diff options
Diffstat (limited to 'kernel')
33 files changed, 1544 insertions, 312 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 6aebdeb2aa34..7b974699f8c2 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -10,7 +10,8 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ - async.o + async.o range.o +obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 4b05bd9479db..028e85663f27 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -548,6 +548,11 @@ int audit_remove_tree_rule(struct audit_krule *rule) return 0; } +static int compare_root(struct vfsmount *mnt, void *arg) +{ + return mnt->mnt_root->d_inode == arg; +} + void audit_trim_trees(void) { struct list_head cursor; @@ -559,7 +564,6 @@ void audit_trim_trees(void) struct path path; struct vfsmount *root_mnt; struct node *node; - struct list_head list; int err; tree = container_of(cursor.next, struct audit_tree, list); @@ -577,24 +581,16 @@ void audit_trim_trees(void) if (!root_mnt) goto skip_it; - list_add_tail(&list, &root_mnt->mnt_list); spin_lock(&hash_lock); list_for_each_entry(node, &tree->chunks, list) { - struct audit_chunk *chunk = find_chunk(node); - struct inode *inode = chunk->watch.inode; - struct vfsmount *mnt; + struct inode *inode = find_chunk(node)->watch.inode; node->index |= 1U<<31; - list_for_each_entry(mnt, &list, mnt_list) { - if (mnt->mnt_root->d_inode == inode) { - node->index &= ~(1U<<31); - break; - } - } + if (iterate_mounts(compare_root, inode, root_mnt)) + node->index &= ~(1U<<31); } spin_unlock(&hash_lock); trim_marked(tree); put_tree(tree); - list_del_init(&list); drop_collected_mounts(root_mnt); skip_it: mutex_lock(&audit_filter_mutex); @@ -603,22 +599,6 @@ skip_it: mutex_unlock(&audit_filter_mutex); } -static int is_under(struct vfsmount *mnt, struct dentry *dentry, - struct path *path) -{ - if (mnt != path->mnt) { - for (;;) { - if (mnt->mnt_parent == mnt) - return 0; - if (mnt->mnt_parent == path->mnt) - break; - mnt = mnt->mnt_parent; - } - dentry = mnt->mnt_mountpoint; - } - return is_subdir(dentry, path->dentry); -} - int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) { @@ -638,13 +618,17 @@ void audit_put_tree(struct audit_tree *tree) put_tree(tree); } +static int tag_mount(struct vfsmount *mnt, void *arg) +{ + return tag_chunk(mnt->mnt_root->d_inode, arg); +} + /* called with audit_filter_mutex */ int audit_add_tree_rule(struct audit_krule *rule) { struct audit_tree *seed = rule->tree, *tree; struct path path; - struct vfsmount *mnt, *p; - struct list_head list; + struct vfsmount *mnt; int err; list_for_each_entry(tree, &tree_list, list) { @@ -670,16 +654,9 @@ int audit_add_tree_rule(struct audit_krule *rule) err = -ENOMEM; goto Err; } - list_add_tail(&list, &mnt->mnt_list); get_tree(tree); - list_for_each_entry(p, &list, mnt_list) { - err = tag_chunk(p->mnt_root->d_inode, tree); - if (err) - break; - } - - list_del(&list); + err = iterate_mounts(tag_mount, tree, mnt); drop_collected_mounts(mnt); if (!err) { @@ -714,31 +691,23 @@ int audit_tag_tree(char *old, char *new) { struct list_head cursor, barrier; int failed = 0; - struct path path; + struct path path1, path2; struct vfsmount *tagged; - struct list_head list; - struct vfsmount *mnt; - struct dentry *dentry; int err; - err = kern_path(new, 0, &path); + err = kern_path(new, 0, &path2); if (err) return err; - tagged = collect_mounts(&path); - path_put(&path); + tagged = collect_mounts(&path2); + path_put(&path2); if (!tagged) return -ENOMEM; - err = kern_path(old, 0, &path); + err = kern_path(old, 0, &path1); if (err) { drop_collected_mounts(tagged); return err; } - mnt = mntget(path.mnt); - dentry = dget(path.dentry); - path_put(&path); - - list_add_tail(&list, &tagged->mnt_list); mutex_lock(&audit_filter_mutex); list_add(&barrier, &tree_list); @@ -746,7 +715,7 @@ int audit_tag_tree(char *old, char *new) while (cursor.next != &tree_list) { struct audit_tree *tree; - struct vfsmount *p; + int good_one = 0; tree = container_of(cursor.next, struct audit_tree, list); get_tree(tree); @@ -754,30 +723,19 @@ int audit_tag_tree(char *old, char *new) list_add(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); - err = kern_path(tree->pathname, 0, &path); - if (err) { - put_tree(tree); - mutex_lock(&audit_filter_mutex); - continue; + err = kern_path(tree->pathname, 0, &path2); + if (!err) { + good_one = path_is_under(&path1, &path2); + path_put(&path2); } - spin_lock(&vfsmount_lock); - if (!is_under(mnt, dentry, &path)) { - spin_unlock(&vfsmount_lock); - path_put(&path); + if (!good_one) { put_tree(tree); mutex_lock(&audit_filter_mutex); continue; } - spin_unlock(&vfsmount_lock); - path_put(&path); - - list_for_each_entry(p, &list, mnt_list) { - failed = tag_chunk(p->mnt_root->d_inode, tree); - if (failed) - break; - } + failed = iterate_mounts(tag_mount, tree, tagged); if (failed) { put_tree(tree); mutex_lock(&audit_filter_mutex); @@ -818,10 +776,8 @@ int audit_tag_tree(char *old, char *new) } list_del(&barrier); list_del(&cursor); - list_del(&list); mutex_unlock(&audit_filter_mutex); - dput(dentry); - mntput(mnt); + path_put(&path1); drop_collected_mounts(tagged); return failed; } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index fc0f928167e7..f3a461c0970a 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1988,7 +1988,6 @@ void __audit_inode(const char *name, const struct dentry *dentry) /** * audit_inode_child - collect inode info for created/removed objects - * @dname: inode's dentry name * @dentry: dentry being audited * @parent: inode of dentry parent * @@ -2000,13 +1999,14 @@ void __audit_inode(const char *name, const struct dentry *dentry) * must be hooked prior, in order to capture the target inode during * unsuccessful attempts. */ -void __audit_inode_child(const char *dname, const struct dentry *dentry, +void __audit_inode_child(const struct dentry *dentry, const struct inode *parent) { int idx; struct audit_context *context = current->audit_context; const char *found_parent = NULL, *found_child = NULL; const struct inode *inode = dentry->d_inode; + const char *dname = dentry->d_name.name; int dirlen = 0; if (!context->in_syscall) @@ -2014,9 +2014,6 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry, if (inode) handle_one(inode); - /* determine matching parent */ - if (!dname) - goto add_names; /* parent is more likely, look for it first */ for (idx = 0; idx < context->name_count; idx++) { diff --git a/kernel/capability.c b/kernel/capability.c index 7f876e60521f..9e4697e9b276 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -135,7 +135,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; - read_lock(&tasklist_lock); + rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) @@ -143,7 +143,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, else ret = security_capget(target, pEp, pIp, pPp); - read_unlock(&tasklist_lock); + rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); diff --git a/kernel/early_res.c b/kernel/early_res.c new file mode 100644 index 000000000000..3cb2c661bb78 --- /dev/null +++ b/kernel/early_res.c @@ -0,0 +1,578 @@ +/* + * early_res, could be used to replace bootmem + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/mm.h> +#include <linux/early_res.h> + +/* + * Early reserved memory areas. + */ +/* + * need to make sure this one is bigger enough before + * find_fw_memmap_area could be used + */ +#define MAX_EARLY_RES_X 32 + +struct early_res { + u64 start, end; + char name[15]; + char overlap_ok; +}; +static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata; + +static int max_early_res __initdata = MAX_EARLY_RES_X; +static struct early_res *early_res __initdata = &early_res_x[0]; +static int early_res_count __initdata; + +static int __init find_overlapped_early(u64 start, u64 end) +{ + int i; + struct early_res *r; + + for (i = 0; i < max_early_res && early_res[i].end; i++) { + r = &early_res[i]; + if (end > r->start && start < r->end) + break; + } + + return i; +} + +/* + * Drop the i-th range from the early reservation map, + * by copying any higher ranges down one over it, and + * clearing what had been the last slot. + */ +static void __init drop_range(int i) +{ + int j; + + for (j = i + 1; j < max_early_res && early_res[j].end; j++) + ; + + memmove(&early_res[i], &early_res[i + 1], + (j - 1 - i) * sizeof(struct early_res)); + + early_res[j - 1].end = 0; + early_res_count--; +} + +static void __init drop_range_partial(int i, u64 start, u64 end) +{ + u64 common_start, common_end; + u64 old_start, old_end; + + old_start = early_res[i].start; + old_end = early_res[i].end; + common_start = max(old_start, start); + common_end = min(old_end, end); + + /* no overlap ? */ + if (common_start >= common_end) + return; + + if (old_start < common_start) { + /* make head segment */ + early_res[i].end = common_start; + if (old_end > common_end) { + char name[15]; + + /* + * Save a local copy of the name, since the + * early_res array could get resized inside + * reserve_early_without_check() -> + * __check_and_double_early_res(), which would + * make the current name pointer invalid. + */ + strncpy(name, early_res[i].name, + sizeof(early_res[i].name) - 1); + /* add another for left over on tail */ + reserve_early_without_check(common_end, old_end, name); + } + return; + } else { + if (old_end > common_end) { + /* reuse the entry for tail left */ + early_res[i].start = common_end; + return; + } + /* all covered */ + drop_range(i); + } +} + +/* + * Split any existing ranges that: + * 1) are marked 'overlap_ok', and + * 2) overlap with the stated range [start, end) + * into whatever portion (if any) of the existing range is entirely + * below or entirely above the stated range. Drop the portion + * of the existing range that overlaps with the stated range, + * which will allow the caller of this routine to then add that + * stated range without conflicting with any existing range. + */ +static void __init drop_overlaps_that_are_ok(u64 start, u64 end) +{ + int i; + struct early_res *r; + u64 lower_start, lower_end; + u64 upper_start, upper_end; + char name[15]; + + for (i = 0; i < max_early_res && early_res[i].end; i++) { + r = &early_res[i]; + + /* Continue past non-overlapping ranges */ + if (end <= r->start || start >= r->end) + continue; + + /* + * Leave non-ok overlaps as is; let caller + * panic "Overlapping early reservations" + * when it hits this overlap. + */ + if (!r->overlap_ok) + return; + + /* + * We have an ok overlap. We will drop it from the early + * reservation map, and add back in any non-overlapping + * portions (lower or upper) as separate, overlap_ok, + * non-overlapping ranges. + */ + + /* 1. Note any non-overlapping (lower or upper) ranges. */ + strncpy(name, r->name, sizeof(name) - 1); + + lower_start = lower_end = 0; + upper_start = upper_end = 0; + if (r->start < start) { + lower_start = r->start; + lower_end = start; + } + if (r->end > end) { + upper_start = end; + upper_end = r->end; + } + + /* 2. Drop the original ok overlapping range */ + drop_range(i); + + i--; /* resume for-loop on copied down entry */ + + /* 3. Add back in any non-overlapping ranges. */ + if (lower_end) + reserve_early_overlap_ok(lower_start, lower_end, name); + if (upper_end) + reserve_early_overlap_ok(upper_start, upper_end, name); + } +} + +static void __init __reserve_early(u64 start, u64 end, char *name, + int overlap_ok) +{ + int i; + struct early_res *r; + + i = find_overlapped_early(start, end); + if (i >= max_early_res) + panic("Too many early reservations"); + r = &early_res[i]; + if (r->end) + panic("Overlapping early reservations " + "%llx-%llx %s to %llx-%llx %s\n", + start, end - 1, name ? name : "", r->start, + r->end - 1, r->name); + r->start = start; + r->end = end; + r->overlap_ok = overlap_ok; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); + early_res_count++; +} + +/* + * A few early reservtations come here. + * + * The 'overlap_ok' in the name of this routine does -not- mean it + * is ok for these reservations to overlap an earlier reservation. + * Rather it means that it is ok for subsequent reservations to + * overlap this one. + * + * Use this entry point to reserve early ranges when you are doing + * so out of "Paranoia", reserving perhaps more memory than you need, + * just in case, and don't mind a subsequent overlapping reservation + * that is known to be needed. + * + * The drop_overlaps_that_are_ok() call here isn't really needed. + * It would be needed if we had two colliding 'overlap_ok' + * reservations, so that the second such would not panic on the + * overlap with the first. We don't have any such as of this + * writing, but might as well tolerate such if it happens in + * the future. + */ +void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 1); +} + +static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end) +{ + u64 start, end, size, mem; + struct early_res *new; + + /* do we have enough slots left ? */ + if ((max_early_res - early_res_count) > max(max_early_res/8, 2)) + return; + + /* double it */ + mem = -1ULL; + size = sizeof(struct early_res) * max_early_res * 2; + if (early_res == early_res_x) + start = 0; + else + start = early_res[0].end; + end = ex_start; + if (start + size < end) + mem = find_fw_memmap_area(start, end, size, + sizeof(struct early_res)); + if (mem == -1ULL) { + start = ex_end; + end = get_max_mapped(); + if (start + size < end) + mem = find_fw_memmap_area(start, end, size, + sizeof(struct early_res)); + } + if (mem == -1ULL) + panic("can not find more space for early_res array"); + + new = __va(mem); + /* save the first one for own */ + new[0].start = mem; + new[0].end = mem + size; + new[0].overlap_ok = 0; + /* copy old to new */ + if (early_res == early_res_x) { + memcpy(&new[1], &early_res[0], + sizeof(struct early_res) * max_early_res); + memset(&new[max_early_res+1], 0, + sizeof(struct early_res) * (max_early_res - 1)); + early_res_count++; + } else { + memcpy(&new[1], &early_res[1], + sizeof(struct early_res) * (max_early_res - 1)); + memset(&new[max_early_res], 0, + sizeof(struct early_res) * max_early_res); + } + memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); + early_res = new; + max_early_res *= 2; + printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n", + max_early_res, mem, mem + size - 1); +} + +/* + * Most early reservations come here. + * + * We first have drop_overlaps_that_are_ok() drop any pre-existing + * 'overlap_ok' ranges, so that we can then reserve this memory + * range without risk of panic'ing on an overlapping overlap_ok + * early reservation. + */ +void __init reserve_early(u64 start, u64 end, char *name) +{ + if (start >= end) + return; + + __check_and_double_early_res(start, end); + + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 0); +} + +void __init reserve_early_without_check(u64 start, u64 end, char *name) +{ + struct early_res *r; + + if (start >= end) + return; + + __check_and_double_early_res(start, end); + + r = &early_res[early_res_count]; + + r->start = start; + r->end = end; + r->overlap_ok = 0; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); + early_res_count++; +} + +void __init free_early(u64 start, u64 end) +{ + struct early_res *r; + int i; + + i = find_overlapped_early(start, end); + r = &early_res[i]; + if (i >= max_early_res || r->end != end || r->start != start) + panic("free_early on not reserved area: %llx-%llx!", + start, end - 1); + + drop_range(i); +} + +void __init free_early_partial(u64 start, u64 end) +{ + struct early_res *r; + int i; + +try_next: + i = find_overlapped_early(start, end); + if (i >= max_early_res) + return; + + r = &early_res[i]; + /* hole ? */ + if (r->end >= end && r->start <= start) { + drop_range_partial(i, start, end); + return; + } + + drop_range_partial(i, start, end); + goto try_next; +} + +#ifdef CONFIG_NO_BOOTMEM +static void __init subtract_early_res(struct range *range, int az) +{ + int i, count; + u64 final_start, final_end; + int idx = 0; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + /* need to skip first one ?*/ + if (early_res != early_res_x) + idx = 1; + +#define DEBUG_PRINT_EARLY_RES 1 + +#if DEBUG_PRINT_EARLY_RES + printk(KERN_INFO "Subtract (%d early reservations)\n", count); +#endif + for (i = idx; i < count; i++) { + struct early_res *r = &early_res[i]; +#if DEBUG_PRINT_EARLY_RES + printk(KERN_INFO " #%d [%010llx - %010llx] %15s\n", i, + r->start, r->end, r->name); +#endif + final_start = PFN_DOWN(r->start); + final_end = PFN_UP(r->end); + if (final_start >= final_end) + continue; + subtract_range(range, az, final_start, final_end); + } + +} + +int __init get_free_all_memory_range(struct range **rangep, int nodeid) +{ + int i, count; + u64 start = 0, end; + u64 size; + u64 mem; + struct range *range; + int nr_range; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + count *= 2; + + size = sizeof(struct range) * count; + end = get_max_mapped(); +#ifdef MAX_DMA32_PFN + if (end > (MAX_DMA32_PFN << PAGE_SHIFT)) + start = MAX_DMA32_PFN << PAGE_SHIFT; +#endif + mem = find_fw_memmap_area(start, end, size, sizeof(struct range)); + if (mem == -1ULL) + panic("can not find more space for range free"); + + range = __va(mem); + /* use early_node_map[] and early_res to get range array at first */ + memset(range, 0, size); + nr_range = 0; + + /* need to go over early_node_map to find out good range for node */ + nr_range = add_from_early_node_map(range, count, nr_range, nodeid); +#ifdef CONFIG_X86_32 + subtract_range(range, count, max_low_pfn, -1ULL); +#endif + subtract_early_res(range, count); + nr_range = clean_sort_range(range, count); + + /* need to clear it ? */ + if (nodeid == MAX_NUMNODES) { + memset(&early_res[0], 0, + sizeof(struct early_res) * max_early_res); + early_res = NULL; + max_early_res = 0; + } + + *rangep = range; + return nr_range; +} +#else +void __init early_res_to_bootmem(u64 start, u64 end) +{ + int i, count; + u64 final_start, final_end; + int idx = 0; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + /* need to skip first one ?