summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c2
-rw-r--r--kernel/auditsc.c49
-rw-r--r--kernel/bpf/core.c2
-rw-r--r--kernel/debug/debug_core.c52
-rw-r--r--kernel/debug/kdb/kdb_bp.c37
-rw-r--r--kernel/debug/kdb/kdb_debugger.c4
-rw-r--r--kernel/debug/kdb/kdb_main.c269
-rw-r--r--kernel/debug/kdb/kdb_private.h3
-rw-r--r--kernel/events/core.c19
-rw-r--r--kernel/exit.c12
-rw-r--r--kernel/kprobes.c2
-rw-r--r--kernel/locking/mutex-debug.c2
-rw-r--r--kernel/module.c91
-rw-r--r--kernel/params.c3
-rw-r--r--kernel/range.c10
-rw-r--r--kernel/sched/core.c13
-rw-r--r--kernel/sched/deadline.c25
-rw-r--r--kernel/sched/fair.c6
-rw-r--r--kernel/sys.c4
-rw-r--r--kernel/time/ntp.c7
-rw-r--r--kernel/time/time.c4
-rw-r--r--kernel/trace/ftrace.c53
-rw-r--r--kernel/trace/trace.c1
-rw-r--r--kernel/trace/trace_events.c69
-rw-r--r--kernel/trace/trace_kdb.c4
-rw-r--r--kernel/workqueue.c25
26 files changed, 503 insertions, 265 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 231b7dcb154b..72ab759a0b43 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1100,7 +1100,7 @@ static void audit_receive(struct sk_buff *skb)
}
/* Run custom bind function on netlink socket group connect or bind requests. */
-static int audit_bind(int group)
+static int audit_bind(struct net *net, int group)
{
if (!capable(CAP_AUDIT_READ))
return -EPERM;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 37c69ab561da..072566dd0caf 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -72,6 +72,8 @@
#include <linux/fs_struct.h>
#include <linux/compat.h>
#include <linux/ctype.h>
+#include <linux/string.h>
+#include <uapi/linux/limits.h>
#include "audit.h"
@@ -1861,8 +1863,7 @@ void __audit_inode(struct filename *name, const struct dentry *dentry,
}
list_for_each_entry_reverse(n, &context->names_list, list) {
- /* does the name pointer match? */
- if (!n->name || n->name->name != name->name)
+ if (!n->name || strcmp(n->name->name, name->name))
continue;
/* match the correct record type */
@@ -1881,14 +1882,44 @@ out_alloc:
n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN);
if (!n)
return;
- if (name)
- /* since name is not NULL we know there is already a matching
- * name record, see audit_getname(), so there must be a type
- * mismatch; reuse the string path since the original name
- * record will keep the string valid until we free it in
- * audit_free_names() */
- n->name = name;
+ /* unfortunately, while we may have a path name to record with the
+ * inode, we can't always rely on the string lasting until the end of
+ * the syscall so we need to create our own copy, it may fail due to
+ * memory allocation issues, but we do our best */
+ if (name) {
+ /* we can't use getname_kernel() due to size limits */
+ size_t len = strlen(name->name) + 1;
+ struct filename *new = __getname();
+
+ if (unlikely(!new))
+ goto out;
+
+ if (len <= (PATH_MAX - sizeof(*new))) {
+ new->name = (char *)(new) + sizeof(*new);
+ new->separate = false;
+ } else if (len <= PATH_MAX) {
+ /* this looks odd, but is due to final_putname() */
+ struct filename *new2;
+ new2 = kmalloc(sizeof(*new2), GFP_KERNEL);
+ if (unlikely(!new2)) {
+ __putname(new);
+ goto out;
+ }
+ new2->name = (char *)new;
+ new2->separate = true;
+ new = new2;
+ } else {
+ /* we should never get here, but let's be safe */
+ __putname(new);
+ goto out;
+ }
+ strlcpy((char *)new->name, name->name, len);
+ new->uptr = NULL;
+ new->aname = n;
+ n->name = new;
+ n->name_put = true;
+ }
out:
if (parent) {
n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6594e457a25..a64e7a207d2b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -163,7 +163,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
- module_free(NULL, hdr);
+ module_memfree(hdr);
}
#endif /* CONFIG_BPF_JIT */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 1adf62b39b96..07ce18ca71e0 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -27,6 +27,9 @@
* version 2. This program is licensed "as is" without any warranty of any
* kind, whether express or implied.
*/
+
+#define pr_fmt(fmt) "KGDB: " fmt
+
#include <linux/pid_namespace.h>
#include <linux/clocksource.h>
#include <linux/serial_core.h>
@@ -196,8 +199,8 @@ int __weak kgdb_validate_break_address(unsigned long addr)
return err;
err = kgdb_arch_remove_breakpoint(&tmp);
if (err)
- printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
- "memory destroyed at: %lx", addr);
+ pr_err("Critical breakpoint error, kernel memory destroyed at: %lx\n",
+ addr);
return err;
}
@@ -256,8 +259,8 @@ int dbg_activate_sw_breakpoints(void)
error = kgdb_arch_set_breakpoint(&kgdb_break[i]);
if (error) {
ret = error;
- printk(KERN_INFO "KGDB: BP install failed: %lx",
- kgdb_break[i].bpt_addr);
+ pr_info("BP install failed: %lx\n",
+ kgdb_break[i].bpt_addr);
continue;
}
@@ -319,8 +322,8 @@ int dbg_deactivate_sw_breakpoints(void)
continue;
error = kgdb_arch_remove_breakpoint(&kgdb_break[i]);
if (error) {
- printk(KERN_INFO "KGDB: BP remove failed: %lx\n",
- kgdb_break[i].bpt_addr);
+ pr_info("BP remove failed: %lx\n",
+ kgdb_break[i].bpt_addr);
ret = error;
}
@@ -367,7 +370,7 @@ int dbg_remove_all_break(void)
goto setundefined;
error = kgdb_arch_remove_breakpoint(&kgdb_break[i]);
if (error)
- printk(KERN_ERR "KGDB: breakpoint remove failed: %lx\n",
+ pr_err("breakpoint remove failed: %lx\n",
kgdb_break[i].bpt_addr);
setundefined:
kgdb_break[i].state = BP_UNDEFINED;
@@ -400,9 +403,9 @@ static int kgdb_io_ready(int print_wait)
if (print_wait) {
#ifdef CONFIG_KGDB_KDB
if (!dbg_kdb_mode)
- printk(KERN_CRIT "KGDB: waiting... or $3#33 for KDB\n");
+ pr_crit("waiting... or $3#33 for KDB\n");
#else
- printk(KERN_CRIT "KGDB: Waiting for remote debugger\n");
+ pr_crit("Waiting for remote debugger\n");
#endif
}
return 1;
@@ -430,8 +433,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
