aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.kexec1
-rw-r--r--kernel/crash_core.c10
-rw-r--r--kernel/cred.c251
-rw-r--r--kernel/events/core.c10
-rw-r--r--kernel/exit.c3
-rw-r--r--kernel/resource.c4
-rw-r--r--kernel/sys_ni.c14
-rw-r--r--kernel/time/posix-stubs.c45
-rw-r--r--kernel/trace/ring_buffer.c184
-rw-r--r--kernel/trace/trace.c16
-rw-r--r--kernel/trace/trace.h1
-rw-r--r--kernel/trace/trace_events_hist.c12
-rw-r--r--kernel/trace/trace_output.c6
13 files changed, 144 insertions, 413 deletions
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 1cc3b1c595d7..2fd510256604 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -94,7 +94,6 @@ config KEXEC_JUMP
config CRASH_DUMP
bool "kernel crash dumps"
depends on ARCH_SUPPORTS_CRASH_DUMP
- depends on ARCH_SUPPORTS_KEXEC
select CRASH_CORE
select KEXEC_CORE
help
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index efe87d501c8c..d4313b53837e 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -199,7 +199,7 @@ static __initdata char *suffix_tbl[] = {
* It returns 0 on success and -EINVAL on failure.
*/
static int __init parse_crashkernel_suffix(char *cmdline,
- unsigned long long *crash_size,
+ unsigned long long *crash_size,
const char *suffix)
{
char *cur = cmdline;
@@ -268,9 +268,9 @@ static int __init __parse_crashkernel(char *cmdline,
unsigned long long *crash_base,
const char *suffix)
{
- char *first_colon, *first_space;
- char *ck_cmdline;
- char *name = "crashkernel=";
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+ char *name = "crashkernel=";
BUG_ON(!crash_size || !crash_base);
*crash_size = 0;
@@ -440,7 +440,7 @@ retry:
return;
}
- if ((crash_base > CRASH_ADDR_LOW_MAX) &&
+ if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
crash_low_size && reserve_crashkernel_low(crash_low_size)) {
memblock_phys_free(crash_base, crash_size);
return;
diff --git a/kernel/cred.c b/kernel/cred.c
index 3c714cb31660..c033a201c808 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
*/
struct cred init_cred = {
.usage = ATOMIC_INIT(4),
-#ifdef CONFIG_DEBUG_CREDENTIALS
- .subscribers = ATOMIC_INIT(2),
- .magic = CRED_MAGIC,
-#endif
.uid = GLOBAL_ROOT_UID,
.gid = GLOBAL_ROOT_GID,
.suid = GLOBAL_ROOT_UID,
@@ -66,31 +62,6 @@ struct cred init_cred = {
.ucounts = &init_ucounts,
};
-static inline void set_cred_subscribers(struct cred *cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- atomic_set(&cred->subscribers, n);
-#endif
-}
-
-static inline int read_cred_subscribers(const struct cred *cred)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- return atomic_read(&cred->subscribers);
-#else
- return 0;
-#endif
-}
-
-static inline void alter_cred_subscribers(const struct cred *_cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- struct cred *cred = (struct cred *) _cred;
-
- atomic_add(n, &cred->subscribers);
-#endif
-}
-
/*
* The RCU callback to actually dispose of a set of credentials
*/
@@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu)
kdebug("put_cred_rcu(%p)", cred);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- if (cred->magic != CRED_MAGIC_DEAD ||
- atomic_read(&cred->usage) != 0 ||
- read_cred_subscribers(cred) != 0)
- panic("CRED: put_cred_rcu() sees %p with"
- " mag %x, put %p, usage %d, subscr %d\n",
- cred, cred->magic, cred->put_addr,
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
-#else
- if (atomic_read(&cred->usage) != 0)
- panic("CRED: put_cred_rcu() sees %p with usage %d\n",
- cred, atomic_read(&cred->usage));
-#endif
+ if (atomic_long_read(&cred->usage) != 0)
+ panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
+ cred, atomic_long_read(&cred->usage));
security_cred_free(cred);
