diff options
author | Trond Myklebust <Trond.Myklebust@netapp.com> | 2006-06-24 08:41:41 -0400 |
---|---|---|
committer | Trond Myklebust <Trond.Myklebust@netapp.com> | 2006-06-24 13:07:53 -0400 |
commit | 816724e65c72a90a44fbad0ef0b59b186c85fa90 (patch) | |
tree | 421fa29aedff988e392f92780637553e275d37a0 /kernel | |
parent | 70ac4385a13f78bc478f26d317511893741b05bd (diff) | |
parent | d384ea691fe4ea8c2dd5b9b8d9042eb181776f18 (diff) | |
download | op-kernel-dev-816724e65c72a90a44fbad0ef0b59b186c85fa90.zip op-kernel-dev-816724e65c72a90a44fbad0ef0b59b186c85fa90.tar.gz |
Merge branch 'master' of /home/trondmy/kernel/linux-2.6/
Conflicts:
fs/nfs/inode.c
fs/super.c
Fix conflicts between patch 'NFS: Split fs/nfs/inode.c' and patch
'VFS: Permit filesystem to override root dentry on mount'
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/acct.c | 2 | ||||
-rw-r--r-- | kernel/auditsc.c | 1 | ||||
-rw-r--r-- | kernel/compat.c | 23 | ||||
-rw-r--r-- | kernel/cpuset.c | 16 | ||||
-rw-r--r-- | kernel/exit.c | 5 | ||||
-rw-r--r-- | kernel/fork.c | 5 | ||||
-rw-r--r-- | kernel/futex.c | 8 | ||||
-rw-r--r-- | kernel/irq/handle.c | 5 | ||||
-rw-r--r-- | kernel/irq/migration.c | 4 | ||||
-rw-r--r-- | kernel/irq/proc.c | 3 | ||||
-rw-r--r-- | kernel/irq/spurious.c | 12 | ||||
-rw-r--r-- | kernel/kexec.c | 6 | ||||
-rw-r--r-- | kernel/ksysfs.c | 19 | ||||
-rw-r--r-- | kernel/power/main.c | 2 | ||||
-rw-r--r-- | kernel/power/power.h | 6 | ||||
-rw-r--r-- | kernel/power/snapshot.c | 260 | ||||
-rw-r--r-- | kernel/power/swsusp.c | 32 | ||||
-rw-r--r-- | kernel/rcupdate.c | 13 | ||||
-rw-r--r-- | kernel/sched.c | 12 | ||||
-rw-r--r-- | kernel/sys.c | 70 | ||||
-rw-r--r-- | kernel/sys_ni.c | 2 | ||||
-rw-r--r-- | kernel/sysctl.c | 11 | ||||
-rw-r--r-- | kernel/timer.c | 30 | ||||
-rw-r--r-- | kernel/user.c | 2 | ||||
-rw-r--r-- | kernel/workqueue.c | 4 |
25 files changed, 378 insertions, 175 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index b327f4d..6802020 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -118,7 +118,7 @@ static int check_free_space(struct file *file) spin_unlock(&acct_globals.lock); /* May block */ - if (vfs_statfs(file->f_dentry->d_inode->i_sb, &sbuf)) + if (vfs_statfs(file->f_dentry, &sbuf)) return res; suspend = sbuf.f_blocks * SUSPEND; resume = sbuf.f_blocks * RESUME; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b097ccb..9ebd96f 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1558,6 +1558,7 @@ int __audit_ipc_obj(struct kern_ipc_perm *ipcp) * @uid: msgq user id * @gid: msgq group id * @mode: msgq mode (permissions) + * @ipcp: in-kernel IPC permissions * * Returns 0 for success or NULL context or < 0 on error. */ diff --git a/kernel/compat.c b/kernel/compat.c index c1601a8..2f67233 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -21,6 +21,7 @@ #include <linux/unistd.h> #include <linux/security.h> #include <linux/timex.h> +#include <linux/migrate.h> #include <asm/uaccess.h> @@ -934,3 +935,25 @@ asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp) return ret; } + +#ifdef CONFIG_NUMA +asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages, + compat_uptr_t __user *pages32, + const int __user *nodes, + int __user *status, + int flags) +{ + const void __user * __user *pages; + int i; + + pages = compat_alloc_user_space(nr_pages * sizeof(void *)); + for (i = 0; i < nr_pages; i++) { + compat_uptr_t p; + + if (get_user(p, pages32 + i) || + put_user(compat_ptr(p), pages + i)) + return -EFAULT; + } + return sys_move_pages(pid, nr_pages, pages, nodes, status, flags); +} +#endif diff --git a/kernel/cpuset.c b/kernel/cpuset.c index ab81fdd..b602f73 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -41,6 +41,7 @@ #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/seq_file.h> +#include <linux/security.h> #include <linux/slab.h> #include <linux/smp_lock.h> #include <linux/spinlock.h> @@ -392,11 +393,11 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data, return 0; } -static struct super_block *cpuset_get_sb(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data) +static int cpuset_get_sb(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data, struct vfsmount *mnt) { - return get_sb_single(fs_type, flags, data, cpuset_fill_super); + return get_sb_single(fs_type, flags, data, cpuset_fill_super, mnt); } static struct file_system_type cpuset_fs_type = { @@ -1177,6 +1178,7 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf) cpumask_t cpus; nodemask_t from, to; struct mm_struct *mm; + int retval; if (sscanf(pidbuf, "%d", &pid) != 1) return -EIO; @@ -1205,6 +1207,12 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf) get_task_struct(tsk); } + retval = security_task_setscheduler(tsk, 0, NULL); + if (retval) { + put_task_struct(tsk); + return retval; + } + mutex_lock(&callback_mutex); task_lock(tsk); diff --git a/kernel/exit.c b/kernel/exit.c index e06d0c1..a3baf92 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -579,7 +579,7 @@ static void exit_mm(struct task_struct * tsk) down_read(&mm->mmap_sem); } atomic_inc(&mm->mm_count); - if (mm != tsk->active_mm) BUG(); + BUG_ON(mm != tsk->active_mm); /* more a memory barrier than a real lock */ task_lock(tsk); tsk->mm = NULL; @@ -1530,8 +1530,7 @@ check_continued: if (options & __WNOTHREAD) break; tsk = next_thread(tsk); - if (tsk->signal != current->signal) - BUG(); + BUG_ON(tsk->signal != current->signal); } while (tsk != current); read_unlock(&tasklist_lock); diff --git a/kernel/fork.c b/kernel/fork.c index ac8100e..49adc0e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -368,6 +368,8 @@ void fastcall __mmdrop(struct mm_struct *mm) */ void mmput(struct mm_struct *mm) { + might_sleep(); + if (atomic_dec_and_test(&mm->mm_users)) { exit_aio(mm); exit_mmap(mm); @@ -623,6 +625,7 @@ out: /* * Allocate a new files structure and copy contents from the * passed in files structure. + * errorp will be valid only when the returned files_struct is NULL. */ static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) { @@ -631,6 +634,7 @@ static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) int open_files, size, i, expand; struct fdtable *old_fdt, *new_fdt; + *errorp = -ENOMEM; newf = alloc_files(); if (!newf) goto out; @@ -744,7 +748,6 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk) * break this. */ tsk->files = NULL; - error = -ENOMEM; newf = dup_fd(oldf, &error); if (!newf) goto out; diff --git a/kernel/futex.c b/kernel/futex.c index 5699c51..e1a380c 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1056,11 +1056,11 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, int val, (unsigned long)uaddr2, val2, val3); } -static struct super_block * -futexfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int futexfs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, + struct vfsmount *mnt) { - return get_sb_pseudo(fs_type, "futex", NULL, 0xBAD1DEA); + return get_sb_pseudo(fs_type, "futex", NULL, 0xBAD1DEA, mnt); } static struct file_system_type futex_fs_type = { diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 51df337..0f65301 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -76,10 +76,11 @@ irqreturn_t no_action(int cpl, void *dev_id, struct pt_regs *regs) /* * Have got an event to handle: */ -fastcall int handle_IRQ_event(unsigned int irq, struct pt_regs *regs, +fastcall irqreturn_t handle_IRQ_event(unsigned int irq, struct pt_regs *regs, struct irqaction *action) { - int ret, retval = 0, status = 0; + irqreturn_t ret, retval = IRQ_NONE; + unsigned int status = 0; if (!(action->flags & SA_INTERRUPT)) local_irq_enable(); diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 134f9f2..a12d00e 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -30,7 +30,7 @@ void move_native_irq(int irq) desc->move_irq = 0; - if (likely(cpus_empty(pending_irq_cpumask[irq]))) + if (unlikely(cpus_empty(pending_irq_cpumask[irq]))) return; if (!desc->handler->set_affinity) @@ -49,7 +49,7 @@ void move_native_irq(int irq) * cause some ioapics to mal-function. * Being paranoid i guess! */ - if (unlikely(!cpus_empty(tmp))) { + if (likely(!cpus_empty(tmp))) { if (likely(!