From 762b6f00a995863afa274d6b5ffa3880dac1714b Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Wed, 15 Feb 2017 23:04:54 +0300 Subject: uapi: fix linux/target_core_user.h userspace compilation errors Consistently use types from linux/types.h to fix the following linux/target_core_user.h userspace compilation errors: /usr/include/linux/target_core_user.h:108:4: error: unknown type name 'uint32_t' uint32_t iov_cnt; /usr/include/linux/target_core_user.h:109:4: error: unknown type name 'uint32_t' uint32_t iov_bidi_cnt; /usr/include/linux/target_core_user.h:110:4: error: unknown type name 'uint32_t' uint32_t iov_dif_cnt; /usr/include/linux/target_core_user.h:111:4: error: unknown type name 'uint64_t' uint64_t cdb_off; /usr/include/linux/target_core_user.h:112:4: error: unknown type name 'uint64_t' uint64_t __pad1; /usr/include/linux/target_core_user.h:113:4: error: unknown type name 'uint64_t' uint64_t __pad2; /usr/include/linux/target_core_user.h:117:4: error: unknown type name 'uint8_t' uint8_t scsi_status; /usr/include/linux/target_core_user.h:118:4: error: unknown type name 'uint8_t' uint8_t __pad1; /usr/include/linux/target_core_user.h:119:4: error: unknown type name 'uint16_t' uint16_t __pad2; /usr/include/linux/target_core_user.h:120:4: error: unknown type name 'uint32_t' uint32_t __pad3; Signed-off-by: Dmitry V. Levin Signed-off-by: Nicholas Bellinger --- include/uapi/linux/target_core_user.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index c506cddb8165..af17b4154ef6 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -105,26 +105,26 @@ struct tcmu_cmd_entry { union { struct { - uint32_t iov_cnt; - uint32_t iov_bidi_cnt; - uint32_t iov_dif_cnt; - uint64_t cdb_off; - uint64_t __pad1; - uint64_t __pad2; + __u32 iov_cnt; + __u32 iov_bidi_cnt; + __u32 iov_dif_cnt; + __u64 cdb_off; + __u64 __pad1; + __u64 __pad2; struct iovec iov[0]; } req; struct { - uint8_t scsi_status; - uint8_t __pad1; - uint16_t __pad2; - uint32_t __pad3; + __u8 scsi_status; + __u8 __pad1; + __u16 __pad2; + __u32 __pad3; char sense_buffer[TCMU_SENSE_BUFFERSIZE]; } rsp; }; } __packed; -#define TCMU_OP_ALIGN_SIZE sizeof(uint64_t) +#define TCMU_OP_ALIGN_SIZE sizeof(__u64) enum tcmu_genl_cmd { TCMU_CMD_UNSPEC, -- cgit v1.2.3 From 51be7a9a261ce18c520fb3928b168feb77522745 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 12 Jan 2017 23:36:32 +0200 Subject: virtio_mmio: expose header to userspace It's handy for userspace emulators like QEMU. Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/Kbuild | 1 + include/uapi/linux/virtio_mmio.h | 141 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 142 insertions(+) create mode 100644 include/uapi/linux/virtio_mmio.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index f330ba4547cf..718fa73310e1 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -458,6 +458,7 @@ header-y += virtio_console.h header-y += virtio_gpu.h header-y += virtio_ids.h header-y += virtio_input.h +header-y += virtio_mmio.h header-y += virtio_net.h header-y += virtio_pci.h header-y += virtio_ring.h diff --git a/include/uapi/linux/virtio_mmio.h b/include/uapi/linux/virtio_mmio.h new file mode 100644 index 000000000000..c4b09689ab64 --- /dev/null +++ b/include/uapi/linux/virtio_mmio.h @@ -0,0 +1,141 @@ +/* + * Virtio platform device driver + * + * Copyright 2011, ARM Ltd. + * + * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007 + * + * This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef _LINUX_VIRTIO_MMIO_H +#define _LINUX_VIRTIO_MMIO_H + +/* + * Control registers + */ + +/* Magic value ("virt" string) - Read Only */ +#define VIRTIO_MMIO_MAGIC_VALUE 0x000 + +/* Virtio device version - Read Only */ +#define VIRTIO_MMIO_VERSION 0x004 + +/* Virtio device ID - Read Only */ +#define VIRTIO_MMIO_DEVICE_ID 0x008 + +/* Virtio vendor ID - Read Only */ +#define VIRTIO_MMIO_VENDOR_ID 0x00c + +/* Bitmask of the