aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/async.c20
-rw-r--r--kernel/bpf/arraymap.c45
-rw-r--r--kernel/bpf/core.c24
-rw-r--r--kernel/bpf/syscall.c54
-rw-r--r--kernel/bpf/verifier.c131
-rw-r--r--kernel/futex.c3
-rw-r--r--kernel/kcov.c4
-rw-r--r--kernel/memremap.c3
-rw-r--r--kernel/module.c11
-rw-r--r--kernel/relay.c1
-rw-r--r--kernel/sched/core.c13
-rw-r--r--kernel/sched/deadline.c2
-rw-r--r--kernel/sched/rt.c24
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/time/hrtimer.c3
-rw-r--r--kernel/time/posix-timers.c39
-rw-r--r--kernel/time/timer.c2
-rw-r--r--kernel/trace/blktrace.c32
-rw-r--r--kernel/trace/ftrace.c1
-rw-r--r--kernel/trace/trace_events.c16
-rw-r--r--kernel/workqueue.c13
21 files changed, 323 insertions, 120 deletions
diff --git a/kernel/async.c b/kernel/async.c
index d2edd6efec56..d84d4860992e 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -84,20 +84,24 @@ static atomic_t entry_count;
static async_cookie_t lowest_in_progress(struct async_domain *domain)
{
- struct list_head *pending;
+ struct async_entry *first = NULL;
async_cookie_t ret = ASYNC_COOKIE_MAX;
unsigned long flags;
spin_lock_irqsave(&async_lock, flags);
- if (domain)
- pending = &domain->pending;
- else
- pending = &async_global_pending;
+ if (domain) {
+ if (!list_empty(&domain->pending))
+ first = list_first_entry(&domain->pending,
+ struct async_entry, domain_list);
+ } else {
+ if (!list_empty(&async_global_pending))
+ first = list_first_entry(&async_global_pending,
+ struct async_entry, global_list);
+ }
- if (!list_empty(pending))
- ret = list_first_entry(pending, struct async_entry,
- domain_list)->cookie;
+ if (first)
+ ret = first->cookie;
spin_unlock_irqrestore(&async_lock, flags);
return ret;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index f3721e150d94..9a1e6ed7babc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -46,9 +46,10 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
+ u32 elem_size, index_mask, max_entries;
+ bool unpriv = !capable(CAP_SYS_ADMIN);
struct bpf_array *array;
- u64 array_size;
- u32 elem_size;
+ u64 array_size, mask64;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -63,11 +64,32 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
elem_size = round_up(attr->value_size, 8);
+ max_entries = attr->max_entries;
+
+ /* On 32 bit archs roundup_pow_of_two() with max_entries that has
+ * upper most bit set in u32 space is undefined behavior due to
+ * resulting 1U << 32, so do it manually here in u64 space.