(desc->status & IRQ_DISABLED))) desc->handler->disable(irq); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index d03b5ee..afacd6f 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -24,6 +24,8 @@ static struct proc_dir_entry *smp_affinity_entry[NR_IRQS]; #ifdef CONFIG_GENERIC_PENDING_IRQ void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) { + set_balance_irq_affinity(irq, mask_val); + /* * Save these away for later use. Re-progam when the * interrupt is pending @@ -33,6 +35,7 @@ void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) #else void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) { + set_balance_irq_affinity(irq, mask_val); irq_affinity[irq] = mask_val; irq_desc[irq].handler->set_affinity(irq, mask_val); } diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 7df9abd..b2fb3c1 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -11,7 +11,7 @@ #include <linux/kallsyms.h> #include <linux/interrupt.h> -static int irqfixup; +static int irqfixup __read_mostly; /* * Recovery handler for misrouted interrupts. @@ -136,9 +136,9 @@ static void report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t actio void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret, struct pt_regs *regs) { - if (action_ret != IRQ_HANDLED) { + if (unlikely(action_ret != IRQ_HANDLED)) { desc->irqs_unhandled++; - if (action_ret != IRQ_NONE) + if (unlikely(action_ret != IRQ_NONE)) report_bad_irq(irq, desc, action_ret); } @@ -152,11 +152,11 @@ void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret, } desc->irq_count++; - if (desc->irq_count < 100000) + if (likely(desc->irq_count < 100000)) return; desc->irq_count = 0; - if (desc->irqs_unhandled > 99900) { + if (unlikely(desc->irqs_unhandled > 99900)) { /* * The interrupt is stuck */ @@ -171,7 +171,7 @@ void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret, desc->irqs_unhandled = 0; } -int noirqdebug; +int noirqdebug __read_mostly; int __init noirqdebug_setup(char *str) { diff --git a/kernel/kexec.c b/kernel/kexec.c index bf39d28..58f0f38 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -902,14 +902,14 @@ static int kimage_load_segment(struct kimage *image, * kexec does not sync, or unmount filesystems so if you need * that to happen you need to do that yourself. */ -struct kimage *kexec_image = NULL; -static struct kimage *kexec_crash_image = NULL; +struct kimage *kexec_image; +struct kimage *kexec_crash_image; /* * A home grown binary mutex. * Nothing can wait so this mutex is safe to use * in interrupt context :) */ -static int kexec_lock = 0; +static int kexec_lock; asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment __user *segments, diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index f119e09..9e28478 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -14,6 +14,7 @@ #include <linux/sysfs.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/kexec.h> #define KERNEL_ATTR_RO(_name) \ static struct subsys_attribute _name##_attr = __ATTR_RO(_name) @@ -48,6 +49,20 @@ static ssize_t uevent_helper_store(struct subsystem *subsys, const char *page, s KERNEL_ATTR_RW(uevent_helper); #endif +#ifdef CONFIG_KEXEC +static ssize_t kexec_loaded_show(struct subsystem *subsys, char *page) +{ + return sprintf(page, "%d\n", !!kexec_image); +} +KERNEL_ATTR_RO(kexec_loaded); + +static ssize_t kexec_crash_loaded_show(struct subsystem *subsys, char *page) +{ + return sprintf(page, "%d\n", !!kexec_crash_image); +} +KERNEL_ATTR_RO(kexec_crash_loaded); +#endif /* CONFIG_KEXEC */ + decl_subsys(kernel, NULL, NULL); EXPORT_SYMBOL_GPL(kernel_subsys); @@ -56,6 +71,10 @@ static struct attribute * kernel_attrs[] = { &uevent_seqnum_attr.attr, &uevent_helper_attr.attr, #endif +#ifdef CONFIG_KEXEC + &kexec_loaded_attr.attr, + &kexec_crash_loaded_attr.attr, +#endif NULL }; diff --git a/kernel/power/main.c b/kernel/power/main.c index 0a907f0..cdf0f07 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -15,7 +15,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/pm.h> - +#include <linux/console.h> #include "power.h" diff --git a/kernel/power/power.h b/kernel/power/power.h index f06f12f..98c4142 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -55,7 +55,7 @@ struct snapshot_handle { unsigned int page; unsigned int page_offset; unsigned int prev; - struct pbe *pbe; + struct pbe *pbe, *last_pbe; void *buffer; unsigned int buf_offset; }; @@ -105,6 +105,10 @@ extern struct bitmap_page *alloc_bitmap(unsigned int nr_bits); extern unsigned long alloc_swap_page(int swap, struct bitmap_page *bitmap); extern void free_all_swap_pages(int swap, struct bitmap_page *bitmap); +extern unsigned int count_special_pages(void); +extern int save_special_mem(void); +extern int restore_special_mem(void); + extern int swsusp_check(void); extern int swsusp_shrink_memory(void); extern void swsusp_free(void); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3eeedbb..3d92841 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -39,8 +39,90 @@ static unsigned int nr_copy_pages; static unsigned int