key_put(cred->session_keyring);
@@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu)
*/
void __put_cred(struct cred *cred)
{
- kdebug("__put_cred(%p{%d,%d})", cred,
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
-
- BUG_ON(atomic_read(&cred->usage) != 0);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(cred) != 0);
- cred->magic = CRED_MAGIC_DEAD;
- cred->put_addr = __builtin_return_address(0);
-#endif
+ kdebug("__put_cred(%p{%ld})", cred,
+ atomic_long_read(&cred->usage));
+
+ BUG_ON(atomic_long_read(&cred->usage) != 0);
BUG_ON(cred == current->cred);
BUG_ON(cred == current->real_cred);
@@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk)
{
struct cred *real_cred, *cred;
- kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
- atomic_read(&tsk->cred->usage),
- read_cred_subscribers(tsk->cred));
+ kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred,
+ atomic_long_read(&tsk->cred->usage));
real_cred = (struct cred *) tsk->real_cred;
tsk->real_cred = NULL;
@@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk)
cred = (struct cred *) tsk->cred;
tsk->cred = NULL;
- validate_creds(cred);
if (real_cred == cred) {
- alter_cred_subscribers(cred, -2);
put_cred_many(cred, 2);
} else {
- validate_creds(real_cred);
- alter_cred_subscribers(real_cred, -1);
put_cred(real_cred);
- alter_cred_subscribers(cred, -1);
put_cred(cred);
}
@@ -230,10 +178,7 @@ struct cred *cred_alloc_blank(void)
if (!new)
return NULL;
- atomic_set(&new->usage, 1);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- new->magic = CRED_MAGIC;
-#endif
+ atomic_long_set(&new->usage, 1);
if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
@@ -264,8 +209,6 @@ struct cred *prepare_creds(void)
const struct cred *old;
struct cred *new;
- validate_process_creds();
-
new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
if (!new)
return NULL;
@@ -276,8 +219,7 @@ struct cred *prepare_creds(void)
memcpy(new, old, sizeof(struct cred));
new->non_rcu = 0;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
+ atomic_long_set(&new->usage, 1);
get_group_info(new->group_info);
get_uid(new->user);
get_user_ns(new->user_ns);
@@ -300,7 +242,6 @@ struct cred *prepare_creds(void)
if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
- validate_creds(new);
return new;
error:
@@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
clone_flags & CLONE_THREAD
) {
p->real_cred = get_cred_many(p->cred, 2);
- alter_cred_subscribers(p->cred, 2);
- kdebug("share_creds(%p{%d,%d})",
- p->cred, atomic_read(&p->cred->usage),
- read_cred_subscribers(p->cred));
+ kdebug("share_creds(%p{%ld})",
+ p->cred, atomic_long_read(&p->cred->usage));
inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
return 0;
}
@@ -404,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
p->cred = p->real_cred = get_cred(new);
inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
- alter_cred_subscribers(new, 2);
- validate_creds(new);
return 0;
error_put:
@@ -457,17 +394,11 @@ int commit_creds(struct cred *new)
struct task_struct *task = current;
const struct cred *old = task->real_cred;
- kdebug("commit_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
+ kdebug("commit_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
BUG_ON(task->cred != old);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(old) < 2);
- validate_creds(old);
- validate_creds(new);
-#endif
- BUG_ON(atomic_read(&new->usage) < 1);
+ BUG_ON(atomic_long_read(&new->usage) < 1);
get_cred(new); /* we will require a ref for the subj creds too */
@@ -502,14 +433,12 @@ int commit_creds(struct cred *new)
* RLIMIT_NPROC limits on user->processes have already been checked
* in set_user().