+ */
+ mask64 = fls_long(max_entries - 1);
+ mask64 = 1ULL << mask64;
+ mask64 -= 1;
+
+ index_mask = mask64;
+ if (unpriv) {
+ /* round up array size to nearest power of 2,
+ * since cpu will speculate within index_mask limits
+ */
+ max_entries = index_mask + 1;
+ /* Check for overflows. */
+ if (max_entries < attr->max_entries)
+ return ERR_PTR(-E2BIG);
+ }
+
array_size = sizeof(*array);
if (percpu)
- array_size += (u64) attr->max_entries * sizeof(void *);
+ array_size += (u64) max_entries * sizeof(void *);
else
- array_size += (u64) attr->max_entries * elem_size;
+ array_size += (u64) max_entries * elem_size;
/* make sure there is no u32 overflow later in round_up() */
if (array_size >= U32_MAX - PAGE_SIZE)
@@ -77,6 +99,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
array = bpf_map_area_alloc(array_size);
if (!array)
return ERR_PTR(-ENOMEM);
+ array->index_mask = index_mask;
+ array->map.unpriv_array = unpriv;
/* copy mandatory map attributes */
array->map.map_type = attr->map_type;
@@ -110,7 +134,7 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
if (unlikely(index >= array->map.max_entries))
return NULL;
- return array->value + array->elem_size * index;
+ return array->value + array->elem_size * (index & array->index_mask);
}
/* Called from eBPF program */
@@ -122,7 +146,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
if (unlikely(index >= array->map.max_entries))
return NULL;
- return this_cpu_ptr(array->pptrs[index]);
+ return this_cpu_ptr(array->pptrs[index & array->index_mask]);
}
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
@@ -142,7 +166,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
- pptr = array->pptrs[index];
+ pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
off += size;
@@ -190,10 +214,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
return -EEXIST;
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
- memcpy(this_cpu_ptr(array->pptrs[index]),
+ memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
else
- memcpy(array->value + array->elem_size * index,
+ memcpy(array->value +
+ array->elem_size * (index & array->index_mask),
value, map->value_size);
return 0;
}
@@ -227,7 +252,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
- pptr = array->pptrs[index];
+ pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
off += size;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index aa6d98154106..879ca844ba1d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -458,6 +458,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
}
EXPORT_SYMBOL_GPL(__bpf_call_base);
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
/**
* __bpf_prog_run - run eBPF program on a given context
* @ctx: is the data we are operating on
@@ -641,7 +642,7 @@ select_insn:
DST = tmp;
CONT;
ALU_MOD_X:
- if (unlikely(SRC == 0))
+ if (unlikely((u32)SRC == 0))
return 0;
tmp = (u32) DST;
DST = do_div(tmp, (u32) SRC);
@@ -660,7 +661,7 @@ select_insn:
DST = div64_u64(DST, SRC);
CONT;
ALU_DIV_X:
- if (unlikely(SRC == 0))
+ if (unlikely((u32)SRC == 0))
return 0;
tmp = (u32) DST;
do_div(tmp, (u32) SRC);
@@ -715,7 +716,7 @@ select_insn:
struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog;
- u64 index = BPF_R3;
+ u32 index = BPF_R3;
if (unlikely(index >= array->map.max_entries))
goto out;
@@ -923,6 +924,13 @@ load_byte:
}
STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */
+#else
+static unsigned int __bpf_prog_ret0(void *ctx, const struct bpf_insn *insn)
+{
+ return 0;
+}
+#endif
+
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
@@ -970,7 +978,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
fp->bpf_func = (void *) __bpf_prog_run;
+#else
+ fp->bpf_func = (void *) __bpf_prog_ret0;
+#endif
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
@@ -979,6 +991,12 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
* be JITed, but falls back to the interpreter.
*/
fp = bpf_int_jit_compile(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+ if (!fp->jited) {
+ *err = -ENOTSUPP;
+ return fp;
+ }
+#endif
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 72ea91df71c9..91a2d3752007 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -565,57 +565,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl)
list_add(&tl->list_node, &bpf_prog_types);
}
-/* fixup insn->imm field of bpf_call instructions:
- * if (insn->imm == BPF_FUNC_map_lookup_elem)
- * insn->imm = bpf_map_lookup_elem - __bpf_call_base;
- * else if (insn->imm == BPF_FUNC_map_update_elem)
- * insn->imm = bpf_map_update_elem - __bpf_call_base;
- * else ...
