preadv & pwritev syscalls.
Subsystems (5)
v3 cover preadv & pwritev syscalls.
Hi,
Next revision of the patch series, with the alignment issue fixed by swapping the last two arguments as suggested by arch maintainers.
I've dropped the now-obsolete wrappers for mips. Ralf, please double-check.
thanks,
Gerd
--- fs/compat.c | 6 ++++++ 1 files changed, 6 insertions(+), 0 deletions(-)
fs/compat.c +6 -0
@@ -1187,6 +1187,9 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign ret =compat_do_readv_writev (READ , file, vec, vlen, &file->f_pos); out: +if (ret >0 ) +add_rchar (current, ret); +inc_syscr (current);fput (file);return ret; }
@@ -1210,6 +1213,9 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig ret =compat_do_readv_writev (WRITE , file, vec, vlen, &file->f_pos); out: +if (ret >0 ) +add_wchar (current, ret); +inc_syscw (current);fput (file);return ret; }
Signature · 6 lines
1.5.6.5 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
PATCH v3 1/3 Add missing accounting calls to compat_sys_{readv,writev}.
--- fs/compat.c | 6 ++++++ 1 files changed, 6 insertions(+), 0 deletions(-)
fs/compat.c +6 -0
@@ -1187,6 +1187,9 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign ret =compat_do_readv_writev (READ , file, vec, vlen, &file->f_pos); out: +if (ret >0 ) +add_rchar (current, ret); +inc_syscr (current);fput (file);return ret; }
@@ -1210,6 +1213,9 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig ret =compat_do_readv_writev (WRITE , file, vec, vlen, &file->f_pos); out: +if (ret >0 ) +add_wchar (current, ret); +inc_syscw (current);fput (file);return ret; }
Signature · 1 line
1.5.6.5
PATCH v3 2/3 Add preadv and pwritev system calls.
In reply to Gerd HoffmannThis 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);
Note that the system call uses another argument ordering (last two args swapped) to avoid unaligned 64bit arguments on the stack.
The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches.
--- arch/x86/ia32/ia32entry.S | 2 + arch/x86/include/asm/unistd_32.h | 2 + arch/x86/include/asm/unistd_64.h | 4 ++ arch/x86/kernel/syscall_table_32.S | 2 + fs/compat.c | 61 ++++++++++++++++++++++++++++++++++++ fs/read_write.c | 48 ++++++++++++++++++++++++++++ 6 files changed, 119 insertions(+), 0 deletions(-)
arch/x86/ia32/ia32entry.S +2 -0
@@ -826,4 +826,6 @@ ia32_sys_call_table: .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 + .quad compat_sys_preadv + .quad compat_sys_pwritev ia32_syscall_end:
arch/x86/include/asm/unistd_32.h +2 -0
@@ -338,6 +338,8 @@#define __NR_dup3 330#define __NR_pipe2 331#define __NR_inotify_init1 332 +#define __NR_preadv 333 +#define __NR_pwritev 334#ifdef __KERNEL__
arch/x86/include/asm/unistd_64.h +4 -0
@@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3) __SYSCALL(__NR_pipe2, sys_pipe2)#define __NR_inotify_init1 294 __SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_preadv 295 +__SYSCALL(__NR_preadv, sys_preadv) +#define __NR_pwritev 296 +__SYSCALL(__NR_pwritev, sys_pwritev)#ifndef __NO_STUBS
arch/x86/kernel/syscall_table_32.S +2 -0
@@ -332,3 +332,5 @@ ENTRY(sys_call_table) .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 + .long sys_preadv + .long sys_pwritev
fs/compat.c +61 -0
67 lines not on this page · raw message
fs/read_write.c +48 -0
54 lines not on this page · raw message
Signature · 1 line
1.5.6.5
PATCH v3 3/3 MIPS: Add preadv(2) and pwritev(2) syscalls.