*/
- alter_cred_subscribers(new, 2);
if (new->user != old->user || new->user_ns != old->user_ns)
inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
rcu_assign_pointer(task->real_cred, new);
rcu_assign_pointer(task->cred, new);
if (new->user != old->user || new->user_ns != old->user_ns)
dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
- alter_cred_subscribers(old, -2);
/* send notifications */
if (!uid_eq(new->uid, old->uid) ||
@@ -539,14 +468,10 @@ EXPORT_SYMBOL(commit_creds);
*/
void abort_creds(struct cred *new)
{
- kdebug("abort_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
+ kdebug("abort_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(new) != 0);
-#endif
- BUG_ON(atomic_read(&new->usage) < 1);
+ BUG_ON(atomic_long_read(&new->usage) < 1);
put_cred(new);
}
EXPORT_SYMBOL(abort_creds);
@@ -562,12 +487,8 @@ const struct cred *override_creds(const struct cred *new)
{
const struct cred *old = current->cred;
- kdebug("override_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
-
- validate_creds(old);
- validate_creds(new);
+ kdebug("override_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
/*
* NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
@@ -576,18 +497,12 @@ const struct cred *override_creds(const struct cred *new)
* we are only installing the cred into the thread-synchronous
* '->cred' pointer, not the '->real_cred' pointer that is
* visible to other threads under RCU.
- *
- * Also note that we did validate_creds() manually, not depending
- * on the validation in 'get_cred()'.
*/
get_new_cred((struct cred *)new);
- alter_cred_subscribers(new, 1);
rcu_assign_pointer(current->cred, new);
- alter_cred_subscribers(old, -1);
- kdebug("override_creds() = %p{%d,%d}", old,
- atomic_read(&old->usage),
- read_cred_subscribers(old));
+ kdebug("override_creds() = %p{%ld}", old,
+ atomic_long_read(&old->usage));
return old;
}
EXPORT_SYMBOL(override_creds);
@@ -603,15 +518,10 @@ void revert_creds(const struct cred *old)
{
const struct cred *override = current->cred;
- kdebug("revert_creds(%p{%d,%d})", old,
- atomic_read(&old->usage),
- read_cred_subscribers(old));
+ kdebug("revert_creds(%p{%ld})", old,
+ atomic_long_read(&old->usage));
- validate_creds(old);
- validate_creds(override);
- alter_cred_subscribers(old, 1);
rcu_assign_pointer(current->cred, old);
- alter_cred_subscribers(override, -1);
put_cred(override);
}
EXPORT_SYMBOL(revert_creds);
@@ -731,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
kdebug("prepare_kernel_cred() alloc %p", new);
old = get_task_cred(daemon);
- validate_creds(old);
*new = *old;
new->non_rcu = 0;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
+ atomic_long_set(&new->usage, 1);
get_uid(new->user);
get_user_ns(new->user_ns);
get_group_info(new->group_info);
@@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
goto error;
put_cred(old);
- validate_creds(new);
return new;
error:
@@ -825,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode)
return security_kernel_create_files_as(new, inode);
}
EXPORT_SYMBOL(set_create_files_as);
-
-#ifdef CONFIG_DEBUG_CREDENTIALS
-
-bool creds_are_invalid(const struct cred *cred)
-{
- if (cred->magic != CRED_MAGIC)
- return true;
- return false;
-}
-EXPORT_SYMBOL(creds_are_invalid);
-
-/*
- * dump invalid credentials