- *
- * this function is called after eBPF program passed verification
- */
-static void fixup_bpf_calls(struct bpf_prog *prog)
-{
- const struct bpf_func_proto *fn;
- int i;
-
- for (i = 0; i < prog->len; i++) {
- struct bpf_insn *insn = &prog->insnsi[i];
-
- if (insn->code == (BPF_JMP | BPF_CALL)) {
- /* we reach here when program has bpf_call instructions
- * and it passed bpf_check(), means that
- * ops->get_func_proto must have been supplied, check it
- */
- BUG_ON(!prog->aux->ops->get_func_proto);
-
- if (insn->imm == BPF_FUNC_get_route_realm)
- prog->dst_needed = 1;
- if (insn->imm == BPF_FUNC_get_prandom_u32)
- bpf_user_rnd_init_once();
- if (insn->imm == BPF_FUNC_tail_call) {
- /* mark bpf_tail_call as different opcode
- * to avoid conditional branch in
- * interpeter for every normal call
- * and to prevent accidental JITing by
- * JIT compiler that doesn't support
- * bpf_tail_call yet
- */
- insn->imm = 0;
- insn->code |= BPF_X;
- continue;
- }
-
- fn = prog->aux->ops->get_func_proto(insn->imm);
- /* all functions that have prototype and verifier allowed
- * programs to call them, must be real in-kernel functions
- */
- BUG_ON(!fn->func);
- insn->imm = fn->func - __bpf_call_base;
- }
- }
-}
-
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
@@ -808,9 +757,6 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- /* fixup BPF_CALL->imm field */
- fixup_bpf_calls(prog);
-
/* eBPF program is ready to be JITed */
prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d7eeebfafe8d..076e4a0ff95e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -702,6 +702,13 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]);
}
+static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
+{
+ const struct bpf_reg_state *reg = &env->cur_state.regs[regno];
+
+ return reg->type == PTR_TO_CTX;
+}
+
static int check_ptr_alignment(struct bpf_verifier_env *env,
struct bpf_reg_state *reg, int off, int size)
{
@@ -896,6 +903,12 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EACCES;
}
+ if (is_ctx_reg(env, insn->dst_reg)) {
+ verbose("BPF_XADD stores into R%d context is not allowed\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+
/* check whether atomic_add can read the memory */
err = check_mem_access(env, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1);
@@ -1187,7 +1200,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
}
}
-static int check_call(struct bpf_verifier_env *env, int func_id)
+static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
struct bpf_verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
@@ -1238,6 +1251,13 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
if (err)
return err;
+ if (func_id == BPF_FUNC_tail_call) {
+ if (meta.map_ptr == NULL) {
+ verbose("verifier bug\n");
+ return -EINVAL;
+ }
+ env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
+ }
err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
if (err)
return err;
@@ -1836,6 +1856,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
+ if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
+ verbose("BPF_ARSH not supported for 32 bit ALU\n");
+ return -EINVAL;
+ }
+
if ((opcode == BPF_LSH || opcode == BPF_RSH ||
opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
@@ -3000,6 +3025,12 @@ static int do_check(struct bpf_verifier_env *env)
if (err)
return err;
+ if (is_ctx_reg(env, insn->dst_reg)) {
+ verbose("BPF_ST stores into R%d context is not allowed\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
@@ -3019,7 +3050,7 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
- err = check_call(env, insn->imm);
+ err = check_call(env, insn->imm, insn_idx);
if (err)
return err;
@@ -3362,6 +3393,99 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
return 0;
}
+/* fixup insn->imm field of bpf_call instructions
+ *
+ * this function is called after eBPF program passed verification
+ */
+static int fixup_bpf_calls(struct bpf_verifier_env *env)
+{
+ struct bpf_prog *prog = env->prog;
+ struct bpf_insn *insn = prog->insnsi;
