From b19e2ca77ee4becadc85341bb0c1cee454dd4fd5 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 7 Aug 2012 21:47:51 +0200 Subject: TTY: use tty_port_link_device So now for those drivers that can use neither tty_port_install nor tty_port_register_driver but still have tty_port available before tty_register_driver we use newly added tty_port_link_device. The rest of the drivers that still do not provide tty_struct <-> tty_port link will have to be converted to implement tty->ops->install. Signed-off-by: Jiri Slaby Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/pdc_cons.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/parisc/kernel') diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c index 47341aa208f2..88238638aee6 100644 --- a/arch/parisc/kernel/pdc_cons.c +++ b/arch/parisc/kernel/pdc_cons.c @@ -202,6 +202,7 @@ static int __init pdc_console_tty_driver_init(void) pdc_console_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_RESET_TERMIOS; tty_set_operations(pdc_console_tty_driver, &pdc_console_tty_ops); + tty_port_link_device(&tty_port, pdc_console_tty_driver, 0); err = tty_register_driver(pdc_console_tty_driver); if (err) { -- cgit v1.3-14-g43fede From fbe752188d5589e7fcbb8e79824e560f77dccc92 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: parisc: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the parisc's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: James E.J. Bottomley Cc: Helge Deller Cc: Parisc Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/parisc/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/parisc/kernel') diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 2c05a9292a81..8c6b6b6561f0 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include @@ -69,8 +70,10 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) barrier(); + rcu_idle_exit(); schedule_preempt_disabled(); check_pgt_cache(); } -- cgit v1.3-14-g43fede From 00df111e7eb505558c54f23861e9341e56dd5fb0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 19 May 2012 00:29:22 -0400 Subject: parisc: fix double restarts Don't bother restoring r28 on syscall restarts; it's clobbered by syscall anyway. Reuse (now unused) ->orig_r28 as "no restarts allowed" flag. Signed-off-by: Al Viro --- arch/parisc/hpux/gate.S | 2 +- arch/parisc/kernel/signal.c | 16 ++++++++-------- arch/parisc/kernel/syscall.S | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'arch/parisc/kernel') diff --git a/arch/parisc/hpux/gate.S b/arch/parisc/hpux/gate.S index 38a1c1b8d4e8..011468857e98 100644 --- a/arch/parisc/hpux/gate.S +++ b/arch/parisc/hpux/gate.S @@ -71,7 +71,7 @@ ENTRY(hpux_gateway_page) STREG %r26, TASK_PT_GR26(%r1) /* 1st argument */ STREG %r27, TASK_PT_GR27(%r1) /* user dp */ STREG %r28, TASK_PT_GR28(%r1) /* return value 0 */ - STREG %r28, TASK_PT_ORIG_R28(%r1) /* return value 0 (saved for signals) */ + STREG %r0, TASK_PT_ORIG_R28(%r1) /* don't prohibit restarts */ STREG %r29, TASK_PT_GR29(%r1) /* 8th argument */ STREG %r31, TASK_PT_GR31(%r1) /* preserve syscall return ptr */ diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 594459bde14e..3790a3237172 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -113,6 +113,8 @@ sys_rt_sigreturn(struct pt_regs *regs, int in_syscall) (usp - sigframe_size); DBG(2,"sys_rt_sigreturn: frame is %p\n", frame); + regs->orig_r28 = 1; /* no restarts for sigreturn */ + #ifdef CONFIG_64BIT compat_frame = (struct compat_rt_sigframe __user *)frame; @@ -462,6 +464,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, static inline void syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) { + if (regs->orig_r28) + return; + regs->orig_r28 = 1; /* no more restarts */ /* Check the return code */ switch (regs->gr[28]) { case -ERESTART_RESTARTBLOCK: @@ -482,8 +487,6 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) * we have to do is fiddle the return pointer. */ regs->gr[31] -= 8; /* delayed branching */ - /* Preserve original r28. */ - regs->gr[28] = regs->orig_r28; break; } } @@ -491,6 +494,9 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) static inline void insert_restart_trampoline(struct pt_regs *regs) { + if (regs->orig_r28) + return; + regs->orig_r28 = 1; /* no more restarts */ switch(regs->gr[28]) { case -ERESTART_RESTARTBLOCK: { /* Restart the system call - no handlers present */ @@ -525,9 +531,6 @@ insert_restart_trampoline(struct pt_regs *regs) flush_user_icache_range(regs->gr[30], regs->gr[30] + 4); regs->gr[31] = regs->gr[30] + 8; - /* Preserve original r28. */ - regs->gr[28] = regs->orig_r28; - return; } case -ERESTARTNOHAND: @@ -539,9 +542,6 @@ insert_restart_trampoline(struct pt_regs *regs) * slot of the branch external instruction. */ regs->gr[31] -= 8; - /* Preserve original r28. */ - regs->gr[28] = regs->orig_r28; - return; } default: diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 82a52b2fb13f..54a9cbfc08ad 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -156,7 +156,7 @@ linux_gateway_entry: STREG %r26, TASK_PT_GR26(%r1) /* 1st argument */ STREG %r27, TASK_PT_GR27(%r1) /* user dp */ STREG %r28, TASK_PT_GR28(%r1) /* return value 0 */ - STREG %r28, TASK_PT_ORIG_R28(%r1) /* return value 0 (saved for signals) */ + STREG %r0, TASK_PT_ORIG_R28(%r1) /* don't prohibit restarts */ STREG %r29, TASK_PT_GR29(%r1) /* return value 1 */ STREG %r31, TASK_PT_GR31(%r1) /* preserve syscall return ptr */ -- cgit v1.3-14-g43fede From e3b880c6ee55e8858a75e3dcf6c3dda04d5e3605 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 19 May 2012 01:13:01 -0400 Subject: parisc: don't bother looping in do_signal() entry.S code had been looping until no pending signals are left since 2005 anyway; no need to bother with that in do_signal() itself. If the failure to set a sigframe up raises SIGSEGV, we'll just pick it up the next time around the loop(s) in entry.S anyway. Signed-off-by: Al Viro --- arch/parisc/kernel/signal.c | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'arch/parisc/kernel') diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 3790a3237172..537996955998 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -439,7 +439,7 @@ give_sigsegv: * OK, we're invoking a handler. */ -static long +static void handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int in_syscall) { @@ -449,7 +449,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, /* Set up the stack frame */ if (!setup_rt_frame(sig, ka, info, oldset, regs, in_syscall)) - return 0; + return; signal_delivered(sig, info, ka, regs, test_thread_flag(TIF_SINGLESTEP) || @@ -457,8 +457,6 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, DBG(1,KERN_DEBUG "do_signal: Exit (success), regs->gr[28] = %ld\n", regs->gr[28]); - - return 1; } static inline void @@ -570,30 +568,17 @@ do_signal(struct pt_regs *regs, long in_syscall) DBG(1,"\ndo_signal: regs=0x%p, sr7 %#lx, in_syscall=%d\n", regs, regs->sr[7], in_syscall); - /* Everyone else checks to see if they are in kernel mode at - this point and exits if that's the case. I'm not sure why - we would be called in that case, but for some reason we - are. */ - - /* May need to force signal if handle_signal failed to deliver */ - while (1) { - signr = get_signal_to_deliver(&info, &ka, regs, NULL); - DBG(3,"do_signal: signr = %d, regs->gr[28] = %ld\n", signr, regs->gr[28]); + signr = get_signal_to_deliver(&info, &ka, regs, NULL); + DBG(3,"do_signal: signr = %d, regs->gr[28] = %ld\n", signr, regs->gr[28]); - if (signr <= 0) - break; - + if (signr > 0) { /* Restart a system call if necessary. */ if (in_syscall) syscall_restart(regs, &ka); - /* Whee! Actually deliver the signal. If the - delivery failed, we need to continue to iterate in - this loop so we can deliver the SIGSEGV... */ - if (handle_signal(signr, &info, &ka, regs, in_syscall)) - return; + handle_signal(signr, &info, &ka, regs, in_syscall); + return; } - /* end of while(1) looping forever if we can't force a signal */ /* Did we come from a system call? */ if (in_syscall) -- cgit v1.3-14-g43fede From 64482bd8ef1700e98d96fb6e240c501d68c8371c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 May 2012 11:59:03 -0400 Subject: parisc: decide whether to go to slow path (tracesys) based on thread flags Signed-off-by: Al Viro --- arch/parisc/include/asm/thread_info.h | 2 ++ arch/parisc/kernel/syscall.S | 7 ++++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'arch/parisc/kernel') diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index d0e2fe7d54a6..d1fb79a36f3d 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -74,6 +74,8 @@ struct thread_info { #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ _TIF_NEED_RESCHED) +#define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \ + _TIF_BLOCKSTEP) #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 54a9cbfc08ad..86742df0b194 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -180,9 +180,10 @@ linux_gateway_entry: /* Are we being ptraced? */ mfctl %cr30, %r1 - LDREG TI_TASK(%r1),%r1 - ldw TASK_PTRACE(%r1), %r1 - bb,<,n %r1,31,.Ltracesys + LDREG TI_FLAGS(%r1),%r1 + ldi _TIF_SYSCALL_TRACE_MASK, %r19 + and,COND(=) %r1, %r19, %r0 + b,n .Ltracesys /* Note! We cannot use the syscall table that is mapped nearby since the gateway page is mapped execute-only. */ -- cgit v1.3-14-g43fede From 751f409db6216ebd134a94f6dcd97779933a5106 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Thu, 4 Oct 2012 17:15:31 -0700 Subject: compat: move compat_siginfo_t definition to asm/compat.h This is a preparatory patch for the introduction of NT_SIGINFO elf note. Make the location of compat_siginfo_t uniform across eight architectures which have it. Now it can be pulled in by including asm/compat.h or linux/compat.h. Most of the copies are verbatim. compat_uid[32]_t had to be replaced by __compat_uid[32]_t. compat_uptr_t had to be moved up before compat_siginfo_t in asm/compat.h on a several architectures (tile already had it moved up). compat_sigval_t had to be relocated from linux/compat.h to asm/compat.h. Signed-off-by: Denys Vlasenko Cc: Oleg Nesterov Cc: Amerigo Wang Cc: "Jonathan M. Foote" Cc: Roland McGrath Cc: Pedro Alves Cc: Fengguang Wu Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/compat.h | 60 +++++++++++++++++++++++++++- arch/arm64/kernel/signal32.c | 53 ------------------------- arch/mips/include/asm/compat-signal.h | 62 ----------------------------- arch/mips/include/asm/compat.h | 69 +++++++++++++++++++++++++++++++- arch/parisc/include/asm/compat.h | 59 ++++++++++++++++++++++++++- arch/parisc/kernel/signal32.h | 52 ------------------------ arch/powerpc/include/asm/compat.h | 60 +++++++++++++++++++++++++++- arch/powerpc/include/asm/siginfo.h | 1 - arch/powerpc/kernel/ppc32.h | 51 ------------------------ arch/s390/include/asm/compat.h | 75 ++++++++++++++++++++++++++++++++++- arch/s390/kernel/compat_linux.h | 68 ------------------------------- arch/sparc/include/asm/compat.h | 61 +++++++++++++++++++++++++++- arch/sparc/include/asm/siginfo.h | 1 - arch/sparc/kernel/signal32.c | 52 ------------------------ arch/tile/include/asm/compat.h | 62 +++++++++++++++++++++++++++++ arch/tile/kernel/compat_signal.c | 57 -------------------------- arch/x86/include/asm/compat.h | 74 +++++++++++++++++++++++++++++++++- arch/x86/include/asm/ia32.h | 67 ------------------------------- include/linux/compat.h | 5 --- 19 files changed, 513 insertions(+), 476 deletions(-) (limited to 'arch/parisc/kernel') diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index a670a33ad736..37e610dc084e 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -55,6 +55,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -130,6 +131,64 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + /* The padding is the same size as AArch64. */ + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid32_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid32_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + __compat_uid32_t _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + compat_uptr_t _addr; /* faulting insn/memory ref. */ + short _addr_lsb; /* LSB of the reported address */ + } _sigfault; + + /* SIGPOLL */ + struct { + compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -139,7 +198,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index ac74c2f261e3..0790a87a4346 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -30,59 +30,6 @@ #include #include -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - /* The padding is the same size as AArch64. */ - int _pad[SI_PAD_SIZE]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - __compat_uid32_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - __compat_uid32_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - __compat_uid32_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - compat_uptr_t _addr; /* faulting insn/memory ref. */ - short _addr_lsb; /* LSB of the reported address */ - } _sigfault; - - /* SIGPOLL */ - struct { - compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - struct compat_sigaction { compat_uptr_t sa_handler; compat_ulong_t sa_flags; diff --git a/arch/mips/include/asm/compat-signal.h b/arch/mips/include/asm/compat-signal.h index 368a99e5c3e1..6599a901b63e 100644 --- a/arch/mips/include/asm/compat-signal.h +++ b/arch/mips/include/asm/compat-signal.h @@ -10,68 +10,6 @@ #include -#define SI_PAD_SIZE32 ((SI_MAX_SIZE/sizeof(int)) - 3) - -typedef struct compat_siginfo { - int si_signo; - int si_code; - int si_errno; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - } _kill; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_uid_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* IRIX SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_clock_t _utime; - int _status; /* exit code */ - compat_clock_t _stime; - } _irix_sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - s32 _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL, SIGXFSZ (To do ...) */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - - /* POSIX.1b timers */ - struct { - timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval;/* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - } _sifields; -} compat_siginfo_t; - static inline int __copy_conv_sigset_to_user(compat_sigset_t __user *d, const sigset_t *s) { diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index b77df0366ee6..58277e0e9cd4 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -43,6 +43,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -124,6 +125,73 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define SI_PAD_SIZE32 (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_code; + int si_errno; + + union { + int _pad[SI_PAD_SIZE32]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + } _kill; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + __compat_uid_t _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* IRIX SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + compat_clock_t _utime; + int _status; /* exit code */ + compat_clock_t _stime; + } _irix_sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + s32 _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL, SIGXFSZ (To do ...) */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + + /* POSIX.1b timers */ + struct { + timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval;/* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -133,7 +201,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 760f331d4fa3..db7a662691a8 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -36,6 +36,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -127,6 +128,63 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + char _pad[sizeof(unsigned int) - sizeof(int)]; + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -136,7 +194,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h index c7800846422c..08a88b5349a2 100644 --- a/arch/parisc/kernel/signal32.h +++ b/arch/parisc/kernel/signal32.h @@ -55,58 +55,6 @@ struct k_sigaction32 { struct compat_sigaction sa; }; -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[((128/sizeof(int)) - 3)]; - - /* kill() */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - char _pad[sizeof(unsigned int) - sizeof(int)]; - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - int copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from); int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from); diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 88e602f6430d..84fdf6857c31 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -38,6 +38,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -114,6 +115,64 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define SI_PAD_SIZE32 (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[SI_PAD_SIZE32]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + __compat_uid_t _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -123,7 +182,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/powerpc/include/asm/siginfo.h b/arch/powerpc/include/asm/siginfo.h index 49495b0534ed..ccce3ef5cd86 100644 --- a/arch/powerpc/include/asm/siginfo.h +++ b/arch/powerpc/include/asm/siginfo.h @@ -10,7 +10,6 @@ #ifdef __powerpc64__ # define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) -# define SI_PAD_SIZE32 ((SI_MAX_SIZE/sizeof(int)) - 3) #endif #include diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h index dc16aefe1dd0..02fb0ee26093 100644 --- a/arch/powerpc/kernel/ppc32.h +++ b/arch/powerpc/kernel/ppc32.h @@ -16,57 +16,6 @@ /* These are here to support 32-bit syscalls on a 64-bit kernel. */ -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_uid_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - #define __old_sigaction32 old_sigaction32 struct __old_sigaction32 { diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 234f1d859cea..a34a9d612fc0 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -65,6 +65,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -144,6 +145,79 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + pid_t _pid; /* sender's pid */ + uid_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + pid_t _pid; /* sender's pid */ + uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + pid_t _pid; /* which child */ + uid_t _uid; /* sender's uid */ + int _status;/* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + __u32 _addr; /* faulting insn/memory ref. - pointer */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + +/* + * How these fields are to be accessed. + */ +#define si_pid _sifields._kill._pid +#define si_uid _sifields._kill._uid +#define si_status _sifields._sigchld._status +#define si_utime _sifields._sigchld._utime +#define si_stime _sifields._sigchld._stime +#define si_value _sifields._rt._sigval +#define si_int _sifields._rt._sigval.sival_int +#define si_ptr _sifields._rt._sigval.sival_ptr +#define si_addr _sifields._sigfault._addr +#define si_band _sifields._sigpoll._band +#define si_fd _sifields._sigpoll._fd +#define si_tid _sifields._timer._tid +#define si_overrun _sifields._timer._overrun + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -153,7 +227,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 9635d759c2b9..90887bd98cf0 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -23,74 +23,6 @@ struct old_sigaction32 { __u32 sa_flags; __u32 sa_restorer; /* Another 32 bit pointer */ }; - -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[((128/sizeof(int)) - 3)]; - - /* kill() */ - struct { - pid_t _pid; /* sender's pid */ - uid_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - pid_t _pid; /* sender's pid */ - uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - pid_t _pid; /* which child */ - uid_t _uid; /* sender's uid */ - int _status;/* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - __u32 _addr; /* faulting insn/memory ref. - pointer */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - -/* - * How these fields are to be accessed. - */ -#define si_pid _sifields._kill._pid -#define si_uid _sifields._kill._uid -#define si_status _sifields._sigchld._status -#define si_utime _sifields._sigchld._utime -#define si_stime _sifields._sigchld._stime -#define si_value _sifields._rt._sigval -#define si_int _sifields._rt._sigval.sival_int -#define si_ptr _sifields._rt._sigval.sival_ptr -#define si_addr _sifields._sigfault._addr -#define si_band _sifields._sigpoll._band -#define si_fd _sifields._sigpoll._fd -#define si_tid _sifields._timer._tid -#define si_overrun _sifields._timer._overrun /* asm/sigcontext.h */ typedef union diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index b8be20d42a0a..cef99fbc0a21 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -36,6 +36,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -147,6 +148,65 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define SI_PAD_SIZE32 (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[SI_PAD_SIZE32]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ + struct { + u32 _addr; /* faulting insn/memory ref. */ + int _trapno; + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -156,7 +216,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/sparc/include/asm/siginfo.h b/arch/sparc/include/asm/siginfo.h index 215900fce21b..dbc182c438b4 100644 --- a/arch/sparc/include/asm/siginfo.h +++ b/arch/sparc/include/asm/siginfo.h @@ -3,7 +3,6 @@ #if defined(__sparc__) && defined(__arch64__) -#define SI_PAD_SIZE32 ((SI_MAX_SIZE/sizeof(int)) - 3) #define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) #define __ARCH_SI_BAND_T int diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index a53e0a5fd3a3..53e48f721ce3 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -54,58 +54,6 @@ struct signal_frame32 { /* __siginfo_rwin_t * */u32 rwin_save; } __attribute__((aligned(8))); -typedef struct compat_siginfo{ - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ - struct { - u32 _addr; /* faulting insn/memory ref. */ - int _trapno; - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -}compat_siginfo_t; - struct rt_signal_frame32 { struct sparc_stackf32 ss; compat_siginfo_t info; diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h index 6e74450ff0a1..3063e6fc8daa 100644 --- a/arch/tile/include/asm/compat.h +++ b/arch/tile/include/asm/compat.h @@ -110,6 +110,68 @@ struct compat_flock64 { typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define COMPAT_SI_PAD_SIZE (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[COMPAT_SI_PAD_SIZE]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + int _overrun_incr; /* amount to add to overrun */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ +#ifdef __ARCH_SI_TRAPNO + int _trapno; /* TRAP # which caused the signal */ +#endif + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c index 474571b84085..7bc0859a9f5e 100644 --- a/arch/tile/kernel/compat_signal.c +++ b/arch/tile/kernel/compat_signal.c @@ -55,63 +55,6 @@ struct compat_ucontext { sigset_t uc_sigmask; /* mask last for extensibility */ }; -#define COMPAT_SI_PAD_SIZE ((SI_MAX_SIZE - 3 * sizeof(int)) / sizeof(int)) - -struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[COMPAT_SI_PAD_SIZE]; - - /* kill() */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - int _overrun_incr; /* amount to add to overrun */ - } _timer; - - /* POSIX.1b signals */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ -#ifdef __ARCH_SI_TRAPNO - int _trapno; /* TRAP # which caused the signal */ -#endif - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -}; - struct compat_rt_sigframe { unsigned char save_area[C_ABI_SAVE_AREA_SIZE]; /* caller save area */ struct compat_siginfo info; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index fedf32b73e65..59c6c401f79f 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -41,6 +41,7 @@ typedef s64 __attribute__((aligned(4))) compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 __attribute__((aligned(4))) compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -124,6 +125,78 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + int _overrun_incr; /* amount to add to overrun */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGCHLD (x32 version) */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_s64 _utime; + compat_s64 _stime; + } _sigchld_x32; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + + struct { + unsigned int _call_addr; /* calling insn */ + int _syscall; /* triggering system call number */ + unsigned int _arch; /* AUDIT_ARCH_* of syscall */ + } _sigsys; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -209,7 +282,6 @@ typedef struct user_regs_struct32 compat_elf_gregset_t; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index b04cbdb138cd..e6232773ce49 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -86,73 +86,6 @@ struct stat64 { unsigned long long st_ino; } __attribute__((packed)); -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[((128 / sizeof(int)) - 3)]; - - /* kill() */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - int _overrun_incr; /* amount to add to overrun */ - } _timer; - - /* POSIX.1b signals */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGCHLD (x32 version) */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_s64 _utime; - compat_s64 _stime; - } _sigchld_x32; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - - struct { - unsigned int _call_addr; /* calling insn */ - int _syscall; /* triggering system call number */ - unsigned int _arch; /* AUDIT_ARCH_* of syscall */ - } _sigsys; - } _sifields; -} compat_siginfo_t; - #define IA32_STACK_TOP IA32_PAGE_OFFSET #ifdef __KERNEL__ diff --git a/include/linux/compat.h b/include/linux/compat.h index fd4e29956d1c..3f53d002c7c5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -160,11 +160,6 @@ struct compat_ustat { char f_fpack[6]; }; -typedef union compat_sigval { - compat_int_t sival_int; - compat_uptr_t sival_ptr; -} compat_sigval_t; - #define COMPAT_SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3) typedef struct compat_sigevent { -- cgit v1.3-14-g43fede From 