aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/audit.c93
-rw-r--r--kernel/auditsc.c47
-rw-r--r--kernel/cpuset.c24
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/irq/handle.c3
-rw-r--r--kernel/itimer.c6
-rw-r--r--kernel/kallsyms.c13
-rw-r--r--kernel/kprobes.c142
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/power/main.c6
-rw-r--r--kernel/printk.c72
-rw-r--r--kernel/profile.c16
-rw-r--r--kernel/sched.c9
-rw-r--r--kernel/signal.c11
-rw-r--r--kernel/spinlock.c8
-rw-r--r--kernel/sys.c2
17 files changed, 338 insertions, 124 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index eb88b446c2cc..b01d26fe8db7 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -29,7 +29,7 @@ obj-$(CONFIG_SYSFS) += ksysfs.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
-ifneq ($(CONFIG_IA64),y)
+ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
# needed for x86 only. Why this used to be enabled for all architectures is beyond
# me. I suspect most platforms don't need this, but until we know that for sure
diff --git a/kernel/audit.c b/kernel/audit.c
index ac26d4d960d3..9c4f1af0c794 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1,4 +1,4 @@
-/* audit.c -- Auditing support -*- linux-c -*-
+/* audit.c -- Auditing support
* Gateway between the kernel (e.g., selinux) and the user-space audit daemon.
* System-call specific features have moved to auditsc.c
*
@@ -38,7 +38,7 @@
* 6) Support low-overhead kernel-based filtering to minimize the
* information that must be passed to user-space.
*
- * Example user-space utilities: http://people.redhat.com/faith/audit/
+ * Example user-space utilities: http://people.redhat.com/sgrubb/audit/
*/
#include <linux/init.h>
@@ -142,7 +142,6 @@ struct audit_buffer {
int total;
int type;
int pid;
- int count; /* Times requeued */
};
void audit_set_type(struct audit_buffer *ab, int type)
@@ -239,36 +238,36 @@ void audit_log_lost(const char *message)
}
-static int audit_set_rate_limit(int limit)
+static int audit_set_rate_limit(int limit, uid_t loginuid)
{
int old = audit_rate_limit;
audit_rate_limit = limit;
- audit_log(current->audit_context, "audit_rate_limit=%d old=%d",
- audit_rate_limit, old);
+ audit_log(NULL, "audit_rate_limit=%d old=%d by auid %u",
+ audit_rate_limit, old, loginuid);
return old;
}
-static int audit_set_backlog_limit(int limit)
+static int audit_set_backlog_limit(int limit, uid_t loginuid)
{
int old = audit_backlog_limit;
audit_backlog_limit = limit;
- audit_log(current->audit_context, "audit_backlog_limit=%d old=%d",
- audit_backlog_limit, old);
+ audit_log(NULL, "audit_backlog_limit=%d old=%d by auid %u",
+ audit_backlog_limit, old, loginuid);
return old;
}
-static int audit_set_enabled(int state)
+static int audit_set_enabled(int state, uid_t loginuid)
{
int old = audit_enabled;
if (state != 0 && state != 1)
return -EINVAL;
audit_enabled = state;
- audit_log(current->audit_context, "audit_enabled=%d old=%d",
- audit_enabled, old);
+ audit_log(NULL, "audit_enabled=%d old=%d by auid %u",
+ audit_enabled, old, loginuid);
return old;
}
-static int audit_set_failure(int state)
+static int audit_set_failure(int state, uid_t loginuid)
{
int old = audit_failure;
if (state != AUDIT_FAIL_SILENT
@@ -276,8 +275,8 @@ static int audit_set_failure(int state)
&& state != AUDIT_FAIL_PANIC)
return -EINVAL;
audit_failure = state;
- audit_log(current->audit_context, "audit_failure=%d old=%d",
- audit_failure, old);
+ audit_log(NULL, "audit_failure=%d old=%d by auid %u",
+ audit_failure, old, loginuid);
return old;
}
@@ -344,6 +343,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
int err;
struct audit_buffer *ab;
u16 msg_type = nlh->nlmsg_type;
+ uid_t loginuid; /* loginuid of sender */