+ const struct bpf_func_proto *fn;
+ const int insn_cnt = prog->len;
+ struct bpf_insn insn_buf[16];
+ struct bpf_prog *new_prog;
+ struct bpf_map *map_ptr;
+ int i, cnt, delta = 0;
+
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
+ insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
+ /* due to JIT bugs clear upper 32-bits of src register
+ * before div/mod operation
+ */
+ insn_buf[0] = BPF_MOV32_REG(insn->src_reg, insn->src_reg);
+ insn_buf[1] = *insn;
+ cnt = 2;
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ if (insn->code != (BPF_JMP | BPF_CALL))
+ continue;
+
+ if (insn->imm == BPF_FUNC_get_route_realm)
+ prog->dst_needed = 1;
+ if (insn->imm == BPF_FUNC_get_prandom_u32)
+ bpf_user_rnd_init_once();
+ if (insn->imm == BPF_FUNC_tail_call) {
+ /* mark bpf_tail_call as different opcode to avoid
+ * conditional branch in the interpeter for every normal
+ * call and to prevent accidental JITing by JIT compiler
+ * that doesn't support bpf_tail_call yet
+ */
+ insn->imm = 0;
+ insn->code |= BPF_X;
+
+ /* instead of changing every JIT dealing with tail_call
+ * emit two extra insns:
+ * if (index >= max_entries) goto out;
+ * index &= array->index_mask;
+ * to avoid out-of-bounds cpu speculation
+ */
+ map_ptr = env->insn_aux_data[i + delta].map_ptr;
+ if (!map_ptr->unpriv_array)
+ continue;
+ insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
+ map_ptr->max_entries, 2);
+ insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
+ container_of(map_ptr,
+ struct bpf_array,
+ map)->index_mask);
+ insn_buf[2] = *insn;
+ cnt = 3;
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ fn = prog->aux->ops->get_func_proto(insn->imm);
+ /* all functions that have prototype and verifier allowed
+ * programs to call them, must be real in-kernel functions
+ */
+ if (!fn->func) {
+ verbose("kernel subsystem misconfigured func %d\n",
+ insn->imm);
+ return -EFAULT;
+ }
+ insn->imm = fn->func - __bpf_call_base;
+ }
+
+ return 0;
+}
+
static void free_states(struct bpf_verifier_env *env)
{
struct bpf_verifier_state_list *sl, *sln;
@@ -3463,6 +3587,9 @@ skip_full_check:
/* program is valid, convert *(u32*)(ctx + off) accesses */
ret = convert_ctx_accesses(env);
+ if (ret == 0)
+ ret = fixup_bpf_calls(env);
+
if (log_level && log_len >= log_size - 1) {
BUG_ON(log_len >= log_size);
/* verifier log exceeded user supplied buffer */
diff --git a/kernel/futex.c b/kernel/futex.c
index 2e074d63e8fa..1e4c72447456 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1801,6 +1801,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
struct futex_q *this, *next;
WAKE_Q(wake_q);
+ if (nr_wake < 0 || nr_requeue < 0)
+ return -EINVAL;
+
if (requeue_pi) {
/*
* Requeue PI only works on two distinct uaddrs. This
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3cbb0c879705..3883df58aa12 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -220,9 +220,9 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
if (unused != 0 || kcov->mode == KCOV_MODE_DISABLED ||
kcov->area == NULL)
return -EINVAL;
- if (kcov->t != NULL)
- return -EBUSY;
t = current;
+ if (kcov->t != NULL || t->kcov != NULL)
+ return -EBUSY;
/* Cache in task struct for performance. */
t->kcov_size = kcov->size;
t->kcov_area = kcov->area;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 06123234f118..426547a21a0c 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -245,7 +245,8 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
/* pages are dead and unused, undo the arch mapping */
align_start = res->start & ~(SECTION_SIZE - 1);
- align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
+ - align_start;
lock_device_hotplug();
mem_hotplug_begin();
diff --git a/kernel/module.c b/kernel/module.c
index f27764fbfa24..ea2d3e3a029d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2833,6 +2833,15 @@ static int check_modinfo_livepatch(struct module *mod, struct load_info *info)
}
#endif /* CONFIG_LIVEPATCH */
+static void check_modinfo_retpoline(struct module *mod, struct load_info *info)
+{
