From 2b1c6bd77d4e6a727ffac8630cd154b2144b751a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 28 Nov 2008 10:09:09 +0100 Subject: generic compat_sys_ustat Due to a different size of ino_t ustat needs a compat handler, but currently only x86 and mips provide one. Add a generic compat_sys_ustat and switch all architectures over to it. Instead of doing various user copy hacks compat_sys_ustat just reimplements sys_ustat as it's trivial. This was suggested by Arnd Bergmann. Found by Eric Sandeen when running xfstests/017 on ppc64, which causes stack smashing warnings on RHEL/Fedora due to the too large amount of data writen by the syscall. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/compat.h') diff --git a/include/linux/compat.h b/include/linux/compat.h index 3fd2194ff573..b880864672de 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -125,6 +125,13 @@ struct compat_dirent { char d_name[256]; }; +struct compat_ustat { + compat_daddr_t f_tfree; + compat_ino_t f_tinode; + char f_fname[6]; + char f_fpack[6]; +}; + typedef union compat_sigval { compat_int_t sival_int; compat_uptr_t sival_ptr; @@ -178,6 +185,7 @@ long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, unsigned nsems, const struct compat_timespec __user *timeout); asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); +asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); -- cgit v1.2.1 From f3554f4bc69803ac2baaf7cf2aa4339e1f4b693e Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Thu, 2 Apr 2009 16:59:23 -0700 Subject: preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann Cc: Arnd Bergmann Cc: Al Viro Cc: Cc: Cc: Ralf Baechle Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/compat.h') diff --git a/include/linux/compat.h b/include/linux/compat.h index b880864672de..9723edd6455c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -191,6 +191,12 @@ asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); +asmlinkage ssize_t compat_sys_preadv(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); -- cgit v1.2.1 From 601cc11d054ae4b5e9b5babec3d8e4667a2cb9b5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 3 Apr 2009 08:03:22 -0700 Subject: Make non-compat preadv/pwritev use native register size Instead of always splitting the file offset into 32-bit 'high' and 'low' parts, just split them into the largest natural word-size - which in C terms is 'unsigned long'. This allows 64-bit architectures to avoid the unnecessary 32-bit shifting and masking for native format (while the compat interfaces will obviously always have to do it). This also changes the order of 'high' and 'low' to be "low first". Why? Because when we have it like this, the 64-bit system calls now don't use the "pos_high" argument at all, and it makes more sense for the native system call to simply match the user-mode prototype. This results in a much more natural calling convention, and allows the compiler to generate much more straightforward code. On x86-64, we now generate testq %rcx, %rcx # pos_l js .L122 #, movq %rcx, -48(%rbp) # pos_l, pos from the C source loff_t pos = pos_from_hilo(pos_h, pos_l); ... if (pos < 0) return -EINVAL; and the 'pos_h' register isn't even touched. It used to generate code like mov %r8d, %r8d # pos_low, pos_low salq $32, %rcx #, tmp71 movq %r8, %rax # pos_low, pos.386 orq %rcx, %rax # tmp71, pos.386 js .L122 #, movq %rax, -48(%rbp) # pos.386, pos which isn't _that_ horrible, but it does show how the natural word size is just a more sensible interface (same arguments will hold in the user level glibc wrapper function, of course, so the kernel side is just half of the equation!) Note: in all cases the user code wrapper can again be the same. You can just do #define HALF_BITS (sizeof(unsigned long)*4) __syscall(PWRITEV, fd, iov, count, offset, (offset >> HALF_BITS) >> HALF_BITS); or something like that. That way the user mode wrapper will also be nicely passing in a zero (it won't actually have to do the shifts, the compiler will understand what is going on) for the last argument. And that is a good idea, even if nobody will necessarily ever care: if we ever do move to a 128-bit lloff_t, this particular system call might be left alone. Of course, that will be the least of our worries if we really ever need to care, so this may not be worth really caring about. [ Fixed for lost 'loff_t' cast noticed by Andrew Morton ] Acked-by: Gerd Hoffmann Cc: H. Peter Anvin Cc: Andrew Morton Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: Ingo Molnar Cc: Ralf Baechle > Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/compat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/compat.h') diff --git a/include/linux/compat.h b/include/linux/compat.h index 9723edd6455c..f2ded21f9a3c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -193,10 +193,10 @@ asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, u32 pos_low, u32 pos_high); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); -- cgit v1.2.1