In reply to Gerd HoffmannFrom: Ralf Baechle <ralf-6z/[email protected]>
From: Ralf Baechle <ralf-6z/[email protected]>
--- arch/mips/include/asm/unistd.h | 18 ++++++++++++------ arch/mips/kernel/scall32-o32.S | 2 ++ arch/mips/kernel/scall64-64.S | 2 ++ arch/mips/kernel/scall64-n32.S | 2 ++ arch/mips/kernel/scall64-o32.S | 2 ++ 5 files changed, 20 insertions(+), 6 deletions(-)
arch/mips/include/asm/unistd.h +12 -6
@@ -350,16 +350,18 @@#define __NR_dup3 (__NR_Linux + 327)#define __NR_pipe2 (__NR_Linux + 328)#define __NR_inotify_init1 (__NR_Linux + 329) +#define __NR_preadv (__NR_Linux + 330) +#define __NR_pwritev (__NR_Linux + 331)/* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 329 +#define __NR_Linux_syscalls 331#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 329 +#define __NR_O32_Linux_syscalls 331#if _MIPS_SIM == _MIPS_SIM_ABI64
@@ -656,16 +658,18 @@#define __NR_dup3 (__NR_Linux + 286)#define __NR_pipe2 (__NR_Linux + 287)#define __NR_inotify_init1 (__NR_Linux + 288) +#define __NR_preadv (__NR_Linux + 289) +#define __NR_pwritev (__NR_Linux + 290)/* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 288 +#define __NR_Linux_syscalls 290#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 288 +#define __NR_64_Linux_syscalls 290#if _MIPS_SIM == _MIPS_SIM_NABI32
@@ -966,16 +970,18 @@#define __NR_dup3 (__NR_Linux + 290)#define __NR_pipe2 (__NR_Linux + 291)#define __NR_inotify_init1 (__NR_Linux + 292) +#define __NR_preadv (__NR_Linux + 293) +#define __NR_pwritev (__NR_Linux + 294)/* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 292 +#define __NR_Linux_syscalls 294#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 292 +#define __NR_N32_Linux_syscalls 294#ifdef __KERNEL__
arch/mips/kernel/scall32-o32.S +2 -0
@@ -650,6 +650,8 @@ einval: li v0, -ENOSYS sys sys_dup3 3 sys sys_pipe2 2 sys sys_inotify_init1 1 + sys sys_preadv 6 /* 4330 */ + sys sys_pwritev 6 .endm /* We pre-compute the number of _instruction_ bytes needed to
arch/mips/kernel/scall64-64.S +2 -0
@@ -487,4 +487,6 @@ sys_call_table: PTR sys_dup3 PTR sys_pipe2 PTR sys_inotify_init1 + PTR sys_preadv + PTR sys_pwritev /* 5390 */ .size sys_call_table,.-sys_call_table
arch/mips/kernel/scall64-n32.S +2 -0
@@ -413,4 +413,6 @@ EXPORT(sysn32_call_table) PTR sys_dup3 /* 5290 */ PTR sys_pipe2 PTR sys_inotify_init1 + PTR sys_preadv + PTR sys_pwritev .size sysn32_call_table,.-sysn32_call_table
arch/mips/kernel/scall64-o32.S +2 -0
@@ -533,4 +533,6 @@ sys_call_table: PTR sys_dup3 PTR sys_pipe2 PTR sys_inotify_init1 + PTR compat_sys_preadv /* 4330 */ + PTR compat_sys_pwritev .size sys_call_table,.-sys_call_table
Signature · 6 lines
1.5.6.5 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 5 lines · Gerd Hoffmann
Next revision of the patch series, with the alignment issue fixed by swapping the last two arguments as suggested by arch maintainers.
I've dropped the now-obsolete wrappers for mips. Ralf, please double-check.
It fixes the alignment issue but still won't work; on MIPS 32-bit userspace will pass the 64-bit argument in two registers but the 64-bit kernel code will assume it to be passed in a single registers. It'd be ugly but passing a pointer to a 64-bit argument would solve the issue; something like this:
sys_preadv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, loff_t __user *pos);
compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
unsigned long vlen, loff_t __user *pos);sys_splice uses loff_t __user * arguments as well and that's why it's doesn't need any compat wrapper.
I'm surprised this works for x86; does x86-64 code really expect 64-bit arguments as 2 32-bit arguments?
Patch 1/3 looks like it's a bug fix and you may want to submit this separate from the remainder of the series for 2.6.28?
Ralf
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
From: Ralf Baechle <[email protected]>
Date: Mon, 15 Dec 2008 16:03:11 +0000
Quoted 11 lines · Gerd Hoffmann
Quoted 6 lines
Next revision of the patch series, with the alignment issue fixed by swapping the last two arguments as suggested by arch maintainers.
I've dropped the now-obsolete wrappers for mips. Ralf, please double-check.
It fixes the alignment issue but still won't work; on MIPS 32-bit userspace will pass the 64-bit argument in two registers but the 64-bit kernel code will assume it to be passed in a single registers.
Same on 32-bit sparc, and I assume 32-bit powerpc as well.
Quoted 2 lines
I'm surprised this works for x86; does x86-64 code really expect 64-bit arguments as 2 32-bit arguments?
Args get pushed onto the stack, so perhaps it works by accident :)
Quoted 13 lines · Ralf Baechle
Quoted 5 lines · Gerd Hoffmann
Next revision of the patch series, with the alignment issue fixed by swapping the last two arguments as suggested by arch maintainers.
I've dropped the now-obsolete wrappers for mips. Ralf, please double-check.