nr_meta_pages; static unsigned long *buffer; +struct arch_saveable_page { + unsigned long start; + unsigned long end; + char *data; + struct arch_saveable_page *next; +}; +static struct arch_saveable_page *arch_pages; + +int swsusp_add_arch_pages(unsigned long start, unsigned long end) +{ + struct arch_saveable_page *tmp; + + while (start < end) { + tmp = kzalloc(sizeof(struct arch_saveable_page), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + tmp->start = start; + tmp->end = ((start >> PAGE_SHIFT) + 1) << PAGE_SHIFT; + if (tmp->end > end) + tmp->end = end; + tmp->next = arch_pages; + start = tmp->end; + arch_pages = tmp; + } + return 0; +} + +static unsigned int count_arch_pages(void) +{ + unsigned int count = 0; + struct arch_saveable_page *tmp = arch_pages; + while (tmp) { + count++; + tmp = tmp->next; + } + return count; +} + +static int save_arch_mem(void) +{ + char *kaddr; + struct arch_saveable_page *tmp = arch_pages; + int offset; + + pr_debug("swsusp: Saving arch specific memory"); + while (tmp) { + tmp->data = (char *)__get_free_page(GFP_ATOMIC); + if (!tmp->data) + return -ENOMEM; + offset = tmp->start - (tmp->start & PAGE_MASK); + /* arch pages might haven't a 'struct page' */ + kaddr = kmap_atomic_pfn(tmp->start >> PAGE_SHIFT, KM_USER0); + memcpy(tmp->data + offset, kaddr + offset, + tmp->end - tmp->start); + kunmap_atomic(kaddr, KM_USER0); + + tmp = tmp->next; + } + return 0; +} + +static int restore_arch_mem(void) +{ + char *kaddr; + struct arch_saveable_page *tmp = arch_pages; + int offset; + + while (tmp) { + if (!tmp->data) + continue; + offset = tmp->start - (tmp->start & PAGE_MASK); + kaddr = kmap_atomic_pfn(tmp->start >> PAGE_SHIFT, KM_USER0); + memcpy(kaddr + offset, tmp->data + offset, + tmp->end - tmp->start); + kunmap_atomic(kaddr, KM_USER0); + free_page((long)tmp->data); + tmp->data = NULL; + tmp = tmp->next; + } + return 0; +} + #ifdef CONFIG_HIGHMEM -unsigned int count_highmem_pages(void) +static unsigned int count_highmem_pages(void) { struct zone *zone; unsigned long zone_pfn; @@ -117,7 +199,7 @@ static int save_highmem_zone(struct zone *zone) return 0; } -int save_highmem(void) +static int save_highmem(void) { struct zone *zone; int res = 0; @@ -134,7 +216,7 @@ int save_highmem(void) return 0; } -int restore_highmem(void) +static int restore_highmem(void) { printk("swsusp: Restoring Highmem\n"); while (highmem_copy) { @@ -150,8 +232,35 @@ int restore_highmem(void) } return 0; } +#else +static inline unsigned int count_highmem_pages(void) {return 0;} +static inline int save_highmem(void) {return 0;} +static inline int restore_highmem(void) {return 0;} #endif +unsigned int count_special_pages(void) +{ + return count_arch_pages() + count_highmem_pages(); +} + +int save_special_mem(void) +{ + int ret; + ret = save_arch_mem(); + if (!ret) + ret = save_highmem(); + return ret; +} + +int restore_special_mem(void) +{ + int ret; + ret = restore_arch_mem(); + if (!ret) + ret = restore_highmem(); + return ret; +} + static int pfn_is_nosave(unsigned long pfn) { unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT; @@ -177,7 +286,6 @@ static int saveable(struct zone *zone, unsigned long *zone_pfn) return 0; page = pfn_to_page(pfn); - BUG_ON(PageReserved(page) && PageNosave(page)); if (PageNosave(page)) return 0; if (PageReserved(page) && pfn_is_nosave(pfn)) @@ -293,62 +401,29 @@ static inline void create_pbe_list(struct pbe *pblist, unsigned int nr_pages) } } -/** - * On resume it is necessary to trace and eventually free the unsafe - * pages that have been allocated, because they are needed for I/O - * (on x86-64 we likely will "eat" these pages once again while - * creating the temporary page translation tables) - */ - -struct eaten_page { - struct eaten_page *next; - char padding[PAGE_SIZE - sizeof(void *)]; -}; - -static struct eaten_page *eaten_pages = NULL; - -static void release_eaten_pages(void) -{ - struct eaten_page *p, *q; - - p = eaten_pages; - while (p) { - q = p->next; - /* We don't want swsusp_free() to free this page again */ - ClearPageNosave(virt_to_page(p)); - free_page((unsigned long)p); - p = q; - } - eaten_pages = NULL; -} +static unsigned int unsafe_pages; /** * @safe_needed - on resume, for storing the PBE list and the image, * we can only use memory pages that do not conflict with the pages - * which had been used before suspend. + * used before