err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type);
if (err)
@@ -351,6 +351,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
pid = NETLINK_CREDS(skb)->pid;
uid = NETLINK_CREDS(skb)->uid;
+ loginuid = NETLINK_CB(skb).loginuid;
seq = nlh->nlmsg_seq;
data = NLMSG_DATA(nlh);
@@ -371,34 +372,36 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
return -EINVAL;
status_get = (struct audit_status *)data;
if (status_get->mask & AUDIT_STATUS_ENABLED) {
- err = audit_set_enabled(status_get->enabled);
+ err = audit_set_enabled(status_get->enabled, loginuid);
if (err < 0) return err;
}
if (status_get->mask & AUDIT_STATUS_FAILURE) {
- err = audit_set_failure(status_get->failure);
+ err = audit_set_failure(status_get->failure, loginuid);
if (err < 0) return err;
}
if (status_get->mask & AUDIT_STATUS_PID) {
int old = audit_pid;
audit_pid = status_get->pid;
- audit_log(current->audit_context,
- "audit_pid=%d old=%d", audit_pid, old);
+ audit_log(NULL, "audit_pid=%d old=%d by auid %u",
+ audit_pid, old, loginuid);
}
if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
- audit_set_rate_limit(status_get->rate_limit);
+ audit_set_rate_limit(status_get->rate_limit, loginuid);
if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
- audit_set_backlog_limit(status_get->backlog_limit);
+ audit_set_backlog_limit(status_get->backlog_limit,
+ loginuid);
break;
case AUDIT_USER:
ab = audit_log_start(NULL);
if (!ab)
break; /* audit_panic has been called */
audit_log_format(ab,
- "user pid=%d uid=%d length=%d msg='%.1024s'",
+ "user pid=%d uid=%d length=%d loginuid=%u"
+ " msg='%.1024s'",
pid, uid,
(int)(nlh->nlmsg_len
- ((char *)data - (char *)nlh)),
- (char *)data);
+ loginuid, (char *)data);
ab->type = AUDIT_USER;
ab->pid = pid;
audit_log_end(ab);
@@ -411,7 +414,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
case AUDIT_LIST:
#ifdef CONFIG_AUDITSYSCALL
err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
- uid, seq, data);
+ uid, seq, data, loginuid);
#else
err = -EOPNOTSUPP;
#endif
@@ -480,7 +483,7 @@ static void audit_log_move(struct audit_buffer *ab)
if (ab->len == 0)
return;
- skb = skb_peek(&ab->sklist);
+ skb = skb_peek_tail(&ab->sklist);
if (!skb || skb_tailroom(skb) <= ab->len + extra) {
skb = alloc_skb(2 * ab->len + extra, GFP_ATOMIC);
if (!skb) {
@@ -519,9 +522,9 @@ static inline int audit_log_drain(struct audit_buffer *ab)
retval = netlink_unicast(audit_sock, skb, audit_pid,
MSG_DONTWAIT);
}
- if (retval == -EAGAIN && ab->count < 5) {
- ++ab->count;
- skb_queue_tail(&ab->sklist, skb);
+ if (retval == -EAGAIN &&
+ (atomic_read(&audit_backlog)) < audit_backlog_limit) {
+ skb_queue_head(&ab->sklist, skb);
audit_log_end_irq(ab);
return 1;
}
@@ -537,8 +540,8 @@ static inline int audit_log_drain(struct audit_buffer *ab)
if (!audit_pid) { /* No daemon */
int offset = ab->nlh ? NLMSG_SPACE(0) : 0;
int len = skb->len - offset;
- printk(KERN_ERR "%*.*s\n",
- len, len, skb->data + offset);
+ skb->data[offset + len] = '\0';
+ printk(KERN_ERR "%s\n", skb->data + offset);
}
kfree_skb(skb);
ab->nlh = NULL;
@@ -617,7 +620,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx)
struct audit_buffer *ab = NULL;
unsigned long flags;
struct timespec t;
- int serial = 0;
+ unsigned int serial;
if (!audit_initialized)
return NULL;
@@ -659,15 +662,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx)
ab->total = 0;
ab->type = AUDIT_KERNEL;
ab->pid = 0;
- ab->count = 0;
#ifdef CONFIG_AUDITSYSCALL
if (ab->ctx)
audit_get_stamp(ab->ctx, &t, &serial);
else
#endif
+ {
t = CURRENT_TIME;
-
+ serial = 0;
+ }
audit_log_format(ab, "audit(%lu.%03lu:%u): ",
t.tv_sec, t.tv_nsec/1000000, serial);
return ab;
@@ -717,6 +721,29 @@ void audit_log_format(struct audit_buffer *ab, const char *fmt, ...)
