From fa4320cefb8537a70cc28c55d311a1f569697cd3 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 2 Nov 2020 14:21:31 +0800 Subject: f2fs: move ioctl interface definitions to separated file Like other filesystem does, we introduce a new file f2fs.h in path of include/uapi/linux/, and move f2fs-specified ioctl interface definitions to that file, after then, in order to use those definitions, userspace developer only need to include the new header file rather than copy & paste definitions from fs/f2fs/f2fs.h. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/uapi/linux/f2fs.h | 87 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 include/uapi/linux/f2fs.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h new file mode 100644 index 000000000000..28bcfe8d2c27 --- /dev/null +++ b/include/uapi/linux/f2fs.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_F2FS_H +#define _UAPI_LINUX_F2FS_H +#include +#include + +/* + * f2fs-specific ioctl commands + */ +#define F2FS_IOCTL_MAGIC 0xf5 +#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1) +#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2) +#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3) +#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) +#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) +#define F2FS_IOC_GARBAGE_COLLECT _IOW(F2FS_IOCTL_MAGIC, 6, __u32) +#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7) +#define F2FS_IOC_DEFRAGMENT _IOWR(F2FS_IOCTL_MAGIC, 8, \ + struct f2fs_defragment) +#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \ + struct f2fs_move_range) +#define F2FS_IOC_FLUSH_DEVICE _IOW(F2FS_IOCTL_MAGIC, 10, \ + struct f2fs_flush_device) +#define F2FS_IOC_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11, \ + struct f2fs_gc_range) +#define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, __u32) +#define F2FS_IOC_SET_PIN_FILE _IOW(F2FS_IOCTL_MAGIC, 13, __u32) +#define F2FS_IOC_GET_PIN_FILE _IOR(F2FS_IOCTL_MAGIC, 14, __u32) +#define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15) +#define F2FS_IOC_RESIZE_FS _IOW(F2FS_IOCTL_MAGIC, 16, __u64) +#define F2FS_IOC_GET_COMPRESS_BLOCKS _IOR(F2FS_IOCTL_MAGIC, 17, __u64) +#define F2FS_IOC_RELEASE_COMPRESS_BLOCKS \ + _IOR(F2FS_IOCTL_MAGIC, 18, __u64) +#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS \ + _IOR(F2FS_IOCTL_MAGIC, 19, __u64) +#define F2FS_IOC_SEC_TRIM_FILE _IOW(F2FS_IOCTL_MAGIC, 20, \ + struct f2fs_sectrim_range) + +/* + * should be same as XFS_IOC_GOINGDOWN. + * Flags for going down operation used by FS_IOC_GOINGDOWN + */ +#define F2FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */ +#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */ +#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */ +#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */ +#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */ +#define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */ + +/* + * Flags used by F2FS_IOC_SEC_TRIM_FILE + */ +#define F2FS_TRIM_FILE_DISCARD 0x1 /* send discard command */ +#define F2FS_TRIM_FILE_ZEROOUT 0x2 /* zero out */ +#define F2FS_TRIM_FILE_MASK 0x3 + +struct f2fs_gc_range { + __u32 sync; + __u64 start; + __u64 len; +}; + +struct f2fs_defragment { + __u64 start; + __u64 len; +}; + +struct f2fs_move_range { + __u32 dst_fd; /* destination fd */ + __u64 pos_in; /* start position in src_fd */ + __u64 pos_out; /* start position in dst_fd */ + __u64 len; /* size to move */ +}; + +struct f2fs_flush_device { + __u32 dev_num; /* device number to flush */ + __u32 segments; /* # of segments to flush */ +}; + +struct f2fs_sectrim_range { + __u64 start; + __u64 len; + __u64 flags; +}; + +#endif /* _UAPI_LINUX_F2FS_H */ -- cgit v1.2.3 From 9e2a5f8cfb4d9371783e21e27bba4338401f1260 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Fri, 30 Oct 2020 13:10:34 +0900 Subject: f2fs: add F2FS_IOC_GET_COMPRESS_OPTION ioctl Added a new F2FS_IOC_GET_COMPRESS_OPTION ioctl to get file compression option of a file. struct f2fs_comp_option { u8 algorithm; => compression algorithm => 0:lzo, 1:lz4, 2:zstd, 3:lzorle u8 log_cluster_size; => log scale cluster size => 2 ~ 8 }; struct f2fs_comp_option option; ioctl(fd, F2FS_IOC_GET_COMPRESS_OPTION, &option); Signed-off-by: Daeho Jeong Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/f2fs.h | 7 +++++++ 2 files changed, 37 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 89c451f09344..c747f5dd595c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3945,6 +3945,33 @@ err: return ret; } +static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_comp_option option; + + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + inode_lock_shared(inode); + + if (!f2fs_compressed_file(inode)) { + inode_unlock_shared(inode); + return -ENODATA; + } + + option.algorithm = F2FS_I(inode)->i_compress_algorithm; + option.log_cluster_size = F2FS_I(inode)->i_log_cluster_size; + + inode_unlock_shared(inode); + + if (copy_to_user((struct f2fs_comp_option __user *)arg, &option, + sizeof(option))) + return -EFAULT; + + return 0; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) @@ -4033,6 +4060,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_reserve_compress_blocks(filp, arg); case F2FS_IOC_SEC_TRIM_FILE: return f2fs_sec_trim_file(filp, arg); + case F2FS_IOC_GET_COMPRESS_OPTION: + return f2fs_ioc_get_compress_option(filp, arg); default: return -ENOTTY; } @@ -4203,6 +4232,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: case F2FS_IOC_SEC_TRIM_FILE: + case F2FS_IOC_GET_COMPRESS_OPTION: break; default: return -ENOIOCTLCMD; diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h index 28bcfe8d2c27..872e61d78f29 100644 --- a/include/uapi/linux/f2fs.h +++ b/include/uapi/linux/f2fs.h @@ -36,6 +36,8 @@ _IOR(F2FS_IOCTL_MAGIC, 19, __u64) #define F2FS_IOC_SEC_TRIM_FILE _IOW(F2FS_IOCTL_MAGIC, 20, \ struct f2fs_sectrim_range) +#define F2FS_IOC_GET_COMPRESS_OPTION _IOR(F2FS_IOCTL_MAGIC, 21, \ + struct f2fs_comp_option) /* * should be same as XFS_IOC_GOINGDOWN. @@ -84,4 +86,9 @@ struct f2fs_sectrim_range { __u64 flags; }; +struct f2fs_comp_option { + __u8 algorithm; + __u8 log_cluster_size; +}; + #endif /* _UAPI_LINUX_F2FS_H */ -- cgit v1.2.3 From 63f9909ff602082597849f684655e93336c50b11 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Fri, 9 Oct 2020 14:15:07 -0400 Subject: fuse: introduce the notion of FUSE_HANDLE_KILLPRIV_V2 We already have FUSE_HANDLE_KILLPRIV flag that says that file server will remove suid/sgid/caps on truncate/chown/write. But that's little different from what Linux VFS implements. To be consistent with Linux VFS behavior what we want is. - caps are always cleared on chown/write/truncate - suid is always cleared on chown, while for truncate/write it is cleared only if caller does not have CAP_FSETID. - sgid is always cleared on chown, while for truncate/write it is cleared only if caller does not have CAP_FSETID as well as file has group execute permission. As previous flag did not provide above semantics. Implement a V2 of the protocol with above said constraints. Server does not know if caller has CAP_FSETID or not. So for the case of write()/truncate(), client will send information in special flag to indicate whether to kill priviliges or not. These changes are in subsequent patches. FUSE_HANDLE_KILLPRIV_V2 relies on WRITE being sent to server to clear suid/sgid/security.capability. But with ->writeback_cache, WRITES are cached in guest. So it is not recommended to use FUSE_HANDLE_KILLPRIV_V2 and writeback_cache together. Though it probably might be good enough for lot of use cases. Signed-off-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- fs/fuse/fuse_i.h | 8 ++++++++ fs/fuse/inode.c | 5 ++++- include/uapi/linux/fuse.h | 11 ++++++++++- 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 8301c5056022..d414c787e362 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -635,6 +635,14 @@ struct fuse_conn { /* show legacy mount options */ unsigned int legacy_opts_show:1; + /* + * fs kills suid/sgid/cap on write/chown/trunc. suid is killed on + * write/trunc only if caller did not have CAP_FSETID. sgid is killed + * on write/truncate only if caller did not have CAP_FSETID as well as + * file has group execute permission. + */ + unsigned handle_killpriv_v2:1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e7e9005b9b66..5a6102cd6473 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1038,6 +1038,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, !fuse_dax_check_alignment(fc, arg->map_alignment)) { ok = false; } + if (arg->flags & FUSE_HANDLE_KILLPRIV_V2) + fc->handle_killpriv_v2 = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1080,7 +1082,8 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | - FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA; + FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | + FUSE_HANDLE_KILLPRIV_V2; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) ia->in.flags |= FUSE_MAP_ALIGNMENT; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 7233502ea991..29bd2e007947 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -175,6 +175,9 @@ * * 7.32 * - add flags to fuse_attr, add FUSE_ATTR_SUBMOUNT, add FUSE_SUBMOUNTS + * + * 7.33 + * - add FUSE_HANDLE_KILLPRIV_V2 */ #ifndef _LINUX_FUSE_H @@ -210,7 +213,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 32 +#define FUSE_KERNEL_MINOR_VERSION 33 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -320,6 +323,11 @@ struct fuse_file_lock { * foffset and moffset fields in struct * fuse_setupmapping_out and fuse_removemapping_one. * FUSE_SUBMOUNTS: kernel supports auto-mounting directory submounts + * FUSE_HANDLE_KILLPRIV_V2: fs kills suid/sgid/cap on write/chown/trunc. + * Upon write/truncate suid/sgid is only killed if caller + * does not have CAP_FSETID. Additionally upon + * write/truncate sgid is killed only if file has group + * execute permission. (Same as Linux VFS behavior). */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -349,6 +357,7 @@ struct fuse_file_lock { #define FUSE_EXPLICIT_INVAL_DATA (1 << 25) #define FUSE_MAP_ALIGNMENT (1 << 26) #define FUSE_SUBMOUNTS (1 << 27) +#define FUSE_HANDLE_KILLPRIV_V2 (1 << 28) /** * CUSE INIT request/reply flags -- cgit v1.2.3 From 10c52c84e3f4872689a64ac7666b34d67e630691 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 11 Nov 2020 17:22:32 +0100 Subject: fuse: rename FUSE_WRITE_KILL_PRIV to FUSE_WRITE_KILL_SUIDGID Kernel has: ATTR_KILL_PRIV -> clear "security.capability" ATTR_KILL_SUID -> clear S_ISUID ATTR_KILL_SGID -> clear S_ISGID if executable Fuse has: FUSE_WRITE_KILL_PRIV -> clear S_ISUID and S_ISGID if executable So FUSE_WRITE_KILL_PRIV implies the complement of ATTR_KILL_PRIV, which is somewhat confusing. Also PRIV implies all privileges, including "security.capability". Change the name to FUSE_WRITE_KILL_SUIDGID and make FUSE_WRITE_KILL_PRIV an alias to perserve API compatibility Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 2 +- include/uapi/linux/fuse.h | 9 ++++++--- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 41b1e14f3820..603af847d596 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1451,7 +1451,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (write) { if (!capable(CAP_FSETID)) - ia->write.in.write_flags |= FUSE_WRITE_KILL_PRIV; + ia->write.in.write_flags |= FUSE_WRITE_KILL_SUIDGID; nres = fuse_send_write(ia, pos, nbytes, owner); } else { diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 29bd2e007947..2623c75b94a5 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -177,7 +177,7 @@ * - add flags to fuse_attr, add FUSE_ATTR_SUBMOUNT, add FUSE_SUBMOUNTS * * 7.33 - * - add FUSE_HANDLE_KILLPRIV_V2 + * - add FUSE_HANDLE_KILLPRIV_V2, FUSE_WRITE_KILL_SUIDGID */ #ifndef _LINUX_FUSE_H @@ -387,11 +387,14 @@ struct fuse_file_lock { * * FUSE_WRITE_CACHE: delayed write from page cache, file handle is guessed * FUSE_WRITE_LOCKOWNER: lock_owner field is valid - * FUSE_WRITE_KILL_PRIV: kill suid and sgid bits + * FUSE_WRITE_KILL_SUIDGID: kill suid and sgid bits */ #define FUSE_WRITE_CACHE (1 << 0) #define FUSE_WRITE_LOCKOWNER (1 << 1) -#define FUSE_WRITE_KILL_PRIV (1 << 2) +#define FUSE_WRITE_KILL_SUIDGID (1 << 2) + +/* Obsolete alias; this flag implies killing suid/sgid only. */ +#define FUSE_WRITE_KILL_PRIV FUSE_WRITE_KILL_SUIDGID /** * Read flags -- cgit v1.2.3 From 3179216135ec09825d7c7875580951a6e69dc5df Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Fri, 9 Oct 2020 14:15:09 -0400 Subject: fuse: setattr should set FATTR_KILL_SUIDGID If fc->handle_killpriv_v2 is enabled, we expect file server to clear suid/sgid/security.capbility upon chown/truncate/write as appropriate. Upon truncate (ATTR_SIZE), suid/sgid are cleared only if caller does not have CAP_FSETID. File server does not know whether caller has CAP_FSETID or not. Hence set FATTR_KILL_SUIDGID upon truncate to let file server know that caller does not have CAP_FSETID and it should kill suid/sgid as appropriate. On chown (ATTR_UID/ATTR_GID) suid/sgid need to be cleared irrespective of capabilities of calling process, so set FATTR_KILL_SUIDGID unconditionally in that case. Signed-off-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 10 ++++++++++ include/uapi/linux/fuse.h | 3 ++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index c3e22a3dd323..28b07ae5e55f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1648,10 +1648,20 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, inarg.valid |= FATTR_FH; inarg.fh = ff->fh; } + + /* Kill suid/sgid for non-directory chown unconditionally */ + if (fc->handle_killpriv_v2 && !S_ISDIR(inode->i_mode) && + attr->ia_valid & (ATTR_UID | ATTR_GID)) + inarg.valid |= FATTR_KILL_SUIDGID; + if (attr->ia_valid & ATTR_SIZE) { /* For mandatory locking in truncate */ inarg.valid |= FATTR_LOCKOWNER; inarg.lock_owner = fuse_lock_owner_id(fc, current->files); + + /* Kill suid/sgid for truncate only if no CAP_FSETID */ + if (fc->handle_killpriv_v2 && !capable(CAP_FSETID)) + inarg.valid |= FATTR_KILL_SUIDGID; } fuse_setattr_fill(fc, &args, inode, &inarg, &outarg); err = fuse_simple_request(fm, &args); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 2623c75b94a5..9eb96e0564be 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -177,7 +177,7 @@ * - add flags to fuse_attr, add FUSE_ATTR_SUBMOUNT, add FUSE_SUBMOUNTS * * 7.33 - * - add FUSE_HANDLE_KILLPRIV_V2, FUSE_WRITE_KILL_SUIDGID + * - add FUSE_HANDLE_KILLPRIV_V2, FUSE_WRITE_KILL_SUIDGID, FATTR_KILL_SUIDGID */ #ifndef _LINUX_FUSE_H @@ -274,6 +274,7 @@ struct fuse_file_lock { #define FATTR_MTIME_NOW (1 << 8) #define FATTR_LOCKOWNER (1 << 9) #define FATTR_CTIME (1 << 10) +#define FATTR_KILL_SUIDGID (1 << 11) /** * Flags returned by the OPEN request -- cgit v1.2.3 From 643a666a89c358ef588d2b3ef9f2dc1efc421e61 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Fri, 9 Oct 2020 14:15:11 -0400 Subject: fuse: add a flag FUSE_OPEN_KILL_SUIDGID for open() request With FUSE_HANDLE_KILLPRIV_V2 support, server will need to kill suid/sgid/ security.capability on open(O_TRUNC), if server supports FUSE_ATOMIC_O_TRUNC. But server needs to kill suid/sgid only if caller does not have CAP_FSETID. Given server does not have this information, client needs to send this info to server. So add a flag FUSE_OPEN_KILL_SUIDGID to fuse_open_in request which tells server to kill suid/sgid (only if group execute is set). This flag is added to the FUSE_OPEN request, as well as the FUSE_CREATE request if the create was non-exclusive, since that might result in an existing file being opened/truncated. Signed-off-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 6 ++++++ fs/fuse/file.c | 6 ++++++ include/uapi/linux/fuse.h | 11 +++++++++-- 3 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 778367d125f9..5d43af1169b7 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -541,6 +541,12 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, inarg.flags = flags; inarg.mode = mode; inarg.umask = current_umask(); + + if (fm->fc->handle_killpriv_v2 && (flags & O_TRUNC) && + !