exception_level = 0;
kgdb_skipexception(ks->ex_vector, ks->linux_regs);
dbg_activate_sw_breakpoints();
- printk(KERN_CRIT "KGDB: re-enter error: breakpoint removed %lx\n",
- addr);
+ pr_crit("re-enter error: breakpoint removed %lx\n", addr);
WARN_ON_ONCE(1);
return 1;
@@ -444,7 +446,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
panic("Recursive entry to debugger");
}
- printk(KERN_CRIT "KGDB: re-enter exception: ALL breakpoints killed\n");
+ pr_crit("re-enter exception: ALL breakpoints killed\n");
#ifdef CONFIG_KGDB_KDB
/* Allow kdb to debug itself one level */
return 0;
@@ -471,6 +473,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
int cpu;
int trace_on = 0;
int online_cpus = num_online_cpus();
+ u64 time_left;
kgdb_info[ks->cpu].enter_kgdb++;
kgdb_info[ks->cpu].exception_state |= exception_state;
@@ -595,9 +598,13 @@ return_normal:
/*
* Wait for the other CPUs to be notified and be waiting for us:
*/
- while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
- atomic_read(&slaves_in_kgdb)) != online_cpus)
+ time_left = loops_per_jiffy * HZ;
+ while (kgdb_do_roundup && --time_left &&
+ (atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) !=
+ online_cpus)
cpu_relax();
+ if (!time_left)
+ pr_crit("KGDB: Timed out waiting for secondary CPUs.\n");
/*
* At this point the primary processor is completely
@@ -795,15 +802,15 @@ static struct console kgdbcons = {
static void sysrq_handle_dbg(int key)
{
if (!dbg_io_ops) {
- printk(KERN_CRIT "ERROR: No KGDB I/O module available\n");
+ pr_crit("ERROR: No KGDB I/O module available\n");
return;
}
if (!kgdb_connected) {
#ifdef CONFIG_KGDB_KDB
if (!dbg_kdb_mode)
- printk(KERN_CRIT "KGDB or $3#33 for KDB\n");
+ pr_crit("KGDB or $3#33 for KDB\n");
#else
- printk(KERN_CRIT "Entering KGDB\n");
+ pr_crit("Entering KGDB\n");
#endif
}
@@ -945,7 +952,7 @@ static void kgdb_initial_breakpoint(void)
{
kgdb_break_asap = 0;
- printk(KERN_CRIT "kgdb: Waiting for connection from remote gdb...\n");
+ pr_crit("Waiting for connection from remote gdb...\n");
kgdb_breakpoint();
}
@@ -964,8 +971,7 @@ int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
if (dbg_io_ops) {
spin_unlock(&kgdb_registration_lock);
- printk(KERN_ERR "kgdb: Another I/O driver is already "
- "registered with KGDB.\n");
+ pr_err("Another I/O driver is already registered with KGDB\n");
return -EBUSY;
}
@@ -981,8 +987,7 @@ int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
spin_unlock(&kgdb_registration_lock);
- printk(KERN_INFO "kgdb: Registered I/O driver %s.\n",
- new_dbg_io_ops->name);
+ pr_info("Registered I/O driver %s\n", new_dbg_io_ops->name);
/* Arm KGDB now. */
kgdb_register_callbacks();
@@ -1017,8 +1022,7 @@ void kgdb_unregister_io_module(struct kgdb_io *old_dbg_io_ops)
spin_unlock(&kgdb_registration_lock);
- printk(KERN_INFO
- "kgdb: Unregistered I/O driver %s, debugger disabled.\n",
+ pr_info("Unregistered I/O driver %s, debugger disabled\n",
old_dbg_io_ops->name);
}
EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index b20d544f20c2..e1dbf4a2c69e 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -531,22 +531,29 @@ void __init kdb_initbptab(void)
for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++)
bp->bp_free = 1;
- kdb_register_repeat("bp", kdb_bp, "[<vaddr>]",
- "Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("bl", kdb_bp, "[<vaddr>]",
- "Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("bp", kdb_bp, "[<vaddr>]",
+ "Set/Display breakpoints", 0,
+ KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("bl", kdb_bp, "[<vaddr>]",
+ "Display breakpoints", 0,
+ KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT)
- kdb_register_repeat("bph", kdb_bp, "[<vaddr>]",
- "[datar [length]|dataw [length]] Set hw brk", 0, KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("bc", kdb_bc, "<bpnum>",
- "Clear Breakpoint", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("be", kdb_bc, "<bpnum>",
- "Enable Breakpoint", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("bd", kdb_bc, "<bpnum>",
- "Disable Breakpoint", 0, KDB_REPEAT_NONE);
-
- kdb_register_repeat("ss", kdb_ss, "",
- "Single Step", 1, KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("bph", kdb_bp, "[<vaddr>]",
+ "[datar [length]|dataw [length]] Set hw brk", 0,
+ KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("bc", kdb_bc, "<bpnum>",
+ "Clear Breakpoint", 0,
+ KDB_ENABLE_FLOW_CTRL);
+ kdb_register_flags("be", kdb_bc, "<bpnum>",
+ "Enable Breakpoint", 0,
+ KDB_ENABLE_FLOW_CTRL);
+ kdb_register_flags("bd", kdb_bc, "<bpnum>",
+ "Disable Breakpoint", 0,
+ KDB_ENABLE_FLOW_CTRL);
+
+ kdb_register_flags("ss", kdb_ss, "",
+ "Single Step", 1,
+ KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
/*
* Architecture dependent initialization.
*/
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index 8859ca34dcfe..15e1a7af5dd0 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -129,6 +129,10 @@ int kdb_stub(struct kgdb_state *ks)
ks->pass_exception = 1;
KDB_FLAG_SET(CATASTROPHIC);
}
+ /* set CATASTROPHIC if the system contains unresponsive processors */
+ for_each_online_cpu(i)
+ if (!kgdb_info[i].enter_kgdb)
+ KDB_FLAG_SET(CATASTROPHIC);
if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
KDB_STATE_CLEAR(SSBPT);
KDB_STATE_CLEAR(DOING_SS);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 379650b984f8..7b40c5f07dce 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -12,6 +12,7 @@
*/
#include <linux/ctype.h>
+#include <linux/types.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/kmsg_dump.h>
@@ -23,6 +24,7 @@
#include <linux/vmalloc.h>
#include <linux/atomic.h>
#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/kallsyms.h>
@@ -42,6 +44,12 @@
#include <linux/slab.h>
#include "kdb_private.h"
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "kdb."
