From 51cc50685a4275c6a02653670af9f108a64e01cf Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 25 Jul 2008 19:45:34 -0700 Subject: SL*B: drop kmem cache argument from constructor Kmem cache passed to constructor is only needed for constructors that are themselves multiplexeres. Nobody uses this "feature", nor does anybody uses passed kmem cache in non-trivial way, so pass only pointer to object. Non-trivial places are: arch/powerpc/mm/init_64.c arch/powerpc/mm/hugetlbpage.c This is flag day, yes. Signed-off-by: Alexey Dobriyan Acked-by: Pekka Enberg Acked-by: Christoph Lameter Cc: Jon Tollefson Cc: Nick Piggin Cc: Matt Mackall [akpm@linux-foundation.org: fix arch/powerpc/mm/hugetlbpage.c] [akpm@linux-foundation.org: fix mm/slab.c] [akpm@linux-foundation.org: fix ubifs] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index b99d73e971a4..80e83e459b17 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1442,7 +1442,7 @@ long do_fork(unsigned long clone_flags, #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif -static void sighand_ctor(struct kmem_cache *cachep, void *data) +static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; -- cgit v1.2.3 From 09a05394fe2448a4139b014936330af23fa7ec83 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: clone This moves all the ptrace initialization and tracing logic for task creation into tracehook.h and ptrace.h inlines. It reorganizes the code slightly, but should not change any behavior. There are four tracehook entry points, at each important stage of task creation. This keeps the interface from the core fork.c code fairly clean, while supporting the complex setup required for ptrace or something like it. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 22 ++++++++++ include/linux/tracehook.h | 100 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 69 +++++++++++++------------------- 3 files changed, 150 insertions(+), 41 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index c74abfc4c7e8..dae6d85520fb 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -154,6 +154,28 @@ static inline int ptrace_event(int mask, int event, unsigned long message) return 1; } +/** + * ptrace_init_task - initialize ptrace state for a new child + * @child: new child task + * @ptrace: true if child should be ptrace'd by parent's tracer + * + * This is called immediately after adding @child to its parent's children + * list. @ptrace is false in the normal case, and true to ptrace @child. + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void ptrace_init_task(struct task_struct *child, bool ptrace) +{ + INIT_LIST_HEAD(&child->ptrace_entry); + INIT_LIST_HEAD(&child->ptraced); + child->parent = child->real_parent; + child->ptrace = 0; + if (unlikely(ptrace)) { + child->ptrace = current->ptrace; + __ptrace_link(child, current->parent); + } +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 967ab473afbc..3ebc58b59766 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -110,4 +110,104 @@ static inline void tracehook_report_exit(long *exit_code) ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); } +/** + * tracehook_prepare_clone - prepare for new child to be cloned + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * + * This is called before a new user task is to be cloned. + * Its return value will be passed to tracehook_finish_clone(). + * + * Called with no locks held. + */ +static inline int tracehook_prepare_clone(unsigned clone_flags) +{ + if (clone_flags & CLONE_UNTRACED) + return 0; + + if (clone_flags & CLONE_VFORK) { + if (current->ptrace & PT_TRACE_VFORK) + return PTRACE_EVENT_VFORK; + } else if ((clone_flags & CSIGNAL) != SIGCHLD) { + if (current->ptrace & PT_TRACE_CLONE) + return PTRACE_EVENT_CLONE; + } else if (current->ptrace & PT_TRACE_FORK) + return PTRACE_EVENT_FORK; + + return 0; +} + +/** + * tracehook_finish_clone - new child created and being attached + * @child: new child task + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * @trace: return value from tracehook_clone_prepare() + * + * This is called immediately after adding @child to its parent's children list. + * The @trace value is that returned by tracehook_prepare_clone(). + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void tracehook_finish_clone(struct task_struct *child, + unsigned long clone_flags, int trace) +{ + ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace); +} + +/** + * tracehook_report_clone - in parent, new child is about to start running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: new child task + * + * Called after a child is set up, but before it has been started running. + * The @trace value is that returned by tracehook_clone_prepare(). + * This is not a good place to block, because the child has not started yet. + * Suspend the child here if desired, and block in tracehook_clone_complete(). + * This must prevent the child from self-reaping if tracehook_clone_complete() + * uses the @child pointer; otherwise it might have died and been released by + * the time tracehook_report_clone_complete() is called. + * + * Called with no locks held, but the child cannot run until this returns. + */ +static inline void tracehook_report_clone(int trace, struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, struct task_struct *child) +{ + if (unlikely(trace)) { + /* + * The child starts up with an immediate SIGSTOP. + */ + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); + } +} + +/** + * tracehook_report_clone_complete - new child is running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: child task, already running + * + * This is called just after the child has started running. This is + * just before the clone/fork syscall returns, or blocks for vfork + * child completion if @clone_flags has the %CLONE_VFORK bit set. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_clone_complete(int trace, + struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, + struct task_struct *child) +{ + if (unlikely(trace)) + ptrace_event(0, trace, pid); +} + #endif /* */ diff --git a/kernel/fork.c b/kernel/fork.c index 80e83e459b17..b42f8ed23611 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -865,8 +866,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) new_flags &= ~PF_SUPERPRIV; new_flags |= PF_FORKNOEXEC; - if (!(clone_flags & CLONE_PTRACE)) - p->ptrace = 0; + new_flags |= PF_STARTING; p->flags = new_flags; clear_freeze_flag(p); } @@ -907,7 +907,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, struct pt_regs *regs, unsigned long stack_size, int __user *child_tidptr, - struct pid *pid) + struct pid *pid, + int trace) { int retval; struct task_struct *p; @@ -1163,8 +1164,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); - INIT_LIST_HEAD(&p->ptrace_entry); - INIT_LIST_HEAD(&p->ptraced); /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible @@ -1195,7 +1194,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_parent = current->real_parent; else p->real_parent = current; - p->parent = p->real_parent; spin_lock(¤t->sighand->siglock); @@ -1237,8 +1235,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (likely(p->pid)) { list_add_tail(&p->sibling, &p->real_parent->children); - if (unlikely(p->ptrace & PT_PTRACED)) - __ptrace_link(p, current->parent); + tracehook_finish_clone(p, clone_flags, trace); if (thread_group_leader(p)) { if (clone_flags & CLONE_NEWPID) @@ -1323,29 +1320,13 @@ struct task_struct * __cpuinit fork_idle(int cpu) struct pt_regs regs; task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, - &init_struct_pid); + &init_struct_pid, 0); if (!IS_ERR(task)) init_idle(task, cpu); return task; } -static int fork_traceflag(unsigned clone_flags) -{ - if (clone_flags & CLONE_UNTRACED) - return 0; - else if (clone_flags & CLONE_VFORK) { - if (current->ptrace & PT_TRACE_VFORK) - return PTRACE_EVENT_VFORK; - } else if ((clone_flags & CSIGNAL) != SIGCHLD) { - if (current->ptrace & PT_TRACE_CLONE) - return PTRACE_EVENT_CLONE; - } else if (current->ptrace & PT_TRACE_FORK) - return PTRACE_EVENT_FORK; - - return 0; -} - /* * Ok, this is the main fork-routine. * @@ -1380,14 +1361,14 @@ long do_fork(unsigned long clone_flags, } } - if (unlikely(current->ptrace)) { - trace = fork_traceflag (clone_flags); - if (trace) - clone_flags |= CLONE_PTRACE; - } + /* + * When called from kernel_thread, don't do user tracing stuff. + */ + if (likely(user_mode(regs))) + trace = tracehook_prepare_clone(clone_flags); p = copy_process(clone_flags, stack_start, regs, stack_size, - child_tidptr, NULL); + child_tidptr, NULL, trace); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. @@ -1405,24 +1386,30 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) { + tracehook_report_clone(trace, regs, clone_flags, nr, p); + + /* + * We set PF_STARTING at creation in case tracing wants to + * use this to distinguish a fully live task from one that + * hasn't gotten to tracehook_report_clone() yet. Now we + * clear it and set the child going. + */ + p->flags &= ~PF_STARTING; + + if (unlikely(clone_flags & CLONE_STOPPED)) { /* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); - } - - if (!