(flags & O_EXCL) && !capable(CAP_FSETID)) { + inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID; + } + args.opcode = FUSE_CREATE; args.nodeid = get_node_id(dir); args.in_numargs = 2; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index aa0a44f7028f..349885353036 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -42,6 +42,12 @@ static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, struct file *file, inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY); if (!fm->fc->atomic_o_trunc) inarg.flags &= ~O_TRUNC; + + if (fm->fc->handle_killpriv_v2 && + (inarg.flags & O_TRUNC) && !capable(CAP_FSETID)) { + inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID; + } + args.opcode = opcode; args.nodeid = nodeid; args.in_numargs = 1; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 9eb96e0564be..98ca64d1beb6 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -178,6 +178,7 @@ * * 7.33 * - add FUSE_HANDLE_KILLPRIV_V2, FUSE_WRITE_KILL_SUIDGID, FATTR_KILL_SUIDGID + * - add FUSE_OPEN_KILL_SUIDGID */ #ifndef _LINUX_FUSE_H @@ -444,6 +445,12 @@ struct fuse_file_lock { */ #define FUSE_ATTR_SUBMOUNT (1 << 0) +/** + * Open flags + * FUSE_OPEN_KILL_SUIDGID: Kill suid and sgid if executable + */ +#define FUSE_OPEN_KILL_SUIDGID (1 << 0) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -605,14 +612,14 @@ struct fuse_setattr_in { struct fuse_open_in { uint32_t flags; - uint32_t unused; + uint32_t open_flags; /* FUSE_OPEN_... */ }; struct fuse_create_in { uint32_t flags; uint32_t mode; uint32_t umask; - uint32_t padding; + uint32_t open_flags; /* FUSE_OPEN_... */ }; struct fuse_open_out { -- cgit v1.2.3 From c21d54f0307ff42a346294899107b570b98c47b5 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 29 Sep 2020 17:09:43 +0200 Subject: KVM: x86: hyper-v: allow KVM_GET_SUPPORTED_HV_CPUID as a system ioctl KVM_GET_SUPPORTED_HV_CPUID is a vCPU ioctl but its output is now independent from vCPU and in some cases VMMs may want to use it as a system ioctl instead. In particular, QEMU doesn CPU feature expansion before any vCPU gets created so KVM_GET_SUPPORTED_HV_CPUID can't be used. Convert KVM_GET_SUPPORTED_HV_CPUID to 'dual' system/vCPU ioctl with the same meaning. Signed-off-by: Vitaly Kuznetsov Message-Id: <20200929150944.1235688-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 16 ++++++++++----- arch/x86/kvm/hyperv.c | 6 +++--- arch/x86/kvm/hyperv.h | 4 ++-- arch/x86/kvm/vmx/evmcs.c | 3 +-- arch/x86/kvm/x86.c | 45 +++++++++++++++++++++++++----------------- include/uapi/linux/kvm.h | 3 ++- 6 files changed, 46 insertions(+), 31 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index e00a66d72372..81d54fe76a2d 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4455,9 +4455,9 @@ that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present. 4.118 KVM_GET_SUPPORTED_HV_CPUID -------------------------------- -:Capability: KVM_CAP_HYPERV_CPUID +:Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system) :Architectures: x86 -:Type: vcpu ioctl +:Type: system ioctl, vcpu ioctl :Parameters: struct kvm_cpuid2 (in/out) :Returns: 0 on success, -1 on error @@ -4502,9 +4502,6 @@ Currently, the following list of CPUID leaves are returned: - HYPERV_CPUID_SYNDBG_INTERFACE - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES -HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was -enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). - Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure with the 'nent' field indicating the number of entries in the variable-size array 'entries'. If the number of entries is too low to describe all Hyper-V @@ -4515,6 +4512,15 @@ number of valid entries in the 'entries' array, which is then filled. 'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved, userspace should not expect to get any particular value there. +Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike +system ioctl which exposes all supported feature bits unconditionally, vcpu +version has the following quirks: +- HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED + feature bit are only exposed when Enlightened VMCS was previously enabled + on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). +- HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC. + (presumes KVM_CREATE_IRQCHIP has already been called). + 4.119 KVM_ARM_VCPU_FINALIZE --------------------------- diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5c7c4060b45c..922c69dcca4d 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1951,8 +1951,8 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args) return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd); } -int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) { uint16_t evmcs_ver = 0; struct kvm_cpuid_entry2 cpuid_entries[] = { @@ -2037,7 +2037,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, * Direct Synthetic timers only make sense with in-kernel * LAPIC */ - if (lapic_in_kernel(vcpu)) + if (!vcpu || lapic_in_kernel(vcpu)) ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; break; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index e68c6c2e9649..6d7def2b0aad 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -126,7 +126,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); -int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); #endif diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index f3199bb02f22..41f24661af04 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -326,7 +326,6 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); /* * vmcs_version represents the range of supported Enlightened VMCS * versions: lower 8 bits is the minimal version, higher 8 bits is the @@ -334,7 +333,7 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) * KVM_EVMCS_VERSION. */ if (kvm_cpu_cap_get(X86_FEATURE_VMX) && - vmx->nested.enlightened_vmcs_enabled) + (!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled)) return (KVM_EVMCS_VERSION << 8) | 1; return 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2db86702cac4..773cb52cb775 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3677,6 +3677,27 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 __user *cpuid_arg) +{ + struct kvm_cpuid2 cpuid; + int r; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) + return r; + + r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries); + if (r) + return r; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) + return r; + + return 0; +} + int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r = 0; @@ -3713,6 +3734,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: + case KVM_CAP_SYS_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -3898,6 +3920,9 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; + case KVM_GET_SUPPORTED_HV_CPUID: + r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); + break; default: r = -EINVAL; break; @@ -4974,25 +4999,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } - case KVM_GET_SUPPORTED_HV_CPUID: { - struct kvm_cpuid2 __user *cpuid_arg = argp; - struct kvm_cpuid2 cpuid; - - r = -EFAULT; - if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) - goto out; - - r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid, - cpuid_arg->entries); - if (r) - goto out; - - r = -EFAULT; - if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) - goto out; - r = 0; + case KVM_GET_SUPPORTED_HV_CPUID: + r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; - } default: r = -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ca41220b40b8..204afbe1240e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1053,6 +1053,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_X86_USER_SPACE_MSR 188 #define KVM_CAP_X86_MSR_FILTER 189 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 +#define KVM_CAP_SYS_HYPERV_CPUID 191 #ifdef KVM_CAP_IRQ_ROUTING @@ -1511,7 +1512,7 @@ struct kvm_enc_region { /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */ #define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) -/* Available with KVM_CAP_HYPERV_CPUID */ +/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */ #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) /* Available with KVM_CAP_ARM_SVE */ -- cgit v1.2.3 From fb04a1eddb1a65b6588a021bdc132270d5ae48bb Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 30 Sep 2020 21:22:22 -0400 Subject: KVM: X86: Implement ring-based dirty memory tracking This patch is heavily based on previous work from Lei Cao and Paolo Bonzini . [1] KVM currently uses large bitmaps to track dirty memory. These bitmaps are copied to userspace when userspace queries KVM for its dirty page information. The use of bitmaps is mostly sufficient for live migration, as large parts of memory are be dirtied from one log-dirty pass to another. However, in a checkpointing system, the number of dirty pages is small and in fact it is often bounded---the VM is paused when it has dirtied a pre-defined number of pages. Traversing a large, sparsely populated bitmap to find set bits is time-consuming, as is copying the bitmap to user-space. A similar issue will be there for live migration when the guest memory is huge while the page dirty procedure is trivial. In that case for each dirty sync we need to pull the whole dirty bitmap to userspace and analyse every bit even if it's mostly zeros. The preferred data structure for above scenarios is a dense list of guest frame numbers (GFN). This patch series stores the dirty list in kernel memory that can be memory mapped into userspace to allow speedy harvesting. This patch enables dirty ring for X86 only. However it should be easily extended to other archs as well. [1] https://patchwork.kernel.org/patch/10471409/ Signed-off-by: Lei Cao Signed-off-by: Paolo Bonzini Signed-off-by: Peter Xu Message-Id: <20201001012222.5767-1-peterx@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 93 +++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 3 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/Makefile | 3 +- arch/x86/kvm/mmu/mmu.c | 8 ++ arch/x86/kvm/mmu/tdp_mmu.c | 2 +- arch/x86/kvm/vmx/vmx.c | 7 ++ arch/x86/kvm/x86.c | 9 ++ include/linux/kvm_dirty_ring.h | 103 +++++++++++++++++++++ include/linux/kvm_host.h | 13 +++ include/trace/events/kvm.h | 63 +++++++++++++ include/uapi/linux/kvm.h | 53 +++++++++++ virt/kvm/dirty_ring.c | 194 ++++++++++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 113 ++++++++++++++++++++++- 14 files changed, 662 insertions(+), 3 deletions(-) create mode 100644 include/linux/kvm_dirty_ring.h create mode 100644 virt/kvm/dirty_ring.c (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 81d54fe76a2d..e264ebc35e27 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -262,6 +262,18 @@ The KVM_RUN ioctl (cf.) communicates with userspace via a shared memory region. This ioctl returns the size of that region. See the KVM_RUN documentation for details. +Besides the size of the KVM_RUN communication region, other areas of +the VCPU file descriptor can be mmap-ed, including: + +- if KVM_CAP_COALESCED_MMIO is available, a page at + KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons, + this page is included in the result of KVM_GET_VCPU_MMAP_SIZE. + KVM_CAP_COALESCED_MMIO is not documented yet. + +- if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at + KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE. For more information on + KVM_CAP_DIRTY_LOG_RING, see section 8.3. + 4.6 KVM_SET_MEMORY_REGION ------------------------- @@ -6396,3 +6408,84 @@ When enabled, KVM will disable paravirtual features provided to the guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf (0x40000001). Otherwise, a guest may use the paravirtual features regardless of what has actually been exposed through the CPUID leaf. + + +8.29 KVM_CAP_DIRTY_LOG_RING +--------------------------- + +:Architectures: x86 +:Parameters: args[0] - size of the dirty log ring + +KVM is capable of tracking dirty memory using ring buffers that are +mmaped into userspace; there is one dirty ring per vcpu. + +The dirty ring is available to userspace as an array of +``struct kvm_dirty_gfn``. Each dirty entry it's defined as:: + + struct kvm_dirty_gfn { + __u32 flags; + __u32 slot; /* as_id | slot_id */ + __u64 offset; + }; + +The following values are defined for the flags field to define the +current state of the entry:: + + #define KVM_DIRTY_GFN_F_DIRTY BIT(0) + #define KVM_DIRTY_GFN_F_RESET BIT(1) + #define KVM_DIRTY_GFN_F_MASK 0x3 + +Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM +ioctl to enable this capability for the new guest and set the size of +the rings. Enabling the capability is only allowed before creating any +vCPU, and the size of the ring must be a power of two. The larger the +ring buffer, the less likely the ring is full and the VM is forced to +exit to userspace. The optimal size depends on the workload, but it is +recommended that it be at least 64 KiB (4096 entries). + +Just like for dirty page bitmaps, the buffer tracks writes to +all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was +set in KVM_SET_USER_MEMORY_REGION. Once a memory region is registered +with the flag set, userspace can start harvesting dirty pages from the +ring buffer. + +An entry in the ring buffer can be unused (flag bits ``00``), +dirty (flag bits ``01``) or harvested (flag bits ``1X``). The +state machine for the entry is as follows:: + + dirtied harvested reset + 00 -----------> 01 -------------> 1X -------+ + ^ | + | | + +------------------------------------------+ + +To harvest the dirty pages, userspace accesses the mmaped ring buffer +to read the dirty GFNs. If the flags has the DIRTY bit set (at this stage +the RESET bit must be cleared), then it means this GFN is a dirty GFN. +The userspace should harvest this GFN and mark the flags from state +``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set +to show that this GFN is harvested and waiting for a reset), and move +on to the next GFN. The userspace should continue to do this until the +flags of a GFN have the DIRTY bit cleared, meaning that it has harvested +all the dirty GFNs that were available. + +It's not necessary for userspace to harvest the all dirty GFNs at once. +However it must collect the dirty GFNs in sequence, i.e., the userspace +program cannot skip one dirty GFN to collect the one next to it. + +After processing one or more entries in the ring buffer, userspace +calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about +it, so that the kernel will reprotect those collected GFNs. +Therefore, the ioctl must be called *before* reading the content of +the dirty pages. + +The dirty ring can get full. When it happens, the KVM_RUN of the +vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL. + +The dirty ring interface has a major difference comparing to the +KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from +userspace, it's still possible that the kernel has not yet flushed the +processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the +flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one +needs to kick the vcpu out of KVM_RUN using a signal. The resulting +vmexit ensures that all dirty GFNs are flushed to the dirty rings. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 69e94aa716e9..f002cdb13a0b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1232,6 +1232,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); + int (*cpu_dirty_log_size)(void); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1744,4 +1745,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define GET_SMSTATE(type, buf, offset) \ (*(type *)((buf) + (offset) - 0x7e00)) +int kvm_cpu_dirty_log_size(void); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 89e5f3d1bba8..8e76d3701db3 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -12,6 +12,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 #define DE_VECTOR 0 #define DB_VECTOR 1 diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index b804444e16d4..4bd14ab01323 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -10,7 +10,8 @@ endif KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ + $(KVM)/dirty_ring.