+
+static int kdb_cmd_enabled = CONFIG_KDB_DEFAULT_ENABLE;
+module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600);
+
#define GREP_LEN 256
char kdb_grep_string[GREP_LEN];
int kdb_grepping_flag;
@@ -121,6 +129,7 @@ static kdbmsg_t kdbmsgs[] = {
KDBMSG(BADLENGTH, "Invalid length field"),
KDBMSG(NOBP, "No Breakpoint exists"),
KDBMSG(BADADDR, "Invalid address"),
+ KDBMSG(NOPERM, "Permission denied"),
};
#undef KDBMSG
@@ -188,6 +197,26 @@ struct task_struct *kdb_curr_task(int cpu)
}
/*
+ * Check whether the flags of the current command and the permissions
+ * of the kdb console has allow a command to be run.
+ */
+static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions,
+ bool no_args)
+{
+ /* permissions comes from userspace so needs massaging slightly */
+ permissions &= KDB_ENABLE_MASK;
+ permissions |= KDB_ENABLE_ALWAYS_SAFE;
+
+ /* some commands change group when launched with no arguments */
+ if (no_args)
+ permissions |= permissions << KDB_ENABLE_NO_ARGS_SHIFT;
+
+ flags |= KDB_ENABLE_ALL;
+
+ return permissions & flags;
+}
+
+/*
* kdbgetenv - This function will return the character string value of
* an environment variable.
* Parameters:
@@ -476,6 +505,15 @@ int kdbgetaddrarg(int argc, const char **argv, int *nextarg,
kdb_symtab_t symtab;
/*
+ * If the enable flags prohibit both arbitrary memory access
+ * and flow control then there are no reasonable grounds to
+ * provide symbol lookup.
+ */
+ if (!kdb_check_flags(KDB_ENABLE_MEM_READ | KDB_ENABLE_FLOW_CTRL,
+ kdb_cmd_enabled, false))
+ return KDB_NOPERM;
+
+ /*
* Process arguments which follow the following syntax:
*
* symbol | numeric-address [+/- numeric-offset]
@@ -641,8 +679,13 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
if (!s->count)
s->usable = 0;
if (s->usable)
- kdb_register(s->name, kdb_exec_defcmd,
- s->usage, s->help, 0);
+ /* macros are always safe because when executed each
+ * internal command re-enters kdb_parse() and is
+ * safety checked individually.
+ */
+ kdb_register_flags(s->name, kdb_exec_defcmd, s->usage,
+ s->help, 0,
+ KDB_ENABLE_ALWAYS_SAFE);
return 0;
}
if (!s->usable)
@@ -1003,25 +1046,22 @@ int kdb_parse(const char *cmdstr)
if (i < kdb_max_commands) {
int result;
+
+ if (!kdb_check_flags(tp->cmd_flags, kdb_cmd_enabled, argc <= 1))
+ return KDB_NOPERM;
+
KDB_STATE_SET(CMD);
result = (*tp->cmd_func)(argc-1, (const char **)argv);
if (result && ignore_errors && result > KDB_CMD_GO)
result = 0;
KDB_STATE_CLEAR(CMD);
- switch (tp->cmd_repeat) {
- case KDB_REPEAT_NONE:
- argc = 0;
- if (argv[0])
- *(argv[0]) = '\0';
- break;
- case KDB_REPEAT_NO_ARGS:
- argc = 1;
- if (argv[1])
- *(argv[1]) = '\0';
- break;
- case KDB_REPEAT_WITH_ARGS:
- break;
- }
+
+ if (tp->cmd_flags & KDB_REPEAT_WITH_ARGS)
+ return result;
+
+ argc = tp->cmd_flags & KDB_REPEAT_NO_ARGS ? 1 : 0;
+ if (argv[argc])
+ *(argv[argc]) = '\0';
return result;
}
@@ -1921,10 +1961,14 @@ static int kdb_rm(int argc, const char **argv)
*/
static int kdb_sr(int argc, const char **argv)
{
+ bool check_mask =
+ !kdb_check_flags(KDB_ENABLE_ALL, kdb_cmd_enabled, false);
+
if (argc != 1)
return KDB_ARGCOUNT;
+
kdb_trap_printk++;
- __handle_sysrq(*argv[1], false);
+ __handle_sysrq(*argv[1], check_mask);
kdb_trap_printk--;
return 0;
@@ -1979,7 +2023,7 @@ static int kdb_lsmod(int argc, const char **argv)
kdb_printf("%-20s%8u 0x%p ", mod->name,
mod->core_size, (void *)mod);
#ifdef CONFIG_MODULE_UNLOAD
- kdb_printf("%4ld ", module_refcount(mod));
+ kdb_printf("%4d ", module_refcount(mod));
#endif
if (mod->state == MODULE_STATE_GOING)
kdb_printf(" (Unloading)");
@@ -2157,6 +2201,8 @@ static void kdb_cpu_status(void)
for (start_cpu = -1, i = 0; i < NR_CPUS; i++) {
if (!cpu_online(i)) {
state = 'F'; /* cpu is offline */
+ } else if (!kgdb_info[i].enter_kgdb) {
+ state = 'D'; /* cpu is online but unresponsive */
} else {
state = ' '; /* cpu is responding to kdb */
if (kdb_task_state_char(KDB_TSK(i)) == 'I')
@@ -2210,7 +2256,7 @@ static int kdb_cpu(int argc, const char **argv)
/*
* Validate cpunum
*/
- if ((cpunum > NR_CPUS) || !cpu_online(cpunum))
+ if ((cpunum > NR_CPUS) || !kgdb_info[cpunum].enter_kgdb)
return KDB_BADCPUNUM;
dbg_switch_cpu = cpunum;
@@ -2375,6 +2421,8 @@ static int kdb_help(int argc, const char **argv)
return 0;
if (!kt->cmd_name)
continue;
+ if (!kdb_check_flags(kt->cmd_flags, kdb_cmd_enabled, true))
+ continue;
if (strlen(kt->cmd_usage) > 20)
space = "\n ";
kdb_printf("%-15.15s %-20s%s%s\n", kt->cmd_name,
@@ -2629,7 +2677,7 @@ static int kdb_grep_help(int argc, const char **argv)
}
/*
- * kdb_register_repeat - This function is used to register a kernel
+ * kdb_register_flags - This function is used to register a kernel
* debugger command.
* Inputs:
* cmd Command name
@@ -2641,12 +2689,12 @@ static int kdb_grep_help(int argc, const char **argv)
* zero for success, one if a duplicate command.
