = -ENOPROTOOPT; break; @@ -1733,6 +1797,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; break; + case SO_RESERVE_MEM: + v.val = sk->sk_reserved_mem; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -2045,6 +2113,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; + newsk->sk_reserved_mem = 0; atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; diff --git a/net/core/stream.c b/net/core/stream.c index 4f1d4aa5fb38..e09ffd410685 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -202,7 +202,7 @@ void sk_stream_kill_queues(struct sock *sk) WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ - sk_mem_reclaim(sk); + sk_mem_reclaim_final(sk); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 40558033f857..2fc6074583a4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -135,7 +135,7 @@ void inet_sock_destruct(struct sock *sk) __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_error_queue); - sk_mem_reclaim(sk); + sk_mem_reclaim_final(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", -- cgit v1.2.3 From a70e3f024d5f4ec7edb17ab5d927eb55397f1d15 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 30 Sep 2021 14:21:04 -0700 Subject: devlink: report maximum number of snapshots with regions Each region has an independently configurable number of maximum snapshots. This information is not reported to userspace, making it not very discoverable. Fix this by adding a new DEVLINK_ATTR_REGION_MAX_SNAPSHOST attribute which is used to report this maximum. Ex: $devlink region pci/0000:af:00.0/nvm-flash: size 10485760 snapshot [] max 1 pci/0000:af:00.0/device-caps: size 4096 snapshot [] max 10 pci/0000:af:00.1/nvm-flash: size 10485760 snapshot [] max 1 pci/0000:af:00.1/device-caps: size 4096 snapshot [] max 10 This information enables users to understand why a new region command may fail due to having too many existing snapshots. Reported-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Jacob Keller Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-region.rst | 4 ++-- Documentation/networking/devlink/ice.rst | 4 ++++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 5 +++++ 4 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index 58fe95e9a49d..f06dca9a1eb6 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -44,8 +44,8 @@ example usage # Show all of the exposed regions with region sizes: $ devlink region show - pci/0000:00:05.0/cr-space: size 1048576 snapshot [1 2] - pci/0000:00:05.0/fw-health: size 64 snapshot [1 2] + pci/0000:00:05.0/cr-space: size 1048576 snapshot [1 2] max 8 + pci/0000:00:05.0/fw-health: size 64 snapshot [1 2] max 8 # Delete a snapshot using: $ devlink region del pci/0000:00:05.0/cr-space snapshot 1 diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index a432dc419fa4..32aea1f7d7f7 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -141,6 +141,10 @@ Users can request an immediate capture of a snapshot via the .. code:: shell + $ devlink region show + pci/0000:01:00.0/nvm-flash: size 10485760 snapshot [] max 1 + pci/0000:01:00.0/device-caps: size 4096 snapshot [] max 10 + $ devlink region new pci/0000:01:00.0/nvm-flash snapshot 1 $ devlink region dump pci/0000:01:00.0/nvm-flash snapshot 1 diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 32f53a0069d6..b897b80770f6 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -551,6 +551,8 @@ enum devlink_attr { DEVLINK_ATTR_RATE_NODE_NAME, /* string */ DEVLINK_ATTR_RATE_PARENT_NODE_NAME, /* string */ + DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index b64303085d0e..4917112406a0 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -5078,6 +5078,11 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, + region->max_snapshots); + if (err) + goto nla_put_failure; + err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; -- cgit v1.2.3 From 4bb2d367a5a2807185a04949ae922d247f650576 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 3 Sep 2021 13:00:32 +0000 Subject: drm/lease: allow empty leases MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This can be used to create a separate DRM file description, thus creating a new GEM handle namespace. My use-case is wlroots. The library splits responsibilities between separate components: the GBM allocator creates buffers, the GLES2 renderer uses EGL to import them and render to them, the DRM backend imports the buffers and displays them. wlroots has a modular architecture, and any of these components can be swapped and replaced with something else. For instance, the pipeline can be set up so that the DRM dumb buffer allocator is used instead of GBM and the Pixman renderer is used instead of GLES2. Library users can also replace any of these components with their own custom one. DMA-BUFs are used to pass buffer references across components. We could use GEM handles instead, but this would result in pain if multiple GPUs are in use: wlroots copies buffers across GPUs as needed. Importing a GEM handle created on one GPU into a completely different GPU will blow up (fail at best, mix unrelated buffers otherwise). Everything is fine if all components use Mesa. However, this isn't always desirable. For instance when running with DRM dumb buffers and the Pixman software renderer it's unfortunate to depend on GBM in the DRM backend just to turn DMA-BUFs into FB IDs. GBM loads Mesa drivers to perform an action which has nothing driver-specific. Additionally, drivers will fail the import if the 3D engine can't use the imported buffer, for instance amdgpu will refuse to import DRM dumb buffers [1]. We might also want to be running with a Vulkan renderer and a Vulkan allocator in the future, and GBM wouldn't be welcome in this setup. To address this, GBM can be side-stepped in the DRM backend, and can be replaced with drmPrimeFDToHandle calls. However because of GEM handle reference counting issues, care must be taken to avoid double-closing the same GEM handle. In particular, it's not possible to share a DRM FD with GBM or EGL and perform some drmPrimeFDToHandle calls manually. So wlroots needs to re-open the DRM FD to create a new GEM handle namespace. However there's no guarantee that the file-system permissions will be set up so that the primary FD can be opened by the compsoitor. On modern systems seatd or logind is a privileged process responsible for doing this, and other processes aren't expected to do it. For historical reasons systemd still allows physically logged in users to open primary DRM nodes, but this doesn't work on non-systemd setups and it's desirable to lock them down at some point. Some might suggest to open the render node instead of re-opening the primary node. However some systems don't have a render node at all (e.g. no GPU, or a split render/display SoC). Solutions to this issue have been discussed in [2]. One solution would be to open the magic /proc/self/fd/ file, but it's a Linux-specific hack (wlroots supports BSDs too). Another solution is to add support for re-opening a DRM primary node to seatd/logind, but they don't support it now and really haven't been designed for this (logind would need to grow a completely new API, because it assumes unique dev_t IDs). Also this seems like pushing down a kernel limitation to user-space a bit too hard. Another solution is to allow creating empty DRM leases. The lessee FD would have its own GEM handle namespace, so wouldn't conflict wth GBM/EGL. It would have the master bit set, but would be able to manage zero resources. wlroots doesn't intend to share this FD with any other process. All in all IMHO that seems like a pretty reasonable solution to the issue at hand. Note, I've discussed with Jonas Ådahl and Mutter plans to adopt a similar design in the future. Example usage in wlroots is available at [3]. IGT test available at [4]. [1]: https://github.com/swaywm/wlroots/issues/2916 [2]: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/110 [3]: https://github.com/swaywm/wlroots/pull/3158 [4]: https://patchwork.freedesktop.org/series/94323/ Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Daniel Stone Cc: Pekka Paalanen Cc: Michel Dänzer Cc: Emil Velikov Cc: Keith Packard Cc: Boris Brezillon Cc: Dave Airlie Acked-by: Pekka Paalanen Reviewed-by: Daniel Stone Link: https://patchwork.freedesktop.org/patch/msgid/20210903130000.1590-2-contact@emersion.fr --- drivers/gpu/drm/drm_lease.c | 39 ++++++++++++++++++--------------------- include/uapi/drm/drm_mode.h | 3 ++- 2 files changed, 20 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index dee4f24a1808..d72c2fac0ff1 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -489,12 +489,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; - /* need some objects */ - if (cl->object_count == 0) { - DRM_DEBUG_LEASE("no objects in lease\n"); - return -EINVAL; - } - if (cl->flags && (cl->flags & ~(O_CLOEXEC | O_NONBLOCK))) { DRM_DEBUG_LEASE("invalid flags\n"); return -EINVAL; @@ -510,23 +504,26 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, object_count = cl->object_count; - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), - array_size(object_count, sizeof(__u32))); - if (IS_ERR(object_ids)) { - ret = PTR_ERR(object_ids); - goto out_lessor; - } - + /* Handle leased objects, if any */ idr_init(&leases); + if (object_count != 0) { + object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), + array_size(object_count, sizeof(__u32))); + if (IS_ERR(object_ids)) { + ret = PTR_ERR(object_ids); + idr_destroy(&leases); + goto out_lessor; + } - /* fill and validate the object idr */ - ret = fill_object_idr(dev, lessor_priv, &leases, - object_count, object_ids); - kfree(object_ids); - if (ret) { - DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret); - idr_destroy(&leases); - goto out_lessor; + /* fill and validate the object idr */ + ret = fill_object_idr(dev, lessor_priv, &leases, + object_count, object_ids); + kfree(object_ids); + if (ret) { + DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret); + idr_destroy(&leases); + goto out_lessor; + } } /* Allocate a file descriptor for the lease */ diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index e4a2570a6058..e1e351682872 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -1112,7 +1112,8 @@ struct drm_mode_destroy_blob { * Lease mode resources, creating another drm_master. * * The @object_ids array must reference at least one CRTC, one connector and - * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. Alternatively, + * the lease can be completely empty. */ struct drm_mode_create_lease { /** @object_ids: Pointer to array of object ids (__u32) */ -- cgit v1.2.3 From 2c28ecad0d099ff914a0675f064db6e5b75e0756 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Mon, 27 Sep 2021 15:05:08 +0300 Subject: ASoC: SOF: topology: Add new token for dynamic pipeline Today, we set up all widgets required for all PCM streams at the time of topology parsing even if they are not used. An optimization would be to only set up the widgets required for currently active PCM streams. This would give the FW the opportunity to power gate unused memory blocks, thereby saving power. For dynamic pipelines, the widgets in the connected DAPM path for each PCM will need to be set up at runtime. This patch introduces a new token, DYNAMIC_PIPELINE, for scheduler type widgets that indicate whether a pipeline should be set up statically during topology load or at runtime when the PCM is opened. Introduce a new field called dynamic_pipeline_widget in struct snd_sof_widget to save the value of the parsed token. The token is set only for the pipeline (scheduler type) widget and must be propagated to all widgets in the same pipeline during topology load. Introduce another field called pipe_widget in struct snd_sof_widget that saves the pointer to the scheduler widget with the same pipeline ID as that of the widget. This field is populated when the pipeline completion callback is invoked during topology loading. Signed-off-by: Ranjani Sridharan Reviewed-by: Guennadi Liakhovetski Reviewed-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Signed-off-by: Daniel Baluta Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210927120517.20505-4-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/tokens.h | 1 + sound/soc/sof/sof-audio.h | 13 +++++++++ sound/soc/sof/topology.c | 62 ++++++++++++++++++++++++++++++++++++++++- 3 files changed, 75 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index a642bf30c027..02b71a8deea4 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -51,6 +51,7 @@ #define SOF_TKN_SCHED_CORE 203 #define SOF_TKN_SCHED_FRAMES 204 #define SOF_TKN_SCHED_TIME_DOMAIN 205 +#define SOF_TKN_SCHED_DYNAMIC_PIPELINE 206 /* volume */ #define SOF_TKN_VOLUME_RAMP_STEP_TYPE 250 diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index 78a4a0c90a29..4a1c38c5618d 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -81,6 +81,8 @@ struct snd_sof_control { bool comp_data_dirty; }; +struct snd_sof_widget; + /* ASoC SOF DAPM widget */ struct snd_sof_widget { struct snd_soc_component *scomp; @@ -90,8 +92,19 @@ struct snd_sof_widget { int core; int id; + /* + * Flag indicating if the widget should be set up dynamically when a PCM is opened. + * This flag is only set for the scheduler type widget in topology. During topology + * loading, this flag is propagated to all the widgets belonging to the same pipeline. + * When this flag is not set, a widget is set up at the time of topology loading + * and retained until the DSP enters D3. It will need to be set up again when resuming + * from D3. + */ + bool dynamic_pipeline_widget; + struct snd_soc_dapm_widget *widget; struct list_head list; /* list in sdev widget list */ + struct snd_sof_widget *pipe_widget; /* extended data for UUID components */ struct sof_ipc_comp_ext comp_ext; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index d8f7b1edefc3..60d1db6a9193 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -572,6 +572,12 @@ static const struct sof_topology_token sched_tokens[] = { offsetof(struct sof_ipc_pipe_new, time_domain), 0}, }; +static const struct sof_topology_token pipeline_tokens[] = { + {SOF_TKN_SCHED_DYNAMIC_PIPELINE, SND_SOC_TPLG_TUPLE_TYPE_BOOL, get_token_u16, + offsetof(struct snd_sof_widget, dynamic_pipeline_widget), 0}, + +}; + /* volume */ static const struct sof_topology_token volume_tokens[] = { {SOF_TKN_VOLUME_RAMP_STEP_TYPE, SND_SOC_TPLG_TUPLE_TYPE_WORD, @@ -1765,6 +1771,15 @@ static int sof_widget_load_pipeline(struct snd_soc_component *scomp, int index, goto err; } + ret = sof_parse_tokens(scomp, swidget, pipeline_tokens, + ARRAY_SIZE(pipeline_tokens), private->array, + le32_to_cpu(private->size)); + if (ret != 0) { + dev_err(scomp->dev, "error: parse dynamic pipeline token failed %d\n", + private->size); + goto err; + } + dev_dbg(scomp->dev, "pipeline %s: period %d pri %d mips %d core %d frames %d\n", swidget->widget->name, pipeline->period, pipeline->priority, pipeline->period_mips, pipeline->core, pipeline->frames_per_sched); @@ -3567,11 +3582,45 @@ int snd_sof_complete_pipeline(struct device *dev, return 1; } +/** + * sof_set_pipe_widget - Set pipe_widget for a component + * @sdev: pointer to struct snd_sof_dev + * @pipe_widget: pointer to struct snd_sof_widget of type snd_soc_dapm_scheduler + * @swidget: pointer to struct snd_sof_widget that has the same pipeline ID as @pipe_widget + * + * Return: 0 if successful, -EINVAL on error. + * The function checks if @swidget is associated with any volatile controls. If so, setting + * the dynamic_pipeline_widget is disallowed. + */ +static int sof_set_pipe_widget(struct snd_sof_dev *sdev, struct snd_sof_widget *pipe_widget, + struct snd_sof_widget *swidget) +{ + struct snd_sof_control *scontrol; + + if (pipe_widget->dynamic_pipeline_widget) { + /* dynamic widgets cannot have volatile kcontrols */ + list_for_each_entry(scontrol, &sdev->kcontrol_list, list) + if (scontrol->comp_id == swidget->comp_id && + (scontrol->access & SNDRV_CTL_ELEM_ACCESS_VOLATILE)) { + dev_err(sdev->dev, + "error: volatile control found for dynamic widget %s\n", + swidget->widget->name); + return -EINVAL; + } + } + + /* set the pipe_widget and apply the dynamic_pipeline_widget_flag */ + swidget->pipe_widget = pipe_widget; + swidget->dynamic_pipeline_widget = pipe_widget->dynamic_pipeline_widget; + + return 0; +} + /* completion - called at completion of firmware loading */ static int sof_complete(struct snd_soc_component *scomp) { struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp); - struct snd_sof_widget *swidget; + struct snd_sof_widget *swidget, *comp_swidget; int ret; /* some widget types require completion notificattion */ @@ -3586,6 +3635,17 @@ static int sof_complete(struct snd_soc_component *scomp) return ret; swidget->complete = ret; + + /* + * Apply the dynamic_pipeline_widget flag and set the pipe_widget field + * for all widgets that have the same pipeline ID as the scheduler widget + */ + list_for_each_entry_reverse(comp_swidget, &sdev->widget_list, list) + if (comp_swidget->pipeline_id == swidget->pipeline_id) { + ret = sof_set_pipe_widget(sdev, swidget, comp_swidget); + if (ret < 0) + return ret; + } break; default: break; -- cgit v1.2.3 From ef5825e3cf0d0af657f5fb4dd86d750ed42fee0a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 2 Sep 2021 11:14:47 +1000 Subject: NFSD: move filehandle format declarations out of "uapi". A small part of the declaration concerning filehandle format are currently in the "uapi" include directory: include/uapi/linux/nfsd/nfsfh.h There is a lot more to the filehandle format, including "enum fid_type" and "enum nfsd_fsid" which are not exported via "uapi". This small part of the filehandle definition is of minimal use outside of the kernel, and I can find no evidence that an other code is using it. Certainly nfs-utils and wireshark (The most likely candidates) do not use these declarations. So move it out of "uapi" by copying the content from include/uapi/linux/nfsd/nfsfh.h into fs/nfsd/nfsfh.h A few unnecessary "#include" directives are not copied, and neither is the #define of fh_auth, which is annotated as being for userspace only. The copyright claims in the uapi file are identical to those in the nfsd file, so there is no need to copy those. The "__u32" style integer types are only needed in "uapi". In kernel-only code we can use the more familiar "u32" style. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsfh.h | 97 ++++++++++++++++++++++++++++++++- fs/nfsd/vfs.c | 1 + include/uapi/linux/nfsd/nfsfh.h | 115 ---------------------------------------- 3 files changed, 97 insertions(+), 116 deletions(-) delete mode 100644 include/uapi/linux/nfsd/nfsfh.h (limited to 'include/uapi') diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 6106697adc04..ad47f16676a8 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -10,9 +10,104 @@ #include #include -#include #include #include +#include + + +/* + * This is the old "dentry style" Linux NFSv2 file handle. + * + * The xino and xdev fields are currently used to transport the + * ino/dev of the exported inode. + */ +struct nfs_fhbase_old { + u32 fb_dcookie; /* dentry cookie - always 0xfeebbaca */ + u32 fb_ino; /* our inode number */ + u32 fb_dirino; /* dir inode number, 0 for directories */ + u32 fb_dev; /* our device */ + u32 fb_xdev; + u32 fb_xino; + u32 fb_generation; +}; + +/* + * This is the new flexible, extensible style NFSv2/v3/v4 file handle. + * + * The file handle starts with a sequence of four-byte words. + * The first word contains a version number (1) and three descriptor bytes + * that tell how the remaining 3 variable length fields should be handled. + * These three bytes are auth_type, fsid_type and fileid_type. + * + * All four-byte values are in host-byte-order. + * + * The auth_type field is deprecated and must be set to 0. + * + * The fsid_type identifies how the filesystem (or export point) is + * encoded. + * Current values: + * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number + * NOTE: we cannot use the kdev_t device id value, because kdev_t.h + * says we mustn't. We must break it up and reassemble. + * 1 - 4 byte user specified identifier + * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED + * 3 - 4 byte device id, encoded for user-space, 4 byte inode number + * 4 - 4 byte inode number and 4 byte uuid + * 5 - 8 byte uuid + * 6 - 16 byte uuid + * 7 - 8 byte inode number and 16 byte uuid + * + * The fileid_type identified how the file within the filesystem is encoded. + * The values for this field are filesystem specific, exccept that + * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' + * in include/linux/exportfs.h for currently registered values. + */ +struct nfs_fhbase_new { + union { + struct { + u8 fb_version_aux; /* == 1, even => nfs_fhbase_old */ + u8 fb_auth_type_aux; + u8 fb_fsid_type_aux; + u8 fb_fileid_type_aux; + u32 fb_auth[1]; + /* u32 fb_fsid[0]; floating */ + /* u32 fb_fileid[0]; floating */ + }; + struct { + u8 fb_version; /* == 1, even => nfs_fhbase_old */ + u8 fb_auth_type; + u8 fb_fsid_type; + u8 fb_fileid_type; + u32 fb_auth_flex[]; /* flexible-array member */ + }; + }; +}; + +struct knfsd_fh { + unsigned int fh_size; /* significant for NFSv3. + * Points to the current size while building + * a new file handle + */ + union { + struct nfs_fhbase_old fh_old; + u32 fh_pad[NFS4_FHSIZE/4]; + struct nfs_fhbase_new fh_new; + } fh_base; +}; + +#define ofh_dcookie fh_base.fh_old.fb_dcookie +#define ofh_ino fh_base.fh_old.fb_ino +#define ofh_dirino fh_base.fh_old.fb_dirino +#define ofh_dev fh_base.fh_old.fb_dev +#define ofh_xdev fh_base.fh_old.fb_xdev +#define ofh_xino fh_base.fh_old.fb_xino +#define ofh_generation fh_base.fh_old.fb_generation + +#define fh_version fh_base.fh_new.fb_version +#define fh_fsid_type fh_base.fh_new.fb_fsid_type +#define fh_auth_type fh_base.fh_new.fb_auth_type +#define fh_fileid_type fh_base.fh_new.fb_fileid_type +#define fh_fsid fh_base.fh_new.fb_auth_flex static inline __u32 ino_t_to_u32(ino_t ino) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 738d564ca4ce..e9c406fd05b6 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -244,6 +244,7 @@ out_nfserr: * returned. Otherwise the covered directory is returned. * NOTE: this mountpoint crossing is not supported properly by all * clients and is explicitly disallowed for NFSv3 + * NeilBrown */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h deleted file mode 100644 index e29e8accc4f4..000000000000 --- a/include/uapi/linux/nfsd/nfsfh.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * This file describes the layout of the file handles as passed - * over the wire. - * - * Copyright (C) 1995, 1996, 1997 Olaf Kirch - */ - -#ifndef _UAPI_LINUX_NFSD_FH_H -#define _UAPI_LINUX_NFSD_FH_H - -#include -#include -#include -#include -#include - -/* - * This is the old "dentry style" Linux NFSv2 file handle. - * - * The xino and xdev fields are currently used to transport the - * ino/dev of the exported inode. - */ -struct nfs_fhbase_old { - __u32 fb_dcookie; /* dentry cookie - always 0xfeebbaca */ - __u32 fb_ino; /* our inode number */ - __u32 fb_dirino; /* dir inode number, 0 for directories */ - __u32 fb_dev; /* our device */ - __u32 fb_xdev; - __u32 fb_xino; - __u32 fb_generation; -}; - -/* - * This is the new flexible, extensible style NFSv2/v3/v4 file handle. - * - * The file handle starts with a sequence of four-byte words. - * The first word contains a version number (1) and three descriptor bytes - * that tell how the remaining 3 variable length fields should be handled. - * These three bytes are auth_type, fsid_type and fileid_type. - * - * All four-byte values are in host-byte-order. - * - * The auth_type field is deprecated and must be set to 0. - * - * The fsid_type identifies how the filesystem (or export point) is - * encoded. - * Current values: - * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number - * NOTE: we cannot use the kdev_t device id value, because kdev_t.h - * says we mustn't. We must break it up and reassemble. - * 1 - 4 byte user specified identifier - * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED - * 3 - 4 byte device id, encoded for user-space, 4 byte inode number - * 4 - 4 byte inode number and 4 byte uuid - * 5 - 8 byte uuid - * 6 - 16 byte uuid - * 7 - 8 byte inode number and 16 byte uuid - * - * The fileid_type identified how the file within the filesystem is encoded. - * The values for this field are filesystem specific, exccept that - * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' - * in include/linux/exportfs.h for currently registered values. - */ -struct nfs_fhbase_new { - union { - struct { - __u8 fb_version_aux; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type_aux; - __u8 fb_fsid_type_aux; - __u8 fb_fileid_type_aux; - __u32 fb_auth[1]; - /* __u32 fb_fsid[0]; floating */ - /* __u32 fb_fileid[0]; floating */ - }; - struct { - __u8 fb_version; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type; - __u8 fb_fsid_type; - __u8 fb_fileid_type; - __u32 fb_auth_flex[]; /* flexible-array member */ - }; - }; -}; - -struct knfsd_fh { - unsigned int fh_size; /* significant for NFSv3. - * Points to the current size while building - * a new file handle - */ - union { - struct nfs_fhbase_old fh_old; - __u32 fh_pad[NFS4_FHSIZE/4]; - struct nfs_fhbase_new fh_new; - } fh_base; -}; - -#define ofh_dcookie fh_base.fh_old.fb_dcookie -#define ofh_ino fh_base.fh_old.fb_ino -#define ofh_dirino fh_base.fh_old.fb_dirino -#define ofh_dev fh_base.fh_old.fb_dev -#define ofh_xdev fh_base.fh_old.fb_xdev -#define ofh_xino fh_base.fh_old.fb_xino -#define ofh_generation fh_base.fh_old.fb_generation - -#define fh_version fh_base.fh_new.fb_version -#define fh_fsid_type fh_base.fh_new.fb_fsid_type -#define fh_auth_type fh_base.fh_new.fb_auth_type -#define fh_fileid_type fh_base.fh_new.fb_fileid_type -#define fh_fsid fh_base.fh_new.fb_auth_flex - -/* Do not use, provided for userspace compatiblity. */ -#define fh_auth fh_base.fh_new.fb_auth - -#endif /* _UAPI_LINUX_NFSD_FH_H */ -- cgit v1.2.3 From bb3425efdcd99f2b4e608e850226f7107b2f993e Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Thu, 30 Sep 2021 17:18:50 +0100 Subject: drm/v3d: add generic ioctl extension Add support to attach generic extensions on job submission. This patch is third prep work to enable multiple syncobjs on job submission. With this work, when the job submission interface needs to be extended to accommodate a new feature, we will use a generic extension struct where an id determines the data type to be pointed. The first application is to enable multiples in/out syncobj (next patch), but the base is already done for future features. Therefore, to attach a new feature, a specific extension struct should subclass drm_v3d_extension and update the list of extensions in a job submission. v2: - remove redundant elements to subclass struct (Daniel) v3: - add comment for v3d_get_extensions Signed-off-by: Melissa Wen Reviewed-by: Iago Toral Quiroga Signed-off-by: Melissa Wen Link: https://patchwork.freedesktop.org/patch/msgid/ed53b1cd7e3125b76f18fe3fb995a04393639bc6.1633016479.git.mwen@igalia.com --- drivers/gpu/drm/v3d/v3d_drv.c | 4 +-- drivers/gpu/drm/v3d/v3d_gem.c | 74 +++++++++++++++++++++++++++++++++++++++++-- include/uapi/drm/v3d_drm.h | 31 ++++++++++++++++++ 3 files changed, 103 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index c1deab2cf38d..3d6b9bcce2f7 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -83,7 +83,6 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, return 0; } - switch (args->param) { case DRM_V3D_PARAM_SUPPORTS_TFU: args->value = 1; @@ -147,7 +146,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) DEFINE_DRM_GEM_FOPS(v3d_drm_fops); /* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP - * protection between clients. Note that render nodes would be be + * protection between clients. Note that render nodes would be * able to submit CLs that could access BOs from clients authenticated * with the master node. The TFU doesn't use the GMP, so it would * need to stay DRM_AUTH until we do buffer size/offset validation. @@ -219,7 +218,6 @@ static int v3d_platform_drm_probe(struct platform_device *pdev) u32 mmu_debug; u32 ident1; - v3d = devm_drm_dev_alloc(dev, &v3d_drm_driver, struct v3d_dev, drm); if (IS_ERR(v3d)) return PTR_ERR(v3d); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index f932e73fb5c6..93f130fb3a13 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -537,6 +537,36 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, } } +/* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data + * according to the extension id (name). + */ +static int +v3d_get_extensions(struct drm_file *file_priv, u64 ext_handles) +{ + struct drm_v3d_extension __user *user_ext; + + user_ext = u64_to_user_ptr(ext_handles); + while (user_ext) { + struct drm_v3d_extension ext; + + if (copy_from_user(&ext, user_ext, sizeof(ext))) { + DRM_DEBUG("Failed to copy submit extension\n"); + return -EFAULT; + } + + switch (ext.id) { + case 0: + default: + DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); + return -EINVAL; + } + + user_ext = u64_to_user_ptr(ext.next); + } + + return 0; +} + /** * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D. * @dev: DRM device @@ -565,15 +595,24 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end); - if (args->pad != 0) + if (args->pad) return -EINVAL; - if (args->flags != 0 && - args->flags != DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { + if (args->flags && + args->flags & ~(DRM_V3D_SUBMIT_CL_FLUSH_CACHE | + DRM_V3D_SUBMIT_EXTENSION)) { DRM_INFO("invalid flags: %d\n", args->flags); return -EINVAL; } + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + ret = v3d_job_init(v3d, file_priv, (void *)&render, sizeof(*render), v3d_render_job_free, args->in_sync_rcl, V3D_RENDER); if (ret) @@ -702,6 +741,19 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia); + if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { + DRM_DEBUG("invalid flags: %d\n", args->flags); + return -EINVAL; + } + + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), v3d_job_free, args->in_sync, V3D_TFU); if (ret) @@ -786,11 +838,27 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]); + if (args->pad) + return -EINVAL; + if (!v3d_has_csd(v3d)) { DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n"); return -EINVAL; } + if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { + DRM_INFO("invalid flags: %d\n", args->flags); + return -EINVAL; + } + + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), v3d_job_free, args->in_sync, V3D_CSD); if (ret) diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 4104f22fb3d3..55b443ca6c0b 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -58,6 +58,20 @@ extern "C" { struct drm_v3d_perfmon_get_values) #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 +#define DRM_V3D_SUBMIT_EXTENSION 0x02 + +/* struct drm_v3d_extension - ioctl extensions + * + * Linked-list of generic extensions where the id identify which struct is + * pointed by ext_data. Therefore, DRM_V3D_EXT_ID_* is used on id to identify + * the extension type. + */ +struct drm_v3d_extension { + __u64 next; + __u32 id; +#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 + __u32 flags; /* mbz */ +}; /** * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D @@ -135,12 +149,16 @@ struct drm_v3d_submit_cl { /* Number of BO handles passed in (size is that times 4). */ __u32 bo_handle_count; + /* DRM_V3D_SUBMIT_* properties */ __u32 flags; /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; __u32 pad; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; }; /** @@ -248,6 +266,12 @@ struct drm_v3d_submit_tfu { __u32 in_sync; /* Sync object to signal when the TFU job is done. */ __u32 out_sync; + + __u32 flags; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; + }; /* Submits a compute shader for dispatch. This job will block on any @@ -276,6 +300,13 @@ struct drm_v3d_submit_csd { /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; + + __u32 flags; + + __u32 pad; }; enum { -- cgit v1.2.3 From e4165ae8304e5ea822fbe5909dd3be5445c058b7 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Thu, 30 Sep 2021 17:19:56 +0100 Subject: drm/v3d: add multiple syncobjs support Using the generic extension from the previous patch, a specific multisync extension enables more than one in/out binary syncobj per job submission. Arrays of syncobjs are set in struct drm_v3d_multisync, that also cares of determining the stage for sync (wait deps) according to the job queue. v2: - subclass the generic extension struct (Daniel) - simplify adding dependency conditions to make understandable (Iago) v3: - fix conditions to consider single or multiples in/out_syncs (Iago) - remove irrelevant comment (Iago) Signed-off-by: Melissa Wen Reviewed-by: Iago Toral Quiroga Signed-off-by: Melissa Wen Link: https://patchwork.freedesktop.org/patch/msgid/ffd8b2e3dd2e0c686db441a0c0a4a0181ff85328.1633016479.git.mwen@igalia.com --- drivers/gpu/drm/v3d/v3d_drv.c | 6 +- drivers/gpu/drm/v3d/v3d_drv.h | 24 ++++-- drivers/gpu/drm/v3d/v3d_gem.c | 185 +++++++++++++++++++++++++++++++++++++----- include/uapi/drm/v3d_drm.h | 49 ++++++++++- 4 files changed, 232 insertions(+), 32 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 3d6b9bcce2f7..bd46396a1ae0 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -96,6 +96,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, case DRM_V3D_PARAM_SUPPORTS_PERFMON: args->value = (v3d->ver >= 40); return 0; + case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT: + args->value = 1; + return 0; default: DRM_DEBUG("Unknown parameter %d\n", args->param); return -EINVAL; @@ -135,9 +138,8 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) struct v3d_file_priv *v3d_priv = file->driver_priv; enum v3d_queue q; - for (q = 0; q < V3D_MAX_QUEUES; q++) { + for (q = 0; q < V3D_MAX_QUEUES; q++) drm_sched_entity_destroy(&v3d_priv->sched_entity[q]); - } v3d_perfmon_close_file(v3d_priv); kfree(v3d_priv); diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index b900a050d5e2..b74b1351bfc8 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -19,15 +19,6 @@ struct reset_control; #define GMP_GRANULARITY (128 * 1024) -/* Enum for each of the V3D queues. */ -enum v3d_queue { - V3D_BIN, - V3D_RENDER, - V3D_TFU, - V3D_CSD, - V3D_CACHE_CLEAN, -}; - #define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1) struct v3d_queue_state { @@ -294,6 +285,21 @@ struct v3d_csd_job { struct drm_v3d_submit_csd args; }; +struct v3d_submit_outsync { + struct drm_syncobj *syncobj; +}; + +struct v3d_submit_ext { + u32 flags; + u32 wait_stage; + + u32 in_sync_count; + u64 in_syncs; + + u32 out_sync_count; + struct v3d_submit_outsync *out_syncs; +}; + /** * __wait_for - magic wait macro * diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 93f130fb3a13..6a000d77c568 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -454,11 +454,12 @@ v3d_job_add_deps(struct drm_file *file_priv, struct v3d_job *job, static int v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, void **container, size_t size, void (*free)(struct kref *ref), - u32 in_sync, enum v3d_queue queue) + u32 in_sync, struct v3d_submit_ext *se, enum v3d_queue queue) { struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct v3d_job *job; - int ret; + bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); + int ret, i; *container = kcalloc(1, size, GFP_KERNEL); if (!*container) { @@ -479,9 +480,28 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, if (ret) goto fail_job; - ret = v3d_job_add_deps(file_priv, job, in_sync, 0); - if (ret) - goto fail_deps; + if (has_multisync) { + if (se->in_sync_count && se->wait_stage == queue) { + struct drm_v3d_sem __user *handle = u64_to_user_ptr(se->in_syncs); + + for (i = 0; i < se->in_sync_count; i++) { + struct drm_v3d_sem in; + + ret = copy_from_user(&in, handle++, sizeof(in)); + if (ret) { + DRM_DEBUG("Failed to copy wait dep handle.\n"); + goto fail_deps; + } + ret = v3d_job_add_deps(file_priv, job, in.handle, 0); + if (ret) + goto fail_deps; + } + } + } else { + ret = v3d_job_add_deps(file_priv, job, in_sync, 0); + if (ret) + goto fail_deps; + } kref_init(&job->refcount); @@ -516,9 +536,11 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, struct v3d_job *job, struct ww_acquire_ctx *acquire_ctx, u32 out_sync, + struct v3d_submit_ext *se, struct dma_fence *done_fence) { struct drm_syncobj *sync_out; + bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); int i; for (i = 0; i < job->bo_count; i++) { @@ -530,20 +552,130 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); /* Update the return sync object for the job */ - sync_out = drm_syncobj_find(file_priv, out_sync); - if (sync_out) { - drm_syncobj_replace_fence(sync_out, done_fence); - drm_syncobj_put(sync_out); + /* If it only supports a single signal semaphore*/ + if (!has_multisync) { + sync_out = drm_syncobj_find(file_priv, out_sync); + if (sync_out) { + drm_syncobj_replace_fence(sync_out, done_fence); + drm_syncobj_put(sync_out); + } + return; + } + + /* If multiple semaphores extension is supported */ + if (se->out_sync_count) { + for (i = 0; i < se->out_sync_count; i++) { + drm_syncobj_replace_fence(se->out_syncs[i].syncobj, + done_fence); + drm_syncobj_put(se->out_syncs[i].syncobj); + } + kvfree(se->out_syncs); + } +} + +static void +v3d_put_multisync_post_deps(struct v3d_submit_ext *se) +{ + unsigned int i; + + if (!(se && se->out_sync_count)) + return; + + for (i = 0; i < se->out_sync_count; i++) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); +} + +static int +v3d_get_multisync_post_deps(struct drm_file *file_priv, + struct v3d_submit_ext *se, + u32 count, u64 handles) +{ + struct drm_v3d_sem __user *post_deps; + int i, ret; + + if (!count) + return 0; + + se->out_syncs = (struct v3d_submit_outsync *) + kvmalloc_array(count, + sizeof(struct v3d_submit_outsync), + GFP_KERNEL); + if (!se->out_syncs) + return -ENOMEM; + + post_deps = u64_to_user_ptr(handles); + + for (i = 0; i < count; i++) { + struct drm_v3d_sem out; + + ret = copy_from_user(&out, post_deps++, sizeof(out)); + if (ret) { + DRM_DEBUG("Failed to copy post dep handles\n"); + goto fail; + } + + se->out_syncs[i].syncobj = drm_syncobj_find(file_priv, + out.handle); + if (!se->out_syncs[i].syncobj) { + ret = -EINVAL; + goto fail; + } } + se->out_sync_count = count; + + return 0; + +fail: + for (i--; i >= 0; i--) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); + + return ret; +} + +/* Get data for multiple binary semaphores synchronization. Parse syncobj + * to be signaled when job completes (out_sync). + */ +static int +v3d_get_multisync_submit_deps(struct drm_file *file_priv, + struct drm_v3d_extension __user *ext, + void *data) +{ + struct drm_v3d_multi_sync multisync; + struct v3d_submit_ext *se = data; + int ret; + + ret = copy_from_user(&multisync, ext, sizeof(multisync)); + if (ret) + return ret; + + if (multisync.pad) + return -EINVAL; + + ret = v3d_get_multisync_post_deps(file_priv, data, multisync.out_sync_count, + multisync.out_syncs); + if (ret) + return ret; + + se->in_sync_count = multisync.in_sync_count; + se->in_syncs = multisync.in_syncs; + se->flags |= DRM_V3D_EXT_ID_MULTI_SYNC; + se->wait_stage = multisync.wait_stage; + + return 0; } /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data * according to the extension id (name). */ static int -v3d_get_extensions(struct drm_file *file_priv, u64 ext_handles) +v3d_get_extensions(struct drm_file *file_priv, + u64 ext_handles, + void *data) { struct drm_v3d_extension __user *user_ext; + int ret; user_ext = u64_to_user_ptr(ext_handles); while (user_ext) { @@ -555,7 +687,11 @@ v3d_get_extensions(struct drm_file *file_priv, u64 ext_handles) } switch (ext.id) { - case 0: + case DRM_V3D_EXT_ID_MULTI_SYNC: + ret = v3d_get_multisync_submit_deps(file_priv, user_ext, data); + if (ret) + return ret; + break; default: DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); return -EINVAL; @@ -586,6 +722,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_cl *args = data; + struct v3d_submit_ext se = {0}; struct v3d_bin_job *bin = NULL; struct v3d_render_job *render = NULL; struct v3d_job *clean_job = NULL; @@ -606,7 +743,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions); + ret = v3d_get_extensions(file_priv, args->extensions, &se); if (ret) { DRM_DEBUG("Failed to get extensions.\n"); return ret; @@ -614,7 +751,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } ret = v3d_job_init(v3d, file_priv, (void *)&render, sizeof(*render), - v3d_render_job_free, args->in_sync_rcl, V3D_RENDER); + v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER); if (ret) goto fail; @@ -624,7 +761,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, if (args->bcl_start != args->bcl_end) { ret = v3d_job_init(v3d, file_priv, (void *)&bin, sizeof(*bin), - v3d_job_free, args->in_sync_bcl, V3D_BIN); + v3d_job_free, args->in_sync_bcl, &se, V3D_BIN); if (ret) goto fail; @@ -638,7 +775,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job), - v3d_job_free, 0, V3D_CACHE_CLEAN); + v3d_job_free, 0, 0, V3D_CACHE_CLEAN); if (ret) goto fail; @@ -698,6 +835,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, last_job, &acquire_ctx, args->out_sync, + &se, last_job->done_fence); if (bin) @@ -716,6 +854,7 @@ fail: v3d_job_cleanup((void *)bin); v3d_job_cleanup((void *)render); v3d_job_cleanup(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -735,6 +874,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, { struct v3d_dev *v3d = to_v3d_dev(dev); struct drm_v3d_submit_tfu *args = data; + struct v3d_submit_ext se = {0}; struct v3d_tfu_job *job = NULL; struct ww_acquire_ctx acquire_ctx; int ret = 0; @@ -747,7 +887,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions); + ret = v3d_get_extensions(file_priv, args->extensions, &se); if (ret) { DRM_DEBUG("Failed to get extensions.\n"); return ret; @@ -755,7 +895,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, } ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), - v3d_job_free, args->in_sync, V3D_TFU); + v3d_job_free, args->in_sync, &se, V3D_TFU); if (ret) goto fail; @@ -803,6 +943,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, v3d_attach_fences_and_unlock_reservation(file_priv, &job->base, &acquire_ctx, args->out_sync, + &se, job->base.done_fence); v3d_job_put(&job->base); @@ -811,6 +952,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, fail: v3d_job_cleanup((void *)job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -831,6 +973,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_csd *args = data; + struct v3d_submit_ext se = {0}; struct v3d_csd_job *job = NULL; struct v3d_job *clean_job = NULL; struct ww_acquire_ctx acquire_ctx; @@ -852,7 +995,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions); + ret = v3d_get_extensions(file_priv, args->extensions, &se); if (ret) { DRM_DEBUG("Failed to get extensions.\n"); return ret; @@ -860,12 +1003,12 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, } ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), - v3d_job_free, args->in_sync, V3D_CSD); + v3d_job_free, args->in_sync, &se, V3D_CSD); if (ret) goto fail; ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job), - v3d_job_free, 0, V3D_CACHE_CLEAN); + v3d_job_free, 0, 0, V3D_CACHE_CLEAN); if (ret) goto fail; @@ -904,6 +1047,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, clean_job, &acquire_ctx, args->out_sync, + &se, clean_job->done_fence); v3d_job_put(&job->base); @@ -918,6 +1062,7 @@ fail_unreserve: fail: v3d_job_cleanup((void *)job); v3d_job_cleanup(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 55b443ca6c0b..3dfc0af8756a 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -73,6 +73,53 @@ struct drm_v3d_extension { __u32 flags; /* mbz */ }; +/* struct drm_v3d_sem - wait/signal semaphore + * + * If binary semaphore, it only takes syncobj handle and ignores flags and + * point fields. Point is defined for timeline syncobj feature. + */ +struct drm_v3d_sem { + __u32 handle; /* syncobj */ + /* rsv below, for future uses */ + __u32 flags; + __u64 point; /* for timeline sem support */ + __u64 mbz[2]; /* must be zero, rsv */ +}; + +/* Enum for each of the V3D queues. */ +enum v3d_queue { + V3D_BIN, + V3D_RENDER, + V3D_TFU, + V3D_CSD, + V3D_CACHE_CLEAN, +}; + +/** + * struct drm_v3d_multi_sync - ioctl extension to add support multiples + * syncobjs for commands submission. + * + * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to + * this extension to define wait and signal dependencies, instead of single + * in/out sync entries on submitting commands. The field flags is used to + * determine the stage to set wait dependencies. + */ +struct drm_v3d_multi_sync { + struct drm_v3d_extension base; + /* Array of wait and signal semaphores */ + __u64 in_syncs; + __u64 out_syncs; + + /* Number of entries */ + __u32 in_sync_count; + __u32 out_sync_count; + + /* set the stage (v3d_queue) to sync */ + __u32 wait_stage; + + __u32 pad; /* mbz */ +}; + /** * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D * engine. @@ -228,6 +275,7 @@ enum drm_v3d_param { DRM_V3D_PARAM_SUPPORTS_CSD, DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH, DRM_V3D_PARAM_SUPPORTS_PERFMON, + DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT, }; struct drm_v3d_get_param { @@ -271,7 +319,6 @@ struct drm_v3d_submit_tfu { /* Pointer to an array of ioctl extensions*/ __u64 extensions; - }; /* Submits a compute shader for dispatch. This job will block on any -- cgit v1.2.3 From dea8ee31a039277576c215fffa13957970246366 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Mon, 27 Sep 2021 17:10:14 +0530 Subject: RISC-V: KVM: Add SBI v0.1 support The KVM host kernel is running in HS-mode needs so we need to handle the SBI calls coming from guest kernel running in VS-mode. This patch adds SBI v0.1 support in KVM RISC-V. Almost all SBI v0.1 calls are implemented in KVM kernel module except GETCHAR and PUTCHART calls which are forwarded to user space because these calls cannot be implemented in kernel space. In future, when we implement SBI v0.2 for Guest, we will forward SBI v0.2 experimental and vendor extension calls to user space. Signed-off-by: Atish Patra Signed-off-by: Anup Patel Acked-by: Paolo Bonzini Reviewed-by: Paolo Bonzini Acked-by: Palmer Dabbelt --- arch/riscv/include/asm/kvm_host.h | 10 +++ arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu.c | 9 ++ arch/riscv/kvm/vcpu_exit.c | 4 + arch/riscv/kvm/vcpu_sbi.c | 185 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 8 ++ 6 files changed, 217 insertions(+) create mode 100644 arch/riscv/kvm/vcpu_sbi.c (limited to 'include/uapi') diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index be159686da46..d7e1696cd2ec 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -74,6 +74,10 @@ struct kvm_mmio_decode { int return_handled; }; +struct kvm_sbi_context { + int return_handled; +}; + #define KVM_MMU_PAGE_CACHE_NR_OBJS 32 struct kvm_mmu_page_cache { @@ -186,6 +190,9 @@ struct kvm_vcpu_arch { /* MMIO instruction details */ struct kvm_mmio_decode mmio_decode; + /* SBI context */ + struct kvm_sbi_context sbi_context; + /* Cache pages needed to program page tables with spinlock held */ struct kvm_mmu_page_cache mmu_page_cache; @@ -253,4 +260,7 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask); void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run); + #endif /* __RISCV_KVM_HOST_H__ */ diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 4beb4e277e96..3226696b8340 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -21,4 +21,5 @@ kvm-y += mmu.o kvm-y += vcpu.o kvm-y += vcpu_exit.o kvm-y += vcpu_switch.o +kvm-y += vcpu_sbi.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 5acec47236c9..c44cabce7dd8 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -867,6 +867,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } } + /* Process SBI value returned from user-space */ + if (run->exit_reason == KVM_EXIT_RISCV_SBI) { + ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); + if (ret) { + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + return ret; + } + } + if (run->immediate_exit) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); return -EINTR; diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index f659be94231d..13bbc3f73713 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -678,6 +678,10 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = stage2_page_fault(vcpu, run, trap); break; + case EXC_SUPERVISOR_SYSCALL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) + ret = kvm_riscv_vcpu_sbi_ecall(vcpu, run); + break; default: break; }; diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c new file mode 100644 index 000000000000..ebdcdbade9c6 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0 +/** + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +#define SBI_VERSION_MAJOR 0 +#define SBI_VERSION_MINOR 1 + +static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, + struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + vcpu->arch.sbi_context.return_handled = 0; + vcpu->stat.ecall_exit_stat++; + run->exit_reason = KVM_EXIT_RISCV_SBI; + run->riscv_sbi.extension_id = cp->a7; + run->riscv_sbi.function_id = cp->a6; + run->riscv_sbi.args[0] = cp->a0; + run->riscv_sbi.args[1] = cp->a1; + run->riscv_sbi.args[2] = cp->a2; + run->riscv_sbi.args[3] = cp->a3; + run->riscv_sbi.args[4] = cp->a4; + run->riscv_sbi.args[5] = cp->a5; + run->riscv_sbi.ret[0] = cp->a0; + run->riscv_sbi.ret[1] = cp->a1; +} + +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + /* Handle SBI return only once */ + if (vcpu->arch.sbi_context.return_handled) + return 0; + vcpu->arch.sbi_context.return_handled = 1; + + /* Update return values */ + cp->a0 = run->riscv_sbi.ret[0]; + cp->a1 = run->riscv_sbi.ret[1]; + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += 4; + + return 0; +} + +#ifdef CONFIG_RISCV_SBI_V01 + +static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, + struct kvm_run *run, u32 type) +{ + int i; + struct kvm_vcpu *tmp; + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) + tmp->arch.power_off = true; + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); + + memset(&run->system_event, 0, sizeof(run->system_event)); + run->system_event.type = type; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + ulong hmask; + int i, ret = 1; + u64 next_cycle; + struct kvm_vcpu *rvcpu; + bool next_sepc = true; + struct cpumask cm, hm; + struct kvm *kvm = vcpu->kvm; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + if (!cp) + return -EINVAL; + + switch (cp->a7) { + case SBI_EXT_0_1_CONSOLE_GETCHAR: + case SBI_EXT_0_1_CONSOLE_PUTCHAR: + /* + * The CONSOLE_GETCHAR/CONSOLE_PUTCHAR SBI calls cannot be + * handled in kernel so we forward these to user-space + */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + next_sepc = false; + ret = 0; + break; + case SBI_EXT_0_1_SET_TIMER: +#if __riscv_xlen == 32 + next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; +#else + next_cycle = (u64)cp->a0; +#endif + kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + break; + case SBI_EXT_0_1_CLEAR_IPI: + kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_SOFT); + break; + case SBI_EXT_0_1_SEND_IPI: + if (cp->a0) + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, + &utrap); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap.scause) { + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + break; + } + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + } + break; + case SBI_EXT_0_1_SHUTDOWN: + kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN); + next_sepc = false; + ret = 0; + break; + case SBI_EXT_0_1_REMOTE_FENCE_I: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: + if (cp->a0) + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, + &utrap); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap.scause) { + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + break; + } + cpumask_clear(&cm); + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + if (rvcpu->cpu < 0) + continue; + cpumask_set_cpu(rvcpu->cpu, &cm); + } + riscv_cpuid_to_hartid_mask(&cm, &hm); + if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) + sbi_remote_fence_i(cpumask_bits(&hm)); + else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) + sbi_remote_hfence_vvma(cpumask_bits(&hm), + cp->a1, cp->a2); + else + sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), + cp->a1, cp->a2, cp->a3); + break; + default: + /* Return error for unsupported SBI calls */ + cp->a0 = SBI_ERR_NOT_SUPPORTED; + break; + }; + + if (next_sepc) + cp->sepc += 4; + + return ret; +} + +#else + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + return 0; +} + +#endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a067410ebea5..322b4b588d75 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -269,6 +269,7 @@ struct kvm_xen_exit { #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 +#define KVM_EXIT_RISCV_SBI 35 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -469,6 +470,13 @@ struct kvm_run { } msr; /* KVM_EXIT_XEN */ struct kvm_xen_exit xen; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; /* Fix the size of the union. */ char padding[256]; }; -- cgit v1.2.3 From 8cb3bf8bff3c47e171f6b66f9ccfc3f1451a11a2 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Sun, 3 Oct 2021 20:45:38 +0200 Subject: ipv6: ioam: Add support for the ip6ip6 encapsulation This patch adds support for the ip6ip6 encapsulation by providing three encap modes: inline, encap and auto. Signed-off-by: Justin Iurman Signed-off-by: David S. Miller --- include/uapi/linux/ioam6_iptunnel.h | 29 ++++ net/ipv6/Kconfig | 6 +- net/ipv6/ioam6_iptunnel.c | 261 +++++++++++++++++++++++++++++------- 3 files changed, 242 insertions(+), 54 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index bae14636a8c8..829ffdfcacca 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -9,9 +9,38 @@ #ifndef _UAPI_LINUX_IOAM6_IPTUNNEL_H #define _UAPI_LINUX_IOAM6_IPTUNNEL_H +/* Encap modes: + * - inline: direct insertion + * - encap: ip6ip6 encapsulation + * - auto: inline for local packets, encap for in-transit packets + */ +enum { + __IOAM6_IPTUNNEL_MODE_MIN, + + IOAM6_IPTUNNEL_MODE_INLINE, + IOAM6_IPTUNNEL_MODE_ENCAP, + IOAM6_IPTUNNEL_MODE_AUTO, + + __IOAM6_IPTUNNEL_MODE_MAX, +}; + +#define IOAM6_IPTUNNEL_MODE_MIN (__IOAM6_IPTUNNEL_MODE_MIN + 1) +#define IOAM6_IPTUNNEL_MODE_MAX (__IOAM6_IPTUNNEL_MODE_MAX - 1) + enum { IOAM6_IPTUNNEL_UNSPEC, + + /* Encap mode */ + IOAM6_IPTUNNEL_MODE, /* u8 */ + + /* Tunnel dst address. + * For encap,auto modes. + */ + IOAM6_IPTUNNEL_DST, /* struct in6_addr */ + + /* IOAM Trace Header */ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + __IOAM6_IPTUNNEL_MAX, }; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index e504204bca92..bf2e5e5fe142 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -332,10 +332,10 @@ config IPV6_IOAM6_LWTUNNEL bool "IPv6: IOAM Pre-allocated Trace insertion support" depends on IPV6 select LWTUNNEL + select DST_CACHE help - Support for the inline insertion of IOAM Pre-allocated - Trace Header (only on locally generated packets), using - the lightweight tunnels mechanism. + Support for the insertion of IOAM Pre-allocated Trace + Header using the lightweight tunnels mechanism. If unsure, say N. diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 5d03101724b9..392c183076ce 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -17,6 +17,10 @@ #include #include #include +#include +#include +#include +#include #define IOAM6_MASK_SHORT_FIELDS 0xff100000 #define IOAM6_MASK_WIDE_FIELDS 0xe00000 @@ -29,6 +33,9 @@ struct ioam6_lwt_encap { } __packed; struct ioam6_lwt { + struct dst_cache cache; + u8 mode; + struct in6_addr tundst; struct ioam6_lwt_encap tuninfo; }; @@ -48,6 +55,10 @@ static struct ioam6_trace_hdr *ioam6_lwt_trace(struct lwtunnel_state *lwt) } static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { + [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, + IOAM6_IPTUNNEL_MODE_MIN, + IOAM6_IPTUNNEL_MODE_MAX), + [IOAM6_IPTUNNEL_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), }; @@ -78,9 +89,10 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1]; struct ioam6_lwt_encap *tuninfo; struct ioam6_trace_hdr *trace; - struct lwtunnel_state *s; - int len_aligned; - int len, err; + struct lwtunnel_state *lwt; + struct ioam6_lwt *ilwt; + int len_aligned, err; + u8 mode; if (family != AF_INET6) return -EINVAL; @@ -90,6 +102,16 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, if (err < 0) return err; + if (!tb[IOAM6_IPTUNNEL_MODE]) + mode = IOAM6_IPTUNNEL_MODE_INLINE; + else + mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]); + + if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) { + NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination"); + return -EINVAL; + } + if (!tb[IOAM6_IPTUNNEL_TRACE]) { NL_SET_ERR_MSG(extack, "missing trace"); return -EINVAL; @@ -102,15 +124,24 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, return -EINVAL; } - len = sizeof(*tuninfo) + trace->remlen * 4; - len_aligned = ALIGN(len, 8); - - s = lwtunnel_state_alloc(len_aligned); - if (!s) + len_aligned = ALIGN(trace->remlen * 4, 8); + lwt = lwtunnel_state_alloc(sizeof(*ilwt) + len_aligned); + if (!lwt) return -ENOMEM; - tuninfo = ioam6_lwt_info(s); - tuninfo->eh.hdrlen = (len_aligned >> 3) - 1; + ilwt = ioam6_lwt_state(lwt); + err = dst_cache_init(&ilwt->cache, GFP_ATOMIC); + if (err) { + kfree(lwt); + return err; + } + + ilwt->mode = mode; + if (tb[IOAM6_IPTUNNEL_DST]) + ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); + + tuninfo = ioam6_lwt_info(lwt); + tuninfo->eh.hdrlen = ((sizeof(*tuninfo) + len_aligned) >> 3) - 1; tuninfo->pad[0] = IPV6_TLV_PADN; tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC; tuninfo->ioamh.opt_type = IPV6_TLV_IOAM; @@ -119,27 +150,39 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, memcpy(&tuninfo->traceh, trace, sizeof(*trace)); - len = len_aligned - len; - if (len == 1) { - tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PAD1; - } else if (len > 0) { + if (len_aligned - trace->remlen * 4) { tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN; - tuninfo->traceh.data[trace->remlen * 4 + 1] = len - 2; + tuninfo->traceh.data[trace->remlen * 4 + 1] = 2; } - s->type = LWTUNNEL_ENCAP_IOAM6; - s->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + lwt->type = LWTUNNEL_ENCAP_IOAM6; + lwt->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; - *ts = s; + *ts = lwt; return 0; } -static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo) +static int ioam6_do_fill(struct net *net, struct sk_buff *skb) { struct ioam6_trace_hdr *trace; - struct ipv6hdr *oldhdr, *hdr; struct ioam6_namespace *ns; + + trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb) + + sizeof(struct ipv6_hopopt_hdr) + 2 + + sizeof(struct ioam6_hdr)); + + ns = ioam6_namespace(net, trace->namespace_id); + if (ns) + ioam6_fill_trace_data(skb, ns, trace, false); + + return 0; +} + +static int ioam6_do_inline(struct net *net, struct sk_buff *skb, + struct ioam6_lwt_encap *tuninfo) +{ + struct ipv6hdr *oldhdr, *hdr; int hdrlen, err; hdrlen = (tuninfo->eh.hdrlen + 1) << 3; @@ -168,79 +211,195 @@ static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo) hdr->nexthdr = NEXTHDR_HOP; hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); - trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb) - + sizeof(struct ipv6_hopopt_hdr) + 2 - + sizeof(struct ioam6_hdr)); + return ioam6_do_fill(net, skb); +} - ns = ioam6_namespace(dev_net(skb_dst(skb)->dev), trace->namespace_id); - if (ns) - ioam6_fill_trace_data(skb, ns, trace); +static int ioam6_do_encap(struct net *net, struct sk_buff *skb, + struct ioam6_lwt_encap *tuninfo, + struct in6_addr *tundst) +{ + struct dst_entry *dst = skb_dst(skb); + struct ipv6hdr *hdr, *inner_hdr; + int hdrlen, len, err; - return 0; + hdrlen = (tuninfo->eh.hdrlen + 1) << 3; + len = sizeof(*hdr) + hdrlen; + + err = skb_cow_head(skb, len + skb->mac_len); + if (unlikely(err)) + return err; + + inner_hdr = ipv6_hdr(skb); + + skb_push(skb, len); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + skb_set_transport_header(skb, sizeof(*hdr)); + + tuninfo->eh.nexthdr = NEXTHDR_IPV6; + memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen); + + hdr = ipv6_hdr(skb); + memcpy(hdr, inner_hdr, sizeof(*hdr)); + + hdr->nexthdr = NEXTHDR_HOP; + hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); + hdr->daddr = *tundst; + ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, + IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); + + skb_postpush_rcsum(skb, hdr, len); + + return ioam6_do_fill(net, skb); } static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct lwtunnel_state *lwt = skb_dst(skb)->lwtstate; + struct dst_entry *dst = skb_dst(skb); + struct in6_addr orig_daddr; + struct ioam6_lwt *ilwt; int err = -EINVAL; if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - /* Only for packets we send and - * that do not contain a Hop-by-Hop yet - */ - if (skb->dev || ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) - goto out; - - err = ioam6_do_inline(skb, ioam6_lwt_info(lwt)); - if (unlikely(err)) + ilwt = ioam6_lwt_state(dst->lwtstate); + orig_daddr = ipv6_hdr(skb)->daddr; + + switch (ilwt->mode) { + case IOAM6_IPTUNNEL_MODE_INLINE: +do_inline: + /* Direct insertion - if there is no Hop-by-Hop yet */ + if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) + goto out; + + err = ioam6_do_inline(net, skb, &ilwt->tuninfo); + if (unlikely(err)) + goto drop; + + break; + case IOAM6_IPTUNNEL_MODE_ENCAP: +do_encap: + /* Encapsulation (ip6ip6) */ + err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst); + if (unlikely(err)) + goto drop; + + break; + case IOAM6_IPTUNNEL_MODE_AUTO: + /* Automatic (RFC8200 compliant): + * - local packets -> INLINE mode + * - in-transit packets -> ENCAP mode + */ + if (!skb->dev) + goto do_inline; + + goto do_encap; + default: goto drop; + } - err = skb_cow_head(skb, LL_RESERVED_SPACE(skb_dst(skb)->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) goto drop; + if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { + preempt_disable(); + dst = dst_cache_get(&ilwt->cache); + preempt_enable(); + + if (unlikely(!dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = hdr->daddr; + fl6.saddr = hdr->saddr; + fl6.flowlabel = ip6_flowinfo(hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = hdr->nexthdr; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + err = dst->error; + dst_release(dst); + goto drop; + } + + preempt_disable(); + dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); + preempt_enable(); + } + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + return dst_output(net, sk, skb); + } out: - return lwt->orig_output(net, sk, skb); - + return dst->lwtstate->orig_output(net, sk, skb); drop: kfree_skb(skb); return err; } +static void ioam6_destroy_state(struct lwtunnel_state *lwt) +{ + dst_cache_destroy(&ioam6_lwt_state(lwt)->cache); +} + static int ioam6_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { - struct ioam6_trace_hdr *trace; + struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); int err; - trace = ioam6_lwt_trace(lwtstate); - - err = nla_put(skb, IOAM6_IPTUNNEL_TRACE, sizeof(*trace), trace); + err = nla_put_u8(skb, IOAM6_IPTUNNEL_MODE, ilwt->mode); if (err) - return err; + goto ret; - return 0; + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst); + if (err) + goto ret; + } + + err = nla_put(skb, IOAM6_IPTUNNEL_TRACE, sizeof(ilwt->tuninfo.traceh), + &ilwt->tuninfo.traceh); +ret: + return err; } static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) { - struct ioam6_trace_hdr *trace = ioam6_lwt_trace(lwtstate); + struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); + int nlsize; + + nlsize = nla_total_size(sizeof(ilwt->mode)) + + nla_total_size(sizeof(ilwt->tuninfo.traceh)); - return nla_total_size(sizeof(*trace)); + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) + nlsize += nla_total_size(sizeof(ilwt->tundst)); + + return nlsize; } static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) { - struct ioam6_trace_hdr *a_hdr = ioam6_lwt_trace(a); - struct ioam6_trace_hdr *b_hdr = ioam6_lwt_trace(b); - - return (a_hdr->namespace_id != b_hdr->namespace_id); + struct ioam6_trace_hdr *trace_a = ioam6_lwt_trace(a); + struct ioam6_trace_hdr *trace_b = ioam6_lwt_trace(b); + struct ioam6_lwt *ilwt_a = ioam6_lwt_state(a); + struct ioam6_lwt *ilwt_b = ioam6_lwt_state(b); + + return (ilwt_a->mode != ilwt_b->mode || + (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && + !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || + trace_a->namespace_id != trace_b->namespace_id); } static const struct lwtunnel_encap_ops ioam6_iptun_ops = { .build_state = ioam6_build_state, + .destroy_state = ioam6_destroy_state, .output = ioam6_output, .fill_encap = ioam6_fill_encap_info, .get_encap_size = ioam6_encap_nlsize, -- cgit v1.2.3 From 571e5c0efcb29c5dac8cf2949d3eed84ec43056c Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 19 May 2021 16:00:22 -0400 Subject: audit: add OPENAT2 record to list "how" info Since the openat2(2) syscall uses a struct open_how pointer to communicate its parameters they are not usefully recorded by the audit SYSCALL record's four existing arguments. Add a new audit record type OPENAT2 that reports the parameters in its third argument, struct open_how with fields oflag, mode and resolve. The new record in the context of an event would look like: time->Wed Mar 17 16:28:53 2021 type=PROCTITLE msg=audit(1616012933.531:184): proctitle= 73797363616C6C735F66696C652F6F70656E617432002F746D702F61756469742D 7465737473756974652D737641440066696C652D6F70656E617432 type=PATH msg=audit(1616012933.531:184): item=1 name="file-openat2" inode=29 dev=00:1f mode=0100600 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=CREATE cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 cap_frootid=0 type=PATH msg=audit(1616012933.531:184): item=0 name="/root/rgb/git/audit-testsuite/tests" inode=25 dev=00:1f mode=040700 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=PARENT cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 cap_frootid=0 type=CWD msg=audit(1616012933.531:184): cwd="/root/rgb/git/audit-testsuite/tests" type=OPENAT2 msg=audit(1616012933.531:184): oflag=0100302 mode=0600 resolve=0xa type=SYSCALL msg=audit(1616012933.531:184): arch=c000003e syscall=437 success=yes exit=4 a0=3 a1=7ffe315f1c53 a2=7ffe315f1550 a3=18 items=2 ppid=528 pid=540 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=ttyS0 ses=1 comm="openat2" exe="/root/rgb/git/audit-testsuite/tests/syscalls_file/openat2" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key="testsuite-1616012933-bjAUcEPO" Link: https://lore.kernel.org/r/d23fbb89186754487850367224b060e26f9b7181.1621363275.git.rgb@redhat.com Signed-off-by: Richard Guy Briggs Acked-by: Christian Brauner [PM: tweak subject, wrap example, move AUDIT_OPENAT2 to 1337] Signed-off-by: Paul Moore --- fs/open.c | 2 ++ include/linux/audit.h | 10 ++++++++++ include/uapi/linux/audit.h | 1 + kernel/audit.h | 2 ++ kernel/auditsc.c | 18 +++++++++++++++++- 5 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/fs/open.c b/fs/open.c index daa324606a41..a7f6cab81267 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1248,6 +1248,8 @@ SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, if (err) return err; + audit_openat2_how(&tmp); + /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; diff --git a/include/linux/audit.h b/include/linux/audit.h index 5fbeeeb6b726..0e0eb4c0fa10 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -399,6 +399,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); +extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); @@ -495,6 +496,12 @@ static inline void audit_mmap_fd(int fd, int flags) __audit_mmap_fd(fd, flags); } +static inline void audit_openat2_how(struct open_how *how) +{ + if (unlikely(!audit_dummy_context())) + __audit_openat2_how(how); +} + static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) @@ -646,6 +653,9 @@ static inline void audit_log_capset(const struct cred *new, static inline void audit_mmap_fd(int fd, int flags) { } +static inline void audit_openat2_how(struct open_how *how) +{ } + static inline void audit_log_kern_module(char *name) { } diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..afa2472ad5d6 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,7 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_OPENAT2 1337 /* Record showing openat2 how args */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.h b/kernel/audit.h index d6a2c899a8db..3b64a97f6091 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -14,6 +14,7 @@ #include #include #include +#include // struct open_how /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). If we get more names we will allocate @@ -188,6 +189,7 @@ struct audit_context { int fd; int flags; } mmap; + struct open_how openat2; struct { int argc; } execve; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8c4335a35274..a4ba53f5354e 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -63,7 +63,7 @@ #include #include #include -#include +#include // struct open_how #include "audit.h" @@ -1306,6 +1306,12 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd, context->mmap.flags); break; + case AUDIT_OPENAT2: + audit_log_format(ab, "oflag=0%llo mode=0%llo resolve=0x%llx", + context->openat2.flags, + context->openat2.mode, + context->openat2.resolve); + break; case AUDIT_EXECVE: audit_log_execve_info(context, &ab); break; @@ -2536,6 +2542,16 @@ void __audit_mmap_fd(int fd, int flags) context->type = AUDIT_MMAP; } +void __audit_openat2_how(struct open_how *how) +{ + struct audit_context *context = audit_context(); + + context->openat2.flags = how->flags; + context->openat2.mode = how->mode; + context->openat2.resolve = how->resolve; + context->type = AUDIT_OPENAT2; +} + void __audit_log_kern_module(char *name) { struct audit_context *context = audit_context(); -- cgit v1.2.3 From cbbd3764b2399ad882cda98435b25144e9ea2124 Mon Sep 17 00:00:00 2001 From: "Huang, Sean Z" Date: Fri, 24 Sep 2021 12:14:42 -0700 Subject: drm/i915/pxp: Create the arbitrary session after boot Create the arbitrary session, with the fixed session id 0xf, after system boot, for the case that application allocates the protected buffer without establishing any protection session. Because the hardware requires at least one alive session for protected buffer creation. This arbitrary session will need to be re-created after teardown or power event because hardware encryption key won't be valid after such cases. The session ID is exposed as part of the uapi so it can be used as part of userspace commands. v2: use gt->uncore->rpm (Chris) v3: s/arb_is_in_play/arb_is_valid (Chris), move set-up to the new init_hw function v4: move interface defs to separate header, set arb_is valid to false on fini (Rodrigo) v5: handle async component binding Signed-off-by: Huang, Sean Z Signed-off-by: Daniele Ceraolo Spurio Cc: Chris Wilson Cc: Rodrigo Vivi Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210924191452.1539378-8-alan.previn.teres.alexis@intel.com --- drivers/gpu/drm/i915/Makefile | 1 + drivers/gpu/drm/i915/pxp/intel_pxp.c | 12 +++ drivers/gpu/drm/i915/pxp/intel_pxp.h | 2 + drivers/gpu/drm/i915/pxp/intel_pxp_session.c | 74 ++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_session.h | 15 ++++ drivers/gpu/drm/i915/pxp/intel_pxp_tee.c | 87 ++++++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_tee.h | 3 + drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h | 36 +++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_types.h | 10 +++ include/uapi/drm/i915_drm.h | 3 + 10 files changed, 243 insertions(+) create mode 100644 drivers/gpu/drm/i915/pxp/intel_pxp_session.c create mode 100644 drivers/gpu/drm/i915/pxp/intel_pxp_session.h create mode 100644 drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index d790b603fbdd..1152348c04a9 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -281,6 +281,7 @@ i915-y += i915_perf.o # Protected execution platform (PXP) support i915-$(CONFIG_DRM_I915_PXP) += \ pxp/intel_pxp.o \ + pxp/intel_pxp_session.o \ pxp/intel_pxp_tee.o # Post-mortem debug and GPU hang state capture diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index f7166dd71d8f..65598487a7b2 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -3,6 +3,7 @@ * Copyright(c) 2020 Intel Corporation. */ #include "intel_pxp.h" +#include "intel_pxp_session.h" #include "intel_pxp_tee.h" #include "gt/intel_context.h" #include "i915_drv.h" @@ -12,6 +13,11 @@ struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp) return container_of(pxp, struct intel_gt, pxp); } +bool intel_pxp_is_active(const struct intel_pxp *pxp) +{ + return pxp->arb_is_valid; +} + /* KCR register definitions */ #define KCR_INIT _MMIO(0x320f0) /* Setting KCR Init bit is required after system boot */ @@ -72,6 +78,8 @@ void intel_pxp_init(struct intel_pxp *pxp) if (!HAS_PXP(gt->i915)) return; + mutex_init(&pxp->tee_mutex); + ret = create_vcs_context(pxp); if (ret) return; @@ -93,6 +101,8 @@ void intel_pxp_fini(struct intel_pxp *pxp) if (!intel_pxp_is_enabled(pxp)) return; + pxp->arb_is_valid = false; + intel_pxp_tee_component_fini(pxp); destroy_vcs_context(pxp); @@ -101,6 +111,8 @@ void intel_pxp_fini(struct intel_pxp *pxp) void intel_pxp_init_hw(struct intel_pxp *pxp) { kcr_pxp_enable(pxp_to_gt(pxp)); + + intel_pxp_create_arb_session(pxp); } void intel_pxp_fini_hw(struct intel_pxp *pxp) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index cd6560b2605c..2960e8338c82 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -15,6 +15,8 @@ static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) #ifdef CONFIG_DRM_I915_PXP struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp); +bool intel_pxp_is_active(const struct intel_pxp *pxp); + void intel_pxp_init(struct intel_pxp *pxp); void intel_pxp_fini(struct intel_pxp *pxp); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c new file mode 100644 index 000000000000..3331868f354c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#include "drm/i915_drm.h" +#include "i915_drv.h" + +#include "intel_pxp.h" +#include "intel_pxp_session.h" +#include "intel_pxp_tee.h" +#include "intel_pxp_types.h" + +#define ARB_SESSION I915_PROTECTED_CONTENT_DEFAULT_SESSION /* shorter define */ + +#define GEN12_KCR_SIP _MMIO(0x32260) /* KCR hwdrm session in play 0-31 */ + +static bool intel_pxp_session_is_in_play(struct intel_pxp *pxp, u32 id) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + intel_wakeref_t wakeref; + u32 sip = 0; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + sip = intel_uncore_read(gt->uncore, GEN12_KCR_SIP); + + return sip & BIT(id); +} + +static int pxp_wait_for_session_state(struct intel_pxp *pxp, u32 id, bool in_play) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + intel_wakeref_t wakeref; + u32 mask = BIT(id); + int ret; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + ret = intel_wait_for_register(gt->uncore, + GEN12_KCR_SIP, + mask, + in_play ? mask : 0, + 100); + + return ret; +} + +int intel_pxp_create_arb_session(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + int ret; + + pxp->arb_is_valid = false; + + if (intel_pxp_session_is_in_play(pxp, ARB_SESSION)) { + drm_err(>->i915->drm, "arb session already in play at creation time\n"); + return -EEXIST; + } + + ret = intel_pxp_tee_cmd_create_arb_session(pxp, ARB_SESSION); + if (ret) { + drm_err(>->i915->drm, "tee cmd for arb session creation failed\n"); + return ret; + } + + ret = pxp_wait_for_session_state(pxp, ARB_SESSION, true); + if (ret) { + drm_err(>->i915->drm, "arb session failed to go in play\n"); + return ret; + } + + pxp->arb_is_valid = true; + + return 0; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h new file mode 100644 index 000000000000..316c3bebed9c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_SESSION_H__ +#define __INTEL_PXP_SESSION_H__ + +#include + +struct intel_pxp; + +int intel_pxp_create_arb_session(struct intel_pxp *pxp); + +#endif /* __INTEL_PXP_SESSION_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c index 0c0c7946e6a0..accbbf9aa6d1 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -8,13 +8,63 @@ #include "drm/i915_component.h" #include "i915_drv.h" #include "intel_pxp.h" +#include "intel_pxp_session.h" #include "intel_pxp_tee.h" +#include "intel_pxp_tee_interface.h" static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) { return &kdev_to_i915(i915_kdev)->gt.pxp; } +static int intel_pxp_tee_io_message(struct intel_pxp *pxp, + void *msg_in, u32 msg_in_size, + void *msg_out, u32 msg_out_max_size, + u32 *msg_out_rcv_size) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_pxp_component *pxp_component = pxp->pxp_component; + int ret = 0; + + mutex_lock(&pxp->tee_mutex); + + /* + * The binding of the component is asynchronous from i915 probe, so we + * can't be sure it has happened. + */ + if (!pxp_component) { + ret = -ENODEV; + goto unlock; + } + + ret = pxp_component->ops->send(pxp_component->tee_dev, msg_in, msg_in_size); + if (ret) { + drm_err(&i915->drm, "Failed to send PXP TEE message\n"); + goto unlock; + } + + ret = pxp_component->ops->recv(pxp_component->tee_dev, msg_out, msg_out_max_size); + if (ret < 0) { + drm_err(&i915->drm, "Failed to receive PXP TEE message\n"); + goto unlock; + } + + if (ret > msg_out_max_size) { + drm_err(&i915->drm, + "Failed to receive PXP TEE message due to unexpected output size\n"); + ret = -ENOSPC; + goto unlock; + } + + if (msg_out_rcv_size) + *msg_out_rcv_size = ret; + + ret = 0; +unlock: + mutex_unlock(&pxp->tee_mutex); + return ret; +} + /** * i915_pxp_tee_component_bind - bind function to pass the function pointers to pxp_tee * @i915_kdev: pointer to i915 kernel device @@ -28,14 +78,24 @@ static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) static int i915_pxp_tee_component_bind(struct device *i915_kdev, struct device *tee_kdev, void *data) { + struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev); + mutex_lock(&pxp->tee_mutex); pxp->pxp_component = data; pxp->pxp_component->tee_dev = tee_kdev; + mutex_unlock(&pxp->tee_mutex); /* the component is required to fully start the PXP HW */ intel_pxp_init_hw(pxp); + if (!pxp->arb_is_valid) { + drm_err(&i915->drm, "Failed to create arb session during bind\n"); + intel_pxp_fini_hw(pxp); + pxp->pxp_component = NULL; + return -EIO; + } + return 0; } @@ -46,7 +106,9 @@ static void i915_pxp_tee_component_unbind(struct device *i915_kdev, intel_pxp_fini_hw(pxp); + mutex_lock(&pxp->tee_mutex); pxp->pxp_component = NULL; + mutex_unlock(&pxp->tee_mutex); } static const struct component_ops i915_pxp_tee_component_ops = { @@ -82,3 +144,28 @@ void intel_pxp_tee_component_fini(struct intel_pxp *pxp) component_del(i915->drm.dev, &i915_pxp_tee_component_ops); pxp->pxp_component_added = false; } + +int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, + int arb_session_id) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct pxp_tee_create_arb_in msg_in = {0}; + struct pxp_tee_create_arb_out msg_out = {0}; + int ret; + + msg_in.header.api_version = PXP_TEE_APIVER; + msg_in.header.command_id = PXP_TEE_ARB_CMDID; + msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); + msg_in.protection_mode = PXP_TEE_ARB_PROTECTION_MODE; + msg_in.session_id = arb_session_id; + + ret = intel_pxp_tee_io_message(pxp, + &msg_in, sizeof(msg_in), + &msg_out, sizeof(msg_out), + NULL); + + if (ret) + drm_err(&i915->drm, "Failed to send tee msg ret=[%d]\n", ret); + + return ret; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h index 23d050a5d3e7..c136053ce340 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h @@ -11,4 +11,7 @@ int intel_pxp_tee_component_init(struct intel_pxp *pxp); void intel_pxp_tee_component_fini(struct intel_pxp *pxp); +int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, + int arb_session_id); + #endif /* __INTEL_PXP_TEE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h new file mode 100644 index 000000000000..36e9b0868f5c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_TEE_INTERFACE_H__ +#define __INTEL_PXP_TEE_INTERFACE_H__ + +#include + +#define PXP_TEE_APIVER 0x40002 +#define PXP_TEE_ARB_CMDID 0x1e +#define PXP_TEE_ARB_PROTECTION_MODE 0x2 + +/* PXP TEE message header */ +struct pxp_tee_cmd_header { + u32 api_version; + u32 command_id; + u32 status; + /* Length of the message (excluding the header) */ + u32 buffer_len; +} __packed; + +/* PXP TEE message input to create a arbitrary session */ +struct pxp_tee_create_arb_in { + struct pxp_tee_cmd_header header; + u32 protection_mode; + u32 session_id; +} __packed; + +/* PXP TEE message output to create a arbitrary session */ +struct pxp_tee_create_arb_out { + struct pxp_tee_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_TEE_INTERFACE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h index 3a8e17e591bd..d393e46a7d98 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -6,6 +6,7 @@ #ifndef __INTEL_PXP_TYPES_H__ #define __INTEL_PXP_TYPES_H__ +#include #include struct intel_context; @@ -16,6 +17,15 @@ struct intel_pxp { bool pxp_component_added; struct intel_context *ce; + + /* + * After a teardown, the arb session can still be in play on the HW + * even if the keys are gone, so we can't rely on the HW state of the + * session to know if it's valid and need to track the status in SW. + */ + bool arb_is_valid; + + struct mutex tee_mutex; /* protects the tee channel binding */ }; #endif /* __INTEL_PXP_TYPES_H__ */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index bde5860b3686..920e9e852e5a 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -3038,6 +3038,9 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From d3ac8d42168a9be7380be8035df8b6d3780ec2a1 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Fri, 24 Sep 2021 12:14:45 -0700 Subject: drm/i915/pxp: interfaces for using protected objects This api allow user mode to create protected buffers and to mark contexts as making use of such objects. Only when using contexts marked in such a way is the execution guaranteed to work as expected. Contexts can only be marked as using protected content at creation time (i.e. the parameter is immutable) and they must be both bannable and not recoverable. Given that the protected session gets invalidated on suspend, contexts created this way hold a runtime pm wakeref until they're either destroyed or invalidated. All protected objects and contexts will be considered invalid when the PXP session is destroyed and all new submissions using them will be rejected. All intel contexts within the invalidated gem contexts will be marked banned. Userspace can detect that an invalidation has occurred via the RESET_STATS ioctl, where we report it the same way as a ban due to a hang. v5: squash patches, rebase on proto_ctx, update kerneldoc v6: rebase on obj create_ext changes v7: Use session counter to check if an object it valid, hold wakeref in context, don't add a new flag to RESET_STATS (Daniel) v8: don't increase guilty count for contexts banned during pxp invalidation (Rodrigo) v9: better comments, avoid wakeref put race between pxp_inval and context_close, add usage examples (Rodrigo) v10: modify internal set/get-protected-context functions to not return -ENODEV when setting PXP param to false or getting param when running on pxp-unsupported hw or getting param when i915 was built with CONFIG_PXP off Signed-off-by: Alan Previn Signed-off-by: Daniele Ceraolo Spurio Signed-off-by: Bommu Krishnaiah Cc: Rodrigo Vivi Cc: Chris Wilson Cc: Lionel Landwerlin Cc: Jason Ekstrand Cc: Daniel Vetter Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210924191452.1539378-11-alan.previn.teres.alexis@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 95 +++++++++++++++++++---- drivers/gpu/drm/i915/gem/i915_gem_context.h | 6 ++ drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 28 +++++++ drivers/gpu/drm/i915/gem/i915_gem_create.c | 72 ++++++++++++----- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 18 +++++ drivers/gpu/drm/i915/gem/i915_gem_object.c | 1 + drivers/gpu/drm/i915/gem/i915_gem_object.h | 6 ++ drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 9 ++- drivers/gpu/drm/i915/gem/selftests/mock_context.c | 4 +- drivers/gpu/drm/i915/pxp/intel_pxp.c | 77 ++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp.h | 12 +++ drivers/gpu/drm/i915/pxp/intel_pxp_session.c | 6 ++ drivers/gpu/drm/i915/pxp/intel_pxp_types.h | 9 +++ include/uapi/drm/i915_drm.h | 94 ++++++++++++++++++++++ 14 files changed, 402 insertions(+), 35 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 8208fd5b72c3..08360d6bbd1e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -77,6 +77,8 @@ #include "gt/intel_gpu_commands.h" #include "gt/intel_ring.h" +#include "pxp/intel_pxp.h" + #include "i915_gem_context.h" #include "i915_trace.h" #include "i915_user_extensions.h" @@ -186,10 +188,13 @@ static int validate_priority(struct drm_i915_private *i915, return 0; } -static void proto_context_close(struct i915_gem_proto_context *pc) +static void proto_context_close(struct drm_i915_private *i915, + struct i915_gem_proto_context *pc) { int i; + if (pc->pxp_wakeref) + intel_runtime_pm_put(&i915->runtime_pm, pc->pxp_wakeref); if (pc->vm) i915_vm_put(pc->vm); if (pc->user_engines) { @@ -241,6 +246,33 @@ static int proto_context_set_persistence(struct drm_i915_private *i915, return 0; } +static int proto_context_set_protected(struct drm_i915_private *i915, + struct i915_gem_proto_context *pc, + bool protected) +{ + int ret = 0; + + if (!protected) { + pc->uses_protected_content = false; + } else if (!intel_pxp_is_enabled(&i915->gt.pxp)) { + ret = -ENODEV; + } else if ((pc->user_flags & BIT(UCONTEXT_RECOVERABLE)) || + !(pc->user_flags & BIT(UCONTEXT_BANNABLE))) { + ret = -EPERM; + } else { + pc->uses_protected_content = true; + + /* + * protected context usage requires the PXP session to be up, + * which in turn requires the device to be active. + */ + pc->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); + ret = intel_pxp_wait_for_arb_start(&i915->gt.pxp); + } + + return ret; +} + static struct i915_gem_proto_context * proto_context_create(struct drm_i915_private *i915, unsigned int flags) { @@ -269,7 +301,7 @@ proto_context_create(struct drm_i915_private *i915, unsigned int flags) return pc; proto_close: - proto_context_close(pc); + proto_context_close(i915, pc); return err; } @@ -693,6 +725,8 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, ret = -EPERM; else if (args->value) pc->user_flags |= BIT(UCONTEXT_BANNABLE); + else if (pc->uses_protected_content) + ret = -EPERM; else pc->user_flags &= ~BIT(UCONTEXT_BANNABLE); break; @@ -700,10 +734,12 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; - else if (args->value) - pc->user_flags |= BIT(UCONTEXT_RECOVERABLE); - else + else if (!args->value) pc->user_flags &= ~BIT(UCONTEXT_RECOVERABLE); + else if (pc->uses_protected_content) + ret = -EPERM; + else + pc->user_flags |= BIT(UCONTEXT_RECOVERABLE); break; case I915_CONTEXT_PARAM_PRIORITY: @@ -731,6 +767,11 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, args->value); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: + ret = proto_context_set_protected(fpriv->dev_priv, pc, + args->value); + break; + case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_RINGSIZE: @@ -956,6 +997,9 @@ static void i915_gem_context_release_work(struct work_struct *work) if (vm) i915_vm_put(vm); + if (ctx->pxp_wakeref) + intel_runtime_pm_put(&ctx->i915->runtime_pm, ctx->pxp_wakeref); + mutex_destroy(&ctx->engines_mutex); mutex_destroy(&ctx->lut_mutex); @@ -1338,6 +1382,11 @@ i915_gem_create_context(struct drm_i915_private *i915, goto err_engines; } + if (pc->uses_protected_content) { + ctx->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); + ctx->uses_protected_content = true; + } + trace_i915_context_create(ctx); return ctx; @@ -1409,7 +1458,7 @@ int i915_gem_context_open(struct drm_i915_private *i915, } ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err; @@ -1436,7 +1485,7 @@ void i915_gem_context_close(struct drm_file *file) unsigned long idx; xa_for_each(&file_priv->proto_context_xa, idx, pc) - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); xa_destroy(&file_priv->proto_context_xa); mutex_destroy(&file_priv->proto_context_lock); @@ -1731,6 +1780,15 @@ static int set_priority(struct i915_gem_context *ctx, return 0; } +static int get_protected(struct i915_gem_context *ctx, + struct drm_i915_gem_context_param *args) +{ + args->size = 0; + args->value = i915_gem_context_uses_protected_content(ctx); + + return 0; +} + static int ctx_setparam(struct drm_i915_file_private *fpriv, struct i915_gem_context *ctx, struct drm_i915_gem_context_param *args) @@ -1754,6 +1812,8 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, ret = -EPERM; else if (args->value) i915_gem_context_set_bannable(ctx); + else if (i915_gem_context_uses_protected_content(ctx)) + ret = -EPERM; /* can't clear this for protected contexts */ else i915_gem_context_clear_bannable(ctx); break; @@ -1761,10 +1821,12 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; - else if (args->value) - i915_gem_context_set_recoverable(ctx); - else + else if (!args->value) i915_gem_context_clear_recoverable(ctx); + else if (i915_gem_context_uses_protected_content(ctx)) + ret = -EPERM; /* can't set this for protected contexts */ + else + i915_gem_context_set_recoverable(ctx); break; case I915_CONTEXT_PARAM_PRIORITY: @@ -1779,6 +1841,7 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, ret = set_persistence(ctx, args); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_RINGSIZE: @@ -1857,7 +1920,7 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv, old = xa_erase(&file_priv->proto_context_xa, id); GEM_BUG_ON(old != pc); - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); /* One for the xarray and one for the caller */ return i915_gem_context_get(ctx); @@ -1943,7 +2006,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, goto err_pc; } - proto_context_close(ext_data.pc); + proto_context_close(i915, ext_data.pc); gem_context_register(ctx, ext_data.fpriv, id); } else { ret = proto_context_register(ext_data.fpriv, ext_data.pc, &id); @@ -1957,7 +2020,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, return 0; err_pc: - proto_context_close(ext_data.pc); + proto_context_close(i915, ext_data.pc); return ret; } @@ -1988,7 +2051,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, GEM_WARN_ON(ctx && pc); if (pc) - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); if (ctx) context_close(ctx); @@ -2106,6 +2169,10 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, args->value = i915_gem_context_is_persistent(ctx); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: + ret = get_protected(ctx, args); + break; + case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_ENGINES: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h index d3279086a5e7..babfecb17ad1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h @@ -108,6 +108,12 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx) clear_bit(CONTEXT_USER_ENGINES, &ctx->flags); } +static inline bool +i915_gem_context_uses_protected_content(const struct i915_gem_context *ctx) +{ + return ctx->uses_protected_content; +} + /* i915_gem_context.c */ void i915_gem_init__contexts(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index c4617e4d9fa9..a627b09c4680 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -198,6 +198,12 @@ struct i915_gem_proto_context { /** @single_timeline: See See &i915_gem_context.syncobj */ bool single_timeline; + + /** @uses_protected_content: See &i915_gem_context.uses_protected_content */ + bool uses_protected_content; + + /** @pxp_wakeref: See &i915_gem_context.pxp_wakeref */ + intel_wakeref_t pxp_wakeref; }; /** @@ -321,6 +327,28 @@ struct i915_gem_context { #define CONTEXT_CLOSED 0 #define CONTEXT_USER_ENGINES 1 + /** + * @uses_protected_content: context uses PXP-encrypted objects. + * + * This flag can only be set at ctx creation time and it's immutable for + * the lifetime of the context. See I915_CONTEXT_PARAM_PROTECTED_CONTENT + * in uapi/drm/i915_drm.h for more info on setting restrictions and + * expected behaviour of marked contexts. + */ + bool uses_protected_content; + + /** + * @pxp_wakeref: wakeref to keep the device awake when PXP is in use + * + * PXP sessions are invalidated when the device is suspended, which in + * turns invalidates all contexts and objects using it. To keep the + * flow simple, we keep the device awake when contexts using PXP objects + * are in use. It is expected that the userspace application only uses + * PXP when the display is on, so taking a wakeref here shouldn't worsen + * our power metrics. + */ + intel_wakeref_t pxp_wakeref; + /** @mutex: guards everything that isn't engines or handles_vma */ struct mutex mutex; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 1d341b8c47c0..8955d6abcef1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -6,6 +6,7 @@ #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" +#include "pxp/intel_pxp.h" #include "i915_drv.h" #include "i915_trace.h" @@ -82,21 +83,11 @@ static int i915_gem_publish(struct drm_i915_gem_object *obj, return 0; } -/** - * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT - * @i915: i915 private - * @size: size of the buffer, in bytes - * @placements: possible placement regions, in priority order - * @n_placements: number of possible placement regions - * - * This function is exposed primarily for selftests and does very little - * error checking. It is assumed that the set of placement regions has - * already been verified to be valid. - */ -struct drm_i915_gem_object * -__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, - struct intel_memory_region **placements, - unsigned int n_placements) +static struct drm_i915_gem_object * +__i915_gem_object_create_user_ext(struct drm_i915_private *i915, u64 size, + struct intel_memory_region **placements, + unsigned int n_placements, + unsigned int ext_flags) { struct intel_memory_region *mr = placements[0]; struct drm_i915_gem_object *obj; @@ -135,6 +126,9 @@ __i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, GEM_BUG_ON(size != obj->base.size); + /* Add any flag set by create_ext options */ + obj->flags |= ext_flags; + trace_i915_gem_object_create(obj); return obj; @@ -145,6 +139,26 @@ object_free: return ERR_PTR(ret); } +/** + * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT + * @i915: i915 private + * @size: size of the buffer, in bytes + * @placements: possible placement regions, in priority order + * @n_placements: number of possible placement regions + * + * This function is exposed primarily for selftests and does very little + * error checking. It is assumed that the set of placement regions has + * already been verified to be valid. + */ +struct drm_i915_gem_object * +__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, + struct intel_memory_region **placements, + unsigned int n_placements) +{ + return __i915_gem_object_create_user_ext(i915, size, placements, + n_placements, 0); +} + int i915_gem_dumb_create(struct drm_file *file, struct drm_device *dev, @@ -224,6 +238,7 @@ struct create_ext { struct drm_i915_private *i915; struct intel_memory_region *placements[INTEL_REGION_UNKNOWN]; unsigned int n_placements; + unsigned long flags; }; static void repr_placements(char *buf, size_t size, @@ -353,8 +368,28 @@ static int ext_set_placements(struct i915_user_extension __user *base, return set_placements(&ext, data); } +static int ext_set_protected(struct i915_user_extension __user *base, void *data) +{ + struct drm_i915_gem_create_ext_protected_content ext; + struct create_ext *ext_data = data; + + if (copy_from_user(&ext, base, sizeof(ext))) + return -EFAULT; + + if (ext.flags) + return -EINVAL; + + if (!intel_pxp_is_enabled(&ext_data->i915->gt.pxp)) + return -ENODEV; + + ext_data->flags |= I915_BO_PROTECTED; + + return 0; +} + static const i915_user_extension_fn create_extensions[] = { [I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements, + [I915_GEM_CREATE_EXT_PROTECTED_CONTENT] = ext_set_protected, }; /** @@ -389,9 +424,10 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, ext_data.n_placements = 1; } - obj = __i915_gem_object_create_user(i915, args->size, - ext_data.placements, - ext_data.n_placements); + obj = __i915_gem_object_create_user_ext(i915, args->size, + ext_data.placements, + ext_data.n_placements, + ext_data.flags); if (IS_ERR(obj)) return PTR_ERR(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index c2f74dba0557..9447ce6ea500 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -21,6 +21,8 @@ #include "gt/intel_gt_pm.h" #include "gt/intel_ring.h" +#include "pxp/intel_pxp.h" + #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_gem_context.h" @@ -810,6 +812,22 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) if (unlikely(!obj)) return ERR_PTR(-ENOENT); + /* + * If the user has opted-in for protected-object tracking, make + * sure the object encryption can be used. + * We only need to do this when the object is first used with + * this context, because the context itself will be banned when + * the protected objects become invalid. + */ + if (i915_gem_context_uses_protected_content(eb->gem_context) && + i915_gem_object_is_protected(obj)) { + err = intel_pxp_key_check(&vm->gt->pxp, obj); + if (err) { + i915_gem_object_put(obj); + return ERR_PTR(err); + } + } + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { i915_gem_object_put(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index b88b121e244a..76ce6a1500bc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -25,6 +25,7 @@ #include #include "display/intel_frontbuffer.h" +#include "pxp/intel_pxp.h" #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_gem_context.h" diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 7f9f2e5ba0ec..9df3ee60604e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -272,6 +272,12 @@ i915_gem_object_clear_tiling_quirk(struct drm_i915_gem_object *obj) clear_bit(I915_TILING_QUIRK_BIT, &obj->flags); } +static inline bool +i915_gem_object_is_protected(const struct drm_i915_gem_object *obj) +{ + return obj->flags & I915_BO_PROTECTED; +} + static inline bool i915_gem_object_type_has(const struct drm_i915_gem_object *obj, unsigned long flags) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index fa2ba9e2a4d0..7c3da4e3e737 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -304,7 +304,7 @@ struct drm_i915_gem_object { I915_BO_ALLOC_PM_EARLY) #define I915_BO_READONLY BIT(6) #define I915_TILING_QUIRK_BIT 7 /* unknown swizzling; do not release! */ - +#define I915_BO_PROTECTED BIT(8) /** * @mem_flags - Mutable placement-related flags * @@ -544,6 +544,13 @@ struct drm_i915_gem_object { bool created:1; } ttm; + /* + * Record which PXP key instance this object was created against (if + * any), so we can use it to determine if the encryption is valid by + * comparing against the current key instance. + */ + u32 pxp_key_instance; + /** Record of address bit 17 of each page at last unbind. */ unsigned long *bit_17; diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c index 067d68a6fe4c..c0a8ef368044 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c @@ -88,7 +88,7 @@ live_context(struct drm_i915_private *i915, struct file *file) return ERR_CAST(pc); ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) return ctx; @@ -163,7 +163,7 @@ kernel_context(struct drm_i915_private *i915, } ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) return ctx; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index 2e188217c3b7..ee507fd8ae19 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -7,6 +7,7 @@ #include "intel_pxp_irq.h" #include "intel_pxp_session.h" #include "intel_pxp_tee.h" +#include "gem/i915_gem_context.h" #include "gt/intel_context.h" #include "i915_drv.h" @@ -178,3 +179,79 @@ void intel_pxp_fini_hw(struct intel_pxp *pxp) intel_pxp_irq_disable(pxp); } + +int intel_pxp_key_check(struct intel_pxp *pxp, struct drm_i915_gem_object *obj) +{ + if (!intel_pxp_is_active(pxp)) + return -ENODEV; + + if (!i915_gem_object_is_protected(obj)) + return -EINVAL; + + GEM_BUG_ON(!pxp->key_instance); + + /* + * If this is the first time we're using this object, it's not + * encrypted yet; it will be encrypted with the current key, so mark it + * as such. If the object is already encrypted, check instead if the + * used key is still valid. + */ + if (!obj->pxp_key_instance) + obj->pxp_key_instance = pxp->key_instance; + else if (obj->pxp_key_instance != pxp->key_instance) + return -ENOEXEC; + + return 0; +} + +void intel_pxp_invalidate(struct intel_pxp *pxp) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_gem_context *ctx, *cn; + + /* ban all contexts marked as protected */ + spin_lock_irq(&i915->gem.contexts.lock); + list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) { + struct i915_gem_engines_iter it; + struct intel_context *ce; + + if (!kref_get_unless_zero(&ctx->ref)) + continue; + + if (likely(!i915_gem_context_uses_protected_content(ctx))) { + i915_gem_context_put(ctx); + continue; + } + + spin_unlock_irq(&i915->gem.contexts.lock); + + /* + * By the time we get here we are either going to suspend with + * quiesced execution or the HW keys are already long gone and + * in this case it is worthless to attempt to close the context + * and wait for its execution. It will hang the GPU if it has + * not already. So, as a fast mitigation, we can ban the + * context as quick as we can. That might race with the + * execbuffer, but currently this is the best that can be done. + */ + for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) + intel_context_ban(ce, NULL); + i915_gem_context_unlock_engines(ctx); + + /* + * The context has been banned, no need to keep the wakeref. + * This is safe from races because the only other place this + * is touched is context_release and we're holding a ctx ref + */ + if (ctx->pxp_wakeref) { + intel_runtime_pm_put(&i915->runtime_pm, + ctx->pxp_wakeref); + ctx->pxp_wakeref = 0; + } + + spin_lock_irq(&i915->gem.contexts.lock); + list_safe_reset_next(ctx, cn, link); + i915_gem_context_put(ctx); + } + spin_unlock_irq(&i915->gem.contexts.lock); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index 54b268280379..430f01ea9860 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -8,6 +8,8 @@ #include "intel_pxp_types.h" +struct drm_i915_gem_object; + static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) { return pxp->ce; @@ -25,6 +27,10 @@ void intel_pxp_fini_hw(struct intel_pxp *pxp); void intel_pxp_mark_termination_in_progress(struct intel_pxp *pxp); int intel_pxp_wait_for_arb_start(struct intel_pxp *pxp); + +int intel_pxp_key_check(struct intel_pxp *pxp, struct drm_i915_gem_object *obj); + +void intel_pxp_invalidate(struct intel_pxp *pxp); #else static inline void intel_pxp_init(struct intel_pxp *pxp) { @@ -38,6 +44,12 @@ static inline int intel_pxp_wait_for_arb_start(struct intel_pxp *pxp) { return -ENODEV; } + +static inline int intel_pxp_key_check(struct intel_pxp *pxp, + struct drm_i915_gem_object *obj) +{ + return -ENODEV; +} #endif #endif /* __INTEL_PXP_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c index 67c30e534d50..c6a5e4197e40 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -72,6 +72,9 @@ static int pxp_create_arb_session(struct intel_pxp *pxp) return ret; } + if (!++pxp->key_instance) + ++pxp->key_instance; + pxp->arb_is_valid = true; return 0; @@ -85,6 +88,9 @@ static int pxp_terminate_arb_session_and_global(struct intel_pxp *pxp) /* must mark termination in progress calling this function */ GEM_WARN_ON(pxp->arb_is_valid); + /* invalidate protected objects */ + intel_pxp_invalidate(pxp); + /* terminate the hw sessions */ ret = intel_pxp_terminate_session(pxp, ARB_SESSION); if (ret) { diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h index 5a170e43c959..c394ab2e452b 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -7,7 +7,9 @@ #define __INTEL_PXP_TYPES_H__ #include +#include #include +#include #include #include @@ -27,6 +29,13 @@ struct intel_pxp { */ bool arb_is_valid; + /* + * Keep track of which key instance we're on, so we can use it to + * determine if an object was created using the current key or a + * previous one. + */ + u32 key_instance; + struct mutex tee_mutex; /* protects the tee channel binding */ /* diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 920e9e852e5a..aa2a7eccfb94 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1846,6 +1846,55 @@ struct drm_i915_gem_context_param { * attempted to use it, never re-use this context param number. */ #define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -2979,8 +3028,12 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 __u64 extensions; }; @@ -3038,6 +3091,47 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + /* ID of the protected content session managed by i915 when PXP is active */ #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf -- cgit v1.2.3 From d154abdda6dcac92c63141035e477ac18077ffd8 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 24 Sep 2021 07:13:54 -0500 Subject: ipmi: Fix a typo Spell "RESPONSE" correctly in a comment. Signed-off-by: Corey Minyard --- include/uapi/linux/ipmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index 32d148309b16..007e65f9243b 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -158,7 +158,7 @@ struct kernel_ipmi_msg { * is used for the receive in-kernel interface and in the receive * IOCTL. * - * The "IPMI_RESPONSE_RESPNOSE_TYPE" is a little strange sounding, but + * The "IPMI_RESPONSE_RESPONSE_TYPE" is a little strange sounding, but * it allows you to get the message results when you send a response * message. */ -- cgit v1.2.3 From 059747c245f0e9af5e109eece7d3414dbe08d513 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 24 Sep 2021 11:42:56 -0500 Subject: ipmi: Add support for IPMB direct messages An application has come up that has a device sitting right on the IPMB that would like to communicate with the BMC on the IPMB using normal IPMI commands. Sending these commands and handling the responses is easy enough, no modifications are needed to the IPMI infrastructure. But if this is an application that also needs to receive IPMB commands and respond, some way is needed to handle these incoming commands and send the responses. Currently, the IPMI message handler only sends commands to the interface and only receives responses from interface. This change extends the interface to receive commands/responses and send commands/responses. These are formatted differently in support of receiving/sending IPMB messages directly. Signed-off-by: Corey Minyard Tested-by: Andrew Manley Reviewed-by: Andrew Manley --- drivers/char/ipmi/ipmi_msghandler.c | 288 +++++++++++++++++++++++++++++++----- include/linux/ipmi_smi.h | 59 ++++++++ include/uapi/linux/ipmi.h | 14 ++ 3 files changed, 328 insertions(+), 33 deletions(-) (limited to 'include/uapi') diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index ad1a8fc379b9..a60201d3f735 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -653,6 +653,11 @@ static int is_ipmb_bcast_addr(struct ipmi_addr *addr) return addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE; } +static int is_ipmb_direct_addr(struct ipmi_addr *addr) +{ + return addr->addr_type == IPMI_IPMB_DIRECT_ADDR_TYPE; +} + static void free_recv_msg_list(struct list_head *q) { struct ipmi_recv_msg *msg, *msg2; @@ -805,6 +810,17 @@ ipmi_addr_equal(struct ipmi_addr *addr1, struct ipmi_addr *addr2) && (ipmb_addr1->lun == ipmb_addr2->lun)); } + if (is_ipmb_direct_addr(addr1)) { + struct ipmi_ipmb_direct_addr *daddr1 + = (struct ipmi_ipmb_direct_addr *) addr1; + struct ipmi_ipmb_direct_addr *daddr2 + = (struct ipmi_ipmb_direct_addr *) addr2; + + return daddr1->slave_addr == daddr2->slave_addr && + daddr1->rq_lun == daddr2->rq_lun && + daddr1->rs_lun == daddr2->rs_lun; + } + if (is_lan_addr(addr1)) { struct ipmi_lan_addr *lan_addr1 = (struct ipmi_lan_addr *) addr1; @@ -843,6 +859,23 @@ int ipmi_validate_addr(struct ipmi_addr *addr, int len) return 0; } + if (is_ipmb_direct_addr(addr)) { + struct ipmi_ipmb_direct_addr *daddr = (void *) addr; + + if (addr->channel != 0) + return -EINVAL; + if (len < sizeof(struct ipmi_ipmb_direct_addr)) + return -EINVAL; + + if (daddr->slave_addr & 0x01) + return -EINVAL; + if (daddr->rq_lun >= 4) + return -EINVAL; + if (daddr->rs_lun >= 4) + return -EINVAL; + return 0; + } + if (is_lan_addr(addr)) { if (len < sizeof(struct ipmi_lan_addr)) return -EINVAL; @@ -862,6 +895,9 @@ unsigned int ipmi_addr_length(int addr_type) || (addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)) return sizeof(struct ipmi_ipmb_addr); + if (addr_type == IPMI_IPMB_DIRECT_ADDR_TYPE) + return sizeof(struct ipmi_ipmb_direct_addr); + if (addr_type == IPMI_LAN_ADDR_TYPE) return sizeof(struct ipmi_lan_addr); @@ -2052,6 +2088,58 @@ out_err: return rv; } +static int i_ipmi_req_ipmb_direct(struct ipmi_smi *intf, + struct ipmi_addr *addr, + long msgid, + struct kernel_ipmi_msg *msg, + struct ipmi_smi_msg *smi_msg, + struct ipmi_recv_msg *recv_msg, + unsigned char source_lun) +{ + struct ipmi_ipmb_direct_addr *daddr; + bool is_cmd = !(recv_msg->msg.netfn & 0x1); + + if (!(intf->handlers->flags & IPMI_SMI_CAN_HANDLE_IPMB_DIRECT)) + return -EAFNOSUPPORT; + + /* Responses must have a completion code. */ + if (!is_cmd && msg->data_len < 1) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EINVAL; + } + + if ((msg->data_len + 4) > IPMI_MAX_MSG_LENGTH) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EMSGSIZE; + } + + daddr = (struct ipmi_ipmb_direct_addr *) addr; + if (daddr->rq_lun > 3 || daddr->rs_lun > 3) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EINVAL; + } + + smi_msg->type = IPMI_SMI_MSG_TYPE_IPMB_DIRECT; + smi_msg->msgid = msgid; + + if (is_cmd) { + smi_msg->data[0] = msg->netfn << 2 | daddr->rs_lun; + smi_msg->data[2] = recv_msg->msgid << 2 | daddr->rq_lun; + } else { + smi_msg->data[0] = msg->netfn << 2 | daddr->rq_lun; + smi_msg->data[2] = recv_msg->msgid << 2 | daddr->rs_lun; + } + smi_msg->data[1] = daddr->slave_addr; + smi_msg->data[3] = msg->cmd; + + memcpy(smi_msg->data + 4, msg->data, msg->data_len); + smi_msg->data_size = msg->data_len + 4; + + smi_msg->user_data = recv_msg; + + return 0; +} + static int i_ipmi_req_lan(struct ipmi_smi *intf, struct ipmi_addr *addr, long msgid, @@ -2241,6 +2329,9 @@ static int i_ipmi_request(struct ipmi_user *user, rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg, source_address, source_lun, retries, retry_time_ms); + } else if (is_ipmb_direct_addr(addr)) { + rv = i_ipmi_req_ipmb_direct(intf, addr, msgid, msg, smi_msg, + recv_msg, source_lun); } else if (is_lan_addr(addr)) { rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg, source_lun, retries, retry_time_ms); @@ -3802,6 +3893,123 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf, return rv; } +static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf, + struct ipmi_smi_msg *msg) +{ + struct cmd_rcvr *rcvr; + int rv = 0; + struct ipmi_user *user = NULL; + struct ipmi_ipmb_direct_addr *daddr; + struct ipmi_recv_msg *recv_msg; + unsigned char netfn = msg->rsp[0] >> 2; + unsigned char cmd = msg->rsp[3]; + + rcu_read_lock(); + /* We always use channel 0 for direct messages. */ + rcvr = find_cmd_rcvr(intf, netfn, cmd, 0); + if (rcvr) { + user = rcvr->user; + kref_get(&user->refcount); + } else + user = NULL; + rcu_read_unlock(); + + if (user == NULL) { + /* We didn't find a user, deliver an error response. */ + ipmi_inc_stat(intf, unhandled_commands); + + msg->data[0] = ((netfn + 1) << 2) | (msg->rsp[4] & 0x3); + msg->data[1] = msg->rsp[2]; + msg->data[2] = msg->rsp[4] & ~0x3; + msg->data[3] = cmd; + msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE; + msg->data_size = 5; + + rcu_read_lock(); + if (!intf->in_shutdown) { + smi_send(intf, intf->handlers, msg, 0); + /* + * We used the message, so return the value + * that causes it to not be freed or + * queued. + */ + rv = -1; + } + rcu_read_unlock(); + } else { + recv_msg = ipmi_alloc_recv_msg(); + if (!recv_msg) { + /* + * We couldn't allocate memory for the + * message, so requeue it for handling + * later. + */ + rv = 1; + kref_put(&user->refcount, free_user); + } else { + /* Extract the source address from the data. */ + daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr; + daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE; + daddr->channel = 0; + daddr->slave_addr = msg->rsp[1]; + daddr->rs_lun = msg->rsp[0] & 3; + daddr->rq_lun = msg->rsp[2] & 3; + + /* + * Extract the rest of the message information + * from the IPMB header. + */ + recv_msg->user = user; + recv_msg->recv_type = IPMI_CMD_RECV_TYPE; + recv_msg->msgid = (msg->rsp[2] >> 2); + recv_msg->msg.netfn = msg->rsp[0] >> 2; + recv_msg->msg.cmd = msg->rsp[3]; + recv_msg->msg.data = recv_msg->msg_data; + + recv_msg->msg.data_len = msg->rsp_size - 4; + memcpy(recv_msg->msg_data, msg->rsp + 4, + msg->rsp_size - 4); + if (deliver_response(intf, recv_msg)) + ipmi_inc_stat(intf, unhandled_commands); + else + ipmi_inc_stat(intf, handled_commands); + } + } + + return rv; +} + +static int handle_ipmb_direct_rcv_rsp(struct ipmi_smi *intf, + struct ipmi_smi_msg *msg) +{ + struct ipmi_recv_msg *recv_msg; + struct ipmi_ipmb_direct_addr *daddr; + + recv_msg = (struct ipmi_recv_msg *) msg->user_data; + if (recv_msg == NULL) { + dev_warn(intf->si_dev, + "IPMI message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); + return 0; + } + + recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE; + recv_msg->msgid = msg->msgid; + daddr = (struct ipmi_ipmb_direct_addr *) &recv_msg->addr; + daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE; + daddr->channel = 0; + daddr->slave_addr = msg->rsp[1]; + daddr->rq_lun = msg->rsp[0] & 3; + daddr->rs_lun = msg->rsp[2] & 3; + recv_msg->msg.netfn = msg->rsp[0] >> 2; + recv_msg->msg.cmd = msg->rsp[3]; + memcpy(recv_msg->msg_data, &msg->rsp[4], msg->rsp_size - 4); + recv_msg->msg.data = recv_msg->msg_data; + recv_msg->msg.data_len = msg->rsp_size - 4; + deliver_local_response(intf, recv_msg); + + return 0; +} + static int handle_lan_get_msg_rsp(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { @@ -4227,18 +4435,40 @@ static int handle_bmc_rsp(struct ipmi_smi *intf, static int handle_one_recv_msg(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { - int requeue; + int requeue = 0; int chan; + unsigned char cc; + bool is_cmd = !((msg->rsp[0] >> 2) & 1); pr_debug("Recv: %*ph\n", msg->rsp_size, msg->rsp); - if ((msg->data_size >= 2) + if (msg->rsp_size < 2) { + /* Message is too small to be correct. */ + dev_warn(intf->si_dev, + "BMC returned too small a message for netfn %x cmd %x, got %d bytes\n", + (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp_size); + +return_unspecified: + /* Generate an error response for the message. */ + msg->rsp[0] = msg->data[0] | (1 << 2); + msg->rsp[1] = msg->data[1]; + msg->rsp[2] = IPMI_ERR_UNSPECIFIED; + msg->rsp_size = 3; + } else if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { + /* commands must have at least 3 bytes, responses 4. */ + if (is_cmd && (msg->rsp_size < 3)) { + ipmi_inc_stat(intf, invalid_commands); + goto out; + } + if (!is_cmd && (msg->rsp_size < 4)) + goto return_unspecified; + } else if ((msg->data_size >= 2) && (msg->data[0] == (IPMI_NETFN_APP_REQUEST << 2)) && (msg->data[1] == IPMI_SEND_MSG_CMD) && (msg->user_data == NULL)) { if (intf->in_shutdown) - goto free_msg; + goto out; /* * This is the local response to a command send, start @@ -4273,21 +4503,6 @@ static int handle_one_recv_msg(struct ipmi_smi *intf, } else /* The message was sent, start the timer. */ intf_start_seq_timer(intf, msg->msgid); -free_msg: - requeue = 0; - goto out; - - } else if (msg->rsp_size < 2) { - /* Message is too small to be correct. */ - dev_warn(intf->si_dev, - "BMC returned too small a message for netfn %x cmd %x, got %d bytes\n", - (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp_size); - - /* Generate an error response for the message. */ - msg->rsp[0] = msg->data[0] | (1 << 2); - msg->rsp[1] = msg->data[1]; - msg->rsp[2] = IPMI_ERR_UNSPECIFIED; - msg->rsp_size = 3; } else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1)) || (msg->rsp[1] != msg->data[1])) { /* @@ -4299,39 +4514,46 @@ free_msg: (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp[0] >> 2, msg->rsp[1]); - /* Generate an error response for the message. */ - msg->rsp[0] = msg->data[0] | (1 << 2); - msg->rsp[1] = msg->data[1]; - msg->rsp[2] = IPMI_ERR_UNSPECIFIED; - msg->rsp_size = 3; + goto return_unspecified; } - if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) - && (msg->rsp[1] == IPMI_SEND_MSG_CMD) - && (msg->user_data != NULL)) { + if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { + if ((msg->data[0] >> 2) & 1) { + /* It's a response to a sent response. */ + chan = 0; + cc = msg->rsp[4]; + goto process_response_response; + } + if (is_cmd) + requeue = handle_ipmb_direct_rcv_cmd(intf, msg); + else + requeue = handle_ipmb_direct_rcv_rsp(intf, msg); + } else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) + && (msg->rsp[1] == IPMI_SEND_MSG_CMD) + && (msg->user_data != NULL)) { /* * It's a response to a response we sent. For this we * deliver a send message response to the user. */ - struct ipmi_recv_msg *recv_msg = msg->user_data; - - requeue = 0; - if (msg->rsp_size < 2) - /* Message is too small to be correct. */ - goto out; + struct ipmi_recv_msg *recv_msg; chan = msg->data[2] & 0x0f; if (chan >= IPMI_MAX_CHANNELS) /* Invalid channel number */ goto out; + cc = msg->rsp[2]; +process_response_response: + recv_msg = msg->user_data; + + requeue = 0; if (!recv_msg) goto out; recv_msg->recv_type = IPMI_RESPONSE_RESPONSE_TYPE; recv_msg->msg.data = recv_msg->msg_data; + recv_msg->msg_data[0] = cc; recv_msg->msg.data_len = 1; - recv_msg->msg_data[0] = msg->rsp[2]; deliver_local_response(intf, recv_msg); } else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) && (msg->rsp[1] == IPMI_GET_MSG_CMD)) { diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index deec18b8944a..9277d21c2690 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -38,6 +38,59 @@ struct ipmi_smi; #define IPMI_WATCH_MASK_CHECK_WATCHDOG (1 << 1) #define IPMI_WATCH_MASK_CHECK_COMMANDS (1 << 2) +/* + * SMI messages + * + * When communicating with an SMI, messages come in two formats: + * + * * Normal (to a BMC over a BMC interface) + * + * * IPMB (over a IPMB to another MC) + * + * When normal, commands are sent using the format defined by a + * standard message over KCS (NetFn must be even): + * + * +-----------+-----+------+ + * | NetFn/LUN | Cmd | Data | + * +-----------+-----+------+ + * + * And responses, similarly, with an completion code added (NetFn must + * be odd): + * + * +-----------+-----+------+------+ + * | NetFn/LUN | Cmd | CC | Data | + * +-----------+-----+------+------+ + * + * With normal messages, only commands are sent and only responses are + * received. + * + * In IPMB mode, we are acting as an IPMB device. Commands will be in + * the following format (NetFn must be even): + * + * +-------------+------+-------------+-----+------+ + * | NetFn/rsLUN | Addr | rqSeq/rqLUN | Cmd | Data | + * +-------------+------+-------------+-----+------+ + * + * Responses will using the following format: + * + * +-------------+------+-------------+-----+------+------+ + * | NetFn/rqLUN | Addr | rqSeq/rsLUN | Cmd | CC | Data | + * +-------------+------+-------------+-----+------+------+ + * + * This is similar to the format defined in the IPMB manual section + * 2.11.1 with the checksums and the first address removed. Also, the + * address is always the remote address. + * + * IPMB messages can be commands and responses in both directions. + * Received commands are handled as received commands from the message + * queue. + */ + +enum ipmi_smi_msg_type { + IPMI_SMI_MSG_TYPE_NORMAL = 0, + IPMI_SMI_MSG_TYPE_IPMB_DIRECT +}; + /* * Messages to/from the lower layer. The smi interface will take one * of these to send. After the send has occurred and a response has @@ -54,6 +107,8 @@ struct ipmi_smi; struct ipmi_smi_msg { struct list_head link; + enum ipmi_smi_msg_type type; + long msgid; void *user_data; @@ -73,6 +128,10 @@ struct ipmi_smi_msg { struct ipmi_smi_handlers { struct module *owner; + /* Capabilities of the SMI. */ +#define IPMI_SMI_CAN_HANDLE_IPMB_DIRECT (1 << 0) + unsigned int flags; + /* * The low-level interface cannot start sending messages to * the upper layer until this function is called. This may diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index 007e65f9243b..966c3070959b 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -80,6 +80,20 @@ struct ipmi_ipmb_addr { unsigned char lun; }; +/* + * Used for messages received directly from an IPMB that have not gone + * through a MC. This is for systems that sit right on an IPMB so + * they can receive commands and respond to them. + */ +#define IPMI_IPMB_DIRECT_ADDR_TYPE 0x81 +struct ipmi_ipmb_direct_addr { + int addr_type; + short channel; + unsigned char slave_addr; + unsigned char rs_lun; + unsigned char rq_lun; +}; + /* * A LAN Address. This is an address to/from a LAN interface bridged * by the BMC, not an address actually out on the LAN. -- cgit v1.2.3 From 29a9f27574692a71c04fd41ca4bbf8eae842af13 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Thu, 23 Sep 2021 16:41:27 +0800 Subject: virt: acrn: Introduce interfaces for MMIO device passthrough MMIO device passthrough enables an OS in a virtual machine to directly access a MMIO device in the host. It promises almost the native performance, which is required in performance-critical scenarios of ACRN. HSM provides the following ioctls: - Assign - ACRN_IOCTL_ASSIGN_MMIODEV Pass data struct acrn_mmiodev from userspace to the hypervisor, and inform the hypervisor to assign a MMIO device to a User VM. - De-assign - ACRN_IOCTL_DEASSIGN_PCIDEV Pass data struct acrn_mmiodev from userspace to the hypervisor, and inform the hypervisor to de-assign a MMIO device from a User VM. These new APIs will be used by user space code vm_assign_mmiodev and vm_deassign_mmiodev in https://github.com/projectacrn/acrn-hypervisor/blob/master/devicemodel/core/vmmapi.c Signed-off-by: Shuo Liu Signed-off-by: Fei Li Link: https://lore.kernel.org/r/20210923084128.18902-2-fei1.li@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 25 +++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 28 ++++++++++++++++++++++++++++ 3 files changed, 79 insertions(+) (limited to 'include/uapi') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 130e12b8652a..f567ca59d7c2 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -114,6 +114,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_ptdev_irq *irq_info; struct acrn_ioeventfd ioeventfd; struct acrn_vm_memmap memmap; + struct acrn_mmiodev *mmiodev; struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; struct acrn_irqfd irqfd; @@ -217,6 +218,30 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_vm_memseg_unmap(vm, &memmap); break; + case ACRN_IOCTL_ASSIGN_MMIODEV: + mmiodev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_mmiodev)); + if (IS_ERR(mmiodev)) + return PTR_ERR(mmiodev); + + ret = hcall_assign_mmiodev(vm->vmid, virt_to_phys(mmiodev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to assign MMIO device!\n"); + kfree(mmiodev); + break; + case ACRN_IOCTL_DEASSIGN_MMIODEV: + mmiodev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_mmiodev)); + if (IS_ERR(mmiodev)) + return PTR_ERR(mmiodev); + + ret = hcall_deassign_mmiodev(vm->vmid, virt_to_phys(mmiodev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to deassign MMIO device!\n"); + kfree(mmiodev); + break; case ACRN_IOCTL_ASSIGN_PCIDEV: pcidev = memdup_user((void __user *)ioctl_param, sizeof(struct acrn_pcidev)); diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index 0cfad05bd1a9..f0c78e52cebb 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -41,6 +41,8 @@ #define HC_RESET_PTDEV_INTR _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x04) #define HC_ASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05) #define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) +#define HC_ASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x07) +#define HC_DEASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x08) #define HC_ID_PM_BASE 0x80UL #define HC_PM_GET_CPU_STATE _HC_ID(HC_ID, HC_ID_PM_BASE + 0x00) @@ -194,6 +196,30 @@ static inline long hcall_set_memory_regions(u64 regions_pa) return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); } +/** + * hcall_assign_mmiodev() - Assign a MMIO device to a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_mmiodev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_assign_mmiodev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_ASSIGN_MMIODEV, vmid, addr); +} + +/** + * hcall_deassign_mmiodev() - De-assign a PCI device from a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_mmiodev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_deassign_mmiodev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_DEASSIGN_MMIODEV, vmid, addr); +} + /** * hcall_assign_pcidev() - Assign a PCI device to a User VM * @vmid: User VM ID diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 353b2a2e4536..470036d6b1ac 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -396,6 +396,7 @@ struct acrn_ptdev_irq { /* Type of PCI device assignment */ #define ACRN_PTDEV_QUIRK_ASSIGN (1U << 0) +#define ACRN_MMIODEV_RES_NUM 3 #define ACRN_PCI_NUM_BARS 6 /** * struct acrn_pcidev - Info for assigning or de-assigning a PCI device @@ -417,6 +418,29 @@ struct acrn_pcidev { __u32 bar[ACRN_PCI_NUM_BARS]; }; +/** + * struct acrn_mmiodev - Info for assigning or de-assigning a MMIO device + * @name: Name of the MMIO device. + * @res[].user_vm_pa: Physical address of User VM of the MMIO region + * for the MMIO device. + * @res[].service_vm_pa: Physical address of Service VM of the MMIO + * region for the MMIO device. + * @res[].size: Size of the MMIO region for the MMIO device. + * @res[].mem_type: Memory type of the MMIO region for the MMIO + * device. + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_mmiodev { + __u8 name[8]; + struct { + __u64 user_vm_pa; + __u64 service_vm_pa; + __u64 size; + __u64 mem_type; + } res[ACRN_MMIODEV_RES_NUM]; +}; + /** * struct acrn_msi_entry - Info for injecting a MSI interrupt to a VM * @msi_addr: MSI addr[19:12] with dest vCPU ID @@ -568,6 +592,10 @@ struct acrn_irqfd { _IOW(ACRN_IOCTL_TYPE, 0x55, struct acrn_pcidev) #define ACRN_IOCTL_DEASSIGN_PCIDEV \ _IOW(ACRN_IOCTL_TYPE, 0x56, struct acrn_pcidev) +#define ACRN_IOCTL_ASSIGN_MMIODEV \ + _IOW(ACRN_IOCTL_TYPE, 0x57, struct acrn_mmiodev) +#define ACRN_IOCTL_DEASSIGN_MMIODEV \ + _IOW(ACRN_IOCTL_TYPE, 0x58, struct acrn_mmiodev) #define ACRN_IOCTL_PM_GET_CPU_STATE \ _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) -- cgit v1.2.3 From 424f1ac2d832f31a2814c799bd50decf6a9f8e74 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Thu, 23 Sep 2021 16:41:28 +0800 Subject: virt: acrn: Introduce interfaces for virtual device creating/destroying The ACRN hypervisor can emulate a virtual device within hypervisor for a Guest VM. The emulated virtual device can work without the ACRN userspace after creation. The hypervisor do the emulation of that device. To support the virtual device creating/destroying, HSM provides the following ioctls: - ACRN_IOCTL_CREATE_VDEV Pass data struct acrn_vdev from userspace to the hypervisor, and inform the hypervisor to create a virtual device for a User VM. - ACRN_IOCTL_DESTROY_VDEV Pass data struct acrn_vdev from userspace to the hypervisor, and inform the hypervisor to destroy a virtual device of a User VM. These new APIs will be used by user space code vm_add_hv_vdev and vm_remove_hv_vdev in https://github.com/projectacrn/acrn-hypervisor/blob/master/devicemodel/core/vmmapi.c Signed-off-by: Shuo Liu Signed-off-by: Fei Li Link: https://lore.kernel.org/r/20210923084128.18902-3-fei1.li@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 24 ++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 92 insertions(+) (limited to 'include/uapi') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index f567ca59d7c2..5419794fccf1 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -118,6 +118,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; struct acrn_irqfd irqfd; + struct acrn_vdev *vdev; struct page *page; u64 cstate_cmd; int i, ret = 0; @@ -266,6 +267,29 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, "Failed to deassign pci device!\n"); kfree(pcidev); break; + case ACRN_IOCTL_CREATE_VDEV: + vdev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vdev)); + if (IS_ERR(vdev)) + return PTR_ERR(vdev); + + ret = hcall_create_vdev(vm->vmid, virt_to_phys(vdev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to create virtual device!\n"); + kfree(vdev); + break; + case ACRN_IOCTL_DESTROY_VDEV: + vdev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vdev)); + if (IS_ERR(vdev)) + return PTR_ERR(vdev); + ret = hcall_destroy_vdev(vm->vmid, virt_to_phys(vdev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to destroy virtual device!\n"); + kfree(vdev); + break; case ACRN_IOCTL_SET_PTDEV_INTR: irq_info = memdup_user((void __user *)ioctl_param, sizeof(struct acrn_ptdev_irq)); diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index f0c78e52cebb..71d300821a18 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -43,6 +43,8 @@ #define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) #define HC_ASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x07) #define HC_DEASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x08) +#define HC_CREATE_VDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x09) +#define HC_DESTROY_VDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x0A) #define HC_ID_PM_BASE 0x80UL #define HC_PM_GET_CPU_STATE _HC_ID(HC_ID, HC_ID_PM_BASE + 0x00) @@ -196,6 +198,30 @@ static inline long hcall_set_memory_regions(u64 regions_pa) return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); } +/** + * hcall_create_vdev() - Create a virtual device for a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_vdev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_create_vdev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_CREATE_VDEV, vmid, addr); +} + +/** + * hcall_destroy_vdev() - Destroy a virtual device of a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_vdev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_destroy_vdev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_DESTROY_VDEV, vmid, addr); +} + /** * hcall_assign_mmiodev() - Assign a MMIO device to a User VM * @vmid: User VM ID diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 470036d6b1ac..ccf47ed92500 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -441,6 +441,44 @@ struct acrn_mmiodev { } res[ACRN_MMIODEV_RES_NUM]; }; +/** + * struct acrn_vdev - Info for creating or destroying a virtual device + * @id: Union of identifier of the virtual device + * @id.value: Raw data of the identifier + * @id.fields.vendor: Vendor id of the virtual PCI device + * @id.fields.device: Device id of the virtual PCI device + * @id.fields.legacy_id: ID of the virtual device if not a PCI device + * @slot: Virtual Bus/Device/Function of the virtual + * device + * @io_base: IO resource base address of the virtual device + * @io_size: IO resource size of the virtual device + * @args: Arguments for the virtual device creation + * + * The created virtual device can be a PCI device or a legacy device (e.g. + * a virtual UART controller) and it is emulated by the hypervisor. This + * structure will be passed to hypervisor directly. + */ +struct acrn_vdev { + /* + * the identifier of the device, the low 32 bits represent the vendor + * id and device id of PCI device and the high 32 bits represent the + * device number of the legacy device + */ + union { + __u64 value; + struct { + __le16 vendor; + __le16 device; + __le32 legacy_id; + } fields; + } id; + + __u64 slot; + __u32 io_addr[ACRN_PCI_NUM_BARS]; + __u32 io_size[ACRN_PCI_NUM_BARS]; + __u8 args[128]; +}; + /** * struct acrn_msi_entry - Info for injecting a MSI interrupt to a VM * @msi_addr: MSI addr[19:12] with dest vCPU ID @@ -596,6 +634,10 @@ struct acrn_irqfd { _IOW(ACRN_IOCTL_TYPE, 0x57, struct acrn_mmiodev) #define ACRN_IOCTL_DEASSIGN_MMIODEV \ _IOW(ACRN_IOCTL_TYPE, 0x58, struct acrn_mmiodev) +#define ACRN_IOCTL_CREATE_VDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x59, struct acrn_vdev) +#define ACRN_IOCTL_DESTROY_VDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x5A, struct acrn_vdev) #define ACRN_IOCTL_PM_GET_CPU_STATE \ _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) -- cgit v1.2.3 From 2a152512a155aaf27c3e67834ffafaed9525a7b5 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 3 Oct 2021 13:56:04 +0300 Subject: RDMA/efa: CQ notifications This patch adds support for CQ notifications through the standard verbs api. In order to achieve that, a new event queue (EQ) object is introduced, which is in charge of reporting completion events to the driver. On driver load, EQs are allocated and their affinity is set to a single cpu. When a user app creates a CQ with a completion channel, the completion vector number is converted to a EQ number, which is in charge of reporting the CQ events. In addition, the CQ creation admin command now returns an offset for the CQ doorbell, which is mapped to the userspace provider and is used to arm the CQ when requested by the user. The EQs use a single doorbell (located on the registers BAR), which encodes the EQ number and arm as part of the doorbell value. The EQs are polled by the driver on each new EQE, and arm it when the poll is completed. Link: https://lore.kernel.org/r/20211003105605.29222-1-galpress@amazon.com Reviewed-by: Firas JahJah Reviewed-by: Yossi Leybovich Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/efa/efa.h | 19 ++- drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 100 ++++++++++++- drivers/infiniband/hw/efa/efa_admin_defs.h | 41 ++++++ drivers/infiniband/hw/efa/efa_com.c | 164 +++++++++++++++++++++ drivers/infiniband/hw/efa/efa_com.h | 38 ++++- drivers/infiniband/hw/efa/efa_com_cmd.c | 35 +++-- drivers/infiniband/hw/efa/efa_com_cmd.h | 10 +- drivers/infiniband/hw/efa/efa_main.c | 181 ++++++++++++++++++++---- drivers/infiniband/hw/efa/efa_regs_defs.h | 7 +- drivers/infiniband/hw/efa/efa_verbs.c | 67 ++++++++- include/uapi/rdma/efa-abi.h | 18 ++- 11 files changed, 625 insertions(+), 55 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h index 87b1dadeb7fe..e0c9ba4c70f4 100644 --- a/drivers/infiniband/hw/efa/efa.h +++ b/drivers/infiniband/hw/efa/efa.h @@ -20,14 +20,14 @@ #define EFA_IRQNAME_SIZE 40 -/* 1 for AENQ + ADMIN */ -#define EFA_NUM_MSIX_VEC 1 #define EFA_MGMNT_MSIX_VEC_IDX 0 +#define EFA_COMP_EQS_VEC_BASE 1 struct efa_irq { irq_handler_t handler; void *data; u32 irqn; + u32 vector; cpumask_t affinity_hint_mask; char name[EFA_IRQNAME_SIZE]; }; @@ -61,6 +61,13 @@ struct efa_dev { struct efa_irq admin_irq; struct efa_stats stats; + + /* Array of completion EQs */ + struct efa_eq *eqs; + unsigned int neqs; + + /* Only stores CQs with interrupts enabled */ + struct xarray cqs_xa; }; struct efa_ucontext { @@ -84,8 +91,11 @@ struct efa_cq { dma_addr_t dma_addr; void *cpu_addr; struct rdma_user_mmap_entry *mmap_entry; + struct rdma_user_mmap_entry *db_mmap_entry; size_t size; u16 cq_idx; + /* NULL when no interrupts requested */ + struct efa_eq *eq; }; struct efa_qp { @@ -116,6 +126,11 @@ struct efa_ah { u8 id[EFA_GID_SIZE]; }; +struct efa_eq { + struct efa_com_eq eeq; + struct efa_irq irq; +}; + int efa_query_device(struct ib_device *ibdev, struct ib_device_attr *props, struct ib_udata *udata); diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h index fa38b34eddb8..0b0b93b529f3 100644 --- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h +++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h @@ -28,7 +28,9 @@ enum efa_admin_aq_opcode { EFA_ADMIN_DEALLOC_PD = 15, EFA_ADMIN_ALLOC_UAR = 16, EFA_ADMIN_DEALLOC_UAR = 17, - EFA_ADMIN_MAX_OPCODE = 17, + EFA_ADMIN_CREATE_EQ = 18, + EFA_ADMIN_DESTROY_EQ = 19, + EFA_ADMIN_MAX_OPCODE = 19, }; enum efa_admin_aq_feature_id { @@ -38,6 +40,7 @@ enum efa_admin_aq_feature_id { EFA_ADMIN_QUEUE_ATTR = 4, EFA_ADMIN_HW_HINTS = 5, EFA_ADMIN_HOST_INFO = 6, + EFA_ADMIN_EVENT_QUEUE_ATTR = 7, }; /* QP transport type */ @@ -430,8 +433,8 @@ struct efa_admin_create_cq_cmd { /* * 4:0 : reserved5 - MBZ * 5 : interrupt_mode_enabled - if set, cq operates - * in interrupt mode (i.e. CQ events and MSI-X are - * generated), otherwise - polling + * in interrupt mode (i.e. CQ events and EQ elements + * are generated), otherwise - polling * 6 : virt - If set, ring base address is virtual * (IOVA returned by MR registration) * 7 : reserved6 - MBZ @@ -448,8 +451,11 @@ struct efa_admin_create_cq_cmd { /* completion queue depth in # of entries. must be power of 2 */ u16 cq_depth; - /* msix vector assigned to this cq */ - u32 msix_vector_idx; + /* EQ number assigned to this cq */ + u16 eqn; + + /* MBZ */ + u16 reserved; /* * CQ ring base address, virtual or physical depending on 'virt' @@ -480,6 +486,15 @@ struct efa_admin_create_cq_resp { /* actual cq depth in number of entries */ u16 cq_actual_depth; + + /* CQ doorbell address, as offset to PCIe DB BAR */ + u32 db_offset; + + /* + * 0 : db_valid - If set, doorbell offset is valid. + * Always set when interrupts are requested. + */ + u32 flags; }; struct efa_admin_destroy_cq_cmd { @@ -669,6 +684,17 @@ struct efa_admin_feature_queue_attr_desc { u16 max_tx_batch; }; +struct efa_admin_event_queue_attr_desc { + /* The maximum number of event queues supported */ + u32 max_eq; + + /* Maximum number of EQEs per Event Queue */ + u32 max_eq_depth; + + /* Supported events bitmask */ + u32 event_bitmask; +}; + struct efa_admin_feature_aenq_desc { /* bitmask for AENQ groups the device can report */ u32 supported_groups; @@ -727,6 +753,8 @@ struct efa_admin_get_feature_resp { struct efa_admin_feature_queue_attr_desc queue_attr; + struct efa_admin_event_queue_attr_desc event_queue_attr; + struct efa_admin_hw_hints hw_hints; } u; }; @@ -810,6 +838,60 @@ struct efa_admin_dealloc_uar_resp { struct efa_admin_acq_common_desc acq_common_desc; }; +struct efa_admin_create_eq_cmd { + struct efa_admin_aq_common_desc aq_common_descriptor; + + /* Size of the EQ in entries, must be power of 2 */ + u16 depth; + + /* MSI-X table entry index */ + u8 msix_vec; + + /* + * 4:0 : entry_size_words - size of EQ entry in + * 32-bit words + * 7:5 : reserved - MBZ + */ + u8 caps; + + /* EQ ring base address */ + struct efa_common_mem_addr ba; + + /* + * Enabled events on this EQ + * 0 : completion_events - Enable completion events + * 31:1 : reserved - MBZ + */ + u32 event_bitmask; + + /* MBZ */ + u32 reserved; +}; + +struct efa_admin_create_eq_resp { + struct efa_admin_acq_common_desc acq_common_desc; + + /* EQ number */ + u16 eqn; + + /* MBZ */ + u16 reserved; +}; + +struct efa_admin_destroy_eq_cmd { + struct efa_admin_aq_common_desc aq_common_descriptor; + + /* EQ number */ + u16 eqn; + + /* MBZ */ + u16 reserved; +}; + +struct efa_admin_destroy_eq_resp { + struct efa_admin_acq_common_desc acq_common_desc; +}; + /* asynchronous event notification groups */ enum efa_admin_aenq_group { EFA_ADMIN_FATAL_ERROR = 1, @@ -899,10 +981,18 @@ struct efa_admin_host_info { #define EFA_ADMIN_CREATE_CQ_CMD_VIRT_MASK BIT(6) #define EFA_ADMIN_CREATE_CQ_CMD_CQ_ENTRY_SIZE_WORDS_MASK GENMASK(4, 0) +/* create_cq_resp */ +#define EFA_ADMIN_CREATE_CQ_RESP_DB_VALID_MASK BIT(0) + /* feature_device_attr_desc */ #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK BIT(0) #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RNR_RETRY_MASK BIT(1) +/* create_eq_cmd */ +#define EFA_ADMIN_CREATE_EQ_CMD_ENTRY_SIZE_WORDS_MASK GENMASK(4, 0) +#define EFA_ADMIN_CREATE_EQ_CMD_VIRT_MASK BIT(6) +#define EFA_ADMIN_CREATE_EQ_CMD_COMPLETION_EVENTS_MASK BIT(0) + /* host_info */ #define EFA_ADMIN_HOST_INFO_DRIVER_MODULE_TYPE_MASK GENMASK(7, 0) #define EFA_ADMIN_HOST_INFO_DRIVER_SUB_MINOR_MASK GENMASK(15, 8) diff --git a/drivers/infiniband/hw/efa/efa_admin_defs.h b/drivers/infiniband/hw/efa/efa_admin_defs.h index 78ff9389ae25..83f20c38a840 100644 --- a/drivers/infiniband/hw/efa/efa_admin_defs.h +++ b/drivers/infiniband/hw/efa/efa_admin_defs.h @@ -118,6 +118,43 @@ struct efa_admin_aenq_entry { u32 inline_data_w4[12]; }; +enum efa_admin_eqe_event_type { + EFA_ADMIN_EQE_EVENT_TYPE_COMPLETION = 0, +}; + +/* Completion event */ +struct efa_admin_comp_event { + /* CQ number */ + u16 cqn; + + /* MBZ */ + u16 reserved; + + /* MBZ */ + u32 reserved2; +}; + +/* Event Queue Element */ +struct efa_admin_eqe { + /* + * 0 : phase + * 8:1 : event_type - Event type + * 31:9 : reserved - MBZ + */ + u32 common; + + /* MBZ */ + u32 reserved; + + union { + /* Event data */ + u32 event_data[2]; + + /* Completion Event */ + struct efa_admin_comp_event comp_event; + } u; +}; + /* aq_common_desc */ #define EFA_ADMIN_AQ_COMMON_DESC_COMMAND_ID_MASK GENMASK(11, 0) #define EFA_ADMIN_AQ_COMMON_DESC_PHASE_MASK BIT(0) @@ -131,4 +168,8 @@ struct efa_admin_aenq_entry { /* aenq_common_desc */ #define EFA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK BIT(0) +/* eqe */ +#define EFA_ADMIN_EQE_PHASE_MASK BIT(0) +#define EFA_ADMIN_EQE_EVENT_TYPE_MASK GENMASK(8, 1) + #endif /* _EFA_ADMIN_H_ */ diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c index 0d523ad736c7..16a24a05fc2a 100644 --- a/drivers/infiniband/hw/efa/efa_com.c +++ b/drivers/infiniband/hw/efa/efa_com.c @@ -56,11 +56,19 @@ static const char *efa_com_cmd_str(u8 cmd) EFA_CMD_STR_CASE(DEALLOC_PD); EFA_CMD_STR_CASE(ALLOC_UAR); EFA_CMD_STR_CASE(DEALLOC_UAR); + EFA_CMD_STR_CASE(CREATE_EQ); + EFA_CMD_STR_CASE(DESTROY_EQ); default: return "unknown command opcode"; } #undef EFA_CMD_STR_CASE } +void efa_com_set_dma_addr(dma_addr_t addr, u32 *addr_high, u32 *addr_low) +{ + *addr_low = lower_32_bits(addr); + *addr_high = upper_32_bits(addr); +} + static u32 efa_com_reg_read32(struct efa_com_dev *edev, u16 offset) { struct efa_com_mmio_read *mmio_read = &edev->mmio_read; @@ -1081,3 +1089,159 @@ int efa_com_dev_reset(struct efa_com_dev *edev, return 0; } + +static int efa_com_create_eq(struct efa_com_dev *edev, + struct efa_com_create_eq_params *params, + struct efa_com_create_eq_result *result) +{ + struct efa_com_admin_queue *aq = &edev->aq; + struct efa_admin_create_eq_resp resp = {}; + struct efa_admin_create_eq_cmd cmd = {}; + int err; + + cmd.aq_common_descriptor.opcode = EFA_ADMIN_CREATE_EQ; + EFA_SET(&cmd.caps, EFA_ADMIN_CREATE_EQ_CMD_ENTRY_SIZE_WORDS, + params->entry_size_in_bytes / 4); + cmd.depth = params->depth; + cmd.event_bitmask = params->event_bitmask; + cmd.msix_vec = params->msix_vec; + + efa_com_set_dma_addr(params->dma_addr, &cmd.ba.mem_addr_high, + &cmd.ba.mem_addr_low); + + err = efa_com_cmd_exec(aq, + (struct efa_admin_aq_entry *)&cmd, + sizeof(cmd), + (struct efa_admin_acq_entry *)&resp, + sizeof(resp)); + if (err) { + ibdev_err_ratelimited(edev->efa_dev, + "Failed to create eq[%d]\n", err); + return err; + } + + result->eqn = resp.eqn; + + return 0; +} + +static void efa_com_destroy_eq(struct efa_com_dev *edev, + struct efa_com_destroy_eq_params *params) +{ + struct efa_com_admin_queue *aq = &edev->aq; + struct efa_admin_destroy_eq_resp resp = {}; + struct efa_admin_destroy_eq_cmd cmd = {}; + int err; + + cmd.aq_common_descriptor.opcode = EFA_ADMIN_DESTROY_EQ; + cmd.eqn = params->eqn; + + err = efa_com_cmd_exec(aq, + (struct efa_admin_aq_entry *)&cmd, + sizeof(cmd), + (struct efa_admin_acq_entry *)&resp, + sizeof(resp)); + if (err) + ibdev_err_ratelimited(edev->efa_dev, + "Failed to destroy EQ-%u [%d]\n", cmd.eqn, + err); +} + +static void efa_com_arm_eq(struct efa_com_dev *edev, struct efa_com_eq *eeq) +{ + u32 val = 0; + + EFA_SET(&val, EFA_REGS_EQ_DB_EQN, eeq->eqn); + EFA_SET(&val, EFA_REGS_EQ_DB_ARM, 1); + + writel(val, edev->reg_bar + EFA_REGS_EQ_DB_OFF); +} + +void efa_com_eq_comp_intr_handler(struct efa_com_dev *edev, + struct efa_com_eq *eeq) +{ + struct efa_admin_eqe *eqe; + u32 processed = 0; + u8 phase; + u32 ci; + + ci = eeq->cc & (eeq->depth - 1); + phase = eeq->phase; + eqe = &eeq->eqes[ci]; + + /* Go over all the events */ + while ((READ_ONCE(eqe->common) & EFA_ADMIN_EQE_PHASE_MASK) == phase) { + /* + * Do not read the rest of the completion entry before the + * phase bit was validated + */ + dma_rmb(); + + eeq->cb(eeq, eqe); + + /* Get next event entry */ + ci++; + processed++; + + if (ci == eeq->depth) { + ci = 0; + phase = !phase; + } + + eqe = &eeq->eqes[ci]; + } + + eeq->cc += processed; + eeq->phase = phase; + efa_com_arm_eq(eeq->edev, eeq); +} + +void efa_com_eq_destroy(struct efa_com_dev *edev, struct efa_com_eq *eeq) +{ + struct efa_com_destroy_eq_params params = { + .eqn = eeq->eqn, + }; + + efa_com_destroy_eq(edev, ¶ms); + dma_free_coherent(edev->dmadev, eeq->depth * sizeof(*eeq->eqes), + eeq->eqes, eeq->dma_addr); +} + +int efa_com_eq_init(struct efa_com_dev *edev, struct efa_com_eq *eeq, + efa_eqe_handler cb, u16 depth, u8 msix_vec) +{ + struct efa_com_create_eq_params params = {}; + struct efa_com_create_eq_result result = {}; + int err; + + params.depth = depth; + params.entry_size_in_bytes = sizeof(*eeq->eqes); + EFA_SET(¶ms.event_bitmask, + EFA_ADMIN_CREATE_EQ_CMD_COMPLETION_EVENTS, 1); + params.msix_vec = msix_vec; + + eeq->eqes = dma_alloc_coherent(edev->dmadev, + params.depth * sizeof(*eeq->eqes), + ¶ms.dma_addr, GFP_KERNEL); + if (!eeq->eqes) + return -ENOMEM; + + err = efa_com_create_eq(edev, ¶ms, &result); + if (err) + goto err_free_coherent; + + eeq->eqn = result.eqn; + eeq->edev = edev; + eeq->dma_addr = params.dma_addr; + eeq->phase = 1; + eeq->depth = params.depth; + eeq->cb = cb; + efa_com_arm_eq(edev, eeq); + + return 0; + +err_free_coherent: + dma_free_coherent(edev->dmadev, params.depth * sizeof(*eeq->eqes), + eeq->eqes, params.dma_addr); + return err; +} diff --git a/drivers/infiniband/hw/efa/efa_com.h b/drivers/infiniband/hw/efa/efa_com.h index 5e4c88877ddb..77282234ce68 100644 --- a/drivers/infiniband/hw/efa/efa_com.h +++ b/drivers/infiniband/hw/efa/efa_com.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_COM_H_ @@ -80,6 +80,9 @@ struct efa_com_admin_queue { }; struct efa_aenq_handlers; +struct efa_com_eq; +typedef void (*efa_eqe_handler)(struct efa_com_eq *eeq, + struct efa_admin_eqe *eqe); struct efa_com_aenq { struct efa_admin_aenq_entry *entries; @@ -112,6 +115,33 @@ struct efa_com_dev { struct efa_com_mmio_read mmio_read; }; +struct efa_com_eq { + struct efa_com_dev *edev; + struct efa_admin_eqe *eqes; + dma_addr_t dma_addr; + u32 cc; /* Consumer counter */ + u16 eqn; + u16 depth; + u8 phase; + efa_eqe_handler cb; +}; + +struct efa_com_create_eq_params { + dma_addr_t dma_addr; + u32 event_bitmask; + u16 depth; + u8 entry_size_in_bytes; + u8 msix_vec; +}; + +struct efa_com_create_eq_result { + u16 eqn; +}; + +struct efa_com_destroy_eq_params { + u16 eqn; +}; + typedef void (*efa_aenq_handler)(void *data, struct efa_admin_aenq_entry *aenq_e); @@ -121,9 +151,13 @@ struct efa_aenq_handlers { efa_aenq_handler unimplemented_handler; }; +void efa_com_set_dma_addr(dma_addr_t addr, u32 *addr_high, u32 *addr_low); int efa_com_admin_init(struct efa_com_dev *edev, struct efa_aenq_handlers *aenq_handlers); void efa_com_admin_destroy(struct efa_com_dev *edev); +int efa_com_eq_init(struct efa_com_dev *edev, struct efa_com_eq *eeq, + efa_eqe_handler cb, u16 depth, u8 msix_vec); +void efa_com_eq_destroy(struct efa_com_dev *edev, struct efa_com_eq *eeq); int efa_com_dev_reset(struct efa_com_dev *edev, enum efa_regs_reset_reason_types reset_reason); void efa_com_set_admin_polling_mode(struct efa_com_dev *edev, bool polling); @@ -140,5 +174,7 @@ int efa_com_cmd_exec(struct efa_com_admin_queue *aq, struct efa_admin_acq_entry *comp, size_t comp_size); void efa_com_aenq_intr_handler(struct efa_com_dev *edev, void *data); +void efa_com_eq_comp_intr_handler(struct efa_com_dev *edev, + struct efa_com_eq *eeq); #endif /* _EFA_COM_H_ */ diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c index f752ef64159c..fb405da4e1db 100644 --- a/drivers/infiniband/hw/efa/efa_com_cmd.c +++ b/drivers/infiniband/hw/efa/efa_com_cmd.c @@ -1,17 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause /* - * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. */ #include "efa_com.h" #include "efa_com_cmd.h" -void efa_com_set_dma_addr(dma_addr_t addr, u32 *addr_high, u32 *addr_low) -{ - *addr_low = lower_32_bits(addr); - *addr_high = upper_32_bits(addr); -} - int efa_com_create_qp(struct efa_com_dev *edev, struct efa_com_create_qp_params *params, struct efa_com_create_qp_result *res) @@ -157,7 +151,7 @@ int efa_com_create_cq(struct efa_com_dev *edev, struct efa_com_create_cq_params *params, struct efa_com_create_cq_result *result) { - struct efa_admin_create_cq_resp cmd_completion; + struct efa_admin_create_cq_resp cmd_completion = {}; struct efa_admin_create_cq_cmd create_cmd = {}; struct efa_com_admin_queue *aq = &edev->aq; int err; @@ -169,6 +163,11 @@ int efa_com_create_cq(struct efa_com_dev *edev, create_cmd.cq_depth = params->cq_depth; create_cmd.num_sub_cqs = params->num_sub_cqs; create_cmd.uar = params->uarn; + if (params->interrupt_mode_enabled) { + EFA_SET(&create_cmd.cq_caps_1, + EFA_ADMIN_CREATE_CQ_CMD_INTERRUPT_MODE_ENABLED, 1); + create_cmd.eqn = params->eqn; + } efa_com_set_dma_addr(params->dma_addr, &create_cmd.cq_ba.mem_addr_high, @@ -187,6 +186,9 @@ int efa_com_create_cq(struct efa_com_dev *edev, result->cq_idx = cmd_completion.cq_idx; result->actual_depth = params->cq_depth; + result->db_off = cmd_completion.db_offset; + result->db_valid = EFA_GET(&cmd_completion.flags, + EFA_ADMIN_CREATE_CQ_RESP_DB_VALID); return 0; } @@ -497,6 +499,23 @@ int efa_com_get_device_attr(struct efa_com_dev *edev, sizeof(resp.u.network_attr.addr)); result->mtu = resp.u.network_attr.mtu; + if (efa_com_check_supported_feature_id(edev, + EFA_ADMIN_EVENT_QUEUE_ATTR)) { + err = efa_com_get_feature(edev, &resp, + EFA_ADMIN_EVENT_QUEUE_ATTR); + if (err) { + ibdev_err_ratelimited( + edev->efa_dev, + "Failed to get event queue attributes %d\n", + err); + return err; + } + + result->max_eq = resp.u.event_queue_attr.max_eq; + result->max_eq_depth = resp.u.event_queue_attr.max_eq_depth; + result->event_bitmask = resp.u.event_queue_attr.event_bitmask; + } + return 0; } diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h index eea4ebfbe6ec..c33010bbf9e8 100644 --- a/drivers/infiniband/hw/efa/efa_com_cmd.h +++ b/drivers/infiniband/hw/efa/efa_com_cmd.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_COM_CMD_H_ @@ -73,7 +73,9 @@ struct efa_com_create_cq_params { u16 cq_depth; u16 num_sub_cqs; u16 uarn; + u16 eqn; u8 entry_size_in_bytes; + bool interrupt_mode_enabled; }; struct efa_com_create_cq_result { @@ -81,6 +83,8 @@ struct efa_com_create_cq_result { u16 cq_idx; /* actual cq depth in # of entries */ u16 actual_depth; + u32 db_off; + bool db_valid; }; struct efa_com_destroy_cq_params { @@ -125,6 +129,9 @@ struct efa_com_get_device_attr_result { u32 max_llq_size; u32 max_rdma_size; u32 device_caps; + u32 max_eq; + u32 max_eq_depth; + u32 event_bitmask; /* EQ events bitmask */ u16 sub_cqs_per_cq; u16 max_sq_sge; u16 max_rq_sge; @@ -260,7 +267,6 @@ union efa_com_get_stats_result { struct efa_com_rdma_read_stats rdma_read_stats; }; -void efa_com_set_dma_addr(dma_addr_t addr, u32 *addr_high, u32 *addr_low); int efa_com_create_qp(struct efa_com_dev *edev, struct efa_com_create_qp_params *params, struct efa_com_create_qp_result *res); diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index 417dea5f90cf..d2a445f6f8e5 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -67,6 +67,47 @@ static void efa_release_bars(struct efa_dev *dev, int bars_mask) pci_release_selected_regions(pdev, release_bars); } +static void efa_process_comp_eqe(struct efa_dev *dev, struct efa_admin_eqe *eqe) +{ + u16 cqn = eqe->u.comp_event.cqn; + struct efa_cq *cq; + + /* Safe to load as we're in irq and removal calls synchronize_irq() */ + cq = xa_load(&dev->cqs_xa, cqn); + if (unlikely(!cq)) { + ibdev_err_ratelimited(&dev->ibdev, + "Completion event on non-existent CQ[%u]", + cqn); + return; + } + + cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); +} + +static void efa_process_eqe(struct efa_com_eq *eeq, struct efa_admin_eqe *eqe) +{ + struct efa_dev *dev = container_of(eeq->edev, struct efa_dev, edev); + + if (likely(EFA_GET(&eqe->common, EFA_ADMIN_EQE_EVENT_TYPE) == + EFA_ADMIN_EQE_EVENT_TYPE_COMPLETION)) + efa_process_comp_eqe(dev, eqe); + else + ibdev_err_ratelimited(&dev->ibdev, + "Unknown event type received %lu", + EFA_GET(&eqe->common, + EFA_ADMIN_EQE_EVENT_TYPE)); +} + +static irqreturn_t efa_intr_msix_comp(int irq, void *data) +{ + struct efa_eq *eq = data; + struct efa_com_dev *edev = eq->eeq.edev; + + efa_com_eq_comp_intr_handler(edev, &eq->eeq); + + return IRQ_HANDLED; +} + static irqreturn_t efa_intr_msix_mgmnt(int irq, void *data) { struct efa_dev *dev = data; @@ -77,26 +118,43 @@ static irqreturn_t efa_intr_msix_mgmnt(int irq, void *data) return IRQ_HANDLED; } -static int efa_request_mgmnt_irq(struct efa_dev *dev) +static int efa_request_irq(struct efa_dev *dev, struct efa_irq *irq) { - struct efa_irq *irq; int err; - irq = &dev->admin_irq; err = request_irq(irq->irqn, irq->handler, 0, irq->name, irq->data); if (err) { - dev_err(&dev->pdev->dev, "Failed to request admin irq (%d)\n", - err); + dev_err(&dev->pdev->dev, "Failed to request irq %s (%d)\n", + irq->name, err); return err; } - dev_dbg(&dev->pdev->dev, "Set affinity hint of mgmnt irq to %*pbl (irq vector: %d)\n", - nr_cpumask_bits, &irq->affinity_hint_mask, irq->irqn); irq_set_affinity_hint(irq->irqn, &irq->affinity_hint_mask); return 0; } +static void efa_setup_comp_irq(struct efa_dev *dev, struct efa_eq *eq, + int vector) +{ + u32 cpu; + + cpu = vector - EFA_COMP_EQS_VEC_BASE; + snprintf(eq->irq.name, EFA_IRQNAME_SIZE, "efa-comp%d@pci:%s", cpu, + pci_name(dev->pdev)); + eq->irq.handler = efa_intr_msix_comp; + eq->irq.data = eq; + eq->irq.vector = vector; + eq->irq.irqn = pci_irq_vector(dev->pdev, vector); + cpumask_set_cpu(cpu, &eq->irq.affinity_hint_mask); +} + +static void efa_free_irq(struct efa_dev *dev, struct efa_irq *irq) +{ + irq_set_affinity_hint(irq->irqn, NULL); + free_irq(irq->irqn, irq->data); +} + static void efa_setup_mgmnt_irq(struct efa_dev *dev) { u32 cpu; @@ -105,8 +163,9 @@ static void efa_setup_mgmnt_irq(struct efa_dev *dev) "efa-mgmnt@pci:%s", pci_name(dev->pdev)); dev->admin_irq.handler = efa_intr_msix_mgmnt; dev->admin_irq.data = dev; - dev->admin_irq.irqn = - pci_irq_vector(dev->pdev, dev->admin_msix_vector_idx); + dev->admin_irq.vector = dev->admin_msix_vector_idx; + dev->admin_irq.irqn = pci_irq_vector(dev->pdev, + dev->admin_msix_vector_idx); cpu = cpumask_first(cpu_online_mask); cpumask_set_cpu(cpu, &dev->admin_irq.affinity_hint_mask); @@ -115,20 +174,11 @@ static void efa_setup_mgmnt_irq(struct efa_dev *dev) dev->admin_irq.name); } -static void efa_free_mgmnt_irq(struct efa_dev *dev) -{ - struct efa_irq *irq; - - irq = &dev->admin_irq; - irq_set_affinity_hint(irq->irqn, NULL); - free_irq(irq->irqn, irq->data); -} - static int efa_set_mgmnt_irq(struct efa_dev *dev) { efa_setup_mgmnt_irq(dev); - return efa_request_mgmnt_irq(dev); + return efa_request_irq(dev, &dev->admin_irq); } static int efa_request_doorbell_bar(struct efa_dev *dev) @@ -234,6 +284,72 @@ static void efa_set_host_info(struct efa_dev *dev) dma_free_coherent(&dev->pdev->dev, bufsz, hinf, hinf_dma); } +static void efa_destroy_eq(struct efa_dev *dev, struct efa_eq *eq) +{ + efa_com_eq_destroy(&dev->edev, &eq->eeq); + efa_free_irq(dev, &eq->irq); +} + +static int efa_create_eq(struct efa_dev *dev, struct efa_eq *eq, u8 msix_vec) +{ + int err; + + efa_setup_comp_irq(dev, eq, msix_vec); + err = efa_request_irq(dev, &eq->irq); + if (err) + return err; + + err = efa_com_eq_init(&dev->edev, &eq->eeq, efa_process_eqe, + dev->dev_attr.max_eq_depth, msix_vec); + if (err) + goto err_free_comp_irq; + + return 0; + +err_free_comp_irq: + efa_free_irq(dev, &eq->irq); + return err; +} + +static int efa_create_eqs(struct efa_dev *dev) +{ + unsigned int neqs = dev->dev_attr.max_eq; + int err; + int i; + + neqs = min_t(unsigned int, neqs, num_online_cpus()); + dev->neqs = neqs; + dev->eqs = kcalloc(neqs, sizeof(*dev->eqs), GFP_KERNEL); + if (!dev->eqs) + return -ENOMEM; + + for (i = 0; i < neqs; i++) { + err = efa_create_eq(dev, &dev->eqs[i], + i + EFA_COMP_EQS_VEC_BASE); + if (err) + goto err_destroy_eqs; + } + + return 0; + +err_destroy_eqs: + for (i--; i >= 0; i--) + efa_destroy_eq(dev, &dev->eqs[i]); + kfree(dev->eqs); + + return err; +} + +static void efa_destroy_eqs(struct efa_dev *dev) +{ + int i; + + for (i = 0; i < dev->neqs; i++) + efa_destroy_eq(dev, &dev->eqs[i]); + + kfree(dev->eqs); +} + static const struct ib_device_ops efa_dev_ops = { .owner = THIS_MODULE, .driver_id = RDMA_DRIVER_EFA, @@ -300,23 +416,29 @@ static int efa_ib_device_add(struct efa_dev *dev) if (err) goto err_release_doorbell_bar; + err = efa_create_eqs(dev); + if (err) + goto err_release_doorbell_bar; + efa_set_host_info(dev); dev->ibdev.node_type = RDMA_NODE_UNSPECIFIED; dev->ibdev.phys_port_cnt = 1; - dev->ibdev.num_comp_vectors = 1; + dev->ibdev.num_comp_vectors = dev->neqs ?: 1; dev->ibdev.dev.parent = &pdev->dev; ib_set_device_ops(&dev->ibdev, &efa_dev_ops); err = ib_register_device(&dev->ibdev, "efa_%d", &pdev->dev); if (err) - goto err_release_doorbell_bar; + goto err_destroy_eqs; ibdev_info(&dev->ibdev, "IB device registered\n"); return 0; +err_destroy_eqs: + efa_destroy_eqs(dev); err_release_doorbell_bar: efa_release_doorbell_bar(dev); return err; @@ -324,9 +446,10 @@ err_release_doorbell_bar: static void efa_ib_device_remove(struct efa_dev *dev) { - efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_NORMAL); ibdev_info(&dev->ibdev, "Unregister ib device\n"); ib_unregister_device(&dev->ibdev); + efa_destroy_eqs(dev); + efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_NORMAL); efa_release_doorbell_bar(dev); } @@ -339,8 +462,12 @@ static int efa_enable_msix(struct efa_dev *dev) { int msix_vecs, irq_num; - /* Reserve the max msix vectors we might need */ - msix_vecs = EFA_NUM_MSIX_VEC; + /* + * Reserve the max msix vectors we might need, one vector is reserved + * for admin. + */ + msix_vecs = min_t(int, pci_msix_vec_count(dev->pdev), + num_online_cpus() + 1); dev_dbg(&dev->pdev->dev, "Trying to enable MSI-X, vectors %d\n", msix_vecs); @@ -421,6 +548,7 @@ static struct efa_dev *efa_probe_device(struct pci_dev *pdev) edev->efa_dev = dev; edev->dmadev = &pdev->dev; dev->pdev = pdev; + xa_init(&dev->cqs_xa); bars = pci_select_bars(pdev, IORESOURCE_MEM) & EFA_BASE_BAR_MASK; err = pci_request_selected_regions(pdev, bars, DRV_MODULE_NAME); @@ -476,7 +604,7 @@ static struct efa_dev *efa_probe_device(struct pci_dev *pdev) return dev; err_free_mgmnt_irq: - efa_free_mgmnt_irq(dev); + efa_free_irq(dev, &dev->admin_irq); err_disable_msix: efa_disable_msix(dev); err_reg_read_destroy: @@ -499,11 +627,12 @@ static void efa_remove_device(struct pci_dev *pdev) edev = &dev->edev; efa_com_admin_destroy(edev); - efa_free_mgmnt_irq(dev); + efa_free_irq(dev, &dev->admin_irq); efa_disable_msix(dev); efa_com_mmio_reg_read_destroy(edev); devm_iounmap(&pdev->dev, edev->reg_bar); efa_release_bars(dev, EFA_BASE_BAR_MASK); + xa_destroy(&dev->cqs_xa); ib_dealloc_device(&dev->ibdev); pci_disable_device(pdev); } diff --git a/drivers/infiniband/hw/efa/efa_regs_defs.h b/drivers/infiniband/hw/efa/efa_regs_defs.h index 4017982fe13b..714ae6258800 100644 --- a/drivers/infiniband/hw/efa/efa_regs_defs.h +++ b/drivers/infiniband/hw/efa/efa_regs_defs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_REGS_H_ @@ -42,6 +42,7 @@ enum efa_regs_reset_reason_types { #define EFA_REGS_MMIO_REG_READ_OFF 0x5c #define EFA_REGS_MMIO_RESP_LO_OFF 0x60 #define EFA_REGS_MMIO_RESP_HI_OFF 0x64 +#define EFA_REGS_EQ_DB_OFF 0x68 /* version register */ #define EFA_REGS_VERSION_MINOR_VERSION_MASK 0xff @@ -93,4 +94,8 @@ enum efa_regs_reset_reason_types { #define EFA_REGS_MMIO_REG_READ_REQ_ID_MASK 0xffff #define EFA_REGS_MMIO_REG_READ_REG_OFF_MASK 0xffff0000 +/* eq_db register */ +#define EFA_REGS_EQ_DB_EQN_MASK 0xffff +#define EFA_REGS_EQ_DB_ARM_MASK 0x80000000 + #endif /* _EFA_REGS_H_ */ diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index e5f9d90aad5e..3353ad4925ee 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -245,6 +245,9 @@ int efa_query_device(struct ib_device *ibdev, if (EFA_DEV_CAP(dev, RNR_RETRY)) resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RNR_RETRY; + if (dev->neqs) + resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS; + err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen)); if (err) { @@ -984,6 +987,12 @@ static int efa_destroy_cq_idx(struct efa_dev *dev, int cq_idx) return efa_com_destroy_cq(&dev->edev, ¶ms); } +static void efa_cq_user_mmap_entries_remove(struct efa_cq *cq) +{ + rdma_user_mmap_entry_remove(cq->db_mmap_entry); + rdma_user_mmap_entry_remove(cq->mmap_entry); +} + int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct efa_dev *dev = to_edev(ibcq->device); @@ -993,15 +1002,25 @@ int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) "Destroy cq[%d] virt[0x%p] freed: size[%lu], dma[%pad]\n", cq->cq_idx, cq->cpu_addr, cq->size, &cq->dma_addr); - rdma_user_mmap_entry_remove(cq->mmap_entry); + efa_cq_user_mmap_entries_remove(cq); efa_destroy_cq_idx(dev, cq->cq_idx); + if (cq->eq) { + xa_erase(&dev->cqs_xa, cq->cq_idx); + synchronize_irq(cq->eq->irq.irqn); + } efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size, DMA_FROM_DEVICE); return 0; } +static struct efa_eq *efa_vec2eq(struct efa_dev *dev, int vec) +{ + return &dev->eqs[vec]; +} + static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq, - struct efa_ibv_create_cq_resp *resp) + struct efa_ibv_create_cq_resp *resp, + bool db_valid) { resp->q_mmap_size = cq->size; cq->mmap_entry = efa_user_mmap_entry_insert(&cq->ucontext->ibucontext, @@ -1011,6 +1030,21 @@ static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq, if (!cq->mmap_entry) return -ENOMEM; + if (db_valid) { + cq->db_mmap_entry = + efa_user_mmap_entry_insert(&cq->ucontext->ibucontext, + dev->db_bar_addr + resp->db_off, + PAGE_SIZE, EFA_MMAP_IO_NC, + &resp->db_mmap_key); + if (!cq->db_mmap_entry) { + rdma_user_mmap_entry_remove(cq->mmap_entry); + return -ENOMEM; + } + + resp->db_off &= ~PAGE_MASK; + resp->comp_mask |= EFA_CREATE_CQ_RESP_DB_OFF; + } + return 0; } @@ -1019,8 +1053,8 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, { struct efa_ucontext *ucontext = rdma_udata_to_drv_context( udata, struct efa_ucontext, ibucontext); + struct efa_com_create_cq_params params = {}; struct efa_ibv_create_cq_resp resp = {}; - struct efa_com_create_cq_params params; struct efa_com_create_cq_result result; struct ib_device *ibdev = ibcq->device; struct efa_dev *dev = to_edev(ibdev); @@ -1065,7 +1099,7 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, goto err_out; } - if (cmd.comp_mask || !is_reserved_cleared(cmd.reserved_50)) { + if (cmd.comp_mask || !is_reserved_cleared(cmd.reserved_58)) { ibdev_dbg(ibdev, "Incompatible ABI params, unknown fields in udata\n"); err = -EINVAL; @@ -1101,29 +1135,45 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, params.dma_addr = cq->dma_addr; params.entry_size_in_bytes = cmd.cq_entry_size; params.num_sub_cqs = cmd.num_sub_cqs; + if (cmd.flags & EFA_CREATE_CQ_WITH_COMPLETION_CHANNEL) { + cq->eq = efa_vec2eq(dev, attr->comp_vector); + params.eqn = cq->eq->eeq.eqn; + params.interrupt_mode_enabled = true; + } + err = efa_com_create_cq(&dev->edev, ¶ms, &result); if (err) goto err_free_mapped; + resp.db_off = result.db_off; resp.cq_idx = result.cq_idx; cq->cq_idx = result.cq_idx; cq->ibcq.cqe = result.actual_depth; WARN_ON_ONCE(entries != result.actual_depth); - err = cq_mmap_entries_setup(dev, cq, &resp); + err = cq_mmap_entries_setup(dev, cq, &resp, result.db_valid); if (err) { ibdev_dbg(ibdev, "Could not setup cq[%u] mmap entries\n", cq->cq_idx); goto err_destroy_cq; } + if (cq->eq) { + err = xa_err(xa_store(&dev->cqs_xa, cq->cq_idx, cq, GFP_KERNEL)); + if (err) { + ibdev_dbg(ibdev, "Failed to store cq[%u] in xarray\n", + cq->cq_idx); + goto err_remove_mmap; + } + } + if (udata->outlen) { err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen)); if (err) { ibdev_dbg(ibdev, "Failed to copy udata for create_cq\n"); - goto err_remove_mmap; + goto err_xa_erase; } } @@ -1132,8 +1182,11 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, return 0; +err_xa_erase: + if (cq->eq) + xa_erase(&dev->cqs_xa, cq->cq_idx); err_remove_mmap: - rdma_user_mmap_entry_remove(cq->mmap_entry); + efa_cq_user_mmap_entries_remove(cq); err_destroy_cq: efa_destroy_cq_idx(dev, cq->cq_idx); err_free_mapped: diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index f89fbb5b1e8d..08035ccf1fff 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* - * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef EFA_ABI_USER_H @@ -52,11 +52,20 @@ struct efa_ibv_alloc_pd_resp { __u8 reserved_30[2]; }; +enum { + EFA_CREATE_CQ_WITH_COMPLETION_CHANNEL = 1 << 0, +}; + struct efa_ibv_create_cq { __u32 comp_mask; __u32 cq_entry_size; __u16 num_sub_cqs; - __u8 reserved_50[6]; + __u8 flags; + __u8 reserved_58[5]; +}; + +enum { + EFA_CREATE_CQ_RESP_DB_OFF = 1 << 0, }; struct efa_ibv_create_cq_resp { @@ -65,7 +74,9 @@ struct efa_ibv_create_cq_resp { __aligned_u64 q_mmap_key; __aligned_u64 q_mmap_size; __u16 cq_idx; - __u8 reserved_d0[6]; + __u8 reserved_d0[2]; + __u32 db_off; + __aligned_u64 db_mmap_key; }; enum { @@ -106,6 +117,7 @@ struct efa_ibv_create_ah_resp { enum { EFA_QUERY_DEVICE_CAPS_RDMA_READ = 1 << 0, EFA_QUERY_DEVICE_CAPS_RNR_RETRY = 1 << 1, + EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS = 1 << 2, }; struct efa_ibv_ex_query_device_resp { -- cgit v1.2.3 From 353407d917b2d87cd8104a0453d012439c6ca4be Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Oct 2021 13:46:42 +0300 Subject: ethtool: Add ability to control transceiver modules' power mode Add a pair of new ethtool messages, 'ETHTOOL_MSG_MODULE_SET' and 'ETHTOOL_MSG_MODULE_GET', that can be used to control transceiver modules parameters and retrieve their status. The first parameter to control is the power mode of the module. It is only relevant for paged memory modules, as flat memory modules always operate in low power mode. When a paged memory module is in low power mode, its power consumption is reduced to the minimum, the management interface towards the host is available and the data path is deactivated. User space can choose to put modules that are not currently in use in low power mode and transition them to high power mode before putting the associated ports administratively up. This is useful for user space that favors reduced power consumption and lower temperatures over reduced link up times. In QSFP-DD modules the transition from low power mode to high power mode can take a few seconds and this transition is only expected to get longer with future / more complex modules. User space can control the power mode of the module via the power mode policy attribute ('ETHTOOL_A_MODULE_POWER_MODE_POLICY'). Possible values: * high: Module is always in high power mode. * auto: Module is transitioned by the host to high power mode when the first port using it is put administratively up and to low power mode when the last port using it is put administratively down. The operational power mode of the module is available to user space via the 'ETHTOOL_A_MODULE_POWER_MODE' attribute. The attribute is not reported to user space when a module is not plugged-in. The user API is designed to be generic enough so that it could be used for modules with different memory maps (e.g., SFF-8636, CMIS). The only implementation of the device driver API in this series is for a MAC driver (mlxsw) where the module is controlled by the device's firmware, but it is designed to be generic enough so that it could also be used by implementations where the module is controlled by the CPU. CMIS testing ============ # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x03 (ModuleReady) LowPwrAllowRequestHW : Off LowPwrRequestSW : Off The module is not in low power mode, as it is not forced by hardware (LowPwrAllowRequestHW is off) or by software (LowPwrRequestSW is off). The power mode can be queried from the kernel. In case LowPwrAllowRequestHW was on, the kernel would need to take into account the state of the LowPwrRequestHW signal, which is not visible to user space. $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy high power-mode high Change the power mode policy to 'auto': # ethtool --set-module swp11 power-mode-policy auto Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x01 (ModuleLowPwr) LowPwrAllowRequestHW : Off LowPwrRequestSW : On Put the associated port administratively up which will instruct the host to transition the module to high power mode: # ip link set dev swp11 up Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode high Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x03 (ModuleReady) LowPwrAllowRequestHW : Off LowPwrRequestSW : Off Put the associated port administratively down which will instruct the host to transition the module to low power mode: # ip link set dev swp11 down Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x01 (ModuleLowPwr) LowPwrAllowRequestHW : Off LowPwrRequestSW : On SFF-8636 testing ================ # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) enabled Power set : Off Power override : On ... Transmit avg optical power (Channel 1) : 0.7733 mW / -1.12 dBm Transmit avg optical power (Channel 2) : 0.7649 mW / -1.16 dBm Transmit avg optical power (Channel 3) : 0.7790 mW / -1.08 dBm Transmit avg optical power (Channel 4) : 0.7837 mW / -1.06 dBm Rcvr signal avg optical power(Channel 1) : 0.9302 mW / -0.31 dBm Rcvr signal avg optical power(Channel 2) : 0.9079 mW / -0.42 dBm Rcvr signal avg optical power(Channel 3) : 0.8993 mW / -0.46 dBm Rcvr signal avg optical power(Channel 4) : 0.8778 mW / -0.57 dBm The module is not in low power mode, as it is not forced by hardware (Power override is on) or by software (Power set is off). The power mode can be queried from the kernel. In case Power override was off, the kernel would need to take into account the state of the LPMode signal, which is not visible to user space. $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy high power-mode high Change the power mode policy to 'auto': # ethtool --set-module swp13 power-mode-policy auto Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) not enabled Power set : On Power override : On ... Transmit avg optical power (Channel 1) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 2) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 3) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 4) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 1) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 2) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 3) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 4) : 0.0000 mW / -inf dBm Put the associated port administratively up which will instruct the host to transition the module to high power mode: # ip link set dev swp13 up Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode high Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) enabled Power set : Off Power override : On ... Transmit avg optical power (Channel 1) : 0.7934 mW / -1.01 dBm Transmit avg optical power (Channel 2) : 0.7859 mW / -1.05 dBm Transmit avg optical power (Channel 3) : 0.7885 mW / -1.03 dBm Transmit avg optical power (Channel 4) : 0.7985 mW / -0.98 dBm Rcvr signal avg optical power(Channel 1) : 0.9325 mW / -0.30 dBm Rcvr signal avg optical power(Channel 2) : 0.9034 mW / -0.44 dBm Rcvr signal avg optical power(Channel 3) : 0.9086 mW / -0.42 dBm Rcvr signal avg optical power(Channel 4) : 0.8885 mW / -0.51 dBm Put the associated port administratively down which will instruct the host to transition the module to low power mode: # ip link set dev swp13 down Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) not enabled Power set : On Power override : On ... Transmit avg optical power (Channel 1) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 2) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 3) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 4) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 1) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 2) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 3) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 4) : 0.0000 mW / -inf dBm Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 71 ++++++++++- include/linux/ethtool.h | 22 ++++ include/uapi/linux/ethtool.h | 23 ++++ include/uapi/linux/ethtool_netlink.h | 17 +++ net/ethtool/Makefile | 2 +- net/ethtool/module.c | 180 +++++++++++++++++++++++++++ net/ethtool/netlink.c | 19 +++ net/ethtool/netlink.h | 4 + 8 files changed, 335 insertions(+), 3 deletions(-) create mode 100644 net/ethtool/module.c (limited to 'include/uapi') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d9b55b7a1a4d..d6fd4b2e243c 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -41,6 +41,11 @@ In the message structure descriptions below, if an attribute name is suffixed with "+", parent nest can contain multiple attributes of the same type. This implements an array of entries. +Attributes that need to be filled-in by device drivers and that are dumped to +user space based on whether they are valid or not should not use zero as a +valid value. This avoids the need to explicitly signal the validity of the +attribute in the device driver API. + Request header ============== @@ -179,7 +184,7 @@ according to message purpose: Userspace to kernel: - ===================================== ================================ + ===================================== ================================= ``ETHTOOL_MSG_STRSET_GET`` get string set ``ETHTOOL_MSG_LINKINFO_GET`` get link settings ``ETHTOOL_MSG_LINKINFO_SET`` set link settings @@ -213,7 +218,9 @@ Userspace to kernel: ``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET`` get standard statistics ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info - ===================================== ================================ + ``ETHTOOL_MSG_MODULE_SET`` set transceiver module parameters + ``ETHTOOL_MSG_MODULE_GET`` get transceiver module parameters + ===================================== ================================= Kernel to userspace: @@ -252,6 +259,7 @@ Kernel to userspace: ``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info + ``ETHTOOL_MSG_MODULE_GET_REPLY`` transceiver module parameters ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1521,6 +1529,63 @@ Kernel response contents: ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array ==================================== ====== ========================== +MODULE_GET +========== + +Gets transceiver module parameters. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested reply header + ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` u8 power mode policy + ``ETHTOOL_A_MODULE_POWER_MODE`` u8 operational power mode + ====================================== ====== ========================== + +The optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute encodes the +transceiver module power mode policy enforced by the host. The default policy +is driver-dependent, but "auto" is the recommended default and it should be +implemented by new drivers and drivers where conformance to a legacy behavior +is not critical. + +The optional ``ETHTHOOL_A_MODULE_POWER_MODE`` attribute encodes the operational +power mode policy of the transceiver module. It is only reported when a module +is plugged-in. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_power_mode + +MODULE_SET +========== + +Sets transceiver module parameters. + +Request contents: + + ====================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested request header + ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` u8 power mode policy + ====================================== ====== ========================== + +When set, the optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute is used +to set the transceiver module power policy enforced by the host. Possible +values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_power_mode_policy + +For SFF-8636 modules, low power mode is forced by the host according to table +6-10 in revision 2.10a of the specification. + +For CMIS modules, low power mode is forced by the host according to table 6-12 +in revision 5.0 of the specification. + Request translation =================== @@ -1620,4 +1685,6 @@ are netlink only. n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` + n/a ``ETHTOOL_MSG_MODULE_GET`` + n/a ``ETHTOOL_MSG_MODULE_SET`` =================================== ===================================== diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 849524b55d89..9adf8d2c3144 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -415,6 +415,17 @@ struct ethtool_module_eeprom { u8 *data; }; +/** + * struct ethtool_module_power_mode_params - module power mode parameters + * @policy: The power mode policy enforced by the host for the plug-in module. + * @mode: The operational power mode of the plug-in module. Should be filled by + * device drivers on get operations. + */ +struct ethtool_module_power_mode_params { + enum ethtool_module_power_mode_policy policy; + enum ethtool_module_power_mode mode; +}; + /** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes @@ -580,6 +591,11 @@ struct ethtool_module_eeprom { * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics. * @get_rmon_stats: Query some of the RMON (RFC 2819) statistics. * Set %ranges to a pointer to zero-terminated array of byte ranges. + * @get_module_power_mode: Get the power mode policy for the plug-in module + * used by the network device and its operational power mode, if + * plugged-in. + * @set_module_power_mode: Set the power mode policy for the plug-in module + * used by the network device. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -705,6 +721,12 @@ struct ethtool_ops { void (*get_rmon_stats)(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); + int (*get_module_power_mode)(struct net_device *dev, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); + int (*set_module_power_mode)(struct net_device *dev, + const struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); }; int ethtool_check_ops(const struct ethtool_ops *ops); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index b6db6590baf0..6de61d53ca5d 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -706,6 +706,29 @@ enum ethtool_stringset { ETH_SS_COUNT }; +/** + * 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. + * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host + * to high power mode when the first port using it is put administratively + * up and to low power mode when the last port using it is put + * administratively down. + */ +enum ethtool_module_power_mode_policy { + ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO, +}; + +/** + * enum ethtool_module_power_mode - plug-in module power mode + * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode. + * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode. + */ +enum ethtool_module_power_mode { + ETHTOOL_MODULE_POWER_MODE_LOW = 1, + ETHTOOL_MODULE_POWER_MODE_HIGH, +}; + /** * 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 5545f1ca9237..ca5fbb59fa42 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -47,6 +47,8 @@ enum { ETHTOOL_MSG_MODULE_EEPROM_GET, ETHTOOL_MSG_STATS_GET, ETHTOOL_MSG_PHC_VCLOCKS_GET, + ETHTOOL_MSG_MODULE_GET, + ETHTOOL_MSG_MODULE_SET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -90,6 +92,8 @@ enum { ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, ETHTOOL_MSG_STATS_GET_REPLY, ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + ETHTOOL_MSG_MODULE_GET_REPLY, + ETHTOOL_MSG_MODULE_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -833,6 +837,19 @@ enum { ETHTOOL_A_STATS_RMON_MAX = (__ETHTOOL_A_STATS_RMON_CNT - 1) }; +/* MODULE */ + +enum { + ETHTOOL_A_MODULE_UNSPEC, + ETHTOOL_A_MODULE_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_MODULE_POWER_MODE_POLICY, /* u8 */ + ETHTOOL_A_MODULE_POWER_MODE, /* u8 */ + + /* add new constants above here */ + __ETHTOOL_A_MODULE_CNT, + ETHTOOL_A_MODULE_MAX = (__ETHTOOL_A_MODULE_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 0a19470efbfb..b76432e70e6b 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.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 + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o diff --git a/net/ethtool/module.c b/net/ethtool/module.c new file mode 100644 index 000000000000..bc2cef11bbda --- /dev/null +++ b/net/ethtool/module.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct module_req_info { + struct ethnl_req_info base; +}; + +struct module_reply_data { + struct ethnl_reply_data base; + struct ethtool_module_power_mode_params power; +}; + +#define MODULE_REPDATA(__reply_base) \ + container_of(__reply_base, struct module_reply_data, base) + +/* MODULE_GET */ + +const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1] = { + [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int module_get_power_mode(struct net_device *dev, + struct module_reply_data *data, + struct netlink_ext_ack *extack) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_power_mode) + return 0; + + return ops->get_module_power_mode(dev, &data->power, extack); +} + +static int module_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct module_reply_data *data = MODULE_REPDATA(reply_base); + struct netlink_ext_ack *extack = info ? info->extack : NULL; + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = module_get_power_mode(dev, data, extack); + if (ret < 0) + goto out_complete; + +out_complete: + ethnl_ops_complete(dev); + return ret; +} + +static int module_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct module_reply_data *data = MODULE_REPDATA(reply_base); + int len = 0; + + if (data->power.policy) + len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE_POLICY */ + + if (data->power.mode) + len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE */ + + return len; +} + +static int module_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct module_reply_data *data = MODULE_REPDATA(reply_base); + + if (data->power.policy && + nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE_POLICY, + data->power.policy)) + return -EMSGSIZE; + + if (data->power.mode && + nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE, data->power.mode)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_module_request_ops = { + .request_cmd = ETHTOOL_MSG_MODULE_GET, + .reply_cmd = ETHTOOL_MSG_MODULE_GET_REPLY, + .hdr_attr = ETHTOOL_A_MODULE_HEADER, + .req_info_size = sizeof(struct module_req_info), + .reply_data_size = sizeof(struct module_reply_data), + + .prepare_data = module_prepare_data, + .reply_size = module_reply_size, + .fill_reply = module_fill_reply, +}; + +/* MODULE_SET */ + +const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1] = { + [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_MODULE_POWER_MODE_POLICY] = + NLA_POLICY_RANGE(NLA_U8, ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO), +}; + +static int module_set_power_mode(struct net_device *dev, struct nlattr **tb, + bool *p_mod, struct netlink_ext_ack *extack) +{ + struct ethtool_module_power_mode_params power = {}; + struct ethtool_module_power_mode_params power_new; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + + if (!tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]) + return 0; + + if (!ops->get_module_power_mode || !ops->set_module_power_mode) { + NL_SET_ERR_MSG_ATTR(extack, + tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY], + "Setting power mode policy is not supported by this device"); + return -EOPNOTSUPP; + } + + power_new.policy = nla_get_u8(tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]); + ret = ops->get_module_power_mode(dev, &power, extack); + if (ret < 0) + return ret; + + if (power_new.policy == power.policy) + return 0; + *p_mod = true; + + return ops->set_module_power_mode(dev, &power_new, extack); +} + +int ethnl_set_module(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct net_device *dev; + bool mod = false; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MODULE_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = module_set_power_mode(dev, tb, &mod, info->extack); + if (ret < 0) + goto out_ops; + + if (!mod) + goto out_ops; + + ethtool_notify(dev, ETHTOOL_MSG_MODULE_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1797a0a90019..38b44c0291b1 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -282,6 +282,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, + [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -593,6 +594,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, + [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, }; /* default notification handler */ @@ -686,6 +688,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -999,6 +1002,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_phc_vclocks_get_policy, .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_MODULE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_module_get_policy, + .maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_MODULE_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_module, + .policy = ethnl_module_set_policy, + .maxattr = ARRAY_SIZE(ethnl_module_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 e8987e28036f..836ee7157848 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -337,6 +337,7 @@ extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; +extern const struct ethnl_request_ops ethnl_module_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]; @@ -373,6 +374,8 @@ 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_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]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); @@ -391,6 +394,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); 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); 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 3dfb51126064b594470b9c0b278188fbc9194709 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Oct 2021 13:46:46 +0300 Subject: ethtool: Add transceiver module extended state Add an extended state and sub-state to describe link issues related to transceiver modules. The 'ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY' extended sub-state tells user space that port is unable to gain a carrier because the CMIS Module State Machine did not reach the ModuleReady (Fully Operational) state. For example, if the module is stuck at ModuleLowPwr or ModuleFault state. In case of the latter, user space can read the fault reason from the module's EEPROM and potentially reset it. Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 10 ++++++++++ include/linux/ethtool.h | 1 + include/uapi/linux/ethtool.h | 6 ++++++ 3 files changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d6fd4b2e243c..7b598c7e3912 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -528,6 +528,8 @@ Link extended states: power required from cable or module ``ETHTOOL_LINK_EXT_STATE_OVERHEAT`` The module is overheated + + ``ETHTOOL_LINK_EXT_STATE_MODULE`` Transceiver module issue ================================================ ============================================ Link extended substates: @@ -621,6 +623,14 @@ Link extended substates: ``ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE`` Cable test failure =================================================== ============================================ + Transceiver module issue substates: + + =================================================== ============================================ + ``ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY`` The CMIS Module State Machine did not reach + the ModuleReady state. For example, if the + module is stuck at ModuleFault state + =================================================== ============================================ + DEBUG_GET ========= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9adf8d2c3144..845a0ffc16ee 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -94,6 +94,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch; enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; + enum ethtool_link_ext_substate_module module; u8 __link_ext_substate; }; }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 6de61d53ca5d..a2223b685451 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -603,6 +603,7 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, ETHTOOL_LINK_EXT_STATE_OVERHEAT, + ETHTOOL_LINK_EXT_STATE_MODULE, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ @@ -649,6 +650,11 @@ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, }; +/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */ +enum ethtool_link_ext_substate_module { + ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1, +}; + #define ETH_GSTRING_LEN 32 /** -- cgit v1.2.3 From bf69bad38cf63d980e8a603f8d1bd1f85b5ed3d9 Mon Sep 17 00:00:00 2001 From: André Almeida Date: Thu, 23 Sep 2021 14:11:05 -0300 Subject: futex: Implement sys_futex_waitv() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support to wait on multiple futexes. This is the interface implemented by this syscall: futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes, unsigned int flags, struct timespec *timeout, clockid_t clockid) struct futex_waitv { __u64 val; __u64 uaddr; __u32 flags; __u32 __reserved; }; Given an array of struct futex_waitv, wait on each uaddr. The thread wakes if a futex_wake() is performed at any uaddr. The syscall returns immediately if any waiter has *uaddr != val. *timeout is an optional absolute timeout value for the operation. This syscall supports only 64bit sized timeout structs. The flags argument of the syscall should be empty, but it can be used for future extensions. Flags for shared futexes, sizes, etc. should be used on the individual flags of each waiter. __reserved is used for explicit padding and should be 0, but it might be used for future extensions. If the userspace uses 32-bit pointers, it should make sure to explicitly cast it when assigning to waitv::uaddr. Returns the array index of one of the woken futexes. There’s no given information of how many were woken, or any particular attribute of it (if it’s the first woken, if it is of the smaller index...). Signed-off-by: André Almeida Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210923171111.300673-17-andrealmeid@collabora.com --- MAINTAINERS | 1 + include/linux/syscalls.h | 5 + include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/futex.h | 25 +++++ kernel/futex/futex.h | 15 +++ kernel/futex/syscalls.c | 119 ++++++++++++++++++++++ kernel/futex/waitwake.c | 201 ++++++++++++++++++++++++++++++++++++++ kernel/sys_ni.c | 1 + 8 files changed, 371 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/MAINTAINERS b/MAINTAINERS index b3094cb1afdd..310fb018acf9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7718,6 +7718,7 @@ M: Ingo Molnar R: Peter Zijlstra R: Darren Hart R: Davidlohr Bueso +R: André Almeida L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 25979682ade5..528a478dbda8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -58,6 +58,7 @@ struct mq_attr; struct compat_stat; struct old_timeval32; struct robust_list_head; +struct futex_waitv; struct getcpu_cache; struct old_linux_dirent; struct perf_event_attr; @@ -623,6 +624,10 @@ asmlinkage long sys_get_robust_list(int pid, asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); +asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, + unsigned int nr_futexes, unsigned int flags, + struct __kernel_timespec __user *timeout, clockid_t clockid); + /* kernel/hrtimer.c */ asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 1c5fb86d455a..4557a8b6086f 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #define __NR_process_mrelease 448 __SYSCALL(__NR_process_mrelease, sys_process_mrelease) +#define __NR_futex_waitv 449 +__SYSCALL(__NR_futex_waitv, sys_futex_waitv) + #undef __NR_syscalls -#define __NR_syscalls 449 +#define __NR_syscalls 450 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 235e5b2facaa..71a5df8d2689 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -43,6 +43,31 @@ #define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \ FUTEX_PRIVATE_FLAG) +/* + * Flags to specify the bit length of the futex word for futex2 syscalls. + * Currently, only 32 is supported. + */ +#define FUTEX_32 2 + +/* + * Max numbers of elements in a futex_waitv array + */ +#define FUTEX_WAITV_MAX 128 + +/** + * struct futex_waitv - A waiter for vectorized wait + * @val: Expected value at uaddr + * @uaddr: User address to wait on + * @flags: Flags for this waiter + * @__reserved: Reserved member to preserve data alignment. Should be 0. + */ +struct futex_waitv { + __u64 val; + __u64 uaddr; + __u32 flags; + __u32 __reserved; +}; + /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 465f7bd5caef..948fcf317681 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -268,6 +268,21 @@ extern int futex_requeue(u32 __user *uaddr1, unsigned int flags, extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); +/** + * struct futex_vector - Auxiliary struct for futex_waitv() + * @w: Userspace provided data + * @q: Kernel side data + * + * Struct used to build an array with all data need for futex_waitv() + */ +struct futex_vector { + struct futex_waitv w; + struct futex_q q; +}; + +extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to); + extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 6e7e36c640a1..6f91a07a6a83 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -199,6 +199,125 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } +/* Mask of available flags for each futex in futex_waitv list */ +#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG) + +/** + * futex_parse_waitv - Parse a waitv array from userspace + * @futexv: Kernel side list of waiters to be filled + * @uwaitv: Userspace list to be parsed + * @nr_futexes: Length of futexv + * + * Return: Error code on failure, 0 on success + */ +static int futex_parse_waitv(struct futex_vector *futexv, + struct futex_waitv __user *uwaitv, + unsigned int nr_futexes) +{ + struct futex_waitv aux; + unsigned int i; + + for (i = 0; i < nr_futexes; i++) { + if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) + return -EFAULT; + + if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved) + return -EINVAL; + + if (!(aux.flags & FUTEX_32)) + return -EINVAL; + + futexv[i].w.flags = aux.flags; + futexv[i].w.val = aux.val; + futexv[i].w.uaddr = aux.uaddr; + futexv[i].q = futex_q_init; + } + + return 0; +} + +/** + * sys_futex_waitv - Wait on a list of futexes + * @waiters: List of futexes to wait on + * @nr_futexes: Length of futexv + * @flags: Flag for timeout (monotonic/realtime) + * @timeout: Optional absolute timeout. + * @clockid: Clock to be used for the timeout, realtime or monotonic. + * + * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes + * if a futex_wake() is performed at any uaddr. The syscall returns immediately + * if any waiter has *uaddr != val. *timeout is an optional timeout value for + * the operation. Each waiter has individual flags. The `flags` argument for + * the syscall should be used solely for specifying the timeout as realtime, if + * needed. Flags for private futexes, sizes, etc. should be used on the + * individual flags of each waiter. + * + * Returns the array index of one of the woken futexes. No further information + * is provided: any number of other futexes may also have been woken by the + * same event, and if more than one futex was woken, the retrned index may + * refer to any one of them. (It is not necessaryily the futex with the + * smallest index, nor the one most recently woken, nor...) + */ + +SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, + unsigned int, nr_futexes, unsigned int, flags, + struct __kernel_timespec __user *, timeout, clockid_t, clockid) +{ + struct hrtimer_sleeper to; + struct futex_vector *futexv; + struct timespec64 ts; + ktime_t time; + int ret; + + /* This syscall supports no flags for now */ + if (flags) + return -EINVAL; + + if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) + return -EINVAL; + + if (timeout) { + int flag_clkid = 0, flag_init = 0; + + if (clockid == CLOCK_REALTIME) { + flag_clkid = FLAGS_CLOCKRT; + flag_init = FUTEX_CLOCK_REALTIME; + } + + if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) + return -EINVAL; + + if (get_timespec64(&ts, timeout)) + return -EFAULT; + + /* + * Since there's no opcode for futex_waitv, use + * FUTEX_WAIT_BITSET that uses absolute timeout as well + */ + ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); + if (ret) + return ret; + + futex_setup_timer(&time, &to, flag_clkid, 0); + } + + futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); + if (!futexv) + return -ENOMEM; + + ret = futex_parse_waitv(futexv, waiters, nr_futexes); + if (!ret) + ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); + + if (timeout) { + hrtimer_cancel(&to.timer); + destroy_hrtimer_on_stack(&to.timer); + } + + kfree(futexv); + return ret; +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index 36880784aa11..4ce0923f1ce3 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -357,6 +357,207 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, __set_current_state(TASK_RUNNING); } +/** + * unqueue_multiple - Remove various futexes from their hash bucket + * @v: The list of futexes to unqueue + * @count: Number of futexes in the list + * + * Helper to unqueue a list of futexes. This can't fail. + * + * Return: + * - >=0 - Index of the last futex that was awoken; + * - -1 - No futex was awoken + */ +static int unqueue_multiple(struct futex_vector *v, int count) +{ + int ret = -1, i; + + for (i = 0; i < count; i++) { + if (!futex_unqueue(&v[i].q)) + ret = i; + } + + return ret; +} + +/** + * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes + * @vs: The futex list to wait on + * @count: The size of the list + * @woken: Index of the last woken futex, if any. Used to notify the + * caller that it can return this index to userspace (return parameter) + * + * Prepare multiple futexes in a single step and enqueue them. This may fail if + * the futex list is invalid or if any futex was already awoken. On success the + * task is ready to interruptible sleep. + * + * Return: + * - 1 - One of the futexes was woken by another thread + * - 0 - Success + * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL + */ +static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) +{ + struct futex_hash_bucket *hb; + bool retry = false; + int ret, i; + u32 uval; + + /* + * Enqueuing multiple futexes is tricky, because we need to enqueue + * each futex on the list before dealing with the next one to avoid + * deadlocking on the hash bucket. But, before enqueuing, we need to + * make sure that current->state is TASK_INTERRUPTIBLE, so we don't + * lose any wake events, which cannot be done before the get_futex_key + * of the next key, because it calls get_user_pages, which can sleep. + * Thus, we fetch the list of futexes keys in two steps, by first + * pinning all the memory keys in the futex key, and only then we read + * each key and queue the corresponding futex. + * + * Private futexes doesn't need to recalculate hash in retry, so skip + * get_futex_key() when retrying. + */ +retry: + for (i = 0; i < count; i++) { + if ((vs[i].w.flags & FUTEX_PRIVATE_FLAG) && retry) + continue; + + ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), + !