summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bounds.c4
-rw-r--r--kernel/bpf/verifier.c90
-rw-r--r--kernel/cgroup.c6
-rw-r--r--kernel/debug/kdb/kdb_io.c15
-rw-r--r--kernel/debug/kdb/kdb_private.h2
-rw-r--r--kernel/debug/kdb/kdb_support.c14
-rw-r--r--kernel/events/core.c7
-rw-r--r--kernel/events/uprobes.c12
-rw-r--r--kernel/futex.c12
-rw-r--r--kernel/irq/manage.c8
-rw-r--r--kernel/kprobes.c27
-rw-r--r--kernel/locking/lockdep.c4
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/printk/printk.c7
-rw-r--r--kernel/sched/core.c4
-rw-r--r--kernel/sched/cpuacct.c2
-rw-r--r--kernel/sched/cputime.c75
-rw-r--r--kernel/sched/fair.c24
-rw-r--r--kernel/sched/sched.h14
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/sysctl.c18
-rw-r--r--kernel/time/alarmtimer.c3
-rw-r--r--kernel/time/posix-cpu-timers.c2
-rw-r--r--kernel/time/posix-timers.c29
-rw-r--r--kernel/time/time.c10
-rw-r--r--kernel/time/timeconst.bc6
26 files changed, 285 insertions, 118 deletions
diff --git a/kernel/bounds.c b/kernel/bounds.c
index e1d1d1952bfa..c37f68d758db 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -12,7 +12,7 @@
#include <linux/log2.h>
#include <linux/spinlock_types.h>
-void foo(void)
+int main(void)
{
/* The enum constants to put into include/generated/bounds.h */
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
@@ -22,4 +22,6 @@ void foo(void)
#endif
DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
/* End of constants */
+
+ return 0;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dafa2708ce9e..1438b7396cb4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -540,10 +540,11 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
/* check_stack_read/write functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
-static int check_stack_write(struct bpf_verifier_state *state, int off,
- int size, int value_regno)
+static int check_stack_write(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *state, int off,
+ int size, int value_regno, int insn_idx)
{
- int i;
+ int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
@@ -558,15 +559,37 @@ static int check_stack_write(struct bpf_verifier_state *state, int off,
}
/* save register state */
- state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
- state->regs[value_regno];
-
- for (i = 0; i < BPF_REG_SIZE; i++)
+ state->spilled_regs[spi] = state->regs[value_regno];
+
+ for (i = 0; i < BPF_REG_SIZE; i++) {
+ if (state->stack_slot_type[MAX_BPF_STACK + off + i] == STACK_MISC &&
+ !env->allow_ptr_leaks) {
+ int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+ int soff = (-spi - 1) * BPF_REG_SIZE;
+
+ /* detected reuse of integer stack slot with a pointer
+ * which means either llvm is reusing stack slot or
+ * an attacker is trying to exploit CVE-2018-3639
+ * (speculative store bypass)
+ * Have to sanitize that slot with preemptive
+ * store of zero.
+ */
+ if (*poff && *poff != soff) {
+ /* disallow programs where single insn stores
+ * into two different stack slots, since verifier
+ * cannot sanitize them
+ */
+ verbose("insn %d cannot access two stack slots fp%d and fp%d",
+ insn_idx, *poff, soff);
+ return -EINVAL;
+ }
+ *poff = soff;
+ }
state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
+ }
} else {
/* regular write of data into stack */
- state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
- (struct bpf_reg_state) {};
+ state->spilled_regs[spi] = (struct bpf_reg_state) {};
for (i = 0; i < size; i++)
state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
@@ -747,7 +770,7 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
* if t==write && value_regno==-1, some unknown value is stored into memory
* if t==read && value_regno==-1, don't care what we read from memory
*/
-static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
+static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off,
int bpf_size, enum bpf_access_type t,
int value_regno)
{
@@ -843,7 +866,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
verbose("attempt to corrupt spilled pointer on stack\n");
return -EACCES;
}
- err = check_stack_write(state, off, size, value_regno);
+ err = check_stack_write(env, state, off, size,
+ value_regno, insn_idx);
} else {
err = check_stack_read(state, off, size, value_regno);
}
@@ -877,7 +901,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
return err;
}
-static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
+static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = env->cur_state.regs;
int err;
@@ -910,13 +934,13 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* check whether atomic_add can read the memory */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1);
if (err)
return err;
/* check whether atomic_add can write into the same memory */
- return check_mem_access(env, insn->dst_reg, insn->off,
+ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1);
}
@@ -1272,7 +1296,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
* is inferred from register state.