features supported by the device (host) + * (32 bits per set) - Read Only */ +#define VIRTIO_MMIO_DEVICE_FEATURES 0x010 + +/* Device (host) features set selector - Write Only */ +#define VIRTIO_MMIO_DEVICE_FEATURES_SEL 0x014 + +/* Bitmask of features activated by the driver (guest) + * (32 bits per set) - Write Only */ +#define VIRTIO_MMIO_DRIVER_FEATURES 0x020 + +/* Activated features set selector - Write Only */ +#define VIRTIO_MMIO_DRIVER_FEATURES_SEL 0x024 + + +#ifndef VIRTIO_MMIO_NO_LEGACY /* LEGACY DEVICES ONLY! */ + +/* Guest's memory page size in bytes - Write Only */ +#define VIRTIO_MMIO_GUEST_PAGE_SIZE 0x028 + +#endif + + +/* Queue selector - Write Only */ +#define VIRTIO_MMIO_QUEUE_SEL 0x030 + +/* Maximum size of the currently selected queue - Read Only */ +#define VIRTIO_MMIO_QUEUE_NUM_MAX 0x034 + +/* Queue size for the currently selected queue - Write Only */ +#define VIRTIO_MMIO_QUEUE_NUM 0x038 + + +#ifndef VIRTIO_MMIO_NO_LEGACY /* LEGACY DEVICES ONLY! */ + +/* Used Ring alignment for the currently selected queue - Write Only */ +#define VIRTIO_MMIO_QUEUE_ALIGN 0x03c + +/* Guest's PFN for the currently selected queue - Read Write */ +#define VIRTIO_MMIO_QUEUE_PFN 0x040 + +#endif + + +/* Ready bit for the currently selected queue - Read Write */ +#define VIRTIO_MMIO_QUEUE_READY 0x044 + +/* Queue notifier - Write Only */ +#define VIRTIO_MMIO_QUEUE_NOTIFY 0x050 + +/* Interrupt status - Read Only */ +#define VIRTIO_MMIO_INTERRUPT_STATUS 0x060 + +/* Interrupt acknowledge - Write Only */ +#define VIRTIO_MMIO_INTERRUPT_ACK 0x064 + +/* Device status register - Read Write */ +#define VIRTIO_MMIO_STATUS 0x070 + +/* Selected queue's Descriptor Table address, 64 bits in two halves */ +#define VIRTIO_MMIO_QUEUE_DESC_LOW 0x080 +#define VIRTIO_MMIO_QUEUE_DESC_HIGH 0x084 + +/* Selected queue's Available Ring address, 64 bits in two halves */ +#define VIRTIO_MMIO_QUEUE_AVAIL_LOW 0x090 +#define VIRTIO_MMIO_QUEUE_AVAIL_HIGH 0x094 + +/* Selected queue's Used Ring address, 64 bits in two halves */ +#define VIRTIO_MMIO_QUEUE_USED_LOW 0x0a0 +#define VIRTIO_MMIO_QUEUE_USED_HIGH 0x0a4 + +/* Configuration atomicity value */ +#define VIRTIO_MMIO_CONFIG_GENERATION 0x0fc + +/* The config space is defined by each driver as + * the per-driver configuration space - Read Write */ +#define VIRTIO_MMIO_CONFIG 0x100 + + + +/* + * Interrupt flags (re: interrupt status & acknowledge registers) + */ + +#define VIRTIO_MMIO_INT_VRING (1 << 0) +#define VIRTIO_MMIO_INT_CONFIG (1 << 1) + +#endif -- cgit v1.2.3 From 53a020c661741f3b87ad3ac6fa545088aaebac9b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 5 Feb 2017 18:15:20 +0100 Subject: virtio_pci: don't duplicate the msix_enable flag in struct pci_dev Signed-off-by: Christoph Hellwig Reviewed-by: Jason Wang Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 90007a1abcab..15b4385a2be1 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -79,7 +79,7 @@ * configuration space */ #define VIRTIO_PCI_CONFIG_OFF(msix_enabled) ((msix_enabled) ? 24 : 20) /* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */ -#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled) +#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled) /* Virtio ABI version, this must match exactly */ #define VIRTIO_PCI_ABI_VERSION 0 -- cgit v1.2.3 From ae7e81c077d60507dcec139e40a6d10cf932cf4b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 1 Feb 2017 18:07:51 +0100 Subject: sched/headers: Prepare for new header dependencies before moving code to We are going to move scheduler ABI details to , which will be used from a number of .c files. Create empty placeholder header that maps to . Include the new header in the files that are going to need it. Acked-by: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/uapi/linux/sched/types.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/uapi/linux/sched/types.