+ if (retpoline_module_ok(get_modinfo(info, "retpoline")))
+ return;
+
+ pr_warn("%s: loading module not compiled with retpoline compiler.\n",
+ mod->name);
+}
+
/* Sets info->hdr and info->len. */
static int copy_module_from_user(const void __user *umod, unsigned long len,
struct load_info *info)
@@ -2985,6 +2994,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK);
}
+ check_modinfo_retpoline(mod, info);
+
if (get_modinfo(info, "staging")) {
add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK);
pr_warn("%s: module is from the staging directory, the quality "
diff --git a/kernel/relay.c b/kernel/relay.c
index 8f18d314a96a..2603e04f55f9 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -611,7 +611,6 @@ free_bufs:
kref_put(&chan->kref, relay_destroy_channel);
mutex_unlock(&relay_channels_mutex);
- kfree(chan);
return NULL;
}
EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ed1ebcc2ff3d..4a1772c0260b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6209,6 +6209,19 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
call_rcu_sched(&old_rd->rcu, free_rootdomain);
}
+void sched_get_rd(struct root_domain *rd)
+{
+ atomic_inc(&rd->refcount);
+}
+
+void sched_put_rd(struct root_domain *rd)
+{
+ if (!atomic_dec_and_test(&rd->refcount))
+ return;
+
+ call_rcu_sched(&rd->rcu, free_rootdomain);
+}
+
static int init_rootdomain(struct root_domain *rd)
{
memset(rd, 0, sizeof(*rd));
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index c77fd444dc3c..04058b6da801 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -724,6 +724,8 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
return;
dl_se->dl_throttled = 1;
+ if (dl_se->runtime > 0)
+ dl_se->runtime = 0;
}
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d361629c0f96..798114f4851d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1896,9 +1896,8 @@ static void push_rt_tasks(struct rq *rq)
* the rt_loop_next will cause the iterator to perform another scan.
*
*/
-static int rto_next_cpu(struct rq *rq)
+static int rto_next_cpu(struct root_domain *rd)
{
- struct root_domain *rd = rq->rd;
int next;
int cpu;
@@ -1974,19 +1973,24 @@ static void tell_cpu_to_push(struct rq *rq)
* Otherwise it is finishing up and an ipi needs to be sent.
*/
if (rq->rd->rto_cpu < 0)
- cpu = rto_next_cpu(rq);
+ cpu = rto_next_cpu(rq->rd);
raw_spin_unlock(&rq->rd->rto_lock);
rto_start_unlock(&rq->rd->rto_loop_start);
- if (cpu >= 0)
+ if (cpu >= 0) {
+ /* Make sure the rd does not get freed while pushing */
+ sched_get_rd(rq->rd);
irq_work_queue_on(&rq->rd->rto_push_work, cpu);
+ }
}
/* Called from hardirq context */
void rto_push_irq_work_func(struct irq_work *work)
{
+ struct root_domain *rd =
+ container_of(work, struct root_domain, rto_push_work);
struct rq *rq;
int cpu;
@@ -2002,18 +2006,20 @@ void rto_push_irq_work_func(struct irq_work *work)
raw_spin_unlock(&rq->lock);
}
- raw_spin_lock(&rq->rd->rto_lock);
+ raw_spin_lock(&rd->rto_lock);
/* Pass the IPI to the next rt overloaded queue */
- cpu = rto_next_cpu(rq);
+ cpu = rto_next_cpu(rd);
- raw_spin_unlock(&rq->rd->rto_lock);
+ raw_spin_unlock(&rd->rto_lock);
- if (cpu < 0)
+ if (cpu < 0) {
+ sched_put_rd(rd);
return;
+ }
/* Try the next RT overloaded CPU */
- irq_work_queue_on(&rq->rd->rto_push_work, cpu);
+ irq_work_queue_on(&rd->rto_push_work, cpu);
}
#endif /* HAVE_RT_PUSH_IPI */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 280c7d5a7657..dd50789ec065 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -590,6 +590,8 @@ struct root_domain {
};
extern struct root_domain def_root_domain;
+extern void sched_get_rd(struct root_domain *rd);
+extern void sched_put_rd(struct root_domain *rd);
#ifdef HAVE_RT_PUSH_IPI
extern void rto_push_irq_work_func(struct irq_work *work);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 369203af6406..bb0bf0651b99 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -653,7 +653,9 @@ static void hrtimer_reprogram(struct hrtimer *timer,
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
base->expires_next.tv64 = KTIME_MAX;
