summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/disasm.c2
-rw-r--r--kernel/bpf/inode.c4
-rw-r--r--kernel/bpf/stackmap.c12
-rw-r--r--kernel/bpf/trampoline.c30
-rw-r--r--kernel/bpf/verifier.c235
-rw-r--r--kernel/entry/common.c4
-rw-r--r--kernel/gcov/clang.c29
-rw-r--r--kernel/irq/chip.c8
-rw-r--r--kernel/irq/dummychip.c2
-rw-r--r--kernel/irq/ipi.c2
-rw-r--r--kernel/irq/irq_sim.c31
-rw-r--r--kernel/irq/irqdesc.c2
-rw-r--r--kernel/irq/irqdomain.c51
-rw-r--r--kernel/irq/manage.c23
-rw-r--r--kernel/irq/matrix.c11
-rw-r--r--kernel/irq/migration.c2
-rw-r--r--kernel/irq/msi.c2
-rw-r--r--kernel/irq/proc.c4
-rw-r--r--kernel/irq/resend.c2
-rw-r--r--kernel/irq/spurious.c4
-rw-r--r--kernel/irq/timings.c8
-rw-r--r--kernel/locking/lockdep.c7
-rw-r--r--kernel/locking/lockdep_internals.h8
-rw-r--r--kernel/locking/qrwlock.c7
-rw-r--r--kernel/power/autosleep.c2
-rw-r--r--kernel/power/snapshot.c2
-rw-r--r--kernel/power/swap.c2
-rw-r--r--kernel/profile.c2
-rw-r--r--kernel/sched/core.c1
-rw-r--r--kernel/sched/cpufreq_schedutil.c29
-rw-r--r--kernel/sched/cputime.c4
-rw-r--r--kernel/seccomp.c2
-rw-r--r--kernel/softirq.c355
-rw-r--r--kernel/sys.c16
-rw-r--r--kernel/time/alarmtimer.c6
-rw-r--r--kernel/time/clocksource.c4
-rw-r--r--kernel/time/hrtimer.c18
-rw-r--r--kernel/time/jiffies.c2
-rw-r--r--kernel/time/ntp.c2
-rw-r--r--kernel/time/posix-cpu-timers.c6
-rw-r--r--kernel/time/posix-timers.c4
-rw-r--r--kernel/time/test_udelay.c7
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c2
-rw-r--r--kernel/time/tick-broadcast.c20
-rw-r--r--kernel/time/tick-common.c7
-rw-r--r--kernel/time/tick-oneshot.c2
-rw-r--r--kernel/time/tick-sched.c10
-rw-r--r--kernel/time/tick-sched.h2
-rw-r--r--kernel/time/time.c2
-rw-r--r--kernel/time/timecounter.c2
-rw-r--r--kernel/time/timekeeping.c46
-rw-r--r--kernel/time/timer.c4
-rw-r--r--kernel/time/vsyscall.c2
-rw-r--r--kernel/trace/trace.c12
-rw-r--r--kernel/trace/trace_dynevent.c6
-rw-r--r--kernel/user_namespace.c65
-rw-r--r--kernel/watchdog.c5
-rw-r--r--kernel/workqueue.c19
58 files changed, 796 insertions, 364 deletions
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 3acc7e0b6916..faa54d58972c 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -84,7 +84,7 @@ static const char *const bpf_atomic_alu_string[16] = {
[BPF_ADD >> 4] = "add",
[BPF_AND >> 4] = "and",
[BPF_OR >> 4] = "or",
- [BPF_XOR >> 4] = "or",
+ [BPF_XOR >> 4] = "xor",
};
static const char *const bpf_ldst_string[] = {
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1576ff331ee4..d2de2abec35b 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -543,11 +543,11 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
return PTR_ERR(raw);
if (type == BPF_TYPE_PROG)
- ret = bpf_prog_new_fd(raw);
+ ret = (f_flags != O_RDWR) ? -EINVAL : bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
ret = bpf_map_new_fd(raw, f_flags);
else if (type == BPF_TYPE_LINK)
- ret = bpf_link_new_fd(raw);
+ ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw);
else
return -ENOENT;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index be35bfb7fb13..6fbc2abe9c91 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -517,9 +517,17 @@ const struct bpf_func_proto bpf_get_stack_proto = {
BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
u32, size, u64, flags)
{
- struct pt_regs *regs = task_pt_regs(task);
+ struct pt_regs *regs;
+ long res;
- return __bpf_get_stack(regs, task, NULL, buf, size, flags);
+ if (!try_get_task_stack(task))
+ return -EFAULT;
+
+ regs = task_pt_regs(task);
+ res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+ put_task_stack(task);
+
+ return res;
}
BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 1f3a4be4b175..4aa8b52adf25 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -9,6 +9,7 @@
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
#include <linux/rcupdate_wait.h>
+#include <linux/module.h>
/* dummy _ops. The verifier will operate on target program's ops. */
const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -87,6 +88,26 @@ out:
return tr;
}
+static int bpf_trampoline_module_get(struct bpf_trampoline *tr)
+{
+ struct module *mod;
+ int err = 0;
+
+ preempt_disable();
+ mod = __module_text_address((unsigned long) tr->func.addr);
+ if (mod && !try_module_get(mod))
+ err = -ENOENT;
+ preempt_enable();
+ tr->mod = mod;
+ return err;
+}
+
+static void bpf_trampoline_module_put(struct bpf_trampoline *tr)
+{
+ module_put(tr->mod);