*/
#define kdb_command_extend 50 /* arbitrary */
-int kdb_register_repeat(char *cmd,
- kdb_func_t func,
- char *usage,
- char *help,
- short minlen,
- kdb_repeat_t repeat)
+int kdb_register_flags(char *cmd,
+ kdb_func_t func,
+ char *usage,
+ char *help,
+ short minlen,
+ kdb_cmdflags_t flags)
{
int i;
kdbtab_t *kp;
@@ -2694,19 +2742,18 @@ int kdb_register_repeat(char *cmd,
kp->cmd_func = func;
kp->cmd_usage = usage;
kp->cmd_help = help;
- kp->cmd_flags = 0;
kp->cmd_minlen = minlen;
- kp->cmd_repeat = repeat;
+ kp->cmd_flags = flags;
return 0;
}
-EXPORT_SYMBOL_GPL(kdb_register_repeat);
+EXPORT_SYMBOL_GPL(kdb_register_flags);
/*
* kdb_register - Compatibility register function for commands that do
* not need to specify a repeat state. Equivalent to
- * kdb_register_repeat with KDB_REPEAT_NONE.
+ * kdb_register_flags with flags set to 0.
* Inputs:
* cmd Command name
* func Function to execute the command
@@ -2721,8 +2768,7 @@ int kdb_register(char *cmd,
char *help,
short minlen)
{
- return kdb_register_repeat(cmd, func, usage, help, minlen,
- KDB_REPEAT_NONE);
+ return kdb_register_flags(cmd, func, usage, help, minlen, 0);
}
EXPORT_SYMBOL_GPL(kdb_register);
@@ -2764,80 +2810,109 @@ static void __init kdb_inittab(void)
for_each_kdbcmd(kp, i)
kp->cmd_name = NULL;
- kdb_register_repeat("md", kdb_md, "<vaddr>",
+ kdb_register_flags("md", kdb_md, "<vaddr>",
"Display Memory Contents, also mdWcN, e.g. md8c1", 1,
- KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("mdr", kdb_md, "<vaddr> <bytes>",
- "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("mdp", kdb_md, "<paddr> <bytes>",
- "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("mds", kdb_md, "<vaddr>",
- "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("mm", kdb_mm, "<vaddr> <contents>",
- "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS);
- kdb_register_repeat("go", kdb_go, "[<vaddr>]",
- "Continue Execution", 1, KDB_REPEAT_NONE);
- kdb_register_repeat("rd", kdb_rd, "",
- "Display Registers", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("rm", kdb_rm, "<reg> <contents>",
- "Modify Registers", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("ef", kdb_ef, "<vaddr>",
- "Display exception frame", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("bt", kdb_bt, "[<vaddr>]",
- "Stack traceback", 1, KDB_REPEAT_NONE);
- kdb_register_repeat("btp", kdb_bt, "<pid>",
- "Display stack for process <pid>", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
- "Backtrace all processes matching state flag", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("btc", kdb_bt, "",
- "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("btt", kdb_bt, "<vaddr>",
+ KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("mdr", kdb_md, "<vaddr> <bytes>",
+ "Display Raw Memory", 0,
+ KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("mdp", kdb_md, "<paddr> <bytes>",
+ "Display Physical Memory", 0,
+ KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("mds", kdb_md, "<vaddr>",
+ "Display Memory Symbolically", 0,
+ KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("mm", kdb_mm, "<vaddr> <contents>",
+ "Modify Memory Contents", 0,
+ KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS);
+ kdb_register_flags("go", kdb_go, "[<vaddr>]",
+ "Continue Execution", 1,
+ KDB_ENABLE_REG_WRITE | KDB_ENABLE_ALWAYS_SAFE_NO_ARGS);
+ kdb_register_flags("rd", kdb_rd, "",
+ "Display Registers", 0,
+ KDB_ENABLE_REG_READ);
+ kdb_register_flags("rm", kdb_rm, "<reg> <contents>",
+ "Modify Registers", 0,
+ KDB_ENABLE_REG_WRITE);
+ kdb_register_flags("ef", kdb_ef, "<vaddr>",
+ "Display exception frame", 0,
+ KDB_ENABLE_MEM_READ);
+ kdb_register_flags("bt", kdb_bt, "[<vaddr>]",
+ "Stack traceback", 1,
+ KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS);
+ kdb_register_flags("btp", kdb_bt, "<pid>",
+ "Display stack for process <pid>", 0,
+ KDB_ENABLE_INSPECT);
+ kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
+ "Backtrace all processes matching state flag", 0,
+ KDB_ENABLE_INSPECT);
+ kdb_register_flags("btc", kdb_bt, "",
+ "Backtrace current process on each cpu", 0,
+ KDB_ENABLE_INSPECT);
+ kdb_register_flags("btt", kdb_bt, "<vaddr>",
"Backtrace process given its struct task address", 0,
- KDB_REPEAT_NONE);
- kdb_register_repeat("env", kdb_env, "",
- "Show environment variables", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("set", kdb_set, "",
- "Set environment variables", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("help", kdb_help, "",
- "Display Help Message", 1, KDB_REPEAT_NONE);
- kdb_register_repeat("?", kdb_help, "",
- "Display Help Message", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("cpu", kdb_cpu, "<cpunum>",
- "Switch to new cpu", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("kgdb", kdb_kgdb, "",
- "Enter kgdb mode", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("ps", kdb_ps, "[<flags>|A]",
- "Display active task list", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("pid", kdb_pid, "<pidnum>",
- "Switch to another task", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("reboot", kdb_reboot, "",
- "Reboot the machine immediately", 0, KDB_REPEAT_NONE);
+ KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS);
+ kdb_register_flags("env", kdb_env, "",
+ "Show environment variables", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
+ kdb_register_flags("set", kdb_set, "",
+ "Set environment variables", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
+ kdb_register_flags("help", kdb_help, "",
+ "Display Help Message", 1,
+ KDB_ENABLE_ALWAYS_SAFE);
+ kdb_register_flags("?", kdb_help, "",
+ "Display Help Message", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
+ kdb_register_flags("cpu", kdb_cpu, "<cpunum>",
+ "Switch to new cpu", 0,
+ KDB_ENABLE_ALWAYS_SAFE_NO_ARGS);
+ kdb_register_flags("kgdb", kdb_kgdb, "",
+ "Enter kgdb mode", 0, 0);
+ kdb_register_flags("ps", kdb_ps, "[<flags>|A]",
+ "Display active task list", 0,
+ KDB_ENABLE_INSPECT);