suspend. * * The unsafe pages are marked with the PG_nosave_free flag - * - * Allocated but unusable (ie eaten) memory pages should be marked - * so that swsusp_free() can release them + * and we count them using unsafe_pages */ static inline void *alloc_image_page(gfp_t gfp_mask, int safe_needed) { void *res; + res = (void *)get_zeroed_page(gfp_mask); if (safe_needed) - do { + while (res && PageNosaveFree(virt_to_page(res))) { + /* The page is unsafe, mark it for swsusp_free() */ + SetPageNosave(virt_to_page(res)); + unsafe_pages++; res = (void *)get_zeroed_page(gfp_mask); - if (res && PageNosaveFree(virt_to_page(res))) { - /* This is for swsusp_free() */ - SetPageNosave(virt_to_page(res)); - ((struct eaten_page *)res)->next = eaten_pages; - eaten_pages = res; - } - } while (res && PageNosaveFree(virt_to_page(res))); - else - res = (void *)get_zeroed_page(gfp_mask); + } if (res) { SetPageNosave(virt_to_page(res)); SetPageNosaveFree(virt_to_page(res)); @@ -374,7 +449,8 @@ unsigned long get_safe_page(gfp_t gfp_mask) * On each page we set up a list of struct_pbe elements. */ -struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed) +static struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, + int safe_needed) { unsigned int num; struct pbe *pblist, *pbe; @@ -642,6 +718,8 @@ static int mark_unsafe_pages(struct pbe *pblist) return -EFAULT; } + unsafe_pages = 0; + return 0; } @@ -719,42 +797,99 @@ static inline struct pbe *unpack_orig_addresses(unsigned long *buf, } /** - * create_image - use metadata contained in the PBE list + * prepare_image - use metadata contained in the PBE list * pointed to by pagedir_nosave to mark the pages that will * be overwritten in the process of restoring the system - * memory state from the image and allocate memory for - * the image avoiding these pages + * memory state from the image ("unsafe" pages) and allocate + * memory for the image + * + * The idea is to allocate the PBE list first and then + * allocate as many pages as it's needed for the image data, + * but not to assign these pages to the PBEs initially. + * Instead, we just mark them as allocated and create a list + * of "safe" which will be used later */ -static int create_image(struct snapshot_handle *handle) +struct safe_page { + struct safe_page *next; + char padding[PAGE_SIZE - sizeof(void *)]; +}; + +static struct safe_page *safe_pages; + +static int prepare_image(struct snapshot_handle *handle) { int error = 0; - struct pbe *p, *pblist; + unsigned int nr_pages = nr_copy_pages; + struct pbe *p, *pblist = NULL; p = pagedir_nosave; error = mark_unsafe_pages(p); if (!error) { - pblist = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 1); + pblist = alloc_pagedir(nr_pages, GFP_ATOMIC, 1); if (pblist) copy_page_backup_list(pblist, p); free_pagedir(p, 0); if (!pblist) error = -ENOMEM; } - if (!error) - error = alloc_data_pages(pblist, GFP_ATOMIC, 1); + safe_pages = NULL; + if (!error && nr_pages > unsafe_pages) { + nr_pages -= unsafe_pages; + while (nr_pages--) { + struct safe_page *ptr; + + ptr = (struct safe_page *)get_zeroed_page(GFP_ATOMIC); + if (!ptr) { + error = -ENOMEM; + break; + } + if (!PageNosaveFree(virt_to_page(ptr))) { + /* The page is "safe", add it to the list */ + ptr->next = safe_pages; + safe_pages = ptr; + } + /* Mark the page as allocated */ + SetPageNosave(virt_to_page(ptr)); + SetPageNosaveFree(virt_to_page(ptr)); + } + } if (!error) { - release_eaten_pages(); pagedir_nosave = pblist; } else { - pagedir_nosave = NULL; handle->pbe = NULL; - nr_copy_pages = 0; - nr_meta_pages = 0; + swsusp_free(); } return error; } +static void *get_buffer(struct snapshot_handle *handle) +{ + struct pbe *pbe = handle->pbe, *last = handle->last_pbe; + struct page *page = virt_to_page(pbe->orig_address); + + if (PageNosave(page) && PageNosaveFree(page)) { + /* + * We have allocated the "original" page frame and we can + * use it directly to store the read page + */ + pbe->address = 0; + if (last && last->next) + last->next = NULL; + return (void *)pbe->orig_address; + } + /* + * The "original" page frame has not been allocated and we have to + * use a "safe" page frame to store the read page + */ + pbe->address = (unsigned long)safe_pages; + safe_pages = safe_pages->next; + if (last) + last->next = pbe; + handle->last_pbe = pbe; + return (void *)pbe->address; +} + /** * snapshot_write_next - used for