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h new file mode 100644 index 000000000000..d162d315f4b5 --- /dev/null +++ b/include/uapi/linux/sched/types.h @@ -0,0 +1,6 @@ +#ifndef _UAPI_LINUX_SCHED_TYPES_H +#define _UAPI_LINUX_SCHED_TYPES_H + +#include + +#endif /* _UAPI_LINUX_SCHED_TYPES_H */ -- cgit v1.2.3 From e2d1e2aec572a2138dea74d53be54a1406d419c0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 1 Feb 2017 18:07:51 +0100 Subject: sched/headers: Move various ABI definitions to Move scheduler ABI types (struct sched_attr, struct sched_param, etc.) into the new UAPI header. This further reduces the size and complexity of . Acked-by: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/uapi/linux/sched/types.h | 68 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h index d162d315f4b5..307acbc82d80 100644 --- a/include/uapi/linux/sched/types.h +++ b/include/uapi/linux/sched/types.h @@ -3,4 +3,72 @@ #include +struct sched_param { + int sched_priority; +}; + +#define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ + +/* + * Extended scheduling parameters data structure. + * + * This is needed because the original struct sched_param can not be + * altered without introducing ABI issues with legacy applications + * (e.g., in sched_getparam()). + * + * However, the possibility of specifying more than just a priority for + * the tasks may be useful for a wide variety of application fields, e.g., + * multimedia, streaming, automation and control, and many others. + * + * This variant (sched_attr) is meant at describing a so-called + * sporadic time-constrained task. In such model a task is specified by: + * - the activation period or minimum instance inter-arrival time; + * - the maximum (or average, depending on the actual scheduling + * discipline) computation time of all instances, a.k.a. runtime; + * - the deadline (relative to the actual activation time) of each + * instance. + * Very briefly, a periodic (sporadic) task asks for the execution of + * some specific computation --which is typically called an instance-- + * (at most) every period. Moreover, each instance typically lasts no more + * than the runtime and must be completed by time instant t equal to + * the instance activation time + the deadline. + * + * This is reflected by the actual fields of the sched_attr structure: + * + * @size size of the structure, for fwd/bwd compat. + * + * @sched_policy task's scheduling policy + * @sched_flags for customizing the scheduler behaviour + * @sched_nice task's nice value (SCHED_NORMAL/BATCH) + * @sched_priority task's static priority (SCHED_FIFO/RR) + * @sched_deadline representative of the task's deadline + * @sched_runtime representative of the task's runtime + * @sched_period representative of the task's period + * + * Given this task model, there are a multiplicity of scheduling algorithms + * and policies, that can be used to ensure all the tasks will make their + * timing constraints. + * + * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the + * only user of this new interface. More information about the algorithm + * available in the scheduling class file or in Documentation/. + */ +struct sched_attr { + u32 size; + + u32 sched_policy; + u64 sched_flags; + + /* SCHED_NORMAL, SCHED_BATCH */ + s32 sched_nice; + + /* SCHED_FIFO, SCHED_RR */ + u32 sched_priority; + + /* SCHED_DEADLINE */ + u64 sched_runtime; + u64 sched_deadline; + u64 sched_period; +}; + #endif /* _UAPI_LINUX_SCHED_TYPES_H */ -- cgit v1.2.3 From a528d35e8bfcc521d7cb70aaf03e1bd296c8493f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 31 Jan 2017 16:46:22 +0000 Subject: statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells Signed-off-by: Al Viro --- include/uapi/linux/fcntl.h | 5 ++ include/uapi/linux/stat.h | 131 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 136 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index