summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c2
-rw-r--r--kernel/bpf/syscall.c25
-rw-r--r--kernel/cgroup.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.c34
-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.c54
-rw-r--r--kernel/sched/deadline.c28
-rw-r--r--kernel/sched/fair.c8
-rw-r--r--kernel/smpboot.c2
-rw-r--r--kernel/sys.c4
-rw-r--r--kernel/time/hrtimer.c2
-rw-r--r--kernel/time/ntp.c7
-rw-r--r--kernel/time/time.c4
-rw-r--r--kernel/trace/trace_kdb.c4
-rw-r--r--kernel/workqueue.c25
25 files changed, 432 insertions, 254 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6594e4..a64e7a2 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/bpf/syscall.c b/kernel/bpf/syscall.c
index 088ac0b..536edc2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -150,7 +150,7 @@ static int map_lookup_elem(union bpf_attr *attr)
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
- void *key, *value;
+ void *key, *value, *ptr;
int err;
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
@@ -169,20 +169,29 @@ static int map_lookup_elem(union bpf_attr *attr)
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
- err = -ENOENT;
- rcu_read_lock();
- value = map->ops->map_lookup_elem(map, key);
+ err = -ENOMEM;
+ value = kmalloc(map->value_size, GFP_USER);
if (!value)
- goto err_unlock;
+ goto free_key;
+
+ rcu_read_lock();
+ ptr = map->ops->map_lookup_elem(map, key);
+ if (ptr)
+ memcpy(value, ptr, map->value_size);
+ rcu_read_unlock();
+
+ err = -ENOENT;
+ if (!ptr)
+ goto free_value;
err = -EFAULT;
if (copy_to_user(uvalue, value, map->value_size) != 0)
- goto err_unlock;
+ goto free_value;
err = 0;
-err_unlock:
- rcu_read_unlock();
+free_value:
+ kfree(value);
free_key:
kfree(key);
err_put:
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index bb263d0..04cfe8a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1909,7 +1909,7 @@ static void cgroup_kill_sb(struct super_block *sb)
*
* And don't kill the default root.
*/
- if (css_has_online_children(&root->cgrp.self) ||
+ if (!list_empty(&root->cgrp.self.children) ||
root == &cgrp_dfl_root)
cgroup_put(&root->cgrp);
else
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 1adf62b..07ce18c 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 b20d544..e1dbf4a 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 8859ca3..15e1a7a 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 379650b..7b40c5f 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 7afd3c8..eaacd16 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 4c1ee7f..19efcf1 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 */
@@ -6779,7 +6776,6 @@ skip_type:
__perf_event_init_context(&cpuctx->ctx);
lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
- cpuctx->ctx.type = cpu_context;
cpuctx->ctx.pmu = pmu;
__perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7423,7 +7419,19 @@ SYSCALL_DEFINE5(perf_event_open,
* task or CPU context:
*/
if (move_group) {
- if (group_leader->ctx->type != ctx->type)
+ /*
+ * Make sure we're both on the same task, or both
+ * per-cpu events.
+ */
+ if (group_leader->ctx->task != ctx->task)
+ goto err_context;
+
+ /*
+ * Make sure we're both events for the same CPU;
+ * grouping events for different CPUs is broken; since
+ * you can never concurrently schedule them anyhow.
+ */
+ if (group_leader->cpu != event->cpu)
goto err_context;
} else {
if (group_leader->ctx != ctx)
diff --git a/kernel/exit.c b/kernel/exit.c
index 1ea4369..6806c55 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 06f5830..ee61992 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 5cf6731..3ef3736 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 3965511..d856e96 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 0af9b2c..728e05b 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 322ea8e..82cfc28 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 b5797b7..5eab11d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1814,6 +1814,10 @@ void __dl_clear_params(struct task_struct *p)
dl_se->dl_period = 0;
dl_se->flags = 0;
dl_se->dl_bw = 0;
+
+ dl_se->dl_throttled = 0;
+ dl_se->dl_new = 1;
+ dl_se->dl_yielded = 0;
}
/*
@@ -1839,7 +1843,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
#endif
RB_CLEAR_NODE(&p->dl.rb_node);
- hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ init_dl_task_timer(&p->dl);
__dl_clear_params(p);
INIT_LIST_HEAD(&p->rt.run_list);
@@ -2049,6 +2053,9 @@ static inline int dl_bw_cpus(int i)
* allocated bandwidth to reflect the new situation.
*
* This function is called while holding p's rq->lock.
+ *
+ * XXX we should delay bw change until the task's 0-lag point, see
+ * __setparam_dl().