writing the system memory snapshot. * @@ -799,15 +934,16 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count) } else if (handle->prev <= nr_meta_pages) { handle->pbe = unpack_orig_addresses(buffer, handle->pbe); if (!handle->pbe) { - error = create_image(handle); + error = prepare_image(handle); if (error) return error; handle->pbe = pagedir_nosave; - handle->buffer = (void *)handle->pbe->address; + handle->last_pbe = NULL; + handle->buffer = get_buffer(handle); } } else { handle->pbe = handle->pbe->next; - handle->buffer = (void *)handle->pbe->address; + handle->buffer = get_buffer(handle); } handle->prev = handle->page; } diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index c4016cb..f0ee4e7 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -62,16 +62,6 @@ unsigned long image_size = 500 * 1024 * 1024; int in_suspend __nosavedata = 0; -#ifdef CONFIG_HIGHMEM -unsigned int count_highmem_pages(void); -int save_highmem(void); -int restore_highmem(void); -#else -static int save_highmem(void) { return 0; } -static int restore_highmem(void) { return 0; } -static unsigned int count_highmem_pages(void) { return 0; } -#endif - /** * The following functions are used for tracing the allocated * swap pages, so that they can be freed in case of an error. @@ -175,6 +165,12 @@ void free_all_swap_pages(int swap, struct bitmap_page *bitmap) */ #define SHRINK_BITE 10000 +static inline unsigned long __shrink_memory(long tmp) +{ + if (tmp > SHRINK_BITE) + tmp = SHRINK_BITE; + return shrink_all_memory(tmp); +} int swsusp_shrink_memory(void) { @@ -186,21 +182,23 @@ int swsusp_shrink_memory(void) printk("Shrinking memory... "); do { - size = 2 * count_highmem_pages(); + size = 2 * count_special_pages(); size += size / 50 + count_data_pages(); size += (size + PBES_PER_PAGE - 1) / PBES_PER_PAGE + PAGES_FOR_IO; tmp = size; for_each_zone (zone) - if (!is_highmem(zone)) + if (!is_highmem(zone) && populated_zone(zone)) { tmp -= zone->free_pages; + tmp += zone->lowmem_reserve[ZONE_NORMAL]; + } if (tmp > 0) { - tmp = shrink_all_memory(SHRINK_BITE); + tmp = __shrink_memory(tmp); if (!tmp) return -ENOMEM; pages += tmp; } else if (size > image_size / PAGE_SIZE) { - tmp = shrink_all_memory(SHRINK_BITE); + tmp = __shrink_memory(size - (image_size / PAGE_SIZE)); pages += tmp; } printk("\b%c", p[i++%4]); @@ -228,7 +226,7 @@ int swsusp_suspend(void) goto Enable_irqs; } - if ((error = save_highmem())) { + if ((error = save_special_mem())) { printk(KERN_ERR "swsusp: Not enough free pages for highmem\n"); goto Restore_highmem; } @@ -239,7 +237,7 @@ int swsusp_suspend(void) /* Restore control flow magically appears here */ restore_processor_state(); Restore_highmem: - restore_highmem(); + restore_special_mem(); device_power_up(); Enable_irqs: local_irq_enable(); @@ -265,7 +263,7 @@ int swsusp_resume(void) */ swsusp_free(); restore_processor_state(); - restore_highmem(); + restore_special_mem(); touch_softlockup_watchdog(); device_power_up(); local_irq_enable(); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 2058f88..20e9710 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -612,14 +612,6 @@ void synchronize_rcu(void) wait_for_completion(&rcu.completion); } -/* - * Deprecated, use synchronize_rcu() or synchronize_sched() instead. - */ -void synchronize_kernel(void) -{ - synchronize_rcu(); -} - module_param(blimit, int, 0); module_param(qhimark, int, 0); module_param(qlowmark, int, 0); @@ -627,7 +619,6 @@ module_param(qlowmark, int, 0); module_param(rsinterval, int, 0); #endif EXPORT_SYMBOL_GPL(rcu_batches_completed); -EXPORT_SYMBOL_GPL_FUTURE(call_rcu); /* WARNING: GPL-only in April 2006. */ -EXPORT_SYMBOL_GPL_FUTURE(call_rcu_bh); /* WARNING: GPL-only in April 2006. */ +EXPORT_SYMBOL_GPL(call_rcu); +EXPORT_SYMBOL_GPL(call_rcu_bh); EXPORT_SYMBOL_GPL(synchronize_rcu); -EXPORT_SYMBOL_GPL_FUTURE(synchronize_kernel); /* WARNING: GPL-only in April 2006. */ diff --git a/kernel/sched.c b/kernel/sched.c index c13f1bd..5dbc426 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3886,6 +3886,10 @@ long sched_setaffinity(pid_t pid, cpumask_t new_mask) !capable(CAP_SYS_NICE)) goto out_unlock; + retval = security_task_setscheduler(p, 0, NULL); + if (retval) + goto out_unlock; + cpus_allowed = cpuset_cpus_allowed(p); cpus_and(new_mask, new_mask, cpus_allowed); retval = set_cpus_allowed(p, new_mask); @@ -3954,7 +3958,10 @@ long