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 5bb1939b65d8..12e5cfe0995e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1289,6 +1289,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } +int kvm_cpu_dirty_log_size(void) +{ + if (kvm_x86_ops.cpu_dirty_log_size) + return kvm_x86_ops.cpu_dirty_log_size(); + + return 0; +} + bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn) { diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index ff28a5c6abd6..cffa51c6049e 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -185,7 +185,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, if ((!is_writable_pte(old_spte) || pfn_changed) && is_writable_pte(new_spte)) { slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn); - mark_page_dirty_in_slot(slot, gfn); + mark_page_dirty_in_slot(kvm, slot, gfn); } } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 46b32aa43811..2b6d538454a6 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7583,6 +7583,11 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit) return supported & BIT(bit); } +static int vmx_cpu_dirty_log_size(void) +{ + return enable_pml ? PML_ENTITY_NUM : 0; +} + static struct kvm_x86_ops vmx_x86_ops __initdata = { .hardware_unsetup = hardware_unsetup, @@ -7712,6 +7717,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .migrate_timers = vmx_migrate_timers, .msr_filter_changed = vmx_msr_filter_changed, + .cpu_dirty_log_size = vmx_cpu_dirty_log_size, }; static __init int hardware_setup(void) @@ -7829,6 +7835,7 @@ static __init int hardware_setup(void) vmx_x86_ops.slot_disable_log_dirty = NULL; vmx_x86_ops.flush_log_dirty = NULL; vmx_x86_ops.enable_log_dirty_pt_masked = NULL; + vmx_x86_ops.cpu_dirty_log_size = NULL; } if (!cpu_has_vmx_preemption_timer()) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b4ac726526f8..6c704a597b7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8754,6 +8754,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; + /* Forbid vmenter if vcpu dirty ring is soft-full */ + if (unlikely(vcpu->kvm->dirty_ring_size && + kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) { + vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; + trace_kvm_dirty_ring_exit(vcpu); + r = 0; + goto out; + } + if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h new file mode 100644 index 000000000000..120e5e90fa1d --- /dev/null +++ b/include/linux/kvm_dirty_ring.h @@ -0,0 +1,103 @@ +#ifndef KVM_DIRTY_RING_H +#define KVM_DIRTY_RING_H + +#include + +/** + * kvm_dirty_ring: KVM internal dirty ring structure + * + * @dirty_index: free running counter that points to the next slot in + * dirty_ring->dirty_gfns, where a new dirty page should go + * @reset_index: free running counter that points to the next dirty page + * in dirty_ring->dirty_gfns for which dirty trap needs to + * be reenabled + * @size: size of the compact list, dirty_ring->dirty_gfns + * @soft_limit: when the number of dirty pages in the list reaches this + * limit, vcpu that owns this ring should exit to userspace + * to allow userspace to harvest all the dirty pages + * @dirty_gfns: the array to keep the dirty gfns + * @index: index of this dirty ring + */ +struct kvm_dirty_ring { + u32 dirty_index; + u32 reset_index; + u32 size; + u32 soft_limit; + struct kvm_dirty_gfn *dirty_gfns; + int index; +}; + +#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +/* + * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * not be included as well, so define these nop functions for the arch. + */ +static inline u32 kvm_dirty_ring_get_rsvd_entries(void) +{ + return 0; +} + +static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, + int index, u32 size) +{ + return 0; +} + +static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) +{ + return NULL; +} + +static inline int kvm_dirty_ring_reset(struct kvm *kvm, + struct kvm_dirty_ring *ring) +{ + return 0; +} + +static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, + u32 slot, u64 offset) +{ +} + +static inline struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, + u32 offset) +{ + return NULL; +} + +static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) +{ +} + +static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) +{ + return true; +} + +#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ + +u32 kvm_dirty_ring_get_rsvd_entries(void); +int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); +struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm); + +/* + * called with kvm->slots_lock held, returns the number of + * processed pages. + */ +int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring); + +/* + * returns =0: successfully pushed + * <0: unable to push, need to wait + */ +void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset); + +/* for use in vm_operations_struct */ +struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); + +void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); +bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); + +#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ + +#endif /* KVM_DIRTY_RING_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ca7c1459a8e3..864b156391c8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -34,6 +34,7 @@ #include #include +#include #ifndef KVM_MAX_VCPU_ID #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS @@ -319,6 +320,7 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; + struct kvm_dirty_ring dirty_ring; }; static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) @@ -505,6 +507,7 @@ struct kvm { struct srcu_struct irq_srcu; pid_t userspace_pid; unsigned int max_halt_poll_ns; + u32 dirty_ring_size; }; #define kvm_err(fmt, ...) \ @@ -1477,4 +1480,14 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ +/* + * This defines how many reserved entries we want to keep before we + * kick the vcpu to the userspace to avoid dirty ring full. This + * value can be tuned to higher if e.g. PML is enabled on the host. + */ +#define KVM_DIRTY_RING_RSVD_ENTRIES 64 + +/* Max number of entries allowed for each kvm dirty ring */ +#define KVM_DIRTY_RING_MAX_ENTRIES 65536 + #endif diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 26cfb0fa8e7e..49d7d0fe29f6 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -399,6 +399,69 @@ TRACE_EVENT(kvm_halt_poll_ns, #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \ trace_kvm_halt_poll_ns(false, vcpu_id, new, old) +TRACE_EVENT(kvm_dirty_ring_push, + TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset), + TP_ARGS(ring, slot, offset), + + TP_STRUCT__entry( + __field(int, index) + __field(u32, dirty_index) + __field(u32, reset_index) + __field(u32, slot) + __field(u64, offset) + ), + + TP_fast_assign( + __entry->index = ring->index; + __entry->dirty_index = ring->dirty_index; + __entry->reset_index = ring->reset_index; + __entry->slot = slot; + __entry->offset = offset; + ), + + TP_printk("ring %d: dirty 0x%x reset 0x%x " + "slot %u offset 0x%llx (used %u)", + __entry->index, __entry->dirty_index, + __entry->reset_index, __entry->slot, __entry->offset, + __entry->dirty_index - __entry->reset_index) +); + +TRACE_EVENT(kvm_dirty_ring_reset, + TP_PROTO(struct kvm_dirty_ring *ring), + TP_ARGS(ring), + + TP_STRUCT__entry( + __field(int, index) + __field(u32, dirty_index) + __field(u32, reset_index) + ), + + TP_fast_assign( + __entry->index = ring->index; + __entry->dirty_index = ring->dirty_index; + __entry->reset_index = ring->reset_index; + ), + + TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)", + __entry->index, __entry->dirty_index, __entry->reset_index, + __entry->dirty_index - __entry->reset_index) +); + +TRACE_EVENT(kvm_dirty_ring_exit, + TP_PROTO(struct kvm_vcpu *vcpu), + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(int, vcpu_id) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + ), + + TP_printk("vcpu %d", __entry->vcpu_id) +); + #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 204afbe1240e..886802b8ffba 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -250,6 +250,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_ARM_NISV 28 #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 +#define KVM_EXIT_DIRTY_RING_FULL 31 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -1054,6 +1055,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_X86_MSR_FILTER 189 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #define KVM_CAP_SYS_HYPERV_CPUID 191 +#define KVM_CAP_DIRTY_LOG_RING 192 #ifdef KVM_CAP_IRQ_ROUTING @@ -1558,6 +1560,9 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_X86_MSR_FILTER */ #define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter) +/* Available with KVM_CAP_DIRTY_LOG_RING */ +#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1711,4 +1716,52 @@ struct kvm_hyperv_eventfd { #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) +/* + * Arch needs to define the macro after implementing the dirty ring + * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the + * starting page offset of the dirty ring structures. + */ +#ifndef KVM_DIRTY_LOG_PAGE_OFFSET +#define KVM_DIRTY_LOG_PAGE_OFFSET 0 +#endif + +/* + * KVM dirty GFN flags, defined as: + * + * |---------------+---------------+--------------| + * | bit 1 (reset) | bit 0 (dirty) | Status | + * |---------------+---------------+--------------| + * | 0 | 0 | Invalid GFN | + * | 0 | 1 | Dirty GFN | + * | 1 | X | GFN to reset | + * |---------------+---------------+--------------| + * + * Lifecycle of a dirty GFN goes like: + * + * dirtied harvested reset + * 00 -----------> 01 -------------> 1X -------+ + * ^ | + * | | + * +------------------------------------------+ + * + * The userspace program is only responsible for the 01->1X state + * conversion after harvesting an entry. Also, it must not skip any + * dirty bits, so that dirty bits are always harvested in sequence. + */ +#define KVM_DIRTY_GFN_F_DIRTY BIT(0) +#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_MASK 0x3 + +/* + * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of + * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The + * size of the gfn buffer is decided by the first argument when + * enabling KVM_CAP_DIRTY_LOG_RING. + */ +struct kvm_dirty_gfn { + __u32 flags; + __u32 slot; + __u64 offset; +}; + #endif /* __LINUX_KVM_H */ diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c new file mode 100644 index 000000000000..9d01299563ee --- /dev/null +++ b/virt/kvm/dirty_ring.c @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * KVM dirty ring implementation + * + * Copyright 2019 Red Hat, Inc. + */ +#include +#include +#include +#include +#include + +int __weak kvm_cpu_dirty_log_size(void) +{ + return 0; +} + +u32 kvm_dirty_ring_get_rsvd_entries(void) +{ + return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(); +} + +static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) +{ + return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); +} + +bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) +{ + return kvm_dirty_ring_used(ring) >= ring->soft_limit; +} + +static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring) +{ + return kvm_dirty_ring_used(ring) >= ring->size; +} + +struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + + WARN_ON_ONCE(vcpu->kvm != kvm); + + return &vcpu->dirty_ring; +} + +static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) +{ + struct kvm_memory_slot *memslot; + int as_id, id; + + as_id = slot >> 16; + id = (u16)slot; + + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) + return; + + memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); + + if (!memslot || (offset + __fls(mask)) >= memslot->npages) + return; + + spin_lock(&kvm->mmu_lock); + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); + spin_unlock(&kvm->mmu_lock); +} + +int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size) +{ + ring->dirty_gfns = vmalloc(size); + if (!ring->dirty_gfns) + return -ENOMEM; + memset(ring->dirty_gfns, 0, size); + + ring->size = size / sizeof(struct kvm_dirty_gfn); + ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries(); + ring->dirty_index = 0; + ring->reset_index = 0; + ring->index = index; + + return 0; +} + +static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = 0; +} + +static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_DIRTY; +} + +static inline bool kvm_dirty_gfn_invalid(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags == 0; +} + +static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags & KVM_DIRTY_GFN_F_RESET; +} + +int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) +{ + u32 cur_slot, next_slot; + u64 cur_offset, next_offset; + unsigned long mask; + int count = 0; + struct kvm_dirty_gfn *entry; + bool first_round = true; + + /* This is only needed to make compilers happy */ + cur_slot = cur_offset = mask = 0; + + while (true) { + entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)]; + + if (!kvm_dirty_gfn_harvested(entry)) + break; + + next_slot = READ_ONCE(entry->slot); + next_offset = READ_ONCE(entry->offset); + + /* Update the flags to reflect that this GFN is reset */ + kvm_dirty_gfn_set_invalid(entry); + + ring->reset_index++; + count++; + /* + * Try to coalesce the reset operations when the guest is + * scanning pages in the same slot. + */ + if (!first_round && next_slot == cur_slot) { + s64 delta = next_offset - cur_offset; + + if (delta >= 0 && delta < BITS_PER_LONG) { + mask |= 1ull << delta; + continue; + } + + /* Backwards visit, careful about overflows! */ + if (delta > -BITS_PER_LONG && delta < 0 && + (mask << -delta >> -delta) == mask) { + cur_offset = next_offset; + mask = (mask << -delta) | 1; + continue; + } + } + kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); + cur_slot = next_slot; + cur_offset = next_offset; + mask = 1; + first_round = false; + } + + kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); + + trace_kvm_dirty_ring_reset(ring); + + return count; +} + +void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset) +{ + struct kvm_dirty_gfn *entry; + + /* It should never get full */ + WARN_ON_ONCE(kvm_dirty_ring_full(ring)); + + entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)]; + + entry->slot = slot; + entry->offset = offset; + /* + * Make sure the data is filled in before we publish this to + * the userspace program. There's no paired kernel-side reader. + */ + smp_wmb(); + kvm_dirty_gfn_set_dirtied(entry); + ring->dirty_index++; + trace_kvm_dirty_ring_push(ring, slot, offset); +} + +struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset) +{ + return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE); +} + +void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) +{ + vfree(ring->dirty_gfns); + ring->dirty_gfns = NULL; +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 68598fdba226..78ef414512bf 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -63,6 +63,8 @@ #define CREATE_TRACE_POINTS #include +#include + /* Worst case buffer size needed for holding an integer. */ #define ITOA_MAX_LEN 12 @@ -415,6 +417,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { + kvm_dirty_ring_free(&vcpu->dirty_ring); kvm_arch_vcpu_destroy(vcpu); /* @@ -2644,8 +2647,13 @@ void mark_page_dirty_in_slot(struct kvm *kvm, { if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; + u32 slot = (memslot->as_id << 16) | memslot->id; - set_bit_le(rel_gfn, memslot->dirty_bitmap); + if (kvm->dirty_ring_size) + kvm_dirty_ring_push(kvm_dirty_ring_get(kvm), + slot, rel_gfn); + else + set_bit_le(rel_gfn, memslot->dirty_bitmap); } } EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot); @@ -3005,6 +3013,17 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); +static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) +{ +#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 + return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && + (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + + kvm->dirty_ring_size / PAGE_SIZE); +#else + return false; +#endif +} + static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; @@ -3020,6 +3039,10 @@ static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif + else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff)) + page = kvm_dirty_ring_get_page( + &vcpu->dirty_ring, + vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET); else return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); @@ -3033,6 +3056,14 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = { static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { + struct kvm_vcpu *vcpu = file->private_data; + unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + + if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || + kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && + ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED))) + return -EINVAL; + vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } @@ -3126,6 +3157,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) if (r) goto vcpu_free_run_page; + if (kvm->dirty_ring_size) { + r = kvm_dirty_ring_alloc(&vcpu->dirty_ring, + id, kvm->dirty_ring_size); + if (r) + goto arch_vcpu_destroy; + } + mutex_lock(&kvm->lock); if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; @@ -3159,6 +3197,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) unlock_vcpu_destroy: mutex_unlock(&kvm->lock); + kvm_dirty_ring_free(&vcpu->dirty_ring); +arch_vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); vcpu_free_run_page: free_page((unsigned long)vcpu->run); @@ -3631,12 +3671,78 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #endif case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; + case KVM_CAP_DIRTY_LOG_RING: +#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 + return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); +#else + return 0; +#endif default: break; } return kvm_vm_ioctl_check_extension(kvm, arg); } +static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) +{ + int r; + + if (!KVM_DIRTY_LOG_PAGE_OFFSET) + return -EINVAL; + + /* the size should be power of 2 */ + if (!size || (size & (size - 1))) + return -EINVAL; + + /* Should be bigger to keep the reserved entries, or a page */ + if (size < kvm_dirty_ring_get_rsvd_entries() * + sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE) + return -EINVAL; + + if (size > KVM_DIRTY_RING_MAX_ENTRIES * + sizeof(struct kvm_dirty_gfn)) + return -E2BIG; + + /* We only allow it to set once */ + if (kvm->dirty_ring_size) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (kvm->created_vcpus) { + /* We don't allow