(vs[i].w.flags & FUTEX_PRIVATE_FLAG), + &vs[i].q.key, FUTEX_READ); + + if (unlikely(ret)) + return ret; + } + + set_current_state(TASK_INTERRUPTIBLE); + + for (i = 0; i < count; i++) { + u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; + struct futex_q *q = &vs[i].q; + u32 val = (u32)vs[i].w.val; + + hb = futex_q_lock(q); + ret = futex_get_value_locked(&uval, uaddr); + + if (!ret && uval == val) { + /* + * The bucket lock can't be held while dealing with the + * next futex. Queue each futex at this moment so hb can + * be unlocked. + */ + futex_queue(q, hb); + continue; + } + + futex_q_unlock(hb); + __set_current_state(TASK_RUNNING); + + /* + * Even if something went wrong, if we find out that a futex + * was woken, we don't return error and return this index to + * userspace + */ + *woken = unqueue_multiple(vs, i); + if (*woken >= 0) + return 1; + + if (ret) { + /* + * If we need to handle a page fault, we need to do so + * without any lock and any enqueued futex (otherwise + * we could lose some wakeup). So we do it here, after + * undoing all the work done so far. In success, we + * retry all the work. + */ + if (get_user(uval, uaddr)) + return -EFAULT; + + retry = true; + goto retry; + } + + if (uval != val) + return -EWOULDBLOCK; + } + + return 0; +} + +/** + * futex_sleep_multiple - Check sleeping conditions and sleep + * @vs: List of futexes to wait for + * @count: Length of vs + * @to: Timeout + * + * Sleep if and only if the timeout hasn't expired and no futex on the list has + * been woken up. + */ +static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to) +{ + if (to && !to->task) + return; + + for (; count; count--, vs++) { + if (!READ_ONCE(vs->q.lock_ptr)) + return; + } + + freezable_schedule(); +} + +/** + * futex_wait_multiple - Prepare to wait on and enqueue several futexes + * @vs: The list of futexes to wait on + * @count: The number of objects + * @to: Timeout before giving up and returning to userspace + * + * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function + * sleeps on a group of futexes and returns on the first futex that is + * wake, or after the timeout has elapsed. + * + * Return: + * - >=0 - Hint to the futex that was awoken + * - <0 - On error + */ +int futex_wait_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to) +{ + int ret, hint = 0; + + if (to) + hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); + + while (1) { + ret = futex_wait_multiple_setup(vs, count, &hint); + if (ret) { + if (ret > 0) { + /* A futex was woken during setup */ + ret = hint; + } + return ret; + } + + futex_sleep_multiple(vs, count, to); + + __set_current_state(TASK_RUNNING); + + ret = unqueue_multiple(vs, count); + if (ret >= 0) + return ret; + + if (to && !to->task) + return -ETIMEDOUT; + else if (signal_pending(current)) + return -ERESTARTSYS; + /* + * The final case is a spurious wakeup, for + * which just retry. + */ + } +} + /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 13ee8334ab6e..d1944258cfc0 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -150,6 +150,7 @@ COND_SYSCALL(set_robust_list); COND_SYSCALL_COMPAT(set_robust_list); COND_SYSCALL(get_robust_list); COND_SYSCALL_COMPAT(get_robust_list); +COND_SYSCALL(futex_waitv); /* kernel/hrtimer.c */ -- cgit v1.2.3 From 460275f124fb072dca218a6b43b6370eebbab20d Mon Sep 17 00:00:00 2001 From: Pali Rohár Date: Tue, 5 Oct 2021 20:09:40 +0200 Subject: PCI: Add PCI_EXP_DEVCTL_PAYLOAD_* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a macro PCI_EXP_DEVCTL_PAYLOAD_* for every possible Max Payload Size in linux/pci_regs.h, in the same style as PCI_EXP_DEVCTL_READRQ_*. Link: https://lore.kernel.org/r/20211005180952.6812-2-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Reviewed-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e709ae8235e7..ff6ccbc6efe9 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -504,6 +504,12 @@ #define PCI_EXP_DEVCTL_URRE 0x0008 /* Unsupported Request Reporting En. */ #define PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */ #define PCI_EXP_DEVCTL_PAYLOAD 0x00e0 /* Max_Payload_Size */ +#define PCI_EXP_DEVCTL_PAYLOAD_128B 0x0000 /* 128 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_256B 0x0020 /* 256 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_512B 0x0040 /* 512 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_1024B 0x0060 /* 1024 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_2048B 0x0080 /* 2048 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_4096B 0x00a0 /* 4096 Bytes */ #define PCI_EXP_DEVCTL_EXT_TAG 0x0100 /* Extended Tag Field Enable */ #define PCI_EXP_DEVCTL_PHANTOM 0x0200 /* Phantom Functions Enable */ #define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ -- cgit v1.2.3 From 4c1e34c0dbffb17accdfe16ac97ab432df9024ff Mon Sep 17 00:00:00 2001 From: Richard Palethorpe Date: Fri, 8 Oct 2021 11:00:53 +0100 Subject: vsock: Enable y2038 safe timeval for timeout Reuse the timeval compat code from core/sock to handle 32-bit and 64-bit timeval structures. Also introduce a new socket option define to allow using y2038 safe timeval under 32-bit. The existing behavior of sock_set_timeout and vsock's timeout setter differ when the time value is out of bounds. vsocks current behavior is retained at the expense of not being able to share the full implementation. This allows the LTP test vsock01 to pass under 32-bit compat mode. Fixes: fe0c72f3db11 ("socket: move compat timeout handling into sock.c") Signed-off-by: Richard Palethorpe Cc: Richard Palethorpe Reviewed-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/net/sock.h | 4 ++++ include/uapi/linux/vm_sockets.h | 13 ++++++++++++- net/core/sock.c | 35 ++++++++++++++++++++++++----------- net/vmw_vsock/af_vsock.c | 25 +++++++++++++++---------- 4 files changed, 55 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/net/sock.h b/include/net/sock.h index caaec7c55e8e..d08ab55fa4a0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2836,4 +2836,8 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +int sock_get_timeout(long timeo, void *optval, bool old_timeval); +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval); + #endif /* _SOCK_H */ diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index 46918a1852d7..c60ca33eac59 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -64,7 +64,7 @@ * timeout for a STREAM socket. */ -#define SO_VM_SOCKETS_CONNECT_TIMEOUT 6 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD 6 /* Option name for using non-blocking send/receive. Use as the option name * for setsockopt(3) or getsockopt(3) to set or get the non-blocking @@ -81,6 +81,17 @@ #define SO_VM_SOCKETS_NONBLOCK_TXRX 7 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW 8 + +#if !defined(__KERNEL__) +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +#define SO_VM_SOCKETS_CONNECT_TIMEOUT SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD +#else +#define SO_VM_SOCKETS_CONNECT_TIMEOUT \ + (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD : SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW) +#endif +#endif + /* The vSocket equivalent of INADDR_ANY. This works for the svm_cid field of * sockaddr_vm and indicates the context ID of the current endpoint. */ diff --git a/net/core/sock.c b/net/core/sock.c index beda31764df9..9862eefce21e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -350,7 +350,7 @@ void sk_error_report(struct sock *sk) } EXPORT_SYMBOL(sk_error_report); -static int sock_get_timeout(long timeo, void *optval, bool old_timeval) +int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -379,12 +379,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } +EXPORT_SYMBOL(sock_get_timeout); -static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, - bool old_timeval) +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval) { - struct __kernel_sock_timeval tv; - if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; @@ -393,8 +392,8 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; - tv.tv_sec = tv32.tv_sec; - tv.tv_usec = tv32.tv_usec; + tv->tv_sec = tv32.tv_sec; + tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; @@ -402,14 +401,28 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; - tv.tv_sec = old_tv.tv_sec; - tv.tv_usec = old_tv.tv_usec; + tv->tv_sec = old_tv.tv_sec; + tv->tv_usec = old_tv.tv_usec; } else { - if (optlen < sizeof(tv)) + if (optlen < sizeof(*tv)) return -EINVAL; - if (copy_from_sockptr(&tv, optval, sizeof(tv))) + if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } + + return 0; +} +EXPORT_SYMBOL(sock_copy_user_timeval); + +static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, + bool old_timeval) +{ + struct __kernel_sock_timeval tv; + int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + + if (err) + return err; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9d0de37b9ec0..7d851eb3a683 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1614,13 +1614,18 @@ static int vsock_connectible_setsockopt(struct socket *sock, vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct __kernel_old_timeval tv; - COPY_IN(tv); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { + struct __kernel_sock_timeval tv; + + err = sock_copy_user_timeval(&tv, optval, optlen, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); + if (err) + break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + - DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ)); + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; @@ -1653,7 +1658,9 @@ static int vsock_connectible_getsockopt(struct socket *sock, union { u64 val64; + struct old_timeval32 tm32; struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; } v; int lv = sizeof(v.val64); @@ -1680,12 +1687,10 @@ static int vsock_connectible_getsockopt(struct socket *sock, v.val64 = vsk->buffer_min_size; break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: - lv = sizeof(v.tm); - v.tm.tv_sec = vsk->connect_timeout / HZ; - v.tm.tv_usec = - (vsk->connect_timeout - - v.tm.tv_sec * HZ) * (1000000 / HZ); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: + lv = sock_get_timeout(vsk->connect_timeout, &v, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; default: -- cgit v1.2.3 From 2c611ad97a82b51221bb0920cc6cac0b1d4c0e52 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Mon, 11 Oct 2021 14:12:37 +0200 Subject: net, neigh: Extend neigh->flags to 32 bit to allow for extensions Currently, all bits in struct ndmsg's ndm_flags are used up with the most recent addition of 435f2e7cc0b7 ("net: bridge: add support for sticky fdb entries"). This makes it impossible to extend the neighboring subsystem with new NTF_* flags: struct ndmsg { __u8 ndm_family; __u8 ndm_pad1; __u16 ndm_pad2; __s32 ndm_ifindex; __u16 ndm_state; __u8 ndm_flags; __u8 ndm_type; }; There are ndm_pad{1,2} attributes which are not used. However, due to uncareful design, the kernel does not enforce them to be zero upon new neighbor entry addition, and given they've been around forever, it is not possible to reuse them today due to risk of breakage. One option to overcome this limitation is to add a new NDA_FLAGS_EXT attribute for extended flags. In struct neighbour, there is a 3 byte hole between protocol and ha_lock, which allows neigh->flags to be extended from 8 to 32 bits while still being on the same cacheline as before. This also allows for all future NTF_* flags being in neigh->flags rather than yet another flags field. Unknown flags in NDA_FLAGS_EXT will be rejected by the kernel. Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/neighbour.h | 14 +++++++---- include/uapi/linux/neighbour.h | 1 + net/core/neighbour.c | 55 ++++++++++++++++++++++++++++++------------ 3 files changed, 50 insertions(+), 20 deletions(-) (limited to 'include/uapi') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index eb2a7c03a5b0..26d4ada0aea9 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -144,11 +144,11 @@ struct neighbour { struct timer_list timer; unsigned long used; atomic_t probes; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + u8 nud_state; + u8 type; + u8 dead; u8 protocol; + u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; @@ -172,7 +172,7 @@ struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; - u8 flags; + u32 flags; u8 protocol; u8 key[]; }; @@ -258,6 +258,10 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 +/* In-kernel representation for NDA_FLAGS_EXT flags: */ +#define NTF_OLD_MASK 0xff +#define NTF_EXT_SHIFT 8 + extern const struct nla_policy nda_policy[]; static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 00a60695fa53..a80cca141855 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -31,6 +31,7 @@ enum { NDA_PROTOCOL, /* Originator of entry */ NDA_NH_ID, NDA_FDB_EXT_ATTRS, + NDA_FLAGS_EXT, __NDA_MAX }; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 3e58037a8ae6..5245e888c981 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -159,7 +159,7 @@ static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, int *notify) { bool rc = false; - u8 ndm_flags; + u32 ndm_flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) return rc; @@ -379,7 +379,7 @@ EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, - u8 flags, bool exempt_from_gc) + u32 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -578,7 +578,7 @@ EXPORT_SYMBOL(neigh_lookup_nodev); static struct neighbour * ___neigh_create(struct neigh_table *tbl, const void *pkey, - struct net_device *dev, u8 flags, + struct net_device *dev, u32 flags, bool exempt_from_gc, bool want_ref) { u32 hash_val, key_len = tbl->key_len; @@ -1789,6 +1789,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, + [NDA_FLAGS_EXT] = { .type = NLA_U32 }, [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; @@ -1861,7 +1862,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_OVERRIDE_ISROUTER; + NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1870,6 +1871,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; + u32 ndm_flags; int err; ASSERT_RTNL(); @@ -1885,6 +1887,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } ndm = nlmsg_data(nlh); + ndm_flags = ndm->ndm_flags; + if (tb[NDA_FLAGS_EXT]) { + u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext & ~0) { + NL_SET_ERR_MSG(extack, "Invalid extended flags"); + goto out; + } + ndm_flags |= (ext << NTF_EXT_SHIFT); + } if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { @@ -1912,14 +1924,13 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); - - if (ndm->ndm_flags & NTF_PROXY) { + if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { - pn->flags = ndm->ndm_flags; + pn->flags = ndm_flags; if (protocol) pn->protocol = protocol; err = 0; @@ -1947,9 +1958,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || - ndm->ndm_flags & NTF_EXT_LEARNED; + ndm_flags & NTF_EXT_LEARNED; neigh = ___neigh_create(tbl, dst, dev, - ndm->ndm_flags & NTF_EXT_LEARNED, + ndm_flags & NTF_EXT_LEARNED, exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); @@ -1969,16 +1980,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (protocol) neigh->protocol = protocol; - if (ndm->ndm_flags & NTF_EXT_LEARNED) + if (ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; - if (ndm->ndm_flags & NTF_ROUTER) + if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; - if (ndm->ndm_flags & NTF_USE) + if (ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (!err && ndm->ndm_flags & NTF_USE) { + if (!err && ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; } @@ -2433,6 +2444,7 @@ out: static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { + u32 neigh_flags, neigh_flags_ext; unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -2442,11 +2454,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = neigh->flags >> NTF_EXT_SHIFT; + neigh_flags = neigh->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = neigh->flags; + ndm->ndm_flags = neigh_flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; @@ -2477,6 +2492,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2490,6 +2507,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { + u32 neigh_flags, neigh_flags_ext; struct nlmsghdr *nlh; struct ndmsg *ndm; @@ -2497,11 +2515,14 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT; + neigh_flags = pn->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_flags = neigh_flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; @@ -2511,6 +2532,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2826,6 +2849,7 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } @@ -2854,6 +2878,7 @@ static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } -- cgit v1.2.3 From 7482e3841d520a368426ac196720601687e2dc47 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 11 Oct 2021 14:12:38 +0200 Subject: net, neigh: Add NTF_MANAGED flag for managed neighbor entries Allow a user space control plane to insert entries with a new NTF_EXT_MANAGED flag. The flag then indicates to the kernel that the neighbor entry should be periodically probed for keeping the entry in NUD_REACHABLE state iff possible. The use case for this is targeting XDP or tc BPF load-balancers which use the bpf_fib_lookup() BPF helper in order to piggyback on neighbor resolution for their backends. Given they cannot be resolved in fast-path, a control plane inserts the L3 (without L2) entries manually into the neighbor table and lets the kernel do the neighbor resolution either on the gateway or on the backend directly in case the latter resides in the same L2. This avoids to deal with L2 in the control plane and to rebuild what the kernel already does best anyway. NTF_EXT_MANAGED can be combined with NTF_EXT_LEARNED in order to avoid GC eviction. The kernel then adds NTF_MANAGED flagged entries to a per-neighbor table which gets triggered by the system work queue to periodically call neigh_event_send() for performing the resolution. The implementation allows migration from/to NTF_MANAGED neighbor entries, so that already existing entries can be converted by the control plane if needed. Potentially, we could make the interval for periodically calling neigh_event_send() configurable; right now it's set to DELAY_PROBE_TIME which is also in line with mlxsw which has similar driver-internal infrastructure c723c735fa6b ("mlxsw: spectrum_router: Periodically update the kernel's neigh table"). In future, the latter could possibly reuse the NTF_MANAGED neighbors as well. Example: # ./ip/ip n replace 192.168.178.30 dev enp5s0 managed extern_learn # ./ip/ip n 192.168.178.30 dev enp5s0 lladdr f4:8c:50:5e:71:9a managed extern_learn REACHABLE [...] Signed-off-by: Daniel Borkmann Acked-by: Roopa Prabhu Link: https://linuxplumbersconf.org/event/11/contributions/953/ Signed-off-by: David S. Miller --- include/net/neighbour.h | 21 +++++--- include/uapi/linux/neighbour.h | 34 +++++++++---- net/core/neighbour.c | 113 ++++++++++++++++++++++++++++++----------- 3 files changed, 120 insertions(+), 48 deletions(-) (limited to 'include/uapi') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 26d4ada0aea9..e8e48be66755 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -155,6 +155,7 @@ struct neighbour { int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; + struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -216,11 +217,13 @@ struct neigh_table { int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; + struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; + struct list_head managed_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; @@ -250,17 +253,21 @@ static inline void *neighbour_priv(const struct neighbour *n) } /* flags for neigh_update() */ -#define NEIGH_UPDATE_F_OVERRIDE 0x00000001 -#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 -#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 -#define NEIGH_UPDATE_F_USE 0x10000000 -#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 -#define NEIGH_UPDATE_F_ISROUTER 0x40000000 -#define NEIGH_UPDATE_F_ADMIN 0x80000000 +#define NEIGH_UPDATE_F_OVERRIDE BIT(0) +#define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) +#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) +#define NEIGH_UPDATE_F_USE BIT(3) +#define NEIGH_UPDATE_F_MANAGED BIT(4) +#define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) +#define NEIGH_UPDATE_F_ISROUTER BIT(6) +#define NEIGH_UPDATE_F_ADMIN BIT(7) /* In-kernel representation for NDA_FLAGS_EXT flags: */ #define NTF_OLD_MASK 0xff #define NTF_EXT_SHIFT 8 +#define NTF_EXT_MASK (NTF_EXT_MANAGED) + +#define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index a80cca141855..db05fb55055e 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -41,14 +41,16 @@ enum { * Neighbor Cache Entry Flags */ -#define NTF_USE 0x01 -#define NTF_SELF 0x02 -#define NTF_MASTER 0x04 -#define NTF_PROXY 0x08 /* == ATF_PUBL */ -#define NTF_EXT_LEARNED 0x10 -#define NTF_OFFLOADED 0x20 -#define NTF_STICKY 0x40 -#define NTF_ROUTER 0x80 +#define NTF_USE (1 << 0) +#define NTF_SELF (1 << 1) +#define NTF_MASTER (1 << 2) +#define NTF_PROXY (1 << 3) /* == ATF_PUBL */ +#define NTF_EXT_LEARNED (1 << 4) +#define NTF_OFFLOADED (1 << 5) +#define NTF_STICKY (1 << 6) +#define NTF_ROUTER (1 << 7) +/* Extended flags under NDA_FLAGS_EXT: */ +#define NTF_EXT_MANAGED (1 << 0) /* * Neighbor Cache Entry States. @@ -66,12 +68,22 @@ enum { #define NUD_PERMANENT 0x80 #define NUD_NONE 0x00 -/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change - * and make no address resolution or NUD. - * NUD_PERMANENT also cannot be deleted by garbage collectors. +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no + * address resolution or NUD. + * + * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true + * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier + * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED + * flagged entries explicitly are (which is also consistent with the routing + * subsystem). + * * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry * states don't make sense and thus are ignored. Such entries don't age and * can roam. + * + * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf + * of a user space control plane, and automatically refreshed so that (if + * possible) they remain in NUD_REACHABLE state. */ struct nda_cacheinfo { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5245e888c981..eae73efa9245 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,6 +122,8 @@ static void neigh_mark_dead(struct neighbour *n) list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } + if (!list_empty(&n->managed_list)) + list_del_init(&n->managed_list); } static void neigh_update_gc_list(struct neighbour *n) @@ -130,7 +132,6 @@ static void neigh_update_gc_list(struct neighbour *n) write_lock_bh(&n->tbl->lock); write_lock(&n->lock); - if (n->dead) goto out; @@ -149,32 +150,59 @@ static void neigh_update_gc_list(struct neighbour *n) list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } +out: + write_unlock(&n->lock); + write_unlock_bh(&n->tbl->lock); +} + +static void neigh_update_managed_list(struct neighbour *n) +{ + bool on_managed_list, add_to_managed; + + write_lock_bh(&n->tbl->lock); + write_lock(&n->lock); + if (n->dead) + goto out; + + add_to_managed = n->flags & NTF_MANAGED; + on_managed_list = !list_empty(&n->managed_list); + if (!add_to_managed && on_managed_list) + list_del_init(&n->managed_list); + else if (add_to_managed && !on_managed_list) + list_add_tail(&n->managed_list, &n->tbl->managed_list); out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } -static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, - int *notify) +static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, + bool *gc_update, bool *managed_update) { - bool rc = false; - u32 ndm_flags; + u32 ndm_flags, old_flags = neigh->flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) - return rc; + return; + + ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0; - ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; - if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; - rc = true; *notify = 1; + *gc_update = true; + } + if ((old_flags ^ ndm_flags) & NTF_MANAGED) { + if (ndm_flags & NTF_MANAGED) + neigh->flags |= NTF_MANAGED; + else + neigh->flags &= ~NTF_MANAGED; + *notify = 1; + *managed_update = true; } - - return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, @@ -422,6 +450,7 @@ do_alloc: refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); + INIT_LIST_HEAD(&n->managed_list); atomic_inc(&tbl->entries); out: @@ -650,7 +679,8 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); - + if (n->flags & NTF_MANAGED) + list_add_tail(&n->managed_list, &n->tbl->managed_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, @@ -1205,8 +1235,6 @@ static void neigh_update_hhs(struct neighbour *neigh) } } - - /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. @@ -1218,6 +1246,7 @@ static void neigh_update_hhs(struct neighbour *neigh) if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. NEIGH_UPDATE_F_USE means that the entry is user triggered. + NEIGH_UPDATE_F_MANAGED means that the entry will be auto-refreshed. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as @@ -1225,17 +1254,15 @@ static void neigh_update_hhs(struct neighbour *neigh) Caller MUST hold reference count on the entry. */ - static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { - bool ext_learn_change = false; - u8 old; - int err; - int notify = 0; - struct net_device *dev; + bool gc_update = false, managed_update = false; int update_isrouter = 0; + struct net_device *dev; + int err, notify = 0; + u8 old; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); @@ -1254,8 +1281,8 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, (old & (NUD_NOARP | NUD_PERMANENT))) goto out; - ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); - if (flags & NEIGH_UPDATE_F_USE) { + neigh_update_flags(neigh, flags, ¬ify, &gc_update, &managed_update); + if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) { new = old & ~NUD_PERMANENT; neigh->nud_state = new; err = 0; @@ -1405,15 +1432,13 @@ out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); - - if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) + if (((new ^ old) & NUD_PERMANENT) || gc_update) neigh_update_gc_list(neigh); - + if (managed_update) + neigh_update_managed_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); - trace_neigh_update_done(neigh, err); - return err; } @@ -1539,6 +1564,20 @@ int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) } EXPORT_SYMBOL(neigh_direct_output); +static void neigh_managed_work(struct work_struct *work) +{ + struct neigh_table *tbl = container_of(work, struct neigh_table, + managed_work.work); + struct neighbour *neigh; + + write_lock_bh(&tbl->lock); + list_for_each_entry(neigh, &tbl->managed_list, managed_list) + neigh_event_send(neigh, NULL); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, + NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); + write_unlock_bh(&tbl->lock); +} + static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); @@ -1685,6 +1724,8 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); + INIT_LIST_HEAD(&tbl->managed_list); + list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); @@ -1716,9 +1757,13 @@ void neigh_table_init(int index, struct neigh_table *tbl) WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); + INIT_DEFERRABLE_WORK(&tbl->managed_work, neigh_managed_work); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, 0); + timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1891,7 +1936,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_FLAGS_EXT]) { u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); - if (ext & ~0) { + if (ext & ~NTF_EXT_MASK) { NL_SET_ERR_MSG(extack, "Invalid extended flags"); goto out; } @@ -1927,6 +1972,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; + if (ndm_flags & NTF_MANAGED) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); + goto out; + } + err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { @@ -1960,7 +2010,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || ndm_flags & NTF_EXT_LEARNED; neigh = ___neigh_create(tbl, dst, dev, - ndm_flags & NTF_EXT_LEARNED, + ndm_flags & + (NTF_EXT_LEARNED | NTF_MANAGED), exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); @@ -1984,12 +2035,14 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, flags |= NEIGH_UPDATE_F_EXT_LEARNED; if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; + if (ndm_flags & NTF_MANAGED) + flags |= NEIGH_UPDATE_F_MANAGED; if (ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (!err && ndm_flags & NTF_USE) { + if (!err && ndm_flags & (NTF_USE | NTF_MANAGED)) { neigh_event_send(neigh, NULL); err = 0; } -- cgit v1.2.3 From 7301d0a9834c7f1f0c91c1f0a46c7b191b1fd0da Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Fri, 8 Oct 2021 15:24:33 +0300 Subject: RDMA/nldev: Add support to get status of all counters This patch adds the ability to get the name, index and status of all counters for each link through RDMA netlink. This can be used for user-space to get the current optional-counter mode. Examples: $ rdma statistic mode link rocep8s0f0/1 optional-counters cc_rx_ce_pkts $ rdma statistic mode supported link rocep8s0f0/1 supported optional-counters cc_rx_ce_pkts,cc_rx_cnp_pkts,cc_tx_cnp_pkts link rocep8s0f1/1 supported optional-counters cc_rx_ce_pkts,cc_rx_cnp_pkts,cc_tx_cnp_pkts Link: https://lore.kernel.org/r/20211008122439.166063-8-markzhang@nvidia.com Signed-off-by: Aharon Landau Signed-off-by: Neta Ostrovsky Signed-off-by: Leon Romanovsky Signed-off-by: Mark Zhang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/nldev.c | 98 ++++++++++++++++++++++++++++++++++++++++ include/uapi/rdma/rdma_netlink.h | 5 ++ 2 files changed, 103 insertions(+) (limited to 'include/uapi') diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 67519730b1ac..210057fef7bd 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -154,6 +154,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = { [RDMA_NLDEV_NET_NS_FD] = { .type = NLA_U32 }, [RDMA_NLDEV_SYS_ATTR_NETNS_MODE] = { .type = NLA_U8 }, [RDMA_NLDEV_SYS_ATTR_COPY_ON_FORK] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_INDEX] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_DYNAMIC] = { .type = NLA_U8 }, }; static int put_driver_name_print_type(struct sk_buff *msg, const char *name, @@ -2264,6 +2266,99 @@ static int nldev_stat_get_dumpit(struct sk_buff *skb, return ret; } +static int nldev_stat_get_counter_status_doit(struct sk_buff *skb, + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX], *table, *entry; + struct rdma_hw_stats *stats; + struct ib_device *device; + struct sk_buff *msg; + u32 devid, port; + int ret, i; + + ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, extack); + if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || + !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) + return -EINVAL; + + devid = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = ib_device_get_by_index(sock_net(skb->sk), devid); + if (!device) + return -EINVAL; + + port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(device, port)) { + ret = -EINVAL; + goto err; + } + + stats = ib_get_hw_stats_port(device, port); + if (!stats) { + ret = -EINVAL; + goto err; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + + nlh = nlmsg_put( + msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_STAT_GET_STATUS), + 0, 0); + + ret = -EMSGSIZE; + if (fill_nldev_handle(msg, device) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) + goto err_msg; + + table = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS); + if (!table) + goto err_msg; + + mutex_lock(&stats->lock); + for (i = 0; i < stats->num_counters; i++) { + entry = nla_nest_start(msg, + RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY); + if (!entry) + goto err_msg_table; + + if (nla_put_string(msg, + RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME, + stats->descs[i].name) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_INDEX, i)) + goto err_msg_entry; + + if ((stats->descs[i].flags & IB_STAT_FLAG_OPTIONAL) && + (nla_put_u8(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_DYNAMIC, + !test_bit(i, stats->is_disabled)))) + goto err_msg_entry; + + nla_nest_end(msg, entry); + } + mutex_unlock(&stats->lock); + + nla_nest_end(msg, table); + nlmsg_end(msg, nlh); + ib_device_put(device); + return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); + +err_msg_entry: + nla_nest_cancel(msg, entry); +err_msg_table: + mutex_unlock(&stats->lock); + nla_nest_cancel(msg, table); +err_msg: + nlmsg_free(msg); +err: + ib_device_put(device); + return ret; +} + static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { [RDMA_NLDEV_CMD_GET] = { .doit = nldev_get_doit, @@ -2353,6 +2448,9 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { .dump = nldev_res_get_mr_raw_dumpit, .flags = RDMA_NL_ADMIN_PERM, }, + [RDMA_NLDEV_CMD_STAT_GET_STATUS] = { + .doit = nldev_stat_get_counter_status_doit, + }, }; void __init nldev_init(void) diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 75a1ae2311d8..e50c357367db 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -297,6 +297,8 @@ enum rdma_nldev_command { RDMA_NLDEV_CMD_RES_SRQ_GET, /* can dump */ + RDMA_NLDEV_CMD_STAT_GET_STATUS, + RDMA_NLDEV_NUM_OPS }; @@ -549,6 +551,9 @@ enum rdma_nldev_attr { RDMA_NLDEV_SYS_ATTR_COPY_ON_FORK, /* u8 */ + RDMA_NLDEV_ATTR_STAT_HWCOUNTER_INDEX, /* u32 */ + RDMA_NLDEV_ATTR_STAT_HWCOUNTER_DYNAMIC, /* u8 */ + /* * Always the end */ -- cgit v1.2.3 From cfc0312d9c83a5bbb66fa73ba47dd1301d75b2e8 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Thu, 7 Oct 2021 15:40:47 -0500 Subject: RDMA/rxe: Move AV from rxe_send_wqe to rxe_send_wr Move the struct rxe_av av from struct rxe_send_wqe to struct rxe_send_wr placing it in wr.ud at the same offset as it was previously. This has the effect of increasing the size of struct rxe_send_wr while keeping the size of struct rxe_send_wqe the same. This better reflects the use of this field which is only used for UD sends. This change has no effect on ABI compatibility so the modified rxe driver will operate with older versions of rdma-core. Link: https://lore.kernel.org/r/20211007204051.10086-2-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_av.c | 2 +- drivers/infiniband/sw/rxe/rxe_verbs.c | 3 ++- include/uapi/rdma/rdma_user_rxe.h | 4 +++- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/sw/rxe/rxe_av.c b/drivers/infiniband/sw/rxe/rxe_av.c index da2e867a1ed9..85580ea5eed0 100644 --- a/drivers/infiniband/sw/rxe/rxe_av.c +++ b/drivers/infiniband/sw/rxe/rxe_av.c @@ -107,5 +107,5 @@ struct rxe_av *rxe_get_av(struct rxe_pkt_info *pkt) if (qp_type(pkt->qp) == IB_QPT_RC || qp_type(pkt->qp) == IB_QPT_UC) return &pkt->qp->pri_av; - return (pkt->wqe) ? &pkt->wqe->av : NULL; + return (pkt->wqe) ? &pkt->wqe->wr.wr.ud.av : NULL; } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index c49ba0381964..4233fd9edfd1 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -581,7 +581,8 @@ static void init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr, if (qp_type(qp) == IB_QPT_UD || qp_type(qp) == IB_QPT_SMI || qp_type(qp) == IB_QPT_GSI) - memcpy(&wqe->av, &to_rah(ud_wr(ibwr)->ah)->av, sizeof(wqe->av)); + memcpy(&wqe->wr.wr.ud.av, &to_rah(ud_wr(ibwr)->ah)->av, + sizeof(struct rxe_av)); if (unlikely(ibwr->send_flags & IB_SEND_INLINE)) copy_inline_data_to_wqe(wqe, ibwr); diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index e283c2220aba..2f1ebbe96434 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -98,6 +98,9 @@ struct rxe_send_wr { __u32 remote_qpn; __u32 remote_qkey; __u16 pkey_index; + __u16 reserved; + __u32 pad[5]; + struct rxe_av av; } ud; struct { __aligned_u64 addr; @@ -148,7 +151,6 @@ struct rxe_dma_info { struct rxe_send_wqe { struct rxe_send_wr wr; - struct rxe_av av; __u32 status; __u32 state; __aligned_u64 iova; -- cgit v1.2.3 From 73a54932100375ba94b31710f1e3f1234f23be0b Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Thu, 7 Oct 2021 15:40:49 -0500 Subject: RDMA/rxe: Create AH index and return to user space Make changes to rdma_user_rxe.h to allow indexing AH objects, passing the index in UD send WRs to the driver and returning the index to the rxe provider. Modify rxe_create_ah() to add an index to AH when created and if called from a new user provider return it to user space. If called from an old provider mark the AH as not having a useful index. Modify rxe_destroy_ah to drop the index before deleting the object. Link: https://lore.kernel.org/r/20211007204051.10086-4-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_verbs.c | 31 ++++++++++++++++++++++++++++++- drivers/infiniband/sw/rxe/rxe_verbs.h | 2 ++ include/uapi/rdma/rdma_user_rxe.h | 8 +++++++- 3 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 4233fd9edfd1..e20f2dd20639 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -158,9 +158,19 @@ static int rxe_create_ah(struct ib_ah *ibah, struct ib_udata *udata) { - int err; struct rxe_dev *rxe = to_rdev(ibah->device); struct rxe_ah *ah = to_rah(ibah); + struct rxe_create_ah_resp __user *uresp = NULL; + int err; + + if (udata) { + /* test if new user provider */ + if (udata->outlen >= sizeof(*uresp)) + uresp = udata->outbuf; + ah->is_user = true; + } else { + ah->is_user = false; + } err = rxe_av_chk_attr(rxe, init_attr->ah_attr); if (err) @@ -170,6 +180,24 @@ static int rxe_create_ah(struct ib_ah *ibah, if (err) return err; + /* create index > 0 */ + rxe_add_index(ah); + ah->ah_num = ah->pelem.index; + + if (uresp) { + /* only if new user provider */ + err = copy_to_user(&uresp->ah_num, &ah->ah_num, + sizeof(uresp->ah_num)); + if (err) { + rxe_drop_index(ah); + rxe_drop_ref(ah); + return -EFAULT; + } + } else if (ah->is_user) { + /* only if old user provider */ + ah->ah_num = 0; + } + rxe_init_av(init_attr->ah_attr, &ah->av); return 0; } @@ -202,6 +230,7 @@ static int rxe_destroy_ah(struct ib_ah *ibah, u32 flags) { struct rxe_ah *ah = to_rah(ibah); + rxe_drop_index(ah); rxe_drop_ref(ah); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 098fde693dbd..c56fae23b6a9 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -48,6 +48,8 @@ struct rxe_ah { struct rxe_pool_entry pelem; struct rxe_pd *pd; struct rxe_av av; + bool is_user; + int ah_num; }; struct rxe_cqe { diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index 2f1ebbe96434..dc9f7a5e203a 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -99,7 +99,8 @@ struct rxe_send_wr { __u32 remote_qkey; __u16 pkey_index; __u16 reserved; - __u32 pad[5]; + __u32 ah_num; + __u32 pad[4]; struct rxe_av av; } ud; struct { @@ -170,6 +171,11 @@ struct rxe_recv_wqe { struct rxe_dma_info dma; }; +struct rxe_create_ah_resp { + __u32 ah_num; + __u32 reserved; +}; + struct rxe_create_cq_resp { struct mminfo mi; }; -- cgit v1.2.3 From 42df6e1d221dddc0f2acf2be37e68d553ad65f96 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 8 Oct 2021 22:06:03 +0200 Subject: netfilter: Introduce egress hook MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support classifying packets with netfilter on egress to satisfy user requirements such as: * outbound security policies for containers (Laura) * filtering and mangling intra-node Direct Server Return (DSR) traffic on a load balancer (Laura) * filtering locally generated traffic coming in through AF_PACKET, such as local ARP traffic generated for clustering purposes or DHCP (Laura; the AF_PACKET plumbing is contained in a follow-up commit) * L2 filtering from ingress and egress for AVB (Audio Video Bridging) and gPTP with nftables (Pablo) * in the future: in-kernel NAT64/NAT46 (Pablo) The egress hook introduced herein complements the ingress hook added by commit e687ad60af09 ("netfilter: add netfilter ingress hook after handle_ing() under unique static key"). A patch for nftables to hook up egress rules from user space has been submitted separately, so users may immediately take advantage of the feature. Alternatively or in addition to netfilter, packets can be classified with traffic control (tc). On ingress, packets are classified first by tc, then by netfilter. On egress, the order is reversed for symmetry. Conceptually, tc and netfilter can be thought of as layers, with netfilter layered above tc. Traffic control is capable of redirecting packets to another interface (man 8 tc-mirred). E.g., an ingress packet may be redirected from the host namespace to a container via a veth connection: tc ingress (host) -> tc egress (veth host) -> tc ingress (veth container) In this case, netfilter egress classifying is not performed when leaving the host namespace! That's because the packet is still on the tc layer. If tc redirects the packet to a physical interface in the host namespace such that it leaves the system, the packet is never subjected to netfilter egress classifying. That is only logical since it hasn't passed through netfilter ingress classifying either. Packets can alternatively be redirected at the netfilter layer using nft fwd. Such a packet *is* subjected to netfilter egress classifying since it has reached the netfilter layer. Internally, the skb->nf_skip_egress flag controls whether netfilter is invoked on egress by __dev_queue_xmit(). Because __dev_queue_xmit() may be called recursively by tunnel drivers such as vxlan, the flag is reverted to false after sch_handle_egress(). This ensures that netfilter is applied both on the overlay and underlying network. Interaction between tc and netfilter is possible by setting and querying skb->mark. If netfilter egress classifying is not enabled on any interface, it is patched out of the data path by way of a static_key and doesn't make a performance difference that is discernible from noise: Before: 1537 1538 1538 1537 1538 1537 Mb/sec After: 1536 1534 1539 1539 1539 1540 Mb/sec Before + tc accept: 1418 1418 1418 1419 1419 1418 Mb/sec After + tc accept: 1419 1424 1418 1419 1422 1420 Mb/sec Before + tc drop: 1620 1619 1619 1619 1620 1620 Mb/sec After + tc drop: 1616 1624 1625 1624 1622 1619 Mb/sec When netfilter egress classifying is enabled on at least one interface, a minimal performance penalty is incurred for every egress packet, even if the interface it's transmitted over doesn't have any netfilter egress rules configured. That is caused by checking dev->nf_hooks_egress against NULL. Measurements were performed on a Core i7-3615QM. Commands to reproduce: ip link add dev foo type dummy ip link set dev foo up modprobe pktgen echo "add_device foo" > /proc/net/pktgen/kpktgend_3 samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh -i foo -n 400000000 -m "11:11:11:11:11:11" -d 1.1.1.1 Accept all traffic with tc: tc qdisc add dev foo clsact tc filter add dev foo egress bpf da bytecode '1,6 0 0 0,' Drop all traffic with tc: tc qdisc add dev foo clsact tc filter add dev foo egress bpf da bytecode '1,6 0 0 2,' Apply this patch when measuring packet drops to avoid errors in dmesg: https://lore.kernel.org/netdev/a73dda33-57f4-95d8-ea51-ed483abd6a7a@iogearbox.net/ Signed-off-by: Lukas Wunner Cc: Laura García Liébana Cc: John Fastabend Cc: Daniel Borkmann Cc: Alexei Starovoitov Cc: Eric Dumazet Cc: Thomas Graf Signed-off-by: Pablo Neira Ayuso --- drivers/net/ifb.c | 3 ++ include/linux/netdevice.h | 4 ++ include/linux/netfilter_netdev.h | 86 ++++++++++++++++++++++++++++++++++++++++ include/linux/skbuff.h | 4 ++ include/uapi/linux/netfilter.h | 1 + net/core/dev.c | 15 ++++++- net/netfilter/Kconfig | 11 +++++ net/netfilter/core.c | 34 ++++++++++++++-- net/netfilter/nfnetlink_hook.c | 16 ++++++-- net/netfilter/nft_chain_filter.c | 4 +- 10 files changed, 168 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index e9258a9f3702..2c319dd27f29 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -75,8 +76,10 @@ static void ifb_ri_tasklet(struct tasklet_struct *t) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { + /* Skip tc and netfilter to prevent redirection loop. */ skb->redirected = 0; skb->tc_skip_classify = 1; + nf_skip_egress(skb, true); u64_stats_update_begin(&txp->tsync); txp->tx_packets++; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d79163208dfd..e9a48068f306 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1861,6 +1861,7 @@ enum netdev_ml_priv_type { * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing + * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) @@ -2161,6 +2162,9 @@ struct net_device { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index 5812b0fb0278..b71b57a83bb4 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -50,11 +50,97 @@ static inline int nf_hook_ingress(struct sk_buff *skb) } #endif /* CONFIG_NETFILTER_INGRESS */ +#ifdef CONFIG_NETFILTER_EGRESS +static inline bool nf_hook_egress_active(void) +{ +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) + return false; +#endif + return true; +} + +/** + * nf_hook_egress - classify packets before transmission + * @skb: packet to be classified + * @rc: result code which shall be returned by __dev_queue_xmit() on failure + * @dev: netdev whose egress hooks shall be applied to @skb + * + * Returns @skb on success or %NULL if the packet was consumed or filtered. + * Caller must hold rcu_read_lock. + * + * On ingress, packets are classified first by tc, then by netfilter. + * On egress, the order is reversed for symmetry. Conceptually, tc and + * netfilter can be thought of as layers, with netfilter layered above tc: + * When tc redirects a packet to another interface, netfilter is not applied + * because the packet is on the tc layer. + * + * The nf_skip_egress flag controls whether netfilter is applied on egress. + * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the + * packet passes through tc and netfilter. Because __dev_queue_xmit() may be + * called recursively by tunnel drivers such as vxlan, the flag is reverted to + * false after sch_handle_egress(). This ensures that netfilter is applied + * both on the overlay and underlying network. + */ +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + struct nf_hook_entries *e; + struct nf_hook_state state; + int ret; + +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + if (skb->nf_skip_egress) + return skb; +#endif + + e = rcu_dereference(dev->nf_hooks_egress); + if (!e) + return skb; + + nf_hook_state_init(&state, NF_NETDEV_EGRESS, + NFPROTO_NETDEV, dev, NULL, NULL, + dev_net(dev), NULL); + ret = nf_hook_slow(skb, &state, e, 0); + + if (ret == 1) { + return skb; + } else if (ret < 0) { + *rc = NET_XMIT_DROP; + return NULL; + } else { /* ret == 0 */ + *rc = NET_XMIT_SUCCESS; + return NULL; + } +} +#else /* CONFIG_NETFILTER_EGRESS */ +static inline bool nf_hook_egress_active(void) +{ + return false; +} + +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + return skb; +} +#endif /* CONFIG_NETFILTER_EGRESS */ + +static inline void nf_skip_egress(struct sk_buff *skb, bool skip) +{ +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + skb->nf_skip_egress = skip; +#endif +} + static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif +#ifdef CONFIG_NETFILTER_EGRESS + RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); +#endif } #endif /* _NETFILTER_NETDEV_H_ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 841e2f0f5240..cb96f1e6460c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -652,6 +652,7 @@ typedef unsigned char *sk_buff_data_t; * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path + * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -868,6 +869,9 @@ struct sk_buff { #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + __u8 nf_skip_egress:1; +#endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index ef9a44286e23..53411ccc69db 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -51,6 +51,7 @@ enum nf_inet_hooks { enum nf_dev_hooks { NF_NETDEV_INGRESS, + NF_NETDEV_EGRESS, NF_NETDEV_NUMHOOKS }; diff --git a/net/core/dev.c b/net/core/dev.c index e4c683029c61..09d74798b440 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3920,6 +3920,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { +#ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; @@ -3955,6 +3956,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) default: break; } +#endif /* CONFIG_NET_CLS_ACT */ return skb; } @@ -4148,13 +4150,20 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; -# ifdef CONFIG_NET_EGRESS +#endif +#ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { + if (nf_hook_egress_active()) { + skb = nf_hook_egress(skb, &rc, dev); + if (!skb) + goto out; + } + nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; + nf_skip_egress(skb, false); } -# endif #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. @@ -5296,6 +5305,7 @@ skip_taps: if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; + nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) @@ -5303,6 +5313,7 @@ skip_taps: if (!skb) goto out; + nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 54395266339d..49c9fae9c62c 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -10,6 +10,17 @@ config NETFILTER_INGRESS This allows you to classify packets from ingress using the Netfilter infrastructure. +config NETFILTER_EGRESS + bool "Netfilter egress support" + default y + select NET_EGRESS + help + This allows you to classify packets before transmission using the + Netfilter infrastructure. + +config NETFILTER_SKIP_EGRESS + def_bool NETFILTER_EGRESS && (NET_CLS_ACT || IFB) + config NETFILTER_NETLINK tristate diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 63d032191e62..3a32a813fcde 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -316,6 +316,12 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hooknum == NF_NETDEV_EGRESS) { + if (dev && dev_net(dev) == net) + return &dev->nf_hooks_egress; + } #endif WARN_ON_ONCE(1); return NULL; @@ -344,6 +350,11 @@ static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) return false; } +static inline bool nf_egress_hook(const struct nf_hook_ops *reg, int pf) +{ + return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; +} + static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL @@ -383,9 +394,18 @@ static int __nf_register_net_hook(struct net *net, int pf, switch (pf) { case NFPROTO_NETDEV: - err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); - if (err < 0) - return err; +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif +#ifndef CONFIG_NETFILTER_EGRESS + if (reg->hooknum == NF_NETDEV_EGRESS) + return -EOPNOTSUPP; +#endif + if ((reg->hooknum != NF_NETDEV_INGRESS && + reg->hooknum != NF_NETDEV_EGRESS) || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) @@ -417,6 +437,10 @@ static int __nf_register_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); @@ -474,6 +498,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index f554e2ea32ee..d5c719c9e36c 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -185,7 +185,7 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) struct net_device *netdev; #endif @@ -221,9 +221,9 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); break; #endif -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) case NFPROTO_NETDEV: - if (hook != NF_NETDEV_INGRESS) + if (hook >= NF_NETDEV_NUMHOOKS) return ERR_PTR(-EOPNOTSUPP); if (!dev) @@ -233,7 +233,15 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de if (!netdev) return ERR_PTR(-ENODEV); - return rcu_dereference(netdev->nf_hooks_ingress); +#ifdef CONFIG_NETFILTER_INGRESS + if (hook == NF_NETDEV_INGRESS) + return rcu_dereference(netdev->nf_hooks_ingress); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hook == NF_NETDEV_EGRESS) + return rcu_dereference(netdev->nf_hooks_egress); +#endif + fallthrough; #endif default: return ERR_PTR(-EPROTONOSUPPORT); diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 5b02408a920b..680fe557686e 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -310,9 +310,11 @@ static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, - .hook_mask = (1 << NF_NETDEV_INGRESS), + .hook_mask = (1 << NF_NETDEV_INGRESS) | + (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; -- cgit v1.2.3 From ea673f17ab7638793a8b9e7fe04b4cb758fa01f1 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Tue, 12 Oct 2021 15:12:45 -0700 Subject: drm/i915/uapi: Add comment clarifying purpose of I915_TILING_* values MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The I915_TILING_* values in our uapi header are intended solely for use with the old get_tiling/set_tiling ioctls that operate on hardware de-tiling fences; all other uapi communication about tiling types is done via framebuffer modifiers rather than with these old values. On newer Intel platforms detiling fences no longer exist so the old get_tiling/set_tiling ioctls are no longer usable and will always return -EOPNOTSUPP. This means there's no reason to add new tiling types (such as the Tile4 format introduced by Xe_HP) to the uapi header here. Any kernel-internal code that needs to represent tiling format should either rely on framebuffer modifiers (as the display code does) or use some kind of non-uapi enum (as the GEM blt selftest now does). References: https://patchwork.freedesktop.org/patch/456656/?series=95308 Cc: Ville Syrjälä Signed-off-by: Matt Roper Reviewed-by: Caz Yokoyama Link: https://patchwork.freedesktop.org/patch/msgid/20211012221245.2609670-1-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index aa2a7eccfb94..9b8e61163c39 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching { #define I915_TILING_NONE 0 #define I915_TILING_X 1 #define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ #define I915_TILING_LAST I915_TILING_Y #define I915_BIT_6_SWIZZLE_NONE 0 -- cgit v1.2.3 From 8b8ff8cc3b8155c18162e8b1f70e1230db176862 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 7 Sep 2021 19:39:01 +0300 Subject: perf/x86: Add new event for AUX output counter index PEBS-via-PT records contain a mask of applicable counters. To identify which event belongs to which counter, a side-band event is needed. Until now, there has been no side-band event, and consequently users were limited to using a single event. Add such a side-band event. Note the event is optimised to output only when the counter index changes for an event. That works only so long as all PEBS-via-PT events are scheduled together, which they are for a recording session because they are in a single group. Also no attribute bit is used to select the new event, so a new kernel is not compatible with older perf tools. The assumption being that PEBS-via-PT is sufficiently esoteric that users will not be troubled by this. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210907163903.11820-2-adrian.hunter@intel.com --- arch/x86/events/core.c | 6 ++++++ arch/x86/events/intel/core.c | 16 ++++++++++++++++ arch/x86/events/perf_event.h | 1 + include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 15 +++++++++++++++ kernel/events/core.c | 30 ++++++++++++++++++++++++++++++ 6 files changed, 69 insertions(+) (limited to 'include/uapi') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..be33423e9762 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); +DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); + DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); @@ -1215,6 +1217,8 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; + static_call_cond(x86_pmu_assign)(event, idx); + switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: @@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable); + static_call_update(x86_pmu_assign, x86_pmu.assign); + static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..a555e7c2dce9 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2402,6 +2402,12 @@ static void intel_pmu_disable_event(struct perf_event *event) intel_pmu_pebs_disable(event); } +static void intel_pmu_assign_event(struct perf_event *event, int idx) +{ + if (is_pebs_pt(event)) + perf_report_aux_output_id(event, idx); +} + static void intel_pmu_del_event(struct perf_event *event) { if (needs_branch_stack(event)) @@ -4494,8 +4500,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value) return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; } +static void intel_aux_output_init(void) +{ + /* Refer also intel_pmu_aux_output_match() */ + if (x86_pmu.intel_cap.pebs_output_pt_available) + x86_pmu.assign = intel_pmu_assign_event; +} + static int intel_pmu_aux_output_match(struct perf_event *event) { + /* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */ if (!x86_pmu.intel_cap.pebs_output_pt_available) return 0; @@ -6301,6 +6315,8 @@ __init int intel_pmu_init(void) if (is_hybrid()) intel_pmu_check_hybrid_pmus((u64)fixed_mask); + intel_aux_output_init(); + return 0; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e3ac05c97b5e..76436a55d9ba 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -726,6 +726,7 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*assign)(struct perf_event *event, int idx); void (*add)(struct perf_event *); void (*del)(struct perf_event *); void (*read)(struct perf_event *event); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2d510ad750ed..126b3a314f3a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1397,6 +1397,7 @@ perf_event_addr_filters(struct perf_event *event) } extern void perf_event_addr_filters_sync(struct perf_event *event); +extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index f92880a15645..c89535de1ec8 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1141,6 +1141,21 @@ enum perf_event_type { */ PERF_RECORD_TEXT_POKE = 20, + /* + * Data written to the AUX area by hardware due to aux_output, may need + * to be matched to the event by an architecture-specific hardware ID. + * This records the hardware ID, but requires sample_id to provide the + * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT + * records from multiple events. + * + * struct { + * struct perf_event_header header; + * u64 hw_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 1cb1f9b8392e..0e90a5084f18 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9062,6 +9062,36 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } +void perf_report_aux_output_id(struct perf_event *event, u64 hw_id) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 hw_id; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + rec.header.type = PERF_RECORD_AUX_OUTPUT_HW_ID; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.hw_id = hw_id; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + static int __perf_event_account_interrupt(struct perf_event *event, int throttle) { -- cgit v1.2.3 From e72aeb9ee0e34c57dc90793d0bf82cab9624d64e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Oct 2021 10:59:18 -0700 Subject: fq_codel: implement L4S style ce_threshold_ect1 marking Add TCA_FQ_CODEL_CE_THRESHOLD_ECT1 boolean option to select Low Latency, Low Loss, Scalable Throughput (L4S) style marking, along with ce_threshold. If enabled, only packets with ECT(1) can be transformed to CE if their sojourn time is above the ce_threshold. Note that this new option does not change rules for codel law. In particular, if TCA_FQ_CODEL_ECN is left enabled (this is the default when fq_codel qdisc is created), ECT(0) packets can still get CE if codel law (as governed by limit/target) decides so. Section 4.3.b of current draft [1] states: b. A scheduler with per-flow queues such as FQ-CoDel or FQ-PIE can be used for L4S. For instance within each queue of an FQ-CoDel system, as well as a CoDel AQM, there is typically also ECN marking at an immediate (unsmoothed) shallow threshold to support use in data centres (see Sec.5.2.7 of [RFC8290]). This can be modified so that the shallow threshold is solely applied to ECT(1) packets. Then if there is a flow of non-ECN or ECT(0) packets in the per-flow-queue, the Classic AQM (e.g. CoDel) is applied; while if there is a flow of ECT(1) packets in the queue, the shallower (typically sub-millisecond) threshold is applied. Tested: tc qd replace dev eth1 root fq_codel ce_threshold_ect1 50usec netperf ... -t TCP_STREAM -- K dctcp tc -s -d qd sh dev eth1 qdisc fq_codel 8022: root refcnt 32 limit 10240p flows 1024 quantum 9212 target 5ms ce_threshold_ect1 49us interval 100ms memory_limit 32Mb ecn drop_batch 64 Sent 14388596616 bytes 9543449 pkt (dropped 0, overlimits 0 requeues 152013) backlog 0b 0p requeues 152013 maxpacket 68130 drop_overlimit 0 new_flow_count 95678 ecn_mark 0 ce_mark 7639 new_flows_len 0 old_flows_len 0 [1] L4S current draft: https://datatracker.ietf.org/doc/html/draft-ietf-tsvwg-l4s-arch Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Ingemar Johansson S Cc: Tom Henderson Cc: Bob Briscoe Signed-off-by: David S. Miller --- include/net/codel.h | 2 ++ include/net/codel_impl.h | 18 +++++++++++++++--- include/uapi/linux/pkt_sched.h | 1 + net/mac80211/sta_info.c | 1 + net/sched/sch_fq_codel.c | 15 +++++++++++---- 5 files changed, 30 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/net/codel.h b/include/net/codel.h index a6e428f80135..5e8b181b76b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,6 +102,7 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled + * @ce_threshold_ect1: if ce_threshold only marks ECT(1) packets */ struct codel_params { codel_time_t target; @@ -109,6 +110,7 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; + bool ce_threshold_ect1; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index d289b91dcd65..7af2c3eb3c43 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,6 +54,7 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; + params->ce_threshold_ect1 = false; params->ecn = false; } @@ -246,9 +247,20 @@ static struct sk_buff *codel_dequeue(void *ctx, vars->rec_inv_sqrt); } end: - if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && - INET_ECN_set_ce(skb)) - stats->ce_mark++; + if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { + bool set_ce = true; + + if (params->ce_threshold_ect1) { + /* Note: if skb_get_dsfield() returns -1, following + * gives INET_ECN_MASK, which is != INET_ECN_ECT_1. + */ + u8 ecn = skb_get_dsfield(skb) & INET_ECN_MASK; + + set_ce = (ecn == INET_ECN_ECT_1); + } + if (set_ce && INET_ECN_set_ce(skb)) + stats->ce_mark++; + } return skb; } diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index ec88590b3198..6be9a84cccfa 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -840,6 +840,7 @@ enum { TCA_FQ_CODEL_CE_THRESHOLD, TCA_FQ_CODEL_DROP_BATCH_SIZE, TCA_FQ_CODEL_MEMORY_LIMIT, + TCA_FQ_CODEL_CE_THRESHOLD_ECT1, __TCA_FQ_CODEL_MAX }; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2b5acb37587f..a39830418434 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -513,6 +513,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->cparams.target = MS2TIME(20); sta->cparams.interval = MS2TIME(100); sta->cparams.ecn = true; + sta->cparams.ce_threshold_ect1 = false; sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index bb0cd6d3d2c2..033d65d06eb1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -362,6 +362,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_CE_THRESHOLD_ECT1] = { .type = NLA_U8 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, @@ -408,6 +409,9 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]) + q->cparams.ce_threshold_ect1 = !!nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]); + if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -544,10 +548,13 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; - if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD && - nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, - codel_time_to_us(q->cparams.ce_threshold))) - goto nla_put_failure; + if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD) { + if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, + codel_time_to_us(q->cparams.ce_threshold))) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_ECT1, q->cparams.ce_threshold_ect1)) + goto nla_put_failure; + } return nla_nest_end(skb, opts); -- cgit v1.2.3 From bea36afa102e37d5e4d9ea519f14d1c92d512e45 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:16 +0900 Subject: ALSA: firewire-motu: add message parser to gather meter information in register DSP model Some of MOTU models allows software to configure their DSP parameters by accessing to their registers. The models multiplex messages for status of DSP into isochronous packet as well as PCM frames. The message includes information of hardware metering, MIDI message, current parameters of DSP. For my convenience, I call them as 'register DSP' model. This patch adds message parser for them to gather hardware meter information. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 35 +++++ sound/firewire/motu/Makefile | 2 +- sound/firewire/motu/amdtp-motu.c | 6 + sound/firewire/motu/motu-protocol-v2.c | 14 +- sound/firewire/motu/motu-protocol-v3.c | 4 +- .../motu/motu-register-dsp-message-parser.c | 145 +++++++++++++++++++++ sound/firewire/motu/motu-stream.c | 6 + sound/firewire/motu/motu.c | 6 + sound/firewire/motu/motu.h | 8 ++ 9 files changed, 219 insertions(+), 7 deletions(-) create mode 100644 sound/firewire/motu/motu-register-dsp-message-parser.c (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index ae12826ed641..347fd7a05596 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -108,4 +108,39 @@ struct snd_firewire_tascam_state { __be32 data[SNDRV_FIREWIRE_TASCAM_STATE_COUNT]; }; +// In below MOTU models, software is allowed to control their DSP by accessing to registers. +// - 828mk2 +// - 896hd +// - Traveler +// - 8 pre +// - Ultralite +// - 4 pre +// - Audio Express +// +// On the other hand, the status of DSP is split into specific messages included in the sequence of +// isochronous packet. ALSA firewire-motu driver gathers the messages and allow userspace applications +// to read it via ioctl. In 828mk2, 896hd, and Traveler, hardware meter for all of physical inputs +// are put into the message, while one pair of physical outputs is selected. The selection is done by +// LSB one byte in asynchronous write quadlet transaction to 0x'ffff'f000'0b2c. +// +// I note that V3HD/V4HD uses asynchronous transaction for the purpose. The destination address is +// registered to 0x'ffff'f000'0b38 and '0b3c by asynchronous write quadlet request. The size of +// message differs between 23 and 51 quadlets. For the case, the number of mixer bus can be extended +// up to 12. + +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT 40 + +/** + * struct snd_firewire_motu_register_dsp_meter - the container for meter information in DSP + * controlled by register access + * @data: Signal level meters. The mapping between position and input/output channel is + * model-dependent. + * + * The structure expresses the part of DSP status for hardware meter. The u8 storage includes linear + * value for audio signal level between 0x00 and 0x7f. + */ +struct snd_firewire_motu_register_dsp_meter { + __u8 data[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT]; +}; + #endif /* _UAPI_SOUND_FIREWIRE_H_INCLUDED */ diff --git a/sound/firewire/motu/Makefile b/sound/firewire/motu/Makefile index acdf66564fb0..edbdf40c7162 100644 --- a/sound/firewire/motu/Makefile +++ b/sound/firewire/motu/Makefile @@ -4,5 +4,5 @@ CFLAGS_amdtp-motu.o := -I$(src) snd-firewire-motu-objs := motu.o amdtp-motu.o motu-transaction.o motu-stream.o \ motu-proc.o motu-pcm.o motu-midi.o motu-hwdep.o \ motu-protocol-v2.o motu-protocol-v3.o \ - motu-protocol-v1.o + motu-protocol-v1.o motu-register-dsp-message-parser.o obj-$(CONFIG_SND_FIREWIRE_MOTU) += snd-firewire-motu.o diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index a18c2c033e83..605b831492ac 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -333,6 +333,7 @@ static unsigned int process_ir_ctx_payloads(struct amdtp_stream *s, unsigned int packets, struct snd_pcm_substream *pcm) { + struct snd_motu *motu = container_of(s, struct snd_motu, tx_stream); struct amdtp_motu *p = s->protocol; unsigned int pcm_frames = 0; int i; @@ -357,6 +358,11 @@ static unsigned int process_ir_ctx_payloads(struct amdtp_stream *s, read_midi_messages(s, buf, data_blocks); } + if (motu->spec->flags & SND_MOTU_SPEC_REGISTER_DSP) { + snd_motu_register_dsp_message_parser_parse(motu, descs, packets, + s->data_block_quadlets); + } + // For tracepoints. if (trace_data_block_sph_enabled() || trace_data_block_message_enabled()) diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c index 2bd4485e4bc7..a5f70efa2e88 100644 --- a/sound/firewire/motu/motu-protocol-v2.c +++ b/sound/firewire/motu/motu-protocol-v2.c @@ -275,7 +275,8 @@ const struct snd_motu_spec snd_motu_spec_828mk2 = { .name = "828mk2", .protocol_version = SND_MOTU_PROTOCOL_V2, .flags = SND_MOTU_SPEC_RX_MIDI_2ND_Q | - SND_MOTU_SPEC_TX_MIDI_2ND_Q, + SND_MOTU_SPEC_TX_MIDI_2ND_Q | + SND_MOTU_SPEC_REGISTER_DSP, .tx_fixed_pcm_chunks = {14, 14, 0}, .rx_fixed_pcm_chunks = {14, 14, 0}, }; @@ -283,7 +284,7 @@ const struct snd_motu_spec snd_motu_spec_828mk2 = { const struct snd_motu_spec snd_motu_spec_896hd = { .name = "896HD", .protocol_version = SND_MOTU_PROTOCOL_V2, - // No support for MIDI. + .flags = SND_MOTU_SPEC_REGISTER_DSP, .tx_fixed_pcm_chunks = {14, 14, 8}, .rx_fixed_pcm_chunks = {14, 14, 8}, }; @@ -292,7 +293,8 @@ const struct snd_motu_spec snd_motu_spec_traveler = { .name = "Traveler", .protocol_version = SND_MOTU_PROTOCOL_V2, .flags = SND_MOTU_SPEC_RX_MIDI_2ND_Q | - SND_MOTU_SPEC_TX_MIDI_2ND_Q, + SND_MOTU_SPEC_TX_MIDI_2ND_Q | + SND_MOTU_SPEC_REGISTER_DSP, .tx_fixed_pcm_chunks = {14, 14, 8}, .rx_fixed_pcm_chunks = {14, 14, 8}, }; @@ -301,7 +303,8 @@ const struct snd_motu_spec snd_motu_spec_ultralite = { .name = "UltraLite", .protocol_version = SND_MOTU_PROTOCOL_V2, .flags = SND_MOTU_SPEC_RX_MIDI_2ND_Q | - SND_MOTU_SPEC_TX_MIDI_2ND_Q, + SND_MOTU_SPEC_TX_MIDI_2ND_Q | + SND_MOTU_SPEC_REGISTER_DSP, .tx_fixed_pcm_chunks = {14, 14, 0}, .rx_fixed_pcm_chunks = {14, 14, 0}, }; @@ -310,7 +313,8 @@ const struct snd_motu_spec snd_motu_spec_8pre = { .name = "8pre", .protocol_version = SND_MOTU_PROTOCOL_V2, .flags = SND_MOTU_SPEC_RX_MIDI_2ND_Q | - SND_MOTU_SPEC_TX_MIDI_2ND_Q, + SND_MOTU_SPEC_TX_MIDI_2ND_Q | + SND_MOTU_SPEC_REGISTER_DSP, // Two dummy chunks always in the end of data block. .tx_fixed_pcm_chunks = {10, 10, 0}, .rx_fixed_pcm_chunks = {6, 6, 0}, diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c index 56e4504e7ec9..d0dd587460de 100644 --- a/sound/firewire/motu/motu-protocol-v3.c +++ b/sound/firewire/motu/motu-protocol-v3.c @@ -293,7 +293,8 @@ const struct snd_motu_spec snd_motu_spec_audio_express = { .name = "AudioExpress", .protocol_version = SND_MOTU_PROTOCOL_V3, .flags = SND_MOTU_SPEC_RX_MIDI_2ND_Q | - SND_MOTU_SPEC_TX_MIDI_3RD_Q, + SND_MOTU_SPEC_TX_MIDI_3RD_Q | + SND_MOTU_SPEC_REGISTER_DSP, .tx_fixed_pcm_chunks = {10, 10, 0}, .rx_fixed_pcm_chunks = {10, 10, 0}, }; @@ -301,6 +302,7 @@ const struct snd_motu_spec snd_motu_spec_audio_express = { const struct snd_motu_spec snd_motu_spec_4pre = { .name = "4pre", .protocol_version = SND_MOTU_PROTOCOL_V3, + .flags = SND_MOTU_SPEC_REGISTER_DSP, .tx_fixed_pcm_chunks = {10, 10, 0}, .rx_fixed_pcm_chunks = {10, 10, 0}, }; diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c new file mode 100644 index 000000000000..efb9708b5b5f --- /dev/null +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// motu-register-dsp-message-parser.c - a part of driver for MOTU FireWire series +// +// Copyright (c) 2021 Takashi Sakamoto + +// Below models allow software to configure their DSP functions by asynchronous transaction +// to access their internal registers. +// * 828 mk2 +// * 896hd +// * Traveler +// * 8 pre +// * Ultralite +// * 4 pre +// * Audio Express +// +// Additionally, isochronous packets from the above models include messages to notify state of +// DSP. The messages are two set of 3 byte data in 2nd and 3rd quadlet of data block. When user +// operates hardware components such as dial and switch, corresponding messages are transferred. +// The messages include Hardware metering and MIDI messages as well. + +#include "motu.h" + +#define MSG_FLAG_POS 4 +#define MSG_FLAG_TYPE_MASK 0xf8 +#define MSG_FLAG_MIDI_MASK 0x01 +#define MSG_FLAG_MODEL_SPECIFIC_MASK 0x06 +#define MSG_FLAG_8PRE 0x00 +#define MSG_FLAG_ULTRALITE 0x04 +#define MSG_FLAG_TRAVELER 0x04 +#define MSG_FLAG_828MK2 0x04 +#define MSG_FLAG_896HD 0x04 +#define MSG_FLAG_4PRE 0x05 // MIDI mask is in 8th byte. +#define MSG_FLAG_AUDIOEXPRESS 0x05 // MIDI mask is in 8th byte. +#define MSG_FLAG_TYPE_SHIFT 3 +#define MSG_VALUE_POS 5 +#define MSG_MIDI_BYTE_POS 6 +#define MSG_METER_IDX_POS 7 + +// In 4 pre and Audio express, meter index is in 6th byte. MIDI flag is in 8th byte and MIDI byte +// is in 7th byte. +#define MSG_METER_IDX_POS_4PRE_AE 6 +#define MSG_MIDI_BYTE_POS_4PRE_AE 7 +#define MSG_FLAG_MIDI_POS_4PRE_AE 8 + +enum register_dsp_msg_type { + // Used for messages with no information. + INVALID = 0x00, + MIXER_SELECT = 0x01, + MIXER_SRC_GAIN = 0x02, + MIXER_SRC_PAN = 0x03, + MIXER_SRC_FLAG = 0x04, + MIXER_OUTPUT_PAIRED_VOLUME = 0x05, + MIXER_OUTPUT_PAIRED_FLAG = 0x06, + MAIN_OUTPUT_PAIRED_VOLUME = 0x07, + HP_OUTPUT_PAIRED_VOLUME = 0x08, + HP_OUTPUT_ASSIGN = 0x09, + // Transferred by all models but the purpose is still unknown. + UNKNOWN_0 = 0x0a, + // Specific to 828mk2, 896hd, Traveler. + UNKNOWN_2 = 0x0c, + // Specific to 828mk2, Traveler, and 896hd (not functional). + LINE_INPUT_BOOST = 0x0d, + // Specific to 828mk2, Traveler, and 896hd (not functional). + LINE_INPUT_NOMINAL_LEVEL = 0x0e, + // Specific to Ultralite, 4 pre, Audio express, and 8 pre (not functional). + INPUT_GAIN_AND_INVERT = 0x15, + // Specific to 4 pre, and Audio express. + INPUT_FLAG = 0x16, + // Specific to 4 pre, and Audio express. + MIXER_SRC_PAIRED_BALANCE = 0x17, + // Specific to 4 pre, and Audio express. + MIXER_SRC_PAIRED_WIDTH = 0x18, + // Transferred by all models. This type of message interposes the series of the other + // messages. The message delivers signal level up to 96.0 kHz. In 828mk2, 896hd, and + // Traveler, one of physical outputs is selected for the message. The selection is done + // by LSB one byte in asynchronous write quadlet transaction to 0x'ffff'f000'0b2c. + METER = 0x1f, +}; + +struct msg_parser { + struct snd_firewire_motu_register_dsp_meter meter; + bool meter_pos_quirk; +}; + +int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu) +{ + struct msg_parser *parser; + parser = devm_kzalloc(&motu->card->card_dev, sizeof(*parser), GFP_KERNEL); + if (!parser) + return -ENOMEM; + if (motu->spec == &snd_motu_spec_4pre || motu->spec == &snd_motu_spec_audio_express) + parser->meter_pos_quirk = true; + motu->message_parser = parser; + return 0; +} + +int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu) +{ + return 0; +} + +void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, + unsigned int desc_count, unsigned int data_block_quadlets) +{ + struct msg_parser *parser = motu->message_parser; + bool meter_pos_quirk = parser->meter_pos_quirk; + int i; + + for (i = 0; i < desc_count; ++i) { + const struct pkt_desc *desc = descs + i; + __be32 *buffer = desc->ctx_payload; + unsigned int data_blocks = desc->data_blocks; + int j; + + for (j = 0; j < data_blocks; ++j) { + u8 *b = (u8 *)buffer; + u8 msg_type = (b[MSG_FLAG_POS] & MSG_FLAG_TYPE_MASK) >> MSG_FLAG_TYPE_SHIFT; + u8 val = b[MSG_VALUE_POS]; + + buffer += data_block_quadlets; + + switch (msg_type) { + case METER: + { + u8 pos; + + if (!meter_pos_quirk) + pos = b[MSG_METER_IDX_POS]; + else + pos = b[MSG_METER_IDX_POS_4PRE_AE]; + + if (pos < 0x80) + pos &= 0x1f; + else + pos = (pos & 0x1f) + 20; + parser->meter.data[pos] = val; + break; + } + default: + break; + } + } + } +} diff --git a/sound/firewire/motu/motu-stream.c b/sound/firewire/motu/motu-stream.c index 9e6ca39ebd7f..654b313ba98d 100644 --- a/sound/firewire/motu/motu-stream.c +++ b/sound/firewire/motu/motu-stream.c @@ -255,6 +255,12 @@ int snd_motu_stream_start_duplex(struct snd_motu *motu) if (err < 0) return err; + if (motu->spec->flags & SND_MOTU_SPEC_REGISTER_DSP) { + err = snd_motu_register_dsp_message_parser_init(motu); + if (err < 0) + return err; + } + err = begin_session(motu); if (err < 0) { dev_err(&motu->unit->device, diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c index f65426238d4c..0edf8f594a55 100644 --- a/sound/firewire/motu/motu.c +++ b/sound/firewire/motu/motu.c @@ -112,6 +112,12 @@ static int motu_probe(struct fw_unit *unit, const struct ieee1394_device_id *ent if (err < 0) goto error; + if (motu->spec->flags & SND_MOTU_SPEC_REGISTER_DSP) { + err = snd_motu_register_dsp_message_parser_new(motu); + if (err < 0) + goto error; + } + err = snd_card_register(card); if (err < 0) goto error; diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index f1a830b358d4..8d6850bb925e 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -78,6 +78,8 @@ struct snd_motu { struct amdtp_domain domain; struct amdtp_motu_cache cache; + + void *message_parser; }; enum snd_motu_spec_flags { @@ -85,6 +87,7 @@ enum snd_motu_spec_flags { SND_MOTU_SPEC_RX_MIDI_3RD_Q = 0x0002, SND_MOTU_SPEC_TX_MIDI_2ND_Q = 0x0004, SND_MOTU_SPEC_TX_MIDI_3RD_Q = 0x0008, + SND_MOTU_SPEC_REGISTER_DSP = 0x0010, }; #define SND_MOTU_CLOCK_RATE_COUNT 6 @@ -270,4 +273,9 @@ static inline int snd_motu_protocol_cache_packet_formats(struct snd_motu *motu) return -ENXIO; } +int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu); +int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu); +void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, + unsigned int desc_count, unsigned int data_block_quadlets); + #endif -- cgit v1.2.3 From 90b28f3bb85c39b11daf29d473ef21a935c70ec5 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:17 +0900 Subject: ALSA: firewire-motu: add message parser for meter information in command DSP model Some of MOTU models allows software to configure their DSP parameters by command included in asynchronous transaction. The models multiplex messages for hardware meters into isochronous packet as well as PCM frames. For convenience, I call them as 'command DSP' model. This patch adds message parser for them to gather hardware meter information. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 30 ++++ sound/firewire/motu/Makefile | 3 +- sound/firewire/motu/amdtp-motu.c | 3 + .../motu/motu-command-dsp-message-parser.c | 160 +++++++++++++++++++++ sound/firewire/motu/motu-protocol-v3.c | 10 +- sound/firewire/motu/motu-stream.c | 4 + sound/firewire/motu/motu.c | 4 + sound/firewire/motu/motu.h | 7 + 8 files changed, 216 insertions(+), 5 deletions(-) create mode 100644 sound/firewire/motu/motu-command-dsp-message-parser.c (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 347fd7a05596..82d4765fbeee 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -143,4 +143,34 @@ struct snd_firewire_motu_register_dsp_meter { __u8 data[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT]; }; +// In below MOTU models, software is allowed to control their DSP by command in frame of +// asynchronous transaction to 0x'ffff'0001'0000: +// +// - 828 mk3 (FireWire only and Hybrid) +// - 896 mk3 (FireWire only and Hybrid) +// - Ultralite mk3 (FireWire only and Hybrid) +// - Traveler mk3 +// - Track 16 +// +// On the other hand, the states of hardware meter is split into specific messages included in the +// sequence of isochronous packet. ALSA firewire-motu driver gathers the message and allow userspace +// application to read it via ioctl. + +#define SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT 400 + +/** + * struct snd_firewire_motu_command_dsp_meter - the container for meter information in DSP + * controlled by command + * @data: Signal level meters. The mapping between position and signal channel is model-dependent. + * + * The structure expresses the part of DSP status for hardware meter. The 32 bit storage is + * estimated to include IEEE 764 32 bit single precision floating point (binary32) value. It is + * expected to be linear value (not logarithm) for audio signal level between 0.0 and +1.0. However, + * the last two quadlets (data[398] and data[399]) are filled with 0xffffffff since they are the + * marker of one period. + */ +struct snd_firewire_motu_command_dsp_meter { + __u32 data[SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT]; +}; + #endif /* _UAPI_SOUND_FIREWIRE_H_INCLUDED */ diff --git a/sound/firewire/motu/Makefile b/sound/firewire/motu/Makefile index edbdf40c7162..3bef2a0b1e2e 100644 --- a/sound/firewire/motu/Makefile +++ b/sound/firewire/motu/Makefile @@ -4,5 +4,6 @@ CFLAGS_amdtp-motu.o := -I$(src) snd-firewire-motu-objs := motu.o amdtp-motu.o motu-transaction.o motu-stream.o \ motu-proc.o motu-pcm.o motu-midi.o motu-hwdep.o \ motu-protocol-v2.o motu-protocol-v3.o \ - motu-protocol-v1.o motu-register-dsp-message-parser.o + motu-protocol-v1.o motu-register-dsp-message-parser.o \ + motu-command-dsp-message-parser.o obj-$(CONFIG_SND_FIREWIRE_MOTU) += snd-firewire-motu.o diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index 605b831492ac..3ea91e281147 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -361,6 +361,9 @@ static unsigned int process_ir_ctx_payloads(struct amdtp_stream *s, if (motu->spec->flags & SND_MOTU_SPEC_REGISTER_DSP) { snd_motu_register_dsp_message_parser_parse(motu, descs, packets, s->data_block_quadlets); + } else if (motu->spec->flags & SND_MOTU_SPEC_COMMAND_DSP) { + snd_motu_command_dsp_message_parser_parse(motu, descs, packets, + s->data_block_quadlets); } // For tracepoints. diff --git a/sound/firewire/motu/motu-command-dsp-message-parser.c b/sound/firewire/motu/motu-command-dsp-message-parser.c new file mode 100644 index 000000000000..6716074f8bc1 --- /dev/null +++ b/sound/firewire/motu/motu-command-dsp-message-parser.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// motu-command-dsp-message-parser.c - a part of driver for MOTU FireWire series +// +// Copyright (c) 2021 Takashi Sakamoto + +// Below models allow software to configure their DSP function by command transferred in +// asynchronous transaction: +// * 828 mk3 (FireWire only and Hybrid) +// * 896 mk3 (FireWire only and Hybrid) +// * Ultralite mk3 (FireWire only and Hybrid) +// * Traveler mk3 +// * Track 16 +// +// Isochronous packets from the above models includes messages to report state of hardware meter. + +#include "motu.h" + +enum msg_parser_state { + INITIALIZED, + FRAGMENT_DETECTED, + AVAILABLE, +}; + +struct msg_parser { + enum msg_parser_state state; + unsigned int interval; + unsigned int message_count; + unsigned int fragment_pos; + unsigned int value_index; + u64 value; + struct snd_firewire_motu_command_dsp_meter meter; +}; + +int snd_motu_command_dsp_message_parser_new(struct snd_motu *motu) +{ + struct msg_parser *parser; + + parser = devm_kzalloc(&motu->card->card_dev, sizeof(*parser), GFP_KERNEL); + if (!parser) + return -ENOMEM; + motu->message_parser = parser; + + return 0; +} + +int snd_motu_command_dsp_message_parser_init(struct snd_motu *motu, enum cip_sfc sfc) +{ + struct msg_parser *parser = motu->message_parser; + + parser->state = INITIALIZED; + + // All of data blocks don't have messages with meaningful information. + switch (sfc) { + case CIP_SFC_176400: + case CIP_SFC_192000: + parser->interval = 4; + break; + case CIP_SFC_88200: + case CIP_SFC_96000: + parser->interval = 2; + break; + case CIP_SFC_32000: + case CIP_SFC_44100: + case CIP_SFC_48000: + default: + parser->interval = 1; + break; + } + + return 0; +} + +#define FRAGMENT_POS 6 +#define MIDI_BYTE_POS 7 +#define MIDI_FLAG_POS 8 +// One value of hardware meter consists of 4 messages. +#define FRAGMENTS_PER_VALUE 4 +#define VALUES_AT_IMAGE_END 0xffffffffffffffff + +void snd_motu_command_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, + unsigned int desc_count, unsigned int data_block_quadlets) +{ + struct msg_parser *parser = motu->message_parser; + unsigned int interval = parser->interval; + int i; + + for (i = 0; i < desc_count; ++i) { + const struct pkt_desc *desc = descs + i; + __be32 *buffer = desc->ctx_payload; + unsigned int data_blocks = desc->data_blocks; + int j; + + for (j = 0; j < data_blocks; ++j) { + u8 *b = (u8 *)buffer; + buffer += data_block_quadlets; + + switch (parser->state) { + case INITIALIZED: + { + u8 fragment = b[FRAGMENT_POS]; + + if (fragment > 0) { + parser->value = fragment; + parser->message_count = 1; + parser->state = FRAGMENT_DETECTED; + } + break; + } + case FRAGMENT_DETECTED: + { + if (parser->message_count % interval == 0) { + u8 fragment = b[FRAGMENT_POS]; + + parser->value >>= 8; + parser->value |= (u64)fragment << 56; + + if (parser->value == VALUES_AT_IMAGE_END) { + parser->state = AVAILABLE; + parser->fragment_pos = 0; + parser->value_index = 0; + parser->message_count = 0; + } + } + ++parser->message_count; + break; + } + case AVAILABLE: + default: + { + if (parser->message_count % interval == 0) { + u8 fragment = b[FRAGMENT_POS]; + + parser->value >>= 8; + parser->value |= (u64)fragment << 56; + ++parser->fragment_pos; + + if (parser->fragment_pos == 4) { + if (parser->value_index < + SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT) { + u32 val = (u32)(parser->value >> 32); + parser->meter.data[parser->value_index] = val; + ++parser->value_index; + } + parser->fragment_pos = 0; + } + + if (parser->value == VALUES_AT_IMAGE_END) { + parser->value_index = 0; + parser->fragment_pos = 0; + parser->message_count = 0; + } + } + ++parser->message_count; + break; + } + } + } + } +} diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c index d0dd587460de..05608e8ca0bc 100644 --- a/sound/firewire/motu/motu-protocol-v3.c +++ b/sound/firewire/motu/motu-protocol-v3.c @@ -261,12 +261,12 @@ int snd_motu_protocol_v3_cache_packet_formats(struct snd_motu *motu) return 0; } - const struct snd_motu_spec snd_motu_spec_828mk3_fw = { .name = "828mk3", .protocol_version = SND_MOTU_PROTOCOL_V3, .flags = SND_MOTU_SPEC_RX_MIDI_3RD_Q | - SND_MOTU_SPEC_TX_MIDI_3RD_Q, + SND_MOTU_SPEC_TX_MIDI_3RD_Q | + SND_MOTU_SPEC_COMMAND_DSP, .tx_fixed_pcm_chunks = {18, 18, 14}, .rx_fixed_pcm_chunks = {14, 14, 10}, }; @@ -275,7 +275,8 @@ const struct snd_motu_spec snd_motu_spec_828mk3_hybrid = { .name = "828mk3", .protocol_version = SND_MOTU_PROTOCOL_V3, .flags = SND_MOTU_SPEC_RX_MIDI_3RD_Q | - SND_MOTU_SPEC_TX_MIDI_3RD_Q, + SND_MOTU_SPEC_TX_MIDI_3RD_Q | + SND_MOTU_SPEC_COMMAND_DSP, .tx_fixed_pcm_chunks = {18, 18, 14}, .rx_fixed_pcm_chunks = {14, 14, 14}, // Additional 4 dummy chunks at higher rate. }; @@ -284,7 +285,8 @@ const struct snd_motu_spec snd_motu_spec_ultralite_mk3 = { .name = "UltraLiteMk3", .protocol_version = SND_MOTU_PROTOCOL_V3, .flags = SND_MOTU_SPEC_RX_MIDI_3RD_Q | - SND_MOTU_SPEC_TX_MIDI_3RD_Q, + SND_MOTU_SPEC_TX_MIDI_3RD_Q | + SND_MOTU_SPEC_COMMAND_DSP, .tx_fixed_pcm_chunks = {18, 14, 10}, .rx_fixed_pcm_chunks = {14, 14, 14}, }; diff --git a/sound/firewire/motu/motu-stream.c b/sound/firewire/motu/motu-stream.c index 654b313ba98d..64aec9c3eefd 100644 --- a/sound/firewire/motu/motu-stream.c +++ b/sound/firewire/motu/motu-stream.c @@ -259,6 +259,10 @@ int snd_motu_stream_start_duplex(struct snd_motu *motu) err = snd_motu_register_dsp_message_parser_init(motu); if (err < 0) return err; + } else if (motu->spec->flags & SND_MOTU_SPEC_COMMAND_DSP) { + err = snd_motu_command_dsp_message_parser_init(motu, motu->tx_stream.sfc); + if (err < 0) + return err; } err = begin_session(motu); diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c index 0edf8f594a55..5fc7ae475537 100644 --- a/sound/firewire/motu/motu.c +++ b/sound/firewire/motu/motu.c @@ -116,6 +116,10 @@ static int motu_probe(struct fw_unit *unit, const struct ieee1394_device_id *ent err = snd_motu_register_dsp_message_parser_new(motu); if (err < 0) goto error; + } else if (motu->spec->flags & SND_MOTU_SPEC_COMMAND_DSP) { + err = snd_motu_command_dsp_message_parser_new(motu); + if (err < 0) + goto error; } err = snd_card_register(card); diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index 8d6850bb925e..d818ce4901c9 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -88,6 +88,7 @@ enum snd_motu_spec_flags { SND_MOTU_SPEC_TX_MIDI_2ND_Q = 0x0004, SND_MOTU_SPEC_TX_MIDI_3RD_Q = 0x0008, SND_MOTU_SPEC_REGISTER_DSP = 0x0010, + SND_MOTU_SPEC_COMMAND_DSP = 0x0020, }; #define SND_MOTU_CLOCK_RATE_COUNT 6 @@ -278,4 +279,10 @@ int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu); void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, unsigned int desc_count, unsigned int data_block_quadlets); + +int snd_motu_command_dsp_message_parser_new(struct snd_motu *motu); +int snd_motu_command_dsp_message_parser_init(struct snd_motu *motu, enum cip_sfc sfc); +void snd_motu_command_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, + unsigned int desc_count, unsigned int data_block_quadlets); + #endif -- cgit v1.2.3 From 58b62ab7025912ce1be36e3ba19d49620a0161b6 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:18 +0900 Subject: ALSA: firewire-motu: add ioctl command to read cached hardware meter This patch adds new ioctl commands for userspace applications to read cached image about hardware meters in register DSP and command DSP models. The content of image differs depending on models. Model-specific parser should be implemented in userspace. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-4-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 2 + .../motu/motu-command-dsp-message-parser.c | 18 +++++++++ sound/firewire/motu/motu-hwdep.c | 44 ++++++++++++++++++++++ .../motu/motu-register-dsp-message-parser.c | 18 +++++++++ sound/firewire/motu/motu.h | 4 ++ 5 files changed, 86 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 82d4765fbeee..a8df8fb03b52 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -80,6 +80,8 @@ union snd_firewire_event { #define SNDRV_FIREWIRE_IOCTL_LOCK _IO('H', 0xf9) #define SNDRV_FIREWIRE_IOCTL_UNLOCK _IO('H', 0xfa) #define SNDRV_FIREWIRE_IOCTL_TASCAM_STATE _IOR('H', 0xfb, struct snd_firewire_tascam_state) +#define SNDRV_FIREWIRE_IOCTL_MOTU_REGISTER_DSP_METER _IOR('H', 0xfc, struct snd_firewire_motu_register_dsp_meter) +#define SNDRV_FIREWIRE_IOCTL_MOTU_COMMAND_DSP_METER _IOR('H', 0xfd, struct snd_firewire_motu_command_dsp_meter) #define SNDRV_FIREWIRE_TYPE_DICE 1 #define SNDRV_FIREWIRE_TYPE_FIREWORKS 2 diff --git a/sound/firewire/motu/motu-command-dsp-message-parser.c b/sound/firewire/motu/motu-command-dsp-message-parser.c index 6716074f8bc1..18689fcfb288 100644 --- a/sound/firewire/motu/motu-command-dsp-message-parser.c +++ b/sound/firewire/motu/motu-command-dsp-message-parser.c @@ -23,6 +23,7 @@ enum msg_parser_state { }; struct msg_parser { + spinlock_t lock; enum msg_parser_state state; unsigned int interval; unsigned int message_count; @@ -39,6 +40,7 @@ int snd_motu_command_dsp_message_parser_new(struct snd_motu *motu) parser = devm_kzalloc(&motu->card->card_dev, sizeof(*parser), GFP_KERNEL); if (!parser) return -ENOMEM; + spin_lock_init(&parser->lock); motu->message_parser = parser; return 0; @@ -83,8 +85,11 @@ void snd_motu_command_dsp_message_parser_parse(struct snd_motu *motu, const stru { struct msg_parser *parser = motu->message_parser; unsigned int interval = parser->interval; + unsigned long flags; int i; + spin_lock_irqsave(&parser->lock, flags); + for (i = 0; i < desc_count; ++i) { const struct pkt_desc *desc = descs + i; __be32 *buffer = desc->ctx_payload; @@ -157,4 +162,17 @@ void snd_motu_command_dsp_message_parser_parse(struct snd_motu *motu, const stru } } } + + spin_unlock_irqrestore(&parser->lock, flags); +} + +void snd_motu_command_dsp_message_parser_copy_meter(struct snd_motu *motu, + struct snd_firewire_motu_command_dsp_meter *meter) +{ + struct msg_parser *parser = motu->message_parser; + unsigned long flags; + + spin_lock_irqsave(&parser->lock, flags); + memcpy(meter, &parser->meter, sizeof(*meter)); + spin_unlock_irqrestore(&parser->lock, flags); } diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index b5ced5d27758..7be576fe4516 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -155,6 +155,50 @@ static int hwdep_ioctl(struct snd_hwdep *hwdep, struct file *file, return hwdep_lock(motu); case SNDRV_FIREWIRE_IOCTL_UNLOCK: return hwdep_unlock(motu); + case SNDRV_FIREWIRE_IOCTL_MOTU_REGISTER_DSP_METER: + { + struct snd_firewire_motu_register_dsp_meter *meter; + int err; + + if (!(motu->spec->flags & SND_MOTU_SPEC_REGISTER_DSP)) + return -ENXIO; + + meter = kzalloc(sizeof(*meter), GFP_KERNEL); + if (!meter) + return -ENOMEM; + + snd_motu_register_dsp_message_parser_copy_meter(motu, meter); + + err = copy_to_user((void __user *)arg, meter, sizeof(*meter)); + kfree(meter); + + if (err) + return -EFAULT; + + return 0; + } + case SNDRV_FIREWIRE_IOCTL_MOTU_COMMAND_DSP_METER: + { + struct snd_firewire_motu_command_dsp_meter *meter; + int err; + + if (!(motu->spec->flags & SND_MOTU_SPEC_COMMAND_DSP)) + return -ENXIO; + + meter = kzalloc(sizeof(*meter), GFP_KERNEL); + if (!meter) + return -ENOMEM; + + snd_motu_command_dsp_message_parser_copy_meter(motu, meter); + + err = copy_to_user((void __user *)arg, meter, sizeof(*meter)); + kfree(meter); + + if (err) + return -EFAULT; + + return 0; + } default: return -ENOIOCTLCMD; } diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index efb9708b5b5f..fe804615294c 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -79,6 +79,7 @@ enum register_dsp_msg_type { }; struct msg_parser { + spinlock_t lock; struct snd_firewire_motu_register_dsp_meter meter; bool meter_pos_quirk; }; @@ -89,6 +90,7 @@ int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu) parser = devm_kzalloc(&motu->card->card_dev, sizeof(*parser), GFP_KERNEL); if (!parser) return -ENOMEM; + spin_lock_init(&parser->lock); if (motu->spec == &snd_motu_spec_4pre || motu->spec == &snd_motu_spec_audio_express) parser->meter_pos_quirk = true; motu->message_parser = parser; @@ -105,8 +107,11 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str { struct msg_parser *parser = motu->message_parser; bool meter_pos_quirk = parser->meter_pos_quirk; + unsigned long flags; int i; + spin_lock_irqsave(&parser->lock, flags); + for (i = 0; i < desc_count; ++i) { const struct pkt_desc *desc = descs + i; __be32 *buffer = desc->ctx_payload; @@ -142,4 +147,17 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str } } } + + spin_unlock_irqrestore(&parser->lock, flags); +} + +void snd_motu_register_dsp_message_parser_copy_meter(struct snd_motu *motu, + struct snd_firewire_motu_register_dsp_meter *meter) +{ + struct msg_parser *parser = motu->message_parser; + unsigned long flags; + + spin_lock_irqsave(&parser->lock, flags); + memcpy(meter, &parser->meter, sizeof(*meter)); + spin_unlock_irqrestore(&parser->lock, flags); } diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index d818ce4901c9..4f70036dea25 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -278,11 +278,15 @@ int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu); int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu); void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, unsigned int desc_count, unsigned int data_block_quadlets); +void snd_motu_register_dsp_message_parser_copy_meter(struct snd_motu *motu, + struct snd_firewire_motu_register_dsp_meter *meter); int snd_motu_command_dsp_message_parser_new(struct snd_motu *motu); int snd_motu_command_dsp_message_parser_init(struct snd_motu *motu, enum cip_sfc sfc); void snd_motu_command_dsp_message_parser_parse(struct snd_motu *motu, const struct pkt_desc *descs, unsigned int desc_count, unsigned int data_block_quadlets); +void snd_motu_command_dsp_message_parser_copy_meter(struct snd_motu *motu, + struct snd_firewire_motu_command_dsp_meter *meter); #endif -- cgit v1.2.3 From dc36a9755a572781903d79f8437d109b72662da5 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:19 +0900 Subject: ALSA: firewire-motu: parse messages for mixer source parameters in register-DSP model In register DSP models, current parameters of DSP are always reported by messages in isochronous packet. When user operates hardware component such as rotary knob, corresponding message is changed. This commit parses the message and cache current parameters of mixer source function, commonly available for all of register DSP models. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-5-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 28 ++++++++++ .../motu/motu-register-dsp-message-parser.c | 64 ++++++++++++++++++++++ 2 files changed, 92 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index a8df8fb03b52..bb5ecff73896 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -145,6 +145,34 @@ struct snd_firewire_motu_register_dsp_meter { __u8 data[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT]; }; +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT 4 +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT 20 + +/** + * snd_firewire_motu_register_dsp_parameter - the container for parameters of DSP controlled + * by register access. + * @mixer.source.gain: The gain of source to mixer. + * @mixer.source.pan: The L/R balance of source to mixer. + * @mixer.source.flag: The flag of source to mixer, including mute, solo. + * @mixer.source.paired_balance: The L/R balance of paired source to mixer, only for 4 pre and + * Audio Express. + * @mixer.source.paired_width: The width of paired source to mixer, only for 4 pre and + * Audio Express. + * + * The structure expresses the set of parameters for DSP controlled by register access. + */ +struct snd_firewire_motu_register_dsp_parameter { + struct { + struct { + __u8 gain[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; + __u8 pan[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; + __u8 flag[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; + __u8 paired_balance[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; + __u8 paired_width[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; + } source[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT]; + } mixer; +}; + // In below MOTU models, software is allowed to control their DSP by command in frame of // asynchronous transaction to 0x'ffff'0001'0000: // diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index fe804615294c..6df40e5ee9db 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -82,6 +82,11 @@ struct msg_parser { spinlock_t lock; struct snd_firewire_motu_register_dsp_meter meter; bool meter_pos_quirk; + + struct snd_firewire_motu_register_dsp_parameter param; + u8 prev_mixer_src_type; + u8 mixer_ch; + u8 mixer_src_ch; }; int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu) @@ -99,6 +104,12 @@ int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu) int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu) { + struct msg_parser *parser = motu->message_parser; + + parser->prev_mixer_src_type = INVALID; + parser->mixer_ch = 0xff; + parser->mixer_src_ch = 0xff; + return 0; } @@ -126,6 +137,59 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str buffer += data_block_quadlets; switch (msg_type) { + case MIXER_SELECT: + { + u8 mixer_ch = val / 0x20; + if (mixer_ch < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT) { + parser->mixer_src_ch = 0; + parser->mixer_ch = mixer_ch; + } + break; + } + case MIXER_SRC_GAIN: + case MIXER_SRC_PAN: + case MIXER_SRC_FLAG: + case MIXER_SRC_PAIRED_BALANCE: + case MIXER_SRC_PAIRED_WIDTH: + { + struct snd_firewire_motu_register_dsp_parameter *param = &parser->param; + u8 mixer_ch = parser->mixer_ch; + u8 mixer_src_ch = parser->mixer_src_ch; + + if (msg_type != parser->prev_mixer_src_type) + mixer_src_ch = 0; + else + ++mixer_src_ch; + parser->prev_mixer_src_type = msg_type; + + if (mixer_ch < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT && + mixer_src_ch < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT) { + u8 mixer_ch = parser->mixer_ch; + + switch (msg_type) { + case MIXER_SRC_GAIN: + param->mixer.source[mixer_ch].gain[mixer_src_ch] = val; + break; + case MIXER_SRC_PAN: + param->mixer.source[mixer_ch].pan[mixer_src_ch] = val; + break; + case MIXER_SRC_FLAG: + param->mixer.source[mixer_ch].flag[mixer_src_ch] = val; + break; + case MIXER_SRC_PAIRED_BALANCE: + param->mixer.source[mixer_ch].paired_balance[mixer_src_ch] = val; + break; + case MIXER_SRC_PAIRED_WIDTH: + param->mixer.source[mixer_ch].paired_width[mixer_src_ch] = val; + break; + default: + break; + } + + parser->mixer_src_ch = mixer_src_ch; + } + break; + } case METER: { u8 pos; -- cgit v1.2.3 From ce69bed5557b05dd1918556d4e90c293382155ae Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:20 +0900 Subject: ALSA: firewire-motu: parse messages for mixer output parameters in register DSP model This commit parses message and cache current parameters of mixer output function, commonly available for all of register DSP model Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-6-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 6 ++++++ .../firewire/motu/motu-register-dsp-message-parser.c | 20 ++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index bb5ecff73896..f663a26c5205 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -158,6 +158,8 @@ struct snd_firewire_motu_register_dsp_meter { * Audio Express. * @mixer.source.paired_width: The width of paired source to mixer, only for 4 pre and * Audio Express. + * @mixer.output.paired_volume: The volume of paired output from mixer. + * @mixer.output.paired_flag: The flag of paired output from mixer. * * The structure expresses the set of parameters for DSP controlled by register access. */ @@ -170,6 +172,10 @@ struct snd_firewire_motu_register_dsp_parameter { __u8 paired_balance[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; __u8 paired_width[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT]; } source[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT]; + struct { + __u8 paired_volume[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT]; + __u8 paired_flag[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT]; + } output; } mixer; }; diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index 6df40e5ee9db..867cb09a3521 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -190,6 +190,26 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str } break; } + case MIXER_OUTPUT_PAIRED_VOLUME: + case MIXER_OUTPUT_PAIRED_FLAG: + { + struct snd_firewire_motu_register_dsp_parameter *param = &parser->param; + u8 mixer_ch = parser->mixer_ch; + + if (mixer_ch < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT) { + switch (msg_type) { + case MIXER_OUTPUT_PAIRED_VOLUME: + param->mixer.output.paired_volume[mixer_ch] = val; + break; + case MIXER_OUTPUT_PAIRED_FLAG: + param->mixer.output.paired_flag[mixer_ch] = val; + break; + default: + break; + } + } + break; + } case METER: { u8 pos; -- cgit v1.2.3 From 6ca81d2b6305a884da441fd0281ff01afd5f8c7e Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:21 +0900 Subject: ALSA: firewire-motu: parse messages for output parameters in register DSP model This commit parses message and cache current parameters of output function, commonly available for all of register DSP model. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-7-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 10 ++++++++++ sound/firewire/motu/motu-register-dsp-message-parser.c | 11 ++++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index f663a26c5205..16ca7b43568b 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -160,6 +160,10 @@ struct snd_firewire_motu_register_dsp_meter { * Audio Express. * @mixer.output.paired_volume: The volume of paired output from mixer. * @mixer.output.paired_flag: The flag of paired output from mixer. + * @output.main_paired_volume: The volume of paired main output. + * @output.hp_paired_volume: The volume of paired hp output. + * @output.hp_paired_assignment: The source assigned to paired hp output. + * @output.reserved: Padding for 32 bit alignment for future extension. * * The structure expresses the set of parameters for DSP controlled by register access. */ @@ -177,6 +181,12 @@ struct snd_firewire_motu_register_dsp_parameter { __u8 paired_flag[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT]; } output; } mixer; + struct { + __u8 main_paired_volume; + __u8 hp_paired_volume; + __u8 hp_paired_assignment; + __u8 reserved[5]; + } output; }; // In below MOTU models, software is allowed to control their DSP by command in frame of diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index 867cb09a3521..244f7ada851f 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -54,7 +54,7 @@ enum register_dsp_msg_type { MIXER_OUTPUT_PAIRED_FLAG = 0x06, MAIN_OUTPUT_PAIRED_VOLUME = 0x07, HP_OUTPUT_PAIRED_VOLUME = 0x08, - HP_OUTPUT_ASSIGN = 0x09, + HP_OUTPUT_PAIRED_ASSIGNMENT = 0x09, // Transferred by all models but the purpose is still unknown. UNKNOWN_0 = 0x0a, // Specific to 828mk2, 896hd, Traveler. @@ -210,6 +210,15 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str } break; } + case MAIN_OUTPUT_PAIRED_VOLUME: + parser->param.output.main_paired_volume = val; + break; + case HP_OUTPUT_PAIRED_VOLUME: + parser->param.output.hp_paired_volume = val; + break; + case HP_OUTPUT_PAIRED_ASSIGNMENT: + parser->param.output.hp_paired_assignment = val; + break; case METER: { u8 pos; -- cgit v1.2.3 From 41cc23389f5fc64bdac78b73935a44bd5abc990d Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:22 +0900 Subject: ALSA: firewire-motu: parse messages for line input parameters in register DSP model This commit parses message and cache current parameters of line input function, available for MOTU 828 mk2 and Traveler. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-8-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 9 +++++++++ sound/firewire/motu/motu-register-dsp-message-parser.c | 6 ++++++ 2 files changed, 15 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 16ca7b43568b..049934e2a53c 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -164,6 +164,10 @@ struct snd_firewire_motu_register_dsp_meter { * @output.hp_paired_volume: The volume of paired hp output. * @output.hp_paired_assignment: The source assigned to paired hp output. * @output.reserved: Padding for 32 bit alignment for future extension. + * @line_input.boost_flag: The flags of boost for line inputs, only for 828mk2 and Traveler. + * @line_input.nominal_level_flag: The flags of nominal level for line inputs, only for 828mk2 and + * Traveler. + * @line_input.reserved: Padding for 32 bit alignment for future extension. * * The structure expresses the set of parameters for DSP controlled by register access. */ @@ -187,6 +191,11 @@ struct snd_firewire_motu_register_dsp_parameter { __u8 hp_paired_assignment; __u8 reserved[5]; } output; + struct { + __u8 boost_flag; + __u8 nominal_level_flag; + __u8 reserved[6]; + } line_input; }; // In below MOTU models, software is allowed to control their DSP by command in frame of diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index 244f7ada851f..85faf7a4e8a3 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -219,6 +219,12 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str case HP_OUTPUT_PAIRED_ASSIGNMENT: parser->param.output.hp_paired_assignment = val; break; + case LINE_INPUT_BOOST: + parser->param.line_input.boost_flag = val; + break; + case LINE_INPUT_NOMINAL_LEVEL: + parser->param.line_input.nominal_level_flag = val; + break; case METER: { u8 pos; -- cgit v1.2.3 From 7d843c494a9b69d07bc0588124599e3f665a1496 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:23 +0900 Subject: ALSA: firewire-motu: parse messages for input parameters in register DSP model This commit parses message and cache current parameters of input function, available for MOTU Ultralite, 4 pre, and Audio Express. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-9-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 12 ++++++ .../motu/motu-register-dsp-message-parser.c | 43 +++++++++++++++++++++- 2 files changed, 53 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 049934e2a53c..6366127e923e 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -147,6 +147,8 @@ struct snd_firewire_motu_register_dsp_meter { #define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_COUNT 4 #define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_MIXER_SRC_COUNT 20 +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_INPUT_COUNT 10 +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_ALIGNED_INPUT_COUNT (SNDRV_FIREWIRE_MOTU_REGISTER_DSP_INPUT_COUNT + 2) /** * snd_firewire_motu_register_dsp_parameter - the container for parameters of DSP controlled @@ -168,6 +170,11 @@ struct snd_firewire_motu_register_dsp_meter { * @line_input.nominal_level_flag: The flags of nominal level for line inputs, only for 828mk2 and * Traveler. * @line_input.reserved: Padding for 32 bit alignment for future extension. + * @input.gain_and_invert: The value including gain and invert for input, only for Ultralite, 4 pre + * and Audio Express. + * @input.flag: The flag of input; e.g. jack detection, phantom power, and pad, only for Ultralite, + * 4 pre and Audio express. + * @reserved: Padding so that the size of structure is kept to 512 byte, but for future extension. * * The structure expresses the set of parameters for DSP controlled by register access. */ @@ -196,6 +203,11 @@ struct snd_firewire_motu_register_dsp_parameter { __u8 nominal_level_flag; __u8 reserved[6]; } line_input; + struct { + __u8 gain_and_invert[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_ALIGNED_INPUT_COUNT]; + __u8 flag[SNDRV_FIREWIRE_MOTU_REGISTER_DSP_ALIGNED_INPUT_COUNT]; + } input; + __u8 reserved[64]; }; // In below MOTU models, software is allowed to control their DSP by command in frame of diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index 85faf7a4e8a3..d94ca4875714 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -87,6 +87,9 @@ struct msg_parser { u8 prev_mixer_src_type; u8 mixer_ch; u8 mixer_src_ch; + + u8 input_ch; + u8 prev_msg_type; }; int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu) @@ -109,6 +112,7 @@ int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu) parser->prev_mixer_src_type = INVALID; parser->mixer_ch = 0xff; parser->mixer_src_ch = 0xff; + parser->prev_msg_type = INVALID; return 0; } @@ -225,6 +229,35 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str case LINE_INPUT_NOMINAL_LEVEL: parser->param.line_input.nominal_level_flag = val; break; + case INPUT_GAIN_AND_INVERT: + case INPUT_FLAG: + { + struct snd_firewire_motu_register_dsp_parameter *param = &parser->param; + u8 input_ch = parser->input_ch; + + if (parser->prev_msg_type != msg_type) + input_ch = 0; + else + ++input_ch; + + if (input_ch < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_INPUT_COUNT) { + switch (msg_type) { + case INPUT_GAIN_AND_INVERT: + param->input.gain_and_invert[input_ch] = val; + break; + case INPUT_FLAG: + param->input.flag[input_ch] = val; + break; + default: + break; + } + parser->input_ch = input_ch; + } + break; + } + case UNKNOWN_0: + case UNKNOWN_2: + break; case METER: { u8 pos; @@ -239,11 +272,17 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str else pos = (pos & 0x1f) + 20; parser->meter.data[pos] = val; - break; + // The message for meter is interruptible to the series of other + // types of messages. Don't cache it. + fallthrough; } + case INVALID: default: - break; + // Don't cache it. + continue; } + + parser->prev_msg_type = msg_type; } } -- cgit v1.2.3 From ca15a09ccc5bd2731c5fcb667e6ea3bbbf8f5772 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:24 +0900 Subject: ALSA: firewire-motu: add ioctl command to read cached parameters in register DSP model This patch adds new ioctl command for userspace applications to read cached parameters of register DSP. The structured data includes model-dependent parameters. Userspace application should be carefully programmed so that what parameter is common and specific. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-10-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 1 + sound/firewire/motu/motu-hwdep.c | 21 +++++++++++++++++++++ .../motu/motu-register-dsp-message-parser.c | 11 +++++++++++ sound/firewire/motu/motu.h | 3 ++- 4 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 6366127e923e..d52691655d79 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -82,6 +82,7 @@ union snd_firewire_event { #define SNDRV_FIREWIRE_IOCTL_TASCAM_STATE _IOR('H', 0xfb, struct snd_firewire_tascam_state) #define SNDRV_FIREWIRE_IOCTL_MOTU_REGISTER_DSP_METER _IOR('H', 0xfc, struct snd_firewire_motu_register_dsp_meter) #define SNDRV_FIREWIRE_IOCTL_MOTU_COMMAND_DSP_METER _IOR('H', 0xfd, struct snd_firewire_motu_command_dsp_meter) +#define SNDRV_FIREWIRE_IOCTL_MOTU_REGISTER_DSP_PARAMETER _IOR('H', 0xfe, struct snd_firewire_motu_register_dsp_parameter) #define SNDRV_FIREWIRE_TYPE_DICE 1 #define SNDRV_FIREWIRE_TYPE_FIREWORKS 2 diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index 7be576fe4516..699136b911c7 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -199,6 +199,27 @@ static int hwdep_ioctl(struct snd_hwdep *hwdep, struct file *file, return 0; } + case SNDRV_FIREWIRE_IOCTL_MOTU_REGISTER_DSP_PARAMETER: + { + struct snd_firewire_motu_register_dsp_parameter *param; + int err; + + if (!(motu->spec->flags & SND_MOTU_SPEC_REGISTER_DSP)) + return -ENXIO; + + param = kzalloc(sizeof(*param), GFP_KERNEL); + if (!param) + return -ENOMEM; + + snd_motu_register_dsp_message_parser_copy_parameter(motu, param); + + err = copy_to_user((void __user *)arg, param, sizeof(*param)); + kfree(param); + if (err) + return -EFAULT; + + return 0; + } default: return -ENOIOCTLCMD; } diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index d94ca4875714..ed9fd0cef200 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -299,3 +299,14 @@ void snd_motu_register_dsp_message_parser_copy_meter(struct snd_motu *motu, memcpy(meter, &parser->meter, sizeof(*meter)); spin_unlock_irqrestore(&parser->lock, flags); } + +void snd_motu_register_dsp_message_parser_copy_parameter(struct snd_motu *motu, + struct snd_firewire_motu_register_dsp_parameter *param) +{ + struct msg_parser *parser = motu->message_parser; + unsigned long flags; + + spin_lock_irqsave(&parser->lock, flags); + memcpy(param, &parser->param, sizeof(*param)); + spin_unlock_irqrestore(&parser->lock, flags); +} diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index 4f70036dea25..fa0b3ab7b78d 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -280,7 +280,8 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str unsigned int desc_count, unsigned int data_block_quadlets); void snd_motu_register_dsp_message_parser_copy_meter(struct snd_motu *motu, struct snd_firewire_motu_register_dsp_meter *meter); - +void snd_motu_register_dsp_message_parser_copy_parameter(struct snd_motu *motu, + struct snd_firewire_motu_register_dsp_parameter *params); int snd_motu_command_dsp_message_parser_new(struct snd_motu *motu); int snd_motu_command_dsp_message_parser_init(struct snd_motu *motu, enum cip_sfc sfc); -- cgit v1.2.3 From 634ec0b2906efd46f6f57977e172aa3470aca432 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 15 Oct 2021 17:08:26 +0900 Subject: ALSA: firewire-motu: notify event for parameter change in register DSP model This commit copies queued event for change of register DSP into userspace when application operates ALSA hwdep character device. The notification occurs only when packet streaming is running. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211015080826.34847-12-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 8 ++++ sound/firewire/motu/motu-hwdep.c | 46 +++++++++++++++++----- .../motu/motu-register-dsp-message-parser.c | 39 ++++++++++++++++++ sound/firewire/motu/motu.h | 2 + 4 files changed, 86 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index d52691655d79..76190a0cb069 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -13,6 +13,7 @@ #define SNDRV_FIREWIRE_EVENT_DIGI00X_MESSAGE 0x746e736c #define SNDRV_FIREWIRE_EVENT_MOTU_NOTIFICATION 0x64776479 #define SNDRV_FIREWIRE_EVENT_TASCAM_CONTROL 0x7473636d +#define SNDRV_FIREWIRE_EVENT_MOTU_REGISTER_DSP_CHANGE 0x4d545244 struct snd_firewire_event_common { unsigned int type; /* SNDRV_FIREWIRE_EVENT_xxx */ @@ -65,6 +66,12 @@ struct snd_firewire_event_tascam_control { struct snd_firewire_tascam_change changes[0]; }; +struct snd_firewire_event_motu_register_dsp_change { + unsigned int type; + __u32 count; // The number of changes. + __u32 changes[]; // Encoded event for change of register DSP. +}; + union snd_firewire_event { struct snd_firewire_event_common common; struct snd_firewire_event_lock_status lock_status; @@ -73,6 +80,7 @@ union snd_firewire_event { struct snd_firewire_event_digi00x_message digi00x_message; struct snd_firewire_event_tascam_control tascam_control; struct snd_firewire_event_motu_notification motu_notification; + struct snd_firewire_event_motu_register_dsp_change motu_register_dsp_change; }; diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index 389e59ff768b..9c2e457ce692 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -25,7 +25,8 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, spin_lock_irq(&motu->lock); - while (!motu->dev_lock_changed && motu->msg == 0) { + while (!motu->dev_lock_changed && motu->msg == 0 && + snd_motu_register_dsp_message_parser_count_event(motu) == 0) { prepare_to_wait(&motu->hwdep_wait, &wait, TASK_INTERRUPTIBLE); spin_unlock_irq(&motu->lock); schedule(); @@ -40,20 +41,46 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS; event.lock_status.status = (motu->dev_lock_count > 0); motu->dev_lock_changed = false; + spin_unlock_irq(&motu->lock); - count = min_t(long, count, sizeof(event.lock_status)); - } else { + count = min_t(long, count, sizeof(event)); + if (copy_to_user(buf, &event, count)) + return -EFAULT; + } else if (motu->msg > 0) { event.motu_notification.type = SNDRV_FIREWIRE_EVENT_MOTU_NOTIFICATION; event.motu_notification.message = motu->msg; motu->msg = 0; + spin_unlock_irq(&motu->lock); - count = min_t(long, count, sizeof(event.motu_notification)); - } + count = min_t(long, count, sizeof(event)); + if (copy_to_user(buf, &event, count)) + return -EFAULT; + } else if (snd_motu_register_dsp_message_parser_count_event(motu) > 0) { + size_t consumed = 0; + u32 __user *ptr; + u32 ev; - spin_unlock_irq(&motu->lock); + spin_unlock_irq(&motu->lock); - if (copy_to_user(buf, &event, count)) - return -EFAULT; + // Header is filled later. + consumed += sizeof(event.motu_register_dsp_change); + + while (consumed < count && + snd_motu_register_dsp_message_parser_copy_event(motu, &ev)) { + ptr = (u32 __user *)(buf + consumed); + if (put_user(ev, ptr)) + return -EFAULT; + consumed += sizeof(ev); + } + + event.motu_register_dsp_change.type = SNDRV_FIREWIRE_EVENT_MOTU_REGISTER_DSP_CHANGE; + event.motu_register_dsp_change.count = + (consumed - sizeof(event.motu_register_dsp_change)) / 4; + if (copy_to_user(buf, &event, sizeof(event.motu_register_dsp_change))) + return -EFAULT; + + count = consumed; + } return count; } @@ -67,7 +94,8 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, poll_wait(file, &motu->hwdep_wait, wait); spin_lock_irq(&motu->lock); - if (motu->dev_lock_changed || motu->msg) + if (motu->dev_lock_changed || motu->msg || + snd_motu_register_dsp_message_parser_count_event(motu) > 0) events = EPOLLIN | EPOLLRDNORM; else events = 0; diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index cda8e6d987cc..cbc06b3b70f6 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -95,6 +95,7 @@ struct msg_parser { u32 event_queue[EVENT_QUEUE_SIZE]; unsigned int push_pos; + unsigned int pull_pos; }; int snd_motu_register_dsp_message_parser_new(struct snd_motu *motu) @@ -122,6 +123,7 @@ int snd_motu_register_dsp_message_parser_init(struct snd_motu *motu) return 0; } +// Rough implementaion of queue without overrun check. static void queue_event(struct snd_motu *motu, u8 msg_type, u8 identifier0, u8 identifier1, u8 val) { struct msg_parser *parser = motu->message_parser; @@ -145,6 +147,7 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str { struct msg_parser *parser = motu->message_parser; bool meter_pos_quirk = parser->meter_pos_quirk; + unsigned int pos = parser->push_pos; unsigned long flags; int i; @@ -351,6 +354,9 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str } } + if (pos != parser->push_pos) + wake_up(&motu->hwdep_wait); + spin_unlock_irqrestore(&parser->lock, flags); } @@ -375,3 +381,36 @@ void snd_motu_register_dsp_message_parser_copy_parameter(struct snd_motu *motu, memcpy(param, &parser->param, sizeof(*param)); spin_unlock_irqrestore(&parser->lock, flags); } + +unsigned int snd_motu_register_dsp_message_parser_count_event(struct snd_motu *motu) +{ + struct msg_parser *parser = motu->message_parser; + + if (parser->pull_pos > parser->push_pos) + return EVENT_QUEUE_SIZE - parser->pull_pos + parser->push_pos; + else + return parser->push_pos - parser->pull_pos; +} + +bool snd_motu_register_dsp_message_parser_copy_event(struct snd_motu *motu, u32 *event) +{ + struct msg_parser *parser = motu->message_parser; + unsigned int pos = parser->pull_pos; + unsigned long flags; + + if (pos == parser->push_pos) + return false; + + spin_lock_irqsave(&parser->lock, flags); + + *event = parser->event_queue[pos]; + + ++pos; + if (pos >= EVENT_QUEUE_SIZE) + pos = 0; + parser->pull_pos = pos; + + spin_unlock_irqrestore(&parser->lock, flags); + + return true; +} diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h index 9703d3af59ec..79704ae6a73e 100644 --- a/sound/firewire/motu/motu.h +++ b/sound/firewire/motu/motu.h @@ -283,6 +283,8 @@ void snd_motu_register_dsp_message_parser_copy_meter(struct snd_motu *motu, struct snd_firewire_motu_register_dsp_meter *meter); void snd_motu_register_dsp_message_parser_copy_parameter(struct snd_motu *motu, struct snd_firewire_motu_register_dsp_parameter *params); +unsigned int snd_motu_register_dsp_message_parser_count_event(struct snd_motu *motu); +bool snd_motu_register_dsp_message_parser_copy_event(struct snd_motu *motu, u32 *event); int snd_motu_command_dsp_message_parser_new(struct snd_motu *motu); int snd_motu_command_dsp_message_parser_init(struct snd_motu *motu, enum cip_sfc sfc); -- cgit v1.2.3 From 9409eb35942713d0cdd471e5ff99c93929d6a749 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Thu, 14 Oct 2021 10:19:46 -0700 Subject: drm/i915: Expose logical engine instance to user Expose logical engine instance to user via query engine info IOCTL. This is required for split-frame workloads as these needs to be placed on engines in a logically contiguous order. The logical mapping can change based on fusing. Rather than having user have knowledge of the fusing we simply just expose the logical mapping with the existing query engine info IOCTL. IGT: https://patchwork.freedesktop.org/patch/445637/?series=92854&rev=1 media UMD: https://github.com/intel/media-driver/pull/1252 v2: (Daniel Vetter) - Add IGT link, placeholder for media UMD Cc: Tvrtko Ursulin Signed-off-by: Matthew Brost Reviewed-by: John Harrison Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-7-matthew.brost@intel.com --- drivers/gpu/drm/i915/i915_query.c | 2 ++ include/uapi/drm/i915_drm.h | 8 +++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 5e2b909827f4..51b368be0fc4 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -124,7 +124,9 @@ query_engine_info(struct drm_i915_private *i915, for_each_uabi_engine(engine, i915) { info.engine.engine_class = engine->uabi_class; info.engine.engine_instance = engine->uabi_instance; + info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE; info.capabilities = engine->uabi_capabilities; + info.logical_instance = ilog2(engine->logical_mask); if (copy_to_user(info_ptr, &info, sizeof(info))) return -EFAULT; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index aa2a7eccfb94..0179f92e0916 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2775,14 +2775,20 @@ struct drm_i915_engine_info { /** @flags: Engine flags. */ __u64 flags; +#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0) /** @capabilities: Capabilities of this engine. */ __u64 capabilities; #define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + /** @logical_instance: Logical instance of engine */ + __u16 logical_instance; + /** @rsvd1: Reserved fields. */ - __u64 rsvd1[4]; + __u16 rsvd1[3]; + /** @rsvd2: Reserved fields. */ + __u64 rsvd2[3]; }; /** -- cgit v1.2.3 From e5e32171a2cf1e434d4f88e12467f3e47d0ec618 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Thu, 14 Oct 2021 10:19:56 -0700 Subject: drm/i915/guc: Connect UAPI to GuC multi-lrc interface Introduce 'set parallel submit' extension to connect UAPI to GuC multi-lrc interface. Kernel doc in new uAPI should explain it all. IGT: https://patchwork.freedesktop.org/patch/447008/?series=93071&rev=1 media UMD: https://github.com/intel/media-driver/pull/1252 v2: (Daniel Vetter) - Add IGT link and placeholder for media UMD link v3: (Kernel test robot) - Fix warning in unpin engines call (John Harrison) - Reword a bunch of the kernel doc v4: (John Harrison) - Add comment why perma-pin is done after setting gem context - Update some comments / docs for proto contexts v5: (John Harrison) - Rework perma-pin comment - Add BUG_IN if context is pinned when setting gem context Cc: Tvrtko Ursulin Signed-off-by: Matthew Brost Reviewed-by: John Harrison Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-17-matthew.brost@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 230 ++++++++++++++++++++- drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 16 +- drivers/gpu/drm/i915/gt/intel_context_types.h | 9 +- drivers/gpu/drm/i915/gt/intel_engine.h | 12 +- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 6 +- .../gpu/drm/i915/gt/intel_execlists_submission.c | 6 +- drivers/gpu/drm/i915/gt/selftest_execlists.c | 12 +- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 114 ++++++++-- include/uapi/drm/i915_drm.h | 131 ++++++++++++ 9 files changed, 505 insertions(+), 31 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index d225d3dd0b40..9a00f11fef46 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -556,9 +556,150 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data) return 0; } +static int +set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, + void *data) +{ + struct i915_context_engines_parallel_submit __user *ext = + container_of_user(base, typeof(*ext), base); + const struct set_proto_ctx_engines *set = data; + struct drm_i915_private *i915 = set->i915; + u64 flags; + int err = 0, n, i, j; + u16 slot, width, num_siblings; + struct intel_engine_cs **siblings = NULL; + intel_engine_mask_t prev_mask; + + /* Disabling for now */ + return -ENODEV; + + /* FIXME: This is NIY for execlists */ + if (!(intel_uc_uses_guc_submission(&i915->gt.uc))) + return -ENODEV; + + if (get_user(slot, &ext->engine_index)) + return -EFAULT; + + if (get_user(width, &ext->width)) + return -EFAULT; + + if (get_user(num_siblings, &ext->num_siblings)) + return -EFAULT; + + if (slot >= set->num_engines) { + drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n", + slot, set->num_engines); + return -EINVAL; + } + + if (set->engines[slot].type != I915_GEM_ENGINE_TYPE_INVALID) { + drm_dbg(&i915->drm, + "Invalid placement[%d], already occupied\n", slot); + return -EINVAL; + } + + if (get_user(flags, &ext->flags)) + return -EFAULT; + + if (flags) { + drm_dbg(&i915->drm, "Unknown flags 0x%02llx", flags); + return -EINVAL; + } + + for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) { + err = check_user_mbz(&ext->mbz64[n]); + if (err) + return err; + } + + if (width < 2) { + drm_dbg(&i915->drm, "Width (%d) < 2\n", width); + return -EINVAL; + } + + if (num_siblings < 1) { + drm_dbg(&i915->drm, "Number siblings (%d) < 1\n", + num_siblings); + return -EINVAL; + } + + siblings = kmalloc_array(num_siblings * width, + sizeof(*siblings), + GFP_KERNEL); + if (!siblings) + return -ENOMEM; + + /* Create contexts / engines */ + for (i = 0; i < width; ++i) { + intel_engine_mask_t current_mask = 0; + struct i915_engine_class_instance prev_engine; + + for (j = 0; j < num_siblings; ++j) { + struct i915_engine_class_instance ci; + + n = i * num_siblings + j; + if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) { + err = -EFAULT; + goto out_err; + } + + siblings[n] = + intel_engine_lookup_user(i915, ci.engine_class, + ci.engine_instance); + if (!siblings[n]) { + drm_dbg(&i915->drm, + "Invalid sibling[%d]: { class:%d, inst:%d }\n", + n, ci.engine_class, ci.engine_instance); + err = -EINVAL; + goto out_err; + } + + if (n) { + if (prev_engine.engine_class != + ci.engine_class) { + drm_dbg(&i915->drm, + "Mismatched class %d, %d\n", + prev_engine.engine_class, + ci.engine_class); + err = -EINVAL; + goto out_err; + } + } + + prev_engine = ci; + current_mask |= siblings[n]->logical_mask; + } + + if (i > 0) { + if (current_mask != prev_mask << 1) { + drm_dbg(&i915->drm, + "Non contiguous logical mask 0x%x, 0x%x\n", + prev_mask, current_mask); + err = -EINVAL; + goto out_err; + } + } + prev_mask = current_mask; + } + + set->engines[slot].type = I915_GEM_ENGINE_TYPE_PARALLEL; + set->engines[slot].num_siblings = num_siblings; + set->engines[slot].width = width; + set->engines[slot].siblings = siblings; + + return 0; + +out_err: + kfree(siblings); + + return err; +} + static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = { [I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance, [I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond, + [I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT] = + set_proto_ctx_engines_parallel_submit, }; static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv, @@ -794,6 +935,7 @@ static int intel_context_set_gem(struct intel_context *ce, GEM_BUG_ON(rcu_access_pointer(ce->gem_context)); RCU_INIT_POINTER(ce->gem_context, ctx); + GEM_BUG_ON(intel_context_is_pinned(ce)); ce->ring_size = SZ_16K; i915_vm_put(ce->vm); @@ -818,6 +960,25 @@ static int intel_context_set_gem(struct intel_context *ce, return ret; } +static void __unpin_engines(struct i915_gem_engines *e, unsigned int count) +{ + while (count--) { + struct intel_context *ce = e->engines[count], *child; + + if (!ce || !test_bit(CONTEXT_PERMA_PIN, &ce->flags)) + continue; + + for_each_child(ce, child) + intel_context_unpin(child); + intel_context_unpin(ce); + } +} + +static void unpin_engines(struct i915_gem_engines *e) +{ + __unpin_engines(e, e->num_engines); +} + static void __free_engines(struct i915_gem_engines *e, unsigned int count) { while (count--) { @@ -933,6 +1094,40 @@ free_engines: return err; } +static int perma_pin_contexts(struct intel_context *ce) +{ + struct intel_context *child; + int i = 0, j = 0, ret; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + ret = intel_context_pin(ce); + if (unlikely(ret)) + return ret; + + for_each_child(ce, child) { + ret = intel_context_pin(child); + if (unlikely(ret)) + goto unwind; + ++i; + } + + set_bit(CONTEXT_PERMA_PIN, &ce->flags); + + return 0; + +unwind: + intel_context_unpin(ce); + for_each_child(ce, child) { + if (j++ < i) + intel_context_unpin(child); + else + break; + } + + return ret; +} + static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, unsigned int num_engines, struct i915_gem_proto_engine *pe) @@ -946,7 +1141,7 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, e->num_engines = num_engines; for (n = 0; n < num_engines; n++) { - struct intel_context *ce; + struct intel_context *ce, *child; int ret; switch (pe[n].type) { @@ -956,7 +1151,13 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, case I915_GEM_ENGINE_TYPE_BALANCED: ce = intel_engine_create_virtual(pe[n].siblings, - pe[n].num_siblings); + pe[n].num_siblings, 0); + break; + + case I915_GEM_ENGINE_TYPE_PARALLEL: + ce = intel_engine_create_parallel(pe[n].siblings, + pe[n].num_siblings, + pe[n].width); break; case I915_GEM_ENGINE_TYPE_INVALID: @@ -977,6 +1178,30 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, err = ERR_PTR(ret); goto free_engines; } + for_each_child(ce, child) { + ret = intel_context_set_gem(child, ctx, pe->sseu); + if (ret) { + err = ERR_PTR(ret); + goto free_engines; + } + } + + /* + * XXX: Must be done after calling intel_context_set_gem as that + * function changes the ring size. The ring is allocated when + * the context is pinned. If the ring size is changed after + * allocation we have a mismatch of the ring size and will cause + * the context to hang. Presumably with a bit of reordering we + * could move the perma-pin step to the backend function + * intel_engine_create_parallel. + */ + if (pe[n].type == I915_GEM_ENGINE_TYPE_PARALLEL) { + ret = perma_pin_contexts(ce); + if (ret) { + err = ERR_PTR(ret); + goto free_engines; + } + } } return e; @@ -1219,6 +1444,7 @@ static void context_close(struct i915_gem_context *ctx) /* Flush any concurrent set_engines() */ mutex_lock(&ctx->engines_mutex); + unpin_engines(__context_engines_static(ctx)); engines_idle_release(ctx, rcu_replace_pointer(ctx->engines, NULL, 1)); i915_gem_context_set_closed(ctx); mutex_unlock(&ctx->engines_mutex); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index a627b09c4680..282cdb8a5c5a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -78,13 +78,16 @@ enum i915_gem_engine_type { /** @I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set */ I915_GEM_ENGINE_TYPE_BALANCED, + + /** @I915_GEM_ENGINE_TYPE_PARALLEL: A parallel engine set */ + I915_GEM_ENGINE_TYPE_PARALLEL, }; /** * struct i915_gem_proto_engine - prototype engine * * This struct describes an engine that a context may contain. Engines - * have three types: + * have four types: * * - I915_GEM_ENGINE_TYPE_INVALID: Invalid engines can be created but they * show up as a NULL in i915_gem_engines::engines[i] and any attempt to @@ -97,6 +100,10 @@ enum i915_gem_engine_type { * * - I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set, described * i915_gem_proto_engine::num_siblings and i915_gem_proto_engine::siblings. + * + * - I915_GEM_ENGINE_TYPE_PARALLEL: A parallel submission engine set, described + * i915_gem_proto_engine::width, i915_gem_proto_engine::num_siblings, and + * i915_gem_proto_engine::siblings. */ struct i915_gem_proto_engine { /** @type: Type of this engine */ @@ -105,10 +112,13 @@ struct i915_gem_proto_engine { /** @engine: Engine, for physical */ struct intel_engine_cs *engine; - /** @num_siblings: Number of balanced siblings */ + /** @num_siblings: Number of balanced or parallel siblings */ unsigned int num_siblings; - /** @siblings: Balanced siblings */ + /** @width: Width of each sibling */ + unsigned int width; + + /** @siblings: Balanced siblings or num_siblings * width for parallel */ struct intel_engine_cs **siblings; /** @sseu: Client-set SSEU parameters */ diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 8309d1141d0a..1d880303a7e4 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -55,9 +55,13 @@ struct intel_context_ops { void (*reset)(struct intel_context *ce); void (*destroy)(struct kref *kref); - /* virtual engine/context interface */ + /* virtual/parallel engine/context interface */ struct intel_context *(*create_virtual)(struct intel_engine_cs **engine, - unsigned int count); + unsigned int count, + unsigned long flags); + struct intel_context *(*create_parallel)(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width); struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine, unsigned int sibling); }; @@ -113,6 +117,7 @@ struct intel_context { #define CONTEXT_NOPREEMPT 8 #define CONTEXT_LRCA_DIRTY 9 #define CONTEXT_GUC_INIT 10 +#define CONTEXT_PERMA_PIN 11 struct { u64 timeout_us; diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index d5ac49c0691e..08559ace0ada 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -282,9 +282,19 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } +#define FORCE_VIRTUAL BIT(0) struct intel_context * intel_engine_create_virtual(struct intel_engine_cs **siblings, - unsigned int count); + unsigned int count, unsigned long flags); + +static inline struct intel_context * +intel_engine_create_parallel(struct intel_engine_cs **engines, + unsigned int num_engines, + unsigned int width) +{ + GEM_BUG_ON(!engines[0]->cops->create_parallel); + return engines[0]->cops->create_parallel(engines, num_engines, width); +} static inline bool intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 2eb798ad068b..ff6753ccb129 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1953,16 +1953,16 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) struct intel_context * intel_engine_create_virtual(struct intel_engine_cs **siblings, - unsigned int count) + unsigned int count, unsigned long flags) { if (count == 0) return ERR_PTR(-EINVAL); - if (count == 1) + if (count == 1 && !(flags & FORCE_VIRTUAL)) return intel_context_create(siblings[0]); GEM_BUG_ON(!siblings[0]->cops->create_virtual); - return siblings[0]->cops->create_virtual(siblings, count); + return siblings[0]->cops->create_virtual(siblings, count, flags); } struct i915_request * diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 43a74b216efb..bedb80057046 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -201,7 +201,8 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine) } static struct intel_context * -execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count); +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags); static struct i915_request * __active_request(const struct intel_timeline * const tl, @@ -3784,7 +3785,8 @@ unlock: } static struct intel_context * -execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags) { struct virtual_engine *ve; unsigned int n; diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 25a8c4f62b0d..b367ecfa42de 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt, GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve)); for (n = 0; n < nctx; n++) { - ve[n] = intel_engine_create_virtual(siblings, nsibling); + ve[n] = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve[n])) { err = PTR_ERR(ve[n]); nctx = n; @@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt, * restrict it to our desired engine within the virtual engine. */ - ve = intel_engine_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_close; @@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt, i915_request_add(rq); } - ce = intel_engine_create_virtual(siblings, nsibling); + ce = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ce)) { err = PTR_ERR(ce); goto out; @@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt, /* XXX We do not handle oversubscription and fairness with normal rq */ for (n = 0; n < nsibling; n++) { - ce = intel_engine_create_virtual(siblings, nsibling); + ce = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ce)) { err = PTR_ERR(ce); goto out; @@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, if (err) goto out_scratch; - ve = intel_engine_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_scratch; @@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt, if (igt_spinner_init(&spin, gt)) return -ENOMEM; - ve = intel_engine_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_spin; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 938dc34e8d3a..7c12364a017a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -124,7 +124,13 @@ struct guc_virtual_engine { }; static struct intel_context * -guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags); + +static struct intel_context * +guc_create_parallel(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width); #define GUC_REQUEST_SIZE 64 /* bytes */ @@ -2609,6 +2615,7 @@ static const struct intel_context_ops guc_context_ops = { .destroy = guc_context_destroy, .create_virtual = guc_create_virtual, + .create_parallel = guc_create_parallel, }; static void submit_work_cb(struct irq_work *wrk) @@ -2858,8 +2865,6 @@ static const struct intel_context_ops virtual_guc_context_ops = { .get_sibling = guc_virtual_get_sibling, }; -/* Future patches will use this function */ -__maybe_unused static int guc_parent_context_pin(struct intel_context *ce, void *vaddr) { struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); @@ -2876,8 +2881,6 @@ static int guc_parent_context_pin(struct intel_context *ce, void *vaddr) return __guc_context_pin(ce, engine, vaddr); } -/* Future patches will use this function */ -__maybe_unused static int guc_child_context_pin(struct intel_context *ce, void *vaddr) { struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); @@ -2889,8 +2892,6 @@ static int guc_child_context_pin(struct intel_context *ce, void *vaddr) return __guc_context_pin(ce, engine, vaddr); } -/* Future patches will use this function */ -__maybe_unused static void guc_parent_context_unpin(struct intel_context *ce) { struct intel_guc *guc = ce_to_guc(ce); @@ -2906,8 +2907,6 @@ static void guc_parent_context_unpin(struct intel_context *ce) lrc_unpin(ce); } -/* Future patches will use this function */ -__maybe_unused static void guc_child_context_unpin(struct intel_context *ce) { GEM_BUG_ON(context_enabled(ce)); @@ -2918,8 +2917,6 @@ static void guc_child_context_unpin(struct intel_context *ce) lrc_unpin(ce); } -/* Future patches will use this function */ -__maybe_unused static void guc_child_context_post_unpin(struct intel_context *ce) { GEM_BUG_ON(!intel_context_is_child(ce)); @@ -2930,6 +2927,98 @@ static void guc_child_context_post_unpin(struct intel_context *ce) intel_context_unpin(ce->parallel.parent); } +static void guc_child_context_destroy(struct kref *kref) +{ + struct intel_context *ce = container_of(kref, typeof(*ce), ref); + + __guc_context_destroy(ce); +} + +static const struct intel_context_ops virtual_parent_context_ops = { + .alloc = guc_virtual_context_alloc, + + .pre_pin = guc_context_pre_pin, + .pin = guc_parent_context_pin, + .unpin = guc_parent_context_unpin, + .post_unpin = guc_context_post_unpin, + + .ban = guc_context_ban, + + .cancel_request = guc_context_cancel_request, + + .enter = guc_virtual_context_enter, + .exit = guc_virtual_context_exit, + + .sched_disable = guc_context_sched_disable, + + .destroy = guc_context_destroy, + + .get_sibling = guc_virtual_get_sibling, +}; + +static const struct intel_context_ops virtual_child_context_ops = { + .alloc = guc_virtual_context_alloc, + + .pre_pin = guc_context_pre_pin, + .pin = guc_child_context_pin, + .unpin = guc_child_context_unpin, + .post_unpin = guc_child_context_post_unpin, + + .cancel_request = guc_context_cancel_request, + + .enter = guc_virtual_context_enter, + .exit = guc_virtual_context_exit, + + .destroy = guc_child_context_destroy, + + .get_sibling = guc_virtual_get_sibling, +}; + +static struct intel_context * +guc_create_parallel(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width) +{ + struct intel_engine_cs **siblings = NULL; + struct intel_context *parent = NULL, *ce, *err; + int i, j; + + siblings = kmalloc_array(num_siblings, + sizeof(*siblings), + GFP_KERNEL); + if (!siblings) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < width; ++i) { + for (j = 0; j < num_siblings; ++j) + siblings[j] = engines[i * num_siblings + j]; + + ce = intel_engine_create_virtual(siblings, num_siblings, + FORCE_VIRTUAL); + if (!ce) { + err = ERR_PTR(-ENOMEM); + goto unwind; + } + + if (i == 0) { + parent = ce; + parent->ops = &virtual_parent_context_ops; + } else { + ce->ops = &virtual_child_context_ops; + intel_context_bind_parent_child(parent, ce); + } + } + + kfree(siblings); + return parent; + +unwind: + if (parent) + intel_context_put(parent); + kfree(siblings); + return err; +} + static bool guc_irq_enable_breadcrumbs(struct intel_breadcrumbs *b) { @@ -3756,7 +3845,8 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, } static struct intel_context * -guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags) { struct guc_virtual_engine *ve; struct intel_guc *guc; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 0179f92e0916..c2a63e1584cb 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1824,6 +1824,7 @@ struct drm_i915_gem_context_param { * Extensions: * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT) */ #define I915_CONTEXT_PARAM_ENGINES 0xa @@ -2098,6 +2099,135 @@ struct i915_context_engines_bond { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +/** + * struct i915_context_engines_parallel_submit - Configure engine for + * parallel submission. + * + * Setup a slot in the context engine map to allow multiple BBs to be submitted + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU + * in parallel. Multiple hardware contexts are created internally in the i915 to + * run these BBs. Once a slot is configured for N BBs only N BBs can be + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how + * many BBs there are based on the slot's configuration. The N BBs are the last + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. + * + * The default placement behavior is to create implicit bonds between each + * context if each context maps to more than 1 physical engine (e.g. context is + * a virtual engine). Also we only allow contexts of same engine class and these + * contexts must be in logically contiguous order. Examples of the placement + * behavior are described below. Lastly, the default is to not allow BBs to be + * preempted mid-batch. Rather insert coordinated preemption points on all + * hardware contexts between each set of BBs. Flags could be added in the future + * to change both of these default behaviors. + * + * Returns -EINVAL if hardware context placement configuration is invalid or if + * the placement configuration isn't supported on the platform / submission + * interface. + * Returns -ENODEV if extension isn't supported on the platform / submission + * interface. + * + * .. code-block:: none + * + * Examples syntax: + * CS[X] = generic engine of same class, logical instance X + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE + * + * Example 1 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=1, + * engines=CS[0],CS[1]) + * + * Results in the following valid placement: + * CS[0], CS[1] + * + * Example 2 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[2],CS[1],CS[3]) + * + * Results in the following valid placements: + * CS[0], CS[1] + * CS[2], CS[3] + * + * This can be thought of as two virtual engines, each containing two + * engines thereby making a 2D array. However, there are bonds tying the + * entries together and placing restrictions on how they can be scheduled. + * Specifically, the scheduler can choose only vertical columns from the 2D + * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the + * scheduler wants to submit to CS[0], it must also choose CS[1] and vice + * versa. Same for CS[2] requires also using CS[3]. + * VE[0] = CS[0], CS[2] + * VE[1] = CS[1], CS[3] + * + * Example 3 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[1],CS[1],CS[3]) + * + * Results in the following valid and invalid placements: + * CS[0], CS[1] + * CS[1], CS[3] - Not logically contiguous, return -EINVAL + */ +struct i915_context_engines_parallel_submit { + /** + * @base: base user extension. + */ + struct i915_user_extension base; + + /** + * @engine_index: slot for parallel engine + */ + __u16 engine_index; + + /** + * @width: number of contexts per parallel engine or in other words the + * number of batches in each submission + */ + __u16 width; + + /** + * @num_siblings: number of siblings per context or in other words the + * number of possible placements for each submission + */ + __u16 num_siblings; + + /** + * @mbz16: reserved for future use; must be zero + */ + __u16 mbz16; + + /** + * @flags: all undefined flags must be zero, currently not defined flags + */ + __u64 flags; + + /** + * @mbz64: reserved for future use; must be zero + */ + __u64 mbz64[3]; + + /** + * @engines: 2-d array of engine instances to configure parallel engine + * + * length = width (i) * num_siblings (j) + * index = j + i * num_siblings + */ + struct i915_engine_class_instance engines[0]; + +} __packed; + +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 width; \ + __u16 num_siblings; \ + __u16 mbz16; \ + __u64 flags; \ + __u64 mbz64[3]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + /** * DOC: Context Engine Map uAPI * @@ -2157,6 +2287,7 @@ struct i915_context_param_engines { __u64 extensions; /* linked chain of extension blocks, 0 terminates */ #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ +#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ struct i915_engine_class_instance engines[0]; } __attribute__((packed)); -- cgit v1.2.3 From b0539f5eddc2eefd24378bda3ee9cbbca916f58d Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Sat, 16 Oct 2021 11:37:51 +0200 Subject: net/smc: add netlink support for SMC-Rv2 Implement the netlink support for SMC-Rv2 related attributes that are provided to user space. Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 17 ++++++++- net/smc/smc_core.c | 98 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 88 insertions(+), 27 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b175bd0165a1..20f33b27787f 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -84,17 +84,28 @@ enum { SMC_NLA_SYS_IS_ISM_V2, /* u8 */ SMC_NLA_SYS_LOCAL_HOST, /* string */ SMC_NLA_SYS_SEID, /* string */ + SMC_NLA_SYS_IS_SMCR_V2, /* u8 */ __SMC_NLA_SYS_MAX, SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 }; -/* SMC_NLA_LGR_V2 nested attributes */ +/* SMC_NLA_LGR_D_V2_COMMON and SMC_NLA_LGR_R_V2_COMMON nested attributes */ enum { SMC_NLA_LGR_V2_VER, /* u8 */ SMC_NLA_LGR_V2_REL, /* u8 */ SMC_NLA_LGR_V2_OS, /* u8 */ SMC_NLA_LGR_V2_NEG_EID, /* string */ SMC_NLA_LGR_V2_PEER_HOST, /* string */ + __SMC_NLA_LGR_V2_MAX, + SMC_NLA_LGR_V2_MAX = __SMC_NLA_LGR_V2_MAX - 1 +}; + +/* SMC_NLA_LGR_R_V2 nested attributes */ +enum { + SMC_NLA_LGR_R_V2_UNSPEC, + SMC_NLA_LGR_R_V2_DIRECT, /* u8 */ + __SMC_NLA_LGR_R_V2_MAX, + SMC_NLA_LGR_R_V2_MAX = __SMC_NLA_LGR_R_V2_MAX - 1 }; /* SMC_GEN_LGR_SMCR attributes */ @@ -106,6 +117,8 @@ enum { SMC_NLA_LGR_R_PNETID, /* string */ SMC_NLA_LGR_R_VLAN_ID, /* u8 */ SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ + SMC_NLA_LGR_R_V2_COMMON, /* nest */ + SMC_NLA_LGR_R_V2, /* nest */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; @@ -138,7 +151,7 @@ enum { SMC_NLA_LGR_D_PNETID, /* string */ SMC_NLA_LGR_D_CHID, /* u16 */ SMC_NLA_LGR_D_PAD, /* flag */ - SMC_NLA_LGR_V2, /* nest */ + SMC_NLA_LGR_D_V2_COMMON, /* nest */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 1ccab993683d..8e642f8f334f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -244,6 +244,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) + goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); @@ -271,12 +273,65 @@ errmsg: return skb->len; } +/* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ +static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb, + struct nlattr *v2_attrs) +{ + char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_eid[SMC_MAX_EID_LEN + 1]; + + if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) + goto errv2attr; + memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); + smc_host[SMC_MAX_HOSTNAME_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) + goto errv2attr; + memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); + smc_eid[SMC_MAX_EID_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); + return -EMSGSIZE; +} + +static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *v2_attrs; + + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); + if (!v2_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); +errattr: + return -EMSGSIZE; +} + static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; - struct nlattr *attrs; + struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) @@ -296,6 +351,15 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (lgr->smc_version > SMC_V1) { + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) + goto errattr; + } nla_nest_end(skb, attrs); return 0; @@ -428,10 +492,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { - char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_pnet[SMC_MAX_PNETID_LEN + 1]; - char smc_eid[SMC_MAX_EID_LEN + 1]; - struct nlattr *v2_attrs; struct nlattr *attrs; void *nlh; @@ -463,32 +524,19 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; + if (lgr->smc_version > SMC_V1) { + struct nlattr *v2_attrs; - v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2); - if (!v2_attrs) - goto errattr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) - goto errv2attr; - memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); - smc_host[SMC_MAX_HOSTNAME_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) - goto errv2attr; - memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); - smc_eid[SMC_MAX_EID_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) - goto errv2attr; - - nla_nest_end(skb, v2_attrs); + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; -errv2attr: - nla_nest_cancel(skb, v2_attrs); errattr: nla_nest_cancel(skb, attrs); errout: -- cgit v1.2.3 From e65c26f413718ed2e6d788491adcd8cebc0f44b6 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 29 Sep 2021 12:15:58 +0900 Subject: counter: Move counter enums to uapi header This is in preparation for a subsequent patch implementing a character device interface for the Counter subsystem. Reviewed-by: David Lechner Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/962a5f2027fafcf4f77c10e1baf520463960d1ee.1632884256.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- MAINTAINERS | 1 + include/linux/counter.h | 42 +-------------------------------- include/uapi/linux/counter.h | 56 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 58 insertions(+), 41 deletions(-) create mode 100644 include/uapi/linux/counter.h (limited to 'include/uapi') diff --git a/MAINTAINERS b/MAINTAINERS index b98a34fcec4b..8310a42abdab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4804,6 +4804,7 @@ F: Documentation/ABI/testing/sysfs-bus-counter F: Documentation/driver-api/generic-counter.rst F: drivers/counter/ F: include/linux/counter.h +F: include/uapi/linux/counter.h CP2615 I2C DRIVER M: Bence Csókás diff --git a/include/linux/counter.h b/include/linux/counter.h index 445f22d8bfe2..7c9f7e23953a 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -9,6 +9,7 @@ #include #include #include +#include struct counter_device; struct counter_count; @@ -27,47 +28,6 @@ enum counter_comp_type { COUNTER_COMP_COUNT_MODE, }; -enum counter_scope { - COUNTER_SCOPE_DEVICE, - COUNTER_SCOPE_SIGNAL, - COUNTER_SCOPE_COUNT, -}; - -enum counter_count_direction { - COUNTER_COUNT_DIRECTION_FORWARD, - COUNTER_COUNT_DIRECTION_BACKWARD, -}; - -enum counter_count_mode { - COUNTER_COUNT_MODE_NORMAL, - COUNTER_COUNT_MODE_RANGE_LIMIT, - COUNTER_COUNT_MODE_NON_RECYCLE, - COUNTER_COUNT_MODE_MODULO_N, -}; - -enum counter_function { - COUNTER_FUNCTION_INCREASE, - COUNTER_FUNCTION_DECREASE, - COUNTER_FUNCTION_PULSE_DIRECTION, - COUNTER_FUNCTION_QUADRATURE_X1_A, - COUNTER_FUNCTION_QUADRATURE_X1_B, - COUNTER_FUNCTION_QUADRATURE_X2_A, - COUNTER_FUNCTION_QUADRATURE_X2_B, - COUNTER_FUNCTION_QUADRATURE_X4, -}; - -enum counter_signal_level { - COUNTER_SIGNAL_LEVEL_LOW, - COUNTER_SIGNAL_LEVEL_HIGH, -}; - -enum counter_synapse_action { - COUNTER_SYNAPSE_ACTION_NONE, - COUNTER_SYNAPSE_ACTION_RISING_EDGE, - COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - COUNTER_SYNAPSE_ACTION_BOTH_EDGES, -}; - /** * struct counter_comp - Counter component node * @type: Counter component data type diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h new file mode 100644 index 000000000000..6113938a6044 --- /dev/null +++ b/include/uapi/linux/counter.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Userspace ABI for Counter character devices + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _UAPI_COUNTER_H_ +#define _UAPI_COUNTER_H_ + +/* Component scope definitions */ +enum counter_scope { + COUNTER_SCOPE_DEVICE, + COUNTER_SCOPE_SIGNAL, + COUNTER_SCOPE_COUNT, +}; + +/* Count direction values */ +enum counter_count_direction { + COUNTER_COUNT_DIRECTION_FORWARD, + COUNTER_COUNT_DIRECTION_BACKWARD, +}; + +/* Count mode values */ +enum counter_count_mode { + COUNTER_COUNT_MODE_NORMAL, + COUNTER_COUNT_MODE_RANGE_LIMIT, + COUNTER_COUNT_MODE_NON_RECYCLE, + COUNTER_COUNT_MODE_MODULO_N, +}; + +/* Count function values */ +enum counter_function { + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_DECREASE, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X1_A, + COUNTER_FUNCTION_QUADRATURE_X1_B, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X2_B, + COUNTER_FUNCTION_QUADRATURE_X4, +}; + +/* Signal values */ +enum counter_signal_level { + COUNTER_SIGNAL_LEVEL_LOW, + COUNTER_SIGNAL_LEVEL_HIGH, +}; + +/* Action mode values */ +enum counter_synapse_action { + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, +}; + +#endif /* _UAPI_COUNTER_H_ */ -- cgit v1.2.3 From b6c50affda5957a3629b149a91c7f6688ffce7f7 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 29 Sep 2021 12:15:59 +0900 Subject: counter: Add character device interface This patch introduces a character device interface for the Counter subsystem. Device data is exposed through standard character device read operations. Device data is gathered when a Counter event is pushed by the respective Counter device driver. Configuration is handled via ioctl operations on the respective Counter character device node. Cc: David Lechner Cc: Gwendal Grignou Cc: Dan Carpenter Cc: Oleksij Rempel Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/b8b8c64b4065aedff43699ad1f0e2f8d1419c15b.1632884256.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/Makefile | 2 +- drivers/counter/counter-chrdev.c | 578 +++++++++++++++++++++++++++++++++++++++ drivers/counter/counter-chrdev.h | 14 + drivers/counter/counter-core.c | 56 +++- include/linux/counter.h | 56 ++++ include/uapi/linux/counter.h | 98 +++++++ 6 files changed, 798 insertions(+), 6 deletions(-) create mode 100644 drivers/counter/counter-chrdev.c create mode 100644 drivers/counter/counter-chrdev.h (limited to 'include/uapi') diff --git a/drivers/counter/Makefile b/drivers/counter/Makefile index 1ab7e087fdc2..8fde6c100ebc 100644 --- a/drivers/counter/Makefile +++ b/drivers/counter/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_COUNTER) += counter.o -counter-y := counter-core.o counter-sysfs.o +counter-y := counter-core.o counter-sysfs.o counter-chrdev.o obj-$(CONFIG_104_QUAD_8) += 104-quad-8.o obj-$(CONFIG_INTERRUPT_CNT) += interrupt-cnt.o diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c new file mode 100644 index 000000000000..967c94ae95bb --- /dev/null +++ b/drivers/counter/counter-chrdev.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic Counter character device interface + * Copyright (C) 2020 William Breathitt Gray + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "counter-chrdev.h" + +struct counter_comp_node { + struct list_head l; + struct counter_component component; + struct counter_comp comp; + void *parent; +}; + +#define counter_comp_read_is_equal(a, b) \ + (a.action_read == b.action_read || \ + a.device_u8_read == b.device_u8_read || \ + a.count_u8_read == b.count_u8_read || \ + a.signal_u8_read == b.signal_u8_read || \ + a.device_u32_read == b.device_u32_read || \ + a.count_u32_read == b.count_u32_read || \ + a.signal_u32_read == b.signal_u32_read || \ + a.device_u64_read == b.device_u64_read || \ + a.count_u64_read == b.count_u64_read || \ + a.signal_u64_read == b.signal_u64_read) + +#define counter_comp_read_is_set(comp) \ + (comp.action_read || \ + comp.device_u8_read || \ + comp.count_u8_read || \ + comp.signal_u8_read || \ + comp.device_u32_read || \ + comp.count_u32_read || \ + comp.signal_u32_read || \ + comp.device_u64_read || \ + comp.count_u64_read || \ + comp.signal_u64_read) + +static ssize_t counter_chrdev_read(struct file *filp, char __user *buf, + size_t len, loff_t *f_ps) +{ + struct counter_device *const counter = filp->private_data; + int err; + unsigned int copied; + + if (!counter->ops) + return -ENODEV; + + if (len < sizeof(struct counter_event)) + return -EINVAL; + + do { + if (kfifo_is_empty(&counter->events)) { + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + err = wait_event_interruptible(counter->events_wait, + !kfifo_is_empty(&counter->events) || + !counter->ops); + if (err < 0) + return err; + if (!counter->ops) + return -ENODEV; + } + + if (mutex_lock_interruptible(&counter->events_lock)) + return -ERESTARTSYS; + err = kfifo_to_user(&counter->events, buf, len, &copied); + mutex_unlock(&counter->events_lock); + if (err < 0) + return err; + } while (!copied); + + return copied; +} + +static __poll_t counter_chrdev_poll(struct file *filp, + struct poll_table_struct *pollt) +{ + struct counter_device *const counter = filp->private_data; + __poll_t events = 0; + + if (!counter->ops) + return events; + + poll_wait(filp, &counter->events_wait, pollt); + + if (!kfifo_is_empty(&counter->events)) + events = EPOLLIN | EPOLLRDNORM; + + return events; +} + +static void counter_events_list_free(struct list_head *const events_list) +{ + struct counter_event_node *p, *n; + struct counter_comp_node *q, *o; + + list_for_each_entry_safe(p, n, events_list, l) { + /* Free associated component nodes */ + list_for_each_entry_safe(q, o, &p->comp_list, l) { + list_del(&q->l); + kfree(q); + } + + /* Free event node */ + list_del(&p->l); + kfree(p); + } +} + +static int counter_set_event_node(struct counter_device *const counter, + struct counter_watch *const watch, + const struct counter_comp_node *const cfg) +{ + struct counter_event_node *event_node; + int err = 0; + struct counter_comp_node *comp_node; + + /* Search for event in the list */ + list_for_each_entry(event_node, &counter->next_events_list, l) + if (event_node->event == watch->event && + event_node->channel == watch->channel) + break; + + /* If event is not already in the list */ + if (&event_node->l == &counter->next_events_list) { + /* Allocate new event node */ + event_node = kmalloc(sizeof(*event_node), GFP_KERNEL); + if (!event_node) + return -ENOMEM; + + /* Configure event node and add to the list */ + event_node->event = watch->event; + event_node->channel = watch->channel; + INIT_LIST_HEAD(&event_node->comp_list); + list_add(&event_node->l, &counter->next_events_list); + } + + /* Check if component watch has already been set before */ + list_for_each_entry(comp_node, &event_node->comp_list, l) + if (comp_node->parent == cfg->parent && + counter_comp_read_is_equal(comp_node->comp, cfg->comp)) { + err = -EINVAL; + goto exit_free_event_node; + } + + /* Allocate component node */ + comp_node = kmalloc(sizeof(*comp_node), GFP_KERNEL); + if (!comp_node) { + err = -ENOMEM; + goto exit_free_event_node; + } + *comp_node = *cfg; + + /* Add component node to event node */ + list_add_tail(&comp_node->l, &event_node->comp_list); + +exit_free_event_node: + /* Free event node if no one else is watching */ + if (list_empty(&event_node->comp_list)) { + list_del(&event_node->l); + kfree(event_node); + } + + return err; +} + +static int counter_enable_events(struct counter_device *const counter) +{ + unsigned long flags; + int err = 0; + + mutex_lock(&counter->n_events_list_lock); + spin_lock_irqsave(&counter->events_list_lock, flags); + + counter_events_list_free(&counter->events_list); + list_replace_init(&counter->next_events_list, + &counter->events_list); + + if (counter->ops->events_configure) + err = counter->ops->events_configure(counter); + + spin_unlock_irqrestore(&counter->events_list_lock, flags); + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static int counter_disable_events(struct counter_device *const counter) +{ + unsigned long flags; + int err = 0; + + spin_lock_irqsave(&counter->events_list_lock, flags); + + counter_events_list_free(&counter->events_list); + + if (counter->ops->events_configure) + err = counter->ops->events_configure(counter); + + spin_unlock_irqrestore(&counter->events_list_lock, flags); + + mutex_lock(&counter->n_events_list_lock); + + counter_events_list_free(&counter->next_events_list); + + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static int counter_add_watch(struct counter_device *const counter, + const unsigned long arg) +{ + void __user *const uwatch = (void __user *)arg; + struct counter_watch watch; + struct counter_comp_node comp_node = {}; + size_t parent, id; + struct counter_comp *ext; + size_t num_ext; + int err = 0; + + if (copy_from_user(&watch, uwatch, sizeof(watch))) + return -EFAULT; + + if (watch.component.type == COUNTER_COMPONENT_NONE) + goto no_component; + + parent = watch.component.parent; + + /* Configure parent component info for comp node */ + switch (watch.component.scope) { + case COUNTER_SCOPE_DEVICE: + ext = counter->ext; + num_ext = counter->num_ext; + break; + case COUNTER_SCOPE_SIGNAL: + if (parent >= counter->num_signals) + return -EINVAL; + parent = array_index_nospec(parent, counter->num_signals); + + comp_node.parent = counter->signals + parent; + + ext = counter->signals[parent].ext; + num_ext = counter->signals[parent].num_ext; + break; + case COUNTER_SCOPE_COUNT: + if (parent >= counter->num_counts) + return -EINVAL; + parent = array_index_nospec(parent, counter->num_counts); + + comp_node.parent = counter->counts + parent; + + ext = counter->counts[parent].ext; + num_ext = counter->counts[parent].num_ext; + break; + default: + return -EINVAL; + } + + id = watch.component.id; + + /* Configure component info for comp node */ + switch (watch.component.type) { + case COUNTER_COMPONENT_SIGNAL: + if (watch.component.scope != COUNTER_SCOPE_SIGNAL) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_SIGNAL_LEVEL; + comp_node.comp.signal_u32_read = counter->ops->signal_read; + break; + case COUNTER_COMPONENT_COUNT: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_U64; + comp_node.comp.count_u64_read = counter->ops->count_read; + break; + case COUNTER_COMPONENT_FUNCTION: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_FUNCTION; + comp_node.comp.count_u32_read = counter->ops->function_read; + break; + case COUNTER_COMPONENT_SYNAPSE_ACTION: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + if (id >= counter->counts[parent].num_synapses) + return -EINVAL; + id = array_index_nospec(id, counter->counts[parent].num_synapses); + + comp_node.comp.type = COUNTER_COMP_SYNAPSE_ACTION; + comp_node.comp.action_read = counter->ops->action_read; + comp_node.comp.priv = counter->counts[parent].synapses + id; + break; + case COUNTER_COMPONENT_EXTENSION: + if (id >= num_ext) + return -EINVAL; + id = array_index_nospec(id, num_ext); + + comp_node.comp = ext[id]; + break; + default: + return -EINVAL; + } + if (!counter_comp_read_is_set(comp_node.comp)) + return -EOPNOTSUPP; + +no_component: + mutex_lock(&counter->n_events_list_lock); + + if (counter->ops->watch_validate) { + err = counter->ops->watch_validate(counter, &watch); + if (err < 0) + goto err_exit; + } + + comp_node.component = watch.component; + + err = counter_set_event_node(counter, &watch, &comp_node); + +err_exit: + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static long counter_chrdev_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct counter_device *const counter = filp->private_data; + int ret = -ENODEV; + + mutex_lock(&counter->ops_exist_lock); + + if (!counter->ops) + goto out_unlock; + + switch (cmd) { + case COUNTER_ADD_WATCH_IOCTL: + ret = counter_add_watch(counter, arg); + break; + case COUNTER_ENABLE_EVENTS_IOCTL: + ret = counter_enable_events(counter); + break; + case COUNTER_DISABLE_EVENTS_IOCTL: + ret = counter_disable_events(counter); + break; + default: + ret = -ENOIOCTLCMD; + break; + } + +out_unlock: + mutex_unlock(&counter->ops_exist_lock); + + return ret; +} + +static int counter_chrdev_open(struct inode *inode, struct file *filp) +{ + struct counter_device *const counter = container_of(inode->i_cdev, + typeof(*counter), + chrdev); + + /* Ensure chrdev is not opened more than 1 at a time */ + if (!atomic_add_unless(&counter->chrdev_lock, 1, 1)) + return -EBUSY; + + get_device(&counter->dev); + filp->private_data = counter; + + return nonseekable_open(inode, filp); +} + +static int counter_chrdev_release(struct inode *inode, struct file *filp) +{ + struct counter_device *const counter = filp->private_data; + int ret = 0; + + mutex_lock(&counter->ops_exist_lock); + + if (!counter->ops) { + /* Free any lingering held memory */ + counter_events_list_free(&counter->events_list); + counter_events_list_free(&counter->next_events_list); + ret = -ENODEV; + goto out_unlock; + } + + ret = counter_disable_events(counter); + if (ret < 0) { + mutex_unlock(&counter->ops_exist_lock); + return ret; + } + +out_unlock: + mutex_unlock(&counter->ops_exist_lock); + + put_device(&counter->dev); + atomic_dec(&counter->chrdev_lock); + + return ret; +} + +static const struct file_operations counter_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = counter_chrdev_read, + .poll = counter_chrdev_poll, + .unlocked_ioctl = counter_chrdev_ioctl, + .open = counter_chrdev_open, + .release = counter_chrdev_release, +}; + +int counter_chrdev_add(struct counter_device *const counter) +{ + /* Initialize Counter events lists */ + INIT_LIST_HEAD(&counter->events_list); + INIT_LIST_HEAD(&counter->next_events_list); + spin_lock_init(&counter->events_list_lock); + mutex_init(&counter->n_events_list_lock); + init_waitqueue_head(&counter->events_wait); + mutex_init(&counter->events_lock); + + /* Initialize character device */ + atomic_set(&counter->chrdev_lock, 0); + cdev_init(&counter->chrdev, &counter_fops); + + /* Allocate Counter events queue */ + return kfifo_alloc(&counter->events, 64, GFP_KERNEL); +} + +void counter_chrdev_remove(struct counter_device *const counter) +{ + kfifo_free(&counter->events); +} + +static int counter_get_data(struct counter_device *const counter, + const struct counter_comp_node *const comp_node, + u64 *const value) +{ + const struct counter_comp *const comp = &comp_node->comp; + void *const parent = comp_node->parent; + u8 value_u8 = 0; + u32 value_u32 = 0; + int ret; + + if (comp_node->component.type == COUNTER_COMPONENT_NONE) + return 0; + + switch (comp->type) { + case COUNTER_COMP_U8: + case COUNTER_COMP_BOOL: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + ret = comp->device_u8_read(counter, &value_u8); + break; + case COUNTER_SCOPE_SIGNAL: + ret = comp->signal_u8_read(counter, parent, &value_u8); + break; + case COUNTER_SCOPE_COUNT: + ret = comp->count_u8_read(counter, parent, &value_u8); + break; + } + *value = value_u8; + return ret; + case COUNTER_COMP_SIGNAL_LEVEL: + case COUNTER_COMP_FUNCTION: + case COUNTER_COMP_ENUM: + case COUNTER_COMP_COUNT_DIRECTION: + case COUNTER_COMP_COUNT_MODE: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + ret = comp->device_u32_read(counter, &value_u32); + break; + case COUNTER_SCOPE_SIGNAL: + ret = comp->signal_u32_read(counter, parent, + &value_u32); + break; + case COUNTER_SCOPE_COUNT: + ret = comp->count_u32_read(counter, parent, &value_u32); + break; + } + *value = value_u32; + return ret; + case COUNTER_COMP_U64: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + return comp->device_u64_read(counter, value); + case COUNTER_SCOPE_SIGNAL: + return comp->signal_u64_read(counter, parent, value); + case COUNTER_SCOPE_COUNT: + return comp->count_u64_read(counter, parent, value); + default: + return -EINVAL; + } + case COUNTER_COMP_SYNAPSE_ACTION: + ret = comp->action_read(counter, parent, comp->priv, + &value_u32); + *value = value_u32; + return ret; + default: + return -EINVAL; + } +} + +/** + * counter_push_event - queue event for userspace reading + * @counter: pointer to Counter structure + * @event: triggered event + * @channel: event channel + * + * Note: If no one is watching for the respective event, it is silently + * discarded. + */ +void counter_push_event(struct counter_device *const counter, const u8 event, + const u8 channel) +{ + struct counter_event ev; + unsigned int copied = 0; + unsigned long flags; + struct counter_event_node *event_node; + struct counter_comp_node *comp_node; + + ev.timestamp = ktime_get_ns(); + ev.watch.event = event; + ev.watch.channel = channel; + + /* Could be in an interrupt context, so use a spin lock */ + spin_lock_irqsave(&counter->events_list_lock, flags); + + /* Search for event in the list */ + list_for_each_entry(event_node, &counter->events_list, l) + if (event_node->event == event && + event_node->channel == channel) + break; + + /* If event is not in the list */ + if (&event_node->l == &counter->events_list) + goto exit_early; + + /* Read and queue relevant comp for userspace */ + list_for_each_entry(comp_node, &event_node->comp_list, l) { + ev.watch.component = comp_node->component; + ev.status = -counter_get_data(counter, comp_node, &ev.value); + + copied += kfifo_in(&counter->events, &ev, 1); + } + +exit_early: + spin_unlock_irqrestore(&counter->events_list_lock, flags); + + if (copied) + wake_up_poll(&counter->events_wait, EPOLLIN); +} +EXPORT_SYMBOL_GPL(counter_push_event); diff --git a/drivers/counter/counter-chrdev.h b/drivers/counter/counter-chrdev.h new file mode 100644 index 000000000000..5529d16703c4 --- /dev/null +++ b/drivers/counter/counter-chrdev.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Counter character device interface + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _COUNTER_CHRDEV_H_ +#define _COUNTER_CHRDEV_H_ + +#include + +int counter_chrdev_add(struct counter_device *const counter); +void counter_chrdev_remove(struct counter_device *const counter); + +#endif /* _COUNTER_CHRDEV_H_ */ diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index 3cda2c47bacb..5acc54539623 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -3,14 +3,22 @@ * Generic Counter interface * Copyright (C) 2020 William Breathitt Gray */ +#include #include #include +#include #include +#include #include #include #include +#include #include +#include +#include +#include +#include "counter-chrdev.h" #include "counter-sysfs.h" /* Provides a unique ID for each counter device */ @@ -18,6 +26,9 @@ static DEFINE_IDA(counter_ida); static void counter_device_release(struct device *dev) { + struct counter_device *const counter = dev_get_drvdata(dev); + + counter_chrdev_remove(counter); ida_free(&counter_ida, dev->id); } @@ -31,6 +42,8 @@ static struct bus_type counter_bus_type = { .dev_name = "counter", }; +static dev_t counter_devt; + /** * counter_register - register Counter to the system * @counter: pointer to Counter to register @@ -53,10 +66,13 @@ int counter_register(struct counter_device *const counter) if (id < 0) return id; + mutex_init(&counter->ops_exist_lock); + /* Configure device structure for Counter */ dev->id = id; dev->type = &counter_device_type; dev->bus = &counter_bus_type; + dev->devt = MKDEV(MAJOR(counter_devt), id); if (counter->parent) { dev->parent = counter->parent; dev->of_node = counter->parent->of_node; @@ -64,18 +80,22 @@ int counter_register(struct counter_device *const counter) device_initialize(dev); dev_set_drvdata(dev, counter); - /* Add Counter sysfs attributes */ err = counter_sysfs_add(counter); if (err < 0) goto err_free_id; - /* Add device to system */ - err = device_add(dev); + err = counter_chrdev_add(counter); if (err < 0) goto err_free_id; + err = cdev_device_add(&counter->chrdev, dev); + if (err < 0) + goto err_remove_chrdev; + return 0; +err_remove_chrdev: + counter_chrdev_remove(counter); err_free_id: put_device(dev); return err; @@ -93,7 +113,16 @@ void counter_unregister(struct counter_device *const counter) if (!counter) return; - device_unregister(&counter->dev); + cdev_device_del(&counter->chrdev, &counter->dev); + + mutex_lock(&counter->ops_exist_lock); + + counter->ops = NULL; + wake_up(&counter->events_wait); + + mutex_unlock(&counter->ops_exist_lock); + + put_device(&counter->dev); } EXPORT_SYMBOL_GPL(counter_unregister); @@ -127,13 +156,30 @@ int devm_counter_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_counter_register); +#define COUNTER_DEV_MAX 256 + static int __init counter_init(void) { - return bus_register(&counter_bus_type); + int err; + + err = bus_register(&counter_bus_type); + if (err < 0) + return err; + + err = alloc_chrdev_region(&counter_devt, 0, COUNTER_DEV_MAX, "counter"); + if (err < 0) + goto err_unregister_bus; + + return 0; + +err_unregister_bus: + bus_unregister(&counter_bus_type); + return err; } static void __exit counter_exit(void) { + unregister_chrdev_region(counter_devt, COUNTER_DEV_MAX); bus_unregister(&counter_bus_type); } diff --git a/include/linux/counter.h b/include/linux/counter.h index 7c9f7e23953a..22b14a552b1d 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -6,9 +6,14 @@ #ifndef _COUNTER_H_ #define _COUNTER_H_ +#include #include #include +#include +#include +#include #include +#include #include struct counter_device; @@ -199,6 +204,20 @@ struct counter_count { size_t num_ext; }; +/** + * struct counter_event_node - Counter Event node + * @l: list of current watching Counter events + * @event: event that triggers + * @channel: event channel + * @comp_list: list of components to watch when event triggers + */ +struct counter_event_node { + struct list_head l; + u8 event; + u8 channel; + struct list_head comp_list; +}; + /** * struct counter_ops - Callbacks from driver * @signal_read: optional read callback for Signals. The read level of @@ -222,6 +241,13 @@ struct counter_count { * @action_write: optional write callback for Synapse action modes. The * action mode to write for the respective Synapse is * passed in via the action parameter. + * @events_configure: optional write callback to configure events. The list of + * struct counter_event_node may be accessed via the + * events_list member of the counter parameter. + * @watch_validate: optional callback to validate a watch. The Counter + * component watch configuration is passed in via the watch + * parameter. A return value of 0 indicates a valid Counter + * component watch configuration. */ struct counter_ops { int (*signal_read)(struct counter_device *counter, @@ -245,6 +271,9 @@ struct counter_ops { struct counter_count *count, struct counter_synapse *synapse, enum counter_synapse_action action); + int (*events_configure)(struct counter_device *counter); + int (*watch_validate)(struct counter_device *counter, + const struct counter_watch *watch); }; /** @@ -260,6 +289,16 @@ struct counter_ops { * @num_ext: number of Counter device extensions specified in @ext * @priv: optional private data supplied by driver * @dev: internal device structure + * @chrdev: internal character device structure + * @events_list: list of current watching Counter events + * @events_list_lock: lock to protect Counter events list operations + * @next_events_list: list of next watching Counter events + * @n_events_list_lock: lock to protect Counter next events list operations + * @events: queue of detected Counter events + * @events_wait: wait queue to allow blocking reads of Counter events + * @events_lock: lock to protect Counter events queue read operations + * @chrdev_lock: lock to limit chrdev to a single open at a time + * @ops_exist_lock: lock to prevent use during removal */ struct counter_device { const char *name; @@ -278,12 +317,29 @@ struct counter_device { void *priv; struct device dev; + struct cdev chrdev; + struct list_head events_list; + spinlock_t events_list_lock; + struct list_head next_events_list; + struct mutex n_events_list_lock; + DECLARE_KFIFO_PTR(events, struct counter_event); + wait_queue_head_t events_wait; + struct mutex events_lock; + /* + * chrdev_lock is locked by counter_chrdev_open() and unlocked by + * counter_chrdev_release(), so a mutex is not possible here because + * chrdev_lock will invariably be held when returning to user space + */ + atomic_t chrdev_lock; + struct mutex ops_exist_lock; }; int counter_register(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, struct counter_device *const counter); +void counter_push_event(struct counter_device *const counter, const u8 event, + const u8 channel); #define COUNTER_COMP_DEVICE_U8(_name, _read, _write) \ { \ diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h index 6113938a6044..d0aa95aeff7b 100644 --- a/include/uapi/linux/counter.h +++ b/include/uapi/linux/counter.h @@ -6,6 +6,19 @@ #ifndef _UAPI_COUNTER_H_ #define _UAPI_COUNTER_H_ +#include +#include + +/* Component type definitions */ +enum counter_component_type { + COUNTER_COMPONENT_NONE, + COUNTER_COMPONENT_SIGNAL, + COUNTER_COMPONENT_COUNT, + COUNTER_COMPONENT_FUNCTION, + COUNTER_COMPONENT_SYNAPSE_ACTION, + COUNTER_COMPONENT_EXTENSION, +}; + /* Component scope definitions */ enum counter_scope { COUNTER_SCOPE_DEVICE, @@ -13,6 +26,91 @@ enum counter_scope { COUNTER_SCOPE_COUNT, }; +/** + * struct counter_component - Counter component identification + * @type: component type (one of enum counter_component_type) + * @scope: component scope (one of enum counter_scope) + * @parent: parent ID (matching the ID suffix of the respective parent sysfs + * path as described by the ABI documentation file + * Documentation/ABI/testing/sysfs-bus-counter) + * @id: component ID (matching the ID provided by the respective *_component_id + * sysfs attribute of the desired component) + * + * For example, if the Count 2 ceiling extension of Counter device 4 is desired, + * set type equal to COUNTER_COMPONENT_EXTENSION, scope equal to + * COUNTER_COUNT_SCOPE, parent equal to 2, and id equal to the value provided by + * the respective /sys/bus/counter/devices/counter4/count2/ceiling_component_id + * sysfs attribute. + */ +struct counter_component { + __u8 type; + __u8 scope; + __u8 parent; + __u8 id; +}; + +/* Event type definitions */ +enum counter_event_type { + /* Count value increased past ceiling */ + COUNTER_EVENT_OVERFLOW, + /* Count value decreased past floor */ + COUNTER_EVENT_UNDERFLOW, + /* Count value increased past ceiling, or decreased past floor */ + COUNTER_EVENT_OVERFLOW_UNDERFLOW, + /* Count value reached threshold */ + COUNTER_EVENT_THRESHOLD, + /* Index signal detected */ + COUNTER_EVENT_INDEX, +}; + +/** + * struct counter_watch - Counter component watch configuration + * @component: component to watch when event triggers + * @event: event that triggers (one of enum counter_event_type) + * @channel: event channel (typically 0 unless the device supports concurrent + * events of the same type) + */ +struct counter_watch { + struct counter_component component; + __u8 event; + __u8 channel; +}; + +/* + * Queues a Counter watch for the specified event. + * + * The queued watches will not be applied until COUNTER_ENABLE_EVENTS_IOCTL is + * called. + */ +#define COUNTER_ADD_WATCH_IOCTL _IOW(0x3E, 0x00, struct counter_watch) +/* + * Enables monitoring the events specified by the Counter watches that were + * queued by COUNTER_ADD_WATCH_IOCTL. + * + * If events are already enabled, the new set of watches replaces the old one. + * Calling this ioctl also has the effect of clearing the queue of watches added + * by COUNTER_ADD_WATCH_IOCTL. + */ +#define COUNTER_ENABLE_EVENTS_IOCTL _IO(0x3E, 0x01) +/* + * Stops monitoring the previously enabled events. + */ +#define COUNTER_DISABLE_EVENTS_IOCTL _IO(0x3E, 0x02) + +/** + * struct counter_event - Counter event data + * @timestamp: best estimate of time of event occurrence, in nanoseconds + * @value: component value + * @watch: component watch configuration + * @status: return status (system error number) + */ +struct counter_event { + __aligned_u64 timestamp; + __aligned_u64 value; + struct counter_watch watch; + __u8 status; +}; + /* Count direction values */ enum counter_count_direction { COUNTER_COUNT_DIRECTION_FORWARD, -- cgit v1.2.3 From 511c1957de9d9f5a70e6760dfb6af4382ae0501d Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Wed, 1 Sep 2021 19:20:00 +0300 Subject: habanalabs: add kernel-doc style comments Modify some comments in the uapi file to be in kernel-doc style. Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 43 ++++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 18 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index d13bb8c1b450..ccfcb4d188fc 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -272,6 +272,16 @@ enum hl_gaudi_pll_index { HL_GAUDI_PLL_MAX }; +/** + * enum hl_device_status - Device status information. + * @HL_DEVICE_STATUS_OPERATIONAL: Device is operational. + * @HL_DEVICE_STATUS_IN_RESET: Device is currently during reset. + * @HL_DEVICE_STATUS_MALFUNCTION: Device is unusable. + * @HL_DEVICE_STATUS_NEEDS_RESET: Device needs reset because auto reset was disabled. + * @HL_DEVICE_STATUS_IN_DEVICE_CREATION: Device is operational but its creation is still in + * progress. + * @HL_DEVICE_STATUS_LAST: Last status. + */ enum hl_device_status { HL_DEVICE_STATUS_OPERATIONAL, HL_DEVICE_STATUS_IN_RESET, @@ -556,33 +566,30 @@ enum gaudi_dcores { HL_GAUDI_ES_DCORE }; +/** + * struct hl_info_args - Main structure to retrieve device related information. + * @return_pointer: User space address of the relevant structure related to HL_INFO_* operation + * mentioned in @op. + * @return_size: Size of the structure used in @return_pointer, just like "size" in "snprintf", it + * limits how many bytes the kernel can write. For hw_events array, the size should be + * hl_info_hw_ip_info.num_of_events * sizeof(__u32). + * @op: Defines which type of information to be retrieved. Refer HL_INFO_* for details. + * @dcore_id: DCORE id for which the information is relevant (for Gaudi refer to enum gaudi_dcores). + * @ctx_id: Context ID of the user. Currently not in use. + * @period_ms: Period value, in milliseconds, for utilization rate in range 100ms - 1000ms in 100 ms + * resolution. Currently not in use. + * @pll_index: Index as defined in hl__pll_index enumeration. + * @pad: Padding to 64 bit. + */ struct hl_info_args { - /* Location of relevant struct in userspace */ __u64 return_pointer; - /* - * The size of the return value. Just like "size" in "snprintf", - * it limits how many bytes the kernel can write - * - * For hw_events array, the size should be - * hl_info_hw_ip_info.num_of_events * sizeof(__u32) - */ __u32 return_size; - - /* HL_INFO_* */ __u32 op; union { - /* Dcore id for which the information is relevant. - * For Gaudi refer to 'enum gaudi_dcores' - */ __u32 dcore_id; - /* Context ID - Currently not in use */ __u32 ctx_id; - /* Period value for utilization rate (100ms - 1000ms, in 100ms - * resolution. - */ __u32 period_ms; - /* PLL frequency retrieval */ __u32 pll_index; }; -- cgit v1.2.3 From d62b9a6976cdac30a3af745de1f935ffe246fcdd Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 23 Sep 2021 12:02:23 +0300 Subject: habanalabs: add support for a long interrupt target value In order to avoid user target value wraparound, we modify the current interface so user will be able to wait for an 8-byte target value rather than a 4-byte value. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 8 ++++---- include/uapi/misc/habanalabs.h | 13 +++++++------ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index a344928363c8..44bab01cd033 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2739,13 +2739,13 @@ static int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, u32 timeout_us, u64 user_address, - u32 target_value, u16 interrupt_offset, + u64 target_value, u16 interrupt_offset, enum hl_cs_wait_status *status) { struct hl_user_pending_interrupt *pend; struct hl_user_interrupt *interrupt; unsigned long timeout, flags; - u32 completion_value; + u64 completion_value; long completion_rc; int rc = 0; @@ -2779,7 +2779,7 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, /* We check for completion value as interrupt could have been received * before we added the node to the wait list */ - if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) { + if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 8)) { dev_err(hdev->dev, "Failed to copy completion value from user\n"); rc = -EFAULT; goto remove_pending_user_interrupt; @@ -2811,7 +2811,7 @@ wait_again: reinit_completion(&pend->fence.completion); spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); - if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) { + if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 8)) { dev_err(hdev->dev, "Failed to copy completion value from user\n"); rc = -EFAULT; diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ccfcb4d188fc..fe73630e1a05 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -897,11 +897,7 @@ struct hl_wait_cs_in { */ __u64 addr; /* Target value for completion comparison */ - __u32 target; - /* Absolute timeout to wait for interrupt - * in microseconds - */ - __u32 interrupt_timeout_us; + __u64 target; }; }; @@ -917,7 +913,12 @@ struct hl_wait_cs_in { /* Multi CS API info- valid entries in multi-CS array */ __u8 seq_arr_len; - __u8 pad[7]; + __u8 pad[3]; + + /* Absolute timeout to wait for an interrupt in microseconds. + * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set + */ + __u32 interrupt_timeout_us; }; #define HL_WAIT_CS_STATUS_COMPLETED 0 -- cgit v1.2.3 From a9498ee575fa116e2891d9a6ff4fc7648dd9d7c8 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 11 Apr 2021 08:26:50 +0300 Subject: habanalabs: define uAPI to export FD for DMA-BUF User process might want to share the device memory with another driver/device, and to allow it to access it over PCIe (P2P). To enable this, we utilize the dma-buf mechanism and add a dma-buf exporter support, so the other driver can import the device memory and access it. The device memory is allocated using our existing allocation uAPI, where the user will get a handle that represents the allocation. The user will then need to call the new uAPI (HL_MEM_OP_EXPORT_DMABUF_FD) and give the handle as a parameter. The driver will return a FD that represents the DMA-BUF object that was created to match that allocation. Signed-off-by: Oded Gabbay Reviewed-by: Tomer Tayar Reviewed-by: Greg Kroah-Hartman Acked-by: Daniel Vetter --- include/uapi/misc/habanalabs.h | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index fe73630e1a05..00b309590499 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -960,6 +960,10 @@ union hl_wait_cs_args { #define HL_MEM_OP_UNMAP 3 /* Opcode to map a hw block */ #define HL_MEM_OP_MAP_BLOCK 4 +/* Opcode to create DMA-BUF object for an existing device memory allocation + * and to export an FD of that DMA-BUF back to the caller + */ +#define HL_MEM_OP_EXPORT_DMABUF_FD 5 /* Memory flags */ #define HL_MEM_CONTIGUOUS 0x1 @@ -1031,11 +1035,26 @@ struct hl_mem_in { /* Virtual address returned from HL_MEM_OP_MAP */ __u64 device_virt_addr; } unmap; + + /* HL_MEM_OP_EXPORT_DMABUF_FD */ + struct { + /* Handle returned from HL_MEM_OP_ALLOC. In Gaudi, + * where we don't have MMU for the device memory, the + * driver expects a physical address (instead of + * a handle) in the device memory space. + */ + __u64 handle; + /* Size of memory allocation. Relevant only for GAUDI */ + __u64 mem_size; + } export_dmabuf_fd; }; /* HL_MEM_OP_* */ __u32 op; - /* HL_MEM_* flags */ + /* HL_MEM_* flags. + * For the HL_MEM_OP_EXPORT_DMABUF_FD opcode, this field holds the + * DMA-BUF file/FD flags. + */ __u32 flags; /* Context ID - Currently not in use */ __u32 ctx_id; @@ -1072,6 +1091,13 @@ struct hl_mem_out { __u32 pad; }; + + /* Returned in HL_MEM_OP_EXPORT_DMABUF_FD. Represents the + * DMA-BUF object that was created to describe a memory + * allocation on the device's memory space. The FD should be + * passed to the importer driver + */ + __s32 fd; }; }; -- cgit v1.2.3 From b15706471abe916a16a38bee4434612998d869d2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 18 Oct 2021 08:37:00 +0200 Subject: ALSA: firewire: Fix C++ style comments in uapi header UAPI headers are built with -std=c90 and C++ style comments are explicitly prohibited. The recent commit overlooked the rule and caused the error at header installation. This patch corrects those. Fixes: bea36afa102e ("ALSA: firewire-motu: add message parser to gather meter information in register DSP model") Fixes: 90b28f3bb85c ("ALSA: firewire-motu: add message parser for meter information in command DSP model") Fixes: 634ec0b2906e ("ALSA: firewire-motu: notify event for parameter change in register DSP model") Reported-by: Stephen Rothwell Acked-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211018113812.0a16efb0@canb.auug.org.au Link: https://lore.kernel.org/r/20211018063700.30834-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 70 +++++++++++++++++++++++-------------------- 1 file changed, 37 insertions(+), 33 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 76190a0cb069..e52a97b3ceaa 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -68,8 +68,8 @@ struct snd_firewire_event_tascam_control { struct snd_firewire_event_motu_register_dsp_change { unsigned int type; - __u32 count; // The number of changes. - __u32 changes[]; // Encoded event for change of register DSP. + __u32 count; /* The number of changes. */ + __u32 changes[]; /* Encoded event for change of register DSP. */ }; union snd_firewire_event { @@ -119,25 +119,27 @@ struct snd_firewire_tascam_state { __be32 data[SNDRV_FIREWIRE_TASCAM_STATE_COUNT]; }; -// In below MOTU models, software is allowed to control their DSP by accessing to registers. -// - 828mk2 -// - 896hd -// - Traveler -// - 8 pre -// - Ultralite -// - 4 pre -// - Audio Express -// -// On the other hand, the status of DSP is split into specific messages included in the sequence of -// isochronous packet. ALSA firewire-motu driver gathers the messages and allow userspace applications -// to read it via ioctl. In 828mk2, 896hd, and Traveler, hardware meter for all of physical inputs -// are put into the message, while one pair of physical outputs is selected. The selection is done by -// LSB one byte in asynchronous write quadlet transaction to 0x'ffff'f000'0b2c. -// -// I note that V3HD/V4HD uses asynchronous transaction for the purpose. The destination address is -// registered to 0x'ffff'f000'0b38 and '0b3c by asynchronous write quadlet request. The size of -// message differs between 23 and 51 quadlets. For the case, the number of mixer bus can be extended -// up to 12. +/* + * In below MOTU models, software is allowed to control their DSP by accessing to registers. + * - 828mk2 + * - 896hd + * - Traveler + * - 8 pre + * - Ultralite + * - 4 pre + * - Audio Express + * + * On the other hand, the status of DSP is split into specific messages included in the sequence of + * isochronous packet. ALSA firewire-motu driver gathers the messages and allow userspace applications + * to read it via ioctl. In 828mk2, 896hd, and Traveler, hardware meter for all of physical inputs + * are put into the message, while one pair of physical outputs is selected. The selection is done by + * LSB one byte in asynchronous write quadlet transaction to 0x'ffff'f000'0b2c. + * + * I note that V3HD/V4HD uses asynchronous transaction for the purpose. The destination address is + * registered to 0x'ffff'f000'0b38 and '0b3c by asynchronous write quadlet request. The size of + * message differs between 23 and 51 quadlets. For the case, the number of mixer bus can be extended + * up to 12. + */ #define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT 40 @@ -219,18 +221,20 @@ struct snd_firewire_motu_register_dsp_parameter { __u8 reserved[64]; }; -// In below MOTU models, software is allowed to control their DSP by command in frame of -// asynchronous transaction to 0x'ffff'0001'0000: -// -// - 828 mk3 (FireWire only and Hybrid) -// - 896 mk3 (FireWire only and Hybrid) -// - Ultralite mk3 (FireWire only and Hybrid) -// - Traveler mk3 -// - Track 16 -// -// On the other hand, the states of hardware meter is split into specific messages included in the -// sequence of isochronous packet. ALSA firewire-motu driver gathers the message and allow userspace -// application to read it via ioctl. +/* + * In below MOTU models, software is allowed to control their DSP by command in frame of + * asynchronous transaction to 0x'ffff'0001'0000: + * + * - 828 mk3 (FireWire only and Hybrid) + * - 896 mk3 (FireWire only and Hybrid) + * - Ultralite mk3 (FireWire only and Hybrid) + * - Traveler mk3 + * - Track 16 + * + * On the other hand, the states of hardware meter is split into specific messages included in the + * sequence of isochronous packet. ALSA firewire-motu driver gathers the message and allow userspace + * application to read it via ioctl. + */ #define SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT 400 -- cgit v1.2.3 From 5aec579e08e4f2be7103ae264ac8f34883eb9273 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 18 Oct 2021 13:40:35 +0200 Subject: ALSA: uapi: Fix a C++ style comment in asound.h UAPI header should have no C++ style comment but only in the traditional C style comment, but there is still one place we used it mistakenly. This patch corrects it. Fixes: 542283566679 ("ALSA: ctl: remove unused macro for timestamping of elem_value") Reviewed-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211018114035.18433-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 5859ca0a1439..5fbb79e30819 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -1002,7 +1002,7 @@ typedef int __bitwise snd_ctl_elem_iface_t; #define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1) #define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE) #define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */ -// (1 << 3) is unused. +/* (1 << 3) is unused. */ #define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE) -- cgit v1.2.3 From 7bbbbfaa7a1b0b03890f25fba5f28bb8c7ef145a Mon Sep 17 00:00:00 2001 From: Alvin Šipraga Date: Mon, 18 Oct 2021 11:37:56 +0200 Subject: ether: add EtherType for proprietary Realtek protocols MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new EtherType ETH_P_REALTEK to the if_ether.h uapi header. The EtherType 0x8899 is used in a number of different protocols from Realtek Semiconductor Corp [1], so no general assumptions should be made when trying to decode such packets. Observed protocols include: 0x1 - Realtek Remote Control protocol [2] 0x2 - Echo protocol [2] 0x3 - Loop detection protocol [2] 0x4 - RTL8365MB 4- and 8-byte switch CPU tag protocols [3] 0x9 - RTL8306 switch CPU tag protocol [4] 0xA - RTL8366RB switch CPU tag protocol [4] [1] https://lore.kernel.org/netdev/CACRpkdYQthFgjwVzHyK3DeYUOdcYyWmdjDPG=Rf9B3VrJ12Rzg@mail.gmail.com/ [2] https://www.wireshark.org/lists/ethereal-dev/200409/msg00090.html [3] https://lore.kernel.org/netdev/20210822193145.1312668-4-alvin@pqrs.dk/ [4] https://lore.kernel.org/netdev/20200708122537.1341307-2-linus.walleij@linaro.org/ Suggested-by: Andrew Lunn Signed-off-by: Alvin Šipraga Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5f589c7a8382..5da4ee234e0b 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -86,6 +86,7 @@ * over Ethernet */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ +#define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ -- cgit v1.2.3 From 917425f71f36ce6f61841497040e10d0166106d8 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:27 +0200 Subject: rtc: add alarm related features Add more alarm related features to be declared by drivers. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-2-alexandre.belloni@bootlin.com --- include/uapi/linux/rtc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index f950bff75e97..f4037c541925 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -114,7 +114,9 @@ struct rtc_pll_info { #define RTC_FEATURE_ALARM 0 #define RTC_FEATURE_ALARM_RES_MINUTE 1 #define RTC_FEATURE_NEED_WEEK_DAY 2 -#define RTC_FEATURE_CNT 3 +#define RTC_FEATURE_ALARM_RES_2S 3 +#define RTC_FEATURE_UPDATE_INTERRUPT 4 +#define RTC_FEATURE_CNT 5 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 6a8af1b6568ad9ee08a419fb12c793f7992cf8a4 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:28 +0200 Subject: rtc: add parameter ioctl Add an ioctl allowing to get and set extra parameters for an RTC. For now, only handle getting available features. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-3-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/rtc.h | 18 ++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/uapi') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 5b8ebe86124a..143c097eff0f 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -208,6 +208,7 @@ static long rtc_dev_ioctl(struct file *file, const struct rtc_class_ops *ops = rtc->ops; struct rtc_time tm; struct rtc_wkalrm alarm; + struct rtc_param param; void __user *uarg = (void __user *)arg; err = mutex_lock_interruptible(&rtc->ops_lock); @@ -221,6 +222,7 @@ static long rtc_dev_ioctl(struct file *file, switch (cmd) { case RTC_EPOCH_SET: case RTC_SET_TIME: + case RTC_PARAM_SET: if (!capable(CAP_SYS_TIME)) err = -EACCES; break; @@ -382,6 +384,44 @@ static long rtc_dev_ioctl(struct file *file, err = -EFAULT; return err; + case RTC_PARAM_GET: + if (copy_from_user(¶m, uarg, sizeof(param))) { + mutex_unlock(&rtc->ops_lock); + return -EFAULT; + } + + switch(param.param) { + long offset; + case RTC_PARAM_FEATURES: + if (param.index != 0) + err = -EINVAL; + param.uvalue = rtc->features[0]; + break; + + default: + err = -EINVAL; + } + + if (!err) + if (copy_to_user(uarg, ¶m, sizeof(param))) + err = -EFAULT; + + break; + + case RTC_PARAM_SET: + if (copy_from_user(¶m, uarg, sizeof(param))) { + mutex_unlock(&rtc->ops_lock); + return -EFAULT; + } + + switch(param.param) { + case RTC_PARAM_FEATURES: + default: + err = -EINVAL; + } + + break; + default: /* Finally try the driver's ioctl interface */ if (ops->ioctl) { diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index f4037c541925..3241f9ecc639 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -14,6 +14,7 @@ #include #include +#include /* * The struct used to pass data via the following ioctl. Similar to the @@ -66,6 +67,17 @@ struct rtc_pll_info { long pll_clock; /* base PLL frequency */ }; +struct rtc_param { + __u64 param; + union { + __u64 uvalue; + __s64 svalue; + __u64 ptr; + }; + __u32 index; + __u32 __pad; +}; + /* * ioctl calls that are permitted to the /dev/rtc interface, if * any of the RTC drivers are enabled. @@ -95,6 +107,9 @@ struct rtc_pll_info { #define RTC_PLL_GET _IOR('p', 0x11, struct rtc_pll_info) /* Get PLL correction */ #define RTC_PLL_SET _IOW('p', 0x12, struct rtc_pll_info) /* Set PLL correction */ +#define RTC_PARAM_GET _IOW('p', 0x13, struct rtc_param) /* Get parameter */ +#define RTC_PARAM_SET _IOW('p', 0x14, struct rtc_param) /* Set parameter */ + #define RTC_VL_DATA_INVALID _BITUL(0) /* Voltage too low, RTC data is invalid */ #define RTC_VL_BACKUP_LOW _BITUL(1) /* Backup voltage is low */ #define RTC_VL_BACKUP_EMPTY _BITUL(2) /* Backup empty or not present */ @@ -118,6 +133,9 @@ struct rtc_pll_info { #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CNT 5 +/* parameter list */ +#define RTC_PARAM_FEATURES 0 + #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 2268551935dbf1abcbb4d4fb7b1ad74dbe0d1be0 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:29 +0200 Subject: rtc: expose correction feature Add a new feature for RTCs able to correct the oscillator imprecision. This is also called offset or trimming. Such drivers have a .set_offset callback, use that to set the feature bit from the core. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-4-alexandre.belloni@bootlin.com --- drivers/rtc/class.c | 3 +++ include/uapi/linux/rtc.h | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index dbccd71589b9..2e0cbc190a8a 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -389,6 +389,9 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) if (!rtc->ops->set_alarm) clear_bit(RTC_FEATURE_ALARM, rtc->features); + if (rtc->ops->set_offset) + set_bit(RTC_FEATURE_CORRECTION, rtc->features); + rtc->owner = owner; rtc_device_get_offset(rtc); diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 3241f9ecc639..c83bb9a4fa4f 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -131,7 +131,8 @@ struct rtc_param { #define RTC_FEATURE_NEED_WEEK_DAY 2 #define RTC_FEATURE_ALARM_RES_2S 3 #define RTC_FEATURE_UPDATE_INTERRUPT 4 -#define RTC_FEATURE_CNT 5 +#define RTC_FEATURE_CORRECTION 5 +#define RTC_FEATURE_CNT 6 /* parameter list */ #define RTC_PARAM_FEATURES 0 -- cgit v1.2.3 From a6d8c6e1a5c6fb982964861dc84c0c7cb0151c7c Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:30 +0200 Subject: rtc: add correction parameter Add a new parameter allowing the get and set the correction using ioctls instead of just sysfs. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-5-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 19 +++++++++++++++++++ include/uapi/linux/rtc.h | 1 + 2 files changed, 20 insertions(+) (limited to 'include/uapi') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 143c097eff0f..abee1fc4705e 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -398,6 +398,16 @@ static long rtc_dev_ioctl(struct file *file, param.uvalue = rtc->features[0]; break; + case RTC_PARAM_CORRECTION: + mutex_unlock(&rtc->ops_lock); + if (param.index != 0) + return -EINVAL; + err = rtc_read_offset(rtc, &offset); + mutex_lock(&rtc->ops_lock); + if (err == 0) + param.svalue = offset; + break; + default: err = -EINVAL; } @@ -416,6 +426,15 @@ static long rtc_dev_ioctl(struct file *file, switch(param.param) { case RTC_PARAM_FEATURES: + err = -EINVAL; + break; + + case RTC_PARAM_CORRECTION: + mutex_unlock(&rtc->ops_lock); + if (param.index != 0) + return -EINVAL; + return rtc_set_offset(rtc, param.svalue); + default: err = -EINVAL; } diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index c83bb9a4fa4f..5debe82439c2 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -136,6 +136,7 @@ struct rtc_param { /* parameter list */ #define RTC_PARAM_FEATURES 0 +#define RTC_PARAM_CORRECTION 1 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 0d20e9fb1262b1f9ac895b287db892bc75b05b84 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:31 +0200 Subject: rtc: add BSM parameter BSM or Backup Switch Mode is a common feature on RTCs, allowing to select how the RTC will decide when to switch from its primary power supply to the backup power supply. It is necessary to be able to set it from userspace as there are uses cases where it has to be done dynamically. Supported values are: RTC_BSM_DISABLED: disabled RTC_BSM_DIRECT: switching will happen as soon as Vbackup > Vdd RTC_BSM_LEVEL: switching will happen around a threshold, usually with an hysteresis RTC_BSM_STANDBY: switching will not happen until Vdd > Vbackup, this is useful to ensure the RTC doesn't draw any power until the device is first powered on. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-6-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 10 ++++++++-- include/linux/rtc.h | 2 ++ include/uapi/linux/rtc.h | 9 ++++++++- 3 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index abee1fc4705e..e104972a28fd 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -409,7 +409,10 @@ static long rtc_dev_ioctl(struct file *file, break; default: - err = -EINVAL; + if (rtc->ops->param_get) + err = rtc->ops->param_get(rtc->dev.parent, ¶m); + else + err = -EINVAL; } if (!err) @@ -436,7 +439,10 @@ static long rtc_dev_ioctl(struct file *file, return rtc_set_offset(rtc, param.svalue); default: - err = -EINVAL; + if (rtc->ops->param_set) + err = rtc->ops->param_set(rtc->dev.parent, ¶m); + else + err = -EINVAL; } break; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 354e0843ab17..47fd1c2d3a57 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -66,6 +66,8 @@ struct rtc_class_ops { int (*alarm_irq_enable)(struct device *, unsigned int enabled); int (*read_offset)(struct device *, long *offset); int (*set_offset)(struct device *, long offset); + int (*param_get)(struct device *, struct rtc_param *param); + int (*param_set)(struct device *, struct rtc_param *param); }; struct rtc_device; diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 5debe82439c2..03e5b776e597 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -132,11 +132,18 @@ struct rtc_param { #define RTC_FEATURE_ALARM_RES_2S 3 #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CORRECTION 5 -#define RTC_FEATURE_CNT 6 +#define RTC_FEATURE_BACKUP_SWITCH_MODE 6 +#define RTC_FEATURE_CNT 7 /* parameter list */ #define RTC_PARAM_FEATURES 0 #define RTC_PARAM_CORRECTION 1 +#define RTC_PARAM_BACKUP_SWITCH_MODE 2 + +#define RTC_BSM_DISABLED 0 +#define RTC_BSM_DIRECT 1 +#define RTC_BSM_LEVEL 2 +#define RTC_BSM_STANDBY 3 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From c68dc1b577eabd5605c6c7c08f3e07ae18d30d5d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Thu, 16 Sep 2021 18:15:35 +0000 Subject: KVM: x86: Report host tsc and realtime values in KVM_GET_CLOCK Handling the migration of TSCs correctly is difficult, in part because Linux does not provide userspace with the ability to retrieve a (TSC, realtime) clock pair for a single instant in time. In lieu of a more convenient facility, KVM can report similar information in the kvm_clock structure. Provide userspace with a host TSC & realtime pair iff the realtime clock is based on the TSC. If userspace provides KVM_SET_CLOCK with a valid realtime value, advance the KVM clock by the amount of elapsed time. Do not step the KVM clock backwards, though, as it is a monotonic oscillator. Suggested-by: Paolo Bonzini Signed-off-by: Oliver Upton Signed-off-by: Paolo Bonzini Message-Id: <20210916181538.968978-5-oupton@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 48 +++++++++++++++++++++++++++++++++-------- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/x86.c | 47 ++++++++++++++++++++++++++++------------ include/uapi/linux/kvm.h | 7 +++++- 4 files changed, 81 insertions(+), 24 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0c0bf26426b3..3b093d6dbe22 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1010,20 +1010,37 @@ such as migration. When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the set of bits that KVM can return in struct kvm_clock_data's flag member. -The only flag defined now is KVM_CLOCK_TSC_STABLE. If set, the returned -value is the exact kvmclock value seen by all VCPUs at the instant -when KVM_GET_CLOCK was called. If clear, the returned value is simply -CLOCK_MONOTONIC plus a constant offset; the offset can be modified -with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock, -but the exact value read by each VCPU could differ, because the host -TSC is not stable. +The following flags are defined: + +KVM_CLOCK_TSC_STABLE + If set, the returned value is the exact kvmclock + value seen by all VCPUs at the instant when KVM_GET_CLOCK was called. + If clear, the returned value is simply CLOCK_MONOTONIC plus a constant + offset; the offset can be modified with KVM_SET_CLOCK. KVM will try + to make all VCPUs follow this clock, but the exact value read by each + VCPU could differ, because the host TSC is not stable. + +KVM_CLOCK_REALTIME + If set, the `realtime` field in the kvm_clock_data + structure is populated with the value of the host's real time + clocksource at the instant when KVM_GET_CLOCK was called. If clear, + the `realtime` field does not contain a value. + +KVM_CLOCK_HOST_TSC + If set, the `host_tsc` field in the kvm_clock_data + structure is populated with the value of the host's timestamp counter (TSC) + at the instant when KVM_GET_CLOCK was called. If clear, the `host_tsc` field + does not contain a value. :: struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; @@ -1040,12 +1057,25 @@ Sets the current timestamp of kvmclock to the value specified in its parameter. In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios such as migration. +The following flags can be passed: + +KVM_CLOCK_REALTIME + If set, KVM will compare the value of the `realtime` field + with the value of the host's real time clocksource at the instant when + KVM_SET_CLOCK was called. The difference in elapsed time is added to the final + kvmclock value that will be provided to guests. + +Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored. + :: struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5271fce6cd65..8b16fa504cd4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1942,4 +1942,7 @@ int kvm_cpu_dirty_log_size(void); int alloc_all_memslots_rmaps(struct kvm *kvm); +#define KVM_CLOCK_VALID_FLAGS \ + (KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3ea4f6ef2474..d3631d149187 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2787,6 +2787,7 @@ static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) struct pvclock_vcpu_time_info hv_clock; unsigned long flags; + data->flags = 0; spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); @@ -2803,10 +2804,20 @@ static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) get_cpu(); if (__this_cpu_read(cpu_tsc_khz)) { +#ifdef CONFIG_X86_64 + struct timespec64 ts; + + if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) { + data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec; + data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC; + } else +#endif + data->host_tsc = rdtsc(); + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - data->clock = __pvclock_read_cycles(&hv_clock, rdtsc()); + data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); } else { data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; } @@ -2818,12 +2829,6 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_clock_data data; - /* - * Zero flags as it's accessed RMW, leave everything else uninitialized - * as clock is always written and no other fields are consumed. - */ - data.flags = 0; - get_kvmclock(kvm, &data); return data.clock; } @@ -4050,7 +4055,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_SYNC_X86_VALID_FIELDS; break; case KVM_CAP_ADJUST_CLOCK: - r = KVM_CLOCK_TSC_STABLE; + r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE | @@ -5847,12 +5852,16 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) { struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data data; - u64 now_ns; + u64 now_raw_ns; if (copy_from_user(&data, argp, sizeof(data))) return -EFAULT; - if (data.flags) + /* + * Only KVM_CLOCK_REALTIME is used, but allow passing the + * result of KVM_GET_CLOCK back to KVM_SET_CLOCK. + */ + if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; kvm_hv_invalidate_tsc_page(kvm); @@ -5866,11 +5875,21 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) * is slightly ahead) here we risk going negative on unsigned * 'system_time' when 'data.clock' is very small. */ - if (kvm->arch.use_master_clock) - now_ns = ka->master_kernel_ns; + if (data.flags & KVM_CLOCK_REALTIME) { + u64 now_real_ns = ktime_get_real_ns(); + + /* + * Avoid stepping the kvmclock backwards. + */ + if (now_real_ns > data.realtime) + data.clock += now_real_ns - data.realtime; + } + + if (ka->use_master_clock) + now_raw_ns = ka->master_kernel_ns; else - now_ns = get_kvmclock_base_ns(); - ka->kvmclock_offset = data.clock - now_ns; + now_raw_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = data.clock - now_raw_ns; kvm_end_pvclock_update(kvm); return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 322b4b588d75..5ca5ffe16cb4 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1231,11 +1231,16 @@ struct kvm_irqfd { /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ #define KVM_CLOCK_TSC_STABLE 2 +#define KVM_CLOCK_REALTIME (1 << 2) +#define KVM_CLOCK_HOST_TSC (1 << 3) struct kvm_clock_data { __u64 clock; __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; /* For KVM_CAP_SW_TLB */ -- cgit v1.2.3 From 3080ea5553cc909b000d1f1d964a9041962f2c5b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 9 Aug 2021 11:21:23 -0700 Subject: stddef: Introduce DECLARE_FLEX_ARRAY() helper There are many places where kernel code wants to have several different typed trailing flexible arrays. This would normally be done with multiple flexible arrays in a union, but since GCC and Clang don't (on the surface) allow this, there have been many open-coded workarounds, usually involving neighboring 0-element arrays at the end of a structure. For example, instead of something like this: struct thing { ... union { struct type1 foo[]; struct type2 bar[]; }; }; code works around the compiler with: struct thing { ... struct type1 foo[0]; struct type2 bar[]; }; Another case is when a flexible array is wanted as the single member within a struct (which itself is usually in a union). For example, this would be worked around as: union many { ... struct { struct type3 baz[0]; }; }; These kinds of work-arounds cause problems with size checks against such zero-element arrays (for example when building with -Warray-bounds and -Wzero-length-bounds, and with the coming FORTIFY_SOURCE improvements), so they must all be converted to "real" flexible arrays, avoiding warnings like this: fs/hpfs/anode.c: In function 'hpfs_add_sector_to_btree': fs/hpfs/anode.c:209:27: warning: array subscript 0 is outside the bounds of an interior zero-length array 'struct bplus_internal_node[0]' [-Wzero-length-bounds] 209 | anode->btree.u.internal[0].down = cpu_to_le32(a); | ~~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from fs/hpfs/hpfs_fn.h:26, from fs/hpfs/anode.c:10: fs/hpfs/hpfs.h:412:32: note: while referencing 'internal' 412 | struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving | ^~~~~~~~ drivers/net/can/usb/etas_es58x/es58x_fd.c: In function 'es58x_fd_tx_can_msg': drivers/net/can/usb/etas_es58x/es58x_fd.c:360:35: warning: array subscript 65535 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[]'} [-Wzero-length-bounds] 360 | tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/net/can/usb/etas_es58x/es58x_core.h:22, from drivers/net/can/usb/etas_es58x/es58x_fd.c:17: drivers/net/can/usb/etas_es58x/es58x_fd.h:231:6: note: while referencing 'raw_msg' 231 | u8 raw_msg[0]; | ^~~~~~~ However, it _is_ entirely possible to have one or more flexible arrays in a struct or union: it just has to be in another struct. And since it cannot be alone in a struct, such a struct must have at least 1 other named member -- but that member can be zero sized. Wrap all this nonsense into the new DECLARE_FLEX_ARRAY() in support of having flexible arrays in unions (or alone in a struct). As with struct_group(), since this is needed in UAPI headers as well, implement the core there, with a non-UAPI wrapper. Additionally update kernel-doc to understand its existence. https://github.com/KSPP/linux/issues/137 Cc: Arnd Bergmann Cc: "Gustavo A. R. Silva" Signed-off-by: Kees Cook --- include/linux/stddef.h | 13 +++++++++++++ include/uapi/linux/stddef.h | 16 ++++++++++++++++ scripts/kernel-doc | 2 ++ 3 files changed, 31 insertions(+) (limited to 'include/uapi') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 8b103a53b000..ca507bd5f808 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -84,4 +84,17 @@ enum { #define struct_group_tagged(TAG, NAME, MEMBERS...) \ __struct_group(TAG, NAME, /* no attrs */, MEMBERS) +/** + * DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define DECLARE_FLEX_ARRAY(TYPE, NAME) \ + __DECLARE_FLEX_ARRAY(TYPE, NAME) + #endif diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 610204f7c275..3021ea25a284 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -25,3 +25,19 @@ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ } + +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 38aa799a776c..5d54b57ff90c 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1263,6 +1263,8 @@ sub dump_struct($$) { $members =~ s/DECLARE_KFIFO\s*\($args,\s*$args,\s*$args\)/$2 \*$1/gos; # replace DECLARE_KFIFO_PTR $members =~ s/DECLARE_KFIFO_PTR\s*\($args,\s*$args\)/$2 \*$1/gos; + # replace DECLARE_FLEX_ARRAY + $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\($args,\s*$args\)/$1 $2\[\]/gos; my $declaration = $members; # Split nested struct/union elements as newer ones -- cgit v1.2.3 From fa7845cfd53f3b1d3f60efa55db89805595bc045 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 9 Aug 2021 11:29:33 -0700 Subject: treewide: Replace open-coded flex arrays in unions In support of enabling -Warray-bounds and -Wzero-length-bounds and correctly handling run-time memcpy() bounds checking, replace all open-coded flexible arrays (i.e. 0-element arrays) in unions with the DECLARE_FLEX_ARRAY() helper macro. This fixes warnings such as: fs/hpfs/anode.c: In function 'hpfs_add_sector_to_btree': fs/hpfs/anode.c:209:27: warning: array subscript 0 is outside the bounds of an interior zero-length array 'struct bplus_internal_node[0]' [-Wzero-length-bounds] 209 | anode->btree.u.internal[0].down = cpu_to_le32(a); | ~~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from fs/hpfs/hpfs_fn.h:26, from fs/hpfs/anode.c:10: fs/hpfs/hpfs.h:412:32: note: while referencing 'internal' 412 | struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving | ^~~~~~~~ drivers/net/can/usb/etas_es58x/es58x_fd.c: In function 'es58x_fd_tx_can_msg': drivers/net/can/usb/etas_es58x/es58x_fd.c:360:35: warning: array subscript 65535 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[]'} [-Wzero-length-bounds] 360 | tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/net/can/usb/etas_es58x/es58x_core.h:22, from drivers/net/can/usb/etas_es58x/es58x_fd.c:17: drivers/net/can/usb/etas_es58x/es58x_fd.h:231:6: note: while referencing 'raw_msg' 231 | u8 raw_msg[0]; | ^~~~~~~ Cc: "Gustavo A. R. Silva" Cc: Arnd Bergmann Cc: Ayush Sawal Cc: Vinay Kumar Yadav Cc: Rohit Maheshwari Cc: Herbert Xu Cc: "David S. Miller" Cc: Kalle Valo Cc: Jakub Kicinski Cc: Stanislaw Gruszka Cc: Luca Coelho Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Andrii Nakryiko Cc: Martin KaFai Lau Cc: Song Liu Cc: Yonghong Song Cc: John Fastabend Cc: KP Singh Cc: Johannes Berg Cc: Mordechay Goodstein Cc: Lee Jones Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: Arunachalam Santhanam Cc: Vincent Mailhol Cc: Mikulas Patocka Cc: linux-crypto@vger.kernel.org Cc: ath10k@lists.infradead.org Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: linux-can@vger.kernel.org Cc: bpf@vger.kernel.org Acked-by: Marc Kleine-Budde # drivers/net/can/usb/etas_es58x/* Signed-off-by: Kees Cook --- drivers/crypto/chelsio/chcr_crypto.h | 14 +++++++++----- drivers/net/can/usb/etas_es58x/es581_4.h | 2 +- drivers/net/can/usb/etas_es58x/es58x_fd.h | 2 +- drivers/net/wireless/ath/ath10k/htt.h | 7 +++++-- drivers/net/wireless/intel/iwlegacy/commands.h | 6 ++++-- drivers/net/wireless/intel/iwlwifi/dvm/commands.h | 6 ++++-- drivers/net/wireless/intel/iwlwifi/fw/api/tx.h | 12 ++++++++---- drivers/scsi/aic94xx/aic94xx_sds.c | 6 ++++-- fs/hpfs/hpfs.h | 8 ++++---- include/linux/filter.h | 6 ++++-- include/scsi/sas.h | 12 ++++++++---- include/uapi/rdma/rdma_user_rxe.h | 4 ++-- include/uapi/sound/asoc.h | 4 ++-- 13 files changed, 56 insertions(+), 33 deletions(-) (limited to 'include/uapi') diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index e89f9e0094b4..c7816c83e324 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -222,8 +222,10 @@ struct chcr_authenc_ctx { }; struct __aead_ctx { - struct chcr_gcm_ctx gcm[0]; - struct chcr_authenc_ctx authenc[]; + union { + DECLARE_FLEX_ARRAY(struct chcr_gcm_ctx, gcm); + DECLARE_FLEX_ARRAY(struct chcr_authenc_ctx, authenc); + }; }; struct chcr_aead_ctx { @@ -245,9 +247,11 @@ struct hmac_ctx { }; struct __crypto_ctx { - struct hmac_ctx hmacctx[0]; - struct ablk_ctx ablkctx[0]; - struct chcr_aead_ctx aeadctx[]; + union { + DECLARE_FLEX_ARRAY(struct hmac_ctx, hmacctx); + DECLARE_FLEX_ARRAY(struct ablk_ctx, ablkctx); + DECLARE_FLEX_ARRAY(struct chcr_aead_ctx, aeadctx); + }; }; struct chcr_context { diff --git a/drivers/net/can/usb/etas_es58x/es581_4.h b/drivers/net/can/usb/etas_es58x/es581_4.h index 4bc60a6df697..667ecb77168c 100644 --- a/drivers/net/can/usb/etas_es58x/es581_4.h +++ b/drivers/net/can/usb/etas_es58x/es581_4.h @@ -192,7 +192,7 @@ struct es581_4_urb_cmd { struct es581_4_rx_cmd_ret rx_cmd_ret; __le64 timestamp; u8 rx_cmd_ret_u8; - u8 raw_msg[0]; + DECLARE_FLEX_ARRAY(u8, raw_msg); } __packed; __le16 reserved_for_crc16_do_not_use; diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.h b/drivers/net/can/usb/etas_es58x/es58x_fd.h index a191891b8777..c4b19a6a33ae 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.h +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.h @@ -219,7 +219,7 @@ struct es58x_fd_urb_cmd { struct es58x_fd_tx_ack_msg tx_ack_msg; __le64 timestamp; __le32 rx_cmd_ret_le32; - u8 raw_msg[0]; + DECLARE_FLEX_ARRAY(u8, raw_msg); } __packed; __le16 reserved_for_crc16_do_not_use; diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index ec689e3ce48a..a6de08d3bf4a 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -1674,8 +1674,11 @@ struct htt_tx_fetch_ind { __le32 token; __le16 num_resp_ids; __le16 num_records; - __le32 resp_ids[0]; /* ath10k_htt_get_tx_fetch_ind_resp_ids() */ - struct htt_tx_fetch_record records[]; + union { + /* ath10k_htt_get_tx_fetch_ind_resp_ids() */ + DECLARE_FLEX_ARRAY(__le32, resp_ids); + DECLARE_FLEX_ARRAY(struct htt_tx_fetch_record, records); + }; } __packed; static inline void * diff --git a/drivers/net/wireless/intel/iwlegacy/commands.h b/drivers/net/wireless/intel/iwlegacy/commands.h index 89c6671b32bc..4a97310f8fee 100644 --- a/drivers/net/wireless/intel/iwlegacy/commands.h +++ b/drivers/net/wireless/intel/iwlegacy/commands.h @@ -1408,8 +1408,10 @@ struct il3945_tx_cmd { * MAC header goes here, followed by 2 bytes padding if MAC header * length is 26 or 30 bytes, followed by payload data */ - u8 payload[0]; - struct ieee80211_hdr hdr[]; + union { + DECLARE_FLEX_ARRAY(u8, payload); + DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr); + }; } __packed; /* diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/commands.h b/drivers/net/wireless/intel/iwlwifi/dvm/commands.h index 235c7a2e3483..75a4b8e26232 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/dvm/commands.h @@ -1251,8 +1251,10 @@ struct iwl_tx_cmd { * MAC header goes here, followed by 2 bytes padding if MAC header * length is 26 or 30 bytes, followed by payload data */ - u8 payload[0]; - struct ieee80211_hdr hdr[]; + union { + DECLARE_FLEX_ARRAY(u8, payload); + DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr); + }; } __packed; /* diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h index 24e4a82a55da..5fddfd391941 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h @@ -239,8 +239,10 @@ struct iwl_tx_cmd { u8 tid_tspec; __le16 pm_frame_timeout; __le16 reserved4; - u8 payload[0]; - struct ieee80211_hdr hdr[0]; + union { + DECLARE_FLEX_ARRAY(u8, payload); + DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr); + }; } __packed; /* TX_CMD_API_S_VER_6 */ struct iwl_dram_sec_info { @@ -713,8 +715,10 @@ struct iwl_mvm_compressed_ba_notif { __le32 tx_rate; __le16 tfd_cnt; __le16 ra_tid_cnt; - struct iwl_mvm_compressed_ba_ratid ra_tid[0]; - struct iwl_mvm_compressed_ba_tfd tfd[]; + union { + DECLARE_FLEX_ARRAY(struct iwl_mvm_compressed_ba_ratid, ra_tid); + DECLARE_FLEX_ARRAY(struct iwl_mvm_compressed_ba_tfd, tfd); + }; } __packed; /* COMPRESSED_BA_RES_API_S_VER_4 */ /** diff --git a/drivers/scsi/aic94xx/aic94xx_sds.c b/drivers/scsi/aic94xx/aic94xx_sds.c index 46815e65f7a4..5def83c88f13 100644 --- a/drivers/scsi/aic94xx/aic94xx_sds.c +++ b/drivers/scsi/aic94xx/aic94xx_sds.c @@ -517,8 +517,10 @@ struct asd_ms_conn_map { u8 num_nodes; u8 usage_model_id; u32 _resvd; - struct asd_ms_conn_desc conn_desc[0]; - struct asd_ms_node_desc node_desc[]; + union { + DECLARE_FLEX_ARRAY(struct asd_ms_conn_desc, conn_desc); + DECLARE_FLEX_ARRAY(struct asd_ms_node_desc, node_desc); + }; } __attribute__ ((packed)); struct asd_ctrla_phy_entry { diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h index d92c4af3e1b4..281dec8f636b 100644 --- a/fs/hpfs/hpfs.h +++ b/fs/hpfs/hpfs.h @@ -409,10 +409,10 @@ struct bplus_header __le16 first_free; /* offset from start of header to first free node in array */ union { - struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving - subtree pointers */ - struct bplus_leaf_node external[0]; /* (external) 3-word entries giving - sector runs */ + /* (internal) 2-word entries giving subtree pointers */ + DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal); + /* (external) 3-word entries giving sector runs */ + DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external); } u; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 4a93c12543ee..4298c5e428a3 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -586,8 +586,10 @@ struct bpf_prog { struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ - struct sock_filter insns[0]; - struct bpf_insn insnsi[]; + union { + DECLARE_FLEX_ARRAY(struct sock_filter, insns); + DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); + }; }; struct sk_filter { diff --git a/include/scsi/sas.h b/include/scsi/sas.h index 4726c1bbec65..64154c1fed02 100644 --- a/include/scsi/sas.h +++ b/include/scsi/sas.h @@ -323,8 +323,10 @@ struct ssp_response_iu { __be32 sense_data_len; __be32 response_data_len; - u8 resp_data[0]; - u8 sense_data[]; + union { + DECLARE_FLEX_ARRAY(u8, resp_data); + DECLARE_FLEX_ARRAY(u8, sense_data); + }; } __attribute__ ((packed)); struct ssp_command_iu { @@ -554,8 +556,10 @@ struct ssp_response_iu { __be32 sense_data_len; __be32 response_data_len; - u8 resp_data[0]; - u8 sense_data[]; + union { + DECLARE_FLEX_ARRAY(u8, resp_data); + DECLARE_FLEX_ARRAY(u8, sense_data); + }; } __attribute__ ((packed)); struct ssp_command_iu { diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index e283c2220aba..7f44d54bb0ab 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -141,8 +141,8 @@ struct rxe_dma_info { __u32 sge_offset; __u32 reserved; union { - __u8 inline_data[0]; - struct rxe_sge sge[0]; + __DECLARE_FLEX_ARRAY(__u8, inline_data); + __DECLARE_FLEX_ARRAY(struct rxe_sge, sge); }; }; diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index da61398b1f8f..053949287ce8 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -240,8 +240,8 @@ struct snd_soc_tplg_vendor_array { struct snd_soc_tplg_private { __le32 size; /* in bytes of private data */ union { - char data[0]; - struct snd_soc_tplg_vendor_array array[0]; + __DECLARE_FLEX_ARRAY(char, data); + __DECLARE_FLEX_ARRAY(struct snd_soc_tplg_vendor_array, array); }; } __attribute__((packed)); -- cgit v1.2.3 From 47c662486cccf03e7062139d069b07ab0126ef59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 13 Aug 2021 12:19:24 -0700 Subject: treewide: Replace 0-element memcpy() destinations with flexible arrays The 0-element arrays that are used as memcpy() destinations are actually flexible arrays. Adjust their structures accordingly so that memcpy() can better reason able their destination size (i.e. they need to be seen as "unknown" length rather than "zero"). In some cases, use of the DECLARE_FLEX_ARRAY() helper is needed when a flexible array is alone in a struct. Cc: "Gustavo A. R. Silva" Cc: Arnd Bergmann Cc: Kalle Valo Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Nilesh Javali Cc: Manish Rangankar Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Larry Finger Cc: Phillip Potter Cc: Greg Kroah-Hartman Cc: Florian Schilhabel Cc: Johannes Berg Cc: Christophe JAILLET Cc: Fabio Aiuto Cc: Ross Schmidt Cc: Marco Cesati Cc: ath10k@lists.infradead.org Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: linux-staging@lists.linux.dev Signed-off-by: Kees Cook --- drivers/net/wireless/ath/ath10k/bmi.h | 10 ++++----- drivers/scsi/qla4xxx/ql4_def.h | 4 ++-- drivers/staging/r8188eu/include/ieee80211.h | 6 +++--- drivers/staging/rtl8712/ieee80211.h | 4 ++-- drivers/staging/rtl8723bs/include/ieee80211.h | 6 +++--- include/linux/ieee80211.h | 30 +++++++++++++-------------- include/uapi/linux/dlm_device.h | 4 ++-- 7 files changed, 32 insertions(+), 32 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/wireless/ath/ath10k/bmi.h b/drivers/net/wireless/ath/ath10k/bmi.h index f6fadcbdd86e..0685c0d2d4ea 100644 --- a/drivers/net/wireless/ath/ath10k/bmi.h +++ b/drivers/net/wireless/ath/ath10k/bmi.h @@ -109,7 +109,7 @@ struct bmi_cmd { struct { __le32 addr; __le32 len; - u8 payload[0]; + u8 payload[]; } write_mem; struct { __le32 addr; @@ -138,18 +138,18 @@ struct bmi_cmd { } rompatch_uninstall; struct { __le32 count; - __le32 patch_ids[0]; /* length of @count */ + __le32 patch_ids[]; /* length of @count */ } rompatch_activate; struct { __le32 count; - __le32 patch_ids[0]; /* length of @count */ + __le32 patch_ids[]; /* length of @count */ } rompatch_deactivate; struct { __le32 addr; } lz_start; struct { __le32 len; /* max BMI_MAX_DATA_SIZE */ - u8 payload[0]; /* length of @len */ + u8 payload[]; /* length of @len */ } lz_data; struct { u8 name[BMI_NVRAM_SEG_NAME_SZ]; @@ -160,7 +160,7 @@ struct bmi_cmd { union bmi_resp { struct { - u8 payload[0]; + DECLARE_FLEX_ARRAY(u8, payload); } read_mem; struct { __le32 result; diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index 031569c496e5..69a590546bf9 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -366,13 +366,13 @@ struct qla4_work_evt { struct { enum iscsi_host_event_code code; uint32_t data_size; - uint8_t data[0]; + uint8_t data[]; } aen; struct { uint32_t status; uint32_t pid; uint32_t data_size; - uint8_t data[0]; + uint8_t data[]; } ping; } u; }; diff --git a/drivers/staging/r8188eu/include/ieee80211.h b/drivers/staging/r8188eu/include/ieee80211.h index bc5b030e9c40..9204dd42f319 100644 --- a/drivers/staging/r8188eu/include/ieee80211.h +++ b/drivers/staging/r8188eu/include/ieee80211.h @@ -185,7 +185,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct { int command; @@ -198,7 +198,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; #ifdef CONFIG_88EU_AP_MODE struct { @@ -210,7 +210,7 @@ struct ieee_param { } add_sta; struct { u8 reserved[2];/* for set max_num_sta */ - u8 buf[0]; + u8 buf[]; } bcn_ie; #endif diff --git a/drivers/staging/rtl8712/ieee80211.h b/drivers/staging/rtl8712/ieee80211.h index 61eff7c5746b..65ceaca9b51e 100644 --- a/drivers/staging/rtl8712/ieee80211.h +++ b/drivers/staging/rtl8712/ieee80211.h @@ -78,7 +78,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct { int command; @@ -91,7 +91,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; } u; }; diff --git a/drivers/staging/rtl8723bs/include/ieee80211.h b/drivers/staging/rtl8723bs/include/ieee80211.h index d6236f5b069d..c11d7e2d2347 100644 --- a/drivers/staging/rtl8723bs/include/ieee80211.h +++ b/drivers/staging/rtl8723bs/include/ieee80211.h @@ -172,7 +172,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct{ int command; @@ -185,7 +185,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; struct { u16 aid; @@ -196,7 +196,7 @@ struct ieee_param { } add_sta; struct { u8 reserved[2];/* for set max_num_sta */ - u8 buf[0]; + u8 buf[]; } bcn_ie; } u; }; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 694264503119..ada3dd79cd08 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1143,7 +1143,7 @@ struct ieee80211_mgmt { __le16 auth_transaction; __le16 status_code; /* possibly followed by Challenge text */ - u8 variable[0]; + u8 variable[]; } __packed auth; struct { __le16 reason_code; @@ -1152,26 +1152,26 @@ struct ieee80211_mgmt { __le16 capab_info; __le16 listen_interval; /* followed by SSID and Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed assoc_req; struct { __le16 capab_info; __le16 status_code; __le16 aid; /* followed by Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed assoc_resp, reassoc_resp; struct { __le16 capab_info; __le16 status_code; - u8 variable[0]; + u8 variable[]; } __packed s1g_assoc_resp, s1g_reassoc_resp; struct { __le16 capab_info; __le16 listen_interval; u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed reassoc_req; struct { __le16 reason_code; @@ -1182,11 +1182,11 @@ struct ieee80211_mgmt { __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params, TIM */ - u8 variable[0]; + u8 variable[]; } __packed beacon; struct { /* only variable items: SSID, Supported rates */ - u8 variable[0]; + DECLARE_FLEX_ARRAY(u8, variable); } __packed probe_req; struct { __le64 timestamp; @@ -1194,7 +1194,7 @@ struct ieee80211_mgmt { __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params */ - u8 variable[0]; + u8 variable[]; } __packed probe_resp; struct { u8 category; @@ -1203,16 +1203,16 @@ struct ieee80211_mgmt { u8 action_code; u8 dialog_token; u8 status_code; - u8 variable[0]; + u8 variable[]; } __packed wme_action; struct{ u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed chan_switch; struct{ u8 action_code; struct ieee80211_ext_chansw_ie data; - u8 variable[0]; + u8 variable[]; } __packed ext_chan_switch; struct{ u8 action_code; @@ -1228,7 +1228,7 @@ struct ieee80211_mgmt { __le16 timeout; __le16 start_seq_num; /* followed by BA Extension */ - u8 variable[0]; + u8 variable[]; } __packed addba_req; struct{ u8 action_code; @@ -1244,11 +1244,11 @@ struct ieee80211_mgmt { } __packed delba; struct { u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed self_prot; struct{ u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed mesh_action; struct { u8 action; @@ -1292,7 +1292,7 @@ struct ieee80211_mgmt { u8 toa[6]; __le16 tod_error; __le16 toa_error; - u8 variable[0]; + u8 variable[]; } __packed ftm; struct { u8 action_code; diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index f880d2831160..e83954c69fff 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[0]; + char name[]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[0]; + char name[]; }; struct dlm_purge_params { -- cgit v1.2.3 From 223f903e9c832699f4e5f422281a60756c1c6cfe Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Oct 2021 09:48:38 -0700 Subject: bpf: Rename BTF_KIND_TAG to BTF_KIND_DECL_TAG Patch set [1] introduced BTF_KIND_TAG to allow tagging declarations for struct/union, struct/union field, var, func and func arguments and these tags will be encoded into dwarf. They are also encoded to btf by llvm for the bpf target. After BTF_KIND_TAG is introduced, we intended to use it for kernel __user attributes. But kernel __user is actually a type attribute. Upstream and internal discussion showed it is not a good idea to mix declaration attribute and type attribute. So we proposed to introduce btf_type_tag as a type attribute and existing btf_tag renamed to btf_decl_tag ([2]). This patch renamed BTF_KIND_TAG to BTF_KIND_DECL_TAG and some other declarations with *_tag to *_decl_tag to make it clear the tag is for declaration. In the future, BTF_KIND_TYPE_TAG might be introduced per [3]. [1] https://lore.kernel.org/bpf/20210914223004.244411-1-yhs@fb.com/ [2] https://reviews.llvm.org/D111588 [3] https://reviews.llvm.org/D111199 Fixes: b5ea834dde6b ("bpf: Support for new btf kind BTF_KIND_TAG") Fixes: 5b84bd10363e ("libbpf: Add support for BTF_KIND_TAG") Fixes: 5c07f2fec003 ("bpftool: Add support for BTF_KIND_TAG") Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211012164838.3345699-1-yhs@fb.com --- Documentation/bpf/btf.rst | 24 ++-- include/uapi/linux/btf.h | 8 +- kernel/bpf/btf.c | 44 +++--- tools/bpf/bpftool/btf.c | 6 +- tools/include/uapi/linux/btf.h | 8 +- tools/lib/bpf/btf.c | 36 ++--- tools/lib/bpf/btf.h | 12 +- tools/lib/bpf/btf_dump.c | 6 +- tools/lib/bpf/libbpf.c | 24 ++-- tools/lib/bpf/libbpf.map | 2 +- tools/lib/bpf/libbpf_internal.h | 4 +- tools/testing/selftests/bpf/README.rst | 4 +- tools/testing/selftests/bpf/btf_helpers.c | 8 +- tools/testing/selftests/bpf/prog_tests/btf.c | 160 ++++++++++----------- tools/testing/selftests/bpf/prog_tests/btf_write.c | 30 ++-- tools/testing/selftests/bpf/progs/tag.c | 6 +- tools/testing/selftests/bpf/test_btf.h | 4 +- 17 files changed, 193 insertions(+), 193 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 1bfe4072f5fc..9e5b4a98af76 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -85,7 +85,7 @@ sequentially and type id is assigned to each recognized type starting from id #define BTF_KIND_VAR 14 /* Variable */ #define BTF_KIND_DATASEC 15 /* Section */ #define BTF_KIND_FLOAT 16 /* Floating point */ - #define BTF_KIND_TAG 17 /* Tag */ + #define BTF_KIND_DECL_TAG 17 /* Decl Tag */ Note that the type section encodes debug info, not just pure types. ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram. @@ -107,7 +107,7 @@ Each type contains the following common data:: * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and TAG. + * FUNC, FUNC_PROTO and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -466,30 +466,30 @@ map definition. No additional type data follow ``btf_type``. -2.2.17 BTF_KIND_TAG -~~~~~~~~~~~~~~~~~~~ +2.2.17 BTF_KIND_DECL_TAG +~~~~~~~~~~~~~~~~~~~~~~~~ ``struct btf_type`` encoding requirement: * ``name_off``: offset to a non-empty string * ``info.kind_flag``: 0 - * ``info.kind``: BTF_KIND_TAG + * ``info.kind``: BTF_KIND_DECL_TAG * ``info.vlen``: 0 * ``type``: ``struct``, ``union``, ``func`` or ``var`` -``btf_type`` is followed by ``struct btf_tag``.:: +``btf_type`` is followed by ``struct btf_decl_tag``.:: - struct btf_tag { + struct btf_decl_tag { __u32 component_idx; }; -The ``name_off`` encodes btf_tag attribute string. +The ``name_off`` encodes btf_decl_tag attribute string. The ``type`` should be ``struct``, ``union``, ``func`` or ``var``. -For ``var`` type, ``btf_tag.component_idx`` must be ``-1``. -For the other three types, if the btf_tag attribute is +For ``var`` type, ``btf_decl_tag.component_idx`` must be ``-1``. +For the other three types, if the btf_decl_tag attribute is applied to the ``struct``, ``union`` or ``func`` itself, -``btf_tag.component_idx`` must be ``-1``. Otherwise, +``btf_decl_tag.component_idx`` must be ``-1``. Otherwise, the attribute is applied to a ``struct``/``union`` member or -a ``func`` argument, and ``btf_tag.component_idx`` should be a +a ``func`` argument, and ``btf_decl_tag.component_idx`` should be a valid index (starting from 0) pointing to a member or an argument. 3. BTF Kernel API diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 642b6ecb37d7..deb12f755f0f 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and TAG. + * FUNC, FUNC_PROTO, VAR and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -74,7 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ - BTF_KIND_TAG = 17, /* Tag */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -174,14 +174,14 @@ struct btf_var_secinfo { __u32 size; }; -/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe * additional information related to the tag applied location. * If component_idx == -1, the tag is applied to a struct, union, * variable or function. Otherwise, it is applied to a struct/union * member or a func argument, and component_idx indicates which member * or argument (0 ... vlen-1). */ -struct btf_tag { +struct btf_decl_tag { __s32 component_idx; }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2ebffb9f57eb..9059053088b9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,7 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -460,12 +460,12 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } -static bool btf_type_is_tag(const struct btf_type *t) +static bool btf_type_is_decl_tag(const struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_TAG; + return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; } -static bool btf_type_is_tag_target(const struct btf_type *t) +static bool btf_type_is_decl_tag_target(const struct btf_type *t) { return btf_type_is_func(t) || btf_type_is_struct(t) || btf_type_is_var(t); @@ -549,7 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || - btf_type_is_tag(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -576,7 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || - btf_type_is_tag(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -630,9 +630,9 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } -static const struct btf_tag *btf_type_tag(const struct btf_type *t) +static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) { - return (const struct btf_tag *)(t + 1); + return (const struct btf_decl_tag *)(t + 1); } static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) @@ -3820,11 +3820,11 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; -static s32 btf_tag_check_meta(struct btf_verifier_env *env, +static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { - const struct btf_tag *tag; + const struct btf_decl_tag *tag; u32 meta_needed = sizeof(*tag); s32 component_idx; const char *value; @@ -3852,7 +3852,7 @@ static s32 btf_tag_check_meta(struct btf_verifier_env *env, return -EINVAL; } - component_idx = btf_type_tag(t)->component_idx; + component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); return -EINVAL; @@ -3863,7 +3863,7 @@ static s32 btf_tag_check_meta(struct btf_verifier_env *env, return meta_needed; } -static int btf_tag_resolve(struct btf_verifier_env *env, +static int btf_decl_tag_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; @@ -3874,7 +3874,7 @@ static int btf_tag_resolve(struct btf_verifier_env *env, u32 vlen; next_type = btf_type_by_id(btf, next_type_id); - if (!next_type || !btf_type_is_tag_target(next_type)) { + if (!next_type || !btf_type_is_decl_tag_target(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } @@ -3883,7 +3883,7 @@ static int btf_tag_resolve(struct btf_verifier_env *env, !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); - component_idx = btf_type_tag(t)->component_idx; + component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx != -1) { if (btf_type_is_var(next_type)) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); @@ -3909,18 +3909,18 @@ static int btf_tag_resolve(struct btf_verifier_env *env, return 0; } -static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type=%u component_idx=%d", t->type, - btf_type_tag(t)->component_idx); + btf_type_decl_tag(t)->component_idx); } -static const struct btf_kind_operations tag_ops = { - .check_meta = btf_tag_check_meta, - .resolve = btf_tag_resolve, +static const struct btf_kind_operations decl_tag_ops = { + .check_meta = btf_decl_tag_check_meta, + .resolve = btf_decl_tag_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, - .log_details = btf_tag_log, + .log_details = btf_decl_tag_log, .show = btf_df_show, }; @@ -4058,7 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, - [BTF_KIND_TAG] = &tag_ops, + [BTF_KIND_DECL_TAG] = &decl_tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4143,7 +4143,7 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); - if (btf_type_is_tag(t)) + if (btf_type_is_decl_tag(t)) return btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 49743ad96851..7b68d4f65fe6 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -37,7 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; struct btf_attach_table { @@ -348,8 +348,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" size=%u", t->size); break; } - case BTF_KIND_TAG: { - const struct btf_tag *tag = (const void *)(t + 1); + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); if (json_output) { jsonw_uint_field(w, "type_id", t->type); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 642b6ecb37d7..deb12f755f0f 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and TAG. + * FUNC, FUNC_PROTO, VAR and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -74,7 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ - BTF_KIND_TAG = 17, /* Tag */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -174,14 +174,14 @@ struct btf_var_secinfo { __u32 size; }; -/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe * additional information related to the tag applied location. * If component_idx == -1, the tag is applied to a struct, union, * variable or function. Otherwise, it is applied to a struct/union * member or a func argument, and component_idx indicates which member * or argument (0 ... vlen-1). */ -struct btf_tag { +struct btf_decl_tag { __s32 component_idx; }; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 60fbd1c6d466..1f6dea11f600 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -309,8 +309,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); - case BTF_KIND_TAG: - return base_size + sizeof(struct btf_tag); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -383,8 +383,8 @@ static int btf_bswap_type_rest(struct btf_type *t) v->size = bswap_32(v->size); } return 0; - case BTF_KIND_TAG: - btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx); + case BTF_KIND_DECL_TAG: + btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx); return 0; default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); @@ -596,7 +596,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -2569,7 +2569,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ } /* - * Append new BTF_KIND_TAG type with: + * Append new BTF_KIND_DECL_TAG type with: * - *value* - non-empty/non-NULL string; * - *ref_type_id* - referenced type ID, it might not exist yet; * - *component_idx* - -1 for tagging reference type, otherwise struct/union @@ -2578,7 +2578,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ * - >0, type ID of newly added BTF type; * - <0, on error. */ -int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx) { struct btf_type *t; @@ -2593,7 +2593,7 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, if (btf_ensure_modifiable(btf)) return libbpf_err(-ENOMEM); - sz = sizeof(struct btf_type) + sizeof(struct btf_tag); + sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag); t = btf_add_type_mem(btf, sz); if (!t) return libbpf_err(-ENOMEM); @@ -2603,9 +2603,9 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, return value_off; t->name_off = value_off; - t->info = btf_type_info(BTF_KIND_TAG, 0, false); + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); t->type = ref_type_id; - btf_tag(t)->component_idx = component_idx; + btf_decl_tag(t)->component_idx = component_idx; return btf_commit_type(btf, sz); } @@ -3427,7 +3427,7 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) } /* Calculate type signature hash of INT or TAG. */ -static long btf_hash_int_tag(struct btf_type *t) +static long btf_hash_int_decl_tag(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); long h; @@ -3705,8 +3705,8 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_common(t); break; case BTF_KIND_INT: - case BTF_KIND_TAG: - h = btf_hash_int_tag(t); + case BTF_KIND_DECL_TAG: + h = btf_hash_int_decl_tag(t); break; case BTF_KIND_ENUM: h = btf_hash_enum(t); @@ -3761,11 +3761,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_FUNC_PROTO: case BTF_KIND_VAR: case BTF_KIND_DATASEC: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: return 0; case BTF_KIND_INT: - h = btf_hash_int_tag(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); @@ -4382,13 +4382,13 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } break; - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); if (ref_type_id < 0) return ref_type_id; t->type = ref_type_id; - h = btf_hash_int_tag(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); @@ -4671,7 +4671,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 864eb51753a1..4011e206e6f7 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -236,7 +236,7 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz); /* tag construction API */ -LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, +LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx); struct btf_dedup_opts { @@ -426,9 +426,9 @@ static inline bool btf_is_float(const struct btf_type *t) return btf_kind(t) == BTF_KIND_FLOAT; } -static inline bool btf_is_tag(const struct btf_type *t) +static inline bool btf_is_decl_tag(const struct btf_type *t) { - return btf_kind(t) == BTF_KIND_TAG; + return btf_kind(t) == BTF_KIND_DECL_TAG; } static inline __u8 btf_int_encoding(const struct btf_type *t) @@ -499,10 +499,10 @@ btf_var_secinfos(const struct btf_type *t) return (struct btf_var_secinfo *)(t + 1); } -struct btf_tag; -static inline struct btf_tag *btf_tag(const struct btf_type *t) +struct btf_decl_tag; +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) { - return (struct btf_tag *)(t + 1); + return (struct btf_decl_tag *)(t + 1); } #ifdef __cplusplus diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index ad6df97295ae..5ef42f0abed1 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -316,7 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: d->type_states[t->type].referenced = 1; break; @@ -584,7 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DATASEC: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: d->type_states[id].order_state = ORDERED; return 0; @@ -2217,7 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: err = btf_dump_unsupported_data(d, t, id); break; case BTF_KIND_INT: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ae0889bebe32..63d738654ff6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -195,8 +195,8 @@ enum kern_feature_id { FEAT_BTF_FLOAT, /* BPF perf link support */ FEAT_PERF_LINK, - /* BTF_KIND_TAG support */ - FEAT_BTF_TAG, + /* BTF_KIND_DECL_TAG support */ + FEAT_BTF_DECL_TAG, __FEAT_CNT, }; @@ -2024,7 +2024,7 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_VAR: return "var"; case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; - case BTF_KIND_TAG: return "tag"; + case BTF_KIND_DECL_TAG: return "decl_tag"; default: return "unknown"; } } @@ -2524,9 +2524,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); - bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); - return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag; + return !has_func || !has_datasec || !has_func_global || !has_float || !has_decl_tag; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2535,15 +2535,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); - bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); struct btf_type *t; int i, j, vlen; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) { - /* replace VAR/TAG with INT */ + if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) { + /* replace VAR/DECL_TAG with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* * using size = 1 is the safest choice, 4 will be too @@ -4248,7 +4248,7 @@ static int probe_kern_btf_float(void) strs, sizeof(strs))); } -static int probe_kern_btf_tag(void) +static int probe_kern_btf_decl_tag(void) { static const char strs[] = "\0tag"; __u32 types[] = { @@ -4258,7 +4258,7 @@ static int probe_kern_btf_tag(void) BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), BTF_VAR_STATIC, /* attr */ - BTF_TYPE_TAG_ENC(1, 2, -1), + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), @@ -4481,8 +4481,8 @@ static struct kern_feature_desc { [FEAT_PERF_LINK] = { "BPF perf link support", probe_perf_link, }, - [FEAT_BTF_TAG] = { - "BTF_KIND_TAG support", probe_kern_btf_tag, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, }, }; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f270d25e4af3..e6fb1ba49369 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -394,5 +394,5 @@ LIBBPF_0.6.0 { bpf_object__prev_map; bpf_object__prev_program; btf__add_btf; - btf__add_tag; + btf__add_decl_tag; } LIBBPF_0.5.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index f7fd3944d46d..f6a5748dd318 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -69,8 +69,8 @@ #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) -#define BTF_TYPE_TAG_ENC(value, type, component_idx) \ - BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 554553acc6d9..5e287e445f75 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -204,7 +204,7 @@ __ https://reviews.llvm.org/D93563 btf_tag test and Clang version ============================== -The btf_tag selftest require LLVM support to recognize the btf_tag attribute. +The btf_tag selftest require LLVM support to recognize the btf_decl_tag attribute. It was introduced in `Clang 14`__. Without it, the btf_tag selftest will be skipped and you will observe: @@ -213,7 +213,7 @@ Without it, the btf_tag selftest will be skipped and you will observe: # btf_tag:SKIP -__ https://reviews.llvm.org/D106614 +__ https://reviews.llvm.org/D111588 Clang dependencies for static linking tests =========================================== diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c index ce103fb0ad1b..668cfa20bb1b 100644 --- a/tools/testing/selftests/bpf/btf_helpers.c +++ b/tools/testing/selftests/bpf/btf_helpers.c @@ -24,12 +24,12 @@ static const char * const btf_kind_str_mapping[] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; static const char *btf_kind_str(__u16 kind) { - if (kind > BTF_KIND_TAG) + if (kind > BTF_KIND_DECL_TAG) return "UNKNOWN"; return btf_kind_str_mapping[kind]; } @@ -178,9 +178,9 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_FLOAT: fprintf(out, " size=%u", t->size); break; - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: fprintf(out, " type_id=%u component_idx=%d", - t->type, btf_tag(t)->component_idx); + t->type, btf_decl_tag(t)->component_idx); break; default: break; diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index acd33d0cd5d9..fa67f25bbef5 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3662,15 +3662,15 @@ static struct btf_raw_test raw_tests[] = { }, { - .descr = "tag test #1, struct/member, well-formed", + .descr = "decl_tag test #1, struct/member, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_STRUCT_ENC(0, 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 32), - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 2, 0), - BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), BTF_END_RAW, }, BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"), @@ -3683,15 +3683,15 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #2, union/member, well-formed", + .descr = "decl_tag test #2, union/member, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_UNION_ENC(NAME_TBD, 2, 4), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 0), - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 2, 0), - BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -3704,13 +3704,13 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #3, variable, well-formed", + .descr = "decl_tag test #3, variable, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ BTF_VAR_ENC(NAME_TBD, 1, 1), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0global\0tag1\0tag2"), @@ -3723,16 +3723,16 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #4, func/parameter, well-formed", + .descr = "decl_tag test #4, func/parameter, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, -1), - BTF_TAG_ENC(NAME_TBD, 3, 0), - BTF_TAG_ENC(NAME_TBD, 3, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 1), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"), @@ -3745,11 +3745,11 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #5, invalid value", + .descr = "decl_tag test #5, invalid value", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TAG_ENC(0, 2, -1), + BTF_DECL_TAG_ENC(0, 2, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag"), @@ -3764,10 +3764,10 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid value", }, { - .descr = "tag test #6, invalid target type", + .descr = "decl_tag test #6, invalid target type", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - BTF_TAG_ENC(NAME_TBD, 1, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 1, -1), BTF_END_RAW, }, BTF_STR_SEC("\0tag1"), @@ -3782,11 +3782,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type", }, { - .descr = "tag test #7, invalid vlen", + .descr = "decl_tag test #7, invalid vlen", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 1), 2), (0), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3801,11 +3801,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "vlen != 0", }, { - .descr = "tag test #8, invalid kflag", + .descr = "decl_tag test #8, invalid kflag", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3820,11 +3820,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid btf_info kind_flag", }, { - .descr = "tag test #9, var, invalid component_idx", + .descr = "decl_tag test #9, var, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag"), @@ -3839,13 +3839,13 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #10, struct member, invalid component_idx", + .descr = "decl_tag test #10, struct member, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_STRUCT_ENC(0, 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 32), - BTF_TAG_ENC(NAME_TBD, 2, 2), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 2), BTF_END_RAW, }, BTF_STR_SEC("\0m1\0m2\0tag"), @@ -3860,14 +3860,14 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #11, func parameter, invalid component_idx", + .descr = "decl_tag test #11, func parameter, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, 2), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 2), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), @@ -3882,14 +3882,14 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #12, < -1 component_idx", + .descr = "decl_tag test #12, < -1 component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, -2), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -2), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), @@ -6672,9 +6672,9 @@ const struct btf_dedup_test dedup_tests[] = { /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ /* tag -> [3] struct s */ - BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ /* tag -> [3] struct s, member 1 */ - BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ /* full copy of the above */ BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [9] */ @@ -6689,8 +6689,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_PTR_ENC(14), /* [13] */ BTF_CONST_ENC(9), /* [14] */ BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [15] */ - BTF_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ - BTF_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ BTF_END_RAW, }, BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"), @@ -6714,8 +6714,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [9] */ BTF_END_RAW, }, @@ -6841,8 +6841,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ - BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ - BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), @@ -6869,8 +6869,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ - BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ - BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), @@ -7036,14 +7036,14 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ /* tag -> t */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ /* tag -> func */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ /* tag -> func arg a1 */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), @@ -7056,9 +7056,9 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), @@ -7084,17 +7084,17 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_ENC(NAME_NTH(3), 4), /* [5] */ /* tag -> f: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ /* tag -> f/a2: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ /* tag -> f: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ - BTF_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ /* tag -> f/a2: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ - BTF_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ BTF_END_RAW, }, BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), @@ -7106,12 +7106,12 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ BTF_END_RAW, }, BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), @@ -7133,17 +7133,17 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), /* tag -> t: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ /* tag -> t/m2: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ /* tag -> t: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ /* tag -> t/m2: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ - BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -7154,12 +7154,12 @@ const struct btf_dedup_test dedup_tests[] = { BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), - BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -7202,8 +7202,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); - case BTF_KIND_TAG: - return base_size + sizeof(struct btf_tag); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index 886e0fc1efb1..b912eeb0b6b4 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -277,26 +277,26 @@ static void gen_btf(struct btf *btf) "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", "raw_dump"); - /* TAG */ - id = btf__add_tag(btf, "tag1", 16, -1); + /* DECL_TAG */ + id = btf__add_decl_tag(btf, "tag1", 16, -1); ASSERT_EQ(id, 18, "tag_id"); t = btf__type_by_id(btf, 18); ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); - ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); ASSERT_EQ(t->type, 16, "tag_type"); - ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, -1, "tag_component_idx"); ASSERT_STREQ(btf_type_raw_dump(btf, 18), - "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); - id = btf__add_tag(btf, "tag2", 14, 1); + id = btf__add_decl_tag(btf, "tag2", 14, 1); ASSERT_EQ(id, 19, "tag_id"); t = btf__type_by_id(btf, 19); ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value"); - ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); ASSERT_EQ(t->type, 14, "tag_type"); - ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, 1, "tag_component_idx"); ASSERT_STREQ(btf_type_raw_dump(btf, 19), - "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); } static void test_btf_add() @@ -336,8 +336,8 @@ static void test_btf_add() "[16] VAR 'var1' type_id=1, linkage=global-alloc", "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", - "[18] TAG 'tag1' type_id=16 component_idx=-1", - "[19] TAG 'tag2' type_id=14 component_idx=1"); + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1"); btf__free(btf); } @@ -389,8 +389,8 @@ static void test_btf_add_btf() "[16] VAR 'var1' type_id=1, linkage=global-alloc", "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", - "[18] TAG 'tag1' type_id=16 component_idx=-1", - "[19] TAG 'tag2' type_id=14 component_idx=1", + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", /* types appended from the second BTF */ "[20] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", @@ -418,8 +418,8 @@ static void test_btf_add_btf() "[35] VAR 'var1' type_id=20, linkage=global-alloc", "[36] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=20 offset=4 size=8", - "[37] TAG 'tag1' type_id=35 component_idx=-1", - "[38] TAG 'tag2' type_id=33 component_idx=1"); + "[37] DECL_TAG 'tag1' type_id=35 component_idx=-1", + "[38] DECL_TAG 'tag2' type_id=33 component_idx=1"); cleanup: btf__free(btf1); diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c index b46b1bfac7da..672d19e7b120 100644 --- a/tools/testing/selftests/bpf/progs/tag.c +++ b/tools/testing/selftests/bpf/progs/tag.c @@ -8,9 +8,9 @@ #define __has_attribute(x) 0 #endif -#if __has_attribute(btf_tag) -#define __tag1 __attribute__((btf_tag("tag1"))) -#define __tag2 __attribute__((btf_tag("tag2"))) +#if __has_attribute(btf_decl_tag) +#define __tag1 __attribute__((btf_decl_tag("tag1"))) +#define __tag2 __attribute__((btf_decl_tag("tag2"))) volatile const bool skip_tests __tag1 __tag2 = false; #else #define __tag1 diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index 0619e06d745e..32c7a57867da 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -69,7 +69,7 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) -#define BTF_TAG_ENC(value, type, component_idx) \ - BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) +#define BTF_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) #endif /* _TEST_BTF_H */ -- cgit v1.2.3 From 6224590d242fc8c6b26941328e02a40b4384949b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 2 Oct 2021 19:36:14 +0100 Subject: io_uring: add flag to not fail link after timeout For some reason non-off IORING_OP_TIMEOUT always fails links, it's pretty inconvenient and unnecessary limits chaining after it to hard linking, which is far from ideal, e.g. doesn't pair well with timeout cancellation. Add a flag forcing it to not fail links on -ETIME. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/17c7ec0fb7a6113cc6be8cdaedcada0ba836ac0e.1633199723.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 8 ++++++-- include/uapi/linux/io_uring.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/fs/io_uring.c b/fs/io_uring.c index 5b3b52815b88..5b3b4f8f9659 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5857,7 +5857,10 @@ err: static void io_req_task_timeout(struct io_kiocb *req, bool *locked) { - req_set_fail(req); + struct io_timeout_data *data = req->async_data; + + if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) + req_set_fail(req); io_req_complete_post(req, -ETIME, 0); } @@ -6063,7 +6066,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK | + IORING_TIMEOUT_ETIME_SUCCESS)) return -EINVAL; /* more than one clock specified is invalid, obviously */ if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b270a07b285e..c45b5e9a9387 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -158,6 +158,7 @@ enum { #define IORING_TIMEOUT_BOOTTIME (1U << 2) #define IORING_TIMEOUT_REALTIME (1U << 3) #define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /* -- cgit v1.2.3 From f4c6217f7f5936f7173d028559ff5d25cce10816 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 6 Oct 2021 19:36:51 +0530 Subject: perf: Add comment about current state of PERF_MEM_LVL_* namespace and remove an extra line Add a comment about PERF_MEM_LVL_* namespace being depricated to some extent in favour of added PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. Remove an extra line present in perf_mem__lvl_scnprintf function. Signed-off-by: Kajol Jain Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211006140654.298352-2-kjain@linux.ibm.com --- include/uapi/linux/perf_event.h | 8 +++++++- tools/include/uapi/linux/perf_event.h | 8 +++++++- tools/perf/util/mem-events.c | 1 - 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c89535de1ec8..a74538c5b4b5 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1256,7 +1256,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a15645..e1701e9c7858 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1241,7 +1241,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index f0e75df72b80..ff7289e28192 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -320,7 +320,6 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - if (mem_info && mem_info->data_src.mem_remote) { strcat(out, "Remote "); l += 7; -- cgit v1.2.3 From fec9cc6175d0ec1e13efe12be491d9bd4de62f80 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 6 Oct 2021 19:36:52 +0530 Subject: perf: Add mem_hops field in perf_mem_data_src structure Going forward, future generation systems can have more hierarchy within the node/package level but currently we don't have any data source encoding field in perf, which can be used to represent this level of data. Add a new field called 'mem_hops' in the perf_mem_data_src structure which can be used to represent intra-node/package or inter-node/off-package details. This field is of size 3 bits where PERF_MEM_HOPS_{NA, 0..6} value can be used to present different hop levels data. Also add corresponding macros to define mem_hop field values and shift value. Currently we define macro for HOPS_0 which corresponds to data coming from another core but same node. For ex: Encodings for mem_hops fields with L2 cache: L2 - local L2 L2 | REMOTE | HOPS_0 - remote core, same node L2 Signed-off-by: Kajol Jain Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211006140654.298352-3-kjain@linux.ibm.com --- include/uapi/linux/perf_event.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index a74538c5b4b5..bd8860eeb291 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1225,14 +1225,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1328,6 +1330,11 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +/* 2-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit v1.2.3 From 0a2b3e363566c4cc8792d37c5e73b9d9295e075c Mon Sep 17 00:00:00 2001 From: Coly Li Date: Wed, 20 Oct 2021 22:38:06 +0800 Subject: bcache: reserve never used bits from bkey.high There sre 3 bits in member high of struct bkey are never used, and no plan to support them in future, - HEADER_SIZE, start at bit 58, length 2 bits - KEY_PINNED, start at bit 55, length 1 bit No any kernel code, or user space tool references or accesses the three bits. Therefore it is possible and feasible to reserve the valuable bits from bkey.high. They can be used in future for other purpose. Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20211020143812.6403-3-colyli@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/bcache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index cf7399f03b71..97413586195b 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -43,9 +43,9 @@ static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ #define KEY_MAX_U64S 8 KEY_FIELD(KEY_PTRS, high, 60, 3) -KEY_FIELD(HEADER_SIZE, high, 58, 2) +KEY_FIELD(__PAD0, high, 58, 2) KEY_FIELD(KEY_CSUM, high, 56, 2) -KEY_FIELD(KEY_PINNED, high, 55, 1) +KEY_FIELD(__PAD1, high, 55, 1) KEY_FIELD(KEY_DIRTY, high, 36, 1) KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) -- cgit v1.2.3 From 7aea2c0b48a568e6732c1d30516febe36bf555f1 Mon Sep 17 00:00:00 2001 From: Michael Tretter Date: Wed, 8 Sep 2021 14:03:15 +0100 Subject: media: allegro: add control to disable encoder buffer The encoder buffer can have a negative impact on the quality of the encoded video. Add a control to allow user space to disable the encoder buffer per channel if the VCU supports the encoder buffer but the quality is not sufficient. Signed-off-by: Michael Tretter Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/allegro-dvt/allegro-core.c | 32 +++++++++++++++++++++-- include/uapi/linux/v4l2-controls.h | 5 ++++ 2 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/media/platform/allegro-dvt/allegro-core.c b/drivers/media/platform/allegro-dvt/allegro-core.c index cb42b6e3d85a..7ec85299d03e 100644 --- a/drivers/media/platform/allegro-dvt/allegro-core.c +++ b/drivers/media/platform/allegro-dvt/allegro-core.c @@ -105,6 +105,12 @@ #define BETA_OFFSET_DIV_2 -1 #define TC_OFFSET_DIV_2 -1 +/* + * This control allows applications to explicitly disable the encoder buffer. + * This value is Allegro specific. + */ +#define V4L2_CID_USER_ALLEGRO_ENCODER_BUFFER (V4L2_CID_USER_ALLEGRO_BASE + 0) + static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Debug level (0-2)"); @@ -275,6 +281,8 @@ struct allegro_channel { struct v4l2_ctrl *mpeg_video_cpb_size; struct v4l2_ctrl *mpeg_video_gop_size; + struct v4l2_ctrl *encoder_buffer; + /* user_id is used to identify the channel during CREATE_CHANNEL */ /* not sure, what to set here and if this is actually required */ int user_id; @@ -1255,7 +1263,7 @@ static int fill_create_channel_param(struct allegro_channel *channel, param->max_transfo_depth_intra = channel->max_transfo_depth_intra; param->max_transfo_depth_inter = channel->max_transfo_depth_inter; - param->encoder_buffer_enabled = channel->dev->has_encoder_buffer; + param->encoder_buffer_enabled = v4l2_ctrl_g_ctrl(channel->encoder_buffer); param->encoder_buffer_offset = 0; param->rate_control_mode = channel->frame_rc_enable ? @@ -1381,7 +1389,7 @@ static int allegro_mcu_send_encode_frame(struct allegro_dev *dev, u64 src_handle) { struct mcu_msg_encode_frame msg; - bool use_encoder_buffer = channel->dev->has_encoder_buffer; + bool use_encoder_buffer = v4l2_ctrl_g_ctrl(channel->encoder_buffer); memset(&msg, 0, sizeof(msg)); @@ -2466,6 +2474,8 @@ static void allegro_destroy_channel(struct allegro_channel *channel) v4l2_ctrl_grab(channel->mpeg_video_cpb_size, false); v4l2_ctrl_grab(channel->mpeg_video_gop_size, false); + v4l2_ctrl_grab(channel->encoder_buffer, false); + if (channel->user_id != -1) { clear_bit(channel->user_id, &dev->channel_user_ids); channel->user_id = -1; @@ -2532,6 +2542,8 @@ static int allegro_create_channel(struct allegro_channel *channel) v4l2_ctrl_grab(channel->mpeg_video_cpb_size, true); v4l2_ctrl_grab(channel->mpeg_video_gop_size, true); + v4l2_ctrl_grab(channel->encoder_buffer, true); + reinit_completion(&channel->completion); allegro_mcu_send_create_channel(dev, channel); timeout = wait_for_completion_timeout(&channel->completion, @@ -2915,6 +2927,10 @@ static int allegro_try_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_VIDEO_BITRATE_MODE: allegro_clamp_bitrate(channel, ctrl); break; + case V4L2_CID_USER_ALLEGRO_ENCODER_BUFFER: + if (!channel->dev->has_encoder_buffer) + ctrl->val = 0; + break; } return 0; @@ -2955,6 +2971,16 @@ static const struct v4l2_ctrl_ops allegro_ctrl_ops = { .s_ctrl = allegro_s_ctrl, }; +static const struct v4l2_ctrl_config allegro_encoder_buffer_ctrl_config = { + .id = V4L2_CID_USER_ALLEGRO_ENCODER_BUFFER, + .name = "Encoder Buffer Enable", + .type = V4L2_CTRL_TYPE_BOOLEAN, + .min = 0, + .max = 1, + .step = 1, + .def = 1, +}; + static int allegro_open(struct file *file) { struct video_device *vdev = video_devdata(file); @@ -3106,6 +3132,8 @@ static int allegro_open(struct file *file) V4L2_CID_MPEG_VIDEO_GOP_SIZE, 0, ALLEGRO_GOP_SIZE_MAX, 1, ALLEGRO_GOP_SIZE_DEFAULT); + channel->encoder_buffer = v4l2_ctrl_new_custom(handler, + &allegro_encoder_buffer_ctrl_config, NULL); v4l2_ctrl_new_std(handler, &allegro_ctrl_ops, V4L2_CID_MIN_BUFFERS_FOR_OUTPUT, diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 133e20444939..5fea5feb0412 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -211,6 +211,11 @@ enum v4l2_colorfx { * We reserve 128 controls for this driver. */ #define V4L2_CID_USER_CCS_BASE (V4L2_CID_USER_BASE + 0x10f0) +/* + * The base for Allegro driver controls. + * We reserve 16 controls for this driver. + */ +#define V4L2_CID_USER_ALLEGRO_BASE (V4L2_CID_USER_BASE + 0x1170) /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls -- cgit v1.2.3 From dfcb63ce1de6b10ba98dee928f9463f37e5a5512 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 19 Oct 2021 19:47:09 +0200 Subject: fq_codel: generalise ce_threshold marking for subset of traffic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit e72aeb9ee0e3 ("fq_codel: implement L4S style ce_threshold_ect1 marking") expanded the ce_threshold feature of FQ-CoDel so it can be applied to a subset of the traffic, using the ECT(1) bit of the ECN field as the classifier. However, hard-coding ECT(1) as the only classifier for this feature seems limiting, so let's expand it to be more general. To this end, change the parameter from a ce_threshold_ect1 boolean, to a one-byte selector/mask pair (ce_threshold_{selector,mask}) which is applied to the whole diffserv/ECN field in the IP header. This makes it possible to classify packets by any value in either the ECN field or the diffserv field. In particular, setting a selector of INET_ECN_ECT_1 and a mask of INET_ECN_MASK corresponds to the functionality before this patch, and a mask of ~INET_ECN_MASK allows using the selector as a straight-forward match against a diffserv code point: # apply ce_threshold to ECT(1) traffic tc qdisc replace dev eth0 root fq_codel ce_threshold 1ms ce_threshold_selector 0x1/0x3 # apply ce_threshold to ECN-capable traffic marked as diffserv AF22 tc qdisc replace dev eth0 root fq_codel ce_threshold 1ms ce_threshold_selector 0x50/0xfc Regardless of the selector chosen, the normal rules for ECN-marking of packets still apply, i.e., the flow must still declare itself ECN-capable by setting one of the bits in the ECN field to get marked at all. v2: - Add tc usage examples to patch description Signed-off-by: Toke Høiland-Jørgensen Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20211019174709.69081-1-toke@redhat.com Signed-off-by: Jakub Kicinski --- include/net/codel.h | 7 +++++-- include/net/codel_impl.h | 14 +++++++------- include/uapi/linux/pkt_sched.h | 3 ++- net/mac80211/sta_info.c | 3 ++- net/sched/sch_fq_codel.c | 13 +++++++++---- 5 files changed, 25 insertions(+), 15 deletions(-) (limited to 'include/uapi') diff --git a/include/net/codel.h b/include/net/codel.h index 5e8b181b76b8..a6c9e34e62b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,7 +102,9 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled - * @ce_threshold_ect1: if ce_threshold only marks ECT(1) packets + * @ce_threshold_selector: apply ce_threshold to packets matching this value + * in the diffserv/ECN byte of the IP header + * @ce_threshold_mask: mask to apply to ce_threshold_selector comparison */ struct codel_params { codel_time_t target; @@ -110,7 +112,8 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; - bool ce_threshold_ect1; + u8 ce_threshold_selector; + u8 ce_threshold_mask; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index 7af2c3eb3c43..137d40d8cbeb 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,7 +54,8 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; - params->ce_threshold_ect1 = false; + params->ce_threshold_mask = 0; + params->ce_threshold_selector = 0; params->ecn = false; } @@ -250,13 +251,12 @@ end: if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { bool set_ce = true; - if (params->ce_threshold_ect1) { - /* Note: if skb_get_dsfield() returns -1, following - * gives INET_ECN_MASK, which is != INET_ECN_ECT_1. - */ - u8 ecn = skb_get_dsfield(skb) & INET_ECN_MASK; + if (params->ce_threshold_mask) { + int dsfield = skb_get_dsfield(skb); - set_ce = (ecn == INET_ECN_ECT_1); + set_ce = (dsfield >= 0 && + (((u8)dsfield & params->ce_threshold_mask) == + params->ce_threshold_selector)); } if (set_ce && INET_ECN_set_ce(skb)) stats->ce_mark++; diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 6be9a84cccfa..f292b467b27f 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -840,7 +840,8 @@ enum { TCA_FQ_CODEL_CE_THRESHOLD, TCA_FQ_CODEL_DROP_BATCH_SIZE, TCA_FQ_CODEL_MEMORY_LIMIT, - TCA_FQ_CODEL_CE_THRESHOLD_ECT1, + TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, + TCA_FQ_CODEL_CE_THRESHOLD_MASK, __TCA_FQ_CODEL_MAX }; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a39830418434..bd52ac3bee90 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -513,7 +513,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->cparams.target = MS2TIME(20); sta->cparams.interval = MS2TIME(100); sta->cparams.ecn = true; - sta->cparams.ce_threshold_ect1 = false; + sta->cparams.ce_threshold_selector = 0; + sta->cparams.ce_threshold_mask = 0; sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 033d65d06eb1..839e1235db05 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -362,7 +362,8 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, - [TCA_FQ_CODEL_CE_THRESHOLD_ECT1] = { .type = NLA_U8 }, + [TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR] = { .type = NLA_U8 }, + [TCA_FQ_CODEL_CE_THRESHOLD_MASK] = { .type = NLA_U8 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, @@ -409,8 +410,10 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } - if (tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]) - q->cparams.ce_threshold_ect1 = !!nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]); + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]) + q->cparams.ce_threshold_selector = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]); + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]) + q->cparams.ce_threshold_mask = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]); if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -552,7 +555,9 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, codel_time_to_us(q->cparams.ce_threshold))) goto nla_put_failure; - if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_ECT1, q->cparams.ce_threshold_ect1)) + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, q->cparams.ce_threshold_selector)) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK, q->cparams.ce_threshold_mask)) goto nla_put_failure; } -- cgit v1.2.3 From 1add667da24273631d4b1f5529789ec5253227f6 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 20 Oct 2021 08:11:47 +0300 Subject: nl80211: vendor-cmd: intel: add more details for IWL_MVM_VENDOR_CMD_HOST_GET_OWNERSHIP Explain more the expected flow for this command. Signed-off-by: Emmanuel Grumbach Link: https://lore.kernel.org/r/20211020051147.29297-1-emmanuel.grumbach@intel.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211-vnd-intel.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211-vnd-intel.h b/include/uapi/linux/nl80211-vnd-intel.h index 0bf177b84fd9..4ed7d0b24512 100644 --- a/include/uapi/linux/nl80211-vnd-intel.h +++ b/include/uapi/linux/nl80211-vnd-intel.h @@ -13,6 +13,35 @@ * enum iwl_mvm_vendor_cmd - supported vendor commands * @IWL_MVM_VENDOR_CMD_GET_CSME_CONN_INFO: reports CSME connection info. * @IWL_MVM_VENDOR_CMD_HOST_GET_OWNERSHIP: asks for ownership on the device. + * This is useful when the CSME firmware owns the device and the kernel + * wants to use it. In case the CSME firmware has no connection active the + * kernel will manage on its own to get ownership of the device. + * When the CSME firmware has an active connection, the user space + * involvement is required. The kernel will assert the RFKILL signal with + * the "device not owned" reason so that nobody can touch the device. Then + * the user space can run the following flow to be able to get connected + * to the very same AP the CSME firmware is currently connected to: + * + * 1) The user space (NetworkManager) boots and sees that the device is + * in RFKILL because the host doesn't own the device + * 2) The user space asks the kernel what AP the CSME firmware is + * connected to (with %IWL_MVM_VENDOR_CMD_GET_CSME_CONN_INFO) + * 3) The user space checks if it has a profile that matches the reply + * from the CSME firmware + * 4) The user space installs a network to the wpa_supplicant with a + * specific BSSID and a specific frequency + * 5) The user space prevents any type of full scan + * 6) The user space asks iwlmei to request ownership on the device (with + * this command) + * 7) iwlmei requests ownership from the CSME firmware + * 8) The CSME firmware grants ownership + * 9) iwlmei tells iwlwifi to lift the RFKILL + * 10) RFKILL OFF is reported to user space + * 11) The host boots the device, loads the firwmare, and connects to a + * specific BSSID without scanning including IP as fast as it can + * 12) The host reports to the CSME firmware that there is a connection + * 13) The TCP connection is preserved and the host has connectivity + * * @IWL_MVM_VENDOR_CMD_ROAMING_FORBIDDEN_EVENT: notifies if roaming is allowed. * It contains a &IWL_MVM_VENDOR_ATTR_ROAMING_FORBIDDEN and a * &IWL_MVM_VENDOR_ATTR_VIF_ADDR attributes. -- cgit v1.2.3 From 63fa04266629b9559d66c4dc18b03e0f9fc04a02 Mon Sep 17 00:00:00 2001 From: Srinivasan Raju Date: Mon, 18 Oct 2021 11:00:54 +0100 Subject: nl80211: Add LC placeholder band definition to nl80211_band Define LC band which is a draft under IEEE 802.11bb. Current NL80211_BAND_LC is a placeholder band and will be more defined IEEE 802.11bb progresses. Signed-off-by: Srinivasan Raju Link: https://lore.kernel.org/r/20211018100143.7565-2-srini.raju@purelifi.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ net/mac80211/mlme.c | 1 + net/mac80211/sta_info.c | 1 + net/mac80211/tx.c | 3 ++- net/wireless/nl80211.c | 1 + net/wireless/util.c | 2 ++ 6 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index eda608b1eb09..6b816ef0155f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4978,6 +4978,7 @@ enum nl80211_txrate_gi { * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 69.12 GHz) * @NL80211_BAND_6GHZ: around 6 GHz band (5.9 - 7.2 GHz) * @NL80211_BAND_S1GHZ: around 900MHz, supported by S1G PHYs + * @NL80211_BAND_LC: light communication band (placeholder) * @NUM_NL80211_BANDS: number of bands, avoid using this in userspace * since newer kernel versions may support more bands */ @@ -4987,6 +4988,7 @@ enum nl80211_band { NL80211_BAND_60GHZ, NL80211_BAND_6GHZ, NL80211_BAND_S1GHZ, + NL80211_BAND_LC, NUM_NL80211_BANDS, }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ac32a1998a7e..16ef7396b6da 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1490,6 +1490,7 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata, fallthrough; case NL80211_BAND_2GHZ: case NL80211_BAND_60GHZ: + case NL80211_BAND_LC: chan_increment = 1; break; case NL80211_BAND_5GHZ: diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2b5acb37587f..36524101d11f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -444,6 +444,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, switch (i) { case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: /* * We use both here, even if we cannot really know for * sure the station will support both, but the only use diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ac9ab007dc6f..5c426b093ee2 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -146,7 +146,8 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, rate = DIV_ROUND_UP(r->bitrate, 1 << shift); switch (sband->band) { - case NL80211_BAND_2GHZ: { + case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: { u32 flag; if (tx->sdata->flags & IEEE80211_SDATA_OPERATING_GMODE) flag = IEEE80211_RATE_MANDATORY_G; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e72efe146d58..81232b73df8f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -866,6 +866,7 @@ nl80211_match_band_rssi_policy[NUM_NL80211_BANDS] = { [NL80211_BAND_5GHZ] = { .type = NLA_S32 }, [NL80211_BAND_6GHZ] = { .type = NLA_S32 }, [NL80211_BAND_60GHZ] = { .type = NLA_S32 }, + [NL80211_BAND_LC] = { .type = NLA_S32 }, }; static const struct nla_policy diff --git a/net/wireless/util.c b/net/wireless/util.c index 18dba3d7c638..2991f711491a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -80,6 +80,7 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) return 0; /* not supported */ switch (band) { case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: if (chan == 14) return MHZ_TO_KHZ(2484); else if (chan < 14) @@ -209,6 +210,7 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) WARN_ON(want); break; case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: want = 7; for (i = 0; i < sband->n_bitrates; i++) { switch (sband->bitrates[i].bitrate) { -- cgit v1.2.3 From f9d366d420af4ce8719c59e60853573c02831f61 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Oct 2021 17:30:39 +0200 Subject: cfg80211: fix kernel-doc for MBSSID EMA The struct member ema_max_profile_periodicity was listed with the wrong name in the kernel-doc, fix that. Link: https://lore.kernel.org/r/20211021173038.18ec2030c66b.Iac731bb299525940948adad2c41f514b7dd81c47@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- include/uapi/linux/nl80211.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 241b29b0796e..7c9d5db4f0e6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5041,7 +5041,7 @@ struct wiphy_iftype_akm_suites { * @mbssid_max_interfaces: maximum number of interfaces supported by the driver * in a multiple BSSID set. This field must be set to a non-zero value * by the driver to advertise MBSSID support. - * @mbssid_max_ema_profile_periodicity: maximum profile periodicity supported by + * @ema_max_profile_periodicity: maximum profile periodicity supported by * the driver. Setting this field to a non-zero value indicates that the * driver supports enhanced multi-BSSID advertisements (EMA AP). */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6b816ef0155f..61cab81e920d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7424,7 +7424,7 @@ enum nl80211_sar_specs_attrs { * @NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY: Used by the kernel * to advertise the maximum profile periodicity supported by the driver * if EMA is enabled. Driver should indicate EMA support to the userspace - * by setting wiphy->mbssid_max_ema_profile_periodicity to + * by setting wiphy->ema_max_profile_periodicity to * a non-zero value. * * @NL80211_MBSSID_CONFIG_ATTR_INDEX: Mandatory parameter to pass the index of @@ -7443,7 +7443,7 @@ enum nl80211_sar_specs_attrs { * * @NL80211_MBSSID_CONFIG_ATTR_EMA: Flag used to enable EMA AP feature. * Setting this flag is permitted only if the driver advertises EMA support - * by setting wiphy->mbssid_max_ema_profile_periodicity to non-zero. + * by setting wiphy->ema_max_profile_periodicity to non-zero. * * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute -- cgit v1.2.3 From c353d7ce76bfbb87a89155616916cea1f0f1e78e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 19 Oct 2021 16:45:00 +0200 Subject: uapi: Add Add a header file providing translation primitives and tables for the conversion of (ASCII) characters to a 14-segments notation, as used by 14-segment alphanumeric displays. This follows the spirit of include/uapi/linux/map_to_7segment.h. Signed-off-by: Geert Uytterhoeven Signed-off-by: Miguel Ojeda --- include/uapi/linux/map_to_14segment.h | 241 ++++++++++++++++++++++++++++++++++ 1 file changed, 241 insertions(+) create mode 100644 include/uapi/linux/map_to_14segment.h (limited to 'include/uapi') diff --git a/include/uapi/linux/map_to_14segment.h b/include/uapi/linux/map_to_14segment.h new file mode 100644 index 000000000000..0346ef76543b --- /dev/null +++ b/include/uapi/linux/map_to_14segment.h @@ -0,0 +1,241 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (C) 2021 Glider bv + * + * Based on include/uapi/linux/map_to_7segment.h: + + * Copyright (c) 2005 Henk Vergonet + */ + +#ifndef MAP_TO_14SEGMENT_H +#define MAP_TO_14SEGMENT_H + +/* This file provides translation primitives and tables for the conversion + * of (ASCII) characters to a 14-segments notation. + * + * The 14 segment's wikipedia notation below is used as standard. + * See: https://en.wikipedia.org/wiki/Fourteen-segment_display + * + * Notation: +---a---+ + * |\ | /| + * f h i j b + * | \|/ | + * +-g1+-g2+ + * | /|\ | + * e k l m c + * |/ | \| + * +---d---+ + * + * Usage: + * + * Register a map variable, and fill it with a character set: + * static SEG14_DEFAULT_MAP(map_seg14); + * + * + * Then use for conversion: + * seg14 = map_to_seg14(&map_seg14, some_char); + * ... + * + * In device drivers it is recommended, if required, to make the char map + * accessible via the sysfs interface using the following scheme: + * + * static ssize_t map_seg14_show(struct device *dev, + * struct device_attribute *attr, char *buf) + * { + * memcpy(buf, &map_seg14, sizeof(map_seg14)); + * return sizeof(map_seg14); + * } + * static ssize_t map_seg14_store(struct device *dev, + * struct device_attribute *attr, + * const char *buf, size_t cnt) + * { + * if (cnt != sizeof(map_seg14)) + * return -EINVAL; + * memcpy(&map_seg14, buf, cnt); + * return cnt; + * } + * static DEVICE_ATTR_RW(map_seg14); + */ +#include +#include + +#include + +#define BIT_SEG14_A 0 +#define BIT_SEG14_B 1 +#define BIT_SEG14_C 2 +#define BIT_SEG14_D 3 +#define BIT_SEG14_E 4 +#define BIT_SEG14_F 5 +#define BIT_SEG14_G1 6 +#define BIT_SEG14_G2 7 +#define BIT_SEG14_H 8 +#define BIT_SEG14_I 9 +#define BIT_SEG14_J 10 +#define BIT_SEG14_K 11 +#define BIT_SEG14_L 12 +#define BIT_SEG14_M 13 +#define BIT_SEG14_RESERVED1 14 +#define BIT_SEG14_RESERVED2 15 + +struct seg14_conversion_map { + __be16 table[128]; +}; + +static __inline__ int map_to_seg14(struct seg14_conversion_map *map, int c) +{ + if (c < 0 || c >= sizeof(map->table) / sizeof(map->table[0])) + return -EINVAL; + + return __be16_to_cpu(map->table[c]); +} + +#define SEG14_CONVERSION_MAP(_name, _map) \ + struct seg14_conversion_map _name = { .table = { _map } } + +/* + * It is recommended to use a facility that allows user space to redefine + * custom character sets for LCD devices. Please use a sysfs interface + * as described above. + */ +#define MAP_TO_SEG14_SYSFS_FILE "map_seg14" + +/******************************************************************************* + * ASCII conversion table + ******************************************************************************/ + +#define _SEG14(sym, a, b, c, d, e, f, g1, g2, h, j, k, l, m, n) \ + __cpu_to_be16( a << BIT_SEG14_A | b << BIT_SEG14_B | \ + c << BIT_SEG14_C | d << BIT_SEG14_D | \ + e << BIT_SEG14_E | f << BIT_SEG14_F | \ + g1 << BIT_SEG14_G1 | g2 << BIT_SEG14_G2 | \ + h << BIT_SEG14_H | j << BIT_SEG14_I | \ + k << BIT_SEG14_J | l << BIT_SEG14_K | \ + m << BIT_SEG14_L | n << BIT_SEG14_M ) + +#define _MAP_0_32_ASCII_SEG14_NON_PRINTABLE \ + 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, + +#define _MAP_33_47_ASCII_SEG14_SYMBOL \ + _SEG14('!', 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('"', 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0), \ + _SEG14('#', 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14('$', 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14('%', 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0), \ + _SEG14('&', 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1), \ + _SEG14('\'',0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0), \ + _SEG14('(', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1), \ + _SEG14(')', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0), \ + _SEG14('*', 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1), \ + _SEG14('+', 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14(',', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0), \ + _SEG14('-', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('.', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('/', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0), + +#define _MAP_48_57_ASCII_SEG14_NUMERIC \ + _SEG14('0', 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0), \ + _SEG14('1', 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0), \ + _SEG14('2', 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('3', 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('4', 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('5', 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('6', 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('7', 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0), \ + _SEG14('8', 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('9', 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0), + +#define _MAP_58_64_ASCII_SEG14_SYMBOL \ + _SEG14(':', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14(';', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0), \ + _SEG14('<', 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1), \ + _SEG14('=', 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('>', 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0), \ + _SEG14('?', 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0), \ + _SEG14('@', 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0), + +#define _MAP_65_90_ASCII_SEG14_ALPHA_UPPER \ + _SEG14('A', 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('B', 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14('C', 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('D', 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('E', 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('F', 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('G', 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('H', 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('I', 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('J', 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('K', 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1), \ + _SEG14('L', 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('M', 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0), \ + _SEG14('N', 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1), \ + _SEG14('O', 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('P', 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('Q', 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('R', 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1), \ + _SEG14('S', 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('T', 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('U', 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('V', 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0), \ + _SEG14('W', 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1), \ + _SEG14('X', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1), \ + _SEG14('Y', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0), \ + _SEG14('Z', 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0), + +#define _MAP_91_96_ASCII_SEG14_SYMBOL \ + _SEG14('[', 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('\\',0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1), \ + _SEG14(']', 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('^', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1), \ + _SEG14('_', 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('`', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0), + +#define _MAP_97_122_ASCII_SEG14_ALPHA_LOWER \ + _SEG14('a', 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('b', 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('c', 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('d', 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0), \ + _SEG14('e', 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0), \ + _SEG14('f', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0), \ + _SEG14('g', 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0), \ + _SEG14('h', 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('i', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('j', 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0), \ + _SEG14('k', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1), \ + _SEG14('l', 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('m', 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0), \ + _SEG14('n', 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('o', 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('p', 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0), \ + _SEG14('q', 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0), \ + _SEG14('r', 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('s', 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1), \ + _SEG14('t', 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('u', 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('v', 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0), \ + _SEG14('w', 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1), \ + _SEG14('x', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1), \ + _SEG14('y', 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0), \ + _SEG14('z', 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0), + +#define _MAP_123_126_ASCII_SEG14_SYMBOL \ + _SEG14('{', 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0), \ + _SEG14('|', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('}', 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1), \ + _SEG14('~', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0), + +/* Maps */ +#define MAP_ASCII14SEG_ALPHANUM \ + _MAP_0_32_ASCII_SEG14_NON_PRINTABLE \ + _MAP_33_47_ASCII_SEG14_SYMBOL \ + _MAP_48_57_ASCII_SEG14_NUMERIC \ + _MAP_58_64_ASCII_SEG14_SYMBOL \ + _MAP_65_90_ASCII_SEG14_ALPHA_UPPER \ + _MAP_91_96_ASCII_SEG14_SYMBOL \ + _MAP_97_122_ASCII_SEG14_ALPHA_LOWER \ + _MAP_123_126_ASCII_SEG14_SYMBOL + +#define SEG14_DEFAULT_MAP(_name) \ + SEG14_CONVERSION_MAP(_name, MAP_ASCII14SEG_ALPHANUM) + +#endif /* MAP_TO_14SEGMENT_H */ -- cgit v1.2.3 From 9eeb3aa33ae005526f672b394c1791578463513f Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Thu, 21 Oct 2021 21:47:51 +0800 Subject: bpf: Add bpf_skc_to_unix_sock() helper The helper is used in tracing programs to cast a socket pointer to a unix_sock pointer. The return value could be NULL if the casting is illegal. Suggested-by: Yonghong Song Signed-off-by: Hengqi Chen Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211021134752.1223426-2-hengqi.chen@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 7 +++++++ kernel/trace/bpf_trace.c | 2 ++ net/core/filter.c | 23 +++++++++++++++++++++++ scripts/bpf_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 7 +++++++ 6 files changed, 42 insertions(+) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d604c8251d88..be3102b4554b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2093,6 +2093,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6b3153841a33..cbcd0d6fca7c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1608,6 +1608,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; + case BPF_FUNC_skc_to_unix_sock: + return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/filter.c b/net/core/filter.c index 4bace37a6a44..8e8d3b49c297 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10723,6 +10723,26 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; +BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) +{ + /* unix_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct unix_sock); + if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { + .func = bpf_skc_to_unix_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], +}; + BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); @@ -10762,6 +10782,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; + case BPF_FUNC_skc_to_unix_sock: + func = &bpf_skc_to_unix_sock_proto; + break; default: return bpf_base_func_proto(func_id); } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 00ac7b79cddb..a6403ddf5de7 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -537,6 +537,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct __sk_buff', @@ -589,6 +590,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct path', 'struct btf_ptr', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From aba64c7da98330141dcdadd5612f088043a83696 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Wed, 20 Oct 2021 00:48:17 -0700 Subject: bpf: Add verified_insns to bpf_prog_info and fdinfo This stat is currently printed in the verifier log and not stored anywhere. To ease consumption of this data, add a field to bpf_prog_aux so it can be exposed via BPF_OBJ_GET_INFO_BY_FD and fdinfo. Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20211020074818.1017682-2-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 8 ++++++-- kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be3102b4554b..31421c74ba08 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -887,6 +887,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ + u32 verified_insns; struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e50c0bfdb7d..5beb321b3b3b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1848,7 +1848,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" - "recursion_misses:\t%llu\n", + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, @@ -1856,7 +1857,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) prog->aux->id, stats.nsecs, stats.cnt, - stats.misses); + stats.misses, + prog->aux->verified_insns); } #endif @@ -3625,6 +3627,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; + info.verified_insns = prog->aux->verified_insns; + if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 21cdff35a2f9..c6616e325803 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14033,6 +14033,7 @@ skip_full_check: env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); + env->prog->aux->verified_insns = env->insn_processed; if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From 63dfe0709643528290c8a6825f278eda0e3f3c2e Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:32 +0900 Subject: can: bittiming: allow TDC{V,O} to be zero and add can_tdc_const::tdc{v,o,f}_min ISO 11898-1 specifies in section 11.3.3 "Transmitter delay compensation" that "the configuration range for [the] SSP position shall be at least 0 to 63 minimum time quanta." Because SSP = TDCV + TDCO, it means that we should allow both TDCV and TDCO to hold zero value in order to honor SSP's minimum possible value. However, current implementation assigned special meaning to TDCV and TDCO's zero values: * TDCV = 0 -> TDCV is automatically measured by the transceiver. * TDCO = 0 -> TDC is off. In order to allow for those values to really be zero and to maintain current features, we introduce two new flags: * CAN_CTRLMODE_TDC_AUTO indicates that the controller support automatic measurement of TDCV. * CAN_CTRLMODE_TDC_MANUAL indicates that the controller support manual configuration of TDCV. N.B.: current implementation failed to provide an option for the driver to indicate that only manual mode was supported. TDC is disabled if both CAN_CTRLMODE_TDC_AUTO and CAN_CTRLMODE_TDC_MANUAL flags are off, c.f. the helper function can_tdc_is_enabled() which is also introduced in this patch. Also, this patch adds three fields: tdcv_min, tdco_min and tdcf_min to struct can_tdc_const. While we are not convinced that those three fields could be anything else than zero, we can imagine that some controllers might specify a lower bound on these. Thus, those minimums are really added "just in case". Comments of struct can_tdc and can_tdc_const are updated accordingly. Finally, the changes are applied to the etas_es58x driver. Link: https://lore.kernel.org/all/20210918095637.20108-2-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/bittiming.c | 10 +++-- drivers/net/can/usb/etas_es58x/es58x_fd.c | 7 +++- include/linux/can/bittiming.h | 64 +++++++++++++++++++++++-------- include/linux/can/dev.h | 4 ++ include/uapi/linux/can/netlink.h | 2 + 5 files changed, 65 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index b1b5a82f0829..9dda44c0ae9d 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -182,9 +182,12 @@ void can_calc_tdco(struct net_device *dev) struct can_tdc *tdc = &priv->tdc; const struct can_tdc_const *tdc_const = priv->tdc_const; - if (!tdc_const) + if (!tdc_const || + !(priv->ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO)) return; + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + /* As specified in ISO 11898-1 section 11.3.3 "Transmitter * delay compensation" (TDC) is only applicable if data BRP is * one or two. @@ -193,9 +196,10 @@ void can_calc_tdco(struct net_device *dev) /* Reuse "normal" sample point and convert it to time quanta */ u32 sample_point_in_tq = can_bit_time(dbt) * dbt->sample_point / 1000; + if (sample_point_in_tq < tdc_const->tdco_min) + return; tdc->tdco = min(sample_point_in_tq, tdc_const->tdco_max); - } else { - tdc->tdco = 0; + priv->ctrlmode |= CAN_CTRLMODE_TDC_AUTO; } } #endif /* CONFIG_CAN_CALC_BITTIMING */ diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index af042aa55f59..4f0cae29f4d8 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -428,7 +428,7 @@ static int es58x_fd_enable_channel(struct es58x_priv *priv) es58x_fd_convert_bittiming(&tx_conf_msg.data_bittiming, &priv->can.data_bittiming); - if (priv->can.tdc.tdco) { + if (can_tdc_is_enabled(&priv->can)) { tx_conf_msg.tdc_enabled = 1; tx_conf_msg.tdco = cpu_to_le16(priv->can.tdc.tdco); tx_conf_msg.tdcf = cpu_to_le16(priv->can.tdc.tdcf); @@ -505,8 +505,11 @@ static const struct can_bittiming_const es58x_fd_data_bittiming_const = { * Register" from Microchip. */ static const struct can_tdc_const es58x_tdc_const = { + .tdcv_min = 0, .tdcv_max = 0, /* Manual mode not supported. */ + .tdco_min = 0, .tdco_max = 127, + .tdcf_min = 0, .tdcf_max = 127 }; @@ -523,7 +526,7 @@ const struct es58x_parameters es58x_fd_param = { .clock = {.freq = 80 * CAN_MHZ}, .ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC, + CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO, .tx_start_of_frame = 0xCEFA, /* FACE in little endian */ .rx_start_of_frame = 0xFECA, /* CAFE in little endian */ .tx_urb_cmd_max_len = ES58X_FD_TX_URB_CMD_MAX_LEN, diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 9de6e9053e34..9e20260611cc 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -19,6 +19,9 @@ /* Megahertz */ #define CAN_MHZ 1000000UL +#define CAN_CTRLMODE_TDC_MASK \ + (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) + /* * struct can_tdc - CAN FD Transmission Delay Compensation parameters * @@ -33,29 +36,43 @@ * * This structure contains the parameters to calculate that SSP. * - * @tdcv: Transmitter Delay Compensation Value. Distance, in time - * quanta, from when the bit is sent on the TX pin to when it is - * received on the RX pin of the transmitter. Possible options: + * -+----------- one bit ----------+-- TX pin + * |<--- Sample Point --->| + * + * --+----------- one bit ----------+-- RX pin + * |<-------- TDCV -------->| + * |<------- TDCO ------->| + * |<----------- Secondary Sample Point ---------->| + * + * @tdcv: Transmitter Delay Compensation Value. The time needed for + * the signal to propagate, i.e. the distance, in time quanta, + * from the start of the bit on the TX pin to when it is received + * on the RX pin. @tdcv depends on the controller modes: + * + * CAN_CTRLMODE_TDC_AUTO is set: The transceiver dynamically + * measures @tdcv for each transmitted CAN FD frame and the + * value provided here should be ignored. * - * 0: automatic mode. The controller dynamically measures @tdcv - * for each transmitted CAN FD frame. + * CAN_CTRLMODE_TDC_MANUAL is set: use the fixed provided @tdcv + * value. * - * Other values: manual mode. Use the fixed provided value. + * N.B. CAN_CTRLMODE_TDC_AUTO and CAN_CTRLMODE_TDC_MANUAL are + * mutually exclusive. Only one can be set at a time. If both + * CAN_TDC_CTRLMODE_AUTO and CAN_TDC_CTRLMODE_MANUAL are unset, + * TDC is disabled and all the values of this structure should be + * ignored. * * @tdco: Transmitter Delay Compensation Offset. Offset value, in time * quanta, defining the distance between the start of the bit * reception on the RX pin of the transceiver and the SSP * position such that SSP = @tdcv + @tdco. * - * If @tdco is zero, then TDC is disabled and both @tdcv and - * @tdcf should be ignored. - * * @tdcf: Transmitter Delay Compensation Filter window. Defines the - * minimum value for the SSP position in time quanta. If SSP is - * less than @tdcf, then no delay compensations occur and the - * normal sampling point is used instead. The feature is enabled - * if and only if @tdcv is set to zero (automatic mode) and @tdcf - * is configured to a value greater than @tdco. + * minimum value for the SSP position in time quanta. If the SSP + * position is less than @tdcf, then no delay compensations occur + * and the normal sampling point is used instead. The feature is + * enabled if and only if @tdcv is set to zero (automatic mode) + * and @tdcf is configured to a value greater than @tdco. */ struct can_tdc { u32 tdcv; @@ -67,19 +84,32 @@ struct can_tdc { * struct can_tdc_const - CAN hardware-dependent constant for * Transmission Delay Compensation * - * @tdcv_max: Transmitter Delay Compensation Value maximum value. - * Should be set to zero if the controller does not support - * manual mode for tdcv. + * @tdcv_min: Transmitter Delay Compensation Value minimum value. If + * the controller does not support manual mode for tdcv + * (c.f. flag CAN_CTRLMODE_TDC_MANUAL) then this value is + * ignored. + * @tdcv_max: Transmitter Delay Compensation Value maximum value. If + * the controller does not support manual mode for tdcv + * (c.f. flag CAN_CTRLMODE_TDC_MANUAL) then this value is + * ignored. + * + * @tdco_min: Transmitter Delay Compensation Offset minimum value. * @tdco_max: Transmitter Delay Compensation Offset maximum value. * Should not be zero. If the controller does not support TDC, * then the pointer to this structure should be NULL. + * + * @tdcf_min: Transmitter Delay Compensation Filter window minimum + * value. If @tdcf_max is zero, this value is ignored. * @tdcf_max: Transmitter Delay Compensation Filter window maximum * value. Should be set to zero if the controller does not * support this feature. */ struct can_tdc_const { + u32 tdcv_min; u32 tdcv_max; + u32 tdco_min; u32 tdco_max; + u32 tdcf_min; u32 tdcf_max; }; diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 2413253e54c7..6dacbbb41e68 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -96,6 +96,10 @@ struct can_priv { #endif }; +static inline bool can_tdc_is_enabled(const struct can_priv *priv) +{ + return !!(priv->ctrlmode & CAN_CTRLMODE_TDC_MASK); +} /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index f730d443b918..004cd09a7d49 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -101,6 +101,8 @@ struct can_ctrlmode { #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ #define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ #define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */ +#define CAN_CTRLMODE_TDC_AUTO 0x200 /* CAN transiver automatically calculates TDCV */ +#define CAN_CTRLMODE_TDC_MANUAL 0x400 /* TDCV is manually set up by user */ /* * CAN device statistics -- cgit v1.2.3 From d99755f71a80df33b981484f0d3bb956ed15a247 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:35 +0900 Subject: can: netlink: add interface for CAN-FD Transmitter Delay Compensation (TDC) Add the netlink interface for TDC parameters of struct can_tdc_const and can_tdc. Contrary to the can_bittiming(_const) structures for which there is just a single IFLA_CAN(_DATA)_BITTMING(_CONST) entry per structure, here, we create a nested entry IFLA_CAN_TDC. Within this nested entry, additional IFLA_CAN_TDC_TDC* entries are added for each of the TDC parameters of the newly introduced struct can_tdc_const and struct can_tdc. For struct can_tdc_const, these are: IFLA_CAN_TDC_TDCV_MIN IFLA_CAN_TDC_TDCV_MAX IFLA_CAN_TDC_TDCO_MIN IFLA_CAN_TDC_TDCO_MAX IFLA_CAN_TDC_TDCF_MIN IFLA_CAN_TDC_TDCF_MAX For struct can_tdc, these are: IFLA_CAN_TDC_TDCV IFLA_CAN_TDC_TDCO IFLA_CAN_TDC_TDCF This is done so that changes can be applied in the future to the structures without breaking the netlink interface. The TDC netlink logic works as follow: * CAN_CTRLMODE_FD is not provided: - if any TDC parameters are provided: error. - TDC parameters not provided: TDC parameters unchanged. * CAN_CTRLMODE_FD is provided and is false: - TDC is deactivated: both the structure and the CAN_CTRLMODE_TDC_{AUTO,MANUAL} flags are flushed. * CAN_CTRLMODE_FD provided and is true: - CAN_CTRLMODE_TDC_{AUTO,MANUAL} and tdc{v,o,f} not provided: call can_calc_tdco() to automatically decide whether TDC should be activated and, if so, set CAN_CTRLMODE_TDC_AUTO and uses the calculated tdco value. - CAN_CTRLMODE_TDC_AUTO and tdco provided: set CAN_CTRLMODE_TDC_AUTO and use the provided tdco value. Here, tdcv is illegal and tdcf is optional. - CAN_CTRLMODE_TDC_MANUAL and both of tdcv and tdco provided: set CAN_CTRLMODE_TDC_MANUAL and use the provided tdcv and tdco value. Here, tdcf is optional. - CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually exclusive. Whenever one flag is turned on, the other will automatically be turned off. Providing both returns an error. - Combination other than the one listed above are illegal and will return an error. N.B. above rules mean that whenever CAN_CTRLMODE_FD is provided, the previous TDC values will be overwritten. The only option to reuse previous TDC value is to not provide CAN_CTRLMODE_FD. All the new parameters are defined as u32. This arbitrary choice is done to mimic the other bittiming values with are also all of type u32. An u16 would have been sufficient to hold the TDC values. This patch completes below series (c.f. [1]): - commit 289ea9e4ae59 ("can: add new CAN FD bittiming parameters: Transmitter Delay Compensation (TDC)") - commit c25cc7993243 ("can: bittiming: add calculation for CAN FD Transmitter Delay Compensation (TDC)") [1] https://lore.kernel.org/linux-can/20210224002008.4158-1-mailhol.vincent@wanadoo.fr/T/#t Link: https://lore.kernel.org/all/20210918095637.20108-5-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/netlink.c | 213 ++++++++++++++++++++++++++++++++++++++- include/uapi/linux/can/netlink.h | 29 +++++- 2 files changed, 235 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index e79c9a2ffbfc..c77cc6ae88b6 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -2,6 +2,7 @@ /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger + * Copyright (C) 2021 Vincent Mailhol */ #include @@ -19,6 +20,19 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { [IFLA_CAN_DATA_BITTIMING] = { .len = sizeof(struct can_bittiming) }, [IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, + [IFLA_CAN_TDC] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { + [IFLA_CAN_TDC_TDCV_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCV_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCO_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCO_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCF_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCF_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCV] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCO] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCF] = { .type = NLA_U32 }, }; static int can_validate(struct nlattr *tb[], struct nlattr *data[], @@ -30,6 +44,7 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], * - nominal/arbitration bittiming * - data bittiming * - control mode with CAN_CTRLMODE_FD set + * - TDC parameters are coherent (details below) */ if (!data) @@ -37,8 +52,43 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); + u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK; is_can_fd = cm->flags & cm->mask & CAN_CTRLMODE_FD; + + /* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually exclusive */ + if (tdc_flags == CAN_CTRLMODE_TDC_MASK) + return -EOPNOTSUPP; + /* If one of the CAN_CTRLMODE_TDC_* flag is set then + * TDC must be set and vice-versa + */ + if (!!tdc_flags != !!data[IFLA_CAN_TDC]) + return -EOPNOTSUPP; + /* If providing TDC parameters, at least TDCO is + * needed. TDCV is needed if and only if + * CAN_CTRLMODE_TDC_MANUAL is set + */ + if (data[IFLA_CAN_TDC]) { + struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; + int err; + + err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, + data[IFLA_CAN_TDC], + can_tdc_policy, extack); + if (err) + return err; + + if (tb_tdc[IFLA_CAN_TDC_TDCV]) { + if (tdc_flags & CAN_CTRLMODE_TDC_AUTO) + return -EOPNOTSUPP; + } else { + if (tdc_flags & CAN_CTRLMODE_TDC_MANUAL) + return -EOPNOTSUPP; + } + + if (!tb_tdc[IFLA_CAN_TDC_TDCO]) + return -EOPNOTSUPP; + } } if (is_can_fd) { @@ -46,7 +96,7 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], return -EOPNOTSUPP; } - if (data[IFLA_CAN_DATA_BITTIMING]) { + if (data[IFLA_CAN_DATA_BITTIMING] || data[IFLA_CAN_TDC]) { if (!is_can_fd) return -EOPNOTSUPP; } @@ -54,11 +104,60 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; + struct can_tdc tdc = { 0 }; + const struct can_tdc_const *tdc_const = priv->tdc_const; + int err; + + if (!tdc_const || !can_tdc_is_enabled(priv)) + return -EOPNOTSUPP; + + err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, nla, + can_tdc_policy, extack); + if (err) + return err; + + if (tb_tdc[IFLA_CAN_TDC_TDCV]) { + u32 tdcv = nla_get_u32(tb_tdc[IFLA_CAN_TDC_TDCV]); + + if (tdcv < tdc_const->tdcv_min || tdcv > tdc_const->tdcv_max) + return -EINVAL; + + tdc.tdcv = tdcv; + } + + if (tb_tdc[IFLA_CAN_TDC_TDCO]) { + u32 tdco = nla_get_u32(tb_tdc[IFLA_CAN_TDC_TDCO]); + + if (tdco < tdc_const->tdco_min || tdco > tdc_const->tdco_max) + return -EINVAL; + + tdc.tdco = tdco; + } + + if (tb_tdc[IFLA_CAN_TDC_TDCF]) { + u32 tdcf = nla_get_u32(tb_tdc[IFLA_CAN_TDC_TDCF]); + + if (tdcf < tdc_const->tdcf_min || tdcf > tdc_const->tdcf_max) + return -EINVAL; + + tdc.tdcf = tdcf; + } + + priv->tdc = tdc; + + return 0; +} + static int can_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct can_priv *priv = netdev_priv(dev); + u32 tdc_mask = 0; int err; /* We need synchronization with dev->stop() */ @@ -138,7 +237,16 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], dev->mtu = CAN_MTU; memset(&priv->data_bittiming, 0, sizeof(priv->data_bittiming)); + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + memset(&priv->tdc, 0, sizeof(priv->tdc)); } + + tdc_mask = cm->mask & CAN_CTRLMODE_TDC_MASK; + /* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually + * exclusive: make sure to turn the other one off + */ + if (tdc_mask) + priv->ctrlmode &= cm->flags | ~CAN_CTRLMODE_TDC_MASK; } if (data[IFLA_CAN_RESTART_MS]) { @@ -187,10 +295,26 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], return -EINVAL; } - memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); + memset(&priv->tdc, 0, sizeof(priv->tdc)); + if (data[IFLA_CAN_TDC]) { + /* TDC parameters are provided: use them */ + err = can_tdc_changelink(priv, data[IFLA_CAN_TDC], + extack); + if (err) { + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + return err; + } + } else if (!tdc_mask) { + /* Neither of TDC parameters nor TDC flags are + * provided: do calculation + */ + can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + &priv->ctrlmode, priv->ctrlmode_supported); + } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly + * turned off. TDC is disabled: do nothing + */ - can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, - &priv->ctrlmode, priv->ctrlmode_supported); + memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); if (priv->do_set_data_bittiming) { /* Finally, set the bit-timing registers */ @@ -227,6 +351,37 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } +static size_t can_tdc_get_size(const struct net_device *dev) +{ + struct can_priv *priv = netdev_priv(dev); + size_t size; + + if (!priv->tdc_const) + return 0; + + size = nla_total_size(0); /* nest IFLA_CAN_TDC */ + if (priv->ctrlmode_supported & CAN_CTRLMODE_TDC_MANUAL) { + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV_MAX */ + } + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO_MAX */ + if (priv->tdc_const->tdcf_max) { + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCF_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCF_MAX */ + } + + if (can_tdc_is_enabled(priv)) { + if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL) + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO */ + if (priv->tdc_const->tdcf_max) + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCF */ + } + + return size; +} + static size_t can_get_size(const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -258,10 +413,56 @@ static size_t can_get_size(const struct net_device *dev) size += nla_total_size(sizeof(*priv->data_bitrate_const) * priv->data_bitrate_const_cnt); size += sizeof(priv->bitrate_max); /* IFLA_CAN_BITRATE_MAX */ + size += can_tdc_get_size(dev); /* IFLA_CAN_TDC */ return size; } +static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct nlattr *nest; + struct can_priv *priv = netdev_priv(dev); + struct can_tdc *tdc = &priv->tdc; + const struct can_tdc_const *tdc_const = priv->tdc_const; + + if (!tdc_const) + return 0; + + nest = nla_nest_start(skb, IFLA_CAN_TDC); + if (!nest) + return -EMSGSIZE; + + if (priv->ctrlmode_supported & CAN_CTRLMODE_TDC_MANUAL && + (nla_put_u32(skb, IFLA_CAN_TDC_TDCV_MIN, tdc_const->tdcv_min) || + nla_put_u32(skb, IFLA_CAN_TDC_TDCV_MAX, tdc_const->tdcv_max))) + goto err_cancel; + if (nla_put_u32(skb, IFLA_CAN_TDC_TDCO_MIN, tdc_const->tdco_min) || + nla_put_u32(skb, IFLA_CAN_TDC_TDCO_MAX, tdc_const->tdco_max)) + goto err_cancel; + if (tdc_const->tdcf_max && + (nla_put_u32(skb, IFLA_CAN_TDC_TDCF_MIN, tdc_const->tdcf_min) || + nla_put_u32(skb, IFLA_CAN_TDC_TDCF_MAX, tdc_const->tdcf_max))) + goto err_cancel; + + if (can_tdc_is_enabled(priv)) { + if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL && + nla_put_u32(skb, IFLA_CAN_TDC_TDCV, tdc->tdcv)) + goto err_cancel; + if (nla_put_u32(skb, IFLA_CAN_TDC_TDCO, tdc->tdco)) + goto err_cancel; + if (tdc_const->tdcf_max && + nla_put_u32(skb, IFLA_CAN_TDC_TDCF, tdc->tdcf)) + goto err_cancel; + } + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -319,7 +520,9 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) (nla_put(skb, IFLA_CAN_BITRATE_MAX, sizeof(priv->bitrate_max), - &priv->bitrate_max)) + &priv->bitrate_max)) || + + (can_tdc_fill_info(skb, dev)) ) return -EMSGSIZE; diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 004cd09a7d49..75b85c60efb2 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -136,10 +136,35 @@ enum { IFLA_CAN_BITRATE_CONST, IFLA_CAN_DATA_BITRATE_CONST, IFLA_CAN_BITRATE_MAX, - __IFLA_CAN_MAX + IFLA_CAN_TDC, + + /* add new constants above here */ + __IFLA_CAN_MAX, + IFLA_CAN_MAX = __IFLA_CAN_MAX - 1 }; -#define IFLA_CAN_MAX (__IFLA_CAN_MAX - 1) +/* + * CAN FD Transmitter Delay Compensation (TDC) + * + * Please refer to struct can_tdc_const and can_tdc in + * include/linux/can/bittiming.h for further details. + */ +enum { + IFLA_CAN_TDC_UNSPEC, + IFLA_CAN_TDC_TDCV_MIN, /* u32 */ + IFLA_CAN_TDC_TDCV_MAX, /* u32 */ + IFLA_CAN_TDC_TDCO_MIN, /* u32 */ + IFLA_CAN_TDC_TDCO_MAX, /* u32 */ + IFLA_CAN_TDC_TDCF_MIN, /* u32 */ + IFLA_CAN_TDC_TDCF_MAX, /* u32 */ + IFLA_CAN_TDC_TDCV, /* u32 */ + IFLA_CAN_TDC_TDCO, /* u32 */ + IFLA_CAN_TDC_TDCF, /* u32 */ + + /* add new constants above here */ + __IFLA_CAN_TDC, + IFLA_CAN_TDC_MAX = __IFLA_CAN_TDC - 1 +}; /* u16 termination range: 1..65535 Ohms */ #define CAN_TERMINATION_DISABLED 0 -- cgit v1.2.3 From a9d496d8e08ca1eb43d14cb734839b24ab0e8083 Mon Sep 17 00:00:00 2001 From: David Edmondson Date: Mon, 20 Sep 2021 11:37:34 +0100 Subject: KVM: x86: Clarify the kvm_run.emulation_failure structure layout Until more flags for kvm_run.emulation_failure flags are defined, it is undetermined whether new payload elements corresponding to those flags will be additive or alternative. As a hint to userspace that an alternative is possible, wrap the current payload elements in a union. Suggested-by: Sean Christopherson Signed-off-by: David Edmondson Reviewed-by: Sean Christopherson Message-Id: <20210920103737.2696756-2-david.edmondson@oracle.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5ca5ffe16cb4..2c8aa8d4dac1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -403,8 +403,12 @@ struct kvm_run { __u32 suberror; __u32 ndata; __u64 flags; - __u8 insn_size; - __u8 insn_bytes[15]; + union { + struct { + __u8 insn_size; + __u8 insn_bytes[15]; + }; + }; } emulation_failure; /* KVM_EXIT_OSI */ struct { -- cgit v1.2.3 From e615e355894e619785af81479ad6f5a05a8a2e3f Mon Sep 17 00:00:00 2001 From: David Edmondson Date: Mon, 20 Sep 2021 11:37:36 +0100 Subject: KVM: x86: On emulation failure, convey the exit reason, etc. to userspace Should instruction emulation fail, include the VM exit reason, etc. in the emulation_failure data passed to userspace, in order that the VMM can report it as a debugging aid when describing the failure. Suggested-by: Joao Martins Signed-off-by: David Edmondson Reviewed-by: Sean Christopherson Message-Id: <20210920103737.2696756-4-david.edmondson@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 ++ arch/x86/kvm/vmx/vmx.c | 5 +-- arch/x86/kvm/x86.c | 73 +++++++++++++++++++++++++++++++++-------- include/uapi/linux/kvm.h | 6 ++++ 4 files changed, 69 insertions(+), 18 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0b8a9ea7a47b..88fce6ab4bbd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1667,6 +1667,9 @@ extern u64 kvm_mce_cap_supported; int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, + u64 *data, u8 ndata); +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 85ce11dac8fd..71f54d85f104 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5408,10 +5408,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vmx->emulation_required && !vmx->rmode.vm86_active && vcpu->arch.exception.pending) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0377e61b8fc0..ac83d873d65b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7664,29 +7664,78 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); -static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata, u8 *insn_bytes, u8 insn_size) { - struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - u32 insn_size = ctxt->fetch.end - ctxt->fetch.data; struct kvm_run *run = vcpu->run; + u64 info[5]; + u8 info_start; + + /* + * Zero the whole array used to retrieve the exit info, as casting to + * u32 for select entries will leave some chunks uninitialized. + */ + memset(&info, 0, sizeof(info)); + + static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1], + &info[2], (u32 *)&info[3], + (u32 *)&info[4]); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; - run->emulation_failure.ndata = 0; + + /* + * There's currently space for 13 entries, but 5 are used for the exit + * reason and info. Restrict to 4 to reduce the maintenance burden + * when expanding kvm_run.emulation_failure in the future. + */ + if (WARN_ON_ONCE(ndata > 4)) + ndata = 4; + + /* Always include the flags as a 'data' entry. */ + info_start = 1; run->emulation_failure.flags = 0; if (insn_size) { - run->emulation_failure.ndata = 3; + BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) + + sizeof(run->emulation_failure.insn_bytes) != 16)); + info_start += 2; run->emulation_failure.flags |= KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; run->emulation_failure.insn_size = insn_size; memset(run->emulation_failure.insn_bytes, 0x90, sizeof(run->emulation_failure.insn_bytes)); - memcpy(run->emulation_failure.insn_bytes, - ctxt->fetch.data, insn_size); + memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size); } + + memcpy(&run->internal.data[info_start], info, sizeof(info)); + memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data, + ndata * sizeof(data[0])); + + run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata; } +static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data, + ctxt->fetch.end - ctxt->fetch.data); +} + +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata) +{ + prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); +} +EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit); + +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; @@ -7701,16 +7750,14 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) if (kvm->arch.exit_on_emulation_error || (emulation_type & EMULTYPE_SKIP)) { - prepare_emulation_failure_exit(vcpu); + prepare_emulation_ctxt_failure_exit(vcpu); return 0; } kvm_queue_exception(vcpu, UD_VECTOR); if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + prepare_emulation_ctxt_failure_exit(vcpu); return 0; } @@ -12336,9 +12383,7 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, * doesn't seem to be a real use-case behind such requests, just return * KVM_EXIT_INTERNAL_ERROR for now. */ - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2c8aa8d4dac1..78f0719cc2a3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -398,6 +398,11 @@ struct kvm_run { * "ndata" is correct, that new fields are enumerated in "flags", * and that each flag enumerates fields that are 64-bit aligned * and sized (so that ndata+internal.data[] is valid/accurate). + * + * Space beyond the defined fields may be used to store arbitrary + * debug information relating to the emulation failure. It is + * accounted for in "ndata" but the format is unspecified and is + * not represented in "flags". Any such information is *not* ABI! */ struct { __u32 suberror; @@ -409,6 +414,7 @@ struct kvm_run { __u8 insn_bytes[15]; }; }; + /* Arbitrary debug data may follow. */ } emulation_failure; /* KVM_EXIT_OSI */ struct { -- cgit v1.2.3 From 1cf4e9a6fbdbc9850216a2a6d8ed52888679a077 Mon Sep 17 00:00:00 2001 From: Luo Jie Date: Sun, 24 Oct 2021 16:27:33 +0800 Subject: net: phy: add constants for fast retrain related register Add the constants for 2.5G fast retrain capability in 10G AN control register, fast retrain status and control register and THP bypass register into mdio.h. Signed-off-by: Luo Jie Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index bdf77dffa5a4..c54e6eae5366 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -53,12 +53,14 @@ #define MDIO_AN_EEE_LPABLE 61 /* EEE link partner ability */ #define MDIO_AN_EEE_ADV2 62 /* EEE advertisement 2 */ #define MDIO_AN_EEE_LPABLE2 63 /* EEE link partner ability 2 */ +#define MDIO_AN_CTRL2 64 /* AN THP bypass request control */ /* Media-dependent registers. */ #define MDIO_PMA_10GBT_SWAPPOL 130 /* 10GBASE-T pair swap & polarity */ #define MDIO_PMA_10GBT_TXPWR 131 /* 10GBASE-T TX power control */ #define MDIO_PMA_10GBT_SNR 133 /* 10GBASE-T SNR margin, lane A. * Lanes B-D are numbered 134-136. */ +#define MDIO_PMA_10GBR_FSRT_CSR 147 /* 10GBASE-R fast retrain status and control */ #define MDIO_PMA_10GBR_FECABLE 170 /* 10GBASE-R FEC ability */ #define MDIO_PCS_10GBX_STAT1 24 /* 10GBASE-X PCS status 1 */ #define MDIO_PCS_10GBRT_STAT1 32 /* 10GBASE-R/-T PCS status 1 */ @@ -239,6 +241,9 @@ #define MDIO_PMA_10GBR_FECABLE_ABLE 0x0001 /* FEC ability */ #define MDIO_PMA_10GBR_FECABLE_ERRABLE 0x0002 /* FEC error indic. ability */ +/* PMA 10GBASE-R Fast Retrain status and control register. */ +#define MDIO_PMA_10GBR_FSRT_ENABLE 0x0001 /* Fast retrain enable */ + /* PCS 10GBASE-R/-T status register 1. */ #define MDIO_PCS_10GBRT_STAT1_BLKLK 0x0001 /* Block lock attained */ @@ -247,6 +252,7 @@ #define MDIO_PCS_10GBRT_STAT2_BER 0x3f00 /* AN 10GBASE-T control register. */ +#define MDIO_AN_10GBT_CTRL_ADVFSRT2_5G 0x0020 /* Advertise 2.5GBASE-T fast retrain */ #define MDIO_AN_10GBT_CTRL_ADV2_5G 0x0080 /* Advertise 2.5GBASE-T */ #define MDIO_AN_10GBT_CTRL_ADV5G 0x0100 /* Advertise 5GBASE-T */ #define MDIO_AN_10GBT_CTRL_ADV10G 0x1000 /* Advertise 10GBASE-T */ @@ -289,6 +295,9 @@ #define MDIO_EEE_2_5GT 0x0001 /* 2.5GT EEE cap */ #define MDIO_EEE_5GT 0x0002 /* 5GT EEE cap */ +/* AN MultiGBASE-T AN control 2 */ +#define MDIO_AN_THP_BP2_5GT 0x0008 /* 2.5GT THP bypass request */ + /* 2.5G/5G Extended abilities register. */ #define MDIO_PMA_NG_EXTABLE_2_5GBT 0x0001 /* 2.5GBASET ability */ #define MDIO_PMA_NG_EXTABLE_5GBT 0x0002 /* 5GBASET ability */ -- cgit v1.2.3 From 36ad9bf1d93d66b901342eab9f8ed6c1537655a6 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 26 Oct 2021 12:16:51 +0100 Subject: ASoC: qdsp6: audioreach: add topology support Add ASoC topology support in audioreach Signed-off-by: Srinivas Kandagatla Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20211026111655.1702-14-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- include/uapi/sound/snd_ar_tokens.h | 208 +++++++ sound/soc/qcom/Kconfig | 1 + sound/soc/qcom/qdsp6/Makefile | 2 +- sound/soc/qcom/qdsp6/audioreach.h | 3 + sound/soc/qcom/qdsp6/q6apm.c | 2 +- sound/soc/qcom/qdsp6/topology.c | 1113 ++++++++++++++++++++++++++++++++++++ 6 files changed, 1327 insertions(+), 2 deletions(-) create mode 100644 include/uapi/sound/snd_ar_tokens.h create mode 100644 sound/soc/qcom/qdsp6/topology.c (limited to 'include/uapi') diff --git a/include/uapi/sound/snd_ar_tokens.h b/include/uapi/sound/snd_ar_tokens.h new file mode 100644 index 000000000000..440c0725660b --- /dev/null +++ b/include/uapi/sound/snd_ar_tokens.h @@ -0,0 +1,208 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef __SND_AR_TOKENS_H__ +#define __SND_AR_TOKENS_H__ + +#define APM_SUB_GRAPH_PERF_MODE_LOW_POWER 0x1 +#define APM_SUB_GRAPH_PERF_MODE_LOW_LATENCY 0x2 + +#define APM_SUB_GRAPH_DIRECTION_TX 0x1 +#define APM_SUB_GRAPH_DIRECTION_RX 0x2 + +/** Scenario ID Audio Playback */ +#define APM_SUB_GRAPH_SID_AUDIO_PLAYBACK 0x1 +/* Scenario ID Audio Record */ +#define APM_SUB_GRAPH_SID_AUDIO_RECORD 0x2 +/* Scenario ID Voice call. */ +#define APM_SUB_GRAPH_SID_VOICE_CALL 0x3 + +/* container capability ID Pre/Post Processing (PP) */ +#define APM_CONTAINER_CAP_ID_PP 0x1 +/* container capability ID Compression/Decompression (CD) */ +#define APM_CONTAINER_CAP_ID_CD 0x2 +/* container capability ID End Point(EP) */ +#define APM_CONTAINER_CAP_ID_EP 0x3 +/* container capability ID Offload (OLC) */ +#define APM_CONTAINER_CAP_ID_OLC 0x4 + +/* container graph position Stream */ +#define APM_CONT_GRAPH_POS_STREAM 0x1 +/* container graph position Per Stream Per Device*/ +#define APM_CONT_GRAPH_POS_PER_STR_PER_DEV 0x2 +/* container graph position Stream-Device */ +#define APM_CONT_GRAPH_POS_STR_DEV 0x3 +/* container graph position Global Device */ +#define APM_CONT_GRAPH_POS_GLOBAL_DEV 0x4 + +#define APM_PROC_DOMAIN_ID_MDSP 0x1 +#define APM_PROC_DOMAIN_ID_ADSP 0x2 +#define APM_PROC_DOMAIN_ID_SDSP 0x4 +#define APM_PROC_DOMAIN_ID_CDSP 0x5 + +#define PCM_INTERLEAVED 1 +#define PCM_DEINTERLEAVED_PACKED 2 +#define PCM_DEINTERLEAVED_UNPACKED 3 +#define AR_I2S_WS_SRC_EXTERNAL 0 +#define AR_I2S_WS_SRC_INTERNAL 1 + +enum ar_event_types { + AR_EVENT_NONE = 0, + AR_PGA_DAPM_EVENT +}; + +/* + * Kcontrol IDs + */ +#define SND_SOC_AR_TPLG_FE_BE_GRAPH_CTL_MIX 256 +#define SND_SOC_AR_TPLG_VOL_CTL 257 + +/** + * %AR_TKN_U32_SUB_GRAPH_INSTANCE_ID: Sub Graph Instance Id + * + * %AR_TKN_U32_SUB_GRAPH_PERF_MODE: Performance mode of subgraph + * APM_SUB_GRAPH_PERF_MODE_LOW_POWER = 1, + * APM_SUB_GRAPH_PERF_MODE_LOW_LATENCY = 2 + * + * %AR_TKN_U32_SUB_GRAPH_DIRECTION: Direction of subgraph + * APM_SUB_GRAPH_DIRECTION_TX = 1, + * APM_SUB_GRAPH_DIRECTION_RX = 2 + * + * %AR_TKN_U32_SUB_GRAPH_SCENARIO_ID: Scenario ID for subgraph + * APM_SUB_GRAPH_SID_AUDIO_PLAYBACK = 1, + * APM_SUB_GRAPH_SID_AUDIO_RECORD = 2, + * APM_SUB_GRAPH_SID_VOICE_CALL = 3 + * + * %AR_TKN_U32_CONTAINER_INSTANCE_ID: Container Instance ID + * + * %AR_TKN_U32_CONTAINER_CAPABILITY_ID: Container capability ID + * APM_CONTAINER_CAP_ID_PP = 1, + * APM_CONTAINER_CAP_ID_CD = 2, + * APM_CONTAINER_CAP_ID_EP = 3, + * APM_CONTAINER_CAP_ID_OLC = 4 + * + * %AR_TKN_U32_CONTAINER_STACK_SIZE: Stack size in the container. + * + * %AR_TKN_U32_CONTAINER_GRAPH_POS: Graph Position + * APM_CONT_GRAPH_POS_STREAM = 1, + * APM_CONT_GRAPH_POS_PER_STR_PER_DEV = 2, + * APM_CONT_GRAPH_POS_STR_DEV = 3, + * APM_CONT_GRAPH_POS_GLOBAL_DEV = 4 + * + * %AR_TKN_U32_CONTAINER_PROC_DOMAIN: Processor domain of container + * APM_PROC_DOMAIN_ID_MDSP = 1, + * APM_PROC_DOMAIN_ID_ADSP = 2, + * APM_PROC_DOMAIN_ID_SDSP = 4, + * APM_PROC_DOMAIN_ID_CDSP = 5 + * + * %AR_TKN_U32_MODULE_ID: Module ID + * + * %AR_TKN_U32_MODULE_INSTANCE_ID: Module Instance ID. + * + * %AR_TKN_U32_MODULE_MAX_IP_PORTS: Module maximum input ports + * + * %AR_TKN_U32_MODULE_MAX_OP_PORTS: Module maximum output ports. + * + * %AR_TKN_U32_MODULE_IN_PORTS: Number of in ports + * + * %AR_TKN_U32_MODULE_OUT_PORTS: Number of out ports. + * + * %AR_TKN_U32_MODULE_SRC_OP_PORT_ID: Source module output port ID + * + * %AR_TKN_U32_MODULE_DST_IN_PORT_ID: Destination module input port ID + * + * %AR_TKN_U32_MODULE_HW_IF_IDX: Interface index types for I2S/LPAIF + * + * %AR_TKN_U32_MODULE_HW_IF_TYPE: Interface type + * LPAIF = 0, + * LPAIF_RXTX = 1, + * LPAIF_WSA = 2, + * LPAIF_VA = 3, + * LPAIF_AXI = 4 + * + * %AR_TKN_U32_MODULE_FMT_INTERLEAVE: PCM Interleaving + * PCM_INTERLEAVED = 1, + * PCM_DEINTERLEAVED_PACKED = 2, + * PCM_DEINTERLEAVED_UNPACKED = 3 + * + * %AR_TKN_U32_MODULE_FMT_DATA: data format + * FIXED POINT = 1, + * IEC60958 PACKETIZED = 3, + * IEC60958 PACKETIZED NON LINEAR = 8, + * COMPR OVER PCM PACKETIZED = 7, + * IEC61937 PACKETIZED = 2, + * GENERIC COMPRESSED = 5 + * + * %AR_TKN_U32_MODULE_FMT_SAMPLE_RATE: sample rate + * + * %AR_TKN_U32_MODULE_FMT_BIT_DEPTH: bit depth + * + * %AR_TKN_U32_MODULE_SD_LINE_IDX: I2S serial data line idx + * I2S_SD0 = 1, + * I2S_SD1 = 2, + * I2S_SD2 = 3, + * I2S_SD3 = 4, + * I2S_QUAD01 = 5, + * I2S_QUAD23 = 6, + * I2S_6CHS = 7, + * I2S_8CHS = 8 + * + * %AR_TKN_U32_MODULE_WS_SRC: Word Select Source + * AR_I2S_WS_SRC_EXTERNAL = 0, + * AR_I2S_WS_SRC_INTERNAL = 1, + * + * %AR_TKN_U32_MODULE_FRAME_SZ_FACTOR: Frame size factor + * + * %AR_TKN_U32_MODULE_LOG_CODE: Log Module Code + * + * %AR_TKN_U32_MODULE_LOG_TAP_POINT_ID: logging tap point of this module + * + * %AR_TKN_U32_MODULE_LOG_MODE: logging mode + * LOG_WAIT = 0, + * LOG_IMMEDIATELY = 1 + * + * %AR_TKN_DAI_INDEX: dai index + * + */ + +/* DAI Tokens */ +#define AR_TKN_DAI_INDEX 1 +/* SUB GRAPH Tokens */ +#define AR_TKN_U32_SUB_GRAPH_INSTANCE_ID 2 +#define AR_TKN_U32_SUB_GRAPH_PERF_MODE 3 +#define AR_TKN_U32_SUB_GRAPH_DIRECTION 4 +#define AR_TKN_U32_SUB_GRAPH_SCENARIO_ID 5 + +/* Container Tokens */ +#define AR_TKN_U32_CONTAINER_INSTANCE_ID 100 +#define AR_TKN_U32_CONTAINER_CAPABILITY_ID 101 +#define AR_TKN_U32_CONTAINER_STACK_SIZE 102 +#define AR_TKN_U32_CONTAINER_GRAPH_POS 103 +#define AR_TKN_U32_CONTAINER_PROC_DOMAIN 104 + +/* Module Tokens */ +#define AR_TKN_U32_MODULE_ID 200 +#define AR_TKN_U32_MODULE_INSTANCE_ID 201 +#define AR_TKN_U32_MODULE_MAX_IP_PORTS 202 +#define AR_TKN_U32_MODULE_MAX_OP_PORTS 203 +#define AR_TKN_U32_MODULE_IN_PORTS 204 +#define AR_TKN_U32_MODULE_OUT_PORTS 205 +#define AR_TKN_U32_MODULE_SRC_OP_PORT_ID 206 +#define AR_TKN_U32_MODULE_DST_IN_PORT_ID 207 +#define AR_TKN_U32_MODULE_SRC_INSTANCE_ID 208 +#define AR_TKN_U32_MODULE_DST_INSTANCE_ID 209 + + +#define AR_TKN_U32_MODULE_HW_IF_IDX 250 +#define AR_TKN_U32_MODULE_HW_IF_TYPE 251 +#define AR_TKN_U32_MODULE_FMT_INTERLEAVE 252 +#define AR_TKN_U32_MODULE_FMT_DATA 253 +#define AR_TKN_U32_MODULE_FMT_SAMPLE_RATE 254 +#define AR_TKN_U32_MODULE_FMT_BIT_DEPTH 255 +#define AR_TKN_U32_MODULE_SD_LINE_IDX 256 +#define AR_TKN_U32_MODULE_WS_SRC 257 +#define AR_TKN_U32_MODULE_FRAME_SZ_FACTOR 258 +#define AR_TKN_U32_MODULE_LOG_CODE 259 +#define AR_TKN_U32_MODULE_LOG_TAP_POINT_ID 260 +#define AR_TKN_U32_MODULE_LOG_MODE 261 + +#endif /* __SND_AR_TOKENS_H__ */ diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig index 6aaf36b44725..75f447de1faf 100644 --- a/sound/soc/qcom/Kconfig +++ b/sound/soc/qcom/Kconfig @@ -101,6 +101,7 @@ config SND_SOC_QDSP6 select SND_SOC_QDSP6_ROUTING select SND_SOC_QDSP6_ASM select SND_SOC_QDSP6_ASM_DAI + select SND_SOC_TOPOLOGY select SND_SOC_QDSP6_APM help To add support for MSM QDSP6 Soc Audio. diff --git a/sound/soc/qcom/qdsp6/Makefile b/sound/soc/qcom/qdsp6/Makefile index 1a0803d97eec..766b824f6597 100644 --- a/sound/soc/qcom/qdsp6/Makefile +++ b/sound/soc/qcom/qdsp6/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only snd-q6dsp-common-objs := q6dsp-common.o q6dsp-lpass-ports.o q6dsp-lpass-clocks.o -snd-q6apm-objs := q6apm.o audioreach.o +snd-q6apm-objs := q6apm.o audioreach.o topology.o obj-$(CONFIG_SND_SOC_QDSP6_COMMON) += snd-q6dsp-common.o obj-$(CONFIG_SND_SOC_QDSP6_CORE) += q6core.o diff --git a/sound/soc/qcom/qdsp6/audioreach.h b/sound/soc/qcom/qdsp6/audioreach.h index 821e1511140f..4f693a2660b5 100644 --- a/sound/soc/qcom/qdsp6/audioreach.h +++ b/sound/soc/qcom/qdsp6/audioreach.h @@ -693,6 +693,9 @@ void *audioreach_alloc_pkt(int payload_size, uint32_t opcode, void *audioreach_alloc_graph_pkt(struct q6apm *apm, struct list_head *sg_list, int graph_id); +/* Topology specific */ +int audioreach_tplg_init(struct snd_soc_component *component); + /* Module specific */ void audioreach_graph_free_buf(struct q6apm_graph *graph); int audioreach_map_memory_regions(struct q6apm_graph *graph, diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c index 046f8f2e0c58..13598ef5bacb 100644 --- a/sound/soc/qcom/qdsp6/q6apm.c +++ b/sound/soc/qcom/qdsp6/q6apm.c @@ -694,7 +694,7 @@ EXPORT_SYMBOL_GPL(q6apm_graph_flush); static int q6apm_audio_probe(struct snd_soc_component *component) { - return 0; + return audioreach_tplg_init(component); } static void q6apm_audio_remove(struct snd_soc_component *component) diff --git a/sound/soc/qcom/qdsp6/topology.c b/sound/soc/qcom/qdsp6/topology.c new file mode 100644 index 000000000000..f31895379925 --- /dev/null +++ b/sound/soc/qcom/qdsp6/topology.c @@ -0,0 +1,1113 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020, Linaro Limited + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "q6apm.h" +#include "audioreach.h" + +struct snd_ar_control { + u32 sgid; /* Sub Graph ID */ + struct snd_soc_component *scomp; +}; + +static struct audioreach_graph_info *audioreach_tplg_alloc_graph_info(struct q6apm *apm, + uint32_t graph_id, + bool *found) +{ + struct audioreach_graph_info *info; + int ret; + + mutex_lock(&apm->lock); + info = idr_find(&apm->graph_info_idr, graph_id); + mutex_unlock(&apm->lock); + + if (info) { + *found = true; + return info; + } + + *found = false; + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&info->sg_list); + + mutex_lock(&apm->lock); + ret = idr_alloc(&apm->graph_info_idr, info, graph_id, graph_id + 1, GFP_KERNEL); + mutex_unlock(&apm->lock); + + if (ret < 0) { + dev_err(apm->dev, "Failed to allocate Graph ID (%x)\n", graph_id); + kfree(info); + return ERR_PTR(ret); + } + + info->id = ret; + + return info; +} + +static void audioreach_tplg_add_sub_graph(struct audioreach_sub_graph *sg, + struct audioreach_graph_info *info) +{ + list_add_tail(&sg->node, &info->sg_list); + sg->info = info; + info->num_sub_graphs++; +} + +static struct audioreach_sub_graph *audioreach_tplg_alloc_sub_graph(struct q6apm *apm, + uint32_t sub_graph_id, + bool *found) +{ + struct audioreach_sub_graph *sg; + int ret; + + if (!sub_graph_id) + return ERR_PTR(-EINVAL); + + /* Find if there is already a matching sub-graph */ + mutex_lock(&apm->lock); + sg = idr_find(&apm->sub_graphs_idr, sub_graph_id); + mutex_unlock(&apm->lock); + + if (sg) { + *found = true; + return sg; + } + + *found = false; + sg = kzalloc(sizeof(*sg), GFP_KERNEL); + if (!sg) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&sg->container_list); + + mutex_lock(&apm->lock); + ret = idr_alloc(&apm->sub_graphs_idr, sg, sub_graph_id, sub_graph_id + 1, GFP_KERNEL); + mutex_unlock(&apm->lock); + + if (ret < 0) { + dev_err(apm->dev, "Failed to allocate Sub-Graph Instance ID (%x)\n", sub_graph_id); + kfree(sg); + return ERR_PTR(ret); + } + + sg->sub_graph_id = ret; + + return sg; +} + +static struct audioreach_container *audioreach_tplg_alloc_container(struct q6apm *apm, + struct audioreach_sub_graph *sg, + uint32_t container_id, + bool *found) +{ + struct audioreach_container *cont; + int ret; + + if (!container_id) + return ERR_PTR(-EINVAL); + + mutex_lock(&apm->lock); + cont = idr_find(&apm->containers_idr, container_id); + mutex_unlock(&apm->lock); + + if (cont) { + *found = true; + return cont; + } + *found = false; + + cont = kzalloc(sizeof(*cont), GFP_KERNEL); + if (!cont) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&cont->modules_list); + + mutex_lock(&apm->lock); + ret = idr_alloc(&apm->containers_idr, cont, container_id, container_id + 1, GFP_KERNEL); + mutex_unlock(&apm->lock); + + if (ret < 0) { + dev_err(apm->dev, "Failed to allocate Container Instance ID (%x)\n", container_id); + kfree(cont); + return ERR_PTR(ret); + } + + cont->container_id = ret; + cont->sub_graph = sg; + /* add to container list */ + list_add_tail(&cont->node, &sg->container_list); + sg->num_containers++; + + return cont; +} + +static struct audioreach_module *audioreach_tplg_alloc_module(struct q6apm *apm, + struct audioreach_container *cont, + struct snd_soc_dapm_widget *w, + uint32_t module_id, bool *found) +{ + struct audioreach_module *mod; + int ret; + + mutex_lock(&apm->lock); + mod = idr_find(&apm->modules_idr, module_id); + mutex_unlock(&apm->lock); + + if (mod) { + *found = true; + return mod; + } + *found = false; + mod = kzalloc(sizeof(*mod), GFP_KERNEL); + if (!mod) + return ERR_PTR(-ENOMEM); + + mutex_lock(&apm->lock); + if (!module_id) { /* alloc module id dynamically */ + ret = idr_alloc_cyclic(&apm->modules_idr, mod, + AR_MODULE_DYNAMIC_INSTANCE_ID_START, + AR_MODULE_DYNAMIC_INSTANCE_ID_END, GFP_KERNEL); + } else { + ret = idr_alloc(&apm->modules_idr, mod, module_id, module_id + 1, GFP_KERNEL); + } + mutex_unlock(&apm->lock); + + if (ret < 0) { + dev_err(apm->dev, "Failed to allocate Module Instance ID (%x)\n", module_id); + kfree(mod); + return ERR_PTR(ret); + } + + mod->instance_id = ret; + /* add to module list */ + list_add_tail(&mod->node, &cont->modules_list); + mod->container = cont; + mod->widget = w; + cont->num_modules++; + + return mod; +} + +static struct snd_soc_tplg_vendor_array *audioreach_get_sg_array( + struct snd_soc_tplg_private *private) +{ + struct snd_soc_tplg_vendor_array *sg_array = NULL; + bool found = false; + int sz; + + for (sz = 0; !found && (sz < le32_to_cpu(private->size)); ) { + struct snd_soc_tplg_vendor_value_elem *sg_elem; + int tkn_count = 0; + + sg_array = (struct snd_soc_tplg_vendor_array *)((u8 *)private->array + sz); + sg_elem = sg_array->value; + sz = sz + le32_to_cpu(sg_array->size); + while (!found && tkn_count <= (le32_to_cpu(sg_array->num_elems) - 1)) { + switch (le32_to_cpu(sg_elem->token)) { + case AR_TKN_U32_SUB_GRAPH_INSTANCE_ID: + found = true; + break; + default: + break; + } + tkn_count++; + sg_elem++; + } + } + + if (found) + return sg_array; + + return NULL; +} + +static struct snd_soc_tplg_vendor_array *audioreach_get_cont_array( + struct snd_soc_tplg_private *private) +{ + struct snd_soc_tplg_vendor_array *cont_array = NULL; + bool found = false; + int sz; + + for (sz = 0; !found && (sz < le32_to_cpu(private->size)); ) { + struct snd_soc_tplg_vendor_value_elem *cont_elem; + int tkn_count = 0; + + cont_array = (struct snd_soc_tplg_vendor_array *)((u8 *)private->array + sz); + cont_elem = cont_array->value; + sz = sz + le32_to_cpu(cont_array->size); + while (!found && tkn_count <= (le32_to_cpu(cont_array->num_elems) - 1)) { + switch (le32_to_cpu(cont_elem->token)) { + case AR_TKN_U32_CONTAINER_INSTANCE_ID: + found = true; + break; + default: + break; + } + tkn_count++; + cont_elem++; + } + } + + if (found) + return cont_array; + + return NULL; +} + +static struct snd_soc_tplg_vendor_array *audioreach_get_module_array( + struct snd_soc_tplg_private *private) +{ + struct snd_soc_tplg_vendor_array *mod_array = NULL; + bool found = false; + int sz = 0; + + for (sz = 0; !found && (sz < le32_to_cpu(private->size)); ) { + struct snd_soc_tplg_vendor_value_elem *mod_elem; + int tkn_count = 0; + + mod_array = (struct snd_soc_tplg_vendor_array *)((u8 *)private->array + sz); + mod_elem = mod_array->value; + sz = sz + le32_to_cpu(mod_array->size); + while (!found && tkn_count <= (le32_to_cpu(mod_array->num_elems) - 1)) { + switch (le32_to_cpu(mod_elem->token)) { + case AR_TKN_U32_MODULE_INSTANCE_ID: + found = true; + break; + default: + break; + } + tkn_count++; + mod_elem++; + } + } + + if (found) + return mod_array; + + return NULL; +} + +static struct audioreach_sub_graph *audioreach_parse_sg_tokens(struct q6apm *apm, + struct snd_soc_tplg_private *private) +{ + struct snd_soc_tplg_vendor_value_elem *sg_elem; + struct snd_soc_tplg_vendor_array *sg_array; + struct audioreach_graph_info *info = NULL; + int graph_id, sub_graph_id, tkn_count = 0; + struct audioreach_sub_graph *sg; + bool found; + + sg_array = audioreach_get_sg_array(private); + sg_elem = sg_array->value; + + while (tkn_count <= (le32_to_cpu(sg_array->num_elems) - 1)) { + switch (le32_to_cpu(sg_elem->token)) { + case AR_TKN_U32_SUB_GRAPH_INSTANCE_ID: + sub_graph_id = le32_to_cpu(sg_elem->value); + sg = audioreach_tplg_alloc_sub_graph(apm, sub_graph_id, &found); + if (IS_ERR(sg)) { + return sg; + } else if (found) { + /* Already parsed data for this sub-graph */ + return sg; + } + break; + case AR_TKN_DAI_INDEX: + /* Sub graph is associated with predefined graph */ + graph_id = le32_to_cpu(sg_elem->value); + info = audioreach_tplg_alloc_graph_info(apm, graph_id, &found); + if (IS_ERR(info)) + return ERR_CAST(info); + break; + case AR_TKN_U32_SUB_GRAPH_PERF_MODE: + sg->perf_mode = le32_to_cpu(sg_elem->value); + break; + case AR_TKN_U32_SUB_GRAPH_DIRECTION: + sg->direction = le32_to_cpu(sg_elem->value); + break; + case AR_TKN_U32_SUB_GRAPH_SCENARIO_ID: + sg->scenario_id = le32_to_cpu(sg_elem->value); + break; + default: + dev_err(apm->dev, "Not a valid token %d for graph\n", sg_elem->token); + break; + + } + tkn_count++; + sg_elem++; + } + + /* Sub graph is associated with predefined graph */ + if (info) + audioreach_tplg_add_sub_graph(sg, info); + + return sg; +} + +static struct audioreach_container *audioreach_parse_cont_tokens(struct q6apm *apm, + struct audioreach_sub_graph *sg, + struct snd_soc_tplg_private *private) +{ + struct snd_soc_tplg_vendor_value_elem *cont_elem; + struct snd_soc_tplg_vendor_array *cont_array; + struct audioreach_container *cont; + int container_id, tkn_count = 0; + bool found = false; + + cont_array = audioreach_get_cont_array(private); + cont_elem = cont_array->value; + + while (tkn_count <= (le32_to_cpu(cont_array->num_elems) - 1)) { + switch (le32_to_cpu(cont_elem->token)) { + case AR_TKN_U32_CONTAINER_INSTANCE_ID: + container_id = le32_to_cpu(cont_elem->value); + cont = audioreach_tplg_alloc_container(apm, sg, container_id, &found); + if (IS_ERR(cont) || found)/* Error or Already parsed container data */ + return cont; + break; + case AR_TKN_U32_CONTAINER_CAPABILITY_ID: + cont->capability_id = le32_to_cpu(cont_elem->value); + break; + case AR_TKN_U32_CONTAINER_STACK_SIZE: + cont->stack_size = le32_to_cpu(cont_elem->value); + break; + case AR_TKN_U32_CONTAINER_GRAPH_POS: + cont->graph_pos = le32_to_cpu(cont_elem->value); + break; + case AR_TKN_U32_CONTAINER_PROC_DOMAIN: + cont->proc_domain = le32_to_cpu(cont_elem->value); + break; + default: + dev_err(apm->dev, "Not a valid token %d for graph\n", cont_elem->token); + break; + + } + tkn_count++; + cont_elem++; + } + + return cont; +} + +static struct audioreach_module *audioreach_parse_common_tokens(struct q6apm *apm, + struct audioreach_container *cont, + struct snd_soc_tplg_private *private, + struct snd_soc_dapm_widget *w) +{ + uint32_t max_ip_port = 0, max_op_port = 0, in_port = 0, out_port = 0; + uint32_t src_mod_inst_id = 0, src_mod_op_port_id = 0; + uint32_t dst_mod_inst_id = 0, dst_mod_ip_port_id = 0; + int module_id = 0, instance_id = 0, tkn_count = 0; + struct snd_soc_tplg_vendor_value_elem *mod_elem; + struct snd_soc_tplg_vendor_array *mod_array; + struct audioreach_module *mod = NULL; + bool found; + + mod_array = audioreach_get_module_array(private); + mod_elem = mod_array->value; + + while (tkn_count <= (le32_to_cpu(mod_array->num_elems) - 1)) { + switch (le32_to_cpu(mod_elem->token)) { + /* common module info */ + case AR_TKN_U32_MODULE_ID: + module_id = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_INSTANCE_ID: + instance_id = le32_to_cpu(mod_elem->value); + mod = audioreach_tplg_alloc_module(apm, cont, w, + instance_id, &found); + if (IS_ERR(mod)) { + return mod; + } else if (found) { + dev_err(apm->dev, "Duplicate Module Instance ID 0x%08x found\n", + instance_id); + return ERR_PTR(-EINVAL); + } + + break; + case AR_TKN_U32_MODULE_MAX_IP_PORTS: + max_ip_port = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_MAX_OP_PORTS: + max_op_port = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_IN_PORTS: + in_port = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_OUT_PORTS: + out_port = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_SRC_OP_PORT_ID: + src_mod_op_port_id = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_SRC_INSTANCE_ID: + src_mod_inst_id = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_DST_INSTANCE_ID: + dst_mod_inst_id = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_DST_IN_PORT_ID: + dst_mod_ip_port_id = le32_to_cpu(mod_elem->value); + + default: + break; + + } + tkn_count++; + mod_elem++; + } + + if (mod) { + mod->module_id = module_id; + mod->max_ip_port = max_ip_port; + mod->max_op_port = max_op_port; + mod->in_port = in_port; + mod->out_port = out_port; + mod->src_mod_inst_id = src_mod_inst_id; + mod->src_mod_op_port_id = src_mod_op_port_id; + mod->dst_mod_inst_id = dst_mod_inst_id; + mod->dst_mod_ip_port_id = dst_mod_ip_port_id; + } + + return mod; +} + +static int audioreach_widget_load_module_common(struct snd_soc_component *component, + int index, struct snd_soc_dapm_widget *w, + struct snd_soc_tplg_dapm_widget *tplg_w) +{ + struct q6apm *apm = dev_get_drvdata(component->dev); + struct audioreach_container *cont; + struct audioreach_sub_graph *sg; + struct audioreach_module *mod; + struct snd_soc_dobj *dobj; + + sg = audioreach_parse_sg_tokens(apm, &tplg_w->priv); + if (IS_ERR(sg)) + return PTR_ERR(sg); + + cont = audioreach_parse_cont_tokens(apm, sg, &tplg_w->priv); + if (IS_ERR(cont)) + return PTR_ERR(cont); + + mod = audioreach_parse_common_tokens(apm, cont, &tplg_w->priv, w); + if (IS_ERR(mod)) + return PTR_ERR(mod); + + dobj = &w->dobj; + dobj->private = mod; + + return 0; +} + +static int audioreach_widget_load_enc_dec_cnv(struct snd_soc_component *component, + int index, struct snd_soc_dapm_widget *w, + struct snd_soc_tplg_dapm_widget *tplg_w) +{ + struct snd_soc_tplg_vendor_value_elem *mod_elem; + struct snd_soc_tplg_vendor_array *mod_array; + struct audioreach_module *mod; + struct snd_soc_dobj *dobj; + int tkn_count = 0; + int ret; + + ret = audioreach_widget_load_module_common(component, index, w, tplg_w); + if (ret) + return ret; + + dobj = &w->dobj; + mod = dobj->private; + mod_array = audioreach_get_module_array(&tplg_w->priv); + mod_elem = mod_array->value; + + while (tkn_count <= (le32_to_cpu(mod_array->num_elems) - 1)) { + switch (le32_to_cpu(mod_elem->token)) { + case AR_TKN_U32_MODULE_FMT_INTERLEAVE: + mod->interleave_type = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_FMT_SAMPLE_RATE: + mod->rate = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_FMT_BIT_DEPTH: + mod->bit_depth = le32_to_cpu(mod_elem->value); + break; + default: + break; + } + tkn_count++; + mod_elem++; + } + + return 0; +} + +static int audioreach_widget_log_module_load(struct audioreach_module *mod, + struct snd_soc_tplg_vendor_array *mod_array) +{ + struct snd_soc_tplg_vendor_value_elem *mod_elem; + int tkn_count = 0; + + mod_elem = mod_array->value; + + while (tkn_count <= (le32_to_cpu(mod_array->num_elems) - 1)) { + switch (le32_to_cpu(mod_elem->token)) { + + case AR_TKN_U32_MODULE_LOG_CODE: + mod->log_code = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_LOG_TAP_POINT_ID: + mod->log_tap_point_id = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_LOG_MODE: + mod->log_mode = le32_to_cpu(mod_elem->value); + break; + default: + break; + } + tkn_count++; + mod_elem++; + } + + return 0; +} + +static int audioreach_widget_dma_module_load(struct audioreach_module *mod, + struct snd_soc_tplg_vendor_array *mod_array) +{ + struct snd_soc_tplg_vendor_value_elem *mod_elem; + int tkn_count = 0; + + mod_elem = mod_array->value; + + while (tkn_count <= (le32_to_cpu(mod_array->num_elems) - 1)) { + switch (le32_to_cpu(mod_elem->token)) { + case AR_TKN_U32_MODULE_HW_IF_IDX: + mod->hw_interface_idx = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_FMT_DATA: + mod->data_format = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_HW_IF_TYPE: + mod->hw_interface_type = le32_to_cpu(mod_elem->value); + break; + default: + break; + } + tkn_count++; + mod_elem++; + } + + return 0; +} + +static int audioreach_widget_i2s_module_load(struct audioreach_module *mod, + struct snd_soc_tplg_vendor_array *mod_array) +{ + struct snd_soc_tplg_vendor_value_elem *mod_elem; + int tkn_count = 0; + + mod_elem = mod_array->value; + + while (tkn_count <= (le32_to_cpu(mod_array->num_elems) - 1)) { + switch (le32_to_cpu(mod_elem->token)) { + case AR_TKN_U32_MODULE_HW_IF_IDX: + mod->hw_interface_idx = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_FMT_DATA: + mod->data_format = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_HW_IF_TYPE: + mod->hw_interface_type = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_SD_LINE_IDX: + mod->sd_line_idx = le32_to_cpu(mod_elem->value); + break; + case AR_TKN_U32_MODULE_WS_SRC: + mod->ws_src = le32_to_cpu(mod_elem->value); + break; + default: + break; + } + tkn_count++; + mod_elem++; + } + + return 0; +} + +static int audioreach_widget_load_buffer(struct snd_soc_component *component, + int index, struct snd_soc_dapm_widget *w, + struct snd_soc_tplg_dapm_widget *tplg_w) +{ + struct snd_soc_tplg_vendor_array *mod_array; + struct audioreach_module *mod; + struct snd_soc_dobj *dobj; + int ret; + + ret = audioreach_widget_load_module_common(component, index, w, tplg_w); + if (ret) + return ret; + + dobj = &w->dobj; + mod = dobj->private; + + mod_array = audioreach_get_module_array(&tplg_w->priv); + + switch (mod->module_id) { + case MODULE_ID_CODEC_DMA_SINK: + case MODULE_ID_CODEC_DMA_SOURCE: + audioreach_widget_dma_module_load(mod, mod_array); + break; + case MODULE_ID_DATA_LOGGING: + audioreach_widget_log_module_load(mod, mod_array); + break; + case MODULE_ID_I2S_SINK: + case MODULE_ID_I2S_SOURCE: + audioreach_widget_i2s_module_load(mod, mod_array); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int audioreach_widget_load_mixer(struct snd_soc_component *component, + int index, struct snd_soc_dapm_widget *w, + struct snd_soc_tplg_dapm_widget *tplg_w) +{ + struct snd_soc_tplg_vendor_value_elem *w_elem; + struct snd_soc_tplg_vendor_array *w_array; + struct snd_ar_control *scontrol; + struct snd_soc_dobj *dobj; + int tkn_count = 0; + + w_array = &tplg_w->priv.array[0]; + + scontrol = kzalloc(sizeof(*scontrol), GFP_KERNEL); + if (!scontrol) + return -ENOMEM; + + scontrol->scomp = component; + dobj = &w->dobj; + dobj->private = scontrol; + + w_elem = w_array->value; + while (tkn_count <= (le32_to_cpu(w_array->num_elems) - 1)) { + switch (le32_to_cpu(w_elem->token)) { + case AR_TKN_U32_SUB_GRAPH_INSTANCE_ID: + scontrol->sgid = le32_to_cpu(w_elem->value); + break; + default: /* ignore other tokens */ + break; + } + tkn_count++; + w_elem++; + } + + return 0; +} + +static int audioreach_pga_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) + +{ + struct snd_soc_dapm_context *dapm = w->dapm; + struct snd_soc_component *c = snd_soc_dapm_to_component(dapm); + struct audioreach_module *mod = w->dobj.private; + struct q6apm *apm = dev_get_drvdata(c->dev); + + switch (event) { + case SND_SOC_DAPM_POST_PMU: + /* apply gain after power up of widget */ + audioreach_gain_set_vol_ctrl(apm, mod, mod->gain); + break; + default: + break; + } + + return 0; +} + +static const struct snd_soc_tplg_widget_events audioreach_widget_ops[] = { + { AR_PGA_DAPM_EVENT, audioreach_pga_event }, +}; + +static int audioreach_widget_load_pga(struct snd_soc_component *component, + int index, struct snd_soc_dapm_widget *w, + struct snd_soc_tplg_dapm_widget *tplg_w) +{ + struct audioreach_module *mod; + struct snd_soc_dobj *dobj; + int ret; + + ret = audioreach_widget_load_module_common(component, index, w, tplg_w); + if (ret) + return ret; + + dobj = &w->dobj; + mod = dobj->private; + mod->gain = VOL_CTRL_DEFAULT_GAIN; + + ret = snd_soc_tplg_widget_bind_event(w, audioreach_widget_ops, + ARRAY_SIZE(audioreach_widget_ops), + le16_to_cpu(tplg_w->event_type)); + if (ret) { + dev_err(component->dev, "matching event handlers NOT found for %d\n", + le16_to_cpu(tplg_w->event_type)); + return -EINVAL; + } + + return 0; +} + +static int audioreach_widget_ready(struct snd_soc_component *component, + int index, struct snd_soc_dapm_widget *w, + struct snd_soc_tplg_dapm_widget *tplg_w) +{ + switch (w->id) { + case snd_soc_dapm_aif_in: + case snd_soc_dapm_aif_out: + audioreach_widget_load_buffer(component, index, w, tplg_w); + break; + case snd_soc_dapm_decoder: + case snd_soc_dapm_encoder: + case snd_soc_dapm_src: + audioreach_widget_load_enc_dec_cnv(component, index, w, tplg_w); + break; + case snd_soc_dapm_buffer: + audioreach_widget_load_buffer(component, index, w, tplg_w); + break; + case snd_soc_dapm_mixer: + return audioreach_widget_load_mixer(component, index, w, tplg_w); + case snd_soc_dapm_pga: + return audioreach_widget_load_pga(component, index, w, tplg_w); + case snd_soc_dapm_dai_link: + case snd_soc_dapm_scheduler: + case snd_soc_dapm_out_drv: + default: + dev_err(component->dev, "Widget type (0x%x) not yet supported\n", w->id); + break; + } + + return 0; +} + +static int audioreach_widget_unload(struct snd_soc_component *scomp, + struct snd_soc_dobj *dobj) +{ + struct snd_soc_dapm_widget *w = container_of(dobj, struct snd_soc_dapm_widget, dobj); + struct q6apm *apm = dev_get_drvdata(scomp->dev); + struct audioreach_container *cont; + struct audioreach_module *mod; + + mod = dobj->private; + cont = mod->container; + + if (w->id == snd_soc_dapm_mixer) { + /* virtual widget */ + kfree(dobj->private); + return 0; + } + + mutex_lock(&apm->lock); + idr_remove(&apm->modules_idr, mod->instance_id); + cont->num_modules--; + + list_del(&mod->node); + kfree(mod); + /* Graph Info has N sub-graphs, sub-graph has N containers, Container has N Modules */ + if (list_empty(&cont->modules_list)) { /* if no modules in the container then remove it */ + struct audioreach_sub_graph *sg = cont->sub_graph; + + idr_remove(&apm->containers_idr, cont->container_id); + list_del(&cont->node); + sg->num_containers--; + kfree(cont); + /* check if there are no more containers in the sub graph and remove it */ + if (list_empty(&sg->container_list)) { + struct audioreach_graph_info *info = sg->info; + + idr_remove(&apm->sub_graphs_idr, sg->sub_graph_id); + list_del(&sg->node); + info->num_sub_graphs--; + kfree(sg); + /* Check if there are no more sub-graphs left then remove graph info */ + if (list_empty(&info->sg_list)) { + idr_remove(&apm->graph_info_idr, info->id); + kfree(info); + } + } + } + + mutex_unlock(&apm->lock); + + return 0; +} + +static struct audioreach_module *audioreach_find_widget(struct snd_soc_component *comp, + const char *name) +{ + struct q6apm *apm = dev_get_drvdata(comp->dev); + struct audioreach_module *module; + int id; + + idr_for_each_entry(&apm->modules_idr, module, id) { + if (!strcmp(name, module->widget->name)) + return module; + } + + return NULL; +} + +static int audioreach_route_load(struct snd_soc_component *scomp, int index, + struct snd_soc_dapm_route *route) +{ + struct audioreach_module *src, *sink; + + src = audioreach_find_widget(scomp, route->source); + sink = audioreach_find_widget(scomp, route->sink); + + if (src && sink) { + src->dst_mod_inst_id = sink->instance_id; + sink->src_mod_inst_id = src->instance_id; + } + + return 0; +} + +static int audioreach_route_unload(struct snd_soc_component *scomp, + struct snd_soc_dobj *dobj) +{ + return 0; +} + +static int audioreach_tplg_complete(struct snd_soc_component *component) +{ + /* TBD */ + return 0; +} + +/* DAI link - used for any driver specific init */ +static int audioreach_link_load(struct snd_soc_component *component, int index, + struct snd_soc_dai_link *link, + struct snd_soc_tplg_link_config *cfg) +{ + link->nonatomic = true; + link->dynamic = true; + link->platforms->name = NULL; + link->platforms->of_node = of_get_compatible_child(component->dev->of_node, + "qcom,q6apm-dais"); + return 0; +} + +static int audioreach_get_audio_mixer(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; + struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol); + struct snd_soc_dapm_widget *dw = snd_soc_dapm_kcontrol_widget(kcontrol); + struct snd_soc_component *c = snd_soc_dapm_to_component(dapm); + struct snd_ar_control *dapm_scontrol = dw->dobj.private; + struct snd_ar_control *scontrol = mc->dobj.private; + struct q6apm *data = dev_get_drvdata(c->dev); + bool connected; + + connected = q6apm_is_sub_graphs_connected(data, scontrol->sgid, dapm_scontrol->sgid); + if (connected) + ucontrol->value.integer.value[0] = 1; + else + ucontrol->value.integer.value[0] = 0; + + return 0; +} + +static int audioreach_put_audio_mixer(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; + struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol); + struct snd_soc_dapm_widget *dw = snd_soc_dapm_kcontrol_widget(kcontrol); + struct snd_soc_component *c = snd_soc_dapm_to_component(dapm); + struct snd_ar_control *dapm_scontrol = dw->dobj.private; + struct snd_ar_control *scontrol = mc->dobj.private; + struct q6apm *data = dev_get_drvdata(c->dev); + + if (ucontrol->value.integer.value[0]) { + q6apm_connect_sub_graphs(data, scontrol->sgid, dapm_scontrol->sgid, true); + snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, NULL); + } else { + q6apm_connect_sub_graphs(data, scontrol->sgid, dapm_scontrol->sgid, false); + snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, NULL); + } + return 0; +} + +static int audioreach_get_vol_ctrl_audio_mixer(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_dapm_widget *dw = snd_soc_dapm_kcontrol_widget(kcontrol); + struct audioreach_module *mod = dw->dobj.private; + + ucontrol->value.integer.value[0] = mod->gain; + + return 0; +} + +static int audioreach_put_vol_ctrl_audio_mixer(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_dapm_widget *dw = snd_soc_dapm_kcontrol_widget(kcontrol); + struct audioreach_module *mod = dw->dobj.private; + + mod->gain = ucontrol->value.integer.value[0]; + + return 1; +} + +static int audioreach_control_load_mix(struct snd_soc_component *scomp, + struct snd_ar_control *scontrol, + struct snd_kcontrol_new *kc, + struct snd_soc_tplg_ctl_hdr *hdr) +{ + struct snd_soc_tplg_vendor_value_elem *c_elem; + struct snd_soc_tplg_vendor_array *c_array; + struct snd_soc_tplg_mixer_control *mc; + int tkn_count = 0; + + mc = container_of(hdr, struct snd_soc_tplg_mixer_control, hdr); + c_array = (struct snd_soc_tplg_vendor_array *)mc->priv.data; + + c_elem = c_array->value; + + while (tkn_count <= (le32_to_cpu(c_array->num_elems) - 1)) { + switch (le32_to_cpu(c_elem->token)) { + case AR_TKN_U32_SUB_GRAPH_INSTANCE_ID: + scontrol->sgid = le32_to_cpu(c_elem->value); + break; + default: + /* Ignore other tokens */ + break; + } + c_elem++; + tkn_count++; + } + + return 0; +} + +static int audioreach_control_load(struct snd_soc_component *scomp, int index, + struct snd_kcontrol_new *kc, + struct snd_soc_tplg_ctl_hdr *hdr) +{ + struct snd_ar_control *scontrol; + struct soc_mixer_control *sm; + struct snd_soc_dobj *dobj; + int ret = 0; + + scontrol = kzalloc(sizeof(*scontrol), GFP_KERNEL); + if (!scontrol) + return -ENOMEM; + + scontrol->scomp = scomp; + + switch (le32_to_cpu(hdr->ops.get)) { + case SND_SOC_AR_TPLG_FE_BE_GRAPH_CTL_MIX: + sm = (struct soc_mixer_control *)kc->private_value; + dobj = &sm->dobj; + ret = audioreach_control_load_mix(scomp, scontrol, kc, hdr); + break; + case SND_SOC_AR_TPLG_VOL_CTL: + sm = (struct soc_mixer_control *)kc->private_value; + dobj = &sm->dobj; + break; + default: + dev_warn(scomp->dev, "control type not supported %d:%d:%d\n", + hdr->ops.get, hdr->ops.put, hdr->ops.info); + kfree(scontrol); + return -EINVAL; + } + + dobj->private = scontrol; + return ret; +} + +static int audioreach_control_unload(struct snd_soc_component *scomp, + struct snd_soc_dobj *dobj) +{ + struct snd_ar_control *scontrol = dobj->private; + + kfree(scontrol); + + return 0; +} + +static const struct snd_soc_tplg_kcontrol_ops audioreach_io_ops[] = { + {SND_SOC_AR_TPLG_FE_BE_GRAPH_CTL_MIX, audioreach_get_audio_mixer, + audioreach_put_audio_mixer, snd_soc_info_volsw}, + {SND_SOC_AR_TPLG_VOL_CTL, audioreach_get_vol_ctrl_audio_mixer, + audioreach_put_vol_ctrl_audio_mixer, snd_soc_info_volsw}, +}; + +static struct snd_soc_tplg_ops audioreach_tplg_ops = { + .io_ops = audioreach_io_ops, + .io_ops_count = ARRAY_SIZE(audioreach_io_ops), + + .control_load = audioreach_control_load, + .control_unload = audioreach_control_unload, + + .widget_ready = audioreach_widget_ready, + .widget_unload = audioreach_widget_unload, + + .complete = audioreach_tplg_complete, + .link_load = audioreach_link_load, + + .dapm_route_load = audioreach_route_load, + .dapm_route_unload = audioreach_route_unload, +}; + +int audioreach_tplg_init(struct snd_soc_component *component) +{ + struct snd_soc_card *card = component->card; + struct device *dev = component->dev; + const struct firmware *fw; + char *tplg_fw_name; + int ret; + + /* Inline with Qualcomm UCM configs and linux-firmware path */ + tplg_fw_name = kasprintf(GFP_KERNEL, "qcom/%s/%s-tplg.bin", card->driver_name, card->name); + if (!tplg_fw_name) + return -ENOMEM; + + ret = request_firmware(&fw, tplg_fw_name, dev); + if (ret < 0) { + dev_err(dev, "tplg firmware loading %s failed %d \n", tplg_fw_name, ret); + goto err; + } + + ret = snd_soc_tplg_component_load(component, &audioreach_tplg_ops, fw); + if (ret < 0) { + dev_err(dev, "tplg component load failed%d\n", ret); + ret = -EINVAL; + } + + release_firmware(fw); +err: + kfree(tplg_fw_name); + + return ret; +} +EXPORT_SYMBOL_GPL(audioreach_tplg_init); -- cgit v1.2.3 From 99ce45d5e7dbde399997a630f45ac9f654fa4bcc Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 26 Oct 2021 09:57:28 +0800 Subject: mctp: Implement extended addressing This change allows an extended address struct - struct sockaddr_mctp_ext - to be passed to sendmsg/recvmsg. This allows userspace to specify output ifindex and physical address information (for sendmsg) or receive the input ifindex/physaddr for incoming messages (for recvmsg). This is typically used by userspace for MCTP address discovery and assignment operations. The extended addressing facility is conditional on a new sockopt: MCTP_OPT_ADDR_EXT; userspace must explicitly enable addressing before the kernel will consume/populate the extended address data. Includes a fix for an uninitialised var: Reported-by: kernel test robot Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/net/mctp.h | 13 +++++-- include/uapi/linux/mctp.h | 11 ++++++ net/mctp/af_mctp.c | 86 ++++++++++++++++++++++++++++++++++++----- net/mctp/route.c | 98 +++++++++++++++++++++++++++++++++++------------ 5 files changed, 170 insertions(+), 39 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7612d760b6a9..8ef26d89ef49 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -365,6 +365,7 @@ struct ucred { #define SOL_TLS 282 #define SOL_XDP 283 #define SOL_MPTCP 284 +#define SOL_MCTP 285 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/mctp.h b/include/net/mctp.h index 2a83443bdfac..23bec708f4c7 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -11,6 +11,7 @@ #include #include +#include #include #include @@ -58,6 +59,9 @@ struct mctp_sock { mctp_eid_t bind_addr; __u8 bind_type; + /* sendmsg()/recvmsg() uses struct sockaddr_mctp_ext */ + bool addr_ext; + /* list of mctp_sk_key, for incoming tag lookup. updates protected * by sk->net->keys_lock */ @@ -153,7 +157,10 @@ struct mctp_sk_key { struct mctp_skb_cb { unsigned int magic; unsigned int net; + int ifindex; /* extended/direct addressing if set */ mctp_eid_t src; + unsigned char halen; + unsigned char haddr[MAX_ADDR_LEN]; }; /* skb control-block accessors with a little extra debugging for initial @@ -177,6 +184,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) { struct mctp_skb_cb *cb = (void *)skb->cb; + BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb)); WARN_ON(cb->magic != 0x4d435450); return (void *)(skb->cb); } @@ -189,8 +197,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) * * Updates to the route table are performed under rtnl; all reads under RCU, * so routes cannot be referenced over a RCU grace period. Specifically: A - * caller cannot block between mctp_route_lookup and passing the route to - * mctp_do_route. + * caller cannot block between mctp_route_lookup and mctp_route_release() */ struct mctp_route { mctp_eid_t min, max; @@ -210,8 +217,6 @@ struct mctp_route { struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, mctp_eid_t daddr); -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); - int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 6acd4ccafbf7..07b0318716fc 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -11,6 +11,7 @@ #include #include +#include typedef __u8 mctp_eid_t; @@ -28,6 +29,14 @@ struct sockaddr_mctp { __u8 __smctp_pad1; }; +struct sockaddr_mctp_ext { + struct sockaddr_mctp smctp_base; + int smctp_ifindex; + __u8 smctp_halen; + __u8 __smctp_pad0[3]; + __u8 smctp_haddr[MAX_ADDR_LEN]; +}; + #define MCTP_NET_ANY 0x0 #define MCTP_ADDR_NULL 0x00 @@ -36,4 +45,6 @@ struct sockaddr_mctp { #define MCTP_TAG_MASK 0x07 #define MCTP_TAG_OWNER 0x08 +#define MCTP_OPT_ADDR_EXT 1 + #endif /* __UAPI_MCTP_H */ diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 66a411d60b6c..d344b02a1cde 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -77,6 +77,7 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; struct sk_buff *skb; @@ -100,11 +101,6 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) - return -EHOSTUNREACH; - skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -116,19 +112,45 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) *(u8 *)skb_put(skb, 1) = addr->smctp_type; rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len); - if (rc < 0) { - kfree_skb(skb); - return rc; - } + if (rc < 0) + goto err_free; /* set up cb */ cb = __mctp_cb(skb); cb->net = addr->smctp_network; + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + + if (extaddr->smctp_halen > sizeof(cb->haddr)) { + rc = -EINVAL; + goto err_free; + } + + cb->ifindex = extaddr->smctp_ifindex; + cb->halen = extaddr->smctp_halen; + memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); + + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + } + rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, addr->smctp_tag); return rc ? : len; + +err_free: + kfree_skb(skb); + return rc; } static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, @@ -136,6 +158,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct sk_buff *skb; size_t msglen; u8 type; @@ -181,6 +204,16 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, addr->smctp_tag = hdr->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); msg->msg_namelen = sizeof(*addr); + + if (msk->addr_ext) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae, + msg->msg_name); + msg->msg_namelen = sizeof(*ae); + ae->smctp_ifindex = cb->ifindex; + ae->smctp_halen = cb->halen; + memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr)); + memcpy(ae->smctp_haddr, cb->haddr, cb->halen); + } } rc = len; @@ -196,12 +229,45 @@ out_free: static int mctp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { - return -EINVAL; + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + int val; + + if (level != SOL_MCTP) + return -EINVAL; + + if (optname == MCTP_OPT_ADDR_EXT) { + if (optlen != sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + msk->addr_ext = val; + return 0; + } + + return -ENOPROTOOPT; } static int mctp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + int len, val; + + if (level != SOL_MCTP) + return -EINVAL; + + if (get_user(len, optlen)) + return -EFAULT; + + if (optname == MCTP_OPT_ADDR_EXT) { + if (len != sizeof(int)) + return -EINVAL; + val = !!msk->addr_ext; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; + } + return -EINVAL; } diff --git a/net/mctp/route.c b/net/mctp/route.c index 82fb5ae524f6..c23ab3547ee5 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -434,6 +434,7 @@ static unsigned int mctp_route_mtu(struct mctp_route *rt) static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) { + struct mctp_skb_cb *cb = mctp_cb(skb); struct mctp_hdr *hdr = mctp_hdr(skb); char daddr_buf[MAX_ADDR_LEN]; char *daddr = NULL; @@ -448,9 +449,14 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) return -EMSGSIZE; } - /* If lookup fails let the device handle daddr==NULL */ - if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) - daddr = daddr_buf; + if (cb->ifindex) { + /* direct route; use the hwaddr we stashed in sendmsg */ + daddr = cb->haddr; + } else { + /* If lookup fails let the device handle daddr==NULL */ + if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) + daddr = daddr_buf; + } rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); @@ -649,16 +655,6 @@ static struct mctp_route *mctp_route_lookup_null(struct net *net, return NULL; } -/* sends a skb to rt and releases the route. */ -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb) -{ - int rc; - - rc = rt->output(rt, skb); - mctp_route_release(rt); - return rc; -} - static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, unsigned int mtu, u8 tag) { @@ -725,7 +721,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* copy message payload */ skb_copy_bits(skb, pos, skb_transport_header(skb2), size); - /* do route, but don't drop the rt reference */ + /* do route */ rc = rt->output(rt, skb2); if (rc) break; @@ -734,7 +730,6 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, pos += size; } - mctp_route_release(rt); consume_skb(skb); return rc; } @@ -744,15 +739,51 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb = mctp_cb(skb); + struct mctp_route tmp_rt; + struct net_device *dev; struct mctp_hdr *hdr; unsigned long flags; unsigned int mtu; mctp_eid_t saddr; + bool ext_rt; int rc; u8 tag; - if (WARN_ON(!rt->dev)) + rc = -ENODEV; + + if (rt) { + ext_rt = false; + dev = NULL; + + if (WARN_ON(!rt->dev)) + goto out_release; + + } else if (cb->ifindex) { + ext_rt = true; + rt = &tmp_rt; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex); + if (!dev) { + rcu_read_unlock(); + return rc; + } + + rt->dev = __mctp_dev_get(dev); + rcu_read_unlock(); + + if (!rt->dev) + goto out_release; + + /* establish temporary route - we set up enough to keep + * mctp_route_output happy + */ + rt->output = mctp_route_output; + rt->mtu = 0; + + } else { return -EINVAL; + } spin_lock_irqsave(&rt->dev->addrs_lock, flags); if (rt->dev->num_addrs == 0) { @@ -765,18 +796,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, spin_unlock_irqrestore(&rt->dev->addrs_lock, flags); if (rc) - return rc; + goto out_release; if (req_tag & MCTP_HDR_FLAG_TO) { rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag); if (rc) - return rc; + goto out_release; tag |= MCTP_HDR_FLAG_TO; } else { tag = req_tag; } - skb->protocol = htons(ETH_P_MCTP); skb->priority = 0; skb_reset_transport_header(skb); @@ -796,12 +826,22 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, mtu = mctp_route_mtu(rt); if (skb->len + sizeof(struct mctp_hdr) <= mtu) { - hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM | - tag; - return mctp_do_route(rt, skb); + hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | + MCTP_HDR_FLAG_EOM | tag; + rc = rt->output(rt, skb); } else { - return mctp_do_fragment_route(rt, skb, mtu, tag); + rc = mctp_do_fragment_route(rt, skb, mtu, tag); } + +out_release: + if (!ext_rt) + mctp_route_release(rt); + + if (dev) + dev_put(dev); + + return rc; + } /* route management */ @@ -942,8 +982,15 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX) goto err_drop; - cb = __mctp_cb(skb); + /* MCTP drivers must populate halen/haddr */ + if (dev->type == ARPHRD_MCTP) { + cb = mctp_cb(skb); + } else { + cb = __mctp_cb(skb); + cb->halen = 0; + } cb->net = READ_ONCE(mdev->net); + cb->ifindex = dev->ifindex; rt = mctp_route_lookup(net, cb->net, mh->dest); @@ -954,7 +1001,8 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, if (!rt) goto err_drop; - mctp_do_route(rt, skb); + rt->output(rt, skb); + mctp_route_release(rt); return NET_RX_SUCCESS; -- cgit v1.2.3 From 8d11a4f43ef4679be0908026907a7613b33d7127 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:33 -0300 Subject: fanotify: Reserve UAPI bits for FAN_FS_ERROR FAN_FS_ERROR allows reporting of event type FS_ERROR to userspace, which is a mechanism to report file system wide problems via fanotify. This commit preallocate userspace visible bits to match the FS_ERROR event. Link: https://lore.kernel.org/r/20211025192746.66445-19-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 1 + include/uapi/linux/fanotify.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index c64d61b673ca..8f152445d75c 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -752,6 +752,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR); BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); + BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 64553df9d735..2990731ddc8b 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -20,6 +20,7 @@ #define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_FS_ERROR 0x00008000 /* Filesystem error */ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ -- cgit v1.2.3 From 130a3c742107acff985541c28360c8b40203559c Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:42 -0300 Subject: fanotify: Emit generic error info for error event The error info is a record sent to users on FAN_FS_ERROR events documenting the type of error. It also carries an error count, documenting how many errors were observed since the last reporting. Link: https://lore.kernel.org/r/20211025192746.66445-28-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 1 + fs/notify/fanotify/fanotify.h | 1 + fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/fanotify.h | 7 +++++++ 4 files changed, 45 insertions(+) (limited to 'include/uapi') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 465f07e70e6d..af61425e6e3b 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -621,6 +621,7 @@ static struct fanotify_event *fanotify_alloc_error_event( return NULL; fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR; + fee->error = report->error; fee->err_count = 1; fee->fsid = *fsid; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index edd7587adcc5..d25f500bf7e7 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -205,6 +205,7 @@ FANOTIFY_NE(struct fanotify_event *event) struct fanotify_error_event { struct fanotify_event fae; + s32 error; /* Error reported by the Filesystem. */ u32 err_count; /* Suppressed errors count */ __kernel_fsid_t fsid; /* FSID this error refers to. */ diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ff4a7373f7a5..fb817028d0b6 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -115,6 +115,8 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) #define FANOTIFY_PIDFD_INFO_HDR_LEN \ sizeof(struct fanotify_event_info_pidfd) +#define FANOTIFY_ERROR_INFO_LEN \ + (sizeof(struct fanotify_event_info_error)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -139,6 +141,9 @@ static size_t fanotify_event_len(unsigned int info_mode, if (!info_mode) return event_len; + if (fanotify_is_error_event(event->mask)) + event_len += FANOTIFY_ERROR_INFO_LEN; + info = fanotify_event_info(event); if (fanotify_event_has_dir_fh(event)) { @@ -324,6 +329,28 @@ static int process_access_response(struct fsnotify_group *group, return -ENOENT; } +static size_t copy_error_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_event_info_error info; + struct fanotify_error_event *fee = FANOTIFY_EE(event); + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR; + info.hdr.pad = 0; + info.hdr.len = FANOTIFY_ERROR_INFO_LEN; + + if (WARN_ON(count < info.hdr.len)) + return -EFAULT; + + info.error = fee->error; + info.error_count = fee->err_count; + + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + return info.hdr.len; +} + static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, int info_type, const char *name, size_t name_len, @@ -530,6 +557,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_is_error_event(event->mask)) { + ret = copy_error_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 2990731ddc8b..bd1932c2074d 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -126,6 +126,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_DFID_NAME 2 #define FAN_EVENT_INFO_TYPE_DFID 3 #define FAN_EVENT_INFO_TYPE_PIDFD 4 +#define FAN_EVENT_INFO_TYPE_ERROR 5 /* Variable length info record following event metadata */ struct fanotify_event_info_header { @@ -160,6 +161,12 @@ struct fanotify_event_info_pidfd { __s32 pidfd; }; +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; + struct fanotify_response { __s32 fd; __u32 response; -- cgit v1.2.3 From 2cc1ae4878282c75a569e8ec677d569601c99dda Mon Sep 17 00:00:00 2001 From: Michael Weiß Date: Sat, 4 Sep 2021 11:59:28 +0200 Subject: dm: introduce audit event module for device mapper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To be able to send auditing events to user space, we introduce a generic dm-audit module. It provides helper functions to emit audit events through the kernel audit subsystem. We claim the AUDIT_DM_CTRL type=1336 and AUDIT_DM_EVENT type=1337 out of the audit event messages range in the corresponding userspace api in 'include/uapi/linux/audit.h' for those events. AUDIT_DM_CTRL is used to provide information about creation and destruction of device mapper targets which are triggered by user space admin control actions. AUDIT_DM_EVENT is used to provide information about actual errors during operation of the mapped device, showing e.g. integrity violations in audit log. Following commits to device mapper targets actually will make use of this to emit those events in relevant cases. The audit logs look like this if executing the following simple test: # dd if=/dev/zero of=test.img bs=1M count=1024 # losetup -f test.img # integritysetup -vD format --integrity sha256 -t 32 /dev/loop0 # integritysetup open -D /dev/loop0 --integrity sha256 integritytest # integritysetup status integritytest # integritysetup close integritytest # integritysetup open -D /dev/loop0 --integrity sha256 integritytest # integritysetup status integritytest # dd if=/dev/urandom of=/dev/loop0 bs=512 count=1 seek=100000 # dd if=/dev/mapper/integritytest of=/dev/null ------------------------- audit.log from auditd type=UNKNOWN[1336] msg=audit(1630425039.363:184): module=integrity op=ctr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425039.471:185): module=integrity op=dtr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425039.611:186): module=integrity op=ctr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425054.475:187): module=integrity op=dtr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425073.171:191): module=integrity op=ctr ppid=3807 pid=3883 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425087.239:192): module=integrity op=dtr ppid=3807 pid=3902 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425093.755:193): module=integrity op=ctr ppid=3807 pid=3906 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1337] msg=audit(1630425112.119:194): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:195): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:196): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:197): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:198): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:199): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:200): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:201): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:202): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:203): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 Signed-off-by: Michael Weiß Signed-off-by: Paul Moore # fix audit.h numbering Signed-off-by: Mike Snitzer --- drivers/md/Kconfig | 9 +++++ drivers/md/Makefile | 4 +++ drivers/md/dm-audit.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/md/dm-audit.h | 66 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/audit.h | 2 ++ 5 files changed, 165 insertions(+) create mode 100644 drivers/md/dm-audit.c create mode 100644 drivers/md/dm-audit.h (limited to 'include/uapi') diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index f45fb372e51b..1bc4f48e9765 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -642,4 +642,13 @@ config DM_ZONED If unsure, say N. +config DM_AUDIT + bool "DM audit events" + depends on AUDIT + help + Generate audit events for device-mapper. + + Enables audit logging of several security relevant events in the + particular device-mapper targets, especially the integrity target. + endif # MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 816945eeed7f..0454b0885b01 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -107,3 +107,7 @@ endif ifeq ($(CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG),y) dm-verity-objs += dm-verity-verify-sig.o endif + +ifeq ($(CONFIG_DM_AUDIT),y) +dm-mod-objs += dm-audit.o +endif diff --git a/drivers/md/dm-audit.c b/drivers/md/dm-audit.c new file mode 100644 index 000000000000..3049dfe67e50 --- /dev/null +++ b/drivers/md/dm-audit.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Creating audit records for mapped devices. + * + * Copyright (C) 2021 Fraunhofer AISEC. All rights reserved. + * + * Authors: Michael Weiß + */ + +#include +#include +#include +#include +#include + +#include "dm-audit.h" +#include "dm-core.h" + +static struct audit_buffer *dm_audit_log_start(int audit_type, + const char *dm_msg_prefix, + const char *op) +{ + struct audit_buffer *ab; + + if (audit_enabled == AUDIT_OFF) + return NULL; + + ab = audit_log_start(audit_context(), GFP_KERNEL, audit_type); + if (unlikely(!ab)) + return NULL; + + audit_log_format(ab, "module=%s op=%s", dm_msg_prefix, op); + return ab; +} + +void dm_audit_log_ti(int audit_type, const char *dm_msg_prefix, const char *op, + struct dm_target *ti, int result) +{ + struct audit_buffer *ab = NULL; + struct mapped_device *md = dm_table_get_md(ti->table); + int dev_major = dm_disk(md)->major; + int dev_minor = dm_disk(md)->first_minor; + + switch (audit_type) { + case AUDIT_DM_CTRL: + ab = dm_audit_log_start(audit_type, dm_msg_prefix, op); + if (unlikely(!ab)) + return; + audit_log_task_info(ab); + audit_log_format(ab, " dev=%d:%d error_msg='%s'", dev_major, + dev_minor, !result ? ti->error : "success"); + break; + case AUDIT_DM_EVENT: + ab = dm_audit_log_start(audit_type, dm_msg_prefix, op); + if (unlikely(!ab)) + return; + audit_log_format(ab, " dev=%d:%d sector=?", dev_major, + dev_minor); + break; + default: /* unintended use */ + return; + } + + audit_log_format(ab, " res=%d", result); + audit_log_end(ab); +} +EXPORT_SYMBOL_GPL(dm_audit_log_ti); + +void dm_audit_log_bio(const char *dm_msg_prefix, const char *op, + struct bio *bio, sector_t sector, int result) +{ + struct audit_buffer *ab; + int dev_major = MAJOR(bio->bi_bdev->bd_dev); + int dev_minor = MINOR(bio->bi_bdev->bd_dev); + + ab = dm_audit_log_start(AUDIT_DM_EVENT, dm_msg_prefix, op); + if (unlikely(!ab)) + return; + + audit_log_format(ab, " dev=%d:%d sector=%llu res=%d", + dev_major, dev_minor, sector, result); + audit_log_end(ab); +} +EXPORT_SYMBOL_GPL(dm_audit_log_bio); diff --git a/drivers/md/dm-audit.h b/drivers/md/dm-audit.h new file mode 100644 index 000000000000..2385f2b659be --- /dev/null +++ b/drivers/md/dm-audit.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Creating audit records for mapped devices. + * + * Copyright (C) 2021 Fraunhofer AISEC. All rights reserved. + * + * Authors: Michael Weiß + */ + +#ifndef DM_AUDIT_H +#define DM_AUDIT_H + +#include +#include + +#ifdef CONFIG_DM_AUDIT +void dm_audit_log_bio(const char *dm_msg_prefix, const char *op, + struct bio *bio, sector_t sector, int result); + +/* + * dm_audit_log_ti() is not intended to be used directly in dm modules, + * the wrapper functions below should be called by dm modules instead. + */ +void dm_audit_log_ti(int audit_type, const char *dm_msg_prefix, const char *op, + struct dm_target *ti, int result); + +static inline void dm_audit_log_ctr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ + dm_audit_log_ti(AUDIT_DM_CTRL, dm_msg_prefix, "ctr", ti, result); +} + +static inline void dm_audit_log_dtr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ + dm_audit_log_ti(AUDIT_DM_CTRL, dm_msg_prefix, "dtr", ti, result); +} + +static inline void dm_audit_log_target(const char *dm_msg_prefix, const char *op, + struct dm_target *ti, int result) +{ + dm_audit_log_ti(AUDIT_DM_EVENT, dm_msg_prefix, op, ti, result); +} +#else +static inline void dm_audit_log_bio(const char *dm_msg_prefix, const char *op, + struct bio *bio, sector_t sector, + int result) +{ +} +static inline void dm_audit_log_target(const char *dm_msg_prefix, + const char *op, struct dm_target *ti, + int result) +{ +} +static inline void dm_audit_log_ctr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ +} + +static inline void dm_audit_log_dtr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ +} +#endif + +#endif diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..809e4c2041b3 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,8 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_DM_CTRL 1338 /* Device Mapper target control */ +#define AUDIT_DM_EVENT 1339 /* Device Mapper events */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ -- cgit v1.2.3 From 0f166e1257a1e24571381b857632b6c7c6ac3a0b Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 27 Oct 2021 21:55:28 +0900 Subject: ALSA: firewire-motu: refine parser for meter information in register DSP models After further investigation, I realize that the total number of elements in array is not enough to store all of related messages from device. This commit refines meter array and message parser. In terms of channel identifier, register DSP models are classified to two categories: 1. the target of output is selectable 828mk2, 896hd, and Traveler are in the category. They transfer messages with channel identifier between 0x00 and 0x13 for input meters, therefore 20 elements are needed to store. On the other hand, they transfer messages with channel identifier for one pair of output meters. The selection is done by asynchronous write transaction to offset 0x'ffff'f000'0b2c. The table for relationship between written value and available identifiers is below: ============= =============== written value identifier pair ============= =============== 0x00000b00 0x80/0x81 0x00000b01 0x82/0x83 ... ... 0x00000b0b 0x96/0x97 ... ... 0x00000b10 0xa0/0xa1 ... ... 0x00000b3f 0xfe/0xff ... ... greater 0xfe/0xff ============= =============== Actually in the above three models, 0x96/0x97 pair is the maximum. Thus the number of available output meter is 24. 2. all of output is available 8 pre, Ultralite, Audio Express, and 4 pre are in the category. They transfer messages for output meters without any selection. The table for available identifier for each direction is below: ============== ========= ========== model input output ============== ========= ========== 8 pre 0x00-0x0f 0x82-0x8d Ultralite 0x00-0x09 0x82-0x8f Audio Express 0x00-0x09 0x80-0x8d 4 pre 0x00-0x09 0x80-0x8d ============== ========= ========== Some of available identifiers might not be used for actual output meters. Anyway, 24 plus 24 elements accommodate the input/output meters. I note that isochronous packet from V3HD/V4HD deliver no message. Notification by asynchronous transaction to registered address seems to be used for the purpose as well as for change of mixer parameter. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211027125529.54295-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 5 ++++- sound/firewire/motu/motu-register-dsp-message-parser.c | 14 +++++++++----- 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index e52a97b3ceaa..68eb0e43c052 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -141,7 +141,10 @@ struct snd_firewire_tascam_state { * up to 12. */ -#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT 40 +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_INPUT_COUNT 24 +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_OUTPUT_COUNT 24 +#define SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT \ + (SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_INPUT_COUNT + SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_OUTPUT_COUNT) /** * struct snd_firewire_motu_register_dsp_meter - the container for meter information in DSP diff --git a/sound/firewire/motu/motu-register-dsp-message-parser.c b/sound/firewire/motu/motu-register-dsp-message-parser.c index cbc06b3b70f6..0c587567540f 100644 --- a/sound/firewire/motu/motu-register-dsp-message-parser.c +++ b/sound/firewire/motu/motu-register-dsp-message-parser.c @@ -335,11 +335,15 @@ void snd_motu_register_dsp_message_parser_parse(struct snd_motu *motu, const str else pos = b[MSG_METER_IDX_POS_4PRE_AE]; - if (pos < 0x80) - pos &= 0x1f; - else - pos = (pos & 0x1f) + 20; - parser->meter.data[pos] = val; + if (pos < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_INPUT_COUNT) { + parser->meter.data[pos] = val; + } else if (pos >= 0x80) { + pos -= (0x80 - SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_INPUT_COUNT); + + if (pos < SNDRV_FIREWIRE_MOTU_REGISTER_DSP_METER_COUNT) + parser->meter.data[pos] = val; + } + // The message for meter is interruptible to the series of other // types of messages. Don't cache it. fallthrough; -- cgit v1.2.3 From 407359d44ed33974137b9158da356d53f999dcf2 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 27 Oct 2021 21:55:29 +0900 Subject: ALSA: firewire-motu: export meter information to userspace as float value In command DSP models, one meter information consists of 4 bytes for IEEE 764 floating point (binary32). In previous patch, it is exported to userspace as 32 bit storage since the storage is also handled in ALSA firewire-motu driver as well in kernel space in which floating point arithmetic is not preferable. On the other hand, ALSA firewire-motu driver doesn't perform floating point calculation. The driver just gather meter information from isochronous packets and fill structure fields for userspace. In 'header' target of Kbuild, UAPI headers are processed before installed. In this timing, #ifdef macro with __KERNEL__ is removed. This mechanism is useful in the case so that the 32 bit storage can be accessible as u32 type in kernel space and float type in user space. We can see the same usage in ''struct acct_v3' in 'include/uapi/linux/acct.h'. This commit is for the above idea. Additionally, due to message protocol, meter information is filled with 0xffffffff in the end of period but 0xffffffff is invalid as binary32. To avoid confusion in userspace application, the last two elements are left without any assignment. Suggested-by: Takashi Iwai Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211027125529.54295-4-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 8 +++++--- sound/firewire/motu/motu-command-dsp-message-parser.c | 7 +++++-- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 68eb0e43c052..39cf6eb75940 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -248,12 +248,14 @@ struct snd_firewire_motu_register_dsp_parameter { * * The structure expresses the part of DSP status for hardware meter. The 32 bit storage is * estimated to include IEEE 764 32 bit single precision floating point (binary32) value. It is - * expected to be linear value (not logarithm) for audio signal level between 0.0 and +1.0. However, - * the last two quadlets (data[398] and data[399]) are filled with 0xffffffff since they are the - * marker of one period. + * expected to be linear value (not logarithm) for audio signal level between 0.0 and +1.0. */ struct snd_firewire_motu_command_dsp_meter { +#ifdef __KERNEL__ __u32 data[SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT]; +#else + float data[SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT]; +#endif }; #endif /* _UAPI_SOUND_FIREWIRE_H_INCLUDED */ diff --git a/sound/firewire/motu/motu-command-dsp-message-parser.c b/sound/firewire/motu/motu-command-dsp-message-parser.c index 18689fcfb288..9efe4d364baf 100644 --- a/sound/firewire/motu/motu-command-dsp-message-parser.c +++ b/sound/firewire/motu/motu-command-dsp-message-parser.c @@ -141,12 +141,15 @@ void snd_motu_command_dsp_message_parser_parse(struct snd_motu *motu, const stru ++parser->fragment_pos; if (parser->fragment_pos == 4) { + // Skip the last two quadlets since they could be + // invalid value (0xffffffff) as floating point + // number. if (parser->value_index < - SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT) { + SNDRV_FIREWIRE_MOTU_COMMAND_DSP_METER_COUNT - 2) { u32 val = (u32)(parser->value >> 32); parser->meter.data[parser->value_index] = val; - ++parser->value_index; } + ++parser->value_index; parser->fragment_pos = 0; } -- cgit v1.2.3 From 31fa8cbce4664946a1688898410fee41ad05364d Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 28 Oct 2021 02:31:40 +0300 Subject: drm: Add R10 and R12 FourCC Add FourCCs for 10- and 12-bit red formats with padding to 16 bits. They correspond to the V4L2 10- and 12-bit greyscale (V4L2_PIX_FMT_Y10 and V4L2_PIX_FMT_Y12) formats, as well as the Bayer formats with the same bit depth (V4L2_PIX_FMT_SBGGR{10,12} and all other Bayer pattern permutations). These formats are not used by any kernel driver at this point, but need to be exposed to applications by libcamera, which uses DRM FourCCs for pixel formats. Signed-off-by: Laurent Pinchart Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20211027233140.12268-1-laurent.pinchart@ideasonboard.com --- drivers/gpu/drm/drm_fourcc.c | 2 ++ include/uapi/drm/drm_fourcc.h | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 783844bfecc1..25837b1d6639 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -134,6 +134,8 @@ const struct drm_format_info *__drm_format_info(u32 format) static const struct drm_format_info formats[] = { { .format = DRM_FORMAT_C8, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_R8, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, + { .format = DRM_FORMAT_R10, .depth = 10, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, + { .format = DRM_FORMAT_R12, .depth = 12, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_RGB332, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_BGR233, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_XRGB4444, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 45a914850be0..7f652c96845b 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -104,6 +104,12 @@ extern "C" { /* 8 bpp Red */ #define DRM_FORMAT_R8 fourcc_code('R', '8', ' ', ' ') /* [7:0] R */ +/* 10 bpp Red */ +#define DRM_FORMAT_R10 fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */ + +/* 12 bpp Red */ +#define DRM_FORMAT_R12 fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */ + /* 16 bpp Red */ #define DRM_FORMAT_R16 fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */ -- cgit v1.2.3 From a390ccb316beb8ea594b8695d53926710ca454a3 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 24 Oct 2021 16:26:07 +0300 Subject: fuse: add FOPEN_NOFLUSH Add flag returned by FUSE_OPEN and FUSE_CREATE requests to avoid flushing data cache on close. Different filesystems implement ->flush() is different ways: - Most disk filesystems do not implement ->flush() at all - Some network filesystem (e.g. nfs) flush local write cache of FMODE_WRITE file and send a "flush" command to server - Some network filesystem (e.g. cifs) flush local write cache of FMODE_WRITE file without sending an additional command to server FUSE flushes local write cache of ANY file, even non FMODE_WRITE and sends a "flush" command to server (if server implements it). The FUSE implementation of ->flush() seems over agressive and arbitrary and does not make a lot of sense when writeback caching is disabled. Instead of deciding on another arbitrary implementation that makes sense, leave the choice of per-file flush behavior in the hands of the server. Link: https://lore.kernel.org/linux-fsdevel/CAJfpegspE8e6aKd47uZtSYX8Y-1e1FWS0VL0DH2Skb9gQP5RJQ@mail.gmail.com/ Suggested-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 3 +++ include/uapi/linux/fuse.h | 7 ++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 26730e699d68..b7f1a164e18a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -476,6 +476,9 @@ static int fuse_flush(struct file *file, fl_owner_t id) if (fuse_is_bad(inode)) return -EIO; + if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache) + return 0; + err = write_inode_now(inode, 1); if (err) return err; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 36ed092227fa..a1dc3ee1d17c 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -184,6 +184,9 @@ * * 7.34 * - add FUSE_SYNCFS + * + * 7.35 + * - add FOPEN_NOFLUSH */ #ifndef _LINUX_FUSE_H @@ -219,7 +222,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 34 +#define FUSE_KERNEL_MINOR_VERSION 35 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -290,12 +293,14 @@ struct fuse_file_lock { * FOPEN_NONSEEKABLE: the file is not seekable * FOPEN_CACHE_DIR: allow caching this directory * FOPEN_STREAM: the file is stream-like (no file position at all) + * FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE) */ #define FOPEN_DIRECT_IO (1 << 0) #define FOPEN_KEEP_CACHE (1 << 1) #define FOPEN_NONSEEKABLE (1 << 2) #define FOPEN_CACHE_DIR (1 << 3) #define FOPEN_STREAM (1 << 4) +#define FOPEN_NOFLUSH (1 << 5) /** * INIT request/reply flags -- cgit v1.2.3 From 72f4c9d57082cdd4054b599b3387220efd944095 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Oct 2021 15:06:34 -0400 Subject: drm/amdgpu/UAPI: rearrange header to better align related items MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the RAS query parameters to align with the INFO query where they are used. No functional change. Reviewed-by: Christian König Reviewed-by: Luben Tuikov Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 0cbd1540aeac..26e45fc5eb1a 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -786,13 +786,6 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_VRAM_LOST_COUNTER 0x1F /* query ras mask of enabled features*/ #define AMDGPU_INFO_RAS_ENABLED_FEATURES 0x20 -/* query video encode/decode caps */ -#define AMDGPU_INFO_VIDEO_CAPS 0x21 - /* Subquery id: Decode */ - #define AMDGPU_INFO_VIDEO_CAPS_DECODE 0 - /* Subquery id: Encode */ - #define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1 - /* RAS MASK: UMC (VRAM) */ #define AMDGPU_INFO_RAS_ENABLED_UMC (1 << 0) /* RAS MASK: SDMA */ @@ -821,6 +814,12 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_RAS_ENABLED_MP1 (1 << 12) /* RAS MASK: FUSE */ #define AMDGPU_INFO_RAS_ENABLED_FUSE (1 << 13) +/* query video encode/decode caps */ +#define AMDGPU_INFO_VIDEO_CAPS 0x21 + /* Subquery id: Decode */ + #define AMDGPU_INFO_VIDEO_CAPS_DECODE 0 + /* Subquery id: Encode */ + #define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT 0 #define AMDGPU_INFO_MMR_SE_INDEX_MASK 0xff -- cgit v1.2.3 From 9330986c03006ab1d33d243b7cfe598a7a3c1baa Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 27 Oct 2021 16:45:00 -0700 Subject: bpf: Add bloom filter map implementation This patch adds the kernel-side changes for the implementation of a bpf bloom filter map. The bloom filter map supports peek (determining whether an element is present in the map) and push (adding an element to the map) operations.These operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_UPDATE_ELEM -> push The bloom filter map does not have keys, only values. In light of this, the bloom filter map's API matches that of queue stack maps: user applications use BPF_MAP_LOOKUP_ELEM/BPF_MAP_UPDATE_ELEM which correspond internally to bpf_map_peek_elem/bpf_map_push_elem, and bpf programs must use the bpf_map_peek_elem and bpf_map_push_elem APIs to query or add an element to the bloom filter map. When the bloom filter map is created, it must be created with a key_size of 0. For updates, the user will pass in the element to add to the map as the value, with a NULL key. For lookups, the user will pass in the element to query in the map as the value, with a NULL key. In the verifier layer, this requires us to modify the argument type of a bloom filter's BPF_FUNC_map_peek_elem call to ARG_PTR_TO_MAP_VALUE; as well, in the syscall layer, we need to copy over the user value so that in bpf_map_peek_elem, we know which specific value to query. A few things to please take note of: * If there are any concurrent lookups + updates, the user is responsible for synchronizing this to ensure no false negative lookups occur. * The number of hashes to use for the bloom filter is configurable from userspace. If no number is specified, the default used will be 5 hash functions. The benchmarks later in this patchset can help compare the performance of using different number of hashes on different entry sizes. In general, using more hashes decreases both the false positive rate and the speed of a lookup. * Deleting an element in the bloom filter map is not supported. * The bloom filter map may be used as an inner map. * The "max_entries" size that is specified at map creation time is used to approximate a reasonable bitmap size for the bloom filter, and is not otherwise strictly enforced. If the user wishes to insert more entries into the bloom filter than "max_entries", they may do so but they should be aware that this may lead to a higher false positive rate. Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211027234504.30744-2-joannekoong@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 9 ++ kernel/bpf/Makefile | 2 +- kernel/bpf/bloom_filter.c | 195 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 24 ++++- kernel/bpf/verifier.c | 19 +++- tools/include/uapi/linux/bpf.h | 9 ++ 8 files changed, 253 insertions(+), 7 deletions(-) create mode 100644 kernel/bpf/bloom_filter.c (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 31421c74ba08..50105e0b8fcc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -169,6 +169,7 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; + u64 map_extra; /* any per-map-type extra fields */ int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..c4424ac2fa02 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 7f33098ca63f..cf6ca339f3cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,7 +7,7 @@ endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c new file mode 100644 index 000000000000..7c50232b7571 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include +#include +#include +#include +#include +#include + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +struct bpf_bloom_filter { + struct bpf_map map; + u32 bitset_mask; + u32 hash_seed; + /* If the size of the values in the bloom filter is u32 aligned, + * then it is more performant to use jhash2 as the underlying hash + * function, else we use jhash. This tracks the number of u32s + * in an u32-aligned value size. If the value size is not u32 aligned, + * this will be 0. + */ + u32 aligned_u32_count; + u32 nr_hash_funcs; + unsigned long bitset[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + if (bloom->aligned_u32_count) + h = jhash2(value, bloom->aligned_u32_count, + bloom->hash_seed + index); + else + h = jhash(value, value_size, bloom->hash_seed + index); + + return h & bloom->bitset_mask; +} + +static int peek_elem(struct bpf_map *map, void *value) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +static int push_elem(struct bpf_map *map, void *value, u64 flags) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static int pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static struct bpf_map *map_alloc(union bpf_attr *attr) +{ + u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_bloom_filter *bloom; + + if (!bpf_capable()) + return ERR_PTR(-EPERM); + + if (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + /* The lower 4 bits of map_extra specify the number of hash functions */ + nr_hash_funcs = attr->map_extra & 0xF; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, attr); + + bloom->nr_hash_funcs = nr_hash_funcs; + bloom->bitset_mask = bitset_mask; + + /* Check whether the value size is u32-aligned */ + if ((attr->value_size & (sizeof(u32) - 1)) == 0) + bloom->aligned_u32_count = + attr->value_size / sizeof(u32); + + if (!(attr->map_flags & BPF_F_ZERO_SEED)) + bloom->hash_seed = get_random_int(); + + return &bloom->map; +} + +static void map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +static int update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + /* The eBPF program should use map_push_elem instead */ + return -EINVAL; +} + +static int check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + return btf_type_is_void(key_type) ? 0 : -EINVAL; +} + +static int bpf_bloom_btf_id; +const struct bpf_map_ops bloom_filter_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = map_alloc, + .map_free = map_free, + .map_push_elem = push_elem, + .map_peek_elem = peek_elem, + .map_pop_elem = pop_elem, + .map_lookup_elem = lookup_elem, + .map_update_elem = update_elem, + .map_check_btf = check_btf, + .map_btf_name = "bpf_bloom_filter", + .map_btf_id = &bpf_bloom_btf_id, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3e1c024ce3ed..f7c2c6354add 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -199,7 +199,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); @@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -553,6 +556,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -561,6 +565,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, + (unsigned long long)map->map_extra, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); @@ -810,7 +815,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -831,6 +836,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -1080,6 +1089,14 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -3881,6 +3898,7 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6616e325803..3c8aa7df1773 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5002,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, return -EINVAL; } break; - + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; default: break; } @@ -5577,6 +5580,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -5644,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; - case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: - case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { -- cgit v1.2.3 From d6aef08a872b9e23eecc92d0e92393473b13c497 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 28 Oct 2021 12:04:54 +0530 Subject: bpf: Add bpf_kallsyms_lookup_name helper This helper allows us to get the address of a kernel symbol from inside a BPF_PROG_TYPE_SYSCALL prog (used by gen_loader), so that we can relocate typeless ksym vars. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211028063501.2239335-2-memxor@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/bpf/syscall.c | 27 +++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 60 insertions(+) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50105e0b8fcc..6deebf8bf78f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2110,6 +2110,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f7c2c6354add..e12a217ead34 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4781,6 +4781,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -4791,6 +4816,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From e77fbf990316d47968a793d8aa920fd62385aec9 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 22 Oct 2021 16:53:36 +0200 Subject: btrfs: send: prepare for v2 protocol This is preparatory work for send protocol update to version 2 and higher. We have many pending protocol update requests but still don't have the basic protocol rev in place, the first thing that must happen is to do the actual versioning support. The protocol version is u32 and is a new member in the send ioctl struct. Validity of the version field is backed by a new flag bit. Old kernels would fail when a higher version is requested. Version protocol 0 will pick the highest supported version, BTRFS_SEND_STREAM_VERSION, that's also exported in sysfs. The version is still unchanged and will be increased once we have new incompatible commands or stream updates. Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 3 ++- fs/btrfs/send.c | 23 +++++++++++++++++++++++ fs/btrfs/send.h | 7 +++++++ include/uapi/linux/btrfs.h | 11 +++++++++-- 4 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c474f7e24163..92424a22d8d6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -82,7 +82,8 @@ struct btrfs_ioctl_send_args_32 { compat_uptr_t clone_sources; /* in */ __u64 parent_root; /* in */ __u64 flags; /* in */ - __u64 reserved[4]; /* in */ + __u32 version; /* in */ + __u8 reserved[28]; /* in */ } __attribute__ ((__packed__)); #define BTRFS_IOC_SEND_32 _IOW(BTRFS_IOCTL_MAGIC, 38, \ diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index afdcbe7844e0..040324d71118 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -84,6 +84,8 @@ struct send_ctx { u64 total_send_size; u64 cmd_send_size[BTRFS_SEND_C_MAX + 1]; u64 flags; /* 'flags' member of btrfs_ioctl_send_args is u64 */ + /* Protocol version compatibility requested */ + u32 proto; struct btrfs_root *send_root; struct btrfs_root *parent_root; @@ -312,6 +314,16 @@ static void inconsistent_snapshot_error(struct send_ctx *sctx, sctx->parent_root->root_key.objectid : 0)); } +__maybe_unused +static bool proto_cmd_ok(const struct send_ctx *sctx, int cmd) +{ + switch (sctx->proto) { + case 1: return cmd < __BTRFS_SEND_C_MAX_V1; + case 2: return cmd < __BTRFS_SEND_C_MAX_V2; + default: return false; + } +} + static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * @@ -7269,6 +7281,17 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) sctx->flags = arg->flags; + if (arg->flags & BTRFS_SEND_FLAG_VERSION) { + if (arg->version > BTRFS_SEND_STREAM_VERSION) { + ret = -EPROTO; + goto out; + } + /* Zero means "use the highest version" */ + sctx->proto = arg->version ?: BTRFS_SEND_STREAM_VERSION; + } else { + sctx->proto = 1; + } + sctx->send_filp = fget(arg->send_fd); if (!sctx->send_filp) { ret = -EBADF; diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h index de91488b7cd0..23bcefc84e49 100644 --- a/fs/btrfs/send.h +++ b/fs/btrfs/send.h @@ -48,6 +48,7 @@ struct btrfs_tlv_header { enum btrfs_send_cmd { BTRFS_SEND_C_UNSPEC, + /* Version 1 */ BTRFS_SEND_C_SUBVOL, BTRFS_SEND_C_SNAPSHOT, @@ -76,6 +77,12 @@ enum btrfs_send_cmd { BTRFS_SEND_C_END, BTRFS_SEND_C_UPDATE_EXTENT, + __BTRFS_SEND_C_MAX_V1, + + /* Version 2 */ + __BTRFS_SEND_C_MAX_V2, + + /* End */ __BTRFS_SEND_C_MAX, }; #define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index d7d3cfead056..738619994e26 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -771,10 +771,16 @@ struct btrfs_ioctl_received_subvol_args { */ #define BTRFS_SEND_FLAG_OMIT_END_CMD 0x4 +/* + * Read the protocol version in the structure + */ +#define BTRFS_SEND_FLAG_VERSION 0x8 + #define BTRFS_SEND_FLAG_MASK \ (BTRFS_SEND_FLAG_NO_FILE_DATA | \ BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \ - BTRFS_SEND_FLAG_OMIT_END_CMD) + BTRFS_SEND_FLAG_OMIT_END_CMD | \ + BTRFS_SEND_FLAG_VERSION) struct btrfs_ioctl_send_args { __s64 send_fd; /* in */ @@ -782,7 +788,8 @@ struct btrfs_ioctl_send_args { __u64 __user *clone_sources; /* in */ __u64 parent_root; /* in */ __u64 flags; /* in */ - __u64 reserved[4]; /* in */ + __u32 version; /* in */ + __u8 reserved[28]; /* in */ }; /* -- cgit v1.2.3 From cf2197ca4b8c199d188593ca6800ea1827c42171 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Fri, 29 Oct 2021 14:09:29 +0800 Subject: bcache: move uapi header bcache.h to bcache code directory The header file include/uapi/linux/bcache.h is not really a user space API heaer. This file defines the ondisk format of bcache internal meta data but no one includes it from user space, bcache-tools has its own copy of this header with minor modification. Therefore, this patch moves include/uapi/linux/bcache.h to bcache code directory as drivers/md/bcache/bcache_ondisk.h. Suggested-by: Arnd Bergmann Suggested-by: Christoph Hellwig Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20211029060930.119923-2-colyli@suse.de Signed-off-by: Jens Axboe --- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/bcache_ondisk.h | 445 ++++++++++++++++++++++++++++++++++++++ drivers/md/bcache/bset.h | 2 +- drivers/md/bcache/features.c | 2 +- drivers/md/bcache/features.h | 3 +- include/uapi/linux/bcache.h | 445 -------------------------------------- 6 files changed, 450 insertions(+), 449 deletions(-) create mode 100644 drivers/md/bcache/bcache_ondisk.h delete mode 100644 include/uapi/linux/bcache.h (limited to 'include/uapi') diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 941685409c68..9ed9c955add7 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -178,7 +178,6 @@ #define pr_fmt(fmt) "bcache: %s() " fmt, __func__ -#include #include #include #include @@ -190,6 +189,7 @@ #include #include +#include "bcache_ondisk.h" #include "bset.h" #include "util.h" #include "closure.h" diff --git a/drivers/md/bcache/bcache_ondisk.h b/drivers/md/bcache/bcache_ondisk.h new file mode 100644 index 000000000000..97413586195b --- /dev/null +++ b/drivers/md/bcache/bcache_ondisk.h @@ -0,0 +1,445 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_BCACHE_H +#define _LINUX_BCACHE_H + +/* + * Bcache on disk data structures + */ + +#include + +#define BITMASK(name, type, field, offset, size) \ +static inline __u64 name(const type *k) \ +{ return (k->field >> offset) & ~(~0ULL << size); } \ + \ +static inline void SET_##name(type *k, __u64 v) \ +{ \ + k->field &= ~(~(~0ULL << size) << offset); \ + k->field |= (v & ~(~0ULL << size)) << offset; \ +} + +/* Btree keys - all units are in sectors */ + +struct bkey { + __u64 high; + __u64 low; + __u64 ptr[]; +}; + +#define KEY_FIELD(name, field, offset, size) \ + BITMASK(name, struct bkey, field, offset, size) + +#define PTR_FIELD(name, offset, size) \ +static inline __u64 name(const struct bkey *k, unsigned int i) \ +{ return (k->ptr[i] >> offset) & ~(~0ULL << size); } \ + \ +static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ +{ \ + k->ptr[i] &= ~(~(~0ULL << size) << offset); \ + k->ptr[i] |= (v & ~(~0ULL << size)) << offset; \ +} + +#define KEY_SIZE_BITS 16 +#define KEY_MAX_U64S 8 + +KEY_FIELD(KEY_PTRS, high, 60, 3) +KEY_FIELD(__PAD0, high, 58, 2) +KEY_FIELD(KEY_CSUM, high, 56, 2) +KEY_FIELD(__PAD1, high, 55, 1) +KEY_FIELD(KEY_DIRTY, high, 36, 1) + +KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) +KEY_FIELD(KEY_INODE, high, 0, 20) + +/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */ + +static inline __u64 KEY_OFFSET(const struct bkey *k) +{ + return k->low; +} + +static inline void SET_KEY_OFFSET(struct bkey *k, __u64 v) +{ + k->low = v; +} + +/* + * The high bit being set is a relic from when we used it to do binary + * searches - it told you where a key started. It's not used anymore, + * and can probably be safely dropped. + */ +#define KEY(inode, offset, size) \ +((struct bkey) { \ + .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \ + .low = (offset) \ +}) + +#define ZERO_KEY KEY(0, 0, 0) + +#define MAX_KEY_INODE (~(~0 << 20)) +#define MAX_KEY_OFFSET (~0ULL >> 1) +#define MAX_KEY KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0) + +#define KEY_START(k) (KEY_OFFSET(k) - KEY_SIZE(k)) +#define START_KEY(k) KEY(KEY_INODE(k), KEY_START(k), 0) + +#define PTR_DEV_BITS 12 + +PTR_FIELD(PTR_DEV, 51, PTR_DEV_BITS) +PTR_FIELD(PTR_OFFSET, 8, 43) +PTR_FIELD(PTR_GEN, 0, 8) + +#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1) + +#define MAKE_PTR(gen, offset, dev) \ + ((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen) + +/* Bkey utility code */ + +static inline unsigned long bkey_u64s(const struct bkey *k) +{ + return (sizeof(struct bkey) / sizeof(__u64)) + KEY_PTRS(k); +} + +static inline unsigned long bkey_bytes(const struct bkey *k) +{ + return bkey_u64s(k) * sizeof(__u64); +} + +#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src)) + +static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) +{ + SET_KEY_INODE(dest, KEY_INODE(src)); + SET_KEY_OFFSET(dest, KEY_OFFSET(src)); +} + +static inline struct bkey *bkey_next(const struct bkey *k) +{ + __u64 *d = (void *) k; + + return (struct bkey *) (d + bkey_u64s(k)); +} + +static inline struct bkey *bkey_idx(const struct bkey *k, unsigned int nr_keys) +{ + __u64 *d = (void *) k; + + return (struct bkey *) (d + nr_keys); +} +/* Enough for a key with 6 pointers */ +#define BKEY_PAD 8 + +#define BKEY_PADDED(key) \ + union { struct bkey key; __u64 key ## _pad[BKEY_PAD]; } + +/* Superblock */ + +/* Version 0: Cache device + * Version 1: Backing device + * Version 2: Seed pointer into btree node checksum + * Version 3: Cache device with new UUID format + * Version 4: Backing device with data offset + */ +#define BCACHE_SB_VERSION_CDEV 0 +#define BCACHE_SB_VERSION_BDEV 1 +#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 +#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 +#define BCACHE_SB_VERSION_CDEV_WITH_FEATURES 5 +#define BCACHE_SB_VERSION_BDEV_WITH_FEATURES 6 +#define BCACHE_SB_MAX_VERSION 6 + +#define SB_SECTOR 8 +#define SB_OFFSET (SB_SECTOR << SECTOR_SHIFT) +#define SB_SIZE 4096 +#define SB_LABEL_SIZE 32 +#define SB_JOURNAL_BUCKETS 256U +/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */ +#define MAX_CACHES_PER_SET 8 + +#define BDEV_DATA_START_DEFAULT 16 /* sectors */ + +struct cache_sb_disk { + __le64 csum; + __le64 offset; /* sector where this sb was written */ + __le64 version; + + __u8 magic[16]; + + __u8 uuid[16]; + union { + __u8 set_uuid[16]; + __le64 set_magic; + }; + __u8 label[SB_LABEL_SIZE]; + + __le64 flags; + __le64 seq; + + __le64 feature_compat; + __le64 feature_incompat; + __le64 feature_ro_compat; + + __le64 pad[5]; + + union { + struct { + /* Cache devices */ + __le64 nbuckets; /* device size */ + + __le16 block_size; /* sectors */ + __le16 bucket_size; /* sectors */ + + __le16 nr_in_set; + __le16 nr_this_dev; + }; + struct { + /* Backing devices */ + __le64 data_offset; + + /* + * block_size from the cache device section is still used by + * backing devices, so don't add anything here until we fix + * things to not need it for backing devices anymore + */ + }; + }; + + __le32 last_mount; /* time overflow in y2106 */ + + __le16 first_bucket; + union { + __le16 njournal_buckets; + __le16 keys; + }; + __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ + __le16 obso_bucket_size_hi; /* obsoleted */ +}; + +/* + * This is for in-memory bcache super block. + * NOTE: cache_sb is NOT exactly mapping to cache_sb_disk, the member + * size, ordering and even whole struct size may be different + * from cache_sb_disk. + */ +struct cache_sb { + __u64 offset; /* sector where this sb was written */ + __u64 version; + + __u8 magic[16]; + + __u8 uuid[16]; + union { + __u8 set_uuid[16]; + __u64 set_magic; + }; + __u8 label[SB_LABEL_SIZE]; + + __u64 flags; + __u64 seq; + + __u64 feature_compat; + __u64 feature_incompat; + __u64 feature_ro_compat; + + union { + struct { + /* Cache devices */ + __u64 nbuckets; /* device size */ + + __u16 block_size; /* sectors */ + __u16 nr_in_set; + __u16 nr_this_dev; + __u32 bucket_size; /* sectors */ + }; + struct { + /* Backing devices */ + __u64 data_offset; + + /* + * block_size from the cache device section is still used by + * backing devices, so don't add anything here until we fix + * things to not need it for backing devices anymore + */ + }; + }; + + __u32 last_mount; /* time overflow in y2106 */ + + __u16 first_bucket; + union { + __u16 njournal_buckets; + __u16 keys; + }; + __u64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ +}; + +static inline _Bool SB_IS_BDEV(const struct cache_sb *sb) +{ + return sb->version == BCACHE_SB_VERSION_BDEV + || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET + || sb->version == BCACHE_SB_VERSION_BDEV_WITH_FEATURES; +} + +BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1); +BITMASK(CACHE_DISCARD, struct cache_sb, flags, 1, 1); +BITMASK(CACHE_REPLACEMENT, struct cache_sb, flags, 2, 3); +#define CACHE_REPLACEMENT_LRU 0U +#define CACHE_REPLACEMENT_FIFO 1U +#define CACHE_REPLACEMENT_RANDOM 2U + +BITMASK(BDEV_CACHE_MODE, struct cache_sb, flags, 0, 4); +#define CACHE_MODE_WRITETHROUGH 0U +#define CACHE_MODE_WRITEBACK 1U +#define CACHE_MODE_WRITEAROUND 2U +#define CACHE_MODE_NONE 3U +BITMASK(BDEV_STATE, struct cache_sb, flags, 61, 2); +#define BDEV_STATE_NONE 0U +#define BDEV_STATE_CLEAN 1U +#define BDEV_STATE_DIRTY 2U +#define BDEV_STATE_STALE 3U + +/* + * Magic numbers + * + * The various other data structures have their own magic numbers, which are + * xored with the first part of the cache set's UUID + */ + +#define JSET_MAGIC 0x245235c1a3625032ULL +#define PSET_MAGIC 0x6750e15f87337f91ULL +#define BSET_MAGIC 0x90135c78b99e07f5ULL + +static inline __u64 jset_magic(struct cache_sb *sb) +{ + return sb->set_magic ^ JSET_MAGIC; +} + +static inline __u64 pset_magic(struct cache_sb *sb) +{ + return sb->set_magic ^ PSET_MAGIC; +} + +static inline __u64 bset_magic(struct cache_sb *sb) +{ + return sb->set_magic ^ BSET_MAGIC; +} + +/* + * Journal + * + * On disk format for a journal entry: + * seq is monotonically increasing; every journal entry has its own unique + * sequence number. + * + * last_seq is the oldest journal entry that still has keys the btree hasn't + * flushed to disk yet. + * + * version is for on disk format changes. + */ + +#define BCACHE_JSET_VERSION_UUIDv1 1 +#define BCACHE_JSET_VERSION_UUID 1 /* Always latest UUID format */ +#define BCACHE_JSET_VERSION 1 + +struct jset { + __u64 csum; + __u64 magic; + __u64 seq; + __u32 version; + __u32 keys; + + __u64 last_seq; + + BKEY_PADDED(uuid_bucket); + BKEY_PADDED(btree_root); + __u16 btree_level; + __u16 pad[3]; + + __u64 prio_bucket[MAX_CACHES_PER_SET]; + + union { + struct bkey start[0]; + __u64 d[0]; + }; +}; + +/* Bucket prios/gens */ + +struct prio_set { + __u64 csum; + __u64 magic; + __u64 seq; + __u32 version; + __u32 pad; + + __u64 next_bucket; + + struct bucket_disk { + __u16 prio; + __u8 gen; + } __attribute((packed)) data[]; +}; + +/* UUIDS - per backing device/flash only volume metadata */ + +struct uuid_entry { + union { + struct { + __u8 uuid[16]; + __u8 label[32]; + __u32 first_reg; /* time overflow in y2106 */ + __u32 last_reg; + __u32 invalidated; + + __u32 flags; + /* Size of flash only volumes */ + __u64 sectors; + }; + + __u8 pad[128]; + }; +}; + +BITMASK(UUID_FLASH_ONLY, struct uuid_entry, flags, 0, 1); + +/* Btree nodes */ + +/* Version 1: Seed pointer into btree node checksum + */ +#define BCACHE_BSET_CSUM 1 +#define BCACHE_BSET_VERSION 1 + +/* + * Btree nodes + * + * On disk a btree node is a list/log of these; within each set the keys are + * sorted + */ +struct bset { + __u64 csum; + __u64 magic; + __u64 seq; + __u32 version; + __u32 keys; + + union { + struct bkey start[0]; + __u64 d[0]; + }; +}; + +/* OBSOLETE */ + +/* UUIDS - per backing device/flash only volume metadata */ + +struct uuid_entry_v0 { + __u8 uuid[16]; + __u8 label[32]; + __u32 first_reg; + __u32 last_reg; + __u32 invalidated; + __u32 pad; +}; + +#endif /* _LINUX_BCACHE_H */ diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index a50dcfda656f..d795c84246b0 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -2,10 +2,10 @@ #ifndef _BCACHE_BSET_H #define _BCACHE_BSET_H -#include #include #include +#include "bcache_ondisk.h" #include "util.h" /* for time_stats */ /* diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6d2b7b84a7b7..634922c5601d 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -6,7 +6,7 @@ * Copyright 2020 Coly Li * */ -#include +#include "bcache_ondisk.h" #include "bcache.h" #include "features.h" diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index d1c8fd3977fc..09161b89c63e 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -2,10 +2,11 @@ #ifndef _BCACHE_FEATURES_H #define _BCACHE_FEATURES_H -#include #include #include +#include "bcache_ondisk.h" + #define BCH_FEATURE_COMPAT 0 #define BCH_FEATURE_RO_COMPAT 1 #define BCH_FEATURE_INCOMPAT 2 diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h deleted file mode 100644 index 97413586195b..000000000000 --- a/include/uapi/linux/bcache.h +++ /dev/null @@ -1,445 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _LINUX_BCACHE_H -#define _LINUX_BCACHE_H - -/* - * Bcache on disk data structures - */ - -#include - -#define BITMASK(name, type, field, offset, size) \ -static inline __u64 name(const type *k) \ -{ return (k->field >> offset) & ~(~0ULL << size); } \ - \ -static inline void SET_##name(type *k, __u64 v) \ -{ \ - k->field &= ~(~(~0ULL << size) << offset); \ - k->field |= (v & ~(~0ULL << size)) << offset; \ -} - -/* Btree keys - all units are in sectors */ - -struct bkey { - __u64 high; - __u64 low; - __u64 ptr[]; -}; - -#define KEY_FIELD(name, field, offset, size) \ - BITMASK(name, struct bkey, field, offset, size) - -#define PTR_FIELD(name, offset, size) \ -static inline __u64 name(const struct bkey *k, unsigned int i) \ -{ return (k->ptr[i] >> offset) & ~(~0ULL << size); } \ - \ -static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ -{ \ - k->ptr[i] &= ~(~(~0ULL << size) << offset); \ - k->ptr[i] |= (v & ~(~0ULL << size)) << offset; \ -} - -#define KEY_SIZE_BITS 16 -#define KEY_MAX_U64S 8 - -KEY_FIELD(KEY_PTRS, high, 60, 3) -KEY_FIELD(__PAD0, high, 58, 2) -KEY_FIELD(KEY_CSUM, high, 56, 2) -KEY_FIELD(__PAD1, high, 55, 1) -KEY_FIELD(KEY_DIRTY, high, 36, 1) - -KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) -KEY_FIELD(KEY_INODE, high, 0, 20) - -/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */ - -static inline __u64 KEY_OFFSET(const struct bkey *k) -{ - return k->low; -} - -static inline void SET_KEY_OFFSET(struct bkey *k, __u64 v) -{ - k->low = v; -} - -/* - * The high bit being set is a relic from when we used it to do binary - * searches - it told you where a key started. It's not used anymore, - * and can probably be safely dropped. - */ -#define KEY(inode, offset, size) \ -((struct bkey) { \ - .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \ - .low = (offset) \ -}) - -#define ZERO_KEY KEY(0, 0, 0) - -#define MAX_KEY_INODE (~(~0 << 20)) -#define MAX_KEY_OFFSET (~0ULL >> 1) -#define MAX_KEY KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0) - -#define KEY_START(k) (KEY_OFFSET(k) - KEY_SIZE(k)) -#define START_KEY(k) KEY(KEY_INODE(k), KEY_START(k), 0) - -#define PTR_DEV_BITS 12 - -PTR_FIELD(PTR_DEV, 51, PTR_DEV_BITS) -PTR_FIELD(PTR_OFFSET, 8, 43) -PTR_FIELD(PTR_GEN, 0, 8) - -#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1) - -#define MAKE_PTR(gen, offset, dev) \ - ((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen) - -/* Bkey utility code */ - -static inline unsigned long bkey_u64s(const struct bkey *k) -{ - return (sizeof(struct bkey) / sizeof(__u64)) + KEY_PTRS(k); -} - -static inline unsigned long bkey_bytes(const struct bkey *k) -{ - return bkey_u64s(k) * sizeof(__u64); -} - -#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src)) - -static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) -{ - SET_KEY_INODE(dest, KEY_INODE(src)); - SET_KEY_OFFSET(dest, KEY_OFFSET(src)); -} - -static inline struct bkey *bkey_next(const struct bkey *k) -{ - __u64 *d = (void *) k; - - return (struct bkey *) (d + bkey_u64s(k)); -} - -static inline struct bkey *bkey_idx(const struct bkey *k, unsigned int nr_keys) -{ - __u64 *d = (void *) k; - - return (struct bkey *) (d + nr_keys); -} -/* Enough for a key with 6 pointers */ -#define BKEY_PAD 8 - -#define BKEY_PADDED(key) \ - union { struct bkey key; __u64 key ## _pad[BKEY_PAD]; } - -/* Superblock */ - -/* Version 0: Cache device - * Version 1: Backing device - * Version 2: Seed pointer into btree node checksum - * Version 3: Cache device with new UUID format - * Version 4: Backing device with data offset - */ -#define BCACHE_SB_VERSION_CDEV 0 -#define BCACHE_SB_VERSION_BDEV 1 -#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 -#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 -#define BCACHE_SB_VERSION_CDEV_WITH_FEATURES 5 -#define BCACHE_SB_VERSION_BDEV_WITH_FEATURES 6 -#define BCACHE_SB_MAX_VERSION 6 - -#define SB_SECTOR 8 -#define SB_OFFSET (SB_SECTOR << SECTOR_SHIFT) -#define SB_SIZE 4096 -#define SB_LABEL_SIZE 32 -#define SB_JOURNAL_BUCKETS 256U -/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */ -#define MAX_CACHES_PER_SET 8 - -#define BDEV_DATA_START_DEFAULT 16 /* sectors */ - -struct cache_sb_disk { - __le64 csum; - __le64 offset; /* sector where this sb was written */ - __le64 version; - - __u8 magic[16]; - - __u8 uuid[16]; - union { - __u8 set_uuid[16]; - __le64 set_magic; - }; - __u8 label[SB_LABEL_SIZE]; - - __le64 flags; - __le64 seq; - - __le64 feature_compat; - __le64 feature_incompat; - __le64 feature_ro_compat; - - __le64 pad[5]; - - union { - struct { - /* Cache devices */ - __le64 nbuckets; /* device size */ - - __le16 block_size; /* sectors */ - __le16 bucket_size; /* sectors */ - - __le16 nr_in_set; - __le16 nr_this_dev; - }; - struct { - /* Backing devices */ - __le64 data_offset; - - /* - * block_size from the cache device section is still used by - * backing devices, so don't add anything here until we fix - * things to not need it for backing devices anymore - */ - }; - }; - - __le32 last_mount; /* time overflow in y2106 */ - - __le16 first_bucket; - union { - __le16 njournal_buckets; - __le16 keys; - }; - __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ - __le16 obso_bucket_size_hi; /* obsoleted */ -}; - -/* - * This is for in-memory bcache super block. - * NOTE: cache_sb is NOT exactly mapping to cache_sb_disk, the member - * size, ordering and even whole struct size may be different - * from cache_sb_disk. - */ -struct cache_sb { - __u64 offset; /* sector where this sb was written */ - __u64 version; - - __u8 magic[16]; - - __u8 uuid[16]; - union { - __u8 set_uuid[16]; - __u64 set_magic; - }; - __u8 label[SB_LABEL_SIZE]; - - __u64 flags; - __u64 seq; - - __u64 feature_compat; - __u64 feature_incompat; - __u64 feature_ro_compat; - - union { - struct { - /* Cache devices */ - __u64 nbuckets; /* device size */ - - __u16 block_size; /* sectors */ - __u16 nr_in_set; - __u16 nr_this_dev; - __u32 bucket_size; /* sectors */ - }; - struct { - /* Backing devices */ - __u64 data_offset; - - /* - * block_size from the cache device section is still used by - * backing devices, so don't add anything here until we fix - * things to not need it for backing devices anymore - */ - }; - }; - - __u32 last_mount; /* time overflow in y2106 */ - - __u16 first_bucket; - union { - __u16 njournal_buckets; - __u16 keys; - }; - __u64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ -}; - -static inline _Bool SB_IS_BDEV(const struct cache_sb *sb) -{ - return sb->version == BCACHE_SB_VERSION_BDEV - || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET - || sb->version == BCACHE_SB_VERSION_BDEV_WITH_FEATURES; -} - -BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1); -BITMASK(CACHE_DISCARD, struct cache_sb, flags, 1, 1); -BITMASK(CACHE_REPLACEMENT, struct cache_sb, flags, 2, 3); -#define CACHE_REPLACEMENT_LRU 0U -#define CACHE_REPLACEMENT_FIFO 1U -#define CACHE_REPLACEMENT_RANDOM 2U - -BITMASK(BDEV_CACHE_MODE, struct cache_sb, flags, 0, 4); -#define CACHE_MODE_WRITETHROUGH 0U -#define CACHE_MODE_WRITEBACK 1U -#define CACHE_MODE_WRITEAROUND 2U -#define CACHE_MODE_NONE 3U -BITMASK(BDEV_STATE, struct cache_sb, flags, 61, 2); -#define BDEV_STATE_NONE 0U -#define BDEV_STATE_CLEAN 1U -#define BDEV_STATE_DIRTY 2U -#define BDEV_STATE_STALE 3U - -/* - * Magic numbers - * - * The various other data structures have their own magic numbers, which are - * xored with the first part of the cache set's UUID - */ - -#define JSET_MAGIC 0x245235c1a3625032ULL -#define PSET_MAGIC 0x6750e15f87337f91ULL -#define BSET_MAGIC 0x90135c78b99e07f5ULL - -static inline __u64 jset_magic(struct cache_sb *sb) -{ - return sb->set_magic ^ JSET_MAGIC; -} - -static inline __u64 pset_magic(struct cache_sb *sb) -{ - return sb->set_magic ^ PSET_MAGIC; -} - -static inline __u64 bset_magic(struct cache_sb *sb) -{ - return sb->set_magic ^ BSET_MAGIC; -} - -/* - * Journal - * - * On disk format for a journal entry: - * seq is monotonically increasing; every journal entry has its own unique - * sequence number. - * - * last_seq is the oldest journal entry that still has keys the btree hasn't - * flushed to disk yet. - * - * version is for on disk format changes. - */ - -#define BCACHE_JSET_VERSION_UUIDv1 1 -#define BCACHE_JSET_VERSION_UUID 1 /* Always latest UUID format */ -#define BCACHE_JSET_VERSION 1 - -struct jset { - __u64 csum; - __u64 magic; - __u64 seq; - __u32 version; - __u32 keys; - - __u64 last_seq; - - BKEY_PADDED(uuid_bucket); - BKEY_PADDED(btree_root); - __u16 btree_level; - __u16 pad[3]; - - __u64 prio_bucket[MAX_CACHES_PER_SET]; - - union { - struct bkey start[0]; - __u64 d[0]; - }; -}; - -/* Bucket prios/gens */ - -struct prio_set { - __u64 csum; - __u64 magic; - __u64 seq; - __u32 version; - __u32 pad; - - __u64 next_bucket; - - struct bucket_disk { - __u16 prio; - __u8 gen; - } __attribute((packed)) data[]; -}; - -/* UUIDS - per backing device/flash only volume metadata */ - -struct uuid_entry { - union { - struct { - __u8 uuid[16]; - __u8 label[32]; - __u32 first_reg; /* time overflow in y2106 */ - __u32 last_reg; - __u32 invalidated; - - __u32 flags; - /* Size of flash only volumes */ - __u64 sectors; - }; - - __u8 pad[128]; - }; -}; - -BITMASK(UUID_FLASH_ONLY, struct uuid_entry, flags, 0, 1); - -/* Btree nodes */ - -/* Version 1: Seed pointer into btree node checksum - */ -#define BCACHE_BSET_CSUM 1 -#define BCACHE_BSET_VERSION 1 - -/* - * Btree nodes - * - * On disk a btree node is a list/log of these; within each set the keys are - * sorted - */ -struct bset { - __u64 csum; - __u64 magic; - __u64 seq; - __u32 version; - __u32 keys; - - union { - struct bkey start[0]; - __u64 d[0]; - }; -}; - -/* OBSOLETE */ - -/* UUIDS - per backing device/flash only volume metadata */ - -struct uuid_entry_v0 { - __u8 uuid[16]; - __u8 label[32]; - __u32 first_reg; - __u32 last_reg; - __u32 invalidated; - __u32 pad; -}; - -#endif /* _LINUX_BCACHE_H */ -- cgit v1.2.3 From 56fa95014a0447f798444e626091cbeb3176af24 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Oct 2021 15:43:29 +0200 Subject: netfilter: nft_meta: add NFT_META_IFTYPE Generalize NFT_META_IIFTYPE to NFT_META_IFTYPE which allows you to match on the interface type of the skb->dev field. This field is used by the netdev family to add an implicit dependency to skip non-ethernet packets when matching on layer 3 and 4 TCP/IP header fields. For backward compatibility, add the NFT_META_IIFTYPE alias to NFT_META_IFTYPE. Add __NFT_META_IIFTYPE, to be used by userspace in the future to match specifically on the iiftype. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 +++- net/netfilter/nft_meta.c | 6 +++++- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e94d1fa554cb..08db4ee06ab6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -896,7 +896,8 @@ enum nft_meta_keys { NFT_META_OIF, NFT_META_IIFNAME, NFT_META_OIFNAME, - NFT_META_IIFTYPE, + NFT_META_IFTYPE, +#define NFT_META_IIFTYPE NFT_META_IFTYPE NFT_META_OIFTYPE, NFT_META_SKUID, NFT_META_SKGID, @@ -923,6 +924,7 @@ enum nft_meta_keys { NFT_META_TIME_HOUR, NFT_META_SDIF, NFT_META_SDIFNAME, + __NFT_META_IIFTYPE, }; /** diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index a7e01e9952f1..516e74635bae 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -244,7 +244,11 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest, case NFT_META_OIF: nft_meta_store_ifindex(dest, nft_out(pkt)); break; - case NFT_META_IIFTYPE: + case NFT_META_IFTYPE: + if (!nft_meta_store_iftype(dest, pkt->skb->dev)) + return false; + break; + case __NFT_META_IIFTYPE: if (!nft_meta_store_iftype(dest, nft_in(pkt))) return false; break; -- cgit v1.2.3 From e47be840e87ea15677bca2043ee7b696ccacf56a Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Fri, 29 Oct 2021 17:14:48 +0800 Subject: vdpa: add new attribute VDPA_ATTR_DEV_MIN_VQ_SIZE This attribute advertises the min value of virtqueue size. The value is 1 by default. Signed-off-by: Wu Zongyong Link: https://lore.kernel.org/r/2bbc417355c4d22298050b1ba887cecfbde3e85d.1635493219.git.wuzongyong@linux.alibaba.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 5 +++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index d783a943647d..fcf02a364878 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -500,6 +500,7 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq int flags, struct netlink_ext_ack *extack) { u16 max_vq_size; + u16 min_vq_size = 1; u32 device_id; u32 vendor_id; void *hdr; @@ -516,6 +517,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq device_id = vdev->config->get_device_id(vdev); vendor_id = vdev->config->get_vendor_id(vdev); max_vq_size = vdev->config->get_vq_num_max(vdev); + if (vdev->config->get_vq_num_min) + min_vq_size = vdev->config->get_vq_num_min(vdev); err = -EMSGSIZE; if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) @@ -528,6 +531,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq goto msg_err; if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size)) goto msg_err; + if (nla_put_u16(msg, VDPA_ATTR_DEV_MIN_VQ_SIZE, min_vq_size)) + goto msg_err; genlmsg_end(msg, hdr); return 0; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 66a41e4ec163..e3b87879514c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -32,6 +32,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_VENDOR_ID, /* u32 */ VDPA_ATTR_DEV_MAX_VQS, /* u32 */ VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ + VDPA_ATTR_DEV_MIN_VQ_SIZE, /* u16 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From c46b38dc8743535e686b911d253a844f0bd50ead Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 28 Oct 2021 22:15:00 +0200 Subject: netfilter: nft_payload: support for inner header matching / mangling Allow to match and mangle on inner headers / payload data after the transport header. There is a new field in the pktinfo structure that stores the inner header offset which is calculated only when requested. Only TCP and UDP supported at this stage. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_payload.c | 56 ++++++++++++++++++++++++++++++-- 3 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 7e3188cf4a7d..a0d9e0b47ab8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -23,6 +23,7 @@ struct module; enum { NFT_PKTINFO_L4PROTO = (1 << 0), + NFT_PKTINFO_INNER = (1 << 1), }; struct nft_pktinfo { @@ -32,6 +33,7 @@ struct nft_pktinfo { u8 tprot; u16 fragoff; unsigned int thoff; + unsigned int inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 08db4ee06ab6..466fd3f4447c 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -753,11 +753,13 @@ enum nft_dynset_attributes { * @NFT_PAYLOAD_LL_HEADER: link layer header * @NFT_PAYLOAD_NETWORK_HEADER: network header * @NFT_PAYLOAD_TRANSPORT_HEADER: transport header + * @NFT_PAYLOAD_INNER_HEADER: inner header / payload */ enum nft_payload_bases { NFT_PAYLOAD_LL_HEADER, NFT_PAYLOAD_NETWORK_HEADER, NFT_PAYLOAD_TRANSPORT_HEADER, + NFT_PAYLOAD_INNER_HEADER, }; /** diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index d1cd6583ee00..cbfe4e4a4ad7 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,6 +22,7 @@ #include #include #include +#include #include static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, @@ -79,6 +80,45 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; } +static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) +{ + unsigned int thoff = nft_thoff(pkt); + + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + return -1; + + switch (pkt->tprot) { + case IPPROTO_UDP: + pkt->inneroff = thoff + sizeof(struct udphdr); + break; + case IPPROTO_TCP: { + struct tcphdr *th, _tcph; + + th = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph), &_tcph); + if (!th) + return -1; + + pkt->inneroff = thoff + __tcp_hdrlen(th); + } + break; + default: + return -1; + } + + pkt->flags |= NFT_PKTINFO_INNER; + + return 0; +} + +static int nft_payload_inner_offset(const struct nft_pktinfo *pkt) +{ + if (!(pkt->flags & NFT_PKTINFO_INNER) && + __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0) + return -1; + + return pkt->inneroff; +} + void nft_payload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -112,6 +152,11 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; offset = nft_thoff(pkt); break; + case NFT_PAYLOAD_INNER_HEADER: + offset = nft_payload_inner_offset(pkt); + if (offset < 0) + goto err; + break; default: BUG(); } @@ -614,6 +659,11 @@ static void nft_payload_set_eval(const struct nft_expr *expr, goto err; offset = nft_thoff(pkt); break; + case NFT_PAYLOAD_INNER_HEADER: + offset = nft_payload_inner_offset(pkt); + if (offset < 0) + goto err; + break; default: BUG(); } @@ -622,7 +672,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr, offset += priv->offset; if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) && - (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER || + ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER && + priv->base != NFT_PAYLOAD_INNER_HEADER) || skb->ip_summed != CHECKSUM_PARTIAL)) { fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); @@ -741,6 +792,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, case NFT_PAYLOAD_LL_HEADER: case NFT_PAYLOAD_NETWORK_HEADER: case NFT_PAYLOAD_TRANSPORT_HEADER: + case NFT_PAYLOAD_INNER_HEADER: break; default: return ERR_PTR(-EOPNOTSUPP); @@ -759,7 +811,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && - base != NFT_PAYLOAD_LL_HEADER) + base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; -- cgit v1.2.3 From dcce162559ee1ce5f64992c4c65197f9270e3d4f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Oct 2021 15:17:49 +0530 Subject: i2c: virtio: Add support for zero-length requests The virtio specification received a new mandatory feature (VIRTIO_I2C_F_ZERO_LENGTH_REQUEST) for zero length requests. Fail if the feature isn't offered by the device. For each read-request, set the VIRTIO_I2C_FLAGS_M_RD flag, as required by the VIRTIO_I2C_F_ZERO_LENGTH_REQUEST feature. This allows us to support zero length requests, like SMBUS Quick, where the buffer need not be sent anymore. Signed-off-by: Viresh Kumar Link: https://lore.kernel.org/r/7c58868cd26d2fc4bd82d0d8b0dfb55636380110.1634808714.git.viresh.kumar@linaro.org Signed-off-by: Michael S. Tsirkin Acked-by: Jie Deng # once the spec is merged --- drivers/i2c/busses/i2c-virtio.c | 56 ++++++++++++++++++++++------------------- include/uapi/linux/virtio_i2c.h | 6 +++++ 2 files changed, 36 insertions(+), 26 deletions(-) (limited to 'include/uapi') diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index f10a603b13fb..1ed4daa918a0 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -62,35 +62,33 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq, for (i = 0; i < num; i++) { int outcnt = 0, incnt = 0; - /* - * We don't support 0 length messages and so filter out - * 0 length transfers by using i2c_adapter_quirks. - */ - if (!msgs[i].len) - break; - /* * Only 7-bit mode supported for this moment. For the address * format, Please check the Virtio I2C Specification. */ reqs[i].out_hdr.addr = cpu_to_le16(msgs[i].addr << 1); + if (msgs[i].flags & I2C_M_RD) + reqs[i].out_hdr.flags |= cpu_to_le32(VIRTIO_I2C_FLAGS_M_RD); + if (i != num - 1) - reqs[i].out_hdr.flags = cpu_to_le32(VIRTIO_I2C_FLAGS_FAIL_NEXT); + reqs[i].out_hdr.flags |= cpu_to_le32(VIRTIO_I2C_FLAGS_FAIL_NEXT); sg_init_one(&out_hdr, &reqs[i].out_hdr, sizeof(reqs[i].out_hdr)); sgs[outcnt++] = &out_hdr; - reqs[i].buf = i2c_get_dma_safe_msg_buf(&msgs[i], 1); - if (!reqs[i].buf) - break; + if (msgs[i].len) { + reqs[i].buf = i2c_get_dma_safe_msg_buf(&msgs[i], 1); + if (!reqs[i].buf) + break; - sg_init_one(&msg_buf, reqs[i].buf, msgs[i].len); + sg_init_one(&msg_buf, reqs[i].buf, msgs[i].len); - if (msgs[i].flags & I2C_M_RD) - sgs[outcnt + incnt++] = &msg_buf; - else - sgs[outcnt++] = &msg_buf; + if (msgs[i].flags & I2C_M_RD) + sgs[outcnt + incnt++] = &msg_buf; + else + sgs[outcnt++] = &msg_buf; + } sg_init_one(&in_hdr, &reqs[i].in_hdr, sizeof(reqs[i].in_hdr)); sgs[outcnt + incnt++] = &in_hdr; @@ -191,7 +189,7 @@ static int virtio_i2c_setup_vqs(struct virtio_i2c *vi) static u32 virtio_i2c_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK); + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } static struct i2c_algorithm virtio_algorithm = { @@ -199,15 +197,16 @@ static struct i2c_algorithm virtio_algorithm = { .functionality = virtio_i2c_func, }; -static const struct i2c_adapter_quirks virtio_i2c_quirks = { - .flags = I2C_AQ_NO_ZERO_LEN, -}; - static int virtio_i2c_probe(struct virtio_device *vdev) { struct virtio_i2c *vi; int ret; + if (!virtio_has_feature(vdev, VIRTIO_I2C_F_ZERO_LENGTH_REQUEST)) { + dev_err(&vdev->dev, "Zero-length request feature is mandatory\n"); + return -EINVAL; + } + vi = devm_kzalloc(&vdev->dev, sizeof(*vi), GFP_KERNEL); if (!vi) return -ENOMEM; @@ -225,7 +224,6 @@ static int virtio_i2c_probe(struct virtio_device *vdev) snprintf(vi->adap.name, sizeof(vi->adap.name), "i2c_virtio at virtio bus %d", vdev->index); vi->adap.algo = &virtio_algorithm; - vi->adap.quirks = &virtio_i2c_quirks; vi->adap.dev.parent = &vdev->dev; vi->adap.dev.of_node = vdev->dev.of_node; i2c_set_adapdata(&vi->adap, vi); @@ -270,11 +268,17 @@ static int virtio_i2c_restore(struct virtio_device *vdev) } #endif +static const unsigned int features[] = { + VIRTIO_I2C_F_ZERO_LENGTH_REQUEST, +}; + static struct virtio_driver virtio_i2c_driver = { - .id_table = id_table, - .probe = virtio_i2c_probe, - .remove = virtio_i2c_remove, - .driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .id_table = id_table, + .probe = virtio_i2c_probe, + .remove = virtio_i2c_remove, + .driver = { .name = "i2c_virtio", }, #ifdef CONFIG_PM_SLEEP diff --git a/include/uapi/linux/virtio_i2c.h b/include/uapi/linux/virtio_i2c.h index 7c6a6fc01ad6..acf3b6069136 100644 --- a/include/uapi/linux/virtio_i2c.h +++ b/include/uapi/linux/virtio_i2c.h @@ -11,9 +11,15 @@ #include #include +/* Virtio I2C Feature bits */ +#define VIRTIO_I2C_F_ZERO_LENGTH_REQUEST 0 + /* The bit 0 of the @virtio_i2c_out_hdr.@flags, used to group the requests */ #define VIRTIO_I2C_FLAGS_FAIL_NEXT _BITUL(0) +/* The bit 1 of the @virtio_i2c_out_hdr.@flags, used to mark a buffer as read */ +#define VIRTIO_I2C_FLAGS_M_RD _BITUL(1) + /** * struct virtio_i2c_out_hdr - the virtio I2C message OUT header * @addr: the controlled device address -- cgit v1.2.3 From ad69dd0bf26b88ec6ab26f8bbe5cd74fbed7672a Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 26 Oct 2021 20:55:13 +0300 Subject: vdpa: Introduce query of device config layout Introduce a command to query a device config layout. An example query of network vdpa device: $ vdpa dev add name bar mgmtdev vdpasim_net $ vdpa dev config show bar: mac 00:35:09:19:48:05 link up link_announce false mtu 1500 $ vdpa dev config show -jp { "config": { "bar": { "mac": "00:35:09:19:48:05", "link ": "up", "link_announce ": false, "mtu": 1500, } } } Signed-off-by: Parav Pandit Signed-off-by: Eli Cohen Acked-by: Jason Wang Link: https://lore.kernel.org/r/20211026175519.87795-3-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 2 + include/uapi/linux/vdpa.h | 6 ++ 3 files changed, 184 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index cbc8fc69cf9b..8fcbdda8590c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include static LIST_HEAD(mdev_head); /* A global mutex that protects vdpa management device and device level operations. */ @@ -66,6 +68,7 @@ static void vdpa_release_dev(struct device *d) ops->free(vdev); ida_simple_remove(&vdpa_index_ida, vdev->index); + mutex_destroy(&vdev->cf_mutex); kfree(vdev); } @@ -127,6 +130,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, if (err) goto err_name; + mutex_init(&vdev->cf_mutex); device_initialize(&vdev->dev); return vdev; @@ -309,6 +313,7 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, { const struct vdpa_config_ops *ops = vdev->config; + mutex_lock(&vdev->cf_mutex); /* * Config accesses aren't supposed to trigger before features are set. * If it does happen we assume a legacy guest. @@ -316,6 +321,7 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, if (!vdev->features_valid) vdpa_set_features(vdev, 0); ops->get_config(vdev, offset, buf, len); + mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_get_config); @@ -329,7 +335,9 @@ EXPORT_SYMBOL_GPL(vdpa_get_config); void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, const void *buf, unsigned int length) { + mutex_lock(&vdev->cf_mutex); vdev->config->set_config(vdev, offset, buf, length); + mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_set_config); @@ -661,6 +669,168 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba return msg->len; } +static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev, + struct sk_buff *msg, u64 features, + const struct virtio_net_config *config) +{ + u16 val_u16; + + if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0) + return 0; + + val_u16 = le16_to_cpu(config->max_virtqueue_pairs); + return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16); +} + +static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) +{ + struct virtio_net_config config = {}; + u64 features; + u16 val_u16; + + vdpa_get_config(vdev, 0, &config, sizeof(config)); + + if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac), + config.mac)) + return -EMSGSIZE; + + val_u16 = le16_to_cpu(config.status); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16)) + return -EMSGSIZE; + + val_u16 = le16_to_cpu(config.mtu); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16)) + return -EMSGSIZE; + + features = vdev->config->get_features(vdev); + + return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); +} + +static int +vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u32 device_id; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, + VDPA_CMD_DEV_CONFIG_GET); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) { + err = -EMSGSIZE; + goto msg_err; + } + + device_id = vdev->config->get_device_id(vdev); + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) { + err = -EMSGSIZE; + goto msg_err; + } + + switch (device_id) { + case VIRTIO_ID_NET: + err = vdpa_dev_net_config_fill(vdev, msg); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + goto msg_err; + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device"); + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_config_fill(vdev, msg, info->snd_portid, info->snd_seq, + 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); + +mdev_err: + put_device(dev); +dev_err: + mutex_unlock(&vdpa_dev_mutex); + if (err) + nlmsg_free(msg); + return err; +} + +static int vdpa_dev_config_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_config_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, + info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int +vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + mutex_lock(&vdpa_dev_mutex); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_config_dump); + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = info.idx; + return msg->len; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, @@ -692,6 +862,12 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_get_doit, .dumpit = vdpa_nl_cmd_dev_get_dumpit, }, + { + .cmd = VDPA_CMD_DEV_CONFIG_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_config_get_doit, + .dumpit = vdpa_nl_cmd_dev_config_get_dumpit, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 267236aab34c..5cc5e501397f 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -63,6 +63,7 @@ struct vdpa_mgmt_dev; * @dev: underlying device * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. + * @cf_mutex: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests * @use_va: indicate whether virtual address must be used by this device @@ -74,6 +75,7 @@ struct vdpa_device { struct device dev; struct device *dma_dev; const struct vdpa_config_ops *config; + struct mutex cf_mutex; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index e3b87879514c..a252f06f9dfd 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -17,6 +17,7 @@ enum vdpa_command { VDPA_CMD_DEV_NEW, VDPA_CMD_DEV_DEL, VDPA_CMD_DEV_GET, /* can dump */ + VDPA_CMD_DEV_CONFIG_GET, /* can dump */ }; enum vdpa_attr { @@ -34,6 +35,11 @@ enum vdpa_attr { VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ VDPA_ATTR_DEV_MIN_VQ_SIZE, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MACADDR, /* binary */ + VDPA_ATTR_DEV_NET_STATUS, /* u8 */ + VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From b9022b53adad88fd6cf2b9718c9e498504f3e1dd Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sun, 31 Oct 2021 16:00:02 +0000 Subject: amt: add control plane of amt interface It adds definitions and control plane code for AMT. this is very similar to udp tunneling interfaces such as gtp, vxlan, etc. In the next patch, data plane code will be added. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- MAINTAINERS | 8 + drivers/net/Kconfig | 16 ++ drivers/net/Makefile | 1 + drivers/net/amt.c | 493 +++++++++++++++++++++++++++++++++++++++++++++++ include/net/amt.h | 235 ++++++++++++++++++++++ include/uapi/linux/amt.h | 62 ++++++ 6 files changed, 815 insertions(+) create mode 100644 drivers/net/amt.c create mode 100644 include/net/amt.h create mode 100644 include/uapi/linux/amt.h (limited to 'include/uapi') diff --git a/MAINTAINERS b/MAINTAINERS index 3b85f039fbf9..917f360b3ece 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1020,6 +1020,14 @@ S: Maintained F: Documentation/devicetree/bindings/iio/light/ams,as73211.yaml F: drivers/iio/light/as73211.c +AMT (Automatic Multicast Tunneling) +M: Taehee Yoo +L: netdev@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git +F: drivers/net/amt.c + ANALOG DEVICES INC AD7192 DRIVER M: Alexandru Tachici L: linux-iio@vger.kernel.org diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index dd335ae1122b..034dbd487c33 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -291,6 +291,22 @@ config GTP To compile this drivers as a module, choose M here: the module will be called gtp. +config AMT + tristate "Automatic Multicast Tunneling (AMT)" + depends on INET && IP_MULTICAST + select NET_UDP_TUNNEL + help + This allows one to create AMT(Automatic Multicast Tunneling) + virtual interfaces that provide multicast tunneling. + There are two roles, Gateway, and Relay. + Gateway Encapsulates IGMP/MLD traffic from listeners to the Relay. + Gateway Decapsulates multicast traffic from the Relay to Listeners. + Relay Encapsulates multicast traffic from Sources to Gateway. + Relay Decapsulates IGMP/MLD traffic from Gateway. + + To compile this drivers as a module, choose M here: the module + will be called amt. + config MACSEC tristate "IEEE 802.1AE MAC-level encryption (MACsec)" select CRYPTO diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 739838623cf6..50b23e71065f 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -14,6 +14,7 @@ obj-$(CONFIG_WIREGUARD) += wireguard/ obj-$(CONFIG_EQUALIZER) += eql.o obj-$(CONFIG_IFB) += ifb.o obj-$(CONFIG_MACSEC) += macsec.o +obj-$(CONFIG_AMT) += amt.o obj-$(CONFIG_MACVLAN) += macvlan.o obj-$(CONFIG_MACVTAP) += macvtap.o obj-$(CONFIG_MII) += mii.o diff --git a/drivers/net/amt.c b/drivers/net/amt.c new file mode 100644 index 000000000000..addab3b1de0a --- /dev/null +++ b/drivers/net/amt.c @@ -0,0 +1,493 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright (c) 2021 Taehee Yoo */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct workqueue_struct *amt_wq; + +static struct socket *amt_create_sock(struct net *net, __be16 port) +{ + struct udp_port_cfg udp_conf; + struct socket *sock; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); + udp_conf.family = AF_INET; + udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + + udp_conf.local_udp_port = port; + + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + return ERR_PTR(err); + + return sock; +} + +static int amt_socket_create(struct amt_dev *amt) +{ + struct udp_tunnel_sock_cfg tunnel_cfg; + struct socket *sock; + + sock = amt_create_sock(amt->net, amt->relay_port); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + /* Mark socket as an encapsulation socket */ + memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); + tunnel_cfg.sk_user_data = amt; + tunnel_cfg.encap_type = 1; + tunnel_cfg.encap_destroy = NULL; + setup_udp_tunnel_sock(amt->net, sock, &tunnel_cfg); + + rcu_assign_pointer(amt->sock, sock); + return 0; +} + +static int amt_dev_open(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + int err; + + amt->ready4 = false; + amt->ready6 = false; + + err = amt_socket_create(amt); + if (err) + return err; + + amt->req_cnt = 0; + amt->remote_ip = 0; + get_random_bytes(&amt->key, sizeof(siphash_key_t)); + + amt->status = AMT_STATUS_INIT; + return err; +} + +static int amt_dev_stop(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + struct socket *sock; + + /* shutdown */ + sock = rtnl_dereference(amt->sock); + RCU_INIT_POINTER(amt->sock, NULL); + synchronize_net(); + if (sock) + udp_tunnel_sock_release(sock); + + amt->ready4 = false; + amt->ready6 = false; + amt->req_cnt = 0; + amt->remote_ip = 0; + + return 0; +} + +static const struct device_type amt_type = { + .name = "amt", +}; + +static int amt_dev_init(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + int err; + + amt->dev = dev; + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&amt->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + + return 0; +} + +static void amt_dev_uninit(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + + gro_cells_destroy(&amt->gro_cells); + free_percpu(dev->tstats); +} + +static const struct net_device_ops amt_netdev_ops = { + .ndo_init = amt_dev_init, + .ndo_uninit = amt_dev_uninit, + .ndo_open = amt_dev_open, + .ndo_stop = amt_dev_stop, + .ndo_get_stats64 = dev_get_tstats64, +}; + +static void amt_link_setup(struct net_device *dev) +{ + dev->netdev_ops = &amt_netdev_ops; + dev->needs_free_netdev = true; + SET_NETDEV_DEVTYPE(dev, &amt_type); + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_MAX_MTU; + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->priv_flags |= IFF_NO_QUEUE; + dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->features |= NETIF_F_NETNS_LOCAL; + dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM; + dev->hw_features |= NETIF_F_FRAGLIST | NETIF_F_RXCSUM; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + eth_hw_addr_random(dev); + eth_zero_addr(dev->broadcast); + ether_setup(dev); +} + +static const struct nla_policy amt_policy[IFLA_AMT_MAX + 1] = { + [IFLA_AMT_MODE] = { .type = NLA_U32 }, + [IFLA_AMT_RELAY_PORT] = { .type = NLA_U16 }, + [IFLA_AMT_GATEWAY_PORT] = { .type = NLA_U16 }, + [IFLA_AMT_LINK] = { .type = NLA_U32 }, + [IFLA_AMT_LOCAL_IP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_AMT_REMOTE_IP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_AMT_DISCOVERY_IP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_AMT_MAX_TUNNELS] = { .type = NLA_U32 }, +}; + +static int amt_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (!data) + return -EINVAL; + + if (!data[IFLA_AMT_LINK]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_LINK], + "Link attribute is required"); + return -EINVAL; + } + + if (!data[IFLA_AMT_MODE]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_MODE], + "Mode attribute is required"); + return -EINVAL; + } + + if (nla_get_u32(data[IFLA_AMT_MODE]) > AMT_MODE_MAX) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_MODE], + "Mode attribute is not valid"); + return -EINVAL; + } + + if (!data[IFLA_AMT_LOCAL_IP]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_DISCOVERY_IP], + "Local attribute is required"); + return -EINVAL; + } + + if (!data[IFLA_AMT_DISCOVERY_IP] && + nla_get_u32(data[IFLA_AMT_MODE]) == AMT_MODE_GATEWAY) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_LOCAL_IP], + "Discovery attribute is required"); + return -EINVAL; + } + + return 0; +} + +static int amt_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct amt_dev *amt = netdev_priv(dev); + int err = -EINVAL; + + amt->net = net; + amt->mode = nla_get_u32(data[IFLA_AMT_MODE]); + + if (data[IFLA_AMT_MAX_TUNNELS]) + amt->max_tunnels = nla_get_u32(data[IFLA_AMT_MAX_TUNNELS]); + else + amt->max_tunnels = AMT_MAX_TUNNELS; + + spin_lock_init(&amt->lock); + amt->max_groups = AMT_MAX_GROUP; + amt->max_sources = AMT_MAX_SOURCE; + amt->hash_buckets = AMT_HSIZE; + amt->nr_tunnels = 0; + get_random_bytes(&amt->hash_seed, sizeof(amt->hash_seed)); + amt->stream_dev = dev_get_by_index(net, + nla_get_u32(data[IFLA_AMT_LINK])); + if (!amt->stream_dev) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK], + "Can't find stream device"); + return -ENODEV; + } + + if (amt->stream_dev->type != ARPHRD_ETHER) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK], + "Invalid stream device type"); + goto err; + } + + amt->local_ip = nla_get_in_addr(data[IFLA_AMT_LOCAL_IP]); + if (ipv4_is_loopback(amt->local_ip) || + ipv4_is_zeronet(amt->local_ip) || + ipv4_is_multicast(amt->local_ip)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LOCAL_IP], + "Invalid Local address"); + goto err; + } + + if (data[IFLA_AMT_RELAY_PORT]) + amt->relay_port = nla_get_be16(data[IFLA_AMT_RELAY_PORT]); + else + amt->relay_port = htons(IANA_AMT_UDP_PORT); + + if (data[IFLA_AMT_GATEWAY_PORT]) + amt->gw_port = nla_get_be16(data[IFLA_AMT_GATEWAY_PORT]); + else + amt->gw_port = htons(IANA_AMT_UDP_PORT); + + if (!amt->relay_port) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "relay port must not be 0"); + goto err; + } + if (amt->mode == AMT_MODE_RELAY) { + amt->qrv = amt->net->ipv4.sysctl_igmp_qrv; + amt->qri = 10; + dev->needed_headroom = amt->stream_dev->needed_headroom + + AMT_RELAY_HLEN; + dev->mtu = amt->stream_dev->mtu - AMT_RELAY_HLEN; + dev->max_mtu = dev->mtu; + dev->min_mtu = ETH_MIN_MTU + AMT_RELAY_HLEN; + } else { + if (!data[IFLA_AMT_DISCOVERY_IP]) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "discovery must be set in gateway mode"); + goto err; + } + if (!amt->gw_port) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "gateway port must not be 0"); + goto err; + } + amt->remote_ip = 0; + amt->discovery_ip = nla_get_in_addr(data[IFLA_AMT_DISCOVERY_IP]); + if (ipv4_is_loopback(amt->discovery_ip) || + ipv4_is_zeronet(amt->discovery_ip) || + ipv4_is_multicast(amt->discovery_ip)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "discovery must be unicast"); + goto err; + } + + dev->needed_headroom = amt->stream_dev->needed_headroom + + AMT_GW_HLEN; + dev->mtu = amt->stream_dev->mtu - AMT_GW_HLEN; + dev->max_mtu = dev->mtu; + dev->min_mtu = ETH_MIN_MTU + AMT_GW_HLEN; + } + amt->qi = AMT_INIT_QUERY_INTERVAL; + + err = register_netdevice(dev); + if (err < 0) { + netdev_dbg(dev, "failed to register new netdev %d\n", err); + goto err; + } + + err = netdev_upper_dev_link(amt->stream_dev, dev, extack); + if (err < 0) { + unregister_netdevice(dev); + goto err; + } + + return 0; +err: + dev_put(amt->stream_dev); + return err; +} + +static void amt_dellink(struct net_device *dev, struct list_head *head) +{ + struct amt_dev *amt = netdev_priv(dev); + + unregister_netdevice_queue(dev, head); + netdev_upper_dev_unlink(amt->stream_dev, dev); + dev_put(amt->stream_dev); +} + +static size_t amt_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(__u32)) + /* IFLA_AMT_MODE */ + nla_total_size(sizeof(__u16)) + /* IFLA_AMT_RELAY_PORT */ + nla_total_size(sizeof(__u16)) + /* IFLA_AMT_GATEWAY_PORT */ + nla_total_size(sizeof(__u32)) + /* IFLA_AMT_LINK */ + nla_total_size(sizeof(__u32)) + /* IFLA_MAX_TUNNELS */ + nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_DISCOVERY_IP */ + nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_REMOTE_IP */ + nla_total_size(sizeof(struct iphdr)); /* IFLA_AMT_LOCAL_IP */ +} + +static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + + if (nla_put_u32(skb, IFLA_AMT_MODE, amt->mode)) + goto nla_put_failure; + if (nla_put_be16(skb, IFLA_AMT_RELAY_PORT, amt->relay_port)) + goto nla_put_failure; + if (nla_put_be16(skb, IFLA_AMT_GATEWAY_PORT, amt->gw_port)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_AMT_LINK, amt->stream_dev->ifindex)) + goto nla_put_failure; + if (nla_put_in_addr(skb, IFLA_AMT_LOCAL_IP, amt->local_ip)) + goto nla_put_failure; + if (nla_put_in_addr(skb, IFLA_AMT_DISCOVERY_IP, amt->discovery_ip)) + goto nla_put_failure; + if (amt->remote_ip) + if (nla_put_in_addr(skb, IFLA_AMT_REMOTE_IP, amt->remote_ip)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_AMT_MAX_TUNNELS, amt->max_tunnels)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static struct rtnl_link_ops amt_link_ops __read_mostly = { + .kind = "amt", + .maxtype = IFLA_AMT_MAX, + .policy = amt_policy, + .priv_size = sizeof(struct amt_dev), + .setup = amt_link_setup, + .validate = amt_validate, + .newlink = amt_newlink, + .dellink = amt_dellink, + .get_size = amt_get_size, + .fill_info = amt_fill_info, +}; + +static struct net_device *amt_lookup_upper_dev(struct net_device *dev) +{ + struct net_device *upper_dev; + struct amt_dev *amt; + + for_each_netdev(dev_net(dev), upper_dev) { + if (netif_is_amt(upper_dev)) { + amt = netdev_priv(upper_dev); + if (amt->stream_dev == dev) + return upper_dev; + } + } + + return NULL; +} + +static int amt_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net_device *upper_dev; + struct amt_dev *amt; + LIST_HEAD(list); + int new_mtu; + + upper_dev = amt_lookup_upper_dev(dev); + if (!upper_dev) + return NOTIFY_DONE; + amt = netdev_priv(upper_dev); + + switch (event) { + case NETDEV_UNREGISTER: + amt_dellink(amt->dev, &list); + unregister_netdevice_many(&list); + break; + case NETDEV_CHANGEMTU: + if (amt->mode == AMT_MODE_RELAY) + new_mtu = dev->mtu - AMT_RELAY_HLEN; + else + new_mtu = dev->mtu - AMT_GW_HLEN; + + dev_set_mtu(amt->dev, new_mtu); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block amt_notifier_block __read_mostly = { + .notifier_call = amt_device_event, +}; + +static int __init amt_init(void) +{ + int err; + + err = register_netdevice_notifier(&amt_notifier_block); + if (err < 0) + goto err; + + err = rtnl_link_register(&amt_link_ops); + if (err < 0) + goto unregister_notifier; + + amt_wq = alloc_workqueue("amt", WQ_UNBOUND, 1); + if (!amt_wq) + goto rtnl_unregister; + + return 0; + +rtnl_unregister: + rtnl_link_unregister(&amt_link_ops); +unregister_notifier: + unregister_netdevice_notifier(&amt_notifier_block); +err: + pr_err("error loading AMT module loaded\n"); + return err; +} +late_initcall(amt_init); + +static void __exit amt_fini(void) +{ + rtnl_link_unregister(&amt_link_ops); + unregister_netdevice_notifier(&amt_notifier_block); + destroy_workqueue(amt_wq); +} +module_exit(amt_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Taehee Yoo "); +MODULE_ALIAS_RTNL_LINK("amt"); diff --git a/include/net/amt.h b/include/net/amt.h new file mode 100644 index 000000000000..ce24ff823555 --- /dev/null +++ b/include/net/amt.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (c) 2021 Taehee Yoo + */ +#ifndef _NET_AMT_H_ +#define _NET_AMT_H_ + +#include +#include + +enum amt_msg_type { + AMT_MSG_DISCOVERY = 1, + AMT_MSG_ADVERTISEMENT, + AMT_MSG_REQUEST, + AMT_MSG_MEMBERSHIP_QUERY, + AMT_MSG_MEMBERSHIP_UPDATE, + AMT_MSG_MULTICAST_DATA, + AMT_MSG_TEARDOWM, + __AMT_MSG_MAX, +}; + +#define AMT_MSG_MAX (__AMT_MSG_MAX - 1) + +enum amt_status { + AMT_STATUS_INIT, + AMT_STATUS_SENT_DISCOVERY, + AMT_STATUS_RECEIVED_DISCOVERY, + AMT_STATUS_SENT_ADVERTISEMENT, + AMT_STATUS_RECEIVED_ADVERTISEMENT, + AMT_STATUS_SENT_REQUEST, + AMT_STATUS_RECEIVED_REQUEST, + AMT_STATUS_SENT_QUERY, + AMT_STATUS_RECEIVED_QUERY, + AMT_STATUS_SENT_UPDATE, + AMT_STATUS_RECEIVED_UPDATE, + __AMT_STATUS_MAX, +}; + +#define AMT_STATUS_MAX (__AMT_STATUS_MAX - 1) + +struct amt_header_discovery { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + reserved:24; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_advertisement { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + reserved:24; +#else +#error "Please fix " +#endif + __be32 nonce; + __be32 ip4; +} __packed; + +struct amt_header_request { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved1:7, + p:1, + reserved2:16; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + p:1, + reserved1:7, + reserved2:16; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_membership_query { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u64 type:4, + version:4, + reserved:6, + l:1, + g:1, + response_mac:48; +#elif defined(__BIG_ENDIAN_BITFIELD) + u64 version:4, + type:4, + g:1, + l:1, + reserved:6, + response_mac:48; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_membership_update { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u64 type:4, + version:4, + reserved:8, + response_mac:48; +#elif defined(__BIG_ENDIAN_BITFIELD) + u64 version:4, + type:4, + reserved:8, + response_mac:48; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_mcast_data { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u16 type:4, + version:4, + reserved:8; +#elif defined(__BIG_ENDIAN_BITFIELD) + u16 version:4, + type:4, + reserved:8; +#else +#error "Please fix " +#endif +} __packed; + +struct amt_gw_headers { + union { + struct amt_header_discovery discovery; + struct amt_header_request request; + struct amt_header_membership_update update; + }; +} __packed; + +struct amt_relay_headers { + union { + struct amt_header_advertisement advertisement; + struct amt_header_membership_query query; + struct amt_header_mcast_data data; + }; +} __packed; + +struct amt_dev { + struct net_device *dev; + struct net_device *stream_dev; + struct net *net; + /* Global lock for amt device */ + spinlock_t lock; + /* Used only in relay mode */ + struct list_head tunnel_list; + struct gro_cells gro_cells; + + /* Protected by RTNL */ + struct delayed_work discovery_wq; + /* Protected by RTNL */ + struct delayed_work req_wq; + /* Protected by RTNL */ + struct delayed_work secret_wq; + /* AMT status */ + enum amt_status status; + /* Generated key */ + siphash_key_t key; + struct socket __rcu *sock; + u32 max_groups; + u32 max_sources; + u32 hash_buckets; + u32 hash_seed; + /* Default 128 */ + u32 max_tunnels; + /* Default 128 */ + u32 nr_tunnels; + /* Gateway or Relay mode */ + u32 mode; + /* Default 2268 */ + __be16 relay_port; + /* Default 2268 */ + __be16 gw_port; + /* Outer local ip */ + __be32 local_ip; + /* Outer remote ip */ + __be32 remote_ip; + /* Outer discovery ip */ + __be32 discovery_ip; + /* Only used in gateway mode */ + __be32 nonce; + /* Gateway sent request and received query */ + bool ready4; + bool ready6; + u8 req_cnt; + u8 qi; + u64 qrv; + u64 qri; + /* Used only in gateway mode */ + u64 mac:48, + reserved:16; +}; + +#define AMT_MAX_GROUP 32 +#define AMT_MAX_SOURCE 128 +#define AMT_HSIZE_SHIFT 8 +#define AMT_HSIZE (1 << AMT_HSIZE_SHIFT) + +#define AMT_INIT_QUERY_INTERVAL 125 +#define IANA_AMT_UDP_PORT 2268 +#define AMT_MAX_TUNNELS 128 +#define AMT_MAX_REQS 128 +#define AMT_GW_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + sizeof(struct amt_gw_headers)) +#define AMT_RELAY_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + sizeof(struct amt_relay_headers)) + +static inline bool netif_is_amt(const struct net_device *dev) +{ + return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "amt"); +} + +#endif /* _NET_AMT_H_ */ diff --git a/include/uapi/linux/amt.h b/include/uapi/linux/amt.h new file mode 100644 index 000000000000..2dccff417195 --- /dev/null +++ b/include/uapi/linux/amt.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (c) 2021 Taehee Yoo + */ +#ifndef _UAPI_AMT_H_ +#define _UAPI_AMT_H_ + +enum ifla_amt_mode { + /* AMT interface works as Gateway mode. + * The Gateway mode encapsulates IGMP/MLD traffic and decapsulates + * multicast traffic. + */ + AMT_MODE_GATEWAY = 0, + /* AMT interface works as Relay mode. + * The Relay mode encapsulates multicast traffic and decapsulates + * IGMP/MLD traffic. + */ + AMT_MODE_RELAY, + __AMT_MODE_MAX, +}; + +#define AMT_MODE_MAX (__AMT_MODE_MAX - 1) + +enum { + IFLA_AMT_UNSPEC, + /* This attribute specify mode etier Gateway or Relay. */ + IFLA_AMT_MODE, + /* This attribute specify Relay port. + * AMT interface is created as Gateway mode, this attribute is used + * to specify relay(remote) port. + * AMT interface is created as Relay mode, this attribute is used + * as local port. + */ + IFLA_AMT_RELAY_PORT, + /* This attribute specify Gateway port. + * AMT interface is created as Gateway mode, this attribute is used + * as local port. + * AMT interface is created as Relay mode, this attribute is not used. + */ + IFLA_AMT_GATEWAY_PORT, + /* This attribute specify physical device */ + IFLA_AMT_LINK, + /* This attribute specify local ip address */ + IFLA_AMT_LOCAL_IP, + /* This attribute specify Relay ip address. + * So, this is not used by Relay. + */ + IFLA_AMT_REMOTE_IP, + /* This attribute specify Discovery ip address. + * When Gateway get started, it send discovery message to find the + * Relay's ip address. + * So, this is not used by Relay. + */ + IFLA_AMT_DISCOVERY_IP, + /* This attribute specify number of maximum tunnel. */ + IFLA_AMT_MAX_TUNNELS, + __IFLA_AMT_MAX, +}; + +#define IFLA_AMT_MAX (__IFLA_AMT_MAX - 1) + +#endif /* _UAPI_AMT_H_ */ -- cgit v1.2.3 From 8845b4681bf44b9d2d2badf2c67cf476e42a86bd Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Fri, 29 Oct 2021 15:49:08 -0700 Subject: bpf: Add alignment padding for "map_extra" + consolidate holes This patch makes 2 changes regarding alignment padding for the "map_extra" field. 1) In the kernel header, "map_extra" and "btf_value_type_id" are rearranged to consolidate the hole. Before: struct bpf_map { ... u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ /* XXX 4 bytes hole, try to pack */ u64 map_extra; /* 48 8 */ int spin_lock_off; /* 56 4 */ int timer_off; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 id; /* 64 4 */ int numa_node; /* 68 4 */ ... bool frozen; /* 117 1 */ /* XXX 10 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 2, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 10 */ } __attribute__((__aligned__(64))); After: struct bpf_map { ... u32 max_entries; /* 36 4 */ u64 map_extra; /* 40 8 */ u32 map_flags; /* 48 4 */ int spin_lock_off; /* 52 4 */ int timer_off; /* 56 4 */ u32 id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ int numa_node; /* 64 4 */ ... bool frozen /* 113 1 */ /* XXX 14 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 1, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 14 */ } __attribute__((__aligned__(64))); 2) Add alignment padding to the bpf_map_info struct More details can be found in commit 36f9814a494a ("bpf: fix uapi hole for 32 bit compat applications") Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211029224909.1721024-3-joannekoong@fb.com --- include/linux/bpf.h | 6 +++--- include/uapi/linux/bpf.h | 1 + tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c098089c1b54..f6743d4bb531 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,23 +168,23 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; - u32 map_flags; u64 map_extra; /* any per-map-type extra fields */ + u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; + u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; - u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 22 bytes hole */ + /* 14 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3 From fcdb44d08a95003c3d040aecdee286156ec6f34e Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 1 Nov 2021 10:36:28 -0700 Subject: net: arp: introduce arp_evict_nocarrier sysctl parameter This change introduces a new sysctl parameter, arp_evict_nocarrier. When set (default) the ARP cache will be cleared on a NOCARRIER event. This new option has been defaulted to '1' which maintains existing behavior. Clearing the ARP cache on NOCARRIER is relatively new, introduced by: commit 859bd2ef1fc1110a8031b967ee656c53a6260a76 Author: David Ahern Date: Thu Oct 11 20:33:49 2018 -0700 net: Evict neighbor entries on carrier down The reason for this changes is to prevent the ARP cache from being cleared when a wireless device roams. Specifically for wireless roams the ARP cache should not be cleared because the underlying network has not changed. Clearing the ARP cache in this case can introduce significant delays sending out packets after a roam. A user reported such a situation here: https://lore.kernel.org/linux-wireless/CACsRnHWa47zpx3D1oDq9JYnZWniS8yBwW1h0WAVZ6vrbwL_S0w@mail.gmail.com/ After some investigation it was found that the kernel was holding onto packets until ARP finished which resulted in this 1 second delay. It was also found that the first ARP who-has was never responded to, which is actually what caues the delay. This change is more or less working around this behavior, but again, there is no reason to clear the cache on a roam anyways. As for the unanswered who-has, we know the packet made it OTA since it was seen while monitoring. Why it never received a response is unknown. In any case, since this is a problem on the AP side of things all that can be done is to work around it until it is solved. Some background on testing/reproducing the packet delay: Hardware: - 2 access points configured for Fast BSS Transition (Though I don't see why regular reassociation wouldn't have the same behavior) - Wireless station running IWD as supplicant - A device on network able to respond to pings (I used one of the APs) Procedure: - Connect to first AP - Ping once to establish an ARP entry - Start a tcpdump - Roam to second AP - Wait for operstate UP event, and note the timestamp - Start pinging Results: Below is the tcpdump after UP. It was recorded the interface went UP at 10:42:01.432875. 10:42:01.461871 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.497976 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.507162 ARP, Reply 192.168.254.1 is-at ac:86:74:55:b0:20, length 46 10:42:02.507185 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 1, length 64 10:42:02.507205 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 2, length 64 10:42:02.507212 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 3, length 64 10:42:02.507219 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 4, length 64 10:42:02.507225 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 5, length 64 10:42:02.507232 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 6, length 64 10:42:02.515373 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 1, length 64 10:42:02.521399 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 2, length 64 10:42:02.521612 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 3, length 64 10:42:02.521941 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 4, length 64 10:42:02.522419 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 5, length 64 10:42:02.523085 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 6, length 64 You can see the first ARP who-has went out very quickly after UP, but was never responded to. Nearly a second later the kernel retries and gets a response. Only then do the ping packets go out. If an ARP entry is manually added prior to UP (after the cache is cleared) it is seen that the first ping is never responded to, so its not only an issue with ARP but with data packets in general. As mentioned prior, the wireless interface was also monitored to verify the ping/ARP packet made it OTA which was observed to be true. Signed-off-by: James Prestwood Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 9 +++++++++ include/linux/inetdevice.h | 2 ++ include/uapi/linux/ip.h | 1 + include/uapi/linux/sysctl.h | 1 + net/ipv4/arp.c | 11 ++++++++++- net/ipv4/devinet.c | 4 ++++ 6 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 16b8bf72feaf..18fde4ed7a5e 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1611,6 +1611,15 @@ arp_accept - BOOLEAN gratuitous arp frame, the arp table will be updated regardless if this setting is on or off. +arp_evict_nocarrier - BOOLEAN + Clears the ARP cache on NOCARRIER events. This option is important for + wireless devices where the ARP cache should not be cleared when roaming + between access points on the same network. In most cases this should + remain as the default (1). + + - 1 - (default): Clear the ARP cache on NOCARRIER events + - 0 - Do not clear ARP cache on NOCARRIER events + mcast_solicit - INTEGER The maximum number of multicast probes in INCOMPLETE state, when the associated hardware address is unknown. Defaults diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a038feb63f23..518b484a7f07 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -133,6 +133,8 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) +#define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ + ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index e42d13b55cf3..e00bbb9c47bb 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -169,6 +169,7 @@ enum IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, IPV4_DEVCONF_DROP_GRATUITOUS_ARP, IPV4_DEVCONF_BC_FORWARDING, + IPV4_DEVCONF_ARP_EVICT_NOCARRIER, __IPV4_DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 1e05d3caa712..6a3b194c50fe 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -482,6 +482,7 @@ enum NET_IPV4_CONF_PROMOTE_SECONDARIES=20, NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, + NET_IPV4_CONF_ARP_EVICT_NOCARRIER=23, }; /* /proc/sys/net/ipv4/netfilter */ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 922dd73e5740..857a144b1ea9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1247,6 +1247,8 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; + struct in_device *in_dev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: @@ -1257,7 +1259,14 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&arp_tbl, dev); - if (!netif_carrier_ok(dev)) + + in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + evict_nocarrier = true; + else + evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev); + + if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&arp_tbl, dev); break; default: diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f4468980b675..ec73a0d52d3e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -75,6 +75,7 @@ static struct ipv4_devconf ipv4_devconf = { [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -87,6 +88,7 @@ static struct ipv4_devconf ipv4_devconf_dflt = { [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -2532,6 +2534,8 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), + DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, + "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), -- cgit v1.2.3 From 18ac597af25e9760b76471524096f5b29eb820e6 Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 1 Nov 2021 10:36:29 -0700 Subject: net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter In most situations the neighbor discovery cache should be cleared on a NOCARRIER event which is currently done unconditionally. But for wireless roams the neighbor discovery cache can and should remain intact since the underlying network has not changed. This patch introduces a sysctl option ndisc_evict_nocarrier which can be disabled by a wireless supplicant during a roam. This allows packets to be sent after a roam immediately without having to wait for neighbor discovery. A user reported roughly a 1 second delay after a roam before packets could be sent out (note, on IPv4). This delay was due to the ARP cache being cleared. During testing of this same scenario using IPv6 no delay was noticed, but regardless there is no reason to clear the ndisc cache for wireless roams. Signed-off-by: James Prestwood Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 9 +++++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 12 ++++++++++++ net/ipv6/ndisc.c | 12 +++++++++++- 5 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 18fde4ed7a5e..c61cc0219f4c 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2350,6 +2350,15 @@ ndisc_tclass - INTEGER * 0 - (default) +ndisc_evict_nocarrier - BOOLEAN + Clears the neighbor discovery table on NOCARRIER events. This option is + important for wireless devices where the neighbor discovery cache should + not be cleared when roaming between access points on the same network. + In most cases this should remain as the default (1). + + - 1 - (default): Clear neighbor discover cache on NOCARRIER events. + - 0 - Do not clear neighbor discovery cache on NOCARRIER events. + mldv1_unsolicited_report_interval - INTEGER The interval in milliseconds in which the next unsolicited MLDv1 report retransmit will take place. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c383630d3f06..20c1f968da7c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -79,6 +79,7 @@ struct ipv6_devconf { __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; + __u8 ndisc_evict_nocarrier; struct ctl_table_header *sysctl_header; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index b243a53fa985..d4178dace0bf 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -193,6 +193,7 @@ enum { DEVCONF_IOAM6_ENABLED, DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, + DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9e1463a2acae..3445f8017430 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -241,6 +241,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, + .ndisc_evict_nocarrier = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -300,6 +301,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, + .ndisc_evict_nocarrier = 1, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -5545,6 +5547,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; + array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; } static inline size_t inet6_ifla6_size(void) @@ -6986,6 +6989,15 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_douintvec, }, + { + .procname = "ndisc_evict_nocarrier", + .data = &ipv6_devconf.ndisc_evict_nocarrier, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)SYSCTL_ONE, + }, { /* sentinel */ } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 184190b9ea25..f03b597e4121 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1794,6 +1794,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: @@ -1810,10 +1811,19 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, in6_dev_put(idev); break; case NETDEV_CHANGE: + idev = in6_dev_get(dev); + if (!idev) + evict_nocarrier = true; + else { + evict_nocarrier = idev->cnf.ndisc_evict_nocarrier && + net->ipv6.devconf_all->ndisc_evict_nocarrier; + in6_dev_put(idev); + } + change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); - if (!netif_carrier_ok(dev)) + if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: -- cgit v1.2.3 From 1aabe578dd86e9f2867c4db4fba9a15f4ba1825d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 2 Nov 2021 15:02:36 -0700 Subject: ethtool: fix ethtool msg len calculation for pause stats ETHTOOL_A_PAUSE_STAT_MAX is the MAX attribute id, so we need to subtract non-stats and add one to get a count (IOW -2+1 == -1). Otherwise we'll see: ethnl cmd 21: calculated reply length 40, but consumed 52 Fixes: 9a27a33027f2 ("ethtool: add standard pause stats") Signed-off-by: Jakub Kicinski Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 3 +++ include/uapi/linux/ethtool_netlink.h | 4 +++- net/ethtool/pause.c | 3 +-- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 1e7bf78cb382..aba348d58ff6 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -10,6 +10,9 @@ #define __ETHTOOL_LINK_MODE_MASK_NWORDS \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) +#define ETHTOOL_PAUSE_STAT_CNT (__ETHTOOL_A_PAUSE_STAT_CNT - \ + ETHTOOL_A_PAUSE_STAT_TX_FRAMES) + enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index ca5fbb59fa42..999777d32dcf 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -411,7 +411,9 @@ enum { ETHTOOL_A_PAUSE_STAT_TX_FRAMES, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, - /* add new constants above here */ + /* add new constants above here + * adjust ETHTOOL_PAUSE_STAT_CNT if adding non-stats! + */ __ETHTOOL_A_PAUSE_STAT_CNT, ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) }; diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 9009f412151e..ee1e5806bc93 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -56,8 +56,7 @@ 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_64bit(sizeof(u64)) * - (ETHTOOL_A_PAUSE_STAT_MAX - 2); + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } -- cgit v1.2.3 From 00b06da29cf9dc633cdba87acd3f57f4df3fd5c7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 Oct 2021 09:14:19 -0500 Subject: signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed As Andy pointed out that there are races between force_sig_info_to_task and sigaction[1] when force_sig_info_task. As Kees discovered[2] ptrace is also able to change these signals. In the case of seeccomp killing a process with a signal it is a security violation to allow the signal to be caught or manipulated. Solve this problem by introducing a new flag SA_IMMUTABLE that prevents sigaction and ptrace from modifying these forced signals. This flag is carefully made kernel internal so that no new ABI is introduced. Longer term I think this can be solved by guaranteeing short circuit delivery of signals in this case. Unfortunately reliable and guaranteed short circuit delivery of these signals is still a ways off from being implemented, tested, and merged. So I have implemented a much simpler alternative for now. [1] https://lkml.kernel.org/r/b5d52d25-7bde-4030-a7b1-7c6f8ab90660@www.fastmail.com [2] https://lkml.kernel.org/r/202110281136.5CE65399A7@keescook Cc: stable@vger.kernel.org Fixes: 307d522f5eb8 ("signal/seccomp: Refactor seccomp signal and coredump generation") Tested-by: Andrea Righi Tested-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/signal_types.h | 3 +++ include/uapi/asm-generic/signal-defs.h | 1 + kernel/signal.c | 8 +++++++- 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 34cb28b8f16c..a70b2bdbf4d9 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -70,6 +70,9 @@ struct ksignal { int sig; }; +/* Used to kill the race between sigaction and forced signals */ +#define SA_IMMUTABLE 0x00800000 + #ifndef __ARCH_UAPI_SA_FLAGS #ifdef SA_RESTORER #define __ARCH_UAPI_SA_FLAGS SA_RESTORER diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index fe929e7b77ca..7572f2f46ee8 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -45,6 +45,7 @@ #define SA_UNSUPPORTED 0x00000400 #define SA_EXPOSE_TAGBITS 0x00000800 /* 0x00010000 used on mips */ +/* 0x00800000 used for internal SA_IMMUTABLE */ /* 0x01000000 used on x86 */ /* 0x02000000 used on x86 */ /* diff --git a/kernel/signal.c b/kernel/signal.c index 6a5e1802b9a2..056a107e3cbc 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1336,6 +1336,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool blocked = sigismember(&t->blocked, sig); if (blocked || ignored || sigdfl) { action->sa.sa_handler = SIG_DFL; + action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) { sigdelset(&t->blocked, sig); recalc_sigpending_and_wake(t); @@ -2760,7 +2761,8 @@ relock: if (!signr) break; /* will return 0 */ - if (unlikely(current->ptrace) && signr != SIGKILL) { + if (unlikely(current->ptrace) && (signr != SIGKILL) && + !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { signr = ptrace_signal(signr, &ksig->info); if (!signr) continue; @@ -4110,6 +4112,10 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) k = &p->sighand->action[sig-1]; spin_lock_irq(&p->sighand->siglock); + if (k->sa.sa_flags & SA_IMMUTABLE) { + spin_unlock_irq(&p->sighand->siglock); + return -EINVAL; + } if (oact) *oact = *k; -- cgit v1.2.3 From eff5cdd745a68863a73095b0b4d62d15e0d9d902 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Oct 2021 16:34:19 +0530 Subject: gpio: virtio: Add IRQ support This patch adds IRQ support for the virtio GPIO driver. Note that this uses the irq_bus_lock/unlock() callbacks, since those operations over virtio may sleep. Reviewed-by: Linus Walleij Signed-off-by: Viresh Kumar Acked-by: Michael S. Tsirkin Signed-off-by: Bartosz Golaszewski --- drivers/gpio/Kconfig | 1 + drivers/gpio/gpio-virtio.c | 302 ++++++++++++++++++++++++++++++++++++++- include/uapi/linux/virtio_gpio.h | 25 ++++ 3 files changed, 324 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 02eb9f647926..072ed610f9c6 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1686,6 +1686,7 @@ config GPIO_MOCKUP config GPIO_VIRTIO tristate "VirtIO GPIO support" depends on VIRTIO + select GPIOLIB_IRQCHIP help Say Y here to enable guest support for virtio-based GPIO controllers. diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c index d24f1c9264bc..aeec4bf0b625 100644 --- a/drivers/gpio/gpio-virtio.c +++ b/drivers/gpio/gpio-virtio.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -28,12 +29,30 @@ struct virtio_gpio_line { unsigned int rxlen; }; +struct vgpio_irq_line { + u8 type; + bool disabled; + bool masked; + bool queued; + bool update_pending; + bool queue_pending; + + struct virtio_gpio_irq_request ireq ____cacheline_aligned; + struct virtio_gpio_irq_response ires ____cacheline_aligned; +}; + struct virtio_gpio { struct virtio_device *vdev; struct mutex lock; /* Protects virtqueue operation */ struct gpio_chip gc; struct virtio_gpio_line *lines; struct virtqueue *request_vq; + + /* irq support */ + struct virtqueue *event_vq; + struct mutex irq_lock; /* Protects irq operation */ + raw_spinlock_t eventq_lock; /* Protects queuing of the buffer */ + struct vgpio_irq_line *irq_lines; }; static int _virtio_gpio_req(struct virtio_gpio *vgpio, u16 type, u16 gpio, @@ -186,6 +205,238 @@ static void virtio_gpio_set(struct gpio_chip *gc, unsigned int gpio, int value) virtio_gpio_req(vgpio, VIRTIO_GPIO_MSG_SET_VALUE, gpio, value, NULL); } +/* Interrupt handling */ +static void virtio_gpio_irq_prepare(struct virtio_gpio *vgpio, u16 gpio) +{ + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[gpio]; + struct virtio_gpio_irq_request *ireq = &irq_line->ireq; + struct virtio_gpio_irq_response *ires = &irq_line->ires; + struct scatterlist *sgs[2], req_sg, res_sg; + int ret; + + if (WARN_ON(irq_line->queued || irq_line->masked || irq_line->disabled)) + return; + + ireq->gpio = cpu_to_le16(gpio); + sg_init_one(&req_sg, ireq, sizeof(*ireq)); + sg_init_one(&res_sg, ires, sizeof(*ires)); + sgs[0] = &req_sg; + sgs[1] = &res_sg; + + ret = virtqueue_add_sgs(vgpio->event_vq, sgs, 1, 1, irq_line, GFP_ATOMIC); + if (ret) { + dev_err(&vgpio->vdev->dev, "failed to add request to eventq\n"); + return; + } + + irq_line->queued = true; + virtqueue_kick(vgpio->event_vq); +} + +static void virtio_gpio_irq_enable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->disabled = false; + irq_line->masked = false; + irq_line->queue_pending = true; + raw_spin_unlock(&vgpio->eventq_lock); + + irq_line->update_pending = true; +} + +static void virtio_gpio_irq_disable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->disabled = true; + irq_line->masked = true; + irq_line->queue_pending = false; + raw_spin_unlock(&vgpio->eventq_lock); + + irq_line->update_pending = true; +} + +static void virtio_gpio_irq_mask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->masked = true; + raw_spin_unlock(&vgpio->eventq_lock); +} + +static void virtio_gpio_irq_unmask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->masked = false; + + /* Queue the buffer unconditionally on unmask */ + virtio_gpio_irq_prepare(vgpio, d->hwirq); + raw_spin_unlock(&vgpio->eventq_lock); +} + +static int virtio_gpio_irq_set_type(struct irq_data *d, unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + switch (type) { + case IRQ_TYPE_EDGE_RISING: + type = VIRTIO_GPIO_IRQ_TYPE_EDGE_RISING; + break; + case IRQ_TYPE_EDGE_FALLING: + type = VIRTIO_GPIO_IRQ_TYPE_EDGE_FALLING; + break; + case IRQ_TYPE_EDGE_BOTH: + type = VIRTIO_GPIO_IRQ_TYPE_EDGE_BOTH; + break; + case IRQ_TYPE_LEVEL_LOW: + type = VIRTIO_GPIO_IRQ_TYPE_LEVEL_LOW; + break; + case IRQ_TYPE_LEVEL_HIGH: + type = VIRTIO_GPIO_IRQ_TYPE_LEVEL_HIGH; + break; + default: + dev_err(&vgpio->vdev->dev, "unsupported irq type: %u\n", type); + return -EINVAL; + } + + irq_line->type = type; + irq_line->update_pending = true; + + return 0; +} + +static void virtio_gpio_irq_bus_lock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + + mutex_lock(&vgpio->irq_lock); +} + +static void virtio_gpio_irq_bus_sync_unlock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + u8 type = irq_line->disabled ? VIRTIO_GPIO_IRQ_TYPE_NONE : irq_line->type; + unsigned long flags; + + if (irq_line->update_pending) { + irq_line->update_pending = false; + virtio_gpio_req(vgpio, VIRTIO_GPIO_MSG_IRQ_TYPE, d->hwirq, type, + NULL); + + /* Queue the buffer only after interrupt is enabled */ + raw_spin_lock_irqsave(&vgpio->eventq_lock, flags); + if (irq_line->queue_pending) { + irq_line->queue_pending = false; + virtio_gpio_irq_prepare(vgpio, d->hwirq); + } + raw_spin_unlock_irqrestore(&vgpio->eventq_lock, flags); + } + + mutex_unlock(&vgpio->irq_lock); +} + +static struct irq_chip vgpio_irq_chip = { + .name = "virtio-gpio", + .irq_enable = virtio_gpio_irq_enable, + .irq_disable = virtio_gpio_irq_disable, + .irq_mask = virtio_gpio_irq_mask, + .irq_unmask = virtio_gpio_irq_unmask, + .irq_set_type = virtio_gpio_irq_set_type, + + /* These are required to implement irqchip for slow busses */ + .irq_bus_lock = virtio_gpio_irq_bus_lock, + .irq_bus_sync_unlock = virtio_gpio_irq_bus_sync_unlock, +}; + +static bool ignore_irq(struct virtio_gpio *vgpio, int gpio, + struct vgpio_irq_line *irq_line) +{ + bool ignore = false; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->queued = false; + + /* Interrupt is disabled currently */ + if (irq_line->masked || irq_line->disabled) { + ignore = true; + goto unlock; + } + + /* + * Buffer is returned as the interrupt was disabled earlier, but is + * enabled again now. Requeue the buffers. + */ + if (irq_line->ires.status == VIRTIO_GPIO_IRQ_STATUS_INVALID) { + virtio_gpio_irq_prepare(vgpio, gpio); + ignore = true; + goto unlock; + } + + if (WARN_ON(irq_line->ires.status != VIRTIO_GPIO_IRQ_STATUS_VALID)) + ignore = true; + +unlock: + raw_spin_unlock(&vgpio->eventq_lock); + + return ignore; +} + +static void virtio_gpio_event_vq(struct virtqueue *vq) +{ + struct virtio_gpio *vgpio = vq->vdev->priv; + struct device *dev = &vgpio->vdev->dev; + struct vgpio_irq_line *irq_line; + int gpio, ret; + unsigned int len; + + while (true) { + irq_line = virtqueue_get_buf(vgpio->event_vq, &len); + if (!irq_line) + break; + + if (len != sizeof(irq_line->ires)) { + dev_err(dev, "irq with incorrect length (%u : %u)\n", + len, (unsigned int)sizeof(irq_line->ires)); + continue; + } + + /* + * Find GPIO line number from the offset of irq_line within the + * irq_lines block. We can also get GPIO number from + * irq-request, but better not to rely on a buffer returned by + * remote. + */ + gpio = irq_line - vgpio->irq_lines; + WARN_ON(gpio >= vgpio->gc.ngpio); + + if (unlikely(ignore_irq(vgpio, gpio, irq_line))) + continue; + + ret = generic_handle_domain_irq(vgpio->gc.irq.domain, gpio); + if (ret) + dev_err(dev, "failed to handle interrupt: %d\n", ret); + }; +} + static void virtio_gpio_request_vq(struct virtqueue *vq) { struct virtio_gpio_line *line; @@ -210,14 +461,15 @@ static void virtio_gpio_free_vqs(struct virtio_device *vdev) static int virtio_gpio_alloc_vqs(struct virtio_gpio *vgpio, struct virtio_device *vdev) { - const char * const names[] = { "requestq" }; + const char * const names[] = { "requestq", "eventq" }; vq_callback_t *cbs[] = { virtio_gpio_request_vq, + virtio_gpio_event_vq, }; - struct virtqueue *vqs[1] = { NULL }; + struct virtqueue *vqs[2] = { NULL, NULL }; int ret; - ret = virtio_find_vqs(vdev, 1, vqs, cbs, names, NULL); + ret = virtio_find_vqs(vdev, vgpio->irq_lines ? 2 : 1, vqs, cbs, names, NULL); if (ret) { dev_err(&vdev->dev, "failed to find vqs: %d\n", ret); return ret; @@ -225,11 +477,23 @@ static int virtio_gpio_alloc_vqs(struct virtio_gpio *vgpio, if (!vqs[0]) { dev_err(&vdev->dev, "failed to find requestq vq\n"); - return -ENODEV; + goto out; } vgpio->request_vq = vqs[0]; + if (vgpio->irq_lines && !vqs[1]) { + dev_err(&vdev->dev, "failed to find eventq vq\n"); + goto out; + } + vgpio->event_vq = vqs[1]; + return 0; + +out: + if (vqs[0] || vqs[1]) + virtio_gpio_free_vqs(vdev); + + return -ENODEV; } static const char **virtio_gpio_get_names(struct virtio_gpio *vgpio, @@ -325,6 +589,30 @@ static int virtio_gpio_probe(struct virtio_device *vdev) vgpio->gc.owner = THIS_MODULE; vgpio->gc.can_sleep = true; + /* Interrupt support */ + if (virtio_has_feature(vdev, VIRTIO_GPIO_F_IRQ)) { + vgpio->irq_lines = devm_kcalloc(dev, ngpio, sizeof(*vgpio->irq_lines), GFP_KERNEL); + if (!vgpio->irq_lines) + return -ENOMEM; + + /* The event comes from the outside so no parent handler */ + vgpio->gc.irq.parent_handler = NULL; + vgpio->gc.irq.num_parents = 0; + vgpio->gc.irq.parents = NULL; + vgpio->gc.irq.default_type = IRQ_TYPE_NONE; + vgpio->gc.irq.handler = handle_level_irq; + vgpio->gc.irq.chip = &vgpio_irq_chip; + + for (i = 0; i < ngpio; i++) { + vgpio->irq_lines[i].type = VIRTIO_GPIO_IRQ_TYPE_NONE; + vgpio->irq_lines[i].disabled = true; + vgpio->irq_lines[i].masked = true; + } + + mutex_init(&vgpio->irq_lock); + raw_spin_lock_init(&vgpio->eventq_lock); + } + ret = virtio_gpio_alloc_vqs(vgpio, vdev); if (ret) return ret; @@ -357,7 +645,13 @@ static const struct virtio_device_id id_table[] = { }; MODULE_DEVICE_TABLE(virtio, id_table); +static const unsigned int features[] = { + VIRTIO_GPIO_F_IRQ, +}; + static struct virtio_driver virtio_gpio_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), .id_table = id_table, .probe = virtio_gpio_probe, .remove = virtio_gpio_remove, diff --git a/include/uapi/linux/virtio_gpio.h b/include/uapi/linux/virtio_gpio.h index 0445f905d8cc..d04af9c5f0de 100644 --- a/include/uapi/linux/virtio_gpio.h +++ b/include/uapi/linux/virtio_gpio.h @@ -5,12 +5,16 @@ #include +/* Virtio GPIO Feature bits */ +#define VIRTIO_GPIO_F_IRQ 0 + /* Virtio GPIO request types */ #define VIRTIO_GPIO_MSG_GET_NAMES 0x0001 #define VIRTIO_GPIO_MSG_GET_DIRECTION 0x0002 #define VIRTIO_GPIO_MSG_SET_DIRECTION 0x0003 #define VIRTIO_GPIO_MSG_GET_VALUE 0x0004 #define VIRTIO_GPIO_MSG_SET_VALUE 0x0005 +#define VIRTIO_GPIO_MSG_IRQ_TYPE 0x0006 /* Possible values of the status field */ #define VIRTIO_GPIO_STATUS_OK 0x0 @@ -21,6 +25,14 @@ #define VIRTIO_GPIO_DIRECTION_OUT 0x01 #define VIRTIO_GPIO_DIRECTION_IN 0x02 +/* Virtio GPIO IRQ types */ +#define VIRTIO_GPIO_IRQ_TYPE_NONE 0x00 +#define VIRTIO_GPIO_IRQ_TYPE_EDGE_RISING 0x01 +#define VIRTIO_GPIO_IRQ_TYPE_EDGE_FALLING 0x02 +#define VIRTIO_GPIO_IRQ_TYPE_EDGE_BOTH 0x03 +#define VIRTIO_GPIO_IRQ_TYPE_LEVEL_HIGH 0x04 +#define VIRTIO_GPIO_IRQ_TYPE_LEVEL_LOW 0x08 + struct virtio_gpio_config { __le16 ngpio; __u8 padding[2]; @@ -44,4 +56,17 @@ struct virtio_gpio_response_get_names { __u8 value[]; }; +/* Virtio GPIO IRQ Request / Response */ +struct virtio_gpio_irq_request { + __le16 gpio; +}; + +struct virtio_gpio_irq_response { + __u8 status; +}; + +/* Possible values of the interrupt status field */ +#define VIRTIO_GPIO_IRQ_STATUS_INVALID 0x0 +#define VIRTIO_GPIO_IRQ_STATUS_VALID 0x1 + #endif /* _LINUX_VIRTIO_GPIO_H */ -- cgit v1.2.3 From 7d0003da6297eb128f3490e396e6fc6df71557cd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 1 Nov 2021 05:11:25 -0400 Subject: virtio_gpio: drop packed attribute Declaring the struct packed here is mostly harmless, but gives a bad example for people to copy. As the struct is packed and aligned manually, let's just drop the attribute. Signed-off-by: Michael S. Tsirkin Acked-by: Viresh Kumar Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/virtio_gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_gpio.h b/include/uapi/linux/virtio_gpio.h index d04af9c5f0de..d4b29d9a39dd 100644 --- a/include/uapi/linux/virtio_gpio.h +++ b/include/uapi/linux/virtio_gpio.h @@ -37,7 +37,7 @@ struct virtio_gpio_config { __le16 ngpio; __u8 padding[2]; __le32 gpio_names_size; -} __packed; +}; /* Virtio GPIO Request / Response */ struct virtio_gpio_request { -- cgit v1.2.3 From 7c7e3d31e7856a8260a254f8c71db416f7f9f5a1 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 5 Nov 2021 16:23:29 -0700 Subject: bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Tested-by: Hengqi Chen Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 20 +++++++++++ kernel/bpf/btf.c | 5 ++- kernel/bpf/mmap_unlock_work.h | 65 ++++++++++++++++++++++++++++++++++ kernel/bpf/stackmap.c | 80 ++++-------------------------------------- kernel/bpf/task_iter.c | 76 +++++++++++++++++++++++++++++++++++---- kernel/bpf/verifier.c | 34 ++++++++++++++++++ kernel/trace/bpf_trace.c | 2 ++ tools/include/uapi/linux/bpf.h | 20 +++++++++++ 9 files changed, 222 insertions(+), 81 deletions(-) create mode 100644 kernel/bpf/mmap_unlock_work.h (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2be6dfd68df9..df3410bff4b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2157,6 +2157,7 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; +extern const struct bpf_func_proto bpf_find_vma_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba5af15e25f5..509eee5f0393 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4938,6 +4938,25 @@ union bpf_attr { * **-ENOENT** if symbol is not found. * * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5120,6 +5139,7 @@ union bpf_attr { FN(trace_vprintk), \ FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ + FN(find_vma), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dbc3ad07e21b..cdb0fba65600 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6342,7 +6342,10 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .arg4_type = ARG_ANYTHING, }; -BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) +BTF_ID_LIST_GLOBAL(btf_task_struct_ids) +BTF_ID(struct, task_struct) +BTF_ID(struct, file) +BTF_ID(struct, vm_area_struct) /* BTF ID set registration API for modules */ diff --git a/kernel/bpf/mmap_unlock_work.h b/kernel/bpf/mmap_unlock_work.h new file mode 100644 index 000000000000..5d18d7d85bef --- /dev/null +++ b/kernel/bpf/mmap_unlock_work.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Facebook + */ + +#ifndef __MMAP_UNLOCK_WORK_H__ +#define __MMAP_UNLOCK_WORK_H__ +#include + +/* irq_work to run mmap_read_unlock() in irq_work */ +struct mmap_unlock_irq_work { + struct irq_work irq_work; + struct mm_struct *mm; +}; + +DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +/* + * We cannot do mmap_read_unlock() when the irq is disabled, because of + * risk to deadlock with rq_lock. To look up vma when the irqs are + * disabled, we need to run mmap_read_unlock() in irq_work. We use a + * percpu variable to do the irq_work. If the irq_work is already used + * by another lookup, we fall over. + */ +static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr) +{ + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = false; + + if (irqs_disabled()) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + work = this_cpu_ptr(&mmap_unlock_work); + if (irq_work_is_busy(&work->irq_work)) { + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } + } else { + /* + * PREEMPT_RT does not allow to trylock mmap sem in + * interrupt disabled context. Force the fallback code. + */ + irq_work_busy = true; + } + } + + *work_ptr = work; + return irq_work_busy; +} + +static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm) +{ + if (!work) { + mmap_read_unlock(mm); + } else { + work->mm = mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); + irq_work_queue(&work->irq_work); + } +} + +#endif /* __MMAP_UNLOCK_WORK_H__ */ diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6e75bbee39f0..1de0a1b03636 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,10 +7,10 @@ #include #include #include -#include #include #include #include "percpu_freelist.h" +#include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ @@ -31,25 +31,6 @@ struct bpf_stack_map { struct stack_map_bucket *buckets[]; }; -/* irq_work to run up_read() for build_id lookup in nmi context */ -struct stack_map_irq_work { - struct irq_work irq_work; - struct mm_struct *mm; -}; - -static void do_up_read(struct irq_work *entry) -{ - struct stack_map_irq_work *work; - - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) - return; - - work = container_of(entry, struct stack_map_irq_work, irq_work); - mmap_read_unlock_non_owner(work->mm); -} - -static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work); - static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -149,35 +130,13 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); struct vm_area_struct *vma; - bool irq_work_busy = false; - struct stack_map_irq_work *work = NULL; - - if (irqs_disabled()) { - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { - work = this_cpu_ptr(&up_read_work); - if (irq_work_is_busy(&work->irq_work)) { - /* cannot queue more up_read, fallback */ - irq_work_busy = true; - } - } else { - /* - * PREEMPT_RT does not allow to trylock mmap sem in - * interrupt disabled context. Force the fallback code. - */ - irq_work_busy = true; - } - } - /* - * We cannot do up_read() when the irq is disabled, because of - * risk to deadlock with rq_lock. To do build_id lookup when the - * irqs are disabled, we need to run up_read() in irq_work. We use - * a percpu variable to do the irq_work. If the irq_work is - * already used by another lookup, we fall back to report ips. - * - * Same fallback is used for kernel stack (!user) on a stackmap - * with build_id. + /* If the irq_work is in use, fall back to report ips. Same + * fallback is used for kernel stack (!user) on a stackmap with + * build_id. */ if (!user || !current || !current->mm || irq_work_busy || !mmap_read_trylock(current->mm)) { @@ -203,19 +162,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; } - - if (!work) { - mmap_read_unlock(current->mm); - } else { - work->mm = current->mm; - - /* The lock will be released once we're out of interrupt - * context. Tell lockdep that we've released it now so - * it doesn't complain that we forgot to release it. - */ - rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); - irq_work_queue(&work->irq_work); - } + bpf_mmap_unlock_mm(work, current->mm); } static struct perf_callchain_entry * @@ -719,16 +666,3 @@ const struct bpf_map_ops stack_trace_map_ops = { .map_btf_name = "bpf_stack_map", .map_btf_id = &stack_trace_map_btf_id, }; - -static int __init stack_map_init(void) -{ - int cpu; - struct stack_map_irq_work *work; - - for_each_possible_cpu(cpu) { - work = per_cpu_ptr(&up_read_work, cpu); - init_irq_work(&work->irq_work, do_up_read); - } - return 0; -} -subsys_initcall(stack_map_init); diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index b48750bfba5a..f171479f7dd6 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -8,6 +8,7 @@ #include #include #include +#include "mmap_unlock_work.h" struct bpf_iter_seq_task_common { struct pid_namespace *ns; @@ -524,10 +525,6 @@ static const struct seq_operations task_vma_seq_ops = { .show = task_vma_seq_show, }; -BTF_ID_LIST(btf_task_file_ids) -BTF_ID(struct, file) -BTF_ID(struct, vm_area_struct) - static const struct bpf_iter_seq_info task_seq_info = { .seq_ops = &task_seq_ops, .init_seq_private = init_seq_pidns, @@ -586,9 +583,74 @@ static struct bpf_iter_reg task_vma_reg_info = { .seq_info = &task_vma_seq_info, }; +BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start, + bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags) +{ + struct mmap_unlock_irq_work *work = NULL; + struct vm_area_struct *vma; + bool irq_work_busy = false; + struct mm_struct *mm; + int ret = -ENOENT; + + if (flags) + return -EINVAL; + + if (!task) + return -ENOENT; + + mm = task->mm; + if (!mm) + return -ENOENT; + + irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); + + if (irq_work_busy || !mmap_read_trylock(mm)) + return -EBUSY; + + vma = find_vma(mm, start); + + if (vma && vma->vm_start <= start && vma->vm_end > start) { + callback_fn((u64)(long)task, (u64)(long)vma, + (u64)(long)callback_ctx, 0, 0); + ret = 0; + } + bpf_mmap_unlock_mm(work, mm); + return ret; +} + +const struct bpf_func_proto bpf_find_vma_proto = { + .func = bpf_find_vma, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_task_struct_ids[0], + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_FUNC, + .arg4_type = ARG_PTR_TO_STACK_OR_NULL, + .arg5_type = ARG_ANYTHING, +}; + +DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +static void do_mmap_read_unlock(struct irq_work *entry) +{ + struct mmap_unlock_irq_work *work; + + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + + work = container_of(entry, struct mmap_unlock_irq_work, irq_work); + mmap_read_unlock_non_owner(work->mm); +} + static int __init task_iter_init(void) { - int ret; + struct mmap_unlock_irq_work *work; + int ret, cpu; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&mmap_unlock_work, cpu); + init_irq_work(&work->irq_work, do_mmap_read_unlock); + } task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; ret = bpf_iter_reg_target(&task_reg_info); @@ -596,13 +658,13 @@ static int __init task_iter_init(void) return ret; task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[0]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_struct_ids[1]; ret = bpf_iter_reg_target(&task_file_reg_info); if (ret) return ret; task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_struct_ids[2]; return bpf_iter_reg_target(&task_vma_reg_info); } late_initcall(task_iter_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0dca726ebfd..1aafb43f61d1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6132,6 +6132,33 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_find_vma_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_find_vma(struct task_struct *task, u64 addr, + * void *callback_fn, void *callback_ctx, u64 flags) + * (callback_fn)(struct task_struct *task, + * struct vm_area_struct *vma, void *callback_ctx); + */ + callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; + + callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; + __mark_reg_known_zero(&callee->regs[BPF_REG_2]); + callee->regs[BPF_REG_2].btf = btf_vmlinux; + callee->regs[BPF_REG_2].btf_id = btf_task_struct_ids[2]; + + /* pointer to stack or null */ + callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_callback_fn = true; + return 0; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; @@ -6489,6 +6516,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } + if (func_id == BPF_FUNC_find_vma) { + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_find_vma_callback_state); + if (err < 0) + return -EINVAL; + } + if (func_id == BPF_FUNC_snprintf) { err = check_bpf_snprintf_call(env, regs); if (err < 0) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..390176a3031a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1208,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_find_vma: + return &bpf_find_vma_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ba5af15e25f5..509eee5f0393 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4938,6 +4938,25 @@ union bpf_attr { * **-ENOENT** if symbol is not found. * * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5120,6 +5139,7 @@ union bpf_attr { FN(trace_vprintk), \ FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ + FN(find_vma), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From aedad3e1c6ddec234b63cfb57ac231da0f680e50 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 5 Nov 2021 16:08:29 -0700 Subject: arm64: mte: change PR_MTE_TCF_NONE back into an unsigned long This constant was previously an unsigned long, but was changed into an int in commit 433c38f40f6a ("arm64: mte: change ASYNC and SYNC TCF settings into bitfields"). This ended up causing spurious unsigned-signed comparison warnings in expressions such as: (x & PR_MTE_TCF_MASK) != PR_MTE_TCF_NONE Therefore, change it back into an unsigned long to silence these warnings. Link: https://linux-review.googlesource.com/id/I07a72310db30227a5b7d789d0b817d78b657c639 Signed-off-by: Peter Collingbourne Link: https://lore.kernel.org/r/20211105230829.2254790-1-pcc@google.com Signed-off-by: Will Deacon --- include/uapi/linux/prctl.h | 2 +- tools/include/uapi/linux/prctl.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 43bd7f713c39..de45fcd2dcbe 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 43bd7f713c39..de45fcd2dcbe 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) -- cgit v1.2.3 From 61082ad6a6e1f999eef7e7e90046486c87933b1e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 15 Mar 2021 16:57:13 +0100 Subject: virtio-mem: support VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE The initial virtio-mem spec states that while unplugged memory should not be read, the device still has to allow for reading unplugged memory inside the usable region. The primary motivation for this default handling was to simplify bringup of virtio-mem, because there were corner cases where Linux might have accidentially read unplugged memory inside added Linux memory blocks. In the meantime, we: 1. Removed /dev/kmem in commit bbcd53c96071 ("drivers/char: remove /dev/kmem for good") 2. Disallowed access to virtio-mem device memory via /dev/mem in commit 2128f4e21aa2 ("virtio-mem: disallow mapping virtio-mem memory via /dev/mem") 3. Sanitized access to virtio-mem device memory via /proc/kcore in commit 0daa322b8ff9 ("fs/proc/kcore: don't read offline sections, logically offline pages and hwpoisoned pages") 4. Sanitized access to virtio-mem device memory via /proc/vmcore in commit ce2814622e84 ("virtio-mem: kdump mode to sanitize /proc/vmcore access") "Accidential" access to unplugged memory is no longer possible; we can support the new VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE feature that will be required by some hypervisors implementing virtio-mem in the near future. Acked-by: Michael S. Tsirkin Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Marek Kedzierski Cc: Hui Zhu Cc: Sebastien Boeuf Cc: Pankaj Gupta Cc: Wei Yang Signed-off-by: David Hildenbrand --- drivers/virtio/virtio_mem.c | 1 + include/uapi/linux/virtio_mem.h | 9 ++++++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 0da0af251c73..96e5a8782769 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -2889,6 +2889,7 @@ static unsigned int virtio_mem_features[] = { #if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA) VIRTIO_MEM_F_ACPI_PXM, #endif + VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, }; static const struct virtio_device_id virtio_mem_id_table[] = { diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index 70e01c687d5e..e9122f1d0e0c 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -68,9 +68,10 @@ * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG). * * There are no guarantees what will happen if unplugged memory is - * read/written. Such memory should, in general, not be touched. E.g., - * even writing might succeed, but the values will simply be discarded at - * random points in time. + * read/written. In general, unplugged memory should not be touched, because + * the resulting action is undefined. There is one exception: without + * VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, unplugged memory inside the usable + * region can be read, to simplify creation of memory dumps. * * It can happen that the device cannot process a request, because it is * busy. The device driver has to retry later. @@ -87,6 +88,8 @@ /* node_id is an ACPI PXM and is valid */ #define VIRTIO_MEM_F_ACPI_PXM 0 +/* unplugged memory must not be accessed */ +#define VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE 1 /* --- virtio-mem: guest -> host requests --- */ -- cgit v1.2.3 From f89315650ba34ec6c91a8bded72796980bee2a4d Mon Sep 17 00:00:00 2001 From: Mark Pashmfouroush Date: Wed, 10 Nov 2021 11:10:15 +0000 Subject: bpf: Add ingress_ifindex to bpf_sk_lookup It may be helpful to have access to the ifindex during bpf socket lookup. An example may be to scope certain socket lookup logic to specific interfaces, i.e. an interface may be made exempt from custom lookup code. Add the ifindex of the arriving connection to the bpf_sk_lookup API. Signed-off-by: Mark Pashmfouroush Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211110111016.5670-2-markpash@cloudflare.com --- include/linux/filter.h | 7 +++++-- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 7 +++++++ net/ipv4/inet_hashtables.c | 8 ++++---- net/ipv4/udp.c | 8 ++++---- net/ipv6/inet6_hashtables.c | 8 ++++---- net/ipv6/udp.c | 8 ++++---- tools/include/uapi/linux/bpf.h | 1 + 8 files changed, 30 insertions(+), 18 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/filter.h b/include/linux/filter.h index 24b7ed2677af..b6a216eb217a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1374,6 +1374,7 @@ struct bpf_sk_lookup_kern { const struct in6_addr *daddr; } v6; struct sock *selected_sk; + u32 ingress_ifindex; bool no_reuseport; }; @@ -1436,7 +1437,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1452,6 +1453,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, .v4.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; @@ -1474,7 +1476,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const __be16 sport, const struct in6_addr *daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1490,6 +1492,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, .v6.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 509eee5f0393..6297eafdc40f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6316,6 +6316,7 @@ struct bpf_sk_lookup { __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* diff --git a/net/core/filter.c b/net/core/filter.c index 8e8d3b49c297..315a58466fc9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10491,6 +10491,7 @@ static bool sk_lookup_is_valid_access(int off, int size, case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, remote_port): case bpf_ctx_range(struct bpf_sk_lookup, local_port): + case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); @@ -10580,6 +10581,12 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; + + case offsetof(struct bpf_sk_lookup, ingress_ifindex): + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + ingress_ifindex, 4, target_size)); + break; } return insn - insn_buf; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 75737267746f..30ab717ff1b8 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -307,7 +307,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum) + __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -315,8 +315,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (hashinfo != &tcp_hashinfo) return NULL; /* only TCP is supported */ - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -340,7 +340,7 @@ struct sock *__inet_lookup_listener(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (result) goto done; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2fffcf2b54f3..5fceee3de65d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -460,7 +460,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, struct udp_table *udptable, struct sk_buff *skb, __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum) + __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -468,8 +468,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, if (udptable != &udp_table) return NULL; /* only UDP is supported */ - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -505,7 +505,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp4_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (sk) { result = sk; goto done; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 67c9114835c8..4514444e96c8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -165,7 +165,7 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, - const u16 hnum) + const u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -173,8 +173,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, if (hashinfo != &tcp_hashinfo) return NULL; /* only TCP is supported */ - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -198,7 +198,7 @@ struct sock *inet6_lookup_listener(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet6_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (result) goto done; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 12c12619ee35..ea4ea525f94a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -195,7 +195,7 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, - u16 hnum) + u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -203,8 +203,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, if (udptable != &udp_table) return NULL; /* only UDP is supported */ - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -240,7 +240,7 @@ struct sock *__udp6_lib_lookup(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp6_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (sk) { result = sk; goto done; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 509eee5f0393..6297eafdc40f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6316,6 +6316,7 @@ struct bpf_sk_lookup { __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* -- cgit v1.2.3 From b56639318bb2be66aceba92836279714488709b4 Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Thu, 21 Oct 2021 10:43:00 -0700 Subject: KVM: SEV: Add support for SEV intra host migration For SEV to work with intra host migration, contents of the SEV info struct such as the ASID (used to index the encryption key in the AMD SP) and the list of memory regions need to be transferred to the target VM. This change adds a commands for a target VMM to get a source SEV VM's sev info. Signed-off-by: Peter Gonda Suggested-by: Sean Christopherson Reviewed-by: Marc Orr Cc: Marc Orr Cc: Paolo Bonzini Cc: Sean Christopherson Cc: David Rientjes Cc: Dr. David Alan Gilbert Cc: Brijesh Singh Cc: Tom Lendacky Cc: Vitaly Kuznetsov Cc: Wanpeng Li Cc: Jim Mattson Cc: Joerg Roedel Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Message-Id: <20211021174303.385706-3-pgonda@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 14 ++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm/sev.c | 152 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 1 + arch/x86/kvm/svm/svm.h | 2 + arch/x86/kvm/x86.c | 6 ++ include/uapi/linux/kvm.h | 1 + 7 files changed, 177 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 3b093d6dbe22..aeeb071c7688 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6911,6 +6911,20 @@ MAP_SHARED mmap will result in an -EINVAL return. When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to perform a bulk copy of tags to/from the guest. +7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM +------------------------------------- + +Architectures: x86 SEV enabled +Type: vm +Parameters: args[0] is the fd of the source vm +Returns: 0 on success + +This capability enables userspace to migrate the encryption context from the VM +indicated by the fd to the VM this is called on. + +This is intended to support intra-host migration of VMs between userspace VMMs, +upgrading the VMM process without interrupting the guest. + 8. Other capabilities. ====================== diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 88fce6ab4bbd..0e9d1786c865 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1476,6 +1476,7 @@ struct kvm_x86_ops { int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 227becd93cb6..8b529022f0cf 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1532,6 +1532,158 @@ static bool cmd_allowed_from_miror(u32 cmd_id) return false; } +static int sev_lock_for_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + /* + * Bail if this VM is already involved in a migration to avoid deadlock + * between two VMs trying to migrate to/from each other. + */ + if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + return -EBUSY; + + mutex_lock(&kvm->lock); + + return 0; +} + +static void sev_unlock_after_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + mutex_unlock(&kvm->lock); + atomic_set_release(&sev->migration_in_progress, 0); +} + + +static int sev_lock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, j; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable(&vcpu->mutex)) + goto out_unlock; + } + + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} + +static void sev_unlock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_unlock(&vcpu->mutex); + } +} + +static void sev_migrate_from(struct kvm_sev_info *dst, + struct kvm_sev_info *src) +{ + dst->active = true; + dst->asid = src->asid; + dst->handle = src->handle; + dst->pages_locked = src->pages_locked; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + + if (dst->misc_cg != src->misc_cg) + sev_misc_cg_uncharge(src); + + put_misc_cg(src->misc_cg); + src->misc_cg = NULL; + + INIT_LIST_HEAD(&dst->regions_list); + list_replace_init(&src->regions_list, &dst->regions_list); +} + +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *src_sev; + struct file *source_kvm_file; + struct kvm *source_kvm; + int ret; + + ret = sev_lock_for_migration(kvm); + if (ret) + return ret; + + if (sev_guest(kvm)) { + ret = -EINVAL; + goto out_unlock; + } + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = source_kvm_file->private_data; + ret = sev_lock_for_migration(source_kvm); + if (ret) + goto out_fput; + + if (!sev_guest(source_kvm) || sev_es_guest(source_kvm)) { + ret = -EINVAL; + goto out_source; + } + + src_sev = &to_kvm_svm(source_kvm)->sev_info; + dst_sev->misc_cg = get_current_misc_cg(); + if (dst_sev->misc_cg != src_sev->misc_cg) { + ret = sev_misc_cg_try_charge(dst_sev); + if (ret) + goto out_dst_put_cgroup; + } + + ret = sev_lock_vcpus_for_migration(kvm); + if (ret) + goto out_dst_cgroup; + ret = sev_lock_vcpus_for_migration(source_kvm); + if (ret) + goto out_dst_vcpu; + + sev_migrate_from(dst_sev, src_sev); + kvm_vm_dead(source_kvm); + ret = 0; + + sev_unlock_vcpus_for_migration(source_kvm); +out_dst_vcpu: + sev_unlock_vcpus_for_migration(kvm); +out_dst_cgroup: + if (ret < 0) { + sev_misc_cg_uncharge(dst_sev); +out_dst_put_cgroup: + put_misc_cg(dst_sev->misc_cg); + dst_sev->misc_cg = NULL; + } +out_source: + sev_unlock_after_migration(source_kvm); +out_fput: + if (source_kvm_file) + fput(source_kvm_file); +out_unlock: + sev_unlock_after_migration(kvm); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1143b4ac900d..b4f2d1d55bd2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4699,6 +4699,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_unreg_region = svm_unregister_enc_region, .vm_copy_enc_context_from = svm_vm_copy_asid_from, + .vm_move_enc_context_from = svm_vm_migrate_from, .can_emulate_instruction = svm_can_emulate_instruction, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 80048841cad9..d4eae06b0695 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -80,6 +80,7 @@ struct kvm_sev_info { u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ + atomic_t migration_in_progress; }; struct kvm_svm { @@ -562,6 +563,7 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd); +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd); void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 622cb75f5e75..4417f375da77 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5845,6 +5845,12 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: + r = -EINVAL; + if (kvm_x86_ops.vm_move_enc_context_from) + r = kvm_x86_ops.vm_move_enc_context_from( + kvm, cap->args[0]); + return r; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 78f0719cc2a3..1daa45268de2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1130,6 +1130,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_BINARY_STATS_FD 203 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 +#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 8c42d2fa4eeab6c37a0b1b1aa7a2715248ef4f34 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 11 Nov 2021 17:26:09 -0800 Subject: bpf: Support BTF_KIND_TYPE_TAG for btf_type_tag attributes LLVM patches ([1] for clang, [2] and [3] for BPF backend) added support for btf_type_tag attributes. This patch added support for the kernel. The main motivation for btf_type_tag is to bring kernel annotations __user, __rcu etc. to btf. With such information available in btf, bpf verifier can detect mis-usages and reject the program. For example, for __user tagged pointer, developers can then use proper helper like bpf_probe_read_user() etc. to read the data. BTF_KIND_TYPE_TAG may also useful for other tracing facility where instead of to require user to specify kernel/user address type, the kernel can detect it by itself with btf. [1] https://reviews.llvm.org/D111199 [2] https://reviews.llvm.org/D113222 [3] https://reviews.llvm.org/D113496 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211112012609.1505032-1-yhs@fb.com --- include/uapi/linux/btf.h | 3 ++- kernel/bpf/btf.c | 14 +++++++++++++- tools/include/uapi/linux/btf.h | 3 ++- 3 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index deb12f755f0f..b0d8fea1951d 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and DECL_TAG. + * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. * "type" is a type_id referring to another type. */ union { @@ -75,6 +75,7 @@ enum { BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ + BTF_KIND_TYPE_TAG = 18, /* Type Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index cdb0fba65600..1dd9ba82da1e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -282,6 +282,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -418,6 +419,7 @@ static bool btf_type_is_modifier(const struct btf_type *t) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return true; } @@ -1737,6 +1739,7 @@ __btf_resolve_size(const struct btf *btf, const struct btf_type *type, case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: id = type->type; type = btf_type_by_id(btf, type->type); break; @@ -2345,6 +2348,8 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { + const char *value; + if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; @@ -2360,7 +2365,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } - /* typedef type must have a valid name, and other ref types, + /* typedef/type_tag type must have a valid name, and other ref types, * volatile, const, restrict, should have a null name. */ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { @@ -2369,6 +2374,12 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } + } else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) { + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } } else { if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); @@ -4059,6 +4070,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, [BTF_KIND_DECL_TAG] = &decl_tag_ops, + [BTF_KIND_TYPE_TAG] = &modifier_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index deb12f755f0f..b0d8fea1951d 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and DECL_TAG. + * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. * "type" is a type_id referring to another type. */ union { @@ -75,6 +75,7 @@ enum { BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ + BTF_KIND_TYPE_TAG = 18, /* Type Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, -- cgit v1.2.3 From ef9f18a9e3a04126cf017216193166abe03dedef Mon Sep 17 00:00:00 2001 From: Dillon Min Date: Tue, 19 Oct 2021 09:43:21 +0100 Subject: media: v4l2-ctrls: Add RGB color effects control Add V4L2_COLORFX_SET_RGB color effects control, V4L2_CID_COLORFX_RGB for RGB color setting. with two mirror changes: - change 0xFFFFFF to 0xffffff - fix comments 2^24 to 2^24 - 1 [hverkuil: dropped spaces around + with V4L2_CID_BASE for consistency] Signed-off-by: Dillon Min Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/control.rst | 9 +++++++++ drivers/media/v4l2-core/v4l2-ctrls-defs.c | 6 ++++-- include/uapi/linux/v4l2-controls.h | 4 +++- 3 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/control.rst b/Documentation/userspace-api/media/v4l/control.rst index f8d0b923da20..3eec65174260 100644 --- a/Documentation/userspace-api/media/v4l/control.rst +++ b/Documentation/userspace-api/media/v4l/control.rst @@ -242,8 +242,17 @@ Control IDs * - ``V4L2_COLORFX_SET_CBCR`` - The Cb and Cr chroma components are replaced by fixed coefficients determined by ``V4L2_CID_COLORFX_CBCR`` control. + * - ``V4L2_COLORFX_SET_RGB`` + - The RGB components are replaced by the fixed RGB components determined + by ``V4L2_CID_COLORFX_RGB`` control. +``V4L2_CID_COLORFX_RGB`` ``(integer)`` + Determines the Red, Green, and Blue coefficients for + ``V4L2_COLORFX_SET_RGB`` color effect. + Bits [7:0] of the supplied 32 bit value are interpreted as Blue component, + bits [15:8] as Green component, bits [23:16] as Red component, and + bits [31:24] must be zero. ``V4L2_CID_COLORFX_CBCR`` ``(integer)`` Determines the Cb and Cr coefficients for ``V4L2_COLORFX_SET_CBCR`` diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 0cb6c0f18b39..431f7ec17557 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -785,6 +785,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MIN_BUFFERS_FOR_OUTPUT: return "Min Number of Output Buffers"; case V4L2_CID_ALPHA_COMPONENT: return "Alpha Component"; case V4L2_CID_COLORFX_CBCR: return "Color Effects, CbCr"; + case V4L2_CID_COLORFX_RGB: return "Color Effects, RGB"; /* * Codec controls @@ -1394,11 +1395,12 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, *min = *max = *step = *def = 0; break; case V4L2_CID_BG_COLOR: + case V4L2_CID_COLORFX_RGB: *type = V4L2_CTRL_TYPE_INTEGER; *step = 1; *min = 0; - /* Max is calculated as RGB888 that is 2^24 */ - *max = 0xFFFFFF; + /* Max is calculated as RGB888 that is 2^24 - 1 */ + *max = 0xffffff; break; case V4L2_CID_COLORFX_CBCR: *type = V4L2_CTRL_TYPE_INTEGER; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 5fea5feb0412..c9eea93a43a9 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -128,6 +128,7 @@ enum v4l2_colorfx { V4L2_COLORFX_SOLARIZATION = 13, V4L2_COLORFX_ANTIQUE = 14, V4L2_COLORFX_SET_CBCR = 15, + V4L2_COLORFX_SET_RGB = 16, }; #define V4L2_CID_AUTOBRIGHTNESS (V4L2_CID_BASE+32) #define V4L2_CID_BAND_STOP_FILTER (V4L2_CID_BASE+33) @@ -145,9 +146,10 @@ enum v4l2_colorfx { #define V4L2_CID_ALPHA_COMPONENT (V4L2_CID_BASE+41) #define V4L2_CID_COLORFX_CBCR (V4L2_CID_BASE+42) +#define V4L2_CID_COLORFX_RGB (V4L2_CID_BASE+43) /* last CID + 1 */ -#define V4L2_CID_LASTP1 (V4L2_CID_BASE+43) +#define V4L2_CID_LASTP1 (V4L2_CID_BASE+44) /* USER-class private control IDs */ -- cgit v1.2.3 From 13cae4a104d2b7205696229ba85d34cc035f8c84 Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Mon, 15 Nov 2021 10:49:21 +0800 Subject: i2c: core: Allow 255 byte transfers for SMBus 3.x SMBus 3.0 increased the maximum block transfer size from 32 bytes to 255 bytes. We increase the size of struct i2c_smbus_data's block[] member. i2c_smbus_xfer() and i2c_smbus_xfer_emulated() now support 255 byte block operations, other block functions remain limited to 32 bytes for compatibility with existing callers. We allow adapters to indicate support for the larger size with I2C_FUNC_SMBUS_V3_BLOCK. Most emulated drivers should be able to use 255 byte blocks by replacing I2C_SMBUS_BLOCK_MAX with I2C_SMBUS_V3_BLOCK_MAX though some will have hardware limitations that need testing. Signed-off-by: Matt Johnston Signed-off-by: David S. Miller --- drivers/i2c/i2c-core-smbus.c | 20 +++++++++++++------- include/linux/i2c.h | 13 +++++++++++++ include/uapi/linux/i2c.h | 5 ++++- 3 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index e5b2d1465e7e..743415584aba 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -303,7 +303,8 @@ static void i2c_smbus_try_get_dmabuf(struct i2c_msg *msg, u8 init_val) bool is_read = msg->flags & I2C_M_RD; unsigned char *dma_buf; - dma_buf = kzalloc(I2C_SMBUS_BLOCK_MAX + (is_read ? 2 : 3), GFP_KERNEL); + dma_buf = kzalloc(I2C_SMBUS_V3_BLOCK_MAX + (is_read ? 2 : 3), + GFP_KERNEL); if (!dma_buf) return; @@ -329,9 +330,10 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, * initialize most things with sane defaults, to keep the code below * somewhat simpler. */ - unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3]; - unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2]; + unsigned char msgbuf0[I2C_SMBUS_V3_BLOCK_MAX+3]; + unsigned char msgbuf1[I2C_SMBUS_V3_BLOCK_MAX+2]; int nmsgs = read_write == I2C_SMBUS_READ ? 2 : 1; + u16 block_max; u8 partial_pec = 0; int status; struct i2c_msg msg[2] = { @@ -350,6 +352,10 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, bool wants_pec = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA); + /* Drivers must opt in to 255 byte max block size */ + block_max = i2c_check_functionality(adapter, I2C_FUNC_SMBUS_V3_BLOCK) + ? I2C_SMBUS_V3_BLOCK_MAX : I2C_SMBUS_BLOCK_MAX; + msgbuf0[0] = command; switch (size) { case I2C_SMBUS_QUICK: @@ -399,7 +405,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); } else { msg[0].len = data->block[0] + 2; - if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) { + if (msg[0].len > block_max + 2) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -413,7 +419,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, case I2C_SMBUS_BLOCK_PROC_CALL: nmsgs = 2; /* Another special case */ read_write = I2C_SMBUS_READ; - if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { + if (data->block[0] > block_max) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -430,7 +436,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); break; case I2C_SMBUS_I2C_BLOCK_DATA: - if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { + if (data->block[0] > block_max) { dev_err(&adapter->dev, "Invalid block %s size %d\n", read_write == I2C_SMBUS_READ ? "read" : "write", data->block[0]); @@ -498,7 +504,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_BLOCK_PROC_CALL: - if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) { + if (msg[1].buf[0] > block_max) { dev_err(&adapter->dev, "Invalid block size returned: %d\n", msg[1].buf[0]); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 16119ac1aa97..353d6b4e7a53 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -52,6 +52,19 @@ typedef int (*i2c_slave_cb_t)(struct i2c_client *client, struct module; struct property_entry; +/* SMBus 3.0 extends the maximum block read/write size to 255 (from 32). + * The larger size is only supported by some drivers, indicated by + * the I2C_FUNC_SMBUS_V3_BLOCK functionality bit. + */ +#define I2C_SMBUS_V3_BLOCK_MAX 255 /* As specified in SMBus 3.0 standard */ + +/* Note compatibility definition in uapi header with 32 byte block */ +union i2c_smbus_data { + __u8 byte; + __u16 word; + __u8 block[I2C_SMBUS_V3_BLOCK_MAX + 1]; /* block[0] is used for length */ +}; + #if IS_ENABLED(CONFIG_I2C) /* Return the Frequency mode string based on the bus frequency */ const char *i2c_freq_mode_string(u32 bus_freq_hz); diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 92326ebde350..7b7d90b50cf0 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -108,6 +108,7 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ #define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ +#define I2C_FUNC_SMBUS_V3_BLOCK 0x20000000 /* Device supports 255 byte block */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) @@ -137,13 +138,15 @@ struct i2c_msg { /* * Data for SMBus Messages */ -#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus standard */ +#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus 2.0 standard */ +#ifndef __KERNEL__ union i2c_smbus_data { __u8 byte; __u16 word; __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ /* and one more for user-space compatibility */ }; +#endif /* i2c_smbus_xfer read or write markers */ #define I2C_SMBUS_READ 1 -- cgit v1.2.3 From 84a107e68b34217eff536e81a6a6f419ee0d0f7e Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Mon, 15 Nov 2021 10:49:22 +0800 Subject: i2c: dev: Handle 255 byte blocks for i2c ioctl I2C_SMBUS is limited to 32 bytes due to compatibility with the 32 byte i2c_smbus_data.block I2C_RDWR allows larger transfers if sufficient sized buffers are passed. Signed-off-by: Matt Johnston Signed-off-by: David S. Miller --- drivers/i2c/i2c-dev.c | 93 +++++++++++++++++++++++++++++++++++++------- include/uapi/linux/i2c-dev.h | 2 + include/uapi/linux/i2c.h | 2 + 3 files changed, 83 insertions(+), 14 deletions(-) (limited to 'include/uapi') diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index bce0e8bb7852..5ee9118c0407 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -46,6 +46,24 @@ struct i2c_dev { struct cdev cdev; }; +/* The userspace union i2c_smbus_data for I2C_SMBUS ioctl is limited + * to 32 bytes (I2C_SMBUS_BLOCK_MAX) for compatibility. + */ +union compat_i2c_smbus_data { + __u8 byte; + __u16 word; + __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ + /* and one more for user-space compatibility */ +}; + +/* Must match i2c-dev.h definition with compat .data member */ +struct i2c_smbus_ioctl_data { + __u8 read_write; + __u8 command; + __u32 size; + union compat_i2c_smbus_data __user *data; +}; + #define I2C_MINORS (MINORMASK + 1) static LIST_HEAD(i2c_dev_list); static DEFINE_SPINLOCK(i2c_dev_list_lock); @@ -235,14 +253,17 @@ static int i2cdev_check_addr(struct i2c_adapter *adapter, unsigned int addr) static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, unsigned nmsgs, struct i2c_msg *msgs) { - u8 __user **data_ptrs; + u8 __user **data_ptrs = NULL; + u16 *orig_lens = NULL; int i, res; + res = -ENOMEM; data_ptrs = kmalloc_array(nmsgs, sizeof(u8 __user *), GFP_KERNEL); - if (data_ptrs == NULL) { - kfree(msgs); - return -ENOMEM; - } + if (data_ptrs == NULL) + goto out; + orig_lens = kmalloc_array(nmsgs, sizeof(u16), GFP_KERNEL); + if (orig_lens == NULL) + goto out; res = 0; for (i = 0; i < nmsgs; i++) { @@ -253,12 +274,30 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, } data_ptrs[i] = (u8 __user *)msgs[i].buf; - msgs[i].buf = memdup_user(data_ptrs[i], msgs[i].len); + msgs[i].buf = NULL; + if (msgs[i].len < 1) { + /* Sanity check */ + res = -EINVAL; + break; + + } + /* Allocate a larger buffer to accommodate possible 255 byte + * blocks. Read results will be dropped later + * if they are too large for the original length. + */ + orig_lens[i] = msgs[i].len; + msgs[i].buf = kmalloc(msgs[i].len + I2C_SMBUS_V3_BLOCK_MAX, + GFP_USER | __GFP_NOWARN); if (IS_ERR(msgs[i].buf)) { res = PTR_ERR(msgs[i].buf); break; } - /* memdup_user allocates with GFP_KERNEL, so DMA is ok */ + if (copy_from_user(msgs[i].buf, data_ptrs[i], msgs[i].len)) { + kfree(msgs[i].buf); + res = -EFAULT; + break; + } + /* Buffer from kmalloc, so DMA is ok */ msgs[i].flags |= I2C_M_DMA_SAFE; /* @@ -274,7 +313,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, */ if (msgs[i].flags & I2C_M_RECV_LEN) { if (!(msgs[i].flags & I2C_M_RD) || - msgs[i].len < 1 || msgs[i].buf[0] < 1 || + msgs[i].buf[0] < 1 || msgs[i].len < msgs[i].buf[0] + I2C_SMBUS_BLOCK_MAX) { i++; @@ -297,12 +336,16 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, res = i2c_transfer(client->adapter, msgs, nmsgs); while (i-- > 0) { if (res >= 0 && (msgs[i].flags & I2C_M_RD)) { - if (copy_to_user(data_ptrs[i], msgs[i].buf, - msgs[i].len)) + if (orig_lens[i] < msgs[i].len) + res = -EINVAL; + else if (copy_to_user(data_ptrs[i], msgs[i].buf, + msgs[i].len)) res = -EFAULT; } kfree(msgs[i].buf); } +out: + kfree(orig_lens); kfree(data_ptrs); kfree(msgs); return res; @@ -310,7 +353,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, u8 read_write, u8 command, u32 size, - union i2c_smbus_data __user *data) + union compat_i2c_smbus_data __user *data) { union i2c_smbus_data temp = {}; int datasize, res; @@ -371,6 +414,16 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, if (copy_from_user(&temp, data, datasize)) return -EFAULT; } + if ((size == I2C_SMBUS_BLOCK_PROC_CALL || + size == I2C_SMBUS_I2C_BLOCK_DATA || + size == I2C_SMBUS_BLOCK_DATA) && + read_write == I2C_SMBUS_WRITE && + temp.block[0] > I2C_SMBUS_BLOCK_MAX) { + /* Don't accept writes larger than the buffer size */ + dev_dbg(&client->adapter->dev, "block write is too large"); + return -EINVAL; + + } if (size == I2C_SMBUS_I2C_BLOCK_BROKEN) { /* Convert old I2C block commands to the new convention. This preserves binary compatibility. */ @@ -380,9 +433,21 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, } res = i2c_smbus_xfer(client->adapter, client->addr, client->flags, read_write, command, size, &temp); - if (!res && ((size == I2C_SMBUS_PROC_CALL) || - (size == I2C_SMBUS_BLOCK_PROC_CALL) || - (read_write == I2C_SMBUS_READ))) { + if (res) + return res; + if ((size == I2C_SMBUS_BLOCK_PROC_CALL || + size == I2C_SMBUS_I2C_BLOCK_DATA || + size == I2C_SMBUS_BLOCK_DATA) && + read_write == I2C_SMBUS_READ && + temp.block[0] > I2C_SMBUS_BLOCK_MAX) { + /* Don't accept reads larger than the buffer size */ + dev_dbg(&client->adapter->dev, "block read is too large"); + return -EINVAL; + + } + if ((size == I2C_SMBUS_PROC_CALL) || + (size == I2C_SMBUS_BLOCK_PROC_CALL) || + (read_write == I2C_SMBUS_READ)) { if (copy_to_user(data, &temp, datasize)) return -EFAULT; } diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 1c4cec4ddd84..46ce31d42f7d 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -39,12 +39,14 @@ /* This is the structure as used in the I2C_SMBUS ioctl call */ +#ifndef __KERNEL__ struct i2c_smbus_ioctl_data { __u8 read_write; __u8 command; __u32 size; union i2c_smbus_data __user *data; }; +#endif /* This is the structure as used in the I2C_RDWR ioctl call */ struct i2c_rdwr_ioctl_data { diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 7b7d90b50cf0..c3534ab1ae53 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -109,6 +109,8 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ #define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ #define I2C_FUNC_SMBUS_V3_BLOCK 0x20000000 /* Device supports 255 byte block */ + /* Note that I2C_SMBUS ioctl only */ + /* supports a 32 byte block */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) -- cgit v1.2.3 From 2f6a470d6545841cf1891b87e360d3998ef024c8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 15 Nov 2021 07:49:46 -0800 Subject: Revert "Merge branch 'mctp-i2c-driver'" This reverts commit 71812af7234f30362b43ccff33f93890ae4c0655, reversing changes made to cc0be1ad686fb29a4d127948486f40b17fb34b50. Wolfram Sang says: Please revert. Besides the driver in net, it modifies the I2C core code. This has not been acked by the I2C maintainer (in this case me). So, please don't pull this in via the net tree. The question raised here (extending SMBus calls to 255 byte) is complicated because we need ABI backwards compatibility. Link: https://lore.kernel.org/all/YZJ9H4eM%2FM7OXVN0@shikoro/ Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/i2c/i2c.txt | 4 - .../bindings/net/mctp-i2c-controller.yaml | 92 -- drivers/i2c/busses/i2c-aspeed.c | 5 +- drivers/i2c/busses/i2c-npcm7xx.c | 3 +- drivers/i2c/i2c-core-smbus.c | 20 +- drivers/i2c/i2c-dev.c | 93 +- drivers/net/mctp/Kconfig | 12 - drivers/net/mctp/Makefile | 1 - drivers/net/mctp/mctp-i2c.c | 982 --------------------- include/linux/i2c.h | 13 - include/uapi/linux/i2c-dev.h | 2 - include/uapi/linux/i2c.h | 7 +- 12 files changed, 25 insertions(+), 1209 deletions(-) delete mode 100644 Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml delete mode 100644 drivers/net/mctp/mctp-i2c.c (limited to 'include/uapi') diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt index fc3dd7ec0445..b864916e087f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c.txt @@ -95,10 +95,6 @@ wants to support one of the below features, it should adapt these bindings. - smbus-alert states that the optional SMBus-Alert feature apply to this bus. -- mctp-controller - indicates that the system is accessible via this bus as an endpoint for - MCTP over I2C transport. - Required properties (per child device) -------------------------------------- diff --git a/Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml b/Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml deleted file mode 100644 index afd11c9422fa..000000000000 --- a/Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml +++ /dev/null @@ -1,92 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/net/mctp-i2c-controller.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: MCTP I2C transport binding - -maintainers: - - Matt Johnston - -description: | - An mctp-i2c-controller defines a local MCTP endpoint on an I2C controller. - MCTP I2C is specified by DMTF DSP0237. - - An mctp-i2c-controller must be attached to an I2C adapter which supports - slave functionality. I2C busses (either directly or as subordinate mux - busses) are attached to the mctp-i2c-controller with a 'mctp-controller' - property on each used bus. Each mctp-controller I2C bus will be presented - to the host system as a separate MCTP I2C instance. - -properties: - compatible: - const: mctp-i2c-controller - - reg: - minimum: 0x40000000 - maximum: 0x4000007f - description: | - 7 bit I2C address of the local endpoint. - I2C_OWN_SLAVE_ADDRESS (1<<30) flag must be set. - -additionalProperties: false - -required: - - compatible - - reg - -examples: - - | - // Basic case of a single I2C bus - #include - - i2c { - #address-cells = <1>; - #size-cells = <0>; - mctp-controller; - - mctp@30 { - compatible = "mctp-i2c-controller"; - reg = <(0x30 | I2C_OWN_SLAVE_ADDRESS)>; - }; - }; - - - | - // Mux topology with multiple MCTP-handling busses under - // a single mctp-i2c-controller. - // i2c1 and i2c6 can have MCTP devices, i2c5 does not. - #include - - i2c1: i2c { - #address-cells = <1>; - #size-cells = <0>; - mctp-controller; - - mctp@50 { - compatible = "mctp-i2c-controller"; - reg = <(0x50 | I2C_OWN_SLAVE_ADDRESS)>; - }; - }; - - i2c-mux { - #address-cells = <1>; - #size-cells = <0>; - i2c-parent = <&i2c1>; - - i2c5: i2c@0 { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - eeprom@33 { - reg = <0x33>; - }; - }; - - i2c6: i2c@1 { - #address-cells = <1>; - #size-cells = <0>; - reg = <1>; - mctp-controller; - }; - }; diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 7395f3702fae..67e8b97c0c95 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -533,7 +533,7 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status) msg->buf[bus->buf_index++] = recv_byte; if (msg->flags & I2C_M_RECV_LEN) { - if (unlikely(recv_byte > I2C_SMBUS_V3_BLOCK_MAX)) { + if (unlikely(recv_byte > I2C_SMBUS_BLOCK_MAX)) { bus->cmd_err = -EPROTO; aspeed_i2c_do_stop(bus); goto out_no_complete; @@ -718,8 +718,7 @@ static int aspeed_i2c_master_xfer(struct i2c_adapter *adap, static u32 aspeed_i2c_functionality(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | - I2C_FUNC_SMBUS_BLOCK_DATA | I2C_FUNC_SMBUS_V3_BLOCK; + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SMBUS_BLOCK_DATA; } #if IS_ENABLED(CONFIG_I2C_SLAVE) diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 6d60f65add85..2ad166355ec9 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -1399,7 +1399,7 @@ static void npcm_i2c_irq_master_handler_read(struct npcm_i2c *bus) if (bus->read_block_use) { /* first byte in block protocol is the size: */ data = npcm_i2c_rd_byte(bus); - data = clamp_val(data, 1, I2C_SMBUS_V3_BLOCK_MAX); + data = clamp_val(data, 1, I2C_SMBUS_BLOCK_MAX); bus->rd_size = data + block_extra_bytes_size; bus->rd_buf[bus->rd_ind++] = data; @@ -2187,7 +2187,6 @@ static u32 npcm_i2c_functionality(struct i2c_adapter *adap) I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SMBUS_BLOCK_DATA | I2C_FUNC_SMBUS_PEC | - I2C_FUNC_SMBUS_V3_BLOCK | I2C_FUNC_SLAVE; } diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index 743415584aba..e5b2d1465e7e 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -303,8 +303,7 @@ static void i2c_smbus_try_get_dmabuf(struct i2c_msg *msg, u8 init_val) bool is_read = msg->flags & I2C_M_RD; unsigned char *dma_buf; - dma_buf = kzalloc(I2C_SMBUS_V3_BLOCK_MAX + (is_read ? 2 : 3), - GFP_KERNEL); + dma_buf = kzalloc(I2C_SMBUS_BLOCK_MAX + (is_read ? 2 : 3), GFP_KERNEL); if (!dma_buf) return; @@ -330,10 +329,9 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, * initialize most things with sane defaults, to keep the code below * somewhat simpler. */ - unsigned char msgbuf0[I2C_SMBUS_V3_BLOCK_MAX+3]; - unsigned char msgbuf1[I2C_SMBUS_V3_BLOCK_MAX+2]; + unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3]; + unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2]; int nmsgs = read_write == I2C_SMBUS_READ ? 2 : 1; - u16 block_max; u8 partial_pec = 0; int status; struct i2c_msg msg[2] = { @@ -352,10 +350,6 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, bool wants_pec = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA); - /* Drivers must opt in to 255 byte max block size */ - block_max = i2c_check_functionality(adapter, I2C_FUNC_SMBUS_V3_BLOCK) - ? I2C_SMBUS_V3_BLOCK_MAX : I2C_SMBUS_BLOCK_MAX; - msgbuf0[0] = command; switch (size) { case I2C_SMBUS_QUICK: @@ -405,7 +399,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); } else { msg[0].len = data->block[0] + 2; - if (msg[0].len > block_max + 2) { + if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -419,7 +413,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, case I2C_SMBUS_BLOCK_PROC_CALL: nmsgs = 2; /* Another special case */ read_write = I2C_SMBUS_READ; - if (data->block[0] > block_max) { + if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -436,7 +430,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); break; case I2C_SMBUS_I2C_BLOCK_DATA: - if (data->block[0] > block_max) { + if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block %s size %d\n", read_write == I2C_SMBUS_READ ? "read" : "write", data->block[0]); @@ -504,7 +498,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_BLOCK_PROC_CALL: - if (msg[1].buf[0] > block_max) { + if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block size returned: %d\n", msg[1].buf[0]); diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 5ee9118c0407..bce0e8bb7852 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -46,24 +46,6 @@ struct i2c_dev { struct cdev cdev; }; -/* The userspace union i2c_smbus_data for I2C_SMBUS ioctl is limited - * to 32 bytes (I2C_SMBUS_BLOCK_MAX) for compatibility. - */ -union compat_i2c_smbus_data { - __u8 byte; - __u16 word; - __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ - /* and one more for user-space compatibility */ -}; - -/* Must match i2c-dev.h definition with compat .data member */ -struct i2c_smbus_ioctl_data { - __u8 read_write; - __u8 command; - __u32 size; - union compat_i2c_smbus_data __user *data; -}; - #define I2C_MINORS (MINORMASK + 1) static LIST_HEAD(i2c_dev_list); static DEFINE_SPINLOCK(i2c_dev_list_lock); @@ -253,17 +235,14 @@ static int i2cdev_check_addr(struct i2c_adapter *adapter, unsigned int addr) static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, unsigned nmsgs, struct i2c_msg *msgs) { - u8 __user **data_ptrs = NULL; - u16 *orig_lens = NULL; + u8 __user **data_ptrs; int i, res; - res = -ENOMEM; data_ptrs = kmalloc_array(nmsgs, sizeof(u8 __user *), GFP_KERNEL); - if (data_ptrs == NULL) - goto out; - orig_lens = kmalloc_array(nmsgs, sizeof(u16), GFP_KERNEL); - if (orig_lens == NULL) - goto out; + if (data_ptrs == NULL) { + kfree(msgs); + return -ENOMEM; + } res = 0; for (i = 0; i < nmsgs; i++) { @@ -274,30 +253,12 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, } data_ptrs[i] = (u8 __user *)msgs[i].buf; - msgs[i].buf = NULL; - if (msgs[i].len < 1) { - /* Sanity check */ - res = -EINVAL; - break; - - } - /* Allocate a larger buffer to accommodate possible 255 byte - * blocks. Read results will be dropped later - * if they are too large for the original length. - */ - orig_lens[i] = msgs[i].len; - msgs[i].buf = kmalloc(msgs[i].len + I2C_SMBUS_V3_BLOCK_MAX, - GFP_USER | __GFP_NOWARN); + msgs[i].buf = memdup_user(data_ptrs[i], msgs[i].len); if (IS_ERR(msgs[i].buf)) { res = PTR_ERR(msgs[i].buf); break; } - if (copy_from_user(msgs[i].buf, data_ptrs[i], msgs[i].len)) { - kfree(msgs[i].buf); - res = -EFAULT; - break; - } - /* Buffer from kmalloc, so DMA is ok */ + /* memdup_user allocates with GFP_KERNEL, so DMA is ok */ msgs[i].flags |= I2C_M_DMA_SAFE; /* @@ -313,7 +274,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, */ if (msgs[i].flags & I2C_M_RECV_LEN) { if (!(msgs[i].flags & I2C_M_RD) || - msgs[i].buf[0] < 1 || + msgs[i].len < 1 || msgs[i].buf[0] < 1 || msgs[i].len < msgs[i].buf[0] + I2C_SMBUS_BLOCK_MAX) { i++; @@ -336,16 +297,12 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, res = i2c_transfer(client->adapter, msgs, nmsgs); while (i-- > 0) { if (res >= 0 && (msgs[i].flags & I2C_M_RD)) { - if (orig_lens[i] < msgs[i].len) - res = -EINVAL; - else if (copy_to_user(data_ptrs[i], msgs[i].buf, - msgs[i].len)) + if (copy_to_user(data_ptrs[i], msgs[i].buf, + msgs[i].len)) res = -EFAULT; } kfree(msgs[i].buf); } -out: - kfree(orig_lens); kfree(data_ptrs); kfree(msgs); return res; @@ -353,7 +310,7 @@ out: static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, u8 read_write, u8 command, u32 size, - union compat_i2c_smbus_data __user *data) + union i2c_smbus_data __user *data) { union i2c_smbus_data temp = {}; int datasize, res; @@ -414,16 +371,6 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, if (copy_from_user(&temp, data, datasize)) return -EFAULT; } - if ((size == I2C_SMBUS_BLOCK_PROC_CALL || - size == I2C_SMBUS_I2C_BLOCK_DATA || - size == I2C_SMBUS_BLOCK_DATA) && - read_write == I2C_SMBUS_WRITE && - temp.block[0] > I2C_SMBUS_BLOCK_MAX) { - /* Don't accept writes larger than the buffer size */ - dev_dbg(&client->adapter->dev, "block write is too large"); - return -EINVAL; - - } if (size == I2C_SMBUS_I2C_BLOCK_BROKEN) { /* Convert old I2C block commands to the new convention. This preserves binary compatibility. */ @@ -433,21 +380,9 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, } res = i2c_smbus_xfer(client->adapter, client->addr, client->flags, read_write, command, size, &temp); - if (res) - return res; - if ((size == I2C_SMBUS_BLOCK_PROC_CALL || - size == I2C_SMBUS_I2C_BLOCK_DATA || - size == I2C_SMBUS_BLOCK_DATA) && - read_write == I2C_SMBUS_READ && - temp.block[0] > I2C_SMBUS_BLOCK_MAX) { - /* Don't accept reads larger than the buffer size */ - dev_dbg(&client->adapter->dev, "block read is too large"); - return -EINVAL; - - } - if ((size == I2C_SMBUS_PROC_CALL) || - (size == I2C_SMBUS_BLOCK_PROC_CALL) || - (read_write == I2C_SMBUS_READ)) { + if (!res && ((size == I2C_SMBUS_PROC_CALL) || + (size == I2C_SMBUS_BLOCK_PROC_CALL) || + (read_write == I2C_SMBUS_READ))) { if (copy_to_user(data, &temp, datasize)) return -EFAULT; } diff --git a/drivers/net/mctp/Kconfig b/drivers/net/mctp/Kconfig index b758b29c2ddf..d8f966cedc89 100644 --- a/drivers/net/mctp/Kconfig +++ b/drivers/net/mctp/Kconfig @@ -3,18 +3,6 @@ if MCTP menu "MCTP Device Drivers" -config MCTP_TRANSPORT_I2C - tristate "MCTP SMBus/I2C transport" - # i2c-mux is optional, but we must build as a module if i2c-mux is a module - depends on I2C_MUX || !I2C_MUX - depends on I2C - depends on I2C_SLAVE - select MCTP_FLOWS - help - Provides a driver to access MCTP devices over SMBus/I2C transport, - from DMTF specification DSP0237. A MCTP protocol network device is - created for each I2C bus that has been assigned a mctp-i2c device. - endmenu endif diff --git a/drivers/net/mctp/Makefile b/drivers/net/mctp/Makefile index 73dc411986a6..e69de29bb2d1 100644 --- a/drivers/net/mctp/Makefile +++ b/drivers/net/mctp/Makefile @@ -1 +0,0 @@ -obj-$(CONFIG_MCTP_TRANSPORT_I2C) += mctp-i2c.o diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c deleted file mode 100644 index ed213b4765a1..000000000000 --- a/drivers/net/mctp/mctp-i2c.c +++ /dev/null @@ -1,982 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Management Controller Transport Protocol (MCTP) - * - * Copyright (c) 2021 Code Construct - * Copyright (c) 2021 Google - */ - -#include -#include -#include -#include -#include -#include -#include - -/* SMBus 3.0 allows 255 data bytes (plus PEC), but the - * first byte is taken for source slave address. - */ -#define MCTP_I2C_MAXBLOCK 255 -#define MCTP_I2C_MAXMTU (MCTP_I2C_MAXBLOCK - 1) -#define MCTP_I2C_MINMTU (64 + 4) -/* Allow space for address, command, byte_count, databytes, PEC */ -#define MCTP_I2C_RXBUFSZ (3 + MCTP_I2C_MAXBLOCK + 1) -#define MCTP_I2C_MINLEN 8 -#define MCTP_I2C_COMMANDCODE 0x0f -#define MCTP_I2C_TX_WORK_LEN 100 -// sufficient for 64kB at min mtu -#define MCTP_I2C_TX_QUEUE_LEN 1100 - -#define MCTP_I2C_OF_PROP "mctp-controller" - -enum { - MCTP_I2C_FLOW_STATE_NEW = 0, - MCTP_I2C_FLOW_STATE_ACTIVE, -}; - -static struct { - /* lock protects clients and also prevents adding/removing adapters - * during mctp_i2c_client probe/remove. - */ - struct mutex lock; - // list of struct mctp_i2c_client - struct list_head clients; -} mi_driver_state; - -struct mctp_i2c_client; - -// The netdev structure. One of these per I2C adapter. -struct mctp_i2c_dev { - struct net_device *ndev; - struct i2c_adapter *adapter; - struct mctp_i2c_client *client; - struct list_head list; // for mctp_i2c_client.devs - - size_t pos; - u8 buffer[MCTP_I2C_RXBUFSZ]; - - struct task_struct *tx_thread; - wait_queue_head_t tx_wq; - struct sk_buff_head tx_queue; - - // a fake entry in our tx queue to perform an unlock operation - struct sk_buff unlock_marker; - - spinlock_t flow_lock; // protects i2c_lock_count and release_count - int i2c_lock_count; - int release_count; -}; - -/* The i2c client structure. One per hardware i2c bus at the top of the - * mux tree, shared by multiple netdevs - */ -struct mctp_i2c_client { - struct i2c_client *client; - u8 lladdr; - - struct mctp_i2c_dev *sel; - struct list_head devs; - spinlock_t curr_lock; // protects sel - - struct list_head list; // for mi_driver_state.clients -}; - -// Header on the wire -struct mctp_i2c_hdr { - u8 dest_slave; - u8 command; - u8 byte_count; - u8 source_slave; -}; - -static int mctp_i2c_recv(struct mctp_i2c_dev *midev); -static int mctp_i2c_slave_cb(struct i2c_client *client, - enum i2c_slave_event event, u8 *val); - -static struct i2c_adapter *mux_root_adapter(struct i2c_adapter *adap) -{ -#if IS_ENABLED(CONFIG_I2C_MUX) - return i2c_root_adapter(&adap->dev); -#else - /* In non-mux config all i2c adapters are root adapters */ - return adap; -#endif -} - -static ssize_t mctp_current_mux_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct mctp_i2c_client *mcli = i2c_get_clientdata(to_i2c_client(dev)); - struct net_device *ndev = NULL; - unsigned long flags; - ssize_t l; - - spin_lock_irqsave(&mcli->curr_lock, flags); - if (mcli->sel) { - ndev = mcli->sel->ndev; - dev_hold(ndev); - } - spin_unlock_irqrestore(&mcli->curr_lock, flags); - l = scnprintf(buf, PAGE_SIZE, "%s\n", ndev ? ndev->name : "(none)"); - if (ndev) - dev_put(ndev); - return l; -} -static DEVICE_ATTR_RO(mctp_current_mux); - -/* Creates a new i2c slave device attached to the root adapter. - * Sets up the slave callback. - * Must be called with a client on a root adapter. - */ -static struct mctp_i2c_client *mctp_i2c_new_client(struct i2c_client *client) -{ - struct mctp_i2c_client *mcli = NULL; - struct i2c_adapter *root = NULL; - int rc; - - if (client->flags & I2C_CLIENT_TEN) { - dev_err(&client->dev, "%s failed, MCTP requires a 7-bit I2C address, addr=0x%x", - __func__, client->addr); - rc = -EINVAL; - goto err; - } - - root = mux_root_adapter(client->adapter); - if (!root) { - dev_err(&client->dev, "%s failed to find root adapter\n", __func__); - rc = -ENOENT; - goto err; - } - if (root != client->adapter) { - dev_err(&client->dev, - "A mctp-i2c-controller client cannot be placed on an I2C mux adapter.\n" - " It should be placed on the mux tree root adapter\n" - " then set mctp-controller property on adapters to attach\n"); - rc = -EINVAL; - goto err; - } - - mcli = kzalloc(sizeof(*mcli), GFP_KERNEL); - if (!mcli) { - rc = -ENOMEM; - goto err; - } - spin_lock_init(&mcli->curr_lock); - INIT_LIST_HEAD(&mcli->devs); - INIT_LIST_HEAD(&mcli->list); - mcli->lladdr = client->addr & 0xff; - mcli->client = client; - i2c_set_clientdata(client, mcli); - - rc = i2c_slave_register(mcli->client, mctp_i2c_slave_cb); - if (rc) { - dev_err(&client->dev, "%s i2c register failed %d\n", __func__, rc); - mcli->client = NULL; - i2c_set_clientdata(client, NULL); - goto err; - } - - rc = device_create_file(&client->dev, &dev_attr_mctp_current_mux); - if (rc) { - dev_err(&client->dev, "%s adding sysfs \"%s\" failed %d\n", __func__, - dev_attr_mctp_current_mux.attr.name, rc); - // continue anyway - } - - return mcli; -err: - if (mcli) { - if (mcli->client) { - device_remove_file(&mcli->client->dev, &dev_attr_mctp_current_mux); - i2c_unregister_device(mcli->client); - } - kfree(mcli); - } - return ERR_PTR(rc); -} - -static void mctp_i2c_free_client(struct mctp_i2c_client *mcli) -{ - int rc; - - WARN_ON(!mutex_is_locked(&mi_driver_state.lock)); - WARN_ON(!list_empty(&mcli->devs)); - WARN_ON(mcli->sel); // sanity check, no locking - - device_remove_file(&mcli->client->dev, &dev_attr_mctp_current_mux); - rc = i2c_slave_unregister(mcli->client); - // leak if it fails, we can't propagate errors upwards - if (rc) - dev_err(&mcli->client->dev, "%s i2c unregister failed %d\n", __func__, rc); - else - kfree(mcli); -} - -/* Switch the mctp i2c device to receive responses. - * Call with curr_lock held - */ -static void __mctp_i2c_device_select(struct mctp_i2c_client *mcli, - struct mctp_i2c_dev *midev) -{ - assert_spin_locked(&mcli->curr_lock); - if (midev) - dev_hold(midev->ndev); - if (mcli->sel) - dev_put(mcli->sel->ndev); - mcli->sel = midev; -} - -// Switch the mctp i2c device to receive responses -static void mctp_i2c_device_select(struct mctp_i2c_client *mcli, - struct mctp_i2c_dev *midev) -{ - unsigned long flags; - - spin_lock_irqsave(&mcli->curr_lock, flags); - __mctp_i2c_device_select(mcli, midev); - spin_unlock_irqrestore(&mcli->curr_lock, flags); -} - -static int mctp_i2c_slave_cb(struct i2c_client *client, - enum i2c_slave_event event, u8 *val) -{ - struct mctp_i2c_client *mcli = i2c_get_clientdata(client); - struct mctp_i2c_dev *midev = NULL; - unsigned long flags; - int rc = 0; - - spin_lock_irqsave(&mcli->curr_lock, flags); - midev = mcli->sel; - if (midev) - dev_hold(midev->ndev); - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - if (!midev) - return 0; - - switch (event) { - case I2C_SLAVE_WRITE_RECEIVED: - if (midev->pos < MCTP_I2C_RXBUFSZ) { - midev->buffer[midev->pos] = *val; - midev->pos++; - } else { - midev->ndev->stats.rx_over_errors++; - } - - break; - case I2C_SLAVE_WRITE_REQUESTED: - /* dest_slave as first byte */ - midev->buffer[0] = mcli->lladdr << 1; - midev->pos = 1; - break; - case I2C_SLAVE_STOP: - rc = mctp_i2c_recv(midev); - break; - default: - break; - } - - dev_put(midev->ndev); - return rc; -} - -// Processes incoming data that has been accumulated by the slave cb -static int mctp_i2c_recv(struct mctp_i2c_dev *midev) -{ - struct net_device *ndev = midev->ndev; - struct mctp_i2c_hdr *hdr; - struct mctp_skb_cb *cb; - struct sk_buff *skb; - u8 pec, calc_pec; - size_t recvlen; - - /* + 1 for the PEC */ - if (midev->pos < MCTP_I2C_MINLEN + 1) { - ndev->stats.rx_length_errors++; - return -EINVAL; - } - recvlen = midev->pos - 1; - - hdr = (void *)midev->buffer; - if (hdr->command != MCTP_I2C_COMMANDCODE) { - ndev->stats.rx_dropped++; - return -EINVAL; - } - - pec = midev->buffer[midev->pos - 1]; - calc_pec = i2c_smbus_pec(0, midev->buffer, recvlen); - if (pec != calc_pec) { - ndev->stats.rx_crc_errors++; - return -EINVAL; - } - - skb = netdev_alloc_skb(ndev, recvlen); - if (!skb) { - ndev->stats.rx_dropped++; - return -ENOMEM; - } - - skb->protocol = htons(ETH_P_MCTP); - skb_put_data(skb, midev->buffer, recvlen); - skb_reset_mac_header(skb); - skb_pull(skb, sizeof(struct mctp_i2c_hdr)); - skb_reset_network_header(skb); - - cb = __mctp_cb(skb); - cb->halen = 1; - cb->haddr[0] = hdr->source_slave; - - if (netif_rx(skb) == NET_RX_SUCCESS) { - ndev->stats.rx_packets++; - ndev->stats.rx_bytes += skb->len; - } else { - ndev->stats.rx_dropped++; - } - return 0; -} - -enum mctp_i2c_flow_state { - MCTP_I2C_TX_FLOW_INVALID, - MCTP_I2C_TX_FLOW_NONE, - MCTP_I2C_TX_FLOW_NEW, - MCTP_I2C_TX_FLOW_EXISTING, -}; - -static enum mctp_i2c_flow_state -mctp_i2c_get_tx_flow_state(struct mctp_i2c_dev *midev, struct sk_buff *skb) -{ - enum mctp_i2c_flow_state state; - struct mctp_sk_key *key; - struct mctp_flow *flow; - unsigned long flags; - - flow = skb_ext_find(skb, SKB_EXT_MCTP); - if (!flow) - return MCTP_I2C_TX_FLOW_NONE; - - key = flow->key; - if (!key) - return MCTP_I2C_TX_FLOW_NONE; - - spin_lock_irqsave(&key->lock, flags); - /* if the key is present but invalid, we're unlikely to be able - * to handle the flow at all; just drop now - */ - if (!key->valid) { - state = MCTP_I2C_TX_FLOW_INVALID; - - } else if (key->dev_flow_state == MCTP_I2C_FLOW_STATE_NEW) { - key->dev_flow_state = MCTP_I2C_FLOW_STATE_ACTIVE; - state = MCTP_I2C_TX_FLOW_NEW; - } else { - state = MCTP_I2C_TX_FLOW_EXISTING; - } - - spin_unlock_irqrestore(&key->lock, flags); - - return state; -} - -/* We're not contending with ourselves here; we only need to exclude other - * i2c clients from using the bus. refcounts are simply to prevent - * recursive locking. - */ -static void mctp_i2c_lock_nest(struct mctp_i2c_dev *midev) -{ - unsigned long flags; - bool lock; - - spin_lock_irqsave(&midev->flow_lock, flags); - lock = midev->i2c_lock_count == 0; - midev->i2c_lock_count++; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - if (lock) - i2c_lock_bus(midev->adapter, I2C_LOCK_SEGMENT); -} - -static void mctp_i2c_unlock_nest(struct mctp_i2c_dev *midev) -{ - unsigned long flags; - bool unlock; - - spin_lock_irqsave(&midev->flow_lock, flags); - if (!WARN_ONCE(midev->i2c_lock_count == 0, "lock count underflow!")) - midev->i2c_lock_count--; - unlock = midev->i2c_lock_count == 0; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - if (unlock) - i2c_unlock_bus(midev->adapter, I2C_LOCK_SEGMENT); -} - -static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) -{ - struct net_device_stats *stats = &midev->ndev->stats; - enum mctp_i2c_flow_state fs; - union i2c_smbus_data *data; - struct mctp_i2c_hdr *hdr; - unsigned int len; - u16 daddr; - int rc; - - fs = mctp_i2c_get_tx_flow_state(midev, skb); - - len = skb->len; - hdr = (void *)skb_mac_header(skb); - data = (void *)&hdr->byte_count; - daddr = hdr->dest_slave >> 1; - - switch (fs) { - case MCTP_I2C_TX_FLOW_NONE: - /* no flow: full lock & unlock */ - mctp_i2c_lock_nest(midev); - mctp_i2c_device_select(midev->client, midev); - rc = __i2c_smbus_xfer(midev->adapter, daddr, I2C_CLIENT_PEC, - I2C_SMBUS_WRITE, hdr->command, - I2C_SMBUS_BLOCK_DATA, data); - mctp_i2c_unlock_nest(midev); - break; - - case MCTP_I2C_TX_FLOW_NEW: - /* new flow: lock, tx, but don't unlock; that will happen - * on flow release - */ - mctp_i2c_lock_nest(midev); - mctp_i2c_device_select(midev->client, midev); - fallthrough; - - case MCTP_I2C_TX_FLOW_EXISTING: - /* existing flow: we already have the lock; just tx */ - rc = __i2c_smbus_xfer(midev->adapter, daddr, I2C_CLIENT_PEC, - I2C_SMBUS_WRITE, hdr->command, - I2C_SMBUS_BLOCK_DATA, data); - break; - - case MCTP_I2C_TX_FLOW_INVALID: - return; - } - - if (rc) { - dev_warn_ratelimited(&midev->adapter->dev, - "%s i2c_smbus_xfer failed %d", __func__, rc); - stats->tx_errors++; - } else { - stats->tx_bytes += len; - stats->tx_packets++; - } -} - -static void mctp_i2c_flow_release(struct mctp_i2c_dev *midev) -{ - unsigned long flags; - bool unlock; - - spin_lock_irqsave(&midev->flow_lock, flags); - if (midev->release_count > midev->i2c_lock_count) { - WARN_ONCE(1, "release count overflow"); - midev->release_count = midev->i2c_lock_count; - } - - midev->i2c_lock_count -= midev->release_count; - unlock = midev->i2c_lock_count == 0 && midev->release_count > 0; - midev->release_count = 0; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - if (unlock) - i2c_unlock_bus(midev->adapter, I2C_LOCK_SEGMENT); -} - -static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *daddr, - const void *saddr, unsigned int len) -{ - struct mctp_i2c_hdr *hdr; - struct mctp_hdr *mhdr; - u8 lldst, llsrc; - - lldst = *((u8 *)daddr); - llsrc = *((u8 *)saddr); - - skb_push(skb, sizeof(struct mctp_i2c_hdr)); - skb_reset_mac_header(skb); - hdr = (void *)skb_mac_header(skb); - mhdr = mctp_hdr(skb); - hdr->dest_slave = (lldst << 1) & 0xff; - hdr->command = MCTP_I2C_COMMANDCODE; - hdr->byte_count = len + 1; - if (hdr->byte_count > MCTP_I2C_MAXBLOCK) - return -EMSGSIZE; - hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01; - mhdr->ver = 0x01; - - return 0; -} - -static int mctp_i2c_tx_thread(void *data) -{ - struct mctp_i2c_dev *midev = data; - struct sk_buff *skb; - unsigned long flags; - - for (;;) { - if (kthread_should_stop()) - break; - - spin_lock_irqsave(&midev->tx_queue.lock, flags); - skb = __skb_dequeue(&midev->tx_queue); - if (netif_queue_stopped(midev->ndev)) - netif_wake_queue(midev->ndev); - spin_unlock_irqrestore(&midev->tx_queue.lock, flags); - - if (skb == &midev->unlock_marker) { - mctp_i2c_flow_release(midev); - - } else if (skb) { - mctp_i2c_xmit(midev, skb); - kfree_skb(skb); - - } else { - wait_event(midev->tx_wq, - !skb_queue_empty(&midev->tx_queue) || - kthread_should_stop()); - } - } - - return 0; -} - -static netdev_tx_t mctp_i2c_start_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct mctp_i2c_dev *midev = netdev_priv(dev); - unsigned long flags; - - spin_lock_irqsave(&midev->tx_queue.lock, flags); - if (skb_queue_len(&midev->tx_queue) >= MCTP_I2C_TX_WORK_LEN) { - netif_stop_queue(dev); - spin_unlock_irqrestore(&midev->tx_queue.lock, flags); - netdev_err(dev, "BUG! Tx Ring full when queue awake!\n"); - return NETDEV_TX_BUSY; - } - - __skb_queue_tail(&midev->tx_queue, skb); - if (skb_queue_len(&midev->tx_queue) == MCTP_I2C_TX_WORK_LEN) - netif_stop_queue(dev); - spin_unlock_irqrestore(&midev->tx_queue.lock, flags); - - wake_up(&midev->tx_wq); - return NETDEV_TX_OK; -} - -static void mctp_i2c_release_flow(struct mctp_dev *mdev, - struct mctp_sk_key *key) - -{ - struct mctp_i2c_dev *midev = netdev_priv(mdev->dev); - unsigned long flags; - - spin_lock_irqsave(&midev->flow_lock, flags); - midev->release_count++; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - /* Ensure we have a release operation queued, through the fake - * marker skb - */ - spin_lock(&midev->tx_queue.lock); - if (!midev->unlock_marker.next) - __skb_queue_tail(&midev->tx_queue, &midev->unlock_marker); - spin_unlock(&midev->tx_queue.lock); - - wake_up(&midev->tx_wq); -} - -static const struct net_device_ops mctp_i2c_ops = { - .ndo_start_xmit = mctp_i2c_start_xmit, -}; - -static const struct header_ops mctp_i2c_headops = { - .create = mctp_i2c_header_create, -}; - -static const struct mctp_netdev_ops mctp_i2c_mctp_ops = { - .release_flow = mctp_i2c_release_flow, -}; - -static void mctp_i2c_net_setup(struct net_device *dev) -{ - dev->type = ARPHRD_MCTP; - - dev->mtu = MCTP_I2C_MAXMTU; - dev->min_mtu = MCTP_I2C_MINMTU; - dev->max_mtu = MCTP_I2C_MAXMTU; - dev->tx_queue_len = MCTP_I2C_TX_QUEUE_LEN; - - dev->hard_header_len = sizeof(struct mctp_i2c_hdr); - dev->addr_len = 1; - - dev->netdev_ops = &mctp_i2c_ops; - dev->header_ops = &mctp_i2c_headops; - dev->needs_free_netdev = true; -} - -static int mctp_i2c_add_netdev(struct mctp_i2c_client *mcli, - struct i2c_adapter *adap) -{ - unsigned long flags; - struct mctp_i2c_dev *midev = NULL; - struct net_device *ndev = NULL; - struct i2c_adapter *root; - char namebuf[30]; - int rc; - - root = mux_root_adapter(adap); - if (root != mcli->client->adapter) { - dev_err(&mcli->client->dev, - "I2C adapter %s is not a child bus of %s", - mcli->client->adapter->name, root->name); - return -EINVAL; - } - - WARN_ON(!mutex_is_locked(&mi_driver_state.lock)); - snprintf(namebuf, sizeof(namebuf), "mctpi2c%d", adap->nr); - ndev = alloc_netdev(sizeof(*midev), namebuf, NET_NAME_ENUM, mctp_i2c_net_setup); - if (!ndev) { - dev_err(&mcli->client->dev, "%s alloc netdev failed\n", __func__); - rc = -ENOMEM; - goto err; - } - dev_net_set(ndev, current->nsproxy->net_ns); - SET_NETDEV_DEV(ndev, &adap->dev); - ndev->dev_addr = &mcli->lladdr; - - midev = netdev_priv(ndev); - skb_queue_head_init(&midev->tx_queue); - INIT_LIST_HEAD(&midev->list); - midev->adapter = adap; - midev->client = mcli; - spin_lock_init(&midev->flow_lock); - midev->i2c_lock_count = 0; - midev->release_count = 0; - /* Hold references */ - get_device(&midev->adapter->dev); - get_device(&midev->client->client->dev); - midev->ndev = ndev; - init_waitqueue_head(&midev->tx_wq); - midev->tx_thread = kthread_create(mctp_i2c_tx_thread, midev, - "%s/tx", namebuf); - if (IS_ERR_OR_NULL(midev->tx_thread)) { - rc = -ENOMEM; - goto err_free; - } - - rc = mctp_register_netdev(ndev, &mctp_i2c_mctp_ops); - if (rc) { - dev_err(&mcli->client->dev, - "%s register netdev \"%s\" failed %d\n", __func__, - ndev->name, rc); - goto err_stop_kthread; - } - spin_lock_irqsave(&mcli->curr_lock, flags); - list_add(&midev->list, &mcli->devs); - // Select a device by default - if (!mcli->sel) - __mctp_i2c_device_select(mcli, midev); - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - wake_up_process(midev->tx_thread); - - return 0; - -err_stop_kthread: - kthread_stop(midev->tx_thread); - -err_free: - free_netdev(ndev); - -err: - return rc; -} - -// Removes and unregisters a mctp-i2c netdev -static void mctp_i2c_free_netdev(struct mctp_i2c_dev *midev) -{ - struct mctp_i2c_client *mcli = midev->client; - unsigned long flags; - - netif_stop_queue(midev->ndev); - kthread_stop(midev->tx_thread); - skb_queue_purge(&midev->tx_queue); - - /* Release references, used only for TX which has stopped */ - put_device(&midev->adapter->dev); - put_device(&mcli->client->dev); - - /* Remove it from the parent mcli */ - spin_lock_irqsave(&mcli->curr_lock, flags); - list_del(&midev->list); - if (mcli->sel == midev) { - struct mctp_i2c_dev *first; - - first = list_first_entry_or_null(&mcli->devs, struct mctp_i2c_dev, list); - __mctp_i2c_device_select(mcli, first); - } - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - /* Remove netdev. mctp_i2c_slave_cb() takes a dev_hold() so removing - * it now is safe. unregister_netdev() frees ndev and midev. - */ - mctp_unregister_netdev(midev->ndev); -} - -// Removes any netdev for adap. mcli is the parent root i2c client -static void mctp_i2c_remove_netdev(struct mctp_i2c_client *mcli, - struct i2c_adapter *adap) -{ - unsigned long flags; - struct mctp_i2c_dev *midev = NULL, *m = NULL; - - WARN_ON(!mutex_is_locked(&mi_driver_state.lock)); - spin_lock_irqsave(&mcli->curr_lock, flags); - // list size is limited by number of MCTP netdevs on a single hardware bus - list_for_each_entry(m, &mcli->devs, list) - if (m->adapter == adap) { - midev = m; - break; - } - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - if (midev) - mctp_i2c_free_netdev(midev); -} - -/* Determines whether a device is an i2c adapter. - * Optionally returns the root i2c_adapter - */ -static struct i2c_adapter *mctp_i2c_get_adapter(struct device *dev, - struct i2c_adapter **ret_root) -{ - struct i2c_adapter *root, *adap; - - if (dev->type != &i2c_adapter_type) - return NULL; - adap = to_i2c_adapter(dev); - root = mux_root_adapter(adap); - WARN_ONCE(!root, "%s failed to find root adapter for %s\n", - __func__, dev_name(dev)); - if (!root) - return NULL; - if (ret_root) - *ret_root = root; - return adap; -} - -/* Determines whether a device is an i2c adapter with the "mctp-controller" - * devicetree property set. If adap is not an OF node, returns match_no_of - */ -static bool mctp_i2c_adapter_match(struct i2c_adapter *adap, bool match_no_of) -{ - if (!adap->dev.of_node) - return match_no_of; - return of_property_read_bool(adap->dev.of_node, MCTP_I2C_OF_PROP); -} - -/* Called for each existing i2c device (adapter or client) when a - * new mctp-i2c client is probed. - */ -static int mctp_i2c_client_try_attach(struct device *dev, void *data) -{ - struct i2c_adapter *adap = NULL, *root = NULL; - struct mctp_i2c_client *mcli = data; - - adap = mctp_i2c_get_adapter(dev, &root); - if (!adap) - return 0; - if (mcli->client->adapter != root) - return 0; - // Must either have mctp-controller property on the adapter, or - // be a root adapter if it's non-devicetree - if (!mctp_i2c_adapter_match(adap, adap == root)) - return 0; - - return mctp_i2c_add_netdev(mcli, adap); -} - -static void mctp_i2c_notify_add(struct device *dev) -{ - struct mctp_i2c_client *mcli = NULL, *m = NULL; - struct i2c_adapter *root = NULL, *adap = NULL; - int rc; - - adap = mctp_i2c_get_adapter(dev, &root); - if (!adap) - return; - // Check for mctp-controller property on the adapter - if (!mctp_i2c_adapter_match(adap, false)) - return; - - /* Find an existing mcli for adap's root */ - mutex_lock(&mi_driver_state.lock); - list_for_each_entry(m, &mi_driver_state.clients, list) { - if (m->client->adapter == root) { - mcli = m; - break; - } - } - - if (mcli) { - rc = mctp_i2c_add_netdev(mcli, adap); - if (rc) - dev_warn(dev, "%s Failed adding mctp-i2c device", - __func__); - } - mutex_unlock(&mi_driver_state.lock); -} - -static void mctp_i2c_notify_del(struct device *dev) -{ - struct i2c_adapter *root = NULL, *adap = NULL; - struct mctp_i2c_client *mcli = NULL; - - adap = mctp_i2c_get_adapter(dev, &root); - if (!adap) - return; - - mutex_lock(&mi_driver_state.lock); - list_for_each_entry(mcli, &mi_driver_state.clients, list) { - if (mcli->client->adapter == root) { - mctp_i2c_remove_netdev(mcli, adap); - break; - } - } - mutex_unlock(&mi_driver_state.lock); -} - -static int mctp_i2c_probe(struct i2c_client *client) -{ - struct mctp_i2c_client *mcli = NULL; - int rc; - - /* Check for >32 byte block support required for MCTP */ - if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_V3_BLOCK)) { - dev_err(&client->dev, - "%s failed, I2C bus driver does not support 255 byte block transfer\n", - __func__); - return -EOPNOTSUPP; - } - - mutex_lock(&mi_driver_state.lock); - mcli = mctp_i2c_new_client(client); - if (IS_ERR(mcli)) { - rc = PTR_ERR(mcli); - mcli = NULL; - goto out; - } else { - list_add(&mcli->list, &mi_driver_state.clients); - } - - // Add a netdev for adapters that have a 'mctp-controller' property - i2c_for_each_dev(mcli, mctp_i2c_client_try_attach); - rc = 0; -out: - mutex_unlock(&mi_driver_state.lock); - return rc; -} - -static int mctp_i2c_remove(struct i2c_client *client) -{ - struct mctp_i2c_client *mcli = i2c_get_clientdata(client); - struct mctp_i2c_dev *midev = NULL, *tmp = NULL; - - mutex_lock(&mi_driver_state.lock); - list_del(&mcli->list); - // Remove all child adapter netdevs - list_for_each_entry_safe(midev, tmp, &mcli->devs, list) - mctp_i2c_free_netdev(midev); - - mctp_i2c_free_client(mcli); - mutex_unlock(&mi_driver_state.lock); - // Callers ignore return code - return 0; -} - -/* We look for a 'mctp-controller' property on I2C busses as they are - * added/deleted, creating/removing netdevs as required. - */ -static int mctp_i2c_notifier_call(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - mctp_i2c_notify_add(dev); - break; - case BUS_NOTIFY_DEL_DEVICE: - mctp_i2c_notify_del(dev); - break; - } - return NOTIFY_DONE; -} - -static struct notifier_block mctp_i2c_notifier = { - .notifier_call = mctp_i2c_notifier_call, -}; - -static const struct i2c_device_id mctp_i2c_id[] = { - { "mctp-i2c", 0 }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, mctp_i2c_id); - -static const struct of_device_id mctp_i2c_of_match[] = { - { .compatible = "mctp-i2c-controller" }, - {}, -}; -MODULE_DEVICE_TABLE(of, mctp_i2c_of_match); - -static struct i2c_driver mctp_i2c_driver = { - .driver = { - .name = "mctp-i2c", - .of_match_table = mctp_i2c_of_match, - }, - .probe_new = mctp_i2c_probe, - .remove = mctp_i2c_remove, - .id_table = mctp_i2c_id, -}; - -static __init int mctp_i2c_init(void) -{ - int rc; - - INIT_LIST_HEAD(&mi_driver_state.clients); - mutex_init(&mi_driver_state.lock); - pr_info("MCTP SMBus/I2C transport driver\n"); - rc = i2c_add_driver(&mctp_i2c_driver); - if (rc) - return rc; - rc = bus_register_notifier(&i2c_bus_type, &mctp_i2c_notifier); - if (rc) { - i2c_del_driver(&mctp_i2c_driver); - return rc; - } - return 0; -} - -static __exit void mctp_i2c_exit(void) -{ - int rc; - - rc = bus_unregister_notifier(&i2c_bus_type, &mctp_i2c_notifier); - if (rc) - pr_warn("%s Could not unregister notifier, %d", __func__, rc); - i2c_del_driver(&mctp_i2c_driver); -} - -module_init(mctp_i2c_init); -module_exit(mctp_i2c_exit); - -MODULE_DESCRIPTION("MCTP SMBus/I2C device"); -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Matt Johnston "); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 353d6b4e7a53..16119ac1aa97 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -52,19 +52,6 @@ typedef int (*i2c_slave_cb_t)(struct i2c_client *client, struct module; struct property_entry; -/* SMBus 3.0 extends the maximum block read/write size to 255 (from 32). - * The larger size is only supported by some drivers, indicated by - * the I2C_FUNC_SMBUS_V3_BLOCK functionality bit. - */ -#define I2C_SMBUS_V3_BLOCK_MAX 255 /* As specified in SMBus 3.0 standard */ - -/* Note compatibility definition in uapi header with 32 byte block */ -union i2c_smbus_data { - __u8 byte; - __u16 word; - __u8 block[I2C_SMBUS_V3_BLOCK_MAX + 1]; /* block[0] is used for length */ -}; - #if IS_ENABLED(CONFIG_I2C) /* Return the Frequency mode string based on the bus frequency */ const char *i2c_freq_mode_string(u32 bus_freq_hz); diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 46ce31d42f7d..1c4cec4ddd84 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -39,14 +39,12 @@ /* This is the structure as used in the I2C_SMBUS ioctl call */ -#ifndef __KERNEL__ struct i2c_smbus_ioctl_data { __u8 read_write; __u8 command; __u32 size; union i2c_smbus_data __user *data; }; -#endif /* This is the structure as used in the I2C_RDWR ioctl call */ struct i2c_rdwr_ioctl_data { diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index c3534ab1ae53..92326ebde350 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -108,9 +108,6 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ #define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ -#define I2C_FUNC_SMBUS_V3_BLOCK 0x20000000 /* Device supports 255 byte block */ - /* Note that I2C_SMBUS ioctl only */ - /* supports a 32 byte block */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) @@ -140,15 +137,13 @@ struct i2c_msg { /* * Data for SMBus Messages */ -#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus 2.0 standard */ -#ifndef __KERNEL__ +#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus standard */ union i2c_smbus_data { __u8 byte; __u16 word; __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ /* and one more for user-space compatibility */ }; -#endif /* i2c_smbus_xfer read or write markers */ #define I2C_SMBUS_READ 1 -- cgit v1.2.3 From ebf7f6f0a6cdcc17a3da52b81e4b3a98c4005028 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 5 Nov 2021 09:30:00 +0800 Subject: bpf: Change value of MAX_TAIL_CALL_CNT from 32 to 33 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the current code, the actual max tail call count is 33 which is greater than MAX_TAIL_CALL_CNT (defined as 32). The actual limit is not consistent with the meaning of MAX_TAIL_CALL_CNT and thus confusing at first glance. We can see the historical evolution from commit 04fd61ab36ec ("bpf: allow bpf programs to tail-call other bpf programs") and commit f9dabe016b63 ("bpf: Undo off-by-one in interpreter tail call count limit"). In order to avoid changing existing behavior, the actual limit is 33 now, this is reasonable. After commit 874be05f525e ("bpf, tests: Add tail call test suite"), we can see there exists failed testcase. On all archs when CONFIG_BPF_JIT_ALWAYS_ON is not set: # echo 0 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf # dmesg | grep -w FAIL Tail call error path, max count reached jited:0 ret 34 != 33 FAIL On some archs: # echo 1 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf # dmesg | grep -w FAIL Tail call error path, max count reached jited:1 ret 34 != 33 FAIL Although the above failed testcase has been fixed in commit 18935a72eb25 ("bpf/tests: Fix error in tail call limit tests"), it would still be good to change the value of MAX_TAIL_CALL_CNT from 32 to 33 to make the code more readable. The 32-bit x86 JIT was using a limit of 32, just fix the wrong comments and limit to 33 tail calls as the constant MAX_TAIL_CALL_CNT updated. For the mips64 JIT, use "ori" instead of "addiu" as suggested by Johan Almbladh. For the riscv JIT, use RV_REG_TCC directly to save one register move as suggested by Björn Töpel. For the other implementations, no function changes, it does not change the current limit 33, the new value of MAX_TAIL_CALL_CNT can reflect the actual max tail call count, the related tail call testcases in test_bpf module and selftests can work well for the interpreter and the JIT. Here are the test results on x86_64: # uname -m x86_64 # echo 0 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf test_suite=test_tail_calls # dmesg | tail -1 test_bpf: test_tail_calls: Summary: 8 PASSED, 0 FAILED, [0/8 JIT'ed] # rmmod test_bpf # echo 1 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf test_suite=test_tail_calls # dmesg | tail -1 test_bpf: test_tail_calls: Summary: 8 PASSED, 0 FAILED, [8/8 JIT'ed] # rmmod test_bpf # ./test_progs -t tailcalls #142 tailcalls:OK Summary: 1/11 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Tiezhu Yang Signed-off-by: Daniel Borkmann Tested-by: Johan Almbladh Tested-by: Ilya Leoshkevich Acked-by: Björn Töpel Acked-by: Johan Almbladh Acked-by: Ilya Leoshkevich Link: https://lore.kernel.org/bpf/1636075800-3264-1-git-send-email-yangtiezhu@loongson.cn --- arch/arm/net/bpf_jit_32.c | 5 +++-- arch/arm64/net/bpf_jit_comp.c | 5 +++-- arch/mips/net/bpf_jit_comp32.c | 3 +-- arch/mips/net/bpf_jit_comp64.c | 2 +- arch/powerpc/net/bpf_jit_comp32.c | 4 ++-- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- arch/riscv/net/bpf_jit_comp32.c | 6 ++---- arch/riscv/net/bpf_jit_comp64.c | 7 +++---- arch/s390/net/bpf_jit_comp.c | 6 +++--- arch/sparc/net/bpf_jit_comp_64.c | 2 +- arch/x86/net/bpf_jit_comp.c | 10 +++++----- arch/x86/net/bpf_jit_comp32.c | 4 ++-- include/linux/bpf.h | 2 +- include/uapi/linux/bpf.h | 2 +- kernel/bpf/core.c | 3 ++- lib/test_bpf.c | 4 ++-- tools/include/uapi/linux/bpf.h | 2 +- 17 files changed, 35 insertions(+), 36 deletions(-) (limited to 'include/uapi') diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index eeb6dc0ecf46..e59b41e9ab0c 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1199,7 +1199,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) /* tmp2[0] = array, tmp2[1] = index */ - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + /* + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ @@ -1208,7 +1209,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) tc = arm_bpf_get_reg64(tcc, tmp, ctx); emit(ARM_CMP_I(tc[0], hi), ctx); _emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx); - _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx); + _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx); emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx); emit(ARM_ADC_I(tc[0], tc[0], 0), ctx); arm_bpf_put_reg64(tcc, tmp, ctx); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 86c9dc0681cc..07c12c42b751 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -287,13 +287,14 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit(A64_CMP(0, r3, tmp), ctx); emit(A64_B_(A64_COND_CS, jmp_offset), ctx); - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + /* + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_HI, jmp_offset), ctx); + emit(A64_B_(A64_COND_CS, jmp_offset), ctx); emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; diff --git a/arch/mips/net/bpf_jit_comp32.c b/arch/mips/net/bpf_jit_comp32.c index bd996ede12f8..044b11b65bca 100644 --- a/arch/mips/net/bpf_jit_comp32.c +++ b/arch/mips/net/bpf_jit_comp32.c @@ -1381,8 +1381,7 @@ void build_prologue(struct jit_context *ctx) * 16-byte area in the parent's stack frame. On a tail call, the * calling function jumps into the prologue after these instructions. */ - emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, - min(MAX_TAIL_CALL_CNT + 1, 0xffff)); + emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff)); emit(ctx, sw, MIPS_R_T9, 0, MIPS_R_SP); /* diff --git a/arch/mips/net/bpf_jit_comp64.c b/arch/mips/net/bpf_jit_comp64.c index 815ade724227..6475828ffb36 100644 --- a/arch/mips/net/bpf_jit_comp64.c +++ b/arch/mips/net/bpf_jit_comp64.c @@ -552,7 +552,7 @@ void build_prologue(struct jit_context *ctx) * On a tail call, the calling function jumps into the prologue * after this instruction. */ - emit(ctx, addiu, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT + 1, 0xffff)); + emit(ctx, ori, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff)); /* === Entry-point for tail calls === */ diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 0da31d41d413..8a4faa05f9e4 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -221,13 +221,13 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC(COND_GE, out); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT(PPC_RAW_CMPLWI(_R0, MAX_TAIL_CALL_CNT)); /* tail_call_cnt++; */ EMIT(PPC_RAW_ADDIC(_R0, _R0, 1)); - PPC_BCC(COND_GT, out); + PPC_BCC(COND_GE, out); /* prog = array->ptrs[index]; */ EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29)); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 8b5157ccfeba..8571aafcc9e1 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -228,12 +228,12 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC(COND_GE, out); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT)); - PPC_BCC(COND_GT, out); + PPC_BCC(COND_GE, out); /* * tail_call_cnt++; diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index e6497424cbf6..529a83b85c1c 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -799,11 +799,10 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); /* - * temp_tcc = tcc - 1; - * if (tcc < 0) + * if (--tcc < 0) * goto out; */ - emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx); + emit(rv_addi(RV_REG_TCC, RV_REG_TCC, -1), ctx); off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); @@ -829,7 +828,6 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) if (is_12b_check(off, insn)) return -1; emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); - emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx); /* Epilogue jumps to *(t0 + 4). */ __build_epilogue(true, ctx); return 0; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index f2a779c7e225..603630b6f3c5 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -327,12 +327,12 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); emit_branch(BPF_JGE, RV_REG_A2, RV_REG_T1, off, ctx); - /* if (TCC-- < 0) + /* if (--TCC < 0) * goto out; */ - emit_addi(RV_REG_T1, tcc, -1, ctx); + emit_addi(RV_REG_TCC, tcc, -1, ctx); off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); - emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx); + emit_branch(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); /* prog = array->ptrs[index]; * if (!prog) @@ -352,7 +352,6 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) if (is_12b_check(off, insn)) return -1; emit_ld(RV_REG_T3, off, RV_REG_T2, ctx); - emit_mv(RV_REG_TCC, RV_REG_T1, ctx); __build_epilogue(true, ctx); return 0; } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 233cc9bcd652..9ff2bd83aad7 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1369,7 +1369,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, jit->prg); /* - * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ @@ -1381,9 +1381,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4_IMM(0xa7080000, REG_W0, 1); /* laal %w1,%w0,off(%r15) */ EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off); - /* clij %w1,MAX_TAIL_CALL_CNT,0x2,out */ + /* clij %w1,MAX_TAIL_CALL_CNT-1,0x2,out */ patch_2_clij = jit->prg; - EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT, + EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT - 1, 2, jit->prg); /* diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 9a2f20cbd48b..0bfe1c72a0c9 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -867,7 +867,7 @@ static void emit_tail_call(struct jit_ctx *ctx) emit(LD32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx); emit_cmpi(tmp, MAX_TAIL_CALL_CNT, ctx); #define OFFSET2 13 - emit_branch(BGU, ctx->idx, ctx->idx + OFFSET2, ctx); + emit_branch(BGEU, ctx->idx, ctx->idx + OFFSET2, ctx); emit_nop(ctx); emit_alu_K(ADD, tmp, 1, ctx); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 726700fabca6..631847907786 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,7 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... * if (index >= array->map.max_entries) * goto out; - * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; * prog = array->ptrs[index]; * if (prog == NULL) @@ -446,14 +446,14 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, EMIT2(X86_JBE, offset); /* jbe out */ /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_indirect_label - (prog + 2 - start); - EMIT2(X86_JA, offset); /* ja out */ + EMIT2(X86_JAE, offset); /* jae out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ @@ -504,14 +504,14 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, int offset; /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_direct_label - (prog + 2 - start); - EMIT2(X86_JA, offset); /* ja out */ + EMIT2(X86_JAE, offset); /* jae out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index da9b7cfa4632..429a89c5468b 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1323,7 +1323,7 @@ static void emit_bpf_tail_call(u8 **pprog, u8 *ip) EMIT2(IA32_JBE, jmp_label(jmp_label1, 2)); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ lo = (u32)MAX_TAIL_CALL_CNT; @@ -1337,7 +1337,7 @@ static void emit_bpf_tail_call(u8 **pprog, u8 *ip) /* cmp ecx,lo */ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), lo); - /* ja out */ + /* jae out */ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); /* add eax,0x1 */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 56098c866704..cc7a0c36e7df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1081,7 +1081,7 @@ struct bpf_array { }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ -#define MAX_TAIL_CALL_CNT 32 +#define MAX_TAIL_CALL_CNT 33 #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6297eafdc40f..a69e4b04ffeb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1744,7 +1744,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2405e39d800f..b52dc845ecea 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1574,7 +1574,8 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) + + if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index adae39567264..0c5cb2d6436a 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14683,7 +14683,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, - .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, }, { "Tail call count preserved across function calls", @@ -14705,7 +14705,7 @@ static struct tail_call_test tail_call_tests[] = { }, .stack_depth = 8, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, - .