On Fri, 3 Apr 2009, Gerd Hoffmann wrote: > Linus Torvalds wrote: > > > > How married are people to this crazy 2x "32 bits" model? > > The tricky corner case are 32bit compat syscalls on 64bit kernel, where > a noticable number of archs (IIRC at least ppc, mips and s390) can't > pass unaligned 64bit values through the syscall abi. The 32/32 split > was done because of that. I really think that the 32-bit interfaces are fine. So I'm literally suggesting a patch something like the appended. Some notes: - I changed the order to "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. But I don't much _care_ about this particular change. I just made it because it seems more logical to me, and if we're changing the order anyway.. - I checked the resulting assembly code. At least on x86-64, gcc is indeed smart enough to convert the "shift by half twice" into just a zero, and I get the following code: testq %rcx, %rcx # pos_l js .L122 #, movq %rcx, -48(%rbp) # pos_l, pos which is 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. So this does indeed improve code generation. - 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 I just think the new thing is more sensible. Does it really matter? Probably not. (In both code sequences, the actual code had other instructions interspersed, so the above code-sequences are just me manually picking out the relevant instructions. Maybe I did something wrong). So I'm not going to commit the suggested patch, but I just personally think it makes more sense that way. 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 (and passing in a zero for the last argument is a good idea, even if nobody will ever care - this will be the _least_ of our problems if we ever do 128-bit loff_t). So the user call wrapper isn't really any more complicated - the HALF_BITS thing may look more complicated than just doing a hard-coded '16' there twice, but if you understand what it's doing it's actually more logical. I think. Comments? Linus --- fs/compat.c | 4 ++-- fs/read_write.c | 14 ++++++++++---- include/linux/compat.h | 4 ++-- include/linux/syscalls.h | 4 ++-- 4 files changed, 16 insertions(+), 10 deletions(-) diff --git a/fs/compat.c b/fs/compat.c index 1c859da..3f84d5f 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1236,7 +1236,7 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, 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) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; struct file *file; @@ -1293,7 +1293,7 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, 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) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; struct file *file; diff --git a/fs/read_write.c b/fs/read_write.c index 6d5d8ff..9ac8b6f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -731,10 +731,16 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, return ret; } +static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) +{ +#define HALF_LONG_BITS (BITS_PER_LONG / 2) + return ((high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; +} + SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, u32, pos_high, u32, pos_low) + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { - loff_t pos = ((loff_t)pos_high << 32) | pos_low; + loff_t pos = pos_from_hilo(pos_h, pos_l); struct file *file; ssize_t ret = -EBADF; int fput_needed; @@ -757,9 +763,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, u32, pos_high, u32, pos_low) + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { - loff_t pos = ((loff_t)pos_high << 32) | pos_low; + loff_t pos = pos_from_hilo(pos_h, pos_l); struct file *file; ssize_t ret = -EBADF; int fput_needed; diff --git a/include/linux/compat.h b/include/linux/compat.h index 9723edd..f2ded21 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); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b299a82..18771ca 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -462,9 +462,9 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html