*/
for (i = 0; i < meta.access_size; i++) {
- err = check_mem_access(env, meta.regno, i, BPF_B, BPF_WRITE, -1);
+ err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1);
if (err)
return err;
}
@@ -2938,7 +2962,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (src_reg + off) is readable,
* the state of dst_reg will be updated by this func
*/
- err = check_mem_access(env, insn->src_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ,
insn->dst_reg);
if (err)
@@ -2978,7 +3002,7 @@ static int do_check(struct bpf_verifier_env *env)
enum bpf_reg_type *prev_dst_type, dst_reg_type;
if (BPF_MODE(insn->code) == BPF_XADD) {
- err = check_xadd(env, insn);
+ err = check_xadd(env, insn_idx, insn);
if (err)
return err;
insn_idx++;
@@ -2997,7 +3021,7 @@ static int do_check(struct bpf_verifier_env *env)
dst_reg_type = regs[insn->dst_reg].type;
/* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
insn->src_reg);
if (err)
@@ -3032,7 +3056,7 @@ static int do_check(struct bpf_verifier_env *env)
}
/* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
-1);
if (err)
@@ -3369,6 +3393,34 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
else
continue;
+ if (type == BPF_WRITE &&
+ env->insn_aux_data[i + delta].sanitize_stack_off) {
+ struct bpf_insn patch[] = {
+ /* Sanitize suspicious stack slot with zero.
+ * There are no memory dependencies for this store,
+ * since it's only using frame pointer and immediate
+ * constant of zero
+ */
+ BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+ env->insn_aux_data[i + delta].sanitize_stack_off,
+ 0),
+ /* the original STX instruction will immediately
+ * overwrite the same stack slot with appropriate value
+ */
+ *insn,
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
continue;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4c233437ee1a..bb0cf1caf1cd 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4386,7 +4386,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
*/
do {
css_task_iter_start(&from->self, &it);
- task = css_task_iter_next(&it);
+
+ do {
+ task = css_task_iter_next(&it);
+ } while (task && (task->flags & PF_EXITING));
+
if (task)
get_task_struct(task);
css_task_iter_end(&it);
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 77777d918676..cc892a9e109d 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -215,7 +215,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
int count;
int i;
int diag, dtab_count;
- int key;
+ int key, buf_size, ret;
diag = kdbgetintenv("DTABCOUNT", &dtab_count);
@@ -335,9 +335,8 @@ poll_again:
else
p_tmp = tmpbuffer;
len = strlen(p_tmp);
- count = kallsyms_symbol_complete(p_tmp,
- sizeof(tmpbuffer) -
- (p_tmp - tmpbuffer));
+ buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer);
+ count = kallsyms_symbol_complete(p_tmp, buf_size);
if (tab == 2 && count > 0) {
kdb_printf("\n%d symbols are found.", count);
if (count > dtab_count) {
@@ -349,9 +348,13 @@ poll_again:
}
kdb_printf("\n");
for (i = 0; i < count; i++) {
- if (WARN_ON(!kallsyms_symbol_next(p_tmp, i)))
+ ret = kallsyms_symbol_next(p_tmp, i, buf_size);
+ if (WARN_ON(!ret))
break;
- kdb_printf("%s ", p_tmp);
+ if (ret != -E2BIG)
+ kdb_printf("%s ", p_tmp);
+ else
+ kdb_printf("%s... ", p_tmp);
*(p_tmp + len) = '\0';
}
if (i >= dtab_count)
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 75014d7f4568..533e04e75a9c 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -83,7 +83,7 @@ typedef struct __ksymtab {
unsigned long sym_start;
unsigned long sym_end;
} kdb_symtab_t;
-extern int kallsyms_symbol_next(char *prefix_name, int flag);
+extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size);
extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
/* Exported Symbols for kernel loadable modules to use. */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index d35cc2d3a4cc..61cd704a21c8 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -129,13 +129,13 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
}
if (i >= ARRAY_SIZE(kdb_name_table)) {
debug_kfree(kdb_name_table[0]);
- memcpy(kdb_name_table, kdb_name_table+1,
+ memmove(kdb_name_table, kdb_name_table+1,
sizeof(kdb_name_table[0]) *
(ARRAY_SIZE(kdb_name_table)-1));
} else {
debug_kfree(knt1);
knt1 = kdb_name_table[i];
- memcpy(kdb_name_table+i, kdb_name_table+i+1,
+ memmove(kdb_name_table+i, kdb_name_table+i+1,
sizeof(kdb_name_table[0]) *
(ARRAY_SIZE(kdb_name_table)-i-1));
}
@@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len)
* Parameters:
* prefix_name prefix of a symbol name to lookup
* flag 0 means search from the head, 1 means continue search.