va_end(args);
}
+void audit_log_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len)
+{
+ int i;
+
+ for (i=0; i<len; i++)
+ audit_log_format(ab, "%02x", buf[i]);
+}
+
+void audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
+{
+ const unsigned char *p = string;
+
+ while (*p) {
+ if (*p == '"' || *p == ' ' || *p < 0x20 || *p > 0x7f) {
+ audit_log_hex(ab, string, strlen(string));
+ return;
+ }
+ p++;
+ }
+ audit_log_format(ab, "\"%s\"", string);
+}
+
+
/* This is a helper-function to print the d_path without using a static
* buffer or allocating another buffer in addition to the one in
* audit_buffer. */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 6f1931381bc9..37b3ac94bc47 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1,4 +1,4 @@
-/* auditsc.c -- System-call auditing support -*- linux-c -*-
+/* auditsc.c -- System-call auditing support
* Handles all system-call specific auditing features.
*
* Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
@@ -123,7 +123,7 @@ struct audit_context {
int major; /* syscall number */
unsigned long argv[4]; /* syscall arguments */
int return_valid; /* return code is valid */
- int return_code;/* syscall return code */
+ long return_code;/* syscall return code */
int auditable; /* 1 if record should be written */
int name_count;
struct audit_names names[AUDIT_NAMES];
@@ -135,6 +135,7 @@ struct audit_context {
uid_t uid, euid, suid, fsuid;
gid_t gid, egid, sgid, fsgid;
unsigned long personality;
+ int arch;
#if AUDIT_DEBUG
int put_count;
@@ -250,7 +251,8 @@ static int audit_copy_rule(struct audit_rule *d, struct audit_rule *s)
return 0;
}
-int audit_receive_filter(int type, int pid, int uid, int seq, void *data)
+int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
+ uid_t loginuid)
{
u32 flags;
struct audit_entry *entry;
@@ -285,6 +287,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data)
err = audit_add_rule(entry, &audit_entlist);
if (!err && (flags & AUDIT_AT_EXIT))
err = audit_add_rule(entry, &audit_extlist);
+ audit_log(NULL, "auid %u added an audit rule\n", loginuid);
break;
case AUDIT_DEL:
flags =((struct audit_rule *)data)->flags;
@@ -294,6 +297,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data)
err = audit_del_rule(data, &audit_entlist);
if (!err && (flags & AUDIT_AT_EXIT))
err = audit_del_rule(data, &audit_extlist);
+ audit_log(NULL, "auid %u removed an audit rule\n", loginuid);
break;
default:
return -EINVAL;
@@ -348,6 +352,10 @@ static int audit_filter_rules(struct task_struct *tsk,
case AUDIT_PERS:
result = (tsk->personality == value);
break;
+ case AUDIT_ARCH:
+ if (ctx)
+ result = (ctx->arch == value);
+ break;
case AUDIT_EXIT:
if (ctx && ctx->return_valid)
@@ -355,7 +363,7 @@ static int audit_filter_rules(struct task_struct *tsk,
break;
case AUDIT_SUCCESS:
if (ctx && ctx->return_valid)
- result = (ctx->return_code >= 0);
+ result = (ctx->return_valid == AUDITSC_SUCCESS);
break;
case AUDIT_DEVMAJOR:
if (ctx) {
@@ -648,8 +656,11 @@ static void audit_log_exit(struct audit_context *context)
audit_log_format(ab, "syscall=%d", context->major);
if (context->personality != PER_LINUX)
audit_log_format(ab, " per=%lx", context->personality);
+ audit_log_format(ab, " arch=%x", context->arch);
if (context->return_valid)
- audit_log_format(ab, " exit=%d", context->return_code);
+ audit_log_format(ab, " success=%s exit=%ld",
+ (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
+ context->return_code);
audit_log_format(ab,
" a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
" pid=%d loginuid=%d uid=%d gid=%d"
@@ -696,9 +707,10 @@ static void audit_log_exit(struct audit_context *context)
if (!ab)
continue; /* audit_panic has been called */
audit_log_format(ab, "item=%d", i);
- if (context->names[i].name)
- audit_log_format(ab, " name=%s",
- context->names[i].name);
+ if (context->names[i].name) {
+ audit_log_format(ab, " name=");
+ audit_log_untrustedstring(ab, context->names[i].name);
+ }
if (context->names[i].ino != (unsigned long)-1)
audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#o"
" uid=%d gid=%d rdev=%02x:%02x",