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, }, { "Tail call error path, NULL target", diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6297eafdc40f..a69e4b04ffeb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1744,7 +1744,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * -- cgit v1.2.3 From b5f57384805a34f497edb8b04d694a8a1b3d81d4 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Fri, 10 Sep 2021 15:18:20 -0400 Subject: drm/amdkfd: Add sysfs bitfields and enums to uAPI These bits are de-facto part of the uAPI, so declare them in a uAPI header. The corresponding bit-fields and enums in user mode are defined in https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/blob/master/include/hsakmttypes.h HSA_CAP_... -> HSA_CAPABILITY HSA_MEM_HEAP_TYPE_... -> HSA_HEAPTYPE HSA_MEM_FLAGS_... -> HSA_MEMORYPROPERTY HSA_CACHE_TYPE_... -> HsaCacheType HSA_IOLINK_TYPE_... -> HSA_IOLINKTYPE HSA_IOLINK_FLAGS_... -> HSA_LINKPROPERTY Signed-off-by: Felix Kuehling Reviewed-by: Jonathan Kim Signed-off-by: Alex Deucher --- MAINTAINERS | 1 + drivers/gpu/drm/amd/amdkfd/kfd_topology.h | 46 +------------ include/uapi/linux/kfd_sysfs.h | 108 ++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+), 45 deletions(-) create mode 100644 include/uapi/linux/kfd_sysfs.h (limited to 'include/uapi') diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..f05a19b22505 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -966,6 +966,7 @@ F: drivers/gpu/drm/amd/include/kgd_kfd_interface.h F: drivers/gpu/drm/amd/include/v9_structs.h F: drivers/gpu/drm/amd/include/vi_structs.h F: include/uapi/linux/kfd_ioctl.h +F: include/uapi/linux/kfd_sysfs.h AMD SPI DRIVER M: Sanjay R Mehta diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index a8db017c9b8e..f0cc59d2fd5d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -25,38 +25,11 @@ #include #include +#include #include "kfd_crat.h" #define KFD_TOPOLOGY_PUBLIC_NAME_SIZE 32 -#define HSA_CAP_HOT_PLUGGABLE 0x00000001 -#define HSA_CAP_ATS_PRESENT 0x00000002 -#define HSA_CAP_SHARED_WITH_GRAPHICS 0x00000004 -#define HSA_CAP_QUEUE_SIZE_POW2 0x00000008 -#define HSA_CAP_QUEUE_SIZE_32BIT 0x00000010 -#define HSA_CAP_QUEUE_IDLE_EVENT 0x00000020 -#define HSA_CAP_VA_LIMIT 0x00000040 -#define HSA_CAP_WATCH_POINTS_SUPPORTED 0x00000080 -#define HSA_CAP_WATCH_POINTS_TOTALBITS_MASK 0x00000f00 -#define HSA_CAP_WATCH_POINTS_TOTALBITS_SHIFT 8 -#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK 0x00003000 -#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT 12 - -#define HSA_CAP_DOORBELL_TYPE_PRE_1_0 0x0 -#define HSA_CAP_DOORBELL_TYPE_1_0 0x1 -#define HSA_CAP_DOORBELL_TYPE_2_0 0x2 -#define HSA_CAP_AQL_QUEUE_DOUBLE_MAP 0x00004000 - -#define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 /* Old buggy user mode depends on this being 0 */ -#define HSA_CAP_MEM_EDCSUPPORTED 0x00100000 -#define HSA_CAP_RASEVENTNOTIFY 0x00200000 -#define HSA_CAP_ASIC_REVISION_MASK 0x03c00000 -#define HSA_CAP_ASIC_REVISION_SHIFT 22 -#define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 -#define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 -#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 -#define HSA_CAP_RESERVED 0xe00f8000 - struct kfd_node_properties { uint64_t hive_id; uint32_t cpu_cores_count; @@ -93,17 +66,6 @@ struct kfd_node_properties { char name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE]; }; -#define HSA_MEM_HEAP_TYPE_SYSTEM 0 -#define HSA_MEM_HEAP_TYPE_FB_PUBLIC 1 -#define HSA_MEM_HEAP_TYPE_FB_PRIVATE 2 -#define HSA_MEM_HEAP_TYPE_GPU_GDS 3 -#define HSA_MEM_HEAP_TYPE_GPU_LDS 4 -#define HSA_MEM_HEAP_TYPE_GPU_SCRATCH 5 - -#define HSA_MEM_FLAGS_HOT_PLUGGABLE 0x00000001 -#define HSA_MEM_FLAGS_NON_VOLATILE 0x00000002 -#define HSA_MEM_FLAGS_RESERVED 0xfffffffc - struct kfd_mem_properties { struct list_head list; uint32_t heap_type; @@ -116,12 +78,6 @@ struct kfd_mem_properties { struct attribute attr; }; -#define HSA_CACHE_TYPE_DATA 0x00000001 -#define HSA_CACHE_TYPE_INSTRUCTION 0x00000002 -#define HSA_CACHE_TYPE_CPU 0x00000004 -#define HSA_CACHE_TYPE_HSACU 0x00000008 -#define HSA_CACHE_TYPE_RESERVED 0xfffffff0 - struct kfd_cache_properties { struct list_head list; uint32_t processor_id_low; diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h new file mode 100644 index 000000000000..e1fb78b4bf09 --- /dev/null +++ b/include/uapi/linux/kfd_sysfs.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT WITH Linux-syscall-note */ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef KFD_SYSFS_H_INCLUDED +#define KFD_SYSFS_H_INCLUDED + +/* Capability bits in node properties */ +#define HSA_CAP_HOT_PLUGGABLE 0x00000001 +#define HSA_CAP_ATS_PRESENT 0x00000002 +#define HSA_CAP_SHARED_WITH_GRAPHICS 0x00000004 +#define HSA_CAP_QUEUE_SIZE_POW2 0x00000008 +#define HSA_CAP_QUEUE_SIZE_32BIT 0x00000010 +#define HSA_CAP_QUEUE_IDLE_EVENT 0x00000020 +#define HSA_CAP_VA_LIMIT 0x00000040 +#define HSA_CAP_WATCH_POINTS_SUPPORTED 0x00000080 +#define HSA_CAP_WATCH_POINTS_TOTALBITS_MASK 0x00000f00 +#define HSA_CAP_WATCH_POINTS_TOTALBITS_SHIFT 8 +#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK 0x00003000 +#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT 12 + +#define HSA_CAP_DOORBELL_TYPE_PRE_1_0 0x0 +#define HSA_CAP_DOORBELL_TYPE_1_0 0x1 +#define HSA_CAP_DOORBELL_TYPE_2_0 0x2 +#define HSA_CAP_AQL_QUEUE_DOUBLE_MAP 0x00004000 + +/* Old buggy user mode depends on this being 0 */ +#define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 + +#define HSA_CAP_MEM_EDCSUPPORTED 0x00100000 +#define HSA_CAP_RASEVENTNOTIFY 0x00200000 +#define HSA_CAP_ASIC_REVISION_MASK 0x03c00000 +#define HSA_CAP_ASIC_REVISION_SHIFT 22 +#define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 +#define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 +#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 +#define HSA_CAP_RESERVED 0xe00f8000 + +/* Heap types in memory properties */ +#define HSA_MEM_HEAP_TYPE_SYSTEM 0 +#define HSA_MEM_HEAP_TYPE_FB_PUBLIC 1 +#define HSA_MEM_HEAP_TYPE_FB_PRIVATE 2 +#define HSA_MEM_HEAP_TYPE_GPU_GDS 3 +#define HSA_MEM_HEAP_TYPE_GPU_LDS 4 +#define HSA_MEM_HEAP_TYPE_GPU_SCRATCH 5 + +/* Flag bits in memory properties */ +#define HSA_MEM_FLAGS_HOT_PLUGGABLE 0x00000001 +#define HSA_MEM_FLAGS_NON_VOLATILE 0x00000002 +#define HSA_MEM_FLAGS_RESERVED 0xfffffffc + +/* Cache types in cache properties */ +#define HSA_CACHE_TYPE_DATA 0x00000001 +#define HSA_CACHE_TYPE_INSTRUCTION 0x00000002 +#define HSA_CACHE_TYPE_CPU 0x00000004 +#define HSA_CACHE_TYPE_HSACU 0x00000008 +#define HSA_CACHE_TYPE_RESERVED 0xfffffff0 + +/* Link types in IO link properties (matches CRAT link types) */ +#define HSA_IOLINK_TYPE_UNDEFINED 0 +#define HSA_IOLINK_TYPE_HYPERTRANSPORT 1 +#define HSA_IOLINK_TYPE_PCIEXPRESS 2 +#define HSA_IOLINK_TYPE_AMBA 3 +#define HSA_IOLINK_TYPE_MIPI 4 +#define HSA_IOLINK_TYPE_QPI_1_1 5 +#define HSA_IOLINK_TYPE_RESERVED1 6 +#define HSA_IOLINK_TYPE_RESERVED2 7 +#define HSA_IOLINK_TYPE_RAPID_IO 8 +#define HSA_IOLINK_TYPE_INFINIBAND 9 +#define HSA_IOLINK_TYPE_RESERVED3 10 +#define HSA_IOLINK_TYPE_XGMI 11 +#define HSA_IOLINK_TYPE_XGOP 12 +#define HSA_IOLINK_TYPE_GZ 13 +#define HSA_IOLINK_TYPE_ETHERNET_RDMA 14 +#define HSA_IOLINK_TYPE_RDMA_OTHER 15 +#define HSA_IOLINK_TYPE_OTHER 16 + +/* Flag bits in IO link properties (matches CRAT flags, excluding the + * bi-directional flag, which is not offially part of the CRAT spec, and + * only used internally in KFD) + */ +#define HSA_IOLINK_FLAGS_ENABLED (1 << 0) +#define HSA_IOLINK_FLAGS_NON_COHERENT (1 << 1) +#define HSA_IOLINK_FLAGS_NO_ATOMICS_32_BIT (1 << 2) +#define HSA_IOLINK_FLAGS_NO_ATOMICS_64_BIT (1 << 3) +#define HSA_IOLINK_FLAGS_NO_PEER_TO_PEER_DMA (1 << 4) +#define HSA_IOLINK_FLAGS_RESERVED 0xffffffe0 + +#endif -- cgit v1.2.3 From e6feefa541f309afed8aa54431681261bc57bcde Mon Sep 17 00:00:00 2001 From: YC Hung Date: Thu, 18 Nov 2021 12:07:43 +0200 Subject: ASoC: SOF: tokens: add token for Mediatek AFE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the definition for Mediatek audio front end(AFE) tokens,include AFE sampling rate, channels, and format. Signed-off-by: YC Hung Reviewed-by: Péter Ujfalusi Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Reviewed-by: Daniel Baluta Signed-off-by: Daniel Baluta Link: https://lore.kernel.org/r/20211118100749.54628-3-daniel.baluta@oss.nxp.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/tokens.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index 02b71a8deea4..b72fa385bebf 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -140,4 +140,9 @@ #define SOF_TKN_INTEL_HDA_RATE 1500 #define SOF_TKN_INTEL_HDA_CH 1501 +/* AFE */ +#define SOF_TKN_MEDIATEK_AFE_RATE 1600 +#define SOF_TKN_MEDIATEK_AFE_CH 1601 +#define SOF_TKN_MEDIATEK_AFE_FORMAT 1602 + #endif -- cgit v1.2.3 From bc2dfc02836b1133d1bf4d22aa13d48ac98eabef Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 23 Oct 2021 11:10:50 +0200 Subject: cfg80211: implement APIs for dedicated radar detection HW If a dedicated (off-channel) radar detection hardware (chain) is available in the hardware/driver, allow this to be used by calling the NL80211_CMD_RADAR_DETECT command with a new flag attribute requesting off-channel radar detection is used. Offchannel CAC (channel availability check) avoids the CAC downtime when switching to a radar channel or when turning on the AP. Drivers advertise support for this using the new feature flag NL80211_EXT_FEATURE_RADAR_OFFCHAN. Tested-by: Evelyn Tsai Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/7468e291ef5d05d692c1738d25b8f778d8ea5c3f.1634979655.git.lorenzo@kernel.org Link: https://lore.kernel.org/r/1e60e60fef00e14401adae81c3d49f3e5f307537.1634979655.git.lorenzo@kernel.org Link: https://lore.kernel.org/r/85fa50f57fc3adb2934c8d9ca0be30394de6b7e8.1634979655.git.lorenzo@kernel.org Link: https://lore.kernel.org/r/4b6c08671ad59aae0ac46fc94c02f31b1610eb72.1634979655.git.lorenzo@kernel.org Link: https://lore.kernel.org/r/241849ccaf2c228873c6f8495bf87b19159ba458.1634979655.git.lorenzo@kernel.org [remove offchan_mutex, fix cfg80211_stop_offchan_radar_detection(), remove gfp_t argument, fix documentation, fix tracing] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 25 ++++++++++ include/uapi/linux/nl80211.h | 13 +++++ net/wireless/core.c | 3 ++ net/wireless/core.h | 13 +++++ net/wireless/mlme.c | 113 +++++++++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.c | 17 ++++--- net/wireless/rdev-ops.h | 17 +++++++ net/wireless/trace.h | 19 ++++++++ 8 files changed, 214 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 423f97b982ff..db8866d42a4b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4072,6 +4072,15 @@ struct mgmt_frame_regs { * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use * those to decrypt (Re)Association Request and encrypt (Re)Association * Response frame. + * + * @set_radar_offchan: Configure dedicated offchannel chain available for + * radar/CAC detection on some hw. This chain can't be used to transmit + * or receive frames and it is bounded to a running wdev. + * Offchannel radar/CAC detection allows to avoid the CAC downtime + * switching to a different channel during CAC detection on the selected + * radar channel. + * The caller is expected to set chandef pointer to NULL in order to + * disable offchannel CAC/radar detection. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4404,6 +4413,8 @@ struct cfg80211_ops { struct cfg80211_color_change_settings *params); int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_fils_aad *fils_aad); + int (*set_radar_offchan)(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef); }; /* @@ -7633,6 +7644,20 @@ void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, gfp_t gfp); +/** + * cfg80211_offchan_cac_event - Channel Availability Check (CAC) offchan event + * @wiphy: the wiphy + * @chandef: chandef for the current channel + * @event: type of event + * + * This function is called when a Channel Availability Check (CAC) is finished, + * started or aborted by a offchannel dedicated chain. + * + * Note that this acquires the wiphy lock. + */ +void cfg80211_offchan_cac_event(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + enum nl80211_radar_event event); /** * cfg80211_gtk_rekey_notify - notify userspace about driver rekeying diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 61cab81e920d..3e734826792f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2639,6 +2639,13 @@ enum nl80211_commands { * Mandatory parameter for the transmitting interface to enable MBSSID. * Optional for the non-transmitting interfaces. * + * @NL80211_ATTR_RADAR_OFFCHAN: Configure dedicated offchannel chain available for + * radar/CAC detection on some hw. This chain can't be used to transmit + * or receive frames and it is bounded to a running wdev. + * Offchannel radar/CAC detection allows to avoid the CAC downtime + * switching on a different channel during CAC detection on the selected + * radar channel. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3145,6 +3152,8 @@ enum nl80211_attrs { NL80211_ATTR_MBSSID_CONFIG, NL80211_ATTR_MBSSID_ELEMS, + NL80211_ATTR_RADAR_OFFCHAN, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -6051,6 +6060,9 @@ enum nl80211_feature_flags { * frames. Userspace has to share FILS AAD details to the driver by using * @NL80211_CMD_SET_FILS_AAD. * + * @NL80211_EXT_FEATURE_RADAR_OFFCHAN: Device supports offchannel radar/CAC + * detection. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6117,6 +6129,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_PROT_RANGE_NEGO_AND_MEASURE, NL80211_EXT_FEATURE_BSS_COLOR, NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, + NL80211_EXT_FEATURE_RADAR_OFFCHAN, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/core.c b/net/wireless/core.c index eb297e1015e0..39b2d4ae581d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -545,6 +545,7 @@ use_default_name: INIT_WORK(&rdev->rfkill_block, cfg80211_rfkill_block_work); INIT_WORK(&rdev->conn_work, cfg80211_conn_work); INIT_WORK(&rdev->event_work, cfg80211_event_work); + INIT_DELAYED_WORK(&rdev->offchan_cac_work, cfg80211_offchan_cac_work); init_waitqueue_head(&rdev->dev_wait); @@ -1207,6 +1208,8 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, cfg80211_pmsr_wdev_down(wdev); + cfg80211_stop_offchan_radar_detection(wdev); + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: __cfg80211_leave_ibss(rdev, dev, true); diff --git a/net/wireless/core.h b/net/wireless/core.h index 1720abf36f92..612d460dcde0 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -84,6 +84,10 @@ struct cfg80211_registered_device { struct delayed_work dfs_update_channels_wk; + struct wireless_dev *offchan_radar_wdev; + struct cfg80211_chan_def offchan_radar_chandef; + struct delayed_work offchan_cac_work; + /* netlink port which started critical protocol (0 means not started) */ u32 crit_proto_nlportid; @@ -491,6 +495,15 @@ cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, void cfg80211_sched_dfs_chan_update(struct cfg80211_registered_device *rdev); +int +cfg80211_start_offchan_radar_detection(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef); + +void cfg80211_stop_offchan_radar_detection(struct wireless_dev *wdev); + +void cfg80211_offchan_cac_work(struct work_struct *work); + bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, struct ieee80211_channel *chan); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 783acd2c4211..46f2ec4d50d7 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -970,3 +970,116 @@ void cfg80211_cac_event(struct net_device *netdev, nl80211_radar_notify(rdev, chandef, event, netdev, gfp); } EXPORT_SYMBOL(cfg80211_cac_event); + +void cfg80211_offchan_cac_work(struct work_struct *work) +{ + struct delayed_work *delayed_work = to_delayed_work(work); + struct cfg80211_registered_device *rdev; + + rdev = container_of(delayed_work, struct cfg80211_registered_device, + offchan_cac_work); + cfg80211_offchan_cac_event(&rdev->wiphy, &rdev->offchan_radar_chandef, + NL80211_RADAR_CAC_FINISHED); +} + +static void +__cfg80211_offchan_cac_event(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + const struct cfg80211_chan_def *chandef, + enum nl80211_radar_event event) +{ + struct wiphy *wiphy = &rdev->wiphy; + struct net_device *netdev; + + lockdep_assert_wiphy(&rdev->wiphy); + + if (event != NL80211_RADAR_CAC_STARTED && !rdev->offchan_radar_wdev) + return; + + switch (event) { + case NL80211_RADAR_CAC_FINISHED: + cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE); + memcpy(&rdev->cac_done_chandef, chandef, sizeof(*chandef)); + queue_work(cfg80211_wq, &rdev->propagate_cac_done_wk); + cfg80211_sched_dfs_chan_update(rdev); + wdev = rdev->offchan_radar_wdev; + rdev->offchan_radar_wdev = NULL; + break; + case NL80211_RADAR_CAC_ABORTED: + cancel_delayed_work(&rdev->offchan_cac_work); + wdev = rdev->offchan_radar_wdev; + rdev->offchan_radar_wdev = NULL; + break; + case NL80211_RADAR_CAC_STARTED: + WARN_ON(!wdev); + rdev->offchan_radar_wdev = wdev; + break; + default: + return; + } + + netdev = wdev ? wdev->netdev : NULL; + nl80211_radar_notify(rdev, chandef, event, netdev, GFP_KERNEL); +} + +void cfg80211_offchan_cac_event(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + enum nl80211_radar_event event) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + + wiphy_lock(wiphy); + __cfg80211_offchan_cac_event(rdev, NULL, chandef, event); + wiphy_unlock(wiphy); +} +EXPORT_SYMBOL(cfg80211_offchan_cac_event); + +int +cfg80211_start_offchan_radar_detection(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef) +{ + unsigned int cac_time_ms; + int err; + + lockdep_assert_wiphy(&rdev->wiphy); + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_RADAR_OFFCHAN)) + return -EOPNOTSUPP; + + if (rdev->offchan_radar_wdev) + return -EBUSY; + + err = rdev_set_radar_offchan(rdev, chandef); + if (err) + return err; + + cac_time_ms = cfg80211_chandef_dfs_cac_time(&rdev->wiphy, chandef); + if (!cac_time_ms) + cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + + rdev->offchan_radar_chandef = *chandef; + __cfg80211_offchan_cac_event(rdev, wdev, chandef, + NL80211_RADAR_CAC_STARTED); + queue_delayed_work(cfg80211_wq, &rdev->offchan_cac_work, + msecs_to_jiffies(cac_time_ms)); + + return 0; +} + +void cfg80211_stop_offchan_radar_detection(struct wireless_dev *wdev) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + + lockdep_assert_wiphy(wiphy); + + if (wdev != rdev->offchan_radar_wdev) + return; + + rdev_set_radar_offchan(rdev, NULL); + + __cfg80211_offchan_cac_event(rdev, NULL, NULL, + NL80211_RADAR_CAC_ABORTED); +} diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index a27b3b5fa210..83a1ba96e172 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -776,6 +776,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MBSSID_CONFIG] = NLA_POLICY_NESTED(nl80211_mbssid_config_policy), [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, + [NL80211_ATTR_RADAR_OFFCHAN] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -9284,12 +9285,6 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, if (err) return err; - if (netif_carrier_ok(dev)) - return -EBUSY; - - if (wdev->cac_started) - return -EBUSY; - err = cfg80211_chandef_dfs_required(wiphy, &chandef, wdev->iftype); if (err < 0) return err; @@ -9300,6 +9295,16 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, if (!cfg80211_chandef_dfs_usable(wiphy, &chandef)) return -EINVAL; + if (nla_get_flag(info->attrs[NL80211_ATTR_RADAR_OFFCHAN])) + return cfg80211_start_offchan_radar_detection(rdev, wdev, + &chandef); + + if (netif_carrier_ok(dev)) + return -EBUSY; + + if (wdev->cac_started) + return -EBUSY; + /* CAC start is offloaded to HW and can't be started manually */ if (wiphy_ext_feature_isset(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD)) return -EOPNOTSUPP; diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index cc1efec4b27b..8672b3ef99e4 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1395,4 +1395,21 @@ rdev_set_fils_aad(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_radar_offchan(struct cfg80211_registered_device *rdev, + struct cfg80211_chan_def *chandef) +{ + struct wiphy *wiphy = &rdev->wiphy; + int ret; + + if (!rdev->ops->set_radar_offchan) + return -EOPNOTSUPP; + + trace_rdev_set_radar_offchan(wiphy, chandef); + ret = rdev->ops->set_radar_offchan(wiphy, chandef); + trace_rdev_return_int(wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index ad6c16a06bcb..0b27eaa14a18 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3674,6 +3674,25 @@ TRACE_EVENT(cfg80211_bss_color_notify, __entry->color_bitmap) ); +TRACE_EVENT(rdev_set_radar_offchan, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef), + + TP_ARGS(wiphy, chandef), + + TP_STRUCT__entry( + WIPHY_ENTRY + CHAN_DEF_ENTRY + ), + + TP_fast_assign( + WIPHY_ASSIGN; + CHAN_DEF_ASSIGN(chandef) + ), + + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT, + WIPHY_PR_ARG, CHAN_DEF_PR_ARG) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- cgit v1.2.3 From b88dbe38dca82425a273d126785866af39ba0770 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Tue, 16 Nov 2021 14:38:35 +0000 Subject: media: uapi: Add VP9 stateless decoder controls Add the VP9 stateless decoder controls plus the documentation that goes with it. Signed-off-by: Boris Brezillon Co-developed-by: Ezequiel Garcia Signed-off-by: Ezequiel Garcia Signed-off-by: Adrian Ratiu Signed-off-by: Andrzej Pietrasiewicz Co-developed-by: Daniel Almeida Signed-off-by: Daniel Almeida Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/biblio.rst | 10 + .../media/v4l/ext-ctrls-codec-stateless.rst | 573 +++++++++++++++++++++ .../userspace-api/media/v4l/pixfmt-compressed.rst | 15 + .../userspace-api/media/v4l/vidioc-g-ext-ctrls.rst | 8 + .../userspace-api/media/v4l/vidioc-queryctrl.rst | 12 + .../userspace-api/media/videodev2.h.rst.exceptions | 2 + drivers/media/v4l2-core/v4l2-ctrls-core.c | 180 +++++++ drivers/media/v4l2-core/v4l2-ctrls-defs.c | 8 + drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/media/v4l2-ctrls.h | 4 + include/uapi/linux/v4l2-controls.h | 284 ++++++++++ include/uapi/linux/videodev2.h | 6 + 12 files changed, 1103 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/media/v4l/biblio.rst b/Documentation/userspace-api/media/v4l/biblio.rst index 7b8e6738ff9e..9cd18c153d19 100644 --- a/Documentation/userspace-api/media/v4l/biblio.rst +++ b/Documentation/userspace-api/media/v4l/biblio.rst @@ -417,3 +417,13 @@ VP8 :title: RFC 6386: "VP8 Data Format and Decoding Guide" :author: J. Bankoski et al. + +.. _vp9: + +VP9 +=== + + +:title: VP9 Bitstream & Decoding Process Specification + +:author: Adrian Grange (Google), Peter de Rivaz (Argon Design), Jonathan Hunt (Argon Design) diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst index 72f5e85b4f34..cc080c4257d0 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst @@ -1458,3 +1458,576 @@ FWHT Flags .. raw:: latex \normalsize + +.. _v4l2-codec-stateless-vp9: + +``V4L2_CID_STATELESS_VP9_COMPRESSED_HDR (struct)`` + Stores VP9 probabilities updates as parsed from the current compressed frame + header. A value of zero in an array element means no update of the relevant + probability. Motion vector-related updates contain a new value or zero. All + other updates contain values translated with inv_map_table[] (see 6.3.5 in + :ref:`vp9`). + +.. c:type:: v4l2_ctrl_vp9_compressed_hdr + +.. tabularcolumns:: |p{1cm}|p{4.8cm}|p{11.4cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_vp9_compressed_hdr + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``tx_mode`` + - Specifies the TX mode. See :ref:`TX Mode ` for more details. + * - __u8 + - ``tx8[2][1]`` + - TX 8x8 probabilities delta. + * - __u8 + - ``tx16[2][2]`` + - TX 16x16 probabilities delta. + * - __u8 + - ``tx32[2][3]`` + - TX 32x32 probabilities delta. + * - __u8 + - ``coef[4][2][2][6][6][3]`` + - Coefficient probabilities delta. + * - __u8 + - ``skip[3]`` + - Skip probabilities delta. + * - __u8 + - ``inter_mode[7][3]`` + - Inter prediction mode probabilities delta. + * - __u8 + - ``interp_filter[4][2]`` + - Interpolation filter probabilities delta. + * - __u8 + - ``is_inter[4]`` + - Is inter-block probabilities delta. + * - __u8 + - ``comp_mode[5]`` + - Compound prediction mode probabilities delta. + * - __u8 + - ``single_ref[5][2]`` + - Single reference probabilities delta. + * - __u8 + - ``comp_ref[5]`` + - Compound reference probabilities delta. + * - __u8 + - ``y_mode[4][9]`` + - Y prediction mode probabilities delta. + * - __u8 + - ``uv_mode[10][9]`` + - UV prediction mode probabilities delta. + * - __u8 + - ``partition[16][3]`` + - Partition probabilities delta. + * - __u8 + - ``mv.joint[3]`` + - Motion vector joint probabilities delta. + * - __u8 + - ``mv.sign[2]`` + - Motion vector sign probabilities delta. + * - __u8 + - ``mv.classes[2][10]`` + - Motion vector class probabilities delta. + * - __u8 + - ``mv.class0_bit[2]`` + - Motion vector class0 bit probabilities delta. + * - __u8 + - ``mv.bits[2][10]`` + - Motion vector bits probabilities delta. + * - __u8 + - ``mv.class0_fr[2][2][3]`` + - Motion vector class0 fractional bit probabilities delta. + * - __u8 + - ``mv.fr[2][3]`` + - Motion vector fractional bit probabilities delta. + * - __u8 + - ``mv.class0_hp[2]`` + - Motion vector class0 high precision fractional bit probabilities delta. + * - __u8 + - ``mv.hp[2]`` + - Motion vector high precision fractional bit probabilities delta. + +.. _vp9_tx_mode: + +``TX Mode`` + +.. tabularcolumns:: |p{6.5cm}|p{0.5cm}|p{10.3cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_TX_MODE_ONLY_4X4`` + - 0 + - Transform size is 4x4. + * - ``V4L2_VP9_TX_MODE_ALLOW_8X8`` + - 1 + - Transform size can be up to 8x8. + * - ``V4L2_VP9_TX_MODE_ALLOW_16X16`` + - 2 + - Transform size can be up to 16x16. + * - ``V4L2_VP9_TX_MODE_ALLOW_32X32`` + - 3 + - transform size can be up to 32x32. + * - ``V4L2_VP9_TX_MODE_SELECT`` + - 4 + - Bitstream contains the transform size for each block. + +See section '7.3.1 Tx mode semantics' of the :ref:`vp9` specification for more details. + +``V4L2_CID_STATELESS_VP9_FRAME (struct)`` + Specifies the frame parameters for the associated VP9 frame decode request. + This includes the necessary parameters for configuring a stateless hardware + decoding pipeline for VP9. The bitstream parameters are defined according + to :ref:`vp9`. + +.. c:type:: v4l2_ctrl_vp9_frame + +.. raw:: latex + + \small + +.. tabularcolumns:: |p{4.7cm}|p{5.5cm}|p{7.1cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_vp9_frame + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - struct :c:type:`v4l2_vp9_loop_filter` + - ``lf`` + - Loop filter parameters. See struct :c:type:`v4l2_vp9_loop_filter` for more details. + * - struct :c:type:`v4l2_vp9_quantization` + - ``quant`` + - Quantization parameters. See :c:type:`v4l2_vp9_quantization` for more details. + * - struct :c:type:`v4l2_vp9_segmentation` + - ``seg`` + - Segmentation parameters. See :c:type:`v4l2_vp9_segmentation` for more details. + * - __u32 + - ``flags`` + - Combination of V4L2_VP9_FRAME_FLAG_* flags. See :ref:`Frame Flags`. + * - __u16 + - ``compressed_header_size`` + - Compressed header size in bytes. + * - __u16 + - ``uncompressed_header_size`` + - Uncompressed header size in bytes. + * - __u16 + - ``frame_width_minus_1`` + - Add 1 to get the frame width expressed in pixels. See section 7.2.3 in :ref:`vp9`. + * - __u16 + - ``frame_height_minus_1`` + - Add 1 to get the frame height expressed in pixels. See section 7.2.3 in :ref:`vp9`. + * - __u16 + - ``render_width_minus_1`` + - Add 1 to get the expected render width expressed in pixels. This is + not used during the decoding process but might be used by HW scalers to + prepare a frame that's ready for scanout. See section 7.2.4 in :ref:`vp9`. + * - __u16 + - render_height_minus_1 + - Add 1 to get the expected render height expressed in pixels. This is + not used during the decoding process but might be used by HW scalers to + prepare a frame that's ready for scanout. See section 7.2.4 in :ref:`vp9`. + * - __u64 + - ``last_frame_ts`` + - "last" reference buffer timestamp. + The timestamp refers to the ``timestamp`` field in + struct :c:type:`v4l2_buffer`. Use the :c:func:`v4l2_timeval_to_ns()` + function to convert the struct :c:type:`timeval` in struct + :c:type:`v4l2_buffer` to a __u64. + * - __u64 + - ``golden_frame_ts`` + - "golden" reference buffer timestamp. + The timestamp refers to the ``timestamp`` field in + struct :c:type:`v4l2_buffer`. Use the :c:func:`v4l2_timeval_to_ns()` + function to convert the struct :c:type:`timeval` in struct + :c:type:`v4l2_buffer` to a __u64. + * - __u64 + - ``alt_frame_ts`` + - "alt" reference buffer timestamp. + The timestamp refers to the ``timestamp`` field in + struct :c:type:`v4l2_buffer`. Use the :c:func:`v4l2_timeval_to_ns()` + function to convert the struct :c:type:`timeval` in struct + :c:type:`v4l2_buffer` to a __u64. + * - __u8 + - ``ref_frame_sign_bias`` + - a bitfield specifying whether the sign bias is set for a given + reference frame. See :ref:`Reference Frame Sign Bias` + for more details. + * - __u8 + - ``reset_frame_context`` + - specifies whether the frame context should be reset to default values. See + :ref:`Reset Frame Context` for more details. + * - __u8 + - ``frame_context_idx`` + - Frame context that should be used/updated. + * - __u8 + - ``profile`` + - VP9 profile. Can be 0, 1, 2 or 3. + * - __u8 + - ``bit_depth`` + - Component depth in bits. Can be 8, 10 or 12. Note that not all profiles + support 10 and/or 12 bits depths. + * - __u8 + - ``interpolation_filter`` + - Specifies the filter selection used for performing inter prediction. See + :ref:`Interpolation Filter` for more details. + * - __u8 + - ``tile_cols_log2`` + - Specifies the base 2 logarithm of the width of each tile (where the + width is measured in units of 8x8 blocks). Shall be less than or equal + to 6. + * - __u8 + - ``tile_rows_log2`` + - Specifies the base 2 logarithm of the height of each tile (where the + height is measured in units of 8x8 blocks). + * - __u8 + - ``reference_mode`` + - Specifies the type of inter prediction to be used. See + :ref:`Reference Mode` for more details. + * - __u8 + - ``reserved[7]`` + - Applications and drivers must set this to zero. + +.. raw:: latex + + \normalsize + +.. _vp9_frame_flags: + +``Frame Flags`` + +.. tabularcolumns:: |p{10.0cm}|p{1.2cm}|p{6.1cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_FRAME_FLAG_KEY_FRAME`` + - 0x001 + - The frame is a key frame. + * - ``V4L2_VP9_FRAME_FLAG_SHOW_FRAME`` + - 0x002 + - The frame should be displayed. + * - ``V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT`` + - 0x004 + - The decoding should be error resilient. + * - ``V4L2_VP9_FRAME_FLAG_INTRA_ONLY`` + - 0x008 + - The frame does not reference other frames. + * - ``V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV`` + - 0x010 + - The frame can use high precision motion vectors. + * - ``V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX`` + - 0x020 + - Frame context should be updated after decoding. + * - ``V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE`` + - 0x040 + - Parallel decoding is used. + * - ``V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING`` + - 0x080 + - Vertical subsampling is enabled. + * - ``V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING`` + - 0x100 + - Horizontal subsampling is enabled. + * - ``V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING`` + - 0x200 + - The full UV range is used. + +.. _vp9_ref_frame_sign_bias: + +``Reference Frame Sign Bias`` + +.. tabularcolumns:: |p{7.0cm}|p{1.2cm}|p{9.1cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_SIGN_BIAS_LAST`` + - 0x1 + - Sign bias is set for the last reference frame. + * - ``V4L2_VP9_SIGN_BIAS_GOLDEN`` + - 0x2 + - Sign bias is set for the golden reference frame. + * - ``V4L2_VP9_SIGN_BIAS_ALT`` + - 0x2 + - Sign bias is set for the alt reference frame. + +.. _vp9_reset_frame_context: + +``Reset Frame Context`` + +.. tabularcolumns:: |p{7.0cm}|p{1.2cm}|p{9.1cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_RESET_FRAME_CTX_NONE`` + - 0 + - Do not reset any frame context. + * - ``V4L2_VP9_RESET_FRAME_CTX_SPEC`` + - 1 + - Reset the frame context pointed to by + :c:type:`v4l2_ctrl_vp9_frame`.frame_context_idx. + * - ``V4L2_VP9_RESET_FRAME_CTX_ALL`` + - 2 + - Reset all frame contexts. + +See section '7.2 Uncompressed header semantics' of the :ref:`vp9` specification +for more details. + +.. _vp9_interpolation_filter: + +``Interpolation Filter`` + +.. tabularcolumns:: |p{9.0cm}|p{1.2cm}|p{7.1cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_INTERP_FILTER_EIGHTTAP`` + - 0 + - Eight tap filter. + * - ``V4L2_VP9_INTERP_FILTER_EIGHTTAP_SMOOTH`` + - 1 + - Eight tap smooth filter. + * - ``V4L2_VP9_INTERP_FILTER_EIGHTTAP_SHARP`` + - 2 + - Eeight tap sharp filter. + * - ``V4L2_VP9_INTERP_FILTER_BILINEAR`` + - 3 + - Bilinear filter. + * - ``V4L2_VP9_INTERP_FILTER_SWITCHABLE`` + - 4 + - Filter selection is signaled at the block level. + +See section '7.2.7 Interpolation filter semantics' of the :ref:`vp9` specification +for more details. + +.. _vp9_reference_mode: + +``Reference Mode`` + +.. tabularcolumns:: |p{9.6cm}|p{0.5cm}|p{7.2cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_REFERENCE_MODE_SINGLE_REFERENCE`` + - 0 + - Indicates that all the inter blocks use only a single reference frame + to generate motion compensated prediction. + * - ``V4L2_VP9_REFERENCE_MODE_COMPOUND_REFERENCE`` + - 1 + - Requires all the inter blocks to use compound mode. Single reference + frame prediction is not allowed. + * - ``V4L2_VP9_REFERENCE_MODE_SELECT`` + - 2 + - Allows each individual inter block to select between single and + compound prediction modes. + +See section '7.3.6 Frame reference mode semantics' of the :ref:`vp9` specification for more details. + +.. c:type:: v4l2_vp9_segmentation + +Encodes the quantization parameters. See section '7.2.10 Segmentation +params syntax' of the :ref:`vp9` specification for more details. + +.. tabularcolumns:: |p{0.8cm}|p{5cm}|p{11.4cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_vp9_segmentation + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``feature_data[8][4]`` + - Data attached to each feature. Data entry is only valid if the feature + is enabled. The array shall be indexed with segment number as the first dimension + (0..7) and one of V4L2_VP9_SEG_* as the second dimension. + See :ref:`Segment Feature IDs`. + * - __u8 + - ``feature_enabled[8]`` + - Bitmask defining which features are enabled in each segment. The value for each + segment is a combination of V4L2_VP9_SEGMENT_FEATURE_ENABLED(id) values where id is + one of V4L2_VP9_SEG_*. See :ref:`Segment Feature IDs`. + * - __u8 + - ``tree_probs[7]`` + - Specifies the probability values to be used when decoding a Segment-ID. + See '5.15. Segmentation map' section of :ref:`vp9` for more details. + * - __u8 + - ``pred_probs[3]`` + - Specifies the probability values to be used when decoding a + Predicted-Segment-ID. See '6.4.14. Get segment id syntax' + section of :ref:`vp9` for more details. + * - __u8 + - ``flags`` + - Combination of V4L2_VP9_SEGMENTATION_FLAG_* flags. See + :ref:`Segmentation Flags`. + * - __u8 + - ``reserved[5]`` + - Applications and drivers must set this to zero. + +.. _vp9_segment_feature: + +``Segment feature IDs`` + +.. tabularcolumns:: |p{6.0cm}|p{1cm}|p{10.3cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_SEG_LVL_ALT_Q`` + - 0 + - Quantizer segment feature. + * - ``V4L2_VP9_SEG_LVL_ALT_L`` + - 1 + - Loop filter segment feature. + * - ``V4L2_VP9_SEG_LVL_REF_FRAME`` + - 2 + - Reference frame segment feature. + * - ``V4L2_VP9_SEG_LVL_SKIP`` + - 3 + - Skip segment feature. + * - ``V4L2_VP9_SEG_LVL_MAX`` + - 4 + - Number of segment features. + +.. _vp9_segmentation_flags: + +``Segmentation Flags`` + +.. tabularcolumns:: |p{10.6cm}|p{0.8cm}|p{5.9cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_SEGMENTATION_FLAG_ENABLED`` + - 0x01 + - Indicates that this frame makes use of the segmentation tool. + * - ``V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP`` + - 0x02 + - Indicates that the segmentation map should be updated during the + decoding of this frame. + * - ``V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE`` + - 0x04 + - Indicates that the updates to the segmentation map are coded + relative to the existing segmentation map. + * - ``V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA`` + - 0x08 + - Indicates that new parameters are about to be specified for each + segment. + * - ``V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE`` + - 0x10 + - Indicates that the segmentation parameters represent the actual values + to be used. + +.. c:type:: v4l2_vp9_quantization + +Encodes the quantization parameters. See section '7.2.9 Quantization params +syntax' of the VP9 specification for more details. + +.. tabularcolumns:: |p{0.8cm}|p{4cm}|p{12.4cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_vp9_quantization + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``base_q_idx`` + - Indicates the base frame qindex. + * - __s8 + - ``delta_q_y_dc`` + - Indicates the Y DC quantizer relative to base_q_idx. + * - __s8 + - ``delta_q_uv_dc`` + - Indicates the UV DC quantizer relative to base_q_idx. + * - __s8 + - ``delta_q_uv_ac`` + - Indicates the UV AC quantizer relative to base_q_idx. + * - __u8 + - ``reserved[4]`` + - Applications and drivers must set this to zero. + +.. c:type:: v4l2_vp9_loop_filter + +This structure contains all loop filter related parameters. See sections +'7.2.8 Loop filter semantics' of the :ref:`vp9` specification for more details. + +.. tabularcolumns:: |p{0.8cm}|p{4cm}|p{12.4cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_vp9_loop_filter + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __s8 + - ``ref_deltas[4]`` + - Contains the adjustment needed for the filter level based on the chosen + reference frame. + * - __s8 + - ``mode_deltas[2]`` + - Contains the adjustment needed for the filter level based on the chosen + mode. + * - __u8 + - ``level`` + - Indicates the loop filter strength. + * - __u8 + - ``sharpness`` + - Indicates the sharpness level. + * - __u8 + - ``flags`` + - Combination of V4L2_VP9_LOOP_FILTER_FLAG_* flags. + See :ref:`Loop Filter Flags `. + * - __u8 + - ``reserved[7]`` + - Applications and drivers must set this to zero. + + +.. _vp9_loop_filter_flags: + +``Loop Filter Flags`` + +.. tabularcolumns:: |p{9.6cm}|p{0.5cm}|p{7.2cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED`` + - 0x1 + - When set, the filter level depends on the mode and reference frame used + to predict a block. + * - ``V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE`` + - 0x2 + - When set, the bitstream contains additional syntax elements that + specify which mode and reference frame deltas are to be updated. diff --git a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst index 0ede39907ee2..967fc803ef94 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst @@ -172,6 +172,21 @@ Compressed Formats - VP9 compressed video frame. The encoder generates one compressed frame per buffer, and the decoder requires one compressed frame per buffer. + * .. _V4L2-PIX-FMT-VP9-FRAME: + + - ``V4L2_PIX_FMT_VP9_FRAME`` + - 'VP9F' + - VP9 parsed frame, including the frame header, as extracted from the container. + This format is adapted for stateless video decoders that implement a + VP9 pipeline with the :ref:`stateless_decoder`. + Metadata associated with the frame to decode is required to be passed + through the ``V4L2_CID_STATELESS_VP9_FRAME`` and + the ``V4L2_CID_STATELESS_VP9_COMPRESSED_HDR`` controls. + See the :ref:`associated Codec Control IDs `. + Exactly one output and one capture buffer must be provided for use with + this pixel format. The output buffer must contain the appropriate number + of macroblocks to decode a full corresponding frame to the matching + capture buffer. * .. _V4L2-PIX-FMT-HEVC: - ``V4L2_PIX_FMT_HEVC`` diff --git a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst index fdde0ae6d521..29971a45a2d4 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst @@ -233,6 +233,14 @@ still cause this situation. - ``p_mpeg2_quantisation`` - A pointer to a struct :c:type:`v4l2_ctrl_mpeg2_quantisation`. Valid if this control is of type ``V4L2_CTRL_TYPE_MPEG2_QUANTISATION``. + * - struct :c:type:`v4l2_ctrl_vp9_compressed_hdr` * + - ``p_vp9_compressed_hdr_probs`` + - A pointer to a struct :c:type:`v4l2_ctrl_vp9_compressed_hdr`. Valid if this + control is of type ``V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR``. + * - struct :c:type:`v4l2_ctrl_vp9_frame` * + - ``p_vp9_frame`` + - A pointer to a struct :c:type:`v4l2_ctrl_vp9_frame`. Valid if this + control is of type ``V4L2_CTRL_TYPE_VP9_FRAME``. * - struct :c:type:`v4l2_ctrl_hdr10_cll_info` * - ``p_hdr10_cll`` - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_cll_info`. Valid if this control is diff --git a/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst b/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst index 2f491c17dd5d..88f630252d98 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst @@ -513,6 +513,18 @@ See also the examples in :ref:`control`. - n/a - A struct :c:type:`v4l2_ctrl_hevc_decode_params`, containing HEVC decoding parameters for stateless video decoders. + * - ``V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR`` + - n/a + - n/a + - n/a + - A struct :c:type:`v4l2_ctrl_vp9_compressed_hdr`, containing VP9 + probabilities updates for stateless video decoders. + * - ``V4L2_CTRL_TYPE_VP9_FRAME`` + - n/a + - n/a + - n/a + - A struct :c:type:`v4l2_ctrl_vp9_frame`, containing VP9 + frame decode parameters for stateless video decoders. .. raw:: latex diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index eb0b1cd37abd..9cbb7a0c354a 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -149,6 +149,8 @@ replace symbol V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_AREA :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_FWHT_PARAMS :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_VP8_FRAME :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_VP9_FRAME :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_HDR10_CLL_INFO :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY :c:type:`v4l2_ctrl_type` diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 70adfc1b9c81..54abe5245dcc 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -283,6 +283,12 @@ static void std_log(const struct v4l2_ctrl *ctrl) case V4L2_CTRL_TYPE_MPEG2_PICTURE: pr_cont("MPEG2_PICTURE"); break; + case V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR: + pr_cont("VP9_COMPRESSED_HDR"); + break; + case V4L2_CTRL_TYPE_VP9_FRAME: + pr_cont("VP9_FRAME"); + break; default: pr_cont("unknown type %d", ctrl->type); break; @@ -317,6 +323,168 @@ static void std_log(const struct v4l2_ctrl *ctrl) #define zero_reserved(s) \ memset(&(s).reserved, 0, sizeof((s).reserved)) +static int +validate_vp9_lf_params(struct v4l2_vp9_loop_filter *lf) +{ + unsigned int i; + + if (lf->flags & ~(V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED | + V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE)) + return -EINVAL; + + /* That all values are in the accepted range. */ + if (lf->level > GENMASK(5, 0)) + return -EINVAL; + + if (lf->sharpness > GENMASK(2, 0)) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(lf->ref_deltas); i++) + if (lf->ref_deltas[i] < -63 || lf->ref_deltas[i] > 63) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(lf->mode_deltas); i++) + if (lf->mode_deltas[i] < -63 || lf->mode_deltas[i] > 63) + return -EINVAL; + + zero_reserved(*lf); + return 0; +} + +static int +validate_vp9_quant_params(struct v4l2_vp9_quantization *quant) +{ + if (quant->delta_q_y_dc < -15 || quant->delta_q_y_dc > 15 || + quant->delta_q_uv_dc < -15 || quant->delta_q_uv_dc > 15 || + quant->delta_q_uv_ac < -15 || quant->delta_q_uv_ac > 15) + return -EINVAL; + + zero_reserved(*quant); + return 0; +} + +static int +validate_vp9_seg_params(struct v4l2_vp9_segmentation *seg) +{ + unsigned int i, j; + + if (seg->flags & ~(V4L2_VP9_SEGMENTATION_FLAG_ENABLED | + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP | + V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE | + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA | + V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE)) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(seg->feature_enabled); i++) { + if (seg->feature_enabled[i] & + ~V4L2_VP9_SEGMENT_FEATURE_ENABLED_MASK) + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(seg->feature_data); i++) { + const int range[] = { 255, 63, 3, 0 }; + + for (j = 0; j < ARRAY_SIZE(seg->feature_data[j]); j++) { + if (seg->feature_data[i][j] < -range[j] || + seg->feature_data[i][j] > range[j]) + return -EINVAL; + } + } + + zero_reserved(*seg); + return 0; +} + +static int +validate_vp9_compressed_hdr(struct v4l2_ctrl_vp9_compressed_hdr *hdr) +{ + if (hdr->tx_mode > V4L2_VP9_TX_MODE_SELECT) + return -EINVAL; + + return 0; +} + +static int +validate_vp9_frame(struct v4l2_ctrl_vp9_frame *frame) +{ + int ret; + + /* Make sure we're not passed invalid flags. */ + if (frame->flags & ~(V4L2_VP9_FRAME_FLAG_KEY_FRAME | + V4L2_VP9_FRAME_FLAG_SHOW_FRAME | + V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT | + V4L2_VP9_FRAME_FLAG_INTRA_ONLY | + V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV | + V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX | + V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE | + V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING | + V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING | + V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING)) + return -EINVAL; + + if (frame->flags & V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT && + frame->flags & V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX) + return -EINVAL; + + if (frame->profile > V4L2_VP9_PROFILE_MAX) + return -EINVAL; + + if (frame->reset_frame_context > V4L2_VP9_RESET_FRAME_CTX_ALL) + return -EINVAL; + + if (frame->frame_context_idx >= V4L2_VP9_NUM_FRAME_CTX) + return -EINVAL; + + /* + * Profiles 0 and 1 only support 8-bit depth, profiles 2 and 3 only 10 + * and 12 bit depths. + */ + if ((frame->profile < 2 && frame->bit_depth != 8) || + (frame->profile >= 2 && + (frame->bit_depth != 10 && frame->bit_depth != 12))) + return -EINVAL; + + /* Profile 0 and 2 only accept YUV 4:2:0. */ + if ((frame->profile == 0 || frame->profile == 2) && + (!(frame->flags & V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING) || + !(frame->flags & V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING))) + return -EINVAL; + + /* Profile 1 and 3 only accept YUV 4:2:2, 4:4:0 and 4:4:4. */ + if ((frame->profile == 1 || frame->profile == 3) && + ((frame->flags & V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING) && + (frame->flags & V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING))) + return -EINVAL; + + if (frame->interpolation_filter > V4L2_VP9_INTERP_FILTER_SWITCHABLE) + return -EINVAL; + + /* + * According to the spec, tile_cols_log2 shall be less than or equal + * to 6. + */ + if (frame->tile_cols_log2 > 6) + return -EINVAL; + + if (frame->reference_mode > V4L2_VP9_REFERENCE_MODE_SELECT) + return -EINVAL; + + ret = validate_vp9_lf_params(&frame->lf); + if (ret) + return ret; + + ret = validate_vp9_quant_params(&frame->quant); + if (ret) + return ret; + + ret = validate_vp9_seg_params(&frame->seg); + if (ret) + return ret; + + zero_reserved(*frame); + return 0; +} + /* * Compound controls validation requires setting unused fields/flags to zero * in order to properly detect unchanged controls with std_equal's memcmp. @@ -690,6 +858,12 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, case V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX: break; + case V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR: + return validate_vp9_compressed_hdr(p); + + case V4L2_CTRL_TYPE_VP9_FRAME: + return validate_vp9_frame(p); + case V4L2_CTRL_TYPE_AREA: area = p; if (!area->width || !area->height) @@ -1255,6 +1429,12 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, case V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY: elem_size = sizeof(struct v4l2_ctrl_hdr10_mastering_display); break; + case V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR: + elem_size = sizeof(struct v4l2_ctrl_vp9_compressed_hdr); + break; + case V4L2_CTRL_TYPE_VP9_FRAME: + elem_size = sizeof(struct v4l2_ctrl_vp9_frame); + break; case V4L2_CTRL_TYPE_AREA: elem_size = sizeof(struct v4l2_area); break; diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 431f7ec17557..54ca4e6b820b 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -1178,6 +1178,8 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_STATELESS_MPEG2_SEQUENCE: return "MPEG-2 Sequence Header"; case V4L2_CID_STATELESS_MPEG2_PICTURE: return "MPEG-2 Picture Header"; case V4L2_CID_STATELESS_MPEG2_QUANTISATION: return "MPEG-2 Quantisation Matrices"; + case V4L2_CID_STATELESS_VP9_COMPRESSED_HDR: return "VP9 Probabilities Updates"; + case V4L2_CID_STATELESS_VP9_FRAME: return "VP9 Frame Decode Parameters"; /* Colorimetry controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ @@ -1506,6 +1508,12 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS: *type = V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS; break; + case V4L2_CID_STATELESS_VP9_COMPRESSED_HDR: + *type = V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR; + break; + case V4L2_CID_STATELESS_VP9_FRAME: + *type = V4L2_CTRL_TYPE_VP9_FRAME; + break; case V4L2_CID_UNIT_CELL_SIZE: *type = V4L2_CTRL_TYPE_AREA; *flags |= V4L2_CTRL_FLAG_READ_ONLY; diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 69b74d0e8a90..9ac557b8e146 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1413,6 +1413,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_VP8: descr = "VP8"; break; case V4L2_PIX_FMT_VP8_FRAME: descr = "VP8 Frame"; break; case V4L2_PIX_FMT_VP9: descr = "VP9"; break; + case V4L2_PIX_FMT_VP9_FRAME: descr = "VP9 Frame"; break; case V4L2_PIX_FMT_HEVC: descr = "HEVC"; break; /* aka H.265 */ case V4L2_PIX_FMT_HEVC_SLICE: descr = "HEVC Parsed Slice Data"; break; case V4L2_PIX_FMT_FWHT: descr = "FWHT"; break; /* used in vicodec */ diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 575b59fbac77..b3ce438f1329 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -50,6 +50,8 @@ struct video_device; * @p_h264_decode_params: Pointer to a struct v4l2_ctrl_h264_decode_params. * @p_h264_pred_weights: Pointer to a struct v4l2_ctrl_h264_pred_weights. * @p_vp8_frame: Pointer to a VP8 frame params structure. + * @p_vp9_compressed_hdr_probs: Pointer to a VP9 frame compressed header probs structure. + * @p_vp9_frame: Pointer to a VP9 frame params structure. * @p_hevc_sps: Pointer to an HEVC sequence parameter set structure. * @p_hevc_pps: Pointer to an HEVC picture parameter set structure. * @p_hevc_slice_params: Pointer to an HEVC slice parameters structure. @@ -80,6 +82,8 @@ union v4l2_ctrl_ptr { struct v4l2_ctrl_hevc_sps *p_hevc_sps; struct v4l2_ctrl_hevc_pps *p_hevc_pps; struct v4l2_ctrl_hevc_slice_params *p_hevc_slice_params; + struct v4l2_ctrl_vp9_compressed_hdr *p_vp9_compressed_hdr_probs; + struct v4l2_ctrl_vp9_frame *p_vp9_frame; struct v4l2_ctrl_hdr10_cll_info *p_hdr10_cll; struct v4l2_ctrl_hdr10_mastering_display *p_hdr10_mastering; struct v4l2_area *p_area; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index c9eea93a43a9..c8e0f84d204d 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -2018,6 +2018,290 @@ struct v4l2_ctrl_hdr10_mastering_display { __u32 min_display_mastering_luminance; }; +/* Stateless VP9 controls */ + +#define V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED 0x1 +#define V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE 0x2 + +/** + * struct v4l2_vp9_loop_filter - VP9 loop filter parameters + * + * @ref_deltas: contains the adjustment needed for the filter level based on the + * chosen reference frame. If this syntax element is not present in the bitstream, + * users should pass its last value. + * @mode_deltas: contains the adjustment needed for the filter level based on the + * chosen mode. If this syntax element is not present in the bitstream, users should + * pass its last value. + * @level: indicates the loop filter strength. + * @sharpness: indicates the sharpness level. + * @flags: combination of V4L2_VP9_LOOP_FILTER_FLAG_{} flags. + * @reserved: padding field. Should be zeroed by applications. + * + * This structure contains all loop filter related parameters. See sections + * '7.2.8 Loop filter semantics' of the VP9 specification for more details. + */ +struct v4l2_vp9_loop_filter { + __s8 ref_deltas[4]; + __s8 mode_deltas[2]; + __u8 level; + __u8 sharpness; + __u8 flags; + __u8 reserved[7]; +}; + +/** + * struct v4l2_vp9_quantization - VP9 quantization parameters + * + * @base_q_idx: indicates the base frame qindex. + * @delta_q_y_dc: indicates the Y DC quantizer relative to base_q_idx. + * @delta_q_uv_dc: indicates the UV DC quantizer relative to base_q_idx. + * @delta_q_uv_ac: indicates the UV AC quantizer relative to base_q_idx. + * @reserved: padding field. Should be zeroed by applications. + * + * Encodes the quantization parameters. See section '7.2.9 Quantization params + * syntax' of the VP9 specification for more details. + */ +struct v4l2_vp9_quantization { + __u8 base_q_idx; + __s8 delta_q_y_dc; + __s8 delta_q_uv_dc; + __s8 delta_q_uv_ac; + __u8 reserved[4]; +}; + +#define V4L2_VP9_SEGMENTATION_FLAG_ENABLED 0x01 +#define V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP 0x02 +#define V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE 0x04 +#define V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA 0x08 +#define V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE 0x10 + +#define V4L2_VP9_SEG_LVL_ALT_Q 0 +#define V4L2_VP9_SEG_LVL_ALT_L 1 +#define V4L2_VP9_SEG_LVL_REF_FRAME 2 +#define V4L2_VP9_SEG_LVL_SKIP 3 +#define V4L2_VP9_SEG_LVL_MAX 4 + +#define V4L2_VP9_SEGMENT_FEATURE_ENABLED(id) (1 << (id)) +#define V4L2_VP9_SEGMENT_FEATURE_ENABLED_MASK 0xf + +/** + * struct v4l2_vp9_segmentation - VP9 segmentation parameters + * + * @feature_data: data attached to each feature. Data entry is only valid if + * the feature is enabled. The array shall be indexed with segment number as + * the first dimension (0..7) and one of V4L2_VP9_SEG_{} as the second dimension. + * @feature_enabled: bitmask defining which features are enabled in each segment. + * The value for each segment is a combination of V4L2_VP9_SEGMENT_FEATURE_ENABLED(id) + * values where id is one of V4L2_VP9_SEG_LVL_{}. + * @tree_probs: specifies the probability values to be used when decoding a + * Segment-ID. See '5.15. Segmentation map' section of the VP9 specification + * for more details. + * @pred_probs: specifies the probability values to be used when decoding a + * Predicted-Segment-ID. See '6.4.14. Get segment id syntax' section of :ref:`vp9` + * for more details. + * @flags: combination of V4L2_VP9_SEGMENTATION_FLAG_{} flags. + * @reserved: padding field. Should be zeroed by applications. + * + * Encodes the quantization parameters. See section '7.2.10 Segmentation params syntax' of + * the VP9 specification for more details. + */ +struct v4l2_vp9_segmentation { + __s16 feature_data[8][4]; + __u8 feature_enabled[8]; + __u8 tree_probs[7]; + __u8 pred_probs[3]; + __u8 flags; + __u8 reserved[5]; +}; + +#define V4L2_VP9_FRAME_FLAG_KEY_FRAME 0x001 +#define V4L2_VP9_FRAME_FLAG_SHOW_FRAME 0x002 +#define V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT 0x004 +#define V4L2_VP9_FRAME_FLAG_INTRA_ONLY 0x008 +#define V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV 0x010 +#define V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX 0x020 +#define V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE 0x040 +#define V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING 0x080 +#define V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING 0x100 +#define V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING 0x200 + +#define V4L2_VP9_SIGN_BIAS_LAST 0x1 +#define V4L2_VP9_SIGN_BIAS_GOLDEN 0x2 +#define V4L2_VP9_SIGN_BIAS_ALT 0x4 + +#define V4L2_VP9_RESET_FRAME_CTX_NONE 0 +#define V4L2_VP9_RESET_FRAME_CTX_SPEC 1 +#define V4L2_VP9_RESET_FRAME_CTX_ALL 2 + +#define V4L2_VP9_INTERP_FILTER_EIGHTTAP 0 +#define V4L2_VP9_INTERP_FILTER_EIGHTTAP_SMOOTH 1 +#define V4L2_VP9_INTERP_FILTER_EIGHTTAP_SHARP 2 +#define V4L2_VP9_INTERP_FILTER_BILINEAR 3 +#define V4L2_VP9_INTERP_FILTER_SWITCHABLE 4 + +#define V4L2_VP9_REFERENCE_MODE_SINGLE_REFERENCE 0 +#define V4L2_VP9_REFERENCE_MODE_COMPOUND_REFERENCE 1 +#define V4L2_VP9_REFERENCE_MODE_SELECT 2 + +#define V4L2_VP9_PROFILE_MAX 3 + +#define V4L2_CID_STATELESS_VP9_FRAME (V4L2_CID_CODEC_STATELESS_BASE + 300) +/** + * struct v4l2_ctrl_vp9_frame - VP9 frame decoding control + * + * @lf: loop filter parameters. See &v4l2_vp9_loop_filter for more details. + * @quant: quantization parameters. See &v4l2_vp9_quantization for more details. + * @seg: segmentation parameters. See &v4l2_vp9_segmentation for more details. + * @flags: combination of V4L2_VP9_FRAME_FLAG_{} flags. + * @compressed_header_size: compressed header size in bytes. + * @uncompressed_header_size: uncompressed header size in bytes. + * @frame_width_minus_1: add 1 to it and you'll get the frame width expressed in pixels. + * @frame_height_minus_1: add 1 to it and you'll get the frame height expressed in pixels. + * @render_width_minus_1: add 1 to it and you'll get the expected render width expressed in + * pixels. This is not used during the decoding process but might be used by HW scalers + * to prepare a frame that's ready for scanout. + * @render_height_minus_1: add 1 to it and you'll get the expected render height expressed in + * pixels. This is not used during the decoding process but might be used by HW scalers + * to prepare a frame that's ready for scanout. + * @last_frame_ts: "last" reference buffer timestamp. + * The timestamp refers to the timestamp field in struct v4l2_buffer. + * Use v4l2_timeval_to_ns() to convert the struct timeval to a __u64. + * @golden_frame_ts: "golden" reference buffer timestamp. + * The timestamp refers to the timestamp field in struct v4l2_buffer. + * Use v4l2_timeval_to_ns() to convert the struct timeval to a __u64. + * @alt_frame_ts: "alt" reference buffer timestamp. + * The timestamp refers to the timestamp field in struct v4l2_buffer. + * Use v4l2_timeval_to_ns() to convert the struct timeval to a __u64. + * @ref_frame_sign_bias: a bitfield specifying whether the sign bias is set for a given + * reference frame. Either of V4L2_VP9_SIGN_BIAS_{}. + * @reset_frame_context: specifies whether the frame context should be reset to default values. + * Either of V4L2_VP9_RESET_FRAME_CTX_{}. + * @frame_context_idx: frame context that should be used/updated. + * @profile: VP9 profile. Can be 0, 1, 2 or 3. + * @bit_depth: bits per components. Can be 8, 10 or 12. Note that not all profiles support + * 10 and/or 12 bits depths. + * @interpolation_filter: specifies the filter selection used for performing inter prediction. + * Set to one of V4L2_VP9_INTERP_FILTER_{}. + * @tile_cols_log2: specifies the base 2 logarithm of the width of each tile (where the width + * is measured in units of 8x8 blocks). Shall be less than or equal to 6. + * @tile_rows_log2: specifies the base 2 logarithm of the height of each tile (where the height + * is measured in units of 8x8 blocks). + * @reference_mode: specifies the type of inter prediction to be used. + * Set to one of V4L2_VP9_REFERENCE_MODE_{}. + * @reserved: padding field. Should be zeroed by applications. + */ +struct v4l2_ctrl_vp9_frame { + struct v4l2_vp9_loop_filter lf; + struct v4l2_vp9_quantization quant; + struct v4l2_vp9_segmentation seg; + __u32 flags; + __u16 compressed_header_size; + __u16 uncompressed_header_size; + __u16 frame_width_minus_1; + __u16 frame_height_minus_1; + __u16 render_width_minus_1; + __u16 render_height_minus_1; + __u64 last_frame_ts; + __u64 golden_frame_ts; + __u64 alt_frame_ts; + __u8 ref_frame_sign_bias; + __u8 reset_frame_context; + __u8 frame_context_idx; + __u8 profile; + __u8 bit_depth; + __u8 interpolation_filter; + __u8 tile_cols_log2; + __u8 tile_rows_log2; + __u8 reference_mode; + __u8 reserved[7]; +}; + +#define V4L2_VP9_NUM_FRAME_CTX 4 + +/** + * struct v4l2_vp9_mv_probs - VP9 Motion vector probability updates + * @joint: motion vector joint probability updates. + * @sign: motion vector sign probability updates. + * @classes: motion vector class probability updates. + * @class0_bit: motion vector class0 bit probability updates. + * @bits: motion vector bits probability updates. + * @class0_fr: motion vector class0 fractional bit probability updates. + * @fr: motion vector fractional bit probability updates. + * @class0_hp: motion vector class0 high precision fractional bit probability updates. + * @hp: motion vector high precision fractional bit probability updates. + * + * This structure contains new values of motion vector probabilities. + * A value of zero in an array element means there is no update of the relevant probability. + * See `struct v4l2_vp9_prob_updates` for details. + */ +struct v4l2_vp9_mv_probs { + __u8 joint[3]; + __u8 sign[2]; + __u8 classes[2][10]; + __u8 class0_bit[2]; + __u8 bits[2][10]; + __u8 class0_fr[2][2][3]; + __u8 fr[2][3]; + __u8 class0_hp[2]; + __u8 hp[2]; +}; + +#define V4L2_CID_STATELESS_VP9_COMPRESSED_HDR (V4L2_CID_CODEC_STATELESS_BASE + 301) + +#define V4L2_VP9_TX_MODE_ONLY_4X4 0 +#define V4L2_VP9_TX_MODE_ALLOW_8X8 1 +#define V4L2_VP9_TX_MODE_ALLOW_16X16 2 +#define V4L2_VP9_TX_MODE_ALLOW_32X32 3 +#define V4L2_VP9_TX_MODE_SELECT 4 + +/** + * struct v4l2_ctrl_vp9_compressed_hdr - VP9 probability updates control + * @tx_mode: specifies the TX mode. Set to one of V4L2_VP9_TX_MODE_{}. + * @tx8: TX 8x8 probability updates. + * @tx16: TX 16x16 probability updates. + * @tx32: TX 32x32 probability updates. + * @coef: coefficient probability updates. + * @skip: skip probability updates. + * @inter_mode: inter mode probability updates. + * @interp_filter: interpolation filter probability updates. + * @is_inter: is inter-block probability updates. + * @comp_mode: compound prediction mode probability updates. + * @single_ref: single ref probability updates. + * @comp_ref: compound ref probability updates. + * @y_mode: Y prediction mode probability updates. + * @uv_mode: UV prediction mode probability updates. + * @partition: partition probability updates. + * @mv: motion vector probability updates. + * + * This structure holds the probabilities update as parsed in the compressed + * header (Spec 6.3). These values represent the value of probability update after + * being translated with inv_map_table[] (see 6.3.5). A value of zero in an array element + * means that there is no update of the relevant probability. + * + * This control is optional and needs to be used when dealing with the hardware which is + * not capable of parsing the compressed header itself. Only drivers which need it will + * implement it. + */ +struct v4l2_ctrl_vp9_compressed_hdr { + __u8 tx_mode; + __u8 tx8[2][1]; + __u8 tx16[2][2]; + __u8 tx32[2][3]; + __u8 coef[4][2][2][6][6][3]; + __u8 skip[3]; + __u8 inter_mode[7][3]; + __u8 interp_filter[4][2]; + __u8 is_inter[4]; + __u8 comp_mode[5]; + __u8 single_ref[5][2]; + __u8 comp_ref[5]; + __u8 y_mode[4][9]; + __u8 uv_mode[10][9]; + __u8 partition[16][3]; + + struct v4l2_vp9_mv_probs mv; +}; + /* MPEG-compression definitions kept for backwards compatibility */ #ifndef __KERNEL__ #define V4L2_CTRL_CLASS_MPEG V4L2_CTRL_CLASS_CODEC diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index f118fe7a9f58..df8b9c486ba1 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -703,6 +703,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_VP8 v4l2_fourcc('V', 'P', '8', '0') /* VP8 */ #define V4L2_PIX_FMT_VP8_FRAME v4l2_fourcc('V', 'P', '8', 'F') /* VP8 parsed frame */ #define V4L2_PIX_FMT_VP9 v4l2_fourcc('V', 'P', '9', '0') /* VP9 */ +#define V4L2_PIX_FMT_VP9_FRAME v4l2_fourcc('V', 'P', '9', 'F') /* VP9 parsed frame */ #define V4L2_PIX_FMT_HEVC v4l2_fourcc('H', 'E', 'V', 'C') /* HEVC aka H.265 */ #define V4L2_PIX_FMT_FWHT v4l2_fourcc('F', 'W', 'H', 'T') /* Fast Walsh Hadamard Transform (vicodec) */ #define V4L2_PIX_FMT_FWHT_STATELESS v4l2_fourcc('S', 'F', 'W', 'H') /* Stateless FWHT (vicodec) */ @@ -1759,6 +1760,8 @@ struct v4l2_ext_control { struct v4l2_ctrl_mpeg2_sequence __user *p_mpeg2_sequence; struct v4l2_ctrl_mpeg2_picture __user *p_mpeg2_picture; struct v4l2_ctrl_mpeg2_quantisation __user *p_mpeg2_quantisation; + struct v4l2_ctrl_vp9_compressed_hdr __user *p_vp9_compressed_hdr_probs; + struct v4l2_ctrl_vp9_frame __user *p_vp9_frame; void __user *ptr; }; } __attribute__ ((packed)); @@ -1823,6 +1826,9 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_MPEG2_QUANTISATION = 0x0250, V4L2_CTRL_TYPE_MPEG2_SEQUENCE = 0x0251, V4L2_CTRL_TYPE_MPEG2_PICTURE = 0x0252, + + V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR = 0x0260, + V4L2_CTRL_TYPE_VP9_FRAME = 0x0261, }; /* Used in the VIDIOC_QUERYCTRL ioctl for querying controls */ -- cgit v1.2.3 From 448f413a8bdc727d25d9a786ccbdb974fb85d973 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Thu, 18 Nov 2021 20:12:40 +0800 Subject: ethtool: add support to set/get tx copybreak buf size via ethtool Add support for ethtool to set/get tx copybreak buf size. Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 1 + net/ethtool/common.c | 1 + net/ethtool/ioctl.c | 1 + 3 files changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index a2223b685451..7bc4b8def12c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -231,6 +231,7 @@ enum tunable_id { ETHTOOL_RX_COPYBREAK, ETHTOOL_TX_COPYBREAK, ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ + ETHTOOL_TX_COPYBREAK_BUF_SIZE, /* * Add your fresh new tunable attribute above and remember to update * tunable_strings[] in net/ethtool/common.c diff --git a/net/ethtool/common.c b/net/ethtool/common.c index c63e0739dc6a..0c5210015911 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -89,6 +89,7 @@ tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout", + [ETHTOOL_TX_COPYBREAK_BUF_SIZE] = "tx-copybreak-buf-size", }; const char diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 65e9bc1058b5..5c5f170a9851 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2396,6 +2396,7 @@ static int ethtool_tunable_valid(const struct ethtool_tunable *tuna) switch (tuna->id) { case ETHTOOL_RX_COPYBREAK: case ETHTOOL_TX_COPYBREAK: + case ETHTOOL_TX_COPYBREAK_BUF_SIZE: if (tuna->len != sizeof(u32) || tuna->type_id != ETHTOOL_TUNABLE_U32) return -EINVAL; -- cgit v1.2.3 From 0b70c256eba8448b072d25c95ee65e59da8970de Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Thu, 18 Nov 2021 20:12:42 +0800 Subject: ethtool: add support to set/get rx buf len via ethtool Add support to set rx buf len via ethtool -G parameter and get rx buf len via ethtool -g parameter. Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 10 ++++++---- include/linux/ethtool.h | 18 ++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 23 +++++++++++++++++++++-- 5 files changed, 47 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 7b598c7e3912..9d98e0511249 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -849,7 +849,7 @@ Request contents: Kernel response contents: - ==================================== ====== ========================== + ==================================== ====== =========================== ``ETHTOOL_A_RINGS_HEADER`` nested reply header ``ETHTOOL_A_RINGS_RX_MAX`` u32 max size of RX ring ``ETHTOOL_A_RINGS_RX_MINI_MAX`` u32 max size of RX mini ring @@ -859,7 +859,8 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_MINI`` u32 size of RX mini ring ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring - ==================================== ====== ========================== + ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ==================================== ====== =========================== RINGS_SET @@ -869,13 +870,14 @@ Sets ring sizes like ``ETHTOOL_SRINGPARAM`` ioctl request. Request contents: - ==================================== ====== ========================== + ==================================== ====== =========================== ``ETHTOOL_A_RINGS_HEADER`` nested reply header ``ETHTOOL_A_RINGS_RX`` u32 size of RX ring ``ETHTOOL_A_RINGS_RX_MINI`` u32 size of RX mini ring ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring - ==================================== ====== ========================== + ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by driver. Driver may impose additional constraints and may not suspport all diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 845a0ffc16ee..0b252b82988b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -67,6 +67,22 @@ enum { ETH_RSS_HASH_FUNCS_COUNT }; +/** + * struct kernel_ethtool_ringparam - RX/TX ring configuration + * @rx_buf_len: Current length of buffers on the rx ring. + */ +struct kernel_ethtool_ringparam { + u32 rx_buf_len; +}; + +/** + * enum ethtool_supported_ring_param - indicator caps for setting ring params + * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + */ +enum ethtool_supported_ring_param { + ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), +}; + #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) #define __ETH_RSS_HASH(name) __ETH_RSS_HASH_BIT(ETH_RSS_HASH_##name##_BIT) @@ -432,6 +448,7 @@ struct ethtool_module_power_mode_params { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. + * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -613,6 +630,7 @@ struct ethtool_module_power_mode_params { struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; + u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 999777d32dcf..cca6e474a085 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -329,6 +329,7 @@ enum { ETHTOOL_A_RINGS_RX_MINI, /* u32 */ ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ + ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 836ee7157848..490598e5eedd 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -356,7 +356,7 @@ 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 + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_RX_BUF_LEN + 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 4e097812a967..bd8e9a7530eb 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -10,6 +10,7 @@ struct rings_req_info { struct rings_reply_data { struct ethnl_reply_data base; struct ethtool_ringparam ringparam; + struct kernel_ethtool_ringparam kernel_ringparam; }; #define RINGS_REPDATA(__reply_base) \ @@ -49,7 +50,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ - nla_total_size(sizeof(u32)); /* _RINGS_TX */ + nla_total_size(sizeof(u32)) + /* _RINGS_TX */ + nla_total_size(sizeof(u32)); /* _RINGS_RX_BUF_LEN */ } static int rings_fill_reply(struct sk_buff *skb, @@ -57,6 +59,7 @@ static int rings_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct rings_reply_data *data = RINGS_REPDATA(reply_base); + const struct kernel_ethtool_ringparam *kernel_ringparam = &data->kernel_ringparam; const struct ethtool_ringparam *ringparam = &data->ringparam; if ((ringparam->rx_max_pending && @@ -78,7 +81,10 @@ static int rings_fill_reply(struct sk_buff *skb, (nla_put_u32(skb, ETHTOOL_A_RINGS_TX_MAX, ringparam->tx_max_pending) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX, - ringparam->tx_pending)))) + ringparam->tx_pending))) || + (kernel_ringparam->rx_buf_len && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, + kernel_ringparam->rx_buf_len)))) return -EMSGSIZE; return 0; @@ -105,10 +111,12 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_RX_MINI] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_TX] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_RX_BUF_LEN] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) { + struct kernel_ethtool_ringparam kernel_ringparam = {}; struct ethtool_ringparam ringparam = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; @@ -142,6 +150,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) ethnl_update_u32(&ringparam.rx_jumbo_pending, tb[ETHTOOL_A_RINGS_RX_JUMBO], &mod); ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod); + ethnl_update_u32(&kernel_ringparam.rx_buf_len, + tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod); ret = 0; if (!mod) goto out_ops; @@ -164,6 +174,15 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) goto out_ops; } + if (kernel_ringparam.rx_buf_len != 0 && + !(ops->supported_ring_params & ETHTOOL_RING_USE_RX_BUF_LEN)) { + ret = -EOPNOTSUPP; + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_RX_BUF_LEN], + "setting rx buf len not supported"); + goto out_ops; + } + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam); if (ret < 0) goto out_ops; -- cgit v1.2.3 From a0c2ccd9b5ad0a9e838158404e041b5a8ff762dd Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 23 Nov 2021 15:50:46 +0800 Subject: mctp: Add MCTP-over-serial transport binding This change adds a MCTP Serial transport binding, as defined by DMTF specificiation DSP0253 - "MCTP Serial Transport Binding". This is implemented as a new serial line discipline, and can be attached to arbitrary tty devices. From the Kconfig description: This driver provides an MCTP-over-serial interface, through a serial line-discipline, as defined by DMTF specification "DSP0253 - MCTP Serial Transport Binding". By attaching the ldisc to a serial device, we get a new net device to transport MCTP packets. This allows communication with external MCTP endpoints which use serial as their transport. It can also be used as an easy way to provide MCTP connectivity between virtual machines, by forwarding data between simple virtual serial devices. Say y here if you need to connect to MCTP endpoints over serial. To compile as a module, use m; the module will be called mctp-serial. Once the N_MCTP line discipline is set [using ioctl(TCIOSETD)], we get a new netdev suitable for MCTP communication. The 'mctp' utility[1] provides a simple wrapper for this ioctl, using 'link serial ': # mctp link serial /dev/ttyS0 & # mctp link dev lo index 1 address 0x00:00:00:00:00:00 net 1 mtu 65536 up dev mctpserial0 index 5 address 0x(no-addr) net 1 mtu 68 down [1]: https://github.com/CodeConstruct/mctp Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- drivers/net/mctp/Kconfig | 18 ++ drivers/net/mctp/Makefile | 1 + drivers/net/mctp/mctp-serial.c | 510 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/tty.h | 1 + 4 files changed, 530 insertions(+) create mode 100644 drivers/net/mctp/mctp-serial.c (limited to 'include/uapi') diff --git a/drivers/net/mctp/Kconfig b/drivers/net/mctp/Kconfig index d8f966cedc89..2929471395ae 100644 --- a/drivers/net/mctp/Kconfig +++ b/drivers/net/mctp/Kconfig @@ -3,6 +3,24 @@ if MCTP menu "MCTP Device Drivers" +config MCTP_SERIAL + tristate "MCTP serial transport" + depends on TTY + select CRC_CCITT + help + This driver provides an MCTP-over-serial interface, through a + serial line-discipline, as defined by DMTF specification "DSP0253 - + MCTP Serial Transport Binding". By attaching the ldisc to a serial + device, we get a new net device to transport MCTP packets. + + This allows communication with external MCTP endpoints which use + serial as their transport. It can also be used as an easy way to + provide MCTP connectivity between virtual machines, by forwarding + data between simple virtual serial devices. + + Say y here if you need to connect to MCTP endpoints over serial. To + compile as a module, use m; the module will be called mctp-serial. + endmenu endif diff --git a/drivers/net/mctp/Makefile b/drivers/net/mctp/Makefile index e69de29bb2d1..d32622613ce4 100644 --- a/drivers/net/mctp/Makefile +++ b/drivers/net/mctp/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_MCTP_SERIAL) += mctp-serial.o diff --git a/drivers/net/mctp/mctp-serial.c b/drivers/net/mctp/mctp-serial.c new file mode 100644 index 000000000000..9ac0e187f36e --- /dev/null +++ b/drivers/net/mctp/mctp-serial.c @@ -0,0 +1,510 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) - serial transport + * binding. This driver is an implementation of the DMTF specificiation + * "DSP0253 - Management Component Transport Protocol (MCTP) Serial Transport + * Binding", available at: + * + * https://www.dmtf.org/sites/default/files/standards/documents/DSP0253_1.0.0.pdf + * + * This driver provides DSP0253-type MCTP-over-serial transport using a Linux + * tty device, by setting the N_MCTP line discipline on the tty. + * + * Copyright (c) 2021 Code Construct + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define MCTP_SERIAL_MTU 68 /* base mtu (64) + mctp header */ +#define MCTP_SERIAL_FRAME_MTU (MCTP_SERIAL_MTU + 6) /* + serial framing */ + +#define MCTP_SERIAL_VERSION 0x1 /* DSP0253 defines a single version: 1 */ + +#define BUFSIZE MCTP_SERIAL_FRAME_MTU + +#define BYTE_FRAME 0x7e +#define BYTE_ESC 0x7d + +static DEFINE_IDA(mctp_serial_ida); + +enum mctp_serial_state { + STATE_IDLE, + STATE_START, + STATE_HEADER, + STATE_DATA, + STATE_ESCAPE, + STATE_TRAILER, + STATE_DONE, + STATE_ERR, +}; + +struct mctp_serial { + struct net_device *netdev; + struct tty_struct *tty; + + int idx; + + /* protects our rx & tx state machines; held during both paths */ + spinlock_t lock; + + struct work_struct tx_work; + enum mctp_serial_state txstate, rxstate; + u16 txfcs, rxfcs, rxfcs_rcvd; + unsigned int txlen, rxlen; + unsigned int txpos, rxpos; + unsigned char txbuf[BUFSIZE], + rxbuf[BUFSIZE]; +}; + +static bool needs_escape(unsigned char c) +{ + return c == BYTE_ESC || c == BYTE_FRAME; +} + +static int next_chunk_len(struct mctp_serial *dev) +{ + int i; + + /* either we have no bytes to send ... */ + if (dev->txpos == dev->txlen) + return 0; + + /* ... or the next byte to send is an escaped byte; requiring a + * single-byte chunk... + */ + if (needs_escape(dev->txbuf[dev->txpos])) + return 1; + + /* ... or we have one or more bytes up to the next escape - this chunk + * will be those non-escaped bytes, and does not include the escaped + * byte. + */ + for (i = 1; i + dev->txpos + 1 < dev->txlen; i++) { + if (needs_escape(dev->txbuf[dev->txpos + i + 1])) + break; + } + + return i; +} + +static int write_chunk(struct mctp_serial *dev, unsigned char *buf, int len) +{ + return dev->tty->ops->write(dev->tty, buf, len); +} + +static void mctp_serial_tx_work(struct work_struct *work) +{ + struct mctp_serial *dev = container_of(work, struct mctp_serial, + tx_work); + unsigned char c, buf[3]; + unsigned long flags; + int len, txlen; + + spin_lock_irqsave(&dev->lock, flags); + + /* txstate represents the next thing to send */ + switch (dev->txstate) { + case STATE_START: + dev->txpos = 0; + fallthrough; + case STATE_HEADER: + buf[0] = BYTE_FRAME; + buf[1] = MCTP_SERIAL_VERSION; + buf[2] = dev->txlen; + + if (!dev->txpos) + dev->txfcs = crc_ccitt(0, buf + 1, 2); + + txlen = write_chunk(dev, buf + dev->txpos, 3 - dev->txpos); + if (txlen <= 0) { + dev->txstate = STATE_ERR; + } else { + dev->txpos += txlen; + if (dev->txpos == 3) { + dev->txstate = STATE_DATA; + dev->txpos = 0; + } + } + break; + + case STATE_ESCAPE: + buf[0] = dev->txbuf[dev->txpos] & ~0x20; + txlen = write_chunk(dev, buf, 1); + if (txlen <= 0) { + dev->txstate = STATE_ERR; + } else { + dev->txpos += txlen; + if (dev->txpos == dev->txlen) { + dev->txstate = STATE_TRAILER; + dev->txpos = 0; + } + } + + break; + + case STATE_DATA: + len = next_chunk_len(dev); + if (len) { + c = dev->txbuf[dev->txpos]; + if (len == 1 && needs_escape(c)) { + buf[0] = BYTE_ESC; + buf[1] = c & ~0x20; + dev->txfcs = crc_ccitt_byte(dev->txfcs, c); + txlen = write_chunk(dev, buf, 2); + if (txlen == 2) + dev->txpos++; + else if (txlen == 1) + dev->txstate = STATE_ESCAPE; + else + dev->txstate = STATE_ERR; + } else { + txlen = write_chunk(dev, + dev->txbuf + dev->txpos, + len); + if (txlen <= 0) { + dev->txstate = STATE_ERR; + } else { + dev->txfcs = crc_ccitt(dev->txfcs, + dev->txbuf + + dev->txpos, + txlen); + dev->txpos += txlen; + } + } + if (dev->txstate == STATE_DATA && + dev->txpos == dev->txlen) { + dev->txstate = STATE_TRAILER; + dev->txpos = 0; + } + break; + } + dev->txstate = STATE_TRAILER; + dev->txpos = 0; + fallthrough; + + case STATE_TRAILER: + buf[0] = dev->txfcs >> 8; + buf[1] = dev->txfcs & 0xff; + buf[2] = BYTE_FRAME; + txlen = write_chunk(dev, buf + dev->txpos, 3 - dev->txpos); + if (txlen <= 0) { + dev->txstate = STATE_ERR; + } else { + dev->txpos += txlen; + if (dev->txpos == 3) { + dev->txstate = STATE_DONE; + dev->txpos = 0; + } + } + break; + default: + netdev_err_once(dev->netdev, "invalid tx state %d\n", + dev->txstate); + } + + if (dev->txstate == STATE_DONE) { + dev->netdev->stats.tx_packets++; + dev->netdev->stats.tx_bytes += dev->txlen; + dev->txlen = 0; + dev->txpos = 0; + clear_bit(TTY_DO_WRITE_WAKEUP, &dev->tty->flags); + dev->txstate = STATE_IDLE; + spin_unlock_irqrestore(&dev->lock, flags); + + netif_wake_queue(dev->netdev); + } else { + spin_unlock_irqrestore(&dev->lock, flags); + } +} + +static netdev_tx_t mctp_serial_tx(struct sk_buff *skb, struct net_device *ndev) +{ + struct mctp_serial *dev = netdev_priv(ndev); + unsigned long flags; + + WARN_ON(dev->txstate != STATE_IDLE); + + if (skb->len > MCTP_SERIAL_MTU) { + dev->netdev->stats.tx_dropped++; + goto out; + } + + spin_lock_irqsave(&dev->lock, flags); + netif_stop_queue(dev->netdev); + skb_copy_bits(skb, 0, dev->txbuf, skb->len); + dev->txpos = 0; + dev->txlen = skb->len; + dev->txstate = STATE_START; + spin_unlock_irqrestore(&dev->lock, flags); + + set_bit(TTY_DO_WRITE_WAKEUP, &dev->tty->flags); + schedule_work(&dev->tx_work); + +out: + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static void mctp_serial_tty_write_wakeup(struct tty_struct *tty) +{ + struct mctp_serial *dev = tty->disc_data; + + schedule_work(&dev->tx_work); +} + +static void mctp_serial_rx(struct mctp_serial *dev) +{ + struct mctp_skb_cb *cb; + struct sk_buff *skb; + + if (dev->rxfcs != dev->rxfcs_rcvd) { + dev->netdev->stats.rx_dropped++; + dev->netdev->stats.rx_crc_errors++; + return; + } + + skb = netdev_alloc_skb(dev->netdev, dev->rxlen); + if (!skb) { + dev->netdev->stats.rx_dropped++; + return; + } + + skb->protocol = htons(ETH_P_MCTP); + skb_put_data(skb, dev->rxbuf, dev->rxlen); + skb_reset_network_header(skb); + + cb = __mctp_cb(skb); + cb->halen = 0; + + netif_rx_ni(skb); + dev->netdev->stats.rx_packets++; + dev->netdev->stats.rx_bytes += dev->rxlen; +} + +static void mctp_serial_push_header(struct mctp_serial *dev, unsigned char c) +{ + switch (dev->rxpos) { + case 0: + if (c == BYTE_FRAME) + dev->rxpos++; + else + dev->rxstate = STATE_ERR; + break; + case 1: + if (c == MCTP_SERIAL_VERSION) { + dev->rxpos++; + dev->rxfcs = crc_ccitt_byte(0, c); + } else { + dev->rxstate = STATE_ERR; + } + break; + case 2: + if (c > MCTP_SERIAL_FRAME_MTU) { + dev->rxstate = STATE_ERR; + } else { + dev->rxlen = c; + dev->rxpos = 0; + dev->rxstate = STATE_DATA; + dev->rxfcs = crc_ccitt_byte(dev->rxfcs, c); + } + break; + } +} + +static void mctp_serial_push_trailer(struct mctp_serial *dev, unsigned char c) +{ + switch (dev->rxpos) { + case 0: + dev->rxfcs_rcvd = c << 8; + dev->rxpos++; + break; + case 1: + dev->rxfcs_rcvd |= c; + dev->rxpos++; + break; + case 2: + if (c != BYTE_FRAME) { + dev->rxstate = STATE_ERR; + } else { + mctp_serial_rx(dev); + dev->rxlen = 0; + dev->rxpos = 0; + dev->rxstate = STATE_IDLE; + } + break; + } +} + +static void mctp_serial_push(struct mctp_serial *dev, unsigned char c) +{ + switch (dev->rxstate) { + case STATE_IDLE: + dev->rxstate = STATE_HEADER; + fallthrough; + case STATE_HEADER: + mctp_serial_push_header(dev, c); + break; + + case STATE_ESCAPE: + c |= 0x20; + fallthrough; + case STATE_DATA: + if (dev->rxstate != STATE_ESCAPE && c == BYTE_ESC) { + dev->rxstate = STATE_ESCAPE; + } else { + dev->rxfcs = crc_ccitt_byte(dev->rxfcs, c); + dev->rxbuf[dev->rxpos] = c; + dev->rxpos++; + dev->rxstate = STATE_DATA; + if (dev->rxpos == dev->rxlen) { + dev->rxpos = 0; + dev->rxstate = STATE_TRAILER; + } + } + break; + + case STATE_TRAILER: + mctp_serial_push_trailer(dev, c); + break; + + case STATE_ERR: + if (c == BYTE_FRAME) + dev->rxstate = STATE_IDLE; + break; + + default: + netdev_err_once(dev->netdev, "invalid rx state %d\n", + dev->rxstate); + } +} + +static void mctp_serial_tty_receive_buf(struct tty_struct *tty, + const unsigned char *c, + const char *f, int len) +{ + struct mctp_serial *dev = tty->disc_data; + int i; + + if (!netif_running(dev->netdev)) + return; + + /* we don't (currently) use the flag bytes, just data. */ + for (i = 0; i < len; i++) + mctp_serial_push(dev, c[i]); +} + +static const struct net_device_ops mctp_serial_netdev_ops = { + .ndo_start_xmit = mctp_serial_tx, +}; + +static void mctp_serial_setup(struct net_device *ndev) +{ + ndev->type = ARPHRD_MCTP; + ndev->mtu = MCTP_SERIAL_MTU; + ndev->hard_header_len = 0; + ndev->addr_len = 0; + ndev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; + ndev->flags = IFF_NOARP; + ndev->netdev_ops = &mctp_serial_netdev_ops; + ndev->needs_free_netdev = true; +} + +static int mctp_serial_open(struct tty_struct *tty) +{ + struct mctp_serial *dev; + struct net_device *ndev; + char name[32]; + int idx, rc; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!tty->ops->write) + return -EOPNOTSUPP; + + if (tty->disc_data) + return -EEXIST; + + idx = ida_alloc(&mctp_serial_ida, GFP_KERNEL); + if (idx < 0) + return idx; + + snprintf(name, sizeof(name), "mctpserial%d", idx); + ndev = alloc_netdev(sizeof(*dev), name, NET_NAME_ENUM, + mctp_serial_setup); + if (!ndev) { + rc = -ENOMEM; + goto free_ida; + } + + dev = netdev_priv(ndev); + dev->idx = idx; + dev->tty = tty; + dev->netdev = ndev; + dev->txstate = STATE_IDLE; + dev->rxstate = STATE_IDLE; + spin_lock_init(&dev->lock); + INIT_WORK(&dev->tx_work, mctp_serial_tx_work); + + rc = register_netdev(ndev); + if (rc) + goto free_netdev; + + tty->receive_room = 64 * 1024; + tty->disc_data = dev; + + return 0; + +free_netdev: + free_netdev(ndev); + +free_ida: + ida_free(&mctp_serial_ida, idx); + return rc; +} + +static void mctp_serial_close(struct tty_struct *tty) +{ + struct mctp_serial *dev = tty->disc_data; + int idx = dev->idx; + + unregister_netdev(dev->netdev); + ida_free(&mctp_serial_ida, idx); +} + +static struct tty_ldisc_ops mctp_ldisc = { + .owner = THIS_MODULE, + .num = N_MCTP, + .name = "mctp", + .open = mctp_serial_open, + .close = mctp_serial_close, + .receive_buf = mctp_serial_tty_receive_buf, + .write_wakeup = mctp_serial_tty_write_wakeup, +}; + +static int __init mctp_serial_init(void) +{ + return tty_register_ldisc(&mctp_ldisc); +} + +static void __exit mctp_serial_exit(void) +{ + tty_unregister_ldisc(&mctp_ldisc); +} + +module_init(mctp_serial_init); +module_exit(mctp_serial_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jeremy Kerr "); +MODULE_DESCRIPTION("MCTP Serial transport"); diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index 376cccf397be..a58deb3061eb 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -38,5 +38,6 @@ #define N_NCI 25 /* NFC NCI UART */ #define N_SPEAKUP 26 /* Speakup communication with synths */ #define N_NULL 27 /* Null ldisc used for error handling */ +#define N_MCTP 28 /* MCTP-over-serial */ #endif /* _UAPI_LINUX_TTY_H */ -- cgit v1.2.3 From b456abe63f60ad93c83a526d33b71574bc32656c Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 19 Nov 2021 17:08:50 -0600 Subject: ALSA: pcm: introduce INFO_NO_REWINDS flag When the hardware can only deal with a monotonically increasing appl_ptr, this flag can be set. In case the application requests a rewind, be it with a snd_pcm_rewind() or with a direct change of a mmap'ed pointer followed by a SNDRV_PCM_IOCTL_SYNC_PTR, this patch checks if a rewind occurred and returns an error. Credits to Takashi Iwai for identifying the path with SYNC_PTR and suggesting the pointer checks. Suggested-by: Takashi Iwai Reviewed-by: Takashi Iwai Reviewed-by: Ranjani Sridharan Reviewed-by: Kai Vehmanen Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20211119230852.206310-3-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/asound.h | 2 +- sound/core/pcm_lib.c | 14 ++++++++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 5fbb79e30819..ff7e638221c5 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -300,7 +300,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */ #define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */ #define SNDRV_PCM_INFO_EXPLICIT_SYNC 0x10000000 /* needs explicit sync of pointers and data */ - +#define SNDRV_PCM_INFO_NO_REWINDS 0x20000000 /* hardware can only support monotonic changes of appl_ptr */ #define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index fdd992772b20..f2090025236b 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2128,6 +2128,7 @@ int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_uframes_t old_appl_ptr = runtime->control->appl_ptr; + snd_pcm_sframes_t diff; int ret; if (old_appl_ptr == appl_ptr) @@ -2135,6 +2136,19 @@ int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, if (appl_ptr >= runtime->boundary) return -EINVAL; + /* + * check if a rewind is requested by the application + */ + if (substream->runtime->info & SNDRV_PCM_INFO_NO_REWINDS) { + diff = appl_ptr - old_appl_ptr; + if (diff >= 0) { + if (diff > runtime->buffer_size) + return -EINVAL; + } else { + if (runtime->boundary + diff > runtime->buffer_size) + return -EINVAL; + } + } runtime->control->appl_ptr = appl_ptr; if (substream->ops->ack) { -- cgit v1.2.3 From 04c76b41ca974b508522831441dd7e5b1b59cbb0 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 10 Nov 2021 15:49:32 +0000 Subject: io_uring: add option to skip CQE posting Emitting a CQE is expensive from the kernel perspective. Often, it's also not convenient for the userspace, spends some cycles on processing and just complicates the logic. A similar problems goes for linked requests, where we post an CQE for each request in the link. Introduce a new flags, IOSQE_CQE_SKIP_SUCCESS, trying to help with it. When set and a request completed successfully, it won't generate a CQE. When fails, it produces an CQE, but all following linked requests will be CQE-less, regardless whether they have IOSQE_CQE_SKIP_SUCCESS or not. The notion of "fail" is the same as for link failing-cancellation, where it's opcode dependent, and _usually_ result >= 0 is a success, but not always. Linked timeouts are a bit special. When the requests it's linked to was not attempted to be executed, e.g. failing linked requests, it follows the description above. Otherwise, whether a linked timeout will post a completion or not solely depends on IOSQE_CQE_SKIP_SUCCESS of that linked timeout request. Linked timeout never "fail" during execution, so for them it's unconditional. It's expected for users to not really care about the result of it but rely solely on the result of the master request. Another reason for such a treatment is that it's racy, and the timeout callback may be running awhile the master request posts its completion. use case 1: If one doesn't care about results of some requests, e.g. normal timeouts, just set IOSQE_CQE_SKIP_SUCCESS. Error result will still be posted and need to be handled. use case 2: Set IOSQE_CQE_SKIP_SUCCESS for all requests of a link but the last, and it'll post a completion only for the last one if everything goes right, otherwise there will be one only one CQE for the first failed request. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0220fbe06f7cf99e6fc71b4297bb1cb6c0e89c2c.1636559119.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 42 +++++++++++++++++++++++++++++++++--------- include/uapi/linux/io_uring.h | 4 ++++ 2 files changed, 37 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/fs/io_uring.c b/fs/io_uring.c index 2a89928ac1ba..7d3589e3a277 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -106,7 +106,8 @@ #define IORING_MAX_REG_BUFFERS (1U << 14) #define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \ - IOSQE_IO_HARDLINK | IOSQE_ASYNC) + IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ + IOSQE_CQE_SKIP_SUCCESS) #define SQE_VALID_FLAGS (SQE_COMMON_FLAGS|IOSQE_BUFFER_SELECT|IOSQE_IO_DRAIN) @@ -721,6 +722,7 @@ enum { REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, + REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT, /* first byte is taken by user flags, shift it to not overlap */ REQ_F_FAIL_BIT = 8, @@ -737,6 +739,7 @@ enum { REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, REQ_F_ASYNC_DATA_BIT, + REQ_F_SKIP_LINK_CQES_BIT, /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, @@ -758,6 +761,8 @@ enum { REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), /* IOSQE_BUFFER_SELECT */ REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), + /* IOSQE_CQE_SKIP_SUCCESS */ + REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT), /* fail rest of links */ REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), @@ -791,6 +796,8 @@ enum { REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), /* ->async_data allocated */ REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT), + /* don't post CQEs while failing linked requests */ + REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT), }; struct async_poll { @@ -1301,6 +1308,10 @@ static inline bool req_has_async_data(struct io_kiocb *req) static inline void req_set_fail(struct io_kiocb *req) { req->flags |= REQ_F_FAIL; + if (req->flags & REQ_F_CQE_SKIP) { + req->flags &= ~REQ_F_CQE_SKIP; + req->flags |= REQ_F_SKIP_LINK_CQES; + } } static inline void req_fail_link_node(struct io_kiocb *req, int res) @@ -1843,7 +1854,8 @@ static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) { - __io_fill_cqe(req->ctx, req->user_data, res, cflags); + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe(req->ctx, req->user_data, res, cflags); } static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, @@ -1859,7 +1871,8 @@ static void io_req_complete_post(struct io_kiocb *req, s32 res, struct io_ring_ctx *ctx = req->ctx; spin_lock(&ctx->completion_lock); - __io_fill_cqe(ctx, req->user_data, res, cflags); + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe(ctx, req->user_data, res, cflags); /* * If we're the last reference to this request, add to our locked * free_list cache. @@ -2067,6 +2080,7 @@ static bool io_kill_linked_timeout(struct io_kiocb *req) link->timeout.head = NULL; if (hrtimer_try_to_cancel(&io->timer) != -1) { list_del(&link->timeout.list); + /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */ io_fill_cqe_req(link, -ECANCELED, 0); io_put_req_deferred(link); return true; @@ -2079,6 +2093,7 @@ static void io_fail_links(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) { struct io_kiocb *nxt, *link = req->link; + bool ignore_cqes = req->flags & REQ_F_SKIP_LINK_CQES; req->link = NULL; while (link) { @@ -2091,7 +2106,10 @@ static void io_fail_links(struct io_kiocb *req) link->link = NULL; trace_io_uring_fail_link(req, link); - io_fill_cqe_req(link, res, 0); + if (!ignore_cqes) { + link->flags &= ~REQ_F_CQE_SKIP; + io_fill_cqe_req(link, res, 0); + } io_put_req_deferred(link); link = nxt; } @@ -2108,6 +2126,7 @@ static bool io_disarm_next(struct io_kiocb *req) req->flags &= ~REQ_F_ARM_LTIMEOUT; if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { io_remove_next_linked(req); + /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */ io_fill_cqe_req(link, -ECANCELED, 0); io_put_req_deferred(link); posted = true; @@ -2372,8 +2391,9 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx) struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); - __io_fill_cqe(ctx, req->user_data, req->result, - req->cflags); + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe(ctx, req->user_data, req->result, + req->cflags); } io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); @@ -2503,12 +2523,14 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) prev = start; wq_list_for_each_resume(pos, prev) { struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); + u32 cflags; /* order with io_complete_rw_iopoll(), e.g. ->result updates */ if (!smp_load_acquire(&req->iopoll_completed)) break; - __io_fill_cqe(ctx, req->user_data, req->result, - io_put_rw_kbuf(req)); + cflags = io_put_rw_kbuf(req); + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe(ctx, req->user_data, req->result, cflags); nr_events++; } @@ -5832,6 +5854,8 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe flags = READ_ONCE(sqe->len); if (flags & ~IORING_POLL_ADD_MULTI) return -EINVAL; + if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP)) + return -EINVAL; io_req_set_refcount(req); poll->events = io_poll_parse_events(sqe, flags); @@ -10442,7 +10466,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | - IORING_FEAT_RSRC_TAGS; + IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index c45b5e9a9387..787f491f0d2a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -70,6 +70,7 @@ enum { IOSQE_IO_HARDLINK_BIT, IOSQE_ASYNC_BIT, IOSQE_BUFFER_SELECT_BIT, + IOSQE_CQE_SKIP_SUCCESS_BIT, }; /* @@ -87,6 +88,8 @@ enum { #define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT) /* select buffer from sqe->buf_group */ #define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT) +/* don't post CQE if request succeeded */ +#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT) /* * io_uring_setup() flags @@ -289,6 +292,7 @@ struct io_uring_params { #define IORING_FEAT_EXT_ARG (1U << 8) #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) +#define IORING_FEAT_CQE_SKIP (1U << 11) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3 From 53db28933e952a8536b002ba8b8c9443ccc0e939 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 25 Nov 2021 14:05:18 +0100 Subject: fuse: extend init flags FUSE_INIT flags are close to running out, so add another 32bits worth of space. Add FUSE_INIT_EXT flag to the old flags field in fuse_init_in. If this flag is set, then fuse_init_in is extended by 48bytes, in which a flags_hi field is allocated to contain the high 32bits of the flags. A flags_hi field is also added to fuse_init_out, allocated out of the remaining unused fields. Known userspace implementations of the fuse protocol have been checked to accept the extended FUSE_INIT request, but this might cause problems with other implementations. If that happens to be the case, the protocol negotiation will have to be extended with an extra initialization request roundtrip. Signed-off-by: Miklos Szeredi --- fs/fuse/inode.c | 60 ++++++++++++++++++++++++++--------------------- include/uapi/linux/fuse.h | 16 +++++++++++-- 2 files changed, 47 insertions(+), 29 deletions(-) (limited to 'include/uapi') diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 8b89e3ba7df3..5a1dad8c1f92 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1109,72 +1109,74 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, process_init_limits(fc, arg); if (arg->minor >= 6) { + u64 flags = arg->flags | (u64) arg->flags2 << 32; + ra_pages = arg->max_readahead / PAGE_SIZE; - if (arg->flags & FUSE_ASYNC_READ) + if (flags & FUSE_ASYNC_READ) fc->async_read = 1; - if (!(arg->flags & FUSE_POSIX_LOCKS)) + if (!(flags & FUSE_POSIX_LOCKS)) fc->no_lock = 1; if (arg->minor >= 17) { - if (!(arg->flags & FUSE_FLOCK_LOCKS)) + if (!(flags & FUSE_FLOCK_LOCKS)) fc->no_flock = 1; } else { - if (!(arg->flags & FUSE_POSIX_LOCKS)) + if (!(flags & FUSE_POSIX_LOCKS)) fc->no_flock = 1; } - if (arg->flags & FUSE_ATOMIC_O_TRUNC) + if (flags & FUSE_ATOMIC_O_TRUNC) fc->atomic_o_trunc = 1; if (arg->minor >= 9) { /* LOOKUP has dependency on proto version */ - if (arg->flags & FUSE_EXPORT_SUPPORT) + if (flags & FUSE_EXPORT_SUPPORT) fc->export_support = 1; } - if (arg->flags & FUSE_BIG_WRITES) + if (flags & FUSE_BIG_WRITES) fc->big_writes = 1; - if (arg->flags & FUSE_DONT_MASK) + if (flags & FUSE_DONT_MASK) fc->dont_mask = 1; - if (arg->flags & FUSE_AUTO_INVAL_DATA) + if (flags & FUSE_AUTO_INVAL_DATA) fc->auto_inval_data = 1; - else if (arg->flags & FUSE_EXPLICIT_INVAL_DATA) + else if (flags & FUSE_EXPLICIT_INVAL_DATA) fc->explicit_inval_data = 1; - if (arg->flags & FUSE_DO_READDIRPLUS) { + if (flags & FUSE_DO_READDIRPLUS) { fc->do_readdirplus = 1; - if (arg->flags & FUSE_READDIRPLUS_AUTO) + if (flags & FUSE_READDIRPLUS_AUTO) fc->readdirplus_auto = 1; } - if (arg->flags & FUSE_ASYNC_DIO) + if (flags & FUSE_ASYNC_DIO) fc->async_dio = 1; - if (arg->flags & FUSE_WRITEBACK_CACHE) + if (flags & FUSE_WRITEBACK_CACHE) fc->writeback_cache = 1; - if (arg->flags & FUSE_PARALLEL_DIROPS) + if (flags & FUSE_PARALLEL_DIROPS) fc->parallel_dirops = 1; - if (arg->flags & FUSE_HANDLE_KILLPRIV) + if (flags & FUSE_HANDLE_KILLPRIV) fc->handle_killpriv = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fm->sb->s_time_gran = arg->time_gran; - if ((arg->flags & FUSE_POSIX_ACL)) { + if ((flags & FUSE_POSIX_ACL)) { fc->default_permissions = 1; fc->posix_acl = 1; fm->sb->s_xattr = fuse_acl_xattr_handlers; } - if (arg->flags & FUSE_CACHE_SYMLINKS) + if (flags & FUSE_CACHE_SYMLINKS) fc->cache_symlinks = 1; - if (arg->flags & FUSE_ABORT_ERROR) + if (flags & FUSE_ABORT_ERROR) fc->abort_err = 1; - if (arg->flags & FUSE_MAX_PAGES) { + if (flags & FUSE_MAX_PAGES) { fc->max_pages = min_t(unsigned int, fc->max_pages_limit, max_t(unsigned int, arg->max_pages, 1)); } if (IS_ENABLED(CONFIG_FUSE_DAX) && - arg->flags & FUSE_MAP_ALIGNMENT && + flags & FUSE_MAP_ALIGNMENT && !fuse_dax_check_alignment(fc, arg->map_alignment)) { ok = false; } - if (arg->flags & FUSE_HANDLE_KILLPRIV_V2) { + if (flags & FUSE_HANDLE_KILLPRIV_V2) { fc->handle_killpriv_v2 = 1; fm->sb->s_flags |= SB_NOSEC; } - if (arg->flags & FUSE_SETXATTR_EXT) + if (flags & FUSE_SETXATTR_EXT) fc->setxattr_ext = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; @@ -1203,13 +1205,14 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, void fuse_send_init(struct fuse_mount *fm) { struct fuse_init_args *ia; + u64 flags; ia = kzalloc(sizeof(*ia), GFP_KERNEL | __GFP_NOFAIL); ia->in.major = FUSE_KERNEL_VERSION; ia->in.minor = FUSE_KERNEL_MINOR_VERSION; ia->in.max_readahead = fm->sb->s_bdi->ra_pages * PAGE_SIZE; - ia->in.flags |= + flags = FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | @@ -1219,13 +1222,16 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | 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_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) - ia->in.flags |= FUSE_MAP_ALIGNMENT; + flags |= FUSE_MAP_ALIGNMENT; #endif if (fm->fc->auto_submounts) - ia->in.flags |= FUSE_SUBMOUNTS; + flags |= FUSE_SUBMOUNTS; + + ia->in.flags = flags; + ia->in.flags2 = flags >> 32; ia->args.opcode = FUSE_INIT; ia->args.in_numargs = 1; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index a1dc3ee1d17c..980f3998c11b 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -187,6 +187,10 @@ * * 7.35 * - add FOPEN_NOFLUSH + * + * 7.36 + * - extend fuse_init_in with reserved fields, add FUSE_INIT_EXT init flag + * - add flags2 to fuse_init_in and fuse_init_out */ #ifndef _LINUX_FUSE_H @@ -222,7 +226,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 35 +#define FUSE_KERNEL_MINOR_VERSION 36 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -341,6 +345,8 @@ struct fuse_file_lock { * write/truncate sgid is killed only if file has group * execute permission. (Same as Linux VFS behavior). * FUSE_SETXATTR_EXT: Server supports extended struct fuse_setxattr_in + * FUSE_INIT_EXT: extended fuse_init_in request + * FUSE_INIT_RESERVED: reserved, do not use */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -372,6 +378,9 @@ struct fuse_file_lock { #define FUSE_SUBMOUNTS (1 << 27) #define FUSE_HANDLE_KILLPRIV_V2 (1 << 28) #define FUSE_SETXATTR_EXT (1 << 29) +#define FUSE_INIT_EXT (1 << 30) +#define FUSE_INIT_RESERVED (1 << 31) +/* bits 32..63 get shifted down 32 bits into the flags2 field */ /** * CUSE INIT request/reply flags @@ -741,6 +750,8 @@ struct fuse_init_in { uint32_t minor; uint32_t max_readahead; uint32_t flags; + uint32_t flags2; + uint32_t unused[11]; }; #define FUSE_COMPAT_INIT_OUT_SIZE 8 @@ -757,7 +768,8 @@ struct fuse_init_out { uint32_t time_gran; uint16_t max_pages; uint16_t map_alignment; - uint32_t unused[8]; + uint32_t flags2; + uint32_t unused[7]; }; #define CUSE_INIT_INFO_MAX 4096 -- cgit v1.2.3 From 3e2b6fdbdc9ab5a02d9d5676a005f30780b97553 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Thu, 11 Nov 2021 09:32:49 -0500 Subject: fuse: send security context of inode on file When a new inode is created, send its security context to server along with creation request (FUSE_CREAT, FUSE_MKNOD, FUSE_MKDIR and FUSE_SYMLINK). This gives server an opportunity to create new file and set security context (possibly atomically). In all the configurations it might not be possible to set context atomically. Like nfs and ceph, use security_dentry_init_security() to dermine security context of inode and send it with create, mkdir, mknod, and symlink requests. Following is the information sent to server. fuse_sectx_header, fuse_secctx, xattr_name, security_context - struct fuse_secctx_header This contains total number of security contexts being sent and total size of all the security contexts (including size of fuse_secctx_header). - struct fuse_secctx This contains size of security context which follows this structure. There is one fuse_secctx instance per security context. - xattr name string This string represents name of xattr which should be used while setting security context. - security context This is the actual security context whose size is specified in fuse_secctx struct. Also add the FUSE_SECURITY_CTX flag for the `flags` field of the fuse_init_out struct. When this flag is set the kernel will append the security context for a newly created inode to the request (create, mkdir, mknod, and symlink). The server is responsible for ensuring that the inode appears atomically (preferrably) with the requested security context. For example, If the server is using SELinux and backed by a "real" linux file system that supports extended attributes it can write the security context value to /proc/thread-self/attr/fscreate before making the syscall to create the inode. This patch is based on patch from Chirantan Ekbote Signed-off-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++ fs/fuse/fuse_i.h | 3 ++ fs/fuse/inode.c | 5 ++- include/uapi/linux/fuse.h | 34 ++++++++++++++++-- 4 files changed, 130 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 0654bfedcbb0..656e921f3506 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -17,6 +17,9 @@ #include #include #include +#include +#include +#include static void fuse_advise_use_readdirplus(struct inode *dir) { @@ -456,6 +459,62 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, return ERR_PTR(err); } +static int get_security_context(struct dentry *entry, umode_t mode, + void **security_ctx, u32 *security_ctxlen) +{ + struct fuse_secctx *fctx; + struct fuse_secctx_header *header; + void *ctx = NULL, *ptr; + u32 ctxlen, total_len = sizeof(*header); + int err, nr_ctx = 0; + const char *name; + size_t namelen; + + err = security_dentry_init_security(entry, mode, &entry->d_name, + &name, &ctx, &ctxlen); + if (err) { + if (err != -EOPNOTSUPP) + goto out_err; + /* No LSM is supporting this security hook. Ignore error */ + ctxlen = 0; + ctx = NULL; + } + + if (ctxlen) { + nr_ctx = 1; + namelen = strlen(name) + 1; + err = -EIO; + if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX)) + goto out_err; + total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen); + } + + err = -ENOMEM; + header = ptr = kzalloc(total_len, GFP_KERNEL); + if (!ptr) + goto out_err; + + header->nr_secctx = nr_ctx; + header->size = total_len; + ptr += sizeof(*header); + if (nr_ctx) { + fctx = ptr; + fctx->size = ctxlen; + ptr += sizeof(*fctx); + + strcpy(ptr, name); + ptr += namelen; + + memcpy(ptr, ctx, ctxlen); + } + *security_ctxlen = total_len; + *security_ctx = header; + err = 0; +out_err: + kfree(ctx); + return err; +} + /* * Atomic create+open operation * @@ -476,6 +535,8 @@ 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; /* Userspace expects S_IFREG in create mode */ BUG_ON((mode & S_IFMT) != S_IFREG); @@ -517,7 +578,20 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, args.out_args[0].value = &outentry; 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 = fuse_simple_request(fm, &args); + kfree(security_ctx); if (err) goto out_free_ff; @@ -620,6 +694,8 @@ 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; @@ -633,7 +709,22 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, args->out_numargs = 1; 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 (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); if (err) goto out_put_forget_req; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 198637b41e19..c1a8b313e6ed 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -765,6 +765,9 @@ struct fuse_conn { /* Propagate syncfs() to server */ unsigned int sync_fs:1; + /* Initialize security xattrs when creating a new inode */ + unsigned int init_security:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 5a1dad8c1f92..63ab45427de5 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1178,6 +1178,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, } if (flags & FUSE_SETXATTR_EXT) fc->setxattr_ext = 1; + if (flags & FUSE_SECURITY_CTX) + fc->init_security = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1222,7 +1224,8 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | 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_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | + FUSE_SECURITY_CTX; #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 980f3998c11b..3f0ea63fec08 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -191,6 +191,8 @@ * 7.36 * - extend fuse_init_in with reserved fields, add FUSE_INIT_EXT init flag * - add flags2 to fuse_init_in and fuse_init_out + * - add FUSE_SECURITY_CTX init flag + * - add security context to create, mkdir, symlink, and mknod requests */ #ifndef _LINUX_FUSE_H @@ -347,6 +349,8 @@ struct fuse_file_lock { * FUSE_SETXATTR_EXT: Server supports extended struct fuse_setxattr_in * FUSE_INIT_EXT: extended fuse_init_in request * FUSE_INIT_RESERVED: reserved, do not use + * FUSE_SECURITY_CTX: add security context to create, mkdir, symlink, and + * mknod */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -381,6 +385,7 @@ struct fuse_file_lock { #define FUSE_INIT_EXT (1 << 30) #define FUSE_INIT_RESERVED (1 << 31) /* bits 32..63 get shifted down 32 bits into the flags2 field */ +#define FUSE_SECURITY_CTX (1ULL << 32) /** * CUSE INIT request/reply flags @@ -877,9 +882,12 @@ struct fuse_dirent { char name[]; }; -#define FUSE_NAME_OFFSET offsetof(struct fuse_dirent, name) -#define FUSE_DIRENT_ALIGN(x) \ +/* Align variable length records to 64bit boundary */ +#define FUSE_REC_ALIGN(x) \ (((x) + sizeof(uint64_t) - 1) & ~(sizeof(uint64_t) - 1)) + +#define FUSE_NAME_OFFSET offsetof(struct fuse_dirent, name) +#define FUSE_DIRENT_ALIGN(x) FUSE_REC_ALIGN(x) #define FUSE_DIRENT_SIZE(d) \ FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen) @@ -996,4 +1004,26 @@ struct fuse_syncfs_in { uint64_t padding; }; +/* + * For each security context, send fuse_secctx with size of security context + * fuse_secctx will be followed by security context name and this in turn + * will be followed by actual context label. + * fuse_secctx, name, context + */ +struct fuse_secctx { + uint32_t size; + uint32_t padding; +}; + +/* + * Contains the information about how many fuse_secctx structures are being + * sent and what's the total size of all security contexts (including + * size of fuse_secctx_header). + * + */ +struct fuse_secctx_header { + uint32_t size; + uint32_t nr_secctx; +}; + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From df0e68c1e9945e2ee86d266ce45597bbd8299b06 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 17 Nov 2021 12:05:59 +0000 Subject: comedi: Move the main COMEDI headers Move the main COMEDI driver headers out of "drivers/comedi/" into new directory "include/linux/comedi/". These are "comedidev.h", "comedilib.h", "comedi_pci.h", "comedi_pcmcia.h", and "comedi_usb.h". Additionally, move the user-space API header "comedi.h" into "include/uapi/linux/" and add "WITH Linux-syscall-note" to its SPDX-License-Identifier. Update the "COMEDI DRIVERS" section of the MAINTAINERS file to account for these changes. Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20211117120604.117740-2-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 + drivers/comedi/comedi.h | 1528 -------------------- drivers/comedi/comedi_buf.c | 3 +- drivers/comedi/comedi_fops.c | 2 +- drivers/comedi/comedi_pci.c | 3 +- drivers/comedi/comedi_pci.h | 57 - drivers/comedi/comedi_pcmcia.c | 3 +- drivers/comedi/comedi_pcmcia.h | 49 - drivers/comedi/comedi_usb.c | 3 +- drivers/comedi/comedi_usb.h | 42 - drivers/comedi/comedidev.h | 1054 -------------- drivers/comedi/comedilib.h | 26 - drivers/comedi/drivers.c | 3 +- drivers/comedi/drivers/8255.c | 2 +- drivers/comedi/drivers/8255_pci.c | 3 +- drivers/comedi/drivers/addi_apci_1032.c | 2 +- drivers/comedi/drivers/addi_apci_1500.c | 2 +- drivers/comedi/drivers/addi_apci_1516.c | 2 +- drivers/comedi/drivers/addi_apci_1564.c | 2 +- drivers/comedi/drivers/addi_apci_16xx.c | 3 +- drivers/comedi/drivers/addi_apci_2032.c | 2 +- drivers/comedi/drivers/addi_apci_2200.c | 2 +- drivers/comedi/drivers/addi_apci_3120.c | 2 +- drivers/comedi/drivers/addi_apci_3501.c | 2 +- drivers/comedi/drivers/addi_apci_3xxx.c | 3 +- drivers/comedi/drivers/addi_watchdog.c | 2 +- drivers/comedi/drivers/adl_pci6208.c | 3 +- drivers/comedi/drivers/adl_pci7x3x.c | 3 +- drivers/comedi/drivers/adl_pci8164.c | 3 +- drivers/comedi/drivers/adl_pci9111.c | 3 +- drivers/comedi/drivers/adl_pci9118.c | 3 +- drivers/comedi/drivers/adq12b.c | 3 +- drivers/comedi/drivers/adv_pci1710.c | 3 +- drivers/comedi/drivers/adv_pci1720.c | 3 +- drivers/comedi/drivers/adv_pci1723.c | 3 +- drivers/comedi/drivers/adv_pci1724.c | 3 +- drivers/comedi/drivers/adv_pci1760.c | 3 +- drivers/comedi/drivers/adv_pci_dio.c | 3 +- drivers/comedi/drivers/aio_aio12_8.c | 2 +- drivers/comedi/drivers/aio_iiro_16.c | 3 +- drivers/comedi/drivers/amplc_dio200.c | 2 +- drivers/comedi/drivers/amplc_dio200_common.c | 3 +- drivers/comedi/drivers/amplc_dio200_pci.c | 3 +- drivers/comedi/drivers/amplc_pc236.c | 3 +- drivers/comedi/drivers/amplc_pc236_common.c | 3 +- drivers/comedi/drivers/amplc_pc263.c | 2 +- drivers/comedi/drivers/amplc_pci224.c | 3 +- drivers/comedi/drivers/amplc_pci230.c | 3 +- drivers/comedi/drivers/amplc_pci236.c | 3 +- drivers/comedi/drivers/amplc_pci263.c | 3 +- drivers/comedi/drivers/c6xdigio.c | 3 +- drivers/comedi/drivers/cb_das16_cs.c | 3 +- drivers/comedi/drivers/cb_pcidas.c | 3 +- drivers/comedi/drivers/cb_pcidas64.c | 3 +- drivers/comedi/drivers/cb_pcidda.c | 3 +- drivers/comedi/drivers/cb_pcimdas.c | 3 +- drivers/comedi/drivers/cb_pcimdda.c | 3 +- drivers/comedi/drivers/comedi_8254.c | 3 +- drivers/comedi/drivers/comedi_8255.c | 2 +- drivers/comedi/drivers/comedi_bond.c | 6 +- drivers/comedi/drivers/comedi_isadma.c | 3 +- drivers/comedi/drivers/comedi_parport.c | 3 +- drivers/comedi/drivers/comedi_test.c | 4 +- drivers/comedi/drivers/contec_pci_dio.c | 3 +- drivers/comedi/drivers/dac02.c | 3 +- drivers/comedi/drivers/daqboard2000.c | 3 +- drivers/comedi/drivers/das08.c | 3 +- drivers/comedi/drivers/das08_cs.c | 3 +- drivers/comedi/drivers/das08_isa.c | 2 +- drivers/comedi/drivers/das08_pci.c | 3 +- drivers/comedi/drivers/das16.c | 3 +- drivers/comedi/drivers/das16m1.c | 2 +- drivers/comedi/drivers/das1800.c | 3 +- drivers/comedi/drivers/das6402.c | 3 +- drivers/comedi/drivers/das800.c | 3 +- drivers/comedi/drivers/dmm32at.c | 2 +- drivers/comedi/drivers/dt2801.c | 2 +- drivers/comedi/drivers/dt2811.c | 3 +- drivers/comedi/drivers/dt2814.c | 3 +- drivers/comedi/drivers/dt2815.c | 3 +- drivers/comedi/drivers/dt2817.c | 2 +- drivers/comedi/drivers/dt282x.c | 3 +- drivers/comedi/drivers/dt3000.c | 3 +- drivers/comedi/drivers/dt9812.c | 3 +- drivers/comedi/drivers/dyna_pci10xx.c | 3 +- drivers/comedi/drivers/fl512.c | 3 +- drivers/comedi/drivers/gsc_hpdi.c | 3 +- drivers/comedi/drivers/icp_multi.c | 3 +- drivers/comedi/drivers/ii_pci20kc.c | 2 +- drivers/comedi/drivers/jr3_pci.c | 3 +- drivers/comedi/drivers/ke_counter.c | 3 +- drivers/comedi/drivers/me4000.c | 3 +- drivers/comedi/drivers/me_daq.c | 3 +- drivers/comedi/drivers/mf6x4.c | 3 +- drivers/comedi/drivers/mite.c | 3 +- drivers/comedi/drivers/mpc624.c | 3 +- drivers/comedi/drivers/multiq3.c | 3 +- drivers/comedi/drivers/ni_6527.c | 3 +- drivers/comedi/drivers/ni_65xx.c | 3 +- drivers/comedi/drivers/ni_660x.c | 3 +- drivers/comedi/drivers/ni_670x.c | 3 +- drivers/comedi/drivers/ni_at_a2150.c | 3 +- drivers/comedi/drivers/ni_at_ao.c | 3 +- drivers/comedi/drivers/ni_atmio.c | 3 +- drivers/comedi/drivers/ni_atmio16d.c | 2 +- drivers/comedi/drivers/ni_daq_700.c | 3 +- drivers/comedi/drivers/ni_daq_dio24.c | 2 +- drivers/comedi/drivers/ni_labpc.c | 3 +- drivers/comedi/drivers/ni_labpc_common.c | 3 +- drivers/comedi/drivers/ni_labpc_cs.c | 3 +- drivers/comedi/drivers/ni_labpc_isadma.c | 3 +- drivers/comedi/drivers/ni_labpc_pci.c | 3 +- drivers/comedi/drivers/ni_mio_cs.c | 2 +- drivers/comedi/drivers/ni_pcidio.c | 3 +- drivers/comedi/drivers/ni_pcimio.c | 4 +- drivers/comedi/drivers/ni_routes.c | 3 +- drivers/comedi/drivers/ni_routes.h | 2 +- .../comedi/drivers/ni_routing/ni_route_values.h | 2 +- drivers/comedi/drivers/ni_tio.h | 2 +- drivers/comedi/drivers/ni_usb6501.c | 3 +- drivers/comedi/drivers/pcl711.c | 3 +- drivers/comedi/drivers/pcl724.c | 2 +- drivers/comedi/drivers/pcl726.c | 3 +- drivers/comedi/drivers/pcl730.c | 2 +- drivers/comedi/drivers/pcl812.c | 3 +- drivers/comedi/drivers/pcl816.c | 3 +- drivers/comedi/drivers/pcl818.c | 3 +- drivers/comedi/drivers/pcm3724.c | 2 +- drivers/comedi/drivers/pcmad.c | 2 +- drivers/comedi/drivers/pcmda12.c | 2 +- drivers/comedi/drivers/pcmmio.c | 3 +- drivers/comedi/drivers/pcmuio.c | 3 +- drivers/comedi/drivers/quatech_daqp_cs.c | 3 +- drivers/comedi/drivers/rtd520.c | 3 +- drivers/comedi/drivers/rti800.c | 2 +- drivers/comedi/drivers/rti802.c | 2 +- drivers/comedi/drivers/s526.c | 2 +- drivers/comedi/drivers/s626.c | 3 +- drivers/comedi/drivers/ssv_dnp.c | 2 +- drivers/comedi/drivers/usbdux.c | 3 +- drivers/comedi/drivers/usbduxfast.c | 2 +- drivers/comedi/drivers/usbduxsigma.c | 3 +- drivers/comedi/drivers/vmk80xx.c | 3 +- drivers/comedi/kcomedilib/kcomedilib_main.c | 6 +- drivers/comedi/proc.c | 2 +- drivers/comedi/range.c | 2 +- include/linux/comedi/comedi_pci.h | 56 + include/linux/comedi/comedi_pcmcia.h | 48 + include/linux/comedi/comedi_usb.h | 41 + include/linux/comedi/comedidev.h | 1053 ++++++++++++++ include/linux/comedi/comedilib.h | 26 + include/uapi/linux/comedi.h | 1528 ++++++++++++++++++++ 152 files changed, 2897 insertions(+), 2999 deletions(-) delete mode 100644 drivers/comedi/comedi.h delete mode 100644 drivers/comedi/comedi_pci.h delete mode 100644 drivers/comedi/comedi_pcmcia.h delete mode 100644 drivers/comedi/comedi_usb.h delete mode 100644 drivers/comedi/comedidev.h delete mode 100644 drivers/comedi/comedilib.h create mode 100644 include/linux/comedi/comedi_pci.h create mode 100644 include/linux/comedi/comedi_pcmcia.h create mode 100644 include/linux/comedi/comedi_usb.h create mode 100644 include/linux/comedi/comedidev.h create mode 100644 include/linux/comedi/comedilib.h create mode 100644 include/uapi/linux/comedi.h (limited to 'include/uapi') diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..f9b50d136c90 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4713,6 +4713,8 @@ M: Ian Abbott M: H Hartley Sweeten S: Odd Fixes F: drivers/comedi/ +F: include/linux/comedi/ +F: include/uapi/linux/comedi.h COMMON CLK FRAMEWORK M: Michael Turquette diff --git a/drivers/comedi/comedi.h b/drivers/comedi/comedi.h deleted file mode 100644 index b5d00a006dbb..000000000000 --- a/drivers/comedi/comedi.h +++ /dev/null @@ -1,1528 +0,0 @@ -/* SPDX-License-Identifier: LGPL-2.0+ */ -/* - * comedi.h - * header file for COMEDI user API - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1998-2001 David A. Schleef - */ - -#ifndef _COMEDI_H -#define _COMEDI_H - -#define COMEDI_MAJORVERSION 0 -#define COMEDI_MINORVERSION 7 -#define COMEDI_MICROVERSION 76 -#define VERSION "0.7.76" - -/* comedi's major device number */ -#define COMEDI_MAJOR 98 - -/* - * maximum number of minor devices. This can be increased, although - * kernel structures are currently statically allocated, thus you - * don't want this to be much more than you actually use. - */ -#define COMEDI_NDEVICES 16 - -/* number of config options in the config structure */ -#define COMEDI_NDEVCONFOPTS 32 - -/* - * NOTE: 'comedi_config --init-data' is deprecated - * - * The following indexes in the config options were used by - * comedi_config to pass firmware blobs from user space to the - * comedi drivers. The request_firmware() hotplug interface is - * now used by all comedi drivers instead. - */ - -/* length of nth chunk of firmware data -*/ -#define COMEDI_DEVCONF_AUX_DATA3_LENGTH 25 -#define COMEDI_DEVCONF_AUX_DATA2_LENGTH 26 -#define COMEDI_DEVCONF_AUX_DATA1_LENGTH 27 -#define COMEDI_DEVCONF_AUX_DATA0_LENGTH 28 -/* most significant 32 bits of pointer address (if needed) */ -#define COMEDI_DEVCONF_AUX_DATA_HI 29 -/* least significant 32 bits of pointer address */ -#define COMEDI_DEVCONF_AUX_DATA_LO 30 -#define COMEDI_DEVCONF_AUX_DATA_LENGTH 31 /* total data length */ - -/* max length of device and driver names */ -#define COMEDI_NAMELEN 20 - -/* packs and unpacks a channel/range number */ - -#define CR_PACK(chan, rng, aref) \ - ((((aref) & 0x3) << 24) | (((rng) & 0xff) << 16) | (chan)) -#define CR_PACK_FLAGS(chan, range, aref, flags) \ - (CR_PACK(chan, range, aref) | ((flags) & CR_FLAGS_MASK)) - -#define CR_CHAN(a) ((a) & 0xffff) -#define CR_RANGE(a) (((a) >> 16) & 0xff) -#define CR_AREF(a) (((a) >> 24) & 0x03) - -#define CR_FLAGS_MASK 0xfc000000 -#define CR_ALT_FILTER 0x04000000 -#define CR_DITHER CR_ALT_FILTER -#define CR_DEGLITCH CR_ALT_FILTER -#define CR_ALT_SOURCE 0x08000000 -#define CR_EDGE 0x40000000 -#define CR_INVERT 0x80000000 - -#define AREF_GROUND 0x00 /* analog ref = analog ground */ -#define AREF_COMMON 0x01 /* analog ref = analog common */ -#define AREF_DIFF 0x02 /* analog ref = differential */ -#define AREF_OTHER 0x03 /* analog ref = other (undefined) */ - -/* counters -- these are arbitrary values */ -#define GPCT_RESET 0x0001 -#define GPCT_SET_SOURCE 0x0002 -#define GPCT_SET_GATE 0x0004 -#define GPCT_SET_DIRECTION 0x0008 -#define GPCT_SET_OPERATION 0x0010 -#define GPCT_ARM 0x0020 -#define GPCT_DISARM 0x0040 -#define GPCT_GET_INT_CLK_FRQ 0x0080 - -#define GPCT_INT_CLOCK 0x0001 -#define GPCT_EXT_PIN 0x0002 -#define GPCT_NO_GATE 0x0004 -#define GPCT_UP 0x0008 -#define GPCT_DOWN 0x0010 -#define GPCT_HWUD 0x0020 -#define GPCT_SIMPLE_EVENT 0x0040 -#define GPCT_SINGLE_PERIOD 0x0080 -#define GPCT_SINGLE_PW 0x0100 -#define GPCT_CONT_PULSE_OUT 0x0200 -#define GPCT_SINGLE_PULSE_OUT 0x0400 - -/* instructions */ - -#define INSN_MASK_WRITE 0x8000000 -#define INSN_MASK_READ 0x4000000 -#define INSN_MASK_SPECIAL 0x2000000 - -#define INSN_READ (0 | INSN_MASK_READ) -#define INSN_WRITE (1 | INSN_MASK_WRITE) -#define INSN_BITS (2 | INSN_MASK_READ | INSN_MASK_WRITE) -#define INSN_CONFIG (3 | INSN_MASK_READ | INSN_MASK_WRITE) -#define INSN_DEVICE_CONFIG (INSN_CONFIG | INSN_MASK_SPECIAL) -#define INSN_GTOD (4 | INSN_MASK_READ | INSN_MASK_SPECIAL) -#define INSN_WAIT (5 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) -#define INSN_INTTRIG (6 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) - -/* command flags */ -/* These flags are used in comedi_cmd structures */ - -#define CMDF_BOGUS 0x00000001 /* do the motions */ - -/* try to use a real-time interrupt while performing command */ -#define CMDF_PRIORITY 0x00000008 - -/* wake up on end-of-scan events */ -#define CMDF_WAKE_EOS 0x00000020 - -#define CMDF_WRITE 0x00000040 - -#define CMDF_RAWDATA 0x00000080 - -/* timer rounding definitions */ -#define CMDF_ROUND_MASK 0x00030000 -#define CMDF_ROUND_NEAREST 0x00000000 -#define CMDF_ROUND_DOWN 0x00010000 -#define CMDF_ROUND_UP 0x00020000 -#define CMDF_ROUND_UP_NEXT 0x00030000 - -#define COMEDI_EV_START 0x00040000 -#define COMEDI_EV_SCAN_BEGIN 0x00080000 -#define COMEDI_EV_CONVERT 0x00100000 -#define COMEDI_EV_SCAN_END 0x00200000 -#define COMEDI_EV_STOP 0x00400000 - -/* compatibility definitions */ -#define TRIG_BOGUS CMDF_BOGUS -#define TRIG_RT CMDF_PRIORITY -#define TRIG_WAKE_EOS CMDF_WAKE_EOS -#define TRIG_WRITE CMDF_WRITE -#define TRIG_ROUND_MASK CMDF_ROUND_MASK -#define TRIG_ROUND_NEAREST CMDF_ROUND_NEAREST -#define TRIG_ROUND_DOWN CMDF_ROUND_DOWN -#define TRIG_ROUND_UP CMDF_ROUND_UP -#define TRIG_ROUND_UP_NEXT CMDF_ROUND_UP_NEXT - -/* trigger sources */ - -#define TRIG_ANY 0xffffffff -#define TRIG_INVALID 0x00000000 - -#define TRIG_NONE 0x00000001 /* never trigger */ -#define TRIG_NOW 0x00000002 /* trigger now + N ns */ -#define TRIG_FOLLOW 0x00000004 /* trigger on next lower level trig */ -#define TRIG_TIME 0x00000008 /* trigger at time N ns */ -#define TRIG_TIMER 0x00000010 /* trigger at rate N ns */ -#define TRIG_COUNT 0x00000020 /* trigger when count reaches N */ -#define TRIG_EXT 0x00000040 /* trigger on external signal N */ -#define TRIG_INT 0x00000080 /* trigger on comedi-internal signal N */ -#define TRIG_OTHER 0x00000100 /* driver defined */ - -/* subdevice flags */ - -#define SDF_BUSY 0x0001 /* device is busy */ -#define SDF_BUSY_OWNER 0x0002 /* device is busy with your job */ -#define SDF_LOCKED 0x0004 /* subdevice is locked */ -#define SDF_LOCK_OWNER 0x0008 /* you own lock */ -#define SDF_MAXDATA 0x0010 /* maxdata depends on channel */ -#define SDF_FLAGS 0x0020 /* flags depend on channel */ -#define SDF_RANGETYPE 0x0040 /* range type depends on channel */ -#define SDF_PWM_COUNTER 0x0080 /* PWM can automatically switch off */ -#define SDF_PWM_HBRIDGE 0x0100 /* PWM is signed (H-bridge) */ -#define SDF_CMD 0x1000 /* can do commands (deprecated) */ -#define SDF_SOFT_CALIBRATED 0x2000 /* subdevice uses software calibration */ -#define SDF_CMD_WRITE 0x4000 /* can do output commands */ -#define SDF_CMD_READ 0x8000 /* can do input commands */ - -/* subdevice can be read (e.g. analog input) */ -#define SDF_READABLE 0x00010000 -/* subdevice can be written (e.g. analog output) */ -#define SDF_WRITABLE 0x00020000 -#define SDF_WRITEABLE SDF_WRITABLE /* spelling error in API */ -/* subdevice does not have externally visible lines */ -#define SDF_INTERNAL 0x00040000 -#define SDF_GROUND 0x00100000 /* can do aref=ground */ -#define SDF_COMMON 0x00200000 /* can do aref=common */ -#define SDF_DIFF 0x00400000 /* can do aref=diff */ -#define SDF_OTHER 0x00800000 /* can do aref=other */ -#define SDF_DITHER 0x01000000 /* can do dithering */ -#define SDF_DEGLITCH 0x02000000 /* can do deglitching */ -#define SDF_MMAP 0x04000000 /* can do mmap() */ -#define SDF_RUNNING 0x08000000 /* subdevice is acquiring data */ -#define SDF_LSAMPL 0x10000000 /* subdevice uses 32-bit samples */ -#define SDF_PACKED 0x20000000 /* subdevice can do packed DIO */ - -/* subdevice types */ - -/** - * enum comedi_subdevice_type - COMEDI subdevice types - * @COMEDI_SUBD_UNUSED: Unused subdevice. - * @COMEDI_SUBD_AI: Analog input. - * @COMEDI_SUBD_AO: Analog output. - * @COMEDI_SUBD_DI: Digital input. - * @COMEDI_SUBD_DO: Digital output. - * @COMEDI_SUBD_DIO: Digital input/output. - * @COMEDI_SUBD_COUNTER: Counter. - * @COMEDI_SUBD_TIMER: Timer. - * @COMEDI_SUBD_MEMORY: Memory, EEPROM, DPRAM. - * @COMEDI_SUBD_CALIB: Calibration DACs. - * @COMEDI_SUBD_PROC: Processor, DSP. - * @COMEDI_SUBD_SERIAL: Serial I/O. - * @COMEDI_SUBD_PWM: Pulse-Width Modulation output. - */ -enum comedi_subdevice_type { - COMEDI_SUBD_UNUSED, - COMEDI_SUBD_AI, - COMEDI_SUBD_AO, - COMEDI_SUBD_DI, - COMEDI_SUBD_DO, - COMEDI_SUBD_DIO, - COMEDI_SUBD_COUNTER, - COMEDI_SUBD_TIMER, - COMEDI_SUBD_MEMORY, - COMEDI_SUBD_CALIB, - COMEDI_SUBD_PROC, - COMEDI_SUBD_SERIAL, - COMEDI_SUBD_PWM -}; - -/* configuration instructions */ - -/** - * enum comedi_io_direction - COMEDI I/O directions - * @COMEDI_INPUT: Input. - * @COMEDI_OUTPUT: Output. - * @COMEDI_OPENDRAIN: Open-drain (or open-collector) output. - * - * These are used by the %INSN_CONFIG_DIO_QUERY configuration instruction to - * report a direction. They may also be used in other places where a direction - * needs to be specified. - */ -enum comedi_io_direction { - COMEDI_INPUT = 0, - COMEDI_OUTPUT = 1, - COMEDI_OPENDRAIN = 2 -}; - -/** - * enum configuration_ids - COMEDI configuration instruction codes - * @INSN_CONFIG_DIO_INPUT: Configure digital I/O as input. - * @INSN_CONFIG_DIO_OUTPUT: Configure digital I/O as output. - * @INSN_CONFIG_DIO_OPENDRAIN: Configure digital I/O as open-drain (or open - * collector) output. - * @INSN_CONFIG_ANALOG_TRIG: Configure analog trigger. - * @INSN_CONFIG_ALT_SOURCE: Configure alternate input source. - * @INSN_CONFIG_DIGITAL_TRIG: Configure digital trigger. - * @INSN_CONFIG_BLOCK_SIZE: Configure block size for DMA transfers. - * @INSN_CONFIG_TIMER_1: Configure divisor for external clock. - * @INSN_CONFIG_FILTER: Configure a filter. - * @INSN_CONFIG_CHANGE_NOTIFY: Configure change notification for digital - * inputs. (New drivers should use - * %INSN_CONFIG_DIGITAL_TRIG instead.) - * @INSN_CONFIG_SERIAL_CLOCK: Configure clock for serial I/O. - * @INSN_CONFIG_BIDIRECTIONAL_DATA: Send and receive byte over serial I/O. - * @INSN_CONFIG_DIO_QUERY: Query direction of digital I/O channel. - * @INSN_CONFIG_PWM_OUTPUT: Configure pulse-width modulator output. - * @INSN_CONFIG_GET_PWM_OUTPUT: Get pulse-width modulator output configuration. - * @INSN_CONFIG_ARM: Arm a subdevice or channel. - * @INSN_CONFIG_DISARM: Disarm a subdevice or channel. - * @INSN_CONFIG_GET_COUNTER_STATUS: Get counter status. - * @INSN_CONFIG_RESET: Reset a subdevice or channel. - * @INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR: Configure counter/timer as - * single pulse generator. - * @INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR: Configure counter/timer as - * pulse train generator. - * @INSN_CONFIG_GPCT_QUADRATURE_ENCODER: Configure counter as a quadrature - * encoder. - * @INSN_CONFIG_SET_GATE_SRC: Set counter/timer gate source. - * @INSN_CONFIG_GET_GATE_SRC: Get counter/timer gate source. - * @INSN_CONFIG_SET_CLOCK_SRC: Set counter/timer master clock source. - * @INSN_CONFIG_GET_CLOCK_SRC: Get counter/timer master clock source. - * @INSN_CONFIG_SET_OTHER_SRC: Set counter/timer "other" source. - * @INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE: Get size (in bytes) of subdevice's - * on-board FIFOs used during streaming - * input/output. - * @INSN_CONFIG_SET_COUNTER_MODE: Set counter/timer mode. - * @INSN_CONFIG_8254_SET_MODE: (Deprecated) Same as - * %INSN_CONFIG_SET_COUNTER_MODE. - * @INSN_CONFIG_8254_READ_STATUS: Read status of 8254 counter channel. - * @INSN_CONFIG_SET_ROUTING: Set routing for a channel. - * @INSN_CONFIG_GET_ROUTING: Get routing for a channel. - * @INSN_CONFIG_PWM_SET_PERIOD: Set PWM period in nanoseconds. - * @INSN_CONFIG_PWM_GET_PERIOD: Get PWM period in nanoseconds. - * @INSN_CONFIG_GET_PWM_STATUS: Get PWM status. - * @INSN_CONFIG_PWM_SET_H_BRIDGE: Set PWM H bridge duty cycle and polarity for - * a relay simultaneously. - * @INSN_CONFIG_PWM_GET_H_BRIDGE: Get PWM H bridge duty cycle and polarity. - * @INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS: Get the hardware timing restraints, - * regardless of trigger sources. - */ -enum configuration_ids { - INSN_CONFIG_DIO_INPUT = COMEDI_INPUT, - INSN_CONFIG_DIO_OUTPUT = COMEDI_OUTPUT, - INSN_CONFIG_DIO_OPENDRAIN = COMEDI_OPENDRAIN, - INSN_CONFIG_ANALOG_TRIG = 16, -/* INSN_CONFIG_WAVEFORM = 17, */ -/* INSN_CONFIG_TRIG = 18, */ -/* INSN_CONFIG_COUNTER = 19, */ - INSN_CONFIG_ALT_SOURCE = 20, - INSN_CONFIG_DIGITAL_TRIG = 21, - INSN_CONFIG_BLOCK_SIZE = 22, - INSN_CONFIG_TIMER_1 = 23, - INSN_CONFIG_FILTER = 24, - INSN_CONFIG_CHANGE_NOTIFY = 25, - - INSN_CONFIG_SERIAL_CLOCK = 26, /*ALPHA*/ - INSN_CONFIG_BIDIRECTIONAL_DATA = 27, - INSN_CONFIG_DIO_QUERY = 28, - INSN_CONFIG_PWM_OUTPUT = 29, - INSN_CONFIG_GET_PWM_OUTPUT = 30, - INSN_CONFIG_ARM = 31, - INSN_CONFIG_DISARM = 32, - INSN_CONFIG_GET_COUNTER_STATUS = 33, - INSN_CONFIG_RESET = 34, - INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR = 1001, - INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR = 1002, - INSN_CONFIG_GPCT_QUADRATURE_ENCODER = 1003, - INSN_CONFIG_SET_GATE_SRC = 2001, - INSN_CONFIG_GET_GATE_SRC = 2002, - INSN_CONFIG_SET_CLOCK_SRC = 2003, - INSN_CONFIG_GET_CLOCK_SRC = 2004, - INSN_CONFIG_SET_OTHER_SRC = 2005, - INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE = 2006, - INSN_CONFIG_SET_COUNTER_MODE = 4097, - INSN_CONFIG_8254_SET_MODE = INSN_CONFIG_SET_COUNTER_MODE, - INSN_CONFIG_8254_READ_STATUS = 4098, - INSN_CONFIG_SET_ROUTING = 4099, - INSN_CONFIG_GET_ROUTING = 4109, - INSN_CONFIG_PWM_SET_PERIOD = 5000, - INSN_CONFIG_PWM_GET_PERIOD = 5001, - INSN_CONFIG_GET_PWM_STATUS = 5002, - INSN_CONFIG_PWM_SET_H_BRIDGE = 5003, - INSN_CONFIG_PWM_GET_H_BRIDGE = 5004, - INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS = 5005, -}; - -/** - * enum device_configuration_ids - COMEDI configuration instruction codes global - * to an entire device. - * @INSN_DEVICE_CONFIG_TEST_ROUTE: Validate the possibility of a - * globally-named route - * @INSN_DEVICE_CONFIG_CONNECT_ROUTE: Connect a globally-named route - * @INSN_DEVICE_CONFIG_DISCONNECT_ROUTE:Disconnect a globally-named route - * @INSN_DEVICE_CONFIG_GET_ROUTES: Get a list of all globally-named routes - * that are valid for a particular device. - */ -enum device_config_route_ids { - INSN_DEVICE_CONFIG_TEST_ROUTE = 0, - INSN_DEVICE_CONFIG_CONNECT_ROUTE = 1, - INSN_DEVICE_CONFIG_DISCONNECT_ROUTE = 2, - INSN_DEVICE_CONFIG_GET_ROUTES = 3, -}; - -/** - * enum comedi_digital_trig_op - operations for configuring a digital trigger - * @COMEDI_DIGITAL_TRIG_DISABLE: Return digital trigger to its default, - * inactive, unconfigured state. - * @COMEDI_DIGITAL_TRIG_ENABLE_EDGES: Set rising and/or falling edge inputs - * that each can fire the trigger. - * @COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: Set a combination of high and/or low - * level inputs that can fire the trigger. - * - * These are used with the %INSN_CONFIG_DIGITAL_TRIG configuration instruction. - * The data for the configuration instruction is as follows... - * - * data[%0] = %INSN_CONFIG_DIGITAL_TRIG - * - * data[%1] = trigger ID - * - * data[%2] = configuration operation - * - * data[%3] = configuration parameter 1 - * - * data[%4] = configuration parameter 2 - * - * data[%5] = configuration parameter 3 - * - * The trigger ID (data[%1]) is used to differentiate multiple digital triggers - * belonging to the same subdevice. The configuration operation (data[%2]) is - * one of the enum comedi_digital_trig_op values. The configuration - * parameters (data[%3], data[%4], and data[%5]) depend on the operation; they - * are not used with %COMEDI_DIGITAL_TRIG_DISABLE. - * - * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES and %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, - * configuration parameter 1 (data[%3]) contains a "left-shift" value that - * specifies the input corresponding to bit 0 of configuration parameters 2 - * and 3. This is useful if the trigger has more than 32 inputs. - * - * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES, configuration parameter 2 (data[%4]) - * specifies which of up to 32 inputs have rising-edge sensitivity, and - * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs - * have falling-edge sensitivity that can fire the trigger. - * - * For %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, configuration parameter 2 (data[%4]) - * specifies which of up to 32 inputs must be at a high level, and - * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs - * must be at a low level for the trigger to fire. - * - * Some sequences of %INSN_CONFIG_DIGITAL_TRIG instructions may have a (partly) - * accumulative effect, depending on the low-level driver. This is useful - * when setting up a trigger that has more than 32 inputs, or has a combination - * of edge- and level-triggered inputs. - */ -enum comedi_digital_trig_op { - COMEDI_DIGITAL_TRIG_DISABLE = 0, - COMEDI_DIGITAL_TRIG_ENABLE_EDGES = 1, - COMEDI_DIGITAL_TRIG_ENABLE_LEVELS = 2 -}; - -/** - * enum comedi_support_level - support level for a COMEDI feature - * @COMEDI_UNKNOWN_SUPPORT: Unspecified support for feature. - * @COMEDI_SUPPORTED: Feature is supported. - * @COMEDI_UNSUPPORTED: Feature is unsupported. - */ -enum comedi_support_level { - COMEDI_UNKNOWN_SUPPORT = 0, - COMEDI_SUPPORTED, - COMEDI_UNSUPPORTED -}; - -/** - * enum comedi_counter_status_flags - counter status bits - * @COMEDI_COUNTER_ARMED: Counter is armed. - * @COMEDI_COUNTER_COUNTING: Counter is counting. - * @COMEDI_COUNTER_TERMINAL_COUNT: Counter reached terminal count. - * - * These bitwise values are used by the %INSN_CONFIG_GET_COUNTER_STATUS - * configuration instruction to report the status of a counter. - */ -enum comedi_counter_status_flags { - COMEDI_COUNTER_ARMED = 0x1, - COMEDI_COUNTER_COUNTING = 0x2, - COMEDI_COUNTER_TERMINAL_COUNT = 0x4, -}; - -/* ioctls */ - -#define CIO 'd' -#define COMEDI_DEVCONFIG _IOW(CIO, 0, struct comedi_devconfig) -#define COMEDI_DEVINFO _IOR(CIO, 1, struct comedi_devinfo) -#define COMEDI_SUBDINFO _IOR(CIO, 2, struct comedi_subdinfo) -#define COMEDI_CHANINFO _IOR(CIO, 3, struct comedi_chaninfo) -/* _IOWR(CIO, 4, ...) is reserved */ -#define COMEDI_LOCK _IO(CIO, 5) -#define COMEDI_UNLOCK _IO(CIO, 6) -#define COMEDI_CANCEL _IO(CIO, 7) -#define COMEDI_RANGEINFO _IOR(CIO, 8, struct comedi_rangeinfo) -#define COMEDI_CMD _IOR(CIO, 9, struct comedi_cmd) -#define COMEDI_CMDTEST _IOR(CIO, 10, struct comedi_cmd) -#define COMEDI_INSNLIST _IOR(CIO, 11, struct comedi_insnlist) -#define COMEDI_INSN _IOR(CIO, 12, struct comedi_insn) -#define COMEDI_BUFCONFIG _IOR(CIO, 13, struct comedi_bufconfig) -#define COMEDI_BUFINFO _IOWR(CIO, 14, struct comedi_bufinfo) -#define COMEDI_POLL _IO(CIO, 15) -#define COMEDI_SETRSUBD _IO(CIO, 16) -#define COMEDI_SETWSUBD _IO(CIO, 17) - -/* structures */ - -/** - * struct comedi_insn - COMEDI instruction - * @insn: COMEDI instruction type (%INSN_xxx). - * @n: Length of @data[]. - * @data: Pointer to data array operated on by the instruction. - * @subdev: Subdevice index. - * @chanspec: A packed "chanspec" value consisting of channel number, - * analog range index, analog reference type, and flags. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_INSN ioctl, and indirectly with the - * %COMEDI_INSNLIST ioctl. - */ -struct comedi_insn { - unsigned int insn; - unsigned int n; - unsigned int __user *data; - unsigned int subdev; - unsigned int chanspec; - unsigned int unused[3]; -}; - -/** - * struct comedi_insnlist - list of COMEDI instructions - * @n_insns: Number of COMEDI instructions. - * @insns: Pointer to array COMEDI instructions. - * - * This is used with the %COMEDI_INSNLIST ioctl. - */ -struct comedi_insnlist { - unsigned int n_insns; - struct comedi_insn __user *insns; -}; - -/** - * struct comedi_cmd - COMEDI asynchronous acquisition command details - * @subdev: Subdevice index. - * @flags: Command flags (%CMDF_xxx). - * @start_src: "Start acquisition" trigger source (%TRIG_xxx). - * @start_arg: "Start acquisition" trigger argument. - * @scan_begin_src: "Scan begin" trigger source. - * @scan_begin_arg: "Scan begin" trigger argument. - * @convert_src: "Convert" trigger source. - * @convert_arg: "Convert" trigger argument. - * @scan_end_src: "Scan end" trigger source. - * @scan_end_arg: "Scan end" trigger argument. - * @stop_src: "Stop acquisition" trigger source. - * @stop_arg: "Stop acquisition" trigger argument. - * @chanlist: Pointer to array of "chanspec" values, containing a - * sequence of channel numbers packed with analog range - * index, etc. - * @chanlist_len: Number of channels in sequence. - * @data: Pointer to miscellaneous set-up data (not used). - * @data_len: Length of miscellaneous set-up data. - * - * This is used with the %COMEDI_CMD or %COMEDI_CMDTEST ioctl to set-up - * or validate an asynchronous acquisition command. The ioctl may modify - * the &struct comedi_cmd and copy it back to the caller. - * - * Optional command @flags values that can be ORed together... - * - * %CMDF_BOGUS - makes %COMEDI_CMD ioctl return error %EAGAIN instead of - * starting the command. - * - * %CMDF_PRIORITY - requests "hard real-time" processing (which is not - * supported in this version of COMEDI). - * - * %CMDF_WAKE_EOS - requests the command makes data available for reading - * after every "scan" period. - * - * %CMDF_WRITE - marks the command as being in the "write" (to device) - * direction. This does not need to be specified by the caller unless the - * subdevice supports commands in either direction. - * - * %CMDF_RAWDATA - prevents the command from "munging" the data between the - * COMEDI sample format and the raw hardware sample format. - * - * %CMDF_ROUND_NEAREST - requests timing periods to be rounded to nearest - * supported values. - * - * %CMDF_ROUND_DOWN - requests timing periods to be rounded down to supported - * values (frequencies rounded up). - * - * %CMDF_ROUND_UP - requests timing periods to be rounded up to supported - * values (frequencies rounded down). - * - * Trigger source values for @start_src, @scan_begin_src, @convert_src, - * @scan_end_src, and @stop_src... - * - * %TRIG_ANY - "all ones" value used to test which trigger sources are - * supported. - * - * %TRIG_INVALID - "all zeroes" value used to indicate that all requested - * trigger sources are invalid. - * - * %TRIG_NONE - never trigger (often used as a @stop_src value). - * - * %TRIG_NOW - trigger after '_arg' nanoseconds. - * - * %TRIG_FOLLOW - trigger follows another event. - * - * %TRIG_TIMER - trigger every '_arg' nanoseconds. - * - * %TRIG_COUNT - trigger when count '_arg' is reached. - * - * %TRIG_EXT - trigger on external signal specified by '_arg'. - * - * %TRIG_INT - trigger on internal, software trigger specified by '_arg'. - * - * %TRIG_OTHER - trigger on other, driver-defined signal specified by '_arg'. - */ -struct comedi_cmd { - unsigned int subdev; - unsigned int flags; - - unsigned int start_src; - unsigned int start_arg; - - unsigned int scan_begin_src; - unsigned int scan_begin_arg; - - unsigned int convert_src; - unsigned int convert_arg; - - unsigned int scan_end_src; - unsigned int scan_end_arg; - - unsigned int stop_src; - unsigned int stop_arg; - - unsigned int *chanlist; - unsigned int chanlist_len; - - short __user *data; - unsigned int data_len; -}; - -/** - * struct comedi_chaninfo - used to retrieve per-channel information - * @subdev: Subdevice index. - * @maxdata_list: Optional pointer to per-channel maximum data values. - * @flaglist: Optional pointer to per-channel flags. - * @rangelist: Optional pointer to per-channel range types. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_CHANINFO ioctl to get per-channel information - * for the subdevice. Use of this requires knowledge of the number of channels - * and subdevice flags obtained using the %COMEDI_SUBDINFO ioctl. - * - * The @maxdata_list member must be %NULL unless the %SDF_MAXDATA subdevice - * flag is set. The @flaglist member must be %NULL unless the %SDF_FLAGS - * subdevice flag is set. The @rangelist member must be %NULL unless the - * %SDF_RANGETYPE subdevice flag is set. Otherwise, the arrays they point to - * must be at least as long as the number of channels. - */ -struct comedi_chaninfo { - unsigned int subdev; - unsigned int __user *maxdata_list; - unsigned int __user *flaglist; - unsigned int __user *rangelist; - unsigned int unused[4]; -}; - -/** - * struct comedi_rangeinfo - used to retrieve the range table for a channel - * @range_type: Encodes subdevice index (bits 27:24), channel index - * (bits 23:16) and range table length (bits 15:0). - * @range_ptr: Pointer to array of @struct comedi_krange to be filled - * in with the range table for the channel or subdevice. - * - * This is used with the %COMEDI_RANGEINFO ioctl to retrieve the range table - * for a specific channel (if the subdevice has the %SDF_RANGETYPE flag set to - * indicate that the range table depends on the channel), or for the subdevice - * as a whole (if the %SDF_RANGETYPE flag is clear, indicating the range table - * is shared by all channels). - * - * The @range_type value is an input to the ioctl and comes from a previous - * use of the %COMEDI_SUBDINFO ioctl (if the %SDF_RANGETYPE flag is clear), - * or the %COMEDI_CHANINFO ioctl (if the %SDF_RANGETYPE flag is set). - */ -struct comedi_rangeinfo { - unsigned int range_type; - void __user *range_ptr; -}; - -/** - * struct comedi_krange - describes a range in a range table - * @min: Minimum value in millionths (1e-6) of a unit. - * @max: Maximum value in millionths (1e-6) of a unit. - * @flags: Indicates the units (in bits 7:0) OR'ed with optional flags. - * - * A range table is associated with a single channel, or with all channels in a - * subdevice, and a list of one or more ranges. A %struct comedi_krange - * describes the physical range of units for one of those ranges. Sample - * values in COMEDI are unsigned from %0 up to some 'maxdata' value. The - * mapping from sample values to physical units is assumed to be nomimally - * linear (for the purpose of describing the range), with sample value %0 - * mapping to @min, and the 'maxdata' sample value mapping to @max. - * - * The currently defined units are %UNIT_volt (%0), %UNIT_mA (%1), and - * %UNIT_none (%2). The @min and @max values are the physical range multiplied - * by 1e6, so a @max value of %1000000 (with %UNIT_volt) represents a maximal - * value of 1 volt. - * - * The only defined flag value is %RF_EXTERNAL (%0x100), indicating that the - * range needs to be multiplied by an external reference. - */ -struct comedi_krange { - int min; - int max; - unsigned int flags; -}; - -/** - * struct comedi_subdinfo - used to retrieve information about a subdevice - * @type: Type of subdevice from &enum comedi_subdevice_type. - * @n_chan: Number of channels the subdevice supports. - * @subd_flags: A mixture of static and dynamic flags describing - * aspects of the subdevice and its current state. - * @timer_type: Timer type. Always set to %5 ("nanosecond timer"). - * @len_chanlist: Maximum length of a channel list if the subdevice - * supports asynchronous acquisition commands. - * @maxdata: Maximum sample value for all channels if the - * %SDF_MAXDATA subdevice flag is clear. - * @flags: Channel flags for all channels if the %SDF_FLAGS - * subdevice flag is clear. - * @range_type: The range type for all channels if the %SDF_RANGETYPE - * subdevice flag is clear. Encodes the subdevice index - * (bits 27:24), a dummy channel index %0 (bits 23:16), - * and the range table length (bits 15:0). - * @settling_time_0: Not used. - * @insn_bits_support: Set to %COMEDI_SUPPORTED if the subdevice supports the - * %INSN_BITS instruction, or to %COMEDI_UNSUPPORTED if it - * does not. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_SUBDINFO ioctl which copies an array of - * &struct comedi_subdinfo back to user space, with one element per subdevice. - * Use of this requires knowledge of the number of subdevices obtained from - * the %COMEDI_DEVINFO ioctl. - * - * These are the @subd_flags values that may be ORed together... - * - * %SDF_BUSY - the subdevice is busy processing an asynchronous command or a - * synchronous instruction. - * - * %SDF_BUSY_OWNER - the subdevice is busy processing an asynchronous - * acquisition command started on the current file object (the file object - * issuing the %COMEDI_SUBDINFO ioctl). - * - * %SDF_LOCKED - the subdevice is locked by a %COMEDI_LOCK ioctl. - * - * %SDF_LOCK_OWNER - the subdevice is locked by a %COMEDI_LOCK ioctl from the - * current file object. - * - * %SDF_MAXDATA - maximum sample values are channel-specific. - * - * %SDF_FLAGS - channel flags are channel-specific. - * - * %SDF_RANGETYPE - range types are channel-specific. - * - * %SDF_PWM_COUNTER - PWM can switch off automatically. - * - * %SDF_PWM_HBRIDGE - or PWM is signed (H-bridge). - * - * %SDF_CMD - the subdevice supports asynchronous commands. - * - * %SDF_SOFT_CALIBRATED - the subdevice uses software calibration. - * - * %SDF_CMD_WRITE - the subdevice supports asynchronous commands in the output - * ("write") direction. - * - * %SDF_CMD_READ - the subdevice supports asynchronous commands in the input - * ("read") direction. - * - * %SDF_READABLE - the subdevice is readable (e.g. analog input). - * - * %SDF_WRITABLE (aliased as %SDF_WRITEABLE) - the subdevice is writable (e.g. - * analog output). - * - * %SDF_INTERNAL - the subdevice has no externally visible lines. - * - * %SDF_GROUND - the subdevice can use ground as an analog reference. - * - * %SDF_COMMON - the subdevice can use a common analog reference. - * - * %SDF_DIFF - the subdevice can use differential inputs (or outputs). - * - * %SDF_OTHER - the subdevice can use some other analog reference. - * - * %SDF_DITHER - the subdevice can do dithering. - * - * %SDF_DEGLITCH - the subdevice can do deglitching. - * - * %SDF_MMAP - this is never set. - * - * %SDF_RUNNING - an asynchronous command is still running. - * - * %SDF_LSAMPL - the subdevice uses "long" (32-bit) samples (for asynchronous - * command data). - * - * %SDF_PACKED - the subdevice packs several DIO samples into a single sample - * (for asynchronous command data). - * - * No "channel flags" (@flags) values are currently defined. - */ -struct comedi_subdinfo { - unsigned int type; - unsigned int n_chan; - unsigned int subd_flags; - unsigned int timer_type; - unsigned int len_chanlist; - unsigned int maxdata; - unsigned int flags; - unsigned int range_type; - unsigned int settling_time_0; - unsigned int insn_bits_support; - unsigned int unused[8]; -}; - -/** - * struct comedi_devinfo - used to retrieve information about a COMEDI device - * @version_code: COMEDI version code. - * @n_subdevs: Number of subdevices the device has. - * @driver_name: Null-terminated COMEDI driver name. - * @board_name: Null-terminated COMEDI board name. - * @read_subdevice: Index of the current "read" subdevice (%-1 if none). - * @write_subdevice: Index of the current "write" subdevice (%-1 if none). - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_DEVINFO ioctl to get basic information about - * the device. - */ -struct comedi_devinfo { - unsigned int version_code; - unsigned int n_subdevs; - char driver_name[COMEDI_NAMELEN]; - char board_name[COMEDI_NAMELEN]; - int read_subdevice; - int write_subdevice; - int unused[30]; -}; - -/** - * struct comedi_devconfig - used to configure a legacy COMEDI device - * @board_name: Null-terminated string specifying the type of board - * to configure. - * @options: An array of integer configuration options. - * - * This is used with the %COMEDI_DEVCONFIG ioctl to configure a "legacy" COMEDI - * device, such as an ISA card. Not all COMEDI drivers support this. Those - * that do either expect the specified board name to match one of a list of - * names registered with the COMEDI core, or expect the specified board name - * to match the COMEDI driver name itself. The configuration options are - * handled in a driver-specific manner. - */ -struct comedi_devconfig { - char board_name[COMEDI_NAMELEN]; - int options[COMEDI_NDEVCONFOPTS]; -}; - -/** - * struct comedi_bufconfig - used to set or get buffer size for a subdevice - * @subdevice: Subdevice index. - * @flags: Not used. - * @maximum_size: Maximum allowed buffer size. - * @size: Buffer size. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_BUFCONFIG ioctl to get or configure the - * maximum buffer size and current buffer size for a COMEDI subdevice that - * supports asynchronous commands. If the subdevice does not support - * asynchronous commands, @maximum_size and @size are ignored and set to 0. - * - * On ioctl input, non-zero values of @maximum_size and @size specify a - * new maximum size and new current size (in bytes), respectively. These - * will by rounded up to a multiple of %PAGE_SIZE. Specifying a new maximum - * size requires admin capabilities. - * - * On ioctl output, @maximum_size and @size and set to the current maximum - * buffer size and current buffer size, respectively. - */ -struct comedi_bufconfig { - unsigned int subdevice; - unsigned int flags; - - unsigned int maximum_size; - unsigned int size; - - unsigned int unused[4]; -}; - -/** - * struct comedi_bufinfo - used to manipulate buffer position for a subdevice - * @subdevice: Subdevice index. - * @bytes_read: Specify amount to advance read position for an - * asynchronous command in the input ("read") direction. - * @buf_write_ptr: Current write position (index) within the buffer. - * @buf_read_ptr: Current read position (index) within the buffer. - * @buf_write_count: Total amount written, modulo 2^32. - * @buf_read_count: Total amount read, modulo 2^32. - * @bytes_written: Specify amount to advance write position for an - * asynchronous command in the output ("write") direction. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_BUFINFO ioctl to optionally advance the - * current read or write position in an asynchronous acquisition data buffer, - * and to get the current read and write positions in the buffer. - */ -struct comedi_bufinfo { - unsigned int subdevice; - unsigned int bytes_read; - - unsigned int buf_write_ptr; - unsigned int buf_read_ptr; - unsigned int buf_write_count; - unsigned int buf_read_count; - - unsigned int bytes_written; - - unsigned int unused[4]; -}; - -/* range stuff */ - -#define __RANGE(a, b) ((((a) & 0xffff) << 16) | ((b) & 0xffff)) - -#define RANGE_OFFSET(a) (((a) >> 16) & 0xffff) -#define RANGE_LENGTH(b) ((b) & 0xffff) - -#define RF_UNIT(flags) ((flags) & 0xff) -#define RF_EXTERNAL 0x100 - -#define UNIT_volt 0 -#define UNIT_mA 1 -#define UNIT_none 2 - -#define COMEDI_MIN_SPEED 0xffffffffu - -/**********************************************************/ -/* everything after this line is ALPHA */ -/**********************************************************/ - -/* - * 8254 specific configuration. - * - * It supports two config commands: - * - * 0 ID: INSN_CONFIG_SET_COUNTER_MODE - * 1 8254 Mode - * I8254_MODE0, I8254_MODE1, ..., I8254_MODE5 - * OR'ed with: - * I8254_BCD, I8254_BINARY - * - * 0 ID: INSN_CONFIG_8254_READ_STATUS - * 1 <-- Status byte returned here. - * B7 = Output - * B6 = NULL Count - * B5 - B0 Current mode. - */ - -enum i8254_mode { - I8254_MODE0 = (0 << 1), /* Interrupt on terminal count */ - I8254_MODE1 = (1 << 1), /* Hardware retriggerable one-shot */ - I8254_MODE2 = (2 << 1), /* Rate generator */ - I8254_MODE3 = (3 << 1), /* Square wave mode */ - I8254_MODE4 = (4 << 1), /* Software triggered strobe */ - /* Hardware triggered strobe (retriggerable) */ - I8254_MODE5 = (5 << 1), - /* Use binary-coded decimal instead of binary (pretty useless) */ - I8254_BCD = 1, - I8254_BINARY = 0 -}; - -/* *** BEGIN GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ - -/* - * Common National Instruments Terminal/Signal names. - * Some of these have no NI_ prefix as they are useful for non-NI hardware, such - * as those that utilize the PXI/RTSI trigger lines. - * - * NOTE ABOUT THE CHOICE OF NAMES HERE AND THE CAMELSCRIPT: - * The choice to use CamelScript and the exact names below is for - * maintainability, clarity, similarity to manufacturer's documentation, - * _and_ a mitigation for confusion that has plagued the use of these drivers - * for years! - * - * More detail: - * There have been significant confusions over the past many years for users - * when trying to understand how to connect to/from signals and terminals on - * NI hardware using comedi. The major reason for this is that the actual - * register values were exposed and required to be used by users. Several - * major reasons exist why this caused major confusion for users: - * 1) The register values are _NOT_ in user documentation, but rather in - * arcane locations, such as a few register programming manuals that are - * increasingly hard to find and the NI MHDDK (comments in example code). - * There is no one place to find the various valid values of the registers. - * 2) The register values are _NOT_ completely consistent. There is no way to - * gain any sense of intuition of which values, or even enums one should use - * for various registers. There was some attempt in prior use of comedi to - * name enums such that a user might know which enums should be used for - * varying purposes, but the end-user had to gain a knowledge of register - * values to correctly wield this approach. - * 3) The names for signals and registers found in the various register level - * programming manuals and vendor-provided documentation are _not_ even - * close to the same names that are in the end-user documentation. - * - * Similar, albeit less, confusion plagued NI's previous version of their own - * drivers. Earlier than 2003, NI greatly simplified the situation for users - * by releasing a new API that abstracted the names of signals/terminals to a - * common and intuitive set of names. - * - * The names below mirror the names chosen and well documented by NI. These - * names are exposed to the user via the comedilib user library. By keeping - * the names below, in spite of the use of CamelScript, maintenance will be - * greatly eased and confusion for users _and_ comedi developers will be - * greatly reduced. - */ - -/* - * Base of abstracted NI names. - * The first 16 bits of *_arg are reserved for channel selection. - * Since we only actually need the first 4 or 5 bits for all register values on - * NI select registers anyways, we'll identify all values >= (1<<15) as being an - * abstracted NI signal/terminal name. - * These values are also used/returned by INSN_DEVICE_CONFIG_TEST_ROUTE, - * INSN_DEVICE_CONFIG_CONNECT_ROUTE, INSN_DEVICE_CONFIG_DISCONNECT_ROUTE, - * and INSN_DEVICE_CONFIG_GET_ROUTES. - */ -#define NI_NAMES_BASE 0x8000u - -#define _TERM_N(base, n, x) ((base) + ((x) & ((n) - 1))) - -/* - * not necessarily all allowed 64 PFIs are valid--certainly not for all devices - */ -#define NI_PFI(x) _TERM_N(NI_NAMES_BASE, 64, x) -/* 8 trigger lines by standard, Some devices cannot talk to all eight. */ -#define TRIGGER_LINE(x) _TERM_N(NI_PFI(-1) + 1, 8, x) -/* 4 RTSI shared MUXes to route signals to/from TRIGGER_LINES on NI hardware */ -#define NI_RTSI_BRD(x) _TERM_N(TRIGGER_LINE(-1) + 1, 4, x) - -/* *** Counter/timer names : 8 counters max *** */ -#define NI_MAX_COUNTERS 8 -#define NI_COUNTER_NAMES_BASE (NI_RTSI_BRD(-1) + 1) -#define NI_CtrSource(x) _TERM_N(NI_COUNTER_NAMES_BASE, NI_MAX_COUNTERS, x) -/* Gate, Aux, A,B,Z are all treated, at times as gates */ -#define NI_GATES_NAMES_BASE (NI_CtrSource(-1) + 1) -#define NI_CtrGate(x) _TERM_N(NI_GATES_NAMES_BASE, NI_MAX_COUNTERS, x) -#define NI_CtrAux(x) _TERM_N(NI_CtrGate(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrA(x) _TERM_N(NI_CtrAux(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrB(x) _TERM_N(NI_CtrA(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrZ(x) _TERM_N(NI_CtrB(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_GATES_NAMES_MAX NI_CtrZ(-1) -#define NI_CtrArmStartTrigger(x) _TERM_N(NI_CtrZ(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrInternalOutput(x) \ - _TERM_N(NI_CtrArmStartTrigger(-1) + 1, NI_MAX_COUNTERS, x) -/** external pin(s) labeled conveniently as CtrOut. */ -#define NI_CtrOut(x) _TERM_N(NI_CtrInternalOutput(-1) + 1, NI_MAX_COUNTERS, x) -/** For Buffered sampling of ctr -- x series capability. */ -#define NI_CtrSampleClock(x) _TERM_N(NI_CtrOut(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_COUNTER_NAMES_MAX NI_CtrSampleClock(-1) - -enum ni_common_signal_names { - /* PXI_Star: this is a non-NI-specific signal */ - PXI_Star = NI_COUNTER_NAMES_MAX + 1, - PXI_Clk10, - PXIe_Clk100, - NI_AI_SampleClock, - NI_AI_SampleClockTimebase, - NI_AI_StartTrigger, - NI_AI_ReferenceTrigger, - NI_AI_ConvertClock, - NI_AI_ConvertClockTimebase, - NI_AI_PauseTrigger, - NI_AI_HoldCompleteEvent, - NI_AI_HoldComplete, - NI_AI_ExternalMUXClock, - NI_AI_STOP, /* pulse signal that occurs when a update is finished(?) */ - NI_AO_SampleClock, - NI_AO_SampleClockTimebase, - NI_AO_StartTrigger, - NI_AO_PauseTrigger, - NI_DI_SampleClock, - NI_DI_SampleClockTimebase, - NI_DI_StartTrigger, - NI_DI_ReferenceTrigger, - NI_DI_PauseTrigger, - NI_DI_InputBufferFull, - NI_DI_ReadyForStartEvent, - NI_DI_ReadyForTransferEventBurst, - NI_DI_ReadyForTransferEventPipelined, - NI_DO_SampleClock, - NI_DO_SampleClockTimebase, - NI_DO_StartTrigger, - NI_DO_PauseTrigger, - NI_DO_OutputBufferFull, - NI_DO_DataActiveEvent, - NI_DO_ReadyForStartEvent, - NI_DO_ReadyForTransferEvent, - NI_MasterTimebase, - NI_20MHzTimebase, - NI_80MHzTimebase, - NI_100MHzTimebase, - NI_200MHzTimebase, - NI_100kHzTimebase, - NI_10MHzRefClock, - NI_FrequencyOutput, - NI_ChangeDetectionEvent, - NI_AnalogComparisonEvent, - NI_WatchdogExpiredEvent, - NI_WatchdogExpirationTrigger, - NI_SCXI_Trig1, - NI_LogicLow, - NI_LogicHigh, - NI_ExternalStrobe, - NI_PFI_DO, - NI_CaseGround, - /* special internal signal used as variable source for RTSI bus: */ - NI_RGOUT0, - - /* just a name to make the next more convenient, regardless of above */ - _NI_NAMES_MAX_PLUS_1, - NI_NUM_NAMES = _NI_NAMES_MAX_PLUS_1 - NI_NAMES_BASE, -}; - -/* *** END GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ - -#define NI_USUAL_PFI_SELECT(x) (((x) < 10) ? (0x1 + (x)) : (0xb + (x))) -#define NI_USUAL_RTSI_SELECT(x) (((x) < 7) ? (0xb + (x)) : 0x1b) - -/* - * mode bits for NI general-purpose counters, set with - * INSN_CONFIG_SET_COUNTER_MODE - */ -#define NI_GPCT_COUNTING_MODE_SHIFT 16 -#define NI_GPCT_INDEX_PHASE_BITSHIFT 20 -#define NI_GPCT_COUNTING_DIRECTION_SHIFT 24 -enum ni_gpct_mode_bits { - NI_GPCT_GATE_ON_BOTH_EDGES_BIT = 0x4, - NI_GPCT_EDGE_GATE_MODE_MASK = 0x18, - NI_GPCT_EDGE_GATE_STARTS_STOPS_BITS = 0x0, - NI_GPCT_EDGE_GATE_STOPS_STARTS_BITS = 0x8, - NI_GPCT_EDGE_GATE_STARTS_BITS = 0x10, - NI_GPCT_EDGE_GATE_NO_STARTS_NO_STOPS_BITS = 0x18, - NI_GPCT_STOP_MODE_MASK = 0x60, - NI_GPCT_STOP_ON_GATE_BITS = 0x00, - NI_GPCT_STOP_ON_GATE_OR_TC_BITS = 0x20, - NI_GPCT_STOP_ON_GATE_OR_SECOND_TC_BITS = 0x40, - NI_GPCT_LOAD_B_SELECT_BIT = 0x80, - NI_GPCT_OUTPUT_MODE_MASK = 0x300, - NI_GPCT_OUTPUT_TC_PULSE_BITS = 0x100, - NI_GPCT_OUTPUT_TC_TOGGLE_BITS = 0x200, - NI_GPCT_OUTPUT_TC_OR_GATE_TOGGLE_BITS = 0x300, - NI_GPCT_HARDWARE_DISARM_MASK = 0xc00, - NI_GPCT_NO_HARDWARE_DISARM_BITS = 0x000, - NI_GPCT_DISARM_AT_TC_BITS = 0x400, - NI_GPCT_DISARM_AT_GATE_BITS = 0x800, - NI_GPCT_DISARM_AT_TC_OR_GATE_BITS = 0xc00, - NI_GPCT_LOADING_ON_TC_BIT = 0x1000, - NI_GPCT_LOADING_ON_GATE_BIT = 0x4000, - NI_GPCT_COUNTING_MODE_MASK = 0x7 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_NORMAL_BITS = - 0x0 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_QUADRATURE_X1_BITS = - 0x1 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_QUADRATURE_X2_BITS = - 0x2 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_QUADRATURE_X4_BITS = - 0x3 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_TWO_PULSE_BITS = - 0x4 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_SYNC_SOURCE_BITS = - 0x6 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_INDEX_PHASE_MASK = 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_LOW_A_LOW_B_BITS = - 0x0 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_LOW_A_HIGH_B_BITS = - 0x1 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_HIGH_A_LOW_B_BITS = - 0x2 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_HIGH_A_HIGH_B_BITS = - 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_ENABLE_BIT = 0x400000, - NI_GPCT_COUNTING_DIRECTION_MASK = - 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_DOWN_BITS = - 0x00 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_UP_BITS = - 0x1 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_HW_UP_DOWN_BITS = - 0x2 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_HW_GATE_BITS = - 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_RELOAD_SOURCE_MASK = 0xc000000, - NI_GPCT_RELOAD_SOURCE_FIXED_BITS = 0x0, - NI_GPCT_RELOAD_SOURCE_SWITCHING_BITS = 0x4000000, - NI_GPCT_RELOAD_SOURCE_GATE_SELECT_BITS = 0x8000000, - NI_GPCT_OR_GATE_BIT = 0x10000000, - NI_GPCT_INVERT_OUTPUT_BIT = 0x20000000 -}; - -/* - * Bits for setting a clock source with - * INSN_CONFIG_SET_CLOCK_SRC when using NI general-purpose counters. - */ -enum ni_gpct_clock_source_bits { - NI_GPCT_CLOCK_SRC_SELECT_MASK = 0x3f, - NI_GPCT_TIMEBASE_1_CLOCK_SRC_BITS = 0x0, - NI_GPCT_TIMEBASE_2_CLOCK_SRC_BITS = 0x1, - NI_GPCT_TIMEBASE_3_CLOCK_SRC_BITS = 0x2, - NI_GPCT_LOGIC_LOW_CLOCK_SRC_BITS = 0x3, - NI_GPCT_NEXT_GATE_CLOCK_SRC_BITS = 0x4, - NI_GPCT_NEXT_TC_CLOCK_SRC_BITS = 0x5, - /* NI 660x-specific */ - NI_GPCT_SOURCE_PIN_i_CLOCK_SRC_BITS = 0x6, - NI_GPCT_PXI10_CLOCK_SRC_BITS = 0x7, - NI_GPCT_PXI_STAR_TRIGGER_CLOCK_SRC_BITS = 0x8, - NI_GPCT_ANALOG_TRIGGER_OUT_CLOCK_SRC_BITS = 0x9, - NI_GPCT_PRESCALE_MODE_CLOCK_SRC_MASK = 0x30000000, - NI_GPCT_NO_PRESCALE_CLOCK_SRC_BITS = 0x0, - /* divide source by 2 */ - NI_GPCT_PRESCALE_X2_CLOCK_SRC_BITS = 0x10000000, - /* divide source by 8 */ - NI_GPCT_PRESCALE_X8_CLOCK_SRC_BITS = 0x20000000, - NI_GPCT_INVERT_CLOCK_SRC_BIT = 0x80000000 -}; - -/* NI 660x-specific */ -#define NI_GPCT_SOURCE_PIN_CLOCK_SRC_BITS(x) (0x10 + (x)) - -#define NI_GPCT_RTSI_CLOCK_SRC_BITS(x) (0x18 + (x)) - -/* no pfi on NI 660x */ -#define NI_GPCT_PFI_CLOCK_SRC_BITS(x) (0x20 + (x)) - -/* - * Possibilities for setting a gate source with - * INSN_CONFIG_SET_GATE_SRC when using NI general-purpose counters. - * May be bitwise-or'd with CR_EDGE or CR_INVERT. - */ -enum ni_gpct_gate_select { - /* m-series gates */ - NI_GPCT_TIMESTAMP_MUX_GATE_SELECT = 0x0, - NI_GPCT_AI_START2_GATE_SELECT = 0x12, - NI_GPCT_PXI_STAR_TRIGGER_GATE_SELECT = 0x13, - NI_GPCT_NEXT_OUT_GATE_SELECT = 0x14, - NI_GPCT_AI_START1_GATE_SELECT = 0x1c, - NI_GPCT_NEXT_SOURCE_GATE_SELECT = 0x1d, - NI_GPCT_ANALOG_TRIGGER_OUT_GATE_SELECT = 0x1e, - NI_GPCT_LOGIC_LOW_GATE_SELECT = 0x1f, - /* more gates for 660x */ - NI_GPCT_SOURCE_PIN_i_GATE_SELECT = 0x100, - NI_GPCT_GATE_PIN_i_GATE_SELECT = 0x101, - /* more gates for 660x "second gate" */ - NI_GPCT_UP_DOWN_PIN_i_GATE_SELECT = 0x201, - NI_GPCT_SELECTED_GATE_GATE_SELECT = 0x21e, - /* - * m-series "second gate" sources are unknown, - * we should add them here with an offset of 0x300 when - * known. - */ - NI_GPCT_DISABLED_GATE_SELECT = 0x8000, -}; - -#define NI_GPCT_GATE_PIN_GATE_SELECT(x) (0x102 + (x)) -#define NI_GPCT_RTSI_GATE_SELECT(x) NI_USUAL_RTSI_SELECT(x) -#define NI_GPCT_PFI_GATE_SELECT(x) NI_USUAL_PFI_SELECT(x) -#define NI_GPCT_UP_DOWN_PIN_GATE_SELECT(x) (0x202 + (x)) - -/* - * Possibilities for setting a source with - * INSN_CONFIG_SET_OTHER_SRC when using NI general-purpose counters. - */ -enum ni_gpct_other_index { - NI_GPCT_SOURCE_ENCODER_A, - NI_GPCT_SOURCE_ENCODER_B, - NI_GPCT_SOURCE_ENCODER_Z -}; - -enum ni_gpct_other_select { - /* m-series gates */ - /* Still unknown, probably only need NI_GPCT_PFI_OTHER_SELECT */ - NI_GPCT_DISABLED_OTHER_SELECT = 0x8000, -}; - -#define NI_GPCT_PFI_OTHER_SELECT(x) NI_USUAL_PFI_SELECT(x) - -/* - * start sources for ni general-purpose counters for use with - * INSN_CONFIG_ARM - */ -enum ni_gpct_arm_source { - NI_GPCT_ARM_IMMEDIATE = 0x0, - /* - * Start both the counter and the adjacent paired counter simultaneously - */ - NI_GPCT_ARM_PAIRED_IMMEDIATE = 0x1, - /* - * If the NI_GPCT_HW_ARM bit is set, we will pass the least significant - * bits (3 bits for 660x or 5 bits for m-series) through to the - * hardware. To select a hardware trigger, pass the appropriate select - * bit, e.g., - * NI_GPCT_HW_ARM | NI_GPCT_AI_START1_GATE_SELECT or - * NI_GPCT_HW_ARM | NI_GPCT_PFI_GATE_SELECT(pfi_number) - */ - NI_GPCT_HW_ARM = 0x1000, - NI_GPCT_ARM_UNKNOWN = NI_GPCT_HW_ARM, /* for backward compatibility */ -}; - -/* digital filtering options for ni 660x for use with INSN_CONFIG_FILTER. */ -enum ni_gpct_filter_select { - NI_GPCT_FILTER_OFF = 0x0, - NI_GPCT_FILTER_TIMEBASE_3_SYNC = 0x1, - NI_GPCT_FILTER_100x_TIMEBASE_1 = 0x2, - NI_GPCT_FILTER_20x_TIMEBASE_1 = 0x3, - NI_GPCT_FILTER_10x_TIMEBASE_1 = 0x4, - NI_GPCT_FILTER_2x_TIMEBASE_1 = 0x5, - NI_GPCT_FILTER_2x_TIMEBASE_3 = 0x6 -}; - -/* - * PFI digital filtering options for ni m-series for use with - * INSN_CONFIG_FILTER. - */ -enum ni_pfi_filter_select { - NI_PFI_FILTER_OFF = 0x0, - NI_PFI_FILTER_125ns = 0x1, - NI_PFI_FILTER_6425ns = 0x2, - NI_PFI_FILTER_2550us = 0x3 -}; - -/* master clock sources for ni mio boards and INSN_CONFIG_SET_CLOCK_SRC */ -enum ni_mio_clock_source { - NI_MIO_INTERNAL_CLOCK = 0, - /* - * Doesn't work for m-series, use NI_MIO_PLL_RTSI_CLOCK() - * the NI_MIO_PLL_* sources are m-series only - */ - NI_MIO_RTSI_CLOCK = 1, - NI_MIO_PLL_PXI_STAR_TRIGGER_CLOCK = 2, - NI_MIO_PLL_PXI10_CLOCK = 3, - NI_MIO_PLL_RTSI0_CLOCK = 4 -}; - -#define NI_MIO_PLL_RTSI_CLOCK(x) (NI_MIO_PLL_RTSI0_CLOCK + (x)) - -/* - * Signals which can be routed to an NI RTSI pin with INSN_CONFIG_SET_ROUTING. - * The numbers assigned are not arbitrary, they correspond to the bits required - * to program the board. - */ -enum ni_rtsi_routing { - NI_RTSI_OUTPUT_ADR_START1 = 0, - NI_RTSI_OUTPUT_ADR_START2 = 1, - NI_RTSI_OUTPUT_SCLKG = 2, - NI_RTSI_OUTPUT_DACUPDN = 3, - NI_RTSI_OUTPUT_DA_START1 = 4, - NI_RTSI_OUTPUT_G_SRC0 = 5, - NI_RTSI_OUTPUT_G_GATE0 = 6, - NI_RTSI_OUTPUT_RGOUT0 = 7, - NI_RTSI_OUTPUT_RTSI_BRD_0 = 8, - /* Pre-m-series always have RTSI clock on line 7 */ - NI_RTSI_OUTPUT_RTSI_OSC = 12 -}; - -#define NI_RTSI_OUTPUT_RTSI_BRD(x) (NI_RTSI_OUTPUT_RTSI_BRD_0 + (x)) - -/* - * Signals which can be routed to an NI PFI pin on an m-series board with - * INSN_CONFIG_SET_ROUTING. These numbers are also returned by - * INSN_CONFIG_GET_ROUTING on pre-m-series boards, even though their routing - * cannot be changed. The numbers assigned are not arbitrary, they correspond - * to the bits required to program the board. - */ -enum ni_pfi_routing { - NI_PFI_OUTPUT_PFI_DEFAULT = 0, - NI_PFI_OUTPUT_AI_START1 = 1, - NI_PFI_OUTPUT_AI_START2 = 2, - NI_PFI_OUTPUT_AI_CONVERT = 3, - NI_PFI_OUTPUT_G_SRC1 = 4, - NI_PFI_OUTPUT_G_GATE1 = 5, - NI_PFI_OUTPUT_AO_UPDATE_N = 6, - NI_PFI_OUTPUT_AO_START1 = 7, - NI_PFI_OUTPUT_AI_START_PULSE = 8, - NI_PFI_OUTPUT_G_SRC0 = 9, - NI_PFI_OUTPUT_G_GATE0 = 10, - NI_PFI_OUTPUT_EXT_STROBE = 11, - NI_PFI_OUTPUT_AI_EXT_MUX_CLK = 12, - NI_PFI_OUTPUT_GOUT0 = 13, - NI_PFI_OUTPUT_GOUT1 = 14, - NI_PFI_OUTPUT_FREQ_OUT = 15, - NI_PFI_OUTPUT_PFI_DO = 16, - NI_PFI_OUTPUT_I_ATRIG = 17, - NI_PFI_OUTPUT_RTSI0 = 18, - NI_PFI_OUTPUT_PXI_STAR_TRIGGER_IN = 26, - NI_PFI_OUTPUT_SCXI_TRIG1 = 27, - NI_PFI_OUTPUT_DIO_CHANGE_DETECT_RTSI = 28, - NI_PFI_OUTPUT_CDI_SAMPLE = 29, - NI_PFI_OUTPUT_CDO_UPDATE = 30 -}; - -#define NI_PFI_OUTPUT_RTSI(x) (NI_PFI_OUTPUT_RTSI0 + (x)) - -/* - * Signals which can be routed to output on a NI PFI pin on a 660x board - * with INSN_CONFIG_SET_ROUTING. The numbers assigned are - * not arbitrary, they correspond to the bits required - * to program the board. Lines 0 to 7 can only be set to - * NI_660X_PFI_OUTPUT_DIO. Lines 32 to 39 can only be set to - * NI_660X_PFI_OUTPUT_COUNTER. - */ -enum ni_660x_pfi_routing { - NI_660X_PFI_OUTPUT_COUNTER = 1, /* counter */ - NI_660X_PFI_OUTPUT_DIO = 2, /* static digital output */ -}; - -/* - * NI External Trigger lines. These values are not arbitrary, but are related - * to the bits required to program the board (offset by 1 for historical - * reasons). - */ -#define NI_EXT_PFI(x) (NI_USUAL_PFI_SELECT(x) - 1) -#define NI_EXT_RTSI(x) (NI_USUAL_RTSI_SELECT(x) - 1) - -/* - * Clock sources for CDIO subdevice on NI m-series boards. Used as the - * scan_begin_arg for a comedi_command. These sources may also be bitwise-or'd - * with CR_INVERT to change polarity. - */ -enum ni_m_series_cdio_scan_begin_src { - NI_CDIO_SCAN_BEGIN_SRC_GROUND = 0, - NI_CDIO_SCAN_BEGIN_SRC_AI_START = 18, - NI_CDIO_SCAN_BEGIN_SRC_AI_CONVERT = 19, - NI_CDIO_SCAN_BEGIN_SRC_PXI_STAR_TRIGGER = 20, - NI_CDIO_SCAN_BEGIN_SRC_G0_OUT = 28, - NI_CDIO_SCAN_BEGIN_SRC_G1_OUT = 29, - NI_CDIO_SCAN_BEGIN_SRC_ANALOG_TRIGGER = 30, - NI_CDIO_SCAN_BEGIN_SRC_AO_UPDATE = 31, - NI_CDIO_SCAN_BEGIN_SRC_FREQ_OUT = 32, - NI_CDIO_SCAN_BEGIN_SRC_DIO_CHANGE_DETECT_IRQ = 33 -}; - -#define NI_CDIO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) -#define NI_CDIO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) - -/* - * scan_begin_src for scan_begin_arg==TRIG_EXT with analog output command on NI - * boards. These scan begin sources can also be bitwise-or'd with CR_INVERT to - * change polarity. - */ -#define NI_AO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) -#define NI_AO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) - -/* - * Bits for setting a clock source with - * INSN_CONFIG_SET_CLOCK_SRC when using NI frequency output subdevice. - */ -enum ni_freq_out_clock_source_bits { - NI_FREQ_OUT_TIMEBASE_1_DIV_2_CLOCK_SRC, /* 10 MHz */ - NI_FREQ_OUT_TIMEBASE_2_CLOCK_SRC /* 100 KHz */ -}; - -/* - * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for - * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). - */ -enum amplc_dio_clock_source { - /* - * Per channel external clock - * input/output pin (pin is only an - * input when clock source set to this value, - * otherwise it is an output) - */ - AMPLC_DIO_CLK_CLKN, - AMPLC_DIO_CLK_10MHZ, /* 10 MHz internal clock */ - AMPLC_DIO_CLK_1MHZ, /* 1 MHz internal clock */ - AMPLC_DIO_CLK_100KHZ, /* 100 kHz internal clock */ - AMPLC_DIO_CLK_10KHZ, /* 10 kHz internal clock */ - AMPLC_DIO_CLK_1KHZ, /* 1 kHz internal clock */ - /* - * Output of preceding counter channel - * (for channel 0, preceding counter - * channel is channel 2 on preceding - * counter subdevice, for first counter - * subdevice, preceding counter - * subdevice is the last counter - * subdevice) - */ - AMPLC_DIO_CLK_OUTNM1, - AMPLC_DIO_CLK_EXT, /* per chip external input pin */ - /* the following are "enhanced" clock sources for PCIe models */ - AMPLC_DIO_CLK_VCC, /* clock input HIGH */ - AMPLC_DIO_CLK_GND, /* clock input LOW */ - AMPLC_DIO_CLK_PAT_PRESENT, /* "pattern present" signal */ - AMPLC_DIO_CLK_20MHZ /* 20 MHz internal clock */ -}; - -/* - * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for - * timer subdevice on some Amplicon DIO PCIe boards (amplc_dio200 driver). - */ -enum amplc_dio_ts_clock_src { - AMPLC_DIO_TS_CLK_1GHZ, /* 1 ns period with 20 ns granularity */ - AMPLC_DIO_TS_CLK_1MHZ, /* 1 us period */ - AMPLC_DIO_TS_CLK_1KHZ /* 1 ms period */ -}; - -/* - * Values for setting a gate source with INSN_CONFIG_SET_GATE_SRC for - * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). - */ -enum amplc_dio_gate_source { - AMPLC_DIO_GAT_VCC, /* internal high logic level */ - AMPLC_DIO_GAT_GND, /* internal low logic level */ - AMPLC_DIO_GAT_GATN, /* per channel external gate input */ - /* - * negated output of counter channel minus 2 - * (for channels 0 or 1, channel minus 2 is channel 1 or 2 on - * the preceding counter subdevice, for the first counter subdevice - * the preceding counter subdevice is the last counter subdevice) - */ - AMPLC_DIO_GAT_NOUTNM2, - AMPLC_DIO_GAT_RESERVED4, - AMPLC_DIO_GAT_RESERVED5, - AMPLC_DIO_GAT_RESERVED6, - AMPLC_DIO_GAT_RESERVED7, - /* the following are "enhanced" gate sources for PCIe models */ - AMPLC_DIO_GAT_NGATN = 6, /* negated per channel gate input */ - /* non-negated output of counter channel minus 2 */ - AMPLC_DIO_GAT_OUTNM2, - AMPLC_DIO_GAT_PAT_PRESENT, /* "pattern present" signal */ - AMPLC_DIO_GAT_PAT_OCCURRED, /* "pattern occurred" latched */ - AMPLC_DIO_GAT_PAT_GONE, /* "pattern gone away" latched */ - AMPLC_DIO_GAT_NPAT_PRESENT, /* negated "pattern present" */ - AMPLC_DIO_GAT_NPAT_OCCURRED, /* negated "pattern occurred" */ - AMPLC_DIO_GAT_NPAT_GONE /* negated "pattern gone away" */ -}; - -/* - * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for - * the counter subdevice on the Kolter Electronic PCI-Counter board - * (ke_counter driver). - */ -enum ke_counter_clock_source { - KE_CLK_20MHZ, /* internal 20MHz (default) */ - KE_CLK_4MHZ, /* internal 4MHz (option) */ - KE_CLK_EXT /* external clock on pin 21 of D-Sub */ -}; - -#endif /* _COMEDI_H */ diff --git a/drivers/comedi/comedi_buf.c b/drivers/comedi/comedi_buf.c index 06bfc859ab31..393966c09740 100644 --- a/drivers/comedi/comedi_buf.c +++ b/drivers/comedi/comedi_buf.c @@ -9,8 +9,7 @@ #include #include - -#include "comedidev.h" +#include #include "comedi_internal.h" #ifdef PAGE_KERNEL_NOCACHE diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 763cea8418f8..55a0cae04b8d 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -23,7 +23,7 @@ #include #include #include -#include "comedidev.h" +#include #include #include diff --git a/drivers/comedi/comedi_pci.c b/drivers/comedi/comedi_pci.c index 54739af7eb71..cc2581902195 100644 --- a/drivers/comedi/comedi_pci.c +++ b/drivers/comedi/comedi_pci.c @@ -9,8 +9,7 @@ #include #include - -#include "comedi_pci.h" +#include /** * comedi_to_pci_dev() - Return PCI device attached to COMEDI device diff --git a/drivers/comedi/comedi_pci.h b/drivers/comedi/comedi_pci.h deleted file mode 100644 index 4e069440cbdc..000000000000 --- a/drivers/comedi/comedi_pci.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedi_pci.h - * header file for Comedi PCI drivers - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDI_PCI_H -#define _COMEDI_PCI_H - -#include - -#include "comedidev.h" - -/* - * PCI Vendor IDs not in - */ -#define PCI_VENDOR_ID_KOLTER 0x1001 -#define PCI_VENDOR_ID_ICP 0x104c -#define PCI_VENDOR_ID_DT 0x1116 -#define PCI_VENDOR_ID_IOTECH 0x1616 -#define PCI_VENDOR_ID_CONTEC 0x1221 -#define PCI_VENDOR_ID_RTD 0x1435 -#define PCI_VENDOR_ID_HUMUSOFT 0x186c - -struct pci_dev *comedi_to_pci_dev(struct comedi_device *dev); - -int comedi_pci_enable(struct comedi_device *dev); -void comedi_pci_disable(struct comedi_device *dev); -void comedi_pci_detach(struct comedi_device *dev); - -int comedi_pci_auto_config(struct pci_dev *pcidev, struct comedi_driver *driver, - unsigned long context); -void comedi_pci_auto_unconfig(struct pci_dev *pcidev); - -int comedi_pci_driver_register(struct comedi_driver *comedi_driver, - struct pci_driver *pci_driver); -void comedi_pci_driver_unregister(struct comedi_driver *comedi_driver, - struct pci_driver *pci_driver); - -/** - * module_comedi_pci_driver() - Helper macro for registering a comedi PCI driver - * @__comedi_driver: comedi_driver struct - * @__pci_driver: pci_driver struct - * - * Helper macro for comedi PCI drivers which do not do anything special - * in module init/exit. This eliminates a lot of boilerplate. Each - * module may only use this macro once, and calling it replaces - * module_init() and module_exit() - */ -#define module_comedi_pci_driver(__comedi_driver, __pci_driver) \ - module_driver(__comedi_driver, comedi_pci_driver_register, \ - comedi_pci_driver_unregister, &(__pci_driver)) - -#endif /* _COMEDI_PCI_H */ diff --git a/drivers/comedi/comedi_pcmcia.c b/drivers/comedi/comedi_pcmcia.c index bb273bb202e6..c53aad0fc2ce 100644 --- a/drivers/comedi/comedi_pcmcia.c +++ b/drivers/comedi/comedi_pcmcia.c @@ -9,8 +9,7 @@ #include #include - -#include "comedi_pcmcia.h" +#include /** * comedi_to_pcmcia_dev() - Return PCMCIA device attached to COMEDI device diff --git a/drivers/comedi/comedi_pcmcia.h b/drivers/comedi/comedi_pcmcia.h deleted file mode 100644 index f2f6e779645b..000000000000 --- a/drivers/comedi/comedi_pcmcia.h +++ /dev/null @@ -1,49 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedi_pcmcia.h - * header file for Comedi PCMCIA drivers - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDI_PCMCIA_H -#define _COMEDI_PCMCIA_H - -#include -#include - -#include "comedidev.h" - -struct pcmcia_device *comedi_to_pcmcia_dev(struct comedi_device *dev); - -int comedi_pcmcia_enable(struct comedi_device *dev, - int (*conf_check)(struct pcmcia_device *p_dev, - void *priv_data)); -void comedi_pcmcia_disable(struct comedi_device *dev); - -int comedi_pcmcia_auto_config(struct pcmcia_device *link, - struct comedi_driver *driver); -void comedi_pcmcia_auto_unconfig(struct pcmcia_device *link); - -int comedi_pcmcia_driver_register(struct comedi_driver *comedi_driver, - struct pcmcia_driver *pcmcia_driver); -void comedi_pcmcia_driver_unregister(struct comedi_driver *comedi_driver, - struct pcmcia_driver *pcmcia_driver); - -/** - * module_comedi_pcmcia_driver() - Helper macro for registering a comedi - * PCMCIA driver - * @__comedi_driver: comedi_driver struct - * @__pcmcia_driver: pcmcia_driver struct - * - * Helper macro for comedi PCMCIA drivers which do not do anything special - * in module init/exit. This eliminates a lot of boilerplate. Each - * module may only use this macro once, and calling it replaces - * module_init() and module_exit() - */ -#define module_comedi_pcmcia_driver(__comedi_driver, __pcmcia_driver) \ - module_driver(__comedi_driver, comedi_pcmcia_driver_register, \ - comedi_pcmcia_driver_unregister, &(__pcmcia_driver)) - -#endif /* _COMEDI_PCMCIA_H */ diff --git a/drivers/comedi/comedi_usb.c b/drivers/comedi/comedi_usb.c index eea8ebf32ed0..d11ea148ebf8 100644 --- a/drivers/comedi/comedi_usb.c +++ b/drivers/comedi/comedi_usb.c @@ -8,8 +8,7 @@ */ #include - -#include "comedi_usb.h" +#include /** * comedi_to_usb_interface() - Return USB interface attached to COMEDI device diff --git a/drivers/comedi/comedi_usb.h b/drivers/comedi/comedi_usb.h deleted file mode 100644 index 601e29d3891c..000000000000 --- a/drivers/comedi/comedi_usb.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* comedi_usb.h - * header file for USB Comedi drivers - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDI_USB_H -#define _COMEDI_USB_H - -#include - -#include "comedidev.h" - -struct usb_interface *comedi_to_usb_interface(struct comedi_device *dev); -struct usb_device *comedi_to_usb_dev(struct comedi_device *dev); - -int comedi_usb_auto_config(struct usb_interface *intf, - struct comedi_driver *driver, unsigned long context); -void comedi_usb_auto_unconfig(struct usb_interface *intf); - -int comedi_usb_driver_register(struct comedi_driver *comedi_driver, - struct usb_driver *usb_driver); -void comedi_usb_driver_unregister(struct comedi_driver *comedi_driver, - struct usb_driver *usb_driver); - -/** - * module_comedi_usb_driver() - Helper macro for registering a comedi USB driver - * @__comedi_driver: comedi_driver struct - * @__usb_driver: usb_driver struct - * - * Helper macro for comedi USB drivers which do not do anything special - * in module init/exit. This eliminates a lot of boilerplate. Each - * module may only use this macro once, and calling it replaces - * module_init() and module_exit() - */ -#define module_comedi_usb_driver(__comedi_driver, __usb_driver) \ - module_driver(__comedi_driver, comedi_usb_driver_register, \ - comedi_usb_driver_unregister, &(__usb_driver)) - -#endif /* _COMEDI_USB_H */ diff --git a/drivers/comedi/comedidev.h b/drivers/comedi/comedidev.h deleted file mode 100644 index 0e1b95ef9a4d..000000000000 --- a/drivers/comedi/comedidev.h +++ /dev/null @@ -1,1054 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedidev.h - * header file for kernel-only structures, variables, and constants - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDIDEV_H -#define _COMEDIDEV_H - -#include -#include -#include -#include -#include - -#include "comedi.h" - -#define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) -#define COMEDI_VERSION_CODE COMEDI_VERSION(COMEDI_MAJORVERSION, \ - COMEDI_MINORVERSION, COMEDI_MICROVERSION) -#define COMEDI_RELEASE VERSION - -#define COMEDI_NUM_BOARD_MINORS 0x30 - -/** - * struct comedi_subdevice - Working data for a COMEDI subdevice - * @device: COMEDI device to which this subdevice belongs. (Initialized by - * comedi_alloc_subdevices().) - * @index: Index of this subdevice within device's array of subdevices. - * (Initialized by comedi_alloc_subdevices().) - * @type: Type of subdevice from &enum comedi_subdevice_type. (Initialized by - * the low-level driver.) - * @n_chan: Number of channels the subdevice supports. (Initialized by the - * low-level driver.) - * @subdev_flags: Various "SDF" flags indicating aspects of the subdevice to - * the COMEDI core and user application. (Initialized by the low-level - * driver.) - * @len_chanlist: Maximum length of a channel list if the subdevice supports - * asynchronous acquisition commands. (Optionally initialized by the - * low-level driver, or changed from 0 to 1 during post-configuration.) - * @private: Private data pointer which is either set by the low-level driver - * itself, or by a call to comedi_alloc_spriv() which allocates storage. - * In the latter case, the storage is automatically freed after the - * low-level driver's "detach" handler is called for the device. - * (Initialized by the low-level driver.) - * @async: Pointer to &struct comedi_async id the subdevice supports - * asynchronous acquisition commands. (Allocated and initialized during - * post-configuration if needed.) - * @lock: Pointer to a file object that performed a %COMEDI_LOCK ioctl on the - * subdevice. (Initially NULL.) - * @busy: Pointer to a file object that is performing an asynchronous - * acquisition command on the subdevice. (Initially NULL.) - * @runflags: Internal flags for use by COMEDI core, mostly indicating whether - * an asynchronous acquisition command is running. - * @spin_lock: Generic spin-lock for use by the COMEDI core and the low-level - * driver. (Initialized by comedi_alloc_subdevices().) - * @io_bits: Bit-mask indicating the channel directions for a DIO subdevice - * with no more than 32 channels. A '1' at a bit position indicates the - * corresponding channel is configured as an output. (Initialized by the - * low-level driver for a DIO subdevice. Forced to all-outputs during - * post-configuration for a digital output subdevice.) - * @maxdata: If non-zero, this is the maximum raw data value of each channel. - * If zero, the maximum data value is channel-specific. (Initialized by - * the low-level driver.) - * @maxdata_list: If the maximum data value is channel-specific, this points - * to an array of maximum data values indexed by channel index. - * (Initialized by the low-level driver.) - * @range_table: If non-NULL, this points to a COMEDI range table for the - * subdevice. If NULL, the range table is channel-specific. (Initialized - * by the low-level driver, will be set to an "invalid" range table during - * post-configuration if @range_table and @range_table_list are both - * NULL.) - * @range_table_list: If the COMEDI range table is channel-specific, this - * points to an array of pointers to COMEDI range tables indexed by - * channel number. (Initialized by the low-level driver.) - * @chanlist: Not used. - * @insn_read: Optional pointer to a handler for the %INSN_READ instruction. - * (Initialized by the low-level driver, or set to a default handler - * during post-configuration.) - * @insn_write: Optional pointer to a handler for the %INSN_WRITE instruction. - * (Initialized by the low-level driver, or set to a default handler - * during post-configuration.) - * @insn_bits: Optional pointer to a handler for the %INSN_BITS instruction - * for a digital input, digital output or digital input/output subdevice. - * (Initialized by the low-level driver, or set to a default handler - * during post-configuration.) - * @insn_config: Optional pointer to a handler for the %INSN_CONFIG - * instruction. (Initialized by the low-level driver, or set to a default - * handler during post-configuration.) - * @do_cmd: If the subdevice supports asynchronous acquisition commands, this - * points to a handler to set it up in hardware. (Initialized by the - * low-level driver.) - * @do_cmdtest: If the subdevice supports asynchronous acquisition commands, - * this points to a handler used to check and possibly tweak a prospective - * acquisition command without setting it up in hardware. (Initialized by - * the low-level driver.) - * @poll: If the subdevice supports asynchronous acquisition commands, this - * is an optional pointer to a handler for the %COMEDI_POLL ioctl which - * instructs the low-level driver to synchronize buffers. (Initialized by - * the low-level driver if needed.) - * @cancel: If the subdevice supports asynchronous acquisition commands, this - * points to a handler used to terminate a running command. (Initialized - * by the low-level driver.) - * @buf_change: If the subdevice supports asynchronous acquisition commands, - * this is an optional pointer to a handler that is called when the data - * buffer for handling asynchronous commands is allocated or reallocated. - * (Initialized by the low-level driver if needed.) - * @munge: If the subdevice supports asynchronous acquisition commands and - * uses DMA to transfer data from the hardware to the acquisition buffer, - * this points to a function used to "munge" the data values from the - * hardware into the format expected by COMEDI. (Initialized by the - * low-level driver if needed.) - * @async_dma_dir: If the subdevice supports asynchronous acquisition commands - * and uses DMA to transfer data from the hardware to the acquisition - * buffer, this sets the DMA direction for the buffer. (initialized to - * %DMA_NONE by comedi_alloc_subdevices() and changed by the low-level - * driver if necessary.) - * @state: Handy bit-mask indicating the output states for a DIO or digital - * output subdevice with no more than 32 channels. (Initialized by the - * low-level driver.) - * @class_dev: If the subdevice supports asynchronous acquisition commands, - * this points to a sysfs comediX_subdY device where X is the minor device - * number of the COMEDI device and Y is the subdevice number. The minor - * device number for the sysfs device is allocated dynamically in the - * range 48 to 255. This is used to allow the COMEDI device to be opened - * with a different default read or write subdevice. (Allocated during - * post-configuration if needed.) - * @minor: If @class_dev is set, this is its dynamically allocated minor - * device number. (Set during post-configuration if necessary.) - * @readback: Optional pointer to memory allocated by - * comedi_alloc_subdev_readback() used to hold the values written to - * analog output channels so they can be read back. The storage is - * automatically freed after the low-level driver's "detach" handler is - * called for the device. (Initialized by the low-level driver.) - * - * This is the main control structure for a COMEDI subdevice. If the subdevice - * supports asynchronous acquisition commands, additional information is stored - * in the &struct comedi_async pointed to by @async. - * - * Most of the subdevice is initialized by the low-level driver's "attach" or - * "auto_attach" handlers but parts of it are initialized by - * comedi_alloc_subdevices(), and other parts are initialized during - * post-configuration on return from that handler. - * - * A low-level driver that sets @insn_bits for a digital input, digital output, - * or DIO subdevice may leave @insn_read and @insn_write uninitialized, in - * which case they will be set to a default handler during post-configuration - * that uses @insn_bits to emulate the %INSN_READ and %INSN_WRITE instructions. - */ -struct comedi_subdevice { - struct comedi_device *device; - int index; - int type; - int n_chan; - int subdev_flags; - int len_chanlist; /* maximum length of channel/gain list */ - - void *private; - - struct comedi_async *async; - - void *lock; - void *busy; - unsigned int runflags; - spinlock_t spin_lock; /* generic spin-lock for COMEDI and drivers */ - - unsigned int io_bits; - - unsigned int maxdata; /* if maxdata==0, use list */ - const unsigned int *maxdata_list; /* list is channel specific */ - - const struct comedi_lrange *range_table; - const struct comedi_lrange *const *range_table_list; - - unsigned int *chanlist; /* driver-owned chanlist (not used) */ - - int (*insn_read)(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - int (*insn_write)(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - int (*insn_bits)(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - int (*insn_config)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, - unsigned int *data); - - int (*do_cmd)(struct comedi_device *dev, struct comedi_subdevice *s); - int (*do_cmdtest)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_cmd *cmd); - int (*poll)(struct comedi_device *dev, struct comedi_subdevice *s); - int (*cancel)(struct comedi_device *dev, struct comedi_subdevice *s); - - /* called when the buffer changes */ - int (*buf_change)(struct comedi_device *dev, - struct comedi_subdevice *s); - - void (*munge)(struct comedi_device *dev, struct comedi_subdevice *s, - void *data, unsigned int num_bytes, - unsigned int start_chan_index); - enum dma_data_direction async_dma_dir; - - unsigned int state; - - struct device *class_dev; - int minor; - - unsigned int *readback; -}; - -/** - * struct comedi_buf_page - Describe a page of a COMEDI buffer - * @virt_addr: Kernel address of page. - * @dma_addr: DMA address of page if in DMA coherent memory. - */ -struct comedi_buf_page { - void *virt_addr; - dma_addr_t dma_addr; -}; - -/** - * struct comedi_buf_map - Describe pages in a COMEDI buffer - * @dma_hw_dev: Low-level hardware &struct device pointer copied from the - * COMEDI device's hw_dev member. - * @page_list: Pointer to array of &struct comedi_buf_page, one for each - * page in the buffer. - * @n_pages: Number of pages in the buffer. - * @dma_dir: DMA direction used to allocate pages of DMA coherent memory, - * or %DMA_NONE if pages allocated from regular memory. - * @refcount: &struct kref reference counter used to free the buffer. - * - * A COMEDI data buffer is allocated as individual pages, either in - * conventional memory or DMA coherent memory, depending on the attached, - * low-level hardware device. (The buffer pages also get mapped into the - * kernel's contiguous virtual address space pointed to by the 'prealloc_buf' - * member of &struct comedi_async.) - * - * The buffer is normally freed when the COMEDI device is detached from the - * low-level driver (which may happen due to device removal), but if it happens - * to be mmapped at the time, the pages cannot be freed until the buffer has - * been munmapped. That is what the reference counter is for. (The virtual - * address space pointed by 'prealloc_buf' is freed when the COMEDI device is - * detached.) - */ -struct comedi_buf_map { - struct device *dma_hw_dev; - struct comedi_buf_page *page_list; - unsigned int n_pages; - enum dma_data_direction dma_dir; - struct kref refcount; -}; - -/** - * struct comedi_async - Control data for asynchronous COMEDI commands - * @prealloc_buf: Kernel virtual address of allocated acquisition buffer. - * @prealloc_bufsz: Buffer size (in bytes). - * @buf_map: Map of buffer pages. - * @max_bufsize: Maximum allowed buffer size (in bytes). - * @buf_write_count: "Write completed" count (in bytes, modulo 2**32). - * @buf_write_alloc_count: "Allocated for writing" count (in bytes, - * modulo 2**32). - * @buf_read_count: "Read completed" count (in bytes, modulo 2**32). - * @buf_read_alloc_count: "Allocated for reading" count (in bytes, - * modulo 2**32). - * @buf_write_ptr: Buffer position for writer. - * @buf_read_ptr: Buffer position for reader. - * @cur_chan: Current position in chanlist for scan (for those drivers that - * use it). - * @scans_done: The number of scans completed. - * @scan_progress: Amount received or sent for current scan (in bytes). - * @munge_chan: Current position in chanlist for "munging". - * @munge_count: "Munge" count (in bytes, modulo 2**32). - * @munge_ptr: Buffer position for "munging". - * @events: Bit-vector of events that have occurred. - * @cmd: Details of comedi command in progress. - * @wait_head: Task wait queue for file reader or writer. - * @cb_mask: Bit-vector of events that should wake waiting tasks. - * @inttrig: Software trigger function for command, or NULL. - * - * Note about the ..._count and ..._ptr members: - * - * Think of the _Count values being integers of unlimited size, indexing - * into a buffer of infinite length (though only an advancing portion - * of the buffer of fixed length prealloc_bufsz is accessible at any - * time). Then: - * - * Buf_Read_Count <= Buf_Read_Alloc_Count <= Munge_Count <= - * Buf_Write_Count <= Buf_Write_Alloc_Count <= - * (Buf_Read_Count + prealloc_bufsz) - * - * (Those aren't the actual members, apart from prealloc_bufsz.) When the - * buffer is reset, those _Count values start at 0 and only increase in value, - * maintaining the above inequalities until the next time the buffer is - * reset. The buffer is divided into the following regions by the inequalities: - * - * [0, Buf_Read_Count): - * old region no longer accessible - * - * [Buf_Read_Count, Buf_Read_Alloc_Count): - * filled and munged region allocated for reading but not yet read - * - * [Buf_Read_Alloc_Count, Munge_Count): - * filled and munged region not yet allocated for reading - * - * [Munge_Count, Buf_Write_Count): - * filled region not yet munged - * - * [Buf_Write_Count, Buf_Write_Alloc_Count): - * unfilled region allocated for writing but not yet written - * - * [Buf_Write_Alloc_Count, Buf_Read_Count + prealloc_bufsz): - * unfilled region not yet allocated for writing - * - * [Buf_Read_Count + prealloc_bufsz, infinity): - * unfilled region not yet accessible - * - * Data needs to be written into the buffer before it can be read out, - * and may need to be converted (or "munged") between the two - * operations. Extra unfilled buffer space may need to allocated for - * writing (advancing Buf_Write_Alloc_Count) before new data is written. - * After writing new data, the newly filled space needs to be released - * (advancing Buf_Write_Count). This also results in the new data being - * "munged" (advancing Munge_Count). Before data is read out of the - * buffer, extra space may need to be allocated for reading (advancing - * Buf_Read_Alloc_Count). After the data has been read out, the space - * needs to be released (advancing Buf_Read_Count). - * - * The actual members, buf_read_count, buf_read_alloc_count, - * munge_count, buf_write_count, and buf_write_alloc_count take the - * value of the corresponding capitalized _Count values modulo 2^32 - * (UINT_MAX+1). Subtracting a "higher" _count value from a "lower" - * _count value gives the same answer as subtracting a "higher" _Count - * value from a lower _Count value because prealloc_bufsz < UINT_MAX+1. - * The modulo operation is done implicitly. - * - * The buf_read_ptr, munge_ptr, and buf_write_ptr members take the value - * of the corresponding capitalized _Count values modulo prealloc_bufsz. - * These correspond to byte indices in the physical buffer. The modulo - * operation is done by subtracting prealloc_bufsz when the value - * exceeds prealloc_bufsz (assuming prealloc_bufsz plus the increment is - * less than or equal to UINT_MAX). - */ -struct comedi_async { - void *prealloc_buf; - unsigned int prealloc_bufsz; - struct comedi_buf_map *buf_map; - unsigned int max_bufsize; - unsigned int buf_write_count; - unsigned int buf_write_alloc_count; - unsigned int buf_read_count; - unsigned int buf_read_alloc_count; - unsigned int buf_write_ptr; - unsigned int buf_read_ptr; - unsigned int cur_chan; - unsigned int scans_done; - unsigned int scan_progress; - unsigned int munge_chan; - unsigned int munge_count; - unsigned int munge_ptr; - unsigned int events; - struct comedi_cmd cmd; - wait_queue_head_t wait_head; - unsigned int cb_mask; - int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s, - unsigned int x); -}; - -/** - * enum comedi_cb - &struct comedi_async callback "events" - * @COMEDI_CB_EOS: end-of-scan - * @COMEDI_CB_EOA: end-of-acquisition/output - * @COMEDI_CB_BLOCK: data has arrived, wakes up read() / write() - * @COMEDI_CB_EOBUF: DEPRECATED: end of buffer - * @COMEDI_CB_ERROR: card error during acquisition - * @COMEDI_CB_OVERFLOW: buffer overflow/underflow - * @COMEDI_CB_ERROR_MASK: events that indicate an error has occurred - * @COMEDI_CB_CANCEL_MASK: events that will cancel an async command - */ -enum comedi_cb { - COMEDI_CB_EOS = BIT(0), - COMEDI_CB_EOA = BIT(1), - COMEDI_CB_BLOCK = BIT(2), - COMEDI_CB_EOBUF = BIT(3), - COMEDI_CB_ERROR = BIT(4), - COMEDI_CB_OVERFLOW = BIT(5), - /* masks */ - COMEDI_CB_ERROR_MASK = (COMEDI_CB_ERROR | COMEDI_CB_OVERFLOW), - COMEDI_CB_CANCEL_MASK = (COMEDI_CB_EOA | COMEDI_CB_ERROR_MASK) -}; - -/** - * struct comedi_driver - COMEDI driver registration - * @driver_name: Name of driver. - * @module: Owning module. - * @attach: The optional "attach" handler for manually configured COMEDI - * devices. - * @detach: The "detach" handler for deconfiguring COMEDI devices. - * @auto_attach: The optional "auto_attach" handler for automatically - * configured COMEDI devices. - * @num_names: Optional number of "board names" supported. - * @board_name: Optional pointer to a pointer to a board name. The pointer - * to a board name is embedded in an element of a driver-defined array - * of static, read-only board type information. - * @offset: Optional size of each element of the driver-defined array of - * static, read-only board type information, i.e. the offset between each - * pointer to a board name. - * - * This is used with comedi_driver_register() and comedi_driver_unregister() to - * register and unregister a low-level COMEDI driver with the COMEDI core. - * - * If @num_names is non-zero, @board_name should be non-NULL, and @offset - * should be at least sizeof(*board_name). These are used by the handler for - * the %COMEDI_DEVCONFIG ioctl to match a hardware device and its driver by - * board name. If @num_names is zero, the %COMEDI_DEVCONFIG ioctl matches a - * hardware device and its driver by driver name. This is only useful if the - * @attach handler is set. If @num_names is non-zero, the driver's @attach - * handler will be called with the COMEDI device structure's board_ptr member - * pointing to the matched pointer to a board name within the driver's private - * array of static, read-only board type information. - * - * The @detach handler has two roles. If a COMEDI device was successfully - * configured by the @attach or @auto_attach handler, it is called when the - * device is being deconfigured (by the %COMEDI_DEVCONFIG ioctl, or due to - * unloading of the driver, or due to device removal). It is also called when - * the @attach or @auto_attach handler returns an error. Therefore, the - * @attach or @auto_attach handlers can defer clean-up on error until the - * @detach handler is called. If the @attach or @auto_attach handlers free - * any resources themselves, they must prevent the @detach handler from - * freeing the same resources. The @detach handler must not assume that all - * resources requested by the @attach or @auto_attach handler were - * successfully allocated. - */ -struct comedi_driver { - /* private: */ - struct comedi_driver *next; /* Next in list of COMEDI drivers. */ - /* public: */ - const char *driver_name; - struct module *module; - int (*attach)(struct comedi_device *dev, struct comedi_devconfig *it); - void (*detach)(struct comedi_device *dev); - int (*auto_attach)(struct comedi_device *dev, unsigned long context); - unsigned int num_names; - const char *const *board_name; - int offset; -}; - -/** - * struct comedi_device - Working data for a COMEDI device - * @use_count: Number of open file objects. - * @driver: Low-level COMEDI driver attached to this COMEDI device. - * @pacer: Optional pointer to a dynamically allocated acquisition pacer - * control. It is freed automatically after the COMEDI device is - * detached from the low-level driver. - * @private: Optional pointer to private data allocated by the low-level - * driver. It is freed automatically after the COMEDI device is - * detached from the low-level driver. - * @class_dev: Sysfs comediX device. - * @minor: Minor device number of COMEDI char device (0-47). - * @detach_count: Counter incremented every time the COMEDI device is detached. - * Used for checking a previous attachment is still valid. - * @hw_dev: Optional pointer to the low-level hardware &struct device. It is - * required for automatically configured COMEDI devices and optional for - * COMEDI devices configured by the %COMEDI_DEVCONFIG ioctl, although - * the bus-specific COMEDI functions only work if it is set correctly. - * It is also passed to dma_alloc_coherent() for COMEDI subdevices that - * have their 'async_dma_dir' member set to something other than - * %DMA_NONE. - * @board_name: Pointer to a COMEDI board name or a COMEDI driver name. When - * the low-level driver's "attach" handler is called by the handler for - * the %COMEDI_DEVCONFIG ioctl, it either points to a matched board name - * string if the 'num_names' member of the &struct comedi_driver is - * non-zero, otherwise it points to the low-level driver name string. - * When the low-lever driver's "auto_attach" handler is called for an - * automatically configured COMEDI device, it points to the low-level - * driver name string. The low-level driver is free to change it in its - * "attach" or "auto_attach" handler if it wishes. - * @board_ptr: Optional pointer to private, read-only board type information in - * the low-level driver. If the 'num_names' member of the &struct - * comedi_driver is non-zero, the handler for the %COMEDI_DEVCONFIG ioctl - * will point it to a pointer to a matched board name string within the - * driver's private array of static, read-only board type information when - * calling the driver's "attach" handler. The low-level driver is free to - * change it. - * @attached: Flag indicating that the COMEDI device is attached to a low-level - * driver. - * @ioenabled: Flag used to indicate that a PCI device has been enabled and - * its regions requested. - * @spinlock: Generic spin-lock for use by the low-level driver. - * @mutex: Generic mutex for use by the COMEDI core module. - * @attach_lock: &struct rw_semaphore used to guard against the COMEDI device - * being detached while an operation is in progress. The down_write() - * operation is only allowed while @mutex is held and is used when - * changing @attached and @detach_count and calling the low-level driver's - * "detach" handler. The down_read() operation is generally used without - * holding @mutex. - * @refcount: &struct kref reference counter for freeing COMEDI device. - * @n_subdevices: Number of COMEDI subdevices allocated by the low-level - * driver for this device. - * @subdevices: Dynamically allocated array of COMEDI subdevices. - * @mmio: Optional pointer to a remapped MMIO region set by the low-level - * driver. - * @iobase: Optional base of an I/O port region requested by the low-level - * driver. - * @iolen: Length of I/O port region requested at @iobase. - * @irq: Optional IRQ number requested by the low-level driver. - * @read_subdev: Optional pointer to a default COMEDI subdevice operated on by - * the read() file operation. Set by the low-level driver. - * @write_subdev: Optional pointer to a default COMEDI subdevice operated on by - * the write() file operation. Set by the low-level driver. - * @async_queue: Storage for fasync_helper(). - * @open: Optional pointer to a function set by the low-level driver to be - * called when @use_count changes from 0 to 1. - * @close: Optional pointer to a function set by the low-level driver to be - * called when @use_count changed from 1 to 0. - * @insn_device_config: Optional pointer to a handler for all sub-instructions - * except %INSN_DEVICE_CONFIG_GET_ROUTES of the %INSN_DEVICE_CONFIG - * instruction. If this is not initialized by the low-level driver, a - * default handler will be set during post-configuration. - * @get_valid_routes: Optional pointer to a handler for the - * %INSN_DEVICE_CONFIG_GET_ROUTES sub-instruction of the - * %INSN_DEVICE_CONFIG instruction set. If this is not initialized by the - * low-level driver, a default handler that copies zero routes back to the - * user will be used. - * - * This is the main control data structure for a COMEDI device (as far as the - * COMEDI core is concerned). There are two groups of COMEDI devices - - * "legacy" devices that are configured by the handler for the - * %COMEDI_DEVCONFIG ioctl, and automatically configured devices resulting - * from a call to comedi_auto_config() as a result of a bus driver probe in - * a low-level COMEDI driver. The "legacy" COMEDI devices are allocated - * during module initialization if the "comedi_num_legacy_minors" module - * parameter is non-zero and use minor device numbers from 0 to - * comedi_num_legacy_minors minus one. The automatically configured COMEDI - * devices are allocated on demand and use minor device numbers from - * comedi_num_legacy_minors to 47. - */ -struct comedi_device { - int use_count; - struct comedi_driver *driver; - struct comedi_8254 *pacer; - void *private; - - struct device *class_dev; - int minor; - unsigned int detach_count; - struct device *hw_dev; - - const char *board_name; - const void *board_ptr; - unsigned int attached:1; - unsigned int ioenabled:1; - spinlock_t spinlock; /* generic spin-lock for low-level driver */ - struct mutex mutex; /* generic mutex for COMEDI core */ - struct rw_semaphore attach_lock; - struct kref refcount; - - int n_subdevices; - struct comedi_subdevice *subdevices; - - /* dumb */ - void __iomem *mmio; - unsigned long iobase; - unsigned long iolen; - unsigned int irq; - - struct comedi_subdevice *read_subdev; - struct comedi_subdevice *write_subdev; - - struct fasync_struct *async_queue; - - int (*open)(struct comedi_device *dev); - void (*close)(struct comedi_device *dev); - int (*insn_device_config)(struct comedi_device *dev, - struct comedi_insn *insn, unsigned int *data); - unsigned int (*get_valid_routes)(struct comedi_device *dev, - unsigned int n_pairs, - unsigned int *pair_data); -}; - -/* - * function prototypes - */ - -void comedi_event(struct comedi_device *dev, struct comedi_subdevice *s); - -struct comedi_device *comedi_dev_get_from_minor(unsigned int minor); -int comedi_dev_put(struct comedi_device *dev); - -bool comedi_is_subdevice_running(struct comedi_subdevice *s); - -void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size); -void comedi_set_spriv_auto_free(struct comedi_subdevice *s); - -int comedi_check_chanlist(struct comedi_subdevice *s, - int n, - unsigned int *chanlist); - -/* range stuff */ - -#define RANGE(a, b) {(a) * 1e6, (b) * 1e6, 0} -#define RANGE_ext(a, b) {(a) * 1e6, (b) * 1e6, RF_EXTERNAL} -#define RANGE_mA(a, b) {(a) * 1e6, (b) * 1e6, UNIT_mA} -#define RANGE_unitless(a, b) {(a) * 1e6, (b) * 1e6, 0} -#define BIP_RANGE(a) {-(a) * 1e6, (a) * 1e6, 0} -#define UNI_RANGE(a) {0, (a) * 1e6, 0} - -extern const struct comedi_lrange range_bipolar10; -extern const struct comedi_lrange range_bipolar5; -extern const struct comedi_lrange range_bipolar2_5; -extern const struct comedi_lrange range_unipolar10; -extern const struct comedi_lrange range_unipolar5; -extern const struct comedi_lrange range_unipolar2_5; -extern const struct comedi_lrange range_0_20mA; -extern const struct comedi_lrange range_4_20mA; -extern const struct comedi_lrange range_0_32mA; -extern const struct comedi_lrange range_unknown; - -#define range_digital range_unipolar5 - -/** - * struct comedi_lrange - Describes a COMEDI range table - * @length: Number of entries in the range table. - * @range: Array of &struct comedi_krange, one for each range. - * - * Each element of @range[] describes the minimum and maximum physical range - * and the type of units. Typically, the type of unit is %UNIT_volt - * (i.e. volts) and the minimum and maximum are in millionths of a volt. - * There may also be a flag that indicates the minimum and maximum are merely - * scale factors for an unknown, external reference. - */ -struct comedi_lrange { - int length; - struct comedi_krange range[]; -}; - -/** - * comedi_range_is_bipolar() - Test if subdevice range is bipolar - * @s: COMEDI subdevice. - * @range: Index of range within a range table. - * - * Tests whether a range is bipolar by checking whether its minimum value - * is negative. - * - * Assumes @range is valid. Does not work for subdevices using a - * channel-specific range table list. - * - * Return: - * %true if the range is bipolar. - * %false if the range is unipolar. - */ -static inline bool comedi_range_is_bipolar(struct comedi_subdevice *s, - unsigned int range) -{ - return s->range_table->range[range].min < 0; -} - -/** - * comedi_range_is_unipolar() - Test if subdevice range is unipolar - * @s: COMEDI subdevice. - * @range: Index of range within a range table. - * - * Tests whether a range is unipolar by checking whether its minimum value - * is at least 0. - * - * Assumes @range is valid. Does not work for subdevices using a - * channel-specific range table list. - * - * Return: - * %true if the range is unipolar. - * %false if the range is bipolar. - */ -static inline bool comedi_range_is_unipolar(struct comedi_subdevice *s, - unsigned int range) -{ - return s->range_table->range[range].min >= 0; -} - -/** - * comedi_range_is_external() - Test if subdevice range is external - * @s: COMEDI subdevice. - * @range: Index of range within a range table. - * - * Tests whether a range is externally reference by checking whether its - * %RF_EXTERNAL flag is set. - * - * Assumes @range is valid. Does not work for subdevices using a - * channel-specific range table list. - * - * Return: - * %true if the range is external. - * %false if the range is internal. - */ -static inline bool comedi_range_is_external(struct comedi_subdevice *s, - unsigned int range) -{ - return !!