to change this value after vcpu created */ + r = -EINVAL; + } else { + kvm->dirty_ring_size = size; + r = 0; + } + + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) +{ + int i; + struct kvm_vcpu *vcpu; + int cleared = 0; + + if (!kvm->dirty_ring_size) + return -EINVAL; + + mutex_lock(&kvm->slots_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) + cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring); + + mutex_unlock(&kvm->slots_lock); + + if (cleared) + kvm_flush_remote_tlbs(kvm); + + return cleared; +} + int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -3667,6 +3773,8 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, kvm->max_halt_poll_ns = cap->args[0]; return 0; } + case KVM_CAP_DIRTY_LOG_RING: + return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); default: return kvm_vm_ioctl_enable_cap(kvm, cap); } @@ -3851,6 +3959,9 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(kvm, arg); break; + case KVM_RESET_DIRTY_RINGS: + r = kvm_vm_ioctl_reset_dirty_pages(kvm); + break; default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } -- cgit v1.2.3 From c12096085b623024416d02db435005cdf79a71bb Mon Sep 17 00:00:00 2001 From: Anthoine Bourgeois Date: Wed, 18 Nov 2020 17:08:07 -0800 Subject: virtio-gpu api: Add a comment on VIRTIO_GPU_SHM_ID_HOST_VISIBLE This provides a description of how the kernel driver uses the shmid to determine capabilities. Signed-off-by: Anthoine Bourgeois Link: http://patchwork.freedesktop.org/patch/msgid/20201119010809.528-3-gurchetansingh@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/linux/virtio_gpu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 0ec6b610402c..97523a95781d 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -115,6 +115,10 @@ enum virtio_gpu_ctrl_type { enum virtio_gpu_shm_id { VIRTIO_GPU_SHM_ID_UNDEFINED = 0, + /* + * VIRTIO_GPU_CMD_RESOURCE_MAP_BLOB + * VIRTIO_GPU_CMD_RESOURCE_UNMAP_BLOB + */ VIRTIO_GPU_SHM_ID_HOST_VISIBLE = 1 }; -- cgit v1.2.3 From e1e8debec6564d0c355aab84c93de8e357f397bd Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Fri, 30 Oct 2020 13:10:35 +0900 Subject: f2fs: add F2FS_IOC_SET_COMPRESS_OPTION ioctl Added a new F2FS_IOC_SET_COMPRESS_OPTION ioctl to change file compression option of a file. struct f2fs_comp_option { u8 algorithm; => compression algorithm => 0:lzo, 1:lz4, 2:zstd, 3:lzorle u8 log_cluster_size; => log scale cluster size => 2 ~ 8 }; struct f2fs_comp_option option; option.algorithm = 1; option.log_cluster_size = 7; ioctl(fd, F2FS_IOC_SET_COMPRESS_OPTION, &option); Signed-off-by: Daeho Jeong [Chao Yu: remove f2fs_is_compress_algorithm_valid()] Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/f2fs.h | 2 ++ 2 files changed, 56 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index c747f5dd595c..ea2f1ba408c4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3972,6 +3972,57 @@ static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg) return 0; } +static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_comp_option option; + int ret = 0; + + if (!f2fs_sb_has_compression(sbi)) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&option, (struct f2fs_comp_option __user *)arg, + sizeof(option))) + return -EFAULT; + + if (!f2fs_compressed_file(inode) || + option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) + return -EINVAL; + + file_start_write(filp); + inode_lock(inode); + + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { + ret = -EBUSY; + goto out; + } + + if (inode->i_size != 0) { + ret = -EFBIG; + goto out; + } + + F2FS_I(inode)->i_compress_algorithm = option.algorithm; + F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size; + F2FS_I(inode)->i_cluster_size = 1 << option.log_cluster_size; + f2fs_mark_inode_dirty_sync(inode, true); + + if (!f2fs_is_compress_backend_ready(inode)) + f2fs_warn(sbi, "compression algorithm is successfully set, " + "but current kernel doesn't support this algorithm."); +out: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) @@ -4062,6 +4113,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_sec_trim_file(filp, arg); case F2FS_IOC_GET_COMPRESS_OPTION: return f2fs_ioc_get_compress_option(filp, arg); + case F2FS_IOC_SET_COMPRESS_OPTION: + return f2fs_ioc_set_compress_option(filp, arg); default: return -ENOTTY; } @@ -4233,6 +4286,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: case F2FS_IOC_SEC_TRIM_FILE: case F2FS_IOC_GET_COMPRESS_OPTION: + case F2FS_IOC_SET_COMPRESS_OPTION: break; default: return -ENOIOCTLCMD; diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h index 872e61d78f29..f00199a2e38b 100644 --- a/include/uapi/linux/f2fs.h +++ b/include/uapi/linux/f2fs.h @@ -38,6 +38,8 @@ struct f2fs_sectrim_range) #define F2FS_IOC_GET_COMPRESS_OPTION _IOR(F2FS_IOCTL_MAGIC, 21, \ struct f2fs_comp_option) +#define F2FS_IOC_SET_COMPRESS_OPTION _IOW(F2FS_IOCTL_MAGIC, 22, \ + struct f2fs_comp_option) /* * should be same as XFS_IOC_GOINGDOWN. -- cgit v1.2.3 From 5fdb322ff2c2b4ad519f490dcb7ebb96c5439af7 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Thu, 3 Dec 2020 15:56:15 +0900 Subject: f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE Added two ioctl to decompress/compress explicitly the compression enabled file in "compress_mode=user" mount option. Using these two ioctls, the users can make a control of compression and decompression of their files. Signed-off-by: Daeho Jeong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 185 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/f2fs.h | 2 + 2 files changed, 187 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8241b8bdb33c..16ea10f2bcf5 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4026,6 +4026,185 @@ out: return ret; } +static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) +{ + DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, page_idx); + struct address_space *mapping = inode->i_mapping; + struct page *page; + pgoff_t redirty_idx = page_idx; + int i, page_len = 0, ret = 0; + + page_cache_ra_unbounded(&ractl, len, 0); + + for (i = 0; i < len; i++, page_idx++) { + page = read_cache_page(mapping, page_idx, NULL, NULL); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + break; + } + page_len++; + } + + for (i = 0; i < page_len; i++, redirty_idx++) { + page = find_lock_page(mapping, redirty_idx); + if (!page) + ret = -ENOENT; + set_page_dirty(page); + f2fs_put_page(page, 1); + f2fs_put_page(page, 0); + } + + return ret; +} + +static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int blk_per_seg = sbi->blocks_per_seg; + int cluster_size = F2FS_I(inode)->i_cluster_size; + int count, ret; + + if (!f2fs_sb_has_compression(sbi) || + F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + f2fs_balance_fs(F2FS_I_SB(inode), true); + + file_start_write(filp); + inode_lock(inode); + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (f2fs_is_mmap_file(inode)) { + ret = -EBUSY; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + if (!atomic_read(&fi->i_compr_blocks)) + goto out; + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + count = last_idx - page_idx; + while (count) { + int len = min(cluster_size, count); + + ret = redirty_blocks(inode, page_idx, len); + if (ret < 0) + break; + + if (get_dirty_pages(inode) >= blk_per_seg) + filemap_fdatawrite(inode->i_mapping); + + count -= len; + page_idx += len; + } + + if (!ret) + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + LLONG_MAX); + + if (ret) + f2fs_warn(sbi, "%s: The file might be partially decompressed " + "(errno=%d). Please delete the file.\n", + __func__, ret); +out: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + +static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int blk_per_seg = sbi->blocks_per_seg; + int cluster_size = F2FS_I(inode)->i_cluster_size; + int count, ret; + + if (!f2fs_sb_has_compression(sbi) || + F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + f2fs_balance_fs(F2FS_I_SB(inode), true); + + file_start_write(filp); + inode_lock(inode); + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (f2fs_is_mmap_file(inode)) { + ret = -EBUSY; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + set_inode_flag(inode, FI_ENABLE_COMPRESS); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + count = last_idx - page_idx; + while (count) { + int len = min(cluster_size, count); + + ret = redirty_blocks(inode, page_idx, len); + if (ret < 0) + break; + + if (get_dirty_pages(inode) >= blk_per_seg) + filemap_fdatawrite(inode->i_mapping); + + count -= len; + page_idx += len; + } + + if (!ret) + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + LLONG_MAX); + + clear_inode_flag(inode, FI_ENABLE_COMPRESS); + + if (ret) + f2fs_warn(sbi, "%s: The file might be partially compressed " + "(errno=%d). Please delete the file.\n", + __func__, ret); +out: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { @@ -4113,6 +4292,10 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_get_compress_option(filp, arg); case F2FS_IOC_SET_COMPRESS_OPTION: return f2fs_ioc_set_compress_option(filp, arg); + case F2FS_IOC_DECOMPRESS_FILE: + return f2fs_ioc_decompress_file(filp, arg); + case F2FS_IOC_COMPRESS_FILE: + return f2fs_ioc_compress_file(filp, arg); default: return -ENOTTY; } @@ -4352,6 +4535,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_SEC_TRIM_FILE: case F2FS_IOC_GET_COMPRESS_OPTION: case F2FS_IOC_SET_COMPRESS_OPTION: + case F2FS_IOC_DECOMPRESS_FILE: + case F2FS_IOC_COMPRESS_FILE: break; default: return -ENOIOCTLCMD; diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h index f00199a2e38b..352a822d4370 100644 --- a/include/uapi/linux/f2fs.h +++ b/include/uapi/linux/f2fs.h @@ -40,6 +40,8 @@ struct f2fs_comp_option) #define F2FS_IOC_SET_COMPRESS_OPTION _IOW(F2FS_IOCTL_MAGIC, 22, \ struct f2fs_comp_option) +#define F2FS_IOC_DECOMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 23) +#define F2FS_IOC_COMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 24) /* * should be same as XFS_IOC_GOINGDOWN. -- cgit v1.2.3 From bccce80bbd44ab50bbec761a51c6293c1ce47e34 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Thu, 3 Dec 2020 22:35:12 +0100 Subject: vfio-ccw: Wire in the request callback The device is being unplugged, so pass the request to userspace to ask for a graceful cleanup. This should free up the thread that would otherwise loop waiting for the device to be fully released. Signed-off-by: Eric Farman Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/s390/cio/vfio_ccw_ops.c | 26 ++++++++++++++++++++++++++ drivers/s390/cio/vfio_ccw_private.h | 4 ++++ include/uapi/linux/vfio.h | 1 + 3 files changed, 31 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 8b3ed5b45277..68106be4ba7a 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -394,6 +394,7 @@ static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info) switch (info->index) { case VFIO_CCW_IO_IRQ_INDEX: case VFIO_CCW_CRW_IRQ_INDEX: + case VFIO_CCW_REQ_IRQ_INDEX: info->count = 1; info->flags = VFIO_IRQ_INFO_EVENTFD; break; @@ -424,6 +425,9 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev, case VFIO_CCW_CRW_IRQ_INDEX: ctx = &private->crw_trigger; break; + case VFIO_CCW_REQ_IRQ_INDEX: + ctx = &private->req_trigger; + break; default: return -EINVAL; } @@ -607,6 +611,27 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev, } } +/* Request removal of the device*/ +static void vfio_ccw_mdev_request(struct mdev_device *mdev, unsigned int count) +{ + struct vfio_ccw_private *private = dev_get_drvdata(mdev_parent_dev(mdev)); + + if (!private) + return; + + if (private->req_trigger) { + if (!(count % 10)) + dev_notice_ratelimited(mdev_dev(private->mdev), + "Relaying device request to user (#%u)\n", + count); + + eventfd_signal(private->req_trigger, 1); + } else if (count == 0) { + dev_notice(mdev_dev(private->mdev), + "No device request channel registered, blocked until released by user\n"); + } +} + static const struct mdev_parent_ops vfio_ccw_mdev_ops = { .owner = THIS_MODULE, .supported_type_groups = mdev_type_groups, @@ -617,6 +642,7 @@ static const struct mdev_parent_ops vfio_ccw_mdev_ops = { .read = vfio_ccw_mdev_read, .write = vfio_ccw_mdev_write, .ioctl = vfio_ccw_mdev_ioctl, + .request = vfio_ccw_mdev_request, }; int vfio_ccw_mdev_reg(struct subchannel *sch) diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index 8723156b29ea..b2c762eb42b9 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -84,7 +84,10 @@ struct vfio_ccw_crw { * @irb: irb info received from interrupt * @scsw: scsw info * @io_trigger: eventfd ctx for signaling userspace I/O results + * @crw_trigger: eventfd ctx for signaling userspace CRW information + * @req_trigger: eventfd ctx for signaling userspace to return device * @io_work: work for deferral process of I/O handling + * @crw_work: work for deferral process of CRW handling */ struct vfio_ccw_private { struct subchannel *sch; @@ -108,6 +111,7 @@ struct vfio_ccw_private { struct eventfd_ctx *io_trigger; struct eventfd_ctx *crw_trigger; + struct eventfd_ctx *req_trigger; struct work_struct io_work; struct work_struct crw_work; } __aligned(8); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 2f313a238a8f..d1812777139f 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -820,6 +820,7 @@ enum { enum { VFIO_CCW_IO_IRQ_INDEX, VFIO_CCW_CRW_IRQ_INDEX, + VFIO_CCW_REQ_IRQ_INDEX, VFIO_CCW_NUM_IRQS }; -- cgit v1.2.3 From 26d060e47e25f2c715a1b2c48fea391f67907a30 Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Thu, 15 Oct 2020 07:11:56 +0800 Subject: gpiolib: cdev: allow edge event timestamps to be configured as REALTIME Using CLOCK_REALTIME as the source for event timestamps is crucial for some specific applications, particularly those requiring timetamps relative to a PTP clock, so provide an option to switch the event timestamp source from the default CLOCK_MONOTONIC to CLOCK_REALTIME. Note that CLOCK_REALTIME was the default source clock for GPIO until Linux 5.7 when it was changed to CLOCK_MONOTONIC due to issues with the shifting of the realtime clock. Providing this option maintains the CLOCK_MONOTONIC as the default, while also providing a path forward for those dependent on the pre-5.7 behaviour. Suggested-by: Jack Winch Signed-off-by: Kent Gibson Link: https://lore.kernel.org/r/20201014231158.34117-2-warthog618@gmail.com Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib-cdev.c | 21 ++++++++++++++++++--- drivers/gpio/gpiolib.h | 1 + include/uapi/linux/gpio.h | 12 +++++++++--- 3 files changed, 28 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 192721f829a3..f64a35767434 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -509,6 +509,7 @@ struct linereq { GPIO_V2_LINE_DIRECTION_FLAGS | \ GPIO_V2_LINE_DRIVE_FLAGS | \ GPIO_V2_LINE_EDGE_FLAGS | \ + GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME | \ GPIO_V2_LINE_BIAS_FLAGS) static void linereq_put_event(struct linereq *lr, @@ -529,6 +530,14 @@ static void linereq_put_event(struct linereq *lr, pr_debug_ratelimited("event FIFO is full - event dropped\n"); } +static u64 line_event_timestamp(struct line *line) +{ + if (test_bit(FLAG_EVENT_CLOCK_REALTIME, &line->desc->flags)) + return ktime_get_real_ns(); + + return ktime_get_ns(); +} + static irqreturn_t edge_irq_thread(int irq, void *p) { struct line *line = p; @@ -546,7 +555,7 @@ static irqreturn_t edge_irq_thread(int irq, void *p) * which case we didn't get the timestamp from * edge_irq_handler(). */ - le.timestamp_ns = ktime_get_ns(); + le.timestamp_ns = line_event_timestamp(line); if (lr->num_lines != 1) line->req_seqno = atomic_inc_return(&lr->seqno); } @@ -590,7 +599,7 @@ static irqreturn_t edge_irq_handler(int irq, void *p) * Just store the timestamp in hardirq context so we get it as * close in time as possible to the actual event. */ - line->timestamp_ns = ktime_get_ns(); + line->timestamp_ns = line_event_timestamp(line); if (lr->num_lines != 1) line->req_seqno = atomic_inc_return(&lr->seqno); @@ -663,7 +672,7 @@ static void debounce_work_func(struct work_struct *work) memset(&le, 0, sizeof(le)); lr = line->req; - le.timestamp_ns = ktime_get_ns(); + le.timestamp_ns = line_event_timestamp(line); le.offset = gpio_chip_hwgpio(line->desc); line->line_seqno++; le.line_seqno = line->line_seqno; @@ -967,6 +976,9 @@ static void gpio_v2_line_config_flags_to_desc_flags(u64 flags, flags & GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN); assign_bit(FLAG_BIAS_DISABLE, flagsp, flags & GPIO_V2_LINE_FLAG_BIAS_DISABLED); + + assign_bit(FLAG_EVENT_CLOCK_REALTIME, flagsp, + flags & GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME); } static long linereq_get_values(struct linereq *lr, void __user *ip) @@ -1930,6 +1942,9 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, if (test_bit(FLAG_EDGE_FALLING, &desc->flags)) info->flags |= GPIO_V2_LINE_FLAG_EDGE_FALLING; + if (test_bit(FLAG_EVENT_CLOCK_REALTIME, &desc->flags)) + info->flags |= GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME; + debounce_period_us = READ_ONCE(desc->debounce_period_us); if (debounce_period_us) { info->attrs[num_attrs].id = GPIO_V2_LINE_ATTR_ID_DEBOUNCE; diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index 42d81454da21..9c32d4ace572 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -116,6 +116,7 @@ struct gpio_desc { #define FLAG_BIAS_DISABLE 15 /* GPIO has pull disabled */ #define FLAG_EDGE_RISING 16 /* GPIO CDEV detects rising edge events */ #define FLAG_EDGE_FALLING 17 /* GPIO CDEV detects falling edge events */ +#define FLAG_EVENT_CLOCK_REALTIME 18 /* GPIO CDEV reports REALTIME timestamps in events */ /* Connection label */ const char *label; diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 2072c260f5d0..e4eb0b8c5cf9 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -65,6 +65,7 @@ struct gpiochip_info { * @GPIO_V2_LINE_FLAG_BIAS_PULL_UP: line has pull-up bias enabled * @GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN: line has pull-down bias enabled * @GPIO_V2_LINE_FLAG_BIAS_DISABLED: line has bias disabled + * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME: line events contain REALTIME timestamps */ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_USED = _BITULL(0), @@ -78,6 +79,7 @@ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_BIAS_PULL_UP = _BITULL(8), GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN = _BITULL(9), GPIO_V2_LINE_FLAG_BIAS_DISABLED = _BITULL(10), + GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME = _BITULL(11), }; /** @@ -270,9 +272,6 @@ enum gpio_v2_line_event_id { /** * struct gpio_v2_line_event - The actual event being pushed to userspace * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds. - * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow - * the accurate measurement of the time between events. It does not provide - * the wall-clock time. * @id: event identifier with value from &enum gpio_v2_line_event_id * @offset: the offset of the line that triggered the event * @seqno: the sequence number for this event in the sequence of events for @@ -280,6 +279,13 @@ enum gpio_v2_line_event_id { * @line_seqno: the sequence number for this event in the sequence of * events on this particular line * @padding: reserved for future use + * + * By default the @timestamp_ns is read from %CLOCK_MONOTONIC and is + * intended to allow the accurate measurement of the time between events. + * It does not provide the wall-clock time. + * + * If the %GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME flag is set then the + * @timestamp_ns is read from %CLOCK_REALTIME. */ struct gpio_v2_line_event { __aligned_u64 timestamp_ns; -- cgit v1.2.3 From f25b463883a8a2d1b7303a63339c0d589fc94f1e Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 17 Nov 2020 13:39:14 -0700 Subject: dmaengine: idxd: add IAX configuration support in the IDXD driver Add support to allow configuration of Intel Analytics Accelerator (IAX) in addition to the Intel Data Streaming Accelerator (DSA). The IAX hardware has the same configuration interface as DSA. The main difference is the type of operations it performs. We can support the DSA and IAX devices on the same driver with some tweaks. IAX has a 64B completion record that needs to be 64B aligned, as opposed to a 32B completion record that is 32B aligned for DSA. IAX also does not support token management. Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/160564555488.1834439.4261958859935360473.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 1 + drivers/dma/idxd/device.c | 37 ++++++++++++++++----- drivers/dma/idxd/idxd.h | 24 +++++++++++--- drivers/dma/idxd/init.c | 14 ++++++++ drivers/dma/idxd/registers.h | 1 + drivers/dma/idxd/submit.c | 2 +- drivers/dma/idxd/sysfs.c | 46 ++++++++++++++++++++++++-- include/uapi/linux/idxd.h | 79 ++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 187 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 010b820d8f74..0db9b82ed8cf 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -28,6 +28,7 @@ struct idxd_cdev_context { */ static struct idxd_cdev_context ictx[IDXD_TYPE_MAX] = { { .name = "dsa" }, + { .name = "iax" } }; struct idxd_user_context { diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index b75f9a09666e..47ff8e387172 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -131,6 +131,8 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) struct idxd_device *idxd = wq->idxd; struct device *dev = &idxd->pdev->dev; int rc, num_descs, i; + int align; + u64 tmp; if (wq->type != IDXD_WQT_KERNEL) return 0; @@ -142,14 +144,27 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) if (rc < 0) return rc; - wq->compls_size = num_descs * sizeof(struct dsa_completion_record); - wq->compls = dma_alloc_coherent(dev, wq->compls_size, - &wq->compls_addr, GFP_KERNEL); - if (!wq->compls) { + if (idxd->type == IDXD_TYPE_DSA) + align = 32; + else if (idxd->type == IDXD_TYPE_IAX) + align = 64; + else + return -ENODEV; + + wq->compls_size = num_descs * idxd->compl_size + align; + wq->compls_raw = dma_alloc_coherent(dev, wq->compls_size, + &wq->compls_addr_raw, GFP_KERNEL); + if (!wq->compls_raw) { rc = -ENOMEM; goto fail_alloc_compls; } + /* Adjust alignment */ + wq->compls_addr = (wq->compls_addr_raw + (align - 1)) & ~(align - 1); + tmp = (u64)wq->compls_raw; + tmp = (tmp + (align - 1)) & ~(align - 1); + wq->compls = (struct dsa_completion_record *)tmp; + rc = alloc_descs(wq, num_descs); if (rc < 0) goto fail_alloc_descs; @@ -163,9 +178,11 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) struct idxd_desc *desc = wq->descs[i]; desc->hw = wq->hw_descs[i]; - desc->completion = &wq->compls[i]; - desc->compl_dma = wq->compls_addr + - sizeof(struct dsa_completion_record) * i; + if (idxd->type == IDXD_TYPE_DSA) + desc->completion = &wq->compls[i]; + else if (idxd->type == IDXD_TYPE_IAX) + desc->iax_completion = &wq->iax_compls[i]; + desc->compl_dma = wq->compls_addr + idxd->compl_size * i; desc->id = i; desc->wq = wq; desc->cpu = -1; @@ -178,7 +195,8 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) fail_sbitmap_init: free_descs(wq); fail_alloc_descs: - dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); + dma_free_coherent(dev, wq->compls_size, wq->compls_raw, + wq->compls_addr_raw); fail_alloc_compls: free_hw_descs(wq); return rc; @@ -193,7 +211,8 @@ void idxd_wq_free_resources(struct idxd_wq *wq) free_hw_descs(wq); free_descs(wq); - dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); + dma_free_coherent(dev, wq->compls_size, wq->compls_raw, + wq->compls_addr_raw); sbitmap_queue_free(&wq->sbq); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 149934f8d097..5a50e91c71bf 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -20,7 +20,8 @@ extern struct kmem_cache *idxd_desc_pool; enum idxd_type { IDXD_TYPE_UNKNOWN = -1, IDXD_TYPE_DSA = 0, - IDXD_TYPE_MAX + IDXD_TYPE_IAX, + IDXD_TYPE_MAX, }; #define IDXD_NAME_SIZE 128 @@ -114,8 +115,13 @@ struct idxd_wq { u32 vec_ptr; /* interrupt steering */ struct dsa_hw_desc **hw_descs; int num_descs; - struct dsa_completion_record *compls; + union { + struct dsa_completion_record *compls; + struct iax_completion_record *iax_compls; + }; + void *compls_raw; dma_addr_t compls_addr; + dma_addr_t compls_addr_raw; int compls_size; struct idxd_desc **descs; struct sbitmap_queue sbq; @@ -196,6 +202,7 @@ struct idxd_device { int token_limit; int nr_tokens; /* non-reserved tokens */ unsigned int wqcfg_size; + int compl_size; union sw_err_reg sw_err; wait_queue_head_t cmd_waitq; @@ -210,9 +217,15 @@ struct idxd_device { /* IDXD software descriptor */ struct idxd_desc { - struct dsa_hw_desc *hw; + union { + struct dsa_hw_desc *hw; + struct iax_hw_desc *iax_hw; + }; dma_addr_t desc_dma; - struct dsa_completion_record *completion; + union { + struct dsa_completion_record *completion; + struct iax_completion_record *iax_completion; + }; dma_addr_t compl_dma; struct dma_async_tx_descriptor txd; struct llist_node llnode; @@ -226,6 +239,7 @@ struct idxd_desc { #define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev) extern struct bus_type dsa_bus_type; +extern struct bus_type iax_bus_type; extern bool support_enqcmd; @@ -271,6 +285,8 @@ static inline void idxd_set_type(struct idxd_device *idxd) if (pdev->device == PCI_DEVICE_ID_INTEL_DSA_SPR0) idxd->type = IDXD_TYPE_DSA; + else if (pdev->device == PCI_DEVICE_ID_INTEL_IAX_SPR0) + idxd->type = IDXD_TYPE_IAX; else idxd->type = IDXD_TYPE_UNKNOWN; } diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 45b0eac640c3..2c051e07c34c 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -36,12 +36,16 @@ static struct mutex idxd_idr_lock; static struct pci_device_id idxd_pci_tbl[] = { /* DSA ver 1.0 platforms */ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0) }, + + /* IAX ver 1.0 platforms */ + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IAX_SPR0) }, { 0, } }; MODULE_DEVICE_TABLE(pci, idxd_pci_tbl); static char *idxd_name[] = { "dsa", + "iax" }; const char *idxd_get_dev_name(struct idxd_device *idxd) @@ -377,6 +381,14 @@ static int idxd_probe(struct idxd_device *idxd) return rc; } +static void idxd_type_init(struct idxd_device *idxd) +{ + if (idxd->type == IDXD_TYPE_DSA) + idxd->compl_size = sizeof(struct dsa_completion_record); + else if (idxd->type == IDXD_TYPE_IAX) + idxd->compl_size = sizeof(struct iax_completion_record); +} + static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -412,6 +424,8 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) idxd_set_type(idxd); + idxd_type_init(idxd); + dev_dbg(dev, "Set PCI master\n"); pci_set_master(pdev); pci_set_drvdata(pdev, idxd); diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 0cdc5405bc53..23c41fe52215 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -5,6 +5,7 @@ /* PCI Config */ #define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define IDXD_MMIO_BAR 0 #define IDXD_WQ_BAR 2 diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index efca5d8468a6..0ff64eeb84be 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -15,7 +15,7 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu) desc = wq->descs[idx]; memset(desc->hw, 0, sizeof(struct dsa_hw_desc)); - memset(desc->completion, 0, sizeof(struct dsa_completion_record)); + memset(desc->completion, 0, idxd->compl_size); desc->cpu = cpu; if (device_pasid_enabled(idxd)) diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 3af83f1fd36e..266423a2cabc 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -41,14 +41,24 @@ static struct device_type dsa_device_type = { .release = idxd_conf_device_release, }; +static struct device_type iax_device_type = { + .name = "iax", + .release = idxd_conf_device_release, +}; + static inline bool is_dsa_dev(struct device *dev) { return dev ? dev->type == &dsa_device_type : false; } +static inline bool is_iax_dev(struct device *dev) +{ + return dev ? dev->type == &iax_device_type : false; +} + static inline bool is_idxd_dev(struct device *dev) { - return is_dsa_dev(dev); + return is_dsa_dev(dev) || is_iax_dev(dev); } static inline bool is_idxd_wq_dev(struct device *dev) @@ -359,8 +369,17 @@ struct bus_type dsa_bus_type = { .shutdown = idxd_config_bus_shutdown, }; +struct bus_type iax_bus_type = { + .name = "iax", + .match = idxd_config_bus_match, + .probe = idxd_config_bus_probe, + .remove = idxd_config_bus_remove, + .shutdown = idxd_config_bus_shutdown, +}; + static struct bus_type *idxd_bus_types[] = { - &dsa_bus_type + &dsa_bus_type, + &iax_bus_type }; static struct idxd_device_driver dsa_drv = { @@ -372,8 +391,18 @@ static struct idxd_device_driver dsa_drv = { }, }; +static struct idxd_device_driver iax_drv = { + .drv = { + .name = "iax", + .bus = &iax_bus_type, + .owner = THIS_MODULE, + .mod_name = KBUILD_MODNAME, + }, +}; + static struct idxd_device_driver *idxd_drvs[] = { - &dsa_drv + &dsa_drv, + &iax_drv }; struct bus_type *idxd_get_bus_type(struct idxd_device *idxd) @@ -385,6 +414,8 @@ static struct device_type *idxd_get_device_type(struct idxd_device *idxd) { if (idxd->type == IDXD_TYPE_DSA) return &dsa_device_type; + else if (idxd->type == IDXD_TYPE_IAX) + return &iax_device_type; else return NULL; } @@ -525,6 +556,9 @@ static ssize_t group_tokens_reserved_store(struct device *dev, if (rc < 0) return -EINVAL; + if (idxd->type == IDXD_TYPE_IAX) + return -EOPNOTSUPP; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) return -EPERM; @@ -570,6 +604,9 @@ static ssize_t group_tokens_allowed_store(struct device *dev, if (rc < 0) return -EINVAL; + if (idxd->type == IDXD_TYPE_IAX) + return -EOPNOTSUPP; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) return -EPERM; @@ -612,6 +649,9 @@ static ssize_t group_use_token_limit_store(struct device *dev, if (rc < 0) return -EINVAL; + if (idxd->type == IDXD_TYPE_IAX) + return -EOPNOTSUPP; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) return -EPERM; diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index fdcdfe414223..236d437947bc 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -26,6 +26,9 @@ #define IDXD_OP_FLAG_DRDBK 0x4000 #define IDXD_OP_FLAG_DSTS 0x8000 +/* IAX */ +#define IDXD_OP_FLAG_RD_SRC2_AECS 0x010000 + /* Opcode */ enum dsa_opcode { DSA_OPCODE_NOOP = 0, @@ -47,6 +50,14 @@ enum dsa_opcode { DSA_OPCODE_CFLUSH = 0x20, }; +enum iax_opcode { + IAX_OPCODE_NOOP = 0, + IAX_OPCODE_DRAIN = 2, + IAX_OPCODE_MEMMOVE, + IAX_OPCODE_DECOMPRESS = 0x42, + IAX_OPCODE_COMPRESS, +}; + /* Completion record status */ enum dsa_completion_status { DSA_COMP_NONE = 0, @@ -80,6 +91,33 @@ enum dsa_completion_status { DSA_COMP_TRANSLATION_FAIL, }; +enum iax_completion_status { + IAX_COMP_NONE = 0, + IAX_COMP_SUCCESS, + IAX_COMP_PAGE_FAULT_IR = 0x04, + IAX_COMP_OUTBUF_OVERFLOW, + IAX_COMP_BAD_OPCODE = 0x10, + IAX_COMP_INVALID_FLAGS, + IAX_COMP_NOZERO_RESERVE, + IAX_COMP_INVALID_SIZE, + IAX_COMP_OVERLAP_BUFFERS = 0x16, + IAX_COMP_INT_HANDLE_INVAL = 0x19, + IAX_COMP_CRA_XLAT, + IAX_COMP_CRA_ALIGN, + IAX_COMP_ADDR_ALIGN, + IAX_COMP_PRIV_BAD, + IAX_COMP_TRAFFIC_CLASS_CONF, + IAX_COMP_PFAULT_RDBA, + IAX_COMP_HW_ERR1, + IAX_COMP_HW_ERR_DRB, + IAX_COMP_TRANSLATION_FAIL, + IAX_COMP_PRS_TIMEOUT, + IAX_COMP_WATCHDOG, + IAX_COMP_INVALID_COMP_FLAG = 0x30, + IAX_COMP_INVALID_FILTER_FLAG, + IAX_COMP_INVALID_NUM_ELEMS = 0x33, +}; + #define DSA_COMP_STATUS_MASK 0x7f #define DSA_COMP_STATUS_WRITE 0x80 @@ -163,6 +201,28 @@ struct dsa_hw_desc { }; } __attribute__((packed)); +struct iax_hw_desc { + uint32_t pasid:20; + uint32_t rsvd:11; + uint32_t priv:1; + uint32_t flags:24; + uint32_t opcode:8; + uint64_t completion_addr; + uint64_t src1_addr; + uint64_t dst_addr; + uint32_t src1_size; + uint16_t int_handle; + union { + uint16_t compr_flags; + uint16_t decompr_flags; + }; + uint64_t src2_addr; + uint32_t max_dst_size; + uint32_t src2_size; + uint32_t filter_flags; + uint32_t num_inputs; +} __attribute__((packed)); + struct dsa_raw_desc { uint64_t field[8]; } __attribute__((packed)); @@ -223,4 +283,23 @@ struct dsa_raw_completion_record { uint64_t field[4]; } __attribute__((packed)); +struct iax_completion_record { + volatile uint8_t status; + uint8_t error_code; + uint16_t rsvd; + uint32_t bytes_completed; + uint64_t fault_addr; + uint32_t invalid_flags; + uint32_t rsvd2; + uint32_t output_size; + uint8_t output_bits; + uint8_t rsvd3; + uint16_t rsvd4; + uint64_t rsvd5[4]; +} __attribute__((packed)); + +struct iax_raw_completion_record { + uint64_t field[8]; +} __attribute__((packed)); + #endif -- cgit v1.2.3 From 06f08dab3ca726b86431889495c45049616d6a15 Mon Sep 17 00:00:00 2001 From: Samuel Cabrero Date: Mon, 30 Nov 2020 19:02:49 +0100 Subject: cifs: Register generic netlink family Register a new generic netlink family to talk to the witness service userspace daemon. Signed-off-by: Samuel Cabrero Reviewed-by: Aurelien Aptel Signed-off-by: Steve French --- fs/cifs/Kconfig | 11 ++++++ fs/cifs/Makefile | 2 + fs/cifs/cifsfs.c | 17 ++++++++- fs/cifs/netlink.c | 69 ++++++++++++++++++++++++++++++++++ fs/cifs/netlink.h | 16 ++++++++ include/uapi/linux/cifs/cifs_netlink.h | 31 +++++++++++++++ 6 files changed, 145 insertions(+), 1 deletion(-) create mode 100644 fs/cifs/netlink.c create mode 100644 fs/cifs/netlink.h create mode 100644 include/uapi/linux/cifs/cifs_netlink.h (limited to 'include/uapi/linux') diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 604f65f4b6c5..664ac5c63d39 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -190,6 +190,17 @@ config CIFS_DFS_UPCALL servers if their addresses change or for implicit mounts of DFS junction points. If unsure, say Y. +config CIFS_SWN_UPCALL + bool "SWN feature support" + depends on CIFS + help + The Service Witness Protocol (SWN) is used to get notifications + from a highly available server of resource state changes. This + feature enables an upcall mechanism for CIFS which contacts an + userspace daemon to establish the DCE/RPC connection to retrieve + the cluster available interfaces and resource change notifications. + If unsure, say Y. + config CIFS_NFSD_EXPORT bool "Allow nfsd to export CIFS file system" depends on CIFS && BROKEN diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 848ebad6af7d..9e398d227b0e 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -18,6 +18,8 @@ cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o +cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o + cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o cifs-$(CONFIG_CIFS_SMB_DIRECT) += smbdirect.o diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 4f27f77d3053..5d32561ae2ed 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -55,6 +55,9 @@ #ifdef CONFIG_CIFS_DFS_UPCALL #include "dfs_cache.h" #endif +#ifdef CONFIG_CIFS_SWN_UPCALL +#include "netlink.h" +#endif #include "fs_context.h" /* @@ -1601,10 +1604,15 @@ init_cifs(void) if (rc) goto out_destroy_dfs_cache; #endif /* CONFIG_CIFS_UPCALL */ +#ifdef CONFIG_CIFS_SWN_UPCALL + rc = cifs_genl_init(); + if (rc) + goto out_register_key_type; +#endif /* CONFIG_CIFS_SWN_UPCALL */ rc = init_cifs_idmap(); if (rc) - goto out_register_key_type; + goto out_cifs_swn_init; rc = register_filesystem(&cifs_fs_type); if (rc) @@ -1620,7 +1628,11 @@ init_cifs(void) out_init_cifs_idmap: exit_cifs_idmap(); +out_cifs_swn_init: +#ifdef CONFIG_CIFS_SWN_UPCALL + cifs_genl_exit(); out_register_key_type: +#endif #ifdef CONFIG_CIFS_UPCALL exit_cifs_spnego(); out_destroy_dfs_cache: @@ -1657,6 +1669,9 @@ exit_cifs(void) unregister_filesystem(&smb3_fs_type); cifs_dfs_release_automount_timer(); exit_cifs_idmap(); +#ifdef CONFIG_CIFS_SWN_UPCALL + cifs_genl_exit(); +#endif #ifdef CONFIG_CIFS_UPCALL exit_cifs_spnego(); #endif diff --git a/fs/cifs/netlink.c b/fs/cifs/netlink.c new file mode 100644 index 000000000000..b9154661fa85 --- /dev/null +++ b/fs/cifs/netlink.