@@ -772,7 +784,7 @@ static inline unsigned int audit_serial(void)
* then the record will be written at syscall exit time (otherwise, it
* will only be written if another part of the kernel requests that it
* be written). */
-void audit_syscall_entry(struct task_struct *tsk, int major,
+void audit_syscall_entry(struct task_struct *tsk, int arch, int major,
unsigned long a1, unsigned long a2,
unsigned long a3, unsigned long a4)
{
@@ -826,6 +838,7 @@ void audit_syscall_entry(struct task_struct *tsk, int major,
if (!audit_enabled)
return;
+ context->arch = arch;
context->major = major;
context->argv[0] = a1;
context->argv[1] = a2;
@@ -849,13 +862,13 @@ void audit_syscall_entry(struct task_struct *tsk, int major,
* filtering, or because some other part of the kernel write an audit
* message), then write out the syscall information. In call cases,
* free the names stored from getname(). */
-void audit_syscall_exit(struct task_struct *tsk, int return_code)
+void audit_syscall_exit(struct task_struct *tsk, int valid, long return_code)
{
struct audit_context *context;
get_task_struct(tsk);
task_lock(tsk);
- context = audit_get_context(tsk, 1, return_code);
+ context = audit_get_context(tsk, valid, return_code);
task_unlock(tsk);
/* Not having a context here is ok, since the parent may have
@@ -868,6 +881,7 @@ void audit_syscall_exit(struct task_struct *tsk, int return_code)
context->in_syscall = 0;
context->auditable = 0;
+
if (context->previous) {
struct audit_context *new_context = context->previous;
context->previous = NULL;
@@ -981,7 +995,7 @@ void audit_inode(const char *name, const struct inode *inode)
}
void audit_get_stamp(struct audit_context *ctx,
- struct timespec *t, int *serial)
+ struct timespec *t, unsigned int *serial)
{
if (ctx) {
t->tv_sec = ctx->ctime.tv_sec;
@@ -996,20 +1010,21 @@ void audit_get_stamp(struct audit_context *ctx,
extern int audit_set_type(struct audit_buffer *ab, int type);
-int audit_set_loginuid(struct audit_context *ctx, uid_t loginuid)
+int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
{
- if (ctx) {
+ if (task->audit_context) {
struct audit_buffer *ab;
ab = audit_log_start(NULL);
if (ab) {
audit_log_format(ab, "login pid=%d uid=%u "
"old loginuid=%u new loginuid=%u",
- ctx->pid, ctx->uid, ctx->loginuid, loginuid);
+ task->pid, task->uid,
+ task->audit_context->loginuid, loginuid);
audit_set_type(ab, AUDIT_LOGIN);
audit_log_end(ab);
}
- ctx->loginuid = loginuid;
+ task->audit_context->loginuid = loginuid;
}
return 0;
}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 961d74044deb..00e8f2575512 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -166,9 +166,8 @@ static struct super_block *cpuset_sb = NULL;
* The hooks from fork and exit, cpuset_fork() and cpuset_exit(), don't
* (usually) grab cpuset_sem. These are the two most performance
* critical pieces of code here. The exception occurs on exit(),
- * if the last task using a cpuset exits, and the cpuset was marked
- * notify_on_release. In that case, the cpuset_sem is taken, the
- * path to the released cpuset calculated, and a usermode call made
+ * when a task in a notify_on_release cpuset exits. Then cpuset_sem
+ * is taken, and if the cpuset count is zero, a usermode call made
* to /sbin/cpuset_release_agent with the name of the cpuset (path
* relative to the root of cpuset file system) as the argument.
*
@@ -1404,6 +1403,18 @@ void cpuset_fork(struct task_struct *tsk)
*
* Description: Detach cpuset from @tsk and release it.
*
+ * Note that cpusets marked notify_on_release force every task
+ * in them to take the global cpuset_sem semaphore when exiting.
+ * This could impact scaling on very large systems. Be reluctant
+ * to use notify_on_release cpusets where very high task exit
+ * scaling is required on large systems.
+ *
+ * Don't even think about derefencing 'cs' after the cpuset use
+ * count goes to zero, except inside a critical section guarded
+ * by the cpuset_sem semaphore. If you don't hold cpuset_sem,
+ * then a zero cpuset use count is a license to any other task to
+ * nuke the cpuset immediately.