+ * buf_size maximum length that can be written to prefix_name
+ * buffer
* Returns:
* 1 if a symbol matches the given prefix.
* 0 if no string found
*/
-int kallsyms_symbol_next(char *prefix_name, int flag)
+int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size)
{
int prefix_len = strlen(prefix_name);
static loff_t pos;
@@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag)
pos = 0;
while ((name = kdb_walk_kallsyms(&pos))) {
- if (strncmp(name, prefix_name, prefix_len) == 0) {
- strncpy(prefix_name, name, strlen(name)+1);
- return 1;
- }
+ if (!strncmp(name, prefix_name, prefix_len))
+ return strscpy(prefix_name, name, buf_size);
}
return 0;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 95bd00d9f2c3..1af0bbf20984 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4331,7 +4331,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
static int __perf_read_group_add(struct perf_event *leader,
u64 read_format, u64 *values)
{
+ struct perf_event_context *ctx = leader->ctx;
struct perf_event *sub;
+ unsigned long flags;
int n = 1; /* skip @nr */
int ret;
@@ -4361,12 +4363,15 @@ static int __perf_read_group_add(struct perf_event *leader,
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(leader);
+ raw_spin_lock_irqsave(&ctx->lock, flags);
+
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
values[n++] += perf_event_count(sub);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(sub);
}
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
return 0;
}
@@ -7737,6 +7742,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
goto unlock;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+ if (event->cpu != smp_processor_id())
+ continue;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
continue;
if (event->attr.config != entry->type)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index a1de021dccba..fbfab5722254 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -608,7 +608,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
BUG_ON((uprobe->offset & ~PAGE_MASK) +
UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
- smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+ smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
set_bit(UPROBE_COPY_INSN, &uprobe->flags);
out:
@@ -1902,10 +1902,18 @@ static void handle_swbp(struct pt_regs *regs)
* After we hit the bp, _unregister + _register can install the
* new and not-yet-analyzed uprobe at the same address, restart.
*/
- smp_rmb(); /* pairs with wmb() in install_breakpoint() */
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
+ /*
+ * Pairs with the smp_wmb() in prepare_uprobe().
+ *
+ * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+ * we must also see the stores to &uprobe->arch performed by the
+ * prepare_uprobe() call.
+ */
+ smp_rmb();
+
/* Tracing handlers use ->utask to communicate with fetch methods */
if (!get_utask())
goto out;
diff --git a/kernel/futex.c b/kernel/futex.c
index c3ea6f2a6997..053d7be08be5 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1467,8 +1467,16 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
int oldval, ret;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
- if (oparg < 0 || oparg > 31)
- return -EINVAL;
+ if (oparg < 0 || oparg > 31) {
+ char comm[sizeof(current->comm)];
+ /*
+ * kill this print and return -EINVAL when userspace
+ * is sane again
+ */
+ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
+ get_task_comm(comm, current), oparg);
+ oparg &= 31;
+ }
oparg = 1 << oparg;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e121645bb8a1..cf94460504bb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -878,6 +878,9 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
local_bh_disable();
ret = action->thread_fn(action->irq, action->dev_id);
+ if (ret == IRQ_HANDLED)
+ atomic_inc(&desc->threads_handled);
+
irq_finalize_oneshot(desc, action);
local_bh_enable();
return ret;
@@ -894,6 +897,9 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
irqreturn_t ret;
ret = action->thread_fn(action->irq, action->dev_id);
+ if (ret == IRQ_HANDLED)
+ atomic_inc(&desc->threads_handled);
+
irq_finalize_oneshot(desc, action);
return ret;
}
@@ -971,8 +977,6 @@ static int irq_thread(void *data)
irq_thread_check_affinity(desc, action);
action_ret = handler_fn(desc, action);
- if (action_ret == IRQ_HANDLED)
- atomic_inc(&desc->threads_handled);
if (action_ret == IRQ_WAKE_THREAD)
irq_wake_secondary(desc, action);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index b9e966bcdd20..f580352cc6e5 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -665,9 +665,10 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
}
/* Cancel unoptimizing for reusing */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
{
struct optimized_kprobe *op;
+ int ret;
BUG_ON(!kprobe_unused(ap));
/*
@@ -681,8 +682,12 @@ static void reuse_unused_kprobe(struct kprobe *ap)