It fixes the alignment issue but still won't work; on MIPS 32-bit userspace will pass the 64-bit argument in two registers but the 64-bit kernel code will assume it to be passed in a single registers. It'd be ugly but passing a pointer to a 64-bit argument would solve the issue; something like this:
Quoted 4 lines
sys_preadv(unsigned long fd, const struct iovec
__user*vec,unsigned long vlen, loff_t __user *pos); compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen, loff_t __user *pos);
Suggestion from the s390 front was to explicitly pass high and low part of pos as two arguments. A bit ugly too, but should work fine as well and it avoids the user pointer dereference. What do you think about this?
Quoted 2 lines
sys_spliceusesloff_t__user* arguments as well and that's why it's doesn't need any compat wrapper.
Well, avoiding the compat wrapper altogether unfortunately isn't going to work because struct iovec looks different in 32 and 64 bit.
Quoted 2 lines
I'm surprised this works for x86; does x86-64 code really expect 64-bit arguments as 2 32-bit arguments?
Args are passed on the stack, not in registers.
Quoted 2 lines
Patch 1/3 looks like it's a bug fix and you may want to submit this separate from the remainder of the series for 2.6.28?
Yep, it is a separate bugfix. Spotted by Christoph while reviewing v1, but there are no other dependencies to this patch series.
cheers,
Gerd
Quoted 5 lines · Gerd Hoffmann
Quoted 5 lines
It fixes the alignment issue but still won't work; on MIPS 32-bit userspace will pass the 64-bit argument in two registers but the 64-bit kernel code will assume it to be passed in a single registers. It'd be ugly but passing a pointer to a 64-bit argument would solve the issue; something like this:
Quoted 8 lines
Quoted 4 lines
sys_preadv(unsigned long fd, const struct iovec
__user*vec,unsigned long vlen, loff_t __user *pos); compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen, loff_t __user *pos);Suggestion from the s390 front was to explicitly pass high and low part of pos as two arguments. A bit ugly too, but should work fine as well and it avoids the user pointer dereference. What do you think about this?
That's what the wrapper which you deleted, was doing ;-) So yes, I like it. It just raises one new problem, endianess - are arguments being passed as low/high or high/low? On MIPS we've been solving the issue with the merge_64() macro which is defined depending on the byte order:
#ifdef __MIPSEB__
#define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL)) #endif
#ifdef __MIPSEL__
#define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL)) #endif
The actual syscall wrapper could use it like:
asmlinkage int compat_sys_pwritev(unsigned long fd,
const struct compat_iovec __user *vec, unsigned a3, unsigned a4, unsigned long vlen)
{
loff_t offset = merge_64(a3, a4);...
If merge_64() was a standard macro in <asm/compat.h> on all architectures, compat_sys_pwrite() could invoke it directly and the need for the compat wrapper around the compat wrapper would go away.
Quoted 4 lines
Quoted 2 lines
I'm surprised this works for x86; does x86-64 code really expect 64-bit arguments as 2 32-bit arguments?
Args are passed on the stack, not in registers.
Same as 32-bit MIPS for argument #4 and up which will be passed on the stack - but the requirement for passing a long long is for it to be passed as an aligned pair of arguments and the original patch got that wrong.
Ralf
Quoted 4 lines · Ralf Baechle
If
merge_64()was a standard macro in <asm/compat.h> on all architectures,compat_sys_pwrite()could invoke it directly and the need for the compat wrapper around the compat wrapper would go away.
+1 for this.
AFAIK, there's issues on s390 and sparc (at least) with sign extension, that they need to wrap anyway, we should really sort that out in the generic compat wrappers as well.
cheers, Kyle
Quoted 11 lines · Ralf Baechle
Quoted 9 lines · Gerd Hoffmann
Quoted 9 lines
It fixes the alignment issue but still won't work; on MIPS 32-bit userspace will pass the 64-bit argument in two registers but the 64-bit kernel code will assume it to be passed in a single registers. It'd be ugly but passing a pointer to a 64-bit argument would solve the issue; something like this:
sys_preadv(unsigned long fd, const struct iovec
__user*vec,unsigned long vlen, loff_t __user *pos); compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen, loff_t __user *pos);
Quoted 6 lines
Quoted 3 lines
Suggestion from the s390 front was to explicitly pass high and low part of pos as two arguments. A bit ugly too, but should work fine as well and it avoids the user pointer dereference. What do you think about this?
That's what the wrapper which you deleted, was doing ;-) So yes, I like it.
Yep, but I'm trying to find a way to have it work without per-arch wrappers ...
Quoted 11 lines
It just raises one new problem, endianess - are arguments being passed as low/high or high/low? On MIPS we've been solving the issue with the
merge_64()macro which is defined depending on the byte order:#ifdef
__MIPSEB__
#definemerge_64(r1, r2)((((r1) &0xffffffffUL) << 32) + ((r2) &0xffffffffUL)) #endif
#ifdef__MIPSEL__
#definemerge_64(r1, r2)((((r2) &0xffffffffUL) << 32) + ((r1) &0xffffffffUL)) #endif
Quoted 8 lines
The actual syscall wrapper could use it like:
asmlinkage int compat_sys_pwritev(unsigned long fd,
const structcompat_iovec__user*vec, unsigned a3, unsigned a4, unsigned long vlen){ loff_t offset = merge_64(a3, a4);...
i.e. the ordering of the splitted argument depends on the os endianness? What is the reason for this?