+ kdb_register_flags("pid", kdb_pid, "<pidnum>",
+ "Switch to another task", 0,
+ KDB_ENABLE_INSPECT);
+ kdb_register_flags("reboot", kdb_reboot, "",
+ "Reboot the machine immediately", 0,
+ KDB_ENABLE_REBOOT);
#if defined(CONFIG_MODULES)
- kdb_register_repeat("lsmod", kdb_lsmod, "",
- "List loaded kernel modules", 0, KDB_REPEAT_NONE);
+ kdb_register_flags("lsmod", kdb_lsmod, "",
+ "List loaded kernel modules", 0,
+ KDB_ENABLE_INSPECT);
#endif
#if defined(CONFIG_MAGIC_SYSRQ)
- kdb_register_repeat("sr", kdb_sr, "<key>",
- "Magic SysRq key", 0, KDB_REPEAT_NONE);
+ kdb_register_flags("sr", kdb_sr, "<key>",
+ "Magic SysRq key", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
#endif
#if defined(CONFIG_PRINTK)
- kdb_register_repeat("dmesg", kdb_dmesg, "[lines]",
- "Display syslog buffer", 0, KDB_REPEAT_NONE);
+ kdb_register_flags("dmesg", kdb_dmesg, "[lines]",
+ "Display syslog buffer", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
#endif
if (arch_kgdb_ops.enable_nmi) {
- kdb_register_repeat("disable_nmi", kdb_disable_nmi, "",
- "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE);
- }
- kdb_register_repeat("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
- "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("kill", kdb_kill, "<-signal> <pid>",
- "Send a signal to a process", 0, KDB_REPEAT_NONE);
- kdb_register_repeat("summary", kdb_summary, "",
- "Summarize the system", 4, KDB_REPEAT_NONE);
- kdb_register_repeat("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
- "Display per_cpu variables", 3, KDB_REPEAT_NONE);
- kdb_register_repeat("grephelp", kdb_grep_help, "",
- "Display help on | grep", 0, KDB_REPEAT_NONE);
+ kdb_register_flags("disable_nmi", kdb_disable_nmi, "",
+ "Disable NMI entry to KDB", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
+ }
+ kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
+ "Define a set of commands, down to endefcmd", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
+ kdb_register_flags("kill", kdb_kill, "<-signal> <pid>",
+ "Send a signal to a process", 0,
+ KDB_ENABLE_SIGNAL);
+ kdb_register_flags("summary", kdb_summary, "",
+ "Summarize the system", 4,
+ KDB_ENABLE_ALWAYS_SAFE);
+ kdb_register_flags("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
+ "Display per_cpu variables", 3,
+ KDB_ENABLE_MEM_READ);
+ kdb_register_flags("grephelp", kdb_grep_help, "",
+ "Display help on | grep", 0,
+ KDB_ENABLE_ALWAYS_SAFE);
}
/* Execute any commands defined in kdb_cmds. */
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 7afd3c8c41d5..eaacd1693954 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -172,10 +172,9 @@ typedef struct _kdbtab {
kdb_func_t cmd_func; /* Function to execute command */
char *cmd_usage; /* Usage String for this command */
char *cmd_help; /* Help message for this command */
- short cmd_flags; /* Parsing flags */
short cmd_minlen; /* Minimum legal # command
* chars required */
- kdb_repeat_t cmd_repeat; /* Does command auto repeat on enter? */
+ kdb_cmdflags_t cmd_flags; /* Command behaviour flags */
} kdbtab_t;
extern int kdb_bt(int, const char **); /* KDB display back trace */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2bebc..882f835a0d85 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
}
static void perf_sample_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs)
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
{
- if (!user_mode(regs)) {
- if (current->mm)
- regs = task_pt_regs(current);
- else
- regs = NULL;
- }
-
- if (regs) {
- regs_user->abi = perf_reg_abi(current);
+ if (user_mode(regs)) {
+ regs_user->abi = perf_reg_abi(current);
regs_user->regs = regs;
+ } else if (current->mm) {
+ perf_get_regs_user(regs_user, regs, regs_user_copy);
} else {
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
}
if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
- perf_sample_regs_user(&data->regs_user, regs);
+ perf_sample_regs_user(&data->regs_user, regs,
+ &data->regs_user_copy);
if (sample_type & PERF_SAMPLE_REGS_USER) {
/* regs dump ABI info */
diff --git a/kernel/exit.c b/kernel/exit.c
index 1ea4369890a3..6806c55475ee 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1287,9 +1287,15 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
static int wait_consider_task(struct wait_opts *wo, int ptrace,
struct task_struct *p)
{
+ /*
+ * We can race with wait_task_zombie() from another thread.
+ * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
+ * can't confuse the checks below.
+ */
+ int exit_state = ACCESS_ONCE(p->exit_state);
int ret;
- if (unlikely(p->exit_state == EXIT_DEAD))
+ if (unlikely(exit_state == EXIT_DEAD))
return 0;
ret = eligible_child(wo, p);
@@ -1310,7 +1316,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
return 0;
}
- if (unlikely(p->exit_state == EXIT_TRACE)) {
+ if (unlikely(exit_state == EXIT_TRACE)) {
/*
* ptrace == 0 means we are the natural parent. In this case
* we should clear notask_error, debugger will notify us.
@@ -1337,7 +1343,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
}
/* slay zombie? */
- if (p->exit_state == EXIT_ZOMBIE) {
+ if (exit_state == EXIT_ZOMBIE) {
/* we don't reap group leaders with subthreads */
if (!delay_group_leader(p)) {
/*
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 06f58309fed2..ee619929cf90 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -127,7 +127,7 @@ static void *alloc_insn_page(void)
static void free_insn_page(void *page)
{
- module_free(NULL, page);
+ module_memfree(page);
}
struct kprobe_insn_cache kprobe_insn_slots = {
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 5cf6731b98e9..3ef3736002d8 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -80,13 +80,13 @@ void debug_mutex_unlock(struct mutex *lock)
DEBUG_LOCKS_WARN_ON(lock->owner != current);
DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
- mutex_clear_owner(lock);
}
/*
* __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
* mutexes so that we can do it here after we've verified state.