+ tr->mod = NULL;
+}
+
static int is_ftrace_location(void *ip)
{
long addr;
@@ -108,6 +129,9 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
ret = unregister_ftrace_direct((long)ip, (long)old_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+
+ if (!ret)
+ bpf_trampoline_module_put(tr);
return ret;
}
@@ -134,10 +158,16 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
return ret;
tr->func.ftrace_managed = ret;
+ if (bpf_trampoline_module_get(tr))
+ return -ENOENT;
+
if (tr->func.ftrace_managed)
ret = register_ftrace_direct((long)ip, (long)new_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+
+ if (ret)
+ bpf_trampoline_module_put(tr);
return ret;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 44e4ec1640f1..0399ac092b36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5856,40 +5856,51 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
return &env->insn_aux_data[env->insn_idx];
}
+enum {
+ REASON_BOUNDS = -1,
+ REASON_TYPE = -2,
+ REASON_PATHS = -3,
+ REASON_LIMIT = -4,
+ REASON_STACK = -5,
+};
+
static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
- u32 *ptr_limit, u8 opcode, bool off_is_neg)
+ const struct bpf_reg_state *off_reg,
+ u32 *alu_limit, u8 opcode)
{
+ bool off_is_neg = off_reg->smin_value < 0;
bool mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
(opcode == BPF_SUB && !off_is_neg);
- u32 off, max;
+ u32 max = 0, ptr_limit = 0;
+
+ if (!tnum_is_const(off_reg->var_off) &&
+ (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+ return REASON_BOUNDS;
switch (ptr_reg->type) {
case PTR_TO_STACK:
/* Offset 0 is out-of-bounds, but acceptable start for the
- * left direction, see BPF_REG_FP.
+ * left direction, see BPF_REG_FP. Also, unknown scalar
+ * offset where we would need to deal with min/max bounds is
+ * currently prohibited for unprivileged.
*/
max = MAX_BPF_STACK + mask_to_left;
- /* Indirect variable offset stack access is prohibited in
- * unprivileged mode so it's not handled here.
- */
- off = ptr_reg->off + ptr_reg->var_off.value;
- if (mask_to_left)
- *ptr_limit = MAX_BPF_STACK + off;
- else
- *ptr_limit = -off - 1;
- return *ptr_limit >= max ? -ERANGE : 0;
+ ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
+ break;
case PTR_TO_MAP_VALUE:
max = ptr_reg->map_ptr->value_size;
- if (mask_to_left) {
- *ptr_limit = ptr_reg->umax_value + ptr_reg->off;
- } else {
- off = ptr_reg->smin_value + ptr_reg->off;
- *ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
- }
- return *ptr_limit >= max ? -ERANGE : 0;
+ ptr_limit = (mask_to_left ?
+ ptr_reg->smin_value :
+ ptr_reg->umax_value) + ptr_reg->off;
+ break;
default:
- return -EINVAL;
+ return REASON_TYPE;
}
+
+ if (ptr_limit >= max)
+ return REASON_LIMIT;
+ *alu_limit = ptr_limit;
+ return 0;
}
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
@@ -5907,7 +5918,7 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
if (aux->alu_state &&
(aux->alu_state != alu_state ||
aux->alu_limit != alu_limit))
- return -EACCES;
+ return REASON_PATHS;
/* Corresponding fixup done in fixup_bpf_calls(). */
aux->alu_state = alu_state;
@@ -5926,14 +5937,22 @@ static int sanitize_val_alu(struct bpf_verifier_env *env,
return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
}
+static bool sanitize_needed(u8 opcode)
+{
+ return opcode == BPF_ADD || opcode == BPF_SUB;
+}
+
static int sanitize_ptr_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
+ const struct bpf_reg_state *off_reg,
struct bpf_reg_state *dst_reg,
- bool off_is_neg)
+ struct bpf_insn_aux_data *tmp_aux,
+ const bool commit_window)
{
+ struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
struct bpf_verifier_state *vstate = env->cur_state;
- struct bpf_insn_aux_data *aux = cur_aux(env);
+ bool off_is_neg = off_reg->smin_value < 0;
bool ptr_is_dst_reg = ptr_reg == dst_reg;
u8 opcode = BPF_OP(insn->code);
u32 alu_state, alu_limit;
@@ -5951,18 +5970,33 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
if (vstate->speculative)
goto do_sim;
- alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
- alu_state |= ptr_is_dst_reg ?
- BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
-
- err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+ err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
if (err < 0)
return err;
+ if (commit_window) {
+ /* In commit phase we narrow the masking window based on
+ * the observed pointer move after the simulated operation.