(clone_flags & CLONE_STOPPED)) - wake_up_new_task(p, clone_flags); - else __set_task_state(p, TASK_STOPPED); - - if (unlikely (trace)) { - current->ptrace_message = nr; - ptrace_notify ((trace << 8) | SIGTRAP); + } else { + wake_up_new_task(p, clone_flags); } + tracehook_report_clone_complete(trace, regs, + clone_flags, nr, p); + if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); wait_for_completion(&vfork); -- cgit v1.2.3 From daded34be96b1975ff8539ff62ad8b158ce7d842 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: vfork-done This moves the PTRACE_EVENT_VFORK_DONE tracing into a tracehook.h inline, tracehook_report_vfork_done(). The change has no effect, just clean-up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 18 ++++++++++++++++++ kernel/fork.c | 5 +---- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3ebc58b59766..830e6e16097d 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -210,4 +210,22 @@ static inline void tracehook_report_clone_complete(int trace, ptrace_event(0, trace, pid); } +/** + * tracehook_report_vfork_done - vfork parent's child has exited or exec'd + * @child: child task, already running + * @pid: new child's PID in the parent's namespace + * + * Called after a %CLONE_VFORK parent has waited for the child to complete. + * The clone/vfork system call will return immediately after this. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_vfork_done(struct task_struct *child, + pid_t pid) +{ + ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); +} + #endif /* */ diff --git a/kernel/fork.c b/kernel/fork.c index b42f8ed23611..abb3ed6298f6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1414,10 +1414,7 @@ long do_fork(unsigned long clone_flags, freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); - if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) { - current->ptrace_message = nr; - ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); - } + tracehook_report_vfork_done(p, nr); } } else { nr = PTR_ERR(p); -- cgit v1.2.3 From 7f2da1e7d0330395e5e9e350b879b98a1ea495df Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 10 May 2008 20:44:54 -0400 Subject: [PATCH] kill altroot long overdue... Signed-off-by: Al Viro --- fs/namei.c | 89 +------------------------------------------ fs/namespace.c | 8 +--- fs/open.c | 3 +- include/asm-alpha/namei.h | 17 --------- include/asm-arm/namei.h | 25 ------------ include/asm-avr32/namei.h | 7 ---- include/asm-blackfin/namei.h | 19 --------- include/asm-cris/namei.h | 17 --------- include/asm-frv/namei.h | 18 --------- include/asm-h8300/namei.h | 17 --------- include/asm-ia64/namei.h | 25 ------------ include/asm-m32r/namei.h | 17 --------- include/asm-m68k/namei.h | 17 --------- include/asm-m68knommu/namei.h | 1 - include/asm-mips/namei.h | 11 ------ include/asm-mn10300/namei.h | 22 ----------- include/asm-parisc/namei.h | 17 --------- include/asm-powerpc/namei.h | 20 ---------- include/asm-s390/namei.h | 21 ---------- include/asm-sh/namei.h | 17 --------- include/asm-sparc/namei.h | 8 ---- include/asm-sparc64/namei.h | 1 - include/asm-um/namei.h | 6 --- include/asm-v850/namei.h | 17 --------- include/asm-x86/namei.h | 11 ------ include/asm-xtensa/namei.h | 26 ------------- include/linux/fs_struct.h | 3 +- include/linux/namei.h | 1 - kernel/exec_domain.c | 1 - kernel/exit.c | 2 - kernel/fork.c | 7 ---- 31 files changed, 5 insertions(+), 466 deletions(-) delete mode 100644 include/asm-alpha/namei.h delete mode 100644 include/asm-arm/namei.h delete mode 100644 include/asm-avr32/namei.h delete mode 100644 include/asm-blackfin/namei.h delete mode 100644 include/asm-cris/namei.h delete mode 100644 include/asm-frv/namei.h delete mode 100644 include/asm-h8300/namei.h delete mode 100644 include/asm-ia64/namei.h delete mode 100644 include/asm-m32r/namei.h delete mode 100644 include/asm-m68k/namei.h delete mode 100644 include/asm-m68knommu/namei.h delete mode 100644 include/asm-mips/namei.h delete mode 100644 include/asm-mn10300/namei.h delete mode 100644 include/asm-parisc/namei.h delete mode 100644 include/asm-powerpc/namei.h delete mode 100644 include/asm-s390/namei.h delete mode 100644 include/asm-sh/namei.h delete mode 100644 include/asm-sparc/namei.h delete mode 100644 include/asm-sparc64/namei.h delete mode 100644 include/asm-um/namei.h delete mode 100644 include/asm-v850/namei.h delete mode 100644 include/asm-x86/namei.h delete mode 100644 include/asm-xtensa/namei.h (limited to 'kernel/fork.c') diff --git a/fs/namei.c b/fs/namei.c index 6c76e1ee9c45..095818089ac1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE]) @@ -562,27 +561,16 @@ out_unlock: return result; } -static int __emul_lookup_dentry(const char *, struct nameidata *); - /* SMP-safe */ -static __always_inline int +static __always_inline void walk_init_root(const char *name, struct nameidata *nd) { struct fs_struct *fs = current->fs; read_lock(&fs->lock); - if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) { - nd->path = fs->altroot; - path_get(&fs->altroot); - read_unlock(&fs->lock); - if (__emul_lookup_dentry(name,nd)) - return 0; - read_lock(&fs->lock); - } nd->path = fs->root; path_get(&fs->root); read_unlock(&fs->lock); - return 1; } /* @@ -623,12 +611,9 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l if (*link == '/') { path_put(&nd->path); - if (!walk_init_root(link, nd)) - /* weird __emul_prefix() stuff did it */ - goto out; + walk_init_root(link, nd); } res = link_path_walk(link, nd); -out: if (nd->depth || res || nd->last_type!=LAST_NORM) return res; /* @@ -1077,67 +1062,6 @@ static int path_walk(const char *name, struct nameidata *nd) return link_path_walk(name, nd); } -/* - * SMP-safe: Returns 1 and nd will have valid dentry and mnt, if - * everything is done. Returns 0 and drops input nd, if lookup failed; - */ -static int __emul_lookup_dentry(const char *name, struct nameidata *nd) -{ - if (path_walk(name, nd)) - return 0; /* something went wrong... */ - - if (!nd->path.dentry->d_inode || - S_ISDIR(nd->path.dentry->d_inode->i_mode)) { - struct path old_path = nd->path; - struct qstr last = nd->last; - int last_type = nd->last_type; - struct fs_struct *fs = current->fs; - - /* - * NAME was not found in alternate root or it's a directory. - * Try to find it in the normal root: - */ - nd->last_type = LAST_ROOT; - read_lock(&fs->lock); - nd->path = fs->root; - path_get(&fs->root); - read_unlock(&fs->lock); - if (path_walk(name, nd) == 0) { - if (nd->path.dentry->d_inode) { - path_put(&old_path); - return 1; - } - path_put(&nd->path); - } - nd->path = old_path; - nd->last = last; - nd->last_type = last_type; - } - return 1; -} - -void set_fs_altroot(void) -{ - char *emul = __emul_prefix(); - struct nameidata nd; - struct path path = {}, old_path; - int err; - struct fs_struct *fs = current->fs; - - if (!emul) - goto set_it; - err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd); - if (!err) - path = nd.path; -set_it: - write_lock(&fs->lock); - old_path = fs->altroot; - fs->altroot = path; - write_unlock(&fs->lock); - if (old_path.dentry) - path_put(&old_path); -} - /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int