(s->range_table->range[range].flags & RF_EXTERNAL); -} - -/** - * comedi_chan_range_is_bipolar() - Test if channel-specific range is bipolar - * @s: COMEDI subdevice. - * @chan: The channel number. - * @range: Index of range within a range table. - * - * Tests whether a range is bipolar by checking whether its minimum value - * is negative. - * - * Assumes @chan and @range are valid. Only works for subdevices with a - * channel-specific range table list. - * - * Return: - * %true if the range is bipolar. - * %false if the range is unipolar. - */ -static inline bool comedi_chan_range_is_bipolar(struct comedi_subdevice *s, - unsigned int chan, - unsigned int range) -{ - return s->range_table_list[chan]->range[range].min < 0; -} - -/** - * comedi_chan_range_is_unipolar() - Test if channel-specific range is unipolar - * @s: COMEDI subdevice. - * @chan: The channel number. - * @range: Index of range within a range table. - * - * Tests whether a range is unipolar by checking whether its minimum value - * is at least 0. - * - * Assumes @chan and @range are valid. Only works for subdevices with a - * channel-specific range table list. - * - * Return: - * %true if the range is unipolar. - * %false if the range is bipolar. - */ -static inline bool comedi_chan_range_is_unipolar(struct comedi_subdevice *s, - unsigned int chan, - unsigned int range) -{ - return s->range_table_list[chan]->range[range].min >= 0; -} - -/** - * comedi_chan_range_is_external() - Test if channel-specific range is external - * @s: COMEDI subdevice. - * @chan: The channel number. - * @range: Index of range within a range table. - * - * Tests whether a range is externally reference by checking whether its - * %RF_EXTERNAL flag is set. - * - * Assumes @chan and @range are valid. Only works for subdevices with a - * channel-specific range table list. - * - * Return: - * %true if the range is bipolar. - * %false if the range is unipolar. - */ -static inline bool comedi_chan_range_is_external(struct comedi_subdevice *s, - unsigned int chan, - unsigned int range) -{ - return !!(s->range_table_list[chan]->range[range].flags & RF_EXTERNAL); -} - -/** - * comedi_offset_munge() - Convert between offset binary and 2's complement - * @s: COMEDI subdevice. - * @val: Value to be converted. - * - * Toggles the highest bit of a sample value to toggle between offset binary - * and 2's complement. Assumes that @s->maxdata is a power of 2 minus 1. - * - * Return: The converted value. - */ -static inline unsigned int comedi_offset_munge(struct comedi_subdevice *s, - unsigned int val) -{ - return val ^ s->maxdata ^ (s->maxdata >> 1); -} - -/** - * comedi_bytes_per_sample() - Determine subdevice sample size - * @s: COMEDI subdevice. - * - * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on - * whether the %SDF_LSAMPL subdevice flag is set or not. - * - * Return: The subdevice sample size. - */ -static inline unsigned int comedi_bytes_per_sample(struct comedi_subdevice *s) -{ - return s->subdev_flags & SDF_LSAMPL ? sizeof(int) : sizeof(short); -} - -/** - * comedi_sample_shift() - Determine log2 of subdevice sample size - * @s: COMEDI subdevice. - * - * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on - * whether the %SDF_LSAMPL subdevice flag is set or not. The log2 of the - * sample size will be 2 or 1 and can be used as the right operand of a - * bit-shift operator to multiply or divide something by the sample size. - * - * Return: log2 of the subdevice sample size. - */ -static inline unsigned int comedi_sample_shift(struct comedi_subdevice *s) -{ - return s->subdev_flags & SDF_LSAMPL ? 2 : 1; -} - -/** - * comedi_bytes_to_samples() - Convert a number of bytes to a number of samples - * @s: COMEDI subdevice. - * @nbytes: Number of bytes - * - * Return: The number of bytes divided by the subdevice sample size. - */ -static inline unsigned int comedi_bytes_to_samples(struct comedi_subdevice *s, - unsigned int nbytes) -{ - return nbytes >> comedi_sample_shift(s); -} - -/** - * comedi_samples_to_bytes() - Convert a number of samples to a number of bytes - * @s: COMEDI subdevice. - * @nsamples: Number of samples. - * - * Return: The number of samples multiplied by the subdevice sample size. - * (Does not check for arithmetic overflow.) - */ -static inline unsigned int comedi_samples_to_bytes(struct comedi_subdevice *s, - unsigned int nsamples) -{ - return nsamples << comedi_sample_shift(s); -} - -/** - * comedi_check_trigger_src() - Trivially validate a comedi_cmd trigger source - * @src: Pointer to the trigger source to validate. - * @flags: Bitmask of valid %TRIG_* for the trigger. - * - * This is used in "step 1" of the do_cmdtest functions of comedi drivers - * to validate the comedi_cmd triggers. The mask of the @src against the - * @flags allows the userspace comedilib to pass all the comedi_cmd - * triggers as %TRIG_ANY and get back a bitmask of the valid trigger sources. - * - * Return: - * 0 if trigger sources in *@src are all supported. - * -EINVAL if any trigger source in *@src is unsupported. - */ -static inline int comedi_check_trigger_src(unsigned int *src, - unsigned int flags) -{ - unsigned int orig_src = *src; - - *src = orig_src & flags; - if (*src == TRIG_INVALID || *src != orig_src) - return -EINVAL; - return 0; -} - -/** - * comedi_check_trigger_is_unique() - Make sure a trigger source is unique - * @src: The trigger source to check. - * - * Return: - * 0 if no more than one trigger source is set. - * -EINVAL if more than one trigger source is set. - */ -static inline int comedi_check_trigger_is_unique(unsigned int src) -{ - /* this test is true if more than one _src bit is set */ - if ((src & (src - 1)) != 0) - return -EINVAL; - return 0; -} - -/** - * comedi_check_trigger_arg_is() - Trivially validate a trigger argument - * @arg: Pointer to the trigger arg to validate. - * @val: The value the argument should be. - * - * Forces *@arg to be @val. - * - * Return: - * 0 if *@arg was already @val. - * -EINVAL if *@arg differed from @val. - */ -static inline int comedi_check_trigger_arg_is(unsigned int *arg, - unsigned int val) -{ - if (*arg != val) { - *arg = val; - return -EINVAL; - } - return 0; -} - -/** - * comedi_check_trigger_arg_min() - Trivially validate a trigger argument min - * @arg: Pointer to the trigger arg to validate. - * @val: The minimum value the argument should be. - * - * Forces *@arg to be at least @val, setting it to @val if necessary. - * - * Return: - * 0 if *@arg was already at least @val. - * -EINVAL if *@arg was less than @val. - */ -static inline int comedi_check_trigger_arg_min(unsigned int *arg, - unsigned int val) -{ - if (*arg < val) { - *arg = val; - return -EINVAL; - } - return 0; -} - -/** - * comedi_check_trigger_arg_max() - Trivially validate a trigger argument max - * @arg: Pointer to the trigger arg to validate. - * @val: The maximum value the argument should be. - * - * Forces *@arg to be no more than @val, setting it to @val if necessary. - * - * Return: - * 0 if*@arg was already no more than @val. - * -EINVAL if *@arg was greater than @val. - */ -static inline int comedi_check_trigger_arg_max(unsigned int *arg, - unsigned int val) -{ - if (*arg > val) { - *arg = val; - return -EINVAL; - } - return 0; -} - -/* - * Must set dev->hw_dev if you wish to dma directly into comedi's buffer. - * Also useful for retrieving a previously configured hardware device of - * known bus type. Set automatically for auto-configured devices. - * Automatically set to NULL when detaching hardware device. - */ -int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev); - -/** - * comedi_buf_n_bytes_ready - Determine amount of unread data in buffer - * @s: COMEDI subdevice. - * - * Determines the number of bytes of unread data in the asynchronous - * acquisition data buffer for a subdevice. The data in question might not - * have been fully "munged" yet. - * - * Returns: The amount of unread data in bytes. - */ -static inline unsigned int comedi_buf_n_bytes_ready(struct comedi_subdevice *s) -{ - return s->async->buf_write_count - s->async->buf_read_count; -} - -unsigned int comedi_buf_write_alloc(struct comedi_subdevice *s, unsigned int n); -unsigned int comedi_buf_write_free(struct comedi_subdevice *s, unsigned int n); - -unsigned int comedi_buf_read_n_available(struct comedi_subdevice *s); -unsigned int comedi_buf_read_alloc(struct comedi_subdevice *s, unsigned int n); -unsigned int comedi_buf_read_free(struct comedi_subdevice *s, unsigned int n); - -unsigned int comedi_buf_write_samples(struct comedi_subdevice *s, - const void *data, unsigned int nsamples); -unsigned int comedi_buf_read_samples(struct comedi_subdevice *s, - void *data, unsigned int nsamples); - -/* drivers.c - general comedi driver functions */ - -#define COMEDI_TIMEOUT_MS 1000 - -int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, - int (*cb)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned long context), - unsigned long context); - -unsigned int comedi_handle_events(struct comedi_device *dev, - struct comedi_subdevice *s); - -int comedi_dio_insn_config(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data, - unsigned int mask); -unsigned int comedi_dio_update_state(struct comedi_subdevice *s, - unsigned int *data); -unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, - struct comedi_cmd *cmd); -unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); -unsigned int comedi_nscans_left(struct comedi_subdevice *s, - unsigned int nscans); -unsigned int comedi_nsamples_left(struct comedi_subdevice *s, - unsigned int nsamples); -void comedi_inc_scan_progress(struct comedi_subdevice *s, - unsigned int num_bytes); - -void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size); -int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices); -int comedi_alloc_subdev_readback(struct comedi_subdevice *s); - -int comedi_readback_insn_read(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - -int comedi_load_firmware(struct comedi_device *dev, struct device *hw_dev, - const char *name, - int (*cb)(struct comedi_device *dev, - const u8 *data, size_t size, - unsigned long context), - unsigned long context); - -int __comedi_request_region(struct comedi_device *dev, - unsigned long start, unsigned long len); -int comedi_request_region(struct comedi_device *dev, - unsigned long start, unsigned long len); -void comedi_legacy_detach(struct comedi_device *dev); - -int comedi_auto_config(struct device *hardware_device, - struct comedi_driver *driver, unsigned long context); -void comedi_auto_unconfig(struct device *hardware_device); - -int comedi_driver_register(struct comedi_driver *driver); -void comedi_driver_unregister(struct comedi_driver *driver); - -/** - * module_comedi_driver() - Helper macro for registering a comedi driver - * @__comedi_driver: comedi_driver struct - * - * Helper macro for comedi drivers which do not do anything special in module - * init/exit. This eliminates a lot of boilerplate. Each module may only use - * this macro once, and calling it replaces module_init() and module_exit(). - */ -#define module_comedi_driver(__comedi_driver) \ - module_driver(__comedi_driver, comedi_driver_register, \ - comedi_driver_unregister) - -#endif /* _COMEDIDEV_H */ diff --git a/drivers/comedi/comedilib.h b/drivers/comedi/comedilib.h deleted file mode 100644 index 0223c9cd9215..000000000000 --- a/drivers/comedi/comedilib.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedilib.h - * Header file for kcomedilib - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1998-2001 David A. Schleef - */ - -#ifndef _LINUX_COMEDILIB_H -#define _LINUX_COMEDILIB_H - -struct comedi_device *comedi_open(const char *path); -int comedi_close(struct comedi_device *dev); -int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev, - unsigned int chan, unsigned int *io); -int comedi_dio_config(struct comedi_device *dev, unsigned int subdev, - unsigned int chan, unsigned int io); -int comedi_dio_bitfield2(struct comedi_device *dev, unsigned int subdev, - unsigned int mask, unsigned int *bits, - unsigned int base_channel); -int comedi_find_subdevice_by_type(struct comedi_device *dev, int type, - unsigned int subd); -int comedi_get_n_channels(struct comedi_device *dev, unsigned int subdevice); - -#endif diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c index 750a6ff3c03c..8eb1f699a857 100644 --- a/drivers/comedi/drivers.c +++ b/drivers/comedi/drivers.c @@ -17,8 +17,7 @@ #include #include #include - -#include "comedidev.h" +#include #include "comedi_internal.h" struct comedi_driver *comedi_drivers; diff --git a/drivers/comedi/drivers/8255.c b/drivers/comedi/drivers/8255.c index e23335c75867..f23a52b7c919 100644 --- a/drivers/comedi/drivers/8255.c +++ b/drivers/comedi/drivers/8255.c @@ -40,7 +40,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/8255_pci.c b/drivers/comedi/drivers/8255_pci.c index 5a810f0e532a..76b8b4762bae 100644 --- a/drivers/comedi/drivers/8255_pci.c +++ b/drivers/comedi/drivers/8255_pci.c @@ -53,8 +53,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/addi_apci_1032.c b/drivers/comedi/drivers/addi_apci_1032.c index 81a246fbcc01..8eec6d9402de 100644 --- a/drivers/comedi/drivers/addi_apci_1032.c +++ b/drivers/comedi/drivers/addi_apci_1032.c @@ -63,8 +63,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/addi_apci_1500.c b/drivers/comedi/drivers/addi_apci_1500.c index b04c15dcfb57..c94c78588889 100644 --- a/drivers/comedi/drivers/addi_apci_1500.c +++ b/drivers/comedi/drivers/addi_apci_1500.c @@ -14,8 +14,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" #include "z8536.h" diff --git a/drivers/comedi/drivers/addi_apci_1516.c b/drivers/comedi/drivers/addi_apci_1516.c index 274ec9fb030c..3c48b72dad9d 100644 --- a/drivers/comedi/drivers/addi_apci_1516.c +++ b/drivers/comedi/drivers/addi_apci_1516.c @@ -14,8 +14,8 @@ */ #include +#include -#include "../comedi_pci.h" #include "addi_watchdog.h" /* diff --git a/drivers/comedi/drivers/addi_apci_1564.c b/drivers/comedi/drivers/addi_apci_1564.c index 06fc7ed96200..0cd40948bee7 100644 --- a/drivers/comedi/drivers/addi_apci_1564.c +++ b/drivers/comedi/drivers/addi_apci_1564.c @@ -68,8 +68,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "addi_tcw.h" #include "addi_watchdog.h" diff --git a/drivers/comedi/drivers/addi_apci_16xx.c b/drivers/comedi/drivers/addi_apci_16xx.c index c306aa41df97..ec2c321d2431 100644 --- a/drivers/comedi/drivers/addi_apci_16xx.c +++ b/drivers/comedi/drivers/addi_apci_16xx.c @@ -14,8 +14,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/addi_apci_2032.c b/drivers/comedi/drivers/addi_apci_2032.c index e9a2b37a4ae0..e048dfc3ec77 100644 --- a/drivers/comedi/drivers/addi_apci_2032.c +++ b/drivers/comedi/drivers/addi_apci_2032.c @@ -16,8 +16,8 @@ #include #include #include +#include -#include "../comedi_pci.h" #include "addi_watchdog.h" /* diff --git a/drivers/comedi/drivers/addi_apci_2200.c b/drivers/comedi/drivers/addi_apci_2200.c index 4c5aee784bd9..00378c9dddc8 100644 --- a/drivers/comedi/drivers/addi_apci_2200.c +++ b/drivers/comedi/drivers/addi_apci_2200.c @@ -14,8 +14,8 @@ */ #include +#include -#include "../comedi_pci.h" #include "addi_watchdog.h" /* diff --git a/drivers/comedi/drivers/addi_apci_3120.c b/drivers/comedi/drivers/addi_apci_3120.c index 1ed3b33d1a30..28a242e69721 100644 --- a/drivers/comedi/drivers/addi_apci_3120.c +++ b/drivers/comedi/drivers/addi_apci_3120.c @@ -14,8 +14,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/addi_apci_3501.c b/drivers/comedi/drivers/addi_apci_3501.c index f0c9642f3f1a..ecb5552f1785 100644 --- a/drivers/comedi/drivers/addi_apci_3501.c +++ b/drivers/comedi/drivers/addi_apci_3501.c @@ -41,8 +41,8 @@ */ #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/addi_apci_3xxx.c b/drivers/comedi/drivers/addi_apci_3xxx.c index a90d59377e18..bc72273e6a29 100644 --- a/drivers/comedi/drivers/addi_apci_3xxx.c +++ b/drivers/comedi/drivers/addi_apci_3xxx.c @@ -15,8 +15,7 @@ #include #include - -#include "../comedi_pci.h" +#include #define CONV_UNIT_NS BIT(0) #define CONV_UNIT_US BIT(1) diff --git a/drivers/comedi/drivers/addi_watchdog.c b/drivers/comedi/drivers/addi_watchdog.c index 69b323fb869f..ed87ab432020 100644 --- a/drivers/comedi/drivers/addi_watchdog.c +++ b/drivers/comedi/drivers/addi_watchdog.c @@ -10,7 +10,7 @@ */ #include -#include "../comedidev.h" +#include #include "addi_tcw.h" #include "addi_watchdog.h" diff --git a/drivers/comedi/drivers/adl_pci6208.c b/drivers/comedi/drivers/adl_pci6208.c index 9ae4cc523dd4..b27354a51f5c 100644 --- a/drivers/comedi/drivers/adl_pci6208.c +++ b/drivers/comedi/drivers/adl_pci6208.c @@ -24,8 +24,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI-6208/6216-GL register map diff --git a/drivers/comedi/drivers/adl_pci7x3x.c b/drivers/comedi/drivers/adl_pci7x3x.c index 8fc45638ff59..e9f22de9b6f1 100644 --- a/drivers/comedi/drivers/adl_pci7x3x.c +++ b/drivers/comedi/drivers/adl_pci7x3x.c @@ -46,8 +46,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "plx9052.h" diff --git a/drivers/comedi/drivers/adl_pci8164.c b/drivers/comedi/drivers/adl_pci8164.c index d5e1bda81557..0c513a67a264 100644 --- a/drivers/comedi/drivers/adl_pci8164.c +++ b/drivers/comedi/drivers/adl_pci8164.c @@ -19,8 +19,7 @@ #include #include - -#include "../comedi_pci.h" +#include #define PCI8164_AXIS(x) ((x) * 0x08) #define PCI8164_CMD_MSTS_REG 0x00 diff --git a/drivers/comedi/drivers/adl_pci9111.c b/drivers/comedi/drivers/adl_pci9111.c index a062c5ab20e9..65454f3ecc91 100644 --- a/drivers/comedi/drivers/adl_pci9111.c +++ b/drivers/comedi/drivers/adl_pci9111.c @@ -42,8 +42,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "plx9052.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/adl_pci9118.c b/drivers/comedi/drivers/adl_pci9118.c index cda3a4267dca..248cec3d894f 100644 --- a/drivers/comedi/drivers/adl_pci9118.c +++ b/drivers/comedi/drivers/adl_pci9118.c @@ -78,8 +78,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "amcc_s5933.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/adq12b.c b/drivers/comedi/drivers/adq12b.c index d719f76709ef..19d765182006 100644 --- a/drivers/comedi/drivers/adq12b.c +++ b/drivers/comedi/drivers/adq12b.c @@ -48,8 +48,7 @@ #include #include - -#include "../comedidev.h" +#include /* address scheme (page 2.17 of the manual) */ #define ADQ12B_CTREG 0x00 diff --git a/drivers/comedi/drivers/adv_pci1710.c b/drivers/comedi/drivers/adv_pci1710.c index 090607760be6..47a800d72e58 100644 --- a/drivers/comedi/drivers/adv_pci1710.c +++ b/drivers/comedi/drivers/adv_pci1710.c @@ -30,8 +30,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "amcc_s5933.h" diff --git a/drivers/comedi/drivers/adv_pci1720.c b/drivers/comedi/drivers/adv_pci1720.c index 2fcd7e8e7d85..2619591ba301 100644 --- a/drivers/comedi/drivers/adv_pci1720.c +++ b/drivers/comedi/drivers/adv_pci1720.c @@ -42,8 +42,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR2 Register map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1723.c b/drivers/comedi/drivers/adv_pci1723.c index 23660a9fdb9c..e2aedb152068 100644 --- a/drivers/comedi/drivers/adv_pci1723.c +++ b/drivers/comedi/drivers/adv_pci1723.c @@ -32,8 +32,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI Bar 2 I/O Register map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1724.c b/drivers/comedi/drivers/adv_pci1724.c index e8ab573c839f..bb43b7deeb56 100644 --- a/drivers/comedi/drivers/adv_pci1724.c +++ b/drivers/comedi/drivers/adv_pci1724.c @@ -38,8 +38,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI bar 2 Register I/O map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1760.c b/drivers/comedi/drivers/adv_pci1760.c index 6de8ab97d346..fcfc2e299110 100644 --- a/drivers/comedi/drivers/adv_pci1760.c +++ b/drivers/comedi/drivers/adv_pci1760.c @@ -22,8 +22,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI-1760 Register Map diff --git a/drivers/comedi/drivers/adv_pci_dio.c b/drivers/comedi/drivers/adv_pci_dio.c index 54c7419c8ca6..5947f08b9a1e 100644 --- a/drivers/comedi/drivers/adv_pci_dio.c +++ b/drivers/comedi/drivers/adv_pci_dio.c @@ -23,8 +23,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "8255.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/aio_aio12_8.c b/drivers/comedi/drivers/aio_aio12_8.c index 4829115921a3..36c3a2d8a352 100644 --- a/drivers/comedi/drivers/aio_aio12_8.c +++ b/drivers/comedi/drivers/aio_aio12_8.c @@ -22,7 +22,7 @@ */ #include -#include "../comedidev.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/aio_iiro_16.c b/drivers/comedi/drivers/aio_iiro_16.c index fe3876235075..b00fab0b89d4 100644 --- a/drivers/comedi/drivers/aio_iiro_16.c +++ b/drivers/comedi/drivers/aio_iiro_16.c @@ -30,8 +30,7 @@ #include #include - -#include "../comedidev.h" +#include #define AIO_IIRO_16_RELAY_0_7 0x00 #define AIO_IIRO_16_INPUT_0_7 0x01 diff --git a/drivers/comedi/drivers/amplc_dio200.c b/drivers/comedi/drivers/amplc_dio200.c index fa19c9e7c56b..4544bcdd8a70 100644 --- a/drivers/comedi/drivers/amplc_dio200.c +++ b/drivers/comedi/drivers/amplc_dio200.c @@ -185,7 +185,7 @@ */ #include -#include "../comedidev.h" +#include #include "amplc_dio200.h" diff --git a/drivers/comedi/drivers/amplc_dio200_common.c b/drivers/comedi/drivers/amplc_dio200_common.c index a3454130d5f8..950c50be4ff3 100644 --- a/drivers/comedi/drivers/amplc_dio200_common.c +++ b/drivers/comedi/drivers/amplc_dio200_common.c @@ -12,8 +12,7 @@ #include #include - -#include "../comedidev.h" +#include #include "amplc_dio200.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/amplc_dio200_pci.c b/drivers/comedi/drivers/amplc_dio200_pci.c index 1bd7a42c8464..527994d82a1f 100644 --- a/drivers/comedi/drivers/amplc_dio200_pci.c +++ b/drivers/comedi/drivers/amplc_dio200_pci.c @@ -214,8 +214,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "amplc_dio200.h" diff --git a/drivers/comedi/drivers/amplc_pc236.c b/drivers/comedi/drivers/amplc_pc236.c index c377af1d5246..b21e0c906aab 100644 --- a/drivers/comedi/drivers/amplc_pc236.c +++ b/drivers/comedi/drivers/amplc_pc236.c @@ -32,8 +32,7 @@ */ #include - -#include "../comedidev.h" +#include #include "amplc_pc236.h" diff --git a/drivers/comedi/drivers/amplc_pc236_common.c b/drivers/comedi/drivers/amplc_pc236_common.c index 981d281e87a1..b8b0a624f72b 100644 --- a/drivers/comedi/drivers/amplc_pc236_common.c +++ b/drivers/comedi/drivers/amplc_pc236_common.c @@ -11,8 +11,7 @@ #include #include - -#include "../comedidev.h" +#include #include "amplc_pc236.h" #include "8255.h" diff --git a/drivers/comedi/drivers/amplc_pc263.c b/drivers/comedi/drivers/amplc_pc263.c index 68da6098ee84..d7f088a8a5e3 100644 --- a/drivers/comedi/drivers/amplc_pc263.c +++ b/drivers/comedi/drivers/amplc_pc263.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include /* PC263 registers */ #define PC263_DO_0_7_REG 0x00 diff --git a/drivers/comedi/drivers/amplc_pci224.c b/drivers/comedi/drivers/amplc_pci224.c index bcf6d61af863..3cf1b7fa565d 100644 --- a/drivers/comedi/drivers/amplc_pci224.c +++ b/drivers/comedi/drivers/amplc_pci224.c @@ -96,8 +96,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/amplc_pci230.c b/drivers/comedi/drivers/amplc_pci230.c index 8911dc2bd2c6..554ee40e321f 100644 --- a/drivers/comedi/drivers/amplc_pci230.c +++ b/drivers/comedi/drivers/amplc_pci230.c @@ -174,8 +174,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/amplc_pci236.c b/drivers/comedi/drivers/amplc_pci236.c index e7f6fa4d101a..482eb261c333 100644 --- a/drivers/comedi/drivers/amplc_pci236.c +++ b/drivers/comedi/drivers/amplc_pci236.c @@ -34,8 +34,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "amplc_pc236.h" #include "plx9052.h" diff --git a/drivers/comedi/drivers/amplc_pci263.c b/drivers/comedi/drivers/amplc_pci263.c index 9217973f1141..1609665c4b18 100644 --- a/drivers/comedi/drivers/amplc_pci263.c +++ b/drivers/comedi/drivers/amplc_pci263.c @@ -24,8 +24,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* PCI263 registers */ #define PCI263_DO_0_7_REG 0x00 diff --git a/drivers/comedi/drivers/c6xdigio.c b/drivers/comedi/drivers/c6xdigio.c index 786fd15698df..14b90d1c64dc 100644 --- a/drivers/comedi/drivers/c6xdigio.c +++ b/drivers/comedi/drivers/c6xdigio.c @@ -30,8 +30,7 @@ #include #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/cb_das16_cs.c b/drivers/comedi/drivers/cb_das16_cs.c index a5d171e71c33..190d73a7d12c 100644 --- a/drivers/comedi/drivers/cb_das16_cs.c +++ b/drivers/comedi/drivers/cb_das16_cs.c @@ -27,8 +27,7 @@ #include #include #include - -#include "../comedi_pcmcia.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/cb_pcidas.c b/drivers/comedi/drivers/cb_pcidas.c index 2f20bd56ec6c..9b603532a4e7 100644 --- a/drivers/comedi/drivers/cb_pcidas.c +++ b/drivers/comedi/drivers/cb_pcidas.c @@ -54,8 +54,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/cb_pcidas64.c b/drivers/comedi/drivers/cb_pcidas64.c index 41a8fea7f48a..7d4808faa1fb 100644 --- a/drivers/comedi/drivers/cb_pcidas64.c +++ b/drivers/comedi/drivers/cb_pcidas64.c @@ -73,8 +73,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "8255.h" #include "plx9080.h" diff --git a/drivers/comedi/drivers/cb_pcidda.c b/drivers/comedi/drivers/cb_pcidda.c index 78cf1603638c..4ed3bcf47973 100644 --- a/drivers/comedi/drivers/cb_pcidda.c +++ b/drivers/comedi/drivers/cb_pcidda.c @@ -27,8 +27,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/cb_pcimdas.c b/drivers/comedi/drivers/cb_pcimdas.c index 2292f69da4f4..64c7d72c7956 100644 --- a/drivers/comedi/drivers/cb_pcimdas.c +++ b/drivers/comedi/drivers/cb_pcimdas.c @@ -34,8 +34,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "plx9052.h" diff --git a/drivers/comedi/drivers/cb_pcimdda.c b/drivers/comedi/drivers/cb_pcimdda.c index 21fc7b3c5f60..69d7803b0e58 100644 --- a/drivers/comedi/drivers/cb_pcimdda.c +++ b/drivers/comedi/drivers/cb_pcimdda.c @@ -67,8 +67,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/comedi_8254.c b/drivers/comedi/drivers/comedi_8254.c index 4bf5daa9e885..fac81567133d 100644 --- a/drivers/comedi/drivers/comedi_8254.c +++ b/drivers/comedi/drivers/comedi_8254.c @@ -116,8 +116,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c index b7ca465933ee..10614603d677 100644 --- a/drivers/comedi/drivers/comedi_8255.c +++ b/drivers/comedi/drivers/comedi_8255.c @@ -29,7 +29,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/comedi_bond.c b/drivers/comedi/drivers/comedi_bond.c index 4392b5927a99..78c39fa84177 100644 --- a/drivers/comedi/drivers/comedi_bond.c +++ b/drivers/comedi/drivers/comedi_bond.c @@ -40,9 +40,9 @@ #include #include #include -#include "../comedi.h" -#include "../comedilib.h" -#include "../comedidev.h" +#include +#include +#include struct bonded_device { struct comedi_device *dev; diff --git a/drivers/comedi/drivers/comedi_isadma.c b/drivers/comedi/drivers/comedi_isadma.c index 479b58e209ba..63457bd4ff78 100644 --- a/drivers/comedi/drivers/comedi_isadma.c +++ b/drivers/comedi/drivers/comedi_isadma.c @@ -9,8 +9,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" diff --git a/drivers/comedi/drivers/comedi_parport.c b/drivers/comedi/drivers/comedi_parport.c index 5338b5eea440..098738a688fe 100644 --- a/drivers/comedi/drivers/comedi_parport.c +++ b/drivers/comedi/drivers/comedi_parport.c @@ -57,8 +57,7 @@ #include #include - -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index cbc225eb1991..0b5c0af1cebf 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -45,10 +45,8 @@ */ #include -#include "../comedidev.h" - +#include #include - #include #include #include diff --git a/drivers/comedi/drivers/contec_pci_dio.c b/drivers/comedi/drivers/contec_pci_dio.c index b8fdd9c1f166..41d42ff14144 100644 --- a/drivers/comedi/drivers/contec_pci_dio.c +++ b/drivers/comedi/drivers/contec_pci_dio.c @@ -18,8 +18,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/dac02.c b/drivers/comedi/drivers/dac02.c index 5ef8114c2c85..4b011d66d7b0 100644 --- a/drivers/comedi/drivers/dac02.c +++ b/drivers/comedi/drivers/dac02.c @@ -25,8 +25,7 @@ */ #include - -#include "../comedidev.h" +#include /* * The output range is selected by jumpering pins on the I/O connector. diff --git a/drivers/comedi/drivers/daqboard2000.c b/drivers/comedi/drivers/daqboard2000.c index f64e747078bd..52e4bf16cbda 100644 --- a/drivers/comedi/drivers/daqboard2000.c +++ b/drivers/comedi/drivers/daqboard2000.c @@ -96,8 +96,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "8255.h" #include "plx9080.h" diff --git a/drivers/comedi/drivers/das08.c b/drivers/comedi/drivers/das08.c index b50743c5b822..c146a168f43b 100644 --- a/drivers/comedi/drivers/das08.c +++ b/drivers/comedi/drivers/das08.c @@ -10,8 +10,7 @@ */ #include - -#include "../comedidev.h" +#include #include "8255.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das08_cs.c b/drivers/comedi/drivers/das08_cs.c index 223479f9ea3c..6075efcf10d6 100644 --- a/drivers/comedi/drivers/das08_cs.c +++ b/drivers/comedi/drivers/das08_cs.c @@ -30,8 +30,7 @@ */ #include - -#include "../comedi_pcmcia.h" +#include #include "das08.h" diff --git a/drivers/comedi/drivers/das08_isa.c b/drivers/comedi/drivers/das08_isa.c index 8c4cfa821423..3d43b77cc9f4 100644 --- a/drivers/comedi/drivers/das08_isa.c +++ b/drivers/comedi/drivers/das08_isa.c @@ -29,7 +29,7 @@ */ #include -#include "../comedidev.h" +#include #include "das08.h" diff --git a/drivers/comedi/drivers/das08_pci.c b/drivers/comedi/drivers/das08_pci.c index 1cd903336a4c..982f3ab0ccbd 100644 --- a/drivers/comedi/drivers/das08_pci.c +++ b/drivers/comedi/drivers/das08_pci.c @@ -23,8 +23,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "das08.h" diff --git a/drivers/comedi/drivers/das16.c b/drivers/comedi/drivers/das16.c index 4ac2622b0fac..362232ad4409 100644 --- a/drivers/comedi/drivers/das16.c +++ b/drivers/comedi/drivers/das16.c @@ -63,8 +63,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c index 75f3dbbe97ac..cc79e318cb2d 100644 --- a/drivers/comedi/drivers/das16m1.c +++ b/drivers/comedi/drivers/das16m1.c @@ -42,7 +42,7 @@ #include #include #include -#include "../comedidev.h" +#include #include "8255.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das1800.c b/drivers/comedi/drivers/das1800.c index f50891a6ee7d..768803742350 100644 --- a/drivers/comedi/drivers/das1800.c +++ b/drivers/comedi/drivers/das1800.c @@ -73,8 +73,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das6402.c b/drivers/comedi/drivers/das6402.c index 96f4107b8054..d411ab7cf37c 100644 --- a/drivers/comedi/drivers/das6402.c +++ b/drivers/comedi/drivers/das6402.c @@ -24,8 +24,7 @@ #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das800.c b/drivers/comedi/drivers/das800.c index bc08324f422f..c95e0fcb94a4 100644 --- a/drivers/comedi/drivers/das800.c +++ b/drivers/comedi/drivers/das800.c @@ -46,8 +46,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/dmm32at.c b/drivers/comedi/drivers/dmm32at.c index 56682f01242f..0f2bea88b8a7 100644 --- a/drivers/comedi/drivers/dmm32at.c +++ b/drivers/comedi/drivers/dmm32at.c @@ -29,7 +29,7 @@ #include #include #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/dt2801.c b/drivers/comedi/drivers/dt2801.c index 0d571d817b4e..230d25010f58 100644 --- a/drivers/comedi/drivers/dt2801.c +++ b/drivers/comedi/drivers/dt2801.c @@ -31,7 +31,7 @@ */ #include -#include "../comedidev.h" +#include #include #define DT2801_TIMEOUT 1000 diff --git a/drivers/comedi/drivers/dt2811.c b/drivers/comedi/drivers/dt2811.c index 0eb5e6ba6916..dbb9f38da289 100644 --- a/drivers/comedi/drivers/dt2811.c +++ b/drivers/comedi/drivers/dt2811.c @@ -40,8 +40,7 @@ #include #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/dt2814.c b/drivers/comedi/drivers/dt2814.c index ed44ce0d151b..c98a5a4a7aec 100644 --- a/drivers/comedi/drivers/dt2814.c +++ b/drivers/comedi/drivers/dt2814.c @@ -27,8 +27,7 @@ #include #include -#include "../comedidev.h" - +#include #include #define DT2814_CSR 0 diff --git a/drivers/comedi/drivers/dt2815.c b/drivers/comedi/drivers/dt2815.c index 5906f32aa01f..03ba2fd18a21 100644 --- a/drivers/comedi/drivers/dt2815.c +++ b/drivers/comedi/drivers/dt2815.c @@ -43,8 +43,7 @@ */ #include -#include "../comedidev.h" - +#include #include #define DT2815_DATA 0 diff --git a/drivers/comedi/drivers/dt2817.c b/drivers/comedi/drivers/dt2817.c index 7c1463e835d3..6738045c7531 100644 --- a/drivers/comedi/drivers/dt2817.c +++ b/drivers/comedi/drivers/dt2817.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include #define DT2817_CR 0 #define DT2817_DATA 1 diff --git a/drivers/comedi/drivers/dt282x.c b/drivers/comedi/drivers/dt282x.c index 2656b4b0e3d0..078f8fba7183 100644 --- a/drivers/comedi/drivers/dt282x.c +++ b/drivers/comedi/drivers/dt282x.c @@ -51,8 +51,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" diff --git a/drivers/comedi/drivers/dt3000.c b/drivers/comedi/drivers/dt3000.c index ec27aa4730d4..fc6e9c30e522 100644 --- a/drivers/comedi/drivers/dt3000.c +++ b/drivers/comedi/drivers/dt3000.c @@ -43,8 +43,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR0 - dual-ported RAM location definitions (dev->mmio) diff --git a/drivers/comedi/drivers/dt9812.c b/drivers/comedi/drivers/dt9812.c index 704b04d2980d..b37b9d8eca0d 100644 --- a/drivers/comedi/drivers/dt9812.c +++ b/drivers/comedi/drivers/dt9812.c @@ -34,8 +34,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include #define DT9812_DIAGS_BOARD_INFO_ADDR 0xFBFF #define DT9812_MAX_WRITE_CMD_PIPE_SIZE 32 diff --git a/drivers/comedi/drivers/dyna_pci10xx.c b/drivers/comedi/drivers/dyna_pci10xx.c index c224422bb126..407a038fb3e0 100644 --- a/drivers/comedi/drivers/dyna_pci10xx.c +++ b/drivers/comedi/drivers/dyna_pci10xx.c @@ -26,8 +26,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #define READ_TIMEOUT 50 diff --git a/drivers/comedi/drivers/fl512.c b/drivers/comedi/drivers/fl512.c index b715f30659fa..139e801fc358 100644 --- a/drivers/comedi/drivers/fl512.c +++ b/drivers/comedi/drivers/fl512.c @@ -21,8 +21,7 @@ */ #include -#include "../comedidev.h" - +#include #include /* diff --git a/drivers/comedi/drivers/gsc_hpdi.c b/drivers/comedi/drivers/gsc_hpdi.c index e35e4a743714..c09d135df38d 100644 --- a/drivers/comedi/drivers/gsc_hpdi.c +++ b/drivers/comedi/drivers/gsc_hpdi.c @@ -34,8 +34,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "plx9080.h" diff --git a/drivers/comedi/drivers/icp_multi.c b/drivers/comedi/drivers/icp_multi.c index 16d2b78de83c..ac4b11dbd741 100644 --- a/drivers/comedi/drivers/icp_multi.c +++ b/drivers/comedi/drivers/icp_multi.c @@ -36,8 +36,7 @@ #include #include - -#include "../comedi_pci.h" +#include #define ICP_MULTI_ADC_CSR 0x00 /* R/W: ADC command/status register */ #define ICP_MULTI_ADC_CSR_ST BIT(0) /* Start ADC */ diff --git a/drivers/comedi/drivers/ii_pci20kc.c b/drivers/comedi/drivers/ii_pci20kc.c index 399255dbe388..4a19bf8462be 100644 --- a/drivers/comedi/drivers/ii_pci20kc.c +++ b/drivers/comedi/drivers/ii_pci20kc.c @@ -30,7 +30,7 @@ #include #include -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/jr3_pci.c b/drivers/comedi/drivers/jr3_pci.c index f963080dd61f..951c23fa0369 100644 --- a/drivers/comedi/drivers/jr3_pci.c +++ b/drivers/comedi/drivers/jr3_pci.c @@ -35,8 +35,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "jr3_pci.h" diff --git a/drivers/comedi/drivers/ke_counter.c b/drivers/comedi/drivers/ke_counter.c index bef1b20c1c8d..b825cf60e1e0 100644 --- a/drivers/comedi/drivers/ke_counter.c +++ b/drivers/comedi/drivers/ke_counter.c @@ -19,8 +19,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI BAR 0 Register I/O map diff --git a/drivers/comedi/drivers/me4000.c b/drivers/comedi/drivers/me4000.c index 0d3d4cafce2e..c5dc8199771f 100644 --- a/drivers/comedi/drivers/me4000.c +++ b/drivers/comedi/drivers/me4000.c @@ -32,8 +32,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "plx9052.h" diff --git a/drivers/comedi/drivers/me_daq.c b/drivers/comedi/drivers/me_daq.c index ef18e387471b..076b15097afd 100644 --- a/drivers/comedi/drivers/me_daq.c +++ b/drivers/comedi/drivers/me_daq.c @@ -23,8 +23,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "plx9052.h" diff --git a/drivers/comedi/drivers/mf6x4.c b/drivers/comedi/drivers/mf6x4.c index 9da8dd748078..14f1d5e9cd59 100644 --- a/drivers/comedi/drivers/mf6x4.c +++ b/drivers/comedi/drivers/mf6x4.c @@ -18,8 +18,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* Registers present in BAR0 memory region */ #define MF624_GPIOC_REG 0x54 diff --git a/drivers/comedi/drivers/mite.c b/drivers/comedi/drivers/mite.c index 70960e3ba878..88f3cd6f54f1 100644 --- a/drivers/comedi/drivers/mite.c +++ b/drivers/comedi/drivers/mite.c @@ -38,8 +38,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "mite.h" diff --git a/drivers/comedi/drivers/mpc624.c b/drivers/comedi/drivers/mpc624.c index 646f4c086204..9e51ff528ed1 100644 --- a/drivers/comedi/drivers/mpc624.c +++ b/drivers/comedi/drivers/mpc624.c @@ -44,8 +44,7 @@ */ #include -#include "../comedidev.h" - +#include #include /* Offsets of different ports */ diff --git a/drivers/comedi/drivers/multiq3.c b/drivers/comedi/drivers/multiq3.c index c1897aee9a9a..07ff5383da99 100644 --- a/drivers/comedi/drivers/multiq3.c +++ b/drivers/comedi/drivers/multiq3.c @@ -26,8 +26,7 @@ */ #include - -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/ni_6527.c b/drivers/comedi/drivers/ni_6527.c index f1a45cf7342a..ac5820085231 100644 --- a/drivers/comedi/drivers/ni_6527.c +++ b/drivers/comedi/drivers/ni_6527.c @@ -20,8 +20,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR1 - Register memory map diff --git a/drivers/comedi/drivers/ni_65xx.c b/drivers/comedi/drivers/ni_65xx.c index 7cd8497420f2..58334de3b253 100644 --- a/drivers/comedi/drivers/ni_65xx.c +++ b/drivers/comedi/drivers/ni_65xx.c @@ -49,8 +49,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR1 Register Map diff --git a/drivers/comedi/drivers/ni_660x.c b/drivers/comedi/drivers/ni_660x.c index e60d0125bcb2..0679bc39e0bc 100644 --- a/drivers/comedi/drivers/ni_660x.c +++ b/drivers/comedi/drivers/ni_660x.c @@ -26,8 +26,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "mite.h" #include "ni_tio.h" diff --git a/drivers/comedi/drivers/ni_670x.c b/drivers/comedi/drivers/ni_670x.c index c197e47486be..c875d251c230 100644 --- a/drivers/comedi/drivers/ni_670x.c +++ b/drivers/comedi/drivers/ni_670x.c @@ -24,8 +24,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #define AO_VALUE_OFFSET 0x00 #define AO_CHAN_OFFSET 0x0c diff --git a/drivers/comedi/drivers/ni_at_a2150.c b/drivers/comedi/drivers/ni_at_a2150.c index 10ad7b88713e..ce5de58c499f 100644 --- a/drivers/comedi/drivers/ni_at_a2150.c +++ b/drivers/comedi/drivers/ni_at_a2150.c @@ -39,8 +39,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/ni_at_ao.c b/drivers/comedi/drivers/ni_at_ao.c index 2a0fb4d460db..a06dfb9da329 100644 --- a/drivers/comedi/drivers/ni_at_ao.c +++ b/drivers/comedi/drivers/ni_at_ao.c @@ -25,8 +25,7 @@ */ #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/ni_atmio.c b/drivers/comedi/drivers/ni_atmio.c index 56c78da475e7..f60a4e459a98 100644 --- a/drivers/comedi/drivers/ni_atmio.c +++ b/drivers/comedi/drivers/ni_atmio.c @@ -73,8 +73,7 @@ #include #include -#include "../comedidev.h" - +#include #include #include "ni_stc.h" diff --git a/drivers/comedi/drivers/ni_atmio16d.c b/drivers/comedi/drivers/ni_atmio16d.c index dffce1aa3e69..0bd4f88a2ac8 100644 --- a/drivers/comedi/drivers/ni_atmio16d.c +++ b/drivers/comedi/drivers/ni_atmio16d.c @@ -39,7 +39,7 @@ #include #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/ni_daq_700.c b/drivers/comedi/drivers/ni_daq_700.c index d40fc89f9cef..0ef20e9a8bc4 100644 --- a/drivers/comedi/drivers/ni_daq_700.c +++ b/drivers/comedi/drivers/ni_daq_700.c @@ -41,8 +41,7 @@ #include #include #include - -#include "../comedi_pcmcia.h" +#include /* daqcard700 registers */ #define DIO_W 0x04 /* WO 8bit */ diff --git a/drivers/comedi/drivers/ni_daq_dio24.c b/drivers/comedi/drivers/ni_daq_dio24.c index 44fb65afc218..84d78f2ee5ac 100644 --- a/drivers/comedi/drivers/ni_daq_dio24.c +++ b/drivers/comedi/drivers/ni_daq_dio24.c @@ -23,7 +23,7 @@ */ #include -#include "../comedi_pcmcia.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/ni_labpc.c b/drivers/comedi/drivers/ni_labpc.c index 1f4a07bd1d26..b25a8e117072 100644 --- a/drivers/comedi/drivers/ni_labpc.c +++ b/drivers/comedi/drivers/ni_labpc.c @@ -48,8 +48,7 @@ */ #include - -#include "../comedidev.h" +#include #include "ni_labpc.h" #include "ni_labpc_isadma.h" diff --git a/drivers/comedi/drivers/ni_labpc_common.c b/drivers/comedi/drivers/ni_labpc_common.c index dd97946eacaf..7c4687226450 100644 --- a/drivers/comedi/drivers/ni_labpc_common.c +++ b/drivers/comedi/drivers/ni_labpc_common.c @@ -12,8 +12,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/ni_labpc_cs.c b/drivers/comedi/drivers/ni_labpc_cs.c index 4f7e2fe21254..62fecb50ec6e 100644 --- a/drivers/comedi/drivers/ni_labpc_cs.c +++ b/drivers/comedi/drivers/ni_labpc_cs.c @@ -38,8 +38,7 @@ */ #include - -#include "../comedi_pcmcia.h" +#include #include "ni_labpc.h" diff --git a/drivers/comedi/drivers/ni_labpc_isadma.c b/drivers/comedi/drivers/ni_labpc_isadma.c index a551aca6e615..dd37ec0d9b15 100644 --- a/drivers/comedi/drivers/ni_labpc_isadma.c +++ b/drivers/comedi/drivers/ni_labpc_isadma.c @@ -10,8 +10,7 @@ #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "ni_labpc.h" diff --git a/drivers/comedi/drivers/ni_labpc_pci.c b/drivers/comedi/drivers/ni_labpc_pci.c index ec180b0fedf7..e2a44bbd9fa6 100644 --- a/drivers/comedi/drivers/ni_labpc_pci.c +++ b/drivers/comedi/drivers/ni_labpc_pci.c @@ -22,8 +22,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "ni_labpc.h" diff --git a/drivers/comedi/drivers/ni_mio_cs.c b/drivers/comedi/drivers/ni_mio_cs.c index 4f37b4e58f09..bd967cdb2036 100644 --- a/drivers/comedi/drivers/ni_mio_cs.c +++ b/drivers/comedi/drivers/ni_mio_cs.c @@ -28,8 +28,8 @@ #include #include +#include -#include "../comedi_pcmcia.h" #include "ni_stc.h" #include "8255.h" diff --git a/drivers/comedi/drivers/ni_pcidio.c b/drivers/comedi/drivers/ni_pcidio.c index 623f8d08d13a..2d58e83420e8 100644 --- a/drivers/comedi/drivers/ni_pcidio.c +++ b/drivers/comedi/drivers/ni_pcidio.c @@ -42,8 +42,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "mite.h" diff --git a/drivers/comedi/drivers/ni_pcimio.c b/drivers/comedi/drivers/ni_pcimio.c index 6c813a490ba5..0b055321023d 100644 --- a/drivers/comedi/drivers/ni_pcimio.c +++ b/drivers/comedi/drivers/ni_pcimio.c @@ -94,9 +94,7 @@ #include #include - -#include "../comedi_pci.h" - +#include #include #include "ni_stc.h" diff --git a/drivers/comedi/drivers/ni_routes.c b/drivers/comedi/drivers/ni_routes.c index f0f8cd424b30..f24eeb464eba 100644 --- a/drivers/comedi/drivers/ni_routes.c +++ b/drivers/comedi/drivers/ni_routes.c @@ -21,8 +21,7 @@ #include #include #include - -#include "../comedi.h" +#include #include "ni_routes.h" #include "ni_routing/ni_route_values.h" diff --git a/drivers/comedi/drivers/ni_routes.h b/drivers/comedi/drivers/ni_routes.h index 036982315584..cff8a463a03f 100644 --- a/drivers/comedi/drivers/ni_routes.h +++ b/drivers/comedi/drivers/ni_routes.h @@ -27,7 +27,7 @@ #include #endif -#include "../comedi.h" +#include /** * struct ni_route_set - Set of destinations with a common source. diff --git a/drivers/comedi/drivers/ni_routing/ni_route_values.h b/drivers/comedi/drivers/ni_routing/ni_route_values.h index 6e358efa6f7f..80880083ea41 100644 --- a/drivers/comedi/drivers/ni_routing/ni_route_values.h +++ b/drivers/comedi/drivers/ni_routing/ni_route_values.h @@ -20,7 +20,7 @@ #ifndef _COMEDI_DRIVERS_NI_ROUTINT_NI_ROUTE_VALUES_H #define _COMEDI_DRIVERS_NI_ROUTINT_NI_ROUTE_VALUES_H -#include "../../comedi.h" +#include #include /* diff --git a/drivers/comedi/drivers/ni_tio.h b/drivers/comedi/drivers/ni_tio.h index e7b05718df9b..9ae2221c3c18 100644 --- a/drivers/comedi/drivers/ni_tio.h +++ b/drivers/comedi/drivers/ni_tio.h @@ -8,7 +8,7 @@ #ifndef _COMEDI_NI_TIO_H #define _COMEDI_NI_TIO_H -#include "../comedidev.h" +#include enum ni_gpct_register { NITIO_G0_AUTO_INC, diff --git a/drivers/comedi/drivers/ni_usb6501.c b/drivers/comedi/drivers/ni_usb6501.c index c42987b74b1d..0dd9edf7bced 100644 --- a/drivers/comedi/drivers/ni_usb6501.c +++ b/drivers/comedi/drivers/ni_usb6501.c @@ -87,8 +87,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include #define NI6501_TIMEOUT 1000 diff --git a/drivers/comedi/drivers/pcl711.c b/drivers/comedi/drivers/pcl711.c index bd6f42fe9e3c..f1c383bd9d87 100644 --- a/drivers/comedi/drivers/pcl711.c +++ b/drivers/comedi/drivers/pcl711.c @@ -29,8 +29,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcl724.c b/drivers/comedi/drivers/pcl724.c index 1a5799278a7a..b3f472c93e80 100644 --- a/drivers/comedi/drivers/pcl724.c +++ b/drivers/comedi/drivers/pcl724.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/pcl726.c b/drivers/comedi/drivers/pcl726.c index 88f25d7e76f7..0430630e6ebb 100644 --- a/drivers/comedi/drivers/pcl726.c +++ b/drivers/comedi/drivers/pcl726.c @@ -50,8 +50,7 @@ #include #include - -#include "../comedidev.h" +#include #define PCL726_AO_MSB_REG(x) (0x00 + ((x) * 2)) #define PCL726_AO_LSB_REG(x) (0x01 + ((x) * 2)) diff --git a/drivers/comedi/drivers/pcl730.c b/drivers/comedi/drivers/pcl730.c index 32a29129e6e8..d2733cd5383d 100644 --- a/drivers/comedi/drivers/pcl730.c +++ b/drivers/comedi/drivers/pcl730.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c index b87ab3840eee..f00976ddfc2a 100644 --- a/drivers/comedi/drivers/pcl812.c +++ b/drivers/comedi/drivers/pcl812.c @@ -114,8 +114,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcl816.c b/drivers/comedi/drivers/pcl816.c index c368a337a0ae..c5acdc8913f8 100644 --- a/drivers/comedi/drivers/pcl816.c +++ b/drivers/comedi/drivers/pcl816.c @@ -35,8 +35,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcl818.c b/drivers/comedi/drivers/pcl818.c index f4b4a686c710..20fcd6d588f8 100644 --- a/drivers/comedi/drivers/pcl818.c +++ b/drivers/comedi/drivers/pcl818.c @@ -97,8 +97,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcm3724.c b/drivers/comedi/drivers/pcm3724.c index 0cb1ad060402..93ae6cffed44 100644 --- a/drivers/comedi/drivers/pcm3724.c +++ b/drivers/comedi/drivers/pcm3724.c @@ -24,7 +24,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/pcmad.c b/drivers/comedi/drivers/pcmad.c index eec89a0afb2f..976eda43881b 100644 --- a/drivers/comedi/drivers/pcmad.c +++ b/drivers/comedi/drivers/pcmad.c @@ -29,7 +29,7 @@ */ #include -#include "../comedidev.h" +#include #define PCMAD_STATUS 0 #define PCMAD_LSB 1 diff --git a/drivers/comedi/drivers/pcmda12.c b/drivers/comedi/drivers/pcmda12.c index 14ab1f0d1e9f..611f13bedca0 100644 --- a/drivers/comedi/drivers/pcmda12.c +++ b/drivers/comedi/drivers/pcmda12.c @@ -40,7 +40,7 @@ */ #include -#include "../comedidev.h" +#include /* AI range is not configurable, it's set by jumpers on the board */ static const struct comedi_lrange pcmda12_ranges = { diff --git a/drivers/comedi/drivers/pcmmio.c b/drivers/comedi/drivers/pcmmio.c index 24a9568d3378..c2402239d551 100644 --- a/drivers/comedi/drivers/pcmmio.c +++ b/drivers/comedi/drivers/pcmmio.c @@ -66,8 +66,7 @@ #include #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/pcmuio.c b/drivers/comedi/drivers/pcmuio.c index b299d648a0eb..33b24dbbb919 100644 --- a/drivers/comedi/drivers/pcmuio.c +++ b/drivers/comedi/drivers/pcmuio.c @@ -65,8 +65,7 @@ #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/quatech_daqp_cs.c b/drivers/comedi/drivers/quatech_daqp_cs.c index fe4408ebf6b3..2a76c75c513b 100644 --- a/drivers/comedi/drivers/quatech_daqp_cs.c +++ b/drivers/comedi/drivers/quatech_daqp_cs.c @@ -41,8 +41,7 @@ */ #include - -#include "../comedi_pcmcia.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/rtd520.c b/drivers/comedi/drivers/rtd520.c index 2d99a648b054..ee5bca2b1c09 100644 --- a/drivers/comedi/drivers/rtd520.c +++ b/drivers/comedi/drivers/rtd520.c @@ -85,8 +85,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "plx9080.h" diff --git a/drivers/comedi/drivers/rti800.c b/drivers/comedi/drivers/rti800.c index 327fd93b8b12..1b02e47bdb4c 100644 --- a/drivers/comedi/drivers/rti800.c +++ b/drivers/comedi/drivers/rti800.c @@ -42,7 +42,7 @@ #include #include #include -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/rti802.c b/drivers/comedi/drivers/rti802.c index 195e2b1ac4c1..d66762a22258 100644 --- a/drivers/comedi/drivers/rti802.c +++ b/drivers/comedi/drivers/rti802.c @@ -22,7 +22,7 @@ */ #include -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/s526.c b/drivers/comedi/drivers/s526.c index 085cf5b449e5..9245c679a3c4 100644 --- a/drivers/comedi/drivers/s526.c +++ b/drivers/comedi/drivers/s526.c @@ -27,7 +27,7 @@ */ #include -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/s626.c b/drivers/comedi/drivers/s626.c index e7aba937d896..0e5f9a9a7fd3 100644 --- a/drivers/comedi/drivers/s626.c +++ b/drivers/comedi/drivers/s626.c @@ -55,8 +55,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "s626.h" diff --git a/drivers/comedi/drivers/ssv_dnp.c b/drivers/comedi/drivers/ssv_dnp.c index 016d315aa584..813bd0853b0b 100644 --- a/drivers/comedi/drivers/ssv_dnp.c +++ b/drivers/comedi/drivers/ssv_dnp.c @@ -19,7 +19,7 @@ /* include files ----------------------------------------------------------- */ #include -#include "../comedidev.h" +#include /* Some global definitions: the registers of the DNP ----------------------- */ /* */ diff --git a/drivers/comedi/drivers/usbdux.c b/drivers/comedi/drivers/usbdux.c index 0350f303d557..92d514b3c1c3 100644 --- a/drivers/comedi/drivers/usbdux.c +++ b/drivers/comedi/drivers/usbdux.c @@ -73,8 +73,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include /* constants for firmware upload and download */ #define USBDUX_FIRMWARE "usbdux_firmware.bin" diff --git a/drivers/comedi/drivers/usbduxfast.c b/drivers/comedi/drivers/usbduxfast.c index 4af012968cb6..39faae0ecb19 100644 --- a/drivers/comedi/drivers/usbduxfast.c +++ b/drivers/comedi/drivers/usbduxfast.c @@ -40,7 +40,7 @@ #include #include #include -#include "../comedi_usb.h" +#include /* * timeout for the USB-transfer diff --git a/drivers/comedi/drivers/usbduxsigma.c b/drivers/comedi/drivers/usbduxsigma.c index 54d7605e909f..2aaeaf44fbe5 100644 --- a/drivers/comedi/drivers/usbduxsigma.c +++ b/drivers/comedi/drivers/usbduxsigma.c @@ -40,8 +40,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include /* timeout for the USB-transfer in ms*/ #define BULK_TIMEOUT 1000 diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 4b00a9ea611a..46023adc5395 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -35,8 +35,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include enum { DEVICE_VMK8055, diff --git a/drivers/comedi/kcomedilib/kcomedilib_main.c b/drivers/comedi/kcomedilib/kcomedilib_main.c index df9bba1b69ed..43fbe1a63b14 100644 --- a/drivers/comedi/kcomedilib/kcomedilib_main.c +++ b/drivers/comedi/kcomedilib/kcomedilib_main.c @@ -16,9 +16,9 @@ #include #include -#include "../comedi.h" -#include "../comedilib.h" -#include "../comedidev.h" +#include +#include +#include MODULE_AUTHOR("David Schleef "); MODULE_DESCRIPTION("Comedi kernel library"); diff --git a/drivers/comedi/proc.c b/drivers/comedi/proc.c index 8bc8e42beb90..2e4496633d3d 100644 --- a/drivers/comedi/proc.c +++ b/drivers/comedi/proc.c @@ -13,7 +13,7 @@ * was cool. */ -#include "comedidev.h" +#include #include "comedi_internal.h" #include #include diff --git a/drivers/comedi/range.c b/drivers/comedi/range.c index a4e6fe0fb729..8f43cf88d784 100644 --- a/drivers/comedi/range.c +++ b/drivers/comedi/range.c @@ -8,7 +8,7 @@ */ #include -#include "comedidev.h" +#include #include "comedi_internal.h" const struct comedi_lrange range_bipolar10 = { 1, {BIP_RANGE(10)} }; diff --git a/include/linux/comedi/comedi_pci.h b/include/linux/comedi/comedi_pci.h new file mode 100644 index 000000000000..2fb50663e3ed --- /dev/null +++ b/include/linux/comedi/comedi_pci.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pci.h + * header file for Comedi PCI drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDI_PCI_H +#define _COMEDI_PCI_H + +#include +#include + +/* + * PCI Vendor IDs not in + */ +#define PCI_VENDOR_ID_KOLTER 0x1001 +#define PCI_VENDOR_ID_ICP 0x104c +#define PCI_VENDOR_ID_DT 0x1116 +#define PCI_VENDOR_ID_IOTECH 0x1616 +#define PCI_VENDOR_ID_CONTEC 0x1221 +#define PCI_VENDOR_ID_RTD 0x1435 +#define PCI_VENDOR_ID_HUMUSOFT 0x186c + +struct pci_dev *comedi_to_pci_dev(struct comedi_device *dev); + +int comedi_pci_enable(struct comedi_device *dev); +void comedi_pci_disable(struct comedi_device *dev); +void comedi_pci_detach(struct comedi_device *dev); + +int comedi_pci_auto_config(struct pci_dev *pcidev, struct comedi_driver *driver, + unsigned long context); +void comedi_pci_auto_unconfig(struct pci_dev *pcidev); + +int comedi_pci_driver_register(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); +void comedi_pci_driver_unregister(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); + +/** + * module_comedi_pci_driver() - Helper macro for registering a comedi PCI driver + * @__comedi_driver: comedi_driver struct + * @__pci_driver: pci_driver struct + * + * Helper macro for comedi PCI drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pci_driver(__comedi_driver, __pci_driver) \ + module_driver(__comedi_driver, comedi_pci_driver_register, \ + comedi_pci_driver_unregister, &(__pci_driver)) + +#endif /* _COMEDI_PCI_H */ diff --git a/include/linux/comedi/comedi_pcmcia.h b/include/linux/comedi/comedi_pcmcia.h new file mode 100644 index 000000000000..a33dfb65b869 --- /dev/null +++ b/include/linux/comedi/comedi_pcmcia.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pcmcia.h + * header file for Comedi PCMCIA drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDI_PCMCIA_H +#define _COMEDI_PCMCIA_H + +#include +#include +#include + +struct pcmcia_device *comedi_to_pcmcia_dev(struct comedi_device *dev); + +int comedi_pcmcia_enable(struct comedi_device *dev, + int (*conf_check)(struct pcmcia_device *p_dev, + void *priv_data)); +void comedi_pcmcia_disable(struct comedi_device *dev); + +int comedi_pcmcia_auto_config(struct pcmcia_device *link, + struct comedi_driver *driver); +void comedi_pcmcia_auto_unconfig(struct pcmcia_device *link); + +int comedi_pcmcia_driver_register(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); +void comedi_pcmcia_driver_unregister(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); + +/** + * module_comedi_pcmcia_driver() - Helper macro for registering a comedi + * PCMCIA driver + * @__comedi_driver: comedi_driver struct + * @__pcmcia_driver: pcmcia_driver struct + * + * Helper macro for comedi PCMCIA drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pcmcia_driver(__comedi_driver, __pcmcia_driver) \ + module_driver(__comedi_driver, comedi_pcmcia_driver_register, \ + comedi_pcmcia_driver_unregister, &(__pcmcia_driver)) + +#endif /* _COMEDI_PCMCIA_H */ diff --git a/include/linux/comedi/comedi_usb.h b/include/linux/comedi/comedi_usb.h new file mode 100644 index 000000000000..5d17dd425bd2 --- /dev/null +++ b/include/linux/comedi/comedi_usb.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* comedi_usb.h + * header file for USB Comedi drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDI_USB_H +#define _COMEDI_USB_H + +#include +#include + +struct usb_interface *comedi_to_usb_interface(struct comedi_device *dev); +struct usb_device *comedi_to_usb_dev(struct comedi_device *dev); + +int comedi_usb_auto_config(struct usb_interface *intf, + struct comedi_driver *driver, unsigned long context); +void comedi_usb_auto_unconfig(struct usb_interface *intf); + +int comedi_usb_driver_register(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); +void comedi_usb_driver_unregister(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); + +/** + * module_comedi_usb_driver() - Helper macro for registering a comedi USB driver + * @__comedi_driver: comedi_driver struct + * @__usb_driver: usb_driver struct + * + * Helper macro for comedi USB drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_usb_driver(__comedi_driver, __usb_driver) \ + module_driver(__comedi_driver, comedi_usb_driver_register, \ + comedi_usb_driver_unregister, &(__usb_driver)) + +#endif /* _COMEDI_USB_H */ diff --git a/include/linux/comedi/comedidev.h b/include/linux/comedi/comedidev.h new file mode 100644 index 000000000000..0a1150900ef3 --- /dev/null +++ b/include/linux/comedi/comedidev.h @@ -0,0 +1,1053 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedidev.h + * header file for kernel-only structures, variables, and constants + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDIDEV_H +#define _COMEDIDEV_H + +#include +#include +#include +#include +#include +#include + +#define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) +#define COMEDI_VERSION_CODE COMEDI_VERSION(COMEDI_MAJORVERSION, \ + COMEDI_MINORVERSION, COMEDI_MICROVERSION) +#define COMEDI_RELEASE VERSION + +#define COMEDI_NUM_BOARD_MINORS 0x30 + +/** + * struct comedi_subdevice - Working data for a COMEDI subdevice + * @device: COMEDI device to which this subdevice belongs. (Initialized by + * comedi_alloc_subdevices().) + * @index: Index of this subdevice within device's array of subdevices. + * (Initialized by comedi_alloc_subdevices().) + * @type: Type of subdevice from &enum comedi_subdevice_type. (Initialized by + * the low-level driver.) + * @n_chan: Number of channels the subdevice supports. (Initialized by the + * low-level driver.) + * @subdev_flags: Various "SDF" flags indicating aspects of the subdevice to + * the COMEDI core and user application. (Initialized by the low-level + * driver.) + * @len_chanlist: Maximum length of a channel list if the subdevice supports + * asynchronous acquisition commands. (Optionally initialized by the + * low-level driver, or changed from 0 to 1 during post-configuration.) + * @private: Private data pointer which is either set by the low-level driver + * itself, or by a call to comedi_alloc_spriv() which allocates storage. + * In the latter case, the storage is automatically freed after the + * low-level driver's "detach" handler is called for the device. + * (Initialized by the low-level driver.) + * @async: Pointer to &struct comedi_async id the subdevice supports + * asynchronous acquisition commands. (Allocated and initialized during + * post-configuration if needed.) + * @lock: Pointer to a file object that performed a %COMEDI_LOCK ioctl on the + * subdevice. (Initially NULL.) + * @busy: Pointer to a file object that is performing an asynchronous + * acquisition command on the subdevice. (Initially NULL.) + * @runflags: Internal flags for use by COMEDI core, mostly indicating whether + * an asynchronous acquisition command is running. + * @spin_lock: Generic spin-lock for use by the COMEDI core and the low-level + * driver. (Initialized by comedi_alloc_subdevices().) + * @io_bits: Bit-mask indicating the channel directions for a DIO subdevice + * with no more than 32 channels. A '1' at a bit position indicates the + * corresponding channel is configured as an output. (Initialized by the + * low-level driver for a DIO subdevice. Forced to all-outputs during + * post-configuration for a digital output subdevice.) + * @maxdata: If non-zero, this is the maximum raw data value of each channel. + * If zero, the maximum data value is channel-specific. (Initialized by + * the low-level driver.) + * @maxdata_list: If the maximum data value is channel-specific, this points + * to an array of maximum data values indexed by channel index. + * (Initialized by the low-level driver.) + * @range_table: If non-NULL, this points to a COMEDI range table for the + * subdevice. If NULL, the range table is channel-specific. (Initialized + * by the low-level driver, will be set to an "invalid" range table during + * post-configuration if @range_table and @range_table_list are both + * NULL.) + * @range_table_list: If the COMEDI range table is channel-specific, this + * points to an array of pointers to COMEDI range tables indexed by + * channel number. (Initialized by the low-level driver.) + * @chanlist: Not used. + * @insn_read: Optional pointer to a handler for the %INSN_READ instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_write: Optional pointer to a handler for the %INSN_WRITE instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_bits: Optional pointer to a handler for the %INSN_BITS instruction + * for a digital input, digital output or digital input/output subdevice. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_config: Optional pointer to a handler for the %INSN_CONFIG + * instruction. (Initialized by the low-level driver, or set to a default + * handler during post-configuration.) + * @do_cmd: If the subdevice supports asynchronous acquisition commands, this + * points to a handler to set it up in hardware. (Initialized by the + * low-level driver.) + * @do_cmdtest: If the subdevice supports asynchronous acquisition commands, + * this points to a handler used to check and possibly tweak a prospective + * acquisition command without setting it up in hardware. (Initialized by + * the low-level driver.) + * @poll: If the subdevice supports asynchronous acquisition commands, this + * is an optional pointer to a handler for the %COMEDI_POLL ioctl which + * instructs the low-level driver to synchronize buffers. (Initialized by + * the low-level driver if needed.) + * @cancel: If the subdevice supports asynchronous acquisition commands, this + * points to a handler used to terminate a running command. (Initialized + * by the low-level driver.) + * @buf_change: If the subdevice supports asynchronous acquisition commands, + * this is an optional pointer to a handler that is called when the data + * buffer for handling asynchronous commands is allocated or reallocated. + * (Initialized by the low-level driver if needed.) + * @munge: If the subdevice supports asynchronous acquisition commands and + * uses DMA to transfer data from the hardware to the acquisition buffer, + * this points to a function used to "munge" the data values from the + * hardware into the format expected by COMEDI. (Initialized by the + * low-level driver if needed.) + * @async_dma_dir: If the subdevice supports asynchronous acquisition commands + * and uses DMA to transfer data from the hardware to the acquisition + * buffer, this sets the DMA direction for the buffer. (initialized to + * %DMA_NONE by comedi_alloc_subdevices() and changed by the low-level + * driver if necessary.) + * @state: Handy bit-mask indicating the output states for a DIO or digital + * output subdevice with no more than 32 channels. (Initialized by the + * low-level driver.) + * @class_dev: If the subdevice supports asynchronous acquisition commands, + * this points to a sysfs comediX_subdY device where X is the minor device + * number of the COMEDI device and Y is the subdevice number. The minor + * device number for the sysfs device is allocated dynamically in the + * range 48 to 255. This is used to allow the COMEDI device to be opened + * with a different default read or write subdevice. (Allocated during + * post-configuration if needed.) + * @minor: If @class_dev is set, this is its dynamically allocated minor + * device number. (Set during post-configuration if necessary.) + * @readback: Optional pointer to memory allocated by + * comedi_alloc_subdev_readback() used to hold the values written to + * analog output channels so they can be read back. The storage is + * automatically freed after the low-level driver's "detach" handler is + * called for the device. (Initialized by the low-level driver.) + * + * This is the main control structure for a COMEDI subdevice. If the subdevice + * supports asynchronous acquisition commands, additional information is stored + * in the &struct comedi_async pointed to by @async. + * + * Most of the subdevice is initialized by the low-level driver's "attach" or + * "auto_attach" handlers but parts of it are initialized by + * comedi_alloc_subdevices(), and other parts are initialized during + * post-configuration on return from that handler. + * + * A low-level driver that sets @insn_bits for a digital input, digital output, + * or DIO subdevice may leave @insn_read and @insn_write uninitialized, in + * which case they will be set to a default handler during post-configuration + * that uses @insn_bits to emulate the %INSN_READ and %INSN_WRITE instructions. + */ +struct comedi_subdevice { + struct comedi_device *device; + int index; + int type; + int n_chan; + int subdev_flags; + int len_chanlist; /* maximum length of channel/gain list */ + + void *private; + + struct comedi_async *async; + + void *lock; + void *busy; + unsigned int runflags; + spinlock_t spin_lock; /* generic spin-lock for COMEDI and drivers */ + + unsigned int io_bits; + + unsigned int maxdata; /* if maxdata==0, use list */ + const unsigned int *maxdata_list; /* list is channel specific */ + + const struct comedi_lrange *range_table; + const struct comedi_lrange *const *range_table_list; + + unsigned int *chanlist; /* driver-owned chanlist (not used) */ + + int (*insn_read)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_write)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_bits)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, + unsigned int *data); + + int (*do_cmd)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*do_cmdtest)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_cmd *cmd); + int (*poll)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*cancel)(struct comedi_device *dev, struct comedi_subdevice *s); + + /* called when the buffer changes */ + int (*buf_change)(struct comedi_device *dev, + struct comedi_subdevice *s); + + void (*munge)(struct comedi_device *dev, struct comedi_subdevice *s, + void *data, unsigned int num_bytes, + unsigned int start_chan_index); + enum dma_data_direction async_dma_dir; + + unsigned int state; + + struct device *class_dev; + int minor; + + unsigned int *readback; +}; + +/** + * struct comedi_buf_page - Describe a page of a COMEDI buffer + * @virt_addr: Kernel address of page. + * @dma_addr: DMA address of page if in DMA coherent memory. + */ +struct comedi_buf_page { + void *virt_addr; + dma_addr_t dma_addr; +}; + +/** + * struct comedi_buf_map - Describe pages in a COMEDI buffer + * @dma_hw_dev: Low-level hardware &struct device pointer copied from the + * COMEDI device's hw_dev member. + * @page_list: Pointer to array of &struct comedi_buf_page, one for each + * page in the buffer. + * @n_pages: Number of pages in the buffer. + * @dma_dir: DMA direction used to allocate pages of DMA coherent memory, + * or %DMA_NONE if pages allocated from regular memory. + * @refcount: &struct kref reference counter used to free the buffer. + * + * A COMEDI data buffer is allocated as individual pages, either in + * conventional memory or DMA coherent memory, depending on the attached, + * low-level hardware device. (The buffer pages also get mapped into the + * kernel's contiguous virtual address space pointed to by the 'prealloc_buf' + * member of &struct comedi_async.) + * + * The buffer is normally freed when the COMEDI device is detached from the + * low-level driver (which may happen due to device removal), but if it happens + * to be mmapped at the time, the pages cannot be freed until the buffer has + * been munmapped. That is what the reference counter is for. (The virtual + * address space pointed by 'prealloc_buf' is freed when the COMEDI device is + * detached.) + */ +struct comedi_buf_map { + struct device *dma_hw_dev; + struct comedi_buf_page *page_list; + unsigned int n_pages; + enum dma_data_direction dma_dir; + struct kref refcount; +}; + +/** + * struct comedi_async - Control data for asynchronous COMEDI commands + * @prealloc_buf: Kernel virtual address of allocated acquisition buffer. + * @prealloc_bufsz: Buffer size (in bytes). + * @buf_map: Map of buffer pages. + * @max_bufsize: Maximum allowed buffer size (in bytes). + * @buf_write_count: "Write completed" count (in bytes, modulo 2**32). + * @buf_write_alloc_count: "Allocated for writing" count (in bytes, + * modulo 2**32). + * @buf_read_count: "Read completed" count (in bytes, modulo 2**32). + * @buf_read_alloc_count: "Allocated for reading" count (in bytes, + * modulo 2**32). + * @buf_write_ptr: Buffer position for writer. + * @buf_read_ptr: Buffer position for reader. + * @cur_chan: Current position in chanlist for scan (for those drivers that + * use it). + * @scans_done: The number of scans completed. + * @scan_progress: Amount received or sent for current scan (in bytes). + * @munge_chan: Current position in chanlist for "munging". + * @munge_count: "Munge" count (in bytes, modulo 2**32). + * @munge_ptr: Buffer position for "munging". + * @events: Bit-vector of events that have occurred. + * @cmd: Details of comedi command in progress. + * @wait_head: Task wait queue for file reader or writer. + * @cb_mask: Bit-vector of events that should wake waiting tasks. + * @inttrig: Software trigger function for command, or NULL. + * + * Note about the ..._count and ..._ptr members: + * + * Think of the _Count values being integers of unlimited size, indexing + * into a buffer of infinite length (though only an advancing portion + * of the buffer of fixed length prealloc_bufsz is accessible at any + * time). Then: + * + * Buf_Read_Count <= Buf_Read_Alloc_Count <= Munge_Count <= + * Buf_Write_Count <= Buf_Write_Alloc_Count <= + * (Buf_Read_Count + prealloc_bufsz) + * + * (Those aren't the actual members, apart from prealloc_bufsz.) When the + * buffer is reset, those _Count values start at 0 and only increase in value, + * maintaining the above inequalities until the next time the buffer is + * reset. The buffer is divided into the following regions by the inequalities: + * + * [0, Buf_Read_Count): + * old region no longer accessible + * + * [Buf_Read_Count, Buf_Read_Alloc_Count): + * filled and munged region allocated for reading but not yet read + * + * [Buf_Read_Alloc_Count, Munge_Count): + * filled and munged region not yet allocated for reading + * + * [Munge_Count, Buf_Write_Count): + * filled region not yet munged + * + * [Buf_Write_Count, Buf_Write_Alloc_Count): + * unfilled region allocated for writing but not yet written + * + * [Buf_Write_Alloc_Count, Buf_Read_Count + prealloc_bufsz): + * unfilled region not yet allocated for writing + * + * [Buf_Read_Count + prealloc_bufsz, infinity): + * unfilled region not yet accessible + * + * Data needs to be written into the buffer before it can be read out, + * and may need to be converted (or "munged") between the two + * operations. Extra unfilled buffer space may need to allocated for + * writing (advancing Buf_Write_Alloc_Count) before new data is written. + * After writing new data, the newly filled space needs to be released + * (advancing Buf_Write_Count). This also results in the new data being + * "munged" (advancing Munge_Count). Before data is read out of the + * buffer, extra space may need to be allocated for reading (advancing + * Buf_Read_Alloc_Count). After the data has been read out, the space + * needs to be released (advancing Buf_Read_Count). + * + * The actual members, buf_read_count, buf_read_alloc_count, + * munge_count, buf_write_count, and buf_write_alloc_count take the + * value of the corresponding capitalized _Count values modulo 2^32 + * (UINT_MAX+1). Subtracting a "higher" _count value from a "lower" + * _count value gives the same answer as subtracting a "higher" _Count + * value from a lower _Count value because prealloc_bufsz < UINT_MAX+1. + * The modulo operation is done implicitly. + * + * The buf_read_ptr, munge_ptr, and buf_write_ptr members take the value + * of the corresponding capitalized _Count values modulo prealloc_bufsz. + * These correspond to byte indices in the physical buffer. The modulo + * operation is done by subtracting prealloc_bufsz when the value + * exceeds prealloc_bufsz (assuming prealloc_bufsz plus the increment is + * less than or equal to UINT_MAX). + */ +struct comedi_async { + void *prealloc_buf; + unsigned int prealloc_bufsz; + struct comedi_buf_map *buf_map; + unsigned int max_bufsize; + unsigned int buf_write_count; + unsigned int buf_write_alloc_count; + unsigned int buf_read_count; + unsigned int buf_read_alloc_count; + unsigned int buf_write_ptr; + unsigned int buf_read_ptr; + unsigned int cur_chan; + unsigned int scans_done; + unsigned int scan_progress; + unsigned int munge_chan; + unsigned int munge_count; + unsigned int munge_ptr; + unsigned int events; + struct comedi_cmd cmd; + wait_queue_head_t wait_head; + unsigned int cb_mask; + int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s, + unsigned int x); +}; + +/** + * enum comedi_cb - &struct comedi_async callback "events" + * @COMEDI_CB_EOS: end-of-scan + * @COMEDI_CB_EOA: end-of-acquisition/output + * @COMEDI_CB_BLOCK: data has arrived, wakes up read() / write() + * @COMEDI_CB_EOBUF: DEPRECATED: end of buffer + * @COMEDI_CB_ERROR: card error during acquisition + * @COMEDI_CB_OVERFLOW: buffer overflow/underflow + * @COMEDI_CB_ERROR_MASK: events that indicate an error has occurred + * @COMEDI_CB_CANCEL_MASK: events that will cancel an async command + */ +enum comedi_cb { + COMEDI_CB_EOS = BIT(0), + COMEDI_CB_EOA = BIT(1), + COMEDI_CB_BLOCK = BIT(2), + COMEDI_CB_EOBUF = BIT(3), + COMEDI_CB_ERROR = BIT(4), + COMEDI_CB_OVERFLOW = BIT(5), + /* masks */ + COMEDI_CB_ERROR_MASK = (COMEDI_CB_ERROR | COMEDI_CB_OVERFLOW), + COMEDI_CB_CANCEL_MASK = (COMEDI_CB_EOA | COMEDI_CB_ERROR_MASK) +}; + +/** + * struct comedi_driver - COMEDI driver registration + * @driver_name: Name of driver. + * @module: Owning module. + * @attach: The optional "attach" handler for manually configured COMEDI + * devices. + * @detach: The "detach" handler for deconfiguring COMEDI devices. + * @auto_attach: The optional "auto_attach" handler for automatically + * configured COMEDI devices. + * @num_names: Optional number of "board names" supported. + * @board_name: Optional pointer to a pointer to a board name. The pointer + * to a board name is embedded in an element of a driver-defined array + * of static, read-only board type information. + * @offset: Optional size of each element of the driver-defined array of + * static, read-only board type information, i.e. the offset between each + * pointer to a board name. + * + * This is used with comedi_driver_register() and comedi_driver_unregister() to + * register and unregister a low-level COMEDI driver with the COMEDI core. + * + * If @num_names is non-zero, @board_name should be non-NULL, and @offset + * should be at least sizeof(*board_name). These are used by the handler for + * the %COMEDI_DEVCONFIG ioctl to match a hardware device and its driver by + * board name. If @num_names is zero, the %COMEDI_DEVCONFIG ioctl matches a + * hardware device and its driver by driver name. This is only useful if the + * @attach handler is set. If @num_names is non-zero, the driver's @attach + * handler will be called with the COMEDI device structure's board_ptr member + * pointing to the matched pointer to a board name within the driver's private + * array of static, read-only board type information. + * + * The @detach handler has two roles. If a COMEDI device was successfully + * configured by the @attach or @auto_attach handler, it is called when the + * device is being deconfigured (by the %COMEDI_DEVCONFIG ioctl, or due to + * unloading of the driver, or due to device removal). It is also called when + * the @attach or @auto_attach handler returns an error. Therefore, the + * @attach or @auto_attach handlers can defer clean-up on error until the + * @detach handler is called. If the @attach or @auto_attach handlers free + * any resources themselves, they must prevent the @detach handler from + * freeing the same resources. The @detach handler must not assume that all + * resources requested by the @attach or @auto_attach handler were + * successfully allocated. + */ +struct comedi_driver { + /* private: */ + struct comedi_driver *next; /* Next in list of COMEDI drivers. */ + /* public: */ + const char *driver_name; + struct module *module; + int (*attach)(struct comedi_device *dev, struct comedi_devconfig *it); + void (*detach)(struct comedi_device *dev); + int (*auto_attach)(struct comedi_device *dev, unsigned long context); + unsigned int num_names; + const char *const *board_name; + int offset; +}; + +/** + * struct comedi_device - Working data for a COMEDI device + * @use_count: Number of open file objects. + * @driver: Low-level COMEDI driver attached to this COMEDI device. + * @pacer: Optional pointer to a dynamically allocated acquisition pacer + * control. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @private: Optional pointer to private data allocated by the low-level + * driver. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @class_dev: Sysfs comediX device. + * @minor: Minor device number of COMEDI char device (0-47). + * @detach_count: Counter incremented every time the COMEDI device is detached. + * Used for checking a previous attachment is still valid. + * @hw_dev: Optional pointer to the low-level hardware &struct device. It is + * required for automatically configured COMEDI devices and optional for + * COMEDI devices configured by the %COMEDI_DEVCONFIG ioctl, although + * the bus-specific COMEDI functions only work if it is set correctly. + * It is also passed to dma_alloc_coherent() for COMEDI subdevices that + * have their 'async_dma_dir' member set to something other than + * %DMA_NONE. + * @board_name: Pointer to a COMEDI board name or a COMEDI driver name. When + * the low-level driver's "attach" handler is called by the handler for + * the %COMEDI_DEVCONFIG ioctl, it either points to a matched board name + * string if the 'num_names' member of the &struct comedi_driver is + * non-zero, otherwise it points to the low-level driver name string. + * When the low-lever driver's "auto_attach" handler is called for an + * automatically configured COMEDI device, it points to the low-level + * driver name string. The low-level driver is free to change it in its + * "attach" or "auto_attach" handler if it wishes. + * @board_ptr: Optional pointer to private, read-only board type information in + * the low-level driver. If the 'num_names' member of the &struct + * comedi_driver is non-zero, the handler for the %COMEDI_DEVCONFIG ioctl + * will point it to a pointer to a matched board name string within the + * driver's private array of static, read-only board type information when + * calling the driver's "attach" handler. The low-level driver is free to + * change it. + * @attached: Flag indicating that the COMEDI device is attached to a low-level + * driver. + * @ioenabled: Flag used to indicate that a PCI device has been enabled and + * its regions requested. + * @spinlock: Generic spin-lock for use by the low-level driver. + * @mutex: Generic mutex for use by the COMEDI core module. + * @attach_lock: &struct rw_semaphore used to guard against the COMEDI device + * being detached while an operation is in progress. The down_write() + * operation is only allowed while @mutex is held and is used when + * changing @attached and @detach_count and calling the low-level driver's + * "detach" handler. The down_read() operation is generally used without + * holding @mutex. + * @refcount: &struct kref reference counter for freeing COMEDI device. + * @n_subdevices: Number of COMEDI subdevices allocated by the low-level + * driver for this device. + * @subdevices: Dynamically allocated array of COMEDI subdevices. + * @mmio: Optional pointer to a remapped MMIO region set by the low-level + * driver. + * @iobase: Optional base of an I/O port region requested by the low-level + * driver. + * @iolen: Length of I/O port region requested at @iobase. + * @irq: Optional IRQ number requested by the low-level driver. + * @read_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the read() file operation. Set by the low-level driver. + * @write_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the write() file operation. Set by the low-level driver. + * @async_queue: Storage for fasync_helper(). + * @open: Optional pointer to a function set by the low-level driver to be + * called when @use_count changes from 0 to 1. + * @close: Optional pointer to a function set by the low-level driver to be + * called when @use_count changed from 1 to 0. + * @insn_device_config: Optional pointer to a handler for all sub-instructions + * except %INSN_DEVICE_CONFIG_GET_ROUTES of the %INSN_DEVICE_CONFIG + * instruction. If this is not initialized by the low-level driver, a + * default handler will be set during post-configuration. + * @get_valid_routes: Optional pointer to a handler for the + * %INSN_DEVICE_CONFIG_GET_ROUTES sub-instruction of the + * %INSN_DEVICE_CONFIG instruction set. If this is not initialized by the + * low-level driver, a default handler that copies zero routes back to the + * user will be used. + * + * This is the main control data structure for a COMEDI device (as far as the + * COMEDI core is concerned). There are two groups of COMEDI devices - + * "legacy" devices that are configured by the handler for the + * %COMEDI_DEVCONFIG ioctl, and automatically configured devices resulting + * from a call to comedi_auto_config() as a result of a bus driver probe in + * a low-level COMEDI driver. The "legacy" COMEDI devices are allocated + * during module initialization if the "comedi_num_legacy_minors" module + * parameter is non-zero and use minor device numbers from 0 to + * comedi_num_legacy_minors minus one. The automatically configured COMEDI + * devices are allocated on demand and use minor device numbers from + * comedi_num_legacy_minors to 47. + */ +struct comedi_device { + int use_count; + struct comedi_driver *driver; + struct comedi_8254 *pacer; + void *private; + + struct device *class_dev; + int minor; + unsigned int detach_count; + struct device *hw_dev; + + const char *board_name; + const void *board_ptr; + unsigned int attached:1; + unsigned int ioenabled:1; + spinlock_t spinlock; /* generic spin-lock for low-level driver */ + struct mutex mutex; /* generic mutex for COMEDI core */ + struct rw_semaphore attach_lock; + struct kref refcount; + + int n_subdevices; + struct comedi_subdevice *subdevices; + + /* dumb */ + void __iomem *mmio; + unsigned long iobase; + unsigned long iolen; + unsigned int irq; + + struct comedi_subdevice *read_subdev; + struct comedi_subdevice *write_subdev; + + struct fasync_struct *async_queue; + + int (*open)(struct comedi_device *dev); + void (*close)(struct comedi_device *dev); + int (*insn_device_config)(struct comedi_device *dev, + struct comedi_insn *insn, unsigned int *data); + unsigned int (*get_valid_routes)(struct comedi_device *dev, + unsigned int n_pairs, + unsigned int *pair_data); +}; + +/* + * function prototypes + */ + +void comedi_event(struct comedi_device *dev, struct comedi_subdevice *s); + +struct comedi_device *comedi_dev_get_from_minor(unsigned int minor); +int comedi_dev_put(struct comedi_device *dev); + +bool comedi_is_subdevice_running(struct comedi_subdevice *s); + +void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size); +void comedi_set_spriv_auto_free(struct comedi_subdevice *s); + +int comedi_check_chanlist(struct comedi_subdevice *s, + int n, + unsigned int *chanlist); + +/* range stuff */ + +#define RANGE(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define RANGE_ext(a, b) {(a) * 1e6, (b) * 1e6, RF_EXTERNAL} +#define RANGE_mA(a, b) {(a) * 1e6, (b) * 1e6, UNIT_mA} +#define RANGE_unitless(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define BIP_RANGE(a) {-(a) * 1e6, (a) * 1e6, 0} +#define UNI_RANGE(a) {0, (a) * 1e6, 0} + +extern const struct comedi_lrange range_bipolar10; +extern const struct comedi_lrange range_bipolar5; +extern const struct comedi_lrange range_bipolar2_5; +extern const struct comedi_lrange range_unipolar10; +extern const struct comedi_lrange range_unipolar5; +extern const struct comedi_lrange range_unipolar2_5; +extern const struct comedi_lrange range_0_20mA; +extern const struct comedi_lrange range_4_20mA; +extern const struct comedi_lrange range_0_32mA; +extern const struct comedi_lrange range_unknown; + +#define range_digital range_unipolar5 + +/** + * struct comedi_lrange - Describes a COMEDI range table + * @length: Number of entries in the range table. + * @range: Array of &struct comedi_krange, one for each range. + * + * Each element of @range[] describes the minimum and maximum physical range + * and the type of units. Typically, the type of unit is %UNIT_volt + * (i.e. volts) and the minimum and maximum are in millionths of a volt. + * There may also be a flag that indicates the minimum and maximum are merely + * scale factors for an unknown, external reference. + */ +struct comedi_lrange { + int length; + struct comedi_krange range[]; +}; + +/** + * comedi_range_is_bipolar() - Test if subdevice range is bipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_range_is_bipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min < 0; +} + +/** + * comedi_range_is_unipolar() - Test if subdevice range is unipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_range_is_unipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min >= 0; +} + +/** + * comedi_range_is_external() - Test if subdevice range is external + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is external. + * %false if the range is internal. + */ +static inline bool comedi_range_is_external(struct comedi_subdevice *s, + unsigned int range) +{ + return !!(s->range_table->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_chan_range_is_bipolar() - Test if channel-specific range is bipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_bipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min < 0; +} + +/** + * comedi_chan_range_is_unipolar() - Test if channel-specific range is unipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_chan_range_is_unipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min >= 0; +} + +/** + * comedi_chan_range_is_external() - Test if channel-specific range is external + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_external(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return !!(s->range_table_list[chan]->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_offset_munge() - Convert between offset binary and 2's complement + * @s: COMEDI subdevice. + * @val: Value to be converted. + * + * Toggles the highest bit of a sample value to toggle between offset binary + * and 2's complement. Assumes that @s->maxdata is a power of 2 minus 1. + * + * Return: The converted value. + */ +static inline unsigned int comedi_offset_munge(struct comedi_subdevice *s, + unsigned int val) +{ + return val ^ s->maxdata ^ (s->maxdata >> 1); +} + +/** + * comedi_bytes_per_sample() - Determine subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. + * + * Return: The subdevice sample size. + */ +static inline unsigned int comedi_bytes_per_sample(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? sizeof(int) : sizeof(short); +} + +/** + * comedi_sample_shift() - Determine log2 of subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. The log2 of the + * sample size will be 2 or 1 and can be used as the right operand of a + * bit-shift operator to multiply or divide something by the sample size. + * + * Return: log2 of the subdevice sample size. + */ +static inline unsigned int comedi_sample_shift(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? 2 : 1; +} + +/** + * comedi_bytes_to_samples() - Convert a number of bytes to a number of samples + * @s: COMEDI subdevice. + * @nbytes: Number of bytes + * + * Return: The number of bytes divided by the subdevice sample size. + */ +static inline unsigned int comedi_bytes_to_samples(struct comedi_subdevice *s, + unsigned int nbytes) +{ + return nbytes >> comedi_sample_shift(s); +} + +/** + * comedi_samples_to_bytes() - Convert a number of samples to a number of bytes + * @s: COMEDI subdevice. + * @nsamples: Number of samples. + * + * Return: The number of samples multiplied by the subdevice sample size. + * (Does not check for arithmetic overflow.) + */ +static inline unsigned int comedi_samples_to_bytes(struct comedi_subdevice *s, + unsigned int nsamples) +{ + return nsamples << comedi_sample_shift(s); +} + +/** + * comedi_check_trigger_src() - Trivially validate a comedi_cmd trigger source + * @src: Pointer to the trigger source to validate. + * @flags: Bitmask of valid %TRIG_* for the trigger. + * + * This is used in "step 1" of the do_cmdtest functions of comedi drivers + * to validate the comedi_cmd triggers. The mask of the @src against the + * @flags allows the userspace comedilib to pass all the comedi_cmd + * triggers as %TRIG_ANY and get back a bitmask of the valid trigger sources. + * + * Return: + * 0 if trigger sources in *@src are all supported. + * -EINVAL if any trigger source in *@src is unsupported. + */ +static inline int comedi_check_trigger_src(unsigned int *src, + unsigned int flags) +{ + unsigned int orig_src = *src; + + *src = orig_src & flags; + if (*src == TRIG_INVALID || *src != orig_src) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_is_unique() - Make sure a trigger source is unique + * @src: The trigger source to check. + * + * Return: + * 0 if no more than one trigger source is set. + * -EINVAL if more than one trigger source is set. + */ +static inline int comedi_check_trigger_is_unique(unsigned int src) +{ + /* this test is true if more than one _src bit is set */ + if ((src & (src - 1)) != 0) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_arg_is() - Trivially validate a trigger argument + * @arg: Pointer to the trigger arg to validate. + * @val: The value the argument should be. + * + * Forces *@arg to be @val. + * + * Return: + * 0 if *@arg was already @val. + * -EINVAL if *@arg differed from @val. + */ +static inline int comedi_check_trigger_arg_is(unsigned int *arg, + unsigned int val) +{ + if (*arg != val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_min() - Trivially validate a trigger argument min + * @arg: Pointer to the trigger arg to validate. + * @val: The minimum value the argument should be. + * + * Forces *@arg to be at least @val, setting it to @val if necessary. + * + * Return: + * 0 if *@arg was already at least @val. + * -EINVAL if *@arg was less than @val. + */ +static inline int comedi_check_trigger_arg_min(unsigned int *arg, + unsigned int val) +{ + if (*arg < val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_max() - Trivially validate a trigger argument max + * @arg: Pointer to the trigger arg to validate. + * @val: The maximum value the argument should be. + * + * Forces *@arg to be no more than @val, setting it to @val if necessary. + * + * Return: + * 0 if*@arg was already no more than @val. + * -EINVAL if *@arg was greater than @val. + */ +static inline int comedi_check_trigger_arg_max(unsigned int *arg, + unsigned int val) +{ + if (*arg > val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/* + * Must set dev->hw_dev if you wish to dma directly into comedi's buffer. + * Also useful for retrieving a previously configured hardware device of + * known bus type. Set automatically for auto-configured devices. + * Automatically set to NULL when detaching hardware device. + */ +int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev); + +/** + * comedi_buf_n_bytes_ready - Determine amount of unread data in buffer + * @s: COMEDI subdevice. + * + * Determines the number of bytes of unread data in the asynchronous + * acquisition data buffer for a subdevice. The data in question might not + * have been fully "munged" yet. + * + * Returns: The amount of unread data in bytes. + */ +static inline unsigned int comedi_buf_n_bytes_ready(struct comedi_subdevice *s) +{ + return s->async->buf_write_count - s->async->buf_read_count; +} + +unsigned int comedi_buf_write_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_write_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_read_n_available(struct comedi_subdevice *s); +unsigned int comedi_buf_read_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_read_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_write_samples(struct comedi_subdevice *s, + const void *data, unsigned int nsamples); +unsigned int comedi_buf_read_samples(struct comedi_subdevice *s, + void *data, unsigned int nsamples); + +/* drivers.c - general comedi driver functions */ + +#define COMEDI_TIMEOUT_MS 1000 + +int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, + int (*cb)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned long context), + unsigned long context); + +unsigned int comedi_handle_events(struct comedi_device *dev, + struct comedi_subdevice *s); + +int comedi_dio_insn_config(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data, + unsigned int mask); +unsigned int comedi_dio_update_state(struct comedi_subdevice *s, + unsigned int *data); +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd); +unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); +unsigned int comedi_nscans_left(struct comedi_subdevice *s, + unsigned int nscans); +unsigned int comedi_nsamples_left(struct comedi_subdevice *s, + unsigned int nsamples); +void comedi_inc_scan_progress(struct comedi_subdevice *s, + unsigned int num_bytes); + +void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size); +int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices); +int comedi_alloc_subdev_readback(struct comedi_subdevice *s); + +int comedi_readback_insn_read(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + +int comedi_load_firmware(struct comedi_device *dev, struct device *hw_dev, + const char *name, + int (*cb)(struct comedi_device *dev, + const u8 *data, size_t size, + unsigned long context), + unsigned long context); + +int __comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +int comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +void comedi_legacy_detach(struct comedi_device *dev); + +int comedi_auto_config(struct device *hardware_device, + struct comedi_driver *driver, unsigned long context); +void comedi_auto_unconfig(struct device *hardware_device); + +int comedi_driver_register(struct comedi_driver *driver); +void comedi_driver_unregister(struct comedi_driver *driver); + +/** + * module_comedi_driver() - Helper macro for registering a comedi driver + * @__comedi_driver: comedi_driver struct + * + * Helper macro for comedi drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only use + * this macro once, and calling it replaces module_init() and module_exit(). + */ +#define module_comedi_driver(__comedi_driver) \ + module_driver(__comedi_driver, comedi_driver_register, \ + comedi_driver_unregister) + +#endif /* _COMEDIDEV_H */ diff --git a/include/linux/comedi/comedilib.h b/include/linux/comedi/comedilib.h new file mode 100644 index 000000000000..0223c9cd9215 --- /dev/null +++ b/include/linux/comedi/comedilib.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedilib.h + * Header file for kcomedilib + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998-2001 David A. Schleef + */ + +#ifndef _LINUX_COMEDILIB_H +#define _LINUX_COMEDILIB_H + +struct comedi_device *comedi_open(const char *path); +int comedi_close(struct comedi_device *dev); +int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int *io); +int comedi_dio_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int io); +int comedi_dio_bitfield2(struct comedi_device *dev, unsigned int subdev, + unsigned int mask, unsigned int *bits, + unsigned int base_channel); +int comedi_find_subdevice_by_type(struct comedi_device *dev, int type, + unsigned int subd); +int comedi_get_n_channels(struct comedi_device *dev, unsigned int subdevice); + +#endif diff --git a/include/uapi/linux/comedi.h b/include/uapi/linux/comedi.h new file mode 100644 index 000000000000..7314e5ee0a1e --- /dev/null +++ b/include/uapi/linux/comedi.h @@ -0,0 +1,1528 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ +/* + * comedi.h + * header file for COMEDI user API + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998-2001 David A. Schleef + */ + +#ifndef _COMEDI_H +#define _COMEDI_H + +#define COMEDI_MAJORVERSION 0 +#define COMEDI_MINORVERSION 7 +#define COMEDI_MICROVERSION 76 +#define VERSION "0.7.76" + +/* comedi's major device number */ +#define COMEDI_MAJOR 98 + +/* + * maximum number of minor devices. This can be increased, although + * kernel structures are currently statically allocated, thus you + * don't want this to be much more than you actually use. + */ +#define COMEDI_NDEVICES 16 + +/* number of config options in the config structure */ +#define COMEDI_NDEVCONFOPTS 32 + +/* + * NOTE: 'comedi_config --init-data' is deprecated + * + * The following indexes in the config options were used by + * comedi_config to pass firmware blobs from user space to the + * comedi drivers. The request_firmware() hotplug interface is + * now used by all comedi drivers instead. + */ + +/* length of nth chunk of firmware data -*/ +#define COMEDI_DEVCONF_AUX_DATA3_LENGTH 25 +#define COMEDI_DEVCONF_AUX_DATA2_LENGTH 26 +#define COMEDI_DEVCONF_AUX_DATA1_LENGTH 27 +#define COMEDI_DEVCONF_AUX_DATA0_LENGTH 28 +/* most significant 32 bits of pointer address (if needed) */ +#define COMEDI_DEVCONF_AUX_DATA_HI 29 +/* least significant 32 bits of pointer address */ +#define COMEDI_DEVCONF_AUX_DATA_LO 30 +#define COMEDI_DEVCONF_AUX_DATA_LENGTH 31 /* total data length */ + +/* max length of device and driver names */ +#define COMEDI_NAMELEN 20 + +/* packs and unpacks a channel/range number */ + +#define CR_PACK(chan, rng, aref) \ + ((((aref) & 0x3) << 24) | (((rng) & 0xff) << 16) | (chan)) +#define CR_PACK_FLAGS(chan, range, aref, flags) \ + (CR_PACK(chan, range, aref) | ((flags) & CR_FLAGS_MASK)) + +#define CR_CHAN(a) ((a) & 0xffff) +#define CR_RANGE(a) (((a) >> 16) & 0xff) +#define CR_AREF(a) (((a) >> 24) & 0x03) + +#define CR_FLAGS_MASK 0xfc000000 +#define CR_ALT_FILTER 0x04000000 +#define CR_DITHER CR_ALT_FILTER +#define CR_DEGLITCH CR_ALT_FILTER +#define CR_ALT_SOURCE 0x08000000 +#define CR_EDGE 0x40000000 +#define CR_INVERT 0x80000000 + +#define AREF_GROUND 0x00 /* analog ref = analog ground */ +#define AREF_COMMON 0x01 /* analog ref = analog common */ +#define AREF_DIFF 0x02 /* analog ref = differential */ +#define AREF_OTHER 0x03 /* analog ref = other (undefined) */ + +/* counters -- these are arbitrary values */ +#define GPCT_RESET 0x0001 +#define GPCT_SET_SOURCE 0x0002 +#define GPCT_SET_GATE 0x0004 +#define GPCT_SET_DIRECTION 0x0008 +#define GPCT_SET_OPERATION 0x0010 +#define GPCT_ARM 0x0020 +#define GPCT_DISARM 0x0040 +#define GPCT_GET_INT_CLK_FRQ 0x0080 + +#define GPCT_INT_CLOCK 0x0001 +#define GPCT_EXT_PIN 0x0002 +#define GPCT_NO_GATE 0x0004 +#define GPCT_UP 0x0008 +#define GPCT_DOWN 0x0010 +#define GPCT_HWUD 0x0020 +#define GPCT_SIMPLE_EVENT 0x0040 +#define GPCT_SINGLE_PERIOD 0x0080 +#define GPCT_SINGLE_PW 0x0100 +#define GPCT_CONT_PULSE_OUT 0x0200 +#define GPCT_SINGLE_PULSE_OUT 0x0400 + +/* instructions */ + +#define INSN_MASK_WRITE 0x8000000 +#define INSN_MASK_READ 0x4000000 +#define INSN_MASK_SPECIAL 0x2000000 + +#define INSN_READ (0 | INSN_MASK_READ) +#define INSN_WRITE (1 | INSN_MASK_WRITE) +#define INSN_BITS (2 | INSN_MASK_READ | INSN_MASK_WRITE) +#define INSN_CONFIG (3 | INSN_MASK_READ | INSN_MASK_WRITE) +#define INSN_DEVICE_CONFIG (INSN_CONFIG | INSN_MASK_SPECIAL) +#define INSN_GTOD (4 | INSN_MASK_READ | INSN_MASK_SPECIAL) +#define INSN_WAIT (5 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) +#define INSN_INTTRIG (6 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) + +/* command flags */ +/* These flags are used in comedi_cmd structures */ + +#define CMDF_BOGUS 0x00000001 /* do the motions */ + +/* try to use a real-time interrupt while performing command */ +#define CMDF_PRIORITY 0x00000008 + +/* wake up on end-of-scan events */ +#define CMDF_WAKE_EOS 0x00000020 + +#define CMDF_WRITE 0x00000040 + +#define CMDF_RAWDATA 0x00000080 + +/* timer rounding definitions */ +#define CMDF_ROUND_MASK 0x00030000 +#define CMDF_ROUND_NEAREST 0x00000000 +#define CMDF_ROUND_DOWN 0x00010000 +#define CMDF_ROUND_UP 0x00020000 +#define CMDF_ROUND_UP_NEXT 0x00030000 + +#define COMEDI_EV_START 0x00040000 +#define COMEDI_EV_SCAN_BEGIN 0x00080000 +#define COMEDI_EV_CONVERT 0x00100000 +#define COMEDI_EV_SCAN_END 0x00200000 +#define COMEDI_EV_STOP 0x00400000 + +/* compatibility definitions */ +#define TRIG_BOGUS CMDF_BOGUS +#define TRIG_RT CMDF_PRIORITY +#define TRIG_WAKE_EOS CMDF_WAKE_EOS +#define TRIG_WRITE CMDF_WRITE +#define TRIG_ROUND_MASK CMDF_ROUND_MASK +#define TRIG_ROUND_NEAREST CMDF_ROUND_NEAREST +#define TRIG_ROUND_DOWN CMDF_ROUND_DOWN +#define TRIG_ROUND_UP CMDF_ROUND_UP +#define TRIG_ROUND_UP_NEXT CMDF_ROUND_UP_NEXT + +/* trigger sources */ + +#define TRIG_ANY 0xffffffff +#define TRIG_INVALID 0x00000000 + +#define TRIG_NONE 0x00000001 /* never trigger */ +#define TRIG_NOW 0x00000002 /* trigger now + N ns */ +#define TRIG_FOLLOW 0x00000004 /* trigger on next lower level trig */ +#define TRIG_TIME 0x00000008 /* trigger at time N ns */ +#define TRIG_TIMER 0x00000010 /* trigger at rate N ns */ +#define TRIG_COUNT 0x00000020 /* trigger when count reaches N */ +#define TRIG_EXT 0x00000040 /* trigger on external signal N */ +#define TRIG_INT 0x00000080 /* trigger on comedi-internal signal N */ +#define TRIG_OTHER 0x00000100 /* driver defined */ + +/* subdevice flags */ + +#define SDF_BUSY 0x0001 /* device is busy */ +#define SDF_BUSY_OWNER 0x0002 /* device is busy with your job */ +#define SDF_LOCKED 0x0004 /* subdevice is locked */ +#define SDF_LOCK_OWNER 0x0008 /* you own lock */ +#define SDF_MAXDATA 0x0010 /* maxdata depends on channel */ +#define SDF_FLAGS 0x0020 /* flags depend on channel */ +#define SDF_RANGETYPE 0x0040 /* range type depends on channel */ +#define SDF_PWM_COUNTER 0x0080 /* PWM can automatically switch off */ +#define SDF_PWM_HBRIDGE 0x0100 /* PWM is signed (H-bridge) */ +#define SDF_CMD 0x1000 /* can do commands (deprecated) */ +#define SDF_SOFT_CALIBRATED 0x2000 /* subdevice uses software calibration */ +#define SDF_CMD_WRITE 0x4000 /* can do output commands */ +#define SDF_CMD_READ 0x8000 /* can do input commands */ + +/* subdevice can be read (e.g. analog input) */ +#define SDF_READABLE 0x00010000 +/* subdevice can be written (e.g. analog output) */ +#define SDF_WRITABLE 0x00020000 +#define SDF_WRITEABLE SDF_WRITABLE /* spelling error in API */ +/* subdevice does not have externally visible lines */ +#define SDF_INTERNAL 0x00040000 +#define SDF_GROUND 0x00100000 /* can do aref=ground */ +#define SDF_COMMON 0x00200000 /* can do aref=common */ +#define SDF_DIFF 0x00400000 /* can do aref=diff */ +#define SDF_OTHER 0x00800000 /* can do aref=other */ +#define SDF_DITHER 0x01000000 /* can do dithering */ +#define SDF_DEGLITCH 0x02000000 /* can do deglitching */ +#define SDF_MMAP 0x04000000 /* can do mmap() */ +#define SDF_RUNNING 0x08000000 /* subdevice is acquiring data */ +#define SDF_LSAMPL 0x10000000 /* subdevice uses 32-bit samples */ +#define SDF_PACKED 0x20000000 /* subdevice can do packed DIO */ + +/* subdevice types */ + +/** + * enum comedi_subdevice_type - COMEDI subdevice types + * @COMEDI_SUBD_UNUSED: Unused subdevice. + * @COMEDI_SUBD_AI: Analog input. + * @COMEDI_SUBD_AO: Analog output. + * @COMEDI_SUBD_DI: Digital input. + * @COMEDI_SUBD_DO: Digital output. + * @COMEDI_SUBD_DIO: Digital input/output. + * @COMEDI_SUBD_COUNTER: Counter. + * @COMEDI_SUBD_TIMER: Timer. + * @COMEDI_SUBD_MEMORY: Memory, EEPROM, DPRAM. + * @COMEDI_SUBD_CALIB: Calibration DACs. + * @COMEDI_SUBD_PROC: Processor, DSP. + * @COMEDI_SUBD_SERIAL: Serial I/O. + * @COMEDI_SUBD_PWM: Pulse-Width Modulation output. + */ +enum comedi_subdevice_type { + COMEDI_SUBD_UNUSED, + COMEDI_SUBD_AI, + COMEDI_SUBD_AO, + COMEDI_SUBD_DI, + COMEDI_SUBD_DO, + COMEDI_SUBD_DIO, + COMEDI_SUBD_COUNTER, + COMEDI_SUBD_TIMER, + COMEDI_SUBD_MEMORY, + COMEDI_SUBD_CALIB, + COMEDI_SUBD_PROC, + COMEDI_SUBD_SERIAL, + COMEDI_SUBD_PWM +}; + +/* configuration instructions */ + +/** + * enum comedi_io_direction - COMEDI I/O directions + * @COMEDI_INPUT: Input. + * @COMEDI_OUTPUT: Output. + * @COMEDI_OPENDRAIN: Open-drain (or open-collector) output. + * + * These are used by the %INSN_CONFIG_DIO_QUERY configuration instruction to + * report a direction. They may also be used in other places where a direction + * needs to be specified. + */ +enum comedi_io_direction { + COMEDI_INPUT = 0, + COMEDI_OUTPUT = 1, + COMEDI_OPENDRAIN = 2 +}; + +/** + * enum configuration_ids - COMEDI configuration instruction codes + * @INSN_CONFIG_DIO_INPUT: Configure digital I/O as input. + * @INSN_CONFIG_DIO_OUTPUT: Configure digital I/O as output. + * @INSN_CONFIG_DIO_OPENDRAIN: Configure digital I/O as open-drain (or open + * collector) output. + * @INSN_CONFIG_ANALOG_TRIG: Configure analog trigger. + * @INSN_CONFIG_ALT_SOURCE: Configure alternate input source. + * @INSN_CONFIG_DIGITAL_TRIG: Configure digital trigger. + * @INSN_CONFIG_BLOCK_SIZE: Configure block size for DMA transfers. + * @INSN_CONFIG_TIMER_1: Configure divisor for external clock. + * @INSN_CONFIG_FILTER: Configure a filter. + * @INSN_CONFIG_CHANGE_NOTIFY: Configure change notification for digital + * inputs. (New drivers should use + * %INSN_CONFIG_DIGITAL_TRIG instead.) + * @INSN_CONFIG_SERIAL_CLOCK: Configure clock for serial I/O. + * @INSN_CONFIG_BIDIRECTIONAL_DATA: Send and receive byte over serial I/O. + * @INSN_CONFIG_DIO_QUERY: Query direction of digital I/O channel. + * @INSN_CONFIG_PWM_OUTPUT: Configure pulse-width modulator output. + * @INSN_CONFIG_GET_PWM_OUTPUT: Get pulse-width modulator output configuration. + * @INSN_CONFIG_ARM: Arm a subdevice or channel. + * @INSN_CONFIG_DISARM: Disarm a subdevice or channel. + * @INSN_CONFIG_GET_COUNTER_STATUS: Get counter status. + * @INSN_CONFIG_RESET: Reset a subdevice or channel. + * @INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR: Configure counter/timer as + * single pulse generator. + * @INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR: Configure counter/timer as + * pulse train generator. + * @INSN_CONFIG_GPCT_QUADRATURE_ENCODER: Configure counter as a quadrature + * encoder. + * @INSN_CONFIG_SET_GATE_SRC: Set counter/timer gate source. + * @INSN_CONFIG_GET_GATE_SRC: Get counter/timer gate source. + * @INSN_CONFIG_SET_CLOCK_SRC: Set counter/timer master clock source. + * @INSN_CONFIG_GET_CLOCK_SRC: Get counter/timer master clock source. + * @INSN_CONFIG_SET_OTHER_SRC: Set counter/timer "other" source. + * @INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE: Get size (in bytes) of subdevice's + * on-board FIFOs used during streaming + * input/output. + * @INSN_CONFIG_SET_COUNTER_MODE: Set counter/timer mode. + * @INSN_CONFIG_8254_SET_MODE: (Deprecated) Same as + * %INSN_CONFIG_SET_COUNTER_MODE. + * @INSN_CONFIG_8254_READ_STATUS: Read status of 8254 counter channel. + * @INSN_CONFIG_SET_ROUTING: Set routing for a channel. + * @INSN_CONFIG_GET_ROUTING: Get routing for a channel. + * @INSN_CONFIG_PWM_SET_PERIOD: Set PWM period in nanoseconds. + * @INSN_CONFIG_PWM_GET_PERIOD: Get PWM period in nanoseconds. + * @INSN_CONFIG_GET_PWM_STATUS: Get PWM status. + * @INSN_CONFIG_PWM_SET_H_BRIDGE: Set PWM H bridge duty cycle and polarity for + * a relay simultaneously. + * @INSN_CONFIG_PWM_GET_H_BRIDGE: Get PWM H bridge duty cycle and polarity. + * @INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS: Get the hardware timing restraints, + * regardless of trigger sources. + */ +enum configuration_ids { + INSN_CONFIG_DIO_INPUT = COMEDI_INPUT, + INSN_CONFIG_DIO_OUTPUT = COMEDI_OUTPUT, + INSN_CONFIG_DIO_OPENDRAIN = COMEDI_OPENDRAIN, + INSN_CONFIG_ANALOG_TRIG = 16, +/* INSN_CONFIG_WAVEFORM = 17, */ +/* INSN_CONFIG_TRIG = 18, */ +/* INSN_CONFIG_COUNTER = 19, */ + INSN_CONFIG_ALT_SOURCE = 20, + INSN_CONFIG_DIGITAL_TRIG = 21, + INSN_CONFIG_BLOCK_SIZE = 22, + INSN_CONFIG_TIMER_1 = 23, + INSN_CONFIG_FILTER = 24, + INSN_CONFIG_CHANGE_NOTIFY = 25, + + INSN_CONFIG_SERIAL_CLOCK = 26, /*ALPHA*/ + INSN_CONFIG_BIDIRECTIONAL_DATA = 27, + INSN_CONFIG_DIO_QUERY = 28, + INSN_CONFIG_PWM_OUTPUT = 29, + INSN_CONFIG_GET_PWM_OUTPUT = 30, + INSN_CONFIG_ARM = 31, + INSN_CONFIG_DISARM = 32, + INSN_CONFIG_GET_COUNTER_STATUS = 33, + INSN_CONFIG_RESET = 34, + INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR = 1001, + INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR = 1002, + INSN_CONFIG_GPCT_QUADRATURE_ENCODER = 1003, + INSN_CONFIG_SET_GATE_SRC = 2001, + INSN_CONFIG_GET_GATE_SRC = 2002, + INSN_CONFIG_SET_CLOCK_SRC = 2003, + INSN_CONFIG_GET_CLOCK_SRC = 2004, + INSN_CONFIG_SET_OTHER_SRC = 2005, + INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE = 2006, + INSN_CONFIG_SET_COUNTER_MODE = 4097, + INSN_CONFIG_8254_SET_MODE = INSN_CONFIG_SET_COUNTER_MODE, + INSN_CONFIG_8254_READ_STATUS = 4098, + INSN_CONFIG_SET_ROUTING = 4099, + INSN_CONFIG_GET_ROUTING = 4109, + INSN_CONFIG_PWM_SET_PERIOD = 5000, + INSN_CONFIG_PWM_GET_PERIOD = 5001, + INSN_CONFIG_GET_PWM_STATUS = 5002, + INSN_CONFIG_PWM_SET_H_BRIDGE = 5003, + INSN_CONFIG_PWM_GET_H_BRIDGE = 5004, + INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS = 5005, +}; + +/** + * enum device_configuration_ids - COMEDI configuration instruction codes global + * to an entire device. + * @INSN_DEVICE_CONFIG_TEST_ROUTE: Validate the possibility of a + * globally-named route + * @INSN_DEVICE_CONFIG_CONNECT_ROUTE: Connect a globally-named route + * @INSN_DEVICE_CONFIG_DISCONNECT_ROUTE:Disconnect a globally-named route + * @INSN_DEVICE_CONFIG_GET_ROUTES: Get a list of all globally-named routes + * that are valid for a particular device. + */ +enum device_config_route_ids { + INSN_DEVICE_CONFIG_TEST_ROUTE = 0, + INSN_DEVICE_CONFIG_CONNECT_ROUTE = 1, + INSN_DEVICE_CONFIG_DISCONNECT_ROUTE = 2, + INSN_DEVICE_CONFIG_GET_ROUTES = 3, +}; + +/** + * enum comedi_digital_trig_op - operations for configuring a digital trigger + * @COMEDI_DIGITAL_TRIG_DISABLE: Return digital trigger to its default, + * inactive, unconfigured state. + * @COMEDI_DIGITAL_TRIG_ENABLE_EDGES: Set rising and/or falling edge inputs + * that each can fire the trigger. + * @COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: Set a combination of high and/or low + * level inputs that can fire the trigger. + * + * These are used with the %INSN_CONFIG_DIGITAL_TRIG configuration instruction. + * The data for the configuration instruction is as follows... + * + * data[%0] = %INSN_CONFIG_DIGITAL_TRIG + * + * data[%1] = trigger ID + * + * data[%2] = configuration operation + * + * data[%3] = configuration parameter 1 + * + * data[%4] = configuration parameter 2 + * + * data[%5] = configuration parameter 3 + * + * The trigger ID (data[%1]) is used to differentiate multiple digital triggers + * belonging to the same subdevice. The configuration operation (data[%2]) is + * one of the enum comedi_digital_trig_op values. The configuration + * parameters (data[%3], data[%4], and data[%5]) depend on the operation; they + * are not used with %COMEDI_DIGITAL_TRIG_DISABLE. + * + * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES and %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, + * configuration parameter 1 (data[%3]) contains a "left-shift" value that + * specifies the input corresponding to bit 0 of configuration parameters 2 + * and 3. This is useful if the trigger has more than 32 inputs. + * + * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES, configuration parameter 2 (data[%4]) + * specifies which of up to 32 inputs have rising-edge sensitivity, and + * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs + * have falling-edge sensitivity that can fire the trigger. + * + * For %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, configuration parameter 2 (data[%4]) + * specifies which of up to 32 inputs must be at a high level, and + * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs + * must be at a low level for the trigger to fire. + * + * Some sequences of %INSN_CONFIG_DIGITAL_TRIG instructions may have a (partly) + * accumulative effect, depending on the low-level driver. This is useful + * when setting up a trigger that has more than 32 inputs, or has a combination + * of edge- and level-triggered inputs. + */ +enum comedi_digital_trig_op { + COMEDI_DIGITAL_TRIG_DISABLE = 0, + COMEDI_DIGITAL_TRIG_ENABLE_EDGES = 1, + COMEDI_DIGITAL_TRIG_ENABLE_LEVELS = 2 +}; + +/** + * enum comedi_support_level - support level for a COMEDI feature + * @COMEDI_UNKNOWN_SUPPORT: Unspecified support for feature. + * @COMEDI_SUPPORTED: Feature is supported. + * @COMEDI_UNSUPPORTED: Feature is unsupported. + */ +enum comedi_support_level { + COMEDI_UNKNOWN_SUPPORT = 0, + COMEDI_SUPPORTED, + COMEDI_UNSUPPORTED +}; + +/** + * enum comedi_counter_status_flags - counter status bits + * @COMEDI_COUNTER_ARMED: Counter is armed. + * @COMEDI_COUNTER_COUNTING: Counter is counting. + * @COMEDI_COUNTER_TERMINAL_COUNT: Counter reached terminal count. + * + * These bitwise values are used by the %INSN_CONFIG_GET_COUNTER_STATUS + * configuration instruction to report the status of a counter. + */ +enum comedi_counter_status_flags { + COMEDI_COUNTER_ARMED = 0x1, + COMEDI_COUNTER_COUNTING = 0x2, + COMEDI_COUNTER_TERMINAL_COUNT = 0x4, +}; + +/* ioctls */ + +#define CIO 'd' +#define COMEDI_DEVCONFIG _IOW(CIO, 0, struct comedi_devconfig) +#define COMEDI_DEVINFO _IOR(CIO, 1, struct comedi_devinfo) +#define COMEDI_SUBDINFO _IOR(CIO, 2, struct comedi_subdinfo) +#define COMEDI_CHANINFO _IOR(CIO, 3, struct comedi_chaninfo) +/* _IOWR(CIO, 4, ...) is reserved */ +#define COMEDI_LOCK _IO(CIO, 5) +#define COMEDI_UNLOCK _IO(CIO, 6) +#define COMEDI_CANCEL _IO(CIO, 7) +#define COMEDI_RANGEINFO _IOR(CIO, 8, struct comedi_rangeinfo) +#define COMEDI_CMD _IOR(CIO, 9, struct comedi_cmd) +#define COMEDI_CMDTEST _IOR(CIO, 10, struct comedi_cmd) +#define COMEDI_INSNLIST _IOR(CIO, 11, struct comedi_insnlist) +#define COMEDI_INSN _IOR(CIO, 12, struct comedi_insn) +#define COMEDI_BUFCONFIG _IOR(CIO, 13, struct comedi_bufconfig) +#define COMEDI_BUFINFO _IOWR(CIO, 14, struct comedi_bufinfo) +#define COMEDI_POLL _IO(CIO, 15) +#define COMEDI_SETRSUBD _IO(CIO, 16) +#define COMEDI_SETWSUBD _IO(CIO, 17) + +/* structures */ + +/** + * struct comedi_insn - COMEDI instruction + * @insn: COMEDI instruction type (%INSN_xxx). + * @n: Length of @data[]. + * @data: Pointer to data array operated on by the instruction. + * @subdev: Subdevice index. + * @chanspec: A packed "chanspec" value consisting of channel number, + * analog range index, analog reference type, and flags. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_INSN ioctl, and indirectly with the + * %COMEDI_INSNLIST ioctl. + */ +struct comedi_insn { + unsigned int insn; + unsigned int n; + unsigned int __user *data; + unsigned int subdev; + unsigned int chanspec; + unsigned int unused[3]; +}; + +/** + * struct comedi_insnlist - list of COMEDI instructions + * @n_insns: Number of COMEDI instructions. + * @insns: Pointer to array COMEDI instructions. + * + * This is used with the %COMEDI_INSNLIST ioctl. + */ +struct comedi_insnlist { + unsigned int n_insns; + struct comedi_insn __user *insns; +}; + +/** + * struct comedi_cmd - COMEDI asynchronous acquisition command details + * @subdev: Subdevice index. + * @flags: Command flags (%CMDF_xxx). + * @start_src: "Start acquisition" trigger source (%TRIG_xxx). + * @start_arg: "Start acquisition" trigger argument. + * @scan_begin_src: "Scan begin" trigger source. + * @scan_begin_arg: "Scan begin" trigger argument. + * @convert_src: "Convert" trigger source. + * @convert_arg: "Convert" trigger argument. + * @scan_end_src: "Scan end" trigger source. + * @scan_end_arg: "Scan end" trigger argument. + * @stop_src: "Stop acquisition" trigger source. + * @stop_arg: "Stop acquisition" trigger argument. + * @chanlist: Pointer to array of "chanspec" values, containing a + * sequence of channel numbers packed with analog range + * index, etc. + * @chanlist_len: Number of channels in sequence. + * @data: Pointer to miscellaneous set-up data (not used). + * @data_len: Length of miscellaneous set-up data. + * + * This is used with the %COMEDI_CMD or %COMEDI_CMDTEST ioctl to set-up + * or validate an asynchronous acquisition command. The ioctl may modify + * the &struct comedi_cmd and copy it back to the caller. + * + * Optional command @flags values that can be ORed together... + * + * %CMDF_BOGUS - makes %COMEDI_CMD ioctl return error %EAGAIN instead of + * starting the command. + * + * %CMDF_PRIORITY - requests "hard real-time" processing (which is not + * supported in this version of COMEDI). + * + * %CMDF_WAKE_EOS - requests the command makes data available for reading + * after every "scan" period. + * + * %CMDF_WRITE - marks the command as being in the "write" (to device) + * direction. This does not need to be specified by the caller unless the + * subdevice supports commands in either direction. + * + * %CMDF_RAWDATA - prevents the command from "munging" the data between the + * COMEDI sample format and the raw hardware sample format. + * + * %CMDF_ROUND_NEAREST - requests timing periods to be rounded to nearest + * supported values. + * + * %CMDF_ROUND_DOWN - requests timing periods to be rounded down to supported + * values (frequencies rounded up). + * + * %CMDF_ROUND_UP - requests timing periods to be rounded up to supported + * values (frequencies rounded down). + * + * Trigger source values for @start_src, @scan_begin_src, @convert_src, + * @scan_end_src, and @stop_src... + * + * %TRIG_ANY - "all ones" value used to test which trigger sources are + * supported. + * + * %TRIG_INVALID - "all zeroes" value used to indicate that all requested + * trigger sources are invalid. + * + * %TRIG_NONE - never trigger (often used as a @stop_src value). + * + * %TRIG_NOW - trigger after '_arg' nanoseconds. + * + * %TRIG_FOLLOW - trigger follows another event. + * + * %TRIG_TIMER - trigger every '_arg' nanoseconds. + * + * %TRIG_COUNT - trigger when count '_arg' is reached. + * + * %TRIG_EXT - trigger on external signal specified by '_arg'. + * + * %TRIG_INT - trigger on internal, software trigger specified by '_arg'. + * + * %TRIG_OTHER - trigger on other, driver-defined signal specified by '_arg'. + */ +struct comedi_cmd { + unsigned int subdev; + unsigned int flags; + + unsigned int start_src; + unsigned int start_arg; + + unsigned int scan_begin_src; + unsigned int scan_begin_arg; + + unsigned int convert_src; + unsigned int convert_arg; + + unsigned int scan_end_src; + unsigned int scan_end_arg; + + unsigned int stop_src; + unsigned int stop_arg; + + unsigned int *chanlist; + unsigned int chanlist_len; + + short __user *data; + unsigned int data_len; +}; + +/** + * struct comedi_chaninfo - used to retrieve per-channel information + * @subdev: Subdevice index. + * @maxdata_list: Optional pointer to per-channel maximum data values. + * @flaglist: Optional pointer to per-channel flags. + * @rangelist: Optional pointer to per-channel range types. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_CHANINFO ioctl to get per-channel information + * for the subdevice. Use of this requires knowledge of the number of channels + * and subdevice flags obtained using the %COMEDI_SUBDINFO ioctl. + * + * The @maxdata_list member must be %NULL unless the %SDF_MAXDATA subdevice + * flag is set. The @flaglist member must be %NULL unless the %SDF_FLAGS + * subdevice flag is set. The @rangelist member must be %NULL unless the + * %SDF_RANGETYPE subdevice flag is set. Otherwise, the arrays they point to + * must be at least as long as the number of channels. + */ +struct comedi_chaninfo { + unsigned int subdev; + unsigned int __user *maxdata_list; + unsigned int __user *flaglist; + unsigned int __user *rangelist; + unsigned int unused[4]; +}; + +/** + * struct comedi_rangeinfo - used to retrieve the range table for a channel + * @range_type: Encodes subdevice index (bits 27:24), channel index + * (bits 23:16) and range table length (bits 15:0). + * @range_ptr: Pointer to array of @struct comedi_krange to be filled + * in with the range table for the channel or subdevice. + * + * This is used with the %COMEDI_RANGEINFO ioctl to retrieve the range table + * for a specific channel (if the subdevice has the %SDF_RANGETYPE flag set to + * indicate that the range table depends on the channel), or for the subdevice + * as a whole (if the %SDF_RANGETYPE flag is clear, indicating the range table + * is shared by all channels). + * + * The @range_type value is an input to the ioctl and comes from a previous + * use of the %COMEDI_SUBDINFO ioctl (if the %SDF_RANGETYPE flag is clear), + * or the %COMEDI_CHANINFO ioctl (if the %SDF_RANGETYPE flag is set). + */ +struct comedi_rangeinfo { + unsigned int range_type; + void __user *range_ptr; +}; + +/** + * struct comedi_krange - describes a range in a range table + * @min: Minimum value in millionths (1e-6) of a unit. + * @max: Maximum value in millionths (1e-6) of a unit. + * @flags: Indicates the units (in bits 7:0) OR'ed with optional flags. + * + * A range table is associated with a single channel, or with all channels in a + * subdevice, and a list of one or more ranges. A %struct comedi_krange + * describes the physical range of units for one of those ranges. Sample + * values in COMEDI are unsigned from %0 up to some 'maxdata' value. The + * mapping from sample values to physical units is assumed to be nomimally + * linear (for the purpose of describing the range), with sample value %0 + * mapping to @min, and the 'maxdata' sample value mapping to @max. + * + * The currently defined units are %UNIT_volt (%0), %UNIT_mA (%1), and + * %UNIT_none (%2). The @min and @max values are the physical range multiplied + * by 1e6, so a @max value of %1000000 (with %UNIT_volt) represents a maximal + * value of 1 volt. + * + * The only defined flag value is %RF_EXTERNAL (%0x100), indicating that the + * range needs to be multiplied by an external reference. + */ +struct comedi_krange { + int min; + int max; + unsigned int flags; +}; + +/** + * struct comedi_subdinfo - used to retrieve information about a subdevice + * @type: Type of subdevice from &enum comedi_subdevice_type. + * @n_chan: Number of channels the subdevice supports. + * @subd_flags: A mixture of static and dynamic flags describing + * aspects of the subdevice and its current state. + * @timer_type: Timer type. Always set to %5 ("nanosecond timer"). + * @len_chanlist: Maximum length of a channel list if the subdevice + * supports asynchronous acquisition commands. + * @maxdata: Maximum sample value for all channels if the + * %SDF_MAXDATA subdevice flag is clear. + * @flags: Channel flags for all channels if the %SDF_FLAGS + * subdevice flag is clear. + * @range_type: The range type for all channels if the %SDF_RANGETYPE + * subdevice flag is clear. Encodes the subdevice index + * (bits 27:24), a dummy channel index %0 (bits 23:16), + * and the range table length (bits 15:0). + * @settling_time_0: Not used. + * @insn_bits_support: Set to %COMEDI_SUPPORTED if the subdevice supports the + * %INSN_BITS instruction, or to %COMEDI_UNSUPPORTED if it + * does not. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_SUBDINFO ioctl which copies an array of + * &struct comedi_subdinfo back to user space, with one element per subdevice. + * Use of this requires knowledge of the number of subdevices obtained from + * the %COMEDI_DEVINFO ioctl. + * + * These are the @subd_flags values that may be ORed together... + * + * %SDF_BUSY - the subdevice is busy processing an asynchronous command or a + * synchronous instruction. + * + * %SDF_BUSY_OWNER - the subdevice is busy processing an asynchronous + * acquisition command started on the current file object (the file object + * issuing the %COMEDI_SUBDINFO ioctl). + * + * %SDF_LOCKED - the subdevice is locked by a %COMEDI_LOCK ioctl. + * + * %SDF_LOCK_OWNER - the subdevice is locked by a %COMEDI_LOCK ioctl from the + * current file object. + * + * %SDF_MAXDATA - maximum sample values are channel-specific. + * + * %SDF_FLAGS - channel flags are channel-specific. + * + * %SDF_RANGETYPE - range types are channel-specific. + * + * %SDF_PWM_COUNTER - PWM can switch off automatically. + * + * %SDF_PWM_HBRIDGE - or PWM is signed (H-bridge). + * + * %SDF_CMD - the subdevice supports asynchronous commands. + * + * %SDF_SOFT_CALIBRATED - the subdevice uses software calibration. + * + * %SDF_CMD_WRITE - the subdevice supports asynchronous commands in the output + * ("write") direction. + * + * %SDF_CMD_READ - the subdevice supports asynchronous commands in the input + * ("read") direction. + * + * %SDF_READABLE - the subdevice is readable (e.g. analog input). + * + * %SDF_WRITABLE (aliased as %SDF_WRITEABLE) - the subdevice is writable (e.g. + * analog output). + * + * %SDF_INTERNAL - the subdevice has no externally visible lines. + * + * %SDF_GROUND - the subdevice can use ground as an analog reference. + * + * %SDF_COMMON - the subdevice can use a common analog reference. + * + * %SDF_DIFF - the subdevice can use differential inputs (or outputs). + * + * %SDF_OTHER - the subdevice can use some other analog reference. + * + * %SDF_DITHER - the subdevice can do dithering. + * + * %SDF_DEGLITCH - the subdevice can do deglitching. + * + * %SDF_MMAP - this is never set. + * + * %SDF_RUNNING - an asynchronous command is still running. + * + * %SDF_LSAMPL - the subdevice uses "long" (32-bit) samples (for asynchronous + * command data). + * + * %SDF_PACKED - the subdevice packs several DIO samples into a single sample + * (for asynchronous command data). + * + * No "channel flags" (@flags) values are currently defined. + */ +struct comedi_subdinfo { + unsigned int type; + unsigned int n_chan; + unsigned int subd_flags; + unsigned int timer_type; + unsigned int len_chanlist; + unsigned int maxdata; + unsigned int flags; + unsigned int range_type; + unsigned int settling_time_0; + unsigned int insn_bits_support; + unsigned int unused[8]; +}; + +/** + * struct comedi_devinfo - used to retrieve information about a COMEDI device + * @version_code: COMEDI version code. + * @n_subdevs: Number of subdevices the device has. + * @driver_name: Null-terminated COMEDI driver name. + * @board_name: Null-terminated COMEDI board name. + * @read_subdevice: Index of the current "read" subdevice (%-1 if none). + * @write_subdevice: Index of the current "write" subdevice (%-1 if none). + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_DEVINFO ioctl to get basic information about + * the device. + */ +struct comedi_devinfo { + unsigned int version_code; + unsigned int n_subdevs; + char driver_name[COMEDI_NAMELEN]; + char board_name[COMEDI_NAMELEN]; + int read_subdevice; + int write_subdevice; + int unused[30]; +}; + +/** + * struct comedi_devconfig - used to configure a legacy COMEDI device + * @board_name: Null-terminated string specifying the type of board + * to configure. + * @options: An array of integer configuration options. + * + * This is used with the %COMEDI_DEVCONFIG ioctl to configure a "legacy" COMEDI + * device, such as an ISA card. Not all COMEDI drivers support this. Those + * that do either expect the specified board name to match one of a list of + * names registered with the COMEDI core, or expect the specified board name + * to match the COMEDI driver name itself. The configuration options are + * handled in a driver-specific manner. + */ +struct comedi_devconfig { + char board_name[COMEDI_NAMELEN]; + int options[COMEDI_NDEVCONFOPTS]; +}; + +/** + * struct comedi_bufconfig - used to set or get buffer size for a subdevice + * @subdevice: Subdevice index. + * @flags: Not used. + * @maximum_size: Maximum allowed buffer size. + * @size: Buffer size. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_BUFCONFIG ioctl to get or configure the + * maximum buffer size and current buffer size for a COMEDI subdevice that + * supports asynchronous commands. If the subdevice does not support + * asynchronous commands, @maximum_size and @size are ignored and set to 0. + * + * On ioctl input, non-zero values of @maximum_size and @size specify a + * new maximum size and new current size (in bytes), respectively. These + * will by rounded up to a multiple of %PAGE_SIZE. Specifying a new maximum + * size requires admin capabilities. + * + * On ioctl output, @maximum_size and @size and set to the current maximum + * buffer size and current buffer size, respectively. + */ +struct comedi_bufconfig { + unsigned int subdevice; + unsigned int flags; + + unsigned int maximum_size; + unsigned int size; + + unsigned int unused[4]; +}; + +/** + * struct comedi_bufinfo - used to manipulate buffer position for a subdevice + * @subdevice: Subdevice index. + * @bytes_read: Specify amount to advance read position for an + * asynchronous command in the input ("read") direction. + * @buf_write_ptr: Current write position (index) within the buffer. + * @buf_read_ptr: Current read position (index) within the buffer. + * @buf_write_count: Total amount written, modulo 2^32. + * @buf_read_count: Total amount read, modulo 2^32. + * @bytes_written: Specify amount to advance write position for an + * asynchronous command in the output ("write") direction. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_BUFINFO ioctl to optionally advance the + * current read or write position in an asynchronous acquisition data buffer, + * and to get the current read and write positions in the buffer. + */ +struct comedi_bufinfo { + unsigned int subdevice; + unsigned int bytes_read; + + unsigned int buf_write_ptr; + unsigned int buf_read_ptr; + unsigned int buf_write_count; + unsigned int buf_read_count; + + unsigned int bytes_written; + + unsigned int unused[4]; +}; + +/* range stuff */ + +#define __RANGE(a, b) ((((a) & 0xffff) << 16) | ((b) & 0xffff)) + +#define RANGE_OFFSET(a) (((a) >> 16) & 0xffff) +#define RANGE_LENGTH(b) ((b) & 0xffff) + +#define RF_UNIT(flags) ((flags) & 0xff) +#define RF_EXTERNAL 0x100 + +#define UNIT_volt 0 +#define UNIT_mA 1 +#define UNIT_none 2 + +#define COMEDI_MIN_SPEED 0xffffffffu + +/**********************************************************/ +/* everything after this line is ALPHA */ +/**********************************************************/ + +/* + * 8254 specific configuration. + * + * It supports two config commands: + * + * 0 ID: INSN_CONFIG_SET_COUNTER_MODE + * 1 8254 Mode + * I8254_MODE0, I8254_MODE1, ..., I8254_MODE5 + * OR'ed with: + * I8254_BCD, I8254_BINARY + * + * 0 ID: INSN_CONFIG_8254_READ_STATUS + * 1 <-- Status byte returned here. + * B7 = Output + * B6 = NULL Count + * B5 - B0 Current mode. + */ + +enum i8254_mode { + I8254_MODE0 = (0 << 1), /* Interrupt on terminal count */ + I8254_MODE1 = (1 << 1), /* Hardware retriggerable one-shot */ + I8254_MODE2 = (2 << 1), /* Rate generator */ + I8254_MODE3 = (3 << 1), /* Square wave mode */ + I8254_MODE4 = (4 << 1), /* Software triggered strobe */ + /* Hardware triggered strobe (retriggerable) */ + I8254_MODE5 = (5 << 1), + /* Use binary-coded decimal instead of binary (pretty useless) */ + I8254_BCD = 1, + I8254_BINARY = 0 +}; + +/* *** BEGIN GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ + +/* + * Common National Instruments Terminal/Signal names. + * Some of these have no NI_ prefix as they are useful for non-NI hardware, such + * as those that utilize the PXI/RTSI trigger lines. + * + * NOTE ABOUT THE CHOICE OF NAMES HERE AND THE CAMELSCRIPT: + * The choice to use CamelScript and the exact names below is for + * maintainability, clarity, similarity to manufacturer's documentation, + * _and_ a mitigation for confusion that has plagued the use of these drivers + * for years! + * + * More detail: + * There have been significant confusions over the past many years for users + * when trying to understand how to connect to/from signals and terminals on + * NI hardware using comedi. The major reason for this is that the actual + * register values were exposed and required to be used by users. Several + * major reasons exist why this caused major confusion for users: + * 1) The register values are _NOT_ in user documentation, but rather in + * arcane locations, such as a few register programming manuals that are + * increasingly hard to find and the NI MHDDK (comments in example code). + * There is no one place to find the various valid values of the registers. + * 2) The register values are _NOT_ completely consistent. There is no way to + * gain any sense of intuition of which values, or even enums one should use + * for various registers. There was some attempt in prior use of comedi to + * name enums such that a user might know which enums should be used for + * varying purposes, but the end-user had to gain a knowledge of register + * values to correctly wield this approach. + * 3) The names for signals and registers found in the various register level + * programming manuals and vendor-provided documentation are _not_ even + * close to the same names that are in the end-user documentation. + * + * Similar, albeit less, confusion plagued NI's previous version of their own + * drivers. Earlier than 2003, NI greatly simplified the situation for users + * by releasing a new API that abstracted the names of signals/terminals to a + * common and intuitive set of names. + * + * The names below mirror the names chosen and well documented by NI. These + * names are exposed to the user via the comedilib user library. By keeping + * the names below, in spite of the use of CamelScript, maintenance will be + * greatly eased and confusion for users _and_ comedi developers will be + * greatly reduced. + */ + +/* + * Base of abstracted NI names. + * The first 16 bits of *_arg are reserved for channel selection. + * Since we only actually need the first 4 or 5 bits for all register values on + * NI select registers anyways, we'll identify all values >= (1<<15) as being an + * abstracted NI signal/terminal name. + * These values are also used/returned by INSN_DEVICE_CONFIG_TEST_ROUTE, + * INSN_DEVICE_CONFIG_CONNECT_ROUTE, INSN_DEVICE_CONFIG_DISCONNECT_ROUTE, + * and INSN_DEVICE_CONFIG_GET_ROUTES. + */ +#define NI_NAMES_BASE 0x8000u + +#define _TERM_N(base, n, x) ((base) + ((x) & ((n) - 1))) + +/* + * not necessarily all allowed 64 PFIs are valid--certainly not for all devices + */ +#define NI_PFI(x) _TERM_N(NI_NAMES_BASE, 64, x) +/* 8 trigger lines by standard, Some devices cannot talk to all eight. */ +#define TRIGGER_LINE(x) _TERM_N(NI_PFI(-1) + 1, 8, x) +/* 4 RTSI shared MUXes to route signals to/from TRIGGER_LINES on NI hardware */ +#define NI_RTSI_BRD(x) _TERM_N(TRIGGER_LINE(-1) + 1, 4, x) + +/* *** Counter/timer names : 8 counters max *** */ +#define NI_MAX_COUNTERS 8 +#define NI_COUNTER_NAMES_BASE (NI_RTSI_BRD(-1) + 1) +#define NI_CtrSource(x) _TERM_N(NI_COUNTER_NAMES_BASE, NI_MAX_COUNTERS, x) +/* Gate, Aux, A,B,Z are all treated, at times as gates */ +#define NI_GATES_NAMES_BASE (NI_CtrSource(-1) + 1) +#define NI_CtrGate(x) _TERM_N(NI_GATES_NAMES_BASE, NI_MAX_COUNTERS, x) +#define NI_CtrAux(x) _TERM_N(NI_CtrGate(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrA(x) _TERM_N(NI_CtrAux(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrB(x) _TERM_N(NI_CtrA(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrZ(x) _TERM_N(NI_CtrB(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_GATES_NAMES_MAX NI_CtrZ(-1) +#define NI_CtrArmStartTrigger(x) _TERM_N(NI_CtrZ(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrInternalOutput(x) \ + _TERM_N(NI_CtrArmStartTrigger(-1) + 1, NI_MAX_COUNTERS, x) +/** external pin(s) labeled conveniently as CtrOut. */ +#define NI_CtrOut(x) _TERM_N(NI_CtrInternalOutput(-1) + 1, NI_MAX_COUNTERS, x) +/** For Buffered sampling of ctr -- x series capability. */ +#define NI_CtrSampleClock(x) _TERM_N(NI_CtrOut(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_COUNTER_NAMES_MAX NI_CtrSampleClock(-1) + +enum ni_common_signal_names { + /* PXI_Star: this is a non-NI-specific signal */ + PXI_Star = NI_COUNTER_NAMES_MAX + 1, + PXI_Clk10, + PXIe_Clk100, + NI_AI_SampleClock, + NI_AI_SampleClockTimebase, + NI_AI_StartTrigger, + NI_AI_ReferenceTrigger, + NI_AI_ConvertClock, + NI_AI_ConvertClockTimebase, + NI_AI_PauseTrigger, + NI_AI_HoldCompleteEvent, + NI_AI_HoldComplete, + NI_AI_ExternalMUXClock, + NI_AI_STOP, /* pulse signal that occurs when a update is finished(?) */ + NI_AO_SampleClock, + NI_AO_SampleClockTimebase, + NI_AO_StartTrigger, + NI_AO_PauseTrigger, + NI_DI_SampleClock, + NI_DI_SampleClockTimebase, + NI_DI_StartTrigger, + NI_DI_ReferenceTrigger, + NI_DI_PauseTrigger, + NI_DI_InputBufferFull, + NI_DI_ReadyForStartEvent, + NI_DI_ReadyForTransferEventBurst, + NI_DI_ReadyForTransferEventPipelined, + NI_DO_SampleClock, + NI_DO_SampleClockTimebase, + NI_DO_StartTrigger, + NI_DO_PauseTrigger, + NI_DO_OutputBufferFull, + NI_DO_DataActiveEvent, + NI_DO_ReadyForStartEvent, + NI_DO_ReadyForTransferEvent, + NI_MasterTimebase, + NI_20MHzTimebase, + NI_80MHzTimebase, + NI_100MHzTimebase, + NI_200MHzTimebase, + NI_100kHzTimebase, + NI_10MHzRefClock, + NI_FrequencyOutput, + NI_ChangeDetectionEvent, + NI_AnalogComparisonEvent, + NI_WatchdogExpiredEvent, + NI_WatchdogExpirationTrigger, + NI_SCXI_Trig1, + NI_LogicLow, + NI_LogicHigh, + NI_ExternalStrobe, + NI_PFI_DO, + NI_CaseGround, + /* special internal signal used as variable source for RTSI bus: */ + NI_RGOUT0, + + /* just a name to make the next more convenient, regardless of above */ + _NI_NAMES_MAX_PLUS_1, + NI_NUM_NAMES = _NI_NAMES_MAX_PLUS_1 - NI_NAMES_BASE, +}; + +/* *** END GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ + +#define NI_USUAL_PFI_SELECT(x) (((x) < 10) ? (0x1 + (x)) : (0xb + (x))) +#define NI_USUAL_RTSI_SELECT(x) (((x) < 7) ? (0xb + (x)) : 0x1b) + +/* + * mode bits for NI general-purpose counters, set with + * INSN_CONFIG_SET_COUNTER_MODE + */ +#define NI_GPCT_COUNTING_MODE_SHIFT 16 +#define NI_GPCT_INDEX_PHASE_BITSHIFT 20 +#define NI_GPCT_COUNTING_DIRECTION_SHIFT 24 +enum ni_gpct_mode_bits { + NI_GPCT_GATE_ON_BOTH_EDGES_BIT = 0x4, + NI_GPCT_EDGE_GATE_MODE_MASK = 0x18, + NI_GPCT_EDGE_GATE_STARTS_STOPS_BITS = 0x0, + NI_GPCT_EDGE_GATE_STOPS_STARTS_BITS = 0x8, + NI_GPCT_EDGE_GATE_STARTS_BITS = 0x10, + NI_GPCT_EDGE_GATE_NO_STARTS_NO_STOPS_BITS = 0x18, + NI_GPCT_STOP_MODE_MASK = 0x60, + NI_GPCT_STOP_ON_GATE_BITS = 0x00, + NI_GPCT_STOP_ON_GATE_OR_TC_BITS = 0x20, + NI_GPCT_STOP_ON_GATE_OR_SECOND_TC_BITS = 0x40, + NI_GPCT_LOAD_B_SELECT_BIT = 0x80, + NI_GPCT_OUTPUT_MODE_MASK = 0x300, + NI_GPCT_OUTPUT_TC_PULSE_BITS = 0x100, + NI_GPCT_OUTPUT_TC_TOGGLE_BITS = 0x200, + NI_GPCT_OUTPUT_TC_OR_GATE_TOGGLE_BITS = 0x300, + NI_GPCT_HARDWARE_DISARM_MASK = 0xc00, + NI_GPCT_NO_HARDWARE_DISARM_BITS = 0x000, + NI_GPCT_DISARM_AT_TC_BITS = 0x400, + NI_GPCT_DISARM_AT_GATE_BITS = 0x800, + NI_GPCT_DISARM_AT_TC_OR_GATE_BITS = 0xc00, + NI_GPCT_LOADING_ON_TC_BIT = 0x1000, + NI_GPCT_LOADING_ON_GATE_BIT = 0x4000, + NI_GPCT_COUNTING_MODE_MASK = 0x7 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_NORMAL_BITS = + 0x0 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_QUADRATURE_X1_BITS = + 0x1 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_QUADRATURE_X2_BITS = + 0x2 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_QUADRATURE_X4_BITS = + 0x3 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_TWO_PULSE_BITS = + 0x4 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_SYNC_SOURCE_BITS = + 0x6 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_INDEX_PHASE_MASK = 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_LOW_A_LOW_B_BITS = + 0x0 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_LOW_A_HIGH_B_BITS = + 0x1 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_HIGH_A_LOW_B_BITS = + 0x2 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_HIGH_A_HIGH_B_BITS = + 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_ENABLE_BIT = 0x400000, + NI_GPCT_COUNTING_DIRECTION_MASK = + 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_DOWN_BITS = + 0x00 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_UP_BITS = + 0x1 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_HW_UP_DOWN_BITS = + 0x2 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_HW_GATE_BITS = + 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_RELOAD_SOURCE_MASK = 0xc000000, + NI_GPCT_RELOAD_SOURCE_FIXED_BITS = 0x0, + NI_GPCT_RELOAD_SOURCE_SWITCHING_BITS = 0x4000000, + NI_GPCT_RELOAD_SOURCE_GATE_SELECT_BITS = 0x8000000, + NI_GPCT_OR_GATE_BIT = 0x10000000, + NI_GPCT_INVERT_OUTPUT_BIT = 0x20000000 +}; + +/* + * Bits for setting a clock source with + * INSN_CONFIG_SET_CLOCK_SRC when using NI general-purpose counters. + */ +enum ni_gpct_clock_source_bits { + NI_GPCT_CLOCK_SRC_SELECT_MASK = 0x3f, + NI_GPCT_TIMEBASE_1_CLOCK_SRC_BITS = 0x0, + NI_GPCT_TIMEBASE_2_CLOCK_SRC_BITS = 0x1, + NI_GPCT_TIMEBASE_3_CLOCK_SRC_BITS = 0x2, + NI_GPCT_LOGIC_LOW_CLOCK_SRC_BITS = 0x3, + NI_GPCT_NEXT_GATE_CLOCK_SRC_BITS = 0x4, + NI_GPCT_NEXT_TC_CLOCK_SRC_BITS = 0x5, + /* NI 660x-specific */ + NI_GPCT_SOURCE_PIN_i_CLOCK_SRC_BITS = 0x6, + NI_GPCT_PXI10_CLOCK_SRC_BITS = 0x7, + NI_GPCT_PXI_STAR_TRIGGER_CLOCK_SRC_BITS = 0x8, + NI_GPCT_ANALOG_TRIGGER_OUT_CLOCK_SRC_BITS = 0x9, + NI_GPCT_PRESCALE_MODE_CLOCK_SRC_MASK = 0x30000000, + NI_GPCT_NO_PRESCALE_CLOCK_SRC_BITS = 0x0, + /* divide source by 2 */ + NI_GPCT_PRESCALE_X2_CLOCK_SRC_BITS = 0x10000000, + /* divide source by 8 */ + NI_GPCT_PRESCALE_X8_CLOCK_SRC_BITS = 0x20000000, + NI_GPCT_INVERT_CLOCK_SRC_BIT = 0x80000000 +}; + +/* NI 660x-specific */ +#define NI_GPCT_SOURCE_PIN_CLOCK_SRC_BITS(x) (0x10 + (x)) + +#define NI_GPCT_RTSI_CLOCK_SRC_BITS(x) (0x18 + (x)) + +/* no pfi on NI 660x */ +#define NI_GPCT_PFI_CLOCK_SRC_BITS(x) (0x20 + (x)) + +/* + * Possibilities for setting a gate source with + * INSN_CONFIG_SET_GATE_SRC when using NI general-purpose counters. + * May be bitwise-or'd with CR_EDGE or CR_INVERT. + */ +enum ni_gpct_gate_select { + /* m-series gates */ + NI_GPCT_TIMESTAMP_MUX_GATE_SELECT = 0x0, + NI_GPCT_AI_START2_GATE_SELECT = 0x12, + NI_GPCT_PXI_STAR_TRIGGER_GATE_SELECT = 0x13, + NI_GPCT_NEXT_OUT_GATE_SELECT = 0x14, + NI_GPCT_AI_START1_GATE_SELECT = 0x1c, + NI_GPCT_NEXT_SOURCE_GATE_SELECT = 0x1d, + NI_GPCT_ANALOG_TRIGGER_OUT_GATE_SELECT = 0x1e, + NI_GPCT_LOGIC_LOW_GATE_SELECT = 0x1f, + /* more gates for 660x */ + NI_GPCT_SOURCE_PIN_i_GATE_SELECT = 0x100, + NI_GPCT_GATE_PIN_i_GATE_SELECT = 0x101, + /* more gates for 660x "second gate" */ + NI_GPCT_UP_DOWN_PIN_i_GATE_SELECT = 0x201, + NI_GPCT_SELECTED_GATE_GATE_SELECT = 0x21e, + /* + * m-series "second gate" sources are unknown, + * we should add them here with an offset of 0x300 when + * known. + */ + NI_GPCT_DISABLED_GATE_SELECT = 0x8000, +}; + +#define NI_GPCT_GATE_PIN_GATE_SELECT(x) (0x102 + (x)) +#define NI_GPCT_RTSI_GATE_SELECT(x) NI_USUAL_RTSI_SELECT(x) +#define NI_GPCT_PFI_GATE_SELECT(x) NI_USUAL_PFI_SELECT(x) +#define NI_GPCT_UP_DOWN_PIN_GATE_SELECT(x) (0x202 + (x)) + +/* + * Possibilities for setting a source with + * INSN_CONFIG_SET_OTHER_SRC when using NI general-purpose counters. + */ +enum ni_gpct_other_index { + NI_GPCT_SOURCE_ENCODER_A, + NI_GPCT_SOURCE_ENCODER_B, + NI_GPCT_SOURCE_ENCODER_Z +}; + +enum ni_gpct_other_select { + /* m-series gates */ + /* Still unknown, probably only need NI_GPCT_PFI_OTHER_SELECT */ + NI_GPCT_DISABLED_OTHER_SELECT = 0x8000, +}; + +#define NI_GPCT_PFI_OTHER_SELECT(x) NI_USUAL_PFI_SELECT(x) + +/* + * start sources for ni general-purpose counters for use with + * INSN_CONFIG_ARM + */ +enum ni_gpct_arm_source { + NI_GPCT_ARM_IMMEDIATE = 0x0, + /* + * Start both the counter and the adjacent paired counter simultaneously + */ + NI_GPCT_ARM_PAIRED_IMMEDIATE = 0x1, + /* + * If the NI_GPCT_HW_ARM bit is set, we will pass the least significant + * bits (3 bits for 660x or 5 bits for m-series) through to the + * hardware. To select a hardware trigger, pass the appropriate select + * bit, e.g., + * NI_GPCT_HW_ARM | NI_GPCT_AI_START1_GATE_SELECT or + * NI_GPCT_HW_ARM | NI_GPCT_PFI_GATE_SELECT(pfi_number) + */ + NI_GPCT_HW_ARM = 0x1000, + NI_GPCT_ARM_UNKNOWN = NI_GPCT_HW_ARM, /* for backward compatibility */ +}; + +/* digital filtering options for ni 660x for use with INSN_CONFIG_FILTER. */ +enum ni_gpct_filter_select { + NI_GPCT_FILTER_OFF = 0x0, + NI_GPCT_FILTER_TIMEBASE_3_SYNC = 0x1, + NI_GPCT_FILTER_100x_TIMEBASE_1 = 0x2, + NI_GPCT_FILTER_20x_TIMEBASE_1 = 0x3, + NI_GPCT_FILTER_10x_TIMEBASE_1 = 0x4, + NI_GPCT_FILTER_2x_TIMEBASE_1 = 0x5, + NI_GPCT_FILTER_2x_TIMEBASE_3 = 0x6 +}; + +/* + * PFI digital filtering options for ni m-series for use with + * INSN_CONFIG_FILTER. + */ +enum ni_pfi_filter_select { + NI_PFI_FILTER_OFF = 0x0, + NI_PFI_FILTER_125ns = 0x1, + NI_PFI_FILTER_6425ns = 0x2, + NI_PFI_FILTER_2550us = 0x3 +}; + +/* master clock sources for ni mio boards and INSN_CONFIG_SET_CLOCK_SRC */ +enum ni_mio_clock_source { + NI_MIO_INTERNAL_CLOCK = 0, + /* + * Doesn't work for m-series, use NI_MIO_PLL_RTSI_CLOCK() + * the NI_MIO_PLL_* sources are m-series only + */ + NI_MIO_RTSI_CLOCK = 1, + NI_MIO_PLL_PXI_STAR_TRIGGER_CLOCK = 2, + NI_MIO_PLL_PXI10_CLOCK = 3, + NI_MIO_PLL_RTSI0_CLOCK = 4 +}; + +#define NI_MIO_PLL_RTSI_CLOCK(x) (NI_MIO_PLL_RTSI0_CLOCK + (x)) + +/* + * Signals which can be routed to an NI RTSI pin with INSN_CONFIG_SET_ROUTING. + * The numbers assigned are not arbitrary, they correspond to the bits required + * to program the board. + */ +enum ni_rtsi_routing { + NI_RTSI_OUTPUT_ADR_START1 = 0, + NI_RTSI_OUTPUT_ADR_START2 = 1, + NI_RTSI_OUTPUT_SCLKG = 2, + NI_RTSI_OUTPUT_DACUPDN = 3, + NI_RTSI_OUTPUT_DA_START1 = 4, + NI_RTSI_OUTPUT_G_SRC0 = 5, + NI_RTSI_OUTPUT_G_GATE0 = 6, + NI_RTSI_OUTPUT_RGOUT0 = 7, + NI_RTSI_OUTPUT_RTSI_BRD_0 = 8, + /* Pre-m-series always have RTSI clock on line 7 */ + NI_RTSI_OUTPUT_RTSI_OSC = 12 +}; + +#define NI_RTSI_OUTPUT_RTSI_BRD(x) (NI_RTSI_OUTPUT_RTSI_BRD_0 + (x)) + +/* + * Signals which can be routed to an NI PFI pin on an m-series board with + * INSN_CONFIG_SET_ROUTING. These numbers are also returned by + * INSN_CONFIG_GET_ROUTING on pre-m-series boards, even though their routing + * cannot be changed. The numbers assigned are not arbitrary, they correspond + * to the bits required to program the board. + */ +enum ni_pfi_routing { + NI_PFI_OUTPUT_PFI_DEFAULT = 0, + NI_PFI_OUTPUT_AI_START1 = 1, + NI_PFI_OUTPUT_AI_START2 = 2, + NI_PFI_OUTPUT_AI_CONVERT = 3, + NI_PFI_OUTPUT_G_SRC1 = 4, + NI_PFI_OUTPUT_G_GATE1 = 5, + NI_PFI_OUTPUT_AO_UPDATE_N = 6, + NI_PFI_OUTPUT_AO_START1 = 7, + NI_PFI_OUTPUT_AI_START_PULSE = 8, + NI_PFI_OUTPUT_G_SRC0 = 9, + NI_PFI_OUTPUT_G_GATE0 = 10, + NI_PFI_OUTPUT_EXT_STROBE = 11, + NI_PFI_OUTPUT_AI_EXT_MUX_CLK = 12, + NI_PFI_OUTPUT_GOUT0 = 13, + NI_PFI_OUTPUT_GOUT1 = 14, + NI_PFI_OUTPUT_FREQ_OUT = 15, + NI_PFI_OUTPUT_PFI_DO = 16, + NI_PFI_OUTPUT_I_ATRIG = 17, + NI_PFI_OUTPUT_RTSI0 = 18, + NI_PFI_OUTPUT_PXI_STAR_TRIGGER_IN = 26, + NI_PFI_OUTPUT_SCXI_TRIG1 = 27, + NI_PFI_OUTPUT_DIO_CHANGE_DETECT_RTSI = 28, + NI_PFI_OUTPUT_CDI_SAMPLE = 29, + NI_PFI_OUTPUT_CDO_UPDATE = 30 +}; + +#define NI_PFI_OUTPUT_RTSI(x) (NI_PFI_OUTPUT_RTSI0 + (x)) + +/* + * Signals which can be routed to output on a NI PFI pin on a 660x board + * with INSN_CONFIG_SET_ROUTING. The numbers assigned are + * not arbitrary, they correspond to the bits required + * to program the board. Lines 0 to 7 can only be set to + * NI_660X_PFI_OUTPUT_DIO. Lines 32 to 39 can only be set to + * NI_660X_PFI_OUTPUT_COUNTER. + */ +enum ni_660x_pfi_routing { + NI_660X_PFI_OUTPUT_COUNTER = 1, /* counter */ + NI_660X_PFI_OUTPUT_DIO = 2, /* static digital output */ +}; + +/* + * NI External Trigger lines. These values are not arbitrary, but are related + * to the bits required to program the board (offset by 1 for historical + * reasons). + */ +#define NI_EXT_PFI(x) (NI_USUAL_PFI_SELECT(x) - 1) +#define NI_EXT_RTSI(x) (NI_USUAL_RTSI_SELECT(x) - 1) + +/* + * Clock sources for CDIO subdevice on NI m-series boards. Used as the + * scan_begin_arg for a comedi_command. These sources may also be bitwise-or'd + * with CR_INVERT to change polarity. + */ +enum ni_m_series_cdio_scan_begin_src { + NI_CDIO_SCAN_BEGIN_SRC_GROUND = 0, + NI_CDIO_SCAN_BEGIN_SRC_AI_START = 18, + NI_CDIO_SCAN_BEGIN_SRC_AI_CONVERT = 19, + NI_CDIO_SCAN_BEGIN_SRC_PXI_STAR_TRIGGER = 20, + NI_CDIO_SCAN_BEGIN_SRC_G0_OUT = 28, + NI_CDIO_SCAN_BEGIN_SRC_G1_OUT = 29, + NI_CDIO_SCAN_BEGIN_SRC_ANALOG_TRIGGER = 30, + NI_CDIO_SCAN_BEGIN_SRC_AO_UPDATE = 31, + NI_CDIO_SCAN_BEGIN_SRC_FREQ_OUT = 32, + NI_CDIO_SCAN_BEGIN_SRC_DIO_CHANGE_DETECT_IRQ = 33 +}; + +#define NI_CDIO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) +#define NI_CDIO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) + +/* + * scan_begin_src for scan_begin_arg==TRIG_EXT with analog output command on NI + * boards. These scan begin sources can also be bitwise-or'd with CR_INVERT to + * change polarity. + */ +#define NI_AO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) +#define NI_AO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) + +/* + * Bits for setting a clock source with + * INSN_CONFIG_SET_CLOCK_SRC when using NI frequency output subdevice. + */ +enum ni_freq_out_clock_source_bits { + NI_FREQ_OUT_TIMEBASE_1_DIV_2_CLOCK_SRC, /* 10 MHz */ + NI_FREQ_OUT_TIMEBASE_2_CLOCK_SRC /* 100 KHz */ +}; + +/* + * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for + * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). + */ +enum amplc_dio_clock_source { + /* + * Per channel external clock + * input/output pin (pin is only an + * input when clock source set to this value, + * otherwise it is an output) + */ + AMPLC_DIO_CLK_CLKN, + AMPLC_DIO_CLK_10MHZ, /* 10 MHz internal clock */ + AMPLC_DIO_CLK_1MHZ, /* 1 MHz internal clock */ + AMPLC_DIO_CLK_100KHZ, /* 100 kHz internal clock */ + AMPLC_DIO_CLK_10KHZ, /* 10 kHz internal clock */ + AMPLC_DIO_CLK_1KHZ, /* 1 kHz internal clock */ + /* + * Output of preceding counter channel + * (for channel 0, preceding counter + * channel is channel 2 on preceding + * counter subdevice, for first counter + * subdevice, preceding counter + * subdevice is the last counter + * subdevice) + */ + AMPLC_DIO_CLK_OUTNM1, + AMPLC_DIO_CLK_EXT, /* per chip external input pin */ + /* the following are "enhanced" clock sources for PCIe models */ + AMPLC_DIO_CLK_VCC, /* clock input HIGH */ + AMPLC_DIO_CLK_GND, /* clock input LOW */ + AMPLC_DIO_CLK_PAT_PRESENT, /* "pattern present" signal */ + AMPLC_DIO_CLK_20MHZ /* 20 MHz internal clock */ +}; + +/* + * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for + * timer subdevice on some Amplicon DIO PCIe boards (amplc_dio200 driver). + */ +enum amplc_dio_ts_clock_src { + AMPLC_DIO_TS_CLK_1GHZ, /* 1 ns period with 20 ns granularity */ + AMPLC_DIO_TS_CLK_1MHZ, /* 1 us period */ + AMPLC_DIO_TS_CLK_1KHZ /* 1 ms period */ +}; + +/* + * Values for setting a gate source with INSN_CONFIG_SET_GATE_SRC for + * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). + */ +enum amplc_dio_gate_source { + AMPLC_DIO_GAT_VCC, /* internal high logic level */ + AMPLC_DIO_GAT_GND, /* internal low logic level */ + AMPLC_DIO_GAT_GATN, /* per channel external gate input */ + /* + * negated output of counter channel minus 2 + * (for channels 0 or 1, channel minus 2 is channel 1 or 2 on + * the preceding counter subdevice, for the first counter subdevice + * the preceding counter subdevice is the last counter subdevice) + */ + AMPLC_DIO_GAT_NOUTNM2, + AMPLC_DIO_GAT_RESERVED4, + AMPLC_DIO_GAT_RESERVED5, + AMPLC_DIO_GAT_RESERVED6, + AMPLC_DIO_GAT_RESERVED7, + /* the following are "enhanced" gate sources for PCIe models */ + AMPLC_DIO_GAT_NGATN = 6, /* negated per channel gate input */ + /* non-negated output of counter channel minus 2 */ + AMPLC_DIO_GAT_OUTNM2, + AMPLC_DIO_GAT_PAT_PRESENT, /* "pattern present" signal */ + AMPLC_DIO_GAT_PAT_OCCURRED, /* "pattern occurred" latched */ + AMPLC_DIO_GAT_PAT_GONE, /* "pattern gone away" latched */ + AMPLC_DIO_GAT_NPAT_PRESENT, /* negated "pattern present" */ + AMPLC_DIO_GAT_NPAT_OCCURRED, /* negated "pattern occurred" */ + AMPLC_DIO_GAT_NPAT_GONE /* negated "pattern gone away" */ +}; + +/* + * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for + * the counter subdevice on the Kolter Electronic PCI-Counter board + * (ke_counter driver). + */ +enum ke_counter_clock_source { + KE_CLK_20MHZ, /* internal 20MHz (default) */ + KE_CLK_4MHZ, /* internal 4MHz (option) */ + KE_CLK_EXT /* external clock on pin 21 of D-Sub */ +}; + +#endif /* _COMEDI_H */ -- cgit v1.2.3 From 7e78781df491e4beb475bac22e6c44236a5002d7 Mon Sep 17 00:00:00 2001 From: Gurchetan Singh Date: Mon, 22 Nov 2021 15:22:09 -0800 Subject: drm/virtgpu api: define a dummy fence signaled event The current virtgpu implementation of poll(..) drops events when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is enabled (otherwise it's like a normal DRM driver). This is because paravirtualized userspaces receives responses in a buffer of type BLOB_MEM_GUEST, not by read(..). To be in line with other DRM drivers and avoid specialized behavior, it is possible to define a dummy event for virtgpu. Paravirtualized userspace will now have to call read(..) on the DRM fd to receive the dummy event. Fixes: b10790434cf2 ("drm/virtgpu api: create context init feature") Reported-by: Daniel Vetter Signed-off-by: Gurchetan Singh Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20211122232210.602-2-gurchetansingh@google.com Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/virtgpu_drv.h | 1 - drivers/gpu/drm/virtio/virtgpu_ioctl.c | 2 +- include/uapi/drm/virtgpu_drm.h | 7 +++++++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index e0265fe74aa5..0a194aaad419 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -138,7 +138,6 @@ struct virtio_gpu_fence_driver { spinlock_t lock; }; -#define VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL 0x10000000 struct virtio_gpu_fence_event { struct drm_pending_event base; struct drm_event event; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 5618a1d5879c..3607646d3229 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -54,7 +54,7 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev, if (!e) return -ENOMEM; - e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL; + e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED; e->event.length = sizeof(e->event); ret = drm_event_reserve_init(dev, file, &e->base, &e->event); diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index a13e20cc66b4..0512fde5e697 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -196,6 +196,13 @@ struct drm_virtgpu_context_init { __u64 ctx_set_params; }; +/* + * Event code that's given when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is in + * effect. The event size is sizeof(drm_event), since there is no additional + * payload. + */ +#define VIRTGPU_EVENT_FENCE_SIGNALED 0x90000000 + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) -- cgit v1.2.3 From aeeecb889165617a841e939117f9a8095d0e7d80 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 28 Nov 2021 14:01:02 +0800 Subject: net: snmp: add statistics for tcp small queue check Once tcp small queue check failed in tcp_small_queue_check(), the throughput of tcp will be limited, and it's hard to distinguish whether it is out of tcp congestion control. Add statistics of LINUX_MIB_TCPSMALLQUEUEFAILURE for this scene. Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp_output.c | 5 ++++- 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 904909d020e2..e32ec6932e82 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -292,6 +292,7 @@ enum LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ + LINUX_MIB_TCPSMALLQUEUEFAILURE, /* TCPSmallQueueFailure */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f30273afb539..43b7a77cd6b4 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), + SNMP_MIB_ITEM("TCPSmallQueueFailure", LINUX_MIB_TCPSMALLQUEUEFAILURE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5079832af5c1..c4ab6c8f0c77 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2524,8 +2524,11 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, * test again the condition. */ smp_mb__after_atomic(); - if (refcount_read(&sk->sk_wmem_alloc) > limit) + if (refcount_read(&sk->sk_wmem_alloc) > limit) { + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSMALLQUEUEFAILURE); return true; + } } return false; } -- cgit v1.2.3 From 5944b5abd8646e8c6ac6af2b55f87dede1dae898 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 30 Nov 2021 12:29:47 +0800 Subject: Bonding: add arp_missed_max option Currently, we use hard code number to verify if we are in the arp_interval timeslice. But some user may want to reduce/extend the verify timeslice. With the similar team option 'missed_max' the uers could change that number based on their own environment. Acked-by: Jay Vosburgh Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- Documentation/networking/bonding.rst | 11 +++++++++++ drivers/net/bonding/bond_main.c | 17 +++++++++-------- drivers/net/bonding/bond_netlink.c | 15 +++++++++++++++ drivers/net/bonding/bond_options.c | 28 ++++++++++++++++++++++++++++ drivers/net/bonding/bond_procfs.c | 2 ++ drivers/net/bonding/bond_sysfs.c | 13 +++++++++++++ include/net/bond_options.h | 1 + include/net/bonding.h | 1 + include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 10 files changed, 82 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 31cfd7d674a6..e5a07cb48f68 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -421,6 +421,17 @@ arp_all_targets consider the slave up only when all of the arp_ip_targets are reachable +arp_missed_max + + Specifies the number of arp_interval monitor checks that must + fail in order for an interface to be marked down by the ARP monitor. + + In order to provide orderly failover semantics, backup interfaces + are permitted an extra monitor check (i.e., they must fail + arp_missed_max + 1 times before being marked down). + + The default value is 2, and the allowable range is 1 - 255. + downdelay Specifies the time, in milliseconds, to wait before disabling diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index cf73eacdda91..f3aa49b97f81 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3129,8 +3129,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (!bond_time_in_interval(bond, trans_start, 2) || - !bond_time_in_interval(bond, slave->last_rx, 2)) { + if (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) || + !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) { bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; @@ -3224,7 +3224,7 @@ static int bond_ab_arp_inspect(struct bonding *bond) /* Backup slave is down if: * - No current_arp_slave AND - * - more than 3*delta since last receive AND + * - more than (missed_max+1)*delta since last receive AND * - the bond has an IP address * * Note: a non-null current_arp_slave indicates @@ -3236,20 +3236,20 @@ static int bond_ab_arp_inspect(struct bonding *bond) */ if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && - !bond_time_in_interval(bond, last_rx, 3)) { + !bond_time_in_interval(bond, last_rx, bond->params.missed_max + 1)) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } /* Active slave is down if: - * - more than 2*delta since transmitting OR - * - (more than 2*delta since receive AND + * - more than missed_max*delta since transmitting OR + * - (more than missed_max*delta since receive AND * the bond has an IP address) */ trans_start = dev_trans_start(slave->dev); if (bond_is_active_slave(slave) && - (!bond_time_in_interval(bond, trans_start, 2) || - !bond_time_in_interval(bond, last_rx, 2))) { + (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) || + !bond_time_in_interval(bond, last_rx, bond->params.missed_max))) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } @@ -5822,6 +5822,7 @@ static int bond_check_params(struct bond_params *params) params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->arp_all_targets = arp_all_targets_value; + params->missed_max = 2; params->updelay = updelay; params->downdelay = downdelay; params->peer_notif_delay = 0; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 5d54e11d18fa..1007bf6d385d 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -110,6 +110,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 }, + [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { @@ -453,6 +454,15 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return err; } + if (data[IFLA_BOND_MISSED_MAX]) { + int missed_max = nla_get_u8(data[IFLA_BOND_MISSED_MAX]); + + bond_opt_initval(&newval, missed_max); + err = __bond_opt_set(bond, BOND_OPT_MISSED_MAX, &newval); + if (err) + return err; + } + return 0; } @@ -515,6 +525,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_ACTOR_SYSTEM */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PEER_NOTIF_DELAY */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_MISSED_MAX */ 0; } @@ -650,6 +661,10 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.tlb_dynamic_lb)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_MISSED_MAX, + bond->params.missed_max)) + goto nla_put_failure; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index a8fde3bc458f..0f48921c4f15 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -78,6 +78,8 @@ static int bond_option_ad_actor_system_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_ad_user_port_key_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_missed_max_set(struct bonding *bond, + const struct bond_opt_value *newval); static const struct bond_opt_value bond_mode_tbl[] = { @@ -213,6 +215,13 @@ static const struct bond_opt_value bond_ad_user_port_key_tbl[] = { { NULL, -1, 0}, }; +static const struct bond_opt_value bond_missed_max_tbl[] = { + { "minval", 1, BOND_VALFLAG_MIN}, + { "maxval", 255, BOND_VALFLAG_MAX}, + { "default", 2, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0}, +}; + static const struct bond_option bond_opts[BOND_OPT_LAST] = { [BOND_OPT_MODE] = { .id = BOND_OPT_MODE, @@ -270,6 +279,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .values = bond_intmax_tbl, .set = bond_option_arp_interval_set }, + [BOND_OPT_MISSED_MAX] = { + .id = BOND_OPT_MISSED_MAX, + .name = "arp_missed_max", + .desc = "Maximum number of missed ARP interval", + .unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB), + .values = bond_missed_max_tbl, + .set = bond_option_missed_max_set + }, [BOND_OPT_ARP_TARGETS] = { .id = BOND_OPT_ARP_TARGETS, .name = "arp_ip_target", @@ -1186,6 +1204,16 @@ static int bond_option_arp_all_targets_set(struct bonding *bond, return 0; } +static int bond_option_missed_max_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + netdev_dbg(bond->dev, "Setting missed max to %s (%llu)\n", + newval->string, newval->value); + bond->params.missed_max = newval->value; + + return 0; +} + static int bond_option_primary_set(struct bonding *bond, const struct bond_opt_value *newval) { diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index f3e3bfd72556..2ec11af5f0cc 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -115,6 +115,8 @@ static void bond_info_show_master(struct seq_file *seq) seq_printf(seq, "ARP Polling Interval (ms): %d\n", bond->params.arp_interval); + seq_printf(seq, "ARP Missed Max: %u\n", + bond->params.missed_max); seq_printf(seq, "ARP IP target/s (n.n.n.n form):"); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index c48b77167fab..9b5a5df23d21 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -303,6 +303,18 @@ static ssize_t bonding_show_arp_targets(struct device *d, static DEVICE_ATTR(arp_ip_target, 0644, bonding_show_arp_targets, bonding_sysfs_store_option); +/* Show the arp missed max. */ +static ssize_t bonding_show_missed_max(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%u\n", bond->params.missed_max); +} +static DEVICE_ATTR(arp_missed_max, 0644, + bonding_show_missed_max, bonding_sysfs_store_option); + /* Show the up and down delays. */ static ssize_t bonding_show_downdelay(struct device *d, struct device_attribute *attr, @@ -779,6 +791,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_ad_actor_sys_prio.attr, &dev_attr_ad_actor_system.attr, &dev_attr_ad_user_port_key.attr, + &dev_attr_arp_missed_max.attr, NULL, }; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index e64833a674eb..dd75c071f67e 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -65,6 +65,7 @@ enum { BOND_OPT_NUM_PEER_NOTIF_ALIAS, BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LACP_ACTIVE, + BOND_OPT_MISSED_MAX, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 15e083e18f75..f6ae3a4baea4 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -121,6 +121,7 @@ struct bond_params { int xmit_policy; int miimon; u8 num_peer_notif; + u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eebd3894fe89..4ac53b30b6dc 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -858,6 +858,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index eebd3894fe89..4ac53b30b6dc 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -858,6 +858,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, }; -- cgit v1.2.3 From e6f2dd0f80674e9d5960337b3e9c2a242441b326 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 29 Nov 2021 19:06:19 -0800 Subject: bpf: Add bpf_loop helper This patch adds the kernel-side and API changes for a new helper function, bpf_loop: long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags); where long (*callback_fn)(u32 index, void *ctx); bpf_loop invokes the "callback_fn" **nr_loops** times or until the callback_fn returns 1. The callback_fn can only return 0 or 1, and this is enforced by the verifier. The callback_fn index is zero-indexed. A few things to please note: ~ The "u64 flags" parameter is currently unused but is included in case a future use case for it arises. ~ In the kernel-side implementation of bpf_loop (kernel/bpf/bpf_iter.c), bpf_callback_t is used as the callback function cast. ~ A program can have nested bpf_loop calls but the program must still adhere to the verifier constraint of its stack depth (the stack depth cannot exceed MAX_BPF_STACK)) ~ Recursive callback_fns do not pass the verifier, due to the call stack for these being too deep. ~ The next patch will include the tests and benchmark Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211130030622.4131246-2-joannekoong@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 25 ++++++++++++ kernel/bpf/bpf_iter.c | 35 +++++++++++++++++ kernel/bpf/helpers.c | 2 + kernel/bpf/verifier.c | 88 ++++++++++++++++++++++++++---------------- tools/include/uapi/linux/bpf.h | 25 ++++++++++++ 6 files changed, 142 insertions(+), 34 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cc7a0c36e7df..cad0829710be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2164,6 +2164,7 @@ extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; +extern const struct bpf_func_proto bpf_loop_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a69e4b04ffeb..211b43afd0fb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4957,6 +4957,30 @@ union bpf_attr { * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. * **-EBUSY** if failed to try lock mmap_lock. * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5140,6 +5164,7 @@ union bpf_attr { FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ FN(find_vma), \ + FN(loop), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b2ee45064e06..b7aef5b3416d 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -714,3 +714,38 @@ const struct bpf_func_proto bpf_for_each_map_elem_proto = { .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; + +/* maximum number of loops */ +#define MAX_LOOPS BIT(23) + +BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, + u64, flags) +{ + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 ret; + u32 i; + + if (flags) + return -EINVAL; + if (nr_loops > MAX_LOOPS) + return -E2BIG; + + for (i = 0; i < nr_loops; i++) { + ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) + return i + 1; + } + + return i; +} + +const struct bpf_func_proto bpf_loop_proto = { + .func = bpf_loop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..52188004a9c3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1378,6 +1378,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_query_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; + case BPF_FUNC_loop: + return &bpf_loop_proto; default: break; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0763cca139a7..d7678d8a925c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6085,6 +6085,27 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_loop_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, + * u64 flags); + * callback_fn(u32 index, void *callback_ctx); + */ + callee->regs[BPF_REG_1].type = SCALAR_VALUE; + callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + + callee->in_callback_fn = true; + return 0; +} + static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -6458,13 +6479,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return err; } - if (func_id == BPF_FUNC_tail_call) { - err = check_reference_leak(env); - if (err) { - verbose(env, "tail_call would lead to reference leak\n"); - return err; - } - } else if (is_release_function(func_id)) { + if (is_release_function(func_id)) { err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", @@ -6475,42 +6490,47 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); - /* check that flags argument in get_local_storage(map, flags) is 0, - * this is required because get_local_storage() can't return an error. - */ - if (func_id == BPF_FUNC_get_local_storage && - !register_is_null(®s[BPF_REG_2])) { - verbose(env, "get_local_storage() doesn't support non-zero flags\n"); - return -EINVAL; - } - - if (func_id == BPF_FUNC_for_each_map_elem) { + switch (func_id) { + case BPF_FUNC_tail_call: + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + break; + case BPF_FUNC_get_local_storage: + /* check that flags argument in get_local_storage(map, flags) is 0, + * this is required because get_local_storage() can't return an error. + */ + if (!register_is_null(®s[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + break; + case BPF_FUNC_for_each_map_elem: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_map_elem_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_timer_set_callback) { + break; + case BPF_FUNC_timer_set_callback: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_timer_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_find_vma) { + break; + case BPF_FUNC_find_vma: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_find_vma_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_snprintf) { + break; + case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); - if (err < 0) - return err; + break; + case BPF_FUNC_loop: + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_loop_callback_state); + break; } + if (err) + return err; + /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a69e4b04ffeb..211b43afd0fb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4957,6 +4957,30 @@ union bpf_attr { * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. * **-EBUSY** if failed to try lock mmap_lock. * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5140,6 +5164,7 @@ union bpf_attr { FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ FN(find_vma), \ + FN(loop), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From ce8299b6f76f28326fedce2b4da90888bd97eab2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Nov 2021 19:32:46 -0800 Subject: Revert "net: snmp: add statistics for tcp small queue check" This reverts commit aeeecb889165617a841e939117f9a8095d0e7d80. The new SNMP variable (TCPSmallQueueFailure) can be incremented for good reasons, even on a 100Gbit single TCP_STREAM flow. If we really wanted to ease driver debugging [1], this would require something more sophisticated. [1] Usually, if a driver is delaying TX completions too much, this can lead to stalls in TCP output. Various work arounds have been used in the past, like skb_orphan() in ndo_start_xmit(). Signed-off-by: Eric Dumazet Cc: Menglong Dong Link: https://lore.kernel.org/r/20211201033246.2826224-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/snmp.h | 1 - net/ipv4/proc.c | 1 - net/ipv4/tcp_output.c | 5 +---- 3 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index e32ec6932e82..904909d020e2 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -292,7 +292,6 @@ enum LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ - LINUX_MIB_TCPSMALLQUEUEFAILURE, /* TCPSmallQueueFailure */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 43b7a77cd6b4..f30273afb539 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -297,7 +297,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), - SNMP_MIB_ITEM("TCPSmallQueueFailure", LINUX_MIB_TCPSMALLQUEUEFAILURE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c4ab6c8f0c77..5079832af5c1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2524,11 +2524,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, * test again the condition. */ smp_mb__after_atomic(); - if (refcount_read(&sk->sk_wmem_alloc) > limit) { - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPSMALLQUEUEFAILURE); + if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; - } } return false; } -- cgit v1.2.3 From 72f6a45202f20f0e1a46b0acb7803369cc53d0b8 Mon Sep 17 00:00:00 2001 From: Xiayu Zhang Date: Wed, 1 Dec 2021 10:57:13 +0800 Subject: Fix Comment of ETH_P_802_3_MIN The description of ETH_P_802_3_MIN is misleading. The value of EthernetType in Ethernet II frame is more than 0x0600, the value of Length in 802.3 frame is less than 0x0600. Signed-off-by: Xiayu Zhang Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5da4ee234e0b..c0c2f3ed5729 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -117,7 +117,7 @@ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ -#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value +#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is more than this value * then the frame is Ethernet II. Else it is 802.3 */ /* -- cgit v1.2.3 From 46334a0cd21bed70d6f1ddef1464f75a0ebe1774 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Dec 2021 10:10:27 -0800 Subject: bpf: Define enum bpf_core_relo_kind as uapi. enum bpf_core_relo_kind is generated by llvm and processed by libbpf. It's a de-facto uapi. With CO-RE in the kernel the bpf_core_relo_kind values become uapi de-jure. Also rename them with BPF_CORE_ prefix to distinguish from conflicting names in bpf_core_read.h. The enums bpf_field_info_kind, bpf_type_id_kind, bpf_type_info_kind, bpf_enum_value_kind are passing different values from bpf program into llvm. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211201181040.23337-5-alexei.starovoitov@gmail.com --- include/uapi/linux/bpf.h | 19 ++++++++++ tools/include/uapi/linux/bpf.h | 19 ++++++++++ tools/lib/bpf/libbpf.c | 2 +- tools/lib/bpf/relo_core.c | 84 +++++++++++++++++++++--------------------- tools/lib/bpf/relo_core.h | 18 +-------- 5 files changed, 82 insertions(+), 60 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 211b43afd0fb..9e66b1880020 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6374,4 +6374,23 @@ enum { BTF_F_ZERO = (1ULL << 3), }; +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 211b43afd0fb..9e66b1880020 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6374,4 +6374,23 @@ enum { BTF_F_ZERO = (1ULL << 3), }; +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 5a2f5a6ae2f9..9eaf2d9820e6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -5523,7 +5523,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog, return -ENOTSUP; } - if (relo->kind != BPF_TYPE_ID_LOCAL && + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && !hashmap__find(cand_cache, type_key, (void **)&cands)) { cands = bpf_core_find_cands(prog->obj, local_btf, local_id); if (IS_ERR(cands)) { diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 56dbe6d16664..d194fb9306ed 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -113,18 +113,18 @@ static bool is_flex_arr(const struct btf *btf, static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: return "byte_off"; - case BPF_FIELD_BYTE_SIZE: return "byte_sz"; - case BPF_FIELD_EXISTS: return "field_exists"; - case BPF_FIELD_SIGNED: return "signed"; - case BPF_FIELD_LSHIFT_U64: return "lshift_u64"; - case BPF_FIELD_RSHIFT_U64: return "rshift_u64"; - case BPF_TYPE_ID_LOCAL: return "local_type_id"; - case BPF_TYPE_ID_TARGET: return "target_type_id"; - case BPF_TYPE_EXISTS: return "type_exists"; - case BPF_TYPE_SIZE: return "type_size"; - case BPF_ENUMVAL_EXISTS: return "enumval_exists"; - case BPF_ENUMVAL_VALUE: return "enumval_value"; + case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off"; + case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz"; + case BPF_CORE_FIELD_EXISTS: return "field_exists"; + case BPF_CORE_FIELD_SIGNED: return "signed"; + case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64"; + case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64"; + case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id"; + case BPF_CORE_TYPE_ID_TARGET: return "target_type_id"; + case BPF_CORE_TYPE_EXISTS: return "type_exists"; + case BPF_CORE_TYPE_SIZE: return "type_size"; + case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists"; + case BPF_CORE_ENUMVAL_VALUE: return "enumval_value"; default: return "unknown"; } } @@ -132,12 +132,12 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: - case BPF_FIELD_BYTE_SIZE: - case BPF_FIELD_EXISTS: - case BPF_FIELD_SIGNED: - case BPF_FIELD_LSHIFT_U64: - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: return true; default: return false; @@ -147,10 +147,10 @@ static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_TYPE_ID_LOCAL: - case BPF_TYPE_ID_TARGET: - case BPF_TYPE_EXISTS: - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_ID_LOCAL: + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: return true; default: return false; @@ -160,8 +160,8 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_ENUMVAL_EXISTS: - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: return true; default: return false; @@ -624,7 +624,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, *field_sz = 0; - if (relo->kind == BPF_FIELD_EXISTS) { + if (relo->kind == BPF_CORE_FIELD_EXISTS) { *val = spec ? 1 : 0; return 0; } @@ -637,7 +637,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, /* a[n] accessor needs special handling */ if (!acc->name) { - if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; /* remember field size for load/store mem size */ sz = btf__resolve_size(spec->btf, acc->type_id); @@ -645,7 +645,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EINVAL; *field_sz = sz; *type_id = acc->type_id; - } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + } else if (relo->kind == BPF_CORE_FIELD_BYTE_SIZE) { sz = btf__resolve_size(spec->btf, acc->type_id); if (sz < 0) return -EINVAL; @@ -697,36 +697,36 @@ static int bpf_core_calc_field_relo(const char *prog_name, *validate = !bitfield; switch (relo->kind) { - case BPF_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { *field_sz = byte_sz; *type_id = field_type_id; } break; - case BPF_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_BYTE_SIZE: *val = byte_sz; break; - case BPF_FIELD_SIGNED: + case BPF_CORE_FIELD_SIGNED: /* enums will be assumed unsigned */ *val = btf_is_enum(mt) || (btf_int_encoding(mt) & BTF_INT_SIGNED); if (validate) *validate = true; /* signedness is never ambiguous */ break; - case BPF_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_LSHIFT_U64: #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ *val = 64 - (bit_off + bit_sz - byte_off * 8); #else *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); #endif break; - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: *val = 64 - bit_sz; if (validate) *validate = true; /* right shift is never ambiguous */ break; - case BPF_FIELD_EXISTS: + case BPF_CORE_FIELD_EXISTS: default: return -EOPNOTSUPP; } @@ -747,20 +747,20 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, } switch (relo->kind) { - case BPF_TYPE_ID_TARGET: + case BPF_CORE_TYPE_ID_TARGET: *val = spec->root_type_id; break; - case BPF_TYPE_EXISTS: + case BPF_CORE_TYPE_EXISTS: *val = 1; break; - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_SIZE: sz = btf__resolve_size(spec->btf, spec->root_type_id); if (sz < 0) return -EINVAL; *val = sz; break; - case BPF_TYPE_ID_LOCAL: - /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */ + case BPF_CORE_TYPE_ID_LOCAL: + /* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */ default: return -EOPNOTSUPP; } @@ -776,10 +776,10 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, const struct btf_enum *e; switch (relo->kind) { - case BPF_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_EXISTS: *val = spec ? 1 : 0; break; - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_VALUE: if (!spec) return -EUCLEAN; /* request instruction poisoning */ t = btf_type_by_id(spec->btf, spec->spec[0].type_id); @@ -1236,7 +1236,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, libbpf_print(LIBBPF_DEBUG, "\n"); /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ - if (relo->kind == BPF_TYPE_ID_LOCAL) { + if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) { targ_res.validate = true; targ_res.poison = false; targ_res.orig_val = local_spec.root_type_id; @@ -1302,7 +1302,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, } /* - * For BPF_FIELD_EXISTS relo or when used BPF program has field + * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field * existence checks or kernel version/config checks, it's expected * that we might not find any candidates. In this case, if field * wasn't found in any candidate, the list of candidates shouldn't diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3b9f8f18346c..3d0b86e7f439 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -4,23 +4,7 @@ #ifndef __RELO_CORE_H #define __RELO_CORE_H -/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value - * has to be adjusted by relocations. - */ -enum bpf_core_relo_kind { - BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ - BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */ - BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ - BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ - BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ - BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ - BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ - BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */ - BPF_TYPE_EXISTS = 8, /* type existence in target kernel */ - BPF_TYPE_SIZE = 9, /* type size in bytes */ - BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ - BPF_ENUMVAL_VALUE = 11, /* enum value integer value */ -}; +#include /* The minimum bpf_core_relo checked by the loader * -- cgit v1.2.3 From fbd94c7afcf99c9f3b1ba1168657ecc428eb2c8d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Dec 2021 10:10:28 -0800 Subject: bpf: Pass a set of bpf_core_relo-s to prog_load command. struct bpf_core_relo is generated by llvm and processed by libbpf. It's a de-facto uapi. With CO-RE in the kernel the struct bpf_core_relo becomes uapi de-jure. Add an ability to pass a set of 'struct bpf_core_relo' to prog_load command and let the kernel perform CO-RE relocations. Note the struct bpf_line_info and struct bpf_func_info have the same layout when passed from LLVM to libbpf and from libbpf to the kernel except "insn_off" fields means "byte offset" when LLVM generates it. Then libbpf converts it to "insn index" to pass to the kernel. The struct bpf_core_relo's "insn_off" field is always "byte offset". Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211201181040.23337-6-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 +++++ include/uapi/linux/bpf.h | 59 +++++++++++++++++++++++++++++++- kernel/bpf/btf.c | 6 ++++ kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 76 ++++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 59 +++++++++++++++++++++++++++++++- tools/lib/bpf/relo_core.h | 53 ----------------------------- 7 files changed, 207 insertions(+), 56 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cad0829710be..8bbf08fbab66 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1732,6 +1732,14 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +struct bpf_core_ctx { + struct bpf_verifier_log *log; + const struct btf *btf; +}; + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9e66b1880020..c26871263f1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -6393,4 +6395,59 @@ enum bpf_core_relo_kind { BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ }; +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index c79595aad55b..0d070461e2b8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6439,3 +6439,9 @@ size_t bpf_core_essential_name_len(const char *name) } return n; } + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn) +{ + return -EOPNOTSUPP; +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 47089d1d67a4..b3ada4085f85 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2184,7 +2184,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD fd_array +#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6c9c0d9a04a0..6522ffdea487 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10273,6 +10273,78 @@ err_free: return err; } +#define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) +#define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_core_relo(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + u32 i, nr_core_relo, ncopy, expected_size, rec_size; + struct bpf_core_relo core_relo = {}; + struct bpf_prog *prog = env->prog; + const struct btf *btf = prog->aux->btf; + struct bpf_core_ctx ctx = { + .log = &env->log, + .btf = btf, + }; + bpfptr_t u_core_relo; + int err; + + nr_core_relo = attr->core_relo_cnt; + if (!nr_core_relo) + return 0; + if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) + return -EINVAL; + + rec_size = attr->core_relo_rec_size; + if (rec_size < MIN_CORE_RELO_SIZE || + rec_size > MAX_CORE_RELO_SIZE || + rec_size % sizeof(u32)) + return -EINVAL; + + u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); + expected_size = sizeof(struct bpf_core_relo); + ncopy = min_t(u32, expected_size, rec_size); + + /* Unlike func_info and line_info, copy and apply each CO-RE + * relocation record one at a time. + */ + for (i = 0; i < nr_core_relo; i++) { + /* future proofing when sizeof(bpf_core_relo) changes */ + err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in core_relo"); + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, core_relo_rec_size), + &expected_size, sizeof(expected_size))) + err = -EFAULT; + } + break; + } + + if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { + err = -EFAULT; + break; + } + + if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { + verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", + i, core_relo.insn_off, prog->len); + err = -EINVAL; + break; + } + + err = bpf_core_apply(&ctx, &core_relo, i, + &prog->insnsi[core_relo.insn_off / 8]); + if (err) + break; + bpfptr_add(&u_core_relo, rec_size); + } + return err; +} + static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) @@ -10303,6 +10375,10 @@ static int check_btf_info(struct bpf_verifier_env *env, if (err) return err; + err = check_core_relo(env, attr, uattr); + if (err) + return err; + return 0; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9e66b1880020..c26871263f1f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -6393,4 +6395,59 @@ enum bpf_core_relo_kind { BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ }; +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3d0b86e7f439..f410691cc4e5 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -6,59 +6,6 @@ #include -/* The minimum bpf_core_relo checked by the loader - * - * CO-RE relocation captures the following data: - * - insn_off - instruction offset (in bytes) within a BPF program that needs - * its insn->imm field to be relocated with actual field info; - * - type_id - BTF type ID of the "root" (containing) entity of a relocatable - * type or field; - * - access_str_off - offset into corresponding .BTF string section. String - * interpretation depends on specific relocation kind: - * - for field-based relocations, string encodes an accessed field using - * a sequence of field and array indices, separated by colon (:). It's - * conceptually very close to LLVM's getelementptr ([0]) instruction's - * arguments for identifying offset to a field. - * - for type-based relocations, strings is expected to be just "0"; - * - for enum value-based relocations, string contains an index of enum - * value within its enum type; - * - * Example to provide a better feel. - * - * struct sample { - * int a; - * struct { - * int b[10]; - * }; - * }; - * - * struct sample *s = ...; - * int x = &s->a; // encoded as "0:0" (a is field #0) - * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, - * // b is field #0 inside anon struct, accessing elem #5) - * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) - * - * type_id for all relocs in this example will capture BTF type id of - * `struct sample`. - * - * Such relocation is emitted when using __builtin_preserve_access_index() - * Clang built-in, passing expression that captures field address, e.g.: - * - * bpf_probe_read(&dst, sizeof(dst), - * __builtin_preserve_access_index(&src->a.b.c)); - * - * In this case Clang will emit field relocation recording necessary data to - * be able to find offset of embedded `a.b.c` field within `src` struct. - * - * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction - */ -struct bpf_core_relo { - __u32 insn_off; - __u32 type_id; - __u32 access_str_off; - enum bpf_core_relo_kind kind; -}; - struct bpf_core_cand { const struct btf *btf; const struct btf_type *t; -- cgit v1.2.3 From 063ebb19d962b45a1b505748d464bd12b5074797 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 1 Dec 2021 17:33:21 +0000 Subject: iommu/virtio: Add definitions for VIRTIO_IOMMU_F_BYPASS_CONFIG Add definitions for the VIRTIO_IOMMU_F_BYPASS_CONFIG, which supersedes VIRTIO_IOMMU_F_BYPASS. Reviewed-by: Kevin Tian Signed-off-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20211201173323.1045819-2-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/uapi/linux/virtio_iommu.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index 237e36a280cb..1ff357f0d72e 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -16,6 +16,7 @@ #define VIRTIO_IOMMU_F_BYPASS 3 #define VIRTIO_IOMMU_F_PROBE 4 #define VIRTIO_IOMMU_F_MMIO 5 +#define VIRTIO_IOMMU_F_BYPASS_CONFIG 6 struct virtio_iommu_range_64 { __le64 start; @@ -36,6 +37,8 @@ struct virtio_iommu_config { struct virtio_iommu_range_32 domain_range; /* Probe buffer size */ __le32 probe_size; + __u8 bypass; + __u8 reserved[3]; }; /* Request types */ @@ -66,11 +69,14 @@ struct virtio_iommu_req_tail { __u8 reserved[3]; }; +#define VIRTIO_IOMMU_ATTACH_F_BYPASS (1 << 0) + struct virtio_iommu_req_attach { struct virtio_iommu_req_head head; __le32 domain; __le32 endpoint; - __u8 reserved[8]; + __le32 flags; + __u8 reserved[4]; struct virtio_iommu_req_tail tail; }; -- cgit v1.2.3 From abaad3d95b5117a17886d37cf0228712801cd259 Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Mon, 6 Dec 2021 12:26:17 -0500 Subject: drm/vmwgfx: Allow checking for gl43 contexts To make sure we're running on top of hardware that can support GL4.3 we need to add a way of querying for those capabilities. DRM_VMW_PARAM_GL43 allows userspace to check for presence of GL4.3 capable contexts. Signed-off-by: Zack Rusin Reviewed-by: Charmaine Lee Link: https://patchwork.freedesktop.org/patch/msgid/20211206172620.3139754-10-zack@kde.org --- drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c | 3 +++ include/uapi/drm/vmwgfx_drm.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index 28af34ab6ed6..471da2b4c177 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -105,6 +105,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, case DRM_VMW_PARAM_SM5: param->value = has_sm5_context(dev_priv); break; + case DRM_VMW_PARAM_GL43: + param->value = has_gl43_context(dev_priv); + break; default: return -EINVAL; } diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 9078775feb51..8277644c1144 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -110,6 +110,7 @@ extern "C" { #define DRM_VMW_PARAM_HW_CAPS2 13 #define DRM_VMW_PARAM_SM4_1 14 #define DRM_VMW_PARAM_SM5 15 +#define DRM_VMW_PARAM_GL43 16 /** * enum drm_vmw_handle_type - handle type for ref ioctls -- cgit v1.2.3 From 50252e4b5e989ce64555c7aef7516bdefc2fea72 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:55 -0800 Subject: aio: fix use-after-free due to missing POLLFREE handling signalfd_poll() and binder_poll() are special in that they use a waitqueue whose lifetime is the current task, rather than the struct file as is normally the case. This is okay for blocking polls, since a blocking poll occurs within one task; however, non-blocking polls require another solution. This solution is for the queue to be cleared before it is freed, by sending a POLLFREE notification to all waiters. Unfortunately, only eventpoll handles POLLFREE. A second type of non-blocking poll, aio poll, was added in kernel v4.18, and it doesn't handle POLLFREE. This allows a use-after-free to occur if a signalfd or binder fd is polled with aio poll, and the waitqueue gets freed. Fix this by making aio poll handle POLLFREE. A patch by Ramji Jiyani (https://lore.kernel.org/r/20211027011834.2497484-1-ramjiyani@google.com) tried to do this by making aio_poll_wake() always complete the request inline if POLLFREE is seen. However, that solution had two bugs. First, it introduced a deadlock, as it unconditionally locked the aio context while holding the waitqueue lock, which inverts the normal locking order. Second, it didn't consider that POLLFREE notifications are missed while the request has been temporarily de-queued. The second problem was solved by my previous patch. This patch then properly fixes the use-after-free by handling POLLFREE in a deadlock-free way. It does this by taking advantage of the fact that freeing of the waitqueue is RCU-delayed, similar to what eventpoll does. Fixes: 2c14fa838cbe ("aio: implement IOCB_CMD_POLL") Cc: # v4.18+ Link: https://lore.kernel.org/r/20211209010455.42744-6-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/aio.c | 137 +++++++++++++++++++++++++++++++--------- include/uapi/asm-generic/poll.h | 2 +- 2 files changed, 107 insertions(+), 32 deletions(-) (limited to 'include/uapi') diff --git a/fs/aio.c b/fs/aio.c index 2bc1352a83d8..c9bb0d3d8593 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1620,6 +1620,51 @@ static void aio_poll_put_work(struct work_struct *work) iocb_put(iocb); } +/* + * Safely lock the waitqueue which the request is on, synchronizing with the + * case where the ->poll() provider decides to free its waitqueue early. + * + * Returns true on success, meaning that req->head->lock was locked, req->wait + * is on req->head, and an RCU read lock was taken. Returns false if the + * request was already removed from its waitqueue (which might no longer exist). + */ +static bool poll_iocb_lock_wq(struct poll_iocb *req) +{ + wait_queue_head_t *head; + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us, then check whether the request is still on the queue. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + head = smp_load_acquire(&req->head); + if (head) { + spin_lock(&head->lock); + if (!list_empty(&req->wait.entry)) + return true; + spin_unlock(&head->lock); + } + rcu_read_unlock(); + return false; +} + +static void poll_iocb_unlock_wq(struct poll_iocb *req) +{ + spin_unlock(&req->head->lock); + rcu_read_unlock(); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1639,24 +1684,25 @@ static void aio_poll_complete_work(struct work_struct *work) * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); - spin_lock(&req->head->lock); - if (!mask && !READ_ONCE(req->cancelled)) { - /* - * The request isn't actually ready to be completed yet. - * Reschedule completion if another wakeup came in. - */ - if (req->work_need_resched) { - schedule_work(&req->work); - req->work_need_resched = false; - } else { - req->work_scheduled = false; + if (poll_iocb_lock_wq(req)) { + if (!mask && !READ_ONCE(req->cancelled)) { + /* + * The request isn't actually ready to be completed yet. + * Reschedule completion if another wakeup came in. + */ + if (req->work_need_resched) { + schedule_work(&req->work); + req->work_need_resched = false; + } else { + req->work_scheduled = false; + } + poll_iocb_unlock_wq(req); + spin_unlock_irq(&ctx->ctx_lock); + return; } - spin_unlock(&req->head->lock); - spin_unlock_irq(&ctx->ctx_lock); - return; - } - list_del_init(&req->wait.entry); - spin_unlock(&req->head->lock); + list_del_init(&req->wait.entry); + poll_iocb_unlock_wq(req); + } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); spin_unlock_irq(&ctx->ctx_lock); @@ -1670,13 +1716,14 @@ static int aio_poll_cancel(struct kiocb *iocb) struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; - spin_lock(&req->head->lock); - WRITE_ONCE(req->cancelled, true); - if (!req->work_scheduled) { - schedule_work(&aiocb->poll.work); - req->work_scheduled = true; - } - spin_unlock(&req->head->lock); + if (poll_iocb_lock_wq(req)) { + WRITE_ONCE(req->cancelled, true); + if (!req->work_scheduled) { + schedule_work(&aiocb->poll.work); + req->work_scheduled = true; + } + poll_iocb_unlock_wq(req); + } /* else, the request was force-cancelled by POLLFREE already */ return 0; } @@ -1728,7 +1775,8 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, * * Don't remove the request from the waitqueue here, as it might * not actually be complete yet (we won't know until vfs_poll() - * is called), and we must not miss any wakeups. + * is called), and we must not miss any wakeups. POLLFREE is an + * exception to this; see below. */ if (req->work_scheduled) { req->work_need_resched = true; @@ -1736,6 +1784,28 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, schedule_work(&req->work); req->work_scheduled = true; } + + /* + * If the waitqueue is being freed early but we can't complete + * the request inline, we have to tear down the request as best + * we can. That means immediately removing the request from its + * waitqueue and preventing all further accesses to the + * waitqueue via the request. We also need to schedule the + * completion work (done above). Also mark the request as + * cancelled, to potentially skip an unneeded call to ->poll(). + */ + if (mask & POLLFREE) { + WRITE_ONCE(req->cancelled, true); + list_del_init(&req->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&req->head, NULL); + } } return 1; } @@ -1743,6 +1813,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; + bool queued; int error; }; @@ -1753,11 +1824,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ - if (unlikely(pt->iocb->poll.head)) { + if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } + pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); @@ -1789,6 +1861,7 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; + apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ @@ -1797,9 +1870,10 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); - if (likely(req->head)) { - spin_lock(&req->head->lock); - if (list_empty(&req->wait.entry) || req->work_scheduled) { + if (likely(apt.queued)) { + bool on_queue = poll_iocb_lock_wq(req); + + if (!on_queue || req->work_scheduled) { /* * aio_poll_wake() already either scheduled the async * completion work, or completed the request inline. @@ -1815,7 +1889,7 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) } else if (cancel) { /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); - } else if (!list_empty(&req->wait.entry)) { + } else if (on_queue) { /* * Actually waiting for an event, so add the request to * active_reqs so that it can be cancelled if needed. @@ -1823,7 +1897,8 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); + if (on_queue) + poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 41b509f410bf..f9c520ce4bf4 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -29,7 +29,7 @@ #define POLLRDHUP 0x2000 #endif -#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */ +#define POLLFREE (__force __poll_t)0x4000 #define POLL_BUSY_LOOP (__force __poll_t)0x8000 -- cgit v1.2.3 From 9dcc38e2813e0cd3b195940c98b181ce6ede8f20 Mon Sep 17 00:00:00 2001 From: Drew DeVault Date: Fri, 10 Dec 2021 14:46:09 -0800 Subject: Increase default MLOCK_LIMIT to 8 MiB This limit has not been updated since 2008, when it was increased to 64 KiB at the request of GnuPG. Until recently, the main use-cases for this feature were (1) preventing sensitive memory from being swapped, as in GnuPG's use-case; and (2) real-time use-cases. In the first case, little memory is called for, and in the second case, the user is generally in a position to increase it if they need more. The introduction of IOURING_REGISTER_BUFFERS adds a third use-case: preparing fixed buffers for high-performance I/O. This use-case will take as much of this memory as it can get, but is still limited to 64 KiB by default, which is very little. This increases the limit to 8 MB, which was chosen fairly arbitrarily as a more generous, but still conservative, default value. It is also possible to raise this limit in userspace. This is easily done, for example, in the use-case of a network daemon: systemd, for instance, provides for this via LimitMEMLOCK in the service file; OpenRC via the rc_ulimit variables. However, there is no established userspace facility for configuring this outside of daemons: end-user applications do not presently have access to a convenient means of raising their limits. The buck, as it were, stops with the kernel. It's much easier to address it here than it is to bring it to hundreds of distributions, and it can only realistically be relied upon to be high-enough by end-user software if it is more-or-less ubiquitous. Most distros don't change this particular rlimit from the kernel-supplied default value, so a change here will easily provide that ubiquity. Link: https://lkml.kernel.org/r/20211028080813.15966-1-sir@cmpwn.com Signed-off-by: Drew DeVault Acked-by: Jens Axboe Acked-by: Cyril Hrubis Acked-by: Johannes Weiner Cc: Pavel Begunkov Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: Andrew Dona-Couch Cc: Ammar Faizi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/resource.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index 74ef57b38f9f..ac5d6a3031db 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -66,10 +66,17 @@ struct rlimit64 { #define _STK_LIM (8*1024*1024) /* - * GPG2 wants 64kB of mlocked memory, to make sure pass phrases - * and other sensitive information are never written to disk. + * Limit the amount of locked memory by some sane default: + * root can always increase this limit if needed. + * + * The main use-cases are (1) preventing sensitive memory + * from being swapped; (2) real-time operations; (3) via + * IOURING_REGISTER_BUFFERS. + * + * The first two don't need much. The latter will take as + * much as it can get. 8MB is a reasonably sane default. */ -#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024) +#define MLOCK_LIMIT (8*1024*1024) /* * Due to binary compatibility, the actual resource numbers -- cgit v1.2.3 From c5fb19937455095573a19ddcbff32e993ed10e35 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 10 Dec 2021 22:16:49 +0800 Subject: bpf: Add bpf_strncmp helper The helper compares two strings: one string is a null-terminated read-only string, and another string has const max storage size but doesn't need to be null-terminated. It can be used to compare file name in tracing or LSM program. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211210141652.877186-2-houtao1@huawei.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/helpers.c | 16 ++++++++++++++++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 4 files changed, 39 insertions(+) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0ceb54c6342f..7a40022e3d00 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2163,6 +2163,7 @@ extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; +extern const struct bpf_func_proto bpf_strncmp_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c26871263f1f..2820c77e4846 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4983,6 +4983,16 @@ union bpf_attr { * Return * The number of loops performed, **-EINVAL** for invalid **flags**, * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5167,6 +5177,7 @@ union bpf_attr { FN(kallsyms_lookup_name), \ FN(find_vma), \ FN(loop), \ + FN(strncmp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 19fecfeaa9c2..8babae03d30a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -565,6 +565,20 @@ const struct bpf_func_proto bpf_strtoul_proto = { }; #endif +BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2) +{ + return strncmp(s1, s2, s1_sz); +} + +const struct bpf_func_proto bpf_strncmp_proto = { + .func = bpf_strncmp, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_CONST_STR, +}; + BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, struct bpf_pidns_info *, nsdata, u32, size) { @@ -1378,6 +1392,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_for_each_map_elem_proto; case BPF_FUNC_loop: return &bpf_loop_proto; + case BPF_FUNC_strncmp: + return &bpf_strncmp_proto; default: break; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c26871263f1f..2820c77e4846 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4983,6 +4983,16 @@ union bpf_attr { * Return * The number of loops performed, **-EINVAL** for invalid **flags**, * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5167,6 +5177,7 @@ union bpf_attr { FN(kallsyms_lookup_name), \ FN(find_vma), \ FN(loop), \ + FN(strncmp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From fb6723daf89083a0d2290f3a0abc777e40766c84 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sat, 29 May 2021 12:33:53 +0900 Subject: ALSA: pcm: comment about relation between msbits hw parameter and [S|U]32 formats Regarding to handling [U|S][32|24] PCM formats, many userspace application developers and driver developers have confusion, since they require them to understand justification or padding. It easily loses consistency and soundness to operate with many type of devices. In this commit, I attempt to solve the situation by adding comment about relation between [S|U]32 formats and 'msbits' hardware parameter. The formats are used for 'left-justified' sample format, and the available bit count in most significant bit is delivered to userspace in msbits hardware parameter (struct snd_pcm_hw_params.msbits), which is decided by msbits constraint added by pcm drivers (snd_pcm_hw_constraint_msbits()). In driver side, the msbits constraint includes two elements; the physical width of format and the available width of the format in most significant bit. The former is used to match SAMPLE_BITS of format. (For my convenience, I ignore wildcard in the usage of the constraint.) As a result of interaction between ALSA pcm core and ALSA pcm application, when the format in which SAMPLE_BITS equals to physical width of the msbits constaint, the msbits parameter is set by referring to the available width of the constraint. When the msbits parameter is not changed in the above process, ALSA pcm core set it alternatively with SAMPLE_BIT of chosen format. In userspace application side, the msbits is only available after calling ioctl(2) with SNDRV_PCM_IOCTL_HW_PARAMS request. Even if the hardware parameter structure includes somewhat value of SAMPLE_BITS interval parameter as width of format, all of the width is not always available since msbits can be less than the width. I note that [S|U]24 formats are used for 'right-justified' 24 bit sample formats within 32 bit frame. The first byte in most significant bit should be invalidated. Although the msbits exposed to userspace should be zero as invalid value, actually it is 32 from physical width of format. [ corrected typos -- tiwai ] Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20210529033353.21641-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 3 +++ include/uapi/sound/asound.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 33451f8ff755..9b187d86e1bd 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -147,6 +147,9 @@ struct snd_pcm_ops { #define SNDRV_PCM_FMTBIT_S24_BE _SNDRV_PCM_FMTBIT(S24_BE) #define SNDRV_PCM_FMTBIT_U24_LE _SNDRV_PCM_FMTBIT(U24_LE) #define SNDRV_PCM_FMTBIT_U24_BE _SNDRV_PCM_FMTBIT(U24_BE) +// For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the +// available bit count in most significant bit. It's for the case of so-called 'left-justified' or +// `right-padding` sample which has less width than 32 bit. #define SNDRV_PCM_FMTBIT_S32_LE _SNDRV_PCM_FMTBIT(S32_LE) #define SNDRV_PCM_FMTBIT_S32_BE _SNDRV_PCM_FMTBIT(S32_BE) #define SNDRV_PCM_FMTBIT_U32_LE _SNDRV_PCM_FMTBIT(U32_LE) diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 5fbb79e30819..cf1d20e34167 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -202,6 +202,9 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */ +// For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the +// available bit count in most significant bit. It's for the case of so-called 'left-justified' or +// `right-padding` sample which has less width than 32 bit. #define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10) #define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11) #define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12) -- cgit v1.2.3 From 55b71f6c29f2a78af42dd453dfed895eba516cb4 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Mon, 13 Dec 2021 17:12:57 +0900 Subject: ALSA: uapi: use C90 comment style instead of C99 style UAPI headers are built with compiler option for C90, thus double-slashes comment introduced in C99 is not preferable. Fixes: fb6723daf890 ("ALSA: pcm: comment about relation between msbits hw parameter and [S|U]32 formats") Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20211213081257.36097-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index cf1d20e34167..1834f58b8ede 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -202,9 +202,11 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */ -// For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the -// available bit count in most significant bit. It's for the case of so-called 'left-justified' or -// `right-padding` sample which has less width than 32 bit. +/* + * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the + * available bit count in most significant bit. It's for the case of so-called 'left-justified' or + * `right-padding` sample which has less width than 32 bit. + */ #define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10) #define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11) #define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12) -- cgit v1.2.3 From f92c1e183604c20ce00eb889315fdaa8f2d9e509 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 Dec 2021 20:32:44 +0100 Subject: bpf: Add get_func_[arg|ret|arg_cnt] helpers Adding following helpers for tracing programs: Get n-th argument of the traced function: long bpf_get_func_arg(void *ctx, u32 n, u64 *value) Get return value of the traced function: long bpf_get_func_ret(void *ctx, u64 *value) Get arguments count of the traced function: long bpf_get_func_arg_cnt(void *ctx) The trampoline now stores number of arguments on ctx-8 address, so it's easy to verify argument index and find return value argument's position. Moving function ip address on the trampoline stack behind the number of functions arguments, so it's now stored on ctx-16 address if it's needed. All helpers above are inlined by verifier. Also bit unrelated small change - using newly added function bpf_prog_has_trampoline in check_get_func_ip. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211208193245.172141-5-jolsa@kernel.org --- arch/x86/net/bpf_jit_comp.c | 15 +++++++- include/linux/bpf.h | 5 +++ include/uapi/linux/bpf.h | 28 +++++++++++++++ kernel/bpf/trampoline.c | 8 +++++ kernel/bpf/verifier.c | 77 +++++++++++++++++++++++++++++++++++++++--- kernel/trace/bpf_trace.c | 55 +++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 28 +++++++++++++++ 7 files changed, 209 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 10fab8cb3fb5..4bbcded07415 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1941,7 +1941,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *orig_call) { int ret, i, nr_args = m->nr_args; - int regs_off, ip_off, stack_size = nr_args * 8; + int regs_off, ip_off, args_off, stack_size = nr_args * 8; struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; @@ -1968,6 +1968,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * + * RBP - args_off [ args count ] always + * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag */ @@ -1978,6 +1980,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i regs_off = stack_size; + /* args count */ + stack_size += 8; + args_off = stack_size; + if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -1996,6 +2002,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ EMIT1(0x53); /* push rbx */ + /* Store number of arguments of the traced function: + * mov rax, nr_args + * mov QWORD PTR [rbp - args_off], rax + */ + emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off); + if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: * mov rax, QWORD PTR [rbp + 8] diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7a40022e3d00..965fffaf0308 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -777,6 +777,7 @@ void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 pages); void bpf_jit_uncharge_modmem(u32 pages); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -805,6 +806,10 @@ static inline bool is_bpf_image_address(unsigned long address) { return false; } +static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + return false; +} #endif struct bpf_func_info_aux { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2820c77e4846..b0383d371b9a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4993,6 +4993,31 @@ union bpf_attr { * An integer less than, equal to, or greater than zero * if the first **s1_sz** bytes of **s1** is found to be * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= arguments count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of arguments of the traced function (for tracing programs). + * + * Return + * The number of arguments of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5178,6 +5203,9 @@ union bpf_attr { FN(find_vma), \ FN(loop), \ FN(strncmp), \ + FN(get_func_arg), \ + FN(get_func_ret), \ + FN(get_func_arg_cnt), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e98de5e73ba5..4b6974a195c1 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -27,6 +27,14 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; /* serializes access to trampoline_table */ static DEFINE_MUTEX(trampoline_mutex); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + enum bpf_attach_type eatype = prog->expected_attach_type; + + return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN; +} + void *bpf_jit_alloc_exec_page(void) { void *image; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b39de3ae50f5..d74e8a99412e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6395,13 +6395,11 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, static int check_get_func_ip(struct bpf_verifier_env *env) { - enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); int func_id = BPF_FUNC_get_func_ip; if (type == BPF_PROG_TYPE_TRACING) { - if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT && - eatype != BPF_MODIFY_RETURN) { + if (!bpf_prog_has_trampoline(env->prog)) { verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n", func_id_name(func_id), func_id); return -ENOTSUPP; @@ -12997,6 +12995,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, static int do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + enum bpf_attach_type eatype = prog->expected_attach_type; bool expect_blinding = bpf_jit_blinding_enabled(prog); enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; @@ -13367,11 +13366,79 @@ patch_map_ops_generic: continue; } + /* Implement bpf_get_func_arg inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); + insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); + insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); + insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); + insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); + insn_buf[7] = BPF_JMP_A(1); + insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); + cnt = 9; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + /* Implement bpf_get_func_ret inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_ret) { + if (eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); + insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); + insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); + insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0); + cnt = 6; + } else { + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); + cnt = 1; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + /* Implement get_func_arg_cnt inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg_cnt) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); + if (!new_prog) + return -ENOMEM; + + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + /* Implement bpf_get_func_ip inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ip) { - /* Load IP address from ctx - 8 */ - insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + /* Load IP address from ctx - 16 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 623dd0684429..cea2ca6df949 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1012,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx) { /* This helper call is inlined by verifier. */ - return ((u64 *)ctx)[-1]; + return ((u64 *)ctx)[-2]; } static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = { @@ -1091,6 +1091,53 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, }; +BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + if ((u64) n >= nr_args) + return -EINVAL; + *value = ((u64 *)ctx)[n]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_arg_proto = { + .func = get_func_arg, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + *value = ((u64 *)ctx)[nr_args]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_ret_proto = { + .func = get_func_ret, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_1(get_func_arg_cnt, void *, ctx) +{ + /* This helper call is inlined by verifier. */ + return ((u64 *)ctx)[-1]; +} + +static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { + .func = get_func_arg_cnt, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1629,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) NULL; case BPF_FUNC_d_path: return &bpf_d_path_proto; + case BPF_FUNC_get_func_arg: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; + case BPF_FUNC_get_func_ret: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; + case BPF_FUNC_get_func_arg_cnt: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2820c77e4846..b0383d371b9a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4993,6 +4993,31 @@ union bpf_attr { * An integer less than, equal to, or greater than zero * if the first **s1_sz** bytes of **s1** is found to be * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= arguments count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of arguments of the traced function (for tracing programs). + * + * Return + * The number of arguments of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5178,6 +5203,9 @@ union bpf_attr { FN(find_vma), \ FN(loop), \ FN(strncmp), \ + FN(get_func_arg), \ + FN(get_func_ret), \ + FN(get_func_arg_cnt), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 98046f7486db723ec8bb99a950a4fa5f5be55cd1 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Thu, 25 Nov 2021 15:05:26 +0800 Subject: fuse: support per inode DAX in fuse protocol Expand the fuse protocol to support per inode DAX. FUSE_HAS_INODE_DAX flag is added indicating if fuse server/client supporting per inode DAX. It can be conveyed in both FUSE_INIT request and reply. FUSE_ATTR_DAX flag is added indicating if DAX shall be enabled for corresponding file. It is conveyed in FUSE_LOOKUP reply. Signed-off-by: Jeffle Xu Reviewed-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 3f0ea63fec08..d6ccee961891 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -193,6 +193,7 @@ * - add flags2 to fuse_init_in and fuse_init_out * - add FUSE_SECURITY_CTX init flag * - add security context to create, mkdir, symlink, and mknod requests + * - add FUSE_HAS_INODE_DAX, FUSE_ATTR_DAX */ #ifndef _LINUX_FUSE_H @@ -351,6 +352,7 @@ struct fuse_file_lock { * FUSE_INIT_RESERVED: reserved, do not use * FUSE_SECURITY_CTX: add security context to create, mkdir, symlink, and * mknod + * FUSE_HAS_INODE_DAX: use per inode DAX */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -386,6 +388,7 @@ struct fuse_file_lock { #define FUSE_INIT_RESERVED (1 << 31) /* 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) /** * CUSE INIT request/reply flags @@ -468,8 +471,10 @@ struct fuse_file_lock { * fuse_attr flags * * FUSE_ATTR_SUBMOUNT: Object is a submount root + * FUSE_ATTR_DAX: Enable DAX for this file in per inode DAX mode */ #define FUSE_ATTR_SUBMOUNT (1 << 0) +#define FUSE_ATTR_DAX (1 << 1) /** * Open flags -- cgit v1.2.3 From 43d5ac7d07023cd133b978de473b3400edad941f Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Tue, 23 Nov 2021 11:24:04 +0000 Subject: drm: document DRM_IOCTL_MODE_GETFB2 There are a few details specific to the GETFB2 IOCTL. It's not immediately clear how user-space should check for the number of planes. Suggest using the handles field or the pitches field. The modifier array is filled with zeroes, ie. DRM_FORMAT_MOD_LINEAR. So explicitly tell user-space to not look at it unless the flag is set. Changes in v2 (Daniel): - Mention that handles should be used to compute the number of planes, and only refer to pitches as a fallback. - Reword bit about undefined modifier. Signed-off-by: Simon Ser Acked-by: Daniel Vetter Acked-by: Pekka Paalanen Acked-by: Daniel Stone Link: https://patchwork.freedesktop.org/patch/msgid/20211123112400.22245-1-contact@emersion.fr --- include/uapi/drm/drm.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 3b810b53ba8b..642808520d92 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -1096,6 +1096,24 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +/** + * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata. + * + * This queries metadata about a framebuffer. User-space fills + * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the + * struct as the output. + * + * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles + * will be filled with GEM buffer handles. Planes are valid until one has a + * zero handle -- this can be used to compute the number of planes. + * + * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid + * until one has a zero &drm_mode_fb_cmd2.pitches. + * + * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set + * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the + * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) /* -- cgit v1.2.3 From 9c9211a3fc7aa41b2952765b62000443b3bb6f23 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 10 Dec 2021 16:59:58 +0800 Subject: net_tstamp: add new flag HWTSTAMP_FLAG_BONDED_PHC_INDEX Since commit 94dd016ae538 ("bond: pass get_ts_info and SIOC[SG]HWTSTAMP ioctl to active device") the user could get bond active interface's PHC index directly. But when there is a failover, the bond active interface will change, thus the PHC index is also changed. This may break the user's program if they did not update the PHC timely. This patch adds a new hwtstamp_config flag HWTSTAMP_FLAG_BONDED_PHC_INDEX. When the user wants to get the bond active interface's PHC, they need to add this flag and be aware the PHC index may be changed. With the new flag. All flag checks in current drivers are removed. Only the checking in net_hwtstamp_validate() is kept. Suggested-by: Jakub Kicinski Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c | 4 ---- drivers/net/dsa/mv88e6xxx/hwtstamp.c | 4 ---- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 3 --- drivers/net/ethernet/aquantia/atlantic/aq_main.c | 3 --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ----- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 3 --- drivers/net/ethernet/broadcom/tg3.c | 3 --- drivers/net/ethernet/cadence/macb_ptp.c | 4 ---- drivers/net/ethernet/cavium/liquidio/lio_main.c | 3 --- drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 3 --- drivers/net/ethernet/cavium/octeon/octeon_mgmt.c | 3 --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 4 ---- drivers/net/ethernet/engleder/tsnep_ptp.c | 3 --- drivers/net/ethernet/freescale/fec_ptp.c | 4 ---- drivers/net/ethernet/freescale/gianfar.c | 4 ---- drivers/net/ethernet/intel/e1000e/netdev.c | 4 ---- drivers/net/ethernet/intel/i40e/i40e_ptp.c | 4 ---- drivers/net/ethernet/intel/ice/ice_ptp.c | 4 ---- drivers/net/ethernet/intel/igb/igb_ptp.c | 4 ---- drivers/net/ethernet/intel/igc/igc_ptp.c | 4 ---- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 4 ---- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 3 --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 4 ---- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 ---- drivers/net/ethernet/microchip/lan743x_ptp.c | 6 ------ drivers/net/ethernet/mscc/ocelot.c | 4 ---- drivers/net/ethernet/neterion/vxge/vxge-main.c | 4 ---- drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 3 --- drivers/net/ethernet/qlogic/qede/qede_ptp.c | 5 ----- drivers/net/ethernet/renesas/ravb_main.c | 4 ---- drivers/net/ethernet/sfc/ptp.c | 3 --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ---- drivers/net/ethernet/ti/cpsw_priv.c | 4 ---- drivers/net/ethernet/ti/netcp_ethss.c | 4 ---- drivers/net/ethernet/xscale/ixp4xx_eth.c | 3 --- drivers/net/phy/dp83640.c | 3 --- drivers/net/phy/mscc/mscc_ptp.c | 3 --- drivers/ptp/ptp_ines.c | 4 ---- include/uapi/linux/net_tstamp.h | 16 +++++++++++++++- net/core/dev_ioctl.c | 2 +- 40 files changed, 16 insertions(+), 144 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c index 40b41c794dfa..b3bc948d6145 100644 --- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c +++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c @@ -52,10 +52,6 @@ static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port, */ clear_bit_unlock(HELLCREEK_HWTSTAMP_ENABLED, &ps->state); - /* Reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_ON: tx_tstamp_enable = true; diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c index 8f74ffc7a279..389f8a6ec0ab 100644 --- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c @@ -100,10 +100,6 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port, */ clear_bit_unlock(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state); - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tstamp_enable = false; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 30d24d19f40d..492ac383f16d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1508,9 +1508,6 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, if (copy_from_user(&config, ifreq->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) - return -EINVAL; - mac_tscr = 0; switch (config.tx_type) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index e22935ce9573..e65ce7199dac 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -231,9 +231,6 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev) static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic, struct hwtstamp_config *config) { - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index aec666e97683..651bc1d7a57a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -15356,11 +15356,6 @@ static int bnx2x_hwtstamp_ioctl(struct bnx2x *bp, struct ifreq *ifr) DP(BNX2X_MSG_PTP, "Requested tx_type: %d, requested rx_filters = %d\n", config.tx_type, config.rx_filter); - if (config.flags) { - BNX2X_ERR("config.flags is reserved for future use\n"); - return -EINVAL; - } - bp->hwtstamp_ioctl_called = true; bp->tx_type = config.tx_type; bp->rx_filter = config.rx_filter; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 8388be119f9a..48520967746f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -417,9 +417,6 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf))) return -EFAULT; - if (stmpconf.flags) - return -EINVAL; - if (stmpconf.tx_type != HWTSTAMP_TX_ON && stmpconf.tx_type != HWTSTAMP_TX_OFF) return -ERANGE; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 283f3c1f1195..c28f8cc00d1c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -13806,9 +13806,6 @@ static int tg3_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf))) return -EFAULT; - if (stmpconf.flags) - return -EINVAL; - if (stmpconf.tx_type != HWTSTAMP_TX_ON && stmpconf.tx_type != HWTSTAMP_TX_OFF) return -ERANGE; diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 095c5a2144a7..fb6b27f46b15 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -464,10 +464,6 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(*tstamp_config))) return -EFAULT; - /* reserved for future extensions */ - if (tstamp_config->flags) - return -EINVAL; - switch (tstamp_config->tx_type) { case HWTSTAMP_TX_OFF: break; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 12eee2bc7f5c..ba28aa444e5a 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2114,9 +2114,6 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf))) return -EFAULT; - if (conf.flags) - return -EINVAL; - switch (conf.tx_type) { case HWTSTAMP_TX_ON: case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index c607756b731f..568f211d91cc 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -1254,9 +1254,6 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf))) return -EFAULT; - if (conf.flags) - return -EINVAL; - switch (conf.tx_type) { case HWTSTAMP_TX_ON: case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 4b4ffdd1044d..103591dcea1c 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -702,9 +702,6 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev, if (copy_from_user(&config, rq->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) /* reserved for future extensions */ - return -EINVAL; - /* Check the status of hardware for tiemstamps */ if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) { /* Get the current state of the PTP clock */ diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index bb45d5df2856..63191692f624 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1917,10 +1917,6 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/engleder/tsnep_ptp.c b/drivers/net/ethernet/engleder/tsnep_ptp.c index 4bfb4d8508f5..eaad453d487e 100644 --- a/drivers/net/ethernet/engleder/tsnep_ptp.c +++ b/drivers/net/ethernet/engleder/tsnep_ptp.c @@ -31,9 +31,6 @@ int tsnep_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index d71eac7e1924..af99017a5453 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -473,10 +473,6 @@ int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: fep->hwts_tx_en = 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index acab58fd3db3..206b7a35eaf5 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2076,10 +2076,6 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: priv->hwts_tx_en = 0; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 44e2dc8328a2..635a95927e93 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3614,10 +3614,6 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) return -EINVAL; - /* flags reserved for future extensions - must be zero */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 09b1d5aed1c9..61e5789d78db 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -1205,10 +1205,6 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work); - /* Reserved for future extensions. */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: pf->ptp_tx = false; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index bf7247c6f58e..dfc7c830acf6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1205,10 +1205,6 @@ int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) static int ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) { - /* Reserved for future extensions. */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: ice_set_tx_tstamp(pf, false); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 0011b15e678c..0ac4cc5eaa2d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1015,10 +1015,6 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter, bool is_l2 = false; u32 regval; - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 30568e3544cd..71813fa8f928 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -560,10 +560,6 @@ static void igc_ptp_enable_tx_timestamp(struct igc_adapter *adapter) static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, struct hwtstamp_config *config) { - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: igc_ptp_disable_tx_timestamp(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 23ddfd79fc8b..336426a67ac1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -992,10 +992,6 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, bool is_l2 = false; u32 regval; - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 8e5820d12362..b1cce4425296 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5142,9 +5142,6 @@ static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) - return -EINVAL; - if (config.tx_type != HWTSTAMP_TX_OFF && config.tx_type != HWTSTAMP_TX_ON) return -ERANGE; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 1333edf1c361..6080ebd9bd94 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -2002,10 +2002,6 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: otx2_config_hw_tx_tstamp(pfvf, false); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index f1c10f2bda78..ad1e4caf48bf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2427,10 +2427,6 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - /* device doesn't support time stamping */ if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) return -EINVAL; diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index 9380e396f648..8b7a8d879083 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -1305,12 +1305,6 @@ int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) { - netif_warn(adapter, drv, adapter->netdev, - "ignoring hwtstamp_config.flags == 0x%08X, expected 0\n", - config.flags); - } - switch (config.tx_type) { case HWTSTAMP_TX_OFF: for (index = 0; index < LAN743X_MAX_TX_CHANNELS; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 876a7ecf86eb..9b42187a026a 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1617,10 +1617,6 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - /* Tx type sanity check */ switch (cfg.tx_type) { case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 1969009a91e7..2c2e9e56ed4e 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -3159,10 +3159,6 @@ static int vxge_hwtstamp_set(struct vxgedev *vdev, void __user *data) if (copy_from_user(&config, data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - /* Transmit HW Timestamp not supported */ switch (config.tx_type) { case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 71d234291fc5..1dc40c537281 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -210,9 +210,6 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - /* Get ieee1588's dev information */ pdev = adapter->ptp_pdev; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 8c28fabb0ff6..39176e765767 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -304,11 +304,6 @@ int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *ifr) "HWTSTAMP IOCTL: Requested tx_type = %d, requested rx_filters = %d\n", config.tx_type, config.rx_filter); - if (config.flags) { - DP_ERR(edev, "config.flags is reserved for future use\n"); - return -EINVAL; - } - ptp->hw_ts_ioctl_called = 1; ptp->tx_type = config.tx_type; ptp->rx_filter = config.rx_filter; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ce09bd45527e..b215cde68e10 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2221,10 +2221,6 @@ static int ravb_hwtstamp_set(struct net_device *ndev, struct ifreq *req) if (copy_from_user(&config, req->ifr_data, sizeof(config))) return -EFAULT; - /* Reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: tstamp_tx_ctrl = 0; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 797e51802ccb..f0ef515e2ade 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1765,9 +1765,6 @@ static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init) { int rc; - if (init->flags) - return -EINVAL; - if ((init->tx_type != HWTSTAMP_TX_OFF) && (init->tx_type != HWTSTAMP_TX_ON)) return -ERANGE; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7e3e1bc0f61d..c26ac288f981 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -638,10 +638,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n", __func__, config.flags, config.tx_type, config.rx_filter); - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - if (config.tx_type != HWTSTAMP_TX_OFF && config.tx_type != HWTSTAMP_TX_ON) return -ERANGE; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index c99dd9735087..8624a044776f 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -626,10 +626,6 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON) return -ERANGE; diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 33c1592d5381..751fb0bc65c5 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2654,10 +2654,6 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - switch (cfg.tx_type) { case HWTSTAMP_TX_OFF: gbe_dev->tx_ts_enabled = 0; diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 65fdad1107fc..df77a22d1b81 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -382,9 +382,6 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index); if (ret) return ret; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 705c16675b80..c2d1a85ec559 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1235,9 +1235,6 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ONESTEP_SYNC) return -ERANGE; diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index edb951695b13..34f829845d06 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1057,9 +1057,6 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) - return -EINVAL; - switch (cfg.tx_type) { case HWTSTAMP_TX_ONESTEP_SYNC: one_step = true; diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c index 6c7c2843ba0b..61f47fb9d997 100644 --- a/drivers/ptp/ptp_ines.c +++ b/drivers/ptp/ptp_ines.c @@ -338,10 +338,6 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - switch (cfg.tx_type) { case HWTSTAMP_TX_OFF: ts_stat_tx = 0; diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index fcc61c73a666..e258e52cfd1f 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -62,7 +62,7 @@ struct so_timestamping { /** * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter * - * @flags: no flags defined right now, must be zero for %SIOCSHWTSTAMP + * @flags: one of HWTSTAMP_FLAG_* * @tx_type: one of HWTSTAMP_TX_* * @rx_filter: one of HWTSTAMP_FILTER_* * @@ -78,6 +78,20 @@ struct hwtstamp_config { int rx_filter; }; +/* possible values for hwtstamp_config->flags */ +enum hwtstamp_flags { + /* + * With this flag, the user could get bond active interface's + * PHC index. Note this PHC index is not stable as when there + * is a failover, the bond active interface will be changed, so + * will be the PHC index. + */ + HWTSTAMP_FLAG_BONDED_PHC_INDEX = (1<<0), + + HWTSTAMP_FLAG_LAST = HWTSTAMP_FLAG_BONDED_PHC_INDEX, + HWTSTAMP_FLAG_MASK = (HWTSTAMP_FLAG_LAST - 1) | HWTSTAMP_FLAG_LAST +}; + /* possible values for hwtstamp_config->tx_type */ enum hwtstamp_tx_types { /* diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 1d309a666932..1b807d119da5 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -192,7 +192,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ + if (cfg.flags & ~HWTSTAMP_FLAG_MASK) return -EINVAL; tx_type = cfg.tx_type; -- cgit v1.2.3 From 326db0dc00e57432b689349b4da3e86c90d5d61a Mon Sep 17 00:00:00 2001 From: Yann Dirson Date: Tue, 14 Dec 2021 00:30:30 +0100 Subject: amdgpu: fix some comment typos Signed-off-by: Yann Dirson Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +- drivers/gpu/drm/amd/amdgpu/soc15.c | 2 +- include/uapi/drm/amdgpu_drm.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 0e7dc23f78e7..b23cb463b106 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -53,7 +53,7 @@ * can be mapped as snooped (cached system pages) or unsnooped * (uncached system pages). * Each VM has an ID associated with it and there is a page table - * associated with each VMID. When execting a command buffer, + * associated with each VMID. When executing a command buffer, * the kernel tells the the ring what VMID to use for that command * buffer. VMIDs are allocated dynamically as commands are submitted. * The userspace drivers maintain their own address space and the kernel diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index a06c4944ed37..0fc1747e4a70 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -744,7 +744,7 @@ static void soc15_reg_base_init(struct amdgpu_device *adev) vega10_reg_base_init(adev); break; case CHIP_RENOIR: - /* It's safe to do ip discovery here for Renior, + /* It's safe to do ip discovery here for Renoir, * it doesn't support SRIOV. */ if (amdgpu_discovery) { r = amdgpu_discovery_reg_base_init(adev); diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 26e45fc5eb1a..0b94ec7b73e7 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -80,7 +80,7 @@ extern "C" { * * %AMDGPU_GEM_DOMAIN_GTT GPU accessible system memory, mapped into the * GPU's virtual address space via gart. Gart memory linearizes non-contiguous - * pages of system memory, allows GPU access system memory in a linezrized + * pages of system memory, allows GPU access system memory in a linearized * fashion. * * %AMDGPU_GEM_DOMAIN_VRAM Local video memory. For APUs, it is memory -- cgit v1.2.3 From 0045e0d3f42ed7d05434bb5bc16acfc793ea4891 Mon Sep 17 00:00:00 2001 From: Yixing Liu Date: Tue, 7 Dec 2021 20:49:01 +0800 Subject: RDMA/hns: Support direct wqe of userspace The current write wqe mechanism is to write to DDR first, and then notify the hardware through doorbell to read the data. Direct wqe is a mechanism to fill wqe directly into the hardware. In the case of light load, the wqe will be filled into pcie bar space of the hardware, this will reduce one memory access operation and therefore reduce the latency. SIMD instructions allows cpu to write the 512 bits at one time to device memory, thus it can be used for posting direct wqe. Add direct wqe enable switch and address mapping. Link: https://lore.kernel.org/r/20211207124901.42123-2-liangwenpeng@huawei.com Signed-off-by: Yixing Liu Signed-off-by: Wenpeng Liang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_device.h | 8 ++--- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +- drivers/infiniband/hw/hns/hns_roce_main.c | 36 +++++++++++++++---- drivers/infiniband/hw/hns/hns_roce_pd.c | 3 ++ drivers/infiniband/hw/hns/hns_roce_qp.c | 54 ++++++++++++++++++++++++++++- include/uapi/rdma/hns-abi.h | 2 ++ 6 files changed, 94 insertions(+), 12 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index e35164ae7376..bc7112a205a7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -182,6 +182,7 @@ enum { HNS_ROCE_CAP_FLAG_FRMR = BIT(8), HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL = BIT(9), HNS_ROCE_CAP_FLAG_ATOMIC = BIT(10), + HNS_ROCE_CAP_FLAG_DIRECT_WQE = BIT(12), HNS_ROCE_CAP_FLAG_SDI_MODE = BIT(14), HNS_ROCE_CAP_FLAG_STASH = BIT(17), }; @@ -228,6 +229,7 @@ struct hns_roce_uar { enum hns_roce_mmap_type { HNS_ROCE_MMAP_TYPE_DB = 1, HNS_ROCE_MMAP_TYPE_TPTR, + HNS_ROCE_MMAP_TYPE_DWQE, }; struct hns_user_mmap_entry { @@ -627,10 +629,6 @@ struct hns_roce_work { u32 queue_num; }; -enum { - HNS_ROCE_QP_CAP_DIRECT_WQE = BIT(5), -}; - struct hns_roce_qp { struct ib_qp ibqp; struct hns_roce_wq rq; @@ -675,6 +673,7 @@ struct hns_roce_qp { struct list_head node; /* all qps are on a list */ struct list_head rq_node; /* all recv qps are on a list */ struct list_head sq_node; /* all send qps are on a list */ + struct hns_user_mmap_entry *dwqe_mmap_entry; }; struct hns_roce_ib_iboe { @@ -1010,6 +1009,7 @@ struct hns_roce_dev { u32 func_num; u32 is_vf; u32 cong_algo_tmpl_id; + u64 dwqe_page; }; static inline struct hns_roce_dev *to_hr_dev(struct ib_device *ib_dev) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index bdf220dc8dd3..2d475348a6cd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1989,7 +1989,8 @@ static void set_default_caps(struct hns_roce_dev *hr_dev) caps->gid_table_len[0] = HNS_ROCE_V2_GID_INDEX_NUM; if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) { - caps->flags |= HNS_ROCE_CAP_FLAG_STASH; + caps->flags |= HNS_ROCE_CAP_FLAG_STASH | + HNS_ROCE_CAP_FLAG_DIRECT_WQE; caps->max_sq_inline = HNS_ROCE_V3_MAX_SQ_INLINE; } else { caps->max_sq_inline = HNS_ROCE_V2_MAX_SQ_INLINE; diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index a906c6078b72..d0b976a86cd5 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -310,9 +310,25 @@ hns_roce_user_mmap_entry_insert(struct ib_ucontext *ucontext, u64 address, entry->address = address; entry->mmap_type = mmap_type; - ret = rdma_user_mmap_entry_insert_exact( - ucontext, &entry->rdma_entry, length, - mmap_type == HNS_ROCE_MMAP_TYPE_DB ? 0 : 1); + switch (mmap_type) { + case HNS_ROCE_MMAP_TYPE_DB: + ret = rdma_user_mmap_entry_insert_exact( + ucontext, &entry->rdma_entry, length, 0); + break; + case HNS_ROCE_MMAP_TYPE_TPTR: + ret = rdma_user_mmap_entry_insert_exact( + ucontext, &entry->rdma_entry, length, 1); + break; + case HNS_ROCE_MMAP_TYPE_DWQE: + ret = rdma_user_mmap_entry_insert_range( + ucontext, &entry->rdma_entry, length, 2, + U32_MAX); + break; + default: + ret = -EINVAL; + break; + } + if (ret) { kfree(entry); return NULL; @@ -439,10 +455,18 @@ static int hns_roce_mmap(struct ib_ucontext *uctx, struct vm_area_struct *vma) entry = to_hns_mmap(rdma_entry); pfn = entry->address >> PAGE_SHIFT; - prot = vma->vm_page_prot; - if (entry->mmap_type != HNS_ROCE_MMAP_TYPE_TPTR) - prot = pgprot_device(prot); + switch (entry->mmap_type) { + case HNS_ROCE_MMAP_TYPE_DB: + case HNS_ROCE_MMAP_TYPE_DWQE: + prot = pgprot_device(vma->vm_page_prot); + break; + case HNS_ROCE_MMAP_TYPE_TPTR: + prot = vma->vm_page_prot; + break; + default: + return -EINVAL; + } ret = rdma_user_mmap_io(uctx, vma, pfn, rdma_entry->npages * PAGE_SIZE, prot, rdma_entry); diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c index 81ffad77ae42..03c349f7ebbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_pd.c +++ b/drivers/infiniband/hw/hns/hns_roce_pd.c @@ -115,6 +115,9 @@ int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar) } else { uar->pfn = ((pci_resource_start(hr_dev->pci_dev, 2)) >> PAGE_SHIFT); + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_DIRECT_WQE) + hr_dev->dwqe_page = + pci_resource_start(hr_dev->pci_dev, 4); } return 0; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 4fcab1611548..c84e1c23722c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -379,6 +379,11 @@ err_out: return ret; } +static void qp_user_mmap_entry_remove(struct hns_roce_qp *hr_qp) +{ + rdma_user_mmap_entry_remove(&hr_qp->dwqe_mmap_entry->rdma_entry); +} + void hns_roce_qp_remove(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) { struct xarray *xa = &hr_dev->qp_table_xa; @@ -780,7 +785,11 @@ static int alloc_qp_buf(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, goto err_inline; } + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_DIRECT_WQE) + hr_qp->en_flags |= HNS_ROCE_QP_CAP_DIRECT_WQE; + return 0; + err_inline: free_rq_inline_buf(hr_qp); @@ -822,6 +831,35 @@ static inline bool kernel_qp_has_rdb(struct hns_roce_dev *hr_dev, hns_roce_qp_has_rq(init_attr)); } +static int qp_mmap_entry(struct hns_roce_qp *hr_qp, + struct hns_roce_dev *hr_dev, + struct ib_udata *udata, + struct hns_roce_ib_create_qp_resp *resp) +{ + struct hns_roce_ucontext *uctx = + rdma_udata_to_drv_context(udata, + struct hns_roce_ucontext, ibucontext); + struct rdma_user_mmap_entry *rdma_entry; + u64 address; + + address = hr_dev->dwqe_page + hr_qp->qpn * HNS_ROCE_DWQE_SIZE; + + hr_qp->dwqe_mmap_entry = + hns_roce_user_mmap_entry_insert(&uctx->ibucontext, address, + HNS_ROCE_DWQE_SIZE, + HNS_ROCE_MMAP_TYPE_DWQE); + + if (!hr_qp->dwqe_mmap_entry) { + ibdev_err(&hr_dev->ib_dev, "failed to get dwqe mmap entry.\n"); + return -ENOMEM; + } + + rdma_entry = &hr_qp->dwqe_mmap_entry->rdma_entry; + resp->dwqe_mmap_key = rdma_user_mmap_get_offset(rdma_entry); + + return 0; +} + static int alloc_user_qp_db(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, struct ib_qp_init_attr *init_attr, @@ -909,10 +947,16 @@ static int alloc_qp_db(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, hr_qp->en_flags |= HNS_ROCE_QP_CAP_OWNER_DB; if (udata) { + if (hr_qp->en_flags & HNS_ROCE_QP_CAP_DIRECT_WQE) { + ret = qp_mmap_entry(hr_qp, hr_dev, udata, resp); + if (ret) + return ret; + } + ret = alloc_user_qp_db(hr_dev, hr_qp, init_attr, udata, ucmd, resp); if (ret) - return ret; + goto err_remove_qp; } else { ret = alloc_kernel_qp_db(hr_dev, hr_qp, init_attr); if (ret) @@ -920,6 +964,12 @@ static int alloc_qp_db(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, } return 0; + +err_remove_qp: + if (hr_qp->en_flags & HNS_ROCE_QP_CAP_DIRECT_WQE) + qp_user_mmap_entry_remove(hr_qp); + + return ret; } static void free_qp_db(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, @@ -933,6 +983,8 @@ static void free_qp_db(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, hns_roce_db_unmap_user(uctx, &hr_qp->rdb); if (hr_qp->en_flags & HNS_ROCE_QP_CAP_SQ_RECORD_DB) hns_roce_db_unmap_user(uctx, &hr_qp->sdb); + if (hr_qp->en_flags & HNS_ROCE_QP_CAP_DIRECT_WQE) + qp_user_mmap_entry_remove(hr_qp); } else { if (hr_qp->en_flags & HNS_ROCE_QP_CAP_RQ_RECORD_DB) hns_roce_free_db(hr_dev, &hr_qp->rdb); diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index 42b177655560..f6fde06db4b4 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -77,10 +77,12 @@ enum hns_roce_qp_cap_flags { HNS_ROCE_QP_CAP_RQ_RECORD_DB = 1 << 0, HNS_ROCE_QP_CAP_SQ_RECORD_DB = 1 << 1, HNS_ROCE_QP_CAP_OWNER_DB = 1 << 2, + HNS_ROCE_QP_CAP_DIRECT_WQE = 1 << 5, }; struct hns_roce_ib_create_qp_resp { __aligned_u64 cap_flags; + __aligned_u64 dwqe_mmap_key; }; struct hns_roce_ib_alloc_ucontext_resp { -- cgit v1.2.3 From 6813b1928758ce64fabbb8ef157f994b7c2235fa Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Tue, 14 Dec 2021 15:16:04 -0800 Subject: mptcp: add missing documented NL params 'loc_id' and 'rem_id' are set in all events linked to subflows but those were missing in the events description in the comments. Fixes: b911c97c7dc7 ("mptcp: add netlink event support") Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c8cc46f80a16..f106a3941cdf 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -136,19 +136,21 @@ struct mptcp_info { * MPTCP_EVENT_REMOVED: token, rem_id * An address has been lost by the peer. * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, - * if_idx [, error] + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, + * saddr4 | saddr6, daddr4 | daddr6, sport, + * dport, backup, if_idx [, error] * A new subflow has been established. 'error' should not be set. * - * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] + * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] * A subflow has been closed. An error (copy of sk_err) could be set if an * error has been detected for this subflow. * - * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] - * The priority of a subflow has changed. 'error' should not be set. + * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] + * The priority of a subflow has changed. 'error' should not be set. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, -- cgit v1.2.3 From d61fd650e9d206a71fda789f02a1ced4b19944c4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:29 +0200 Subject: fanotify: introduce group flag FAN_REPORT_TARGET_FID FAN_REPORT_FID is ambiguous in that it reports the fid of the child for some events and the fid of the parent for create/delete/move events. The new FAN_REPORT_TARGET_FID flag is an implicit request to report the fid of the target object of the operation (a.k.a the child inode) also in create/delete/move events in addition to the fid of the parent and the name of the child. To reduce the test matrix for uninteresting use cases, the new FAN_REPORT_TARGET_FID flag requires both FAN_REPORT_NAME and FAN_REPORT_FID. The convenience macro FAN_REPORT_DFID_NAME_TARGET combines FAN_REPORT_TARGET_FID with all the required flags. Link: https://lore.kernel.org/r/20211129201537.1932819-4-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 48 ++++++++++++++++++++++++++++---------- fs/notify/fanotify/fanotify_user.c | 11 ++++++++- include/linux/fanotify.h | 2 +- include/uapi/linux/fanotify.h | 4 ++++ 4 files changed, 51 insertions(+), 14 deletions(-) (limited to 'include/uapi') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 652fe84cb8ac..85e542b164c8 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -458,17 +458,41 @@ out_err: } /* - * The inode to use as identifier when reporting fid depends on the event. - * Report the modified directory inode on dirent modification events. - * Report the "victim" inode otherwise. + * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for + * some events and the fid of the parent for create/delete/move events. + * + * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported + * also in create/delete/move events in addition to the fid of the parent + * and the name of the child. + */ +static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask) +{ + if (mask & ALL_FSNOTIFY_DIRENT_EVENTS) + return (fid_mode & FAN_REPORT_TARGET_FID); + + return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR); +} + +/* + * The inode to use as identifier when reporting fid depends on the event + * and the group flags. + * + * With the group flag FAN_REPORT_TARGET_FID, always report the child fid. + * + * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory + * fid on dirent events and the child fid otherwise. + * * For example: - * FS_ATTRIB reports the child inode even if reported on a watched parent. - * FS_CREATE reports the modified dir inode and not the created inode. + * FS_ATTRIB reports the child fid even if reported on a watched parent. + * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID. + * and reports the created child fid with FAN_REPORT_TARGET_FID. */ static struct inode *fanotify_fid_inode(u32 event_mask, const void *data, - int data_type, struct inode *dir) + int data_type, struct inode *dir, + unsigned int fid_mode) { - if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) + if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) && + !(fid_mode & FAN_REPORT_TARGET_FID)) return dir; return fsnotify_data_inode(data, data_type); @@ -647,10 +671,11 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, { struct fanotify_event *event = NULL; gfp_t gfp = GFP_KERNEL_ACCOUNT; - struct inode *id = fanotify_fid_inode(mask, data, data_type, dir); + unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); + struct inode *id = fanotify_fid_inode(mask, data, data_type, dir, + fid_mode); struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir); const struct path *path = fsnotify_data_path(data, data_type); - unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); struct mem_cgroup *old_memcg; struct inode *child = NULL; bool name_event = false; @@ -660,11 +685,10 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) { /* - * With both flags FAN_REPORT_DIR_FID and FAN_REPORT_FID, we - * report the child fid for events reported on a non-dir child + * For certain events and group flags, report the child fid * in addition to reporting the parent fid and maybe child name. */ - if ((fid_mode & FAN_REPORT_FID) && id != dirid && !ondir) + if (fanotify_report_child_fid(fid_mode, mask) && id != dirid) child = id; id = dirid; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ab24c37f1fdf..00bbc29712bb 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1275,6 +1275,15 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID)) return -EINVAL; + /* + * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID + * and is used as an indication to report both dir and child fid on all + * dirent events. + */ + if ((fid_mode & FAN_REPORT_TARGET_FID) && + (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) + return -EINVAL; + f_flags = O_RDWR | FMODE_NONOTIFY; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; @@ -1667,7 +1676,7 @@ static int __init fanotify_user_setup(void) FANOTIFY_DEFAULT_MAX_USER_MARKS); BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 11); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 616af2ea20f3..376e050e6f38 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -25,7 +25,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FANOTIFY_PERM_CLASSES) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) #define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index bd1932c2074d..60f73639a896 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -57,9 +57,13 @@ #define FAN_REPORT_FID 0x00000200 /* Report unique file id */ #define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ #define FAN_REPORT_NAME 0x00000800 /* Report events with name */ +#define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ /* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ #define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) +/* Convenience macro - FAN_REPORT_TARGET_FID requires all other FID flags */ +#define FAN_REPORT_DFID_NAME_TARGET (FAN_REPORT_DFID_NAME | \ + FAN_REPORT_FID | FAN_REPORT_TARGET_FID) /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ -- cgit v1.2.3 From 3982534ba5ce45e890b2f5ef5e7372c1accd14c7 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:34 +0200 Subject: fanotify: record old and new parent and name in FAN_RENAME event In the special case of FAN_RENAME event, we record both the old and new parent and name. Link: https://lore.kernel.org/r/20211129201537.1932819-9-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 42 ++++++++++++++++++++++++++++++++++++++---- include/uapi/linux/fanotify.h | 2 ++ 2 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 5f184b2d6ea7..db81eab90544 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -592,21 +592,28 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir, __kernel_fsid_t *fsid, const struct qstr *name, struct inode *child, + struct dentry *moved, unsigned int *hash, gfp_t gfp) { struct fanotify_name_event *fne; struct fanotify_info *info; struct fanotify_fh *dfh, *ffh; + struct inode *dir2 = moved ? d_inode(moved->d_parent) : NULL; + const struct qstr *name2 = moved ? &moved->d_name : NULL; unsigned int dir_fh_len = fanotify_encode_fh_len(dir); + unsigned int dir2_fh_len = fanotify_encode_fh_len(dir2); unsigned int child_fh_len = fanotify_encode_fh_len(child); unsigned long name_len = name ? name->len : 0; + unsigned long name2_len = name2 ? name2->len : 0; unsigned int len, size; /* Reserve terminating null byte even for empty name */ - size = sizeof(*fne) + name_len + 1; + size = sizeof(*fne) + name_len + name2_len + 2; if (dir_fh_len) size += FANOTIFY_FH_HDR_LEN + dir_fh_len; + if (dir2_fh_len) + size += FANOTIFY_FH_HDR_LEN + dir2_fh_len; if (child_fh_len) size += FANOTIFY_FH_HDR_LEN + child_fh_len; fne = kmalloc(size, gfp); @@ -623,6 +630,11 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir, len = fanotify_encode_fh(dfh, dir, dir_fh_len, hash, 0); fanotify_info_set_dir_fh(info, len); } + if (dir2_fh_len) { + dfh = fanotify_info_dir2_fh(info); + len = fanotify_encode_fh(dfh, dir2, dir2_fh_len, hash, 0); + fanotify_info_set_dir2_fh(info, len); + } if (child_fh_len) { ffh = fanotify_info_file_fh(info); len = fanotify_encode_fh(ffh, child, child_fh_len, hash, 0); @@ -632,11 +644,22 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir, fanotify_info_copy_name(info, name); *hash ^= full_name_hash((void *)name_len, name->name, name_len); } + if (name2_len) { + fanotify_info_copy_name2(info, name2); + *hash ^= full_name_hash((void *)name2_len, name2->name, + name2_len); + } pr_debug("%s: size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n", __func__, size, dir_fh_len, child_fh_len, info->name_len, info->name_len, fanotify_info_name(info)); + if (dir2_fh_len) { + pr_debug("%s: dir2_fh_len=%u name2_len=%u name2='%.*s'\n", + __func__, dir2_fh_len, info->name2_len, + info->name2_len, fanotify_info_name2(info)); + } + return &fne->fae; } @@ -692,6 +715,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir); const struct path *path = fsnotify_data_path(data, data_type); struct mem_cgroup *old_memcg; + struct dentry *moved = NULL; struct inode *child = NULL; bool name_event = false; unsigned int hash = 0; @@ -727,6 +751,15 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) { name_event = true; } + + /* + * In the special case of FAN_RENAME event, we record both + * old and new parent+name. + * 'dirid' and 'file_name' are the old parent+name and + * 'moved' has the new parent+name. + */ + if (mask & FAN_RENAME) + moved = fsnotify_data_dentry(data, data_type); } /* @@ -748,9 +781,9 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, } else if (fanotify_is_error_event(mask)) { event = fanotify_alloc_error_event(group, fsid, data, data_type, &hash); - } else if (name_event && (file_name || child)) { - event = fanotify_alloc_name_event(id, fsid, file_name, child, - &hash, gfp); + } else if (name_event && (file_name || moved || child)) { + event = fanotify_alloc_name_event(dirid, fsid, file_name, child, + moved, &hash, gfp); } else if (fid_mode) { event = fanotify_alloc_fid_event(id, fsid, &hash, gfp); } else { @@ -860,6 +893,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); + BUILD_BUG_ON(FAN_RENAME != FS_RENAME); BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20); diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 60f73639a896..9d0e2dc5767b 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -28,6 +28,8 @@ #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ +#define FAN_RENAME 0x10000000 /* File was renamed */ + #define FAN_ONDIR 0x40000000 /* Event occurred against dir */ /* helper events */ -- cgit v1.2.3 From 7326e382c21e9c23c89c88369afdc90b82a14da8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:36 +0200 Subject: fanotify: report old and/or new parent+name in FAN_RENAME event In the special case of FAN_RENAME event, we report old or new or both old and new parent+name. A single info record will be reported if either the old or new dir is watched and two records will be reported if both old and new dir (or their filesystem) are watched. The old and new parent+name are reported using new info record types FAN_EVENT_INFO_TYPE_{OLD,NEW}_DFID_NAME, so if a single info record is reported, it is clear to the application, to which dir entry the fid+name info is referring to. Link: https://lore.kernel.org/r/20211129201537.1932819-11-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 7 +++++ fs/notify/fanotify/fanotify.h | 18 +++++++++++++ fs/notify/fanotify/fanotify_user.c | 52 ++++++++++++++++++++++++++++++++++---- include/uapi/linux/fanotify.h | 6 +++++ 4 files changed, 78 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 14bc0f12cc9f..0da305b6f3e2 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -153,6 +153,13 @@ static bool fanotify_should_merge(struct fanotify_event *old, if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR)) return false; + /* + * FAN_RENAME event is reported with special info record types, + * so we cannot merge it with other events. + */ + if ((old->mask & FAN_RENAME) != (new->mask & FAN_RENAME)) + return false; + switch (old->type) { case FANOTIFY_EVENT_TYPE_PATH: return fanotify_path_equal(fanotify_event_path(old), diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 8fa3bc0effd4..a3d5b751cac5 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -373,6 +373,13 @@ static inline int fanotify_event_dir_fh_len(struct fanotify_event *event) return info ? fanotify_info_dir_fh_len(info) : 0; } +static inline int fanotify_event_dir2_fh_len(struct fanotify_event *event) +{ + struct fanotify_info *info = fanotify_event_info(event); + + return info ? fanotify_info_dir2_fh_len(info) : 0; +} + static inline bool fanotify_event_has_object_fh(struct fanotify_event *event) { /* For error events, even zeroed fh are reported. */ @@ -386,6 +393,17 @@ static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event) return fanotify_event_dir_fh_len(event) > 0; } +static inline bool fanotify_event_has_dir2_fh(struct fanotify_event *event) +{ + return fanotify_event_dir2_fh_len(event) > 0; +} + +static inline bool fanotify_event_has_any_dir_fh(struct fanotify_event *event) +{ + return fanotify_event_has_dir_fh(event) || + fanotify_event_has_dir2_fh(event); +} + struct fanotify_path_event { struct fanotify_event fae; struct path path; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index e4a11f56782d..eb2a0251b318 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -129,12 +129,29 @@ static int fanotify_fid_info_len(int fh_len, int name_len) FANOTIFY_EVENT_ALIGN); } +/* FAN_RENAME may have one or two dir+name info records */ +static int fanotify_dir_name_info_len(struct fanotify_event *event) +{ + struct fanotify_info *info = fanotify_event_info(event); + int dir_fh_len = fanotify_event_dir_fh_len(event); + int dir2_fh_len = fanotify_event_dir2_fh_len(event); + int info_len = 0; + + if (dir_fh_len) + info_len += fanotify_fid_info_len(dir_fh_len, + info->name_len); + if (dir2_fh_len) + info_len += fanotify_fid_info_len(dir2_fh_len, + info->name2_len); + + return info_len; +} + static size_t fanotify_event_len(unsigned int info_mode, struct fanotify_event *event) { size_t event_len = FAN_EVENT_METADATA_LEN; struct fanotify_info *info; - int dir_fh_len; int fh_len; int dot_len = 0; @@ -146,9 +163,8 @@ static size_t fanotify_event_len(unsigned int info_mode, info = fanotify_event_info(event); - if (fanotify_event_has_dir_fh(event)) { - dir_fh_len = fanotify_event_dir_fh_len(event); - event_len += fanotify_fid_info_len(dir_fh_len, info->name_len); + if (fanotify_event_has_any_dir_fh(event)) { + event_len += fanotify_dir_name_info_len(event); } else if ((info_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { /* @@ -379,6 +395,8 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, return -EFAULT; break; case FAN_EVENT_INFO_TYPE_DFID_NAME: + case FAN_EVENT_INFO_TYPE_OLD_DFID_NAME: + case FAN_EVENT_INFO_TYPE_NEW_DFID_NAME: if (WARN_ON_ONCE(!name || !name_len)) return -EFAULT; break; @@ -478,11 +496,19 @@ static int copy_info_records_to_user(struct fanotify_event *event, unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; /* - * Event info records order is as follows: dir fid + name, child fid. + * Event info records order is as follows: + * 1. dir fid + name + * 2. (optional) new dir fid + new name + * 3. (optional) child fid */ if (fanotify_event_has_dir_fh(event)) { info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : FAN_EVENT_INFO_TYPE_DFID; + + /* FAN_RENAME uses special info types */ + if (event->mask & FAN_RENAME) + info_type = FAN_EVENT_INFO_TYPE_OLD_DFID_NAME; + ret = copy_fid_info_to_user(fanotify_event_fsid(event), fanotify_info_dir_fh(info), info_type, @@ -496,6 +522,22 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + /* New dir fid+name may be reported in addition to old dir fid+name */ + if (fanotify_event_has_dir2_fh(event)) { + info_type = FAN_EVENT_INFO_TYPE_NEW_DFID_NAME; + ret = copy_fid_info_to_user(fanotify_event_fsid(event), + fanotify_info_dir2_fh(info), + info_type, + fanotify_info_name2(info), + info->name2_len, buf, count); + if (ret < 0) + return ret; + + buf += ret; + count -= ret; + total_bytes += ret; + } + if (fanotify_event_has_object_fh(event)) { const char *dot = NULL; int dot_len = 0; diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 9d0e2dc5767b..e8ac38cc2fd6 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -134,6 +134,12 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_PIDFD 4 #define FAN_EVENT_INFO_TYPE_ERROR 5 +/* Special info types for FAN_RENAME */ +#define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 +/* Reserved for FAN_EVENT_INFO_TYPE_OLD_DFID 11 */ +#define FAN_EVENT_INFO_TYPE_NEW_DFID_NAME 12 +/* Reserved for FAN_EVENT_INFO_TYPE_NEW_DFID 13 */ + /* Variable length info record following event metadata */ struct fanotify_event_info_header { __u8 info_type; -- cgit v1.2.3 From fb82437fdd8cd8ac41b1265e40a96668e33c3a8d Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 18 Nov 2021 16:13:00 +0200 Subject: PCI: Change capability register offsets to hex Convert offsets of capability registers from decimal to hex. This matches the spec documents and is less error prone. [bhelgaas: also convert other capabilities with offsets > 8] Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210825160516.GA3576414@bjorn-Precision-5520/ Link: https://lore.kernel.org/r/aa067278adacbb59a675366052714081f4980f26.1637244780.git.baruch@tkos.co.il Signed-off-by: Baruch Siach Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 138 +++++++++++++++++++++--------------------- 1 file changed, 69 insertions(+), 69 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ff6ccbc6efe9..fe86f5310d76 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -301,23 +301,23 @@ #define PCI_SID_ESR_FIC 0x20 /* First In Chassis Flag */ #define PCI_SID_CHASSIS_NR 3 /* Chassis Number */ -/* Message Signalled Interrupt registers */ +/* Message Signaled Interrupt registers */ -#define PCI_MSI_FLAGS 2 /* Message Control */ +#define PCI_MSI_FLAGS 0x02 /* Message Control */ #define PCI_MSI_FLAGS_ENABLE 0x0001 /* MSI feature enabled */ #define PCI_MSI_FLAGS_QMASK 0x000e /* Maximum queue size available */ #define PCI_MSI_FLAGS_QSIZE 0x0070 /* Message queue size configured */ #define PCI_MSI_FLAGS_64BIT 0x0080 /* 64-bit addresses allowed */ #define PCI_MSI_FLAGS_MASKBIT 0x0100 /* Per-vector masking capable */ #define PCI_MSI_RFU 3 /* Rest of capability flags */ -#define PCI_MSI_ADDRESS_LO 4 /* Lower 32 bits */ -#define PCI_MSI_ADDRESS_HI 8 /* Upper 32 bits (if PCI_MSI_FLAGS_64BIT set) */ -#define PCI_MSI_DATA_32 8 /* 16 bits of data for 32-bit devices */ -#define PCI_MSI_MASK_32 12 /* Mask bits register for 32-bit devices */ -#define PCI_MSI_PENDING_32 16 /* Pending intrs for 32-bit devices */ -#define PCI_MSI_DATA_64 12 /* 16 bits of data for 64-bit devices */ -#define PCI_MSI_MASK_64 16 /* Mask bits register for 64-bit devices */ -#define PCI_MSI_PENDING_64 20 /* Pending intrs for 64-bit devices */ +#define PCI_MSI_ADDRESS_LO 0x04 /* Lower 32 bits */ +#define PCI_MSI_ADDRESS_HI 0x08 /* Upper 32 bits (if PCI_MSI_FLAGS_64BIT set) */ +#define PCI_MSI_DATA_32 0x08 /* 16 bits of data for 32-bit devices */ +#define PCI_MSI_MASK_32 0x0c /* Mask bits register for 32-bit devices */ +#define PCI_MSI_PENDING_32 0x10 /* Pending intrs for 32-bit devices */ +#define PCI_MSI_DATA_64 0x0c /* 16 bits of data for 64-bit devices */ +#define PCI_MSI_MASK_64 0x10 /* Mask bits register for 64-bit devices */ +#define PCI_MSI_PENDING_64 0x14 /* Pending intrs for 64-bit devices */ /* MSI-X registers (in MSI-X capability) */ #define PCI_MSIX_FLAGS 2 /* Message Control */ @@ -335,10 +335,10 @@ /* MSI-X Table entry format (in memory mapped by a BAR) */ #define PCI_MSIX_ENTRY_SIZE 16 -#define PCI_MSIX_ENTRY_LOWER_ADDR 0 /* Message Address */ -#define PCI_MSIX_ENTRY_UPPER_ADDR 4 /* Message Upper Address */ -#define PCI_MSIX_ENTRY_DATA 8 /* Message Data */ -#define PCI_MSIX_ENTRY_VECTOR_CTRL 12 /* Vector Control */ +#define PCI_MSIX_ENTRY_LOWER_ADDR 0x0 /* Message Address */ +#define PCI_MSIX_ENTRY_UPPER_ADDR 0x4 /* Message Upper Address */ +#define PCI_MSIX_ENTRY_DATA 0x8 /* Message Data */ +#define PCI_MSIX_ENTRY_VECTOR_CTRL 0xc /* Vector Control */ #define PCI_MSIX_ENTRY_CTRL_MASKBIT 0x00000001 /* CompactPCI Hotswap Register */ @@ -470,7 +470,7 @@ /* PCI Express capability registers */ -#define PCI_EXP_FLAGS 2 /* Capabilities register */ +#define PCI_EXP_FLAGS 0x02 /* Capabilities register */ #define PCI_EXP_FLAGS_VERS 0x000f /* Capability version */ #define PCI_EXP_FLAGS_TYPE 0x00f0 /* Device/Port type */ #define PCI_EXP_TYPE_ENDPOINT 0x0 /* Express Endpoint */ @@ -484,7 +484,7 @@ #define PCI_EXP_TYPE_RC_EC 0xa /* Root Complex Event Collector */ #define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */ #define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */ -#define PCI_EXP_DEVCAP 4 /* Device capabilities */ +#define PCI_EXP_DEVCAP 0x04 /* Device capabilities */ #define PCI_EXP_DEVCAP_PAYLOAD 0x00000007 /* Max_Payload_Size */ #define PCI_EXP_DEVCAP_PHANTOM 0x00000018 /* Phantom functions */ #define PCI_EXP_DEVCAP_EXT_TAG 0x00000020 /* Extended tags */ @@ -497,7 +497,7 @@ #define PCI_EXP_DEVCAP_PWR_VAL 0x03fc0000 /* Slot Power Limit Value */ #define PCI_EXP_DEVCAP_PWR_SCL 0x0c000000 /* Slot Power Limit Scale */ #define PCI_EXP_DEVCAP_FLR 0x10000000 /* Function Level Reset */ -#define PCI_EXP_DEVCTL 8 /* Device Control */ +#define PCI_EXP_DEVCTL 0x08 /* Device Control */ #define PCI_EXP_DEVCTL_CERE 0x0001 /* Correctable Error Reporting En. */ #define PCI_EXP_DEVCTL_NFERE 0x0002 /* Non-Fatal Error Reporting Enable */ #define PCI_EXP_DEVCTL_FERE 0x0004 /* Fatal Error Reporting Enable */ @@ -522,7 +522,7 @@ #define PCI_EXP_DEVCTL_READRQ_2048B 0x4000 /* 2048 Bytes */ #define PCI_EXP_DEVCTL_READRQ_4096B 0x5000 /* 4096 Bytes */ #define PCI_EXP_DEVCTL_BCR_FLR 0x8000 /* Bridge Configuration Retry / FLR */ -#define PCI_EXP_DEVSTA 10 /* Device Status */ +#define PCI_EXP_DEVSTA 0x0a /* Device Status */ #define PCI_EXP_DEVSTA_CED 0x0001 /* Correctable Error Detected */ #define PCI_EXP_DEVSTA_NFED 0x0002 /* Non-Fatal Error Detected */ #define PCI_EXP_DEVSTA_FED 0x0004 /* Fatal Error Detected */ @@ -530,7 +530,7 @@ #define PCI_EXP_DEVSTA_AUXPD 0x0010 /* AUX Power Detected */ #define PCI_EXP_DEVSTA_TRPND 0x0020 /* Transactions Pending */ #define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V1 12 /* v1 endpoints without link end here */ -#define PCI_EXP_LNKCAP 12 /* Link Capabilities */ +#define PCI_EXP_LNKCAP 0x0c /* Link Capabilities */ #define PCI_EXP_LNKCAP_SLS 0x0000000f /* Supported Link Speeds */ #define PCI_EXP_LNKCAP_SLS_2_5GB 0x00000001 /* LNKCAP2 SLS Vector bit 0 */ #define PCI_EXP_LNKCAP_SLS_5_0GB 0x00000002 /* LNKCAP2 SLS Vector bit 1 */ @@ -549,7 +549,7 @@ #define PCI_EXP_LNKCAP_DLLLARC 0x00100000 /* Data Link Layer Link Active Reporting Capable */ #define PCI_EXP_LNKCAP_LBNC 0x00200000 /* Link Bandwidth Notification Capability */ #define PCI_EXP_LNKCAP_PN 0xff000000 /* Port Number */ -#define PCI_EXP_LNKCTL 16 /* Link Control */ +#define PCI_EXP_LNKCTL 0x10 /* Link Control */ #define PCI_EXP_LNKCTL_ASPMC 0x0003 /* ASPM Control */ #define PCI_EXP_LNKCTL_ASPM_L0S 0x0001 /* L0s Enable */ #define PCI_EXP_LNKCTL_ASPM_L1 0x0002 /* L1 Enable */ @@ -562,7 +562,7 @@ #define PCI_EXP_LNKCTL_HAWD 0x0200 /* Hardware Autonomous Width Disable */ #define PCI_EXP_LNKCTL_LBMIE 0x0400 /* Link Bandwidth Management Interrupt Enable */ #define PCI_EXP_LNKCTL_LABIE 0x0800 /* Link Autonomous Bandwidth Interrupt Enable */ -#define PCI_EXP_LNKSTA 18 /* Link Status */ +#define PCI_EXP_LNKSTA 0x12 /* Link Status */ #define PCI_EXP_LNKSTA_CLS 0x000f /* Current Link Speed */ #define PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */ #define PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */ @@ -582,7 +582,7 @@ #define PCI_EXP_LNKSTA_LBMS 0x4000 /* Link Bandwidth Management Status */ #define PCI_EXP_LNKSTA_LABS 0x8000 /* Link Autonomous Bandwidth Status */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1 20 /* v1 endpoints with link end here */ -#define PCI_EXP_SLTCAP 20 /* Slot Capabilities */ +#define PCI_EXP_SLTCAP 0x14 /* Slot Capabilities */ #define PCI_EXP_SLTCAP_ABP 0x00000001 /* Attention Button Present */ #define PCI_EXP_SLTCAP_PCP 0x00000002 /* Power Controller Present */ #define PCI_EXP_SLTCAP_MRLSP 0x00000004 /* MRL Sensor Present */ @@ -595,7 +595,7 @@ #define PCI_EXP_SLTCAP_EIP 0x00020000 /* Electromechanical Interlock Present */ #define PCI_EXP_SLTCAP_NCCS 0x00040000 /* No Command Completed Support */ #define PCI_EXP_SLTCAP_PSN 0xfff80000 /* Physical Slot Number */ -#define PCI_EXP_SLTCTL 24 /* Slot Control */ +#define PCI_EXP_SLTCTL 0x18 /* Slot Control */ #define PCI_EXP_SLTCTL_ABPE 0x0001 /* Attention Button Pressed Enable */ #define PCI_EXP_SLTCTL_PFDE 0x0002 /* Power Fault Detected Enable */ #define PCI_EXP_SLTCTL_MRLSCE 0x0004 /* MRL Sensor Changed Enable */ @@ -617,7 +617,7 @@ #define PCI_EXP_SLTCTL_EIC 0x0800 /* Electromechanical Interlock Control */ #define PCI_EXP_SLTCTL_DLLSCE 0x1000 /* Data Link Layer State Changed Enable */ #define PCI_EXP_SLTCTL_IBPD_DISABLE 0x4000 /* In-band PD disable */ -#define PCI_EXP_SLTSTA 26 /* Slot Status */ +#define PCI_EXP_SLTSTA 0x1a /* Slot Status */ #define PCI_EXP_SLTSTA_ABP 0x0001 /* Attention Button Pressed */ #define PCI_EXP_SLTSTA_PFD 0x0002 /* Power Fault Detected */ #define PCI_EXP_SLTSTA_MRLSC 0x0004 /* MRL Sensor Changed */ @@ -627,15 +627,15 @@ #define PCI_EXP_SLTSTA_PDS 0x0040 /* Presence Detect State */ #define PCI_EXP_SLTSTA_EIS 0x0080 /* Electromechanical Interlock Status */ #define PCI_EXP_SLTSTA_DLLSC 0x0100 /* Data Link Layer State Changed */ -#define PCI_EXP_RTCTL 28 /* Root Control */ +#define PCI_EXP_RTCTL 0x1c /* Root Control */ #define PCI_EXP_RTCTL_SECEE 0x0001 /* System Error on Correctable Error */ #define PCI_EXP_RTCTL_SENFEE 0x0002 /* System Error on Non-Fatal Error */ #define PCI_EXP_RTCTL_SEFEE 0x0004 /* System Error on Fatal Error */ #define PCI_EXP_RTCTL_PMEIE 0x0008 /* PME Interrupt Enable */ #define PCI_EXP_RTCTL_CRSSVE 0x0010 /* CRS Software Visibility Enable */ -#define PCI_EXP_RTCAP 30 /* Root Capabilities */ +#define PCI_EXP_RTCAP 0x1e /* Root Capabilities */ #define PCI_EXP_RTCAP_CRSVIS 0x0001 /* CRS Software Visibility capability */ -#define PCI_EXP_RTSTA 32 /* Root Status */ +#define PCI_EXP_RTSTA 0x20 /* Root Status */ #define PCI_EXP_RTSTA_PME 0x00010000 /* PME status */ #define PCI_EXP_RTSTA_PENDING 0x00020000 /* PME pending */ /* @@ -646,7 +646,7 @@ * Use pcie_capability_read_word() and similar interfaces to use them * safely. */ -#define PCI_EXP_DEVCAP2 36 /* Device Capabilities 2 */ +#define PCI_EXP_DEVCAP2 0x24 /* Device Capabilities 2 */ #define PCI_EXP_DEVCAP2_COMP_TMOUT_DIS 0x00000010 /* Completion Timeout Disable supported */ #define PCI_EXP_DEVCAP2_ARI 0x00000020 /* Alternative Routing-ID */ #define PCI_EXP_DEVCAP2_ATOMIC_ROUTE 0x00000040 /* Atomic Op routing */ @@ -658,7 +658,7 @@ #define PCI_EXP_DEVCAP2_OBFF_MSG 0x00040000 /* New message signaling */ #define PCI_EXP_DEVCAP2_OBFF_WAKE 0x00080000 /* Re-use WAKE# for OBFF */ #define PCI_EXP_DEVCAP2_EE_PREFIX 0x00200000 /* End-End TLP Prefix */ -#define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ +#define PCI_EXP_DEVCTL2 0x28 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */ #define PCI_EXP_DEVCTL2_COMP_TMOUT_DIS 0x0010 /* Completion Timeout Disable */ #define PCI_EXP_DEVCTL2_ARI 0x0020 /* Alternative Routing-ID */ @@ -670,9 +670,9 @@ #define PCI_EXP_DEVCTL2_OBFF_MSGA_EN 0x2000 /* Enable OBFF Message type A */ #define PCI_EXP_DEVCTL2_OBFF_MSGB_EN 0x4000 /* Enable OBFF Message type B */ #define PCI_EXP_DEVCTL2_OBFF_WAKE_EN 0x6000 /* OBFF using WAKE# signaling */ -#define PCI_EXP_DEVSTA2 42 /* Device Status 2 */ -#define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V2 44 /* v2 endpoints without link end here */ -#define PCI_EXP_LNKCAP2 44 /* Link Capabilities 2 */ +#define PCI_EXP_DEVSTA2 0x2a /* Device Status 2 */ +#define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V2 0x2c /* end of v2 EPs w/o link */ +#define PCI_EXP_LNKCAP2 0x2c /* Link Capabilities 2 */ #define PCI_EXP_LNKCAP2_SLS_2_5GB 0x00000002 /* Supported Speed 2.5GT/s */ #define PCI_EXP_LNKCAP2_SLS_5_0GB 0x00000004 /* Supported Speed 5GT/s */ #define PCI_EXP_LNKCAP2_SLS_8_0GB 0x00000008 /* Supported Speed 8GT/s */ @@ -680,7 +680,7 @@ #define PCI_EXP_LNKCAP2_SLS_32_0GB 0x00000020 /* Supported Speed 32GT/s */ #define PCI_EXP_LNKCAP2_SLS_64_0GB 0x00000040 /* Supported Speed 64GT/s */ #define PCI_EXP_LNKCAP2_CROSSLINK 0x00000100 /* Crosslink supported */ -#define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ +#define PCI_EXP_LNKCTL2 0x30 /* Link Control 2 */ #define PCI_EXP_LNKCTL2_TLS 0x000f #define PCI_EXP_LNKCTL2_TLS_2_5GT 0x0001 /* Supported Speed 2.5GT/s */ #define PCI_EXP_LNKCTL2_TLS_5_0GT 0x0002 /* Supported Speed 5GT/s */ @@ -691,12 +691,12 @@ #define PCI_EXP_LNKCTL2_ENTER_COMP 0x0010 /* Enter Compliance */ #define PCI_EXP_LNKCTL2_TX_MARGIN 0x0380 /* Transmit Margin */ #define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ -#define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ -#define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */ +#define PCI_EXP_LNKSTA2 0x32 /* Link Status 2 */ +#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 */ -#define PCI_EXP_SLTCTL2 56 /* Slot Control 2 */ -#define PCI_EXP_SLTSTA2 58 /* Slot Status 2 */ +#define PCI_EXP_SLTCTL2 0x38 /* Slot Control 2 */ +#define PCI_EXP_SLTSTA2 0x3a /* Slot Status 2 */ /* Extended Capabilities (PCI-X 2.0 and Express) */ #define PCI_EXT_CAP_ID(header) (header & 0x0000ffff) @@ -742,7 +742,7 @@ #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 /* Advanced Error Reporting */ -#define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */ +#define PCI_ERR_UNCOR_STATUS 0x04 /* Uncorrectable Error Status */ #define PCI_ERR_UNC_UND 0x00000001 /* Undefined */ #define PCI_ERR_UNC_DLP 0x00000010 /* Data Link Protocol */ #define PCI_ERR_UNC_SURPDN 0x00000020 /* Surprise Down */ @@ -760,11 +760,11 @@ #define PCI_ERR_UNC_MCBTLP 0x00800000 /* MC blocked TLP */ #define PCI_ERR_UNC_ATOMEG 0x01000000 /* Atomic egress blocked */ #define PCI_ERR_UNC_TLPPRE 0x02000000 /* TLP prefix blocked */ -#define PCI_ERR_UNCOR_MASK 8 /* Uncorrectable Error Mask */ +#define PCI_ERR_UNCOR_MASK 0x08 /* Uncorrectable Error Mask */ /* Same bits as above */ -#define PCI_ERR_UNCOR_SEVER 12 /* Uncorrectable Error Severity */ +#define PCI_ERR_UNCOR_SEVER 0x0c /* Uncorrectable Error Severity */ /* Same bits as above */ -#define PCI_ERR_COR_STATUS 16 /* Correctable Error Status */ +#define PCI_ERR_COR_STATUS 0x10 /* Correctable Error Status */ #define PCI_ERR_COR_RCVR 0x00000001 /* Receiver Error Status */ #define PCI_ERR_COR_BAD_TLP 0x00000040 /* Bad TLP Status */ #define PCI_ERR_COR_BAD_DLLP 0x00000080 /* Bad DLLP Status */ @@ -773,20 +773,20 @@ #define PCI_ERR_COR_ADV_NFAT 0x00002000 /* Advisory Non-Fatal */ #define PCI_ERR_COR_INTERNAL 0x00004000 /* Corrected Internal */ #define PCI_ERR_COR_LOG_OVER 0x00008000 /* Header Log Overflow */ -#define PCI_ERR_COR_MASK 20 /* Correctable Error Mask */ +#define PCI_ERR_COR_MASK 0x14 /* Correctable Error Mask */ /* Same bits as above */ -#define PCI_ERR_CAP 24 /* Advanced Error Capabilities */ -#define PCI_ERR_CAP_FEP(x) ((x) & 31) /* First Error Pointer */ +#define PCI_ERR_CAP 0x18 /* Advanced Error Capabilities & Ctrl*/ +#define PCI_ERR_CAP_FEP(x) ((x) & 0x1f) /* First Error Pointer */ #define PCI_ERR_CAP_ECRC_GENC 0x00000020 /* ECRC Generation Capable */ #define PCI_ERR_CAP_ECRC_GENE 0x00000040 /* ECRC Generation Enable */ #define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */ #define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ -#define PCI_ERR_HEADER_LOG 28 /* Header Log Register (16 bytes) */ -#define PCI_ERR_ROOT_COMMAND 44 /* Root Error Command */ +#define PCI_ERR_HEADER_LOG 0x1c /* Header Log Register (16 bytes) */ +#define PCI_ERR_ROOT_COMMAND 0x2c /* Root Error Command */ #define PCI_ERR_ROOT_CMD_COR_EN 0x00000001 /* Correctable Err Reporting Enable */ #define PCI_ERR_ROOT_CMD_NONFATAL_EN 0x00000002 /* Non-Fatal Err Reporting Enable */ #define PCI_ERR_ROOT_CMD_FATAL_EN 0x00000004 /* Fatal Err Reporting Enable */ -#define PCI_ERR_ROOT_STATUS 48 +#define PCI_ERR_ROOT_STATUS 0x30 #define PCI_ERR_ROOT_COR_RCV 0x00000001 /* ERR_COR Received */ #define PCI_ERR_ROOT_MULTI_COR_RCV 0x00000002 /* Multiple ERR_COR */ #define PCI_ERR_ROOT_UNCOR_RCV 0x00000004 /* ERR_FATAL/NONFATAL */ @@ -795,52 +795,52 @@ #define PCI_ERR_ROOT_NONFATAL_RCV 0x00000020 /* Non-Fatal Received */ #define PCI_ERR_ROOT_FATAL_RCV 0x00000040 /* Fatal Received */ #define PCI_ERR_ROOT_AER_IRQ 0xf8000000 /* Advanced Error Interrupt Message Number */ -#define PCI_ERR_ROOT_ERR_SRC 52 /* Error Source Identification */ +#define PCI_ERR_ROOT_ERR_SRC 0x34 /* Error Source Identification */ /* Virtual Channel */ -#define PCI_VC_PORT_CAP1 4 +#define PCI_VC_PORT_CAP1 0x04 #define PCI_VC_CAP1_EVCC 0x00000007 /* extended VC count */ #define PCI_VC_CAP1_LPEVCC 0x00000070 /* low prio extended VC count */ #define PCI_VC_CAP1_ARB_SIZE 0x00000c00 -#define PCI_VC_PORT_CAP2 8 +#define PCI_VC_PORT_CAP2 0x08 #define PCI_VC_CAP2_32_PHASE 0x00000002 #define PCI_VC_CAP2_64_PHASE 0x00000004 #define PCI_VC_CAP2_128_PHASE 0x00000008 #define PCI_VC_CAP2_ARB_OFF 0xff000000 -#define PCI_VC_PORT_CTRL 12 +#define PCI_VC_PORT_CTRL 0x0c #define PCI_VC_PORT_CTRL_LOAD_TABLE 0x00000001 -#define PCI_VC_PORT_STATUS 14 +#define PCI_VC_PORT_STATUS 0x0e #define PCI_VC_PORT_STATUS_TABLE 0x00000001 -#define PCI_VC_RES_CAP 16 +#define PCI_VC_RES_CAP 0x10 #define PCI_VC_RES_CAP_32_PHASE 0x00000002 #define PCI_VC_RES_CAP_64_PHASE 0x00000004 #define PCI_VC_RES_CAP_128_PHASE 0x00000008 #define PCI_VC_RES_CAP_128_PHASE_TB 0x00000010 #define PCI_VC_RES_CAP_256_PHASE 0x00000020 #define PCI_VC_RES_CAP_ARB_OFF 0xff000000 -#define PCI_VC_RES_CTRL 20 +#define PCI_VC_RES_CTRL 0x14 #define PCI_VC_RES_CTRL_LOAD_TABLE 0x00010000 #define PCI_VC_RES_CTRL_ARB_SELECT 0x000e0000 #define PCI_VC_RES_CTRL_ID 0x07000000 #define PCI_VC_RES_CTRL_ENABLE 0x80000000 -#define PCI_VC_RES_STATUS 26 +#define PCI_VC_RES_STATUS 0x1a #define PCI_VC_RES_STATUS_TABLE 0x00000001 #define PCI_VC_RES_STATUS_NEGO 0x00000002 #define PCI_CAP_VC_BASE_SIZEOF 0x10 -#define PCI_CAP_VC_PER_VC_SIZEOF 0x0C +#define PCI_CAP_VC_PER_VC_SIZEOF 0x0c /* Power Budgeting */ -#define PCI_PWR_DSR 4 /* Data Select Register */ -#define PCI_PWR_DATA 8 /* Data Register */ +#define PCI_PWR_DSR 0x04 /* Data Select Register */ +#define PCI_PWR_DATA 0x08 /* Data Register */ #define PCI_PWR_DATA_BASE(x) ((x) & 0xff) /* Base Power */ #define PCI_PWR_DATA_SCALE(x) (((x) >> 8) & 3) /* Data Scale */ #define PCI_PWR_DATA_PM_SUB(x) (((x) >> 10) & 7) /* PM Sub State */ #define PCI_PWR_DATA_PM_STATE(x) (((x) >> 13) & 3) /* PM State */ #define PCI_PWR_DATA_TYPE(x) (((x) >> 15) & 7) /* Type */ #define PCI_PWR_DATA_RAIL(x) (((x) >> 18) & 7) /* Power Rail */ -#define PCI_PWR_CAP 12 /* Capability */ +#define PCI_PWR_CAP 0x0c /* Capability */ #define PCI_PWR_CAP_BUDGET(x) ((x) & 1) /* Included in system budget */ -#define PCI_EXT_CAP_PWR_SIZEOF 16 +#define PCI_EXT_CAP_PWR_SIZEOF 0x10 /* Root Complex Event Collector Endpoint Association */ #define PCI_RCEC_RCIEP_BITMAP 4 /* Associated Bitmap for RCiEPs */ @@ -964,7 +964,7 @@ #define PCI_SRIOV_VFM_MI 0x1 /* Dormant.MigrateIn */ #define PCI_SRIOV_VFM_MO 0x2 /* Active.MigrateOut */ #define PCI_SRIOV_VFM_AV 0x3 /* Active.Available */ -#define PCI_EXT_CAP_SRIOV_SIZEOF 64 +#define PCI_EXT_CAP_SRIOV_SIZEOF 0x40 #define PCI_LTR_MAX_SNOOP_LAT 0x4 #define PCI_LTR_MAX_NOSNOOP_LAT 0x6 @@ -1017,12 +1017,12 @@ #define PCI_TPH_LOC_NONE 0x000 /* no location */ #define PCI_TPH_LOC_CAP 0x200 /* in capability */ #define PCI_TPH_LOC_MSIX 0x400 /* in MSI-X */ -#define PCI_TPH_CAP_ST_MASK 0x07FF0000 /* st table mask */ -#define PCI_TPH_CAP_ST_SHIFT 16 /* st table shift */ -#define PCI_TPH_BASE_SIZEOF 12 /* size with no st table */ +#define PCI_TPH_CAP_ST_MASK 0x07FF0000 /* ST table mask */ +#define PCI_TPH_CAP_ST_SHIFT 16 /* ST table shift */ +#define PCI_TPH_BASE_SIZEOF 0xc /* size with no ST table */ /* Downstream Port Containment */ -#define PCI_EXP_DPC_CAP 4 /* DPC Capability */ +#define PCI_EXP_DPC_CAP 0x04 /* DPC Capability */ #define PCI_EXP_DPC_IRQ 0x001F /* Interrupt Message Number */ #define PCI_EXP_DPC_CAP_RP_EXT 0x0020 /* Root Port Extensions */ #define PCI_EXP_DPC_CAP_POISONED_TLP 0x0040 /* Poisoned TLP Egress Blocking Supported */ @@ -1030,19 +1030,19 @@ #define PCI_EXP_DPC_RP_PIO_LOG_SIZE 0x0F00 /* RP PIO Log Size */ #define PCI_EXP_DPC_CAP_DL_ACTIVE 0x1000 /* ERR_COR signal on DL_Active supported */ -#define PCI_EXP_DPC_CTL 6 /* DPC control */ +#define PCI_EXP_DPC_CTL 0x06 /* DPC control */ #define PCI_EXP_DPC_CTL_EN_FATAL 0x0001 /* Enable trigger on ERR_FATAL message */ #define PCI_EXP_DPC_CTL_EN_NONFATAL 0x0002 /* Enable trigger on ERR_NONFATAL message */ #define PCI_EXP_DPC_CTL_INT_EN 0x0008 /* DPC Interrupt Enable */ -#define PCI_EXP_DPC_STATUS 8 /* DPC Status */ +#define PCI_EXP_DPC_STATUS 0x08 /* DPC Status */ #define PCI_EXP_DPC_STATUS_TRIGGER 0x0001 /* Trigger Status */ #define PCI_EXP_DPC_STATUS_TRIGGER_RSN 0x0006 /* Trigger Reason */ #define PCI_EXP_DPC_STATUS_INTERRUPT 0x0008 /* Interrupt Status */ #define PCI_EXP_DPC_RP_BUSY 0x0010 /* Root Port Busy */ #define PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT 0x0060 /* Trig Reason Extension */ -#define PCI_EXP_DPC_SOURCE_ID 10 /* DPC Source Identifier */ +#define PCI_EXP_DPC_SOURCE_ID 0x0A /* DPC Source Identifier */ #define PCI_EXP_DPC_RP_PIO_STATUS 0x0C /* RP PIO Status */ #define PCI_EXP_DPC_RP_PIO_MASK 0x10 /* RP PIO Mask */ -- cgit v1.2.3 From 006ea1b5822f9019bd722ffc6242bc0880879e3d Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Wed, 15 Dec 2021 10:17:37 +0100 Subject: drm/fourcc: Add packed 10bit YUV 4:2:0 format Adds a format that is 3 10bit YUV 4:2:0 samples packed into a 32bit word (with 2 spare bits). Supported on Broadcom BCM2711 chips. Signed-off-by: Dave Stevenson Signed-off-by: Maxime Ripard Acked-by: Thomas Zimmermann Link: https://lore.kernel.org/r/20211215091739.135042-2-maxime@cerno.tech --- drivers/gpu/drm/drm_fourcc.c | 3 +++ include/uapi/drm/drm_fourcc.h | 11 +++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 25837b1d6639..07741b678798 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -269,6 +269,9 @@ const struct drm_format_info *__drm_format_info(u32 format) .num_planes = 3, .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0, .vsub = 0, .is_yuv = true }, + { .format = DRM_FORMAT_P030, .depth = 0, .num_planes = 2, + .char_per_block = { 4, 8, 0 }, .block_w = { 3, 3, 0 }, .block_h = { 1, 1, 0 }, + .hsub = 2, .vsub = 2, .is_yuv = true}, }; unsigned int i; diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 7f652c96845b..fc0c1454d275 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -314,6 +314,13 @@ extern "C" { */ #define DRM_FORMAT_P016 fourcc_code('P', '0', '1', '6') /* 2x2 subsampled Cr:Cb plane 16 bits per channel */ +/* 2 plane YCbCr420. + * 3 10 bit components and 2 padding bits packed into 4 bytes. + * index 0 = Y plane, [31:0] x:Y2:Y1:Y0 2:10:10:10 little endian + * index 1 = Cr:Cb plane, [63:0] x:Cr2:Cb2:Cr1:x:Cb1:Cr0:Cb0 [2:10:10:10:2:10:10:10] little endian + */ +#define DRM_FORMAT_P030 fourcc_code('P', '0', '3', '0') /* 2x2 subsampled Cr:Cb plane 10 bits per channel packed */ + /* 3 plane non-subsampled (444) YCbCr * 16 bits per component, but only 10 bits are used and 6 bits are padded * index 0: Y plane, [15:0] Y:x [10:6] little endian @@ -854,6 +861,10 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) * and UV. Some SAND-using hardware stores UV in a separate tiled * image from Y to reduce the column height, which is not supported * with these modifiers. + * + * The DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT modifier is also + * supported for DRM_FORMAT_P030 where the columns remain as 128 bytes + * wide, but as this is a 10 bpp format that translates to 96 pixels. */ #define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \ -- cgit v1.2.3 From cb1c4aba055f928ffae0c868e8dfe08eeab302e7 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Mon, 6 Dec 2021 14:47:46 +0530 Subject: perf: Add new macros for mem_hops field Add new macros for mem_hops field which can be used to represent remote-node, socket and board level details. Currently the code had macro for HOPS_0, which corresponds to data coming from another core but same node. Add new macros for HOPS_1 to HOPS_3 to represent remote-node, socket and board level data. For ex: Encodings for mem_hops fields with L2 cache: L2 - local L2 L2 | REMOTE | HOPS_0 - remote core, same node L2 L2 | REMOTE | HOPS_1 - remote node, same socket L2 L2 | REMOTE | HOPS_2 - remote socket, same board L2 L2 | REMOTE | HOPS_3 - remote board L2 Signed-off-by: Kajol Jain Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211206091749.87585-2-kjain@linux.ibm.com --- include/uapi/linux/perf_event.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index bd8860eeb291..1b65042ab1db 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1332,7 +1332,10 @@ union perf_mem_data_src { /* hop level */ #define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -/* 2-7 available */ +#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ +#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ +#define PERF_MEM_HOPS_3 0x04 /* remote board */ +/* 5-7 available */ #define PERF_MEM_HOPS_SHIFT 43 #define PERF_MEM_S(a, s) \ -- cgit v1.2.3 From 7adc576512110ef32b0424a727ee1d04359fc205 Mon Sep 17 00:00:00 2001 From: Baowen Zheng Date: Fri, 17 Dec 2021 19:16:23 +0100 Subject: flow_offload: add skip_hw and skip_sw to control if offload the action We add skip_hw and skip_sw for user to control if offload the action to hardware. We also add in_hw_count for user to indicate if the action is offloaded to any hardware. Signed-off-by: Baowen Zheng Signed-off-by: Simon Horman Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + include/uapi/linux/pkt_cls.h | 9 +++-- net/sched/act_api.c | 83 ++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 84 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/net/act_api.h b/include/net/act_api.h index b418bb0e44e0..15c6a881817d 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -44,6 +44,7 @@ struct tc_action { u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; + u32 in_hw_count; }; #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 6836ccb9c45d..ee38b35c3f57 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -19,13 +19,16 @@ enum { TCA_ACT_FLAGS, TCA_ACT_HW_STATS, TCA_ACT_USED_HW_STATS, + TCA_ACT_IN_HW_COUNT, __TCA_ACT_MAX }; /* See other TCA_ACT_FLAGS_ * flags in include/net/act_api.h. */ -#define TCA_ACT_FLAGS_NO_PERCPU_STATS 1 /* Don't use percpu allocator for - * actions stats. - */ +#define TCA_ACT_FLAGS_NO_PERCPU_STATS (1 << 0) /* Don't use percpu allocator for + * actions stats. + */ +#define TCA_ACT_FLAGS_SKIP_HW (1 << 1) /* don't offload action to HW */ +#define TCA_ACT_FLAGS_SKIP_SW (1 << 2) /* don't use action in SW */ /* tca HW stats type * When user does not pass the attribute, he does not care. diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 5c21401b0555..d446e89ececc 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -131,6 +131,12 @@ static void free_tcf(struct tc_action *p) kfree(p); } +static void offload_action_hw_count_set(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count = hw_count; +} + static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) { if (is_tcf_pedit(act)) @@ -139,6 +145,29 @@ static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) return 1; } +static bool tc_act_skip_hw(u32 flags) +{ + return (flags & TCA_ACT_FLAGS_SKIP_HW) ? true : false; +} + +static bool tc_act_skip_sw(u32 flags) +{ + return (flags & TCA_ACT_FLAGS_SKIP_SW) ? true : false; +} + +static bool tc_act_in_hw(struct tc_action *act) +{ + return !!act->in_hw_count; +} + +/* SKIP_HW and SKIP_SW are mutually exclusive flags. */ +static bool tc_act_flags_valid(u32 flags) +{ + flags &= TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW; + + return flags ^ (TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW); +} + static int offload_action_init(struct flow_offload_action *fl_action, struct tc_action *act, enum offload_act_command cmd, @@ -155,6 +184,7 @@ static int offload_action_init(struct flow_offload_action *fl_action, } static int tcf_action_offload_cmd(struct flow_offload_action *fl_act, + u32 *hw_count, struct netlink_ext_ack *extack) { int err; @@ -164,6 +194,9 @@ static int tcf_action_offload_cmd(struct flow_offload_action *fl_act, if (err < 0) return err; + if (hw_count) + *hw_count = err; + return 0; } @@ -171,12 +204,17 @@ static int tcf_action_offload_cmd(struct flow_offload_action *fl_act, static int tcf_action_offload_add(struct tc_action *action, struct netlink_ext_ack *extack) { + bool skip_sw = tc_act_skip_sw(action->tcfa_flags); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; struct flow_offload_action *fl_action; + u32 in_hw_count = 0; int num, err = 0; + if (tc_act_skip_hw(action->tcfa_flags)) + return 0; + num = tcf_offload_act_num_actions_single(action); fl_action = offload_action_alloc(num); if (!fl_action) @@ -193,7 +231,13 @@ static int tcf_action_offload_add(struct tc_action *action, goto fl_err; } - err = tcf_action_offload_cmd(fl_action, extack); + err = tcf_action_offload_cmd(fl_action, &in_hw_count, extack); + if (!err) + offload_action_hw_count_set(action, in_hw_count); + + if (skip_sw && !tc_act_in_hw(action)) + err = -EINVAL; + tc_cleanup_offload_action(&fl_action->action); fl_err: @@ -205,13 +249,24 @@ fl_err: static int tcf_action_offload_del(struct tc_action *action) { struct flow_offload_action fl_act = {}; + u32 in_hw_count = 0; int err = 0; + if (!tc_act_in_hw(action)) + return 0; + err = offload_action_init(&fl_act, action, FLOW_ACT_DESTROY, NULL); if (err) return err; - return tcf_action_offload_cmd(&fl_act, NULL); + err = tcf_action_offload_cmd(&fl_act, &in_hw_count, NULL); + if (err) + return err; + + if (action->in_hw_count != in_hw_count) + return -EINVAL; + + return 0; } static void tcf_action_cleanup(struct tc_action *p) @@ -821,6 +876,9 @@ restart_act_graph: jmp_prgcnt -= 1; continue; } + + if (tc_act_skip_sw(a->tcfa_flags)) + continue; repeat: ret = a->ops->act(skb, a, res); if (ret == TC_ACT_REPEAT) @@ -926,6 +984,9 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) a->tcfa_flags, a->tcfa_flags)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_ACT_IN_HW_COUNT, a->in_hw_count)) + goto nla_put_failure; + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -1005,7 +1066,9 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_COOKIE] = { .type = NLA_BINARY, .len = TC_COOKIE_MAX_SIZE }, [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, - [TCA_ACT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAGS_NO_PERCPU_STATS), + [TCA_ACT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAGS_NO_PERCPU_STATS | + TCA_ACT_FLAGS_SKIP_HW | + TCA_ACT_FLAGS_SKIP_SW), [TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY), }; @@ -1118,8 +1181,13 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, } } hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); - if (tb[TCA_ACT_FLAGS]) + if (tb[TCA_ACT_FLAGS]) { userflags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); + if (!tc_act_flags_valid(userflags.value)) { + err = -EINVAL; + goto err_out; + } + } err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, tp, userflags.value | flags, extack); @@ -1194,8 +1262,11 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, sz += tcf_action_fill_size(act); /* Start from index 0 */ actions[i - 1] = act; - if (!tc_act_bind(flags)) - tcf_action_offload_add(act, extack); + if (!tc_act_bind(flags)) { + err = tcf_action_offload_add(act, extack); + if (tc_act_skip_sw(act->tcfa_flags) && err) + goto err; + } } /* We have to commit them all together, because if any error happened in -- cgit v1.2.3 From 28f350a67d291575492057c92ceb8518ecbace95 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 29 Nov 2021 15:32:41 +0200 Subject: cfg80211: Fix order of enum nl80211_band_iftype_attr documentation And fix the comment. Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.4ef43aff0c5d.I96dcb743bcd4f387ba4cfaa61987aeb642ad762b@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 3e734826792f..bf69ecbc1c24 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3747,13 +3747,12 @@ enum nl80211_mpath_info { * capabilities IE * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE: HE PPE thresholds information as * defined in HE capabilities IE - * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently - * defined * @NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA: HE 6GHz band capabilities (__le16), * given for all 6 GHz band channels * @NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS: vendor element capabilities that are * advertised on this band/for this iftype (binary) * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use + * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band attribute currently defined */ enum nl80211_band_iftype_attr { __NL80211_BAND_IFTYPE_ATTR_INVALID, -- cgit v1.2.3 From a083ee8a4e03348fb90a4b24cbe957b3252c7b04 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 29 Nov 2021 15:32:34 +0200 Subject: cfg80211: Add support for notifying association comeback Thought the underline driver MLME can handle association temporal rejection with comeback, it is still useful to notify this to user space, as user space might want to handle the temporal rejection differently. For example, in case the comeback time is too long, user space can deauthenticate immediately and try to associate with a different AP. Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.2467809e8cb3.I45574185b582666bc78eef0c29a4c36b478e5382@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 ++++++++++++ include/uapi/linux/nl80211.h | 7 +++++++ net/wireless/nl80211.c | 38 ++++++++++++++++++++++++++++++++++++++ net/wireless/trace.h | 17 +++++++++++++++++ 4 files changed, 74 insertions(+) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a887086cb103..c9a9073d4c2a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8287,6 +8287,18 @@ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif); +/** + * cfg80211_assoc_comeback - notification of association that was + * temporarly rejected with a comeback + * @netdev: network device + * @bss: the bss entry with which association is in progress. + * @timeout: timeout interval value TUs. + * + * this function may sleep. the caller must hold the corresponding wdev's mutex. + */ +void cfg80211_assoc_comeback(struct net_device *netdev, + struct cfg80211_bss *bss, u32 timeout); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index bf69ecbc1c24..a8e20d25252b 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1232,6 +1232,11 @@ * &NL80211_ATTR_FILS_NONCES - for FILS Nonces * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) * + * @NL80211_CMD_ASSOC_COMEBACK: notification about an association + * temporal rejection with comeback. The event includes %NL80211_ATTR_MAC + * to describe the BSSID address of the AP and %NL80211_ATTR_TIMEOUT to + * specify the timeout value. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1474,6 +1479,8 @@ enum nl80211_commands { NL80211_CMD_SET_FILS_AAD, + NL80211_CMD_ASSOC_COMEBACK, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index bfa5d7428a3f..71da0d506502 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17064,6 +17064,44 @@ static void nl80211_send_remain_on_chan_event( nlmsg_free(msg); } +void cfg80211_assoc_comeback(struct net_device *netdev, + struct cfg80211_bss *bss, u32 timeout) +{ + struct wireless_dev *wdev = netdev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct sk_buff *msg; + void *hdr; + + trace_cfg80211_assoc_comeback(wdev, bss->bssid, timeout); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_ASSOC_COMEBACK); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bss->bssid) || + nla_put_u32(msg, NL80211_ATTR_TIMEOUT, timeout)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_assoc_comeback); + void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, unsigned int duration, gfp_t gfp) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index e854d52db1a6..01710f0c8a03 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3696,6 +3696,23 @@ TRACE_EVENT(rdev_set_radar_offchan, WIPHY_PR_ARG, CHAN_DEF_PR_ARG) ); +TRACE_EVENT(cfg80211_assoc_comeback, + TP_PROTO(struct wireless_dev *wdev, const u8 *bssid, u32 timeout), + TP_ARGS(wdev, bssid, timeout), + TP_STRUCT__entry( + WDEV_ENTRY + MAC_ENTRY(bssid) + __field(u32, timeout) + ), + TP_fast_assign( + WDEV_ASSIGN; + MAC_ASSIGN(bssid, bssid); + __entry->timeout = timeout; + ), + TP_printk(WDEV_PR_FMT ", " MAC_PR_FMT ", timeout: %u TUs", + WDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->timeout) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- cgit v1.2.3 From a95bfb876fa87e2d0fa718ee61a8030ddf162d2b Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 29 Nov 2021 14:11:24 +0100 Subject: cfg80211: rename offchannel_chain structs to background_chain to avoid confusion with ETSI standard ETSI standard defines "Offchannel CAC" as: "Off-Channel CAC is performed by a number of non-continuous checks spread over a period in time. This period, which is required to determine the presence of radar signals, is defined as the Off-Channel CAC Time.. Minimum Off-Channel CAC Time 6 minutes and Maximum Off-Channel CAC Time 4 hours..". mac80211 implementation refers to a dedicated hw chain used for continuous radar monitoring. Rename offchannel_* references to background_* in order to avoid confusion with ETSI standard. Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/4204cc1d648d76b44557981713231e030a3bd991.1638190762.git.lorenzo@kernel.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 20 +++++----- include/net/mac80211.h | 10 ++--- include/uapi/linux/nl80211.h | 14 +++---- net/mac80211/cfg.c | 10 ++--- net/wireless/chan.c | 6 +-- net/wireless/core.c | 13 ++++--- net/wireless/core.h | 20 +++++----- net/wireless/mlme.c | 89 ++++++++++++++++++++++---------------------- net/wireless/nl80211.c | 8 ++-- net/wireless/rdev-ops.h | 10 ++--- net/wireless/trace.h | 2 +- 11 files changed, 102 insertions(+), 100 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c9a9073d4c2a..e29d904eccff 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4073,14 +4073,14 @@ struct mgmt_frame_regs { * those to decrypt (Re)Association Request and encrypt (Re)Association * Response frame. * - * @set_radar_offchan: Configure dedicated offchannel chain available for + * @set_radar_background: Configure dedicated offchannel chain available for * radar/CAC detection on some hw. This chain can't be used to transmit * or receive frames and it is bounded to a running wdev. - * Offchannel radar/CAC detection allows to avoid the CAC downtime + * Background radar/CAC detection allows to avoid the CAC downtime * switching to a different channel during CAC detection on the selected * radar channel. * The caller is expected to set chandef pointer to NULL in order to - * disable offchannel CAC/radar detection. + * disable background CAC/radar detection. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4413,8 +4413,8 @@ struct cfg80211_ops { struct cfg80211_color_change_settings *params); int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_fils_aad *fils_aad); - int (*set_radar_offchan)(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef); + int (*set_radar_background)(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef); }; /* @@ -7626,9 +7626,9 @@ cfg80211_radar_event(struct wiphy *wiphy, } static inline void -cfg80211_offchan_radar_event(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef, - gfp_t gfp) +cfg80211_background_radar_event(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + gfp_t gfp) { __cfg80211_radar_event(wiphy, chandef, true, gfp); } @@ -7663,13 +7663,13 @@ void cfg80211_cac_event(struct net_device *netdev, enum nl80211_radar_event event, gfp_t gfp); /** - * cfg80211_offchan_cac_abort - Channel Availability Check offchan abort event + * cfg80211_background_cac_abort - Channel Availability Check offchan abort event * @wiphy: the wiphy * * This function is called by the driver when a Channel Availability Check * (CAC) is aborted by a offchannel dedicated chain. */ -void cfg80211_offchan_cac_abort(struct wiphy *wiphy); +void cfg80211_background_cac_abort(struct wiphy *wiphy); /** * cfg80211_gtk_rekey_notify - notify userspace about driver rekeying diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 28e66cdae3ec..8907338d52b5 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3939,14 +3939,14 @@ struct ieee80211_prep_tx_info { * twt structure. * @twt_teardown_request: Update the hw with TWT teardown request received * from the peer. - * @set_radar_offchan: Configure dedicated offchannel chain available for + * @set_radar_background: Configure dedicated offchannel chain available for * radar/CAC detection on some hw. This chain can't be used to transmit * or receive frames and it is bounded to a running wdev. - * Offchannel radar/CAC detection allows to avoid the CAC downtime + * Background radar/CAC detection allows to avoid the CAC downtime * switching to a different channel during CAC detection on the selected * radar channel. * The caller is expected to set chandef pointer to NULL in order to - * disable offchannel CAC/radar detection. + * disable background CAC/radar detection. * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to * resolve a path for hardware flow offloading */ @@ -4277,8 +4277,8 @@ struct ieee80211_ops { struct ieee80211_twt_setup *twt); void (*twt_teardown_request)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u8 flowid); - int (*set_radar_offchan)(struct ieee80211_hw *hw, - struct cfg80211_chan_def *chandef); + int (*set_radar_background)(struct ieee80211_hw *hw, + struct cfg80211_chan_def *chandef); int (*net_fill_forward_path)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a8e20d25252b..5ce20fb44f24 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2646,10 +2646,10 @@ enum nl80211_commands { * Mandatory parameter for the transmitting interface to enable MBSSID. * Optional for the non-transmitting interfaces. * - * @NL80211_ATTR_RADAR_OFFCHAN: Configure dedicated offchannel chain available for - * radar/CAC detection on some hw. This chain can't be used to transmit - * or receive frames and it is bounded to a running wdev. - * Offchannel radar/CAC detection allows to avoid the CAC downtime + * @NL80211_ATTR_RADAR_BACKGROUND: Configure dedicated offchannel chain + * available for radar/CAC detection on some hw. This chain can't be used + * to transmit or receive frames and it is bounded to a running wdev. + * Background radar/CAC detection allows to avoid the CAC downtime * switching on a different channel during CAC detection on the selected * radar channel. * @@ -3159,7 +3159,7 @@ enum nl80211_attrs { NL80211_ATTR_MBSSID_CONFIG, NL80211_ATTR_MBSSID_ELEMS, - NL80211_ATTR_RADAR_OFFCHAN, + NL80211_ATTR_RADAR_BACKGROUND, /* add attributes here, update the policy in nl80211.c */ @@ -6066,7 +6066,7 @@ enum nl80211_feature_flags { * frames. Userspace has to share FILS AAD details to the driver by using * @NL80211_CMD_SET_FILS_AAD. * - * @NL80211_EXT_FEATURE_RADAR_OFFCHAN: Device supports offchannel radar/CAC + * @NL80211_EXT_FEATURE_RADAR_BACKGROUND: Device supports background radar/CAC * detection. * * @NUM_NL80211_EXT_FEATURES: number of extended features. @@ -6135,7 +6135,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_PROT_RANGE_NEGO_AND_MEASURE, NL80211_EXT_FEATURE_BSS_COLOR, NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, - NL80211_EXT_FEATURE_RADAR_OFFCHAN, + NL80211_EXT_FEATURE_RADAR_BACKGROUND, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 8f15d9f30aac..dc3746d5cdc1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4414,15 +4414,15 @@ out: } static int -ieee80211_set_radar_offchan(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef) +ieee80211_set_radar_background(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); - if (!local->ops->set_radar_offchan) + if (!local->ops->set_radar_background) return -EOPNOTSUPP; - return local->ops->set_radar_offchan(&local->hw, chandef); + return local->ops->set_radar_background(&local->hw, chandef); } const struct cfg80211_ops mac80211_config_ops = { @@ -4529,5 +4529,5 @@ const struct cfg80211_ops mac80211_config_ops = { .reset_tid_config = ieee80211_reset_tid_config, .set_sar_specs = ieee80211_set_sar_specs, .color_change = ieee80211_color_change, - .set_radar_offchan = ieee80211_set_radar_offchan, + .set_radar_background = ieee80211_set_radar_background, }; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index ac2e5677524a..eb822052d344 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -718,13 +718,13 @@ static bool cfg80211_offchan_chain_is_active(struct cfg80211_registered_device *rdev, struct ieee80211_channel *channel) { - if (!rdev->offchan_radar_wdev) + if (!rdev->background_radar_wdev) return false; - if (!cfg80211_chandef_valid(&rdev->offchan_radar_chandef)) + if (!cfg80211_chandef_valid(&rdev->background_radar_chandef)) return false; - return cfg80211_is_sub_chan(&rdev->offchan_radar_chandef, channel); + return cfg80211_is_sub_chan(&rdev->background_radar_chandef, channel); } bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, diff --git a/net/wireless/core.c b/net/wireless/core.c index c4ea903f8184..132c575c5540 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -545,9 +545,10 @@ use_default_name: INIT_WORK(&rdev->rfkill_block, cfg80211_rfkill_block_work); INIT_WORK(&rdev->conn_work, cfg80211_conn_work); INIT_WORK(&rdev->event_work, cfg80211_event_work); - INIT_WORK(&rdev->offchan_cac_abort_wk, cfg80211_offchan_cac_abort_wk); - INIT_DELAYED_WORK(&rdev->offchan_cac_done_wk, - cfg80211_offchan_cac_done_wk); + INIT_WORK(&rdev->background_cac_abort_wk, + cfg80211_background_cac_abort_wk); + INIT_DELAYED_WORK(&rdev->background_cac_done_wk, + cfg80211_background_cac_done_wk); init_waitqueue_head(&rdev->dev_wait); @@ -1057,13 +1058,13 @@ void wiphy_unregister(struct wiphy *wiphy) cancel_work_sync(&rdev->conn_work); flush_work(&rdev->event_work); cancel_delayed_work_sync(&rdev->dfs_update_channels_wk); - cancel_delayed_work_sync(&rdev->offchan_cac_done_wk); + cancel_delayed_work_sync(&rdev->background_cac_done_wk); flush_work(&rdev->destroy_work); flush_work(&rdev->sched_scan_stop_wk); flush_work(&rdev->propagate_radar_detect_wk); flush_work(&rdev->propagate_cac_done_wk); flush_work(&rdev->mgmt_registrations_update_wk); - flush_work(&rdev->offchan_cac_abort_wk); + flush_work(&rdev->background_cac_abort_wk); #ifdef CONFIG_PM if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) @@ -1212,7 +1213,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, cfg80211_pmsr_wdev_down(wdev); - cfg80211_stop_offchan_radar_detection(wdev); + cfg80211_stop_background_radar_detection(wdev); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: diff --git a/net/wireless/core.h b/net/wireless/core.h index fb8d9006d838..3a7dbd63d8c6 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -84,10 +84,10 @@ struct cfg80211_registered_device { struct delayed_work dfs_update_channels_wk; - struct wireless_dev *offchan_radar_wdev; - struct cfg80211_chan_def offchan_radar_chandef; - struct delayed_work offchan_cac_done_wk; - struct work_struct offchan_cac_abort_wk; + struct wireless_dev *background_radar_wdev; + struct cfg80211_chan_def background_radar_chandef; + struct delayed_work background_cac_done_wk; + struct work_struct background_cac_abort_wk; /* netlink port which started critical protocol (0 means not started) */ u32 crit_proto_nlportid; @@ -497,15 +497,15 @@ cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, void cfg80211_sched_dfs_chan_update(struct cfg80211_registered_device *rdev); int -cfg80211_start_offchan_radar_detection(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, - struct cfg80211_chan_def *chandef); +cfg80211_start_background_radar_detection(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef); -void cfg80211_stop_offchan_radar_detection(struct wireless_dev *wdev); +void cfg80211_stop_background_radar_detection(struct wireless_dev *wdev); -void cfg80211_offchan_cac_done_wk(struct work_struct *work); +void cfg80211_background_cac_done_wk(struct work_struct *work); -void cfg80211_offchan_cac_abort_wk(struct work_struct *work); +void cfg80211_background_cac_abort_wk(struct work_struct *work); bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, struct ieee80211_channel *chan); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index e970076e1098..c8155a483ec2 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -920,7 +920,7 @@ void __cfg80211_radar_event(struct wiphy *wiphy, cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_UNAVAILABLE); if (offchan) - queue_work(cfg80211_wq, &rdev->offchan_cac_abort_wk); + queue_work(cfg80211_wq, &rdev->background_cac_abort_wk); cfg80211_sched_dfs_chan_update(rdev); @@ -975,10 +975,10 @@ void cfg80211_cac_event(struct net_device *netdev, EXPORT_SYMBOL(cfg80211_cac_event); static void -__cfg80211_offchan_cac_event(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, - const struct cfg80211_chan_def *chandef, - enum nl80211_radar_event event) +__cfg80211_background_cac_event(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + const struct cfg80211_chan_def *chandef, + enum nl80211_radar_event event) { struct wiphy *wiphy = &rdev->wiphy; struct net_device *netdev; @@ -988,7 +988,7 @@ __cfg80211_offchan_cac_event(struct cfg80211_registered_device *rdev, if (!cfg80211_chandef_valid(chandef)) return; - if (!rdev->offchan_radar_wdev) + if (!rdev->background_radar_wdev) return; switch (event) { @@ -997,12 +997,12 @@ __cfg80211_offchan_cac_event(struct cfg80211_registered_device *rdev, memcpy(&rdev->cac_done_chandef, chandef, sizeof(*chandef)); queue_work(cfg80211_wq, &rdev->propagate_cac_done_wk); cfg80211_sched_dfs_chan_update(rdev); - wdev = rdev->offchan_radar_wdev; + wdev = rdev->background_radar_wdev; break; case NL80211_RADAR_CAC_ABORTED: - if (!cancel_delayed_work(&rdev->offchan_cac_done_wk)) + if (!cancel_delayed_work(&rdev->background_cac_done_wk)) return; - wdev = rdev->offchan_radar_wdev; + wdev = rdev->background_radar_wdev; break; case NL80211_RADAR_CAC_STARTED: break; @@ -1015,49 +1015,49 @@ __cfg80211_offchan_cac_event(struct cfg80211_registered_device *rdev, } static void -cfg80211_offchan_cac_event(struct cfg80211_registered_device *rdev, - const struct cfg80211_chan_def *chandef, - enum nl80211_radar_event event) +cfg80211_background_cac_event(struct cfg80211_registered_device *rdev, + const struct cfg80211_chan_def *chandef, + enum nl80211_radar_event event) { wiphy_lock(&rdev->wiphy); - __cfg80211_offchan_cac_event(rdev, rdev->offchan_radar_wdev, - chandef, event); + __cfg80211_background_cac_event(rdev, rdev->background_radar_wdev, + chandef, event); wiphy_unlock(&rdev->wiphy); } -void cfg80211_offchan_cac_done_wk(struct work_struct *work) +void cfg80211_background_cac_done_wk(struct work_struct *work) { struct delayed_work *delayed_work = to_delayed_work(work); struct cfg80211_registered_device *rdev; rdev = container_of(delayed_work, struct cfg80211_registered_device, - offchan_cac_done_wk); - cfg80211_offchan_cac_event(rdev, &rdev->offchan_radar_chandef, - NL80211_RADAR_CAC_FINISHED); + background_cac_done_wk); + cfg80211_background_cac_event(rdev, &rdev->background_radar_chandef, + NL80211_RADAR_CAC_FINISHED); } -void cfg80211_offchan_cac_abort_wk(struct work_struct *work) +void cfg80211_background_cac_abort_wk(struct work_struct *work) { struct cfg80211_registered_device *rdev; rdev = container_of(work, struct cfg80211_registered_device, - offchan_cac_abort_wk); - cfg80211_offchan_cac_event(rdev, &rdev->offchan_radar_chandef, - NL80211_RADAR_CAC_ABORTED); + background_cac_abort_wk); + cfg80211_background_cac_event(rdev, &rdev->background_radar_chandef, + NL80211_RADAR_CAC_ABORTED); } -void cfg80211_offchan_cac_abort(struct wiphy *wiphy) +void cfg80211_background_cac_abort(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - queue_work(cfg80211_wq, &rdev->offchan_cac_abort_wk); + queue_work(cfg80211_wq, &rdev->background_cac_abort_wk); } -EXPORT_SYMBOL(cfg80211_offchan_cac_abort); +EXPORT_SYMBOL(cfg80211_background_cac_abort); int -cfg80211_start_offchan_radar_detection(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, - struct cfg80211_chan_def *chandef) +cfg80211_start_background_radar_detection(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef) { unsigned int cac_time_ms; int err; @@ -1065,19 +1065,19 @@ cfg80211_start_offchan_radar_detection(struct cfg80211_registered_device *rdev, lockdep_assert_wiphy(&rdev->wiphy); if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_RADAR_OFFCHAN)) + NL80211_EXT_FEATURE_RADAR_BACKGROUND)) return -EOPNOTSUPP; /* Offchannel chain already locked by another wdev */ - if (rdev->offchan_radar_wdev && rdev->offchan_radar_wdev != wdev) + if (rdev->background_radar_wdev && rdev->background_radar_wdev != wdev) return -EBUSY; /* CAC already in progress on the offchannel chain */ - if (rdev->offchan_radar_wdev == wdev && - delayed_work_pending(&rdev->offchan_cac_done_wk)) + if (rdev->background_radar_wdev == wdev && + delayed_work_pending(&rdev->background_cac_done_wk)) return -EBUSY; - err = rdev_set_radar_offchan(rdev, chandef); + err = rdev_set_radar_background(rdev, chandef); if (err) return err; @@ -1085,30 +1085,31 @@ cfg80211_start_offchan_radar_detection(struct cfg80211_registered_device *rdev, if (!cac_time_ms) cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; - rdev->offchan_radar_chandef = *chandef; - rdev->offchan_radar_wdev = wdev; /* Get offchain ownership */ + rdev->background_radar_chandef = *chandef; + rdev->background_radar_wdev = wdev; /* Get offchain ownership */ - __cfg80211_offchan_cac_event(rdev, wdev, chandef, - NL80211_RADAR_CAC_STARTED); - queue_delayed_work(cfg80211_wq, &rdev->offchan_cac_done_wk, + __cfg80211_background_cac_event(rdev, wdev, chandef, + NL80211_RADAR_CAC_STARTED); + queue_delayed_work(cfg80211_wq, &rdev->background_cac_done_wk, msecs_to_jiffies(cac_time_ms)); return 0; } -void cfg80211_stop_offchan_radar_detection(struct wireless_dev *wdev) +void cfg80211_stop_background_radar_detection(struct wireless_dev *wdev) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); lockdep_assert_wiphy(wiphy); - if (wdev != rdev->offchan_radar_wdev) + if (wdev != rdev->background_radar_wdev) return; - rdev_set_radar_offchan(rdev, NULL); - rdev->offchan_radar_wdev = NULL; /* Release offchain ownership */ + rdev_set_radar_background(rdev, NULL); + rdev->background_radar_wdev = NULL; /* Release offchain ownership */ - __cfg80211_offchan_cac_event(rdev, wdev, &rdev->offchan_radar_chandef, - NL80211_RADAR_CAC_ABORTED); + __cfg80211_background_cac_event(rdev, wdev, + &rdev->background_radar_chandef, + NL80211_RADAR_CAC_ABORTED); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 71da0d506502..6ee21049b028 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -776,7 +776,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MBSSID_CONFIG] = NLA_POLICY_NESTED(nl80211_mbssid_config_policy), [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, - [NL80211_ATTR_RADAR_OFFCHAN] = { .type = NLA_FLAG }, + [NL80211_ATTR_RADAR_BACKGROUND] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -9305,9 +9305,9 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, goto unlock; } - if (nla_get_flag(info->attrs[NL80211_ATTR_RADAR_OFFCHAN])) { - err = cfg80211_start_offchan_radar_detection(rdev, wdev, - &chandef); + if (nla_get_flag(info->attrs[NL80211_ATTR_RADAR_BACKGROUND])) { + err = cfg80211_start_background_radar_detection(rdev, wdev, + &chandef); goto unlock; } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 8672b3ef99e4..439bcf52369c 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1396,17 +1396,17 @@ rdev_set_fils_aad(struct cfg80211_registered_device *rdev, } static inline int -rdev_set_radar_offchan(struct cfg80211_registered_device *rdev, - struct cfg80211_chan_def *chandef) +rdev_set_radar_background(struct cfg80211_registered_device *rdev, + struct cfg80211_chan_def *chandef) { struct wiphy *wiphy = &rdev->wiphy; int ret; - if (!rdev->ops->set_radar_offchan) + if (!rdev->ops->set_radar_background) return -EOPNOTSUPP; - trace_rdev_set_radar_offchan(wiphy, chandef); - ret = rdev->ops->set_radar_offchan(wiphy, chandef); + trace_rdev_set_radar_background(wiphy, chandef); + ret = rdev->ops->set_radar_background(wiphy, chandef); trace_rdev_return_int(wiphy, ret); return ret; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 01710f0c8a03..228079d7690a 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3677,7 +3677,7 @@ TRACE_EVENT(cfg80211_bss_color_notify, __entry->color_bitmap) ); -TRACE_EVENT(rdev_set_radar_offchan, +TRACE_EVENT(rdev_set_radar_background, TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef), TP_ARGS(wiphy, chandef), -- cgit v1.2.3 From 47301a74bbfa80cef876e646a8c5fec03c20fc8d Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Fri, 26 Nov 2021 12:55:18 +0530 Subject: nl80211: Add support to set AP settings flags with single attribute In previous method each AP settings flag is represented by a top-level flag attribute and conversion to enum cfg80211_ap_settings_flags had to be done before sending them to driver. This commit is to make it easier to define new AP settings flags and sending them to driver. This commit also deprecate sending of %NL80211_ATTR_EXTERNAL_AUTH_SUPPORT in %NL80211_CMD_START_AP. But to maintain backwards compatibility checks for %NL80211_ATTR_EXTERNAL_AUTH_SUPPORT in %NL80211_CMD_START_AP when %NL80211_ATTR_AP_SETTINGS_FLAGS not present in %NL80211_CMD_START_AP. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1637911519-21306-1-git-send-email-vjakkam@codeaurora.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 ----------- include/uapi/linux/nl80211.h | 20 +++++++++++++++++++- net/wireless/nl80211.c | 8 ++++++-- 3 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b59baf9dfd67..d19e48f9fdc6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1187,17 +1187,6 @@ struct cfg80211_unsol_bcast_probe_resp { const u8 *tmpl; }; -/** - * enum cfg80211_ap_settings_flags - AP settings flags - * - * Used by cfg80211_ap_settings - * - * @AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external authentication - */ -enum cfg80211_ap_settings_flags { - AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = BIT(0), -}; - /** * struct cfg80211_ap_settings - AP configuration * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5ce20fb44f24..ab461b2be157 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2477,7 +2477,9 @@ enum nl80211_commands { * space supports external authentication. This attribute shall be used * with %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP request. The driver * may offload authentication processing to user space if this capability - * is indicated in the respective requests from the user space. + * is indicated in the respective requests from the user space. (This flag + * attribute deprecated for %NL80211_CMD_START_AP, use + * %NL80211_ATTR_AP_SETTINGS_FLAGS) * * @NL80211_ATTR_NSS: Station's New/updated RX_NSS value notified using this * u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED. @@ -2653,6 +2655,10 @@ enum nl80211_commands { * switching on a different channel during CAC detection on the selected * radar channel. * + * @NL80211_ATTR_AP_SETTINGS_FLAGS: u32 attribute contains ap settings flags, + * enumerated in &enum nl80211_ap_settings_flags. This attribute shall be + * used with %NL80211_CMD_START_AP request. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3161,6 +3167,8 @@ enum nl80211_attrs { NL80211_ATTR_RADAR_BACKGROUND, + NL80211_ATTR_AP_SETTINGS_FLAGS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -7481,4 +7489,14 @@ enum nl80211_mbssid_config_attributes { NL80211_MBSSID_CONFIG_ATTR_MAX = __NL80211_MBSSID_CONFIG_ATTR_LAST - 1, }; +/** + * enum nl80211_ap_settings_flags - AP settings flags + * + * @NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external + * authentication. + */ +enum nl80211_ap_settings_flags { + NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = 1 << 0, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 6ee21049b028..578bff9c378b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -777,6 +777,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_NESTED(nl80211_mbssid_config_policy), [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, [NL80211_ATTR_RADAR_BACKGROUND] = { .type = NLA_FLAG }, + [NL80211_ATTR_AP_SETTINGS_FLAGS] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -5714,8 +5715,11 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) nl80211_calculate_ap_params(params); - if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) - params->flags |= AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; + if (info->attrs[NL80211_ATTR_AP_SETTINGS_FLAGS]) + params->flags = nla_get_u32( + info->attrs[NL80211_ATTR_AP_SETTINGS_FLAGS]); + else if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) + params->flags |= NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; wdev_lock(wdev); err = rdev_start_ap(rdev, dev, params); -- cgit v1.2.3 From 87c1aec15dee8bdb245aabbd181f9f9e1a4770ae Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Fri, 26 Nov 2021 12:55:19 +0530 Subject: nl80211: Add support to offload SA Query procedures for AP SME device Add a flag attribute to use in ap settings to indicate userspace supports offloading of SA Query procedures to driver. Also add AP SME device feature flag to advertise that the SA Query procedures offloaded to driver when userspace indicates support for offloading of SA Query procedures. Driver handles SA Query procedures in driver's SME it self and skip sending SA Query request or response frames to userspace when userspace indicates support for SA Query procedures offload. But if userspace doesn't advertise support for SA Query procedures offload driver shall not offload SA Query procedures handling. Also userspace with SA Query procedures offload capability shall skip SA Query specific validations when driver indicates support for handling SA Query procedures. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1637911519-21306-2-git-send-email-vjakkam@codeaurora.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ab461b2be157..d997252de986 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5760,13 +5760,15 @@ enum nl80211_tdls_operation { NL80211_TDLS_DISABLE_LINK, }; -/* +/** * enum nl80211_ap_sme_features - device-integrated AP features - * Reserved for future use, no bits are defined in - * NL80211_ATTR_DEVICE_AP_SME yet. + * @NL80211_AP_SME_SA_QUERY_OFFLOAD: SA Query procedures offloaded to driver + * when user space indicates support for SA Query procedures offload during + * "start ap" with %NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT. + */ enum nl80211_ap_sme_features { + NL80211_AP_SME_SA_QUERY_OFFLOAD = 1 << 0, }; - */ /** * enum nl80211_feature_flags - device/driver features @@ -7494,9 +7496,15 @@ enum nl80211_mbssid_config_attributes { * * @NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external * authentication. + * @NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT: Userspace supports SA Query + * procedures offload to driver. If driver advertises + * %NL80211_AP_SME_SA_QUERY_OFFLOAD in AP SME features, userspace shall + * ignore SA Query procedures and validations when this flag is set by + * userspace. */ enum nl80211_ap_settings_flags { NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = 1 << 0, + NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT = 1 << 1, }; #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From d9a8297e873eda9d47aa5895ca47dc12eca0b198 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 1 Dec 2021 11:09:25 +0100 Subject: nl82011: clarify interface combinations wrt. channels Thinking about MLD (Draft 802.11be) now, it's clear that we'll have new limitations where different stations (or links) must be on _different_ channels (or in different frequency ranges even.) Clarify that the current limit of multiple channels is a maximum and the same one is OK. Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20211201110924.2816d91b6862.I2d997abd525574529f88e941d90aeb640dbb1abf@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d997252de986..f1a9d6594df2 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5578,7 +5578,7 @@ enum nl80211_iface_limit_attrs { * => allows 8 of AP/GO that can have BI gcd >= min gcd * * numbers = [ #{STA} <= 2 ], channels = 2, max = 2 - * => allows two STAs on different channels + * => allows two STAs on the same or on different channels * * numbers = [ #{STA} <= 1, #{P2P-client,P2P-GO} <= 3 ], max = 4 * => allows a STA plus three P2P interfaces -- cgit v1.2.3 From ed98ea2128b6fd83bce13716edf8f5fe6c47f574 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Fri, 17 Dec 2021 09:01:52 +0800 Subject: audit: replace zero-length array with flexible-array member Zero-length arrays are deprecated and should be replaced with flexible-array members. Link: https://github.com/KSPP/linux/issues/78 Signed-off-by: Xiu Jianfeng Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 9176a095fefc..8eda133ca4c1 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -514,7 +514,7 @@ struct audit_rule_data { __u32 values[AUDIT_MAX_FIELDS]; __u32 fieldflags[AUDIT_MAX_FIELDS]; __u32 buflen; /* total length of string fields */ - char buf[0]; /* string fields buffer */ + char buf[]; /* string fields buffer */ }; #endif /* _UAPI_LINUX_AUDIT_H_ */ -- cgit v1.2.3 From dbcefdeb2a58039f4c81d0361056fbdd9be906a1 Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Mon, 20 Dec 2021 10:31:04 +0800 Subject: mctp: emit RTM_NEWADDR and RTM_DELADDR Userspace can receive notification of MCTP address changes via RTNLGRP_MCTP_IFADDR rtnetlink multicast group. Signed-off-by: Matt Johnston Link: https://lore.kernel.org/r/20211220023104.1965509-1-matt@codeconstruct.com.au Signed-off-by: Jakub Kicinski --- include/uapi/linux/rtnetlink.h | 2 ++ net/mctp/device.c | 53 ++++++++++++++++++++++++++++++++++++++---- 2 files changed, 50 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 5888492a5257..93d934cc4613 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -754,6 +754,8 @@ enum rtnetlink_groups { #define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP RTNLGRP_BRVLAN, #define RTNLGRP_BRVLAN RTNLGRP_BRVLAN + RTNLGRP_MCTP_IFADDR, +#define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/net/mctp/device.c b/net/mctp/device.c index 8799ee77e7b7..ef2755f82f87 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -35,14 +35,24 @@ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->mctp_ptr); } -static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb, - struct mctp_dev *mdev, mctp_eid_t eid) +static int mctp_addrinfo_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(1) // IFA_LOCAL + + nla_total_size(1) // IFA_ADDRESS + ; +} + +/* flag should be NLM_F_MULTI for dump calls */ +static int mctp_fill_addrinfo(struct sk_buff *skb, + struct mctp_dev *mdev, mctp_eid_t eid, + int msg_type, u32 portid, u32 seq, int flag) { struct ifaddrmsg *hdr; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWADDR, sizeof(*hdr), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, + msg_type, sizeof(*hdr), flag); if (!nlh) return -EMSGSIZE; @@ -72,10 +82,14 @@ static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; + u32 portid, seq; int rc = 0; + portid = NETLINK_CB(cb->skb).portid; + seq = cb->nlh->nlmsg_seq; for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) { - rc = mctp_fill_addrinfo(skb, cb, mdev, mdev->addrs[mcb->a_idx]); + rc = mctp_fill_addrinfo(skb, mdev, mdev->addrs[mcb->a_idx], + RTM_NEWADDR, portid, seq, NLM_F_MULTI); if (rc < 0) break; } @@ -127,6 +141,32 @@ out: return skb->len; } +static void mctp_addr_notify(struct mctp_dev *mdev, mctp_eid_t eid, int msg_type, + struct sk_buff *req_skb, struct nlmsghdr *req_nlh) +{ + u32 portid = NETLINK_CB(req_skb).portid; + struct net *net = dev_net(mdev->dev); + struct sk_buff *skb; + int rc = -ENOBUFS; + + skb = nlmsg_new(mctp_addrinfo_size(), GFP_KERNEL); + if (!skb) + goto out; + + rc = mctp_fill_addrinfo(skb, mdev, eid, msg_type, + portid, req_nlh->nlmsg_seq, 0); + if (rc < 0) { + WARN_ON_ONCE(rc == -EMSGSIZE); + goto out; + } + + rtnl_notify(skb, net, portid, RTNLGRP_MCTP_IFADDR, req_nlh, GFP_KERNEL); + return; +out: + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_MCTP_IFADDR, rc); +} + static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = { [IFA_ADDRESS] = { .type = NLA_U8 }, [IFA_LOCAL] = { .type = NLA_U8 }, @@ -189,6 +229,7 @@ static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, kfree(tmp_addrs); + mctp_addr_notify(mdev, addr->s_addr, RTM_NEWADDR, skb, nlh); mctp_route_add_local(mdev, addr->s_addr); return 0; @@ -244,6 +285,8 @@ static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, mdev->num_addrs--; spin_unlock_irqrestore(&mdev->addrs_lock, flags); + mctp_addr_notify(mdev, addr->s_addr, RTM_DELADDR, skb, nlh); + return 0; } -- cgit v1.2.3 From cb8747b7d2a9e3d687a19a007575071d4b71cd05 Mon Sep 17 00:00:00 2001 From: Ismael Luceno Date: Mon, 15 Nov 2021 14:46:47 +0100 Subject: uapi: Fix undefined __always_inline on non-glibc systems This macro is defined by glibc itself, which makes the issue go unnoticed on those systems. On non-glibc systems it causes build failures on several utilities and libraries, like bpftool and objtool. Fixes: 1d509f2a6ebc ("x86/insn: Support big endian cross-compiles") Fixes: 2d7ce0e8a704 ("tools/virtio: more stubs") Fixes: 3fb321fde22d ("selftests/net: ipv6 flowlabel") Fixes: 50b3ed57dee9 ("selftests/bpf: test bpf flow dissection") Fixes: 9cacf81f8161 ("bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE") Fixes: a4b2061242ec ("tools include uapi: Grab a copy of linux/in.h") Fixes: b12d6ec09730 ("bpf: btf: add btf print functionality") Fixes: c0dd967818a2 ("tools, include: Grab a copy of linux/erspan.h") Fixes: c4b6014e8bb0 ("tools: Add copy of perf_event.h to tools/include/linux/") Signed-off-by: Ismael Luceno Acked-by: Masami Hiramatsu Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20211115134647.1921-1-ismael@iodev.co.uk Cc: Martin Schwidefsky Cc: Vasily Gorbik --- include/uapi/linux/byteorder/big_endian.h | 1 + include/uapi/linux/byteorder/little_endian.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/byteorder/big_endian.h b/include/uapi/linux/byteorder/big_endian.h index 2199adc6a6c2..80aa5c41a763 100644 --- a/include/uapi/linux/byteorder/big_endian.h +++ b/include/uapi/linux/byteorder/big_endian.h @@ -9,6 +9,7 @@ #define __BIG_ENDIAN_BITFIELD #endif +#include #include #include diff --git a/include/uapi/linux/byteorder/little_endian.h b/include/uapi/linux/byteorder/little_endian.h index 601c904fd5cd..cd98982e7523 100644 --- a/include/uapi/linux/byteorder/little_endian.h +++ b/include/uapi/linux/byteorder/little_endian.h @@ -9,6 +9,7 @@ #define __LITTLE_ENDIAN_BITFIELD #endif +#include #include #include -- cgit v1.2.3 From 80b3485f7d7bdb2468f2a9d6a346a1132d248309 Mon Sep 17 00:00:00 2001 From: "David E. Box" Date: Tue, 7 Dec 2021 17:50:10 -0800 Subject: PCI: Add #defines for accessing PCIe DVSEC fields Add #defines for accessing Vendor ID, Revision, Length, and ID offsets in the Designated Vendor Specific Extended Capability (DVSEC). Defined in PCIe r5.0, sec 7.9.6. Reviewed-by: Rafael J. Wysocki Acked-by: Bjorn Helgaas Signed-off-by: David E. Box Link: https://lore.kernel.org/r/20211208015015.891275-2-david.e.box@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/pci_regs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ff6ccbc6efe9..318f3f1f9e92 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1086,7 +1086,11 @@ /* Designated Vendor-Specific (DVSEC, PCI_EXT_CAP_ID_DVSEC) */ #define PCI_DVSEC_HEADER1 0x4 /* Designated Vendor-Specific Header1 */ +#define PCI_DVSEC_HEADER1_VID(x) ((x) & 0xffff) +#define PCI_DVSEC_HEADER1_REV(x) (((x) >> 16) & 0xf) +#define PCI_DVSEC_HEADER1_LEN(x) (((x) >> 20) & 0xfff) #define PCI_DVSEC_HEADER2 0x8 /* Designated Vendor-Specific Header2 */ +#define PCI_DVSEC_HEADER2_ID(x) ((x) & 0xffff) /* Data Link Feature */ #define PCI_DLF_CAP 0x04 /* Capabilities Register */ -- cgit v1.2.3 From e6911affa416dc4e0c0b3f04cbe6b02ce13277f1 Mon Sep 17 00:00:00 2001 From: Xu Jia Date: Wed, 22 Dec 2021 17:06:58 +0800 Subject: xfrm: Add support for SM3 secure hash This patch allows IPsec to use SM3 HMAC authentication algorithm. Signed-off-by: Xu Jia Signed-off-by: Steffen Klassert --- include/uapi/linux/pfkeyv2.h | 1 + net/xfrm/xfrm_algo.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index d65b11785260..798ba9ffd48c 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -309,6 +309,7 @@ struct sadb_x_filter { #define SADB_X_AALG_SHA2_512HMAC 7 #define SADB_X_AALG_RIPEMD160HMAC 8 #define SADB_X_AALG_AES_XCBC_MAC 9 +#define SADB_X_AALG_SM3_256HMAC 10 #define SADB_X_AALG_NULL 251 /* kame */ #define SADB_AALG_MAX 251 diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 4dae3ab8d030..00b5444a4d86 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -341,6 +341,26 @@ static struct xfrm_algo_desc aalg_list[] = { .pfkey_supported = 0, }, +{ + .name = "hmac(sm3)", + .compat = "sm3", + + .uinfo = { + .auth = { + .icv_truncbits = 256, + .icv_fullbits = 256, + } + }, + + .pfkey_supported = 1, + + .desc = { + .sadb_alg_id = SADB_X_AALG_SM3_256HMAC, + .sadb_alg_ivlen = 0, + .sadb_alg_minbits = 256, + .sadb_alg_maxbits = 256 + } +}, }; static struct xfrm_algo_desc ealg_list[] = { -- cgit v1.2.3 From 23b6a6df94c6ce434e7947cfad14b1640fb9f794 Mon Sep 17 00:00:00 2001 From: Xu Jia Date: Wed, 22 Dec 2021 17:06:59 +0800 Subject: xfrm: Add support for SM4 symmetric cipher algorithm This patch adds SM4 encryption algorithm entry to ealg_list. Signed-off-by: Xu Jia Signed-off-by: Steffen Klassert --- include/uapi/linux/pfkeyv2.h | 1 + net/xfrm/xfrm_algo.c | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index 798ba9ffd48c..8abae1f6749c 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -330,6 +330,7 @@ struct sadb_x_filter { #define SADB_X_EALG_AES_GCM_ICV16 20 #define SADB_X_EALG_CAMELLIACBC 22 #define SADB_X_EALG_NULL_AES_GMAC 23 +#define SADB_X_EALG_SM4CBC 24 #define SADB_EALG_MAX 253 /* last EALG */ /* private allocations should use 249-255 (RFC2407) */ #define SADB_X_EALG_SERPENTCBC 252 /* draft-ietf-ipsec-ciph-aes-cbc-00 */ diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 00b5444a4d86..094734fbec96 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -572,6 +572,27 @@ static struct xfrm_algo_desc ealg_list[] = { .sadb_alg_maxbits = 288 } }, +{ + .name = "cbc(sm4)", + .compat = "sm4", + + .uinfo = { + .encr = { + .geniv = "echainiv", + .blockbits = 128, + .defkeybits = 128, + } + }, + + .pfkey_supported = 1, + + .desc = { + .sadb_alg_id = SADB_X_EALG_SM4CBC, + .sadb_alg_ivlen = 16, + .sadb_alg_minbits = 128, + .sadb_alg_maxbits = 256 + } +}, }; static struct xfrm_algo_desc calg_list[] = { -- cgit v1.2.3 From 4e484b3e969b52effd95c17f7a86f39208b2ccf4 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Wed, 22 Dec 2021 14:11:18 +0100 Subject: xfrm: rate limit SA mapping change message to user space Kernel generates mapping change message, XFRM_MSG_MAPPING, when a source port chage is detected on a input state with UDP encapsulation set. Kernel generates a message for each IPsec packet with new source port. For a high speed flow per packet mapping change message can be excessive, and can overload the user space listener. Introduce rate limiting for XFRM_MSG_MAPPING message to the user space. The rate limiting is configurable via netlink, when adding a new SA or updating it. Use the new attribute XFRMA_MTIMER_THRESH in seconds. v1->v2 change: update xfrm_sa_len() v2->v3 changes: use u32 insted unsigned long to reduce size of struct xfrm_state fix xfrm_ompat size Reported-by: kernel test robot accept XFRM_MSG_MAPPING only when XFRMA_ENCAP is present Co-developed-by: Thomas Egerer Signed-off-by: Thomas Egerer Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 5 +++++ include/uapi/linux/xfrm.h | 1 + net/xfrm/xfrm_compat.c | 6 ++++-- net/xfrm/xfrm_state.c | 23 ++++++++++++++++++++++- net/xfrm/xfrm_user.c | 18 +++++++++++++++++- 5 files changed, 49 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2308210793a0..2589e4c0501b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -200,6 +200,11 @@ struct xfrm_state { struct xfrm_algo_aead *aead; const char *geniv; + /* mapping change rate limiting */ + __be16 new_mapping_sport; + u32 new_mapping; /* seconds */ + u32 mapping_maxage; /* seconds for input SA */ + /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; struct sock __rcu *encap_sk; diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index eda0426ec4c2..4e29d7851890 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -313,6 +313,7 @@ enum xfrm_attr_type_t { XFRMA_SET_MARK, /* __u32 */ XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ + XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 2bf269390163..a0f62fa02e06 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -127,6 +127,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, + [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -274,9 +275,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_SET_MARK: case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: + case XFRMA_MTIMER_THRESH: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -431,7 +433,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a2f4001221d1..78d51399a0f4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1593,6 +1593,9 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->km.seq = orig->km.seq; x->replay = orig->replay; x->preplay = orig->preplay; + x->mapping_maxage = orig->mapping_maxage; + x->new_mapping = 0; + x->new_mapping_sport = 0; return x; @@ -2242,7 +2245,7 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) } EXPORT_SYMBOL(km_query); -int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) +static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int err = -EINVAL; struct xfrm_mgr *km; @@ -2257,6 +2260,24 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) rcu_read_unlock(); return err; } + +int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) +{ + int ret = 0; + + if (x->mapping_maxage) { + if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage || + x->new_mapping_sport != sport) { + x->new_mapping_sport = sport; + x->new_mapping = jiffies / HZ; + ret = __km_new_mapping(x, ipaddr, sport); + } + } else { + ret = __km_new_mapping(x, ipaddr, sport); + } + + return ret; +} EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7c36cc1f3d79..130240680655 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -282,6 +282,10 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = 0; + if (attrs[XFRMA_MTIMER_THRESH]) + if (!attrs[XFRMA_ENCAP]) + err = -EINVAL; + out: return err; } @@ -521,6 +525,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; + struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH]; if (re) { struct xfrm_replay_state_esn *replay_esn; @@ -552,6 +557,9 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, if (rt) x->replay_maxdiff = nla_get_u32(rt); + + if (mt) + x->mapping_maxage = nla_get_u32(mt); } static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) @@ -1024,8 +1032,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (ret) goto out; } - if (x->security) + if (x->security) { ret = copy_sec_ctx(x->security, skb); + if (ret) + goto out; + } + if (x->mapping_maxage) + ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage); out: return ret; } @@ -3069,6 +3082,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); + if (x->mapping_maxage) + l += nla_total_size(sizeof(x->mapping_maxage)); + return l; } -- cgit v1.2.3 From 48f31169830f589e4c7ac475ccc7414951ded3f0 Mon Sep 17 00:00:00 2001 From: Dani Liberman Date: Thu, 14 Oct 2021 22:38:41 +0300 Subject: habanalabs: change wait for interrupt timeout to 64 bit In order to increase maximum wait-for-interrupt timeout, change it to 64 bit variable. This wait is used only by newer ASICs, so no problem in changing this interface at this time. Signed-off-by: Dani Liberman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 22 +++++++++++++++++----- include/uapi/misc/habanalabs.h | 18 +++++++++++------- 2 files changed, 28 insertions(+), 12 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 9ebcd9894d83..54a5425a77a0 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2765,8 +2765,23 @@ static int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) return 0; } +static inline unsigned long hl_usecs64_to_jiffies(const u64 usecs) +{ + if (usecs <= U32_MAX) + return usecs_to_jiffies(usecs); + + /* + * If the value in nanoseconds is larger than 64 bit, use the largest + * 64 bit value. + */ + if (usecs >= ((u64)(U64_MAX / NSEC_PER_USEC))) + return nsecs_to_jiffies(U64_MAX); + + return nsecs_to_jiffies(usecs * NSEC_PER_USEC); +} + static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, - u32 timeout_us, u64 user_address, + u64 timeout_us, u64 user_address, u64 target_value, u16 interrupt_offset, u32 *status, u64 *timestamp) @@ -2778,10 +2793,7 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, long completion_rc; int rc = 0; - if (timeout_us == U32_MAX) - timeout = timeout_us; - else - timeout = usecs_to_jiffies(timeout_us); + timeout = hl_usecs64_to_jiffies(timeout_us); hl_ctx_get(hdev, ctx); diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 00b309590499..c5760acebdd1 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -911,14 +911,18 @@ struct hl_wait_cs_in { */ __u32 flags; - /* Multi CS API info- valid entries in multi-CS array */ - __u8 seq_arr_len; - __u8 pad[3]; + union { + struct { + /* Multi CS API info- valid entries in multi-CS array */ + __u8 seq_arr_len; + __u8 pad[7]; + }; - /* Absolute timeout to wait for an interrupt in microseconds. - * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set - */ - __u32 interrupt_timeout_us; + /* Absolute timeout to wait for an interrupt in microseconds. + * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set + */ + __u64 interrupt_timeout_us; + }; }; #define HL_WAIT_CS_STATUS_COMPLETED 0 -- cgit v1.2.3 From 1679c7ee580fdaa2a5df398a526b2eddc857f2a1 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Mon, 25 Oct 2021 09:47:04 +0300 Subject: habanalabs: expand clock throttling information uAPI In addition to the clock throttling reason, user should be able to obtain also the start time and the duration of the throttling event. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/device.c | 3 +++ drivers/misc/habanalabs/common/habanalabs.h | 31 +++++++++++++++++++++-- drivers/misc/habanalabs/common/habanalabs_ioctl.c | 27 ++++++++++++++++++-- drivers/misc/habanalabs/gaudi/gaudi.c | 22 +++++++++++++--- drivers/misc/habanalabs/goya/goya.c | 25 +++++++++++++++--- include/uapi/misc/habanalabs.h | 16 ++++++++++-- 6 files changed, 110 insertions(+), 14 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index eb5800b403b6..0da5a55490ff 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -455,6 +455,7 @@ static int device_early_init(struct hl_device *hdev) INIT_LIST_HEAD(&hdev->fpriv_list); mutex_init(&hdev->fpriv_list_lock); atomic_set(&hdev->in_reset, 0); + mutex_init(&hdev->clk_throttling.lock); return 0; @@ -495,6 +496,8 @@ static void device_early_fini(struct hl_device *hdev) mutex_destroy(&hdev->fpriv_list_lock); + mutex_destroy(&hdev->clk_throttling.lock); + hl_cb_mgr_fini(hdev, &hdev->kernel_cb_mgr); kfree(hdev->hl_chip_info); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 92d12c8ba569..fc201537f7a9 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -2378,6 +2378,32 @@ struct multi_cs_data { u8 update_ts; }; +/** + * struct hl_clk_throttle_timestamp - current/last clock throttling timestamp + * @start: timestamp taken when 'start' event is received in driver + * @end: timestamp taken when 'end' event is received in driver + */ +struct hl_clk_throttle_timestamp { + ktime_t start; + ktime_t end; +}; + +/** + * struct hl_clk_throttle - keeps current/last clock throttling timestamps + * @timestamp: timestamp taken by driver and firmware, index 0 refers to POWER + * index 1 refers to THERMAL + * @lock: protects this structure as it can be accessed from both event queue + * context and info_ioctl context + * @current_reason: bitmask represents the current clk throttling reasons + * @aggregated_reason: bitmask represents aggregated clk throttling reasons since driver load + */ +struct hl_clk_throttle { + struct hl_clk_throttle_timestamp timestamp[HL_CLK_THROTTLE_TYPE_MAX]; + struct mutex lock; + u32 current_reason; + u32 aggregated_reason; +}; + /** * struct hl_device - habanalabs device structure. * @pdev: pointer to PCI device, can be NULL in case of simulator device. @@ -2445,6 +2471,7 @@ struct multi_cs_data { * @pci_mem_region: array of memory regions in the PCI * @state_dump_specs: constants and dictionaries needed to dump system state. * @multi_cs_completion: array of multi-CS completion. + * @clk_throttling: holds information about current/previous clock throttling events * @dram_used_mem: current DRAM memory consumption. * @timeout_jiffies: device CS timeout value. * @max_power: the max power of the device, as configured by the sysadmin. This @@ -2474,7 +2501,6 @@ struct multi_cs_data { * @high_pll: high PLL profile frequency. * @soft_reset_cnt: number of soft reset since the driver was loaded. * @hard_reset_cnt: number of hard reset since the driver was loaded. - * @clk_throttling_reason: bitmask represents the current clk throttling reasons * @id: device minor. * @id_control: minor of the control device * @cpu_pci_msb_addr: 50-bit extension bits for the device CPU's 40-bit @@ -2604,6 +2630,8 @@ struct hl_device { struct multi_cs_completion multi_cs_completion[ MULTI_CS_MAX_USER_CTX]; + struct hl_clk_throttle clk_throttling; + u32 *stream_master_qid_arr; atomic64_t dram_used_mem; u64 timeout_jiffies; @@ -2622,7 +2650,6 @@ struct hl_device { u32 high_pll; u32 soft_reset_cnt; u32 hard_reset_cnt; - u32 clk_throttling_reason; u16 id; u16 id_control; u16 cpu_pci_msb_addr; diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 86c3257d9ae1..19726c6b642a 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -313,15 +313,38 @@ static int pci_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args) static int clk_throttle_info(struct hl_fpriv *hpriv, struct hl_info_args *args) { + void __user *out = (void __user *) (uintptr_t) args->return_pointer; struct hl_device *hdev = hpriv->hdev; struct hl_info_clk_throttle clk_throttle = {0}; + ktime_t end_time, zero_time = ktime_set(0, 0); u32 max_size = args->return_size; - void __user *out = (void __user *) (uintptr_t) args->return_pointer; + int i; if ((!max_size) || (!out)) return -EINVAL; - clk_throttle.clk_throttling_reason = hdev->clk_throttling_reason; + mutex_lock(&hdev->clk_throttling.lock); + + clk_throttle.clk_throttling_reason = hdev->clk_throttling.current_reason; + + for (i = 0 ; i < HL_CLK_THROTTLE_TYPE_MAX ; i++) { + if (!(hdev->clk_throttling.aggregated_reason & BIT(i))) + continue; + + clk_throttle.clk_throttling_timestamp_us[i] = + ktime_to_us(hdev->clk_throttling.timestamp[i].start); + + if (ktime_compare(hdev->clk_throttling.timestamp[i].end, zero_time)) + end_time = ktime_get(); + else + end_time = hdev->clk_throttling.timestamp[i].end; + + clk_throttle.clk_throttling_duration_ns[i] = + ktime_to_ns(ktime_sub(end_time, + hdev->clk_throttling.timestamp[i].start)); + + } + mutex_unlock(&hdev->clk_throttling.lock); return copy_to_user(out, &clk_throttle, min((size_t) max_size, sizeof(clk_throttle))) ? -EFAULT : 0; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 2724ab3747f2..b4814369062e 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -7925,27 +7925,39 @@ static int tpc_krn_event_to_tpc_id(u16 tpc_dec_event_type) static void gaudi_print_clk_change_info(struct hl_device *hdev, u16 event_type) { + ktime_t zero_time = ktime_set(0, 0); + + mutex_lock(&hdev->clk_throttling.lock); + switch (event_type) { case GAUDI_EVENT_FIX_POWER_ENV_S: - hdev->clk_throttling_reason |= HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.current_reason |= HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].start = ktime_get(); + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = zero_time; dev_info_ratelimited(hdev->dev, "Clock throttling due to power consumption\n"); break; case GAUDI_EVENT_FIX_POWER_ENV_E: - hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = ktime_get(); dev_info_ratelimited(hdev->dev, "Power envelop is safe, back to optimal clock\n"); break; case GAUDI_EVENT_FIX_THERMAL_ENV_S: - hdev->clk_throttling_reason |= HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.current_reason |= HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].start = ktime_get(); + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = zero_time; dev_info_ratelimited(hdev->dev, "Clock throttling due to overheating\n"); break; case GAUDI_EVENT_FIX_THERMAL_ENV_E: - hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = ktime_get(); dev_info_ratelimited(hdev->dev, "Thermal envelop is safe, back to optimal clock\n"); break; @@ -7955,6 +7967,8 @@ static void gaudi_print_clk_change_info(struct hl_device *hdev, event_type); break; } + + mutex_unlock(&hdev->clk_throttling.lock); } static void gaudi_handle_eqe(struct hl_device *hdev, diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 3bbcab7da25e..7b3683f2a6dc 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -4768,24 +4768,39 @@ static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) static void goya_print_clk_change_info(struct hl_device *hdev, u16 event_type) { + ktime_t zero_time = ktime_set(0, 0); + + mutex_lock(&hdev->clk_throttling.lock); + switch (event_type) { case GOYA_ASYNC_EVENT_ID_FIX_POWER_ENV_S: - hdev->clk_throttling_reason |= HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.current_reason |= HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].start = ktime_get(); + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = zero_time; dev_info_ratelimited(hdev->dev, "Clock throttling due to power consumption\n"); break; + case GOYA_ASYNC_EVENT_ID_FIX_POWER_ENV_E: - hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_POWER; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_POWER].end = ktime_get(); dev_info_ratelimited(hdev->dev, "Power envelop is safe, back to optimal clock\n"); break; + case GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_S: - hdev->clk_throttling_reason |= HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.current_reason |= HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].start = ktime_get(); + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = zero_time; dev_info_ratelimited(hdev->dev, "Clock throttling due to overheating\n"); break; + case GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_E: - hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_THERMAL; + hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = ktime_get(); dev_info_ratelimited(hdev->dev, "Thermal envelop is safe, back to optimal clock\n"); break; @@ -4795,6 +4810,8 @@ static void goya_print_clk_change_info(struct hl_device *hdev, u16 event_type) event_type); break; } + + mutex_unlock(&hdev->clk_throttling.lock); } void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry) diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index c5760acebdd1..257b9630773e 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -473,15 +473,27 @@ struct hl_info_pci_counters { __u64 replay_cnt; }; -#define HL_CLK_THROTTLE_POWER 0x1 -#define HL_CLK_THROTTLE_THERMAL 0x2 +enum hl_clk_throttling_type { + HL_CLK_THROTTLE_TYPE_POWER, + HL_CLK_THROTTLE_TYPE_THERMAL, + HL_CLK_THROTTLE_TYPE_MAX +}; + +/* clk_throttling_reason masks */ +#define HL_CLK_THROTTLE_POWER (1 << HL_CLK_THROTTLE_TYPE_POWER) +#define HL_CLK_THROTTLE_THERMAL (1 << HL_CLK_THROTTLE_TYPE_THERMAL) /** * struct hl_info_clk_throttle - clock throttling reason * @clk_throttling_reason: each bit represents a clk throttling reason + * @clk_throttling_timestamp_us: represents CPU timestamp in microseconds of the start-event + * @clk_throttling_duration_ns: the clock throttle time in nanosec */ struct hl_info_clk_throttle { __u32 clk_throttling_reason; + __u32 pad; + __u64 clk_throttling_timestamp_us[HL_CLK_THROTTLE_TYPE_MAX]; + __u64 clk_throttling_duration_ns[HL_CLK_THROTTLE_TYPE_MAX]; }; /** -- cgit v1.2.3 From 49c052dad691ba1a3dc3559b74e99f2ec2fa0319 Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Sun, 24 Oct 2021 19:02:32 +0300 Subject: habanalabs: add new opcodes for INFO IOCTL Add implementation for new opcodes in the INFO IOCTL: 1. Retrieve the replaced DRAM rows from f/w. 2. Retrieve the pending DRAM rows from f/w. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/firmware_if.c | 66 +++++++++++++++++++++++ drivers/misc/habanalabs/common/habanalabs.h | 3 ++ drivers/misc/habanalabs/common/habanalabs_ioctl.c | 43 +++++++++++++++ drivers/misc/habanalabs/include/common/cpucp_if.h | 33 +++++++++++- include/uapi/misc/habanalabs.h | 4 ++ 5 files changed, 148 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c index 9addcfba6a8b..70e992bdbde7 100644 --- a/drivers/misc/habanalabs/common/firmware_if.c +++ b/drivers/misc/habanalabs/common/firmware_if.c @@ -972,6 +972,72 @@ int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power) return rc; } +int hl_fw_dram_replaced_row_get(struct hl_device *hdev, + struct cpucp_hbm_row_info *info) +{ + struct cpucp_hbm_row_info *cpucp_repl_rows_info_cpu_addr; + dma_addr_t cpucp_repl_rows_info_dma_addr; + struct cpucp_packet pkt = {}; + u64 result; + int rc; + + cpucp_repl_rows_info_cpu_addr = + hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, + sizeof(struct cpucp_hbm_row_info), + &cpucp_repl_rows_info_dma_addr); + if (!cpucp_repl_rows_info_cpu_addr) { + dev_err(hdev->dev, + "Failed to allocate DMA memory for CPU-CP replaced rows info packet\n"); + return -ENOMEM; + } + + memset(cpucp_repl_rows_info_cpu_addr, 0, sizeof(struct cpucp_hbm_row_info)); + + pkt.ctl = cpu_to_le32(CPUCP_PACKET_HBM_REPLACED_ROWS_INFO_GET << + CPUCP_PKT_CTL_OPCODE_SHIFT); + pkt.addr = cpu_to_le64(cpucp_repl_rows_info_dma_addr); + pkt.data_max_size = cpu_to_le32(sizeof(struct cpucp_hbm_row_info)); + + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + HL_CPUCP_INFO_TIMEOUT_USEC, &result); + if (rc) { + dev_err(hdev->dev, + "Failed to handle CPU-CP replaced rows info pkt, error %d\n", rc); + goto out; + } + + memcpy(info, cpucp_repl_rows_info_cpu_addr, sizeof(*info)); + +out: + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, + sizeof(struct cpucp_hbm_row_info), + cpucp_repl_rows_info_cpu_addr); + + return rc; +} + +int hl_fw_dram_pending_row_get(struct hl_device *hdev, u32 *pend_rows_num) +{ + struct cpucp_packet pkt; + u64 result; + int rc; + + memset(&pkt, 0, sizeof(pkt)); + + pkt.ctl = cpu_to_le32(CPUCP_PACKET_HBM_PENDING_ROWS_STATUS << CPUCP_PKT_CTL_OPCODE_SHIFT); + + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result); + if (rc) { + dev_err(hdev->dev, + "Failed to handle CPU-CP pending rows info pkt, error %d\n", rc); + goto out; + } + + *pend_rows_num = (u32) result; +out: + return rc; +} + void hl_fw_ask_hard_reset_without_linux(struct hl_device *hdev) { struct static_fw_load_mgr *static_loader = diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index fc201537f7a9..a19563c416ac 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -3012,6 +3012,9 @@ int hl_fw_dynamic_send_protocol_cmd(struct hl_device *hdev, struct fw_load_mgr *fw_loader, enum comms_cmd cmd, unsigned int size, bool wait_ok, u32 timeout); +int hl_fw_dram_replaced_row_get(struct hl_device *hdev, + struct cpucp_hbm_row_info *info); +int hl_fw_dram_pending_row_get(struct hl_device *hdev, u32 *pend_rows_num); int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3], bool is_wc[3]); int hl_pci_elbi_read(struct hl_device *hdev, u64 addr, u32 *data); diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 19726c6b642a..68c655acdec8 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -503,6 +503,43 @@ static int open_stats_info(struct hl_fpriv *hpriv, struct hl_info_args *args) min((size_t) max_size, sizeof(open_stats_info))) ? -EFAULT : 0; } +static int dram_pending_rows_info(struct hl_fpriv *hpriv, struct hl_info_args *args) +{ + struct hl_device *hdev = hpriv->hdev; + u32 max_size = args->return_size; + u32 pend_rows_num = 0; + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + int rc; + + if ((!max_size) || (!out)) + return -EINVAL; + + rc = hl_fw_dram_pending_row_get(hdev, &pend_rows_num); + if (rc) + return rc; + + return copy_to_user(out, &pend_rows_num, + min_t(size_t, max_size, sizeof(pend_rows_num))) ? -EFAULT : 0; +} + +static int dram_replaced_rows_info(struct hl_fpriv *hpriv, struct hl_info_args *args) +{ + struct hl_device *hdev = hpriv->hdev; + u32 max_size = args->return_size; + struct cpucp_hbm_row_info info = {0}; + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + int rc; + + if ((!max_size) || (!out)) + return -EINVAL; + + rc = hl_fw_dram_replaced_row_get(hdev, &info); + if (rc) + return rc; + + return copy_to_user(out, &info, min_t(size_t, max_size, sizeof(info))) ? -EFAULT : 0; +} + static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data, struct device *dev) { @@ -589,6 +626,12 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data, case HL_INFO_OPEN_STATS: return open_stats_info(hpriv, args); + case HL_INFO_DRAM_REPLACED_ROWS: + return dram_replaced_rows_info(hpriv, args); + + case HL_INFO_DRAM_PENDING_ROWS: + return dram_pending_rows_info(hpriv, args); + default: dev_err(dev, "Invalid request %d\n", args->op); rc = -ENOTTY; diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h index 17927968e19a..5e19c763f3f0 100644 --- a/drivers/misc/habanalabs/include/common/cpucp_if.h +++ b/drivers/misc/habanalabs/include/common/cpucp_if.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 * - * Copyright 2020 HabanaLabs, Ltd. + * Copyright 2021 HabanaLabs, Ltd. * All Rights Reserved. * */ @@ -377,6 +377,13 @@ enum pq_init_status { * a different engine or QMAN according to enum cpucp_idle_mask. * The bit will be 1 if the engine is NOT idle. * + * CPUCP_PACKET_HBM_REPLACED_ROWS_INFO_GET - + * Fetch all HBM replaced-rows and prending to be replaced rows data. + * + * CPUCP_PACKET_HBM_PENDING_ROWS_STATUS - + * Fetch status of HBM rows pending replacement and need a reboot to + * be replaced. + * * CPUCP_PACKET_POWER_SET - * Resets power history of device to 0 */ @@ -424,6 +431,8 @@ enum cpucp_packet_id { CPUCP_PACKET_NIC_STAT_REGS_CLR, /* internal */ CPUCP_PACKET_NIC_STAT_REGS_ALL_GET, /* internal */ CPUCP_PACKET_IS_IDLE_CHECK, /* internal */ + CPUCP_PACKET_HBM_REPLACED_ROWS_INFO_GET,/* internal */ + CPUCP_PACKET_HBM_PENDING_ROWS_STATUS, /* internal */ CPUCP_PACKET_POWER_SET, /* internal */ }; @@ -692,6 +701,7 @@ struct eq_generic_event { #define CPUCP_MAX_NIC_LANES (CPUCP_MAX_NICS * CPUCP_LANES_PER_NIC) #define CPUCP_NIC_MASK_ARR_LEN ((CPUCP_MAX_NICS + 63) / 64) #define CPUCP_NIC_POLARITY_ARR_LEN ((CPUCP_MAX_NIC_LANES + 63) / 64) +#define CPUCP_HBM_ROW_REPLACE_MAX 32 struct cpucp_sensor { __le32 type; @@ -837,4 +847,25 @@ struct cpucp_nic_status { __le32 high_ber_cnt; }; +enum cpucp_hbm_row_replace_cause { + REPLACE_CAUSE_DOUBLE_ECC_ERR, + REPLACE_CAUSE_MULTI_SINGLE_ECC_ERR, +}; + +struct cpucp_hbm_row_info { + __u8 hbm_idx; + __u8 pc; + __u8 sid; + __u8 bank_idx; + __le16 row_addr; + __u8 replaced_row_cause; /* enum cpucp_hbm_row_replace_cause */ + __u8 pad; +}; + +struct cpucp_hbm_row_replaced_rows_info { + __le16 num_replaced_rows; + __u8 pad[6]; + struct cpucp_hbm_row_info replaced_rows[CPUCP_HBM_ROW_REPLACE_MAX]; +}; + #endif /* CPUCP_IF_H */ diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 257b9630773e..9b4d72897061 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -334,6 +334,8 @@ enum hl_server_type { * HL_INFO_TOTAL_ENERGY - Retrieve total energy consumption * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency * HL_INFO_OPEN_STATS - Retrieve info regarding recent device open calls + * HL_INFO_DRAM_REPLACED_ROWS - Retrieve DRAM replaced rows info + * HL_INFO_DRAM_PENDING_ROWS - Retrieve DRAM pending rows num */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -353,6 +355,8 @@ enum hl_server_type { #define HL_INFO_PLL_FREQUENCY 16 #define HL_INFO_POWER 17 #define HL_INFO_OPEN_STATS 18 +#define HL_INFO_DRAM_REPLACED_ROWS 21 +#define HL_INFO_DRAM_PENDING_ROWS 22 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 -- cgit v1.2.3 From 3e55b5dbf929a40966b8eb7d4de94fad3bb404bd Mon Sep 17 00:00:00 2001 From: Dani Liberman Date: Wed, 3 Nov 2021 10:09:59 +0200 Subject: habanalabs: add support for fetching historic errors A new uAPI is added for debug purposes of the user-space to retrieve errors related data from previous session (before device reset was performed). Inforamtion is filled when a razwi or CS timeout happens and can contain one of the following: 1. Retrieve timestamp of last time the device was opened and razwi or CS timeout happened. 2. Retrieve information about last CS timeout. 3. Retrieve information about last razwi error. This information doesn't contain user data, so no danger of data leakage between users. Signed-off-by: Dani Liberman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 8 + drivers/misc/habanalabs/common/habanalabs.h | 37 +++++ drivers/misc/habanalabs/common/habanalabs_drv.c | 4 + drivers/misc/habanalabs/common/habanalabs_ioctl.c | 60 ++++++++ drivers/misc/habanalabs/gaudi/gaudi.c | 167 +++++++++++++++------ include/uapi/misc/habanalabs.h | 58 ++++++- 6 files changed, 290 insertions(+), 44 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index e97b21988dea..c1fd4ba14c60 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -733,6 +733,14 @@ static void cs_timedout(struct work_struct *work) hdev = cs->ctx->hdev; + /* Save only the first CS timeout parameters */ + rc = atomic_cmpxchg(&hdev->last_error.cs_write_disable, 0, 1); + if (!rc) { + hdev->last_error.open_dev_timestamp = hdev->last_successful_open_ktime; + hdev->last_error.cs_timeout_timestamp = ktime_get(); + hdev->last_error.cs_timeout_seq = cs->sequence; + } + switch (cs->type) { case CS_TYPE_SIGNAL: dev_err(hdev->dev, diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 9aa144d2fe40..612a9f461b38 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -2405,6 +2405,40 @@ struct hl_clk_throttle { u32 aggregated_reason; }; +/** + * struct last_error_session_info - info about last session in which CS timeout or + * razwi error occurred. + * @open_dev_timestamp: device open timestamp. + * @cs_timeout_timestamp: CS timeout timestamp. + * @razwi_timestamp: razwi timestamp. + * @cs_write_disable: if set writing to CS parameters in the structure is disabled so the + * first (root cause) CS timeout will not be overwritten. + * @razwi_write_disable: if set writing to razwi parameters in the structure is disabled so the + * first (root cause) razwi will not be overwritten. + * @cs_timeout_seq: CS timeout sequence number. + * @razwi_addr: address that caused razwi. + * @razwi_engine_id_1: engine id of the razwi initiator, if it was initiated by engine that does + * not have engine id it will be set to U16_MAX. + * @razwi_engine_id_2: second engine id of razwi initiator. Might happen that razwi have 2 possible + * engines which one them caused the razwi. In that case, it will contain the + * second possible engine id, otherwise it will be set to U16_MAX. + * @razwi_non_engine_initiator: in case the initiator of the razwi does not have engine id. + * @razwi_type: cause of razwi, page fault or access error, otherwise it will be set to U8_MAX. + */ +struct last_error_session_info { + ktime_t open_dev_timestamp; + ktime_t cs_timeout_timestamp; + ktime_t razwi_timestamp; + atomic_t cs_write_disable; + atomic_t razwi_write_disable; + u64 cs_timeout_seq; + u64 razwi_addr; + u16 razwi_engine_id_1; + u16 razwi_engine_id_2; + u8 razwi_non_engine_initiator; + u8 razwi_type; +}; + /** * struct hl_device - habanalabs device structure. * @pdev: pointer to PCI device, can be NULL in case of simulator device. @@ -2488,6 +2522,7 @@ struct hl_clk_throttle { * device initialization. Mainly used to debug and * workaround firmware bugs * @dram_pci_bar_start: start bus address of PCIe bar towards DRAM. + * @last_successful_open_ktime: timestamp (ktime) of the last successful device open. * @last_successful_open_jif: timestamp (jiffies) of the last successful * device open. * @last_open_session_duration_jif: duration (jiffies) of the last device open @@ -2632,6 +2667,7 @@ struct hl_device { struct multi_cs_completion multi_cs_completion[ MULTI_CS_MAX_USER_CTX]; struct hl_clk_throttle clk_throttling; + struct last_error_session_info last_error; u32 *stream_master_qid_arr; atomic64_t dram_used_mem; @@ -2645,6 +2681,7 @@ struct hl_device { u64 open_counter; u64 fw_poll_interval_usec; atomic_t in_reset; + ktime_t last_successful_open_ktime; enum hl_pll_frequency curr_pll_profile; enum cpucp_card_types card_type; u32 major; diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c index 85034f2f2e89..1070c80d739c 100644 --- a/drivers/misc/habanalabs/common/habanalabs_drv.c +++ b/drivers/misc/habanalabs/common/habanalabs_drv.c @@ -187,8 +187,12 @@ int hl_device_open(struct inode *inode, struct file *filp) hl_debugfs_add_file(hpriv); + atomic_set(&hdev->last_error.cs_write_disable, 0); + atomic_set(&hdev->last_error.razwi_write_disable, 0); + hdev->open_counter++; hdev->last_successful_open_jif = jiffies; + hdev->last_successful_open_ktime = ktime_get(); return 0; diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 68c655acdec8..360a1e9bbd5d 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -540,6 +540,57 @@ static int dram_replaced_rows_info(struct hl_fpriv *hpriv, struct hl_info_args * return copy_to_user(out, &info, min_t(size_t, max_size, sizeof(info))) ? -EFAULT : 0; } +static int last_err_open_dev_info(struct hl_fpriv *hpriv, struct hl_info_args *args) +{ + struct hl_info_last_err_open_dev_time info = {0}; + struct hl_device *hdev = hpriv->hdev; + u32 max_size = args->return_size; + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + + if ((!max_size) || (!out)) + return -EINVAL; + + info.timestamp = ktime_to_ns(hdev->last_error.open_dev_timestamp); + + return copy_to_user(out, &info, min_t(size_t, max_size, sizeof(info))) ? -EFAULT : 0; +} + +static int cs_timeout_info(struct hl_fpriv *hpriv, struct hl_info_args *args) +{ + struct hl_info_cs_timeout_event info = {0}; + struct hl_device *hdev = hpriv->hdev; + u32 max_size = args->return_size; + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + + if ((!max_size) || (!out)) + return -EINVAL; + + info.seq = hdev->last_error.cs_timeout_seq; + info.timestamp = ktime_to_ns(hdev->last_error.cs_timeout_timestamp); + + return copy_to_user(out, &info, min_t(size_t, max_size, sizeof(info))) ? -EFAULT : 0; +} + +static int razwi_info(struct hl_fpriv *hpriv, struct hl_info_args *args) +{ + struct hl_device *hdev = hpriv->hdev; + u32 max_size = args->return_size; + struct hl_info_razwi_event info = {0}; + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + + if ((!max_size) || (!out)) + return -EINVAL; + + info.timestamp = ktime_to_ns(hdev->last_error.razwi_timestamp); + info.addr = hdev->last_error.razwi_addr; + info.engine_id_1 = hdev->last_error.razwi_engine_id_1; + info.engine_id_2 = hdev->last_error.razwi_engine_id_2; + info.no_engine_id = hdev->last_error.razwi_non_engine_initiator; + info.error_type = hdev->last_error.razwi_type; + + return copy_to_user(out, &info, min_t(size_t, max_size, sizeof(info))) ? -EFAULT : 0; +} + static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data, struct device *dev) { @@ -632,6 +683,15 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data, case HL_INFO_DRAM_PENDING_ROWS: return dram_pending_rows_info(hpriv, args); + case HL_INFO_LAST_ERR_OPEN_DEV_TIME: + return last_err_open_dev_info(hpriv, args); + + case HL_INFO_CS_TIMEOUT_EVENT: + return cs_timeout_info(hpriv, args); + + case HL_INFO_RAZWI_EVENT: + return razwi_info(hpriv, args); + default: dev_err(dev, "Invalid request %d\n", args->op); rc = -ENOTTY; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index a9e279bfebae..aed55db368d7 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -6970,8 +6970,9 @@ event_not_supported: snprintf(desc, size, "N/A"); } -static const char *gaudi_get_razwi_initiator_dma_name(struct hl_device *hdev, - u32 x_y, bool is_write) +static const char *gaudi_get_razwi_initiator_dma_name(struct hl_device *hdev, u32 x_y, + bool is_write, s32 *engine_id_1, + s32 *engine_id_2) { u32 dma_id[2], dma_offset, err_cause[2], mask, i; @@ -7011,44 +7012,64 @@ static const char *gaudi_get_razwi_initiator_dma_name(struct hl_device *hdev, switch (x_y) { case RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_S_0: case RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_S_1: - if ((err_cause[0] & mask) && !(err_cause[1] & mask)) + if ((err_cause[0] & mask) && !(err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_0; return "DMA0"; - else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) + } else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_2; return "DMA2"; - else + } else { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_0; + *engine_id_2 = GAUDI_ENGINE_ID_DMA_2; return "DMA0 or DMA2"; + } case RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_S_0: case RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_S_1: - if ((err_cause[0] & mask) && !(err_cause[1] & mask)) + if ((err_cause[0] & mask) && !(err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_1; return "DMA1"; - else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) + } else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_3; return "DMA3"; - else + } else { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_1; + *engine_id_2 = GAUDI_ENGINE_ID_DMA_3; return "DMA1 or DMA3"; + } case RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_N_0: case RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_N_1: - if ((err_cause[0] & mask) && !(err_cause[1] & mask)) + if ((err_cause[0] & mask) && !(err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_4; return "DMA4"; - else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) + } else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_6; return "DMA6"; - else + } else { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_4; + *engine_id_2 = GAUDI_ENGINE_ID_DMA_6; return "DMA4 or DMA6"; + } case RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_0: case RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_1: - if ((err_cause[0] & mask) && !(err_cause[1] & mask)) + if ((err_cause[0] & mask) && !(err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_5; return "DMA5"; - else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) + } else if (!(err_cause[0] & mask) && (err_cause[1] & mask)) { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_7; return "DMA7"; - else + } else { + *engine_id_1 = GAUDI_ENGINE_ID_DMA_5; + *engine_id_2 = GAUDI_ENGINE_ID_DMA_7; return "DMA5 or DMA7"; + } } unknown_initiator: return "unknown initiator"; } -static const char *gaudi_get_razwi_initiator_name(struct hl_device *hdev, - bool is_write) +static const char *gaudi_get_razwi_initiator_name(struct hl_device *hdev, bool is_write, + u32 *engine_id_1, u32 *engine_id_2) { u32 val, x_y, axi_id; @@ -7061,24 +7082,35 @@ static const char *gaudi_get_razwi_initiator_name(struct hl_device *hdev, switch (x_y) { case RAZWI_INITIATOR_ID_X_Y_TPC0_NIC0: - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) { + *engine_id_1 = GAUDI_ENGINE_ID_TPC_0; return "TPC0"; - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC)) + } + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC)) { + *engine_id_1 = GAUDI_ENGINE_ID_NIC_0; return "NIC0"; + } break; case RAZWI_INITIATOR_ID_X_Y_TPC1: + *engine_id_1 = GAUDI_ENGINE_ID_TPC_1; return "TPC1"; case RAZWI_INITIATOR_ID_X_Y_MME0_0: case RAZWI_INITIATOR_ID_X_Y_MME0_1: + *engine_id_1 = GAUDI_ENGINE_ID_MME_0; return "MME0"; case RAZWI_INITIATOR_ID_X_Y_MME1_0: case RAZWI_INITIATOR_ID_X_Y_MME1_1: + *engine_id_1 = GAUDI_ENGINE_ID_MME_1; return "MME1"; case RAZWI_INITIATOR_ID_X_Y_TPC2: + *engine_id_1 = GAUDI_ENGINE_ID_TPC_2; return "TPC2"; case RAZWI_INITIATOR_ID_X_Y_TPC3_PCI_CPU_PSOC: - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) { + *engine_id_1 = GAUDI_ENGINE_ID_TPC_3; return "TPC3"; + } + /* PCI, CPU or PSOC does not have engine id*/ if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_PCI)) return "PCI"; if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_CPU)) @@ -7094,32 +7126,49 @@ static const char *gaudi_get_razwi_initiator_name(struct hl_device *hdev, case RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_N_1: case RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_0: case RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_1: - return gaudi_get_razwi_initiator_dma_name(hdev, x_y, is_write); + return gaudi_get_razwi_initiator_dma_name(hdev, x_y, is_write, + engine_id_1, engine_id_2); case RAZWI_INITIATOR_ID_X_Y_TPC4_NIC1_NIC2: - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) { + *engine_id_1 = GAUDI_ENGINE_ID_TPC_4; return "TPC4"; - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC)) + } + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC)) { + *engine_id_1 = GAUDI_ENGINE_ID_NIC_1; return "NIC1"; - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC_FT)) + } + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC_FT)) { + *engine_id_1 = GAUDI_ENGINE_ID_NIC_2; return "NIC2"; + } break; case RAZWI_INITIATOR_ID_X_Y_TPC5: + *engine_id_1 = GAUDI_ENGINE_ID_TPC_5; return "TPC5"; case RAZWI_INITIATOR_ID_X_Y_MME2_0: case RAZWI_INITIATOR_ID_X_Y_MME2_1: + *engine_id_1 = GAUDI_ENGINE_ID_MME_2; return "MME2"; case RAZWI_INITIATOR_ID_X_Y_MME3_0: case RAZWI_INITIATOR_ID_X_Y_MME3_1: + *engine_id_1 = GAUDI_ENGINE_ID_MME_3; return "MME3"; case RAZWI_INITIATOR_ID_X_Y_TPC6: + *engine_id_1 = GAUDI_ENGINE_ID_TPC_6; return "TPC6"; case RAZWI_INITIATOR_ID_X_Y_TPC7_NIC4_NIC5: - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_TPC)) { + *engine_id_1 = GAUDI_ENGINE_ID_TPC_7; return "TPC7"; - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC)) + } + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC)) { + *engine_id_1 = GAUDI_ENGINE_ID_NIC_4; return "NIC4"; - if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC_FT)) + } + if (axi_id == RAZWI_INITIATOR_ID_AXI_ID(AXI_ID_NIC_FT)) { + *engine_id_1 = GAUDI_ENGINE_ID_NIC_5; return "NIC5"; + } break; default: break; @@ -7136,27 +7185,28 @@ static const char *gaudi_get_razwi_initiator_name(struct hl_device *hdev, return "unknown initiator"; } -static void gaudi_print_razwi_info(struct hl_device *hdev) +static void gaudi_print_and_get_razwi_info(struct hl_device *hdev, u32 *engine_id_1, + u32 *engine_id_2) { + if (RREG32(mmMMU_UP_RAZWI_WRITE_VLD)) { dev_err_ratelimited(hdev->dev, "RAZWI event caused by illegal write of %s\n", - gaudi_get_razwi_initiator_name(hdev, true)); + gaudi_get_razwi_initiator_name(hdev, true, engine_id_1, engine_id_2)); WREG32(mmMMU_UP_RAZWI_WRITE_VLD, 0); } if (RREG32(mmMMU_UP_RAZWI_READ_VLD)) { dev_err_ratelimited(hdev->dev, "RAZWI event caused by illegal read of %s\n", - gaudi_get_razwi_initiator_name(hdev, false)); + gaudi_get_razwi_initiator_name(hdev, false, engine_id_1, engine_id_2)); WREG32(mmMMU_UP_RAZWI_READ_VLD, 0); } } -static void gaudi_print_mmu_error_info(struct hl_device *hdev) +static void gaudi_print_and_get_mmu_error_info(struct hl_device *hdev, u64 *addr, u8 *type) { struct gaudi_device *gaudi = hdev->asic_specific; - u64 addr; u32 val; if (!(gaudi->hw_cap_initialized & HW_CAP_MMU)) @@ -7164,24 +7214,24 @@ static void gaudi_print_mmu_error_info(struct hl_device *hdev) val = RREG32(mmMMU_UP_PAGE_ERROR_CAPTURE); if (val & MMU_UP_PAGE_ERROR_CAPTURE_ENTRY_VALID_MASK) { - addr = val & MMU_UP_PAGE_ERROR_CAPTURE_VA_49_32_MASK; - addr <<= 32; - addr |= RREG32(mmMMU_UP_PAGE_ERROR_CAPTURE_VA); + *addr = val & MMU_UP_PAGE_ERROR_CAPTURE_VA_49_32_MASK; + *addr <<= 32; + *addr |= RREG32(mmMMU_UP_PAGE_ERROR_CAPTURE_VA); - dev_err_ratelimited(hdev->dev, "MMU page fault on va 0x%llx\n", - addr); + dev_err_ratelimited(hdev->dev, "MMU page fault on va 0x%llx\n", *addr); + *type = HL_RAZWI_PAGE_FAULT; WREG32(mmMMU_UP_PAGE_ERROR_CAPTURE, 0); } val = RREG32(mmMMU_UP_ACCESS_ERROR_CAPTURE); if (val & MMU_UP_ACCESS_ERROR_CAPTURE_ENTRY_VALID_MASK) { - addr = val & MMU_UP_ACCESS_ERROR_CAPTURE_VA_49_32_MASK; - addr <<= 32; - addr |= RREG32(mmMMU_UP_ACCESS_ERROR_CAPTURE_VA); + *addr = val & MMU_UP_ACCESS_ERROR_CAPTURE_VA_49_32_MASK; + *addr <<= 32; + *addr |= RREG32(mmMMU_UP_ACCESS_ERROR_CAPTURE_VA); - dev_err_ratelimited(hdev->dev, - "MMU access error on va 0x%llx\n", addr); + dev_err_ratelimited(hdev->dev, "MMU access error on va 0x%llx\n", *addr); + *type = HL_RAZWI_MMU_ACCESS_ERROR; WREG32(mmMMU_UP_ACCESS_ERROR_CAPTURE, 0); } @@ -7700,15 +7750,46 @@ static void gaudi_handle_qman_err(struct hl_device *hdev, u16 event_type) static void gaudi_print_irq_info(struct hl_device *hdev, u16 event_type, bool razwi) { + u32 engine_id_1, engine_id_2; char desc[64] = ""; + u64 razwi_addr = 0; + u8 razwi_type; + int rc; + + /* + * Init engine id by default as not valid and only if razwi initiated from engine with + * engine id it will get valid value. + * Init razwi type to default, will be changed only if razwi caused by page fault of + * MMU access error + */ + engine_id_1 = U16_MAX; + engine_id_2 = U16_MAX; + razwi_type = U8_MAX; gaudi_get_event_desc(event_type, desc, sizeof(desc)); dev_err_ratelimited(hdev->dev, "Received H/W interrupt %d [\"%s\"]\n", event_type, desc); if (razwi) { - gaudi_print_razwi_info(hdev); - gaudi_print_mmu_error_info(hdev); + gaudi_print_and_get_razwi_info(hdev, &engine_id_1, &engine_id_2); + gaudi_print_and_get_mmu_error_info(hdev, &razwi_addr, &razwi_type); + + /* In case it's the first razwi, save its parameters*/ + rc = atomic_cmpxchg(&hdev->last_error.razwi_write_disable, 0, 1); + if (!rc) { + hdev->last_error.open_dev_timestamp = hdev->last_successful_open_ktime; + hdev->last_error.razwi_timestamp = ktime_get(); + hdev->last_error.razwi_addr = razwi_addr; + hdev->last_error.razwi_engine_id_1 = engine_id_1; + hdev->last_error.razwi_engine_id_2 = engine_id_2; + /* + * If first engine id holds non valid value the razwi initiator + * does not have engine id + */ + hdev->last_error.razwi_non_engine_initiator = (engine_id_1 == U16_MAX); + hdev->last_error.razwi_type = razwi_type; + + } } } diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 9b4d72897061..eb8565fdae70 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -336,6 +336,14 @@ enum hl_server_type { * HL_INFO_OPEN_STATS - Retrieve info regarding recent device open calls * HL_INFO_DRAM_REPLACED_ROWS - Retrieve DRAM replaced rows info * HL_INFO_DRAM_PENDING_ROWS - Retrieve DRAM pending rows num + * HL_INFO_LAST_ERR_OPEN_DEV_TIME - Retrieve timestamp of the last time the device was opened + * and CS timeout or razwi error occurred. + * HL_INFO_CS_TIMEOUT_EVENT - Retrieve CS timeout timestamp and its related CS sequence number. + * HL_INFO_RAZWI_EVENT - Retrieve parameters of razwi: + * Timestamp of razwi. + * The address which accessing it caused the razwi. + * Razwi initiator. + * Razwi cause, was it a page fault or MMU access error. */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -357,8 +365,11 @@ enum hl_server_type { #define HL_INFO_OPEN_STATS 18 #define HL_INFO_DRAM_REPLACED_ROWS 21 #define HL_INFO_DRAM_PENDING_ROWS 22 +#define HL_INFO_LAST_ERR_OPEN_DEV_TIME 23 +#define HL_INFO_CS_TIMEOUT_EVENT 24 +#define HL_INFO_RAZWI_EVENT 25 -#define HL_INFO_VERSION_MAX_LEN 128 +#define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 /** @@ -575,6 +586,51 @@ struct hl_info_cs_counters { __u64 ctx_validation_drop_cnt; }; +/** + * struct hl_info_last_err_open_dev_time - last error boot information. + * @timestamp: timestamp of last time the device was opened and error occurred. + */ +struct hl_info_last_err_open_dev_time { + __s64 timestamp; +}; + +/** + * struct hl_info_cs_timeout_event - last CS timeout information. + * @timestamp: timestamp when last CS timeout event occurred. + * @seq: sequence number of last CS timeout event. + */ +struct hl_info_cs_timeout_event { + __s64 timestamp; + __u64 seq; +}; + +#define HL_RAZWI_PAGE_FAULT 0 +#define HL_RAZWI_MMU_ACCESS_ERROR 1 + +/** + * struct hl_info_razwi_event - razwi information. + * @timestamp: timestamp of razwi. + * @addr: address which accessing it caused razwi. + * @engine_id_1: engine id of the razwi initiator, if it was initiated by engine that does not + * have engine id it will be set to U16_MAX. + * @engine_id_2: second engine id of razwi initiator. Might happen that razwi have 2 possible + * engines which one them caused the razwi. In that case, it will contain the + * second possible engine id, otherwise it will be set to U16_MAX. + * @no_engine_id: if razwi initiator does not have engine id, this field will be set to 1, + * otherwise 0. + * @error_type: cause of razwi, page fault or access error, otherwise it will be set to U8_MAX. + * @pad: padding to 64 bit. + */ +struct hl_info_razwi_event { + __s64 timestamp; + __u64 addr; + __u16 engine_id_1; + __u16 engine_id_2; + __u8 no_engine_id; + __u8 error_type; + __u8 pad[2]; +}; + enum gaudi_dcores { HL_GAUDI_WS_DCORE, HL_GAUDI_WN_DCORE, -- cgit v1.2.3 From 75a5c44d143bc1818e8004a8bee6993aba3a75cf Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Thu, 18 Nov 2021 10:44:05 +0200 Subject: habanalabs: add power information type to POWER_GET packet In new f/w versions, it is required to explicitly indicate the power information type when querying the F/W for power info. When getting the current power level it should be set to power_input. Signed-off-by: Tomer Tayar Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/firmware_if.c | 1 + include/uapi/misc/habanalabs.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c index cf67800f2b47..ac5bd017d294 100644 --- a/drivers/misc/habanalabs/common/firmware_if.c +++ b/drivers/misc/habanalabs/common/firmware_if.c @@ -969,6 +969,7 @@ int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power) pkt.ctl = cpu_to_le32(CPUCP_PACKET_POWER_GET << CPUCP_PKT_CTL_OPCODE_SHIFT); + pkt.type = cpu_to_le16(CPUCP_POWER_INPUT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), HL_CPUCP_INFO_TIMEOUT_USEC, &result); diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index eb8565fdae70..cd86937c572d 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -333,6 +333,7 @@ enum hl_server_type { * HL_INFO_SYNC_MANAGER - Retrieve sync manager info per dcore * HL_INFO_TOTAL_ENERGY - Retrieve total energy consumption * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency + * HL_INFO_POWER - Retrieve power information * HL_INFO_OPEN_STATS - Retrieve info regarding recent device open calls * HL_INFO_DRAM_REPLACED_ROWS - Retrieve DRAM replaced rows info * HL_INFO_DRAM_PENDING_ROWS - Retrieve DRAM pending rows num -- cgit v1.2.3 From 1880f7acd7e0edacbd46385036253801ddc4273f Mon Sep 17 00:00:00 2001 From: Dani Liberman Date: Tue, 9 Nov 2021 11:33:28 +0200 Subject: habanalabs: add SOB information to signal submission uAPI For debug purpose, add SOB address and SOB initial counter value before current submission to uAPI output. Using SOB address and initial counter, user can calculate how much of the submmision has been completed. Signed-off-by: Dani Liberman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 37 ++++++++++++++++++---- drivers/misc/habanalabs/common/habanalabs.h | 5 +++ drivers/misc/habanalabs/common/hw_queue.c | 3 ++ include/uapi/misc/habanalabs.h | 10 +++++- 4 files changed, 47 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 4e893364a3cc..7a277f442207 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -1277,7 +1277,8 @@ static u32 get_stream_master_qid_mask(struct hl_device *hdev, u32 qid) static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, u32 num_chunks, u64 *cs_seq, u32 flags, - u32 encaps_signals_handle, u32 timeout) + u32 encaps_signals_handle, u32 timeout, + u16 *signal_initial_sob_count) { bool staged_mid, int_queues_only = true; struct hl_device *hdev = hpriv->hdev; @@ -1444,6 +1445,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, goto free_cs_object; } + *signal_initial_sob_count = cs->initial_sob_count; + rc = HL_CS_STATUS_SUCCESS; goto put_cs; @@ -1472,6 +1475,7 @@ static int hl_cs_ctx_switch(struct hl_fpriv *hpriv, union hl_cs_args *args, int rc = 0, do_ctx_switch; void __user *chunks; u32 num_chunks, tmp; + u16 sob_count; int ret; do_ctx_switch = atomic_cmpxchg(&ctx->thread_ctx_switch_token, 1, 0); @@ -1512,7 +1516,7 @@ static int hl_cs_ctx_switch(struct hl_fpriv *hpriv, union hl_cs_args *args, rc = 0; } else { rc = cs_ioctl_default(hpriv, chunks, num_chunks, - cs_seq, 0, 0, hdev->timeout_jiffies); + cs_seq, 0, 0, hdev->timeout_jiffies, &sob_count); } mutex_unlock(&hpriv->restore_phase_mutex); @@ -1963,7 +1967,8 @@ out: static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, void __user *chunks, u32 num_chunks, - u64 *cs_seq, u32 flags, u32 timeout) + u64 *cs_seq, u32 flags, u32 timeout, + u32 *signal_sob_addr_offset, u16 *signal_initial_sob_count) { struct hl_cs_encaps_sig_handle *encaps_sig_hdl = NULL; bool handle_found = false, is_wait_cs = false, @@ -2195,6 +2200,9 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, goto free_cs_object; } + *signal_sob_addr_offset = cs->sob_addr_offset; + *signal_initial_sob_count = cs->initial_sob_count; + rc = HL_CS_STATUS_SUCCESS; if (is_wait_cs) wait_cs_submitted = true; @@ -2225,6 +2233,7 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) void __user *chunks; u32 num_chunks, flags, timeout, signals_count = 0, sob_addr = 0, handle_id = 0; + u16 sob_initial_count = 0; int rc; rc = hl_cs_sanity_checks(hpriv, args); @@ -2255,7 +2264,8 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) case CS_TYPE_WAIT: case CS_TYPE_COLLECTIVE_WAIT: rc = cs_ioctl_signal_wait(hpriv, cs_type, chunks, num_chunks, - &cs_seq, args->in.cs_flags, timeout); + &cs_seq, args->in.cs_flags, timeout, + &sob_addr, &sob_initial_count); break; case CS_RESERVE_SIGNALS: rc = cs_ioctl_reserve_signals(hpriv, @@ -2271,20 +2281,33 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) rc = cs_ioctl_default(hpriv, chunks, num_chunks, &cs_seq, args->in.cs_flags, args->in.encaps_sig_handle_id, - timeout); + timeout, &sob_initial_count); break; } out: if (rc != -EAGAIN) { memset(args, 0, sizeof(*args)); - if (cs_type == CS_RESERVE_SIGNALS) { + switch (cs_type) { + case CS_RESERVE_SIGNALS: args->out.handle_id = handle_id; args->out.sob_base_addr_offset = sob_addr; args->out.count = signals_count; - } else { + break; + case CS_TYPE_SIGNAL: + args->out.sob_base_addr_offset = sob_addr; + args->out.sob_count_before_submission = sob_initial_count; + args->out.seq = cs_seq; + break; + case CS_TYPE_DEFAULT: + args->out.sob_count_before_submission = sob_initial_count; + args->out.seq = cs_seq; + break; + default: args->out.seq = cs_seq; + break; } + args->out.status = rc; } diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 77ac4bb98137..93d0a85265be 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -1545,6 +1545,9 @@ struct hl_userptr { * @submission_time_jiffies: submission time of the cs * @type: CS_TYPE_*. * @encaps_sig_hdl_id: encaps signals handle id, set for the first staged cs. + * @sob_addr_offset: sob offset from the configuration base address. + * @initial_sob_count: count of completed signals in SOB before current submission of signal or + * cs with encaps signals. * @submitted: true if CS was submitted to H/W. * @completed: true if CS was completed by device. * @timedout : true if CS was timedout. @@ -1580,6 +1583,8 @@ struct hl_cs { u64 submission_time_jiffies; enum hl_cs_type type; u32 encaps_sig_hdl_id; + u32 sob_addr_offset; + u16 initial_sob_count; u8 submitted; u8 completed; u8 timedout; diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c index 0743319b10c7..fc841d651210 100644 --- a/drivers/misc/habanalabs/common/hw_queue.c +++ b/drivers/misc/habanalabs/common/hw_queue.c @@ -429,6 +429,9 @@ static int init_signal_cs(struct hl_device *hdev, rc = hl_cs_signal_sob_wraparound_handler(hdev, q_idx, &hw_sob, 1, false); + job->cs->sob_addr_offset = hw_sob->sob_addr; + job->cs->initial_sob_count = prop->next_sob_val - 1; + return rc; } diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index cd86937c572d..648850b954a3 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -929,9 +929,17 @@ struct hl_cs_out { /* * SOB base address offset - * Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set + * Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY or HL_CS_FLAGS_SIGNAL is set */ __u32 sob_base_addr_offset; + + /* + * Count of completed signals in SOB before current signal submission. + * Valid only when (HL_CS_FLAGS_ENCAP_SIGNALS & HL_CS_FLAGS_STAGED_SUBMISSION) + * or HL_CS_FLAGS_SIGNAL is set + */ + __u16 sob_count_before_submission; + __u16 pad[3]; }; union hl_cs_args { -- cgit v1.2.3 From b9d31cada7d9f137028c11534fff77fec8511690 Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Tue, 2 Nov 2021 11:34:18 +0200 Subject: habanalabs: change wait_for_interrupt implementation Currently the cq counters are allocated in userspace memory, and mapped by the driver to the device address space. A new requirement that is part of new future API related to this one, requires that cq counters will be allocated in kernel memory. We leverage the existing cb_create API with KERNEL_MAPPED flag set to allocate this memory. That way we gain two things: 1. The memory cannot be freed while in use since it's protected by refcount in driver. 2. No need to wake up the user thread upon each interrupt from CQ, because the kernel has direct access to the counter. Therefore, it can make comparison with the target value in the interrupt handler and wake up the user thread only if the counter reaches the target value. This is instead of waking the thread up to copy counter value from user then go sleep again if target value wasn't reached. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_buffer.c | 31 ++++-- .../misc/habanalabs/common/command_submission.c | 111 ++++++++++++++++++++- drivers/misc/habanalabs/common/habanalabs.h | 5 + drivers/misc/habanalabs/common/irq.c | 8 +- include/uapi/misc/habanalabs.h | 61 +++++++---- 5 files changed, 189 insertions(+), 27 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c index c591f0487272..d4eb9fb9ea12 100644 --- a/drivers/misc/habanalabs/common/command_buffer.c +++ b/drivers/misc/habanalabs/common/command_buffer.c @@ -380,8 +380,9 @@ int hl_cb_destroy(struct hl_device *hdev, struct hl_cb_mgr *mgr, u64 cb_handle) } static int hl_cb_info(struct hl_device *hdev, struct hl_cb_mgr *mgr, - u64 cb_handle, u32 *usage_cnt) + u64 cb_handle, u32 flags, u32 *usage_cnt, u64 *device_va) { + struct hl_vm_va_block *va_block; struct hl_cb *cb; u32 handle; int rc = 0; @@ -402,7 +403,18 @@ static int hl_cb_info(struct hl_device *hdev, struct hl_cb_mgr *mgr, goto out; } - *usage_cnt = atomic_read(&cb->cs_cnt); + if (flags & HL_CB_FLAGS_GET_DEVICE_VA) { + va_block = list_first_entry(&cb->va_block_list, struct hl_vm_va_block, node); + if (va_block) { + *device_va = va_block->start; + } else { + dev_err(hdev->dev, "CB is not mapped to the device's MMU\n"); + rc = -EINVAL; + goto out; + } + } else { + *usage_cnt = atomic_read(&cb->cs_cnt); + } out: spin_unlock(&mgr->cb_lock); @@ -414,7 +426,7 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data) union hl_cb_args *args = data; struct hl_device *hdev = hpriv->hdev; enum hl_device_status status; - u64 handle = 0; + u64 handle = 0, device_va; u32 usage_cnt = 0; int rc; @@ -450,9 +462,16 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data) case HL_CB_OP_INFO: rc = hl_cb_info(hdev, &hpriv->cb_mgr, args->in.cb_handle, - &usage_cnt); - memset(args, 0, sizeof(*args)); - args->out.usage_cnt = usage_cnt; + args->in.flags, + &usage_cnt, + &device_va); + + memset(&args->out, 0, sizeof(args->out)); + + if (args->in.flags & HL_CB_FLAGS_GET_DEVICE_VA) + args->out.device_va = device_va; + else + args->out.usage_cnt = usage_cnt; break; default: diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index b9fed6b6d1ab..7073fa6b9f0f 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2845,6 +2845,106 @@ static int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) } static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, + struct hl_cb_mgr *cb_mgr, u64 timeout_us, + u64 cq_counters_handle, u64 cq_counters_offset, + u64 target_value, struct hl_user_interrupt *interrupt, + u32 *status, + u64 *timestamp) +{ + struct hl_user_pending_interrupt *pend; + unsigned long timeout, flags; + long completion_rc; + struct hl_cb *cb; + int rc = 0; + u32 handle; + + timeout = hl_usecs64_to_jiffies(timeout_us); + + hl_ctx_get(hdev, ctx); + + cq_counters_handle >>= PAGE_SHIFT; + handle = (u32) cq_counters_handle; + + cb = hl_cb_get(hdev, cb_mgr, handle); + if (!cb) { + hl_ctx_put(ctx); + return -EINVAL; + } + + pend = kzalloc(sizeof(*pend), GFP_KERNEL); + if (!pend) { + hl_cb_put(cb); + hl_ctx_put(ctx); + return -ENOMEM; + } + + hl_fence_init(&pend->fence, ULONG_MAX); + + pend->cq_kernel_addr = (u64 *) cb->kernel_address + cq_counters_offset; + pend->cq_target_value = target_value; + + /* We check for completion value as interrupt could have been received + * before we added the node to the wait list + */ + if (*pend->cq_kernel_addr >= target_value) { + *status = HL_WAIT_CS_STATUS_COMPLETED; + /* There was no interrupt, we assume the completion is now. */ + pend->fence.timestamp = ktime_get(); + } + + if (!timeout_us || (*status == HL_WAIT_CS_STATUS_COMPLETED)) + goto set_timestamp; + + /* Add pending user interrupt to relevant list for the interrupt + * handler to monitor + */ + spin_lock_irqsave(&interrupt->wait_list_lock, flags); + list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head); + spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + + /* Wait for interrupt handler to signal completion */ + completion_rc = wait_for_completion_interruptible_timeout(&pend->fence.completion, + timeout); + if (completion_rc > 0) { + *status = HL_WAIT_CS_STATUS_COMPLETED; + } else { + if (completion_rc == -ERESTARTSYS) { + dev_err_ratelimited(hdev->dev, + "user process got signal while waiting for interrupt ID %d\n", + interrupt->interrupt_id); + rc = -EINTR; + *status = HL_WAIT_CS_STATUS_ABORTED; + } else { + if (pend->fence.error == -EIO) { + dev_err_ratelimited(hdev->dev, + "interrupt based wait ioctl aborted(error:%d) due to a reset cycle initiated\n", + pend->fence.error); + rc = -EIO; + *status = HL_WAIT_CS_STATUS_ABORTED; + } else { + dev_err_ratelimited(hdev->dev, "Waiting for interrupt ID %d timedout\n", + interrupt->interrupt_id); + rc = -ETIMEDOUT; + } + *status = HL_WAIT_CS_STATUS_BUSY; + } + } + + spin_lock_irqsave(&interrupt->wait_list_lock, flags); + list_del(&pend->wait_list_node); + spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + +set_timestamp: + *timestamp = ktime_to_ns(pend->fence.timestamp); + + kfree(pend); + hl_cb_put(cb); + hl_ctx_put(ctx); + + return rc; +} + +static int _hl_interrupt_wait_ioctl_user_addr(struct hl_device *hdev, struct hl_ctx *ctx, u64 timeout_us, u64 user_address, u64 target_value, struct hl_user_interrupt *interrupt, @@ -2861,7 +2961,7 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, hl_ctx_get(hdev, ctx); - pend = kmalloc(sizeof(*pend), GFP_KERNEL); + pend = kzalloc(sizeof(*pend), GFP_KERNEL); if (!pend) { hl_ctx_put(ctx); return -ENOMEM; @@ -2990,7 +3090,14 @@ static int hl_interrupt_wait_ioctl(struct hl_fpriv *hpriv, void *data) else interrupt = &hdev->user_interrupt[interrupt_id - first_interrupt]; - rc = _hl_interrupt_wait_ioctl(hdev, hpriv->ctx, + if (args->in.flags & HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ) + rc = _hl_interrupt_wait_ioctl(hdev, hpriv->ctx, &hpriv->cb_mgr, + args->in.interrupt_timeout_us, args->in.cq_counters_handle, + args->in.cq_counters_offset, + args->in.target, interrupt, &status, + ×tamp); + else + rc = _hl_interrupt_wait_ioctl_user_addr(hdev, hpriv->ctx, args->in.interrupt_timeout_us, args->in.addr, args->in.target, interrupt, &status, ×tamp); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 4d4986177776..78772fe548b9 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -876,10 +876,15 @@ struct hl_user_interrupt { * pending on an interrupt * @wait_list_node: node in the list of user threads pending on an interrupt * @fence: hl fence object for interrupt completion + * @cq_target_value: CQ target value + * @cq_kernel_addr: CQ kernel address, to be used in the cq interrupt + * handler for taget value comparison */ struct hl_user_pending_interrupt { struct list_head wait_list_node; struct hl_fence fence; + u64 cq_target_value; + u64 *cq_kernel_addr; }; /** diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c index 64e0d9de21bd..6454ea12bf3a 100644 --- a/drivers/misc/habanalabs/common/irq.c +++ b/drivers/misc/habanalabs/common/irq.c @@ -145,8 +145,12 @@ static void handle_user_cq(struct hl_device *hdev, spin_lock(&user_cq->wait_list_lock); list_for_each_entry(pend, &user_cq->wait_list_head, wait_list_node) { - pend->fence.timestamp = now; - complete_all(&pend->fence.completion); + if ((pend->cq_kernel_addr && + *(pend->cq_kernel_addr) >= pend->cq_target_value) || + !pend->cq_kernel_addr) { + pend->fence.timestamp = now; + complete_all(&pend->fence.completion); + } } spin_unlock(&user_cq->wait_list_lock); } diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 648850b954a3..371dfc4243b3 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -680,7 +680,10 @@ struct hl_info_args { #define HL_MAX_CB_SIZE (0x200000 - 32) /* Indicates whether the command buffer should be mapped to the device's MMU */ -#define HL_CB_FLAGS_MAP 0x1 +#define HL_CB_FLAGS_MAP 0x1 + +/* Used with HL_CB_OP_INFO opcode to get the device va address for kernel mapped CB */ +#define HL_CB_FLAGS_GET_DEVICE_VA 0x2 struct hl_cb_in { /* Handle of CB or 0 if we want to create one */ @@ -702,11 +705,16 @@ struct hl_cb_out { /* Handle of CB */ __u64 cb_handle; - /* Information about CB */ - struct { - /* Usage count of CB */ - __u32 usage_cnt; - __u32 pad; + union { + /* Information about CB */ + struct { + /* Usage count of CB */ + __u32 usage_cnt; + __u32 pad; + }; + + /* CB mapped address to device MMU */ + __u64 device_va; }; }; }; @@ -947,9 +955,10 @@ union hl_cs_args { struct hl_cs_out out; }; -#define HL_WAIT_CS_FLAGS_INTERRUPT 0x2 -#define HL_WAIT_CS_FLAGS_INTERRUPT_MASK 0xFFF00000 -#define HL_WAIT_CS_FLAGS_MULTI_CS 0x4 +#define HL_WAIT_CS_FLAGS_INTERRUPT 0x2 +#define HL_WAIT_CS_FLAGS_INTERRUPT_MASK 0xFFF00000 +#define HL_WAIT_CS_FLAGS_MULTI_CS 0x4 +#define HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ 0x10 #define HL_WAIT_MULTI_CS_LIST_MAX_LEN 32 @@ -969,14 +978,23 @@ struct hl_wait_cs_in { }; struct { - /* User address for completion comparison. - * upon interrupt, driver will compare the value pointed - * by this address with the supplied target value. - * in order not to perform any comparison, set address - * to all 1s. - * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set - */ - __u64 addr; + union { + /* User address for completion comparison. + * upon interrupt, driver will compare the value pointed + * by this address with the supplied target value. + * in order not to perform any comparison, set address + * to all 1s. + * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set + */ + __u64 addr; + + /* cq_counters_handle to a kernel mapped cb which contains + * cq counters. + * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ is set + */ + __u64 cq_counters_handle; + }; + /* Target value for completion comparison */ __u64 target; }; @@ -1004,6 +1022,15 @@ struct hl_wait_cs_in { */ __u64 interrupt_timeout_us; }; + + /* + * cq counter offset inside the counters cb pointed by cq_counters_handle above. + * upon interrupt, driver will compare the value pointed + * by this address (cq_counters_handle + cq_counters_offset) + * with the supplied target value. + * relevant only when HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ is set + */ + __u64 cq_counters_offset; }; #define HL_WAIT_CS_STATUS_COMPLETED 0 -- cgit v1.2.3 From 7175f02c4e5f5a9430113ab9ca0fd0ce98b28a51 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Sun, 26 Dec 2021 16:01:27 +0300 Subject: uapi: fix linux/nfc.h userspace compilation errors Replace sa_family_t with __kernel_sa_family_t to fix the following linux/nfc.h userspace compilation errors: /usr/include/linux/nfc.h:266:2: error: unknown type name 'sa_family_t' sa_family_t sa_family; /usr/include/linux/nfc.h:274:2: error: unknown type name 'sa_family_t' sa_family_t sa_family; Fixes: 23b7869c0fd0 ("NFC: add the NFC socket raw protocol") Fixes: d646960f7986 ("NFC: Initial LLCP support") Cc: Signed-off-by: Dmitry V. Levin Reviewed-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/uapi/linux/nfc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index f6e3c8c9c744..aadad43d943a 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -263,7 +263,7 @@ enum nfc_sdp_attr { #define NFC_SE_ENABLED 0x1 struct sockaddr_nfc { - sa_family_t sa_family; + __kernel_sa_family_t sa_family; __u32 dev_idx; __u32 target_idx; __u32 nfc_protocol; @@ -271,7 +271,7 @@ struct sockaddr_nfc { #define NFC_LLCP_MAX_SERVICE_NAME 63 struct sockaddr_nfc_llcp { - sa_family_t sa_family; + __kernel_sa_family_t sa_family; __u32 dev_idx; __u32 target_idx; __u32 nfc_protocol; -- cgit v1.2.3 From 79b69a83705e621b258ac6d8ae6d3bfdb4b930aa Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 26 Dec 2021 13:03:47 +0100 Subject: nfc: uapi: use kernel size_t to fix user-space builds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix user-space builds if it includes /usr/include/linux/nfc.h before some of other headers: /usr/include/linux/nfc.h:281:9: error: unknown type name ‘size_t’ 281 | size_t service_name_len; | ^~~~~~ Fixes: d646960f7986 ("NFC: Initial LLCP support") Cc: Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/uapi/linux/nfc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index aadad43d943a..4fa4e979e948 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -278,7 +278,7 @@ struct sockaddr_nfc_llcp { __u8 dsap; /* Destination SAP, if known */ __u8 ssap; /* Source SAP to be bound to */ char service_name[NFC_LLCP_MAX_SERVICE_NAME]; /* Service name URI */; - size_t service_name_len; + __kernel_size_t service_name_len; }; /* NFC socket protocols */ -- cgit v1.2.3 From 0db89fa243e5edc5de38c88b369e4c3755c5fb74 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Wed, 22 Dec 2021 12:31:41 +0800 Subject: ACPI: Introduce Platform Firmware Runtime Update device driver Introduce the pfr_update driver which can be used for Platform Firmware Runtime code injection and driver update [1]. The user is expected to provide the EFI capsule, and pass it to the driver by writing the capsule to a device special file. The capsule is transferred by the driver to the platform firmware with the help of an ACPI _DSM method under the special ACPI Platform Firmware Runtime Update device (INTC1080), and the actual firmware update is carried out by the low-level Management Mode code in the platform firmware. This change allows certain pieces of the platform firmware to be updated on the fly while the system is running (runtime) without the need to restart it, which is key in the cases when the system needs to be available 100% of the time and it cannot afford the downtime related to restarting it, or when the work carried out by the system is particularly important, so it cannot be interrupted, and it is not practical to wait until it is complete. Link: https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf # [1] Tested-by: Hongyu Ning Signed-off-by: Chen Yu [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + drivers/acpi/Kconfig | 18 + drivers/acpi/Makefile | 1 + drivers/acpi/pfr_update.c | 575 +++++++++++++++++++++ include/uapi/linux/pfrut.h | 174 +++++++ 5 files changed, 769 insertions(+) create mode 100644 drivers/acpi/pfr_update.c create mode 100644 include/uapi/linux/pfrut.h (limited to 'include/uapi') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index cfe6cccf0f44..687efcf245c1 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -367,6 +367,7 @@ Code Seq# Include File Comments 0xE5 00-3F linux/fuse.h 0xEC 00-01 drivers/platform/chrome/cros_ec_dev.h ChromeOS EC driver +0xEE 00-09 uapi/linux/pfrut.h Platform Firmware Runtime Update and Telemetry 0xF3 00-3F drivers/usb/misc/sisusbvga/sisusb.h sisfb (in development) 0xF6 all LTTng Linux Trace Toolkit Next Generation diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index cdbdf68bd98f..d0b3ca9d4a97 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -517,6 +517,24 @@ config ACPI_CONFIGFS userspace. The configurable ACPI groups will be visible under /config/acpi, assuming configfs is mounted under /config. +config ACPI_PFRUT + tristate "ACPI Platform Firmware Runtime Update and Telemetry" + depends on 64BIT + help + This mechanism allows certain pieces of the platform firmware + to be updated on the fly while the system is running (runtime) + without the need to restart it, which is key in the cases when + the system needs to be available 100% of the time and it cannot + afford the downtime related to restarting it, or when the work + carried out by the system is particularly important, so it cannot + be interrupted, and it is not practical to wait until it is complete. + + The existing firmware code can be modified (driver update) or + extended by adding new code to the firmware (code injection). + + To compile this driver as module, choose M here: + the module will be called pfr_update. + if ARM64 source "drivers/acpi/arm64/Kconfig" diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 3018714e87d9..2ad2e821cc08 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -102,6 +102,7 @@ obj-$(CONFIG_ACPI_CPPC_LIB) += cppc_acpi.o obj-$(CONFIG_ACPI_SPCR_TABLE) += spcr.o obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o obj-$(CONFIG_ACPI_PPTT) += pptt.o +obj-$(CONFIG_ACPI_PFRUT) += pfr_update.o # processor has its own "processor." module_param namespace processor-y := processor_driver.o diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c new file mode 100644 index 000000000000..149b5b2530b9 --- /dev/null +++ b/drivers/acpi/pfr_update.c @@ -0,0 +1,575 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACPI Platform Firmware Runtime Update Device driver + * + * Copyright (C) 2021 Intel Corporation + * Author: Chen Yu + * + * pfr_update driver is used for Platform Firmware Runtime + * Update, which includes the code injection and driver update. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define PFRU_FUNC_STANDARD_QUERY 0 +#define PFRU_FUNC_QUERY_UPDATE_CAP 1 +#define PFRU_FUNC_QUERY_BUF 2 +#define PFRU_FUNC_START 3 + +#define PFRU_CODE_INJECT_TYPE 1 +#define PFRU_DRIVER_UPDATE_TYPE 2 + +#define PFRU_REVID_1 1 +#define PFRU_REVID_2 2 +#define PFRU_DEFAULT_REV_ID PFRU_REVID_1 + +enum cap_index { + CAP_STATUS_IDX = 0, + CAP_UPDATE_IDX = 1, + CAP_CODE_TYPE_IDX = 2, + CAP_FW_VER_IDX = 3, + CAP_CODE_RT_VER_IDX = 4, + CAP_DRV_TYPE_IDX = 5, + CAP_DRV_RT_VER_IDX = 6, + CAP_DRV_SVN_IDX = 7, + CAP_PLAT_ID_IDX = 8, + CAP_OEM_ID_IDX = 9, + CAP_OEM_INFO_IDX = 10, + CAP_NR_IDX +}; + +enum buf_index { + BUF_STATUS_IDX = 0, + BUF_EXT_STATUS_IDX = 1, + BUF_ADDR_LOW_IDX = 2, + BUF_ADDR_HI_IDX = 3, + BUF_SIZE_IDX = 4, + BUF_NR_IDX +}; + +enum update_index { + UPDATE_STATUS_IDX = 0, + UPDATE_EXT_STATUS_IDX = 1, + UPDATE_AUTH_TIME_LOW_IDX = 2, + UPDATE_AUTH_TIME_HI_IDX = 3, + UPDATE_EXEC_TIME_LOW_IDX = 4, + UPDATE_EXEC_TIME_HI_IDX = 5, + UPDATE_NR_IDX +}; + +enum pfru_start_action { + START_STAGE = 0, + START_ACTIVATE = 1, + START_STAGE_ACTIVATE = 2, +}; + +struct pfru_device { + u32 rev_id, index; + struct device *parent_dev; + struct miscdevice miscdev; +}; + +static DEFINE_IDA(pfru_ida); + +/* + * Manual reference: + * https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf + * + * pfru_guid is the parameter for _DSM method + */ +static const guid_t pfru_guid = + GUID_INIT(0xECF9533B, 0x4A3C, 0x4E89, 0x93, 0x9E, 0xC7, 0x71, + 0x12, 0x60, 0x1C, 0x6D); + +/* pfru_code_inj_guid is the UUID to identify code injection EFI capsule file */ +static const guid_t pfru_code_inj_guid = + GUID_INIT(0xB2F84B79, 0x7B6E, 0x4E45, 0x88, 0x5F, 0x3F, 0xB9, + 0xBB, 0x18, 0x54, 0x02); + +/* pfru_drv_update_guid is the UUID to identify driver update EFI capsule file */ +static const guid_t pfru_drv_update_guid = + GUID_INIT(0x4569DD8C, 0x75F1, 0x429A, 0xA3, 0xD6, 0x24, 0xDE, + 0x80, 0x97, 0xA0, 0xDF); + +static inline int pfru_valid_revid(u32 id) +{ + return id == PFRU_REVID_1 || id == PFRU_REVID_2; +} + +static inline struct pfru_device *to_pfru_dev(struct file *file) +{ + return container_of(file->private_data, struct pfru_device, miscdev); +} + +static int query_capability(struct pfru_update_cap_info *cap_hdr, + struct pfru_device *pfru_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev); + union acpi_object *out_obj; + int ret = -EINVAL; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, + pfru_dev->rev_id, + PFRU_FUNC_QUERY_UPDATE_CAP, + NULL, ACPI_TYPE_PACKAGE); + if (!out_obj) + return ret; + + if (out_obj->package.count < CAP_NR_IDX || + out_obj->package.elements[CAP_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_UPDATE_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_CODE_TYPE_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_FW_VER_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_CODE_RT_VER_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_DRV_TYPE_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_DRV_RT_VER_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_DRV_SVN_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_PLAT_ID_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_OEM_ID_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_OEM_INFO_IDX].type != ACPI_TYPE_BUFFER) + goto free_acpi_buffer; + + cap_hdr->status = out_obj->package.elements[CAP_STATUS_IDX].integer.value; + if (cap_hdr->status != DSM_SUCCEED) { + ret = -EBUSY; + dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", cap_hdr->status); + goto free_acpi_buffer; + } + + cap_hdr->update_cap = out_obj->package.elements[CAP_UPDATE_IDX].integer.value; + memcpy(&cap_hdr->code_type, + out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.pointer, + out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.length); + cap_hdr->fw_version = + out_obj->package.elements[CAP_FW_VER_IDX].integer.value; + cap_hdr->code_rt_version = + out_obj->package.elements[CAP_CODE_RT_VER_IDX].integer.value; + memcpy(&cap_hdr->drv_type, + out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.pointer, + out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.length); + cap_hdr->drv_rt_version = + out_obj->package.elements[CAP_DRV_RT_VER_IDX].integer.value; + cap_hdr->drv_svn = + out_obj->package.elements[CAP_DRV_SVN_IDX].integer.value; + memcpy(&cap_hdr->platform_id, + out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.pointer, + out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.length); + memcpy(&cap_hdr->oem_id, + out_obj->package.elements[CAP_OEM_ID_IDX].buffer.pointer, + out_obj->package.elements[CAP_OEM_ID_IDX].buffer.length); + cap_hdr->oem_info_len = + out_obj->package.elements[CAP_OEM_INFO_IDX].buffer.length; + + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int query_buffer(struct pfru_com_buf_info *info, + struct pfru_device *pfru_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev); + union acpi_object *out_obj; + int ret = -EINVAL; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, + pfru_dev->rev_id, PFRU_FUNC_QUERY_BUF, + NULL, ACPI_TYPE_PACKAGE); + if (!out_obj) + return ret; + + if (out_obj->package.count < BUF_NR_IDX || + out_obj->package.elements[BUF_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_ADDR_LOW_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_ADDR_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_SIZE_IDX].type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + info->status = out_obj->package.elements[BUF_STATUS_IDX].integer.value; + info->ext_status = + out_obj->package.elements[BUF_EXT_STATUS_IDX].integer.value; + if (info->status != DSM_SUCCEED) { + ret = -EBUSY; + dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", info->status); + dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n", info->ext_status); + + goto free_acpi_buffer; + } + + info->addr_lo = + out_obj->package.elements[BUF_ADDR_LOW_IDX].integer.value; + info->addr_hi = + out_obj->package.elements[BUF_ADDR_HI_IDX].integer.value; + info->buf_size = out_obj->package.elements[BUF_SIZE_IDX].integer.value; + + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int get_image_type(const struct efi_manage_capsule_image_header *img_hdr, + struct pfru_device *pfru_dev) +{ + const efi_guid_t *image_type_id = &img_hdr->image_type_id; + + /* check whether this is a code injection or driver update */ + if (guid_equal(image_type_id, &pfru_code_inj_guid)) + return PFRU_CODE_INJECT_TYPE; + + if (guid_equal(image_type_id, &pfru_drv_update_guid)) + return PFRU_DRIVER_UPDATE_TYPE; + + return -EINVAL; +} + +static int adjust_efi_size(const struct efi_manage_capsule_image_header *img_hdr, + int size) +{ + /* + * The (u64 hw_ins) was introduced in UEFI spec version 2, + * and (u64 capsule_support) was introduced in version 3. + * The size needs to be adjusted accordingly. That is to + * say, version 1 should subtract the size of hw_ins+capsule_support, + * and version 2 should sbstract the size of capsule_support. + */ + size += sizeof(struct efi_manage_capsule_image_header); + switch (img_hdr->ver) { + case 1: + return size - 2 * sizeof(u64); + + case 2: + return size - sizeof(u64); + + default: + /* only support version 1 and 2 */ + return -EINVAL; + } +} + +static bool applicable_image(const void *data, struct pfru_update_cap_info *cap, + struct pfru_device *pfru_dev) +{ + struct pfru_payload_hdr *payload_hdr; + const efi_capsule_header_t *cap_hdr = data; + const struct efi_manage_capsule_header *m_hdr; + const struct efi_manage_capsule_image_header *m_img_hdr; + const struct efi_image_auth *auth; + int type, size; + + /* + * If the code in the capsule is older than the current + * firmware code, the update will be rejected by the firmware, + * so check the version of it upfront without engaging the + * Management Mode update mechanism which may be costly. + */ + size = cap_hdr->headersize; + m_hdr = data + size; + /* + * Current data structure size plus variable array indicated + * by number of (emb_drv_cnt + payload_cnt) + */ + size += offsetof(struct efi_manage_capsule_header, offset_list) + + (m_hdr->emb_drv_cnt + m_hdr->payload_cnt) * sizeof(u64); + m_img_hdr = data + size; + + type = get_image_type(m_img_hdr, pfru_dev); + if (type < 0) + return false; + + size = adjust_efi_size(m_img_hdr, size); + if (size < 0) + return false; + + auth = data + size; + size += sizeof(u64) + auth->auth_info.hdr.len; + payload_hdr = (struct pfru_payload_hdr *)(data + size); + + /* finally compare the version */ + if (type == PFRU_CODE_INJECT_TYPE) + return payload_hdr->rt_ver >= cap->code_rt_version; + + return payload_hdr->rt_ver >= cap->drv_rt_version; +} + +static void print_update_debug_info(struct pfru_updated_result *result, + struct pfru_device *pfru_dev) +{ + dev_dbg(pfru_dev->parent_dev, "Update result:\n"); + dev_dbg(pfru_dev->parent_dev, "Authentication Time Low:%lld\n", + result->low_auth_time); + dev_dbg(pfru_dev->parent_dev, "Authentication Time High:%lld\n", + result->high_auth_time); + dev_dbg(pfru_dev->parent_dev, "Execution Time Low:%lld\n", + result->low_exec_time); + dev_dbg(pfru_dev->parent_dev, "Execution Time High:%lld\n", + result->high_exec_time); +} + +static int start_update(int action, struct pfru_device *pfru_dev) +{ + union acpi_object *out_obj, in_obj, in_buf; + struct pfru_updated_result update_result; + acpi_handle handle; + int ret = -EINVAL; + + memset(&in_obj, 0, sizeof(in_obj)); + memset(&in_buf, 0, sizeof(in_buf)); + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_INTEGER; + in_buf.integer.value = action; + + handle = ACPI_HANDLE(pfru_dev->parent_dev); + out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, + pfru_dev->rev_id, PFRU_FUNC_START, + &in_obj, ACPI_TYPE_PACKAGE); + if (!out_obj) + return ret; + + if (out_obj->package.count < UPDATE_NR_IDX || + out_obj->package.elements[UPDATE_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + update_result.status = + out_obj->package.elements[UPDATE_STATUS_IDX].integer.value; + update_result.ext_status = + out_obj->package.elements[UPDATE_EXT_STATUS_IDX].integer.value; + + if (update_result.status != DSM_SUCCEED) { + ret = -EBUSY; + dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", update_result.status); + dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n", + update_result.ext_status); + + goto free_acpi_buffer; + } + + update_result.low_auth_time = + out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].integer.value; + update_result.high_auth_time = + out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].integer.value; + update_result.low_exec_time = + out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].integer.value; + update_result.high_exec_time = + out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].integer.value; + + print_update_debug_info(&update_result, pfru_dev); + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static long pfru_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct pfru_update_cap_info cap_hdr; + struct pfru_device *pfru_dev = to_pfru_dev(file); + void __user *p = (void __user *)arg; + u32 rev; + int ret; + + switch (cmd) { + case PFRU_IOC_QUERY_CAP: + ret = query_capability(&cap_hdr, pfru_dev); + if (ret) + return ret; + + if (copy_to_user(p, &cap_hdr, sizeof(cap_hdr))) + return -EFAULT; + + return 0; + + case PFRU_IOC_SET_REV: + if (copy_from_user(&rev, p, sizeof(rev))) + return -EFAULT; + + if (!pfru_valid_revid(rev)) + return -EINVAL; + + pfru_dev->rev_id = rev; + + return 0; + + case PFRU_IOC_STAGE: + return start_update(START_STAGE, pfru_dev); + + case PFRU_IOC_ACTIVATE: + return start_update(START_ACTIVATE, pfru_dev); + + case PFRU_IOC_STAGE_ACTIVATE: + return start_update(START_STAGE_ACTIVATE, pfru_dev); + + default: + return -ENOTTY; + } +} + +static ssize_t pfru_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + struct pfru_device *pfru_dev = to_pfru_dev(file); + struct pfru_update_cap_info cap; + struct pfru_com_buf_info buf_info; + phys_addr_t phy_addr; + struct iov_iter iter; + struct iovec iov; + char *buf_ptr; + int ret; + + ret = query_buffer(&buf_info, pfru_dev); + if (ret) + return ret; + + if (len > buf_info.buf_size) + return -EINVAL; + + iov.iov_base = (void __user *)buf; + iov.iov_len = len; + iov_iter_init(&iter, WRITE, &iov, 1, len); + + /* map the communication buffer */ + phy_addr = (phys_addr_t)((buf_info.addr_hi << 32) | buf_info.addr_lo); + buf_ptr = memremap(phy_addr, buf_info.buf_size, MEMREMAP_WB); + if (IS_ERR(buf_ptr)) + return PTR_ERR(buf_ptr); + + if (!copy_from_iter_full(buf_ptr, len, &iter)) { + ret = -EINVAL; + goto unmap; + } + + /* check if the capsule header has a valid version number */ + ret = query_capability(&cap, pfru_dev); + if (ret) + goto unmap; + + if (!applicable_image(buf_ptr, &cap, pfru_dev)) + ret = -EINVAL; + +unmap: + memunmap(buf_ptr); + + return ret ?: len; +} + +static const struct file_operations acpi_pfru_fops = { + .owner = THIS_MODULE, + .write = pfru_write, + .unlocked_ioctl = pfru_ioctl, + .llseek = noop_llseek, +}; + +static int acpi_pfru_remove(struct platform_device *pdev) +{ + struct pfru_device *pfru_dev = platform_get_drvdata(pdev); + + misc_deregister(&pfru_dev->miscdev); + + return 0; +} + +static void pfru_put_idx(void *data) +{ + struct pfru_device *pfru_dev = data; + + ida_free(&pfru_ida, pfru_dev->index); +} + +static int acpi_pfru_probe(struct platform_device *pdev) +{ + acpi_handle handle = ACPI_HANDLE(&pdev->dev); + struct pfru_device *pfru_dev; + int ret; + + if (!acpi_has_method(handle, "_DSM")) { + dev_dbg(&pdev->dev, "Missing _DSM\n"); + return -ENODEV; + } + + pfru_dev = devm_kzalloc(&pdev->dev, sizeof(*pfru_dev), GFP_KERNEL); + if (!pfru_dev) + return -ENOMEM; + + ret = ida_alloc(&pfru_ida, GFP_KERNEL); + if (ret < 0) + return ret; + + pfru_dev->index = ret; + ret = devm_add_action_or_reset(&pdev->dev, pfru_put_idx, pfru_dev); + if (ret) + return ret; + + pfru_dev->rev_id = PFRU_DEFAULT_REV_ID; + pfru_dev->parent_dev = &pdev->dev; + + pfru_dev->miscdev.minor = MISC_DYNAMIC_MINOR; + pfru_dev->miscdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pfru%d", pfru_dev->index); + if (!pfru_dev->miscdev.name) + return -ENOMEM; + + pfru_dev->miscdev.nodename = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "acpi_pfr_update%d", pfru_dev->index); + if (!pfru_dev->miscdev.nodename) + return -ENOMEM; + + pfru_dev->miscdev.fops = &acpi_pfru_fops; + pfru_dev->miscdev.parent = &pdev->dev; + + ret = misc_register(&pfru_dev->miscdev); + if (ret) + return ret; + + platform_set_drvdata(pdev, pfru_dev); + + return 0; +} + +static const struct acpi_device_id acpi_pfru_ids[] = { + {"INTC1080"}, + {} +}; +MODULE_DEVICE_TABLE(acpi, acpi_pfru_ids); + +static struct platform_driver acpi_pfru_driver = { + .driver = { + .name = "pfr_update", + .acpi_match_table = acpi_pfru_ids, + }, + .probe = acpi_pfru_probe, + .remove = acpi_pfru_remove, +}; +module_platform_driver(acpi_pfru_driver); + +MODULE_DESCRIPTION("Platform Firmware Runtime Update device driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h new file mode 100644 index 000000000000..fa97e80a93b7 --- /dev/null +++ b/include/uapi/linux/pfrut.h @@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Platform Firmware Runtime Update header + * + * Copyright(c) 2021 Intel Corporation. All rights reserved. + */ +#ifndef __PFRUT_H__ +#define __PFRUT_H__ + +#include +#include + +#define PFRUT_IOCTL_MAGIC 0xEE + +/** + * PFRU_IOC_SET_REV - _IOW(PFRUT_IOCTL_MAGIC, 0x01, unsigned int) + * + * Return: + * * 0 - success + * * -EFAULT - fail to read the revision id + * * -EINVAL - user provides an invalid revision id + * + * Set the Revision ID for Platform Firmware Runtime Update. + */ +#define PFRU_IOC_SET_REV _IOW(PFRUT_IOCTL_MAGIC, 0x01, unsigned int) + +/** + * PFRU_IOC_STAGE - _IOW(PFRUT_IOCTL_MAGIC, 0x02, unsigned int) + * + * Return: + * * 0 - success + * * -EINVAL - stage phase returns invalid result + * + * Stage a capsule image from communication buffer and perform authentication. + */ +#define PFRU_IOC_STAGE _IOW(PFRUT_IOCTL_MAGIC, 0x02, unsigned int) + +/** + * PFRU_IOC_ACTIVATE - _IOW(PFRUT_IOCTL_MAGIC, 0x03, unsigned int) + * + * Return: + * * 0 - success + * * -EINVAL - activate phase returns invalid result + * + * Activate a previously staged capsule image. + */ +#define PFRU_IOC_ACTIVATE _IOW(PFRUT_IOCTL_MAGIC, 0x03, unsigned int) + +/** + * PFRU_IOC_STAGE_ACTIVATE - _IOW(PFRUT_IOCTL_MAGIC, 0x04, unsigned int) + * + * Return: + * * 0 - success + * * -EINVAL - stage/activate phase returns invalid result. + * + * Perform both stage and activation action. + */ +#define PFRU_IOC_STAGE_ACTIVATE _IOW(PFRUT_IOCTL_MAGIC, 0x04, unsigned int) + +/** + * PFRU_IOC_QUERY_CAP - _IOR(PFRUT_IOCTL_MAGIC, 0x05, + * struct pfru_update_cap_info) + * + * Return: + * * 0 - success + * * -EINVAL - query phase returns invalid result + * * -EFAULT - the result fails to be copied to userspace + * + * Retrieve information on the Platform Firmware Runtime Update capability. + * The information is a struct pfru_update_cap_info. + */ +#define PFRU_IOC_QUERY_CAP _IOR(PFRUT_IOCTL_MAGIC, 0x05, struct pfru_update_cap_info) + +/** + * struct pfru_payload_hdr - Capsule file payload header. + * + * @sig: Signature of this capsule file. + * @hdr_version: Revision of this header structure. + * @hdr_size: Size of this header, including the OemHeader bytes. + * @hw_ver: The supported firmware version. + * @rt_ver: Version of the code injection image. + * @platform_id: A platform specific GUID to specify the platform what + * this capsule image support. + */ +struct pfru_payload_hdr { + __u32 sig; + __u32 hdr_version; + __u32 hdr_size; + __u32 hw_ver; + __u32 rt_ver; + __u8 platform_id[16]; +}; + +enum pfru_dsm_status { + DSM_SUCCEED = 0, + DSM_FUNC_NOT_SUPPORT = 1, + DSM_INVAL_INPUT = 2, + DSM_HARDWARE_ERR = 3, + DSM_RETRY_SUGGESTED = 4, + DSM_UNKNOWN = 5, + DSM_FUNC_SPEC_ERR = 6, +}; + +/** + * struct pfru_update_cap_info - Runtime update capability information. + * + * @status: Indicator of whether this query succeed. + * @update_cap: Bitmap to indicate whether the feature is supported. + * @code_type: A buffer containing an image type GUID. + * @fw_version: Platform firmware version. + * @code_rt_version: Code injection runtime version for anti-rollback. + * @drv_type: A buffer containing an image type GUID. + * @drv_rt_version: The version of the driver update runtime code. + * @drv_svn: The secure version number(SVN) of the driver update runtime code. + * @platform_id: A buffer containing a platform ID GUID. + * @oem_id: A buffer containing an OEM ID GUID. + * @oem_info_len: Length of the buffer containing the vendor specific information. + */ +struct pfru_update_cap_info { + __u32 status; + __u32 update_cap; + + __u8 code_type[16]; + __u32 fw_version; + __u32 code_rt_version; + + __u8 drv_type[16]; + __u32 drv_rt_version; + __u32 drv_svn; + + __u8 platform_id[16]; + __u8 oem_id[16]; + + __u32 oem_info_len; +}; + +/** + * struct pfru_com_buf_info - Communication buffer information. + * + * @status: Indicator of whether this query succeed. + * @ext_status: Implementation specific query result. + * @addr_lo: Low 32bit physical address of the communication buffer to hold + * a runtime update package. + * @addr_hi: High 32bit physical address of the communication buffer to hold + * a runtime update package. + * @buf_size: Maximum size in bytes of the communication buffer. + */ +struct pfru_com_buf_info { + __u32 status; + __u32 ext_status; + __u64 addr_lo; + __u64 addr_hi; + __u32 buf_size; +}; + +/** + * struct pfru_updated_result - Platform firmware runtime update result information. + * @status: Indicator of whether this update succeed. + * @ext_status: Implementation specific update result. + * @low_auth_time: Low 32bit value of image authentication time in nanosecond. + * @high_auth_time: High 32bit value of image authentication time in nanosecond. + * @low_exec_time: Low 32bit value of image execution time in nanosecond. + * @high_exec_time: High 32bit value of image execution time in nanosecond. + */ +struct pfru_updated_result { + __u32 status; + __u32 ext_status; + __u64 low_auth_time; + __u64 high_auth_time; + __u64 low_exec_time; + __u64 high_exec_time; +}; + +#endif /* __PFRUT_H__ */ -- cgit v1.2.3 From b0013e037a8b07772c74ce24f1ae4743b30fc3cf Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Wed, 22 Dec 2021 12:32:02 +0800 Subject: ACPI: Introduce Platform Firmware Runtime Telemetry driver This driver allows user space to fetch telemetry data from the firmware with the help of the Platform Firmware Runtime Telemetry interface. Both PFRU and PFRT are based on ACPI _DSM interfaces located under special device objects in the ACPI Namespace, but these interfaces are different from each other, so it is better to provide a separate driver from each of them, even though they share some common definitions and naming conventions. Tested-by: Hongyu Ning Signed-off-by: Chen Yu [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/Kconfig | 8 +- drivers/acpi/Makefile | 2 +- drivers/acpi/pfr_telemetry.c | 434 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pfrut.h | 88 +++++++++ 4 files changed, 529 insertions(+), 3 deletions(-) create mode 100644 drivers/acpi/pfr_telemetry.c (limited to 'include/uapi') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index d0b3ca9d4a97..91f1da16934d 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -532,8 +532,12 @@ config ACPI_PFRUT The existing firmware code can be modified (driver update) or extended by adding new code to the firmware (code injection). - To compile this driver as module, choose M here: - the module will be called pfr_update. + Besides, the telemetry driver allows user space to fetch telemetry + data from the firmware with the help of the Platform Firmware Runtime + Telemetry interface. + + To compile the drivers as modules, choose M here: + the modules will be called pfr_update and pfr_telemetry. if ARM64 source "drivers/acpi/arm64/Kconfig" diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 2ad2e821cc08..d3dc79298ce3 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -102,7 +102,7 @@ obj-$(CONFIG_ACPI_CPPC_LIB) += cppc_acpi.o obj-$(CONFIG_ACPI_SPCR_TABLE) += spcr.o obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o obj-$(CONFIG_ACPI_PPTT) += pptt.o -obj-$(CONFIG_ACPI_PFRUT) += pfr_update.o +obj-$(CONFIG_ACPI_PFRUT) += pfr_update.o pfr_telemetry.o # processor has its own "processor." module_param namespace processor-y := processor_driver.o diff --git a/drivers/acpi/pfr_telemetry.c b/drivers/acpi/pfr_telemetry.c new file mode 100644 index 000000000000..da50dd80192c --- /dev/null +++ b/drivers/acpi/pfr_telemetry.c @@ -0,0 +1,434 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACPI Platform Firmware Runtime Telemetry driver + * + * Copyright (C) 2021 Intel Corporation + * Author: Chen Yu + * + * This driver allows user space to fetch telemetry data from the + * firmware with the help of the Platform Firmware Runtime Telemetry + * interface. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define PFRT_LOG_EXEC_IDX 0 +#define PFRT_LOG_HISTORY_IDX 1 + +#define PFRT_LOG_ERR 0 +#define PFRT_LOG_WARN 1 +#define PFRT_LOG_INFO 2 +#define PFRT_LOG_VERB 4 + +#define PFRT_FUNC_SET_LEV 1 +#define PFRT_FUNC_GET_LEV 2 +#define PFRT_FUNC_GET_DATA 3 + +#define PFRT_REVID_1 1 +#define PFRT_REVID_2 2 +#define PFRT_DEFAULT_REV_ID PFRT_REVID_1 + +enum log_index { + LOG_STATUS_IDX = 0, + LOG_EXT_STATUS_IDX = 1, + LOG_MAX_SZ_IDX = 2, + LOG_CHUNK1_LO_IDX = 3, + LOG_CHUNK1_HI_IDX = 4, + LOG_CHUNK1_SZ_IDX = 5, + LOG_CHUNK2_LO_IDX = 6, + LOG_CHUNK2_HI_IDX = 7, + LOG_CHUNK2_SZ_IDX = 8, + LOG_ROLLOVER_CNT_IDX = 9, + LOG_RESET_CNT_IDX = 10, + LOG_NR_IDX +}; + +struct pfrt_log_device { + int index; + struct pfrt_log_info info; + struct device *parent_dev; + struct miscdevice miscdev; +}; + +/* pfrt_guid is the parameter for _DSM method */ +static const guid_t pfrt_log_guid = + GUID_INIT(0x75191659, 0x8178, 0x4D9D, 0xB8, 0x8F, 0xAC, 0x5E, + 0x5E, 0x93, 0xE8, 0xBF); + +static DEFINE_IDA(pfrt_log_ida); + +static inline struct pfrt_log_device *to_pfrt_log_dev(struct file *file) +{ + return container_of(file->private_data, struct pfrt_log_device, miscdev); +} + +static int get_pfrt_log_data_info(struct pfrt_log_data_info *data_info, + struct pfrt_log_device *pfrt_log_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev); + union acpi_object *out_obj, in_obj, in_buf; + int ret = -EBUSY; + + memset(&in_obj, 0, sizeof(in_obj)); + memset(&in_buf, 0, sizeof(in_buf)); + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_INTEGER; + in_buf.integer.value = pfrt_log_dev->info.log_type; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid, + pfrt_log_dev->info.log_revid, PFRT_FUNC_GET_DATA, + &in_obj, ACPI_TYPE_PACKAGE); + if (!out_obj) + return -EINVAL; + + if (out_obj->package.count < LOG_NR_IDX || + out_obj->package.elements[LOG_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_MAX_SZ_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK1_LO_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK1_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK1_SZ_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK2_LO_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK2_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK2_SZ_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_ROLLOVER_CNT_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_RESET_CNT_IDX].type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + data_info->status = out_obj->package.elements[LOG_STATUS_IDX].integer.value; + data_info->ext_status = + out_obj->package.elements[LOG_EXT_STATUS_IDX].integer.value; + if (data_info->status != DSM_SUCCEED) { + dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", data_info->status); + dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", + data_info->ext_status); + goto free_acpi_buffer; + } + + data_info->max_data_size = + out_obj->package.elements[LOG_MAX_SZ_IDX].integer.value; + data_info->chunk1_addr_lo = + out_obj->package.elements[LOG_CHUNK1_LO_IDX].integer.value; + data_info->chunk1_addr_hi = + out_obj->package.elements[LOG_CHUNK1_HI_IDX].integer.value; + data_info->chunk1_size = + out_obj->package.elements[LOG_CHUNK1_SZ_IDX].integer.value; + data_info->chunk2_addr_lo = + out_obj->package.elements[LOG_CHUNK2_LO_IDX].integer.value; + data_info->chunk2_addr_hi = + out_obj->package.elements[LOG_CHUNK2_HI_IDX].integer.value; + data_info->chunk2_size = + out_obj->package.elements[LOG_CHUNK2_SZ_IDX].integer.value; + data_info->rollover_cnt = + out_obj->package.elements[LOG_ROLLOVER_CNT_IDX].integer.value; + data_info->reset_cnt = + out_obj->package.elements[LOG_RESET_CNT_IDX].integer.value; + + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int set_pfrt_log_level(int level, struct pfrt_log_device *pfrt_log_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev); + union acpi_object *out_obj, *obj, in_obj, in_buf; + enum pfru_dsm_status status, ext_status; + int ret = 0; + + memset(&in_obj, 0, sizeof(in_obj)); + memset(&in_buf, 0, sizeof(in_buf)); + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_INTEGER; + in_buf.integer.value = level; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid, + pfrt_log_dev->info.log_revid, PFRT_FUNC_SET_LEV, + &in_obj, ACPI_TYPE_PACKAGE); + if (!out_obj) + return -EINVAL; + + obj = &out_obj->package.elements[0]; + status = obj->integer.value; + if (status != DSM_SUCCEED) { + obj = &out_obj->package.elements[1]; + ext_status = obj->integer.value; + dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", status); + dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", ext_status); + ret = -EBUSY; + } + + kfree(out_obj); + + return ret; +} + +static int get_pfrt_log_level(struct pfrt_log_device *pfrt_log_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev); + union acpi_object *out_obj, *obj; + enum pfru_dsm_status status, ext_status; + int ret = -EBUSY; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid, + pfrt_log_dev->info.log_revid, PFRT_FUNC_GET_LEV, + NULL, ACPI_TYPE_PACKAGE); + if (!out_obj) + return -EINVAL; + + obj = &out_obj->package.elements[0]; + if (obj->type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + status = obj->integer.value; + if (status != DSM_SUCCEED) { + obj = &out_obj->package.elements[1]; + ext_status = obj->integer.value; + dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", status); + dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", ext_status); + goto free_acpi_buffer; + } + + obj = &out_obj->package.elements[2]; + if (obj->type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + ret = obj->integer.value; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int valid_log_level(u32 level) +{ + return level == PFRT_LOG_ERR || level == PFRT_LOG_WARN || + level == PFRT_LOG_INFO || level == PFRT_LOG_VERB; +} + +static int valid_log_type(u32 type) +{ + return type == PFRT_LOG_EXEC_IDX || type == PFRT_LOG_HISTORY_IDX; +} + +static inline int valid_log_revid(u32 id) +{ + return id == PFRT_REVID_1 || id == PFRT_REVID_2; +} + +static long pfrt_log_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct pfrt_log_device *pfrt_log_dev = to_pfrt_log_dev(file); + struct pfrt_log_data_info data_info; + struct pfrt_log_info info; + void __user *p; + int ret = 0; + + p = (void __user *)arg; + + switch (cmd) { + case PFRT_LOG_IOC_SET_INFO: + if (copy_from_user(&info, p, sizeof(info))) + return -EFAULT; + + if (valid_log_revid(info.log_revid)) + pfrt_log_dev->info.log_revid = info.log_revid; + + if (valid_log_level(info.log_level)) { + ret = set_pfrt_log_level(info.log_level, pfrt_log_dev); + if (ret < 0) + return ret; + + pfrt_log_dev->info.log_level = info.log_level; + } + + if (valid_log_type(info.log_type)) + pfrt_log_dev->info.log_type = info.log_type; + + return 0; + + case PFRT_LOG_IOC_GET_INFO: + info.log_level = get_pfrt_log_level(pfrt_log_dev); + if (ret < 0) + return ret; + + info.log_type = pfrt_log_dev->info.log_type; + info.log_revid = pfrt_log_dev->info.log_revid; + if (copy_to_user(p, &info, sizeof(info))) + return -EFAULT; + + return 0; + + case PFRT_LOG_IOC_GET_DATA_INFO: + ret = get_pfrt_log_data_info(&data_info, pfrt_log_dev); + if (ret) + return ret; + + if (copy_to_user(p, &data_info, sizeof(struct pfrt_log_data_info))) + return -EFAULT; + + return 0; + + default: + return -ENOTTY; + } +} + +static int +pfrt_log_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct pfrt_log_device *pfrt_log_dev; + struct pfrt_log_data_info info; + unsigned long psize, vsize; + phys_addr_t base_addr; + int ret; + + if (vma->vm_flags & VM_WRITE) + return -EROFS; + + /* changing from read to write with mprotect is not allowed */ + vma->vm_flags &= ~VM_MAYWRITE; + + pfrt_log_dev = to_pfrt_log_dev(file); + + ret = get_pfrt_log_data_info(&info, pfrt_log_dev); + if (ret) + return ret; + + base_addr = (phys_addr_t)((info.chunk2_addr_hi << 32) | info.chunk2_addr_lo); + /* pfrt update has not been launched yet */ + if (!base_addr) + return -ENODEV; + + psize = info.max_data_size; + /* base address and total buffer size must be page aligned */ + if (!PAGE_ALIGNED(base_addr) || !PAGE_ALIGNED(psize)) + return -ENODEV; + + vsize = vma->vm_end - vma->vm_start; + if (vsize > psize) + return -EINVAL; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + if (io_remap_pfn_range(vma, vma->vm_start, PFN_DOWN(base_addr), + vsize, vma->vm_page_prot)) + return -EAGAIN; + + return 0; +} + +static const struct file_operations acpi_pfrt_log_fops = { + .owner = THIS_MODULE, + .mmap = pfrt_log_mmap, + .unlocked_ioctl = pfrt_log_ioctl, + .llseek = noop_llseek, +}; + +static int acpi_pfrt_log_remove(struct platform_device *pdev) +{ + struct pfrt_log_device *pfrt_log_dev = platform_get_drvdata(pdev); + + misc_deregister(&pfrt_log_dev->miscdev); + + return 0; +} + +static void pfrt_log_put_idx(void *data) +{ + struct pfrt_log_device *pfrt_log_dev = data; + + ida_free(&pfrt_log_ida, pfrt_log_dev->index); +} + +static int acpi_pfrt_log_probe(struct platform_device *pdev) +{ + acpi_handle handle = ACPI_HANDLE(&pdev->dev); + struct pfrt_log_device *pfrt_log_dev; + int ret; + + if (!acpi_has_method(handle, "_DSM")) { + dev_dbg(&pdev->dev, "Missing _DSM\n"); + return -ENODEV; + } + + pfrt_log_dev = devm_kzalloc(&pdev->dev, sizeof(*pfrt_log_dev), GFP_KERNEL); + if (!pfrt_log_dev) + return -ENOMEM; + + ret = ida_alloc(&pfrt_log_ida, GFP_KERNEL); + if (ret < 0) + return ret; + + pfrt_log_dev->index = ret; + ret = devm_add_action_or_reset(&pdev->dev, pfrt_log_put_idx, pfrt_log_dev); + if (ret) + return ret; + + pfrt_log_dev->info.log_revid = PFRT_DEFAULT_REV_ID; + pfrt_log_dev->parent_dev = &pdev->dev; + + pfrt_log_dev->miscdev.minor = MISC_DYNAMIC_MINOR; + pfrt_log_dev->miscdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pfrt%d", + pfrt_log_dev->index); + if (!pfrt_log_dev->miscdev.name) + return -ENOMEM; + + pfrt_log_dev->miscdev.nodename = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "acpi_pfr_telemetry%d", + pfrt_log_dev->index); + if (!pfrt_log_dev->miscdev.nodename) + return -ENOMEM; + + pfrt_log_dev->miscdev.fops = &acpi_pfrt_log_fops; + pfrt_log_dev->miscdev.parent = &pdev->dev; + + ret = misc_register(&pfrt_log_dev->miscdev); + if (ret) + return ret; + + platform_set_drvdata(pdev, pfrt_log_dev); + + return 0; +} + +static const struct acpi_device_id acpi_pfrt_log_ids[] = { + {"INTC1081"}, + {} +}; +MODULE_DEVICE_TABLE(acpi, acpi_pfrt_log_ids); + +static struct platform_driver acpi_pfrt_log_driver = { + .driver = { + .name = "pfr_telemetry", + .acpi_match_table = acpi_pfrt_log_ids, + }, + .probe = acpi_pfrt_log_probe, + .remove = acpi_pfrt_log_remove, +}; +module_platform_driver(acpi_pfrt_log_driver); + +MODULE_DESCRIPTION("Platform Firmware Runtime Update Telemetry driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h index fa97e80a93b7..42fa15f8310d 100644 --- a/include/uapi/linux/pfrut.h +++ b/include/uapi/linux/pfrut.h @@ -171,4 +171,92 @@ struct pfru_updated_result { __u64 high_exec_time; }; +/** + * struct pfrt_log_data_info - Log Data from telemetry service. + * @status: Indicator of whether this update succeed. + * @ext_status: Implementation specific update result. + * @chunk1_addr_lo: Low 32bit physical address of the telemetry data chunk1 + * starting address. + * @chunk1_addr_hi: High 32bit physical address of the telemetry data chunk1 + * starting address. + * @chunk2_addr_lo: Low 32bit physical address of the telemetry data chunk2 + * starting address. + * @chunk2_addr_hi: High 32bit physical address of the telemetry data chunk2 + * starting address. + * @max_data_size: Maximum supported size of data of all data chunks combined. + * @chunk1_size: Data size in bytes of the telemetry data chunk1 buffer. + * @chunk2_size: Data size in bytes of the telemetry data chunk2 buffer. + * @rollover_cnt: Number of times telemetry data buffer is overwritten + * since telemetry buffer reset. + * @reset_cnt: Number of times telemetry services resets that results in + * rollover count and data chunk buffers are reset. + */ +struct pfrt_log_data_info { + __u32 status; + __u32 ext_status; + __u64 chunk1_addr_lo; + __u64 chunk1_addr_hi; + __u64 chunk2_addr_lo; + __u64 chunk2_addr_hi; + __u32 max_data_size; + __u32 chunk1_size; + __u32 chunk2_size; + __u32 rollover_cnt; + __u32 reset_cnt; +}; + +/** + * struct pfrt_log_info - Telemetry log information. + * @log_level: The telemetry log level. + * @log_type: The telemetry log type(history and execution). + * @log_revid: The telemetry log revision id. + */ +struct pfrt_log_info { + __u32 log_level; + __u32 log_type; + __u32 log_revid; +}; + +/** + * PFRT_LOG_IOC_SET_INFO - _IOW(PFRUT_IOCTL_MAGIC, 0x06, + * struct pfrt_log_info) + * + * Return: + * * 0 - success + * * -EFAULT - fail to get the setting parameter + * * -EINVAL - fail to set the log level + * + * Set the PFRT log level and log type. The input information is + * a struct pfrt_log_info. + */ +#define PFRT_LOG_IOC_SET_INFO _IOW(PFRUT_IOCTL_MAGIC, 0x06, struct pfrt_log_info) + +/** + * PFRT_LOG_IOC_GET_INFO - _IOR(PFRUT_IOCTL_MAGIC, 0x07, + * struct pfrt_log_info) + * + * Return: + * * 0 - success + * * -EINVAL - fail to get the log level + * * -EFAULT - fail to copy the result back to userspace + * + * Retrieve log level and log type of the telemetry. The information is + * a struct pfrt_log_info. + */ +#define PFRT_LOG_IOC_GET_INFO _IOR(PFRUT_IOCTL_MAGIC, 0x07, struct pfrt_log_info) + +/** + * PFRT_LOG_IOC_GET_DATA_INFO - _IOR(PFRUT_IOCTL_MAGIC, 0x08, + * struct pfrt_log_data_info) + * + * Return: + * * 0 - success + * * -EINVAL - fail to get the log buffer information + * * -EFAULT - fail to copy the log buffer information to userspace + * + * Retrieve data information about the telemetry. The information + * is a struct pfrt_log_data_info. + */ +#define PFRT_LOG_IOC_GET_DATA_INFO _IOR(PFRUT_IOCTL_MAGIC, 0x08, struct pfrt_log_data_info) + #endif /* __PFRUT_H__ */ -- cgit v1.2.3 From 1bb412d46ca9df90a3fe4b704f5385f03621455d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 29 Dec 2021 16:09:37 +0800 Subject: net_tstamp: define new flag HWTSTAMP_FLAG_BONDED_PHC_INDEX As we defined the new hwtstamp_config flag HWTSTAMP_FLAG_BONDED_PHC_INDEX as enum, it's not easy for userspace program to check if the flag is supported when build. Let's define the new flag so user space could build it on old kernel with ifdef check. Fixes: 9c9211a3fc7a ("net_tstamp: add new flag HWTSTAMP_FLAG_BONDED_PHC_INDEX") Signed-off-by: Hangbin Liu Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- include/uapi/linux/net_tstamp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index e258e52cfd1f..55501e5e7ac8 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -87,6 +87,7 @@ enum hwtstamp_flags { * will be the PHC index. */ HWTSTAMP_FLAG_BONDED_PHC_INDEX = (1<<0), +#define HWTSTAMP_FLAG_BONDED_PHC_INDEX HWTSTAMP_FLAG_BONDED_PHC_INDEX HWTSTAMP_FLAG_LAST = HWTSTAMP_FLAG_BONDED_PHC_INDEX, HWTSTAMP_FLAG_MASK = (HWTSTAMP_FLAG_LAST - 1) | HWTSTAMP_FLAG_LAST -- cgit v1.2.3 From 0f2a6c3b9219bdf497750258cd2ad513f0056b42 Mon Sep 17 00:00:00 2001 From: Muhammad Sammar Date: Sun, 5 Sep 2021 15:16:21 +0300 Subject: net/mlx5: Add misc5 flow table match parameters Add support for misc5 match parameter as per HW spec, this will allow matching on tunnel_header fields. Signed-off-by: Muhammad Sammar Signed-off-by: Yevgeny Kliteynik --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- include/linux/mlx5/device.h | 1 + include/linux/mlx5/mlx5_ifc.h | 25 ++++++++++++++++++++++- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 2 +- 4 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 7711db245c63..5469b08d635f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -203,7 +203,7 @@ struct mlx5_ft_underlay_qp { u32 qpn; }; -#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_c00 +#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_e00 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 9c25edfd59a6..604b85dd770a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1117,6 +1117,7 @@ enum { MLX5_MATCH_MISC_PARAMETERS_2 = 1 << 3, MLX5_MATCH_MISC_PARAMETERS_3 = 1 << 4, MLX5_MATCH_MISC_PARAMETERS_4 = 1 << 5, + MLX5_MATCH_MISC_PARAMETERS_5 = 1 << 6, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 18b816b41545..c74c5e147cb9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -670,6 +670,26 @@ struct mlx5_ifc_fte_match_set_misc4_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_fte_match_set_misc5_bits { + u8 macsec_tag_0[0x20]; + + u8 macsec_tag_1[0x20]; + + u8 macsec_tag_2[0x20]; + + u8 macsec_tag_3[0x20]; + + u8 tunnel_header_0[0x20]; + + u8 tunnel_header_1[0x20]; + + u8 tunnel_header_2[0x20]; + + u8 tunnel_header_3[0x20]; + + u8 reserved_at_100[0x100]; +}; + struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; @@ -1839,7 +1859,9 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_misc4_bits misc_parameters_4; - u8 reserved_at_c00[0x400]; + struct mlx5_ifc_fte_match_set_misc5_bits misc_parameters_5; + + u8 reserved_at_e00[0x200]; }; enum { @@ -5977,6 +5999,7 @@ enum { MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_4 = 0x5, + MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_5 = 0x6, }; struct mlx5_ifc_query_flow_group_out_bits { diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index ca2372864b70..e539c84d63f1 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -252,7 +252,7 @@ enum mlx5_ib_device_query_context_attrs { MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT), }; -#define MLX5_IB_DW_MATCH_PARAM 0x90 +#define MLX5_IB_DW_MATCH_PARAM 0xA0 struct mlx5_ib_match_params { __u32 match_params[MLX5_IB_DW_MATCH_PARAM]; -- cgit v1.2.3 From 79d39fc503b43b566feae5bc9a57dfcffdf41bd1 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 28 Dec 2021 21:06:10 +0800 Subject: net/smc: Add netlink net namespace support This adds net namespace ID to diag of linkgroup, helps us to distinguish different namespaces, and net_cookie is unique in the whole system. Signed-off-by: Tony Lu Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 2 ++ include/uapi/linux/smc_diag.h | 11 ++++++----- net/smc/smc_core.c | 3 +++ net/smc/smc_diag.c | 16 +++++++++------- 4 files changed, 20 insertions(+), 12 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 20f33b27787f..6c2874fd2c00 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -119,6 +119,8 @@ enum { SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ SMC_NLA_LGR_R_V2_COMMON, /* nest */ SMC_NLA_LGR_R_V2, /* nest */ + SMC_NLA_LGR_R_NET_COOKIE, /* u64 */ + SMC_NLA_LGR_R_PAD, /* flag */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 8cb3a6fef553..c7008d87f1a4 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -84,11 +84,12 @@ struct smc_diag_conninfo { /* SMC_DIAG_LINKINFO */ struct smc_diag_linkinfo { - __u8 link_id; /* link identifier */ - __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ - __u8 ibport; /* RDMA device port number */ - __u8 gid[40]; /* local GID */ - __u8 peer_gid[40]; /* peer GID */ + __u8 link_id; /* link identifier */ + __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ + __u8 ibport; /* RDMA device port number */ + __u8 gid[40]; /* local GID */ + __u8 peer_gid[40]; /* peer GID */ + __aligned_u64 net_cookie; /* RDMA device net namespace */ }; struct smc_diag_lgrinfo { diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index b53cdecf621d..e47538451612 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -348,6 +348,9 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_R_NET_COOKIE, + lgr->net->net_cookie, SMC_NLA_LGR_R_PAD)) + goto errattr; memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN); smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index c952986a6aca..7c8dad28c18d 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -145,19 +145,21 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, if (smc->conn.lgr && !smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { + struct smc_link *link = smc->conn.lnk; + struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net); + struct smc_diag_lgrinfo linfo = { .role = smc->conn.lgr->role, - .lnk[0].ibport = smc->conn.lnk->ibport, - .lnk[0].link_id = smc->conn.lnk->link_id, + .lnk[0].ibport = link->ibport, + .lnk[0].link_id = link->link_id, + .lnk[0].net_cookie = net->net_cookie, }; memcpy(linfo.lnk[0].ibname, smc->conn.lgr->lnk[0].smcibdev->ibdev->name, - sizeof(smc->conn.lnk->smcibdev->ibdev->name)); - smc_gid_be16_convert(linfo.lnk[0].gid, - smc->conn.lnk->gid); - smc_gid_be16_convert(linfo.lnk[0].peer_gid, - smc->conn.lnk->peer_gid); + sizeof(link->smcibdev->ibdev->name)); + smc_gid_be16_convert(linfo.lnk[0].gid, link->gid); + smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid); if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0) goto errout; -- cgit v1.2.3 From ccae4a19c9140a34a0c5f0658812496dd8bbdeaf Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 25 Oct 2021 17:31:54 +0100 Subject: btrfs: remove no longer needed logic for replaying directory deletes Now that we log only dir index keys when logging a directory, we no longer need to deal with dir item keys in the log replay code for replaying directory deletes. This is also true for the case when we replay a log tree created by a kernel that still logs dir items. So remove the remaining code of the replay of directory deletes algorithm that deals with dir item keys. Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 158 ++++++++++++++++++---------------------- include/uapi/linux/btrfs_tree.h | 4 +- 2 files changed, 72 insertions(+), 90 deletions(-) (limited to 'include/uapi') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 06defcd559a0..3da8452f682c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2203,7 +2203,7 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans, */ static noinline int find_dir_range(struct btrfs_root *root, struct btrfs_path *path, - u64 dirid, int key_type, + u64 dirid, u64 *start_ret, u64 *end_ret) { struct btrfs_key key; @@ -2216,7 +2216,7 @@ static noinline int find_dir_range(struct btrfs_root *root, return 1; key.objectid = dirid; - key.type = key_type; + key.type = BTRFS_DIR_LOG_INDEX_KEY; key.offset = *start_ret; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); @@ -2230,7 +2230,7 @@ static noinline int find_dir_range(struct btrfs_root *root, if (ret != 0) btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - if (key.type != key_type || key.objectid != dirid) { + if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto next; } @@ -2257,7 +2257,7 @@ next: btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - if (key.type != key_type || key.objectid != dirid) { + if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto out; } @@ -2288,95 +2288,82 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, int ret; struct extent_buffer *eb; int slot; - u32 item_size; struct btrfs_dir_item *di; - struct btrfs_dir_item *log_di; int name_len; - unsigned long ptr; - unsigned long ptr_end; char *name; - struct inode *inode; + struct inode *inode = NULL; struct btrfs_key location; -again: + /* + * Currenly we only log dir index keys. Even if we replay a log created + * by an older kernel that logged both dir index and dir item keys, all + * we need to do is process the dir index keys, we (and our caller) can + * safely ignore dir item keys (key type BTRFS_DIR_ITEM_KEY). + */ + ASSERT(dir_key->type == BTRFS_DIR_INDEX_KEY); + eb = path->nodes[0]; slot = path->slots[0]; - item_size = btrfs_item_size_nr(eb, slot); - ptr = btrfs_item_ptr_offset(eb, slot); - ptr_end = ptr + item_size; - while (ptr < ptr_end) { - di = (struct btrfs_dir_item *)ptr; - name_len = btrfs_dir_name_len(eb, di); - name = kmalloc(name_len, GFP_NOFS); - if (!name) { - ret = -ENOMEM; - goto out; - } - read_extent_buffer(eb, name, (unsigned long)(di + 1), - name_len); - log_di = NULL; - if (log && dir_key->type == BTRFS_DIR_ITEM_KEY) { - log_di = btrfs_lookup_dir_item(trans, log, log_path, - dir_key->objectid, - name, name_len, 0); - } else if (log && dir_key->type == BTRFS_DIR_INDEX_KEY) { - log_di = btrfs_lookup_dir_index_item(trans, log, - log_path, - dir_key->objectid, - dir_key->offset, - name, name_len, 0); - } - if (!log_di) { - btrfs_dir_item_key_to_cpu(eb, di, &location); - btrfs_release_path(path); - btrfs_release_path(log_path); - inode = read_one_inode(root, location.objectid); - if (!inode) { - kfree(name); - return -EIO; - } + di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); + name_len = btrfs_dir_name_len(eb, di); + name = kmalloc(name_len, GFP_NOFS); + if (!name) { + ret = -ENOMEM; + goto out; + } - ret = link_to_fixup_dir(trans, root, - path, location.objectid); - if (ret) { - kfree(name); - iput(inode); - goto out; - } + read_extent_buffer(eb, name, (unsigned long)(di + 1), name_len); - inc_nlink(inode); - ret = btrfs_unlink_inode(trans, BTRFS_I(dir), - BTRFS_I(inode), name, name_len); - if (!ret) - ret = btrfs_run_delayed_items(trans); - kfree(name); - iput(inode); - if (ret) - goto out; + if (log) { + struct btrfs_dir_item *log_di; - /* there might still be more names under this key - * check and repeat if required - */ - ret = btrfs_search_slot(NULL, root, dir_key, path, - 0, 0); - if (ret == 0) - goto again; + log_di = btrfs_lookup_dir_index_item(trans, log, log_path, + dir_key->objectid, + dir_key->offset, + name, name_len, 0); + if (IS_ERR(log_di)) { + ret = PTR_ERR(log_di); + goto out; + } else if (log_di) { + /* The dentry exists in the log, we have nothing to do. */ ret = 0; goto out; - } else if (IS_ERR(log_di)) { - kfree(name); - return PTR_ERR(log_di); } - btrfs_release_path(log_path); - kfree(name); + } - ptr = (unsigned long)(di + 1); - ptr += name_len; + btrfs_dir_item_key_to_cpu(eb, di, &location); + btrfs_release_path(path); + btrfs_release_path(log_path); + inode = read_one_inode(root, location.objectid); + if (!inode) { + ret = -EIO; + goto out; } - ret = 0; + + ret = link_to_fixup_dir(trans, root, path, location.objectid); + if (ret) + goto out; + + inc_nlink(inode); + ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(inode), name, + name_len); + if (ret) + goto out; + + ret = btrfs_run_delayed_items(trans); + if (ret) + goto out; + + /* + * Unlike dir item keys, dir index keys can only have one name (entry) in + * them, as there are no key collisions since each key has a unique offset + * (an index number), so we're done. + */ out: btrfs_release_path(path); btrfs_release_path(log_path); + kfree(name); + iput(inode); return ret; } @@ -2496,7 +2483,6 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, { u64 range_start; u64 range_end; - int key_type = BTRFS_DIR_LOG_ITEM_KEY; int ret = 0; struct btrfs_key dir_key; struct btrfs_key found_key; @@ -2504,7 +2490,7 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct inode *dir; dir_key.objectid = dirid; - dir_key.type = BTRFS_DIR_ITEM_KEY; + dir_key.type = BTRFS_DIR_INDEX_KEY; log_path = btrfs_alloc_path(); if (!log_path) return -ENOMEM; @@ -2518,14 +2504,14 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, btrfs_free_path(log_path); return 0; } -again: + range_start = 0; range_end = 0; while (1) { if (del_all) range_end = (u64)-1; else { - ret = find_dir_range(log, path, dirid, key_type, + ret = find_dir_range(log, path, dirid, &range_start, &range_end); if (ret < 0) goto out; @@ -2552,8 +2538,10 @@ again: btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); if (found_key.objectid != dirid || - found_key.type != dir_key.type) - goto next_type; + found_key.type != dir_key.type) { + ret = 0; + goto out; + } if (found_key.offset > range_end) break; @@ -2572,15 +2560,7 @@ again: break; range_start = range_end + 1; } - -next_type: ret = 0; - if (key_type == BTRFS_DIR_LOG_ITEM_KEY) { - key_type = BTRFS_DIR_LOG_INDEX_KEY; - dir_key.type = BTRFS_DIR_INDEX_KEY; - btrfs_release_path(path); - goto again; - } out: btrfs_release_path(path); btrfs_free_path(log_path); diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index e1c4c732aaba..5416f1f1a77a 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -146,7 +146,9 @@ /* * dir items are the name -> inode pointers in a directory. There is one - * for every name in a directory. + * for every name in a directory. BTRFS_DIR_LOG_ITEM_KEY is no longer used + * but it's still defined here for documentation purposes and to help avoid + * having its numerical value reused in the future. */ #define BTRFS_DIR_LOG_ITEM_KEY 60 #define BTRFS_DIR_LOG_INDEX_KEY 72 -- cgit v1.2.3 From 5bc03b28ec24670e67c453ecb2bfbb9053b86838 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 20 Dec 2021 11:51:47 +0100 Subject: nl80211: clarify comment for mesh PLINK_BLOCKED state When a mesh link is in blocked state, it is very useful to still allow auth requests from the peer to re-establish it. When a remote node is power cycled, the peer state can easily end up in blocked state if multiple auth attempts are performed. Since this can lead to several minutes of downtime, we should accept auth attempts of the peer after it has come back. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20211220105147.88625-1-nbd@nbd.name Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f1a9d6594df2..195a238a322e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5623,7 +5623,7 @@ enum nl80211_if_combination_attrs { * @NL80211_PLINK_ESTAB: mesh peer link is established * @NL80211_PLINK_HOLDING: mesh peer link is being closed or cancelled * @NL80211_PLINK_BLOCKED: all frames transmitted from this mesh - * plink are discarded + * plink are discarded, except for authentication frames * @NUM_NL80211_PLINK_STATES: number of peer link states * @MAX_NL80211_PLINK_STATES: highest numerical value of plink states */ -- cgit v1.2.3 From 403a2e236538c6b479ea5bfc8b75a75540cfba6b Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Mon, 13 Dec 2021 11:51:34 -0700 Subject: dmaengine: idxd: change MSIX allocation based on per wq activation Change the driver where WQ interrupt is requested only when wq is being enabled. This new scheme set things up so that request_threaded_irq() is only called when a kernel wq type is being enabled. This also sets up for future interrupt request where different interrupt handler such as wq occupancy interrupt can be setup instead of the wq completion interrupt. Not calling request_irq() until the WQ actually needs an irq also prevents wasting of CPU irq vectors on x86 systems, which is a limited resource. idxd_flush_pending_descs() is moved to device.c since descriptor flushing is now part of wq disable rather than shutdown(). Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/163942149487.2412839.6691222855803875848.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/device.c | 161 ++++++++++++++++++++++++++++------------------ drivers/dma/idxd/dma.c | 12 ++++ drivers/dma/idxd/idxd.h | 7 +- drivers/dma/idxd/init.c | 133 ++++---------------------------------- drivers/dma/idxd/irq.c | 3 + include/uapi/linux/idxd.h | 1 + 6 files changed, 132 insertions(+), 185 deletions(-) (limited to 'include/uapi') diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 8233a29f859d..280b41417f41 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -19,36 +19,6 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd); static void idxd_wq_disable_cleanup(struct idxd_wq *wq); /* Interrupt control bits */ -void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id) -{ - struct idxd_irq_entry *ie; - struct irq_data *data; - - ie = idxd_get_ie(idxd, vec_id); - data = irq_get_irq_data(ie->vector); - pci_msi_mask_irq(data); -} - -void idxd_mask_msix_vectors(struct idxd_device *idxd) -{ - struct pci_dev *pdev = idxd->pdev; - int msixcnt = pci_msix_vec_count(pdev); - int i; - - for (i = 0; i < msixcnt; i++) - idxd_mask_msix_vector(idxd, i); -} - -void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id) -{ - struct idxd_irq_entry *ie; - struct irq_data *data; - - ie = idxd_get_ie(idxd, vec_id); - data = irq_get_irq_data(ie->vector); - pci_msi_unmask_irq(data); -} - void idxd_unmask_error_interrupts(struct idxd_device *idxd) { union genctrl_reg genctrl; @@ -593,7 +563,6 @@ void idxd_device_reset(struct idxd_device *idxd) idxd_device_clear_state(idxd); idxd->state = IDXD_DEV_DISABLED; idxd_unmask_error_interrupts(idxd); - idxd_msix_perm_setup(idxd); spin_unlock(&idxd->dev_lock); } @@ -732,36 +701,6 @@ void idxd_device_clear_state(struct idxd_device *idxd) idxd_device_wqs_clear_state(idxd); } -void idxd_msix_perm_setup(struct idxd_device *idxd) -{ - union msix_perm mperm; - int i, msixcnt; - - msixcnt = pci_msix_vec_count(idxd->pdev); - if (msixcnt < 0) - return; - - mperm.bits = 0; - mperm.pasid = idxd->pasid; - mperm.pasid_en = device_pasid_enabled(idxd); - for (i = 1; i < msixcnt; i++) - iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); -} - -void idxd_msix_perm_clear(struct idxd_device *idxd) -{ - union msix_perm mperm; - int i, msixcnt; - - msixcnt = pci_msix_vec_count(idxd->pdev); - if (msixcnt < 0) - return; - - mperm.bits = 0; - for (i = 1; i < msixcnt; i++) - iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); -} - static void idxd_group_config_write(struct idxd_group *group) { struct idxd_device *idxd = group->idxd; @@ -1158,6 +1097,106 @@ int idxd_device_load_config(struct idxd_device *idxd) return 0; } +static void idxd_flush_pending_descs(struct idxd_irq_entry *ie) +{ + struct idxd_desc *desc, *itr; + struct llist_node *head; + LIST_HEAD(flist); + enum idxd_complete_type ctype; + + spin_lock(&ie->list_lock); + head = llist_del_all(&ie->pending_llist); + if (head) { + llist_for_each_entry_safe(desc, itr, head, llnode) + list_add_tail(&desc->list, &ie->work_list); + } + + list_for_each_entry_safe(desc, itr, &ie->work_list, list) + list_move_tail(&desc->list, &flist); + spin_unlock(&ie->list_lock); + + list_for_each_entry_safe(desc, itr, &flist, list) { + list_del(&desc->list); + ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT; + idxd_dma_complete_txd(desc, ctype, true); + } +} + +static void idxd_device_set_perm_entry(struct idxd_device *idxd, + struct idxd_irq_entry *ie) +{ + union msix_perm mperm; + + if (ie->pasid == INVALID_IOASID) + return; + + mperm.bits = 0; + mperm.pasid = ie->pasid; + mperm.pasid_en = 1; + iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8); +} + +static void idxd_device_clear_perm_entry(struct idxd_device *idxd, + struct idxd_irq_entry *ie) +{ + iowrite32(0, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8); +} + +void idxd_wq_free_irq(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct idxd_irq_entry *ie = &wq->ie; + + synchronize_irq(ie->vector); + free_irq(ie->vector, ie); + idxd_flush_pending_descs(ie); + if (idxd->request_int_handles) + idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); + idxd_device_clear_perm_entry(idxd, ie); + ie->vector = -1; + ie->int_handle = INVALID_INT_HANDLE; + ie->pasid = INVALID_IOASID; +} + +int idxd_wq_request_irq(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct pci_dev *pdev = idxd->pdev; + struct device *dev = &pdev->dev; + struct idxd_irq_entry *ie; + int rc; + + ie = &wq->ie; + ie->vector = pci_irq_vector(pdev, ie->id); + ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID; + idxd_device_set_perm_entry(idxd, ie); + + rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie); + if (rc < 0) { + dev_err(dev, "Failed to request irq %d.\n", ie->vector); + goto err_irq; + } + + if (idxd->request_int_handles) { + rc = idxd_device_request_int_handle(idxd, ie->id, &ie->int_handle, + IDXD_IRQ_MSIX); + if (rc < 0) + goto err_int_handle; + } else { + ie->int_handle = ie->id; + } + + return 0; + +err_int_handle: + ie->int_handle = INVALID_INT_HANDLE; + free_irq(ie->vector, ie); +err_irq: + idxd_device_clear_perm_entry(idxd, ie); + ie->pasid = INVALID_IOASID; + return rc; +} + int __drv_enable_wq(struct idxd_wq *wq) { struct idxd_device *idxd = wq->idxd; diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c index 2ce873994e33..bfff59617d04 100644 --- a/drivers/dma/idxd/dma.c +++ b/drivers/dma/idxd/dma.c @@ -289,6 +289,14 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev) mutex_lock(&wq->wq_lock); wq->type = IDXD_WQT_KERNEL; + + rc = idxd_wq_request_irq(wq); + if (rc < 0) { + idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR; + dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc); + goto err_irq; + } + rc = __drv_enable_wq(wq); if (rc < 0) { dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc); @@ -329,6 +337,8 @@ err_ref: err_res_alloc: __drv_disable_wq(wq); err: + idxd_wq_free_irq(wq); +err_irq: wq->type = IDXD_WQT_NONE; mutex_unlock(&wq->wq_lock); return rc; @@ -344,6 +354,8 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev) idxd_wq_free_resources(wq); __drv_disable_wq(wq); percpu_ref_exit(&wq->wq_active); + idxd_wq_free_irq(wq); + wq->type = IDXD_WQT_NONE; mutex_unlock(&wq->wq_lock); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index d77be03dd8b0..6353e762286d 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -548,15 +548,10 @@ void idxd_wqs_quiesce(struct idxd_device *idxd); bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc); /* device interrupt control */ -void idxd_msix_perm_setup(struct idxd_device *idxd); -void idxd_msix_perm_clear(struct idxd_device *idxd); irqreturn_t idxd_misc_thread(int vec, void *data); irqreturn_t idxd_wq_thread(int irq, void *data); void idxd_mask_error_interrupts(struct idxd_device *idxd); void idxd_unmask_error_interrupts(struct idxd_device *idxd); -void idxd_mask_msix_vectors(struct idxd_device *idxd); -void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id); -void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id); /* device control */ int idxd_register_idxd_drv(void); @@ -595,6 +590,8 @@ int idxd_wq_disable_pasid(struct idxd_wq *wq); void __idxd_wq_quiesce(struct idxd_wq *wq); void idxd_wq_quiesce(struct idxd_wq *wq); int idxd_wq_init_percpu_ref(struct idxd_wq *wq); +void idxd_wq_free_irq(struct idxd_wq *wq); +int idxd_wq_request_irq(struct idxd_wq *wq); /* submission */ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 03c735727f68..3505efb7ae71 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -90,7 +90,6 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) } dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt); - idxd_msix_perm_setup(idxd); ie = idxd_get_ie(idxd, 0); ie->vector = pci_irq_vector(pdev, 0); @@ -99,65 +98,26 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) dev_err(dev, "Failed to allocate misc interrupt.\n"); goto err_misc_irq; } - - dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", ie->vector); + dev_dbg(dev, "Requested idxd-misc handler on msix vector %d\n", ie->vector); for (i = 0; i < idxd->max_wqs; i++) { int msix_idx = i + 1; ie = idxd_get_ie(idxd, msix_idx); - - /* MSIX vector 0 special, wq irq entry starts at 1 */ ie->id = msix_idx; - ie->vector = pci_irq_vector(pdev, msix_idx); ie->int_handle = INVALID_INT_HANDLE; - if (device_pasid_enabled(idxd) && i > 0) - ie->pasid = idxd->pasid; - else - ie->pasid = INVALID_IOASID; + ie->pasid = INVALID_IOASID; + spin_lock_init(&ie->list_lock); init_llist_head(&ie->pending_llist); INIT_LIST_HEAD(&ie->work_list); - - rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie); - if (rc < 0) { - dev_err(dev, "Failed to allocate irq %d.\n", ie->vector); - goto err_wq_irqs; - } - - dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", i, ie->vector); - if (idxd->request_int_handles) { - rc = idxd_device_request_int_handle(idxd, i, &ie->int_handle, - IDXD_IRQ_MSIX); - if (rc < 0) { - free_irq(ie->vector, ie); - goto err_wq_irqs; - } - dev_dbg(dev, "int handle requested: %u\n", ie->int_handle); - } else { - ie->int_handle = msix_idx; - } - } idxd_unmask_error_interrupts(idxd); return 0; - err_wq_irqs: - while (--i >= 0) { - ie = &idxd->wqs[i]->ie; - free_irq(ie->vector, ie); - if (ie->int_handle != INVALID_INT_HANDLE) { - idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); - ie->int_handle = INVALID_INT_HANDLE; - ie->pasid = INVALID_IOASID; - } - ie->vector = -1; - } err_misc_irq: - /* Disable error interrupt generation */ idxd_mask_error_interrupts(idxd); - idxd_msix_perm_clear(idxd); pci_free_irq_vectors(pdev); dev_err(dev, "No usable interrupts\n"); return rc; @@ -167,20 +127,15 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd) { struct pci_dev *pdev = idxd->pdev; struct idxd_irq_entry *ie; - int i; + int msixcnt; - for (i = 0; i < idxd->irq_cnt; i++) { - ie = idxd_get_ie(idxd, i); - if (ie->int_handle != INVALID_INT_HANDLE) { - idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); - ie->int_handle = INVALID_INT_HANDLE; - ie->pasid = INVALID_IOASID; - } - free_irq(ie->vector, ie); - ie->vector = -1; - } + msixcnt = pci_msix_vec_count(pdev); + if (msixcnt <= 0) + return; + ie = idxd_get_ie(idxd, 0); idxd_mask_error_interrupts(idxd); + free_irq(ie->vector, ie); pci_free_irq_vectors(pdev); } @@ -592,8 +547,6 @@ static int idxd_probe(struct idxd_device *idxd) if (rc) goto err_config; - dev_dbg(dev, "IDXD interrupt setup complete.\n"); - idxd->major = idxd_cdev_get_major(idxd); rc = perfmon_pmu_init(idxd); @@ -689,31 +642,6 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return rc; } -static void idxd_flush_pending_descs(struct idxd_irq_entry *ie) -{ - struct idxd_desc *desc, *itr; - struct llist_node *head; - LIST_HEAD(flist); - enum idxd_complete_type ctype; - - spin_lock(&ie->list_lock); - head = llist_del_all(&ie->pending_llist); - if (head) { - llist_for_each_entry_safe(desc, itr, head, llnode) - list_add_tail(&desc->list, &ie->work_list); - } - - list_for_each_entry_safe(desc, itr, &ie->work_list, list) - list_move_tail(&desc->list, &flist); - spin_unlock(&ie->list_lock); - - list_for_each_entry_safe(desc, itr, &flist, list) { - list_del(&desc->list); - ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT; - idxd_dma_complete_txd(desc, ctype, true); - } -} - void idxd_wqs_quiesce(struct idxd_device *idxd) { struct idxd_wq *wq; @@ -726,46 +654,19 @@ void idxd_wqs_quiesce(struct idxd_device *idxd) } } -static void idxd_release_int_handles(struct idxd_device *idxd) -{ - struct device *dev = &idxd->pdev->dev; - int i, rc; - - for (i = 1; i < idxd->irq_cnt; i++) { - struct idxd_irq_entry *ie = idxd_get_ie(idxd, i); - - if (ie->int_handle != INVALID_INT_HANDLE) { - rc = idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); - if (rc < 0) - dev_warn(dev, "irq handle %d release failed\n", ie->int_handle); - else - dev_dbg(dev, "int handle released: %u\n", ie->int_handle); - } - } -} - static void idxd_shutdown(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); - int rc, i; struct idxd_irq_entry *irq_entry; - int msixcnt = pci_msix_vec_count(pdev); + int rc; rc = idxd_device_disable(idxd); if (rc) dev_err(&pdev->dev, "Disabling device failed\n"); - dev_dbg(&pdev->dev, "%s called\n", __func__); - idxd_mask_msix_vectors(idxd); + irq_entry = &idxd->ie; + synchronize_irq(irq_entry->vector); idxd_mask_error_interrupts(idxd); - - for (i = 0; i < msixcnt; i++) { - irq_entry = idxd_get_ie(idxd, i); - synchronize_irq(irq_entry->vector); - if (i == 0) - continue; - idxd_flush_pending_descs(irq_entry); - } flush_workqueue(idxd->wq); } @@ -773,8 +674,6 @@ static void idxd_remove(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); struct idxd_irq_entry *irq_entry; - int msixcnt = pci_msix_vec_count(pdev); - int i; idxd_unregister_devices(idxd); /* @@ -790,12 +689,8 @@ static void idxd_remove(struct pci_dev *pdev) if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); - for (i = 0; i < msixcnt; i++) { - irq_entry = idxd_get_ie(idxd, i); - free_irq(irq_entry->vector, irq_entry); - } - idxd_msix_perm_clear(idxd); - idxd_release_int_handles(idxd); + irq_entry = idxd_get_ie(idxd, 0); + free_irq(irq_entry->vector, irq_entry); pci_free_irq_vectors(pdev); pci_iounmap(pdev, idxd->reg_base); iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index a1316f341dd6..743ead5ebc57 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -158,6 +158,9 @@ static void idxd_int_handle_revoke(struct work_struct *work) struct idxd_irq_entry *ie = idxd_get_ie(idxd, i); struct idxd_wq *wq = ie_to_wq(ie); + if (ie->int_handle == INVALID_INT_HANDLE) + continue; + rc = idxd_device_request_int_handle(idxd, i, &new_handle, IDXD_IRQ_MSIX); if (rc < 0) { dev_warn(dev, "get int handle %d failed: %d\n", i, rc); diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index c750eac09fc9..a8f0ff75c430 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -28,6 +28,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000, IDXD_SCMD_WQ_NO_SIZE = 0x800e0000, IDXD_SCMD_WQ_NO_PRIV = 0x800f0000, + IDXD_SCMD_WQ_IRQ_ERR = 0x80100000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 -- cgit v1.2.3 From 383f0993fc77152b0773c85ed69d6734baf9cb48 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 14 Dec 2021 01:02:26 +0900 Subject: can: netlink: report the CAN controller mode supported flags Currently, the CAN netlink interface provides no easy ways to check the capabilities of a given controller. The only method from the command line is to try each CAN_CTRLMODE_* individually to check whether the netlink interface returns an -EOPNOTSUPP error or not (alternatively, one may find it easier to directly check the source code of the driver instead...) This patch introduces a method for the user to check both the supported and the static capabilities. The proposed method introduces a new IFLA nest: IFLA_CAN_CTRLMODE_EXT which extends the current IFLA_CAN_CTRLMODE. This is done to guaranty a full forward and backward compatibility between the kernel and the user land applications. The IFLA_CAN_CTRLMODE_EXT nest contains one single entry: IFLA_CAN_CTRLMODE_SUPPORTED. Because this entry is only used in one direction: kernel to userland, no new struct nla_policy are introduced. Below table explains how IFLA_CAN_CTRLMODE_SUPPORTED (hereafter: "supported") and can_ctrlmode::flags (hereafter: "flags") allow us to identify both the supported and the static capabilities, when masked with any of the CAN_CTRLMODE_* bit flags: supported & flags & Controller capabilities CAN_CTRLMODE_* CAN_CTRLMODE_* ----------------------------------------------------------------------- false false Feature not supported (always disabled) false true Static feature (always enabled) true false Feature supported but disabled true true Feature supported and enabled Link: https://lore.kernel.org/all/20211213160226.56219-5-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/netlink.c | 31 ++++++++++++++++++++++++++++++- include/uapi/linux/can/netlink.h | 13 +++++++++++++ 2 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 26c336808be5..7633d98e3912 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -21,6 +21,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { [IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, [IFLA_CAN_TDC] = { .type = NLA_NESTED }, + [IFLA_CAN_CTRLMODE_EXT] = { .type = NLA_NESTED }, }; static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { @@ -383,6 +384,12 @@ static size_t can_tdc_get_size(const struct net_device *dev) return size; } +static size_t can_ctrlmode_ext_get_size(void) +{ + return nla_total_size(0) + /* nest IFLA_CAN_CTRLMODE_EXT */ + nla_total_size(sizeof(u32)); /* IFLA_CAN_CTRLMODE_SUPPORTED */ +} + static size_t can_get_size(const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -415,6 +422,7 @@ static size_t can_get_size(const struct net_device *dev) priv->data_bitrate_const_cnt); size += sizeof(priv->bitrate_max); /* IFLA_CAN_BITRATE_MAX */ size += can_tdc_get_size(dev); /* IFLA_CAN_TDC */ + size += can_ctrlmode_ext_get_size(); /* IFLA_CAN_CTRLMODE_EXT */ return size; } @@ -472,6 +480,25 @@ err_cancel: return -EMSGSIZE; } +static int can_ctrlmode_ext_fill_info(struct sk_buff *skb, + const struct can_priv *priv) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, IFLA_CAN_CTRLMODE_EXT); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, IFLA_CAN_CTRLMODE_SUPPORTED, + priv->ctrlmode_supported)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + + nla_nest_end(skb, nest); + return 0; +} + static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -531,7 +558,9 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) sizeof(priv->bitrate_max), &priv->bitrate_max)) || - (can_tdc_fill_info(skb, dev)) + can_tdc_fill_info(skb, dev) || + + can_ctrlmode_ext_fill_info(skb, priv) ) return -EMSGSIZE; diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 75b85c60efb2..02ec32d69474 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -137,6 +137,7 @@ enum { IFLA_CAN_DATA_BITRATE_CONST, IFLA_CAN_BITRATE_MAX, IFLA_CAN_TDC, + IFLA_CAN_CTRLMODE_EXT, /* add new constants above here */ __IFLA_CAN_MAX, @@ -166,6 +167,18 @@ enum { IFLA_CAN_TDC_MAX = __IFLA_CAN_TDC - 1 }; +/* + * IFLA_CAN_CTRLMODE_EXT nest: controller mode extended parameters + */ +enum { + IFLA_CAN_CTRLMODE_UNSPEC, + IFLA_CAN_CTRLMODE_SUPPORTED, /* u32 */ + + /* add new constants above here */ + __IFLA_CAN_CTRLMODE, + IFLA_CAN_CTRLMODE_MAX = __IFLA_CAN_CTRLMODE - 1 +}; + /* u16 termination range: 1..65535 Ohms */ #define CAN_TERMINATION_DISABLED 0 -- cgit v1.2.3 From a457fd5660efa9cf960d2461156a1025bfdb13fa Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 26 Nov 2021 17:05:51 +0530 Subject: RISC-V: KVM: Add VM capability to allow userspace get GPA bits The number of GPA bits supported for a RISC-V Guest/VM is based on the MMU mode used by the G-stage translation. The KVM RISC-V will detect and use the best possible MMU mode for the G-stage in kvm_arch_init(). We add a generic VM capability KVM_CAP_VM_GPA_BITS which can be used by the KVM userspace to get the number of GPA (guest physical address) bits supported for a Guest/VM. Signed-off-by: Anup Patel Reviewed-and-tested-by: Atish Patra --- arch/riscv/include/asm/kvm_host.h | 1 + arch/riscv/kvm/mmu.c | 5 +++++ arch/riscv/kvm/vm.c | 3 +++ include/uapi/linux/kvm.h | 1 + 4 files changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 52e19888ce43..99ef6a120617 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -218,6 +218,7 @@ void kvm_riscv_stage2_free_pgd(struct kvm *kvm); void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu); void kvm_riscv_stage2_mode_detect(void); unsigned long kvm_riscv_stage2_mode(void); +int kvm_riscv_stage2_gpa_bits(void); void kvm_riscv_stage2_vmid_detect(void); unsigned long kvm_riscv_stage2_vmid_bits(void); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 5f2736c2e773..9af67dbdc66a 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -769,3 +769,8 @@ unsigned long kvm_riscv_stage2_mode(void) { return stage2_mode >> HGATP_MODE_SHIFT; } + +int kvm_riscv_stage2_gpa_bits(void) +{ + return stage2_gpa_bits; +} diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7619691d8953..c768f75279ef 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -74,6 +74,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_NR_MEMSLOTS: r = KVM_USER_MEM_SLOTS; break; + case KVM_CAP_VM_GPA_BITS: + r = kvm_riscv_stage2_gpa_bits(); + break; default: r = 0; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 1daa45268de2..469f05d69c8d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1131,6 +1131,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 +#define KVM_CAP_VM_GPA_BITS 207 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From eac1b93c14d645ef147b049ace0d5230df755548 Mon Sep 17 00:00:00 2001 From: Coco Li Date: Wed, 5 Jan 2022 02:48:38 -0800 Subject: gro: add ability to control gro max packet size Eric Dumazet suggested to allow users to modify max GRO packet size. We have seen GRO being disabled by users of appliances (such as wifi access points) because of claimed bufferbloat issues, or some work arounds in sch_cake, to split GRO/GSO packets. Instead of disabling GRO completely, one can chose to limit the maximum packet size of GRO packets, depending on their latency constraints. This patch adds a per device gro_max_size attribute that can be changed with ip link command. ip link set dev eth0 gro_max_size 16000 Suggested-by: Eric Dumazet Signed-off-by: Coco Li Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 +++++++++++ include/uapi/linux/if_link.h | 1 + net/core/dev.c | 1 + net/core/gro.c | 6 +++++- net/core/rtnetlink.c | 22 ++++++++++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + 6 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6f99c8f51b60..3213c7227b59 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1942,6 +1942,8 @@ enum netdev_ml_priv_type { * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. + * @gro_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO) * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. @@ -2131,6 +2133,8 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; +#define GRO_MAX_SIZE 65536 + unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -4806,6 +4810,13 @@ static inline void netif_set_gso_max_segs(struct net_device *dev, WRITE_ONCE(dev->gso_max_segs, segs); } +static inline void netif_set_gro_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_max_size, size); +} + static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4ac53b30b6dc..6218f93f5c1a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -347,6 +347,7 @@ enum { */ IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index 6c8b226b5f2f..83a4089990a0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10180,6 +10180,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->gro_max_size = GRO_MAX_SIZE; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP diff --git a/net/core/gro.c b/net/core/gro.c index 8ec8b44596da..a11b286d1495 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -132,10 +132,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; + unsigned int gro_max_size; unsigned int new_truesize; struct sk_buff *lp; - if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) + /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ + gro_max_size = READ_ONCE(p->dev->gro_max_size); + + if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) return -E2BIG; lp = NAPI_GRO_CB(p)->last; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d6eba554b137..e476403231f0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1026,6 +1026,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + 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(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ @@ -1728,6 +1729,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || 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) || #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif @@ -1880,6 +1882,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED }, [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, + [IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2299,6 +2302,14 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], } } + if (tb[IFLA_GRO_MAX_SIZE]) { + u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]); + + if (gro_max_size > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + } return 0; } @@ -2772,6 +2783,15 @@ static int do_setlink(const struct sk_buff *skb, } } + if (tb[IFLA_GRO_MAX_SIZE]) { + u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]); + + if (dev->gro_max_size ^ gro_max_size) { + netif_set_gro_max_size(dev, gro_max_size); + status |= DO_SETLINK_MODIFIED; + } + } + if (tb[IFLA_OPERSTATE]) set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); @@ -3222,6 +3242,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE])); if (tb[IFLA_GSO_MAX_SEGS]) 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])); return dev; } diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 4ac53b30b6dc..6218f93f5c1a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -347,6 +347,7 @@ enum { */ IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, __IFLA_MAX }; -- cgit v1.2.3 From 14243b387137a4afbe1df5d9dc15182d6657bb79 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 10 Dec 2021 16:36:23 +0000 Subject: KVM: x86/xen: Add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery This adds basic support for delivering 2 level event channels to a guest. Initially, it only supports delivery via the IRQ routing table, triggered by an eventfd. In order to do so, it has a kvm_xen_set_evtchn_fast() function which will use the pre-mapped shared_info page if it already exists and is still valid, while the slow path through the irqfd_inject workqueue will remap the shared_info page if necessary. It sets the bits in the shared_info page but not the vcpu_info; that is deferred to __kvm_xen_has_interrupt() which raises the vector to the appropriate vCPU. Add a 'verbose' mode to xen_shinfo_test while adding test cases for this. Signed-off-by: David Woodhouse Message-Id: <20211210163625.2886-5-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 21 ++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/irq_comm.c | 12 + arch/x86/kvm/x86.c | 3 +- arch/x86/kvm/xen.c | 262 ++++++++++++++++++++- arch/x86/kvm/xen.h | 9 + include/linux/kvm_host.h | 7 + include/uapi/linux/kvm.h | 11 + .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 184 ++++++++++++++- 9 files changed, 503 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c168be764707..6b683dfea8f2 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1799,6 +1799,7 @@ No flags are specified so far, the corresponding field must be set to zero. struct kvm_irq_routing_msi msi; struct kvm_irq_routing_s390_adapter adapter; struct kvm_irq_routing_hv_sint hv_sint; + struct kvm_irq_routing_xen_evtchn xen_evtchn; __u32 pad[8]; } u; }; @@ -1808,6 +1809,7 @@ No flags are specified so far, the corresponding field must be set to zero. #define KVM_IRQ_ROUTING_MSI 2 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 #define KVM_IRQ_ROUTING_HV_SINT 4 + #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 flags: @@ -1859,6 +1861,20 @@ address_hi must be zero. __u32 sint; }; + struct kvm_irq_routing_xen_evtchn { + __u32 port; + __u32 vcpu; + __u32 priority; + }; + + +When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL bit +in its indication of supported features, routing to Xen event channels +is supported. Although the priority field is present, only the value +KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported, which means delivery by +2 level event channels. FIFO event channel support may be added in +the future. + 4.55 KVM_SET_TSC_KHZ -------------------- @@ -7413,6 +7429,7 @@ PVHVM guests. Valid flags are:: #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 2) + #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 3) The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG ioctl is available, for the guest to set its hypercall page. @@ -7432,6 +7449,10 @@ The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls. +The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries +of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority +field set to indicate 2 level event channel delivery. + 8.31 KVM_CAP_PPC_MULTITCE ------------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6e61e11e750f..623fb7c4992c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -610,6 +610,7 @@ struct kvm_vcpu_xen { u64 last_steal; u64 runstate_entry_time; u64 runstate_times[4]; + unsigned long evtchn_pending_sel; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 39ad02d6dc63..6e0dab04320e 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -24,6 +24,7 @@ #include "hyperv.h" #include "x86.h" +#include "xen.h" static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -175,6 +176,13 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, return r; break; +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + if (!level) + return -1; + + return kvm_xen_set_evtchn_fast(e, kvm); +#endif default: break; } @@ -310,6 +318,10 @@ int kvm_set_routing_entry(struct kvm *kvm, e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + return kvm_xen_setup_evtchn(kvm, e, ue); +#endif default: return -EINVAL; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 42bde45a1bc2..3050601d5d73 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4188,7 +4188,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_SHARED_INFO; + KVM_XEN_HVM_CONFIG_SHARED_INFO | + KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE; break; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index da4bf2c6407f..ceddabd1f5c6 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "trace.h" @@ -195,6 +196,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { + unsigned long evtchn_pending_sel = READ_ONCE(v->arch.xen.evtchn_pending_sel); + bool atomic = in_atomic() || !task_is_running(current); int err; u8 rc = 0; @@ -204,6 +207,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) */ struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache; struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool ghc_valid = slots->generation == ghc->generation && + !kvm_is_error_hva(ghc->hva) && ghc->memslot; + unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending); /* No need for compat handling here */ @@ -219,8 +225,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) * cache in kvm_read_guest_offset_cached(), but just uses * __get_user() instead. And falls back to the slow path. */ - if (likely(slots->generation == ghc->generation && - !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { + if (!evtchn_pending_sel && ghc_valid) { /* Fast path */ pagefault_disable(); err = __get_user(rc, (u8 __user *)ghc->hva + offset); @@ -239,11 +244,82 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) * and we'll end up getting called again from a context where we *can* * fault in the page and wait for it. */ - if (in_atomic() || !task_is_running(current)) + if (atomic) return 1; - kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, - sizeof(rc)); + if (!ghc_valid) { + err = kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len); + if (err || !ghc->memslot) { + /* + * If this failed, userspace has screwed up the + * vcpu_info mapping. No interrupts for you. + */ + return 0; + } + } + + /* + * Now we have a valid (protected by srcu) userspace HVA in + * ghc->hva which points to the struct vcpu_info. If there + * are any bits in the in-kernel evtchn_pending_sel then + * we need to write those to the guest vcpu_info and set + * its evtchn_upcall_pending flag. If there aren't any bits + * to add, we only want to *check* evtchn_upcall_pending. + */ + if (evtchn_pending_sel) { + bool long_mode = v->kvm->arch.xen.long_mode; + + if (!user_access_begin((void __user *)ghc->hva, sizeof(struct vcpu_info))) + return 0; + + if (IS_ENABLED(CONFIG_64BIT) && long_mode) { + struct vcpu_info __user *vi = (void __user *)ghc->hva; + + /* Attempt to set the evtchn_pending_sel bits in the + * guest, and if that succeeds then clear the same + * bits in the in-kernel version. */ + asm volatile("1:\t" LOCK_PREFIX "orq %0, %1\n" + "\tnotq %0\n" + "\t" LOCK_PREFIX "andq %0, %2\n" + "2:\n" + "\t.section .fixup,\"ax\"\n" + "3:\tjmp\t2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (evtchn_pending_sel), + "+m" (vi->evtchn_pending_sel), + "+m" (v->arch.xen.evtchn_pending_sel) + : "0" (evtchn_pending_sel)); + } else { + struct compat_vcpu_info __user *vi = (void __user *)ghc->hva; + u32 evtchn_pending_sel32 = evtchn_pending_sel; + + /* Attempt to set the evtchn_pending_sel bits in the + * guest, and if that succeeds then clear the same + * bits in the in-kernel version. */ + asm volatile("1:\t" LOCK_PREFIX "orl %0, %1\n" + "\tnotl %0\n" + "\t" LOCK_PREFIX "andl %0, %2\n" + "2:\n" + "\t.section .fixup,\"ax\"\n" + "3:\tjmp\t2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (evtchn_pending_sel32), + "+m" (vi->evtchn_pending_sel), + "+m" (v->arch.xen.evtchn_pending_sel) + : "0" (evtchn_pending_sel32)); + } + rc = 1; + unsafe_put_user(rc, (u8 __user *)ghc->hva + offset, err); + + err: + user_access_end(); + + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + } else { + __get_user(rc, (u8 __user *)ghc->hva + offset); + } return rc; } @@ -740,3 +816,179 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } + +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + +/* + * This follows the kvm_set_irq() API, so it returns: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm) +{ + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + struct kvm_vcpu *vcpu; + unsigned long *pending_bits, *mask_bits; + unsigned long flags; + int port_word_bit; + bool kick_vcpu = false; + int idx; + int rc; + + vcpu = kvm_get_vcpu_by_id(kvm, e->xen_evtchn.vcpu); + if (!vcpu) + return -1; + + if (!vcpu->arch.xen.vcpu_info_set) + return -1; + + if (e->xen_evtchn.port >= max_evtchn_port(kvm)) + return -1; + + rc = -EWOULDBLOCK; + read_lock_irqsave(&gpc->lock, flags); + + idx = srcu_read_lock(&kvm->srcu); + if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, PAGE_SIZE)) + goto out_rcu; + + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { + struct shared_info *shinfo = gpc->khva; + pending_bits = (unsigned long *)&shinfo->evtchn_pending; + mask_bits = (unsigned long *)&shinfo->evtchn_mask; + port_word_bit = e->xen_evtchn.port / 64; + } else { + struct compat_shared_info *shinfo = gpc->khva; + pending_bits = (unsigned long *)&shinfo->evtchn_pending; + mask_bits = (unsigned long *)&shinfo->evtchn_mask; + port_word_bit = e->xen_evtchn.port / 32; + } + + /* + * If this port wasn't already set, and if it isn't masked, then + * we try to set the corresponding bit in the in-kernel shadow of + * evtchn_pending_sel for the target vCPU. And if *that* wasn't + * already set, then we kick the vCPU in question to write to the + * *real* evtchn_pending_sel in its own guest vcpu_info struct. + */ + if (test_and_set_bit(e->xen_evtchn.port, pending_bits)) { + rc = 0; /* It was already raised */ + } else if (test_bit(e->xen_evtchn.port, mask_bits)) { + rc = -1; /* Masked */ + } else { + rc = 1; /* Delivered. But was the vCPU waking already? */ + if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel)) + kick_vcpu = true; + } + + out_rcu: + srcu_read_unlock(&kvm->srcu, idx); + read_unlock_irqrestore(&gpc->lock, flags); + + if (kick_vcpu) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } + + return rc; +} + +/* This is the version called from kvm_set_irq() as the .set function */ +static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + bool mm_borrowed = false; + int rc; + + if (!level) + return -1; + + rc = kvm_xen_set_evtchn_fast(e, kvm); + if (rc != -EWOULDBLOCK) + return rc; + + if (current->mm != kvm->mm) { + /* + * If not on a thread which already belongs to this KVM, + * we'd better be in the irqfd workqueue. + */ + if (WARN_ON_ONCE(current->mm)) + return -EINVAL; + + kthread_use_mm(kvm->mm); + mm_borrowed = true; + } + + /* + * For the irqfd workqueue, using the main kvm->lock mutex is + * fine since this function is invoked from kvm_set_irq() with + * no other lock held, no srcu. In future if it will be called + * directly from a vCPU thread (e.g. on hypercall for an IPI) + * then it may need to switch to using a leaf-node mutex for + * serializing the shared_info mapping. + */ + mutex_lock(&kvm->lock); + + /* + * It is theoretically possible for the page to be unmapped + * and the MMU notifier to invalidate the shared_info before + * we even get to use it. In that case, this looks like an + * infinite loop. It was tempting to do it via the userspace + * HVA instead... but that just *hides* the fact that it's + * an infinite loop, because if a fault occurs and it waits + * for the page to come back, it can *still* immediately + * fault and have to wait again, repeatedly. + * + * Conversely, the page could also have been reinstated by + * another thread before we even obtain the mutex above, so + * check again *first* before remapping it. + */ + do { + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + int idx; + + rc = kvm_xen_set_evtchn_fast(e, kvm); + if (rc != -EWOULDBLOCK) + break; + + idx = srcu_read_lock(&kvm->srcu); + rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, + PAGE_SIZE, false); + srcu_read_unlock(&kvm->srcu, idx); + } while(!rc); + + mutex_unlock(&kvm->lock); + + if (mm_borrowed) + kthread_unuse_mm(kvm->mm); + + return rc; +} + +int kvm_xen_setup_evtchn(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) + +{ + if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm)) + return -EINVAL; + + /* We only support 2 level event channels for now */ + if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) + return -EINVAL; + + e->xen_evtchn.port = ue->u.xen_evtchn.port; + e->xen_evtchn.vcpu = ue->u.xen_evtchn.vcpu; + e->xen_evtchn.priority = ue->u.xen_evtchn.priority; + e->set = evtchn_set_fn; + + return 0; +} diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index cc0cf5f37450..adbcc9ed59db 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -24,6 +24,12 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc); void kvm_xen_init_vm(struct kvm *kvm); void kvm_xen_destroy_vm(struct kvm *kvm); +int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm); +int kvm_xen_setup_evtchn(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue); + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -134,6 +140,9 @@ struct compat_shared_info { struct compat_arch_shared_info arch; }; +#define COMPAT_EVTCHN_2L_NR_CHANNELS (8 * \ + sizeof_field(struct compat_shared_info, \ + evtchn_pending)) struct compat_vcpu_runstate_info { int state; uint64_t state_entry_time; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9bbb1f1d9e48..3c47b146851a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -497,6 +497,12 @@ struct kvm_hv_sint { u32 sint; }; +struct kvm_xen_evtchn { + u32 port; + u32 vcpu; + u32 priority; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -517,6 +523,7 @@ struct kvm_kernel_irq_routing_entry { } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; + struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 469f05d69c8d..fbfd70d965c6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1163,11 +1163,20 @@ struct kvm_irq_routing_hv_sint { __u32 sint; }; +struct kvm_irq_routing_xen_evtchn { + __u32 port; + __u32 vcpu; + __u32 priority; +}; + +#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1)) + /* gsi routing entry types */ #define KVM_IRQ_ROUTING_IRQCHIP 1 #define KVM_IRQ_ROUTING_MSI 2 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 #define KVM_IRQ_ROUTING_HV_SINT 4 +#define KVM_IRQ_ROUTING_XEN_EVTCHN 5 struct kvm_irq_routing_entry { __u32 gsi; @@ -1179,6 +1188,7 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing_msi msi; struct kvm_irq_routing_s390_adapter adapter; struct kvm_irq_routing_hv_sint hv_sint; + struct kvm_irq_routing_xen_evtchn xen_evtchn; __u32 pad[8]; } u; }; @@ -1209,6 +1219,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) struct kvm_xen_hvm_config { __u32 flags; diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index a0699f00b3d6..478e0ae8b93e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,6 +14,9 @@ #include #include #include +#include + +#include #define VCPU_ID 5 @@ -22,10 +25,15 @@ #define SHINFO_REGION_SLOT 10 #define PAGE_SIZE 4096 +#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) +#define DUMMY_REGION_SLOT 11 + +#define SHINFO_ADDR (SHINFO_REGION_GPA) #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) #define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) +#define SHINFO_VADDR (SHINFO_REGION_GVA) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) #define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) @@ -73,15 +81,37 @@ struct vcpu_info { struct pvclock_vcpu_time_info time; }; /* 64 bytes (x86) */ +struct shared_info { + struct vcpu_info vcpu_info[32]; + unsigned long evtchn_pending[64]; + unsigned long evtchn_mask[64]; + struct pvclock_wall_clock wc; + uint32_t wc_sec_hi; + /* arch_shared_info here */ +}; + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static const char *runstate_names[] = { + "running", + "runnable", + "blocked", + "offline" +}; + +struct { + struct kvm_irq_routing info; + struct kvm_irq_routing_entry entries[2]; +} irq_routes; + static void evtchn_handler(struct ex_regs *regs) { struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; vi->evtchn_upcall_pending = 0; + vi->evtchn_pending_sel = 0; GUEST_SYNC(0x20); } @@ -127,7 +157,25 @@ static void guest_code(void) GUEST_SYNC(6); GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); - GUEST_DONE(); + /* Attempt to deliver a *masked* interrupt */ + GUEST_SYNC(7); + + /* Wait until we see the bit set */ + struct shared_info *si = (void *)SHINFO_VADDR; + while (!si->evtchn_pending[0]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Now deliver an *unmasked* interrupt */ + GUEST_SYNC(8); + + while (!si->evtchn_pending[1]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Change memslots and deliver an interrupt */ + GUEST_SYNC(9); + + for (;;) + __asm__ __volatile__ ("rep nop" : : : "memory"); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -144,9 +192,18 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) return 0; } +static void handle_alrm(int sig) +{ + TEST_FAIL("IRQ delivery timed out"); +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + bool verbose; + + verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || + !strncmp(argv[1], "--verbose", 10)); int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { @@ -155,6 +212,7 @@ int main(int argc, char *argv[]) } bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); clock_gettime(CLOCK_REALTIME, &min_ts); @@ -166,6 +224,11 @@ int main(int argc, char *argv[]) SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2); + struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR); + + int zero_fd = open("/dev/zero", O_RDONLY); + TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero"); + struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, .msr = XEN_HYPERCALL_MSR, @@ -184,6 +247,16 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); + /* + * Test what happens when the HVA of the shinfo page is remapped after + * the kernel has a reference to it. But make sure we copy the clock + * info over since that's only set at setup time, and we test it later. + */ + struct pvclock_wall_clock wc_copy = shinfo->wc; + void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0); + TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info"); + shinfo->wc = wc_copy; + struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, .u.gpa = VCPU_INFO_ADDR, @@ -214,6 +287,49 @@ int main(int argc, char *argv[]) vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); } + int irq_fd[2] = { -1, -1 }; + + if (do_eventfd_tests) { + irq_fd[0] = eventfd(0, 0); + irq_fd[1] = eventfd(0, 0); + + /* Unexpected, but not a KVM failure */ + if (irq_fd[0] == -1 || irq_fd[1] == -1) + do_eventfd_tests = false; + } + + if (do_eventfd_tests) { + irq_routes.info.nr = 2; + + irq_routes.entries[0].gsi = 32; + irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[0].u.xen_evtchn.port = 15; + irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + irq_routes.entries[1].gsi = 33; + irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[1].u.xen_evtchn.port = 66; + irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes); + + struct kvm_irqfd ifd = { }; + + ifd.fd = irq_fd[0]; + ifd.gsi = 32; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + ifd.fd = irq_fd[1]; + ifd.gsi = 33; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + struct sigaction sa = { }; + sa.sa_handler = handle_alrm; + sigaction(SIGALRM, &sa, NULL); + } + struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); vinfo->evtchn_upcall_pending = 0; @@ -248,6 +364,8 @@ int main(int argc, char *argv[]) switch (uc.args[1]) { case 0: + if (verbose) + printf("Delivering evtchn upcall\n"); evtchn_irq_expected = true; vinfo->evtchn_upcall_pending = 1; break; @@ -256,11 +374,16 @@ int main(int argc, char *argv[]) TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); if (!do_runstate_tests) goto done; + if (verbose) + printf("Testing runstate %s\n", runstate_names[uc.args[1]]); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 4: + if (verbose) + printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = (uint64_t)-1; @@ -274,6 +397,8 @@ int main(int argc, char *argv[]) break; case 5: + if (verbose) + printf("Testing RUNSTATE_DATA\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = RUNSTATE_running; @@ -282,16 +407,54 @@ int main(int argc, char *argv[]) rst.u.runstate.time_offline = 0x5a; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 6: + if (verbose) + printf("Testing steal time\n"); /* Yield until scheduler delay exceeds target */ rundelay = get_run_delay() + MIN_STEAL_TIME; do { sched_yield(); } while (get_run_delay() < rundelay); break; + + case 7: + if (!do_eventfd_tests) + goto done; + if (verbose) + printf("Testing masked event channel\n"); + shinfo->evtchn_mask[0] = 0x8000; + eventfd_write(irq_fd[0], 1UL); + alarm(1); + break; + + case 8: + if (verbose) + printf("Testing unmasked event channel\n"); + /* Unmask that, but deliver the other one */ + shinfo->evtchn_pending[0] = 0; + shinfo->evtchn_mask[0] = 0; + eventfd_write(irq_fd[1], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + + case 9: + if (verbose) + printf("Testing event channel after memslot change\n"); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0); + eventfd_write(irq_fd[0], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + case 0x20: TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); evtchn_irq_expected = false; + if (shinfo->evtchn_pending[1] && + shinfo->evtchn_pending[0]) + goto done; break; } break; @@ -318,6 +481,16 @@ int main(int argc, char *argv[]) ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); ti2 = addr_gpa2hva(vm, PVTIME_ADDR); + if (verbose) { + printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec); + printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul, + ti->tsc_shift, ti->flags); + printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul, + ti2->tsc_shift, ti2->flags); + } + vm_ts.tv_sec = wc->sec; vm_ts.tv_nsec = wc->nsec; TEST_ASSERT(wc->version && !(wc->version & 1), @@ -341,6 +514,15 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); + if (verbose) { + printf("Runstate: %s(%d), entry %" PRIu64 " ns\n", + rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown", + rs->state, rs->state_entry_time); + for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) { + printf("State %s: %" PRIu64 " ns\n", + runstate_names[i], rs->time[i]); + } + } TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch"); TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time, "State entry time mismatch"); -- cgit v1.2.3 From 50a483405c420f5f35b8dbb71425459835ae44eb Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 6 Dec 2021 11:35:06 +0900 Subject: kbuild: move headers_check.pl to usr/include/ This script is only used by usr/include/Makefile. Make it local to the directory. Update the comment in include/uapi/linux/soundcard.h because 'make headers_check' is no longer functional. Signed-off-by: Masahiro Yamada --- include/uapi/linux/soundcard.h | 2 +- scripts/headers_check.pl | 171 ----------------------------------------- usr/include/Makefile | 6 +- usr/include/headers_check.pl | 171 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 176 insertions(+), 174 deletions(-) delete mode 100755 scripts/headers_check.pl create mode 100755 usr/include/headers_check.pl (limited to 'include/uapi') diff --git a/include/uapi/linux/soundcard.h b/include/uapi/linux/soundcard.h index f3b21f989872..ac1318793a86 100644 --- a/include/uapi/linux/soundcard.h +++ b/include/uapi/linux/soundcard.h @@ -1051,7 +1051,7 @@ typedef struct mixer_vol_table { * the GPL version of OSS-4.x and build against that version * of the header. * - * We redefine the extern keyword so that make headers_check + * We redefine the extern keyword so that usr/include/headers_check.pl * does not complain about SEQ_USE_EXTBUF. */ #define SEQ_DECLAREBUF() SEQ_USE_EXTBUF() diff --git a/scripts/headers_check.pl b/scripts/headers_check.pl deleted file mode 100755 index b6aec5e4365f..000000000000 --- a/scripts/headers_check.pl +++ /dev/null @@ -1,171 +0,0 @@ -#!/usr/bin/env perl -# SPDX-License-Identifier: GPL-2.0 -# -# headers_check.pl execute a number of trivial consistency checks -# -# Usage: headers_check.pl dir arch [files...] -# dir: dir to look for included files -# arch: architecture -# files: list of files to check -# -# The script reads the supplied files line by line and: -# -# 1) for each include statement it checks if the -# included file actually exists. -# Only include files located in asm* and linux* are checked. -# The rest are assumed to be system include files. -# -# 2) It is checked that prototypes does not use "extern" -# -# 3) Check for leaked CONFIG_ symbols - -use warnings; -use strict; -use File::Basename; - -my ($dir, $arch, @files) = @ARGV; - -my $ret = 0; -my $line; -my $lineno = 0; -my $filename; - -foreach my $file (@files) { - $filename = $file; - - open(my $fh, '<', $filename) - or die "$filename: $!\n"; - $lineno = 0; - while ($line = <$fh>) { - $lineno++; - &check_include(); - &check_asm_types(); - &check_sizetypes(); - &check_declarations(); - # Dropped for now. Too much noise &check_config(); - } - close $fh; -} -exit $ret; - -sub check_include -{ - if ($line =~ m/^\s*#\s*include\s+<((asm|linux).*)>/) { - my $inc = $1; - my $found; - $found = stat($dir . "/" . $inc); - if (!$found) { - $inc =~ s#asm/#asm-$arch/#; - $found = stat($dir . "/" . $inc); - } - if (!$found) { - printf STDERR "$filename:$lineno: included file '$inc' is not exported\n"; - $ret = 1; - } - } -} - -sub check_declarations -{ - # soundcard.h is what it is - if ($line =~ m/^void seqbuf_dump\(void\);/) { - return; - } - # drm headers are being C++ friendly - if ($line =~ m/^extern "C"/) { - return; - } - if ($line =~ m/^(\s*extern|unsigned|char|short|int|long|void)\b/) { - printf STDERR "$filename:$lineno: " . - "userspace cannot reference function or " . - "variable defined in the kernel\n"; - } -} - -sub check_config -{ - if ($line =~ m/[^a-zA-Z0-9_]+CONFIG_([a-zA-Z0-9_]+)[^a-zA-Z0-9_]/) { - printf STDERR "$filename:$lineno: leaks CONFIG_$1 to userspace where it is not valid\n"; - } -} - -my $linux_asm_types; -sub check_asm_types -{ - if ($filename =~ /types.h|int-l64.h|int-ll64.h/o) { - return; - } - if ($lineno == 1) { - $linux_asm_types = 0; - } elsif ($linux_asm_types >= 1) { - return; - } - if ($line =~ m/^\s*#\s*include\s+/) { - $linux_asm_types = 1; - printf STDERR "$filename:$lineno: " . - "include of is preferred over \n" - # Warn until headers are all fixed - #$ret = 1; - } -} - -my $linux_types; -my %import_stack = (); -sub check_include_typesh -{ - my $path = $_[0]; - my $import_path; - - my $fh; - my @file_paths = ($path, $dir . "/" . $path, dirname($filename) . "/" . $path); - for my $possible ( @file_paths ) { - if (not $import_stack{$possible} and open($fh, '<', $possible)) { - $import_path = $possible; - $import_stack{$import_path} = 1; - last; - } - } - if (eof $fh) { - return; - } - - my $line; - while ($line = <$fh>) { - if ($line =~ m/^\s*#\s*include\s+/) { - $linux_types = 1; - last; - } - if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) { - check_include_typesh($included); - } - } - close $fh; - delete $import_stack{$import_path}; -} - -sub check_sizetypes -{ - if ($filename =~ /types.h|int-l64.h|int-ll64.h/o) { - return; - } - if ($lineno == 1) { - $linux_types = 0; - } elsif ($linux_types >= 1) { - return; - } - if ($line =~ m/^\s*#\s*include\s+/) { - $linux_types = 1; - return; - } - if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) { - check_include_typesh($included); - } - if ($line =~ m/__[us](8|16|32|64)\b/) { - printf STDERR "$filename:$lineno: " . - "found __[us]{8,16,32,64} type " . - "without #include \n"; - $linux_types = 2; - # Warn until headers are all fixed - #$ret = 1; - } -} diff --git a/usr/include/Makefile b/usr/include/Makefile index 1c2ae1368079..94403806ea56 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -99,10 +99,12 @@ quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ $(CC) $(c_flags) -S -o /dev/null -x c /dev/null \ $(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \ - $(PERL) $(srctree)/scripts/headers_check.pl $(obj) $(SRCARCH) $<; \ + $(PERL) $(srctree)/$(src)/headers_check.pl $(obj) $(SRCARCH) $<; \ touch $@ $(obj)/%.hdrtest: $(obj)/%.h FORCE $(call if_changed_dep,hdrtest) -clean-files += $(filter-out Makefile, $(notdir $(wildcard $(obj)/*))) +# Since GNU Make 4.3, $(patsubst $(obj)/%/,%,$(wildcard $(obj)/*/)) works. +# To support older Make versions, use a somewhat tedious way. +clean-files += $(filter-out Makefile headers_check.pl, $(notdir $(wildcard $(obj)/*))) diff --git a/usr/include/headers_check.pl b/usr/include/headers_check.pl new file mode 100755 index 000000000000..b6aec5e4365f --- /dev/null +++ b/usr/include/headers_check.pl @@ -0,0 +1,171 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +# +# headers_check.pl execute a number of trivial consistency checks +# +# Usage: headers_check.pl dir arch [files...] +# dir: dir to look for included files +# arch: architecture +# files: list of files to check +# +# The script reads the supplied files line by line and: +# +# 1) for each include statement it checks if the +# included file actually exists. +# Only include files located in asm* and linux* are checked. +# The rest are assumed to be system include files. +# +# 2) It is checked that prototypes does not use "extern" +# +# 3) Check for leaked CONFIG_ symbols + +use warnings; +use strict; +use File::Basename; + +my ($dir, $arch, @files) = @ARGV; + +my $ret = 0; +my $line; +my $lineno = 0; +my $filename; + +foreach my $file (@files) { + $filename = $file; + + open(my $fh, '<', $filename) + or die "$filename: $!\n"; + $lineno = 0; + while ($line = <$fh>) { + $lineno++; + &check_include(); + &check_asm_types(); + &check_sizetypes(); + &check_declarations(); + # Dropped for now. Too much noise &check_config(); + } + close $fh; +} +exit $ret; + +sub check_include +{ + if ($line =~ m/^\s*#\s*include\s+<((asm|linux).*)>/) { + my $inc = $1; + my $found; + $found = stat($dir . "/" . $inc); + if (!$found) { + $inc =~ s#asm/#asm-$arch/#; + $found = stat($dir . "/" . $inc); + } + if (!$found) { + printf STDERR "$filename:$lineno: included file '$inc' is not exported\n"; + $ret = 1; + } + } +} + +sub check_declarations +{ + # soundcard.h is what it is + if ($line =~ m/^void seqbuf_dump\(void\);/) { + return; + } + # drm headers are being C++ friendly + if ($line =~ m/^extern "C"/) { + return; + } + if ($line =~ m/^(\s*extern|unsigned|char|short|int|long|void)\b/) { + printf STDERR "$filename:$lineno: " . + "userspace cannot reference function or " . + "variable defined in the kernel\n"; + } +} + +sub check_config +{ + if ($line =~ m/[^a-zA-Z0-9_]+CONFIG_([a-zA-Z0-9_]+)[^a-zA-Z0-9_]/) { + printf STDERR "$filename:$lineno: leaks CONFIG_$1 to userspace where it is not valid\n"; + } +} + +my $linux_asm_types; +sub check_asm_types +{ + if ($filename =~ /types.h|int-l64.h|int-ll64.h/o) { + return; + } + if ($lineno == 1) { + $linux_asm_types = 0; + } elsif ($linux_asm_types >= 1) { + return; + } + if ($line =~ m/^\s*#\s*include\s+/) { + $linux_asm_types = 1; + printf STDERR "$filename:$lineno: " . + "include of is preferred over \n" + # Warn until headers are all fixed + #$ret = 1; + } +} + +my $linux_types; +my %import_stack = (); +sub check_include_typesh +{ + my $path = $_[0]; + my $import_path; + + my $fh; + my @file_paths = ($path, $dir . "/" . $path, dirname($filename) . "/" . $path); + for my $possible ( @file_paths ) { + if (not $import_stack{$possible} and open($fh, '<', $possible)) { + $import_path = $possible; + $import_stack{$import_path} = 1; + last; + } + } + if (eof $fh) { + return; + } + + my $line; + while ($line = <$fh>) { + if ($line =~ m/^\s*#\s*include\s+/) { + $linux_types = 1; + last; + } + if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) { + check_include_typesh($included); + } + } + close $fh; + delete $import_stack{$import_path}; +} + +sub check_sizetypes +{ + if ($filename =~ /types.h|int-l64.h|int-ll64.h/o) { + return; + } + if ($lineno == 1) { + $linux_types = 0; + } elsif ($linux_types >= 1) { + return; + } + if ($line =~ m/^\s*#\s*include\s+/) { + $linux_types = 1; + return; + } + if (my $included = ($line =~ /^\s*#\s*include\s+[<"](\S+)[>"]/)[0]) { + check_include_typesh($included); + } + if ($line =~ m/__[us](8|16|32|64)\b/) { + printf STDERR "$filename:$lineno: " . + "found __[us]{8,16,32,64} type " . + "without #include \n"; + $linux_types = 2; + # Warn until headers are all fixed + #$ret = 1; + } +} -- cgit v1.2.3 From 1ed147e29e505de819aaa5b57919c25348f72e1f Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 25 Nov 2021 21:01:11 +0900 Subject: exfat: move super block magic number to magic.h Move exfat superblock magic number from local definition to magic.h. It is also needed by userspace programs that call fstatfs(). Acked-by: Christian Brauner Signed-off-by: Namjae Jeon --- fs/exfat/exfat_fs.h | 1 - fs/exfat/super.c | 1 + include/uapi/linux/magic.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index a8f5bc536dcf..9665fa0b2d56 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -10,7 +10,6 @@ #include #include -#define EXFAT_SUPER_MAGIC 0x2011BAB0UL #define EXFAT_ROOT_INO 1 #define EXFAT_CLUSTERS_UNTRACKED (~0u) diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 4b5d02b1df58..8c9fb7dcec16 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "exfat_raw.h" #include "exfat_fs.h" diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 35687dcb1a42..8ab81ea13424 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -43,6 +43,7 @@ #define MINIX3_SUPER_MAGIC 0x4d5a /* minix v3 fs, 60 char names */ #define MSDOS_SUPER_MAGIC 0x4d44 /* MD */ +#define EXFAT_SUPER_MAGIC 0x2011BAB0 #define NCP_SUPER_MAGIC 0x564c /* Guess, what 0x564c is :-) */ #define NFS_SUPER_MAGIC 0x6969 #define OCFS2_SUPER_MAGIC 0x7461636f -- cgit v1.2.3 From 9b7a4de9f126d8c8d59052088213990159417d5b Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 16 Dec 2021 10:45:03 +0100 Subject: drm/amdkfd: make SPDX License expression more sound Commit b5f57384805a ("drm/amdkfd: Add sysfs bitfields and enums to uAPI") adds include/uapi/linux/kfd_sysfs.h with the "GPL-2.0 OR MIT WITH Linux-syscall-note" SPDX-License expression. The command ./scripts/spdxcheck.py warns: include/uapi/linux/kfd_sysfs.h: 1:48 Exception not valid for license MIT: Linux-syscall-note For a uapi header, the file under GPLv2 License must be combined with the Linux-syscall-note, but combining the MIT License with the Linux-syscall-note makes no sense, as the note provides an exception for GPL-licensed code, not for permissively licensed code. So, reorganize the SPDX expression to only combine the note with the GPL License condition. This makes spdxcheck happy again. Fixes: b5f57384805a ("drm/amdkfd: Add sysfs bitfields and enums to uAPI") Signed-off-by: Lukas Bulwahn Reviewed-by: kstewart@linuxfoundation.org Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_sysfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h index e1fb78b4bf09..3e330f368917 100644 --- a/include/uapi/linux/kfd_sysfs.h +++ b/include/uapi/linux/kfd_sysfs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT WITH Linux-syscall-note */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ /* * Copyright 2021 Advanced Micro Devices, Inc. * -- cgit v1.2.3 From b1ae6dc41eaaa98bb75671e0f3665bfda248c3e7 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 5 Jan 2022 13:55:12 -0800 Subject: module: add in-kernel support for decompressing Current scheme of having userspace decompress kernel modules before loading them into the kernel runs afoul of LoadPin security policy, as it loses link between the source of kernel module on the disk and binary blob that is being loaded into the kernel. To solve this issue let's implement decompression in kernel, so that we can pass a file descriptor of compressed module file into finit_module() which will keep LoadPin happy. To let userspace know what compression/decompression scheme kernel supports it will create /sys/module/compression attribute. kmod can read this attribute and decide if it can pass compressed file to finit_module(). New MODULE_INIT_COMPRESSED_DATA flag indicates that the kernel should attempt to decompress the data read from file descriptor prior to trying load the module. To simplify things kernel will only implement single decompression method matching compression method selected when generating modules. This patch implements gzip and xz; more can be added later, Signed-off-by: Dmitry Torokhov Signed-off-by: Luis Chamberlain --- include/uapi/linux/module.h | 1 + init/Kconfig | 13 +++ kernel/Makefile | 1 + kernel/module-internal.h | 19 ++++ kernel/module.c | 35 ++++-- kernel/module_decompress.c | 271 ++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 329 insertions(+), 11 deletions(-) create mode 100644 kernel/module_decompress.c (limited to 'include/uapi') diff --git a/include/uapi/linux/module.h b/include/uapi/linux/module.h index 50d98ec5e866..03a33ffffcba 100644 --- a/include/uapi/linux/module.h +++ b/include/uapi/linux/module.h @@ -5,5 +5,6 @@ /* Flags for sys_finit_module: */ #define MODULE_INIT_IGNORE_MODVERSIONS 1 #define MODULE_INIT_IGNORE_VERMAGIC 2 +#define MODULE_INIT_COMPRESSED_FILE 4 #endif /* _UAPI_LINUX_MODULE_H */ diff --git a/init/Kconfig b/init/Kconfig index f2ae41e6717f..faf3a4b5cc8f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2274,6 +2274,19 @@ config MODULE_COMPRESS_ZSTD endchoice +config MODULE_DECOMPRESS + bool "Support in-kernel module decompression" + depends on MODULE_COMPRESS_GZIP || MODULE_COMPRESS_XZ + select ZLIB_INFLATE if MODULE_COMPRESS_GZIP + select XZ_DEC if MODULE_COMPRESS_XZ + help + + Support for decompressing kernel modules by the kernel itself + instead of relying on userspace to perform this task. Useful when + load pinning security policy is enabled. + + If unsure, say N. + config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS bool "Allow loading of modules with missing namespace imports" help diff --git a/kernel/Makefile b/kernel/Makefile index 186c49582f45..56f4ee97f328 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -67,6 +67,7 @@ obj-y += up.o endif obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_MODULE_DECOMPRESS) += module_decompress.o obj-$(CONFIG_MODULE_SIG) += module_signing.o obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o diff --git a/kernel/module-internal.h b/kernel/module-internal.h index 33783abc377b..8c381c99062f 100644 --- a/kernel/module-internal.h +++ b/kernel/module-internal.h @@ -22,6 +22,11 @@ struct load_info { bool sig_ok; #ifdef CONFIG_KALLSYMS unsigned long mod_kallsyms_init_off; +#endif +#ifdef CONFIG_MODULE_DECOMPRESS + struct page **pages; + unsigned int max_pages; + unsigned int used_pages; #endif struct { unsigned int sym, str, mod, vers, info, pcpu; @@ -29,3 +34,17 @@ struct load_info { }; extern int mod_verify_sig(const void *mod, struct load_info *info); + +#ifdef CONFIG_MODULE_DECOMPRESS +int module_decompress(struct load_info *info, const void *buf, size_t size); +void module_decompress_cleanup(struct load_info *info); +#else +static inline int module_decompress(struct load_info *info, + const void *buf, size_t size) +{ + return -EOPNOTSUPP; +} +static inline void module_decompress_cleanup(struct load_info *info) +{ +} +#endif diff --git a/kernel/module.c b/kernel/module.c index 320ec908045f..34fe2824eb56 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3173,9 +3173,12 @@ out: return err; } -static void free_copy(struct load_info *info) +static void free_copy(struct load_info *info, int flags) { - vfree(info->hdr); + if (flags & MODULE_INIT_COMPRESSED_FILE) + module_decompress_cleanup(info); + else + vfree(info->hdr); } static int rewrite_section_headers(struct load_info *info, int flags) @@ -4124,7 +4127,7 @@ static int load_module(struct load_info *info, const char __user *uargs, } /* Get rid of temporary copy. */ - free_copy(info); + free_copy(info, flags); /* Done! */ trace_module_load(mod); @@ -4173,7 +4176,7 @@ static int load_module(struct load_info *info, const char __user *uargs, module_deallocate(mod, info); free_copy: - free_copy(info); + free_copy(info, flags); return err; } @@ -4200,7 +4203,8 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; - void *hdr = NULL; + void *buf = NULL; + int len; int err; err = may_init_module(); @@ -4210,15 +4214,24 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC)) + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) return -EINVAL; - err = kernel_read_file_from_fd(fd, 0, &hdr, INT_MAX, NULL, + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); - if (err < 0) - return err; - info.hdr = hdr; - info.len = err; + if (len < 0) + return len; + + if (flags & MODULE_INIT_COMPRESSED_FILE) { + err = module_decompress(&info, buf, len); + vfree(buf); /* compressed data is no longer needed */ + if (err) + return err; + } else { + info.hdr = buf; + info.len = len; + } return load_module(&info, uargs, flags); } diff --git a/kernel/module_decompress.c b/kernel/module_decompress.c new file mode 100644 index 000000000000..aeefd95a3337 --- /dev/null +++ b/kernel/module_decompress.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2021 Google LLC. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "module-internal.h" + +static int module_extend_max_pages(struct load_info *info, unsigned int extent) +{ + struct page **new_pages; + + new_pages = kvmalloc_array(info->max_pages + extent, + sizeof(info->pages), GFP_KERNEL); + if (!new_pages) + return -ENOMEM; + + memcpy(new_pages, info->pages, info->max_pages * sizeof(info->pages)); + kvfree(info->pages); + info->pages = new_pages; + info->max_pages += extent; + + return 0; +} + +static struct page *module_get_next_page(struct load_info *info) +{ + struct page *page; + int error; + + if (info->max_pages == info->used_pages) { + error = module_extend_max_pages(info, info->used_pages); + if (error) + return ERR_PTR(error); + } + + page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); + if (!page) + return ERR_PTR(-ENOMEM); + + info->pages[info->used_pages++] = page; + return page; +} + +#ifdef CONFIG_MODULE_COMPRESS_GZIP +#include +#define MODULE_COMPRESSION gzip +#define MODULE_DECOMPRESS_FN module_gzip_decompress + +/* + * Calculate length of the header which consists of signature, header + * flags, time stamp and operating system ID (10 bytes total), plus + * an optional filename. + */ +static size_t module_gzip_header_len(const u8 *buf, size_t size) +{ + const u8 signature[] = { 0x1f, 0x8b, 0x08 }; + size_t len = 10; + + if (size < len || memcmp(buf, signature, sizeof(signature))) + return 0; + + if (buf[3] & 0x08) { + do { + /* + * If we can't find the end of the file name we must + * be dealing with a corrupted file. + */ + if (len == size) + return 0; + } while (buf[len++] != '\0'); + } + + return len; +} + +static ssize_t module_gzip_decompress(struct load_info *info, + const void *buf, size_t size) +{ + struct z_stream_s s = { 0 }; + size_t new_size = 0; + size_t gzip_hdr_len; + ssize_t retval; + int rc; + + gzip_hdr_len = module_gzip_header_len(buf, size); + if (!gzip_hdr_len) { + pr_err("not a gzip compressed module\n"); + return -EINVAL; + } + + s.next_in = buf + gzip_hdr_len; + s.avail_in = size - gzip_hdr_len; + + s.workspace = kmalloc(zlib_inflate_workspacesize(), GFP_KERNEL); + if (!s.workspace) + return -ENOMEM; + + rc = zlib_inflateInit2(&s, -MAX_WBITS); + if (rc != Z_OK) { + pr_err("failed to initialize decompresser: %d\n", rc); + retval = -EINVAL; + goto out; + } + + do { + struct page *page = module_get_next_page(info); + if (!page) { + retval = -ENOMEM; + goto out_inflate_end; + } + + s.next_out = kmap(page); + s.avail_out = PAGE_SIZE; + rc = zlib_inflate(&s, 0); + kunmap(page); + + new_size += PAGE_SIZE - s.avail_out; + } while (rc == Z_OK); + + if (rc != Z_STREAM_END) { + pr_err("decompression failed with status %d\n", rc); + retval = -EINVAL; + goto out_inflate_end; + } + + retval = new_size; + +out_inflate_end: + zlib_inflateEnd(&s); +out: + kfree(s.workspace); + return retval; +} +#elif CONFIG_MODULE_COMPRESS_XZ +#include +#define MODULE_COMPRESSION xz +#define MODULE_DECOMPRESS_FN module_xz_decompress + +static ssize_t module_xz_decompress(struct load_info *info, + const void *buf, size_t size) +{ + static const u8 signature[] = { 0xfd, '7', 'z', 'X', 'Z', 0 }; + struct xz_dec *xz_dec; + struct xz_buf xz_buf; + enum xz_ret xz_ret; + size_t new_size = 0; + ssize_t retval; + + if (size < sizeof(signature) || + memcmp(buf, signature, sizeof(signature))) { + pr_err("not an xz compressed module\n"); + return -EINVAL; + } + + xz_dec = xz_dec_init(XZ_DYNALLOC, (u32)-1); + if (!xz_dec) + return -ENOMEM; + + xz_buf.in_size = size; + xz_buf.in = buf; + xz_buf.in_pos = 0; + + do { + struct page *page = module_get_next_page(info); + if (!page) { + retval = -ENOMEM; + goto out; + } + + xz_buf.out = kmap(page); + xz_buf.out_pos = 0; + xz_buf.out_size = PAGE_SIZE; + xz_ret = xz_dec_run(xz_dec, &xz_buf); + kunmap(page); + + new_size += xz_buf.out_pos; + } while (xz_buf.out_pos == PAGE_SIZE && xz_ret == XZ_OK); + + if (xz_ret != XZ_STREAM_END) { + pr_err("decompression failed with status %d\n", xz_ret); + retval = -EINVAL; + goto out; + } + + retval = new_size; + + out: + xz_dec_end(xz_dec); + return retval; +} +#else +#error "Unexpected configuration for CONFIG_MODULE_DECOMPRESS" +#endif + +int module_decompress(struct load_info *info, const void *buf, size_t size) +{ + unsigned int n_pages; + ssize_t data_size; + int error; + + /* + * Start with number of pages twice as big as needed for + * compressed data. + */ + n_pages = DIV_ROUND_UP(size, PAGE_SIZE) * 2; + error = module_extend_max_pages(info, n_pages); + + data_size = MODULE_DECOMPRESS_FN(info, buf, size); + if (data_size < 0) { + error = data_size; + goto err; + } + + info->hdr = vmap(info->pages, info->used_pages, VM_MAP, PAGE_KERNEL); + if (!info->hdr) { + error = -ENOMEM; + goto err; + } + + info->len = data_size; + return 0; + +err: + module_decompress_cleanup(info); + return error; +} + +void module_decompress_cleanup(struct load_info *info) +{ + int i; + + if (info->hdr) + vunmap(info->hdr); + + for (i = 0; i < info->used_pages; i++) + __free_page(info->pages[i]); + + kvfree(info->pages); + + info->pages = NULL; + info->max_pages = info->used_pages = 0; +} + +static ssize_t compression_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", __stringify(MODULE_COMPRESSION)); +} +static struct kobj_attribute module_compression_attr = __ATTR_RO(compression); + +static int __init module_decompress_sysfs_init(void) +{ + int error; + + error = sysfs_create_file(&module_kset->kobj, + &module_compression_attr.attr); + if (error) + pr_warn("Failed to create 'compression' attribute"); + + return 0; +} +late_initcall(module_decompress_sysfs_init); -- cgit v1.2.3 From a0b3a15eab6bc2e90008460b646d53e7d9dcdbbb Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 10 Jan 2022 18:28:33 -0500 Subject: ceph: move CEPH_SUPER_MAGIC definition to magic.h The uapi headers are missing the ceph definition. Move it there so userland apps can ID cephfs. Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/super.c | 2 ++ fs/ceph/super.h | 3 --- include/uapi/linux/magic.h | 1 + 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/fs/ceph/super.c b/fs/ceph/super.c index eb255d24e321..dbcf9b743c88 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -27,6 +27,8 @@ #include #include +#include + static DEFINE_SPINLOCK(ceph_fsc_lock); static LIST_HEAD(ceph_fsc_list); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 0d489a973d5e..dc9fe7ed3fa8 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -25,9 +25,6 @@ #include #endif -/* f_type in struct statfs */ -#define CEPH_SUPER_MAGIC 0x00c36400 - /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 35687dcb1a42..53a3c20394cf 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -6,6 +6,7 @@ #define AFFS_SUPER_MAGIC 0xadff #define AFS_SUPER_MAGIC 0x5346414F #define AUTOFS_SUPER_MAGIC 0x0187 +#define CEPH_SUPER_MAGIC 0x00c36400 #define CODA_SUPER_MAGIC 0x73757245 #define CRAMFS_MAGIC 0x28cd3d45 /* some random number */ #define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */ -- cgit v1.2.3 From be50b2065dfa3d88428fdfdc340d154d96bf6848 Mon Sep 17 00:00:00 2001 From: Guang Zeng Date: Wed, 5 Jan 2022 04:35:29 -0800 Subject: kvm: x86: Add support for getting/setting expanded xstate buffer With KVM_CAP_XSAVE, userspace uses a hardcoded 4KB buffer to get/set xstate data from/to KVM. This doesn't work when dynamic xfeatures (e.g. AMX) are exposed to the guest as they require a larger buffer size. Introduce a new capability (KVM_CAP_XSAVE2). Userspace VMM gets the required xstate buffer size via KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2). KVM_SET_XSAVE is extended to work with both legacy and new capabilities by doing properly-sized memdup_user() based on the guest fpu container. KVM_GET_XSAVE is kept for backward-compatible reason. Instead, KVM_GET_XSAVE2 is introduced under KVM_CAP_XSAVE2 as the preferred interface for getting xstate buffer (4KB or larger size) from KVM (Link: https://lkml.org/lkml/2021/12/15/510) Also, update the api doc with the new KVM_GET_XSAVE2 ioctl. Signed-off-by: Guang Zeng Signed-off-by: Wei Wang Signed-off-by: Jing Liu Signed-off-by: Kevin Tian Signed-off-by: Yang Zhong Message-Id: <20220105123532.12586-19-yang.zhong@intel.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 42 ++++++++++++++++++++++++++++++++++++-- arch/x86/include/uapi/asm/kvm.h | 16 ++++++++++++++- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/cpuid.h | 2 ++ arch/x86/kvm/x86.c | 45 ++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/kvm.h | 4 ++++ 6 files changed, 106 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index f4ea5e41a4d0..d3791a14eb9a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1569,6 +1569,7 @@ otherwise it will return EBUSY error. struct kvm_xsave { __u32 region[1024]; + __u32 extra[0]; }; This ioctl would copy current vcpu's xsave struct to the userspace. @@ -1577,7 +1578,7 @@ This ioctl would copy current vcpu's xsave struct to the userspace. 4.43 KVM_SET_XSAVE ------------------ -:Capability: KVM_CAP_XSAVE +:Capability: KVM_CAP_XSAVE and KVM_CAP_XSAVE2 :Architectures: x86 :Type: vcpu ioctl :Parameters: struct kvm_xsave (in) @@ -1588,9 +1589,18 @@ This ioctl would copy current vcpu's xsave struct to the userspace. struct kvm_xsave { __u32 region[1024]; + __u32 extra[0]; }; -This ioctl would copy userspace's xsave struct to the kernel. +This ioctl would copy userspace's xsave struct to the kernel. It copies +as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2), +when invoked on the vm file descriptor. The size value returned by +KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096. +Currently, it is only greater than 4096 if a dynamic feature has been +enabled with ``arch_prctl()``, but this may change in the future. + +The offsets of the state save areas in struct kvm_xsave follow the +contents of CPUID leaf 0xD on the host. 4.44 KVM_GET_XCRS @@ -5535,6 +5545,34 @@ the trailing ``'\0'``, is indicated by ``name_size`` in the header. The Stats Data block contains an array of 64-bit values in the same order as the descriptors in Descriptors block. +4.42 KVM_GET_XSAVE2 +------------------ + +:Capability: KVM_CAP_XSAVE2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xsave (out) +:Returns: 0 on success, -1 on error + + +:: + + struct kvm_xsave { + __u32 region[1024]; + __u32 extra[0]; + }; + +This ioctl would copy current vcpu's xsave struct to the userspace. It +copies as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) +when invoked on the vm file descriptor. The size value returned by +KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096. +Currently, it is only greater than 4096 if a dynamic feature has been +enabled with ``arch_prctl()``, but this may change in the future. + +The offsets of the state save areas in struct kvm_xsave follow the contents +of CPUID leaf 0xD on the host. + + 5. The kvm_run structure ======================== diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5a776a08f78c..2da3316bb559 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -373,9 +373,23 @@ struct kvm_debugregs { __u64 reserved[9]; }; -/* for KVM_CAP_XSAVE */ +/* for KVM_CAP_XSAVE and KVM_CAP_XSAVE2 */ struct kvm_xsave { + /* + * KVM_GET_XSAVE2 and KVM_SET_XSAVE write and read as many bytes + * as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) + * respectively, when invoked on the vm file descriptor. + * + * The size value returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) + * will always be at least 4096. Currently, it is only greater + * than 4096 if a dynamic feature has been enabled with + * ``arch_prctl()``, but this may change in the future. + * + * The offsets of the state save areas in struct kvm_xsave follow + * the contents of CPUID leaf 0xD on the host. + */ __u32 region[1024]; + __u32 extra[0]; }; #define KVM_MAX_XCRS 16 diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ba4c3d5d2386..c55e57b30e81 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -32,7 +32,7 @@ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); -static u32 xstate_required_size(u64 xstate_bv, bool compacted) +u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c99edfff7f82..8a770b481d9d 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -30,6 +30,8 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); +u32 xstate_required_size(u64 xstate_bv, bool compacted); + int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 993eee6451ea..bde18ca657db 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4314,6 +4314,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) else r = 0; break; + case KVM_CAP_XSAVE2: { + u64 guest_perm = xstate_get_guest_group_perm(); + + r = xstate_required_size(supported_xcr0 & guest_perm, false); + if (r < sizeof(struct kvm_xsave)) + r = sizeof(struct kvm_xsave); + break; + } default: break; } @@ -4917,6 +4925,16 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, vcpu->arch.pkru); } +static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) +{ + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) + return; + + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, + state, size, vcpu->arch.pkru); +} + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { @@ -5370,6 +5388,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XSAVE: { + r = -EINVAL; + if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave)) + break; + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xsave) @@ -5384,7 +5406,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XSAVE: { - u.xsave = memdup_user(argp, sizeof(*u.xsave)); + int size = vcpu->arch.guest_fpu.uabi_size; + + u.xsave = memdup_user(argp, size); if (IS_ERR(u.xsave)) { r = PTR_ERR(u.xsave); goto out_nofree; @@ -5393,6 +5417,25 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; } + + case KVM_GET_XSAVE2: { + int size = vcpu->arch.guest_fpu.uabi_size; + + u.xsave = kzalloc(size, GFP_KERNEL_ACCOUNT); + r = -ENOMEM; + if (!u.xsave) + break; + + kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + + r = -EFAULT; + if (copy_to_user(argp, u.xsave, size)) + break; + + r = 0; + break; + } + case KVM_GET_XCRS: { u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT); r = -ENOMEM; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index fbfd70d965c6..9563d294f181 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1132,6 +1132,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_MTE 205 #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #define KVM_CAP_VM_GPA_BITS 207 +#define KVM_CAP_XSAVE2 208 #ifdef KVM_CAP_IRQ_ROUTING @@ -1622,6 +1623,9 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) + struct kvm_s390_pv_sec_parm { __u64 origin; __u64 length; -- cgit v1.2.3 From 612f330ec56f12c0d099286c45f82d835845f136 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 5 Jan 2022 13:46:40 +0200 Subject: vdpa: Add support for returning device configuration information Add netlink attribute to store the negotiated features. This can be used by userspace to get the current state of the vdpa instance. Examples: $ vdpa dev config show vdpa-a vdpa-a: mac 00:00:00:00:88:88 link up link_announce false max_vq_pairs 16 mtu 1500 negotiated_features CSUM GUEST_CSUM MTU MAC HOST_TSO4 HOST_TSO6 STATUS \ CTRL_VQ MQ CTRL_MAC_ADDR VERSION_1 ACCESS_PLATFORM $ vdpa -j dev config show vdpa-a {"config":{"vdpa-a":{"mac":"00:00:00:00:88:88","link ":"up","link_announce":false, \ "max_vq_pairs":16,"mtu":1500,"negotiated_features":["CSUM","GUEST_CSUM","MTU","MAC", \ "HOST_TSO4","HOST_TSO6","STATUS","CTRL_VQ","MQ","CTRL_MAC_ADDR","VERSION_1", \ "ACCESS_PLATFORM"]}}} $ vdpa -jp dev config show vdpa-a { "config": { "vdpa-a": { "mac": "00:00:00:00:88:88", "link ": "up", "link_announce ": false, "max_vq_pairs": 16, "mtu": 1500, "negotiated_features": [ "CSUM","GUEST_CSUM","MTU","MAC","HOST_TSO4","HOST_TSO6","STATUS","CTRL_VQ","MQ", \ "CTRL_MAC_ADDR","VERSION_1","ACCESS_PLATFORM" ] } } } Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220105114646.577224-9-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa.c | 3 +++ include/uapi/linux/vdpa.h | 4 ++++ 2 files changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 96d31b80fdce..60cf821175fa 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -846,6 +846,9 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms return -EMSGSIZE; features = vdev->config->get_driver_features(vdev); + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features, + VDPA_ATTR_PAD)) + return -EMSGSIZE; return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index a252f06f9dfd..db3738ef3beb 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -23,6 +23,9 @@ enum vdpa_command { enum vdpa_attr { VDPA_ATTR_UNSPEC, + /* Pad attribute for 64b alignment */ + VDPA_ATTR_PAD = VDPA_ATTR_UNSPEC, + /* bus name (optional) + dev name together make the parent device handle */ VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */ VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ @@ -40,6 +43,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */ VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ + VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From cd2629f6df1cab5b3df34705ae7f3bde6147fce3 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 5 Jan 2022 13:46:42 +0200 Subject: vdpa: Support reporting max device capabilities Add max_supported_vqs and supported_features fields to struct vdpa_mgmt_dev. Upstream drivers need to feel these values according to the device capabilities. These values are reported back in a netlink message when showing management devices. Examples: $ auxiliary/mlx5_core.sf.1: supported_classes net max_supported_vqs 257 dev_features CSUM GUEST_CSUM MTU HOST_TSO4 HOST_TSO6 STATUS CTRL_VQ MQ \ CTRL_MAC_ADDR VERSION_1 ACCESS_PLATFORM $ vdpa -j mgmtdev show {"mgmtdev":{"auxiliary/mlx5_core.sf.1":{"supported_classes":["net"], \ "max_supported_vqs":257,"dev_features":["CSUM","GUEST_CSUM","MTU", \ "HOST_TSO4","HOST_TSO6","STATUS","CTRL_VQ","MQ","CTRL_MAC_ADDR", \ "VERSION_1","ACCESS_PLATFORM"]}}} $ vdpa -jp mgmtdev show { "mgmtdev": { "auxiliary/mlx5_core.sf.1": { "supported_classes": [ "net" ], "max_supported_vqs": 257, "dev_features": ["CSUM","GUEST_CSUM","MTU","HOST_TSO4", \ "HOST_TSO6","STATUS","CTRL_VQ","MQ", \ "CTRL_MAC_ADDR","VERSION_1","ACCESS_PLATFORM"] } } } Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220105114646.577224-11-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu --- drivers/vdpa/vdpa.c | 10 ++++++++++ include/linux/vdpa.h | 2 ++ include/uapi/linux/vdpa.h | 2 ++ 3 files changed, 14 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 60cf821175fa..34fa251db8cc 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -514,6 +514,16 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m err = -EMSGSIZE; goto msg_err; } + if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, + mdev->max_supported_vqs)) { + err = -EMSGSIZE; + goto msg_err; + } + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES, + mdev->supported_features, VDPA_ATTR_PAD)) { + err = -EMSGSIZE; + goto msg_err; + } genlmsg_end(msg, hdr); return 0; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 6d4d7e4fe208..a6047fd6cf12 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -460,6 +460,8 @@ struct vdpa_mgmt_dev { const struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; + u64 supported_features; + u32 max_supported_vqs; }; int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index db3738ef3beb..1061d8d2d09d 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -44,6 +44,8 @@ enum vdpa_attr { VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ + VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From 9a10064f5625d5572c3626c1516e0bebc6c9fe9b Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Fri, 14 Jan 2022 14:05:59 -0800 Subject: mm: add a field to store names for private anonymous memory In many userspace applications, and especially in VM based applications like Android uses heavily, there are multiple different allocators in use. At a minimum there is libc malloc and the stack, and in many cases there are libc malloc, the stack, direct syscalls to mmap anonymous memory, and multiple VM heaps (one for small objects, one for big objects, etc.). Each of these layers usually has its own tools to inspect its usage; malloc by compiling a debug version, the VM through heap inspection tools, and for direct syscalls there is usually no way to track them. On Android we heavily use a set of tools that use an extended version of the logic covered in Documentation/vm/pagemap.txt to walk all pages mapped in userspace and slice their usage by process, shared (COW) vs. unique mappings, backing, etc. This can account for real physical memory usage even in cases like fork without exec (which Android uses heavily to share as many private COW pages as possible between processes), Kernel SamePage Merging, and clean zero pages. It produces a measurement of the pages that only exist in that process (USS, for unique), and a measurement of the physical memory usage of that process with the cost of shared pages being evenly split between processes that share them (PSS). If all anonymous memory is indistinguishable then figuring out the real physical memory usage (PSS) of each heap requires either a pagemap walking tool that can understand the heap debugging of every layer, or for every layer's heap debugging tools to implement the pagemap walking logic, in which case it is hard to get a consistent view of memory across the whole system. Tracking the information in userspace leads to all sorts of problems. It either needs to be stored inside the process, which means every process has to have an API to export its current heap information upon request, or it has to be stored externally in a filesystem that somebody needs to clean up on crashes. It needs to be readable while the process is still running, so it has to have some sort of synchronization with every layer of userspace. Efficiently tracking the ranges requires reimplementing something like the kernel vma trees, and linking to it from every layer of userspace. It requires more memory, more syscalls, more runtime cost, and more complexity to separately track regions that the kernel is already tracking. This patch adds a field to /proc/pid/maps and /proc/pid/smaps to show a userspace-provided name for anonymous vmas. The names of named anonymous vmas are shown in /proc/pid/maps and /proc/pid/smaps as [anon:]. Userspace can set the name for a region of memory by calling prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name) Setting the name to NULL clears it. The name length limit is 80 bytes including NUL-terminator and is checked to contain only printable ascii characters (including space), except '[',']','\','$' and '`'. Ascii strings are being used to have a descriptive identifiers for vmas, which can be understood by the users reading /proc/pid/maps or /proc/pid/smaps. Names can be standardized for a given system and they can include some variable parts such as the name of the allocator or a library, tid of the thread using it, etc. The name is stored in a pointer in the shared union in vm_area_struct that points to a null terminated string. Anonymous vmas with the same name (equivalent strings) and are otherwise mergeable will be merged. The name pointers are not shared between vmas even if they contain the same name. The name pointer is stored in a union with fields that are only used on file-backed mappings, so it does not increase memory usage. CONFIG_ANON_VMA_NAME kernel configuration is introduced to enable this feature. It keeps the feature disabled by default to prevent any additional memory overhead and to avoid confusing procfs parsers on systems which are not ready to support named anonymous vmas. The patch is based on the original patch developed by Colin Cross, more specifically on its latest version [1] posted upstream by Sumit Semwal. It used a userspace pointer to store vma names. In that design, name pointers could be shared between vmas. However during the last upstreaming attempt, Kees Cook raised concerns [2] about this approach and suggested to copy the name into kernel memory space, perform validity checks [3] and store as a string referenced from vm_area_struct. One big concern is about fork() performance which would need to strdup anonymous vma names. Dave Hansen suggested experimenting with worst-case scenario of forking a process with 64k vmas having longest possible names [4]. I ran this experiment on an ARM64 Android device and recorded a worst-case regression of almost 40% when forking such a process. This regression is addressed in the followup patch which replaces the pointer to a name with a refcounted structure that allows sharing the name pointer between vmas of the same name. Instead of duplicating the string during fork() or when splitting a vma it increments the refcount. [1] https://lore.kernel.org/linux-mm/20200901161459.11772-4-sumit.semwal@linaro.org/ [2] https://lore.kernel.org/linux-mm/202009031031.D32EF57ED@keescook/ [3] https://lore.kernel.org/linux-mm/202009031022.3834F692@keescook/ [4] https://lore.kernel.org/linux-mm/5d0358ab-8c47-2f5f-8e43-23b89d6a8e95@intel.com/ Changes for prctl(2) manual page (in the options section): PR_SET_VMA Sets an attribute specified in arg2 for virtual memory areas starting from the address specified in arg3 and spanning the size specified in arg4. arg5 specifies the value of the attribute to be set. Note that assigning an attribute to a virtual memory area might prevent it from being merged with adjacent virtual memory areas due to the difference in that attribute's value. Currently, arg2 must be one of: PR_SET_VMA_ANON_NAME Set a name for anonymous virtual memory areas. arg5 should be a pointer to a null-terminated string containing the name. The name length including null byte cannot exceed 80 bytes. If arg5 is NULL, the name of the appropriate anonymous virtual memory areas will be reset. The name can contain only printable ascii characters (including space), except '[',']','\','$' and '`'. This feature is available only if the kernel is built with the CONFIG_ANON_VMA_NAME option enabled. [surenb@google.com: docs: proc.rst: /proc/PID/maps: fix malformed table] Link: https://lkml.kernel.org/r/20211123185928.2513763-1-surenb@google.com [surenb: rebased over v5.15-rc6, replaced userpointer with a kernel copy, added input sanitization and CONFIG_ANON_VMA_NAME config. The bulk of the work here was done by Colin Cross, therefore, with his permission, keeping him as the author] Link: https://lkml.kernel.org/r/20211019215511.3771969-2-surenb@google.com Signed-off-by: Colin Cross Signed-off-by: Suren Baghdasaryan Reviewed-by: Kees Cook Cc: Stephen Rothwell Cc: Al Viro Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: David Rientjes Cc: "Eric W. Biederman" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jan Glauber Cc: Johannes Weiner Cc: John Stultz Cc: Mel Gorman Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Rob Landley Cc: "Serge E. Hallyn" Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.rst | 6 +- fs/proc/task_mmu.c | 12 +++- fs/userfaultfd.c | 7 +- include/linux/mm.h | 13 +++- include/linux/mm_types.h | 64 ++++++++++++++++-- include/uapi/linux/prctl.h | 3 + kernel/fork.c | 2 + kernel/sys.c | 63 ++++++++++++++++++ mm/Kconfig | 14 ++++ mm/madvise.c | 129 +++++++++++++++++++++++++++++++++++-- mm/mempolicy.c | 3 +- mm/mlock.c | 2 +- mm/mmap.c | 38 ++++++----- mm/mprotect.c | 2 +- 14 files changed, 324 insertions(+), 34 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 8d7f141c6fc7..061744c436d9 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -426,12 +426,14 @@ with the memory region, as the case would be with BSS (uninitialized data). The "pathname" shows the name associated file for this mapping. If the mapping is not associated with a file: - ======= ==================================== + ============= ==================================== [heap] the heap of the program [stack] the stack of the main process [vdso] the "virtual dynamic shared object", the kernel system call handler - ======= ==================================== + [anon:] an anonymous mapping that has been + named by userspace + ============= ==================================== or if empty, the mapping is anonymous. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ad667dbc96f5..e6998652fd67 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -308,6 +308,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) name = arch_vma_name(vma); if (!name) { + const char *anon_name; + if (!mm) { name = "[vdso]"; goto done; @@ -319,8 +321,16 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) goto done; } - if (is_stack(vma)) + if (is_stack(vma)) { name = "[stack]"; + goto done; + } + + anon_name = vma_anon_name(vma); + if (anon_name) { + seq_pad(m, ' '); + seq_printf(m, "[anon:%s]", anon_name); + } } done: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 22bf14ab2d16..5b2af7b82776 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -877,7 +877,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, vma_anon_name(vma)); if (prev) vma = prev; else @@ -1436,7 +1436,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx })); + ((struct vm_userfaultfd_ctx){ ctx }), + vma_anon_name(vma)); if (prev) { vma = prev; goto next; @@ -1613,7 +1614,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, vma_anon_name(vma)); if (prev) { vma = prev; goto next; diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..7000442984b9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2658,7 +2658,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, const char *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); @@ -3391,5 +3391,16 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) return 0; } +#ifdef CONFIG_ANON_VMA_NAME +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name); +#else +static inline int +madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name) { + return 0; +} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c3a6e6209600..799e2ee626b2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -426,11 +426,19 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * containing the name given to the vma, or NULL if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* Serialized by mmap_sem. */ + char *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -875,4 +883,52 @@ typedef struct { unsigned long val; } swp_entry_t; +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling vma_anon_name() and while using + * the returned pointer. + */ +extern const char *vma_anon_name(struct vm_area_struct *vma); + +/* + * mmap_lock should be read-locked for orig_vma->vm_mm. + * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be + * isolated. + */ +extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma); + +/* + * mmap_lock should be write-locked or vma should have been isolated under + * write-locked mmap_lock protection. + */ +extern void free_vma_anon_name(struct vm_area_struct *vma); + +/* mmap_lock should be read-locked */ +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + const char *vma_name = vma_anon_name(vma); + + /* either both NULL, or pointers to same string */ + if (vma_name == name) + return true; + + return name && vma_name && !strcmp(name, vma_name); +} +#else /* CONFIG_ANON_VMA_NAME */ +static inline const char *vma_anon_name(struct vm_area_struct *vma) +{ + return NULL; +} +static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_vma_anon_name(struct vm_area_struct *vma) {} +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + return true; +} +#endif /* CONFIG_ANON_VMA_NAME */ + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index bb73e9a0b24f..e998764f0262 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,4 +272,7 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 3244cc56b697..4cf20b5f2da3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,12 +365,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; + dup_vma_anon_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { + free_vma_anon_name(vma); kmem_cache_free(vm_area_cachep, vma); } diff --git a/kernel/sys.c b/kernel/sys.c index 8fdac0d90504..2450a9f33cb0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2261,6 +2261,66 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) +#ifdef CONFIG_ANON_VMA_NAME + +#define ANON_VMA_NAME_MAX_LEN 80 +#define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" + +static inline bool is_valid_name_char(char ch) +{ + /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ + return ch > 0x1f && ch < 0x7f && + !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); +} + +static int prctl_set_vma(unsigned long opt, unsigned long addr, + unsigned long size, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + const char __user *uname; + char *name, *pch; + int error; + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + uname = (const char __user *)arg; + if (uname) { + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + + if (IS_ERR(name)) + return PTR_ERR(name); + + for (pch = name; *pch != '\0'; pch++) { + if (!is_valid_name_char(*pch)) { + kfree(name); + return -EINVAL; + } + } + } else { + /* Reset the name */ + name = NULL; + } + + mmap_write_lock(mm); + error = madvise_set_anon_name(mm, addr, size, name); + mmap_write_unlock(mm); + kfree(name); + break; + default: + error = -EINVAL; + } + + return error; +} + +#else /* CONFIG_ANON_VMA_NAME */ +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long size, unsigned long arg) +{ + return -EINVAL; +} +#endif /* CONFIG_ANON_VMA_NAME */ + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2530,6 +2590,9 @@ 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_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; diff --git a/mm/Kconfig b/mm/Kconfig index 356f4f2c779e..53d7485fc38f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -900,6 +900,20 @@ config IO_MAPPING config SECRETMEM def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED +config ANON_VMA_NAME + bool "Anonymous VMA name support" + depends on PROC_FS && ADVISE_SYSCALLS && MMU + + help + Allow naming anonymous virtual memory areas. + + This feature allows assigning names to virtual memory areas. Assigned + names can be later retrieved from /proc/pid/maps and /proc/pid/smaps + and help identifying individual anonymous memory areas. + Assigning a name to anonymous virtual memory area might prevent that + area from being merged with adjacent virtual memory areas due to the + difference in their name. + source "mm/damon/Kconfig" endmenu diff --git a/mm/madvise.c b/mm/madvise.c index 4b9c5509990c..413bbc6e40a0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -62,19 +63,84 @@ static int madvise_need_mmap_write(int behavior) } } +#ifdef CONFIG_ANON_VMA_NAME +static inline bool has_vma_anon_name(struct vm_area_struct *vma) +{ + return !vma->vm_file && vma->anon_name; +} + +const char *vma_anon_name(struct vm_area_struct *vma) +{ + if (!has_vma_anon_name(vma)) + return NULL; + + mmap_assert_locked(vma->vm_mm); + + return vma->anon_name; +} + +void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + if (!has_vma_anon_name(orig_vma)) + return; + + new_vma->anon_name = kstrdup(orig_vma->anon_name, GFP_KERNEL); +} + +void free_vma_anon_name(struct vm_area_struct *vma) +{ + if (!has_vma_anon_name(vma)) + return; + + kfree(vma->anon_name); + vma->anon_name = NULL; +} + +/* mmap_lock should be write-locked */ +static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +{ + if (!name) { + free_vma_anon_name(vma); + return 0; + } + + if (vma->anon_name) { + /* Same name, nothing to do here */ + if (!strcmp(name, vma->anon_name)) + return 0; + + free_vma_anon_name(vma); + } + vma->anon_name = kstrdup(name, GFP_KERNEL); + if (!vma->anon_name) + return -ENOMEM; + + return 0; +} +#else /* CONFIG_ANON_VMA_NAME */ +static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +{ + if (name) + return -EINVAL; + + return 0; +} +#endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_sem held for writing; */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, - unsigned long end, unsigned long new_flags) + unsigned long end, unsigned long new_flags, + const char *name) { struct mm_struct *mm = vma->vm_mm; int error; pgoff_t pgoff; - if (new_flags == vma->vm_flags) { + if (new_flags == vma->vm_flags && is_same_vma_anon_name(vma, name)) { *prev = vma; return 0; } @@ -82,7 +148,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, name); if (*prev) { vma = *prev; goto success; @@ -111,6 +177,11 @@ success: * vm_flags is protected by the mmap_lock held in write mode. */ vma->vm_flags = new_flags; + if (!vma->vm_file) { + error = replace_vma_anon_name(vma, name); + if (error) + return error; + } return 0; } @@ -938,7 +1009,8 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, break; } - error = madvise_update_vma(vma, prev, start, end, new_flags); + error = madvise_update_vma(vma, prev, start, end, new_flags, + vma_anon_name(vma)); out: /* @@ -1118,6 +1190,55 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, return unmapped_error; } +#ifdef CONFIG_ANON_VMA_NAME +static int madvise_vma_anon_name(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + unsigned long name) +{ + int error; + + /* Only anonymous mappings can be named */ + if (vma->vm_file) + return -EBADF; + + error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, + (const char *)name); + + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; + return error; +} + +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name) +{ + unsigned long end; + unsigned long len; + + if (start & ~PAGE_MASK) + return -EINVAL; + len = (len_in + ~PAGE_MASK) & PAGE_MASK; + + /* Check to see whether len was rounded up from small -ve to zero */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + return madvise_walk_vmas(mm, start, end, (unsigned long)name, + madvise_vma_anon_name); +} +#endif /* CONFIG_ANON_VMA_NAME */ /* * The madvise(2) system call. * diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f6248affaf38..679f47b3a079 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -810,7 +810,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx); + new_pol, vma->vm_userfaultfd_ctx, + vma_anon_name(vma)); if (prev) { vma = prev; next = vma->vm_next; diff --git a/mm/mlock.c b/mm/mlock.c index e263d62ae2d0..8f584eddd305 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -512,7 +512,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index bfb0ea164a90..85edb0011453 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1029,7 +1029,8 @@ again: */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -1047,6 +1048,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; + if (!is_same_vma_anon_name(vma, anon_name)) + return 0; return 1; } @@ -1079,9 +1082,10 @@ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; @@ -1100,9 +1104,10 @@ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); @@ -1113,9 +1118,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, } /* - * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out - * whether that can be merged with its predecessor or its successor. - * Or both (it neatly fills a hole). + * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), + * figure out whether that can be merged with its predecessor or its + * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when @@ -1160,7 +1165,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -1190,7 +1196,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, anon_name)) { /* * OK, it can. Can we now merge in the successor as well? */ @@ -1199,7 +1205,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx) && + vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ @@ -1222,7 +1228,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, anon_name)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); @@ -1754,7 +1760,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -1803,7 +1809,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, - NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (merge) { /* ->mmap() can change vma->vm_file and fput the original file. So * fput the vma->vm_file here or we would add an extra fput for file @@ -3056,7 +3062,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -3249,7 +3255,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index e552f5e0ccbd..0138dfcdb1d8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -464,7 +464,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); -- cgit v1.2.3 From 21b084fdf2a49ca1634e8e360e9ab6f9ff0dee11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 14 Jan 2022 14:08:21 -0800 Subject: mm/mempolicy: wire up syscall set_mempolicy_home_node Link: https://lkml.kernel.org/r/20211202123810.267175-4-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/syscalls.h | 3 +++ include/uapi/asm-generic/unistd.h | 5 ++++- kernel/sys_ni.c | 1 + 21 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index ca5a32228cd6..3515bc4f16a4 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -489,3 +489,4 @@ # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease 559 common futex_waitv sys_futex_waitv +560 common set_mempolicy_home_node sys_ni_syscall diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 543100151f2b..ac964612d8b0 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -463,3 +463,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 6bdb5f5db438..4e65da3445c7 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 450 +#define __NR_compat_syscalls 451 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 41ea1195e44b..604a2053d006 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -905,6 +905,8 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 707ae121f6d3..78b1d03e86e1 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -370,3 +370,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 45bc32a41b90..b1f3940bc298 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -449,3 +449,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 2204bde3ce4a..820145e47350 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -455,3 +455,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 72d02d363f36..253ff994ed2e 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -388,3 +388,4 @@ # 447 reserved for memfd_secret 448 n32 process_mrelease sys_process_mrelease 449 n32 futex_waitv sys_futex_waitv +450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index e2c481fcede6..3f1886ad9d80 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -364,3 +364,4 @@ # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3714c97b2643..8f243e35a7b2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -437,3 +437,4 @@ # 447 reserved for memfd_secret 448 o32 process_mrelease sys_process_mrelease 449 o32 futex_waitv sys_futex_waitv +450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 358c00000755..68b46fe2f17c 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -447,3 +447,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 15109af9d075..2600b4237292 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -529,3 +529,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index ed9c5c2eafad..799147658dee 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index d9539d28bdaa..2de85c977f54 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 46adabcb1720..4398cc6fb68d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -495,3 +495,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7e25543693de..320480a8db4f 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -454,3 +454,4 @@ 447 i386 memfd_secret sys_memfd_secret 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv +450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index fe8f8dd157b4..c84d12608cd2 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -371,6 +371,7 @@ 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 3e3e1a506bed..52c94ab5c205 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -420,3 +420,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 528a478dbda8..819c0cb00b6d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1057,6 +1057,9 @@ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type ru const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); asmlinkage long sys_memfd_secret(unsigned int flags); +asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 4557a8b6086f..1c48b0ae3ba3 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -883,8 +883,11 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) + #undef __NR_syscalls -#define __NR_syscalls 450 +#define __NR_syscalls 451 /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index d1944258cfc0..a492f159624f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -297,6 +297,7 @@ COND_SYSCALL(get_mempolicy); COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); +COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); -- cgit v1.2.3 From dea2903719283c156b53741126228c4a1b40440f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 10 Jan 2022 19:00:02 -0500 Subject: cifs: move superblock magic defitions to magic.h Help userland apps to identify cifs and smb2 mounts. Signed-off-by: Jeff Layton Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 3 ++- fs/cifs/cifsglob.h | 2 -- fs/cifs/smb1ops.c | 3 ++- fs/cifs/smb2glob.h | 2 -- fs/cifs/smb2ops.c | 5 +++-- include/uapi/linux/magic.h | 4 ++++ 6 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index a62a4305f79d..36b2e0cb9736 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "cifsfs.h" #include "cifspdu.h" @@ -202,7 +203,7 @@ cifs_read_super(struct super_block *sb) sb->s_time_max = ts.tv_sec; } - sb->s_magic = CIFS_MAGIC_NUMBER; + sb->s_magic = CIFS_SUPER_MAGIC; sb->s_op = &cifs_super_ops; sb->s_xattr = cifs_xattr_handlers; rc = super_setup_bdi(sb); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f88d2b10045a..f84978b76bb6 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -24,8 +24,6 @@ #include "../smbfs_common/smb2pdu.h" #include "smb2pdu.h" -#define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */ - #define SMB_PATH_MAX 260 #define CIFS_PORT 445 #define RFC1001_PORT 139 diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 6364c09296e8..8272c91e15ef 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -7,6 +7,7 @@ #include #include +#include #include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" @@ -887,7 +888,7 @@ cifs_queryfs(const unsigned int xid, struct cifs_tcon *tcon, { int rc = -EOPNOTSUPP; - buf->f_type = CIFS_MAGIC_NUMBER; + buf->f_type = CIFS_SUPER_MAGIC; /* * We could add a second check for a QFS Unix capability bit diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index ca692b2283cd..4125fd113cfb 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -13,8 +13,6 @@ #ifndef _SMB2_GLOB_H #define _SMB2_GLOB_H -#define SMB2_MAGIC_NUMBER 0xFE534D42 - /* ***************************************************************** * Constants go here diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index c2368c9110b0..af5d0830bc8a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "cifsfs.h" #include "cifsglob.h" #include "smb2pdu.h" @@ -2757,7 +2758,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, goto qfs_exit; rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base; - buf->f_type = SMB2_MAGIC_NUMBER; + buf->f_type = SMB2_SUPER_MAGIC; info = (struct smb2_fs_full_size_info *)( le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp); rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset), @@ -2799,7 +2800,7 @@ smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB311_posix_qfs_info(xid, tcon, fid.persistent_fid, fid.volatile_fid, buf); - buf->f_type = SMB2_MAGIC_NUMBER; + buf->f_type = SMB2_SUPER_MAGIC; SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); return rc; } diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 35687dcb1a42..a9f4dcb7b457 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -51,6 +51,7 @@ #define QNX6_SUPER_MAGIC 0x68191122 /* qnx6 fs detection */ #define AFS_FS_MAGIC 0x6B414653 + #define REISERFS_SUPER_MAGIC 0x52654973 /* used by gcc */ /* used by file system utilities that look at the superblock, etc. */ @@ -59,6 +60,9 @@ #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" #define SMB_SUPER_MAGIC 0x517B +#define CIFS_SUPER_MAGIC 0xFF534D42 /* the first four bytes of SMB PDUs */ +#define SMB2_SUPER_MAGIC 0xFE534D42 + #define CGROUP_SUPER_MAGIC 0x27e0eb #define CGROUP2_SUPER_MAGIC 0x63677270 -- cgit v1.2.3 From 8e930a66993be0a5f9a97c7c1c76ef09db4ef8bb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jan 2022 18:09:22 -0800 Subject: uuid: discourage people from using UAPI header in new code Discourage people from using UAPI header in new code by adding a note. Link: https://lkml.kernel.org/r/20211216113552.81199-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/uuid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index e5a7eecef7c3..32615dc5f0cf 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -1,4 +1,5 @@ /* 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 * -- cgit v1.2.3 From c7e4289cbe668c2743ac0fd623a2518dbc191dc0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jan 2022 18:09:25 -0800 Subject: uuid: remove licence boilerplate text from the header Remove licence boilerplate text from the UAPI header. Link: https://lkml.kernel.org/r/20211216113552.81199-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/uuid.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index 32615dc5f0cf..c0f4bd9b040e 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -5,15 +5,6 @@ * * Copyright (C) 2010, Intel Corp. * Huang Ying - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation; - * - * 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. */ #ifndef _UAPI_LINUX_UUID_H_ -- cgit v1.2.3 From 5bf18281534451bf1ad56a45a3085cd7ad46860d Mon Sep 17 00:00:00 2001 From: wangyong Date: Wed, 19 Jan 2022 18:10:15 -0800 Subject: delayacct: track delays from memory compact Delay accounting does not track the delay of memory compact. When there is not enough free memory, tasks can spend a amount of their time waiting for compact. To get the impact of tasks in direct memory compact, measure the delay when allocating memory through memory compact. Also update tools/accounting/getdelays.c: / # ./getdelays_next -di -p 304 print delayacct stats ON printing IO accounting PID 304 CPU count real total virtual total delay total delay average 277 780000000 849039485 18877296 0.068ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 5 11088812685 2217ms THRASHING count delay total delay average 0 0 0ms COMPACT count delay total delay average 3 72758 0ms watch: read=0, write=0, cancelled_write=0 Link: https://lkml.kernel.org/r/1638619795-71451-1-git-send-email-wang.yong12@zte.com.cn Signed-off-by: wangyong Reviewed-by: Jiang Xuexin Reviewed-by: Zhang Wenya Reviewed-by: Yang Yang Reviewed-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 28 ++++++++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 16 ++++++++++++++++ mm/page_alloc.c | 3 +++ tools/accounting/getdelays.c | 8 +++++++- 5 files changed, 59 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 435c3654a0ff..3e03d010bd2e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -42,8 +42,12 @@ struct task_delay_info { u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ + u64 compact_start; + u64 compact_delay; /* wait for memory compact */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ + u32 compact_count; /* total count of memory compact */ }; #endif @@ -72,6 +76,8 @@ extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); +extern void __delayacct_compact_start(void); +extern void __delayacct_compact_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -170,6 +176,24 @@ static inline void delayacct_swapin_end(void) __delayacct_swapin_end(); } +static inline void delayacct_compact_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_start(); +} + +static inline void delayacct_compact_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_end(); +} + #else static inline void delayacct_init(void) {} @@ -200,6 +224,10 @@ static inline void delayacct_swapin_start(void) {} static inline void delayacct_swapin_end(void) {} +static inline void delayacct_compact_start(void) +{} +static inline void delayacct_compact_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index ccbd08709321..12327d32378f 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 10 +#define TASKSTATS_VERSION 11 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -172,6 +172,10 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ + + /* Delay waiting for memory compact */ + __u64 compact_count; + __u64 compact_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 97699848c1f0..c5e8cea9e05f 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -155,10 +155,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; + tmp = d->compact_delay_total + tsk->delays->compact_delay; + d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; + d->compact_count += tsk->delays->compact_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -213,3 +216,16 @@ void __delayacct_swapin_end(void) ¤t->delays->swapin_delay, ¤t->delays->swapin_count); } + +void __delayacct_compact_start(void) +{ + current->delays->compact_start = local_clock(); +} + +void __delayacct_compact_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->compact_start, + ¤t->delays->compact_delay, + ¤t->delays->compact_count); +} diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c5952749ad40..635063f49671 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -72,6 +72,7 @@ #include #include #include +#include #include #include #include @@ -4348,6 +4349,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; psi_memstall_enter(&pflags); + delayacct_compact_start(); noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, @@ -4355,6 +4357,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); + delayacct_compact_end(); if (*compact_result == COMPACT_SKIPPED) return NULL; diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 5ef1c15e88ad..11e86739456d 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t) "RECLAIM %12s%15s%15s\n" " %15llu%15llu%15llums\n" "THRASHING%12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "COMPACT %12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, - average_ms(t->thrashing_delay_total, t->thrashing_count)); + average_ms(t->thrashing_delay_total, t->thrashing_count), + "count", "delay total", "delay average", + (unsigned long long)t->compact_count, + (unsigned long long)t->compact_delay_total, + average_ms(t->compact_delay_total, t->compact_count)); } static void task_context_switch_counts(struct taskstats *t) -- cgit v1.2.3 From f23653fe64479d96910bfda2b700b1af17c991ac Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 26 Jan 2022 09:22:54 +0000 Subject: tty: Partially revert the removal of the Cyclades public API Fix a user API regression introduced with commit f76edd8f7ce0 ("tty: cyclades, remove this orphan"), which removed a part of the API and caused compilation errors for user programs using said part, such as GCC 9 in its libsanitizer component[1]: .../libsanitizer/sanitizer_common/sanitizer_platform_limits_posix.cc:160:10: fatal error: linux/cyclades.h: No such file or directory 160 | #include | ^~~~~~~~~~~~~~~~~~ compilation terminated. make[4]: *** [Makefile:664: sanitizer_platform_limits_posix.lo] Error 1 As the absolute minimum required bring `struct cyclades_monitor' and ioctl numbers back then so as to make the library build again. Add a preprocessor warning as to the obsolescence of the features provided. References: [1] GCC PR sanitizer/100379, "cyclades.h is removed from linux kernel header files", Fixes: f76edd8f7ce0 ("tty: cyclades, remove this orphan") Cc: stable@vger.kernel.org # v5.13+ Reviewed-by: Christoph Hellwig Signed-off-by: Maciej W. Rozycki Link: https://lore.kernel.org/r/alpine.DEB.2.20.2201260733430.11348@tpp.orcam.me.uk Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/cyclades.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/uapi/linux/cyclades.h (limited to 'include/uapi') diff --git a/include/uapi/linux/cyclades.h b/include/uapi/linux/cyclades.h new file mode 100644 index 000000000000..6225c5aebe06 --- /dev/null +++ b/include/uapi/linux/cyclades.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_CYCLADES_H +#define _UAPI_LINUX_CYCLADES_H + +#warning "Support for features provided by this header has been removed" +#warning "Please consider updating your code" + +struct cyclades_monitor { + unsigned long int_count; + unsigned long char_count; + unsigned long char_max; + unsigned long char_last; +}; + +#define CYGETMON 0x435901 +#define CYGETTHRESH 0x435902 +#define CYSETTHRESH 0x435903 +#define CYGETDEFTHRESH 0x435904 +#define CYSETDEFTHRESH 0x435905 +#define CYGETTIMEOUT 0x435906 +#define CYSETTIMEOUT 0x435907 +#define CYGETDEFTIMEOUT 0x435908 +#define CYSETDEFTIMEOUT 0x435909 +#define CYSETRFLOW 0x43590a +#define CYGETRFLOW 0x43590b +#define CYSETRTSDTR_INV 0x43590c +#define CYGETRTSDTR_INV 0x43590d +#define CYZSETPOLLCYCLE 0x43590e +#define CYZGETPOLLCYCLE 0x43590f +#define CYGETCD1400VER 0x435910 +#define CYSETWAIT 0x435912 +#define CYGETWAIT 0x435913 + +#endif /* _UAPI_LINUX_CYCLADES_H */ -- cgit v1.2.3 From dd6e631220181162478984d2d46dd979e04d8e75 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 26 Jan 2022 07:49:45 -0500 Subject: KVM: x86: add system attribute to retrieve full set of supported xsave states Because KVM_GET_SUPPORTED_CPUID is meant to be passed (by simple-minded VMMs) to KVM_SET_CPUID2, it cannot include any dynamic xsave states that have not been enabled. Probing those, for example so that they can be passed to ARCH_REQ_XCOMP_GUEST_PERM, requires a new ioctl or arch_prctl. The latter is in fact worse, even though that is what the rest of the API uses, because it would require supported_xcr0 to be moved from the KVM module to the kernel just for this use. In addition, the value would be nonsensical (or an error would have to be returned) until the KVM module is loaded in. Therefore, to limit the growth of system ioctls, add a /dev/kvm variant of KVM_{GET,HAS}_DEVICE_ATTR, and implement it in x86 with just one group (0) and attribute (KVM_X86_XCOMP_GUEST_SUPP). Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 4 +++- arch/x86/include/uapi/asm/kvm.h | 3 +++ arch/x86/kvm/x86.c | 51 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 4 files changed, 58 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index bb8cfddbb22d..a4267104db50 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -3268,6 +3268,7 @@ number. :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, KVM_CAP_VCPU_ATTRIBUTES for vcpu device + KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device (no set) :Type: device ioctl, vm ioctl, vcpu ioctl :Parameters: struct kvm_device_attr :Returns: 0 on success, -1 on error @@ -3302,7 +3303,8 @@ transferred is defined by the particular attribute. ------------------------ :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, - KVM_CAP_VCPU_ATTRIBUTES for vcpu device + KVM_CAP_VCPU_ATTRIBUTES for vcpu device + KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device :Type: device ioctl, vm ioctl, vcpu ioctl :Parameters: struct kvm_device_attr :Returns: 0 on success, -1 on error diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 2da3316bb559..bf6e96011dfe 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -452,6 +452,9 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 +/* attributes for system fd (group 0) */ +#define KVM_X86_XCOMP_GUEST_SUPP 0 + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 76a5dcfcabdb..c25a6ef0ff06 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4230,6 +4230,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: + case KVM_CAP_SYS_ATTRIBUTES: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4343,6 +4344,40 @@ static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) return uaddr; } +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = kvm_get_attr_addr(attr); + + if (attr->group) + return -ENXIO; + + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + if (put_user(supported_xcr0, uaddr)) + return -EFAULT; + return 0; + default: + return -ENXIO; + break; + } +} + +static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) +{ + if (attr->group) + return -ENXIO; + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + return 0; + default: + return -ENXIO; + } +} + long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4431,6 +4466,22 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; + case KVM_GET_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_get_attr(&attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_has_attr(&attr); + break; + } default: r = -EINVAL; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 9563d294f181..b46bcdb0cab1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1133,6 +1133,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 +#define KVM_CAP_SYS_ATTRIBUTES 209 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 06feec6005c9d9500cd286ec440aabf8b2ddd94d Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 12 Jan 2022 22:50:39 +0300 Subject: ASoC: hdmi-codec: Fix OOB memory accesses Correct size of iec_status array by changing it to the size of status array of the struct snd_aes_iec958. This fixes out-of-bounds slab read accesses made by memcpy() of the hdmi-codec driver. This problem is reported by KASAN. Cc: stable@vger.kernel.org Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20220112195039.1329-1-digetx@gmail.com Signed-off-by: Mark Brown --- include/uapi/sound/asound.h | 4 +++- sound/soc/codecs/hdmi-codec.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index ff7e638221c5..228279ea0670 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -56,8 +56,10 @@ * * ****************************************************************************/ +#define AES_IEC958_STATUS_SIZE 24 + struct snd_aes_iec958 { - unsigned char status[24]; /* AES/IEC958 channel status bits */ + unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */ unsigned char subcode[147]; /* AES/IEC958 subcode bits */ unsigned char pad; /* nothing */ unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */ diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index b61f980cabdc..b07607a9ecea 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -277,7 +277,7 @@ struct hdmi_codec_priv { bool busy; struct snd_soc_jack *jack; unsigned int jack_status; - u8 iec_status[5]; + u8 iec_status[AES_IEC958_STATUS_SIZE]; }; static const struct snd_soc_dapm_widget hdmi_widgets[] = { -- cgit v1.2.3 From f6c6804c43fa18d3cee64b55490dfbd3bef1363a Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Fri, 28 Jan 2022 15:40:25 +0000 Subject: kvm: Move KVM_GET_XSAVE2 IOCTL definition at the end of kvm.h This way we can more easily find the next free IOCTL number when adding new IOCTLs. Fixes: be50b2065dfa ("kvm: x86: Add support for getting/setting expanded xstate buffer") Signed-off-by: Janosch Frank Message-Id: <20220128154025.102666-1-frankja@linux.ibm.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b46bcdb0cab1..5191b57e1562 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1624,9 +1624,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -/* Available with KVM_CAP_XSAVE2 */ -#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) - struct kvm_s390_pv_sec_parm { __u64 origin; __u64 length; @@ -2048,4 +2045,7 @@ struct kvm_stats_desc { #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From ddecd22878601a606d160680fa85802b75d92eb6 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 31 Jan 2022 11:34:07 +0100 Subject: perf: uapi: Document perf_event_attr::sig_data truncation on 32 bit architectures Due to the alignment requirements of siginfo_t, as described in 3ddb3fd8cdb0 ("signal, perf: Fix siginfo_t by avoiding u64 on 32-bit architectures"), siginfo_t::si_perf_data is limited to an unsigned long. However, perf_event_attr::sig_data is an u64, to avoid having to deal with compat conversions. Due to being an u64, it may not immediately be clear to users that sig_data is truncated on 32 bit architectures. Add a comment to explicitly point this out, and hopefully help some users save time by not having to deduce themselves what's happening. Reported-by: Dmitry Vyukov Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20220131103407.1971678-3-elver@google.com --- include/uapi/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1b65042ab1db..82858b697c05 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -465,6 +465,8 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via * siginfo_t::si_perf_data, e.g. to permit user to identify the event. + * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be + * truncated accordingly on 32 bit architectures. */ __u64 sig_data; }; -- cgit v1.2.3 From c86d86131ab75696fc52d98571148842e067d620 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Wed, 2 Feb 2022 06:09:04 +0300 Subject: Partially revert "net/smc: Add netlink net namespace support" The change of sizeof(struct smc_diag_linkinfo) by commit 79d39fc503b4 ("net/smc: Add netlink net namespace support") introduced an ABI regression: since struct smc_diag_lgrinfo contains an object of type "struct smc_diag_linkinfo", offset of all subsequent members of struct smc_diag_lgrinfo was changed by that change. As result, applications compiled with the old version of struct smc_diag_linkinfo will receive garbage in struct smc_diag_lgrinfo.role if the kernel implements this new version of struct smc_diag_linkinfo. Fix this regression by reverting the part of commit 79d39fc503b4 that changes struct smc_diag_linkinfo. After all, there is SMC_GEN_NETLINK interface which is good enough, so there is probably no need to touch the smc_diag ABI in the first place. Fixes: 79d39fc503b4 ("net/smc: Add netlink net namespace support") Signed-off-by: Dmitry V. Levin Reviewed-by: Karsten Graul Link: https://lore.kernel.org/r/20220202030904.GA9742@altlinux.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/smc_diag.h | 11 +++++------ net/smc/smc_diag.c | 2 -- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index c7008d87f1a4..8cb3a6fef553 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -84,12 +84,11 @@ struct smc_diag_conninfo { /* SMC_DIAG_LINKINFO */ struct smc_diag_linkinfo { - __u8 link_id; /* link identifier */ - __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ - __u8 ibport; /* RDMA device port number */ - __u8 gid[40]; /* local GID */ - __u8 peer_gid[40]; /* peer GID */ - __aligned_u64 net_cookie; /* RDMA device net namespace */ + __u8 link_id; /* link identifier */ + __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ + __u8 ibport; /* RDMA device port number */ + __u8 gid[40]; /* local GID */ + __u8 peer_gid[40]; /* peer GID */ }; struct smc_diag_lgrinfo { diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index b8898c787d23..1fca2f90a9c7 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -146,13 +146,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_link *link = smc->conn.lnk; - struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net); struct smc_diag_lgrinfo linfo = { .role = smc->conn.lgr->role, .lnk[0].ibport = link->ibport, .lnk[0].link_id = link->link_id, - .lnk[0].net_cookie = net->net_cookie, }; memcpy(linfo.lnk[0].ibname, -- cgit v1.2.3 From 164666fa66669d437bdcc8d5f1744a2aee73be41 Mon Sep 17 00:00:00 2001 From: Demi Marie Obenour Date: Mon, 31 Jan 2022 12:23:07 -0500 Subject: Improve docs for IOCTL_GNTDEV_MAP_GRANT_REF --------------cKY3Ggs6VDUCSn4I6iN78sHA Content-Type: multipart/mixed; boundary="------------g0T69ASidFiPhh4eOY4XzIg1" --------------g0T69ASidFiPhh4eOY4XzIg1 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable The current implementation of gntdev guarantees that the first call to IOCTL_GNTDEV_MAP_GRANT_REF will set @index to 0. This is required to use gntdev for Wayland, which is a future desire of Qubes OS. Additionally, requesting zero grants results in an error, but this was not documented either. Document both of these. Signed-off-by: Demi Marie Obenour Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/f66c5a4e-2034-00b5-a635-6983bd999c07@gmail.com Signed-off-by: Juergen Gross --- include/uapi/xen/gntdev.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index 9ac5515b9bc2..7a7145395c09 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -47,7 +47,13 @@ struct ioctl_gntdev_grant_ref { /* * Inserts the grant references into the mapping table of an instance * of gntdev. N.B. This does not perform the mapping, which is deferred - * until mmap() is called with @index as the offset. + * until mmap() is called with @index as the offset. @index should be + * considered opaque to userspace, with one exception: if no grant + * references have ever been inserted into the mapping table of this + * instance, @index will be set to 0. This is necessary to use gntdev + * with userspace APIs that expect a file descriptor that can be + * mmap()'d at offset 0, such as Wayland. If @count is set to 0, this + * ioctl will fail. */ #define IOCTL_GNTDEV_MAP_GRANT_REF \ _IOC(_IOC_NONE, 'G', 0, sizeof(struct ioctl_gntdev_map_grant_ref)) -- cgit v1.2.3 From d1ca60efc53d665cf89ed847a14a510a81770b81 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 2 Feb 2022 12:00:56 +0100 Subject: netfilter: ctnetlink: disable helper autoassign When userspace, e.g. conntrackd, inserts an entry with a specified helper, its possible that the helper is lost immediately after its added: ctnetlink_create_conntrack -> nf_ct_helper_ext_add + assign helper -> ctnetlink_setup_nat -> ctnetlink_parse_nat_setup -> parse_nat_setup -> nfnetlink_parse_nat_setup -> nf_nat_setup_info -> nf_conntrack_alter_reply -> __nf_ct_try_assign_helper ... and __nf_ct_try_assign_helper will zero the helper again. Set IPS_HELPER bit to bypass auto-assign logic, its unwanted, just like when helper is assigned via ruleset. Dropped old 'not strictly necessary' comment, it referred to use of rcu_assign_pointer() before it got replaced by RCU_INIT_POINTER(). NB: Fixes tag intentionally incorrect, this extends the referenced commit, but this change won't build without IPS_HELPER introduced there. Fixes: 6714cf5465d280 ("netfilter: nf_conntrack: fix explicit helper attachment and NAT") Reported-by: Pham Thanh Tuyen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_common.h | 2 +- net/netfilter/nf_conntrack_netlink.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 4b3395082d15..26071021e986 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -106,7 +106,7 @@ enum ip_conntrack_status { IPS_NAT_CLASH = IPS_UNTRACKED, #endif - /* Conntrack got a helper explicitly attached via CT target. */ + /* Conntrack got a helper explicitly attached (ruleset, ctnetlink). */ IPS_HELPER_BIT = 13, IPS_HELPER = (1 << IPS_HELPER_BIT), diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index ac438370f94a..7032402ffd33 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2311,7 +2311,8 @@ ctnetlink_create_conntrack(struct net *net, if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); - /* not in hash table yet so not strictly necessary */ + /* disable helper auto-assignment for this entry */ + ct->status |= IPS_HELPER; RCU_INIT_POINTER(help->helper, helper); } } else { -- cgit v1.2.3