+ *
**/
void cpuset_exit(struct task_struct *tsk)
@@ -1415,10 +1426,13 @@ void cpuset_exit(struct task_struct *tsk)
tsk->cpuset = NULL;
task_unlock(tsk);
- if (atomic_dec_and_test(&cs->count)) {
+ if (notify_on_release(cs)) {
down(&cpuset_sem);
- check_for_release(cs);
+ if (atomic_dec_and_test(&cs->count))
+ check_for_release(cs);
up(&cpuset_sem);
+ } else {
+ atomic_dec(&cs->count);
}
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 7be283d98983..edaa50b5bbfa 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -846,6 +846,8 @@ fastcall NORET_TYPE void do_exit(long code)
for (;;) ;
}
+EXPORT_SYMBOL_GPL(do_exit);
+
NORET_TYPE void complete_and_exit(struct completion *comp, long code)
{
if (comp)
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 2fb0e46e11f3..436c7d93c00a 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -30,6 +30,7 @@
*/
irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned = {
[0 ... NR_IRQS-1] = {
+ .status = IRQ_DISABLED,
.handler = &no_irq_type,
.lock = SPIN_LOCK_UNLOCKED
}
@@ -118,8 +119,6 @@ fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs)
*/
desc->handler->ack(irq);
action_ret = handle_IRQ_event(irq, regs, desc->action);
- if (!noirqdebug)
- note_interrupt(irq, desc, action_ret);
desc->handler->end(irq);
return 1;
}
diff --git a/kernel/itimer.c b/kernel/itimer.c
index e9a40e947e07..1dc988e0d2c7 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -123,7 +123,11 @@ static inline void it_real_arm(struct task_struct *p, unsigned long interval)
return;
if (interval > (unsigned long) LONG_MAX)
interval = LONG_MAX;
- p->signal->real_timer.expires = jiffies + interval;
+ /* the "+ 1" below makes sure that the timer doesn't go off before
+ * the interval requested. This could happen if
+ * time requested % (usecs per jiffy) is more than the usecs left
+ * in the current jiffy */
+ p->signal->real_timer.expires = jiffies + interval + 1;
add_timer(&p->signal->real_timer);
}
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 1627f8d6e0cd..13bcec151b57 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -46,6 +46,14 @@ static inline int is_kernel_inittext(unsigned long addr)
return 0;
}
+static inline int is_kernel_extratext(unsigned long addr)
+{
+ if (addr >= (unsigned long)_sextratext
+ && addr <= (unsigned long)_eextratext)
+ return 1;
+ return 0;
+}
+
static inline int is_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)
@@ -169,8 +177,9 @@ const char *kallsyms_lookup(unsigned long addr,
namebuf[0] = 0;
if ((all_var && is_kernel(addr)) ||
- (!all_var && (is_kernel_text(addr) || is_kernel_inittext(addr)))) {
- unsigned long symbol_end=0;
+ (!all_var && (is_kernel_text(addr) || is_kernel_inittext(addr) ||
+ is_kernel_extratext(addr)))) {
+ unsigned long symbol_end = 0;
/* do a binary search on the sorted kallsyms_addresses array */
low = 0;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1d5dd1337bd1..037142b72a49 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -44,6 +44,7 @@ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
unsigned int kprobe_cpu = NR_CPUS;
static DEFINE_SPINLOCK(kprobe_lock);
+static struct kprobe *curr_kprobe;
/* Locks kprobe: irqs must be disabled */
void lock_kprobes(void)
@@ -73,22 +74,139 @@ struct kprobe *get_kprobe(void *addr)
return NULL;
}
+/*
+ * Aggregate handlers for multiple kprobes support - these handlers
+ * take care of invoking the individual kprobe handlers on p->list
+ */
+int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kprobe *kp;
+
+ list_for_each_entry(kp, &p->list, list) {
+ if (kp->pre_handler) {
+ curr_kprobe = kp;
+ kp->pre_handler(kp, regs);
+ curr_kprobe = NULL;
+ }
+ }
+ return 0;
+}
+
+void aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
+ unsigned long flags)
+{
+ struct kprobe *kp;
+
+ list_for_each_entry(kp, &p->list, list) {