+ base->hang_detected = 0;
base->hres_active = 0;
+ base->next_timer = NULL;
}
/*
@@ -1827,6 +1829,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
}
+ cpu_base->active_bases = 0;
cpu_base->cpu = cpu;
hrtimer_init_hres(cpu_base);
#ifdef CONFIG_PREEMPT_RT_BASE
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 464a98155a0e..6084618436fd 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -506,20 +506,26 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
static struct pid *good_sigevent(sigevent_t * event)
{
struct task_struct *rtn = current->group_leader;
- int sig = event->sigev_signo;
- if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
- (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
- !same_thread_group(rtn, current) ||
- (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
+ switch (event->sigev_notify) {
+ case SIGEV_SIGNAL | SIGEV_THREAD_ID:
+ rtn = find_task_by_vpid(event->sigev_notify_thread_id);
+ if (!rtn || !same_thread_group(rtn, current))
+ return NULL;
+ /* FALLTHRU */
+ case SIGEV_SIGNAL:
+ case SIGEV_THREAD:
+ if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
+ return NULL;
+ if (sig_kernel_only(event->sigev_signo) ||
+ sig_kernel_coredump(event->sigev_signo))
+ return NULL;
+ /* FALLTHRU */
+ case SIGEV_NONE:
+ return task_pid(rtn);
+ default:
return NULL;
-
- if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
- (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) ||
- sig_kernel_coredump(sig)))
- return NULL;
-
- return task_pid(rtn);
+ }
}
void posix_timers_register_clock(const clockid_t clock_id,
@@ -747,8 +753,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
/* interval timer ? */
if (iv.tv64)
cur_setting->it_interval = ktime_to_timespec(iv);
- else if (!hrtimer_active(timer) &&
- (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ else if (!hrtimer_active(timer) && timr->it_sigev_notify != SIGEV_NONE)
return;
now = timer->base->get_time();
@@ -759,7 +764,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
* expiry is > now.
*/
if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
- (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
+ timr->it_sigev_notify == SIGEV_NONE))
timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
remaining = __hrtimer_expires_remaining_adjusted(timer, now);
@@ -769,7 +774,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
* A single shot SIGEV_NONE timer must return 0, when
* it is expired !
*/
- if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ if (timr->it_sigev_notify != SIGEV_NONE)
cur_setting->it_value.tv_nsec = 1;
} else
cur_setting->it_value = ktime_to_timespec(remaining);
@@ -881,7 +886,7 @@ common_timer_set(struct k_itimer *timr, int flags,
timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
/* SIGEV_NONE timers are not queued ! See common_timer_get */
- if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
+ if (timr->it_sigev_notify == SIGEV_NONE) {
/* Setup correct expiry time for relative timers */
if (mode == HRTIMER_MODE_REL) {
hrtimer_add_expires(timer, timer->base->get_time());
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 8e75e7442aaa..ec0169f49c39 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1731,7 +1731,7 @@ void run_local_timers(void)
hrtimer_run_queues();
/* Raise the softirq only if required. */
if (time_before(jiffies, base->clk)) {
- if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+ if (!IS_ENABLED(CONFIG_NO_HZ_COMMON))
return;
/* CPU is awake, so check the deferrable base. */
base++;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index dbafc5df03f3..4e17d55ba127 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -57,7 +57,8 @@ static struct tracer_flags blk_tracer_flags = {
};
/* Global reference count of probes */
-static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+static DEFINE_MUTEX(blk_probe_mutex);
+static int blk_probes_ref;
static void blk_register_tracepoints(void);
static void blk_unregister_tracepoints(void);
@@ -306,11 +307,26 @@ static void blk_trace_free(struct blk_trace *bt)