beed138bd359..813afd6eee71 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -63,5 +63,10 @@ #define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */ #define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */ +#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */ +#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */ +#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */ +#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */ + #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 7fec7e36d921..51a6b86e3700 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -1,6 +1,7 @@ #ifndef _UAPI_LINUX_STAT_H #define _UAPI_LINUX_STAT_H +#include #if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) @@ -41,5 +42,135 @@ #endif +/* + * Timestamp structure for the timestamps in struct statx. + * + * tv_sec holds the number of seconds before (negative) or after (positive) + * 00:00:00 1st January 1970 UTC. + * + * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is + * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time. + * + * Note that if both tv_sec and tv_nsec are non-zero, then the two values must + * either be both positive or both negative. + * + * __reserved is held in case we need a yet finer resolution. + */ +struct statx_timestamp { + __s64 tv_sec; + __s32 tv_nsec; + __s32 __reserved; +}; + +/* + * Structures for the extended file attribute retrieval system call + * (statx()). + * + * The caller passes a mask of what they're specifically interested in as a + * parameter to statx(). What statx() actually got will be indicated in + * st_mask upon return. + * + * For each bit in the mask argument: + * + * - if the datum is not supported: + * + * - the bit will be cleared, and + * + * - the datum will be set to an appropriate fabricated value if one is + * available (eg. CIFS can take a default uid and gid), otherwise + * + * - the field will be cleared; + * + * - otherwise, if explicitly requested: + * + * - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is + * set or if the datum is considered out of date, and + * + * - the field will be filled in and the bit will be set; + * + * - otherwise, if not requested, but available in approximate form without any + * effort, it will be filled in anyway, and the bit will be set upon return + * (it might not be up to date, however, and no attempt will be made to + * synchronise the internal state first); + * + * - otherwise the field and the bit will be cleared before returning. + * + * Items in STATX_BASIC_STATS may be marked unavailable on return, but they + * will have values installed for compatibility purposes so that stat() and + * co. can be emulated in userspace. + */ +struct statx { + /* 0x00 */ + __u32 stx_mask; /* What results were written [uncond] */ + __u32 stx_blksize; /* Preferred general I/O size [uncond] */ + __u64 stx_attributes; /* Flags conveying information about the file [uncond] */ + /* 0x10 */ + __u32 stx_nlink; /* Number of hard links */ + __u32 stx_uid; /* User ID of owner */ + __u32 stx_gid; /* Group ID of owner */ + __u16 stx_mode; /* File mode */ + __u16 __spare0[1]; + /* 0x20 */ + __u64 stx_ino; /* Inode number */ + __u64 stx_size; /* File size */ + __u64 stx_blocks; /* Number of 512-byte blocks allocated */ + __u64 __spare1[1]; + /* 0x40 */ + struct statx_timestamp stx_atime; /* Last access time */ + struct statx_timestamp stx_btime; /* File creation time */ + struct statx_timestamp stx_ctime; /* Last attribute change time */ + struct statx_timestamp stx_mtime; /* Last data modification time */ + /* 0x80 */ + __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */ + __u32 stx_rdev_minor; + __u32 stx_dev_major; /* ID of device containing file [uncond] */ + __u32 stx_dev_minor; + /* 0x90 */ + __u64 __spare2[14]; /* Spare space for future expansion */ + /* 0x100 */ +}; + +/* + * Flags to be