6b2dbba8b6ac4df26f72eda1e5ea7bab9f950e08 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Oct 2012 16:31:25 -0700 Subject: mm: replace vma prio_tree with an interval tree Implement an interval tree as a replacement for the VMA prio_tree. The algorithms are similar to lib/interval_tree.c; however that code can't be directly reused as the interval endpoints are not explicitly stored in the VMA. So instead, the common algorithm is moved into a template and the details (node type, how to get interval endpoints from the node, etc) are filled in using the C preprocessor. Once the interval tree functions are available, using them as a replacement to the VMA prio tree is a relatively simple, mechanical job. Signed-off-by: Michel Lespinasse Cc: Rik van Riel Cc: Hillf Danton Cc: Peter Zijlstra Cc: Catalin Marinas Cc: Andrea Arcangeli Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/fault-armv.c | 3 +- arch/arm/mm/flush.c | 3 +- arch/parisc/kernel/cache.c | 3 +- arch/x86/mm/hugetlbpage.c | 3 +- fs/hugetlbfs/inode.c | 9 +- fs/inode.c | 2 +- include/linux/fs.h | 6 +- include/linux/interval_tree_tmpl.h | 215 +++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 30 +++--- include/linux/mm_types.h | 14 +-- kernel/events/uprobes.c | 3 +- kernel/fork.c | 2 +- lib/interval_tree.c | 166 ++-------------------------- lib/prio_tree.c | 19 +--- mm/Makefile | 4 +- mm/filemap_xip.c | 3 +- mm/fremap.c | 2 +- mm/hugetlb.c | 3 +- mm/interval_tree.c | 61 +++++++++++ mm/memory-failure.c | 3 +- mm/memory.c | 9 +- mm/mmap.c | 22 ++-- mm/nommu.c | 12 +-- mm/prio_tree.c | 208 ----------------------------------- mm/rmap.c | 18 ++-- 25 files changed, 357 insertions(+), 466 deletions(-) create mode 100644 include/linux/interval_tree_tmpl.h create mode 100644 mm/interval_tree.c delete mode 100644 mm/prio_tree.c (limited to 'arch/parisc/kernel') diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 7599e2625c7d..2a5907b5c8d2 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -134,7 +134,6 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *mpnt; - struct prio_tree_iter iter; unsigned long offset; pgoff_t pgoff; int aliases = 0; @@ -147,7 +146,7 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma, * cache coherency. */ flush_dcache_mmap_lock(mapping); - vma_prio_tree_foreach(mpnt, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { /* * If this VMA is not in our MM, we can ignore it. * Note that we intentionally mask out the VMA diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 40ca11ed6e5f..1c8f7f564175 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -196,7 +196,6 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p { struct mm_struct *mm = current->active_mm; struct vm_area_struct *mpnt; - struct prio_tree_iter iter; pgoff_t pgoff; /* @@ -208,7 +207,7 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); flush_dcache_mmap_lock(mapping); - vma_prio_tree_foreach(mpnt, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { unsigned long offset; /* diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 9d181890a7e3..48e16dc20102 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -276,7 +276,6 @@ void flush_dcache_page(struct page *page) { struct address_space *mapping = page_mapping(page); struct vm_area_struct *mpnt; - struct prio_tree_iter iter; unsigned long offset; unsigned long addr, old_addr = 0; pgoff_t pgoff; @@ -299,7 +298,7 @@ void flush_dcache_page(struct page *page) * to flush one address here for them all to become coherent */ flush_dcache_mmap_lock(mapping); - vma_prio_tree_foreach(mpnt, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index b91e48512425..937bff5cdaa7 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -71,7 +71,6 @@ huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - struct prio_tree_iter iter; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; @@ -81,7 +80,7 @@ huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) return (pte_t *)pmd_alloc(mm, pud, addr); mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) { + vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 0a0ab8e21b19..c5bc355d8243 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -397,17 +397,16 @@ static void hugetlbfs_evict_inode(struct inode *inode) } static inline void -hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff) +hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff) { struct vm_area_struct *vma; - struct prio_tree_iter iter; - vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) { + vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) { unsigned long v_offset; /* * Can the expression below overflow on 32-bit arches? - * No, because the prio_tree returns us only those vmas + * No, because the interval tree returns us only those vmas * which overlap the truncated area starting at pgoff, * and no vma on a 32-bit arch can span beyond the 4GB. */ @@ -432,7 +431,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_size_write(inode, offset); mutex_lock(&mapping->i_mmap_mutex); - if (!prio_tree_empty(&mapping->i_mmap)) + if (!RB_EMPTY_ROOT(&mapping->i_mmap)) hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff); mutex_unlock(&mapping->i_mmap_mutex); truncate_hugepages(inode, offset); diff --git a/fs/inode.c b/fs/inode.c index ac8d904b3f16..b03c71957246 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -348,7 +348,7 @@ void address_space_init_once(struct address_space *mapping) mutex_init(&mapping->i_mmap_mutex); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); - INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap); + mapping->i_mmap = RB_ROOT; INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); } EXPORT_SYMBOL(address_space_init_once); diff --git a/include/linux/fs.h b/include/linux/fs.h index 5a8a273d5b2f..c617ed024df8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -401,7 +401,7 @@ struct inodes_stat_t { #include #include #include -#include +#include #include #include #include @@ -669,7 +669,7 @@ struct address_space { struct radix_tree_root page_tree; /* radix tree of all pages */ spinlock_t tree_lock; /* and lock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ - struct prio_tree_root i_mmap; /* tree of private and shared mappings */ + struct rb_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct mutex i_mmap_mutex; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ @@ -741,7 +741,7 @@ int mapping_tagged(struct address_space *mapping, int tag); */ static inline int mapping_mapped(struct address_space *mapping) { - return !prio_tree_empty(&mapping->i_mmap) || + return !RB_EMPTY_ROOT(&mapping->i_mmap) || !list_empty(&mapping->i_mmap_nonlinear); } diff --git a/include/linux/interval_tree_tmpl.h b/include/linux/interval_tree_tmpl.h new file mode 100644 index 000000000000..c65deda31413 --- /dev/null +++ b/include/linux/interval_tree_tmpl.h @@ -0,0 +1,215 @@ +/* + Interval Trees + (C) 2012 Michel Lespinasse + + 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. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + include/linux/interval_tree_tmpl.h +*/ + +/* + * Template for implementing interval trees + * + * ITSTRUCT: struct type of the interval tree nodes + * ITRB: name of struct rb_node field within ITSTRUCT + * ITTYPE: type of the interval endpoints + * ITSUBTREE: name of ITTYPE field within ITSTRUCT holding last-in-subtree + * ITSTART(n): start endpoint of ITSTRUCT node n + * ITLAST(n): last endpoing of ITSTRUCT node n + * ITSTATIC: 'static' or empty + * ITPREFIX: prefix to use for the inline tree definitions + */ + +/* IT(name) -> ITPREFIX_name */ +#define _ITNAME(prefix, name) prefix ## _ ## name +#define ITNAME(prefix, name) _ITNAME(prefix, name) +#define IT(name) ITNAME(ITPREFIX, name) + +/* Callbacks for augmented rbtree insert and remove */ + +static inline ITTYPE IT(compute_subtree_last)(ITSTRUCT *node) +{ + ITTYPE max = ITLAST(node), subtree_last; + if (node->ITRB.rb_left) { + subtree_last = rb_entry(node->ITRB.rb_left, + ITSTRUCT, ITRB)->ITSUBTREE; + if (max < subtree_last) + max = subtree_last; + } + if (node->ITRB.rb_right) { + subtree_last = rb_entry(node->ITRB.rb_right, + ITSTRUCT, ITRB)->ITSUBTREE; + if (max < subtree_last) + max = subtree_last; + } + return max; +} + +static void IT(augment_propagate)(struct rb_node *rb, struct rb_node *stop) +{ + while (rb != stop) { + ITSTRUCT *node = rb_entry(rb, ITSTRUCT, ITRB); + ITTYPE subtree_last = IT(compute_subtree_last)(node); + if (node->ITSUBTREE == subtree_last) + break; + node->ITSUBTREE = subtree_last; + rb = rb_parent(&node->ITRB); + } +} + +static void IT(augment_copy)(struct rb_node *rb_old, struct rb_node *rb_new) +{ + ITSTRUCT *old = rb_entry(rb_old, ITSTRUCT, ITRB); + ITSTRUCT *new = rb_entry(rb_new, ITSTRUCT, ITRB); + + new->ITSUBTREE = old->ITSUBTREE; +} + +static void IT(augment_rotate)(struct rb_node *rb_old, struct rb_node *rb_new) +{ + ITSTRUCT *old = rb_entry(rb_old, ITSTRUCT, ITRB); + ITSTRUCT *new = rb_entry(rb_new, ITSTRUCT, ITRB); + + new->ITSUBTREE = old->ITSUBTREE; + old->ITSUBTREE = IT(compute_subtree_last)(old); +} + +static const struct rb_augment_callbacks IT(augment_callbacks) = { + IT(augment_propagate), IT(augment_copy), IT(augment_rotate) +}; + +/* Insert / remove interval nodes from the tree */ + +ITSTATIC void IT(insert)(ITSTRUCT *node, struct rb_root *root) +{ + struct rb_node **link = &root->rb_node, *rb_parent = NULL; + ITTYPE start = ITSTART(node), last = ITLAST(node); + ITSTRUCT *parent; + + while (*link) { + rb_parent = *link; + parent = rb_entry(rb_parent, ITSTRUCT, ITRB); + if (parent->ITSUBTREE < last) + parent->ITSUBTREE = last; + if (start < ITSTART(parent)) + link = &parent->ITRB.rb_left; + else + link = &parent->ITRB.rb_right; + } + + node->ITSUBTREE = last; + rb_link_node(&node->ITRB, rb_parent, link); + rb_insert_augmented(&node->ITRB, root, &IT(augment_callbacks)); +} + +ITSTATIC void IT(remove)(ITSTRUCT *node, struct rb_root *root) +{ + rb_erase_augmented(&node->ITRB, root, &IT(augment_callbacks)); +} + +/* + * Iterate over intervals intersecting [start;last] + * + * Note that a node's interval intersects [start;last] iff: + * Cond1: ITSTART(node) <= last + * and + * Cond2: start <= ITLAST(node) + */ + +static ITSTRUCT *IT(subtree_search)(ITSTRUCT *node, ITTYPE start, ITTYPE last) +{ + while (true) { + /* + * Loop invariant: start <= node->ITSUBTREE + * (Cond2 is satisfied by one of the subtree nodes) + */ + if (node->ITRB.rb_left) { + ITSTRUCT *left = rb_entry(node->ITRB.rb_left, + ITSTRUCT, ITRB); + if (start <= left->ITSUBTREE) { + /* + * Some nodes in left subtree satisfy Cond2. + * Iterate to find the leftmost such node N. + * If it also satisfies Cond1, that's the match + * we are looking for. Otherwise, there is no + * matching interval as nodes to the right of N + * can't satisfy Cond1 either. + */ + node = left; + continue; + } + } + if (ITSTART(node) <= last) { /* Cond1 */ + if (start <= ITLAST(node)) /* Cond2 */ + return node; /* node is leftmost match */ + if (node->ITRB.rb_right) { + node = rb_entry(node->ITRB.rb_right, + ITSTRUCT, ITRB); + if (start <= node->ITSUBTREE) + continue; + } + } + return NULL; /* No match */ + } +} + +ITSTATIC ITSTRUCT *IT(iter_first)(struct rb_root *root, + ITTYPE start, ITTYPE last) +{ + ITSTRUCT *node; + + if (!root->rb_node) + return NULL; + node = rb_entry(root->rb_node, ITSTRUCT, ITRB); + if (node->ITSUBTREE < start) + return NULL; + return IT(subtree_search)(node, start, last); +} + +ITSTATIC ITSTRUCT *IT(iter_next)(ITSTRUCT *node, ITTYPE start, ITTYPE last) +{ + struct rb_node *rb = node->ITRB.rb_right, *prev; + + while (true) { + /* + * Loop invariants: + * Cond1: ITSTART(node) <= last + * rb == node->ITRB.rb_right + * + * First, search right subtree if suitable + */ + if (rb) { + ITSTRUCT *right = rb_entry(rb, ITSTRUCT, ITRB); + if (start <= right->ITSUBTREE) + return IT(subtree_search)(right, start, last); + } + + /* Move up the tree until we come from a node's left child */ + do { + rb = rb_parent(&node->ITRB); + if (!rb) + return NULL; + prev = &node->ITRB; + node = rb_entry(rb, ITSTRUCT, ITRB); + rb = node->ITRB.rb_right; + } while (prev == rb); + + /* Check if the node intersects [start;last] */ + if (last < ITSTART(node)) /* !Cond1 */ + return NULL; + else if (start <= ITLAST(node)) /* Cond2 */ + return node; + } +} diff --git a/include/linux/mm.h b/include/linux/mm.h index 5ddb11b2b4bb..0f671ef09eba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -1355,22 +1354,27 @@ extern void zone_pcp_reset(struct zone *zone); extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); -/* prio_tree.c */ -void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); -void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); -void vma_prio_tree_remove(struct vm_area_struct *, struct prio_tree_root *); -struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma, - struct prio_tree_iter *iter); - -#define vma_prio_tree_foreach(vma, iter, root, begin, end) \ - for (prio_tree_iter_init(iter, root, begin, end), vma = NULL; \ - (vma = vma_prio_tree_next(vma, iter)); ) +/* interval_tree.c */ +void vma_interval_tree_add(struct vm_area_struct *vma, + struct vm_area_struct *old, + struct address_space *mapping); +void vma_interval_tree_insert(struct vm_area_struct *node, + struct rb_root *root); +void vma_interval_tree_remove(struct vm_area_struct *node, + struct rb_root *root); +struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root *root, + unsigned long start, unsigned long last); +struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, + unsigned long start, unsigned long last); + +#define vma_interval_tree_foreach(vma, root, start, last) \ + for (vma = vma_interval_tree_iter_first(root, start, last); \ + vma; vma = vma_interval_tree_iter_next(vma, start, last)) static inline void vma_nonlinear_insert(struct vm_area_struct *vma, struct list_head *list) { - vma->shared.vm_set.parent = NULL; - list_add_tail(&vma->shared.vm_set.list, list); + list_add_tail(&vma->shared.nonlinear, list); } /* mmap.c */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a57a43f5ca7c..31f8a3af7d94 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include #include @@ -240,18 +239,15 @@ struct vm_area_struct { /* * For areas with an address space and backing store, - * linkage into the address_space->i_mmap prio tree, or - * linkage to the list of like vmas hanging off its node, or + * linkage into the address_space->i_mmap interval tree, or * linkage of vma in the address_space->i_mmap_nonlinear list. */ union { struct { - struct list_head list; - void *parent; /* aligns with prio_tree_node parent */ - struct vm_area_struct *head; - } vm_set; - - struct raw_prio_tree_node prio_tree_node; + struct rb_node rb; + unsigned long rb_subtree_last; + } linear; + struct list_head nonlinear; } shared; /* diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 912ef48d28ab..1d9c0a985960 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -735,7 +735,6 @@ static struct map_info * build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { unsigned long pgoff = offset >> PAGE_SHIFT; - struct prio_tree_iter iter; struct vm_area_struct *vma; struct map_info *curr = NULL; struct map_info *prev = NULL; @@ -744,7 +743,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register) again: mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; diff --git a/kernel/fork.c b/kernel/fork.c index 972762e01024..90dace52715e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -423,7 +423,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mapping->i_mmap_writable++; flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ - vma_prio_tree_add(tmp, mpnt); + vma_interval_tree_add(tmp, mpnt, mapping); flush_dcache_mmap_unlock(mapping); mutex_unlock(&mapping->i_mmap_mutex); } diff --git a/lib/interval_tree.c b/lib/interval_tree.c index 6fd540b1e499..77a793e0644b 100644 --- a/lib/interval_tree.c +++ b/lib/interval_tree.c @@ -1,159 +1,13 @@ #include #include -/* Callbacks for augmented rbtree insert and remove */ - -static inline unsigned long -compute_subtree_last(struct interval_tree_node *node) -{ - unsigned long max = node->last, subtree_last; - if (node->rb.rb_left) { - subtree_last = rb_entry(node->rb.rb_left, - struct interval_tree_node, rb)->__subtree_last; - if (max < subtree_last) - max = subtree_last; - } - if (node->rb.rb_right) { - subtree_last = rb_entry(node->rb.rb_right, - struct interval_tree_node, rb)->__subtree_last; - if (max < subtree_last) - max = subtree_last; - } - return max; -} - -RB_DECLARE_CALLBACKS(static, augment_callbacks, struct interval_tree_node, rb, - unsigned long, __subtree_last, compute_subtree_last) - -/* Insert / remove interval nodes from the tree */ - -void interval_tree_insert(struct interval_tree_node *node, - struct rb_root *root) -{ - struct rb_node **link = &root->rb_node, *rb_parent = NULL; - unsigned long start = node->start, last = node->last; - struct interval_tree_node *parent; - - while (*link) { - rb_parent = *link; - parent = rb_entry(rb_parent, struct interval_tree_node, rb); - if (parent->__subtree_last < last) - parent->__subtree_last = last; - if (start < parent->start) - link = &parent->rb.rb_left; - else - link = &parent->rb.rb_right; - } - - node->__subtree_last = last; - rb_link_node(&node->rb, rb_parent, link); - rb_insert_augmented(&node->rb, root, &augment_callbacks); -} - -void interval_tree_remove(struct interval_tree_node *node, - struct rb_root *root) -{ - rb_erase_augmented(&node->rb, root, &augment_callbacks); -} - -/* - * Iterate over intervals intersecting [start;last] - * - * Note that a node's interval intersects [start;last] iff: - * Cond1: node->start <= last - * and - * Cond2: start <= node->last - */ - -static struct interval_tree_node * -subtree_search(struct interval_tree_node *node, - unsigned long start, unsigned long last) -{ - while (true) { - /* - * Loop invariant: start <= node->__subtree_last - * (Cond2 is satisfied by one of the subtree nodes) - */ - if (node->rb.rb_left) { - struct interval_tree_node *left = - rb_entry(node->rb.rb_left, - struct interval_tree_node, rb); - if (start <= left->__subtree_last) { - /* - * Some nodes in left subtree satisfy Cond2. - * Iterate to find the leftmost such node N. - * If it also satisfies Cond1, that's the match - * we are looking for. Otherwise, there is no - * matching interval as nodes to the right of N - * can't satisfy Cond1 either. - */ - node = left; - continue; - } - } - if (node->start <= last) { /* Cond1 */ - if (start <= node->last) /* Cond2 */ - return node; /* node is leftmost match */ - if (node->rb.rb_right) { - node = rb_entry(node->rb.rb_right, - struct interval_tree_node, rb); - if (start <= node->__subtree_last) - continue; - } - } - return NULL; /* No match */ - } -} - -struct interval_tree_node * -interval_tree_iter_first(struct rb_root *root, - unsigned long start, unsigned long last) -{ - struct interval_tree_node *node; - - if (!root->rb_node) - return NULL; - node = rb_entry(root->rb_node, struct interval_tree_node, rb); - if (node->__subtree_last < start) - return NULL; - return subtree_search(node, start, last); -} - -struct interval_tree_node * -interval_tree_iter_next(struct interval_tree_node *node, - unsigned long start, unsigned long last) -{ - struct rb_node *rb = node->rb.rb_right, *prev; - - while (true) { - /* - * Loop invariants: - * Cond1: node->start <= last - * rb == node->rb.rb_right - * - * First, search right subtree if suitable - */ - if (rb) { - struct interval_tree_node *right = - rb_entry(rb, struct interval_tree_node, rb); - if (start <= right->__subtree_last) - return subtree_search(right, start, last); - } - - /* Move up the tree until we come from a node's left child */ - do { - rb = rb_parent(&node->rb); - if (!rb) - return NULL; - prev = &node->rb; - node = rb_entry(rb, struct interval_tree_node, rb); - rb = node->rb.rb_right; - } while (prev == rb); - - /* Check if the node intersects [start;last] */ - if (last < node->start) /* !Cond1 */ - return NULL; - else if (start <= node->last) /* Cond2 */ - return node; - } -} +#define ITSTRUCT struct interval_tree_node +#define ITRB rb +#define ITTYPE unsigned long +#define ITSUBTREE __subtree_last +#define ITSTART(n) ((n)->start) +#define ITLAST(n) ((n)->last) +#define ITSTATIC +#define ITPREFIX interval_tree + +#include diff --git a/lib/prio_tree.c b/lib/prio_tree.c index 4e0d2edff2b4..bba37148c15e 100644 --- a/lib/prio_tree.c +++ b/lib/prio_tree.c @@ -44,27 +44,12 @@ * The following macros are used for implementing prio_tree for i_mmap */ -#define RADIX_INDEX(vma) ((vma)->vm_pgoff) -#define VMA_SIZE(vma) (((vma)->vm_end - (vma)->vm_start) >> PAGE_SHIFT) -/* avoid overflow */ -#define HEAP_INDEX(vma) ((vma)->vm_pgoff + (VMA_SIZE(vma) - 1)) - - static void get_index(const struct prio_tree_root *root, const struct prio_tree_node *node, unsigned long *radix, unsigned long *heap) { - if (root->raw) { - struct vm_area_struct *vma = prio_tree_entry( - node, struct vm_area_struct, shared.prio_tree_node); - - *radix = RADIX_INDEX(vma); - *heap = HEAP_INDEX(vma); - } - else { - *radix = node->start; - *heap = node->last; - } + *radix = node->start; + *heap = node->last; } static unsigned long index_bits_to_maxindex[BITS_PER_LONG]; diff --git a/mm/Makefile b/mm/Makefile index 92753e2d82da..6b025f80af34 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -14,9 +14,9 @@ endif obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ - prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ + util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o $(mmu-y) + compaction.o interval_tree.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 91750227a191..a52daee11d3f 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -167,7 +167,6 @@ __xip_unmap (struct address_space * mapping, { struct vm_area_struct *vma; struct mm_struct *mm; - struct prio_tree_iter iter; unsigned long address; pte_t *pte; pte_t pteval; @@ -184,7 +183,7 @@ __xip_unmap (struct address_space * mapping, retry: mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { mm = vma->vm_mm; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); diff --git a/mm/fremap.c b/mm/fremap.c index 3d731a498788..3899a86851ce 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -214,7 +214,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); vma->vm_flags |= VM_NONLINEAR; - vma_prio_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); flush_dcache_mmap_unlock(mapping); mutex_unlock(&mapping->i_mmap_mutex); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f1bb534254f6..c9b40e3a9936 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2474,7 +2474,6 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; - struct prio_tree_iter iter; pgoff_t pgoff; /* @@ -2491,7 +2490,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * __unmap_hugepage_range() is called as the lock is already held */ mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; diff --git a/mm/interval_tree.c b/mm/interval_tree.c new file mode 100644 index 000000000000..7dc565660e56 --- /dev/null +++ b/mm/interval_tree.c @@ -0,0 +1,61 @@ +/* + * mm/interval_tree.c - interval tree for mapping->i_mmap + * + * Copyright (C) 2012, Michel Lespinasse + * + * This file is released under the GPL v2. + */ + +#include +#include + +#define ITSTRUCT struct vm_area_struct +#define ITRB shared.linear.rb +#define ITTYPE unsigned long +#define ITSUBTREE shared.linear.rb_subtree_last +#define ITSTART(n) ((n)->vm_pgoff) +#define ITLAST(n) ((n)->vm_pgoff + \ + (((n)->vm_end - (n)->vm_start) >> PAGE_SHIFT) - 1) +#define ITSTATIC +#define ITPREFIX vma_interval_tree + +#include + +/* Insert old immediately after vma in the interval tree */ +void vma_interval_tree_add(struct vm_area_struct *vma, + struct vm_area_struct *old, + struct address_space *mapping) +{ + struct rb_node **link; + struct vm_area_struct *parent; + unsigned long last; + + if (unlikely(vma->vm_flags & VM_NONLINEAR)) { + list_add(&vma->shared.nonlinear, &old->shared.nonlinear); + return; + } + + last = ITLAST(vma); + + if (!old->shared.linear.rb.rb_right) { + parent = old; + link = &old->shared.linear.rb.rb_right; + } else { + parent = rb_entry(old->shared.linear.rb.rb_right, + struct vm_area_struct, shared.linear.rb); + if (parent->shared.linear.rb_subtree_last < last) + parent->shared.linear.rb_subtree_last = last; + while (parent->shared.linear.rb.rb_left) { + parent = rb_entry(parent->shared.linear.rb.rb_left, + struct vm_area_struct, shared.linear.rb); + if (parent->shared.linear.rb_subtree_last < last) + parent->shared.linear.rb_subtree_last = last; + } + link = &parent->shared.linear.rb.rb_left; + } + + vma->shared.linear.rb_subtree_last = last; + rb_link_node(&vma->shared.linear.rb, &parent->shared.linear.rb, link); + rb_insert_augmented(&vma->shared.linear.rb, &mapping->i_mmap, + &vma_interval_tree_augment_callbacks); +} diff --git a/mm/memory-failure.c b/mm/memory-failure.c index a6e2141a6610..c38a6257d082 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -431,7 +431,6 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, { struct vm_area_struct *vma; struct task_struct *tsk; - struct prio_tree_iter iter; struct address_space *mapping = page->mapping; mutex_lock(&mapping->i_mmap_mutex); @@ -442,7 +441,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, if (!task_early_kill(tsk)) continue; - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* * Send early kill signal to tasks where a vma covers diff --git a/mm/memory.c b/mm/memory.c index e09c04813186..d205e4381a34 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2801,14 +2801,13 @@ static void unmap_mapping_range_vma(struct vm_area_struct *vma, zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } -static inline void unmap_mapping_range_tree(struct prio_tree_root *root, +static inline void unmap_mapping_range_tree(struct rb_root *root, struct zap_details *details) { struct vm_area_struct *vma; - struct prio_tree_iter