From 40e041a2c858b3caefc757e26cb85bfceae5062b Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 8 Aug 2014 14:25:27 -0700 Subject: shm: add sealing API If two processes share a common memory region, they usually want some guarantees to allow safe access. This often includes: - one side cannot overwrite data while the other reads it - one side cannot shrink the buffer while the other accesses it - one side cannot grow the buffer beyond previously set boundaries If there is a trust-relationship between both parties, there is no need for policy enforcement. However, if there's no trust relationship (eg., for general-purpose IPC) sharing memory-regions is highly fragile and often not possible without local copies. Look at the following two use-cases: 1) A graphics client wants to share its rendering-buffer with a graphics-server. The memory-region is allocated by the client for read/write access and a second FD is passed to the server. While scanning out from the memory region, the server has no guarantee that the client doesn't shrink the buffer at any time, requiring rather cumbersome SIGBUS handling. 2) A process wants to perform an RPC on another process. To avoid huge bandwidth consumption, zero-copy is preferred. After a message is assembled in-memory and a FD is passed to the remote side, both sides want to be sure that neither modifies this shared copy, anymore. The source may have put sensible data into the message without a separate copy and the target may want to parse the message inline, to avoid a local copy. While SIGBUS handling, POSIX mandatory locking and MAP_DENYWRITE provide ways to achieve most of this, the first one is unproportionally ugly to use in libraries and the latter two are broken/racy or even disabled due to denial of service attacks. This patch introduces the concept of SEALING. If you seal a file, a specific set of operations is blocked on that file forever. Unlike locks, seals can only be set, never removed. Hence, once you verified a specific set of seals is set, you're guaranteed that no-one can perform the blocked operations on this file, anymore. An initial set of SEALS is introduced by this patch: - SHRINK: If SEAL_SHRINK is set, the file in question cannot be reduced in size. This affects ftruncate() and open(O_TRUNC). - GROW: If SEAL_GROW is set, the file in question cannot be increased in size. This affects ftruncate(), fallocate() and write(). - WRITE: If SEAL_WRITE is set, no write operations (besides resizing) are possible. This affects fallocate(PUNCH_HOLE), mmap() and write(). - SEAL: If SEAL_SEAL is set, no further seals can be added to a file. This basically prevents the F_ADD_SEAL operation on a file and can be set to prevent others from adding further seals that you don't want. The described use-cases can easily use these seals to provide safe use without any trust-relationship: 1) The graphics server can verify that a passed file-descriptor has SEAL_SHRINK set. This allows safe scanout, while the client is allowed to increase buffer size for window-resizing on-the-fly. Concurrent writes are explicitly allowed. 2) For general-purpose IPC, both processes can verify that SEAL_SHRINK, SEAL_GROW and SEAL_WRITE are set. This guarantees that neither process can modify the data while the other side parses it. Furthermore, it guarantees that even with writable FDs passed to the peer, it cannot increase the size to hit memory-limits of the source process (in case the file-storage is accounted to the source). The new API is an extension to fcntl(), adding two new commands: F_GET_SEALS: Return a bitset describing the seals on the file. This can be called on any FD if the underlying file supports sealing. F_ADD_SEALS: Change the seals of a given file. This requires WRITE access to the file and F_SEAL_SEAL may not already be set. Furthermore, the underlying file must support sealing and there may not be any existing shared mapping of that file. Otherwise, EBADF/EPERM is returned. The given seals are _added_ to the existing set of seals on the file. You cannot remove seals again. The fcntl() handler is currently specific to shmem and disabled on all files. A file needs to explicitly support sealing for this interface to work. A separate syscall is added in a follow-up, which creates files that support sealing. There is no intention to support this on other file-systems. Semantics are unclear for non-volatile files and we lack any use-case right now. Therefore, the implementation is specific to shmem. Signed-off-by: David Herrmann Acked-by: Hugh Dickins Cc: Michael Kerrisk Cc: Ryan Lortie Cc: Lennart Poettering Cc: Daniel Mack Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/fcntl.