*/ + if (early_res != early_res_x) + idx = 1; + + printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n", + count - idx, max_early_res, start, end); + for (i = idx; i < count; i++) { + struct early_res *r = &early_res[i]; + printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, + r->start, r->end, r->name); + final_start = max(start, r->start); + final_end = min(end, r->end); + if (final_start >= final_end) { + printk(KERN_CONT "\n"); + continue; + } + printk(KERN_CONT " ==> [%010llx - %010llx]\n", + final_start, final_end); + reserve_bootmem_generic(final_start, final_end - final_start, + BOOTMEM_DEFAULT); + } + /* clear them */ + memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); + early_res = NULL; + max_early_res = 0; + early_res_count = 0; +} +#endif + +/* Check for already reserved areas */ +static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) +{ + int i; + u64 addr = *addrp; + int changed = 0; + struct early_res *r; +again: + i = find_overlapped_early(addr, addr + size); + r = &early_res[i]; + if (i < max_early_res && r->end) { + *addrp = addr = round_up(r->end, align); + changed = 1; + goto again; + } + return changed; +} + +/* Check for already reserved areas */ +static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) +{ + int i; + u64 addr = *addrp, last; + u64 size = *sizep; + int changed = 0; +again: + last = addr + size; + for (i = 0; i < max_early_res && early_res[i].end; i++) { + struct early_res *r = &early_res[i]; + if (last > r->start && addr < r->start) { + size = r->start - addr; + changed = 1; + goto again; + } + if (last > r->end && addr < r->end) { + addr = round_up(r->end, align); + size = last - addr; + changed = 1; + goto again; + } + if (last <= r->end && addr >= r->start) { + (*sizep)++; + return 0; + } + } + if (changed) { + *addrp = addr; + *sizep = size; + } + return changed; +} + +/* + * Find a free area with specified alignment in a specific range. + * only with the area.between start to end is active range from early_node_map + * so they are good as RAM + */ +u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, + u64 size, u64 align) +{ + u64 addr, last; + + addr = round_up(ei_start, align); + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + goto out; + while (bad_addr(&addr, size, align) && addr+size <= ei_last) + ; + last = addr + size; + if (last > ei_last) + goto out; + if (last > end) + goto out; + + return addr; + +out: + return -1ULL; +} + +u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start, + u64 *sizep, u64 align) +{ + u64 addr, last; + + addr = round_up(ei_start, align); + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + goto out; + *sizep = ei_last - addr; + while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last) + ; + last = addr + *sizep; + if (last > ei_last) + goto out; + + return addr; + +out: + return -1ULL; +} diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 235716556bf1..d49afb2395e5 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -146,7 +146,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, struct task_struct *p; ret = -ESRCH; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_task_by_vpid(pid); if (!p) goto err_unlock; @@ -157,7 +157,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->compat_robust_list; - read_unlock(&tasklist_lock); + rcu_read_unlock(); } if (put_user(sizeof(*head), len_ptr)) @@ -165,7 +165,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, return put_user(ptr_to_compat(head), head_ptr); err_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return ret; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index ecc3fa28f666..d70394f12ee9 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -18,11 +18,7 @@ #include "internals.h" -/** - * dynamic_irq_init - initialize a dynamically allocated irq - * @irq: irq number to initialize - */ -void dynamic_irq_init(unsigned int irq) +static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data) { struct irq_desc *desc; unsigned long flags; @@ -41,7 +37,8 @@ void dynamic_irq_init(unsigned int irq) desc->depth = 1; desc->msi_desc = NULL; desc->handler_data = NULL; - desc->chip_data = NULL; + if (!keep_chip_data) + desc->chip_data = NULL; desc->action = NULL; desc->irq_count = 0; desc->irqs_unhandled = 0; @@ -55,10 +52,26 @@ void dynamic_irq_init(unsigned int irq) } /** - * dynamic_irq_cleanup - cleanup a dynamically allocated irq + * dynamic_irq_init - initialize a dynamically allocated irq * @irq: irq number to initialize */ -void dynamic_irq_cleanup(unsigned int irq) +void dynamic_irq_init(unsigned int irq) +{ + dynamic_irq_init_x(irq, false); +} + +/** + * dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq + * @irq: irq number to initialize + * + * does not set irq_to_desc(irq)->chip_data to NULL + */ +void dynamic_irq_init_keep_chip_data(unsigned int irq) +{ + dynamic_irq_init_x(irq, true); +} + +static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; @@ -77,7 +90,8 @@ void dynamic_irq_cleanup(unsigned int irq) } desc->msi_desc = NULL; desc->handler_data = NULL; - desc->chip_data = NULL; + if (!keep_chip_data) + desc->chip_data = NULL; desc->handle_irq = handle_bad_irq; desc->chip = &no_irq_chip; desc->name = NULL; @@ -85,6 +99,26 @@ void dynamic_irq_cleanup(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); } +/** + * dynamic_irq_cleanup - cleanup a dynamically allocated irq + * @irq: irq number to initialize + */ +void dynamic_irq_cleanup(unsigned int irq) +{ + dynamic_irq_cleanup_x(irq, false); +} + +/** + * dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq + * @irq: irq number to initialize + * + * does not set irq_to_desc(irq)->chip_data to NULL + */ +void dynamic_irq_cleanup_keep_chip_data(unsigned int irq) +{ + dynamic_irq_cleanup_x(irq, true); +} + /** * set_irq_chip - set the irq chip for an irq diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 814940e7f485..76d5a671bfe1 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -19,7 +19,7 @@ #include <linux/kernel_stat.h> #include <linux/rculist.h> #include <linux/hash.h> -#include <linux/bootmem.h> +#include <linux/radix-tree.h> #include <trace/events/irq.h> #include "internals.h" @@ -87,12 +87,8 @@ void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr) { void *ptr; - if (slab_is_available()) - ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), - GFP_ATOMIC, node); - else - ptr = alloc_bootmem_node(NODE_DATA(node), - nr * sizeof(*desc->kstat_irqs)); + ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), + GFP_ATOMIC, node); /* * don't overwite if can not get new one @@ -132,7 +128,26 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node) */ DEFINE_RAW_SPINLOCK(sparse_irq_lock); -struct irq_desc **irq_desc_ptrs __read_mostly; +static RADIX_TREE(irq_desc_tree, GFP_ATOMIC); + +static void set_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + radix_tree_insert(&irq_desc_tree, irq, desc); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return radix_tree_lookup(&irq_desc_tree, irq); +} + +void replace_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + void **ptr; + + ptr = radix_tree_lookup_slot(&irq_desc_tree, irq); + if (ptr) + radix_tree_replace_slot(ptr, desc); +} static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { [0 ... NR_IRQS_LEGACY-1] = { @@ -164,9 +179,6 @@ int __init early_irq_init(void) legacy_count = ARRAY_SIZE(irq_desc_legacy); node = first_online_node; - /* allocate irq_desc_ptrs array based on nr_irqs */ - irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT); - /* allocate based on nr_cpu_ids */ kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids * sizeof(int), GFP_NOWAIT, node); @@ -180,23 +192,12 @@ int __init early_irq_init(void) lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); alloc_desc_masks(&desc[i], node, true); init_desc_masks(&desc[i]); - irq_desc_ptrs[i] = desc + i; + set_irq_desc(i, &desc[i]); } - for (i = legacy_count; i < nr_irqs; i++) - irq_desc_ptrs[i] = NULL; - return arch_early_irq_init(); } -struct irq_desc *irq_to_desc(unsigned int irq) -{ - if (irq_desc_ptrs && irq < nr_irqs) - return irq_desc_ptrs[irq]; - - return NULL; -} - struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) { struct irq_desc *desc; @@ -208,21 +209,18 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) return NULL; } - desc = irq_desc_ptrs[irq]; + desc = irq_to_desc(irq); if (desc) return desc; raw_spin_lock_irqsave(&sparse_irq_lock, flags); /* We have to check it to avoid races with another CPU */ - desc = irq_desc_ptrs[irq]; + desc = irq_to_desc(irq); if (desc) goto out_unlock; - if (slab_is_available()) - desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); - else - desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc)); + desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); printk(KERN_DEBUG " alloc irq_desc for %d on node %d\n", irq, node); if (!desc) { @@ -231,7 +229,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) } init_one_irq_desc(irq, desc, node); - irq_desc_ptrs[irq] = desc; + set_irq_desc(irq, desc); out_unlock: raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index b2821f070a3d..c63f3bc88f0b 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -21,11 +21,7 @@ extern void clear_kstat_irqs(struct irq_desc *desc); extern raw_spinlock_t sparse_irq_lock; #ifdef CONFIG_SPARSE_IRQ -/* irq_desc_ptrs allocated at boot time */ -extern struct irq_desc **irq_desc_ptrs; -#else -/* irq_desc_ptrs is a fixed size array */ -extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; +void replace_irq_desc(unsigned int irq, struct irq_desc *desc); #endif #ifdef CONFIG_PROC_FS diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index 26bac9d8f860..963559dbd858 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -70,7 +70,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, raw_spin_lock_irqsave(&sparse_irq_lock, flags); /* We have to check it to avoid races with another CPU */ - desc = irq_desc_ptrs[irq]; + desc = irq_to_desc(irq); if (desc && old_desc != desc) goto out_unlock; @@ -90,7 +90,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, goto out_unlock; } - irq_desc_ptrs[irq] = desc; + replace_irq_desc(irq, desc); raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); /* free the old one */ diff --git a/kernel/kexec.c b/kernel/kexec.c index ef077fb73155..87ebe8adc474 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -41,7 +41,7 @@ #include <asm/sections.h> /* Per cpu memory for storing cpu states in case of system crash. */ -note_buf_t* crash_notes; +note_buf_t __percpu *crash_notes; /* vmcoreinfo stuff */ static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ccec774c716d..fa034d29cf73 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -42,9 +42,11 @@ #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/debugfs.h> +#include <linux/sysctl.h> #include <linux/kdebug.h> #include <linux/memory.h> #include <linux/ftrace.h> +#include <linux/cpu.h> #include <asm-generic/sections.h> #include <asm/cacheflush.h> @@ -105,57 +107,74 @@ static struct kprobe_blackpoint kprobe_blacklist[] = { * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster */ -#define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) - struct kprobe_insn_page { struct list_head list; kprobe_opcode_t *insns; /* Page of instruction slots */ - char slot_used[INSNS_PER_PAGE]; int nused; int ngarbage; + char slot_used[]; +}; + +#define KPROBE_INSN_PAGE_SIZE(slots) \ + (offsetof(struct kprobe_insn_page, slot_used) + \ + (sizeof(char) * (slots))) + +struct kprobe_insn_cache { + struct list_head pages; /* list of kprobe_insn_page */ + size_t insn_size; /* size of instruction slot */ + int nr_garbage; }; +static int slots_per_page(struct kprobe_insn_cache *c) +{ + return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t)); +} + enum kprobe_slot_state { SLOT_CLEAN = 0, SLOT_DIRTY = 1, SLOT_USED = 2, }; -static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_pages */ -static LIST_HEAD(kprobe_insn_pages); -static int kprobe_garbage_slots; -static int collect_garbage_slots(void); +static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_slots */ +static struct kprobe_insn_cache kprobe_insn_slots = { + .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), + .insn_size = MAX_INSN_SIZE, + .nr_garbage = 0, +}; +static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c); /** * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ -static kprobe_opcode_t __kprobes *__get_insn_slot(void) +static kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; retry: - list_for_each_entry(kip, &kprobe_insn_pages, list) { - if (kip->nused < INSNS_PER_PAGE) { + list_for_each_entry(kip, &c->pages, list) { + if (kip->nused < slots_per_page(c)) { int i; - for (i = 0; i < INSNS_PER_PAGE; i++) { + for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; kip->nused++; - return kip->insns + (i * MAX_INSN_SIZE); + return kip->insns + (i * c->insn_size); } } - /* Surprise! No unused slots. Fix kip->nused. */ - kip->nused = INSNS_PER_PAGE; + /* kip->nused is broken. Fix it. */ + kip->nused = slots_per_page(c); + WARN_ON(1); } } /* If there are any garbage slots, collect it and try again. */ - if (kprobe_garbage_slots && collect_garbage_slots() == 0) { + if (c->nr_garbage && collect_garbage_slots(c) == 0) goto retry; - } - /* All out of space. Need to allocate a new page. Use slot 0. */ - kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL); + + /* All out of space. Need to allocate a new page. */ + kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL); if (!kip) return NULL; @@ -170,20 +189,23 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void) return NULL; } INIT_LIST_HEAD(&kip->list); - list_add(&kip->list, &kprobe_insn_pages); - memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE); + memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); kip->slot_used[0] = SLOT_USED; kip->nused = 1; kip->ngarbage = 0; + list_add(&kip->list, &c->pages); return kip->insns; } + kprobe_opcode_t __kprobes *get_insn_slot(void) { - kprobe_opcode_t *ret; + kprobe_opcode_t *ret = NULL; + mutex_lock(&kprobe_insn_mutex); - ret = __get_insn_slot(); + ret = __get_insn_slot(&kprobe_insn_slots); mutex_unlock(&kprobe_insn_mutex); + return ret; } @@ -199,7 +221,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) * so as not to have to set it up again the * next time somebody inserts a probe. */ - if (!list_is_singular(&kprobe_insn_pages)) { + if (!list_is_singular(&kip->list)) { list_del(&kip->list); module_free(NULL, kip->insns); kfree(kip); @@ -209,51 +231,84 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) return 0; } -static int __kprobes collect_garbage_slots(void) +static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip, *next; /* Ensure no-one is interrupted on the garbages */ synchronize_sched(); - list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) { + list_for_each_entry_safe(kip, next, &c->pages, list) { int i; if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ - for (i = 0; i < INSNS_PER_PAGE; i++) { + for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i)) break; } } - kprobe_garbage_slots = 0; + c->nr_garbage = 0; return 0; } -void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) +static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; - mutex_lock(&kprobe_insn_mutex); - list_for_each_entry(kip, &kprobe_insn_pages, list) { - if (kip->insns <= slot && - slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) { - int i = (slot - kip->insns) / MAX_INSN_SIZE; + list_for_each_entry(kip, &c->pages, list) { + long idx = ((long)slot - (long)kip->insns) / c->insn_size; + if (idx >= 0 && idx < slots_per_page(c)) { + WARN_ON(kip->slot_used[idx] != SLOT_USED); if (dirty) { - kip->slot_used[i] = SLOT_DIRTY; + kip->slot_used[idx] = SLOT_DIRTY; kip->ngarbage++; + if (++c->nr_garbage > slots_per_page(c)) + collect_garbage_slots(c); } else - collect_one_slot(kip, i); - break; + collect_one_slot(kip, idx); + return; } } + /* Could not free this slot. */ + WARN_ON(1); +} - if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE) - collect_garbage_slots(); - +void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) +{ + mutex_lock(&kprobe_insn_mutex); + __free_insn_slot(&kprobe_insn_slots, slot, dirty); mutex_unlock(&kprobe_insn_mutex); } +#ifdef CONFIG_OPTPROBES +/* For optimized_kprobe buffer */ +static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */ +static struct kprobe_insn_cache kprobe_optinsn_slots = { + .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), + /* .insn_size is initialized later */ + .nr_garbage = 0, +}; +/* Get a slot for optimized_kprobe buffer */ +kprobe_opcode_t __kprobes *get_optinsn_slot(void) +{ + kprobe_opcode_t *ret = NULL; + + mutex_lock(&kprobe_optinsn_mutex); + ret = __get_insn_slot(&kprobe_optinsn_slots); + mutex_unlock(&kprobe_optinsn_mutex); + + return ret; +} + +void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty) +{ + mutex_lock(&kprobe_optinsn_mutex); + __free_insn_slot(&kprobe_optinsn_slots, slot, dirty); + mutex_unlock(&kprobe_optinsn_mutex); +} +#endif #endif /* We have preemption disabled.. so it is safe to use __ versions */ @@ -284,23 +339,401 @@ struct kprobe __kprobes *get_kprobe(void *addr) if (p->addr == addr) return p; } + + return NULL; +} + +static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); + +/* Return true if the kprobe is an aggregator */ +static inline int kprobe_aggrprobe(struct kprobe *p) +{ + return p->pre_handler == aggr_pre_handler; +} + +/* + * Keep all fields in the kprobe consistent + */ +static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) +{ + memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t)); + memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn)); +} + +#ifdef CONFIG_OPTPROBES +/* NOTE: change this value only with kprobe_mutex held */ +static bool kprobes_allow_optimization; + +/* + * Call all pre_handler on the list, but ignores its return value. + * This must be called from arch-dep optimized caller. + */ +void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &p->list, list) { + if (kp->pre_handler && likely(!kprobe_disabled(kp))) { + set_kprobe_instance(kp); + kp->pre_handler(kp, regs); + } + reset_kprobe_instance(); + } +} + +/* Return true(!0) if the kprobe is ready for optimization. */ +static inline int kprobe_optready(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if (kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + return arch_prepared_optinsn(&op->optinsn); + } + + return 0; +} + +/* + * Return an optimized kprobe whose optimizing code replaces + * instructions including addr (exclude breakpoint). + */ +struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr) +{ + int i; + struct kprobe *p = NULL; + struct optimized_kprobe *op; + + /* Don't check i == 0, since that is a breakpoint case. */ + for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) + p = get_kprobe((void *)(addr - i)); + + if (p && kprobe_optready(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (arch_within_optimized_kprobe(op, addr)) + return p; + } + return NULL; } +/* Optimization staging list, protected by kprobe_mutex */ +static LIST_HEAD(optimizing_list); + +static void kprobe_optimizer(struct work_struct *work); +static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); +#define OPTIMIZE_DELAY 5 + +/* Kprobe jump optimizer */ +static __kprobes void