kfree(bt);
}
+static void get_probe_ref(void)
+{
+ mutex_lock(&blk_probe_mutex);
+ if (++blk_probes_ref == 1)
+ blk_register_tracepoints();
+ mutex_unlock(&blk_probe_mutex);
+}
+
+static void put_probe_ref(void)
+{
+ mutex_lock(&blk_probe_mutex);
+ if (!--blk_probes_ref)
+ blk_unregister_tracepoints();
+ mutex_unlock(&blk_probe_mutex);
+}
+
static void blk_trace_cleanup(struct blk_trace *bt)
{
blk_trace_free(bt);
- if (atomic_dec_and_test(&blk_probes_ref))
- blk_unregister_tracepoints();
+ put_probe_ref();
}
int blk_trace_remove(struct request_queue *q)
@@ -522,8 +538,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (cmpxchg(&q->blk_trace, NULL, bt))
goto err;
- if (atomic_inc_return(&blk_probes_ref) == 1)
- blk_register_tracepoints();
+ get_probe_ref();
return 0;
err:
@@ -1469,9 +1484,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
if (bt == NULL)
return -EINVAL;
- if (atomic_dec_and_test(&blk_probes_ref))
- blk_unregister_tracepoints();
-
+ put_probe_ref();
blk_trace_free(bt);
return 0;
}
@@ -1502,8 +1515,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
if (cmpxchg(&q->blk_trace, NULL, bt))
goto free_bt;
- if (atomic_inc_return(&blk_probes_ref) == 1)
- blk_register_tracepoints();
+ get_probe_ref();
return 0;
free_bt:
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 5b8d7189e147..2884fe01cb54 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3911,7 +3911,6 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
func_g.type = filter_parse_regex(glob, strlen(glob),
&func_g.search, &not);
func_g.len = strlen(func_g.search);
- func_g.search = glob;
/* we do not support '!' for function probes */
if (WARN_ON(not))
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0b85d516b491..f23149a4136b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2202,6 +2202,7 @@ void trace_event_enum_update(struct trace_enum_map **map, int len)
{
struct trace_event_call *call, *p;
const char *last_system = NULL;
+ bool first = false;
int last_i;
int i;
@@ -2209,15 +2210,28 @@ void trace_event_enum_update(struct trace_enum_map **map, int len)
list_for_each_entry_safe(call, p, &ftrace_events, list) {
/* events are usually grouped together with systems */
if (!last_system || call->class->system != last_system) {
+ first = true;
last_i = 0;
last_system = call->class->system;
}
+ /*
+ * Since calls are grouped by systems, the likelyhood that the
+ * next call in the iteration belongs to the same system as the
+ * previous call is high. As an optimization, we skip seaching
+ * for a map[] that matches the call's system if the last call
+ * was from the same system. That's what last_i is for. If the
+ * call has the same system as the previous call, then last_i
+ * will be the index of the first map[] that has a matching
+ * system.
+ */
for (i = last_i; i < len; i++) {
if (call->class->system == map[i]->system) {
/* Save the first system if need be */
- if (!last_i)
+ if (first) {
last_i = i;
+ first = false;
+ }
update_event_printk(call, map[i]);
}
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 7eed129f114a..0750110471e4 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -50,6 +50,7 @@
#include <linux/uaccess.h>
#include <linux/locallock.h>
#include <linux/delay.h>
+#include <linux/nmi.h>
#include "workqueue_internal.h"
@@ -4465,6 +4466,12 @@ void show_workqueue_state(void)
if (pwq->nr_active || !list_empty(&pwq->delayed_works))
show_pwq(pwq);
spin_unlock_irqrestore(&pwq->pool->lock, flags);
+ /*
+ * We could be printing a lot from atomic context, e.g.
+ * sysrq-t -> show_workqueue_state(). Avoid triggering
+ * hard lockup.
+ */
+ touch_nmi_watchdog();
}
}
@@ -4492,6 +4499,12 @@ void show_workqueue_state(void)
pr_cont("\n");
next_pool:
spin_unlock_irqrestore(&pool->lock, flags);
+ /*
+ * We could be printing a lot from atomic context, e.g.
+ * sysrq-t -> show_workqueue_state(). Avoid triggering
+ * hard lockup.
+ */
+ touch_nmi_watchdog();
}
rcu_read_unlock();
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-29 22:34:43 +0000