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 074b886c6be0..beed138bd359 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -27,6 +27,21 @@ #define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7) #define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8) +/* + * Set/Get seals + */ +#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9) +#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10) + +/* + * Types of seals + */ +#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */ +#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ +#define F_SEAL_GROW 0x0004 /* prevent file from growing */ +#define F_SEAL_WRITE 0x0008 /* prevent writes */ +/* (1U << 31) is reserved for signed error codes */ + /* * Types of directory notifications that may be requested. */ -- cgit v1.2.3 From 9183df25fe7b194563db3fec6dc3202a5855839c Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 8 Aug 2014 14:25:29 -0700 Subject: shm: add memfd_create() syscall memfd_create() is similar to mmap(MAP_ANON), but returns a file-descriptor that you can pass to mmap(). It can support sealing and avoids any connection to user-visible mount-points. Thus, it's not subject to quotas on mounted file-systems, but can be used like malloc()'ed memory, but with a file-descriptor to it. memfd_create() returns the raw shmem file, so calls like ftruncate() can be used to modify the underlying inode. Also calls like fstat() will return proper information and mark the file as regular file. If you want sealing, you can specify MFD_ALLOW_SEALING. Otherwise, sealing is not supported (like on all other regular files). Compared to O_TMPFILE, it does not require a tmpfs mount-point and is not subject to a filesystem size limit. It is still properly accounted to memcg limits, though, and to the same overcommit or no-overcommit accounting as all user memory. Signed-off-by: David Herrmann Acked-by: Hugh Dickins Cc: Michael Kerrisk Cc: Ryan Lortie Cc: Lennart Poettering Cc: Daniel Mack Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/syscalls/syscall_32.tbl | 1 + arch/x86/syscalls/syscall_64.tbl | 1 + include/linux/syscalls.h | 1 + include/uapi/linux/memfd.h | 8 +++++ kernel/sys_ni.c | 1 + mm/shmem.c | 73 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 85 insertions(+) create mode 100644 include/uapi/linux/memfd.h (limited to 'include/uapi/linux') diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index d1b4a119d4a5..028b78168d85 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -362,3 +362,4 @@ 353 i386 renameat2 sys_renameat2 354 i386 seccomp sys_seccomp 355 i386 getrandom sys_getrandom +356 i386 memfd_create sys_memfd_create diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 252c804bb1aa..ca2b9aa78c81 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -325,6 +325,7 @@ 316 common renameat2 sys_renameat2 317 common seccomp sys_seccomp 318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 701daff5d899..15a069425cbf 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -802,6 +802,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); asmlinkage long sys_eventfd(unsigned int count); asmlinkage long sys_eventfd2(unsigned int count, int flags); +asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h new file mode 100644 index 000000000000..534e364bda92 --- /dev/null +++ b/include/uapi/linux/memfd.h @@ -0,0 +1,8 @@ +#ifndef _UAPI_LINUX_MEMFD_H +#define _UAPI_LINUX_MEMFD_H + +/* flags for memfd_create(2) (unsigned int) */ +#define MFD_CLOEXEC 0x0001U +#define MFD_ALLOW_SEALING 0x0002U + +#endif /* _UAPI_LINUX_MEMFD_H */ diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 2904a2105914..1f79e3714533 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -197,6 +197,7 @@ cond_syscall(compat_sys_timerfd_settime); cond_syscall(compat_sys_timerfd_gettime); cond_syscall(sys_eventfd); cond_syscall(sys_eventfd2); +cond_syscall(sys_memfd_create); /* performance counters: */ cond_syscall(sys_perf_event_open); diff --git a/mm/shmem.c b/mm/shmem.c index 8b43bb7a4efe..4a5498795a2b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -66,7 +66,9 @@ static struct vfsmount *shm_mnt; #include #include #include +#include #include +#include #include #include @@ -2732,6 +2734,77 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) shmem_show_mpol(seq, sbinfo->mpol); return 0; } + +#define MFD_NAME_PREFIX "memfd:" +#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) +#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) + +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING) + +SYSCALL_DEFINE2(memfd_create, + const char __user *, uname, + unsigned int, flags) +{ + struct shmem_inode_info *info; + struct file *file; + int fd, error; + char *name; + long len; + + if (flags & ~(unsigned int)MFD_ALL_FLAGS) + return -EINVAL; + + /* length includes terminating zero */ + len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); + if (len <= 0) + return -EFAULT; + if (len > MFD_NAME_MAX_LEN + 1) + return -EINVAL; + + name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_TEMPORARY); + if (!name) + return -ENOMEM; + + strcpy(name, MFD_NAME_PREFIX); + if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) { + error = -EFAULT; + goto err_name; + } + + /* terminating-zero may have changed after strnlen_user() returned */ + if (name[len + MFD_NAME_PREFIX_LEN - 1]) { + error = -EFAULT; + goto err_name; + } + + fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); + if (fd < 0) { + error = fd; + goto err_name; + } + + file = shmem_file_setup(name, 0, VM_NORESERVE); + if (IS_ERR(file)) { + error = PTR_ERR(file); + goto err_fd; + } + info = SHMEM_I(file_inode(file)); + file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; + file->f_flags |= O_RDWR | O_LARGEFILE; + if (flags & MFD_ALLOW_SEALING) + info->seals &= ~F_SEAL_SEAL; + + fd_install(fd, file); + kfree(name); + return fd; + +err_fd: + put_unused_fd(fd); +err_name: + kfree(name); + return error; +} + #endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) -- cgit v1.2.3 From cb1052581e2bddd6096544f3f944f4e7fdad4c7f Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Fri, 8 Aug 2014 14:25:57 -0700 Subject: kexec: implementation of new syscall kexec_file_load Previous patch provided the interface definition and this patch prvides implementation of new syscall. Previously segment list was prepared in user space. Now user space just passes kernel fd, initrd fd and command line and kernel will create a segment list internally. This patch contains generic part of the code. Actual segment preparation and loading is done by arch and image specific loader. Which comes in next patch. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Vivek Goyal Cc: Borislav Petkov Cc: Michael Kerrisk Cc: Yinghai Lu Cc: Eric Biederman Cc: H. Peter Anvin Cc: Matthew Garrett Cc: Greg Kroah-Hartman Cc: Dave Young Cc: WANG Chao Cc: Baoquan He Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/machine_kexec_64.c | 45 ++++ include/linux/kexec.h | 53 ++++ include/uapi/linux/kexec.h | 11 + kernel/kexec.c | 483 ++++++++++++++++++++++++++++++++++++- 4 files changed, 587 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 679cef0791cd..c8875b5545e1 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -22,6 +22,10 @@ #include #include +static struct kexec_file_ops *kexec_file_loaders[] = { + NULL, +}; + static void free_transition_pgtable(struct kimage *image) { free_page((unsigned long)image->arch.pud); @@ -283,3 +287,44 @@ void arch_crash_save_vmcoreinfo(void) (unsigned long)&_text - __START_KERNEL); } +/* arch-dependent functionality related to kexec file-based syscall */ + +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + int i, ret = -ENOEXEC; + struct kexec_file_ops *fops; + + for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { + fops = kexec_file_loaders[i]; + if (!fops || !fops->probe) + continue; + + ret = fops->probe(buf, buf_len); + if (!ret) { + image->fops = fops; + return ret; + } + } + + return ret; +} + +void *arch_kexec_kernel_image_load(struct kimage *image) +{ + if (!image->fops || !image->fops->load) + return ERR_PTR(-ENOEXEC); + + return image->fops->load(image, image->kernel_buf, + image->kernel_buf_len, image->initrd_buf, + image->initrd_buf_len, image->cmdline_buf, + image->cmdline_buf_len); +} + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + if (!image->fops || !image->fops->cleanup) + return 0; + + return image->fops->cleanup(image); +} diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 66d56ac0f64c..8e80901e466f 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -121,13 +121,57 @@ struct kimage { #define KEXEC_TYPE_DEFAULT 0 #define KEXEC_TYPE_CRASH 1 unsigned int preserve_context : 1; + /* If set, we are using file mode kexec syscall */ + unsigned int file_mode:1; #ifdef ARCH_HAS_KIMAGE_ARCH struct kimage_arch arch; #endif + + /* Additional fields for file based kexec syscall */ + void *kernel_buf; + unsigned long kernel_buf_len; + + void *initrd_buf; + unsigned long initrd_buf_len; + + char *cmdline_buf; + unsigned long cmdline_buf_len; + + /* File operations provided by image loader */ + struct kexec_file_ops *fops; + + /* Image loader handling the kernel can store a pointer here */ + void *image_loader_data; }; +/* + * Keeps track of buffer parameters as provided by caller for requesting + * memory placement of buffer. + */ +struct kexec_buf { + struct kimage *image; + char *buffer; + unsigned long bufsz; + unsigned long memsz; + unsigned long buf_align; + unsigned long buf_min; + unsigned long buf_max; + bool top_down; /* allocate from top of memory hole */ +}; +typedef int (kexec_probe_t)(const char *kernel_buf, unsigned long kernel_size); +typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len); +typedef int (kexec_cleanup_t)(struct kimage *image); + +struct kexec_file_ops { + kexec_probe_t *probe; + kexec_load_t *load; + kexec_cleanup_t *cleanup; +}; /* kexec interface functions */ extern void machine_kexec(struct kimage *image); @@ -138,6 +182,11 @@ extern asmlinkage long sys_kexec_load(unsigned long entry, struct kexec_segment __user *segments, unsigned long flags); extern int kernel_kexec(void); +extern int kexec_add_buffer(struct kimage *image, char *buffer, + unsigned long bufsz, unsigned long memsz, + unsigned long buf_align, unsigned long buf_min, + unsigned long buf_max, bool top_down, + unsigned long *load_addr); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); extern void crash_kexec(struct pt_regs *); @@ -188,6 +237,10 @@ extern int kexec_load_disabled; #define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT) #endif +/* List of defined/legal kexec file flags */ +#define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ + KEXEC_FILE_NO_INITRAMFS) + #define VMCOREINFO_BYTES (4096) #define VMCOREINFO_NOTE_NAME "VMCOREINFO" #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index d6629d49a243..6925f5b42f89 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -13,6 +13,17 @@ #define KEXEC_PRESERVE_CONTEXT 0x00000002 #define KEXEC_ARCH_MASK 0xffff0000 +/* + * Kexec file load interface flags. + * KEXEC_FILE_UNLOAD : Unload already loaded kexec/kdump image. + * KEXEC_FILE_ON_CRASH : Load/unload operation belongs to kdump image. + * KEXEC_FILE_NO_INITRAMFS : No initramfs is being loaded. Ignore the initrd + * fd field. + */ +#define KEXEC_FILE_UNLOAD 0x00000001 +#define KEXEC_FILE_ON_CRASH 0x00000002 +#define KEXEC_FILE_NO_INITRAMFS 0x00000004 + /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. */ diff --git a/kernel/kexec.c b/kernel/kexec.c index ec4386c1b94f..9b46219254dd 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -6,6 +6,8 @@ * Version 2. See the file COPYING for more details. */ +#define pr_fmt(fmt) "kexec: " fmt + #include #include #include @@ -327,6 +329,221 @@ out_free_image: return ret; } +static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len) +{ + struct fd f = fdget(fd); + int ret; + struct kstat stat; + loff_t pos; + ssize_t bytes = 0; + + if (!f.file) + return -EBADF; + + ret = vfs_getattr(&f.file->f_path, &stat); + if (ret) + goto out; + + if (stat.size > INT_MAX) { + ret = -EFBIG; + goto out; + } + + /* Don't hand 0 to vmalloc, it whines. */ + if (stat.size == 0) { + ret = -EINVAL; + goto out; + } + + *buf = vmalloc(stat.size); + if (!