iter; pgoff_t vba, vea, zba, zea; - vma_prio_tree_foreach(vma, &iter, root, + vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; @@ -2839,7 +2838,7 @@ static inline void unmap_mapping_range_list(struct list_head *head, * across *all* the pages in each nonlinear VMA, not just the pages * whose virtual address lies outside the file truncation point. */ - list_for_each_entry(vma, head, shared.vm_set.list) { + list_for_each_entry(vma, head, shared.nonlinear) { details->nonlinear_vma = vma; unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); } @@ -2883,7 +2882,7 @@ void unmap_mapping_range(struct address_space *mapping, mutex_lock(&mapping->i_mmap_mutex); - if (unlikely(!prio_tree_empty(&mapping->i_mmap))) + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); diff --git a/mm/mmap.c b/mm/mmap.c index e3c365ff1b6a..5ac533f88e99 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -199,14 +199,14 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, flush_dcache_mmap_lock(mapping); if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.vm_set.list); + list_del_init(&vma->shared.nonlinear); else - vma_prio_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* - * Unlink a file-based vm structure from its prio_tree, to hide + * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) @@ -411,7 +411,7 @@ static void __vma_link_file(struct vm_area_struct *vma) if (unlikely(vma->vm_flags & VM_NONLINEAR)) vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); else - vma_prio_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -449,7 +449,7 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, /* * Helper for vma_adjust() in the split_vma insert case: insert a vma into the - * mm's list and rbtree. It has already been inserted into the prio_tree. + * mm's list and rbtree. It has already been inserted into the interval tree. */ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { @@ -491,7 +491,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, struct vm_area_struct *next = vma->vm_next; struct vm_area_struct *importer = NULL; struct address_space *mapping = NULL; - struct prio_tree_root *root = NULL; + struct rb_root *root = NULL; struct anon_vma *anon_vma = NULL; struct file *file = vma->vm_file; long adjust_next = 0; @@ -554,7 +554,7 @@ again: remove_next = 1 + (end > next->vm_end); mutex_lock(&mapping->i_mmap_mutex); if (insert) { /* - * Put into prio_tree now, so instantiated pages + * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. @@ -582,9 +582,9 @@ again: remove_next = 1 + (end > next->vm_end); if (root) { flush_dcache_mmap_lock(mapping); - vma_prio_tree_remove(vma, root); + vma_interval_tree_remove(vma, root); if (adjust_next) - vma_prio_tree_remove(next, root); + vma_interval_tree_remove(next, root); } vma->vm_start = start; @@ -597,8 +597,8 @@ again: remove_next = 1 + (end > next->vm_end); if (root) { if (adjust_next) - vma_prio_tree_insert(next, root); - vma_prio_tree_insert(vma, root); + vma_interval_tree_insert(next, root); + vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } diff --git a/mm/nommu.c b/mm/nommu.c index 12e84e69dd06..45131b41bcdb 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -698,7 +698,7 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); - vma_prio_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); mutex_unlock(&mapping->i_mmap_mutex); } @@ -764,7 +764,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); - vma_prio_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); mutex_unlock(&mapping->i_mmap_mutex); } @@ -2044,7 +2044,6 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, size_t newsize) { struct vm_area_struct *vma; - struct prio_tree_iter iter; struct vm_region *region; pgoff_t low, high; size_t r_size, r_top; @@ -2056,8 +2055,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, mutex_lock(&inode->i_mapping->i_mmap_mutex); /* search for VMAs that fall within the dead zone */ - vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap, - low, high) { + vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) { /* found one - only interested if it's shared out of the page * cache */ if (vma->vm_flags & VM_SHARED) { @@ -2073,8 +2071,8 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, * we don't check for any regions that start beyond the EOF as there * shouldn't be any */ - vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap, - 0, ULONG_MAX) { + vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, + 0, ULONG_MAX) { if (!(vma->vm_flags & VM_SHARED)) continue; diff --git a/mm/prio_tree.c b/mm/prio_tree.c deleted file mode 100644 index 799dcfd7cd8c..000000000000 --- a/mm/prio_tree.c +++ /dev/null @@ -1,208 +0,0 @@ -/* - * mm/prio_tree.c - priority search tree for mapping->i_mmap - * - * Copyright (C) 2004, Rajesh Venkatasubramanian - * - * This file is released under the GPL v2. - * - * Based on the radix priority search tree proposed by Edward M. McCreight - * SIAM Journal of Computing, vol. 14, no.2, pages 257-276, May 1985 - * - * 02Feb2004 Initial version - */ - -#include -#include -#include - -/* - * See lib/prio_tree.c for details on the general radix priority search tree - * code. - */ - -/* - * The following #defines are mirrored from lib/prio_tree.c. They're only used - * for debugging, and should be removed (along with the debugging code using - * them) when switching also VMAs to the regular prio_tree code. - */ - -#define RADIX_INDEX(vma) ((vma)->vm_pgoff) -#define VMA_SIZE(vma) (((vma)->vm_end - (vma)->vm_start) >> PAGE_SHIFT) -/* avoid overflow */ -#define HEAP_INDEX(vma) ((vma)->vm_pgoff + (VMA_SIZE(vma) - 1)) - -/* - * Radix priority search tree for address_space->i_mmap - * - * For each vma that map a unique set of file pages i.e., unique [radix_index, - * heap_index] value, we have a corresponding priority search tree node. If - * multiple vmas have identical [radix_index, heap_index] value, then one of - * them is used as a tree node and others are stored in a vm_set list. The tree - * node points to the first vma (head) of the list using vm_set.head. - * - * prio_tree_root - * | - * A vm_set.head - * / \ / - * L R -> H-I-J-K-M-N-O-P-Q-S - * ^ ^ <-- vm_set.list --> - * tree nodes - * - * We need some way to identify whether a vma is a tree node, head of a vm_set - * list, or just a member of a vm_set list. We cannot use vm_flags to store - * such information. The reason is, in the above figure, it is possible that - * vm_flags' of R and H are covered by the different mmap_sems. When R is - * removed under R->mmap_sem, H replaces R as a tree node. Since we do not hold - * H->mmap_sem, we cannot use H->vm_flags for marking that H is a tree node now. - * That's why some trick involving shared.vm_set.parent is used for identifying - * tree nodes and list head nodes. - * - * vma radix priority search tree node rules: - * - * vma->shared.vm_set.parent != NULL ==> a tree node - * vma->shared.vm_set.head != NULL ==> list of others mapping same range - * vma->shared.vm_set.head == NULL ==> no others map the same range - * - * vma->shared.vm_set.parent == NULL - * vma->shared.vm_set.head != NULL ==> list head of vmas mapping same range - * vma->shared.vm_set.head == NULL ==> a list node - */ - -/* - * Add a new vma known to map the same set of pages as the old vma: - * useful for fork's dup_mmap as well as vma_prio_tree_insert below. - * Note that it just happens to work correctly on i_mmap_nonlinear too. - */ -void vma_prio_tree_add(struct vm_area_struct *vma, struct vm_area_struct *old) -{ - /* Leave these BUG_ONs till prio_tree patch stabilizes */ - BUG_ON(RADIX_INDEX(vma) != RADIX_INDEX(old)); - BUG_ON(HEAP_INDEX(vma) != HEAP_INDEX(old)); - - vma->shared.vm_set.head = NULL; - vma->shared.vm_set.parent = NULL; - - if (!old->shared.vm_set.parent) - list_add(&vma->shared.vm_set.list, - &old->shared.vm_set.list); - else if (old->shared.vm_set.head) - list_add_tail(&vma->shared.vm_set.list, - &old->shared.vm_set.head->shared.vm_set.list); - else { - INIT_LIST_HEAD(&vma->shared.vm_set.list); - vma->shared.vm_set.head = old; - old->shared.vm_set.head = vma; - } -} - -void vma_prio_tree_insert(struct vm_area_struct *vma, - struct prio_tree_root *root) -{ - struct prio_tree_node *ptr; - struct vm_area_struct *old; - - vma->shared.vm_set.head = NULL; - - ptr = raw_prio_tree_insert(root, &vma->shared.prio_tree_node); - if (ptr != (struct prio_tree_node *) &vma->shared.prio_tree_node) { - old = prio_tree_entry(ptr, struct vm_area_struct, - shared.prio_tree_node); - vma_prio_tree_add(vma, old); - } -} - -void vma_prio_tree_remove(struct vm_area_struct *vma, - struct prio_tree_root *root) -{ - struct vm_area_struct *node, *head, *new_head; - - if (!vma->shared.vm_set.head) { - if (!vma->shared.vm_set.parent) - list_del_init(&vma->shared.vm_set.list); - else - raw_prio_tree_remove(root, &vma->shared.prio_tree_node); - } else { - /* Leave this BUG_ON till prio_tree patch stabilizes */ - BUG_ON(vma->shared.vm_set.head->shared.vm_set.head != vma); - if (vma->shared.vm_set.parent) { - head = vma->shared.vm_set.head; - if (!list_empty(&head->shared.vm_set.list)) { - new_head = list_entry( - head->shared.vm_set.list.next, - struct vm_area_struct, - shared.vm_set.list); - list_del_init(&head->shared.vm_set.list); - } else - new_head = NULL; - - raw_prio_tree_replace(root, &vma->shared.prio_tree_node, - &head->shared.prio_tree_node); - head->shared.vm_set.head = new_head; - if (new_head) - new_head->shared.vm_set.head = head; - - } else { - node = vma->shared.vm_set.head; - if (!list_empty(&vma->shared.vm_set.list)) { - new_head = list_entry( - vma->shared.vm_set.list.next, - struct vm_area_struct, - shared.vm_set.list); - list_del_init(&vma->shared.vm_set.list); - node->shared.vm_set.head = new_head; - new_head->shared.vm_set.head = node; - } else - node->shared.vm_set.head = NULL; - } - } -} - -/* - * Helper function to enumerate vmas that map a given file page or a set of - * contiguous file pages. The function returns vmas that at least map a single - * page in the given range of contiguous file pages. - */ -struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma, - struct prio_tree_iter *iter) -{ - struct prio_tree_node *ptr; - struct vm_area_struct *next; - - if (!vma) { - /* - * First call is with NULL vma - */ - ptr = prio_tree_next(iter); - if (ptr) { - next = prio_tree_entry(ptr, struct vm_area_struct, - shared.prio_tree_node); - prefetch(next->shared.vm_set.head); - return next; - } else - return NULL; - } - - if (vma->shared.vm_set.parent) { - if (vma->shared.vm_set.head) { - next = vma->shared.vm_set.head; - prefetch(next->shared.vm_set.list.next); - return next; - } - } else { - next = list_entry(vma->shared.vm_set.list.next, - struct vm_area_struct, shared.vm_set.list); - if (!next->shared.vm_set.head) { - prefetch(next->shared.vm_set.list.next); - return next; - } - } - - ptr = prio_tree_next(iter); - if (ptr) { - next = prio_tree_entry(ptr, struct vm_area_struct, - shared.prio_tree_node); - prefetch(next->shared.vm_set.head); - return next; - } else - return NULL; -} diff --git a/mm/rmap.c b/mm/rmap.c index 0f3b7cda2a24..7b5b51d25fc5 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -820,7 +820,6 @@ static int page_referenced_file(struct page *page, struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; - struct prio_tree_iter iter; int referenced = 0; /* @@ -846,7 +845,7 @@ static int page_referenced_file(struct page *page, */ mapcount = page_mapcount(page); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; @@ -945,13 +944,12 @@ static int page_mkclean_file(struct address_space *mapping, struct page *page) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; - struct prio_tree_iter iter; int ret = 0; BUG_ON(PageAnon(page)); mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (vma->vm_flags & VM_SHARED) { unsigned long address = vma_address(page, vma); if (address == -EFAULT) @@ -1547,7 +1545,6 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; - struct prio_tree_iter iter; int ret = SWAP_AGAIN; unsigned long cursor; unsigned long max_nl_cursor = 0; @@ -1555,7 +1552,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) unsigned int mapcount; mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; @@ -1576,7 +1573,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) goto out; list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.vm_set.list) { + shared.nonlinear) { cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) max_nl_cursor = cursor; @@ -1608,7 +1605,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) do { list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.vm_set.list) { + shared.nonlinear) { cursor = (unsigned long) vma->vm_private_data; while ( cursor < max_nl_cursor && cursor < vma->vm_end - vma->vm_start) { @@ -1631,7 +1628,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) * in locked vmas). Reset cursor on all unreserved nonlinear * vmas, now forgetting on which ones it had