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Netlink routines for CIFS + * + * Copyright (c) 2020 Samuel Cabrero + */ + +#include +#include + +#include "netlink.h" +#include "cifsglob.h" +#include "cifs_debug.h" + +static const struct nla_policy cifs_genl_policy[CIFS_GENL_ATTR_MAX + 1] = { +}; + +static struct genl_ops cifs_genl_ops[] = { +}; + +static const struct genl_multicast_group cifs_genl_mcgrps[] = { + [CIFS_GENL_MCGRP_SWN] = { .name = CIFS_GENL_MCGRP_SWN_NAME }, +}; + +struct genl_family cifs_genl_family = { + .name = CIFS_GENL_NAME, + .version = CIFS_GENL_VERSION, + .hdrsize = 0, + .maxattr = CIFS_GENL_ATTR_MAX, + .module = THIS_MODULE, + .policy = cifs_genl_policy, + .ops = cifs_genl_ops, + .n_ops = ARRAY_SIZE(cifs_genl_ops), + .mcgrps = cifs_genl_mcgrps, + .n_mcgrps = ARRAY_SIZE(cifs_genl_mcgrps), +}; + +/** + * cifs_genl_init - Register generic netlink family + * + * Return zero if initialized successfully, otherwise non-zero. + */ +int cifs_genl_init(void) +{ + int ret; + + ret = genl_register_family(&cifs_genl_family); + if (ret < 0) { + cifs_dbg(VFS, "%s: failed to register netlink family\n", + __func__); + return ret; + } + + return 0; +} + +/** + * cifs_genl_exit - Unregister generic netlink family + */ +void cifs_genl_exit(void) +{ + int ret; + + ret = genl_unregister_family(&cifs_genl_family); + if (ret < 0) { + cifs_dbg(VFS, "%s: failed to unregister netlink family\n", + __func__); + } +} diff --git a/fs/cifs/netlink.h b/fs/cifs/netlink.h new file mode 100644 index 000000000000..e2fa8ed24c54 --- /dev/null +++ b/fs/cifs/netlink.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Netlink routines for CIFS + * + * Copyright (c) 2020 Samuel Cabrero + */ + +#ifndef _CIFS_NETLINK_H +#define _CIFS_NETLINK_H + +extern struct genl_family cifs_genl_family; + +extern int cifs_genl_init(void); +extern void cifs_genl_exit(void); + +#endif /* _CIFS_NETLINK_H */ diff --git a/include/uapi/linux/cifs/cifs_netlink.h b/include/uapi/linux/cifs/cifs_netlink.h new file mode 100644 index 000000000000..cdb1bd78fbc7 --- /dev/null +++ b/include/uapi/linux/cifs/cifs_netlink.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ +/* + * Netlink routines for CIFS + * + * Copyright (c) 2020 Samuel Cabrero + */ + + +#ifndef _UAPILINUX_CIFS_NETLINK_H +#define _UAPILINUX_CIFS_NETLINK_H + +#define CIFS_GENL_NAME "cifs" +#define CIFS_GENL_VERSION 0x1 + +#define CIFS_GENL_MCGRP_SWN_NAME "cifs_mcgrp_swn" + +enum cifs_genl_multicast_groups { + CIFS_GENL_MCGRP_SWN, +}; + +enum cifs_genl_attributes { + __CIFS_GENL_ATTR_MAX, +}; +#define CIFS_GENL_ATTR_MAX (__CIFS_GENL_ATTR_MAX - 1) + +enum cifs_genl_commands { + __CIFS_GENL_CMD_MAX +}; +#define CIFS_GENL_CMD_MAX (__CIFS_GENL_CMD_MAX - 1) + +#endif /* _UAPILINUX_CIFS_NETLINK_H */ -- cgit v1.2.3 From bf80e5d4259a192d6b06ae17e79a5e9dab48bf51 Mon Sep 17 00:00:00 2001 From: Samuel Cabrero Date: Mon, 30 Nov 2020 19:02:51 +0100 Subject: cifs: Send witness register and unregister commands to userspace daemon + Define the generic netlink family commands and message attributes to communicate with the userspace daemon + The register and unregister commands are sent when connecting or disconnecting a tree. The witness registration keeps a pointer to the tcon and has the same lifetime. + Each registration has an id allocated by an IDR. This id is sent to the userspace daemon in the register command, and will be included in the notification messages from the userspace daemon to retrieve from the IDR the matching registration. + The authentication information is bundled in the register message. If kerberos is used the message just carries a flag. Signed-off-by: Samuel Cabrero Reviewed-by: Aurelien Aptel Signed-off-by: Steve French --- fs/cifs/Makefile | 2 +- fs/cifs/cifs_swn.c | 421 +++++++++++++++++++++++++++++++++ fs/cifs/cifs_swn.h | 17 ++ fs/cifs/connect.c | 26 +- fs/cifs/netlink.c | 11 + include/uapi/linux/cifs/cifs_netlink.h | 15 ++ 6 files changed, 489 insertions(+), 3 deletions(-) create mode 100644 fs/cifs/cifs_swn.c create mode 100644 fs/cifs/cifs_swn.h (limited to 'include/uapi/linux') diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 9e398d227b0e..5213b20843b5 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -18,7 +18,7 @@ cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o -cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o +cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c new file mode 100644 index 000000000000..c0af03955d0c --- /dev/null +++ b/fs/cifs/cifs_swn.c @@ -0,0 +1,421 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Witness Service client for CIFS + * + * Copyright (c) 2020 Samuel Cabrero + */ + +#include +#include +#include + +#include "cifs_swn.h" +#include "cifsglob.h" +#include "cifsproto.h" +#include "fscache.h" +#include "cifs_debug.h" +#include "netlink.h" + +static DEFINE_IDR(cifs_swnreg_idr); +static DEFINE_MUTEX(cifs_swnreg_idr_mutex); + +struct cifs_swn_reg { + int id; + struct kref ref_count; + + const char *net_name; + const char *share_name; + bool net_name_notify; + bool share_name_notify; + bool ip_notify; + + struct cifs_tcon *tcon; +}; + +static int cifs_swn_auth_info_krb(struct cifs_tcon *tcon, struct sk_buff *skb) +{ + int ret; + + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_KRB_AUTH); + if (ret < 0) + return ret; + + return 0; +} + +static int cifs_swn_auth_info_ntlm(struct cifs_tcon *tcon, struct sk_buff *skb) +{ + int ret; + + if (tcon->ses->user_name != NULL) { + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_USER_NAME, tcon->ses->user_name); + if (ret < 0) + return ret; + } + + if (tcon->ses->password != NULL) { + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_PASSWORD, tcon->ses->password); + if (ret < 0) + return ret; + } + + if (tcon->ses->domainName != NULL) { + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_DOMAIN_NAME, tcon->ses->domainName); + if (ret < 0) + return ret; + } + + return 0; +} + +/* + * Sends a register message to the userspace daemon based on the registration. + * The authentication information to connect to the witness service is bundled + * into the message. + */ +static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg) +{ + struct sk_buff *skb; + struct genlmsghdr *hdr; + enum securityEnum authtype; + int ret; + + skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb == NULL) { + ret = -ENOMEM; + goto fail; + } + + hdr = genlmsg_put(skb, 0, 0, &cifs_genl_family, 0, CIFS_GENL_CMD_SWN_REGISTER); + if (hdr == NULL) { + ret = -ENOMEM; + goto nlmsg_fail; + } + + ret = nla_put_u32(skb, CIFS_GENL_ATTR_SWN_REGISTRATION_ID, swnreg->id); + if (ret < 0) + goto nlmsg_fail; + + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_NET_NAME, swnreg->net_name); + if (ret < 0) + goto nlmsg_fail; + + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_SHARE_NAME, swnreg->share_name); + if (ret < 0) + goto nlmsg_fail; + + ret = nla_put(skb, CIFS_GENL_ATTR_SWN_IP, sizeof(struct sockaddr_storage), + &swnreg->tcon->ses->server->dstaddr); + if (ret < 0) + goto nlmsg_fail; + + if (swnreg->net_name_notify) { + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_NET_NAME_NOTIFY); + if (ret < 0) + goto nlmsg_fail; + } + + if (swnreg->share_name_notify) { + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_SHARE_NAME_NOTIFY); + if (ret < 0) + goto nlmsg_fail; + } + + if (swnreg->ip_notify) { + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_IP_NOTIFY); + if (ret < 0) + goto nlmsg_fail; + } + + authtype = cifs_select_sectype(swnreg->tcon->ses->server, swnreg->tcon->ses->sectype); + switch (authtype) { + case Kerberos: + ret = cifs_swn_auth_info_krb(swnreg->tcon, skb); + if (ret < 0) { + cifs_dbg(VFS, "%s: Failed to get kerberos auth info: %d\n", __func__, ret); + goto nlmsg_fail; + } + break; + case LANMAN: + case NTLM: + case NTLMv2: + case RawNTLMSSP: + ret = cifs_swn_auth_info_ntlm(swnreg->tcon, skb); + if (ret < 0) { + cifs_dbg(VFS, "%s: Failed to get NTLM auth info: %d\n", __func__, ret); + goto nlmsg_fail; + } + break; + default: + cifs_dbg(VFS, "%s: secType %d not supported!\n", __func__, authtype); + ret = -EINVAL; + goto nlmsg_fail; + } + + genlmsg_end(skb, hdr); + genlmsg_multicast(&cifs_genl_family, skb, 0, CIFS_GENL_MCGRP_SWN, GFP_ATOMIC); + + cifs_dbg(FYI, "%s: Message to register for network name %s with id %d sent\n", __func__, + swnreg->net_name, swnreg->id); + + return 0; + +nlmsg_fail: + genlmsg_cancel(skb, hdr); + nlmsg_free(skb); +fail: + return ret; +} + +/* + * Sends an uregister message to the userspace daemon based on the registration + */ +static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg) +{ + struct sk_buff *skb; + struct genlmsghdr *hdr; + int ret; + + skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb == NULL) + return -ENOMEM; + + hdr = genlmsg_put(skb, 0, 0, &cifs_genl_family, 0, CIFS_GENL_CMD_SWN_UNREGISTER); + if (hdr == NULL) { + ret = -ENOMEM; + goto nlmsg_fail; + } + + ret = nla_put_u32(skb, CIFS_GENL_ATTR_SWN_REGISTRATION_ID, swnreg->id); + if (ret < 0) + goto nlmsg_fail; + + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_NET_NAME, swnreg->net_name); + if (ret < 0) + goto nlmsg_fail; + + ret = nla_put_string(skb, CIFS_GENL_ATTR_SWN_SHARE_NAME, swnreg->share_name); + if (ret < 0) + goto nlmsg_fail; + + ret = nla_put(skb, CIFS_GENL_ATTR_SWN_IP, sizeof(struct sockaddr_storage), + &swnreg->tcon->ses->server->dstaddr); + if (ret < 0) + goto nlmsg_fail; + + if (swnreg->net_name_notify) { + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_NET_NAME_NOTIFY); + if (ret < 0) + goto nlmsg_fail; + } + + if (swnreg->share_name_notify) { + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_SHARE_NAME_NOTIFY); + if (ret < 0) + goto nlmsg_fail; + } + + if (swnreg->ip_notify) { + ret = nla_put_flag(skb, CIFS_GENL_ATTR_SWN_IP_NOTIFY); + if (ret < 0) + goto nlmsg_fail; + } + + genlmsg_end(skb, hdr); + genlmsg_multicast(&cifs_genl_family, skb, 0, CIFS_GENL_MCGRP_SWN, GFP_ATOMIC); + + cifs_dbg(FYI, "%s: Message to unregister for network name %s with id %d sent\n", __func__, + swnreg->net_name, swnreg->id); + + return 0; + +nlmsg_fail: + genlmsg_cancel(skb, hdr); + nlmsg_free(skb); + return ret; +} + +/* + * Try to find a matching registration for the tcon's server name and share name. + * Calls to this funciton must be protected by cifs_swnreg_idr_mutex. + * TODO Try to avoid memory allocations + */ +static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon) +{ + struct cifs_swn_reg *swnreg; + int id; + const char *share_name; + const char *net_name; + + net_name = extract_hostname(tcon->treeName); + if (IS_ERR_OR_NULL(net_name)) { + int ret; + + ret = PTR_ERR(net_name); + cifs_dbg(VFS, "%s: failed to extract host name from target '%s': %d\n", + __func__, tcon->treeName, ret); + return NULL; + } + + share_name = extract_sharename(tcon->treeName); + if (IS_ERR_OR_NULL(share_name)) { + int ret; + + ret = PTR_ERR(net_name); + cifs_dbg(VFS, "%s: failed to extract share name from target '%s': %d\n", + __func__, tcon->treeName, ret); + kfree(net_name); + return NULL; + } + + idr_for_each_entry(&cifs_swnreg_idr, swnreg, id) { + if (strcasecmp(swnreg->net_name, net_name) != 0 + || strcasecmp(swnreg->share_name, share_name) != 0) { + continue; + } + + mutex_unlock(&cifs_swnreg_idr_mutex); + + cifs_dbg(FYI, "Existing swn registration for %s:%s found\n", swnreg->net_name, + swnreg->share_name); + + kfree(net_name); + kfree(share_name); + + return swnreg; + } + + kfree(net_name); + kfree(share_name); + + return NULL; +} + +/* + * Get a registration for the tcon's server and share name, allocating a new one if it does not + * exists + */ +static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) +{ + struct cifs_swn_reg *reg = NULL; + int ret; + + mutex_lock(&cifs_swnreg_idr_mutex); + + /* Check if we are already registered for this network and share names */ + reg = cifs_find_swn_reg(tcon); + if (IS_ERR(reg)) { + return reg; + } else if (reg != NULL) { + kref_get(®->ref_count); + mutex_unlock(&cifs_swnreg_idr_mutex); + return reg; + } + + reg = kmalloc(sizeof(struct cifs_swn_reg), GFP_ATOMIC); + if (reg == NULL) { + mutex_unlock(&cifs_swnreg_idr_mutex); + return ERR_PTR(-ENOMEM); + } + + kref_init(®->ref_count); + + reg->id = idr_alloc(&cifs_swnreg_idr, reg, 1, 0, GFP_ATOMIC); + if (reg->id < 0) { + cifs_dbg(FYI, "%s: failed to allocate registration id\n", __func__); + ret = reg->id; + goto fail; + } + + reg->net_name = extract_hostname(tcon->treeName); + if (IS_ERR(reg->net_name)) { + ret = PTR_ERR(reg->net_name); + cifs_dbg(VFS, "%s: failed to extract host name from target: %d\n", __func__, ret); + goto fail_idr; + } + + reg->share_name = extract_sharename(tcon->treeName); + if (IS_ERR(reg->share_name)) { + ret = PTR_ERR(reg->share_name); + cifs_dbg(VFS, "%s: failed to extract share name from target: %d\n", __func__, ret); + goto fail_net_name; + } + + reg->net_name_notify = true; + reg->share_name_notify = true; + reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT); + + reg->tcon = tcon; + + mutex_unlock(&cifs_swnreg_idr_mutex); + + return reg; + +fail_net_name: + kfree(reg->net_name); +fail_idr: + idr_remove(&cifs_swnreg_idr, reg->id); +fail: + kfree(reg); + mutex_unlock(&cifs_swnreg_idr_mutex); + return ERR_PTR(ret); +} + +static void cifs_swn_reg_release(struct kref *ref) +{ + struct cifs_swn_reg *swnreg = container_of(ref, struct cifs_swn_reg, ref_count); + int ret; + + ret = cifs_swn_send_unregister_message(swnreg); + if (ret < 0) + cifs_dbg(VFS, "%s: Failed to send unregister message: %d\n", __func__, ret); + + idr_remove(&cifs_swnreg_idr, swnreg->id); + kfree(swnreg->net_name); + kfree(swnreg->share_name); + kfree(swnreg); +} + +static void cifs_put_swn_reg(struct cifs_swn_reg *swnreg) +{ + mutex_lock(&cifs_swnreg_idr_mutex); + kref_put(&swnreg->ref_count, cifs_swn_reg_release); + mutex_unlock(&cifs_swnreg_idr_mutex); +} + +int cifs_swn_register(struct cifs_tcon *tcon) +{ + struct cifs_swn_reg *swnreg; + int ret; + + swnreg = cifs_get_swn_reg(tcon); + if (IS_ERR(swnreg)) + return PTR_ERR(swnreg); + + ret = cifs_swn_send_register_message(swnreg); + if (ret < 0) { + cifs_dbg(VFS, "%s: Failed to send swn register message: %d\n", __func__, ret); + /* Do not put the swnreg or return error, the echo task will retry */ + } + + return 0; +} + +int cifs_swn_unregister(struct cifs_tcon *tcon) +{ + struct cifs_swn_reg *swnreg; + + mutex_lock(&cifs_swnreg_idr_mutex); + + swnreg = cifs_find_swn_reg(tcon); + if (swnreg == NULL) { + mutex_unlock(&cifs_swnreg_idr_mutex); + return -EEXIST; + } + + mutex_unlock(&cifs_swnreg_idr_mutex); + + cifs_put_swn_reg(swnreg); + + return 0; +} diff --git a/fs/cifs/cifs_swn.h b/fs/cifs/cifs_swn.h new file mode 100644 index 000000000000..69c7bd1035da --- /dev/null +++ b/fs/cifs/cifs_swn.