*buf) { + ret = -ENOMEM; + goto out; + } + + pos = 0; + while (pos < stat.size) { + bytes = kernel_read(f.file, pos, (char *)(*buf) + pos, + stat.size - pos); + if (bytes < 0) { + vfree(*buf); + ret = bytes; + goto out; + } + + if (bytes == 0) + break; + pos += bytes; + } + + if (pos != stat.size) { + ret = -EBADF; + vfree(*buf); + goto out; + } + + *buf_len = pos; +out: + fdput(f); + return ret; +} + +/* Architectures can provide this probe function */ +int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + return -ENOEXEC; +} + +void * __weak arch_kexec_kernel_image_load(struct kimage *image) +{ + return ERR_PTR(-ENOEXEC); +} + +void __weak arch_kimage_file_post_load_cleanup(struct kimage *image) +{ +} + +/* + * Free up memory used by kernel, initrd, and comand line. This is temporary + * memory allocation which is not needed any more after these buffers have + * been loaded into separate segments and have been copied elsewhere. + */ +static void kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->kernel_buf); + image->kernel_buf = NULL; + + vfree(image->initrd_buf); + image->initrd_buf = NULL; + + kfree(image->cmdline_buf); + image->cmdline_buf = NULL; + + /* See if architecture has anything to cleanup post load */ + arch_kimage_file_post_load_cleanup(image); +} + +/* + * In file mode list of segments is prepared by kernel. Copy relevant + * data from user space, do error checking, prepare segment list + */ +static int +kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, + const char __user *cmdline_ptr, + unsigned long cmdline_len, unsigned flags) +{ + int ret = 0; + void *ldata; + + ret = copy_file_from_fd(kernel_fd, &image->kernel_buf, + &image->kernel_buf_len); + if (ret) + return ret; + + /* Call arch image probe handlers */ + ret = arch_kexec_kernel_image_probe(image, image->kernel_buf, + image->kernel_buf_len); + + if (ret) + goto out; + + /* It is possible that there no initramfs is being loaded */ + if (!(flags & KEXEC_FILE_NO_INITRAMFS)) { + ret = copy_file_from_fd(initrd_fd, &image->initrd_buf, + &image->initrd_buf_len); + if (ret) + goto out; + } + + if (cmdline_len) { + image->cmdline_buf = kzalloc(cmdline_len, GFP_KERNEL); + if (!image->cmdline_buf) { + ret = -ENOMEM; + goto out; + } + + ret = copy_from_user(image->cmdline_buf, cmdline_ptr, + cmdline_len); + if (ret) { + ret = -EFAULT; + goto out; + } + + image->cmdline_buf_len = cmdline_len; + + /* command line should be a string with last byte null */ + if (image->cmdline_buf[cmdline_len - 1] != '\0') { + ret = -EINVAL; + goto out; + } + } + + /* Call arch image load handlers */ + ldata = arch_kexec_kernel_image_load(image); + + if (IS_ERR(ldata)) { + ret = PTR_ERR(ldata); + goto out; + } + + image->image_loader_data = ldata; +out: + /* In case of error, free up all allocated memory in this function */ + if (ret) + kimage_file_post_load_cleanup(image); + return ret; +} + +static int +kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, + int initrd_fd, const char __user *cmdline_ptr, + unsigned long cmdline_len, unsigned long flags) +{ + int ret; + struct kimage *image; + + image = do_kimage_alloc_init(); + if (!image) + return -ENOMEM; + + image->file_mode = 1; + + ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd, + cmdline_ptr, cmdline_len, flags); + if (ret) + goto out_free_image; + + ret = sanity_check_segment_list(image); + if (ret) + goto out_free_post_load_bufs; + + ret = -ENOMEM; + image->control_code_page = kimage_alloc_control_pages(image, + get_order(KEXEC_CONTROL_PAGE_SIZE)); + if (!image->control_code_page) { + pr_err("Could not allocate control_code_buffer\n"); + goto