/* Enable the probe again */
ap->flags &= ~KPROBE_FLAG_DISABLED;
/* Optimize it again (remove from op->list) */
- BUG_ON(!kprobe_optready(ap));
+ ret = kprobe_optready(ap);
+ if (ret)
+ return ret;
+
optimize_kprobe(ap);
+ return 0;
}
/* Remove optimized instructions */
@@ -894,11 +899,16 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt)
#define kprobe_disarmed(p) kprobe_disabled(p)
#define wait_for_kprobe_optimizer() do {} while (0)
-/* There should be no unused kprobes can be reused without optimization */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
{
+ /*
+ * If the optimized kprobe is NOT supported, the aggr kprobe is
+ * released at the same time that the last aggregated kprobe is
+ * unregistered.
+ * Thus there should be no chance to reuse unused kprobe.
+ */
printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
- BUG_ON(kprobe_unused(ap));
+ return -EINVAL;
}
static void free_aggr_kprobe(struct kprobe *p)
@@ -1276,9 +1286,12 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
goto out;
}
init_aggr_kprobe(ap, orig_p);
- } else if (kprobe_unused(ap))
+ } else if (kprobe_unused(ap)) {
/* This probe is going to die. Rescue it */
- reuse_unused_kprobe(ap);
+ ret = reuse_unused_kprobe(ap);
+ if (ret)
+ goto out;
+ }
if (kprobe_gone(ap)) {
/*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 61a15e538435..26fc428476b9 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4010,7 +4010,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- if (unlikely(!lock_stat))
+ if (unlikely(!lock_stat || !debug_locks))
return;
if (unlikely(current->lockdep_recursion))
@@ -4030,7 +4030,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- if (unlikely(!lock_stat))
+ if (unlikely(!lock_stat || !debug_locks))
return;
if (unlikely(current->lockdep_recursion))
diff --git a/kernel/module.c b/kernel/module.c
index 0651f2d25fc9..2325c9821f2a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4011,7 +4011,7 @@ static unsigned long mod_find_symname(struct module *mod, const char *name)
for (i = 0; i < kallsyms->num_symtab; i++)
if (strcmp(name, symname(kallsyms, i)) == 0 &&
- kallsyms->symtab[i].st_info != 'U')
+ kallsyms->symtab[i].st_shndx != SHN_UNDEF)
return kallsyms->symtab[i].st_value;
return 0;
}
@@ -4057,6 +4057,10 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
if (mod->state == MODULE_STATE_UNFORMED)
continue;
for (i = 0; i < kallsyms->num_symtab; i++) {
+
+ if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
+ continue;
+
ret = fn(data, symname(kallsyms, i),
mod, kallsyms->symtab[i].st_value);
if (ret != 0)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9ae22e845029..09f9842f9f42 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1010,7 +1010,12 @@ static void __init log_buf_len_update(unsigned size)
/* save requested log_buf_len since it's too early to process it */
static int __init log_buf_len_setup(char *str)
{
- unsigned size = memparse(str, &str);
+ unsigned int size;
+
+ if (!str)
+ return -EINVAL;
+
+ size = memparse(str, &str);
log_buf_len_update(size);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 917be221438b..6b3fff6a6437 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4087,8 +4087,8 @@ static int __sched_setscheduler(struct task_struct *p,
int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
struct rq *rq;
- /* may grab non-irq protected spin_locks */
- BUG_ON(in_interrupt());
+ /* The pi code expects interrupts enabled */
+ BUG_ON(pi && in_interrupt());
recheck:
/* double check policy once rq lock held */
if (policy < 0) {
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index bc0b309c3f19..4c882791c10c 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -297,7 +297,7 @@ static int cpuacct_stats_show(struct seq_file *sf, void *v)
for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) {
seq_printf(sf, "%s %lld\n",
cpuacct_stat_desc[stat],
- cputime64_to_clock_t(val[stat]));
+ nsec_to_clock_t(val[stat]));
}
return 0;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5ebee3164e64..448d6426fa5f 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -37,6 +37,18 @@ void disable_sched_clock_irqtime(void)
sched_clock_irqtime = 0;
}
+static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
+ enum cpu_usage_stat idx)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ u64_stats_update_begin(&irqtime->sync);
+ cpustat[idx] += delta;
+ irqtime->total += delta;
+ irqtime->tick_delta += delta;
+ u64_stats_update_end(&irqtime->sync);
+}
+
/*
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
@@ -54,7 +66,6 @@ void irqtime_account_irq(struct task_struct *curr)
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- u64_stats_update_begin(&irqtime->sync);
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
@@ -62,48 +73,29 @@ void irqtime_account_irq(struct task_struct *curr)
* that do not consume any time, but still wants to run.