sched_getaffinity(pid_t pid, cpumask_t *mask) if (!p) goto out_unlock; - retval = 0; + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + cpus_and(*mask, p->cpus_allowed, cpu_online_map); out_unlock: @@ -4046,6 +4053,9 @@ asmlinkage long sys_sched_yield(void) static inline void __cond_resched(void) { +#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP + __might_sleep(__FILE__, __LINE__); +#endif /* * The BKS might be reacquired before we have dropped * PREEMPT_ACTIVE, which could trigger a second diff --git a/kernel/sys.c b/kernel/sys.c index 0b6ec0e..90930b2 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -13,7 +13,6 @@ #include <linux/notifier.h> #include <linux/reboot.h> #include <linux/prctl.h> -#include <linux/init.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/kernel.h> @@ -57,6 +56,12 @@ #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a,b) (-EINVAL) #endif +#ifndef GET_ENDIAN +# define GET_ENDIAN(a,b) (-EINVAL) +#endif +#ifndef SET_ENDIAN +# define SET_ENDIAN(a,b) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -1860,23 +1865,20 @@ out: * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. * - * tasklist_lock locking optimisation: - * If we are current and single threaded, we do not need to take the tasklist - * lock or the siglock. No one else can take our signal_struct away, - * no one else can reap the children to update signal->c* counters, and - * no one else can race with the signal-> fields. - * If we do not take the tasklist_lock, the signal-> fields could be read - * out of order while another thread was just exiting. So we place a - * read memory barrier when we avoid the lock. On the writer side, - * write memory barrier is implied in __exit_signal as __exit_signal releases - * the siglock spinlock after updating the signal-> fields. - * - * We don't really need the siglock when we access the non c* fields - * of the signal_struct (for RUSAGE_SELF) even in multithreaded - * case, since we take the tasklist lock for read and the non c* signal-> - * fields are updated only in __exit_signal, which is called with - * tasklist_lock taken for write, hence these two threads cannot execute - * concurrently. + * Locking: + * We need to take the siglock for CHILDEREN, SELF and BOTH + * for the cases current multithreaded, non-current single threaded + * non-current multithreaded. Thread traversal is now safe with + * the siglock held. + * Strictly speaking, we donot need to take the siglock if we are current and + * single threaded, as no one else can take our signal_struct away, no one + * else can reap the children to update signal->c* counters, and no one else + * can race with the signal-> fields. If we do not take any lock, the + * signal-> fields could be read out of order while another thread was just + * exiting. So we should place a read memory barrier when we avoid the lock. + * On the writer side, write memory barrier is implied in __exit_signal + * as __exit_signal releases the siglock spinlock after updating the signal-> + * fields. But we don't do this yet to keep things simple. * */ @@ -1885,35 +1887,25 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; cputime_t utime, stime; - int need_lock = 0; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; - if (p != current || !thread_group_empty(p)) - need_lock = 1; - - if (need_lock) { - read_lock(&tasklist_lock); - if (unlikely(!p->signal)) { - read_unlock(&tasklist_lock); - return; - } - } else - /* See locking comments above */ - smp_rmb(); + rcu_read_lock(); + if (!lock_task_sighand(p, &flags)) { + rcu_read_unlock(); + return; + } switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: - spin_lock_irqsave(&p->sighand->siglock, flags); utime = p->signal->cutime; stime = p->signal->cstime; r->ru_nvcsw = p->signal->cnvcsw; r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; - spin_unlock_irqrestore(&p->sighand->siglock, flags); if (who == RUSAGE_CHILDREN) break; @@ -1941,8 +1933,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) BUG(); } - if (need_lock) - read_unlock(&tasklist_lock); + unlock_task_sighand(p, &flags); + rcu_read_unlock(); + cputime_to_timeval(utime, &r->ru_utime); cputime_to_timeval(stime, &r->ru_stime); } @@ -2057,6 +2050,13 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, return -EFAULT; return 0; } + case PR_GET_ENDIAN: + error = GET_ENDIAN(current, arg2); + break; + case