From bed1ffca022cc876fb83161d26670e9b5d3cf36b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Mar 2009 15:42:11 +0100 Subject: tracing/syscalls: core infrastructure for syscalls tracing, enhancements Impact: new feature This adds the generic support for syscalls tracing. This is currently exploited through a devoted tracer but other tracing engines can use it. (They just have to play with {start,stop}_ftrace_syscalls() and use the display callbacks unless they want to override them.) The syscalls prototypes definitions are abused here to steal some metadata informations: - syscall name, param types, param names, number of params The syscall addr is not directly saved during this definition because we don't know if its prototype is available in the namespace. But we don't really need it. The arch has just to build a function able to resolve the syscall number to its metadata struct. The current tracer prints the syscall names, parameters names and values (and their types optionally). Currently the value is a raw hex but higher level values diplaying is on my TODO list. Signed-off-by: Frederic Weisbecker LKML-Reference: <1236955332-10133-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 58 insertions(+), 2 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9f900cfd06..0cff9bb80b0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -65,6 +65,7 @@ struct old_linux_dirent; #include #include #include +#include #define __SC_DECL1(t1, a1) t1 a1 #define __SC_DECL2(t2, a2, ...) t2 a2, __SC_DECL1(__VA_ARGS__) @@ -95,7 +96,46 @@ struct old_linux_dirent; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) +#ifdef CONFIG_FTRACE_SYSCALLS +#define __SC_STR_ADECL1(t, a) #a +#define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__) +#define __SC_STR_ADECL3(t, a, ...) #a, __SC_STR_ADECL2(__VA_ARGS__) +#define __SC_STR_ADECL4(t, a, ...) #a, __SC_STR_ADECL3(__VA_ARGS__) +#define __SC_STR_ADECL5(t, a, ...) #a, __SC_STR_ADECL4(__VA_ARGS__) +#define __SC_STR_ADECL6(t, a, ...) #a, __SC_STR_ADECL5(__VA_ARGS__) + +#define __SC_STR_TDECL1(t, a) #t +#define __SC_STR_TDECL2(t, a, ...) #t, __SC_STR_TDECL1(__VA_ARGS__) +#define __SC_STR_TDECL3(t, a, ...) #t, __SC_STR_TDECL2(__VA_ARGS__) +#define __SC_STR_TDECL4(t, a, ...) #t, __SC_STR_TDECL3(__VA_ARGS__) +#define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) +#define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) + +#define SYSCALL_METADATA(sname, nb) \ + static const struct syscall_metadata __used \ + __attribute__((__aligned__(4))) \ + __attribute__((section("__syscalls_metadata"))) \ + __syscall_meta_##sname = { \ + .name = "sys"#sname, \ + .nb_args = nb, \ + .types = types_##sname, \ + .args = args_##sname, \ + } + +#define SYSCALL_DEFINE0(sname) \ + static const struct syscall_metadata __used \ + __attribute__((__aligned__(4))) \ + __attribute__((section("__syscalls_metadata"))) \ + __syscall_meta_##sname = { \ + .name = "sys_"#sname, \ + .nb_args = 0, \ + }; \ + asmlinkage long sys_##sname(void) + +#else #define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) +#endif + #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) #define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) @@ -117,10 +157,26 @@ struct old_linux_dirent; #endif #endif +#ifdef CONFIG_FTRACE_SYSCALLS +#define SYSCALL_DEFINEx(x, sname, ...) \ + static const char *types_##sname[] = { \ + __SC_STR_TDECL##x(__VA_ARGS__) \ + }; \ + static const char *args_##sname[] = { \ + __SC_STR_ADECL##x(__VA_ARGS__) \ + }; \ + SYSCALL_METADATA(sname, x); \ + __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) +#else +#define SYSCALL_DEFINEx(x, sname, ...) \ + __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) +#endif + #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS #define SYSCALL_DEFINE(name) static inline long SYSC_##name -#define SYSCALL_DEFINEx(x, name, ...) \ + +#define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)); \ static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__)); \ asmlinkage long SyS##name(__SC_LONG##x(__VA_ARGS__)) \ @@ -134,7 +190,7 @@ struct old_linux_dirent; #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ #define SYSCALL_DEFINE(name) asmlinkage long sys_##name -#define SYSCALL_DEFINEx(x, name, ...) \ +#define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)) #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ -- cgit v1.2.3 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/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9f900cfd06..b299a82a05e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -461,6 +461,10 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos); 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); +asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); 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); -- cgit v1.2.3 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/syscalls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b299a82a05e..18771cac2f8 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); -- cgit v1.2.3