*/
+ mutex_clear_owner(lock);
atomic_set(&lock->count, 1);
}
diff --git a/kernel/module.c b/kernel/module.c
index 3965511ae133..d856e96a3cce 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -772,9 +772,18 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
return 0;
}
-unsigned long module_refcount(struct module *mod)
+/**
+ * module_refcount - return the refcount or -1 if unloading
+ *
+ * @mod: the module we're checking
+ *
+ * Returns:
+ * -1 if the module is in the process of unloading
+ * otherwise the number of references in the kernel to the module
+ */
+int module_refcount(struct module *mod)
{
- return (unsigned long)atomic_read(&mod->refcnt) - MODULE_REF_BASE;
+ return atomic_read(&mod->refcnt) - MODULE_REF_BASE;
}
EXPORT_SYMBOL(module_refcount);
@@ -856,7 +865,7 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod)
struct module_use *use;
int printed_something = 0;
- seq_printf(m, " %lu ", module_refcount(mod));
+ seq_printf(m, " %i ", module_refcount(mod));
/*
* Always include a trailing , so userspace can differentiate
@@ -908,7 +917,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr);
static ssize_t show_refcnt(struct module_attribute *mattr,
struct module_kobject *mk, char *buffer)
{
- return sprintf(buffer, "%lu\n", module_refcount(mk->mod));
+ return sprintf(buffer, "%i\n", module_refcount(mk->mod));
}
static struct module_attribute modinfo_refcnt =
@@ -1795,7 +1804,7 @@ static void unset_module_core_ro_nx(struct module *mod) { }
static void unset_module_init_ro_nx(struct module *mod) { }
#endif
-void __weak module_free(struct module *mod, void *module_region)
+void __weak module_memfree(void *module_region)
{
vfree(module_region);
}
@@ -1804,6 +1813,10 @@ void __weak module_arch_cleanup(struct module *mod)
{
}
+void __weak module_arch_freeing_init(struct module *mod)
+{
+}
+
/* Free a module, remove from lists, etc. */
static void free_module(struct module *mod)
{
@@ -1841,7 +1854,8 @@ static void free_module(struct module *mod)
/* This may be NULL, but that's OK */
unset_module_init_ro_nx(mod);
- module_free(mod, mod->module_init);
+ module_arch_freeing_init(mod);
+ module_memfree(mod->module_init);
kfree(mod->args);
percpu_modfree(mod);
@@ -1850,7 +1864,7 @@ static void free_module(struct module *mod)
/* Finally, free the core (containing the module structure) */
unset_module_core_ro_nx(mod);
- module_free(mod, mod->module_core);
+ module_memfree(mod->module_core);
#ifdef CONFIG_MPU
update_protections(current->mm);
@@ -2785,7 +2799,7 @@ static int move_module(struct module *mod, struct load_info *info)
*/
kmemleak_ignore(ptr);
if (!ptr) {
- module_free(mod, mod->module_core);
+ module_memfree(mod->module_core);
return -ENOMEM;
}
memset(ptr, 0, mod->init_size);
@@ -2930,8 +2944,9 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
static void module_deallocate(struct module *mod, struct load_info *info)
{
percpu_modfree(mod);
- module_free(mod, mod->module_init);
- module_free(mod, mod->module_core);
+ module_arch_freeing_init(mod);
+ module_memfree(mod->module_init);
+ module_memfree(mod->module_core);
}
int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -2983,10 +2998,31 @@ static void do_mod_ctors(struct module *mod)
#endif
}
+/* For freeing module_init on success, in case kallsyms traversing */
+struct mod_initfree {
+ struct rcu_head rcu;
+ void *module_init;
+};
+
+static void do_free_init(struct rcu_head *head)
+{
+ struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
+ module_memfree(m->module_init);
+ kfree(m);
+}
+
/* This is where the real work happens */
static int do_init_module(struct module *mod)
{
int ret = 0;
+ struct mod_initfree *freeinit;
+
+ freeinit = kmalloc(sizeof(*freeinit), GFP_KERNEL);
+ if (!freeinit) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ freeinit->module_init = mod->module_init;
/*
* We want to find out whether @mod uses async during init. Clear
@@ -2999,18 +3035,7 @@ static int do_init_module(struct module *mod)
if (mod->init != NULL)
ret = do_one_initcall(mod->init);
if (ret < 0) {
- /*
- * Init routine failed: abort. Try to protect us from
- * buggy refcounters.
- */
- mod->state = MODULE_STATE_GOING;
- synchronize_sched();
- module_put(mod);
- blocking_notifier_call_chain(&module_notify_list,
- MODULE_STATE_GOING, mod);
- free_module(mod);
- wake_up_all(&module_wq);
- return ret;
+ goto fail_free_freeinit;
}
if (ret > 0) {
pr_warn("%s: '%s'->init suspiciously returned %d, it should "
@@ -3055,15 +3080,35 @@ static int do_init_module(struct module *mod)
mod->strtab = mod->core_strtab;
#endif
unset_module_init_ro_nx(mod);
- module_free(mod, mod->module_init);
+ module_arch_freeing_init(mod);
mod->module_init = NULL;
mod->init_size = 0;
mod->init_ro_size = 0;
mod->init_text_size = 0;
+ /*
+ * We want to free module_init, but be aware that kallsyms may be
+ * walking this with preempt disabled. In all the failure paths,
+ * we call synchronize_rcu/synchronize_sched, but we don't want
+ * to slow down the success path, so use actual RCU here.
+ */
+ call_rcu(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
wake_up_all(&module_wq);
return 0;
+
+fail_free_freeinit:
+ kfree(freeinit);
+fail:
+ /* Try to protect us from buggy refcounters. */
+ mod->state = MODULE_STATE_GOING;
+ synchronize_sched();
+ module_put(mod);
+ blocking_notifier_call_chain(&module_notify_list,
+ MODULE_STATE_GOING, mod);
+ free_module(mod);
+ wake_up_all(&module_wq);
+ return ret;
}
static int may_init_module(void)
diff --git a/kernel/params.c b/kernel/params.c
index 0af9b2c4e56c..728e05b167de 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -642,12 +642,15 @@ static __modinit int add_sysfs_param(struct module_kobject *mk,
mk->mp->grp.attrs = new_attrs;
/* Tack new one on the end. */
+ memset(&mk->mp->attrs[mk->mp->num], 0, sizeof(mk->mp->attrs[0]));
sysfs_attr_init(&mk->mp->attrs[mk->mp->num].mattr.attr);
mk->mp->attrs[mk->mp->num].param = kp;
mk->mp->attrs[mk->mp->num].mattr.show = param_attr_show;
/* Do not allow runtime DAC changes to make param writable. */
if ((kp->perm & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0)
mk->mp->attrs[mk->mp->num].mattr.store = param_attr_store;
+ else
+ mk->mp->attrs[mk->mp->num].mattr.store = NULL;
mk->mp->attrs[mk->mp->num].mattr.attr.name = (char *)name;
mk->mp->attrs[mk->mp->num].mattr.attr.mode = kp->perm;
mk->mp->num++;
diff --git a/kernel/range.c b/kernel/range.c
index 322ea8e93e4b..82cfc285b046 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -113,12 +113,12 @@ 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;
+ if (r1->start < r2->start)
+ return -1;
+ if (r1->start > r2->start)
+ return 1;
+ return 0;
}
int clean_sort_range(struct range *range, int az)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b78add6..c0accc00566e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7113,9 +7113,6 @@ void __init sched_init(void)
#ifdef CONFIG_RT_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
- alloc_size += num_possible_cpus() * cpumask_size();
-#endif
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
@@ -7135,13 +7132,13 @@ void __init sched_init(void)
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_RT_GROUP_SCHED */
+ }
#ifdef CONFIG_CPUMASK_OFFSTACK
- for_each_possible_cpu(i) {
- per_cpu(load_balance_mask, i) = (void *)ptr;
- ptr += cpumask_size();
- }
-#endif /* CONFIG_CPUMASK_OFFSTACK */
+ for_each_possible_cpu(i) {
+ per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
+ cpumask_size(), GFP_KERNEL, cpu_to_node(i));
}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
init_rt_bandwidth(&def_rt_bandwidth,
global_rt_period(), global_rt_runtime());
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e5db8c6feebd..b52092f2636d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -570,24 +570,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
static
int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
{
- int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
- int rorun = dl_se->runtime <= 0;
-
- if (!rorun && !dmiss)
- return 0;
-
- /*
- * If we are beyond our current deadline and we are still
- * executing, then we have already used some of the runtime of
- * the next instance. Thus, if we do not account that, we are
- * stealing bandwidth from the system at each deadline miss!