*/
if (hardirq_count())
- irqtime->hardirq_time += delta;
+ irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
- irqtime->softirq_time += delta;
-
- u64_stats_update_end(&irqtime->sync);
+ irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
-static cputime_t irqtime_account_update(u64 irqtime, int idx, cputime_t maxtime)
+static cputime_t irqtime_tick_accounted(cputime_t maxtime)
{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
- cputime_t irq_cputime;
-
- irq_cputime = nsecs_to_cputime64(irqtime) - cpustat[idx];
- irq_cputime = min(irq_cputime, maxtime);
- cpustat[idx] += irq_cputime;
-
- return irq_cputime;
-}
+ struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ cputime_t delta;
-static cputime_t irqtime_account_hi_update(cputime_t maxtime)
-{
- return irqtime_account_update(__this_cpu_read(cpu_irqtime.hardirq_time),
- CPUTIME_IRQ, maxtime);
-}
+ delta = nsecs_to_cputime(irqtime->tick_delta);
+ delta = min(delta, maxtime);
+ irqtime->tick_delta -= cputime_to_nsecs(delta);
-static cputime_t irqtime_account_si_update(cputime_t maxtime)
-{
- return irqtime_account_update(__this_cpu_read(cpu_irqtime.softirq_time),
- CPUTIME_SOFTIRQ, maxtime);
+ return delta;
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
#define sched_clock_irqtime (0)
-static cputime_t irqtime_account_hi_update(cputime_t dummy)
-{
- return 0;
-}
-
-static cputime_t irqtime_account_si_update(cputime_t dummy)
+static cputime_t irqtime_tick_accounted(cputime_t dummy)
{
return 0;
}
@@ -143,7 +135,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
/* Add user time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
+ task_group_account_field(p, index, cputime_to_nsecs(cputime));
/* Account for user time used */
acct_account_cputime(p);
@@ -168,11 +160,11 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
/* Add guest time to cpustat. */
if (task_nice(p) > 0) {
- cpustat[CPUTIME_NICE] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
+ cpustat[CPUTIME_NICE] += cputime_to_nsecs(cputime);
+ cpustat[CPUTIME_GUEST_NICE] += cputime_to_nsecs(cputime);
} else {
- cpustat[CPUTIME_USER] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST] += (__force u64) cputime;
+ cpustat[CPUTIME_USER] += cputime_to_nsecs(cputime);
+ cpustat[CPUTIME_GUEST] += cputime_to_nsecs(cputime);
}
}
@@ -193,7 +185,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
account_group_system_time(p, cputime);
/* Add system time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
+ task_group_account_field(p, index, cputime_to_nsecs(cputime));
/* Account for system time used */
acct_account_cputime(p);
@@ -234,7 +226,7 @@ void account_steal_time(cputime_t cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
- cpustat[CPUTIME_STEAL] += (__force u64) cputime;
+ cpustat[CPUTIME_STEAL] += cputime_to_nsecs(cputime);
}
/*
@@ -247,9 +239,9 @@ void account_idle_time(cputime_t cputime)
struct rq *rq = this_rq();
if (atomic_read(&rq->nr_iowait) > 0)
- cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+ cpustat[CPUTIME_IOWAIT] += cputime_to_nsecs(cputime);
else
- cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+ cpustat[CPUTIME_IDLE] += cputime_to_nsecs(cputime);
}
/*
@@ -290,10 +282,7 @@ static inline cputime_t account_other_time(cputime_t max)
accounted = steal_account_process_time(max);
if (accounted < max)
- accounted += irqtime_account_hi_update(max - accounted);
-
- if (accounted < max)
- accounted += irqtime_account_si_update(max - accounted);
+ accounted += irqtime_tick_accounted(max - accounted);
return accounted;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f81adb476c03..0c91d72f3e8f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3502,7 +3502,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* put back on, and if we advance min_vruntime, we'll be placed back
* further than we started -- ie. we'll be penalized.