+ if (kp->post_handler) {
+ curr_kprobe = kp;
+ kp->post_handler(kp, regs, flags);
+ curr_kprobe = NULL;
+ }
+ }
+ return;
+}
+
+int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr)
+{
+ /*
+ * if we faulted "during" the execution of a user specified
+ * probe handler, invoke just that probe's fault handler
+ */
+ if (curr_kprobe && curr_kprobe->fault_handler) {
+ if (curr_kprobe->fault_handler(curr_kprobe, regs, trapnr))
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * 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)
+{
+ ap->addr = p->addr;
+ ap->opcode = p->opcode;
+ memcpy(&ap->ainsn, &p->ainsn, sizeof(struct arch_specific_insn));
+
+ ap->pre_handler = aggr_pre_handler;
+ ap->post_handler = aggr_post_handler;
+ ap->fault_handler = aggr_fault_handler;
+
+ INIT_LIST_HEAD(&ap->list);
+ list_add(&p->list, &ap->list);
+
+ INIT_HLIST_NODE(&ap->hlist);
+ hlist_del(&p->hlist);
+ hlist_add_head(&ap->hlist,
+ &kprobe_table[hash_ptr(ap->addr, KPROBE_HASH_BITS)]);
+}
+
+/*
+ * This is the second or subsequent kprobe at the address - handle
+ * the intricacies
+ * TODO: Move kcalloc outside the spinlock
+ */
+static int register_aggr_kprobe(struct kprobe *old_p, struct kprobe *p)
+{
+ int ret = 0;
+ struct kprobe *ap;
+
+ if (old_p->break_handler || p->break_handler) {
+ ret = -EEXIST; /* kprobe and jprobe can't (yet) coexist */
+ } else if (old_p->pre_handler == aggr_pre_handler) {
+ list_add(&p->list, &old_p->list);
+ } else {
+ ap = kcalloc(1, sizeof(struct kprobe), GFP_ATOMIC);
+ if (!ap)
+ return -ENOMEM;
+ add_aggr_kprobe(ap, old_p);
+ list_add(&p->list, &ap->list);
+ }
+ return ret;
+}
+
+/* kprobe removal house-keeping routines */
+static inline void cleanup_kprobe(struct kprobe *p, unsigned long flags)
+{
+ *p->addr = p->opcode;
+ hlist_del(&p->hlist);
+ flush_icache_range((unsigned long) p->addr,
+ (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+ spin_unlock_irqrestore(&kprobe_lock, flags);
+ arch_remove_kprobe(p);
+}
+
+static inline void cleanup_aggr_kprobe(struct kprobe *old_p,
+ struct kprobe *p, unsigned long flags)
+{
+ list_del(&p->list);
+ if (list_empty(&old_p->list)) {
+ cleanup_kprobe(old_p, flags);
+ kfree(old_p);
+ } else
+ spin_unlock_irqrestore(&kprobe_lock, flags);
+}
+
int register_kprobe(struct kprobe *p)
{
int ret = 0;
unsigned long flags = 0;
+ struct kprobe *old_p;
if ((ret = arch_prepare_kprobe(p)) != 0) {
goto rm_kprobe;
}
spin_lock_irqsave(&kprobe_lock, flags);
- INIT_HLIST_NODE(&p->hlist);
- if (get_kprobe(p->addr)) {
- ret = -EEXIST;
+ old_p = get_kprobe(p->addr);
+ if (old_p) {
+ ret = register_aggr_kprobe(old_p, p);
goto out;
}
- arch_copy_kprobe(p);
+ arch_copy_kprobe(p);
+ INIT_HLIST_NODE(&p->hlist);
hlist_add_head(&p->hlist,
&kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
@@ -107,13 +225,17 @@ rm_kprobe:
void unregister_kprobe(struct kprobe *p)
{
unsigned long flags;
- arch_remove_kprobe(p);
+ struct kprobe *old_p;
+
spin_lock_irqsave(&kprobe_lock, flags);
- *p->addr = p->opcode;
- hlist_del(&p->hlist);
- flush_icache_range((unsigned long) p->addr,
- (unsigned long) p->addr + sizeof(kprobe_opcode_t));
- spin_unlock_irqrestore(&kprobe_lock, flags);
+ old_p = get_kprobe(p->addr);
+ if (old_p) {
+ if (old_p->pre_handler == aggr_pre_handler)
+ cleanup_aggr_kprobe(old_p, p, flags);
+ else
+ cleanup_kprobe(p, flags);
+ } else
+ spin_unlock_irqrestore(&kprobe_lock, flags);
}
static struct notifier_block kprobe_exceptions_nb = {
diff --git a/kernel/module.c b/kernel/module.c
index 5734ab09d3f9..83b3d376708c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1758,6 +1758,7 @@ sys_init_module(void __user *umod,
const char __user *uargs)
{
struct module *mod;
+ mm_segment_t old_fs = get_fs();
int ret = 0;
/* Must have permission */
@@ -1775,6 +1776,9 @@ sys_init_module(void __user *umod,
return PTR_ERR(mod);
}