kprobe_optimizer(struct work_struct *work) +{ + struct optimized_kprobe *op, *tmp; + + /* Lock modules while optimizing kprobes */ + mutex_lock(&module_mutex); + mutex_lock(&kprobe_mutex); + if (kprobes_all_disarmed || !kprobes_allow_optimization) + goto end; + + /* + * Wait for quiesence period to ensure all running interrupts + * are done. Because optprobe may modify multiple instructions + * there is a chance that Nth instruction is interrupted. In that + * case, running interrupt can return to 2nd-Nth byte of jump + * instruction. This wait is for avoiding it. + */ + synchronize_sched(); + + /* + * The optimization/unoptimization refers online_cpus via + * stop_machine() and cpu-hotplug modifies online_cpus. + * And same time, text_mutex will be held in cpu-hotplug and here. + * This combination can cause a deadlock (cpu-hotplug try to lock + * text_mutex but stop_machine can not be done because online_cpus + * has been changed) + * To avoid this deadlock, we need to call get_online_cpus() + * for preventing cpu-hotplug outside of text_mutex locking. + */ + get_online_cpus(); + mutex_lock(&text_mutex); + list_for_each_entry_safe(op, tmp, &optimizing_list, list) { + WARN_ON(kprobe_disabled(&op->kp)); + if (arch_optimize_kprobe(op) < 0) + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + list_del_init(&op->list); + } + mutex_unlock(&text_mutex); + put_online_cpus(); +end: + mutex_unlock(&kprobe_mutex); + mutex_unlock(&module_mutex); +} + +/* Optimize kprobe if p is ready to be optimized */ +static __kprobes void optimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + /* Check if the kprobe is disabled or not ready for optimization. */ + if (!kprobe_optready(p) || !kprobes_allow_optimization || + (kprobe_disabled(p) || kprobes_all_disarmed)) + return; + + /* Both of break_handler and post_handler are not supported. */ + if (p->break_handler || p->post_handler) + return; + + op = container_of(p, struct optimized_kprobe, kp); + + /* Check there is no other kprobes at the optimized instructions */ + if (arch_check_optimized_kprobe(op) < 0) + return; + + /* Check if it is already optimized. */ + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + return; + + op->kp.flags |= KPROBE_FLAG_OPTIMIZED; + list_add(&op->list, &optimizing_list); + if (!delayed_work_pending(&optimizing_work)) + schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); +} + +/* Unoptimize a kprobe if p is optimized */ +static __kprobes void unoptimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + else + /* Replace jump with break */ + arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } +} + +/* Remove optimized instructions */ +static void __kprobes kill_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) { + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } + /* Don't unoptimize, because the target code will be freed. */ + arch_remove_optimized_kprobe(op); +} + +/* Try to prepare optimized instructions */ +static __kprobes void prepare_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_prepare_optimized_kprobe(op); +} + +/* Free optimized instructions and optimized_kprobe */ +static __kprobes void free_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_remove_optimized_kprobe(op); + kfree(op); +} + +/* Allocate new optimized_kprobe and try to prepare optimized instructions */ +static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); + if (!op) + return NULL; + + INIT_LIST_HEAD(&op->list); + op->kp.addr = p->addr; + arch_prepare_optimized_kprobe(op); + + return &op->kp; +} + +static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); + +/* + * Prepare an optimized_kprobe and optimize it + * NOTE: p must be a normal registered kprobe + */ +static __kprobes void try_to_optimize_kprobe(struct kprobe *p) +{ + struct kprobe *ap; + struct optimized_kprobe *op; + + ap = alloc_aggr_kprobe(p); + if (!ap) + return; + + op = container_of(ap, struct optimized_kprobe, kp); + if (!arch_prepared_optinsn(&op->optinsn)) { + /* If failed to setup optimizing, fallback to kprobe */ + free_aggr_kprobe(ap); + return; + } + + init_aggr_kprobe(ap, p); + optimize_kprobe(ap); +} + +#ifdef CONFIG_SYSCTL +static void __kprobes optimize_all_kprobes(void) +{ + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + /* If optimization is already allowed, just return */ + if (kprobes_allow_optimization) + return; + + kprobes_allow_optimization = true; + mutex_lock(&text_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) + if (!kprobe_disabled(p)) + optimize_kprobe(p); + } + mutex_unlock(&text_mutex); + printk(KERN_INFO "Kprobes globally optimized\n"); +} + +static void __kprobes unoptimize_all_kprobes(void) +{ + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + /* If optimization is already prohibited, just return */ + if (!kprobes_allow_optimization) + return; + + kprobes_allow_optimization = false; + printk(KERN_INFO "Kprobes globally unoptimized\n"); + get_online_cpus(); /* For avoiding text_mutex deadlock */ + mutex_lock(&text_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) { + if (!kprobe_disabled(p)) + unoptimize_kprobe(p); + } + } + + mutex_unlock(&text_mutex); + put_online_cpus(); + /* Allow all currently running kprobes to complete */ + synchronize_sched(); +} + +int sysctl_kprobes_optimization; +int proc_kprobes_optimization_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, + loff_t *ppos) +{ + int ret; + + mutex_lock(&kprobe_mutex); + sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + + if (sysctl_kprobes_optimization) + optimize_all_kprobes(); + else + unoptimize_all_kprobes(); + mutex_unlock(&kprobe_mutex); + + return ret; +} +#endif /* CONFIG_SYSCTL */ + +static void __kprobes __arm_kprobe(struct kprobe *p) +{ + struct kprobe *old_p; + + /* Check collision with other optimized kprobes */ + old_p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(old_p)) + unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */ + + arch_arm_kprobe(p); + optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ +} + +static void __kprobes __disarm_kprobe(struct kprobe *p) +{ + struct kprobe *old_p; + + unoptimize_kprobe(p); /* Try to unoptimize */ + arch_disarm_kprobe(p); + + /* If another kprobe was blocked, optimize it. */ + old_p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(old_p)) + optimize_kprobe(old_p); +} + +#else /* !CONFIG_OPTPROBES */ + +#define optimize_kprobe(p) do {} while (0) +#define unoptimize_kprobe(p) do {} while (0) +#define kill_optimized_kprobe(p) do {} while (0) +#define prepare_optimized_kprobe(p) do {} while (0) +#define try_to_optimize_kprobe(p) do {} while (0) +#define __arm_kprobe(p) arch_arm_kprobe(p) +#define __disarm_kprobe(p) arch_disarm_kprobe(p) + +static __kprobes void free_aggr_kprobe(struct kprobe *p) +{ + kfree(p); +} + +static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + return kzalloc(sizeof(struct kprobe), GFP_KERNEL); +} +#endif /* CONFIG_OPTPROBES */ + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { + /* + * Here, since __arm_kprobe() doesn't use stop_machine(), + * this doesn't cause deadlock on text_mutex. So, we don't + * need get_online_cpus(). + */ mutex_lock(&text_mutex); - arch_arm_kprobe(kp); + __arm_kprobe(kp); mutex_unlock(&text_mutex); } /* Disarm a kprobe with text_mutex */ static void __kprobes disarm_kprobe(struct kprobe *kp) { + get_online_cpus(); /* For avoiding text_mutex deadlock */ mutex_lock(&text_mutex); - arch_disarm_kprobe(kp); + __disarm_kprobe(kp); mutex_unlock(&text_mutex); + put_online_cpus(); } /* @@ -369,7 +802,7 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) void __kprobes kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; - if (p->pre_handler != aggr_pre_handler) { + if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) @@ -493,21 +926,16 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp) } /* - * Keep all fields in the kprobe consistent - */ -static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) -{ - memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t)); - memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn)); -} - -/* * Add the new probe to ap->list. Fail if this is the * second jprobe at the address - two jprobes can't coexist */ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); + + if (p->break_handler || p->post_handler) + unoptimize_kprobe(ap); /* Fall back to normal kprobe */ + if (p->break_handler) { if (ap->break_handler) return -EEXIST; @@ -522,7 +950,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) /* Arm the breakpoint again. */ - arm_kprobe(ap); + __arm_kprobe(ap); } return 0; } @@ -531,12 +959,13 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ -static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) +static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { + /* Copy p's insn slot to ap */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; - ap->flags = p->flags; + ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ @@ -546,8 +975,9 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); - list_add_rcu(&p->list, &ap->list); + INIT_HLIST_NODE(&ap->hlist); + list_add_rcu(&p->list, &ap->list); hlist_replace_rcu(&p->hlist, &ap->hlist); } @@ -561,12 +991,12 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, int ret = 0; struct kprobe *ap = old_p; - if (old_p->pre_handler != aggr_pre_handler) { - /* If old_p is