From 04ed9642370b4a4c066364b78e628422e3f5644a Mon Sep 17 00:00:00 2001 From: Christopher Yeoh Date: Wed, 3 Aug 2011 10:52:48 +1000 Subject: [PATCH] - Add x86_64 specific wire up - Change behaviour so process_vm_readv and process_vm_writev return the number of bytes successfully read or written even if an error occurs - Add more kernel doc interface comments - rename some internal functions (process_vm_rw_check_iovecs, process_vm_rw) so they make more sense. - Add licence message - Fix kernel-doc comment format Still need to do benchmarking to see if the optimisation for small copies using a local on-stack array in process_vm_rw_core is worth it. Signed-off-by: Chris Yeoh Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: Randy Dunlap Signed-off-by: Andrew Morton --- arch/x86/ia32/ia32entry.S | 2 + arch/x86/include/asm/unistd_64.h | 4 + kernel/sys_ni.c | 4 + mm/process_vm_access.c | 203 +++++++++++++++++++------------ 4 files changed, 132 insertions(+), 81 deletions(-) diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index a0e866d233ee..6a177c529161 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -850,4 +850,6 @@ ia32_sys_call_table: .quad sys_syncfs .quad compat_sys_sendmmsg /* 345 */ .quad sys_setns + .quad compat_sys_process_vm_readv + .quad compat_sys_process_vm_writev ia32_syscall_end: diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 705bf139288c..1f1d1efad0e6 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -681,6 +681,10 @@ __SYSCALL(__NR_syncfs, sys_syncfs) __SYSCALL(__NR_sendmmsg, sys_sendmmsg) #define __NR_setns 308 __SYSCALL(__NR_setns, sys_setns) +#define __NR_process_vm_readv 309 +__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) +#define __NR_process_vm_writev 310 +__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 62cbc8877fef..7a34e9fcc816 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -146,6 +146,10 @@ cond_syscall(sys_io_submit); cond_syscall(sys_io_cancel); cond_syscall(sys_io_getevents); cond_syscall(sys_syslog); +cond_syscall(sys_process_vm_readv); +cond_syscall(sys_process_vm_writev); +cond_syscall(compat_sys_process_vm_readv); +cond_syscall(compat_sys_process_vm_writev); /* arch-specific weak syscall entries */ cond_syscall(sys_pciconfig_read); diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 0df769664925..5ac8abc0d09b 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -1,7 +1,12 @@ /* - * linux/mm/process_vm_access.c + * linux/mm/process_vm_access.c * - * Copyright (C) 2010-2011 Christopher Yeoh , IBM Corp. + * Copyright (C) 2010-2011 Christopher Yeoh , IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. */ #include @@ -16,7 +21,7 @@ #include #endif -/* +/** * process_vm_rw_pages - read/write pages from task specified * @task: task to read/write from * @mm: mm for task @@ -31,19 +36,22 @@ * @lvec_offset: offset in bytes from current iovec iov_base we are up to * @vm_write: 0 means copy from, 1 means copy to * @nr_pages_to_copy: number of pages to copy + * @bytes_copied: returns number of bytes successfully copied + * Returns 0 on success, error code otherwise */ -static ssize_t process_vm_rw_pages(struct task_struct *task, - struct mm_struct *mm, - struct page **process_pages, - unsigned long pa, - unsigned long start_offset, - unsigned long len, - const struct iovec *lvec, - unsigned long lvec_cnt, - unsigned long *lvec_current, - size_t *lvec_offset, - int vm_write, - unsigned int nr_pages_to_copy) +static int process_vm_rw_pages(struct task_struct *task, + struct mm_struct *mm, + struct page **process_pages, + unsigned long pa, + unsigned long start_offset, + unsigned long len, + const struct iovec *lvec, + unsigned long lvec_cnt, + unsigned long *lvec_current, + size_t *lvec_offset, + int vm_write, + unsigned int nr_pages_to_copy, + ssize_t *bytes_copied) { int pages_pinned; void *target_kaddr; @@ -51,8 +59,9 @@ static ssize_t process_vm_rw_pages(struct task_struct *task, int j; int ret; ssize_t bytes_to_copy; - ssize_t bytes_copied = 0; - ssize_t rc = -EFAULT; + ssize_t rc = 0; + + *bytes_copied = 0; /* Get the pages we're interested in */ down_read(&mm->mmap_sem); @@ -61,8 +70,10 @@ static ssize_t process_vm_rw_pages(struct task_struct *task, vm_write, 0, process_pages, NULL); up_read(&mm->mmap_sem); - if (pages_pinned != nr_pages_to_copy) + if (pages_pinned != nr_pages_to_copy) { + rc = -EFAULT; goto end; + } /* Do the copy for each page */ for (pgs_copied = 0; @@ -81,7 +92,7 @@ static ssize_t process_vm_rw_pages(struct task_struct *task, * - bytes remaining in destination iovec */ bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset, - len - bytes_copied); + len - *bytes_copied); bytes_to_copy = min_t(ssize_t, bytes_to_copy, lvec[*lvec_current].iov_len - *lvec_offset); @@ -99,10 +110,12 @@ static ssize_t process_vm_rw_pages(struct task_struct *task, target_kaddr, bytes_to_copy); kunmap(process_pages[pgs_copied]); if (ret) { + *bytes_copied += bytes_to_copy - ret; pgs_copied++; + rc = -EFAULT; goto end; } - bytes_copied += bytes_to_copy; + *bytes_copied += bytes_to_copy; *lvec_offset += bytes_to_copy; if (*lvec_offset == lvec[*lvec_current].iov_len) { /* @@ -120,8 +133,6 @@ static ssize_t process_vm_rw_pages(struct task_struct *task, } } - rc = bytes_copied; - end: if (vm_write) { for (j = 0; j < pages_pinned; j++) { @@ -140,7 +151,7 @@ end: /* Maximum number of pages kmalloc'd to hold struct page's during copy */ #define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2) -/* +/** * process_vm_rw_single_vec - read/write pages from task specified * @addr: start memory address of target process * @len: size of area to copy to/from @@ -153,35 +164,38 @@ end: * @mm: mm for task * @task: task to read/write from * @vm_write: 0 means copy from, 1 means copy to + * @bytes_copied: returns number of bytes successfully copied + * Returns 0 on success or on failure error code */ -static ssize_t process_vm_rw_single_vec(unsigned long addr, - unsigned long len, - const struct iovec *lvec, - unsigned long lvec_cnt, - unsigned long *lvec_current, - size_t *lvec_offset, - struct page **process_pages, - struct mm_struct *mm, - struct task_struct *task, - int vm_write) +static int process_vm_rw_single_vec(unsigned long addr, + unsigned long len, + const struct iovec *lvec, + unsigned long lvec_cnt, + unsigned long *lvec_current, + size_t *lvec_offset, + struct page **process_pages, + struct mm_struct *mm, + struct task_struct *task, + int vm_write, + ssize_t *bytes_copied) { unsigned long pa = addr & PAGE_MASK; unsigned long start_offset = addr - pa; unsigned long nr_pages; - ssize_t bytes_copied = 0; - ssize_t rc; + ssize_t bytes_copied_loop; + ssize_t rc = 0; unsigned long nr_pages_copied = 0; unsigned long nr_pages_to_copy; unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES / sizeof(struct pages *); + *bytes_copied = 0; /* Work out address and page range required */ if (len == 0) return 0; nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1; - while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) { nr_pages_to_copy = min(nr_pages - nr_pages_copied, max_pages_per_loop); @@ -190,35 +204,49 @@ static ssize_t process_vm_rw_single_vec(unsigned long addr, start_offset, len, lvec, lvec_cnt, lvec_current, lvec_offset, - vm_write, nr_pages_to_copy); + vm_write, nr_pages_to_copy, + &bytes_copied_loop); start_offset = 0; + *bytes_copied += bytes_copied_loop; - if (rc < 0) + if (rc < 0) { return rc; - else { - bytes_copied += rc; - len -= rc; + } else { + len -= bytes_copied_loop; nr_pages_copied += nr_pages_to_copy; pa += nr_pages_to_copy * PAGE_SIZE; } } - rc = bytes_copied; return rc; } -static ssize_t process_vm_rw(pid_t pid, const struct iovec *lvec, - unsigned long liovcnt, - const struct iovec *rvec, - unsigned long riovcnt, - unsigned long flags, int vm_write) +/** + * process_vm_rw_core - core of reading/writing pages from task specified + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, + unsigned long liovcnt, + const struct iovec *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) { struct task_struct *task; struct page **process_pages = NULL; struct