out_free_post_load_bufs; + } + + image->swap_page = kimage_alloc_control_pages(image, 0); + if (!image->swap_page) { + pr_err(KERN_ERR "Could not allocate swap buffer\n"); + goto out_free_control_pages; + } + + *rimage = image; + return 0; +out_free_control_pages: + kimage_free_page_list(&image->control_pages); +out_free_post_load_bufs: + kimage_file_post_load_cleanup(image); + kfree(image->image_loader_data); +out_free_image: + kfree(image); + return ret; +} + static int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end) @@ -644,6 +861,16 @@ static void kimage_free(struct kimage *image) /* Free the kexec control pages... */ kimage_free_page_list(&image->control_pages); + + kfree(image->image_loader_data); + + /* + * Free up any temporary buffers allocated. This might hit if + * error occurred much later after buffer allocation. + */ + if (image->file_mode) + kimage_file_post_load_cleanup(image); + kfree(image); } @@ -772,10 +999,14 @@ static int kimage_load_normal_segment(struct kimage *image, unsigned long maddr; size_t ubytes, mbytes; int result; - unsigned char __user *buf; + unsigned char __user *buf = NULL; + unsigned char *kbuf = NULL; result = 0; - buf = segment->buf; + if (image->file_mode) + kbuf = segment->kbuf; + else + buf = segment->buf; ubytes = segment->bufsz; mbytes = segment->memsz; maddr = segment->mem; @@ -807,7 +1038,11 @@ static int kimage_load_normal_segment(struct kimage *image, PAGE_SIZE - (maddr & ~PAGE_MASK)); uchunk = min(ubytes, mchunk); - result = copy_from_user(ptr, buf, uchunk); + /* For file based kexec, source pages are in kernel memory */ + if (image->file_mode) + memcpy(ptr, kbuf, uchunk); + else + result = copy_from_user(ptr, buf, uchunk); kunmap(page); if (result) { result = -EFAULT; @@ -815,7 +1050,10 @@ static int kimage_load_normal_segment(struct kimage *image, } ubytes -= uchunk; maddr += mchunk; - buf += mchunk; + if (image->file_mode) + kbuf += mchunk; + else + buf += mchunk; mbytes -= mchunk; } out: @@ -1062,7 +1300,72 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags) { - return -ENOSYS; + int ret = 0, i; + struct kimage **dest_image, *image; + + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return -EPERM; + + /* Make sure we have a legal set of flags */ + if (flags != (flags & KEXEC_FILE_FLAGS)) + return -EINVAL; + + image = NULL; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + + dest_image = &kexec_image; + if (flags & KEXEC_FILE_ON_CRASH) + dest_image = &kexec_crash_image; + + if (flags & KEXEC_FILE_UNLOAD) + goto exchange; + + /* + * In case of crash, new kernel gets loaded in reserved region. It is + * same memory where old crash kernel might be loaded. Free any + * current crash dump kernel before we corrupt it. + */ + if (flags & KEXEC_FILE_ON_CRASH) + kimage_free(xchg(&kexec_crash_image, NULL)); + + ret = kimage_file_alloc_init(&image, kernel_fd, initrd_fd, cmdline_ptr, + cmdline_len, flags); + if (ret) + goto out; + + ret = machine_kexec_prepare(image); + if (ret) + goto out; + + for (i = 0; i < image->nr_segments; i++) { + struct kexec_segment *ksegment; + + ksegment = &image->segment[i]; + pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n", + i, ksegment->buf, ksegment->bufsz, ksegment->mem, + ksegment->memsz); + + ret = kimage_load_segment(image, &image->segment[i]); + if (ret) + goto out; + } + + kimage_terminate(image); + + /* + * Free up any temporary buffers allocated which are not needed + * after image has been loaded + */ + kimage_file_post_load_cleanup(image); +exchange: + image = xchg(dest_image, image); +out: + mutex_unlock(&kexec_mutex); + kimage_free(image); + return ret; } void crash_kexec(struct pt_regs *regs) @@ -1620,6 +1923,176 @@ static int __init crash_save_vmcoreinfo_init(void) subsys_initcall(crash_save_vmcoreinfo_init); +static int __kexec_add_segment(struct kimage *image, char *buf, + unsigned long bufsz, unsigned long mem, + unsigned long memsz) +{ + struct kexec_segment *ksegment; + + ksegment = &image->segment[image->nr_segments]; + ksegment->kbuf = buf; + ksegment->bufsz = bufsz; + ksegment->mem = mem; + ksegment->memsz = memsz; + image->nr_segments++; + + return 