do_path_lookup(int dfd, const char *name, unsigned int flags, struct nameidata *nd) @@ -1153,14 +1077,6 @@ static int do_path_lookup(int dfd, const char *name, if (*name=='/') { read_lock(&fs->lock); - if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) { - nd->path = fs->altroot; - path_get(&fs->altroot); - read_unlock(&fs->lock); - if (__emul_lookup_dentry(name,nd)) - goto out; /* found in altroot */ - read_lock(&fs->lock); - } nd->path = fs->root; path_get(&fs->root); read_unlock(&fs->lock); @@ -1194,7 +1110,6 @@ static int do_path_lookup(int dfd, const char *name, } retval = path_walk(name, nd); -out: if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && nd->path.dentry->d_inode)) audit_inode(name, nd->path.dentry); diff --git a/fs/namespace.c b/fs/namespace.c index f30b11e2240e..c4fcf48acef8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1972,7 +1972,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, struct fs_struct *fs) { struct mnt_namespace *new_ns; - struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL; + struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct vfsmount *p, *q; new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL); @@ -2015,10 +2015,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, pwdmnt = p; fs->pwd.mnt = mntget(q); } - if (p == fs->altroot.mnt) { - altrootmnt = p; - fs->altroot.mnt = mntget(q); - } } p = next_mnt(p, mnt_ns->root); q = next_mnt(q, new_ns->root); @@ -2029,8 +2025,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); - if (altrootmnt) - mntput(altrootmnt); return new_ns; } diff --git a/fs/open.c b/fs/open.c index 8e02d42bfe44..d3a2a00f52dc 100644 --- a/fs/open.c +++ b/fs/open.c @@ -548,7 +548,7 @@ asmlinkage long sys_chroot(const char __user * filename) struct nameidata nd; int error; - error = __user_walk(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY | LOOKUP_NOALT, &nd); + error = __user_walk(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &nd); if (error) goto out; @@ -561,7 +561,6 @@ asmlinkage long sys_chroot(const char __user * filename) goto dput_and_out; set_fs_root(current->fs, &nd.path); - set_fs_altroot(); error = 0; dput_and_out: path_put(&nd.path); diff --git a/include/asm-alpha/namei.h b/include/asm-alpha/namei.h deleted file mode 100644 index 5cc9bb39499d..000000000000 --- a/include/asm-alpha/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $ - * linux/include/asm-alpha/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __ALPHA_NAMEI_H -#define __ALPHA_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __ALPHA_NAMEI_H */ diff --git a/include/asm-arm/namei.h b/include/asm-arm/namei.h deleted file mode 100644 index a402d3b9d0f7..000000000000 --- a/include/asm-arm/namei.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * linux/include/asm-arm/namei.h - * - * Routines to handle famous /usr/gnemul - * Derived from the Sparc version of this file - * - * Included from linux/fs/namei.c - */ - -#ifndef __ASMARM_NAMEI_H -#define __ASMARM_NAMEI_H - -#define ARM_BSD_EMUL "usr/gnemul/bsd/" - -static inline char *__emul_prefix(void) -{ - switch (current->personality) { - case PER_BSD: - return ARM_BSD_EMUL; - default: - return NULL; - } -} - -#endif /* __ASMARM_NAMEI_H */ diff --git a/include/asm-avr32/namei.h b/include/asm-avr32/namei.h deleted file mode 100644 index f0a26de06cab..000000000000 --- a/include/asm-avr32/namei.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef __ASM_AVR32_NAMEI_H -#define __ASM_AVR32_NAMEI_H - -/* This dummy routine may be changed to something useful */ -#define __emul_prefix() NULL - -#endif /* __ASM_AVR32_NAMEI_H */ diff --git a/include/asm-blackfin/namei.h b/include/asm-blackfin/namei.h deleted file mode 100644 index 8b89a2d65cb4..000000000000 --- a/include/asm-blackfin/namei.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * linux/include/asm/namei.h - * - * Included from linux/fs/namei.c - * - * Changes made by Lineo Inc. May 2001 - */ - -#ifndef __BFIN_NAMEI_H -#define __BFIN_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif diff --git a/include/asm-cris/namei.h b/include/asm-cris/namei.h deleted file mode 100644 index 8a3be7a6d9f6..000000000000 --- a/include/asm-cris/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.1 2000/07/10 16:32:31 bjornw Exp $ - * linux/include/asm-cris/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __CRIS_NAMEI_H -#define __CRIS_NAMEI_H - -/* used to find file-system prefixes for doing emulations - * see for example asm-sparc/namei.h - * we don't use it... - */ - -#define __emul_prefix() NULL - -#endif /* __CRIS_NAMEI_H */ diff --git a/include/asm-frv/namei.h b/include/asm-frv/namei.h deleted file mode 100644 index 4ea57171d951..000000000000 --- a/include/asm-frv/namei.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-frv/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __ASM_NAMEI_H -#define __ASM_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif - diff --git a/include/asm-h8300/namei.h b/include/asm-h8300/namei.h deleted file mode 100644 index ab6f196db6e0..000000000000 --- a/include/asm-h8300/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * linux/include/asm-h8300/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __H8300_NAMEI_H -#define __H8300_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif diff --git a/include/asm-ia64/namei.h b/include/asm-ia64/namei.h deleted file mode 100644 index 78e768079083..000000000000 --- a/include/asm-ia64/namei.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _ASM_IA64_NAMEI_H -#define _ASM_IA64_NAMEI_H - -/* - * Modified 1998, 1999, 2001 - * David Mosberger-Tang , Hewlett-Packard Co - */ - -#include -#include - -#define EMUL_PREFIX_LINUX_IA32 "/emul/ia32-linux/" - -static inline char * -__emul_prefix (void) -{ - switch (current->personality) { - case PER_LINUX32: - return EMUL_PREFIX_LINUX_IA32; - default: - return NULL; - } -} - -#endif /* _ASM_IA64_NAMEI_H */ diff --git a/include/asm-m32r/namei.h b/include/asm-m32r/namei.h deleted file mode 100644 index 210f8056b805..000000000000 --- a/include/asm-m32r/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _ASM_M32R_NAMEI_H -#define _ASM_M32R_NAMEI_H - -/* - * linux/include/asm-m32r/namei.h - * - * Included from linux/fs/namei.c - */ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_M32R_NAMEI_H */ diff --git a/include/asm-m68k/namei.h b/include/asm-m68k/namei.h deleted file mode 100644 index f33f243b644a..000000000000 --- a/include/asm-m68k/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * linux/include/asm-m68k/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __M68K_NAMEI_H -#define __M68K_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif diff --git a/include/asm-m68knommu/namei.h b/include/asm-m68knommu/namei.h deleted file mode 100644 index 31a85d27b931..000000000000 --- a/include/asm-m68knommu/namei.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-mips/namei.h b/include/asm-mips/namei.h deleted file mode 100644 index a6605a752469..000000000000 --- a/include/asm-mips/namei.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_NAMEI_H -#define _ASM_NAMEI_H - -/* - * This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_NAMEI_H */ diff --git a/include/asm-mn10300/namei.h b/include/asm-mn10300/namei.h deleted file mode 100644 index bd9ce94aeb65..000000000000 --- a/include/asm-mn10300/namei.h +++ /dev/null @@ -1,22 +0,0 @@ -/* Emulation stuff - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#ifndef _ASM_NAMEI_H -#define _ASM_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_NAMEI_H */ diff --git a/include/asm-parisc/namei.h b/include/asm-parisc/namei.h deleted file mode 100644 index 8d29b3d9fb33..000000000000 --- a/include/asm-parisc/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $ - * linux/include/asm-parisc/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __PARISC_NAMEI_H -#define __PARISC_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __PARISC_NAMEI_H */ diff --git a/include/asm-powerpc/namei.h b/include/asm-powerpc/namei.h deleted file mode 100644 index 657443474a6a..000000000000 --- a/include/asm-powerpc/namei.