- */
- if (dmiss) {
- dl_se->runtime = rorun ? dl_se->runtime : 0;
- dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
- }
-
- return 1;
+ return (dl_se->runtime <= 0);
}
extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -826,10 +809,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
* parameters of the task might need updating. Otherwise,
* we want a replenishment of its runtime.
*/
- if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
- replenish_dl_entity(dl_se, pi_se);
- else
+ if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
update_dl_entity(dl_se, pi_se);
+ else if (flags & ENQUEUE_REPLENISH)
+ replenish_dl_entity(dl_se, pi_se);
__enqueue_dl_entity(dl_se);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df2cdf77f899..40667cbf371b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4005,6 +4005,10 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
+ /* init_cfs_bandwidth() was not called */
+ if (!cfs_b->throttled_cfs_rq.next)
+ return;
+
hrtimer_cancel(&cfs_b->period_timer);
hrtimer_cancel(&cfs_b->slack_timer);
}
@@ -4424,7 +4428,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
* wl = S * s'_i; see (2)
*/
if (W > 0 && w < W)
- wl = (w * tg->shares) / W;
+ wl = (w * (long)tg->shares) / W;
else
wl = tg->shares;
diff --git a/kernel/sys.c b/kernel/sys.c
index a8c9f5a7dda6..ea9c88109894 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2210,9 +2210,13 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
up_write(&me->mm->mmap_sem);
break;
case PR_MPX_ENABLE_MANAGEMENT:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
error = MPX_ENABLE_MANAGEMENT(me);
break;
case PR_MPX_DISABLE_MANAGEMENT:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
error = MPX_DISABLE_MANAGEMENT(me);
break;
default:
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 87a346fd6d61..28bf91c60a0b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -633,6 +633,13 @@ int ntp_validate_timex(struct timex *txc)
if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
return -EPERM;
+ if (txc->modes & ADJ_FREQUENCY) {
+ if (LONG_MIN / PPM_SCALE > txc->freq)
+ return -EINVAL;
+ if (LONG_MAX / PPM_SCALE < txc->freq)
+ return -EINVAL;
+ }
+
return 0;
}
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6390517e77d4..2c85b7724af4 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -196,6 +196,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
if (tv) {
if (copy_from_user(&user_tv, tv, sizeof(*tv)))
return -EFAULT;
+
+ if (!timeval_valid(&user_tv))
+ return -EINVAL;
+
new_ts.tv_sec = user_tv.tv_sec;
new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 929a733d302e..224e768bdc73 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2497,12 +2497,14 @@ static void ftrace_run_update_code(int command)
}
static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
- struct ftrace_hash *old_hash)
+ struct ftrace_ops_hash *old_hash)
{
ops->flags |= FTRACE_OPS_FL_MODIFYING;
- ops->old_hash.filter_hash = old_hash;
+ ops->old_hash.filter_hash = old_hash->filter_hash;
+ ops->old_hash.notrace_hash = old_hash->notrace_hash;
ftrace_run_update_code(command);
ops->old_hash.filter_hash = NULL;
+ ops->old_hash.notrace_hash = NULL;
ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
}
@@ -3579,7 +3581,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
static int ftrace_probe_registered;
-static void __enable_ftrace_function_probe(struct ftrace_hash *old_hash)
+static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
{
int ret;
int i;
@@ -3637,6 +3639,7 @@ int
register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data)
{
+ struct ftrace_ops_hash old_hash_ops;
struct ftrace_func_probe *entry;
struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
struct ftrace_hash *old_hash = *orig_hash;
@@ -3658,6 +3661,10 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
mutex_lock(&trace_probe_ops.func_hash->regex_lock);
+ old_hash_ops.filter_hash = old_hash;
+ /* Probes only have filters */
+ old_hash_ops.notrace_hash = NULL;
+
hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
if (!hash) {
count = -ENOMEM;
@@ -3718,7 +3725,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
- __enable_ftrace_function_probe(old_hash);
+ __enable_ftrace_function_probe(&old_hash_ops);
if (!ret)
free_ftrace_hash_rcu(old_hash);
@@ -4006,10 +4013,34 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
}
static void ftrace_ops_update_code(struct ftrace_ops *ops,
- struct ftrace_hash *old_hash)
+ struct ftrace_ops_hash *old_hash)
{
- if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
+ struct ftrace_ops *op;
+
+ if (!ftrace_enabled)
+ return;
+
+ if (ops->flags & FTRACE_OPS_FL_ENABLED) {
ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
+ return;
+ }
+
+ /*
+ * If this is the shared global_ops filter, then we need to
+ * check if there is another ops that shares it, is enabled.
+ * If so, we still need to run the modify code.