0; +} + +static int locate_mem_hole_top_down(unsigned long start, unsigned long end, + struct kexec_buf *kbuf) +{ + struct kimage *image = kbuf->image; + unsigned long temp_start, temp_end; + + temp_end = min(end, kbuf->buf_max); + temp_start = temp_end - kbuf->memsz; + + do { + /* align down start */ + temp_start = temp_start & (~(kbuf->buf_align - 1)); + + if (temp_start < start || temp_start < kbuf->buf_min) + return 0; + + temp_end = temp_start + kbuf->memsz - 1; + + /* + * Make sure this does not conflict with any of existing + * segments + */ + if (kimage_is_destination_range(image, temp_start, temp_end)) { + temp_start = temp_start - PAGE_SIZE; + continue; + } + + /* We found a suitable memory range */ + break; + } while (1); + + /* If we are here, we found a suitable memory range */ + __kexec_add_segment(image, kbuf->buffer, kbuf->bufsz, temp_start, + kbuf->memsz); + + /* Success, stop navigating through remaining System RAM ranges */ + return 1; +} + +static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end, + struct kexec_buf *kbuf) +{ + struct kimage *image = kbuf->image; + unsigned long temp_start, temp_end; + + temp_start = max(start, kbuf->buf_min); + + do { + temp_start = ALIGN(temp_start, kbuf->buf_align); + temp_end = temp_start + kbuf->memsz - 1; + + if (temp_end > end || temp_end > kbuf->buf_max) + return 0; + /* + * Make sure this does not conflict with any of existing + * segments + */ + if (kimage_is_destination_range(image, temp_start, temp_end)) { + temp_start = temp_start + PAGE_SIZE; + continue; + } + + /* We found a suitable memory range */ + break; + } while (1); + + /* If we are here, we found a suitable memory range */ + __kexec_add_segment(image, kbuf->buffer, kbuf->bufsz, temp_start, + kbuf->memsz); + + /* Success, stop navigating through remaining System RAM ranges */ + return 1; +} + +static int locate_mem_hole_callback(u64 start, u64 end, void *arg) +{ + struct kexec_buf *kbuf = (struct kexec_buf *)arg; + unsigned long sz = end - start + 1; + + /* Returning 0 will take to next memory range */ + if (sz < kbuf->memsz) + return 0; + + if (end < kbuf->buf_min || start > kbuf->buf_max) + return 0; + + /* + * Allocate memory top down with-in ram range. Otherwise bottom up + * allocation. + */ + if (kbuf->top_down) + return locate_mem_hole_top_down(start, end, kbuf); + return locate_mem_hole_bottom_up(start, end, kbuf); +} + +/* + * Helper function for placing a buffer in a kexec segment. This assumes + * that kexec_mutex is held. + */ +int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz, + unsigned long memsz, unsigned long buf_align, + unsigned long buf_min, unsigned long buf_max, + bool top_down, unsigned long *load_addr) +{ + + struct kexec_segment *ksegment; + struct kexec_buf buf, *kbuf; + int ret; + + /* Currently adding segment this way is allowed only in file mode */ + if (!image->file_mode) + return -EINVAL; + + if (image->nr_segments >= KEXEC_SEGMENT_MAX) + return -EINVAL; + + /* + * Make sure we are not trying to add buffer after allocating + * control pages. All segments need to be placed first before + * any control pages are allocated. As control page allocation + * logic goes through list of segments to make sure there are + * no destination overlaps. + */ + if (!list_empty(&image->control_pages)) { + WARN_ON(1); + return -EINVAL; + } + + memset(&buf, 0, sizeof(struct kexec_buf)); + kbuf = &buf; + kbuf->image = image; + kbuf->buffer = buffer; + kbuf->bufsz = bufsz; + + kbuf->memsz = ALIGN(memsz, PAGE_SIZE); + kbuf->buf_align = max(buf_align, PAGE_SIZE); + kbuf->buf_min = buf_min; + kbuf->buf_max = buf_max; + kbuf->top_down = top_down; + + /* Walk the RAM ranges and allocate a suitable range for the buffer */ + ret = walk_system_ram_res(0, -1, kbuf, locate_mem_hole_callback); + if (ret != 1) { + /* A suitable memory range could not be found for buffer */ + return -EADDRNOTAVAIL; + } + + /* Found a suitable memory range */ + ksegment = &image->segment[image->nr_segments - 1]; + *load_addr = ksegment->mem; + return 0; +} + + /* * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. -- cgit v1.2.3