*/
static int dl_overflow(struct task_struct *p, int policy,
const struct sched_attr *attr)
@@ -3251,15 +3258,31 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
{
struct sched_dl_entity *dl_se = &p->dl;
- init_dl_task_timer(dl_se);
dl_se->dl_runtime = attr->sched_runtime;
dl_se->dl_deadline = attr->sched_deadline;
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
dl_se->flags = attr->sched_flags;
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
- dl_se->dl_throttled = 0;
- dl_se->dl_new = 1;
- dl_se->dl_yielded = 0;
+
+ /*
+ * Changing the parameters of a task is 'tricky' and we're not doing
+ * the correct thing -- also see task_dead_dl() and switched_from_dl().
+ *
+ * What we SHOULD do is delay the bandwidth release until the 0-lag
+ * point. This would include retaining the task_struct until that time
+ * and change dl_overflow() to not immediately decrement the current
+ * amount.
+ *
+ * Instead we retain the current runtime/deadline and let the new
+ * parameters take effect after the current reservation period lapses.
+ * This is safe (albeit pessimistic) because the 0-lag point is always
+ * before the current scheduling deadline.
+ *
+ * We can still have temporary overloads because we do not delay the
+ * change in bandwidth until that time; so admission control is
+ * not on the safe side. It does however guarantee tasks will never
+ * consume more than promised.
+ */
}
/*
@@ -4642,6 +4665,9 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
struct dl_bw *cur_dl_b;
unsigned long flags;
+ if (!cpumask_weight(cur))
+ return ret;
+
rcu_read_lock_sched();
cur_dl_b = dl_bw_of(cpumask_any(cur));
trial_cpus = cpumask_weight(trial);
@@ -7113,9 +7139,6 @@ 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 +7158,13 @@ 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());
@@ -7295,13 +7318,12 @@ void __might_sleep(const char *file, int line, int preempt_offset)
* since we will exit with TASK_RUNNING make sure we enter with it,
* otherwise we will destroy state.
*/
- if (WARN_ONCE(current->state != TASK_RUNNING,
+ WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
"do not call blocking ops when !TASK_RUNNING; "
"state=%lx set at [<%p>] %pS\n",
current->state,
(void *)current->task_state_change,
- (void *)current->task_state_change))
- __set_current_state(TASK_RUNNING);
+ (void *)current->task_state_change);
___might_sleep(file, line, preempt_offset);
}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e5db8c6..726470d 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);
}
@@ -1111,6 +1094,7 @@ static void task_dead_dl(struct task_struct *p)
* Since we are TASK_DEAD we won't slip out of the domain!
*/
raw_spin_lock_irq(&dl_b->lock);
+ /* XXX we should retain the bw until 0-lag */
dl_b->total_bw -= p->dl.dl_bw;
raw_spin_unlock_irq(&dl_b->lock);
@@ -1631,8 +1615,8 @@ static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
static void switched_from_dl(struct rq *rq, struct task_struct *p)
{
+ /* XXX we should retain the bw until 0-lag */
cancel_dl_timer(rq, p);
-
__dl_clear_params(p);
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df2cdf7..fe331fc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1730,7 +1730,7 @@ static int preferred_group_nid(struct task_struct *p, int nid)
nodes = node_online_map;
for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
unsigned long max_faults = 0;
- nodemask_t max_group;
+ nodemask_t max_group = NODE_MASK_NONE;
int a, b;
/* Are there nodes at this distance from each other? */
@@ -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/smpboot.c b/kernel/smpboot.c
index f032fb5..40190f2 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -280,6 +280,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
unsigned int cpu;
int ret = 0;
+ get_online_cpus();
mutex_lock(&smpboot_threads_lock);
for_each_online_cpu(cpu) {
ret = __smpboot_create_thread(plug_thread, cpu);
@@ -292,6 +293,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
list_add(&plug_thread->list, &hotplug_threads);
out:
mutex_unlock(&smpboot_threads_lock);
+ put_online_cpus();
return ret;
}
EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
diff --git a/kernel/sys.c b/kernel/sys.c
index a8c9f5a..ea9c881 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/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aa..d8c724c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -122,7 +122,7 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
boot = ktime_add(mono, off_boot);
xtim = ktime_add(mono, off_real);
- tai = ktime_add(xtim, off_tai);
+ tai = ktime_add(mono, off_tai);
base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 87a346f..28bf91c 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 6390517..2c85b77 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/trace_kdb.c b/kernel/trace/trace_kdb.c
index b0b1c44..3ccf5c2 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 6202b08..beeeac9 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;
}
/**
OpenPOWER on IntegriCloud