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Witness Service client for CIFS + * + * Copyright (c) 2020 Samuel Cabrero + */ + +#ifndef _CIFS_SWN_H +#define _CIFS_SWN_H + +struct cifs_tcon; + +extern int cifs_swn_register(struct cifs_tcon *tcon); + +extern int cifs_swn_unregister(struct cifs_tcon *tcon); + +#endif /* _CIFS_SWN_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ead1c086b88d..68ef2da7c74b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -62,6 +62,9 @@ #include "dfs_cache.h" #endif #include "fs_context.h" +#ifdef CONFIG_CIFS_SWN_UPCALL +#include "cifs_swn.h" +#endif extern mempool_t *cifs_req_poolp; extern bool disable_legacy_dialects; @@ -1944,7 +1947,17 @@ cifs_put_tcon(struct cifs_tcon *tcon) return; } - /* TODO witness unregister */ +#ifdef CONFIG_CIFS_SWN_UPCALL + if (tcon->use_witness) { + int rc; + + rc = cifs_swn_unregister(tcon); + if (rc < 0) { + cifs_dbg(VFS, "%s: Failed to unregister for witness notifications: %d\n", + __func__, rc); + } + } +#endif list_del_init(&tcon->tcon_list); spin_unlock(&cifs_tcp_ses_lock); @@ -2111,8 +2124,17 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (ctx->witness) { if (ses->server->vals->protocol_id >= SMB30_PROT_ID) { if (tcon->capabilities & SMB2_SHARE_CAP_CLUSTER) { - /* TODO witness register */ + /* + * Set witness in use flag in first place + * to retry registration in the echo task + */ tcon->use_witness = true; + /* And try to register immediately */ + rc = cifs_swn_register(tcon); + if (rc < 0) { + cifs_dbg(VFS, "Failed to register for witness notifications: %d\n", rc); + goto out_fail; + } } else { /* TODO: try to extend for non-cluster uses (eg multichannel) */ cifs_dbg(VFS, "witness requested on mount but no CLUSTER capability on share\n"); diff --git a/fs/cifs/netlink.c b/fs/cifs/netlink.c index b9154661fa85..83008a56def5 100644 --- a/fs/cifs/netlink.c +++ b/fs/cifs/netlink.c @@ -13,6 +13,17 @@ #include "cifs_debug.h" static const struct nla_policy cifs_genl_policy[CIFS_GENL_ATTR_MAX + 1] = { + [CIFS_GENL_ATTR_SWN_REGISTRATION_ID] = { .type = NLA_U32 }, + [CIFS_GENL_ATTR_SWN_NET_NAME] = { .type = NLA_STRING }, + [CIFS_GENL_ATTR_SWN_SHARE_NAME] = { .type = NLA_STRING }, + [CIFS_GENL_ATTR_SWN_IP] = { .len = sizeof(struct sockaddr_storage) }, + [CIFS_GENL_ATTR_SWN_NET_NAME_NOTIFY] = { .type = NLA_FLAG }, + [CIFS_GENL_ATTR_SWN_SHARE_NAME_NOTIFY] = { .type = NLA_FLAG }, + [CIFS_GENL_ATTR_SWN_IP_NOTIFY] = { .type = NLA_FLAG }, + [CIFS_GENL_ATTR_SWN_KRB_AUTH] = { .type = NLA_FLAG }, + [CIFS_GENL_ATTR_SWN_USER_NAME] = { .type = NLA_STRING }, + [CIFS_GENL_ATTR_SWN_PASSWORD] = { .type = NLA_STRING }, + [CIFS_GENL_ATTR_SWN_DOMAIN_NAME] = { .type = NLA_STRING }, }; static struct genl_ops cifs_genl_ops[] = { diff --git a/include/uapi/linux/cifs/cifs_netlink.h b/include/uapi/linux/cifs/cifs_netlink.h index cdb1bd78fbc7..5662e2774513 100644 --- a/include/uapi/linux/cifs/cifs_netlink.h +++ b/include/uapi/linux/cifs/cifs_netlink.h @@ -19,11 +19,26 @@ enum cifs_genl_multicast_groups { }; enum cifs_genl_attributes { + CIFS_GENL_ATTR_UNSPEC, + CIFS_GENL_ATTR_SWN_REGISTRATION_ID, + CIFS_GENL_ATTR_SWN_NET_NAME, + CIFS_GENL_ATTR_SWN_SHARE_NAME, + CIFS_GENL_ATTR_SWN_IP, + CIFS_GENL_ATTR_SWN_NET_NAME_NOTIFY, + CIFS_GENL_ATTR_SWN_SHARE_NAME_NOTIFY, + CIFS_GENL_ATTR_SWN_IP_NOTIFY, + CIFS_GENL_ATTR_SWN_KRB_AUTH, + CIFS_GENL_ATTR_SWN_USER_NAME, + CIFS_GENL_ATTR_SWN_PASSWORD, + CIFS_GENL_ATTR_SWN_DOMAIN_NAME, __CIFS_GENL_ATTR_MAX, }; #define CIFS_GENL_ATTR_MAX (__CIFS_GENL_ATTR_MAX - 1) enum cifs_genl_commands { + CIFS_GENL_CMD_UNSPEC, + CIFS_GENL_CMD_SWN_REGISTER, + CIFS_GENL_CMD_SWN_UNREGISTER, __CIFS_GENL_CMD_MAX }; #define CIFS_GENL_CMD_MAX (__CIFS_GENL_CMD_MAX - 1) -- cgit v1.2.3 From fed979a7e082bd9f25f9002c3c4f8740dacd0bc8 Mon Sep 17 00:00:00 2001 From: Samuel Cabrero Date: Mon, 30 Nov 2020 19:02:52 +0100 Subject: cifs: Set witness notification handler for messages from userspace daemon + Set a handler for the witness notification messages received from the userspace daemon. + Handle the resource state change notification. When the resource becomes unavailable or available set the tcp status to CifsNeedReconnect for all channels. Signed-off-by: Samuel Cabrero Reviewed-by: Aurelien Aptel Signed-off-by: Steve French --- fs/cifs/cifs_swn.c | 86 ++++++++++++++++++++++++++++++++++ fs/cifs/cifs_swn.h | 4 ++ fs/cifs/netlink.c | 9 ++++ include/uapi/linux/cifs/cifs_netlink.h | 17 +++++++ 4 files changed, 116 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c index c0af03955d0c..63b0764af5d5 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/cifs/cifs_swn.c @@ -383,6 +383,92 @@ static void cifs_put_swn_reg(struct cifs_swn_reg *swnreg) mutex_unlock(&cifs_swnreg_idr_mutex); } +static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const char *name, int state) +{ + int i; + + switch (state) { + case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE: + cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name); + for (i = 0; i < swnreg->tcon->ses->chan_count; i++) { + spin_lock(&GlobalMid_Lock); + if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting) + swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + } + break; + case CIFS_SWN_RESOURCE_STATE_AVAILABLE: + cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name); + for (i = 0; i < swnreg->tcon->ses->chan_count; i++) { + spin_lock(&GlobalMid_Lock); + if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting) + swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + } + break; + case CIFS_SWN_RESOURCE_STATE_UNKNOWN: + cifs_dbg(FYI, "%s: resource name '%s' changed to unknown state\n", __func__, name); + break; + } + return 0; +} + +int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info) +{ + struct cifs_swn_reg *swnreg; + char name[256]; + int type; + + if (info->attrs[CIFS_GENL_ATTR_SWN_REGISTRATION_ID]) { + int swnreg_id; + + swnreg_id = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_REGISTRATION_ID]); + mutex_lock(&cifs_swnreg_idr_mutex); + swnreg = idr_find(&cifs_swnreg_idr, swnreg_id); + mutex_unlock(&cifs_swnreg_idr_mutex); + if (swnreg == NULL) { + cifs_dbg(FYI, "%s: registration id %d not found\n", __func__, swnreg_id); + return -EINVAL; + } + } else { + cifs_dbg(FYI, "%s: missing registration id attribute\n", __func__); + return -EINVAL; + } + + if (info->attrs[CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE]) { + type = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE]); + } else { + cifs_dbg(FYI, "%s: missing notification type attribute\n", __func__); + return -EINVAL; + } + + switch (type) { + case CIFS_SWN_NOTIFICATION_RESOURCE_CHANGE: { + int state; + + if (info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_NAME]) { + nla_strlcpy(name, info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_NAME], + sizeof(name)); + } else { + cifs_dbg(FYI, "%s: missing resource name attribute\n", __func__); + return -EINVAL; + } + if (info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_STATE]) { + state = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_STATE]); + } else { + cifs_dbg(FYI, "%s: missing resource state attribute\n", __func__); + return -EINVAL; + } + return cifs_swn_resource_state_changed(swnreg, name, state); + } + default: + cifs_dbg(FYI, "%s: unknown notification type %d\n", __func__, type); + break; + } + + return 0; +} + int cifs_swn_register(struct cifs_tcon *tcon) { struct cifs_swn_reg *swnreg; diff --git a/fs/cifs/cifs_swn.h b/fs/cifs/cifs_swn.h index 69c7bd1035da..7ef9ecedbd05 100644 --- a/fs/cifs/cifs_swn.h +++ b/fs/cifs/cifs_swn.h @@ -9,9 +9,13 @@ #define _CIFS_SWN_H struct cifs_tcon; +struct sk_buff; +struct genl_info; extern int cifs_swn_register(struct cifs_tcon *tcon); extern int cifs_swn_unregister(struct cifs_tcon *tcon); +extern int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info); + #endif /* _CIFS_SWN_H */ diff --git a/fs/cifs/netlink.c b/fs/cifs/netlink.c index 83008a56def5..5aaabe4cc0a7 100644 --- a/fs/cifs/netlink.c +++ b/fs/cifs/netlink.c @@ -11,6 +11,7 @@ #include "netlink.h" #include "cifsglob.h" #include "cifs_debug.h" +#include "cifs_swn.h" static const struct nla_policy cifs_genl_policy[CIFS_GENL_ATTR_MAX + 1] = { [CIFS_GENL_ATTR_SWN_REGISTRATION_ID] = { .type = NLA_U32 }, @@ -24,9 +25,17 @@ static const struct nla_policy cifs_genl_policy[CIFS_GENL_ATTR_MAX + 1] = { [CIFS_GENL_ATTR_SWN_USER_NAME] = { .type = NLA_STRING }, [CIFS_GENL_ATTR_SWN_PASSWORD] = { .type = NLA_STRING }, [CIFS_GENL_ATTR_SWN_DOMAIN_NAME] = { .type = NLA_STRING }, + [CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE] = { .type = NLA_U32 }, + [CIFS_GENL_ATTR_SWN_RESOURCE_STATE] = { .type = NLA_U32 }, + [CIFS_GENL_ATTR_SWN_RESOURCE_NAME] = { .type = NLA_STRING}, }; static struct genl_ops cifs_genl_ops[] = { + { + .cmd = CIFS_GENL_CMD_SWN_NOTIFY, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = cifs_swn_notify, + }, }; static const struct genl_multicast_group cifs_genl_mcgrps[] = { diff --git a/include/uapi/linux/cifs/cifs_netlink.h b/include/uapi/linux/cifs/cifs_netlink.h index 5662e2774513..da3107582f49 100644 --- a/include/uapi/linux/cifs/cifs_netlink.h +++ b/include/uapi/linux/cifs/cifs_netlink.h @@ -31,6 +31,9 @@ enum cifs_genl_attributes { CIFS_GENL_ATTR_SWN_USER_NAME, CIFS_GENL_ATTR_SWN_PASSWORD, CIFS_GENL_ATTR_SWN_DOMAIN_NAME, + CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE, + CIFS_GENL_ATTR_SWN_RESOURCE_STATE, + CIFS_GENL_ATTR_SWN_RESOURCE_NAME, __CIFS_GENL_ATTR_MAX, }; #define CIFS_GENL_ATTR_MAX (__CIFS_GENL_ATTR_MAX - 1) @@ -39,8 +42,22 @@ enum cifs_genl_commands { CIFS_GENL_CMD_UNSPEC, CIFS_GENL_CMD_SWN_REGISTER, CIFS_GENL_CMD_SWN_UNREGISTER, + CIFS_GENL_CMD_SWN_NOTIFY, __CIFS_GENL_CMD_MAX }; #define CIFS_GENL_CMD_MAX (__CIFS_GENL_CMD_MAX - 1) +enum cifs_swn_notification_type { + CIFS_SWN_NOTIFICATION_RESOURCE_CHANGE = 0x01, + CIFS_SWN_NOTIFICATION_CLIENT_MOVE = 0x02, + CIFS_SWN_NOTIFICATION_SHARE_MOVE = 0x03, + CIFS_SWN_NOTIFICATION_IP_CHANGE = 0x04, +}; + +enum cifs_swn_resource_state { + CIFS_SWN_RESOURCE_STATE_UNKNOWN = 0x00, + CIFS_SWN_RESOURCE_STATE_AVAILABLE = 0x01, + CIFS_SWN_RESOURCE_STATE_UNAVAILABLE = 0xFF +}; + #endif /* _UAPILINUX_CIFS_NETLINK_H */ -- cgit v1.2.3 From 75f4d4544db9fa34e1f04174f27d9f8a387be37d Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 15 Dec 2020 11:25:31 +0100 Subject: devlink: use _BITUL() macro instead of BIT() in the UAPI header The BIT() macro is not available for the UAPI headers. Moreover, it can be defined differently in user space headers. Thus, replace its usage with the _BITUL() macro which is already used in other macro definitions in . Fixes: dc64cc7c6310 ("devlink: Add devlink reload limit option") Signed-off-by: Tobias Klauser Link: https://lore.kernel.org/r/20201215102531.16958-1-tklauser@distanz.ch Signed-off-by: Jakub Kicinski --- include/uapi/linux/devlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 5203f54a2be1..cf89c318f2ac 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -322,7 +322,7 @@ enum devlink_reload_limit { DEVLINK_RELOAD_LIMIT_MAX = __DEVLINK_RELOAD_LIMIT_MAX - 1 }; -#define DEVLINK_RELOAD_LIMITS_VALID_MASK (BIT(__DEVLINK_RELOAD_LIMIT_MAX) - 1) +#define DEVLINK_RELOAD_LIMITS_VALID_MASK (_BITUL(__DEVLINK_RELOAD_LIMIT_MAX) - 1) enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ -- cgit v1.2.3 From 1e38f0031c3055c9c7e5ffcb3bb09c95f69614ee Mon Sep 17 00:00:00 2001 From: "Enrico Weigelt, metux IT consult" Date: Wed, 2 Dec 2020 12:19:30 +0100 Subject: uapi: virtio_ids.h: consistent indentions Fixing the differing indentions to be consistent and properly aligned. Signed-off-by: Enrico Weigelt, metux IT consult Link: https://lore.kernel.org/r/20201202111931.31953-1-info@metux.net Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index b052355ac7a3..3cb55e5277a1 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -29,24 +29,24 @@ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ -#define VIRTIO_ID_NET 1 /* virtio net */ -#define VIRTIO_ID_BLOCK 2 /* virtio block */ -#define VIRTIO_ID_CONSOLE 3 /* virtio console */ -#define VIRTIO_ID_RNG 4 /* virtio rng */ -#define VIRTIO_ID_BALLOON 5 /* virtio balloon */ -#define VIRTIO_ID_RPMSG 7 /* virtio remote processor messaging */ -#define VIRTIO_ID_SCSI 8 /* virtio scsi */ -#define VIRTIO_ID_9P 9 /* 9p virtio console */ -#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */ -#define VIRTIO_ID_CAIF 12 /* Virtio caif */ -#define VIRTIO_ID_GPU 16 /* virtio GPU */ -#define VIRTIO_ID_INPUT 18 /* virtio input */ -#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ -#define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ -#define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ -#define VIRTIO_ID_MEM 24 /* virtio mem */ -#define VIRTIO_ID_FS 26 /* virtio filesystem */ -#define VIRTIO_ID_PMEM 27 /* virtio pmem */ -#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ +#define VIRTIO_ID_NET 1 /* virtio net */ +#define VIRTIO_ID_BLOCK 2 /* virtio block */ +#define VIRTIO_ID_CONSOLE 3 /* virtio console */ +#define VIRTIO_ID_RNG 4 /* virtio rng */ +#define VIRTIO_ID_BALLOON 5 /* virtio balloon */ +#define VIRTIO_ID_RPMSG 7 /* virtio remote processor messaging */ +#define VIRTIO_ID_SCSI 8 /* virtio scsi */ +#define VIRTIO_ID_9P 9 /* 9p virtio console */ +#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */ +#define VIRTIO_ID_CAIF 12 /* Virtio caif */ +#define VIRTIO_ID_GPU 16 /* virtio GPU */ +#define VIRTIO_ID_INPUT 18 /* virtio input */ +#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ +#define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ +#define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ +#define VIRTIO_ID_MEM 24 /* virtio mem */ +#define VIRTIO_ID_FS 26 /* virtio filesystem */ +#define VIRTIO_ID_PMEM 27 /* virtio pmem */ +#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ #endif /* _LINUX_VIRTIO_IDS_H */ -- cgit v1.2.3 From be618636de4186521ffba2cbe5105e9c3481b9cb Mon Sep 17 00:00:00 2001 From: "Enrico Weigelt, metux IT consult" Date: Wed, 2 Dec 2020 12:19:31 +0100 Subject: uapi: virtio_ids: add missing device type IDs from OASIS spec The OASIS virtio spec (1.1) defines several IDs that aren't reflected in the header yet. Fixing this by adding the missing IDs, even though they're not yet used by the kernel yet. Signed-off-by: Enrico Weigelt, metux IT consult Link: https://lore.kernel.org/r/20201202111931.31953-2-info@metux.net Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 3cb55e5277a1..bc1c0621f5ed 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -34,15 +34,21 @@ #define VIRTIO_ID_CONSOLE 3 /* virtio console */ #define VIRTIO_ID_RNG 4 /* virtio rng */ #define VIRTIO_ID_BALLOON 5 /* virtio balloon */ +#define VIRTIO_ID_IOMEM 6 /* virtio ioMemory */ #define VIRTIO_ID_RPMSG 7 /* virtio remote processor messaging */ #define VIRTIO_ID_SCSI 8 /* virtio scsi */ #define VIRTIO_ID_9P 9 /* 9p virtio console */ +#define VIRTIO_ID_MAC80211_WLAN 10 /* virtio WLAN MAC */ #define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */ #define VIRTIO_ID_CAIF 12 /* Virtio caif */ +#define VIRTIO_ID_MEMORY_BALLOON 13 /* virtio memory balloon */ #define VIRTIO_ID_GPU 16 /* virtio GPU */ +#define VIRTIO_ID_CLOCK 17 /* virtio clock/timer */ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ +#define VIRTIO_ID_SIGNAL_DIST 21 /* virtio signal distribution device */ +#define VIRTIO_ID_PSTORE 22 /* virtio pstore device */ #define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ #define VIRTIO_ID_MEM 24 /* virtio mem */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ -- cgit v1.2.3 From bcce55f556e824d43f352d76b94509185585e38d Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sat, 19 Dec 2020 13:19:24 +0100 Subject: ppp: Fix PPPIOCUNBRIDGECHAN request number PPPIOCGL2TPSTATS already uses 54. This shouldn't be a problem in practice, but let's keep the logical decreasing assignment scheme. Fixes: 4cf476ced45d ("ppp: add PPPIOCBRIDGECHAN and PPPIOCUNBRIDGECHAN ioctls") Signed-off-by: Guillaume Nault Link: https://lore.kernel.org/r/e3a4c355e3820331d8e1fffef8522739aae58b57.1608380117.