stx_mask + * + * Query request/result mask for statx() and struct statx::stx_mask. + * + * These bits should be set in the mask argument of statx() to request + * particular items when calling statx(). + */ +#define STATX_TYPE 0x00000001U /* Want/got stx_mode & S_IFMT */ +#define STATX_MODE 0x00000002U /* Want/got stx_mode & ~S_IFMT */ +#define STATX_NLINK 0x00000004U /* Want/got stx_nlink */ +#define STATX_UID 0x00000008U /* Want/got stx_uid */ +#define STATX_GID 0x00000010U /* Want/got stx_gid */ +#define STATX_ATIME 0x00000020U /* Want/got stx_atime */ +#define STATX_MTIME 0x00000040U /* Want/got stx_mtime */ +#define STATX_CTIME 0x00000080U /* Want/got stx_ctime */ +#define STATX_INO 0x00000100U /* Want/got stx_ino */ +#define STATX_SIZE 0x00000200U /* Want/got stx_size */ +#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ +#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ +#define STATX_BTIME 0x00000800U /* Want/got stx_btime */ +#define STATX_ALL 0x00000fffU /* All currently supported flags */ + +/* + * Attributes to be found in stx_attributes + * + * These give information about the features or the state of a file that might + * be of use to ordinary userspace programs such as GUIs or ls rather than + * specialised tools. + * + * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS + * semantically. Where possible, the numerical value is picked to correspond + * also. + */ +#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ +#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ +#define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ +#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ +#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ + +#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ + #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3 From dd0db88d8094a6d9d4d1fc5fcd56ab619f54ccf8 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 9 Mar 2017 16:16:49 -0800 Subject: userfaultfd: non-cooperative: rollback userfaultfd_exit Patch series "userfaultfd non-cooperative further update for 4.11 merge window". Unfortunately I noticed one relevant bug in userfaultfd_exit while doing more testing. I've been doing testing before and this was also tested by kbuild bot and exercised by the selftest, but this bug never reproduced before. I dropped userfaultfd_exit as result. I dropped it because of implementation difficulty in receiving signals in __mmput and because I think -ENOSPC as result from the background UFFDIO_COPY should be enough already. Before I decided to remove userfaultfd_exit, I noticed userfaultfd_exit wasn't exercised by the selftest and when I tried to exercise it, after moving it to a more correct place in __mmput where it would make more sense and where the vma list is stable, it resulted in the event_wait_completion in D state. So then I added the second patch to be sure even if we call userfaultfd_event_wait_completion too late during task exit(), we won't risk to generate tasks in D state. The same check exists in handle_userfault() for the same reason, except it makes a difference there, while here is just a robustness check and it's run under WARN_ON_ONCE. While looking at the userfaultfd_event_wait_completion() function I looked back at its callers too while at it and I think it's not ok to stop executing dup_fctx on the fcs list because we relay on userfaultfd_event_wait_completion to execute userfaultfd_ctx_put(fctx->orig) which is paired against userfaultfd_ctx_get(fctx->orig) in dup_userfault just before list_add(fcs). This change only takes care of fctx->orig but this area also needs further review looking for similar problems in fctx->new. The only patch that is urgent is the first because it's an use after free during a SMP race condition that affects all processes if CONFIG_USERFAULTFD=y. Very hard to reproduce though and probably impossible