mm_struct *mm; unsigned long i; - ssize_t rc; - ssize_t bytes_copied; + ssize_t rc = 0; + ssize_t bytes_copied_loop; + ssize_t bytes_copied = 0; unsigned long nr_pages = 0; unsigned long nr_pages_iov; unsigned long iov_l_curr_idx = 0; @@ -279,38 +307,53 @@ static ssize_t process_vm_rw(pid_t pid, const struct iovec *lvec, atomic_inc(&mm->mm_users); task_unlock(task); - rc = 0; for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) { - bytes_copied = process_vm_rw_single_vec( + rc = process_vm_rw_single_vec( (unsigned long)rvec[i].iov_base, rvec[i].iov_len, lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset, - process_pages, mm, task, vm_write); - if (bytes_copied < 0) { - rc = bytes_copied; + process_pages, mm, task, vm_write, &bytes_copied_loop); + bytes_copied += bytes_copied_loop; + if (rc != 0) { + /* If we have managed to copy any data at all then + we return the number of bytes copied. Otherwise + we return the error code */ + if (bytes_copied) + rc = bytes_copied; goto put_mm; - } else { - rc += bytes_copied; } } + rc = bytes_copied; put_mm: mmput(mm); put_task_struct: put_task_struct(task); - free_proc_pages: kfree(process_pages); return rc; } -static ssize_t process_vm_rw_check_iovecs(pid_t pid, - const struct iovec __user *lvec, - unsigned long liovcnt, - const struct iovec __user *rvec, - unsigned long riovcnt, - unsigned long flags, int vm_write) +/** + * process_vm_rw - check iovecs before calling core routine + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw(pid_t pid, + const struct iovec __user *lvec, + unsigned long liovcnt, + const struct iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) { struct iovec iovstack_l[UIO_FASTIOV]; struct iovec iovstack_r[UIO_FASTIOV]; @@ -336,8 +379,8 @@ static ssize_t process_vm_rw_check_iovecs(pid_t pid, if (rc <= 0) goto free_iovecs; - rc = process_vm_rw(pid, iov_l, liovcnt, iov_r, riovcnt, flags, - vm_write); + rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, + vm_write); free_iovecs: if (iov_r != iovstack_r) @@ -352,8 +395,7 @@ SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec, unsigned long, liovcnt, const struct iovec __user *, rvec, unsigned long, riovcnt, unsigned long, flags) { - return process_vm_rw_check_iovecs(pid, lvec, liovcnt, rvec, riovcnt, - flags, 0); + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0); } SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, @@ -361,19 +403,18 @@ SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, unsigned long, liovcnt, const struct iovec __user *, rvec, unsigned long, riovcnt, unsigned long, flags) { - return process_vm_rw_check_iovecs(pid, lvec, liovcnt, rvec, riovcnt, - flags, 1); + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1); } #ifdef CONFIG_COMPAT asmlinkage ssize_t -compat_process_vm_rw_check_iovecs(compat_pid_t pid, - const struct compat_iovec __user *lvec, - unsigned long liovcnt, - const struct compat_iovec __user *rvec, - unsigned long riovcnt, - unsigned long flags, int vm_write) +compat_process_vm_rw(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) { struct iovec iovstack_l[UIO_FASTIOV]; struct iovec iovstack_r[UIO_FASTIOV]; @@ -406,8 +447,8 @@ compat_process_vm_rw_check_iovecs(compat_pid_t pid, if (rc <= 0) goto free_iovecs; - rc = process_vm_rw(pid, iov_l, liovcnt, iov_r, riovcnt, flags, - vm_write); + rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, + vm_write); free_iovecs: if (iov_r != iovstack_r) @@ -427,8 +468,8 @@ compat_sys_process_vm_readv(compat_pid_t pid, unsigned long riovcnt, unsigned long flags) { - return compat_process_vm_rw_check_iovecs(pid, lvec, liovcnt, rvec, - riovcnt, flags, 0); + return compat_process_vm_rw(pid, lvec, liovcnt, rvec, + riovcnt, flags, 0); } asmlinkage ssize_t @@ -439,8 +480,8 @@ compat_sys_process_vm_writev(compat_pid_t pid, unsigned long riovcnt, unsigned long flags) { - return compat_process_vm_rw_check_iovecs(pid, lvec, liovcnt, rvec, - riovcnt, flags, 1); + return compat_process_vm_rw(pid, lvec, liovcnt, rvec, + riovcnt, flags, 1); } #endif -- 2.39.5