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ppp-ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h index 8dbecb3ad036..1cc5ce0ae062 100644 --- a/include/uapi/linux/ppp-ioctl.h +++ b/include/uapi/linux/ppp-ioctl.h @@ -116,7 +116,7 @@ struct pppol2tp_ioc_stats { #define PPPIOCGCHAN _IOR('t', 55, int) /* get ppp channel number */ #define PPPIOCGL2TPSTATS _IOR('t', 54, struct pppol2tp_ioc_stats) #define PPPIOCBRIDGECHAN _IOW('t', 53, int) /* bridge one channel to another */ -#define PPPIOCUNBRIDGECHAN _IO('t', 54) /* unbridge channel */ +#define PPPIOCUNBRIDGECHAN _IO('t', 52) /* unbridge channel */ #define SIOCGPPPSTATS (SIOCDEVPRIVATE + 0) #define SIOCGPPPVER (SIOCDEVPRIVATE + 1) /* NEVER change this!! */ -- cgit v1.2.3 From b4e70d8dd9ea6bd5d5fb3122586f652326ca09cd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 27 Dec 2020 12:35:43 +0100 Subject: netfilter: nftables: add set expression flags The set flag NFT_SET_EXPR provides a hint to the kernel that userspace supports for multiple expressions per set element. In the same direction, NFT_DYNSET_F_EXPR specifies that dynset expression defines multiple expressions per set element. This allows new userspace software with old kernels to bail out with EOPNOTSUPP. This update is similar to ef516e8625dd ("netfilter: nf_tables: reintroduce the NFT_SET_CONCAT flag"). The NFT_SET_EXPR flag needs to be set on when the NFTA_SET_EXPRESSIONS attribute is specified. The NFT_SET_EXPR flag is not set on with NFTA_SET_EXPR to retain backward compatibility in old userspace binaries. Fixes: 48b0ae046ee9 ("netfilter: nftables: netlink support for several set element expressions") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 3 +++ net/netfilter/nf_tables_api.c | 6 +++++- net/netfilter/nft_dynset.c | 9 +++++++-- 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 28b6ee53305f..b1633e7ba529 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -293,6 +293,7 @@ enum nft_rule_compat_attributes { * @NFT_SET_EVAL: set can be updated from the evaluation path * @NFT_SET_OBJECT: set contains stateful objects * @NFT_SET_CONCAT: set contains a concatenation + * @NFT_SET_EXPR: set contains expressions */ enum nft_set_flags { NFT_SET_ANONYMOUS = 0x1, @@ -303,6 +304,7 @@ enum nft_set_flags { NFT_SET_EVAL = 0x20, NFT_SET_OBJECT = 0x40, NFT_SET_CONCAT = 0x80, + NFT_SET_EXPR = 0x100, }; /** @@ -706,6 +708,7 @@ enum nft_dynset_ops { enum nft_dynset_flags { NFT_DYNSET_F_INV = (1 << 0), + NFT_DYNSET_F_EXPR = (1 << 1), }; /** diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4186b1e52d58..15c467f1a9dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4162,7 +4162,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | - NFT_SET_OBJECT | NFT_SET_CONCAT)) + NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR)) return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == @@ -4304,6 +4304,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, struct nlattr *tmp; int left; + if (!(flags & NFT_SET_EXPR)) { + err = -EINVAL; + goto err_set_alloc_name; + } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index f35df221a633..0b053f75cd60 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -19,6 +19,7 @@ struct nft_dynset { enum nft_registers sreg_key:8; enum nft_registers sreg_data:8; bool invert; + bool expr; u8 num_exprs; u64 timeout; struct nft_expr *expr_array[NFT_SET_EXPR_MAX]; @@ -175,11 +176,12 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_FLAGS]) { u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS])); - - if (flags & ~NFT_DYNSET_F_INV) + if (flags & ~(NFT_DYNSET_F_INV | NFT_DYNSET_F_EXPR)) return -EOPNOTSUPP; if (flags & NFT_DYNSET_F_INV) priv->invert = true; + if (flags & NFT_DYNSET_F_EXPR) + priv->expr = true; } set = nft_set_lookup_global(ctx->net, ctx->table, @@ -261,6 +263,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, struct nlattr *tmp; int left; + if (!priv->expr) + return -EINVAL; + i = 0; nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { -- cgit v1.2.3 From cf0720697143f3eaa0779cca5a6602d8557d1c6f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 30 Dec 2020 19:37:53 -0800 Subject: net: suggest L2 discards be counted towards rx_dropped From the existing definitions it's unclear which stat to use to report filtering based on L2 dst addr in old broadcast-medium Ethernet. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 874cc12a34d9..82708c6db432 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -75,8 +75,9 @@ struct rtnl_link_stats { * * @rx_dropped: Number of packets received but not processed, * e.g. due to lack of resources or unsupported protocol. - * For hardware interfaces this counter should not include packets - * dropped by the device which are counted separately in + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in * @rx_missed_errors (since procfs folds those two counters together). * * @tx_dropped: Number of packets dropped on their way to transmission, -- cgit v1.2.3 From 647daca25d24fb6eadc7b6cd680ad3e6eed0f3d5 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 4 Jan 2021 14:20:01 -0600 Subject: KVM: SVM: Add support for booting APs in an SEV-ES guest Typically under KVM, an AP is booted using the INIT-SIPI-SIPI sequence, where the guest vCPU register state is updated and then the vCPU is VMRUN to begin execution of the AP. For an SEV-ES guest, this won't work because the guest register state is encrypted. Following the GHCB specification, the hypervisor must not alter the guest register state, so KVM must track an AP/vCPU boot. Should the guest want to park the AP, it must use the AP Reset Hold exit event in place of, for example, a HLT loop. First AP boot (first INIT-SIPI-SIPI sequence): Execute the AP (vCPU) as it was initialized and measured by the SEV-ES support. It is up to the guest to transfer control of the AP to the proper location. Subsequent AP boot: KVM will expect to receive an AP Reset Hold exit event indicating that the vCPU is being parked and will require an INIT-SIPI-SIPI sequence to awaken it. When the AP Reset Hold exit event is received, KVM will place the vCPU into a simulated HLT mode. Upon receiving the INIT-SIPI-SIPI sequence, KVM will make the vCPU runnable. It is again up to the guest to then transfer control of the AP to the proper location. To differentiate between an actual HLT and an AP Reset Hold, a new MP state is introduced, KVM_MP_STATE_AP_RESET_HOLD, which the vCPU is placed in upon receiving the AP Reset Hold exit event. Additionally, to communicate the AP Reset Hold exit event up to userspace (if needed), a new exit reason is introduced, KVM_EXIT_AP_RESET_HOLD. A new x86 ops function is introduced, vcpu_deliver_sipi_vector, in order to accomplish AP booting. For VMX, vcpu_deliver_sipi_vector is set to the original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(). SVM adds a new function that, for non SEV-ES guests, invokes the original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(), but for SEV-ES guests, implements the logic above. Signed-off-by: Tom Lendacky Message-Id: Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/svm/sev.c | 22 ++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 10 ++++++++++ arch/x86/kvm/svm/svm.h | 2 ++ arch/x86/kvm/vmx/vmx.c | 2 ++ arch/x86/kvm/x86.c | 26 +++++++++++++++++++++----- include/uapi/linux/kvm.h | 2 ++ 8 files changed, 63 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index afed3da3b3a0..3d6616f6f6ef 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1299,6 +1299,8 @@ struct kvm_x86_ops { void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); + + void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); }; struct kvm_x86_nested_ops { @@ -1480,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 78823227c592..43cceadd073e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; - kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 563ced07b0b8..c8ffdbc81709 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; @@ -1888,6 +1889,9 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); break; + case SVM_VMGEXIT_AP_HLT_LOOP: + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + break; case SVM_VMGEXIT_AP_JUMP_TABLE: { struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; @@ -2040,3 +2044,21 @@ void sev_es_vcpu_put(struct vcpu_svm *svm) wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); } } + +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* First SIPI: Use the values as initially set by the VMM */ + if (!svm->received_first_sipi) { + svm->received_first_sipi = true; + return; + } + + /* + * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where + * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a + * non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->ghcb, 1); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 6824d611dc5d..7ef171790d02 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4382,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); } +static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + if (!sev_es_guest(vcpu->kvm)) + return kvm_vcpu_deliver_sipi_vector(vcpu, vector); + + sev_vcpu_deliver_sipi_vector(vcpu, vector); +} + static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); @@ -4524,6 +4532,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .msr_filter_changed = svm_msr_filter_changed, .complete_emulated_msr = svm_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5431e6335e2e..0fe874ae5498 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -185,6 +185,7 @@ struct vcpu_svm { struct vmcb_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; + bool received_first_sipi; /* SEV-ES scratch area support */ void *ghcb_sa; @@ -591,6 +592,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); void sev_es_vcpu_put(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75c9c6a0a3a4..2af05d3b0590 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7707,6 +7707,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, .cpu_dirty_log_size = vmx_cpu_dirty_log_size, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; static __init int hardware_setup(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f6e7b25c40e2..0287840b93e0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7976,17 +7976,22 @@ void kvm_arch_exit(void) kmem_cache_destroy(x86_fpu_cache); } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) { ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + vcpu->arch.mp_state = state; return 1; } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; + vcpu->run->exit_reason = reason; return 0; } } + +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +{ + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} EXPORT_SYMBOL_GPL(kvm_vcpu_halt); int kvm_emulate_halt(struct kvm_vcpu *vcpu) @@ -8000,6 +8005,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -9096,6 +9109,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9522,8 +9536,9 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && - vcpu->arch.pv.pv_unhalted) + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || + vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && + vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; @@ -10154,6 +10169,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } +EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); int kvm_arch_hardware_enable(void) { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 886802b8ffba..374c67875cdb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -251,6 +251,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 #define KVM_EXIT_DIRTY_RING_FULL 31 +#define KVM_EXIT_AP_RESET_HOLD 32 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -573,6 +574,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_CHECK_STOP 6 #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 +#define KVM_MP_STATE_AP_RESET_HOLD 9 struct kvm_mp_state { __u32 mp_state; -- cgit v1.2.3 From b16671e8f493e3df40b1fb0dff4078f391c5099a Mon Sep 17 00:00:00 2001 From: Coly Li Date: Mon, 4 Jan 2021 15:41:21 +0800 Subject: bcache: introduce BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE for large bucket When large bucket feature was added, BCH_FEATURE_INCOMPAT_LARGE_BUCKET was introduced into the incompat feature set. It used bucket_size_hi (which was added at the tail of struct cache_sb_disk) to extend current 16bit bucket size to 32bit with existing bucket_size in struct cache_sb_disk. This is not a good idea, there are two obvious problems, - Bucket size is always value power of 2, if store log2(bucket size) in existing bucket_size of struct cache_sb_disk, it is unnecessary to add bucket_size_hi. - Macro csum_set() assumes d[SB_JOURNAL_BUCKETS] is the last member in struct cache_sb_disk, bucket_size_hi was added after d[] which makes csum_set calculate an unexpected super block checksum. To fix the above problems, this patch introduces a new incompat feature bit BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, when this bit is set, it means bucket_size in struct cache_sb_disk stores the order of power-of-2 bucket size value. When user specifies a bucket size larger than 32768 sectors, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE will be set to incompat feature set, and bucket_size stores log2(bucket size) more than store the real bucket size value. The obsoleted BCH_FEATURE_INCOMPAT_LARGE_BUCKET won't be used anymore, it is renamed to BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET and still only recognized by kernel driver for legacy compatible purpose. The previous bucket_size_hi is renmaed to obso_bucket_size_hi in struct cache_sb_disk and not used in bcache-tools anymore. For cache device created with BCH_FEATURE_INCOMPAT_LARGE_BUCKET feature, bcache-tools and kernel driver still recognize the feature string and display it as "obso_large_bucket". With this change, the unnecessary extra space extend of bcache on-disk super block can be avoided, and csum_set() may generate expected check sum as well. Fixes: ffa470327572 ("bcache: add bucket_size_hi into struct cache_sb_disk for large bucket") Signed-off-by: Coly Li Cc: stable@vger.kernel.org # 5.9+ Signed-off-by: Jens Axboe --- drivers/md/bcache/features.c | 2 +- drivers/md/bcache/features.h | 11 ++++++++--- drivers/md/bcache/super.c | 22 +++++++++++++++++++--- include/uapi/linux/bcache.h | 2 +- 4 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6469223f0b77..d636b7b2d070 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -17,7 +17,7 @@ struct feature { }; static struct feature feature_list[] = { - {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET, + {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, "large_bucket"}, {0, 0, 0 }, }; diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index e73724c2b49b..84fc2c0f0101 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -13,11 +13,15 @@ /* Feature set definition */ /* Incompat feature set */ -#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET 0x0001 /* 32bit bucket size */ +/* 32bit bucket size, obsoleted */ +#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET 0x0001 +/* real bucket size is (1 << bucket_size) */ +#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE 0x0002 #define BCH_FEATURE_COMPAT_SUPP 0 #define BCH_FEATURE_RO_COMPAT_SUPP 0 -#define BCH_FEATURE_INCOMPAT_SUPP BCH_FEATURE_INCOMPAT_LARGE_BUCKET +#define BCH_FEATURE_INCOMPAT_SUPP (BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \ + BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE) #define BCH_HAS_COMPAT_FEATURE(sb, mask) \ ((sb)->feature_compat & (mask)) @@ -77,7 +81,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \ ~BCH##_FEATURE_INCOMPAT_##flagname; \ } -BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE); static inline bool bch_has_unknown_compat_features(struct cache_sb *sb) { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index f4674a3298af..3999641f1775 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -64,9 +64,25 @@ static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s { unsigned int bucket_size = le16_to_cpu(s->bucket_size); - if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES && - bch_has_feature_large_bucket(sb)) - bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16; + if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) { + if (bch_has_feature_large_bucket(sb)) { + unsigned int max, order; + + max = sizeof(unsigned int) * BITS_PER_BYTE - 1; + order = le16_to_cpu(s->bucket_size); + /* + * bcache tool will make sure the overflow won't + * happen, an error message here is enough. + */ + if (order > max) + pr_err("Bucket size (1 << %u) overflows\n", + order); + bucket_size = 1 << order; + } else if (bch_has_feature_obso_large_bucket(sb)) { + bucket_size += + le16_to_cpu(s->obso_bucket_size_hi) << 16; + } + } return bucket_size; } diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 52e8bcb33981..cf7399f03b71 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -213,7 +213,7 @@ struct cache_sb_disk { __le16 keys; }; __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ - __le16 bucket_size_hi; + __le16 obso_bucket_size_hi; /* obsoleted */ }; /* -- cgit v1.2.3 From a53e3c189cc6460b60e152af3fc24edf8e0ea9d2 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 18 Jan 2021 16:37:00 +0100 Subject: media: v4l2-subdev.h: BIT() is not available in userspace The BIT macro is not available in userspace, so replace BIT(0) by 0x00000001. Signed-off-by: Hans Verkuil Fixes: 6446ec6cbf46 ("media: v4l2-subdev: add VIDIOC_SUBDEV_QUERYCAP ioctl") Cc: Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-subdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 00850b98078a..a38454d9e0f5 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -176,7 +176,7 @@ struct v4l2_subdev_capability { }; /* The v4l2 sub-device video device node is registered in read-only mode. */ -#define V4L2_SUBDEV_CAP_RO_SUBDEV BIT(0) +#define V4L2_SUBDEV_CAP_RO_SUBDEV 0x00000001 /* Backwards compatibility define --- to be removed */ #define v4l2_subdev_edid v4l2_edid -- cgit v1.2.3