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _ASM_POWERPC_NAMEI_H -#define _ASM_POWERPC_NAMEI_H - -#ifdef __KERNEL__ - -/* - * Adapted from include/asm-alpha/namei.h - * - * Included from fs/namei.c - */ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NAMEI_H */ diff --git a/include/asm-s390/namei.h b/include/asm-s390/namei.h deleted file mode 100644 index 3e286bdde4b0..000000000000 --- a/include/asm-s390/namei.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * include/asm-s390/namei.h - * - * S390 version - * - * Derived from "include/asm-i386/namei.h" - * - * Included from linux/fs/namei.c - */ - -#ifndef __S390_NAMEI_H -#define __S390_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __S390_NAMEI_H */ diff --git a/include/asm-sh/namei.h b/include/asm-sh/namei.h deleted file mode 100644 index 338a5d947143..000000000000 --- a/include/asm-sh/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.3 2000/07/04 06:24:49 gniibe Exp $ - * linux/include/asm-sh/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __ASM_SH_NAMEI_H -#define __ASM_SH_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __ASM_SH_NAMEI_H */ diff --git a/include/asm-sparc/namei.h b/include/asm-sparc/namei.h deleted file mode 100644 index eff944b8e321..000000000000 --- a/include/asm-sparc/namei.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef ___ASM_SPARC_NAMEI_H -#define ___ASM_SPARC_NAMEI_H -#if defined(__sparc__) && defined(__arch64__) -#include -#else -#include -#endif -#endif diff --git a/include/asm-sparc64/namei.h b/include/asm-sparc64/namei.h deleted file mode 100644 index 1344a910ba2f..000000000000 --- a/include/asm-sparc64/namei.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-um/namei.h b/include/asm-um/namei.h deleted file mode 100644 index 002984d5bc85..000000000000 --- a/include/asm-um/namei.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __UM_NAMEI_H -#define __UM_NAMEI_H - -#include "asm/arch/namei.h" - -#endif diff --git a/include/asm-v850/namei.h b/include/asm-v850/namei.h deleted file mode 100644 index ee8339b23843..000000000000 --- a/include/asm-v850/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * linux/include/asm-v850/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __V850_NAMEI_H__ -#define __V850_NAMEI_H__ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __V850_NAMEI_H__ */ diff --git a/include/asm-x86/namei.h b/include/asm-x86/namei.h deleted file mode 100644 index 415ef5d9550e..000000000000 --- a/include/asm-x86/namei.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_NAMEI_H -#define _ASM_X86_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_X86_NAMEI_H */ diff --git a/include/asm-xtensa/namei.h b/include/asm-xtensa/namei.h deleted file mode 100644 index 3fdff039d27d..000000000000 --- a/include/asm-xtensa/namei.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * include/asm-xtensa/namei.h - * - * Included from linux/fs/namei.c - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ - -#ifndef _XTENSA_NAMEI_H -#define _XTENSA_NAMEI_H - -#ifdef __KERNEL__ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __KERNEL__ */ -#endif /* _XTENSA_NAMEI_H */ diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 282f54219129..9e5a06e78d02 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -7,7 +7,7 @@ struct fs_struct { atomic_t count; rwlock_t lock; int umask; - struct path root, pwd, altroot; + struct path root, pwd; }; #define INIT_FS { \ @@ -19,7 +19,6 @@ struct fs_struct { extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); -extern void set_fs_altroot(void); extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); diff --git a/include/linux/namei.h b/include/linux/namei.h index 3cf62d26d493..768773d57857 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -47,7 +47,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_DIRECTORY 2 #define LOOKUP_CONTINUE 4 #define LOOKUP_PARENT 16 -#define LOOKUP_NOALT 32 #define LOOKUP_REVAL 64 /* * Intent data diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index c1ef192aa655..0d407e886735 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -168,7 +168,6 @@ __set_personality(u_long personality) current->personality = personality; oep = current_thread_info()->exec_domain; current_thread_info()->exec_domain = ep; - set_fs_altroot(); module_put(oep->module); return 0; diff --git a/kernel/exit.c b/kernel/exit.c index 6cdf60712bd2..0caf590548a0 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -565,8 +565,6 @@ void put_fs_struct(struct fs_struct *fs) if (atomic_dec_and_test(&fs->count)) { path_put(&fs->root); path_put(&fs->pwd); - if (fs->altroot.dentry) - path_put(&fs->altroot); kmem_cache_free(fs_cachep, fs); } } diff --git a/kernel/fork.c b/kernel/fork.c index abb3ed6298f6..5e050c1317c4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -657,13 +657,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old) path_get(&old->root); fs->pwd = old->pwd; path_get(&old->pwd); - if (old->altroot.dentry) { - fs->altroot = old->altroot; - path_get(&old->altroot); - } else { - fs->altroot.mnt = NULL; - fs->altroot.dentry = NULL; - } read_unlock(&old->lock); } return fs; -- cgit v1.2.3 From 5995477ab7f3522c497c9c4a1c55373e9d655574 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sun, 27 Jul 2008 17:29:15 +0200 Subject: task IO accounting: improve code readability Put all i/o statistics in struct proc_io_accounting and use inline functions to initialize and increment statistics, removing a lot of single variable assignments. This also reduces the kernel size as following (with CONFIG_TASK_XACCT=y and CONFIG_TASK_IO_ACCOUNTING=y). text data bss dec hex filename 11651 0 0 11651 2d83 kernel/exit.o.before 11619 0 0 11619 2d63 kernel/exit.o.after 10886 132 136 11154 2b92 kernel/fork.o.before 10758 132 136 11026 2b12 kernel/fork.o.after 3082029 807968 4818600 8708597 84e1f5 vmlinux.o.before 3081869 807968 4818600 8708437 84e155 vmlinux.o.after Signed-off-by: Andrea Righi Acked-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/proc/base.c | 57 ++++++++++------------------------ include/linux/sched.h | 19 ++++-------- include/linux/task_io_accounting.h | 27 ++++++++++++++-- include/linux/task_io_accounting_ops.h | 56 +++++++++++++++++++++++++++------ kernel/exit.c | 30 ++---------------- kernel/fork.c | 15 ++------- kernel/tsacct.c | 14 ++++----- 7 files changed, 104 insertions(+), 114 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index e74308bdabd3..3d94906c7aa8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -2402,44 +2403,17 @@ static int proc_base_fill_cache(struct file *filp, void *dirent, #ifdef CONFIG_TASK_IO_ACCOUNTING static int do_io_accounting(struct task_struct *task, char *buffer, int whole) { - u64 rchar, wchar, syscr, syscw; - struct task_io_accounting ioac; - - rchar = task->rchar; - wchar = task->wchar; - syscr = task->syscr; - syscw = task->syscw; - memcpy(&ioac, &task->ioac, sizeof(ioac)); - - if (whole) { - unsigned long flags; - - if (lock_task_sighand(task, &flags)) { - struct signal_struct *sig = task->signal; - struct task_struct *t = task; - - rchar += sig->rchar; - wchar += sig->wchar; - syscr += sig->syscr; - syscw += sig->syscw; - - ioac.read_bytes += sig->ioac.read_bytes; - ioac.write_bytes += sig->ioac.write_bytes; - ioac.cancelled_write_bytes += - sig->ioac.cancelled_write_bytes; - while_each_thread(task, t) { - rchar += t->rchar; - wchar += t->wchar; - syscr += t->syscr; - syscw += t->syscw; - - ioac.read_bytes += t->ioac.read_bytes; - ioac.write_bytes += t->ioac.write_bytes; - ioac.cancelled_write_bytes += - t->ioac.cancelled_write_bytes; - } - unlock_task_sighand(task, &flags); - } + struct proc_io_accounting acct = task->ioac; + unsigned long flags; + + if (whole && lock_task_sighand(task, &flags)) { + struct task_struct *t = task; + + task_io_accounting_add(&acct, &task->signal->ioac); + while_each_thread(task, t) + task_io_accounting_add(&acct, &t->ioac); + + unlock_task_sighand(task, &flags); } return sprintf(buffer, "rchar: %llu\n" @@ -2449,9 +2423,10 