*/
- if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
+ if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
update_min_vruntime(cfs_rq);
}
@@ -3976,9 +3976,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
/*
* Add to the _head_ of the list, so that an already-started
- * distribute_cfs_runtime will not see us
+ * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
+ * not running add to the tail so that later runqueues don't get starved.
*/
- list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ if (cfs_b->distribute_running)
+ list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ else
+ list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
/*
* If we're the first throttled task, make sure the bandwidth
@@ -4121,14 +4125,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
* in us over-using our runtime if it is all used during this loop, but
* only by limited amounts in that extreme case.
*/
- while (throttled && cfs_b->runtime > 0) {
+ while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
runtime = cfs_b->runtime;
+ cfs_b->distribute_running = 1;
raw_spin_unlock(&cfs_b->lock);
/* we can't nest cfs_b->lock while distributing bandwidth */
runtime = distribute_cfs_runtime(cfs_b, runtime,
runtime_expires);
raw_spin_lock(&cfs_b->lock);
+ cfs_b->distribute_running = 0;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
cfs_b->runtime -= min(runtime, cfs_b->runtime);
@@ -4239,6 +4245,11 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
/* confirm we're still not at a refresh boundary */
raw_spin_lock(&cfs_b->lock);
+ if (cfs_b->distribute_running) {
+ raw_spin_unlock(&cfs_b->lock);
+ return;
+ }
+
if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
raw_spin_unlock(&cfs_b->lock);
return;
@@ -4248,6 +4259,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
runtime = cfs_b->runtime;
expires = cfs_b->runtime_expires;
+ if (runtime)
+ cfs_b->distribute_running = 1;
+
raw_spin_unlock(&cfs_b->lock);
if (!runtime)
@@ -4258,6 +4272,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
raw_spin_lock(&cfs_b->lock);
if (expires == cfs_b->runtime_expires)
cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ cfs_b->distribute_running = 0;
raw_spin_unlock(&cfs_b->lock);
}
@@ -4366,6 +4381,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
+ cfs_b->distribute_running = 0;
}
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f564a1d2c9d5..ec6e838e991a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4,6 +4,7 @@
#include <linux/sched/rt.h>
#include <linux/u64_stats_sync.h>
#include <linux/sched/deadline.h>
+#include <linux/kernel_stat.h>
#include <linux/binfmts.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
@@ -254,6 +255,8 @@ struct cfs_bandwidth {
/* statistics */
int nr_periods, nr_throttled;
u64 throttled_time;
+
+ bool distribute_running;
#endif
};
@@ -1742,14 +1745,19 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
- u64 hardirq_time;
- u64 softirq_time;
+ u64 total;
+ u64 tick_delta;
u64 irq_start_time;
struct u64_stats_sync sync;
};
DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
static inline u64 irq_time_read(int cpu)
{
struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
@@ -1758,7 +1766,7 @@ static inline u64 irq_time_read(int cpu)
do {
seq = __u64_stats_fetch_begin(&irqtime->sync);
- total = irqtime->softirq_time + irqtime->hardirq_time;
+ total = irqtime->total;
} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
return total;
diff --git a/kernel/signal.c b/kernel/signal.c
index 4364e57e6038..424306163edc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -991,7 +991,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t,
- from_ancestor_ns || (info == SEND_SIG_FORCED)))
+ from_ancestor_ns || (info == SEND_SIG_PRIV) || (info == SEND_SIG_FORCED)))
goto ret;
pending = group ? &t->signal->shared_pending : &t->pending;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7df6be31be36..23f658d311c0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1795,6 +1795,24 @@ static struct ctl_table fs_table[] = {
.extra2 = &one,
},
{
+ .procname = "protected_fifos",
+ .data = &sysctl_protected_fifos,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
+ {
+ .procname = "protected_regular",
+ .data = &sysctl_protected_regular,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