without SLUB poisoning enabled. This patch (of 3): I once reproduced this oops with the userfaultfd selftest, it's not easily reproducible and it requires SLUB poisoning to reproduce. general protection fault: 0000 [#1] SMP Modules linked in: CPU: 2 PID: 18421 Comm: userfaultfd Tainted: G ------------ T 3.10.0+ #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 task: ffff8801f83b9440 ti: ffff8801f833c000 task.ti: ffff8801f833c000 RIP: 0010:[] [] userfaultfd_exit+0x29/0xa0 RSP: 0018:ffff8801f833fe80 EFLAGS: 00010202 RAX: ffff8801f833ffd8 RBX: 6b6b6b6b6b6b6b6b RCX: ffff8801f83b9440 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800baf18600 RBP: ffff8801f833fee8 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: ffffffff8127ceb3 R12: 0000000000000000 R13: ffff8800baf186b0 R14: ffff8801f83b99f8 R15: 00007faed746c700 FS: 0000000000000000(0000) GS:ffff88023fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007faf0966f028 CR3: 0000000001bc6000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: do_exit+0x297/0xd10 SyS_exit+0x17/0x20 tracesys+0xdd/0xe2 Code: 00 00 66 66 66 66 90 55 48 89 e5 41 54 53 48 83 ec 58 48 8b 1f 48 85 db 75 11 eb 73 66 0f 1f 44 00 00 48 8b 5b 10 48 85 db 74 64 <4c> 8b a3 b8 00 00 00 4d 85 e4 74 eb 41 f6 84 24 2c 01 00 00 80 RIP [] userfaultfd_exit+0x29/0xa0 RSP ---[ end trace 9fecd6dcb442846a ]--- In the debugger I located the "mm" pointer in the stack and walking mm->mmap->vm_next through the end shows the vma->vm_next list is fully consistent and it is null terminated list as expected. So this has to be an SMP race condition where userfaultfd_exit was running while the vma list was being modified by another CPU. When userfaultfd_exit() run one of the ->vm_next pointers pointed to SLAB_POISON (RBX is the vma pointer and is 0x6b6b..). The reason is that it's not running in __mmput but while there are still other threads running and it's not holding the mmap_sem (it can't as it has to wait the even to be received by the manager). So this is an use after free that was happening for all processes. One more implementation problem aside from the race condition: userfaultfd_exit has really to check a flag in mm->flags before walking the vma or it's going to slowdown the exit() path for regular tasks. One more implementation problem: at that point signals can't be delivered so it would also create a task in D state if the manager doesn't read the event. The major design issue: it overall looks superfluous as the manager can check for -ENOSPC in the background transfer: if (mmget_not_zero(ctx->mm)) { [..] } else { return -ENOSPC; } It's safer to roll it back and re-introduce it later if at all. [rppt@linux.vnet.ibm.com: documentation fixup after removal of UFFD_EVENT_EXIT] Link: http://lkml.kernel.org/r/1488345437-4364-1-git-send-email-rppt@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/20170224181957.19736-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: Mike Rapoport Acked-by: Mike Rapoport Cc: "Dr. David Alan Gilbert" Cc: Mike Kravetz Cc: Pavel Emelyanov Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index c055947c5c98..3b059530dac9 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -18,8 +18,7 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) -#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT | \ - UFFD_FEATURE_EVENT_FORK | \ +#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ @@ -113,7 +112,6 @@ struct uffd_msg { #define UFFD_EVENT_REMAP 0x14 #define UFFD_EVENT_REMOVE 0x15 #define UFFD_EVENT_UNMAP 0x16 -#define UFFD_EVENT_EXIT 0x17 /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ @@ -163,7 +161,6 @@ struct uffdio_api { #define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) #define UFFD_FEATURE_MISSING_SHMEM (1<<5) #define UFFD_FEATURE_EVENT_UNMAP (1<<6) -#define UFFD_FEATURE_EVENT_EXIT (1<<7) __u64 features; __u64 ioctls; -- cgit v1.2.3