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole) "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", - rchar, wchar, syscr, syscw, - ioac.read_bytes, ioac.write_bytes, - ioac.cancelled_write_bytes); + acct.chr.rchar, acct.chr.wchar, + acct.chr.syscr, acct.chr.syscw, + acct.blk.read_bytes, acct.blk.write_bytes, + acct.blk.cancelled_write_bytes); } static int proc_tid_io_accounting(struct task_struct *task, char *buffer) diff --git a/include/linux/sched.h b/include/linux/sched.h index f59318a0099b..034c1ca6b332 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -505,10 +505,7 @@ struct signal_struct { unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; -#ifdef CONFIG_TASK_XACCT - u64 rchar, wchar, syscr, syscw; -#endif - struct task_io_accounting ioac; + struct proc_io_accounting ioac; /* * Cumulative ns of scheduled CPU time for dead threads in the @@ -1256,11 +1253,7 @@ struct task_struct { unsigned long ptrace_message; siginfo_t *last_siginfo; /* For ptrace use. */ -#ifdef CONFIG_TASK_XACCT -/* i/o counters(bytes read/written, #syscalls */ - u64 rchar, wchar, syscr, syscw; -#endif - struct task_io_accounting ioac; + struct proc_io_accounting ioac; #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ @@ -2190,22 +2183,22 @@ extern long sched_group_rt_period(struct task_group *tg); #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { - tsk->rchar += amt; + tsk->ioac.chr.rchar += amt; } static inline void add_wchar(struct task_struct *tsk, ssize_t amt) { - tsk->wchar += amt; + tsk->ioac.chr.wchar += amt; } static inline void inc_syscr(struct task_struct *tsk) { - tsk->syscr++; + tsk->ioac.chr.syscr++; } static inline void inc_syscw(struct task_struct *tsk) { - tsk->syscw++; + tsk->ioac.chr.syscw++; } #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index 44d00e9cceea..165390f8b936 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -1,5 +1,5 @@ /* - * task_io_accounting: a structure which is used for recording a single task's + * proc_io_accounting: a structure which is used for recording a single task's * IO statistics. * * Don't include this header file directly - it is designed to be dragged in via @@ -8,6 +8,22 @@ * Blame akpm@osdl.org for all this. */ +#ifdef CONFIG_TASK_XACCT +struct task_chr_io_accounting { + /* bytes read */ + u64 rchar; + /* bytes written */ + u64 wchar; + /* # of read syscalls */ + u64 syscr; + /* # of write syscalls */ + u64 syscw; +}; +#else /* CONFIG_TASK_XACCT */ +struct task_chr_io_accounting { +}; +#endif /* CONFIG_TASK_XACCT */ + #ifdef CONFIG_TASK_IO_ACCOUNTING struct task_io_accounting { /* @@ -31,7 +47,12 @@ struct task_io_accounting { */ u64 cancelled_write_bytes; }; -#else +#else /* CONFIG_TASK_IO_ACCOUNTING */ struct task_io_accounting { }; -#endif +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +struct proc_io_accounting { + struct task_chr_io_accounting chr; + struct task_io_accounting blk; +}; diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index ff46c6fad79d..e6f958ebe97f 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -9,7 +9,7 @@ #ifdef CONFIG_TASK_IO_ACCOUNTING static inline void task_io_account_read(size_t bytes) { - current->ioac.read_bytes += bytes; + current->ioac.blk.read_bytes += bytes; } /* @@ -18,12 +18,12 @@ static inline void task_io_account_read(size_t bytes) */ static inline unsigned long task_io_get_inblock(const struct task_struct *p) { - return p->ioac.read_bytes >> 9; + return p->ioac.blk.read_bytes >> 9; } static inline void task_io_account_write(size_t bytes) { - current->ioac.write_bytes += bytes; + current->ioac.blk.write_bytes += bytes; } /* @@ -32,17 +32,25 @@ static inline void task_io_account_write(size_t bytes) */ static inline unsigned long task_io_get_oublock(const struct task_struct *p) { - return p->ioac.write_bytes >> 9; + return p->ioac.blk.write_bytes >> 9; } static inline void task_io_account_cancelled_write(size_t bytes) { - current->ioac.cancelled_write_bytes += bytes; + current->ioac.blk.cancelled_write_bytes += bytes; } -static inline void task_io_accounting_init(struct task_struct *tsk) +static inline void task_io_accounting_init(struct proc_io_accounting *ioac) { - memset(&tsk->ioac, 0, sizeof(tsk->ioac)); + memset(ioac, 0, sizeof(*ioac)); +} + +static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + dst->blk.read_bytes += src->blk.read_bytes; + dst->blk.write_bytes += src->blk.write_bytes; + dst->blk.cancelled_write_bytes += src->blk.cancelled_write_bytes; } #else @@ -69,9 +77,37 @@ static inline void task_io_account_cancelled_write(size_t bytes) { } -static inline void task_io_accounting_init(struct task_struct *tsk) +static inline void task_io_accounting_init(struct proc_io_accounting *ioac) +{ +} + +static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) { } -#endif /* CONFIG_TASK_IO_ACCOUNTING */ -#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +#ifdef CONFIG_TASK_XACCT +static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + dst->chr.rchar += src->chr.rchar; + dst->chr.wchar += src->chr.wchar; + dst->chr.syscr += src->chr.syscr; + dst->chr.syscw += src->chr.syscw; +} +#else +static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ +} +#endif /* CONFIG_TASK_XACCT */ + +static inline void task_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + task_chr_io_accounting_add(dst, src); + task_blk_io_accounting_add(dst, src); +} +#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ diff --git a/kernel/exit.c b/kernel/exit.c index 0caf590548a0..eb4d6470d1d0 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -121,18 +121,7 @@ static void __exit_signal(struct task_struct *tsk) sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); -#ifdef CONFIG_TASK_XACCT - sig->rchar += tsk->rchar; - sig->wchar += tsk->wchar; - sig->syscr += tsk->syscr; - sig->syscw += tsk->syscw; -#endif /* CONFIG_TASK_XACCT */ -#ifdef CONFIG_TASK_IO_ACCOUNTING - sig->ioac.read_bytes += tsk->ioac.read_bytes; - sig->ioac.write_bytes += tsk->ioac.write_bytes; - sig->ioac.cancelled_write_bytes += - tsk->ioac.cancelled_write_bytes; -#endif /* CONFIG_TASK_IO_ACCOUNTING */ + task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1363,21 +1352,8 @@ static int wait_task_zombie(struct task_struct *p, int options, psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; -#ifdef CONFIG_TASK_XACCT - psig->rchar += p->rchar + sig->rchar; - psig->wchar += p->wchar + sig->wchar; - psig->syscr += p->syscr + sig->syscr; - psig->syscw += p->syscw + sig->syscw; -#endif /* CONFIG_TASK_XACCT */ -#ifdef CONFIG_TASK_IO_ACCOUNTING - psig->ioac.read_bytes += - p->ioac.read_bytes + sig->ioac.read_bytes; - psig->ioac.write_bytes += - p->ioac.write_bytes + sig->ioac.write_bytes; - psig->ioac.cancelled_write_bytes += - p->ioac.cancelled_write_bytes + - sig->ioac.cancelled_write_bytes; -#endif /* CONFIG_TASK_IO_ACCOUNTING */ + task_io_accounting_add(&psig->ioac, &p->ioac); + task_io_accounting_add(&psig->ioac, &sig->ioac); spin_unlock_irq(&p->parent->sighand->siglock); } diff --git a/kernel/fork.c b/kernel/fork.c index 5e050c1317c4..8214ba7c8bb1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -806,12 +806,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; -#ifdef CONFIG_TASK_XACCT - sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0; -#endif -#ifdef CONFIG_TASK_IO_ACCOUNTING - memset(&sig->ioac, 0, sizeof(sig->ioac)); -#endif + task_io_accounting_init(&sig->ioac); sig->sum_sched_runtime = 0; INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); @@ -994,13 +989,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->last_switch_timestamp = 0; #endif -#ifdef CONFIG_TASK_XACCT - p->rchar = 0; /* I/O counter: bytes read */ - p->wchar = 0; /* I/O counter: bytes written */ - p->syscr = 0; /* I/O counter: read syscalls */ - p->syscw = 0; /* I/O counter: write syscalls */ -#endif - task_io_accounting_init(p); + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); p->it_virt_expires = cputime_zero; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 3da47ccdc5e5..f9cd2561689c 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -94,14 +94,14 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) stats->hiwater_vm = mm->hiwater_vm * PAGE_SIZE / KB; mmput(mm); } - stats->read_char = p->rchar; - stats->write_char = p->wchar; - stats->read_syscalls = p->syscr; - stats->write_syscalls = p->syscw; + stats->read_char = p->ioac.chr.rchar; + stats->write_char = p->ioac.chr.wchar; + stats->read_syscalls = p->ioac.chr.syscr; + stats->write_syscalls = p->ioac.chr.syscw; #ifdef CONFIG_TASK_IO_ACCOUNTING - stats->read_bytes = p->ioac.read_bytes; - stats->write_bytes = p->ioac.write_bytes; - stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes; + stats->read_bytes = p->ioac.blk.read_bytes; + stats->write_bytes = p->ioac.blk.write_bytes; + stats->cancelled_write_bytes = p->ioac.blk.cancelled_write_bytes; #else stats->read_bytes = 0; stats->write_bytes = 0; -- cgit v1.2.3 From cddb8a5c14aa89810b40495d94d3d2a0faee6619 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:29 -0700 Subject: mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli Signed-off-by: Nick Piggin Signed-off-by: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kvm/Kconfig | 1 + include/linux/mm_types.h | 4 + include/linux/mmu_notifier.h | 279 +++++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 3 + mm/Kconfig | 3 + mm/Makefile | 1 + mm/filemap_xip.c | 3 +- mm/fremap.c | 3 + mm/hugetlb.c | 3 + mm/memory.c | 35 +++++- mm/mmap.c | 2 + mm/mmu_notifier.c | 277 ++++++++++++++++++++++++++++++++++++++++++ mm/mprotect.c | 3 + mm/mremap.c | 6 + mm/rmap.c | 13 +- 15 files changed, 623 insertions(+), 13 deletions(-) create mode 100644 include/linux/mmu_notifier.h create mode 100644 mm/mmu_notifier.c (limited to 'kernel/fork.c') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8d45fabc5f3b..ce3251ce5504 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM tristate "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM select PREEMPT_NOTIFIERS + select MMU_NOTIFIER select ANON_INODES ---help--- Support hosting fully virtualized guest machines using hardware diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 746f975b58ef..386edbe2cb4e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -253,6 +254,9 @@ struct mm_struct { struct file *exe_file; unsigned long num_exe_file_vmas; #endif +#ifdef CONFIG_MMU_NOTIFIER + struct mmu_notifier_mm *mmu_notifier_mm; +#endif }; #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h new file mode 100644 index 000000000000..b77486d152cd --- /dev/null +++ b/include/linux/mmu_notifier.h @@ -0,0 +1,279 @@ +#ifndef _LINUX_MMU_NOTIFIER_H +#define _LINUX_MMU_NOTIFIER_H + +#include +#include +#include + +struct mmu_notifier; +struct mmu_notifier_ops; + +#ifdef CONFIG_MMU_NOTIFIER + +/* + * The mmu notifier_mm structure is allocated and installed in + * mm->mmu_notifier_mm inside the mm_take_all_locks() protected + * critical section and it's released only when mm_count reaches zero + * in mmdrop(). + */ +struct mmu_notifier_mm { + /* all mmu notifiers registerd in this mm are queued in this list */ + struct hlist_head list; + /* to serialize the list modifications and hlist_unhashed */ + spinlock_t lock; +}; + +struct mmu_notifier_ops { + /* + * Called either by mmu_notifier_unregister or when the mm is + * being destroyed by exit_mmap, always before all pages are + * freed. This can run concurrently with other mmu notifier + * methods (the ones invoked outside the mm context) and it + * should tear down all secondary mmu mappings and freeze the + * secondary mmu. If this method isn't implemented you've to + * be sure that nothing could possibly write to the pages + * through the secondary mmu by the time the last thread with + * tsk->mm == mm exits. + * + * As side note: the pages freed after ->release returns could + * be immediately reallocated by the gart at an alias physical + * address with a different cache model, so if ->release isn't + * implemented because all _software_ driven memory accesses + * through the secondary mmu are terminated by the time the + * last thread of this mm quits, you've also to be sure that + * speculative _hardware_ operations can't allocate dirty + * cachelines in the cpu that could not be snooped and made + * coherent with the other read and write operations happening + * through the gart alias address, so leading to memory + * corruption. + */ + void (*release)(struct mmu_notifier *mn, + struct mm_struct *mm); + + /* + * clear_flush_young is called after the VM is + * test-and-clearing the young/accessed bitflag in the + * pte. This way the VM will provide proper aging to the + * accesses to the page through the secondary MMUs and not + * only to the ones through the Linux pte. + */ + int (*clear_flush_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * Before this is invoked any secondary MMU is still ok to + * read/write to the page previously pointed to by the Linux + * pte because the page hasn't been freed yet and it won't be + * freed until this returns. If required set_page_dirty has to + * be called internally to this method. + */ + void (*invalidate_page)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * invalidate_range_start() and invalidate_range_end() must be + * paired and are called only when the mmap_sem and/or the + * locks protecting the reverse maps are held. The subsystem + * must guarantee that no additional references are taken to + * the pages in the range established between the call to + * invalidate_range_start() and the matching call to + * invalidate_range_end(). + * + * Invalidation of multiple concurrent ranges may be + * optionally permitted by the driver. Either way the + * establishment of sptes is forbidden in the range passed to + * invalidate_range_begin/end for the whole duration of the + * invalidate_range_begin/end critical section. + * + * invalidate_range_start() is called when all pages in the + * range are still mapped and have at least a refcount of one. + * + * invalidate_range_end() is called when all pages in the + * range have been unmapped and the pages have been freed by + * the VM. + * + * The VM will remove the page table entries and potentially + * the page between invalidate_range_start() and + * invalidate_range_end(). If the page must not be freed + * because of pending I/O or other circumstances then the + * invalidate_range_start() callback (or the initial mapping + * by the driver) must make sure that the refcount is kept + * elevated. + * + * If the driver increases the refcount when the pages are + * initially mapped into an address space then either + * invalidate_range_start() or invalidate_range_end() may + * decrease the refcount. If the refcount is decreased on + * invalidate_range_start() then the VM can free pages as page + * table entries are removed. If the refcount is only + * droppped on invalidate_range_end() then the driver itself + * will drop the last refcount but it must take care to flush + * any secondary tlb before doing the final free on the + * page. Pages will no longer be referenced by the linux + * address space but may still be referenced by sptes until + * the last refcount is dropped. + */ + void (*invalidate_range_start)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); + void (*invalidate_range_end)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); +}; + +/* + * The notifier chains are protected by mmap_sem and/or the reverse map + * semaphores. Notifier chains are only changed when all reverse maps and + * the mmap_sem locks are taken. + * + * Therefore notifier chains can only be traversed when either + * + * 1. mmap_sem is held. + * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock). + * 3. No other concurrent thread can access the list (release) + */ +struct mmu_notifier { + struct hlist_node hlist; + const struct mmu_notifier_ops *ops; +}; + +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return unlikely(mm->mmu_notifier_mm); +} + +extern int mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern int __mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void mmu_notifier_unregister(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); +extern void __mmu_notifier_release(struct mm_struct *mm); +extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end); + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_release(mm); +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_clear_flush_young(mm, address); + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_page(mm, address); +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_start(mm, start, end); +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_end(mm, start, end); +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ + mm->mmu_notifier_mm = NULL; +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_mm_destroy(mm); +} + +/* + * These two macros will sometime replace ptep_clear_flush. + * ptep_clear_flush is impleemnted as macro itself, so this also is + * implemented as a macro until ptep_clear_flush will converted to an + * inline function, to diminish the risk of compilation failure. The + * invalidate_page method over time can be moved outside the PT lock + * and these two macros can be later removed. + */ +#define ptep_clear_flush_notify(__vma, __address, __ptep) \ +({ \ + pte_t __pte; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __pte = ptep_clear_flush(___vma, ___address, __ptep); \ + mmu_notifier_invalidate_page(___vma->vm_mm, ___address); \ + __pte; \ +}) + +#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ + __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ + ___address); \ + __young; \ +}) + +#else /* CONFIG_MMU_NOTIFIER */ + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ +} + +#define ptep_clear_flush_young_notify ptep_clear_flush_young +#define ptep_clear_flush_notify ptep_clear_flush + +#endif /* CONFIG_MMU_NOTIFIER */ + +#endif /* _LINUX_MMU_NOTIFIER_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 8214ba7c8bb1..7ce2ebe84796 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -414,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; + mmu_notifier_mm_init(mm); return mm; } @@ -446,6 +448,7 @@ void __mmdrop(struct mm_struct *mm) BUG_ON(mm == &init_mm); mm_free_pgd(mm); destroy_context(mm); + mmu_notifier_mm_destroy(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); diff --git a/mm/Kconfig b/mm/Kconfig index efee5d379df4..446c6588c753 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -208,3 +208,6 @@ config NR_QUICK config VIRT_TO_BUS def_bool y depends on !ARCH_NO_VIRT_TO_BUS + +config MMU_NOTIFIER + bool diff --git a/mm/Makefile b/mm/Makefile index 06ca2381fef1..da4ccf015aea 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_SHMEM) += shmem.o obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o obj-$(CONFIG_SLOB) += slob.o +obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 98a3f31ccd6a..380ab402d711 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -188,7 +189,7 @@ __xip_unmap (struct address_space * mapping, if (pte) { /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); page_remove_rmap(page, vma); dec_mm_counter(mm, file_rss); BUG_ON(pte_dirty(pteval)); diff --git a/mm/fremap.c b/mm/fremap.c index 07a9c82ce1a3..7881638e4a12 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -214,7 +215,9 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, spin_unlock(&mapping->i_mmap_lock); } + mmu_notifier_invalidate_range_start(mm, start, start + size); err = populate_range(mm, vma, start, size, pgoff); + mmu_notifier_invalidate_range_end(mm, start, start + size); if (!err && !(flags & MAP_NONBLOCK)) { if (unlikely(has_write_lock)) { downgrade_write(&mm->mmap_sem); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3be79dc18c5c..80eb0d31d0d3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -1672,6 +1673,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); + mmu_notifier_invalidate_range_start(mm, start, end); spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); @@ -1713,6 +1715,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range_end(mm, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { list_del(&page->lru); put_page(page); diff --git a/mm/memory.c b/mm/memory.c index a8ca04faaea6..67f0ab9077d9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -652,6 +653,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long next; unsigned long addr = vma->vm_start; unsigned long end = vma->vm_end; + int ret; /* * Don't copy ptes where a page fault will fill them correctly. @@ -667,17 +669,33 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_start(src_mm, addr, end); + + ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next)) - return -ENOMEM; + if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next))) { + ret = -ENOMEM; + break; + } } while (dst_pgd++, src_pgd++, addr = next, addr != end); - return 0; + + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_end(src_mm, + vma->vm_start, end); + return ret; } static unsigned long zap_pte_range(struct mmu_gather *tlb, @@ -881,7 +899,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, unsigned long start = start_addr; spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; int fullmm = (*tlbp)->fullmm; + struct mm_struct *mm = vma->vm_mm; + mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { unsigned long end; @@ -946,6 +966,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } } out: + mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); return start; /* which is now the end (or restart) address */ } @@ -1616,10 +1637,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, { pgd_t *pgd; unsigned long next; - unsigned long end = addr + size; + unsigned long start = addr, end = addr + size; int err; BUG_ON(addr >= end); + mmu_notifier_invalidate_range_start(mm, start, end); pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); @@ -1627,6 +1649,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); + mmu_notifier_invalidate_range_end(mm, start, end); return err; } EXPORT_SYMBOL_GPL(apply_to_page_range); @@ -1839,7 +1862,7 @@ gotten: * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush(vma, address, page_table); + ptep_clear_flush_notify(vma, address, page_table); set_pte_at(mm, address, page_table, entry); update_mmu_cache(vma, address, entry); lru_cache_add_active(new_page); diff --git a/mm/mmap.c b/mm/mmap.c index e5f9cb83d6d4..245c3d69067b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -2061,6 +2062,7 @@ void exit_mmap(struct mm_struct *mm) /* mm's last user has gone, and its about to be pulled down */ arch_exit_mmap(mm); + mmu_notifier_release(mm); lru_add_drain(); flush_cache_mm(mm); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c new file mode 100644 index 000000000000..5f4ef0250bee --- /dev/null +++ b/mm/mmu_notifier.c @@ -0,0 +1,277 @@ +/* + * linux/mm/mmu_notifier.c + * + * Copyright (C) 2008 Qumranet, Inc. + * Copyright (C) 2008 SGI + * Christoph Lameter + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include +#include +#include +#include +#include +#include +#include + +/* + * This function can't run concurrently against mmu_notifier_register + * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap + * runs with mm_users == 0. Other tasks may still invoke mmu notifiers + * in parallel despite there being no task using this mm any more, + * through the vmas outside of the exit_mmap context, such as with + * vmtruncate. This serializes against mmu_notifier_unregister with + * the mmu_notifier_mm->lock in addition to RCU and it serializes + * against the other mmu notifiers with RCU. struct mmu_notifier_mm + * can't go away from under us as exit_mmap holds an mm_count pin + * itself. + */ +void __mmu_notifier_release(struct mm_struct *mm) +{ + struct mmu_notifier *mn; + + spin_lock(&mm->mmu_notifier_mm->lock); + while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { + mn = hlist_entry(mm->mmu_notifier_mm->list.first, + struct mmu_notifier, + hlist); + /* + * We arrived before mmu_notifier_unregister so + * mmu_notifier_unregister will do nothing other than + * to wait ->release to finish and + * mmu_notifier_unregister to return. + */ + hlist_del_init_rcu(&mn->hlist); + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + spin_unlock(&mm->mmu_notifier_mm->lock); + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); + spin_lock(&mm->mmu_notifier_mm->lock); + } + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * synchronize_rcu