- */
-static void dump_invalid_creds(const struct cred *cred, const char *label,
- const struct task_struct *tsk)
-{
- pr_err("%s credentials: %p %s%s%s\n",
- label, cred,
- cred == &init_cred ? "[init]" : "",
- cred == tsk->real_cred ? "[real]" : "",
- cred == tsk->cred ? "[eff]" : "");
- pr_err("->magic=%x, put_addr=%p\n",
- cred->magic, cred->put_addr);
- pr_err("->usage=%d, subscr=%d\n",
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
- pr_err("->*uid = { %d,%d,%d,%d }\n",
- from_kuid_munged(&init_user_ns, cred->uid),
- from_kuid_munged(&init_user_ns, cred->euid),
- from_kuid_munged(&init_user_ns, cred->suid),
- from_kuid_munged(&init_user_ns, cred->fsuid));
- pr_err("->*gid = { %d,%d,%d,%d }\n",
- from_kgid_munged(&init_user_ns, cred->gid),
- from_kgid_munged(&init_user_ns, cred->egid),
- from_kgid_munged(&init_user_ns, cred->sgid),
- from_kgid_munged(&init_user_ns, cred->fsgid));
-#ifdef CONFIG_SECURITY
- pr_err("->security is %p\n", cred->security);
- if ((unsigned long) cred->security >= PAGE_SIZE &&
- (((unsigned long) cred->security & 0xffffff00) !=
- (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
- pr_err("->security {%x, %x}\n",
- ((u32*)cred->security)[0],
- ((u32*)cred->security)[1]);
-#endif
-}
-
-/*
- * report use of invalid credentials
- */
-void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line)
-{
- pr_err("Invalid credentials\n");
- pr_err("At %s:%u\n", file, line);
- dump_invalid_creds(cred, "Specified", current);
- BUG();
-}
-EXPORT_SYMBOL(__invalid_creds);
-
-/*
- * check the credentials on a process
- */
-void __validate_process_creds(struct task_struct *tsk,
- const char *file, unsigned line)
-{
- if (tsk->cred == tsk->real_cred) {
- if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
- creds_are_invalid(tsk->cred)))
- goto invalid_creds;
- } else {
- if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
- read_cred_subscribers(tsk->cred) < 1 ||
- creds_are_invalid(tsk->real_cred) ||
- creds_are_invalid(tsk->cred)))
- goto invalid_creds;
- }
- return;
-
-invalid_creds:
- pr_err("Invalid process credentials\n");
- pr_err("At %s:%u\n", file, line);
-
- dump_invalid_creds(tsk->real_cred, "Real", tsk);
- if (tsk->cred != tsk->real_cred)
- dump_invalid_creds(tsk->cred, "Effective", tsk);
- else
- pr_err("Effective creds == Real creds\n");
- BUG();
-}
-EXPORT_SYMBOL(__validate_process_creds);
-
-/*
- * check creds for do_exit()
- */
-void validate_creds_for_do_exit(struct task_struct *tsk)
-{
- kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
- tsk->real_cred, tsk->cred,
- atomic_read(&tsk->cred->usage),
- read_cred_subscribers(tsk->cred));
-
- __validate_process_creds(tsk, __FILE__, __LINE__);
-}
-
-#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c9d123e13b57..9efd0d7775e7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1947,6 +1947,16 @@ static bool perf_event_validate_size(struct perf_event *event)
group_leader->nr_siblings + 1) > 16*1024)
return false;
+ /*
+ * When creating a new group leader, group_leader->ctx is initialized
+ * after the size has been validated, but we cannot safely use
+ * for_each_sibling_event() until group_leader->ctx is set. A new group
+ * leader cannot have any siblings yet, so we can safely skip checking
+ * the non-existent siblings.