fallen behind. */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) + list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) vma->vm_private_data = NULL; out: mutex_unlock(&mapping->i_mmap_mutex); @@ -1748,13 +1745,12 @@ static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *, struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; - struct prio_tree_iter iter; int ret = SWAP_AGAIN; if (!mapping) return ret; mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; -- cgit v1.3-14-g43fede From 91a27b2a756784714e924e5e854b919273082d26 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 10 Oct 2012 15:25:28 -0400 Subject: vfs: define struct filename and have getname() return it getname() is intended to copy pathname strings from userspace into a kernel buffer. The result is just a string in kernel space. It would however be quite helpful to be able to attach some ancillary info to the string. For instance, we could attach some audit-related info to reduce the amount of audit-related processing needed. When auditing is enabled, we could also call getname() on the string more than once and not need to recopy it from userspace. This patchset converts the getname()/putname() interfaces to return a struct instead of a string. For now, the struct just tracks the string in kernel space and the original userland pointer for it. Later, we'll add other information to the struct as it becomes convenient. Signed-off-by: Jeff Layton Signed-off-by: Al Viro --- arch/alpha/kernel/osf_sys.c | 16 ++--- arch/arm64/kernel/sys.c | 4 +- arch/arm64/kernel/sys_compat.c | 6 +- arch/avr32/kernel/process.c | 4 +- arch/blackfin/kernel/process.c | 4 +- arch/cris/arch-v10/kernel/process.c | 4 +- arch/cris/arch-v32/kernel/process.c | 4 +- arch/h8300/kernel/process.c | 4 +- arch/hexagon/kernel/syscall.c | 4 +- arch/ia64/kernel/process.c | 4 +- arch/m32r/kernel/process.c | 4 +- arch/microblaze/kernel/sys_microblaze.c | 4 +- arch/mips/kernel/linux32.c | 4 +- arch/mips/kernel/syscall.c | 4 +- arch/openrisc/kernel/process.c | 4 +- arch/parisc/hpux/fs.c | 4 +- arch/parisc/kernel/process.c | 4 +- arch/parisc/kernel/sys_parisc32.c | 4 +- arch/score/kernel/sys_score.c | 4 +- arch/sh/kernel/process_32.c | 4 +- arch/sh/kernel/process_64.c | 4 +- arch/sparc/kernel/process_32.c | 4 +- arch/sparc/kernel/process_64.c | 4 +- arch/sparc/kernel/sys_sparc32.c | 4 +- arch/tile/kernel/process.c | 8 +-- arch/unicore32/kernel/sys.c | 4 +- arch/xtensa/kernel/process.c | 4 +- fs/compat.c | 12 ++-- fs/exec.c | 13 ++-- fs/filesystems.c | 4 +- fs/namei.c | 108 ++++++++++++++++++++------------ fs/namespace.c | 4 +- fs/open.c | 4 +- fs/quota/quota.c | 4 +- include/linux/audit.h | 12 ++-- include/linux/fs.h | 14 ++++- ipc/mqueue.c | 13 ++-- kernel/acct.c | 4 +- kernel/auditsc.c | 64 ++++++++++--------- mm/swapfile.c | 11 ++-- 40 files changed, 218 insertions(+), 175 deletions(-) (limited to 'arch/parisc/kernel') diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 63e77e3944ce..9eb090582cf1 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -449,7 +449,7 @@ osf_ufs_mount(char *dirname, struct ufs_args __user *args, int flags) { int retval; struct cdfs_args tmp; - char *devname; + struct filename *devname; retval = -EFAULT; if (copy_from_user(&tmp, args, sizeof(tmp))) @@ -458,7 +458,7 @@ osf_ufs_mount(char *dirname, struct ufs_args __user *args, int flags) retval = PTR_ERR(devname); if (IS_ERR(devname)) goto out; - retval = do_mount(devname, dirname, "ext2", flags, NULL); + retval = do_mount(devname->name, dirname, "ext2", flags, NULL); putname(devname); out: return retval; @@ -469,7 +469,7 @@ osf_cdfs_mount(char *dirname, struct cdfs_args __user *args, int flags) { int retval; struct cdfs_args tmp; - char *devname; + struct filename *devname; retval = -EFAULT; if (copy_from_user(&tmp, args, sizeof(tmp))) @@ -478,7 +478,7 @@ osf_cdfs_mount(char *dirname, struct cdfs_args __user *args, int flags) retval = PTR_ERR(devname); if (IS_ERR(devname)) goto out; - retval = do_mount(devname, dirname, "iso9660", flags, NULL); + retval = do_mount(devname->name, dirname, "iso9660", flags, NULL); putname(devname); out: return retval; @@ -499,7 +499,7 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path, int, flag, void __user *, data) { int retval; - char *name; + struct filename *name; name = getname(path); retval = PTR_ERR(name); @@ -507,13 +507,13 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path, goto out; switch (typenr) { case 1: - retval = osf_ufs_mount(name, data, flag); + retval = osf_ufs_mount(name->name, data, flag); break; case 6: - retval = osf_cdfs_mount(name, data, flag); + retval = osf_cdfs_mount(name->name, data, flag); break; case 9: - retval = osf_procfs_mount(name, data, flag); + retval = osf_procfs_mount(name->name, data, flag); break; default: retval = -EINVAL; diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c index 905fcfb0ddd0..b120df37de35 100644 --- a/arch/arm64/kernel/sys.c +++ b/arch/arm64/kernel/sys.c @@ -50,13 +50,13 @@ asmlinkage long sys_execve(const char __user *filenamei, struct pt_regs *regs) { long error; - char * filename; + struct filename *filename; filename = getname(filenamei); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 93f10e27dc79..e521087cb0c4 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -56,14 +56,14 @@ asmlinkage int compat_sys_execve(const char __user *filenamei, struct pt_regs *regs) { int error; - char * filename; + struct filename *filename; filename = getname(filenamei); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, compat_ptr(argv), compat_ptr(envp), - regs); + error = compat_do_execve(filename->name, compat_ptr(argv), + compat_ptr(envp), regs); putname(filename); out: return error; diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 92c5af98a6f7..1bb0a8abd79b 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -388,14 +388,14 @@ asmlinkage int sys_execve(const char __user *ufilename, struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname(ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, uargv, uenvp, regs); + error = do_execve(filename->name, uargv, uenvp, regs); putname(filename); out: diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 62bcea7dcc6d..bb1cc721fcf7 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -213,14 +213,14 @@ asmlinkage int sys_execve(const char __user *name, const char __user *const __user *envp) { int error; - char *filename; + struct filename *filename; struct pt_regs *regs = (struct pt_regs *)((&name) + 6); filename = getname(name); error = PTR_ERR(filename); if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); return error; } diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index bee8df43c201..15ac7150371f 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -212,14 +212,14 @@ asmlinkage int sys_execve(const char *fname, struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname(fname); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index 0570e8ce603d..4e9992246359 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -224,7 +224,7 @@ sys_execve(const char *fname, struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname(fname); error = PTR_ERR(filename); @@ -232,7 +232,7 @@ sys_execve(const char *fname, if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index f153ed1a4c08..e8dc1393a13a 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -217,14 +217,14 @@ asmlinkage int sys_execve(const char *name, int dummy, ...) { int error; - char * filename; + struct filename *filename; struct pt_regs *regs = (struct pt_regs *) ((unsigned char *)&dummy-4); filename = getname(name); error = PTR_ERR(filename); if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); return error; } diff --git a/arch/hexagon/kernel/syscall.c b/arch/hexagon/kernel/syscall.c index 553cd60ee659..25a9bfe3445d 100644 --- a/arch/hexagon/kernel/syscall.c +++ b/arch/hexagon/kernel/syscall.c @@ -40,7 +40,7 @@ asmlinkage int sys_execve(char __user *ufilename, const char __user *const __user *envp) { struct pt_regs *pregs = current_thread_info()->regs; - char *filename; + struct filename *filename; int retval; filename = getname(ufilename); @@ -48,7 +48,7 @@ asmlinkage int sys_execve(char __user *ufilename, if (IS_ERR(filename)) return retval; - retval = do_execve(filename, argv, envp, pregs); + retval = do_execve(filename->name, argv, envp, pregs); putname(filename); return retval; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index ee31fe9b310e..35e106f2ed13 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -614,14 +614,14 @@ sys_execve (const char __user *filename, const char __user *const __user *envp, struct pt_regs *regs) { - char *fname; + struct filename *fname; int error; fname = getname(filename); error = PTR_ERR(fname); if (IS_ERR(fname)) goto out; - error = do_execve(fname, argv, envp, regs); + error = do_execve(fname->name, argv, envp, regs); putname(fname); out: return error; diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 384e63f3a4c4..e7366276ef30 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -296,14 +296,14 @@ asmlinkage int sys_execve(const char __user *ufilename, unsigned long r6, struct pt_regs regs) { int error; - char *filename; + struct filename *filename; filename = getname(ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, uargv, uenvp, ®s); + error = do_execve(filename->name, uargv, uenvp, ®s); putname(filename); out: return error; diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c index e5b154f24f85..404c0f24bd41 100644 --- a/arch/microblaze/kernel/sys_microblaze.c +++ b/arch/microblaze/kernel/sys_microblaze.c @@ -54,13 +54,13 @@ asmlinkage long microblaze_execve(const char __user *filenamei, struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname(filenamei); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 922a554cd108..3a21acedf882 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -83,13 +83,13 @@ out: asmlinkage int sys32_execve(nabi_no_regargs struct pt_regs regs) { int error; - char * filename; + struct filename *filename; filename = getname(compat_ptr(regs.regs[4])); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, compat_ptr(regs.regs[5]), + error = compat_do_execve(filename->name, compat_ptr(regs.regs[5]), compat_ptr(regs.regs[6]), ®s); putname(filename); diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index b08220c82113..2bd561bc05ae 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -133,13 +133,13 @@ _sys_clone(nabi_no_regargs struct pt_regs regs) asmlinkage int sys_execve(nabi_no_regargs struct pt_regs regs) { int error; - char * filename; + struct filename *filename; filename = getname((const char __user *) (long)regs.regs[4]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) (long)regs.regs[5], (const char __user *const __user *) (long)regs.regs[6], ®s); diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 55210f37d1a3..c35f3ab1a8d3 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -271,7 +271,7 @@ asmlinkage long _sys_execve(const char __user *name, struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname(name); error = PTR_ERR(filename); @@ -279,7 +279,7 @@ asmlinkage long _sys_execve(const char __user *name, if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index 6785de7bd2a0..a0760b87fd4e 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -34,14 +34,14 @@ int hpux_execve(struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname((const char __user *) regs->gr[26]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) regs->gr[25], (const char __user *const __user *) regs->gr[24], regs); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 8c6b6b6561f0..cbc37216bf90 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -342,13 +342,13 @@ unsigned long thread_saved_pc(struct task_struct *t) asmlinkage int sys_execve(struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname((const char __user *) regs->gr[26]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) regs->gr[25], (const char __user *const __user *) regs->gr[24], regs); diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index dc9a62462323..bf5b93a885d3 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -60,14 +60,14 @@ asmlinkage int sys32_execve(struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; DBG(("sys32_execve(%p) r26 = 0x%lx\n", regs, regs->gr[26])); filename = getname((const char __user *) regs->gr[26]); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, compat_ptr(regs->gr[25]), + error = compat_do_execve(filename->name, compat_ptr(regs->gr[25]), compat_ptr(regs->gr[24]), regs); putname(filename); out: diff --git a/arch/score/kernel/sys_score.c b/arch/score/kernel/sys_score.c index 21e867974066..d45cf00a3351 100644 --- a/arch/score/kernel/sys_score.c +++ b/arch/score/kernel/sys_score.c @@ -92,14 +92,14 @@ asmlinkage long score_execve(struct pt_regs *regs) { int error; - char *filename; + struct filename *filename; filename = getname((char __user*)regs->regs[4]); error = PTR_ERR(filename); if (IS_ERR(filename)) return error; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *)regs->regs[5], (const char __user *const __user *)regs->regs[6], regs); diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 59521e8a164d..ba7345f37bc9 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -298,14 +298,14 @@ asmlinkage int sys_execve(const char __user *ufilename, { struct pt_regs *regs = RELOC_HIDE(&__regs, 0); int error; - char *filename; + struct filename *filename; filename = getname(ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, uargv, uenvp, regs); + error = do_execve(filename->name, uargv, uenvp, regs); putname(filename); out: return error; diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index 602545b12a86..98a709f0c3c4 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -491,14 +491,14 @@ asmlinkage int sys_execve(const char *ufilename, char **uargv, struct pt_regs *pregs) { int error; - char *filename; + struct filename *filename; filename = getname((char __user *)ufilename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *)uargv, (const char __user *const __user *)uenvp, pregs); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index 14006d8aca28..487bffb36f5e 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -482,7 +482,7 @@ int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs) asmlinkage int sparc_execve(struct pt_regs *regs) { int error, base = 0; - char *filename; + struct filename *filename; /* Check for indirect call. */ if(regs->u_regs[UREG_G1] == 0) @@ -492,7 +492,7 @@ asmlinkage int sparc_execve(struct pt_regs *regs) error = PTR_ERR(filename); if(IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) regs->u_regs[base + UREG_I1], (const char __user *const __user *) diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index aff0c72fac09..fcaa59421126 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -722,7 +722,7 @@ EXPORT_SYMBOL(dump_fpu); asmlinkage int sparc_execve(struct pt_regs *regs) { int error, base = 0; - char *filename; + struct filename *filename; /* User register window flush is done by entry.S */ @@ -734,7 +734,7 @@ asmlinkage int sparc_execve(struct pt_regs *regs) error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, + error = do_execve(filename->name, (const char __user *const __user *) regs->u_regs[base + UREG_I1], (const char __user *const __user *) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index d862499eb01c..c3239811a1b5 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -403,7 +403,7 @@ asmlinkage long compat_sys_rt_sigaction(int sig, asmlinkage long sparc32_execve(struct pt_regs *regs) { int error, base = 0; - char *filename; + struct filename *filename; /* User register window flush is done by entry.S */ @@ -416,7 +416,7 @@ asmlinkage long sparc32_execve(struct pt_regs *regs) if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, + error = compat_do_execve(filename->name, compat_ptr(regs->u_regs[base + UREG_I1]), compat_ptr(regs->u_regs[base + UREG_I2]), regs); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 6be799150501..622560030a58 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -594,13 +594,13 @@ SYSCALL_DEFINE4(execve, const char __user *, path, struct pt_regs *, regs) { long error; - char *filename; + struct filename *filename; filename = getname(path); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); if (error == 0) single_step_execve(); @@ -615,13 +615,13 @@ long compat_sys_execve(const char __user *path, struct pt_regs *regs) { long error; - char *filename; + struct filename *filename; filename = getname(path); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = compat_do_execve(filename, argv, envp, regs); + error = compat_do_execve(filename->name, argv, envp, regs); putname(filename); if (error == 0) single_step_execve(); diff --git a/arch/unicore32/kernel/sys.c b/arch/unicore32/kernel/sys.c index 5fd9af773e15..fabdee96110b 100644 --- a/arch/unicore32/kernel/sys.c +++ b/arch/unicore32/kernel/sys.c @@ -51,13 +51,13 @@ asmlinkage long __sys_execve(const char __user *filename, struct pt_regs *regs) { int error; - char *fn; + struct filename *fn; fn = getname(filename); error = PTR_ERR(fn); if (IS_ERR(fn)) goto out; - error = do_execve(fn, argv, envp, regs); + error = do_execve(fn->name, argv, envp, regs); putname(fn); out: return error; diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index bc44311aa18c..bc020825cce5 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -328,13 +328,13 @@ long xtensa_execve(const char __user *name, struct pt_regs *regs) { long error; - char * filename; + struct filename *filename; filename = getname(name); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename->name, argv, envp, regs); putname(filename); out: return error; diff --git a/fs/compat.c b/fs/compat.c index b7a24d0ca30d..015e1e1f87c6 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -776,16 +776,16 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, char *kernel_type; unsigned long data_page; char *kernel_dev; - char *dir_page; + struct filename *dir; int retval; retval = copy_mount_string(type, &kernel_type); if (retval < 0) goto out; - dir_page = getname(dir_name); - retval = PTR_ERR(dir_page); - if (IS_ERR(dir_page)) + dir = getname(dir_name); + retval = PTR_ERR(dir); + if (IS_ERR(dir)) goto out1; retval = copy_mount_string(dev_name, &kernel_dev); @@ -807,7 +807,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, } } - retval = do_mount(kernel_dev, dir_page, kernel_type, + retval = do_mount(kernel_dev, dir->name, kernel_type, flags, (void*)data_page); out4: @@ -815,7 +815,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, out3: kfree(kernel_dev); out2: - putname(dir_page); + putname(dir); out1: kfree(kernel_type); out: diff --git a/fs/exec.c b/fs/exec.c index ca434534ae9a..4e591e20e108 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -105,7 +105,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt) SYSCALL_DEFINE1(uselib, const char __user *, library) { struct file *file; - char *tmp = getname(library); + struct filename *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, @@ -116,7 +116,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) if (IS_ERR(tmp)) goto out; - file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW); + file = do_filp_open(AT_FDCWD, tmp->name, &uselib_flags, LOOKUP_FOLLOW); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) @@ -1664,10 +1664,10 @@ SYSCALL_DEFINE3(execve, const char __user *const __user *, argv, const char __user *const __user *, envp) { - const char *path = getname(filename); + struct filename *path = getname(filename); int error = PTR_ERR(path); if (!IS_ERR(path)) { - error = do_execve(path, argv, envp, current_pt_regs()); + error = do_execve(path->name, argv, envp, current_pt_regs()); putname(path); } return error; @@ -1677,10 +1677,11 @@ asmlinkage long compat_sys_execve(const char __user * filename, const compat_uptr_t __user * argv, const compat_uptr_t __user * envp) { - const char *path = getname(filename); + struct filename *path = getname(filename); int error = PTR_ERR(path); if (!IS_ERR(path)) { - error = compat_do_execve(path, argv, envp, current_pt_regs()); + error = compat_do_execve(path->name, argv, envp, + current_pt_regs()); putname(path); } return error; diff --git a/fs/filesystems.c b/fs/filesystems.c index 96f24286667a..da165f6adcbf 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL(unregister_filesystem); static int fs_index(const char __user * __name) { struct file_system_type * tmp; - char * name; + struct filename *name; int err, index; name = getname(__name); @@ -135,7 +135,7 @@ static int fs_index(const char __user * __name) err = -EINVAL; read_lock(&file_systems_lock); for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) { - if (strcmp(tmp->name,name) == 0) { + if (strcmp(tmp->name, name->name) == 0) { err = index; break; } diff --git a/fs/namei.c b/fs/namei.c index 9cc0fce7fc91..ec638d27642f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -117,18 +117,37 @@ * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ -static char *getname_flags(const char __user *filename, int flags, int *empty) +void final_putname(struct filename *name) { - char *result = __getname(), *err; + __putname(name->name); + kfree(name); +} + +static struct filename * +getname_flags(const char __user *filename, int flags, int *empty) +{ + struct filename *result, *err; + char *kname; int len; + /* FIXME: create dedicated slabcache? */ + result = kzalloc(sizeof(*result), GFP_KERNEL); if (unlikely(!result)) return ERR_PTR(-ENOMEM); - len = strncpy_from_user(result, filename, PATH_MAX); - err = ERR_PTR(len); - if (unlikely(len < 0)) + kname = __getname(); + if (unlikely(!kname)) { + err = ERR_PTR(-ENOMEM); + goto error_free_name; + } + + result->name = kname; + result->uptr = filename; + len = strncpy_from_user(kname, filename, PATH_MAX); + if (unlikely(len < 0)) { + err = ERR_PTR(len); goto error; + } /* The empty path is special. */ if (unlikely(!len)) { @@ -146,22 +165,25 @@ static char *getname_flags(const char __user *filename, int flags, int *empty) } error: - __putname(result); + __putname(kname); +error_free_name: + kfree(result); return err; } -char *getname(const char __user * filename) +struct filename * +getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } +EXPORT_SYMBOL(getname); #ifdef CONFIG_AUDITSYSCALL -void putname(const char *name) +void putname(struct filename *name) { if (unlikely(!audit_dummy_context())) - audit_putname(name); - else - __putname(name); + return audit_putname(name); + final_putname(name); } #endif @@ -2093,13 +2115,13 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { struct nameidata nd; - char *tmp = getname_flags(name, flags, empty); + struct filename *tmp = getname_flags(name, flags, empty); int err = PTR_ERR(tmp); if (!IS_ERR(tmp)) { BUG_ON(flags & LOOKUP_PARENT); - err = do_path_lookup(dfd, tmp, flags, &nd); + err = do_path_lookup(dfd, tmp->name, flags, &nd); putname(tmp); if (!err) *path = nd.path; @@ -2113,22 +2135,22 @@ int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } -static int user_path_parent(int dfd, const char __user *path, - struct nameidata *nd, char **name) +static struct filename * +user_path_parent(int dfd, const char __user *path, struct nameidata *nd) { - char *s = getname(path); + struct filename *s = getname(path); int error; if (IS_ERR(s)) - return PTR_ERR(s); + return s; - error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd); - if (error) + error = do_path_lookup(dfd, s->name, LOOKUP_PARENT, nd); + if (error) { putname(s); - else - *name = s; + return ERR_PTR(error); + } - return error; + return s; } /* @@ -3039,11 +3061,11 @@ EXPORT_SYMBOL(done_path_create); struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir) { - char *tmp = getname(pathname); + struct filename *tmp = getname(pathname); struct dentry *res; if (IS_ERR(tmp)) return ERR_CAST(tmp); - res = kern_path_create(dfd, tmp, path, is_dir); + res = kern_path_create(dfd, tmp->name, path, is_dir); putname(tmp); return res; } @@ -3248,13 +3270,13 @@ out: static long do_rmdir(int dfd, const char __user *pathname) { int error = 0; - char * name; + struct filename *name; struct dentry *dentry; struct nameidata nd; - error = user_path_parent(dfd, pathname, &nd, &name); - if (error) - return error; + name = user_path_parent(dfd, pathname, &nd); + if (IS_ERR(name)) + return PTR_ERR(name); switch(nd.last_type) { case LAST_DOTDOT: @@ -3343,14 +3365,14 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) static long do_unlinkat(int dfd, const char __user *pathname) { int error; - char *name; + struct filename *name; struct dentry *dentry; struct nameidata nd; struct inode *inode = NULL; - error = user_path_parent(dfd, pathname, &nd, &name); - if (error) - return error; + name = user_path_parent(dfd, pathname, &nd); + if (IS_ERR(name)) + return PTR_ERR(name); error = -EISDIR; if (nd.last_type != LAST_NORM) @@ -3434,7 +3456,7 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { int error; - char *from; + struct filename *from; struct dentry *dentry; struct path path; @@ -3447,9 +3469,9 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, if (IS_ERR(dentry)) goto out_putname; - error = security_path_symlink(&path, dentry, from); + error = security_path_symlink(&path, dentry, from->name); if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, from); + error = vfs_symlink(path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); out_putname: putname(from); @@ -3729,17 +3751,21 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct nameidata oldnd, newnd; - char *from; - char *to; + struct filename *from; + struct filename *to; int error; - error = user_path_parent(olddfd, oldname, &oldnd, &from); - if (error) + from = user_path_parent(olddfd, oldname, &oldnd); + if (IS_ERR(from)) { + error = PTR_ERR(from); goto exit; + } - error = user_path_parent(newdfd, newname, &newnd, &to); - if (error) + to = user_path_parent(newdfd, newname, &newnd); + if (IS_ERR(to)) { + error = PTR_ERR(to); goto exit1; + } error = -EXDEV; if (oldnd.path.mnt != newnd.path.mnt) diff --git a/fs/namespace.c b/fs/namespace.c index fc33207e28ad..24960626bb6b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2408,7 +2408,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, { int ret; char *kernel_type; - char *kernel_dir; + struct filename *kernel_dir; char *kernel_dev; unsigned long data_page; @@ -2430,7 +2430,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, if (ret < 0) goto out_data; - ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags, + ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags, (void *) data_page); free_page(data_page); diff --git a/fs/open.c b/fs/open.c index a015437e1535..81dd92ac10ff 100644 --- a/fs/open.c +++ b/fs/open.c @@ -895,13 +895,13 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_flags op; int lookup = build_open_flags(flags, mode, &op); - char *tmp = getname(filename); + struct filename *tmp = getname(filename); int fd = PTR_ERR(tmp); if (!IS_ERR(tmp)) { fd = get_unused_fd_flags(flags); if (fd >= 0) { - struct file *f = do_filp_open(dfd, tmp, &op, lookup); + struct file *f = do_filp_open(dfd, tmp->name, &op, lookup); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index ff0135d6bc51..af1661f7a54f 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -331,11 +331,11 @@ static struct super_block *quotactl_block(const char __user *special, int cmd) #ifdef CONFIG_BLOCK struct block_device *bdev; struct super_block *sb; - char *tmp = getname(special); + struct filename *tmp = getname(special); if (IS_ERR(tmp)) return ERR_CAST(tmp); - bdev = lookup_bdev(tmp); + bdev = lookup_bdev(tmp->name); putname(tmp); if (IS_ERR(bdev)) return ERR_CAST(bdev); diff --git a/include/linux/audit.h b/include/linux/audit.h index 3df643d1ac5b..94d29164803f 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -460,6 +460,8 @@ extern int audit_classify_arch(int arch); #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ +struct filename; + #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ /* Public API */ @@ -469,8 +471,8 @@ extern void __audit_syscall_entry(int arch, int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); -extern void __audit_getname(const char *name); -extern void audit_putname(const char *name); +extern void __audit_getname(struct filename *name); +extern void audit_putname(struct filename *name); extern void __audit_inode(const char *name, const struct dentry *dentry, unsigned int parent); extern void __audit_inode_child(const struct inode *parent, @@ -505,7 +507,7 @@ static inline void audit_syscall_exit(void *pt_regs) __audit_syscall_exit(success, return_code); } } -static inline void audit_getname(const char *name) +static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); @@ -663,9 +665,9 @@ static inline int audit_dummy_context(void) { return 1; } -static inline void audit_getname(const char *name) +static inline void audit_getname(struct filename *name) { } -static inline void audit_putname(const char *name) +static inline void audit_putname(struct filename *name) { } static inline void __audit_inode(const char *name, const struct dentry *dentry, unsigned int parent) diff --git a/include/linux/fs.h b/include/linux/fs.h index b44b4ca82164..6c93b46f46dc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2196,6 +2196,10 @@ static inline int break_lease(struct inode *inode, unsigned int mode) #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ +struct filename { + const char *name; /* pointer to actual string */ + const __user char *uptr; /* original userland pointer */ +}; extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); @@ -2208,7 +2212,9 @@ extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); -extern char * getname(const char __user *); + +extern struct filename *getname(const char __user *); + enum { FILE_CREATED = 1, FILE_OPENED = 2 @@ -2228,12 +2234,14 @@ extern void __init vfs_caches_init(unsigned long); extern struct kmem_cache *names_cachep; +extern void final_putname(struct filename *name); + #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) #ifndef CONFIG_AUDITSYSCALL -#define putname(name) __putname(name) +#define putname(name) final_putname(name) #else -extern void putname(const char *name); +extern void putname(struct filename *name); #endif #ifdef CONFIG_BLOCK diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 9553ed006042..6c5d9dcc9030 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -772,7 +772,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, { struct path path; struct file *filp; - char *name; + struct filename *name; struct mq_attr attr; int fd, error; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; @@ -795,7 +795,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, ro = mnt_want_write(mnt); /* we'll drop it in any case */ error = 0; mutex_lock(&root->d_inode->i_mutex); - path.dentry = lookup_one_len(name, root, strlen(name)); + path.dentry = lookup_one_len(name->name, root, strlen(name->name)); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; @@ -804,7 +804,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, if (oflag & O_CREAT) { if (path.dentry->d_inode) { /* entry already exists */ - audit_inode(name, path.dentry, 0); + audit_inode(name->name, path.dentry, 0); if (oflag & O_EXCL) { error = -EEXIST; goto out; @@ -824,7 +824,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, error = -ENOENT; goto out; } - audit_inode(name, path.dentry, 0); + audit_inode(name->name, path.dentry, 0); filp = do_open(&path, oflag); } @@ -849,7 +849,7 @@ out_putname: SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) { int err; - char *name; + struct filename *name; struct dentry *dentry; struct inode *inode = NULL; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; @@ -863,7 +863,8 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) if (err) goto out_name; mutex_lock_nested(&mnt->mnt_root->d_inode->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name, mnt->mnt_root, strlen(name)); + dentry = lookup_one_len(name->name, mnt->mnt_root, + strlen(name->name)); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_unlock; diff --git a/kernel/acct.c b/kernel/acct.c index 5be01017d30f..08354195eecc 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -260,10 +260,10 @@ SYSCALL_DEFINE1(acct, const char __user *, name) return -EPERM; if (name) { - char *tmp = getname(name); + struct filename *tmp = getname(name); if (IS_ERR(tmp)) return (PTR_ERR(tmp)); - error = acct_on(tmp); + error = acct_on(tmp->name); putname(tmp); } else { struct bsd_acct_struct *acct; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d147585e9ef3..d4d82319eed5 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -103,28 +103,29 @@ struct audit_cap_data { * we don't let putname() free it (instead we free all of the saved * pointers at syscall exit time). * - * Further, in fs/namei.c:path_lookup() we store the inode and device. */ + * Further, in fs/namei.c:path_lookup() we store the inode and device. + */ struct audit_names { - struct list_head list; /* audit_context->names_list */ - const char *name; - unsigned long ino; - dev_t dev; - umode_t mode; - kuid_t uid; - kgid_t gid; - dev_t rdev; - u32 osid; - struct audit_cap_data fcap; - unsigned int fcap_ver; - int name_len; /* number of name's characters to log */ - unsigned char type; /* record type */ - bool name_put; /* call __putname() for this name */ + struct list_head list; /* audit_context->names_list */ + struct filename *name; + unsigned long ino; + dev_t dev; + umode_t mode; + kuid_t uid; + kgid_t gid; + dev_t rdev; + u32 osid; + struct audit_cap_data fcap; + unsigned int fcap_ver; + int name_len; /* number of name's characters to log */ + unsigned char type; /* record type */ + bool name_put; /* call __putname() for this name */ /* * This was an allocated audit_names and not from the array of * names allocated in the task audit context. Thus this name * should be freed on syscall exit */ - bool should_free; + bool should_free; }; struct audit_aux_data { @@ -996,7 +997,7 @@ static inline void audit_free_names(struct audit_context *context) context->ino_count); list_for_each_entry(n, &context->names_list, list) { printk(KERN_ERR "names[%d] = %p = %s\n", i, - n->name, n->name ?: "(null)"); + n->name, n->name->name ?: "(null)"); } dump_stack(); return; @@ -1553,7 +1554,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, case AUDIT_NAME_FULL: /* log the full path */ audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, n->name); + audit_log_untrustedstring(ab, n->name->name); break; case 0: /* name was specified as a relative path and the @@ -1563,7 +1564,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, default: /* log the name's directory component */ audit_log_format(ab, " name="); - audit_log_n_untrustedstring(ab, n->name, + audit_log_n_untrustedstring(ab, n->name->name, n->name_len); } } else @@ -2026,7 +2027,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context, * Add a name to the list of audit names for this context. * Called from fs/namei.c:getname(). */ -void __audit_getname(const char *name) +void __audit_getname(struct filename *name) { struct audit_context *context = current->audit_context; struct audit_names *n; @@ -2040,6 +2041,11 @@ void __audit_getname(const char *name) return; } +#if AUDIT_DEBUG + /* The filename _must_ have a populated ->name */ + BUG_ON(!name->name); +#endif + n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); if (!n) return; @@ -2059,7 +2065,7 @@ void __audit_getname(const char *name) * then we delay the putname until syscall exit. * Called from include/linux/fs.h:putname(). */ -void audit_putname(const char *name) +void audit_putname(struct filename *name) { struct audit_context *context = current->audit_context; @@ -2074,7 +2080,7 @@ void audit_putname(const char *name) list_for_each_entry(n, &context->names_list, list) printk(KERN_ERR "name[%d] = %p = %s\n", i, - n->name, n->name ?: "(null)"); + n->name, n->name->name ?: "(null)"); } #endif __putname(name); @@ -2088,8 +2094,8 @@ void audit_putname(const char *name) " put_count=%d\n", __FILE__, __LINE__, context->serial, context->major, - context->in_syscall, name, context->name_count, - context->put_count); + context->in_syscall, name->name, + context->name_count, context->put_count); dump_stack(); } } @@ -2152,7 +2158,7 @@ void __audit_inode(const char *name, const struct dentry *dentry, list_for_each_entry_reverse(n, &context->names_list, list) { /* does the name pointer match? */ - if (n->name != name) + if (!n->name || n->name->name != name) continue; /* match the correct record type */ @@ -2175,7 +2181,7 @@ out_alloc: return; out: if (parent) { - n->name_len = n->name ? parent_len(n->name) : AUDIT_NAME_FULL; + n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL; n->type = AUDIT_TYPE_PARENT; } else { n->name_len = AUDIT_NAME_FULL; @@ -2220,7 +2226,7 @@ void __audit_inode_child(const struct inode *parent, continue; if (n->ino == parent->i_ino && - !audit_compare_dname_path(dname, n->name, n->name_len)) { + !audit_compare_dname_path(dname, n->name->name, n->name_len)) { found_parent = n; break; } @@ -2236,8 +2242,8 @@ void __audit_inode_child(const struct inode *parent, if (found_parent && (n->name != found_parent->name)) continue; - if (!strcmp(dname, n->name) || - !audit_compare_dname_path(dname, n->name, + if (!strcmp(dname, n->name->name) || + !audit_compare_dname_path(dname, n->name->name, found_parent ? found_parent->name_len : AUDIT_NAME_FULL)) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 14e254c768fc..90d2ed591de9 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1483,7 +1483,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; - char *pathname; + struct filename *pathname; int oom_score_adj; int i, type, prev; int err; @@ -1498,8 +1498,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (IS_ERR(pathname)) goto out; - victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0); - putname(pathname); + victim = filp_open(pathname->name, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; @@ -1936,7 +1935,7 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; - char *name; + struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; int i; @@ -1967,7 +1966,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) name = NULL; goto bad_swap; } - swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0); + swap_file = filp_open(name->name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; @@ -2053,7 +2052,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) printk(KERN_INFO "Adding %uk swap on %s. " "Priority:%d extents:%d across:%lluk %s%s%s\n", - p->pages<<(PAGE_SHIFT-10), name, p->prio, + p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", -- cgit v1.3-14-g43fede