+ {
.procname = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index d67ef56ca9bc..a0ee81f49a87 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -786,7 +786,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now = alarm_bases[type].gettime();
- exp = ktime_add(now, exp);
+
+ exp = ktime_add_safe(now, exp);
}
if (alarmtimer_do_nsleep(&alarm, exp))
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 39008d78927a..21a27bb73587 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -103,7 +103,7 @@ static void bump_cpu_timer(struct k_itimer *timer,
continue;
timer->it.cpu.expires += incr;
- timer->it_overrun += 1 << i;
+ timer->it_overrun += 1LL << i;
delta -= incr;
}
}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index fc7c37ad90a0..0e6ed2e7d066 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -355,6 +355,17 @@ static __init int init_posix_timers(void)
__initcall(init_posix_timers);
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+ s64 sum = timr->it_overrun_last + (s64)baseval;
+
+ return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
static void schedule_next_timer(struct k_itimer *timr)
{
struct hrtimer *timer = &timr->it.real.timer;
@@ -362,12 +373,11 @@ static void schedule_next_timer(struct k_itimer *timr)
if (timr->it.real.interval.tv64 == 0)
return;
- timr->it_overrun += (unsigned int) hrtimer_forward(timer,
- timer->base->get_time(),
- timr->it.real.interval);
+ timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+ timr->it.real.interval);
timr->it_overrun_last = timr->it_overrun;
- timr->it_overrun = -1;
+ timr->it_overrun = -1LL;
++timr->it_requeue_pending;
hrtimer_restart(timer);
}
@@ -396,7 +406,7 @@ void do_schedule_next_timer(struct siginfo *info)
else
schedule_next_timer(timr);
- info->si_overrun += timr->it_overrun_last;
+ info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
}
if (timr)
@@ -491,8 +501,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
now = ktime_add(now, kj);
}
#endif
- timr->it_overrun += (unsigned int)
- hrtimer_forward(timer, now,
+ timr->it_overrun += hrtimer_forward(timer, now,
timr->it.real.interval);
ret = HRTIMER_RESTART;
++timr->it_requeue_pending;
@@ -633,7 +642,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
it_id_set = IT_ID_SET;
new_timer->it_id = (timer_t) new_timer_id;
new_timer->it_clock = which_clock;
- new_timer->it_overrun = -1;
+ new_timer->it_overrun = -1LL;
if (timer_event_spec) {
if (copy_from_user(&event, timer_event_spec, sizeof (event))) {
@@ -762,7 +771,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
*/
if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
timr->it_sigev_notify == SIGEV_NONE))
- timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
+ timr->it_overrun += hrtimer_forward(timer, now, iv);
remaining = __hrtimer_expires_remaining_adjusted(timer, now);
/* Return 0 only, when the timer is expired and not pending */
@@ -824,7 +833,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
if (!timr)
return -EINVAL;
- overrun = timr->it_overrun_last;
+ overrun = timer_overrun_to_int(timr, 0);
unlock_timer(timr, flags);
return overrun;
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 39468651a064..a5b6d98ea7b1 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -704,6 +704,16 @@ u64 nsec_to_clock_t(u64 x)
#endif
}
+u64 jiffies64_to_nsecs(u64 j)
+{
+#if !(NSEC_PER_SEC % HZ)
+ return (NSEC_PER_SEC / HZ) * j;
+# else
+ return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN);
+#endif
+}
+EXPORT_SYMBOL(jiffies64_to_nsecs);
+
/**
* nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index c48688904f9f..f83bbb81600b 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -98,6 +98,12 @@ define timeconst(hz) {
print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n"
print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n"
print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n"
+
+ cd=gcd(hz,1000000000)
+ print "#define HZ_TO_NSEC_NUM\t\t", 1000000000/cd, "\n"
+ print "#define HZ_TO_NSEC_DEN\t\t", hz/cd, "\n"
+ print "#define NSEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+ print "#define NSEC_TO_HZ_DEN\t\t", 1000000000/cd, "\n"
print "\n"
print "#endif /* KERNEL_TIMECONST_H */\n"
generated by cgit v1.2.3 (git 2.0.4) at 2024-12-27 05:02:06 +0000