+ */
+ if (event == group_leader)
+ return true;
+
for_each_sibling_event(sibling, group_leader) {
if (__perf_event_read_size(sibling->attr.read_format,
group_leader->nr_siblings + 1) > 16*1024)
diff --git a/kernel/exit.c b/kernel/exit.c
index ee9f43bed49a..aedc0832c9f4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -824,8 +824,6 @@ void __noreturn do_exit(long code)
ptrace_event(PTRACE_EVENT_EXIT, code);
user_events_exit(tsk);
- validate_creds_for_do_exit(tsk);
-
io_uring_files_cancel();
exit_signals(tsk); /* sets PF_EXITING */
@@ -909,7 +907,6 @@ void __noreturn do_exit(long code)
if (tsk->task_frag.page)
put_page(tsk->task_frag.page);
- validate_creds_for_do_exit(tsk);
exit_task_stack_account(tsk);
check_stack_usage();
diff --git a/kernel/resource.c b/kernel/resource.c
index 866ef3663a0b..91be1bc50b60 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1844,8 +1844,8 @@ get_free_mem_region(struct device *dev, struct resource *base,
write_lock(&resource_lock);
for (addr = gfr_start(base, size, align, flags);
- gfr_continue(base, addr, size, flags);
- addr = gfr_next(addr, size, flags)) {
+ gfr_continue(base, addr, align, flags);
+ addr = gfr_next(addr, align, flags)) {
if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
REGION_DISJOINT)
continue;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0..9a846439b36a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -201,6 +201,20 @@ COND_SYSCALL(recvmmsg_time32);
COND_SYSCALL_COMPAT(recvmmsg_time32);
COND_SYSCALL_COMPAT(recvmmsg_time64);
+/* Posix timer syscalls may be configured out */
+COND_SYSCALL(timer_create);
+COND_SYSCALL(timer_gettime);
+COND_SYSCALL(timer_getoverrun);
+COND_SYSCALL(timer_settime);
+COND_SYSCALL(timer_delete);
+COND_SYSCALL(clock_adjtime);
+COND_SYSCALL(getitimer);
+COND_SYSCALL(setitimer);
+COND_SYSCALL(alarm);
+COND_SYSCALL_COMPAT(timer_create);
+COND_SYSCALL_COMPAT(getitimer);
+COND_SYSCALL_COMPAT(setitimer);
+
/*
* Architecture specific syscalls: see further below
*/
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 828aeecbd1e8..9b6fcb8d85e7 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -17,40 +17,6 @@
#include <linux/time_namespace.h>
#include <linux/compat.h>
-#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
-/* Architectures may override SYS_NI and COMPAT_SYS_NI */
-#include <asm/syscall_wrapper.h>
-#endif
-
-asmlinkage long sys_ni_posix_timers(void)
-{
- pr_err_once("process %d (%s) attempted a POSIX timer syscall "
- "while CONFIG_POSIX_TIMERS is not set\n",
- current->pid, current->comm);
- return -ENOSYS;
-}
-
-#ifndef SYS_NI
-#define SYS_NI(name) SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers)
-#endif
-
-#ifndef COMPAT_SYS_NI
-#define COMPAT_SYS_NI(name) SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers)
-#endif
-
-SYS_NI(timer_create);
-SYS_NI(timer_gettime);
-SYS_NI(timer_getoverrun);
-SYS_NI(timer_settime);
-SYS_NI(timer_delete);
-SYS_NI(clock_adjtime);
-SYS_NI(getitimer);
-SYS_NI(setitimer);
-SYS_NI(clock_adjtime32);
-#ifdef __ARCH_WANT_SYS_ALARM
-SYS_NI(alarm);
-#endif
-
/*
* We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC
* as it is easy to remain compatible with little code. CLOCK_BOOTTIME
@@ -158,18 +124,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
which_clock);
}
-#ifdef CONFIG_COMPAT
-COMPAT_SYS_NI(timer_create);
-#endif
-
-#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
-COMPAT_SYS_NI(getitimer);
-COMPAT_SYS_NI(setitimer);
-#endif
-
#ifdef CONFIG_COMPAT_32BIT_TIME
-SYS_NI(timer_settime32);
-SYS_NI(timer_gettime32);
SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
struct old_timespec32 __user *, tp)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8d2a4f00eca9..83eab547f1d1 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
*cnt = rb_time_cnt(top);
- /* If top and msb counts don't match, this interrupted a write */
- if (*cnt != rb_time_cnt(msb))
+ /* If top, msb or bottom counts don't match, this interrupted a write */
+ if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
return false;
/* The shift to msb will lose its cnt bits */