PR_SET_ENDIAN: + error = SET_ENDIAN(current, arg2); + break; + default: error = -EINVAL; break; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 5433195..6991bec 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -87,6 +87,7 @@ cond_syscall(sys_inotify_init); cond_syscall(sys_inotify_add_watch); cond_syscall(sys_inotify_rm_watch); cond_syscall(sys_migrate_pages); +cond_syscall(sys_move_pages); cond_syscall(sys_chown16); cond_syscall(sys_fchown16); cond_syscall(sys_getegid16); @@ -132,3 +133,4 @@ cond_syscall(sys_mincore); cond_syscall(sys_madvise); cond_syscall(sys_mremap); cond_syscall(sys_remap_file_pages); +cond_syscall(compat_sys_move_pages); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0d656e6..eb8bd21 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -59,6 +59,7 @@ extern int proc_nr_files(ctl_table *table, int write, struct file *filp, extern int C_A_D; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; +extern int sysctl_panic_on_oom; extern int max_threads; extern int sysrq_enabled; extern int core_uses_pid; @@ -398,7 +399,7 @@ static ctl_table kern_table[] = { .strategy = &sysctl_string, }, #endif -#ifdef CONFIG_HOTPLUG +#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) { .ctl_name = KERN_HOTPLUG, .procname = "hotplug", @@ -702,6 +703,14 @@ static ctl_table vm_table[] = { .proc_handler = &proc_dointvec, }, { + .ctl_name = VM_PANIC_ON_OOM, + .procname = "panic_on_oom", + .data = &sysctl_panic_on_oom, + .maxlen = sizeof(sysctl_panic_on_oom), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = VM_OVERCOMMIT_RATIO, .procname = "overcommit_ratio", .data = &sysctl_overcommit_ratio, diff --git a/kernel/timer.c b/kernel/timer.c index 9e49dee..f35b393 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -383,23 +383,19 @@ EXPORT_SYMBOL(del_timer_sync); static int cascade(tvec_base_t *base, tvec_t *tv, int index) { /* cascade all the timers from tv up one level */ - struct list_head *head, *curr; + struct timer_list *timer, *tmp; + struct list_head tv_list; + + list_replace_init(tv->vec + index, &tv_list); - head = tv->vec + index; - curr = head->next; /* - * We are removing _all_ timers from the list, so we don't have to - * detach them individually, just clear the list afterwards. + * We are removing _all_ timers from the list, so we + * don't have to detach them individually. */ - while (curr != head) { - struct timer_list *tmp; - - tmp = list_entry(curr, struct timer_list, entry); - BUG_ON(tmp->base != base); - curr = curr->next; - internal_add_timer(base, tmp); + list_for_each_entry_safe(timer, tmp, &tv_list, entry) { + BUG_ON(timer->base != base); + internal_add_timer(base, timer); } - INIT_LIST_HEAD(head); return index; } @@ -419,10 +415,10 @@ static inline void __run_timers(tvec_base_t *base) spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->timer_jiffies)) { - struct list_head work_list = LIST_HEAD_INIT(work_list); + struct list_head work_list; struct list_head *head = &work_list; int index = base->timer_jiffies & TVR_MASK; - + /* * Cascade timers: */ @@ -431,8 +427,8 @@ static inline void __run_timers(tvec_base_t *base) (!cascade(base, &base->tv3, INDEX(1))) && !cascade(base, &base->tv4, INDEX(2))) cascade(base, &base->tv5, INDEX(3)); - ++base->timer_jiffies; - list_splice_init(base->tv1.vec + index, &work_list); + ++base->timer_jiffies; + list_replace_init(base->tv1.vec + index, &work_list); while (!list_empty(head)) { void (*fn)(unsigned long); unsigned long data; diff --git a/kernel/user.c b/kernel/user.c index 4b1eb74..6408c04 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -148,7 +148,7 @@ struct user_struct * alloc_uid(uid_t uid) new->mq_bytes = 0; new->locked_shm = 0; - if (alloc_uid_keyring(new) < 0) { + if (alloc_uid_keyring(new, current) < 0) { kmem_cache_free(uid_cachep, new); return NULL; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 880fb41..740c5ab 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -531,11 +531,11 @@ int current_is_keventd(void) static void take_over_work(struct workqueue_struct *wq, unsigned int cpu) { struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu); - LIST_HEAD(list); + struct list_head list; struct work_struct *work; spin_lock_irq(&cwq->lock); - list_splice_init(&cwq->worklist, &list); + list_replace_init(&cwq->worklist, &list); while (!list_empty(&list)) { printk("Taking work for %s\n", wq->name); |