+ /* flush the icache in correct context */
+ set_fs(KERNEL_DS);
+
/* Flush the instruction cache, since we've played with text */
if (mod->module_init)
flush_icache_range((unsigned long)mod->module_init,
@@ -1783,6 +1787,8 @@ sys_init_module(void __user *umod,
flush_icache_range((unsigned long)mod->module_core,
(unsigned long)mod->module_core + mod->core_size);
+ set_fs(old_fs);
+
/* Now sew it into the lists. They won't access us, since
strong_try_module_get() will fail. */
stop_machine_run(__link_module, mod, NR_CPUS);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7960ddf04a57..4cdebc972ff2 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -156,14 +156,14 @@ static int enter_state(suspend_state_t state)
goto Unlock;
}
- pr_debug("PM: Preparing system for suspend\n");
+ pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
if ((error = suspend_prepare(state)))
goto Unlock;
- pr_debug("PM: Entering state.\n");
+ pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_enter(state);
- pr_debug("PM: Finishing up.\n");
+ pr_debug("PM: Finishing wakeup.\n");
suspend_finish(state);
Unlock:
up(&pm_sem);
diff --git a/kernel/printk.c b/kernel/printk.c
index 290a07ce2c8a..01b58d7d17ff 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -160,42 +160,6 @@ static int __init console_setup(char *str)
__setup("console=", console_setup);
-/**
- * add_preferred_console - add a device to the list of preferred consoles.
- *
- * The last preferred console added will be used for kernel messages
- * and stdin/out/err for init. Normally this is used by console_setup
- * above to handle user-supplied console arguments; however it can also
- * be used by arch-specific code either to override the user or more
- * commonly to provide a default console (ie from PROM variables) when
- * the user has not supplied one.
- */
-int __init add_preferred_console(char *name, int idx, char *options)
-{
- struct console_cmdline *c;
- int i;
-
- /*
- * See if this tty is not yet registered, and
- * if we have a slot free.
- */
- for(i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++)
- if (strcmp(console_cmdline[i].name, name) == 0 &&
- console_cmdline[i].index == idx) {
- selected_console = i;
- return 0;
- }
- if (i == MAX_CMDLINECONSOLES)
- return -E2BIG;
- selected_console = i;
- c = &console_cmdline[i];
- memcpy(c->name, name, sizeof(c->name));
- c->name[sizeof(c->name) - 1] = 0;
- c->options = options;
- c->index = idx;
- return 0;
-}
-
static int __init log_buf_len_setup(char *str)
{
unsigned long size = memparse(str, &str);
@@ -671,6 +635,42 @@ static void call_console_drivers(unsigned long start, unsigned long end) {}
#endif
/**
+ * add_preferred_console - add a device to the list of preferred consoles.
+ *
+ * The last preferred console added will be used for kernel messages
+ * and stdin/out/err for init. Normally this is used by console_setup
+ * above to handle user-supplied console arguments; however it can also
+ * be used by arch-specific code either to override the user or more
+ * commonly to provide a default console (ie from PROM variables) when
+ * the user has not supplied one.
+ */
+int __init add_preferred_console(char *name, int idx, char *options)
+{
+ struct console_cmdline *c;
+ int i;
+
+ /*
+ * See if this tty is not yet registered, and
+ * if we have a slot free.
+ */
+ for(i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++)
+ if (strcmp(console_cmdline[i].name, name) == 0 &&
+ console_cmdline[i].index == idx) {
+ selected_console = i;
+ return 0;
+ }
+ if (i == MAX_CMDLINECONSOLES)
+ return -E2BIG;
+ selected_console = i;
+ c = &console_cmdline[i];
+ memcpy(c->name, name, sizeof(c->name));
+ c->name[sizeof(c->name) - 1] = 0;
+ c->options = options;
+ c->index = idx;
+ return 0;
+}
+
+/**
* acquire_console_sem - lock the console system for exclusive use.