@@ -700,44 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
return local_try_cmpxchg(l, &expect, set);
}
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
- unsigned long cnt, top, bottom, msb;
- unsigned long cnt2, top2, bottom2, msb2;
- u64 val;
-
- /* The cmpxchg always fails if it interrupted an update */
- if (!__rb_time_read(t, &val, &cnt2))
- return false;
-
- if (val != expect)
- return false;
-
- cnt = local_read(&t->cnt);
- if ((cnt & 3) != cnt2)
- return false;
-
- cnt2 = cnt + 1;
-
- rb_time_split(val, &top, &bottom, &msb);
- top = rb_time_val_cnt(top, cnt);
- bottom = rb_time_val_cnt(bottom, cnt);
-
- rb_time_split(set, &top2, &bottom2, &msb2);
- top2 = rb_time_val_cnt(top2, cnt2);
- bottom2 = rb_time_val_cnt(bottom2, cnt2);
-
- if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
- return false;
- if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
- return false;
- if (!rb_time_read_cmpxchg(&t->top, top, top2))
- return false;
- if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
- return false;
- return true;
-}
-
#else /* 64 bits */
/* local64_t always succeeds */
@@ -751,11 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val)
{
local64_set(&t->time, val);
}
-
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
- return local64_try_cmpxchg(&t->time, &expect, set);
-}
#endif
/*
@@ -1787,6 +1744,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
free_buffer_page(bpage);
}
+ free_page((unsigned long)cpu_buffer->free_page);
+
kfree(cpu_buffer);
}
@@ -2407,7 +2366,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
*/
barrier();
- if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE)
+ if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
/* Writer corrupted the read? */
goto reset;
@@ -2981,25 +2940,6 @@ static unsigned rb_calculate_event_length(unsigned length)
return length;
}
-static u64 rb_time_delta(struct ring_buffer_event *event)
-{
- switch (event->type_len) {
- case RINGBUF_TYPE_PADDING:
- return 0;
-
- case RINGBUF_TYPE_TIME_EXTEND:
- return rb_event_time_stamp(event);
-
- case RINGBUF_TYPE_TIME_STAMP:
- return 0;
-
- case RINGBUF_TYPE_DATA:
- return event->time_delta;
- default:
- return 0;
- }
-}
-
static inline bool
rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
@@ -3007,8 +2947,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long new_index, old_index;
struct buffer_page *bpage;
unsigned long addr;
- u64 write_stamp;
- u64 delta;
new_index = rb_event_index(event);
old_index = new_index + rb_event_ts_length(event);
@@ -3017,14 +2955,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
bpage = READ_ONCE(cpu_buffer->tail_page);
- delta = rb_time_delta(event);
-
- if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
- return false;
-
- /* Make sure the write stamp is read before testing the location */
- barrier();
-
+ /*
+ * Make sure the tail_page is still the same and
+ * the next write location is the end of this event
+ */
if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
unsigned long write_mask =
local_read(&bpage->write) & ~RB_WRITE_MASK;
@@ -3035,20 +2969,20 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
* to make sure that the next event adds an absolute
* value and does not rely on the saved write stamp, which
* is now going to be bogus.
+ *
+ * By setting the before_stamp to zero, the next event
+ * is not going to use the write_stamp and will instead
+ * create an absolute timestamp. This means there's no
+ * reason to update the wirte_stamp!
*/
rb_time_set(&cpu_buffer->before_stamp, 0);
- /* Something came in, can't discard */
- if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
- write_stamp, write_stamp - delta))
- return false;
-
/*
* If an event were to come in now, it would see that the
* write_stamp and the before_stamp are different, and assume
* that this event just added itself before updating
* the write stamp. The interrupting event will fix the
- * write stamp for us, and use the before stamp as its delta.
+ * write stamp for us, and use an absolute timestamp.