not an aggr_probe, create new aggr_kprobe. */ - ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL); + if (!kprobe_aggrprobe(old_p)) { + /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */ + ap = alloc_aggr_kprobe(old_p); if (!ap) return -ENOMEM; - add_aggr_kprobe(ap, old_p); + init_aggr_kprobe(ap, old_p); } if (kprobe_gone(ap)) { @@ -585,6 +1015,9 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, */ return ret; + /* Prepare optimized instructions if possible. */ + prepare_optimized_kprobe(ap); + /* * Clear gone flag to prevent allocating new slot again, and * set disabled flag because it is not armed yet. @@ -593,6 +1026,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, | KPROBE_FLAG_DISABLED; } + /* Copy ap's insn slot to p */ copy_kprobe(ap, p); return add_new_kprobe(ap, p); } @@ -743,27 +1177,34 @@ int __kprobes register_kprobe(struct kprobe *p) p->nmissed = 0; INIT_LIST_HEAD(&p->list); mutex_lock(&kprobe_mutex); + + get_online_cpus(); /* For avoiding text_mutex deadlock. */ + mutex_lock(&text_mutex); + old_p = get_kprobe(p->addr); if (old_p) { + /* Since this may unoptimize old_p, locking text_mutex. */ ret = register_aggr_kprobe(old_p, p); goto out; } - mutex_lock(&text_mutex); ret = arch_prepare_kprobe(p); if (ret) - goto out_unlock_text; + goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arch_arm_kprobe(p); + __arm_kprobe(p); + + /* Try to optimize kprobe */ + try_to_optimize_kprobe(p); -out_unlock_text: - mutex_unlock(&text_mutex); out: + mutex_unlock(&text_mutex); + put_online_cpus(); mutex_unlock(&kprobe_mutex); if (probed_mod) @@ -785,7 +1226,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) return -EINVAL; if (old_p == p || - (old_p->pre_handler == aggr_pre_handler && + (kprobe_aggrprobe(old_p) && list_is_singular(&old_p->list))) { /* * Only probe on the hash list. Disarm only if kprobes are @@ -793,7 +1234,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) * already have been removed. We save on flushing icache. */ if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) - disarm_kprobe(p); + disarm_kprobe(old_p); hlist_del_rcu(&old_p->hlist); } else { if (p->break_handler && !kprobe_gone(p)) @@ -809,8 +1250,13 @@ noclean: list_del_rcu(&p->list); if (!kprobe_disabled(old_p)) { try_to_disable_aggr_kprobe(old_p); - if (!kprobes_all_disarmed && kprobe_disabled(old_p)) - disarm_kprobe(old_p); + if (!kprobes_all_disarmed) { + if (kprobe_disabled(old_p)) + disarm_kprobe(old_p); + else + /* Try to optimize this probe again */ + optimize_kprobe(old_p); + } } } return 0; @@ -827,7 +1273,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) old_p = list_entry(p->list.next, struct kprobe, list); list_del(&p->list); arch_remove_kprobe(old_p); - kfree(old_p); + free_aggr_kprobe(old_p); } } @@ -1123,7 +1569,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) struct kprobe *kp; p->flags |= KPROBE_FLAG_GONE; - if (p->pre_handler == aggr_pre_handler) { + if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. @@ -1132,6 +1578,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; p->break_handler = NULL; + kill_optimized_kprobe(p); } /* * Here, we can remove insn_slot safely, because no thread calls @@ -1241,6 +1688,15 @@ static int __init init_kprobes(void) } } +#if defined(CONFIG_OPTPROBES) +#if defined(__ARCH_WANT_KPROBES_INSN_SLOT) + /* Init kprobe_optinsn_slots */ + kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; +#endif + /* By default, kprobes can be optimized */ + kprobes_allow_optimization = true; +#endif + /* By default, kprobes are armed */ kprobes_all_disarmed = false; @@ -1259,7 +1715,7 @@ static int __init init_kprobes(void) #ifdef CONFIG_DEBUG_FS static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, - const char *sym, int offset,char *modname) + const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; @@ -1269,19 +1725,21 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, kprobe_type = "j"; else kprobe_type = "k"; + if (sym) - seq_printf(pi, "%p %s %s+0x%x %s %s%s\n", + seq_printf(pi, "%p %s %s+0x%x %s ", p->addr, kprobe_type, sym, offset, - (modname ? modname : " "), - (kprobe_gone(p) ? "[GONE]" : ""), - ((kprobe_disabled(p) && !kprobe_gone(p)) ? - "[DISABLED]" : "")); + (modname ? modname : " ")); else - seq_printf(pi, "%p %s %p %s%s\n", - p->addr, kprobe_type, p->addr, - (kprobe_gone(p) ? "[GONE]" : ""), - ((kprobe_disabled(p) && !kprobe_gone(p)) ? - "[DISABLED]" : "")); + seq_printf(pi, "%p %s %p ", + p->addr, kprobe_type, p->addr); + + if (!pp) + pp = p; + seq_printf(pi, "%s%s%s\n", + (kprobe_gone(p) ? "[GONE]" : ""), + ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), + (kprobe_optimized(pp) ? "[OPTIMIZED]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -1317,11 +1775,11 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) hlist_for_each_entry_rcu(p, node, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); - if (p->pre_handler == aggr_pre_handler) { + if (kprobe_aggrprobe(p)) { list_for_each_entry_rcu(kp, &p->list, list) - report_probe(pi, kp, sym, offset, modname); + report_probe(pi, kp, sym, offset, modname, p); } else - report_probe(pi, p, sym, offset, modname); + report_probe(pi, p, sym, offset, modname, NULL); } preempt_enable(); return 0; @@ -1399,12 +1857,13 @@ int __kprobes enable_kprobe(struct kprobe *kp) goto out; } - if (!kprobes_all_disarmed && kprobe_disabled(p)) - arm_kprobe(p); - - p->flags &= ~KPROBE_FLAG_DISABLED; if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; + + if (!kprobes_all_disarmed && kprobe_disabled(p)) { + p->flags &= ~KPROBE_FLAG_DISABLED; + arm_kprobe(p); + } out: mutex_unlock(&kprobe_mutex); return ret; @@ -1424,12 +1883,13 @@ static void __kprobes arm_all_kprobes(void) if (!kprobes_all_disarmed) goto already_enabled; + /* Arming kprobes doesn't optimize kprobe itself */ mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_disabled(p)) - arch_arm_kprobe(p); + __arm_kprobe(p); } mutex_unlock(&text_mutex); @@ -1456,16 +1916,23 @@ static void __kprobes disarm_all_kprobes(void) kprobes_all_disarmed = true; printk(KERN_INFO "Kprobes globally disabled\n"); + + /* + * Here we call get_online_cpus() for avoiding text_mutex deadlock, + * because disarming may also unoptimize kprobes. + */ + get_online_cpus(); mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - arch_disarm_kprobe(p); + __disarm_kprobe(p); } } mutex_unlock(&text_mutex); + put_online_cpus(); mutex_unlock(&kprobe_mutex); /* Allow all currently running kprobes to complete */ synchronize_sched(); diff --git a/kernel/module.c b/kernel/module.c index f82386bd9ee9..e5538d5f00ad 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -474,9 +474,10 @@ static void module_unload_init(struct module *mod) INIT_LIST_HEAD(&mod->modules_which_use_me); for_each_possible_cpu(cpu) - local_set(__module_ref_addr(mod, cpu), 0); + per_cpu_ptr(mod->refptr, cpu)->count = 0; + /* Hold reference count during initialization. */ - local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1); + __this_cpu_write(mod->refptr->count, 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; } @@ -619,7 +620,7 @@ unsigned int module_refcount(struct module *mod) int cpu; for_each_possible_cpu(cpu) - total += local_read(__module_ref_addr(mod, cpu)); + total += per_cpu_ptr(mod->refptr, cpu)->count; return total; } EXPORT_SYMBOL(module_refcount); @@ -796,14 +797,15 @@ static struct module_attribute refcnt = { void module_put(struct module *module) { if (module) { - unsigned int cpu = get_cpu(); - local_dec(__module_ref_addr(module, cpu)); + preempt_disable(); + __this_cpu_dec(module->refptr->count); + trace_module_put(module, _RET_IP_, - local_read(__module_ref_addr(module, cpu))); + __this_cpu_read(module->refptr->count)); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); - put_cpu(); + preempt_enable(); } } EXPORT_SYMBOL(module_put); @@ -1397,9 +1399,9 @@ static void free_module(struct module *mod) kfree(mod->args); if (mod->percpu) percpu_modfree(mod->percpu); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) +#if defined(CONFIG_MODULE_UNLOAD) if (mod->refptr) - percpu_modfree(mod->refptr); + free_percpu(mod->refptr); #endif /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -2162,9 +2164,8 @@ static noinline struct module *load_module(void __user *umod, mod = (void *)sechdrs[modindex].sh_addr; kmemleak_load_module(mod, hdr, sechdrs, secstrings); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t), - mod->name); +#if defined(CONFIG_MODULE_UNLOAD) + mod->refptr = alloc_percpu(struct module_ref); if (!mod->refptr) { err = -ENOMEM; goto free_init; @@ -2396,8 +2397,8 @@ static noinline struct module *load_module(void __user *umod, kobject_put(&mod->mkobj.kobj); free_unload: module_unload_free(mod); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - percpu_modfree(mod->refptr); +#if defined(CONFIG_MODULE_UNLOAD) + free_percpu(mod->refptr); free_init: #endif module_free(mod, mod->module_init); diff --git a/kernel/padata.c b/kernel/padata.c index 6f9bcb8313d6..93caf65ff57c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -642,6 +642,9 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask, if (!pd) goto err_free_inst; + if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL)) + goto err_free_pd; + rcu_assign_pointer(pinst->pd, pd); pinst->wq = wq; @@ -654,12 +657,14 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask, pinst->cpu_notifier.priority = 0; err = register_hotcpu_notifier(&pinst->cpu_notifier); if (err) - goto err_free_pd; + goto err_free_cpumask; mutex_init(&pinst->lock); return pinst; +err_free_cpumask: + free_cpumask_var(pinst->cpumask); err_free_pd: padata_free_pd(pd); err_free_inst: @@ -685,6 +690,7 @@ void padata_free(struct padata_instance *pinst) unregister_hotcpu_notifier(&pinst->cpu_notifier); padata_free_pd(pinst->pd); + free_cpumask_var(pinst->cpumask); kfree(pinst); } EXPORT_SYMBOL(padata_free); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 495440779ce3..00d1fda58ab6 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -256,7 +256,7 @@ static int posix_get_monotonic_coarse(clockid_t which_clock, return 0; } -int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp) +static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp) { *tp = ktime_to_timespec(KTIME_LOW_RES); return 0; diff --git a/kernel/printk.c b/kernel/printk.c index 1751c456b71f..40674122ecf2 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -35,6 +35,7 @@ #include <linux/kexec.