here prevents mmu_notifier_release to + * return to exit_mmap (which would proceed freeing all pages + * in the mm) until the ->release method returns, if it was + * invoked by mmu_notifier_unregister. + * + * The mmu_notifier_mm can't go away from under us because one + * mm_count is hold by exit_mmap. + */ + synchronize_rcu(); +} + +/* + * If no young bitflag is supported by the hardware, ->clear_flush_young can + * unmap the address and return 1 or 0 depending if the mapping previously + * existed or not. + */ +int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + int young = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->clear_flush_young) + young |= mn->ops->clear_flush_young(mn, mm, address); + } + rcu_read_unlock(); + + return young; +} + +void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_page) + mn->ops->invalidate_page(mn, mm, address); + } + rcu_read_unlock(); +} + +void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range_start) + mn->ops->invalidate_range_start(mn, mm, start, end); + } + rcu_read_unlock(); +} + +void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range_end) + mn->ops->invalidate_range_end(mn, mm, start, end); + } + rcu_read_unlock(); +} + +static int do_mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm, + int take_mmap_sem) +{ + struct mmu_notifier_mm *mmu_notifier_mm; + int ret; + + BUG_ON(atomic_read(&mm->mm_users) <= 0); + + ret = -ENOMEM; + mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); + if (unlikely(!mmu_notifier_mm)) + goto out; + + if (take_mmap_sem) + down_write(&mm->mmap_sem); + ret = mm_take_all_locks(mm); + if (unlikely(ret)) + goto out_cleanup; + + if (!mm_has_notifiers(mm)) { + INIT_HLIST_HEAD(&mmu_notifier_mm->list); + spin_lock_init(&mmu_notifier_mm->lock); + mm->mmu_notifier_mm = mmu_notifier_mm; + mmu_notifier_mm = NULL; + } + atomic_inc(&mm->mm_count); + + /* + * Serialize the update against mmu_notifier_unregister. A + * side note: mmu_notifier_release can't run concurrently with + * us because we hold the mm_users pin (either implicitly as + * current->mm or explicitly with get_task_mm() or similar). + * We can't race against any other mmu notifier method either + * thanks to mm_take_all_locks(). + */ + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list); + spin_unlock(&mm->mmu_notifier_mm->lock); + + mm_drop_all_locks(mm); +out_cleanup: + if (take_mmap_sem) + up_write(&mm->mmap_sem); + /* kfree() does nothing if mmu_notifier_mm is NULL */ + kfree(mmu_notifier_mm); +out: + BUG_ON(atomic_read(&mm->mm_users) <= 0); + return ret; +} + +/* + * Must not hold mmap_sem nor any other VM related lock when calling + * this registration function. Must also ensure mm_users can't go down + * to zero while this runs to avoid races with mmu_notifier_release, + * so mm has to be current->mm or the mm should be pinned safely such + * as with get_task_mm(). If the mm is not current->mm, the mm_users + * pin should be released by calling mmput after mmu_notifier_register + * returns. mmu_notifier_unregister must be always called to + * unregister the notifier. mm_count is automatically pinned to allow + * mmu_notifier_unregister to safely run at any time later, before or + * after exit_mmap. ->release will always be called before exit_mmap + * frees the pages. + */ +int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +{ + return do_mmu_notifier_register(mn, mm, 1); +} +EXPORT_SYMBOL_GPL(mmu_notifier_register); + +/* + * Same as mmu_notifier_register but here the caller must hold the + * mmap_sem in write mode. + */ +int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +{ + return do_mmu_notifier_register(mn, mm, 0); +} +EXPORT_SYMBOL_GPL(__mmu_notifier_register); + +/* this is called after the last mmu_notifier_unregister() returned */ +void __mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list)); + kfree(mm->mmu_notifier_mm); + mm->mmu_notifier_mm = LIST_POISON1; /* debug */ +} + +/* + * This releases the mm_count pin automatically and frees the mm + * structure if it was the last user of it. It serializes against + * running mmu notifiers with RCU and against mmu_notifier_unregister + * with the unregister lock + RCU. All sptes must be dropped before + * calling mmu_notifier_unregister. ->release or any other notifier + * method may be invoked concurrently with mmu_notifier_unregister, + * and only after mmu_notifier_unregister returned we're guaranteed + * that ->release or any other method can't run anymore. + */ +void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) +{ + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + spin_lock(&mm->mmu_notifier_mm->lock); + if (!hlist_unhashed(&mn->hlist)) { + hlist_del_rcu(&mn->hlist); + + /* + * RCU here will force exit_mmap to wait ->release to finish + * before freeing the pages. + */ + rcu_read_lock(); + spin_unlock(&mm->mmu_notifier_mm->lock); + /* + * exit_mmap will block in mmu_notifier_release to + * guarantee ->release is called before freeing the + * pages. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); + } else + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * Wait any running method to finish, of course including + * ->release if it was run by mmu_notifier_relase instead of us. + */ + synchronize_rcu(); + + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + mmdrop(mm); +} +EXPORT_SYMBOL_GPL(mmu_notifier_unregister); diff --git a/mm/mprotect.c b/mm/mprotect.c index abd645a3b0a0..fded06f923f4 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -203,10 +204,12 @@ success: dirty_accountable = 1; } + mmu_notifier_invalidate_range_start(mm, start, end); if (is_vm_hugetlb_page(vma)) hugetlb_change_protection(vma, start, end, vma->vm_page_prot); else change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable); + mmu_notifier_invalidate_range_end(mm, start, end); vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); vm_stat_account(mm, newflags, vma->vm_file, nrpages); return 0; diff --git a/mm/mremap.c b/mm/mremap.c index 08e3c7f2bd15..1a7743923c8c 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -74,7 +75,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; + unsigned long old_start; + old_start = old_addr; + mmu_notifier_invalidate_range_start(vma->vm_mm, + old_start, old_end); if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before @@ -116,6 +121,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) spin_unlock(&mapping->i_mmap_lock); + mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end); } #define LATENCY_LIMIT (64 * PAGE_SIZE) diff --git a/mm/rmap.c b/mm/rmap.c index 39ae5a9bf382..99bc3f9cd796 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -49,6 +49,7 @@ #include #include #include +#include #include @@ -287,7 +288,7 @@ static int page_referenced_one(struct page *page, if (vma->vm_flags & VM_LOCKED) { referenced++; *mapcount = 1; /* break early from loop */ - } else if (ptep_clear_flush_young(vma, address, pte)) + } else if (ptep_clear_flush_young_notify(vma, address, pte)) referenced++; /* Pretend the page is referenced if the task has the @@ -457,7 +458,7 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma) pte_t entry; flush_cache_page(vma, address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, address, pte); + entry = ptep_clear_flush_notify(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(mm, address, pte, entry); @@ -705,14 +706,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * skipped over this mm) then we should reactivate it. */ if (!migration && ((vma->vm_flags & VM_LOCKED) || - (ptep_clear_flush_young(vma, address, pte)))) { + (ptep_clear_flush_young_notify(vma, address, pte)))) { ret = SWAP_FAIL; goto out_unmap; } /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -837,12 +838,12 @@ static void try_to_unmap_cluster(unsigned long cursor, page = vm_normal_page(vma, address, *pte); BUG_ON(!page || PageAnon(page)); - if (ptep_clear_flush_young(vma, address, pte)) + if (ptep_clear_flush_young_notify(vma, address, pte)) continue; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ if (page->index != linear_page_index(vma, address)) -- cgit v1.2.3