*/
/*
@@ -3485,7 +3419,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
return;
/*
- * If this interrupted another event,
+ * If this interrupted another event,
*/
if (atomic_inc_return(this_cpu_ptr(&checking)) != 1)
goto out;
@@ -3579,7 +3513,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
* absolute timestamp.
* Don't bother if this is the start of a new page (w == 0).
*/
- if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+ if (!w) {
+ /* Use the sub-buffer timestamp */
+ info->delta = 0;
+ } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
info->length += RB_LEN_TIME_EXTEND;
} else {
@@ -3602,26 +3539,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE)) {
- /* before and after may now different, fix it up*/
- b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- if (a_ok && b_ok && info->before != info->after)
- (void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
- info->before, info->after);
- if (a_ok && b_ok)
- check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
+ check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
return rb_move_tail(cpu_buffer, tail, info);
}
if (likely(tail == w)) {
- u64 save_before;
- bool s_ok;
-
/* Nothing interrupted us between A and C */
/*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts);
- barrier();
- /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
- RB_WARN_ON(cpu_buffer, !s_ok);
+ /*
+ * If something came in between C and D, the write stamp
+ * may now not be in sync. But that's fine as the before_stamp
+ * will be different and then next event will just be forced
+ * to use an absolute timestamp.
+ */
if (likely(!(info->add_timestamp &
(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
/* This did not interrupt any time update */
@@ -3629,41 +3559,40 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
else
/* Just use full timestamp for interrupting event */
info->delta = info->ts;
- barrier();
check_buffer(cpu_buffer, info, tail);
- if (unlikely(info->ts != save_before)) {
- /* SLOW PATH - Interrupted between C and E */
-
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- RB_WARN_ON(cpu_buffer, !a_ok);
-
- /* Write stamp must only go forward */
- if (save_before > info->after) {
- /*
- * We do not care about the result, only that
- * it gets updated atomically.
- */
- (void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, save_before);
- }
- }
} else {
u64 ts;
/* SLOW PATH - Interrupted between A and C */
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- /* Was interrupted before here, write_stamp must be valid */
+
+ /* Save the old before_stamp */
+ a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
RB_WARN_ON(cpu_buffer, !a_ok);
+
+ /*
+ * Read a new timestamp and update the before_stamp to make
+ * the next event after this one force using an absolute
+ * timestamp. This is in case an interrupt were to come in
+ * between E and F.
+ */
ts = rb_time_stamp(cpu_buffer->buffer);
+ rb_time_set(&cpu_buffer->before_stamp, ts);
+
barrier();
- /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
- info->after < ts &&
- rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, ts)) {
- /* Nothing came after this event between C and E */
+ /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+ /* Was interrupted before here, write_stamp must be valid */
+ RB_WARN_ON(cpu_buffer, !a_ok);
+ barrier();
+ /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+ info->after == info->before && info->after < ts) {
+ /*
+ * Nothing came after this event between C and F, it is
+ * safe to use info->after for the delta as it
+ * matched info->before and is still valid.