I'd prefer to have the ordering coded explicitly instead, like this:
asmlinkage int compat_sys_pwritev(unsigned long fd,
const struct compat_iovec __user *vec, unsigned long vlen, unsigned pos_low, unsigned pos_high)
{
loff_t pos = pos_low | (loff_t)pos_high << 32;
[ ... ]cheers,
Gerd
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 3 lines · Gerd Hoffmann
i.e. the ordering of the splitted argument depends on the os endianness? What is the reason for this?
Eh? The splitting will occur at the C ABI level, not as a result of glibc (though, it could be done that way if you really wanted, but then you're just moving the wrapper up the chain.)
A 64-bit value on a 32-bit machine will look like, in a register pair, like it looks in memory, with MSB/LSB ordering.
Quoted 9 lines
I'd prefer to have the ordering coded explicitly instead, like this:
asmlinkage int compat_sys_pwritev(unsigned long fd,
const structcompat_iovec__user*vec, unsigned long vlen, unsignedpos_low, unsignedpos_high){ loff_t pos = pos_low | (loff_t)pos_high << 32; [ ... ]
Sadly this isn't possible without a wrapper unless you can guarantee it was passed low high instead of high low. Unless you munge it in userspace, you can't.
regards, Kyle
Arnd Bergmann
maintainerQuoted 10 lines · Kyle McMartin
Quoted 9 lines
I'd prefer to have the ordering coded explicitly instead, like this:
asmlinkage int compat_sys_pwritev(unsigned long fd, const struct
compat_iovec__user*vec, unsigned long vlen, unsignedpos_low, unsignedpos_high)
{
loff_t pos =pos_low| (loff_t)pos_high << 32;
[ ... ]
Quoted 4 lines
Sadly this isn't possible without a wrapper unless you can guarantee it was passed low high instead of high low. Unless you munge it in userspace, you can't.
Exactly, we have to munge it in userspace anyway because of the argument ordering requirement we get if we pass it as a single u64. I vote for the explicit split as well, this will give us a straightforward wrapper in user space, unlike the swapped arguments that are just asking for trouble, and will make it easy to have a common compat_sys_pwritev function.
Arnd <><
Quoted 7 lines · Kyle McMartin
Quoted 2 lines · Gerd Hoffmann
i.e. the ordering of the splitted argument depends on the os endianness? What is the reason for this?
Eh? The splitting will occur at the C ABI level, not as a result of glibc (though, it could be done that way if you really wanted, but then you're just moving the wrapper up the chain.)
Ah, ok. You'll just declare 64bit arg for userspace, gcc splits it into two 32bit in native byte order, and then the kernel picks up the two 32bit values and has to reassemble them correctly, right?
The application-visible API must be compatible to the existing implementations, i.e. this ...
pread(long fd, struct iovec *vec, long vlen, off_t pos);
... prototype with the unaligned 64bit pos argument (in 32compat case).
Looks like there is no way around wrapping stuff then for the archs wanting aligned 64bit values. The only choice we have is to do the wrap-o-magic in glibc or in the kernel.
I'd tend handle the wrapping in kernel space then because it is less confusing and we have to wrap only in case the ABI for $arch requires it.
Comments?
Gerd
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 20 lines · Gerd Hoffmann
Quoted 7 lines · Kyle McMartin
Quoted 2 lines · Gerd Hoffmann
i.e. the ordering of the splitted argument depends on the os endianness? What is the reason for this?
Eh? The splitting will occur at the C ABI level, not as a result of glibc (though, it could be done that way if you really wanted, but then you're just moving the wrapper up the chain.)
Ah, ok. You'll just declare 64bit arg for userspace, gcc splits it into two 32bit in native byte order, and then the kernel picks up the two 32bit values and has to reassemble them correctly, right?
The application-visible API must be compatible to the existing implementations, i.e. this ...
pread(long fd, struct iovec *vec, long vlen, off_t pos);... prototype with the unaligned 64bit pos argument (in 32compat case).
Quoted 8 lines
Looks like there is no way around wrapping stuff then for the archs wanting aligned 64bit values. The only choice we have is to do the wrap-o-magic in glibc or in the kernel.
I'd tend handle the wrapping in kernel space then because it is less confusing and we have to wrap only in case the ABI for $arch requires it.
Comments?
Please do it just the way that Arnd suggested: explicitly pass the upper and lower part of loff_t as separate arguments.
It's the most simple approach.
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html