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> +#include <linux/syslog.h> #include <asm/uaccess.h> @@ -258,38 +259,23 @@ static inline void boot_delay_msec(void) } #endif -/* - * Commands to do_syslog: - * - * 0 -- Close the log. Currently a NOP. - * 1 -- Open the log. Currently a NOP. - * 2 -- Read from the log. - * 3 -- Read all messages remaining in the ring buffer. - * 4 -- Read and clear all messages remaining in the ring buffer - * 5 -- Clear ring buffer. - * 6 -- Disable printk's to console - * 7 -- Enable printk's to console - * 8 -- Set level of messages printed to console - * 9 -- Return number of unread characters in the log buffer - * 10 -- Return size of the log buffer - */ -int do_syslog(int type, char __user *buf, int len) +int do_syslog(int type, char __user *buf, int len, bool from_file) { unsigned i, j, limit, count; int do_clear = 0; char c; int error = 0; - error = security_syslog(type); + error = security_syslog(type, from_file); if (error) return error; switch (type) { - case 0: /* Close log */ + case SYSLOG_ACTION_CLOSE: /* Close log */ break; - case 1: /* Open log */ + case SYSLOG_ACTION_OPEN: /* Open log */ break; - case 2: /* Read from log */ + case SYSLOG_ACTION_READ: /* Read from log */ error = -EINVAL; if (!buf || len < 0) goto out; @@ -320,10 +306,12 @@ int do_syslog(int type, char __user *buf, int len) if (!error) error = i; break; - case 4: /* Read/clear last kernel messages */ + /* Read/clear last kernel messages */ + case SYSLOG_ACTION_READ_CLEAR: do_clear = 1; /* FALL THRU */ - case 3: /* Read last kernel messages */ + /* Read last kernel messages */ + case SYSLOG_ACTION_READ_ALL: error = -EINVAL; if (!buf || len < 0) goto out; @@ -376,21 +364,25 @@ int do_syslog(int type, char __user *buf, int len) } } break; - case 5: /* Clear ring buffer */ + /* Clear ring buffer */ + case SYSLOG_ACTION_CLEAR: logged_chars = 0; break; - case 6: /* Disable logging to console */ + /* Disable logging to console */ + case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == -1) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; - case 7: /* Enable logging to console */ + /* Enable logging to console */ + case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != -1) { console_loglevel = saved_console_loglevel; saved_console_loglevel = -1; } break; - case 8: /* Set level of messages printed to console */ + /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_LEVEL: error = -EINVAL; if (len < 1 || len > 8) goto out; @@ -401,10 +393,12 @@ int do_syslog(int type, char __user *buf, int len) saved_console_loglevel = -1; error = 0; break; - case 9: /* Number of chars in the log buffer */ + /* Number of chars in the log buffer */ + case SYSLOG_ACTION_SIZE_UNREAD: error = log_end - log_start; break; - case 10: /* Size of the log buffer */ + /* Size of the log buffer */ + case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: @@ -417,7 +411,7 @@ out: SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { - return do_syslog(type, buf, len); + return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } /* diff --git a/kernel/range.c b/kernel/range.c new file mode 100644 index 000000000000..74e2e6114927 --- /dev/null +++ b/kernel/range.c @@ -0,0 +1,163 @@ +/* + * Range add and subtract + */ +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sort.h> + +#include <linux/range.h> + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +int add_range(struct range *range, int az, int nr_range, u64 start, u64 end) +{ + if (start >= end) + return nr_range; + + /* Out of slots: */ + if (nr_range >= az) + return nr_range; + + range[nr_range].start = start; + range[nr_range].end = end; + + nr_range++; + + return nr_range; +} + +int add_range_with_merge(struct range *range, int az, int nr_range, + u64 start, u64 end) +{ + int i; + + if (start >= end) + return nr_range; + + /* Try to merge it with old one: */ + for (i = 0; i < nr_range; i++) { + u64 final_start, final_end; + u64 common_start, common_end; + + if (!range[i].end) + continue; + + common_start = max(range[i].start, start); + common_end = min(range[i].end, end); + if (common_start > common_end) + continue; + + final_start = min(range[i].start, start); + final_end = max(range[i].end, end); + + range[i].start = final_start; + range[i].end = final_end; + return nr_range; + } + + /* Need to add it: */ + return add_range(range, az, nr_range, start, end); +} + +void subtract_range(struct range *range, int az, u64 start, u64 end) +{ + int i, j; + + if (start >= end) + return; + + for (j = 0; j < az; j++) { + if (!range[j].end) + continue; + + if (start <= range[j].start && end >= range[j].end) { + range[j].start = 0; + range[j].end = 0; + continue; + } + + if (start <= range[j].start && end < range[j].end && + range[j].start < end) { + range[j].start = end; + continue; + } + + + if (start > range[j].start && end >= range[j].end && + range[j].end > start) { + range[j].end = start; + continue; + } + + if (start > range[j].start && end < range[j].end) { + /* Find the new spare: */ + for (i = 0; i < az; i++) { + if (range[i].end == 0) + break; + } + if (i < az) { + range[i].end = range[j].end; + range[i].start = end; + } else { + printk(KERN_ERR "run of slot in ranges\n"); + } + range[j].end = start; + continue; + } + } +} + +static int cmp_range(const void *x1, const void *x2) +{ + const struct range *r1 = x1; + const struct range *r2 = x2; + s64 start1, start2; + + start1 = r1->start; + start2 = r2->start; + + return start1 - start2; +} + +int clean_sort_range(struct range *range, int az) +{ + int i, j, k = az - 1, nr_range = 0; + + for (i = 0; i < k; i++) { + if (range[i].end) + continue; + for (j = k; j > i; j--) { + if (range[j].end) { + k = j; + break; + } + } + if (j == i) + break; + range[i].start = range[k].start; + range[i].end = range[k].end; + range[k].start = 0; + range[k].end = 0; + k--; + } + /* count it */ + for (i = 0; i < az; i++) { + if (!range[i].end) { + nr_range = i; + break; + } + } + + /* sort them */ + sort(range, nr_range, sizeof(struct range), cmp_range, NULL); + + return nr_range; +} + +void sort_range(struct range *range, int nr_range) +{ + /* sort them */ + sort(range, nr_range, sizeof(struct range), cmp_range, NULL); +} diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 258cdf0a91eb..58df55bf83ed 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -818,13 +818,13 @@ static void rcu_torture_timer(unsigned long unused) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]); + __this_cpu_inc(rcu_torture_count[pipe_count]); completed = cur_ops->completed() - completed; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]); + __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); } @@ -877,13 +877,13 @@ rcu_torture_reader(void *arg) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]); + __this_cpu_inc(rcu_torture_count[pipe_count]); completed = cur_ops->completed() - completed; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]); + __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); schedule(); diff --git a/kernel/resource.c b/kernel/resource.c index 4e9d87fd7bc5..2d5be5d9bf5f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -304,7 +304,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) { struct resource res; - unsigned long pfn, len; + unsigned long pfn, end_pfn; u64 orig_end; int ret = -1; @@ -314,9 +314,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, orig_end = res.end; while ((res.start < res.end) && (find_next_system_ram(&res, "System RAM") >= 0)) { - pfn = (unsigned long)(res.start >> PAGE_SHIFT); - len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT); - ret = (*func)(pfn, len, arg); + pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; + end_pfn = (res.end + 1) >> PAGE_SHIFT; + if (end_pfn > pfn) + ret = (*func)(pfn, end_pfn - pfn, arg); if (ret) break; res.start = res.end + 1; diff --git a/kernel/sched.c b/kernel/sched.c index 6a212c97f523..abb36b16b93b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1521,7 +1521,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static __read_mostly unsigned long *update_shares_data; +static __read_mostly unsigned long __percpu *update_shares_data; static void __set_se_shares(struct sched_entity *se, unsigned long shares); @@ -8813,7 +8813,7 @@ struct cgroup_subsys cpu_cgroup_subsys = { struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 *cpuusage; + u64 __percpu *cpuusage; struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; struct cpuacct *parent; }; diff --git a/kernel/signal.c b/kernel/signal.c index 934ae5e687b9..5bb9baffa4f1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -159,6 +159,10 @@ void recalc_sigpending(void) /* Given the mask, find the first available signal that should be serviced. */ +#define SYNCHRONOUS_MASK \ + (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ + sigmask(SIGTRAP) | sigmask(SIGFPE)) + int next_signal(struct sigpending *pending, sigset_t *mask) { unsigned long i, *s, *m, x; @@ -166,26 +170,39 @@ int next_signal(struct sigpending *pending, sigset_t *mask) s = pending->signal.sig; m = mask->sig; + + /* + * Handle the first word specially: it contains the + * synchronous signals that need to be dequeued first. + */ + x = *s &~ *m; + if (x) { + if (x & SYNCHRONOUS_MASK) + x &= SYNCHRONOUS_MASK; + sig = ffz(~x) + 1; + return sig; + } + switch (_NSIG_WORDS) { default: - for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m) - if ((x = *s &~ *m) != 0) { - sig = ffz(~x) + i*_NSIG_BPW + 1; - break; - } + for (i = 1; i < _NSIG_WORDS; ++i) { + x = *++s &~ *++m; + if (!x) + continue; + sig = ffz(~x) + i*_NSIG_BPW + 1; + break; + } break; - case 2: if ((x = s[0] &~ m[0]) != 0) - sig = 1; - else if ((x = s[1] &~ m[1]) != 0) - sig = _NSIG_BPW + 1; - else + case 2: + x = s[1] &~ m[1]; + if (!x) break; - sig += ffz(~x); + sig = ffz(~x) + _NSIG_BPW + 1; break; - case 1: if ((x = *s &~ *m) != 0) - sig = ffz(~x) + 1; + case 1: + /* Nothing to do */ break; } diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 912823e2a11b..9bb9fb1bd79c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -45,7 +45,7 @@ static int refcount; static struct workqueue_struct *stop_machine_wq; static struct stop_machine_data active, idle; static const struct cpumask *active_cpus; -static void *stop_machine_work; +static void __percpu *stop_machine_work; static void set_state(enum stopmachine_state newstate) { diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8a68b2448468..0ef19c614f6d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -50,6 +50,7 @@ #include <linux/ftrace.h> #include <linux/slow-work.h> #include <linux/perf_event.h> +#include <linux/kprobes.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -1441,7 +1442,7 @@ static struct ctl_table fs_table[] = { }; static struct ctl_table debug_table[] = { -#if defined(CONFIG_X86) || defined(CONFIG_PPC) +#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) { .procname = "exception-trace", .data = &show_unhandled_signals, @@ -1450,6 +1451,17 @@ static struct ctl_table debug_table[] = { .proc_handler = proc_dointvec }, #endif +#if defined(CONFIG_OPTPROBES) + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { } }; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 8f5d16e0707a..8cd50d8f9bde 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1331,7 +1331,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, ssize_t result; char *pathname; int flags; - int acc_mode, fmode; + int acc_mode; pathname = sysctl_getname(name, nlen, &table); result = PTR_ERR(pathname); @@ -1342,15 +1342,12 @@ static ssize_t binary_sysctl(const int *name, int nlen, if (oldval && oldlen && newval && newlen) { flags = O_RDWR; acc_mode = MAY_READ | MAY_WRITE; - fmode = FMODE_READ | FMODE_WRITE; } else if (newval && newlen) { flags = O_WRONLY; acc_mode = MAY_WRITE; - fmode = FMODE_WRITE; } else if (oldval && oldlen) { flags = O_RDONLY; acc_mode = MAY_READ; - fmode = FMODE_READ; } else { result = 0; goto out_putname; @@ -1361,7 +1358,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, if (result) goto out_putname; - result = may_open(&nd.path, acc_mode, fmode); + result = may_open(&nd.path, acc_mode, flags); if (result) goto out_putpath; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index ea8384d3caa7..899ca51be5e8 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -46,15 +46,13 @@ static struct genl_family family = { .maxattr = TASKSTATS_CMD_ATTR_MAX, }; -static struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] -__read_mostly = { +static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = { [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; -static struct nla_policy -cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] __read_mostly = { +static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = { [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, }; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 13700833c181..1f663d23e85e 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -453,6 +453,18 @@ static inline int clocksource_watchdog_kthread(void *data) { return 0; } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ /** + * clocksource_suspend - suspend the clocksource(s) + */ +void clocksource_suspend(void) +{ + struct clocksource *cs; + + list_for_each_entry_reverse(cs, &clocksource_list, list) + if (cs->suspend) + cs->suspend(cs); +} + +/** * clocksource_resume - resume the clocksource(s) */ void clocksource_resume(void) @@ -461,7 +473,7 @@ void clocksource_resume(void) list_for_each_entry(cs, &clocksource_list, list) if (cs->resume) - cs->resume(); + cs->resume(cs); clocksource_resume_watchdog(); } diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 4800f933910e..7c0f180d6e9d 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -58,10 +58,10 @@ static s64 time_offset; static long time_constant = 2; /* maximum error (usecs): */ -long time_maxerror = NTP_PHASE_LIMIT; +static long time_maxerror = NTP_PHASE_LIMIT; /* estimated error (usecs): */ -long time_esterror = NTP_PHASE_LIMIT; +static long time_esterror = NTP_PHASE_LIMIT; /* frequency offset (scaled nsecs/secs): */ static s64 time_freq; @@ -142,11 +142,11 @@ static void ntp_update_offset(long offset) * Select how the frequency is to be controlled * and in which mode (PLL or FLL). */ - secs = xtime.tv_sec - time_reftime; + secs = get_seconds() - time_reftime; if (unlikely(time_status & STA_FREQHOLD)) secs = 0; - time_reftime = xtime.tv_sec; + time_reftime = get_seconds(); offset64 = offset; freq_adj = (offset64 * secs) << @@ -368,7 +368,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) * reference time to current time. */ if (!(time_status & STA_PLL) && (txc->status & STA_PLL)) - time_reftime = xtime.tv_sec; + time_reftime = get_seconds(); /* only set allowed bits */ time_status &= STA_RONLY; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e2ab064c6d41..16736379a9ca 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -622,6 +622,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) write_sequnlock_irqrestore(&xtime_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); + clocksource_suspend(); return 0; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index d9d6206e0b14..07f945a99430 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -540,9 +540,10 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (ret) return ret; - if (copy_to_user(arg, &buts, sizeof(buts))) + if (copy_to_user(arg, &buts, sizeof(buts))) { + blk_trace_remove(q); return -EFAULT; - + } return 0; } EXPORT_SYMBOL_GPL(blk_trace_setup); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8c1b2d290718..0287f9f52f5a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -20,6 +20,7 @@ #include <linux/cpu.h> #include <linux/fs.h> +#include <asm/local.h> #include "trace.h" /* diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index b2477caf09c2..df74c7982255 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -8,6 +8,7 @@ #include <linux/kthread.h> #include <linux/module.h> #include <linux/time.h> +#include <asm/local.h> struct rb_page { u64 ts; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 032c57ca6502..ed01fdba4a55 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -92,12 +92,12 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled); static inline void ftrace_disable_cpu(void) { preempt_disable(); - __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled)); + __this_cpu_inc(ftrace_cpu_disabled); } static inline void ftrace_enable_cpu(void) { - __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled)); + __this_cpu_dec(ftrace_cpu_disabled); preempt_enable(); } @@ -1166,7 +1166,7 @@ trace_function(struct trace_array *tr, struct ftrace_entry *entry; /* If we are reading the ring buffer, don't trace */ - if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled)))) + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return; event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index e998a824e9db..3fc2a575664f 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -188,7 +188,7 @@ static int __trace_graph_entry(struct trace_array *tr, struct ring_buffer *buffer = tr->buffer; struct ftrace_graph_ent_entry *entry; - if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled)))) + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return 0; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, @@ -247,7 +247,7 @@ static void __trace_graph_return(struct trace_array *tr, struct ring_buffer *buffer = tr->buffer; struct ftrace_graph_ret_entry *entry; - if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled)))) + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, |