+ */
+ if (ops->func_hash != &global_ops.local_hash)
+ return;
+
+ do_for_each_ftrace_op(op, ftrace_ops_list) {
+ if (op->func_hash == &global_ops.local_hash &&
+ op->flags & FTRACE_OPS_FL_ENABLED) {
+ ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash);
+ /* Only need to do this once */
+ return;
+ }
+ } while_for_each_ftrace_op(op);
}
static int
@@ -4017,6 +4048,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
unsigned long ip, int remove, int reset, int enable)
{
struct ftrace_hash **orig_hash;
+ struct ftrace_ops_hash old_hash_ops;
struct ftrace_hash *old_hash;
struct ftrace_hash *hash;
int ret;
@@ -4053,9 +4085,11 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
mutex_lock(&ftrace_lock);
old_hash = *orig_hash;
+ old_hash_ops.filter_hash = ops->func_hash->filter_hash;
+ old_hash_ops.notrace_hash = ops->func_hash->notrace_hash;
ret = ftrace_hash_move(ops, enable, orig_hash, hash);
if (!ret) {
- ftrace_ops_update_code(ops, old_hash);
+ ftrace_ops_update_code(ops, &old_hash_ops);
free_ftrace_hash_rcu(old_hash);
}
mutex_unlock(&ftrace_lock);
@@ -4267,6 +4301,7 @@ static void __init set_ftrace_early_filters(void)
int ftrace_regex_release(struct inode *inode, struct file *file)
{
struct seq_file *m = (struct seq_file *)file->private_data;
+ struct ftrace_ops_hash old_hash_ops;
struct ftrace_iterator *iter;
struct ftrace_hash **orig_hash;
struct ftrace_hash *old_hash;
@@ -4300,10 +4335,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
mutex_lock(&ftrace_lock);
old_hash = *orig_hash;
+ old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash;
+ old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash;
ret = ftrace_hash_move(iter->ops, filter_hash,
orig_hash, iter->hash);
if (!ret) {
- ftrace_ops_update_code(iter->ops, old_hash);
+ ftrace_ops_update_code(iter->ops, &old_hash_ops);
free_ftrace_hash_rcu(old_hash);
}
mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2e767972e99c..4a9079b9f082 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6918,7 +6918,6 @@ void __init trace_init(void)
tracepoint_printk = 0;
}
tracer_alloc_buffers();
- init_ftrace_syscalls();
trace_event_init();
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 366a78a3e61e..b03a0ea77b99 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2429,12 +2429,39 @@ static __init int event_trace_memsetup(void)
return 0;
}
+static __init void
+early_enable_events(struct trace_array *tr, bool disable_first)
+{
+ char *buf = bootup_event_buf;
+ char *token;
+ int ret;
+
+ while (true) {
+ token = strsep(&buf, ",");
+
+ if (!token)
+ break;
+ if (!*token)
+ continue;
+
+ /* Restarting syscalls requires that we stop them first */
+ if (disable_first)
+ ftrace_set_clr_event(tr, token, 0);
+
+ ret = ftrace_set_clr_event(tr, token, 1);
+ if (ret)
+ pr_warn("Failed to enable trace event: %s\n", token);
+
+ /* Put back the comma to allow this to be called again */
+ if (buf)
+ *(buf - 1) = ',';
+ }
+}
+
static __init int event_trace_enable(void)
{
struct trace_array *tr = top_trace_array();
struct ftrace_event_call **iter, *call;
- char *buf = bootup_event_buf;
- char *token;
int ret;
if (!tr)
@@ -2456,18 +2483,7 @@ static __init int event_trace_enable(void)
*/
__trace_early_add_events(tr);
- while (true) {
- token = strsep(&buf, ",");
-
- if (!token)
- break;
- if (!*token)
- continue;
-
- ret = ftrace_set_clr_event(tr, token, 1);
- if (ret)
- pr_warn("Failed to enable trace event: %s\n", token);
- }
+ early_enable_events(tr, false);
trace_printk_start_comm();
@@ -2478,6 +2494,31 @@ static __init int event_trace_enable(void)
return 0;
}
+/*
+ * event_trace_enable() is called from trace_event_init() first to
+ * initialize events and perhaps start any events that are on the
+ * command line. Unfortunately, there are some events that will not
+ * start this early, like the system call tracepoints that need
+ * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable()
+ * is called before pid 1 starts, and this flag is never set, making
+ * the syscall tracepoint never get reached, but the event is enabled
+ * regardless (and not doing anything).
+ */
+static __init int event_trace_enable_again(void)
+{
+ struct trace_array *tr;
+
+ tr = top_trace_array();
+ if (!tr)
+ return -ENODEV;
+
+ early_enable_events(tr, true);
+
+ return 0;
+}
+
+early_initcall(event_trace_enable_again);
+
static __init int event_trace_init(void)
{
struct trace_array *tr;
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index b0b1c44e923a..3ccf5c2c1320 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -132,8 +132,8 @@ static int kdb_ftdump(int argc, const char **argv)
static __init int kdb_ftrace_register(void)
{
- kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
- "Dump ftrace log", 0, KDB_REPEAT_NONE);
+ kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
+ "Dump ftrace log", 0, KDB_ENABLE_ALWAYS_SAFE);
return 0;
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6202b08f1933..beeeac9e0e3e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1841,17 +1841,11 @@ static void pool_mayday_timeout(unsigned long __pool)
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
- *
- * Return:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
*/
-static bool maybe_create_worker(struct worker_pool *pool)
+static void maybe_create_worker(struct worker_pool *pool)
__releases(&pool->lock)
__acquires(&pool->lock)
{
- if (!need_to_create_worker(pool))
- return false;
restart:
spin_unlock_irq(&pool->lock);
@@ -1877,7 +1871,6 @@ restart:
*/
if (need_to_create_worker(pool))
goto restart;
- return true;
}
/**
@@ -1897,16 +1890,14 @@ restart:
* multiple times. Does GFP_KERNEL allocations.
*
* Return:
- * %false if the pool don't need management and the caller can safely start
- * processing works, %true indicates that the function released pool->lock
- * and reacquired it to perform some management function and that the
- * conditions that the caller verified while holding the lock before
- * calling the function might no longer be true.
+ * %false if the pool doesn't need management and the caller can safely
+ * start processing works, %true if management function was performed and
+ * the conditions that the caller verified before calling the function may
+ * no longer be true.
*/
static bool manage_workers(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
- bool ret = false;
/*
* Anyone who successfully grabs manager_arb wins the arbitration
@@ -1919,12 +1910,12 @@ static bool manage_workers(struct worker *worker)
* actual management, the pool may stall indefinitely.
*/
if (!mutex_trylock(&pool->manager_arb))
- return ret;
+ return false;
- ret |= maybe_create_worker(pool);
+ maybe_create_worker(pool);
mutex_unlock(&pool->manager_arb);
- return ret;
+ return true;
}
/**
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-07 21:38:21 +0000