+ */
info->delta = ts - info->after;
} else {
/*
- * Interrupted between C and E:
+ * Interrupted between C and F:
* Lost the previous events time stamp. Just set the
* delta to zero, and this will be the same time as
* the event this event interrupted. And the events that
@@ -3714,6 +3643,12 @@ rb_reserve_next_event(struct trace_buffer *buffer,
int nr_loops = 0;
int add_ts_default;
+ /* ring buffer does cmpxchg, make sure it is safe in NMI context */
+ if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+ (unlikely(in_nmi()))) {
+ return NULL;
+ }
+
rb_start_commit(cpu_buffer);
/* The commit page can not change after this */
@@ -3737,6 +3672,8 @@ rb_reserve_next_event(struct trace_buffer *buffer,
if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
add_ts_default = RB_ADD_STAMP_ABSOLUTE;
info.length += RB_LEN_TIME_EXTEND;
+ if (info.length > BUF_MAX_DATA_SIZE)
+ goto out_fail;
} else {
add_ts_default = RB_ADD_STAMP_NONE;
}
@@ -5118,7 +5055,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
if (!iter)
return NULL;
- iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags);
+ /* Holds the entire event: data and meta data */
+ iter->event = kmalloc(BUF_PAGE_SIZE, flags);
if (!iter->event) {
kfree(iter);
return NULL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index fbcd3bafb93e..199df497db07 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4722,7 +4722,11 @@ static int s_show(struct seq_file *m, void *v)
iter->leftover = ret;
} else {
- print_trace_line(iter);
+ ret = print_trace_line(iter);
+ if (ret == TRACE_TYPE_PARTIAL_LINE) {
+ iter->seq.full = 0;
+ trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+ }
ret = trace_print_seq(m, &iter->seq);
/*
* If we overflow the seq_file buffer, then it will
@@ -4964,6 +4968,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp)
return 0;
}
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp)
+{
+ tracing_release_file_tr(inode, filp);
+ return single_release(inode, filp);
+}
+
static int tracing_mark_open(struct inode *inode, struct file *filp)
{
stream_open(inode, filp);
@@ -6344,7 +6354,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
if (!tr->array_buffer.buffer)
return 0;
- /* Do not allow tracing while resizng ring buffer */
+ /* Do not allow tracing while resizing ring buffer */
tracing_stop_tr(tr);
ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
@@ -6352,7 +6362,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
goto out_start;
#ifdef CONFIG_TRACER_MAX_TRACE
- if (!tr->current_trace->use_max_tr)
+ if (!tr->allocated_snapshot)
goto out;
ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b7f4ea25a194..0489e72c8169 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -617,6 +617,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp);
int tracing_open_generic_tr(struct inode *inode, struct file *filp);
int tracing_open_file_tr(struct inode *inode, struct file *filp);
int tracing_release_file_tr(struct inode *inode, struct file *filp);
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
bool tracer_tracing_is_on(struct trace_array *tr);
void tracer_tracing_on(struct trace_array *tr);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1abc07fba1b9..5ecf3c8bde20 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5623,10 +5623,12 @@ static int event_hist_open(struct inode *inode, struct file *file)
{
int ret;
- ret = security_locked_down(LOCKDOWN_TRACEFS);
+ ret = tracing_open_file_tr(inode, file);
if (ret)
return ret;
+ /* Clear private_data to avoid warning in single_open() */
+ file->private_data = NULL;
return single_open(file, hist_show, file);
}
@@ -5634,7 +5636,7 @@ const struct file_operations event_hist_fops = {
.open = event_hist_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_file_tr,
};
#ifdef CONFIG_HIST_TRIGGERS_DEBUG
@@ -5900,10 +5902,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
{
int ret;
- ret = security_locked_down(LOCKDOWN_TRACEFS);
+ ret = tracing_open_file_tr(inode, file);
if (ret)
return ret;
+ /* Clear private_data to avoid warning in single_open() */
+ file->private_data = NULL;
return single_open(file, hist_debug_show, file);
}
@@ -5911,7 +5915,7 @@ const struct file_operations event_hist_debug_fops = {
.open = event_hist_debug_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_file_tr,
};
#endif
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d8b302d01083..3e7fa44dc2b2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1587,11 +1587,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
{
struct print_entry *field;
struct trace_seq *s = &iter->seq;
+ int max = iter->ent_size - offsetof(struct print_entry, buf);
trace_assign_type(field, iter->ent);
seq_print_ip_sym(s, field->ip, flags);
- trace_seq_printf(s, ": %s", field->buf);
+ trace_seq_printf(s, ": %.*s", max, field->buf);
return trace_handle_return(s);
}
@@ -1600,10 +1601,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct print_entry *field;
+ int max = iter->ent_size - offsetof(struct print_entry, buf);
trace_assign_type(field, iter->ent);
- trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
+ trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
return trace_handle_return(&iter->seq);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-30 02:00:36 +0000