*
* Acquires a semaphore which guarantees that the caller has
diff --git a/kernel/profile.c b/kernel/profile.c
index 0221a50ca867..ad8cbb75ffa2 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -49,15 +49,19 @@ static DECLARE_MUTEX(profile_flip_mutex);
static int __init profile_setup(char * str)
{
+ static char __initdata schedstr[] = "schedule";
int par;
- if (!strncmp(str, "schedule", 8)) {
+ if (!strncmp(str, schedstr, strlen(schedstr))) {
prof_on = SCHED_PROFILING;
- printk(KERN_INFO "kernel schedule profiling enabled\n");
- if (str[7] == ',')
- str += 8;
- }
- if (get_option(&str,&par)) {
+ if (str[strlen(schedstr)] == ',')
+ str += strlen(schedstr) + 1;
+ if (get_option(&str, &par))
+ prof_shift = par;
+ printk(KERN_INFO
+ "kernel schedule profiling enabled (shift: %ld)\n",
+ prof_shift);
+ } else if (get_option(&str, &par)) {
prof_shift = par;
prof_on = CPU_PROFILING;
printk(KERN_INFO "kernel profiling enabled (shift: %ld)\n",
diff --git a/kernel/sched.c b/kernel/sched.c
index 0dc3158667a2..f12a0c8a7d98 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3755,19 +3755,22 @@ EXPORT_SYMBOL(cond_resched);
*/
int cond_resched_lock(spinlock_t * lock)
{
+ int ret = 0;
+
if (need_lockbreak(lock)) {
spin_unlock(lock);
cpu_relax();
+ ret = 1;
spin_lock(lock);
}
if (need_resched()) {
_raw_spin_unlock(lock);
preempt_enable_no_resched();
__cond_resched();
+ ret = 1;
spin_lock(lock);
- return 1;
}
- return 0;
+ return ret;
}
EXPORT_SYMBOL(cond_resched_lock);
@@ -4243,7 +4246,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk)
/* No more Mr. Nice Guy. */
if (dest_cpu == NR_CPUS) {
- tsk->cpus_allowed = cpuset_cpus_allowed(tsk);
+ cpus_setall(tsk->cpus_allowed);
dest_cpu = any_online_cpu(tsk->cpus_allowed);
/*
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f3debc77c5b..b3c24c732c5a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -522,7 +522,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
{
int sig = 0;
- sig = next_signal(pending, mask);
+ /* SIGKILL must have priority, otherwise it is quite easy
+ * to create an unkillable process, sending sig < SIGKILL
+ * to self */
+ if (unlikely(sigismember(&pending->signal, SIGKILL))) {
+ if (!sigismember(mask, SIGKILL))
+ sig = SIGKILL;
+ }
+
+ if (likely(!sig))
+ sig = next_signal(pending, mask);
if (sig) {
if (current->notifier) {
if (sigismember(current->notifier_mask, sig)) {
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index e15ed17863f1..0c3f9d8bbe17 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -294,7 +294,7 @@ EXPORT_SYMBOL(_spin_unlock_irq);
void __lockfunc _spin_unlock_bh(spinlock_t *lock)
{
_raw_spin_unlock(lock);
- preempt_enable();
+ preempt_enable_no_resched();
local_bh_enable();
}
EXPORT_SYMBOL(_spin_unlock_bh);
@@ -318,7 +318,7 @@ EXPORT_SYMBOL(_read_unlock_irq);
void __lockfunc _read_unlock_bh(rwlock_t *lock)
{
_raw_read_unlock(lock);
- preempt_enable();
+ preempt_enable_no_resched();
local_bh_enable();
}
EXPORT_SYMBOL(_read_unlock_bh);
@@ -342,7 +342,7 @@ EXPORT_SYMBOL(_write_unlock_irq);
void __lockfunc _write_unlock_bh(rwlock_t *lock)
{
_raw_write_unlock(lock);
- preempt_enable();
+ preempt_enable_no_resched();
local_bh_enable();
}
EXPORT_SYMBOL(_write_unlock_bh);
@@ -354,7 +354,7 @@ int __lockfunc _spin_trylock_bh(spinlock_t *lock)
if (_raw_spin_trylock(lock))
return 1;
- preempt_enable();
+ preempt_enable_no_resched();
local_bh_enable();
return 0;
}
diff --git a/kernel/sys.c b/kernel/sys.c
index f64e97cabe25..f006632c2ba7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1195,7 +1195,7 @@ static int groups_from_user(struct group_info *group_info,
return 0;
}
-/* a simple shell-metzner sort */
+/* a simple Shell sort */
static void groups_sort(struct group_info *group_info)
{
int base, max, stride;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.