+ */
+ alu_state = tmp_aux->alu_state;
+ alu_limit = abs(tmp_aux->alu_limit - alu_limit);
+ } else {
+ alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+ alu_state |= ptr_is_dst_reg ?
+ BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+ }
+
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
if (err < 0)
return err;
do_sim:
+ /* If we're in commit phase, we're done here given we already
+ * pushed the truncated dst_reg into the speculative verification
+ * stack.
+ */
+ if (commit_window)
+ return 0;
+
/* Simulate and find potential out-of-bounds access under
* speculative execution from truncation as a result of
* masking when off was not within expected range. If off
@@ -5979,7 +6013,46 @@ do_sim:
ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
if (!ptr_is_dst_reg && ret)
*dst_reg = tmp;
- return !ret ? -EFAULT : 0;
+ return !ret ? REASON_STACK : 0;
+}
+
+static int sanitize_err(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, int reason,
+ const struct bpf_reg_state *off_reg,
+ const struct bpf_reg_state *dst_reg)
+{
+ static const char *err = "pointer arithmetic with it prohibited for !root";
+ const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
+ u32 dst = insn->dst_reg, src = insn->src_reg;
+
+ switch (reason) {
+ case REASON_BOUNDS:
+ verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
+ off_reg == dst_reg ? dst : src, err);
+ break;
+ case REASON_TYPE:
+ verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
+ off_reg == dst_reg ? src : dst, err);
+ break;
+ case REASON_PATHS:
+ verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
+ dst, op, err);
+ break;
+ case REASON_LIMIT:
+ verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
+ dst, op, err);
+ break;
+ case REASON_STACK:
+ verbose(env, "R%d could not be pushed for speculative verification, %s\n",
+ dst, err);
+ break;
+ default:
+ verbose(env, "verifier internal error: unknown reason (%d)\n",
+ reason);
+ break;
+ }
+
+ return -EACCES;
}
/* check that stack access falls within stack limits and that 'reg' doesn't
@@ -6016,6 +6089,37 @@ static int check_stack_access_for_ptr_arithmetic(
return 0;
}
+static int sanitize_check_bounds(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ const struct bpf_reg_state *dst_reg)
+{
+ u32 dst = insn->dst_reg;
+
+ /* For unprivileged we require that resulting offset must be in bounds
+ * in order to be able to sanitize access later on.
+ */
+ if (env->bypass_spec_v1)
+ return 0;
+
+ switch (dst_reg->type) {
+ case PTR_TO_STACK:
+ if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
+ dst_reg->off + dst_reg->var_off.value))
+ return -EACCES;
+ break;
+ case PTR_TO_MAP_VALUE:
+ if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+ verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+ "prohibited for !root\n", dst);
+ return -EACCES;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
* Caller should also handle BPF_MOV case separately.
@@ -6035,8 +6139,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
- u32 dst = insn->dst_reg, src = insn->src_reg;
+ struct bpf_insn_aux_data tmp_aux = {};
u8 opcode = BPF_OP(insn->code);
+ u32 dst = insn->dst_reg;
int ret;
dst_reg = &regs[dst];
@@ -6084,13 +6189,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
- case PTR_TO_MAP_VALUE:
- if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
- verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
- off_reg == dst_reg ? dst : src);
- return -EACCES;
- }
- fallthrough;
default:
break;
}
@@ -6108,13 +6206,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
/* pointer types do not carry 32-bit bounds at the moment. */
__mark_reg32_unbounded(dst_reg);
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
+ &tmp_aux, false);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
+ }
+
switch (opcode) {
case BPF_ADD:
- ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
- if (ret < 0) {
- verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
- return ret;
- }
/* We can take a fixed offset as long as it doesn't overflow
* the s32 'off' field
*/
@@ -6165,11 +6265,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
break;
case BPF_SUB:
- ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
- if (ret < 0) {
- verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
- return ret;
- }
if (dst_reg == off_reg) {
/* scalar -= pointer. Creates an unknown scalar */
verbose(env, "R%d tried to subtract pointer from scalar\n",
@@ -6250,21 +6345,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
- /* For unprivileged we require that resulting offset must be in bounds
- * in order to be able to sanitize access later on.
- */
- if (!env->bypass_spec_v1) {
- if (dst_reg->type == PTR_TO_MAP_VALUE &&
- check_map_access(env, dst, dst_reg->off, 1, false)) {
- verbose(env, "R%d pointer arithmetic of map value goes out of range, "
- "prohibited for !root\n", dst);
- return -EACCES;
- } else if (dst_reg->type == PTR_TO_STACK &&
- check_stack_access_for_ptr_arithmetic(
- env, dst, dst_reg, dst_reg->off +
- dst_reg->var_off.value)) {
- return -EACCES;
- }
+ if (sanitize_check_bounds(env, insn, dst_reg) < 0)
+ return -EACCES;
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
+ &tmp_aux, true);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
return 0;
@@ -6858,9 +6945,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
s32 s32_min_val, s32_max_val;
u32 u32_min_val, u32_max_val;
u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
- u32 dst = insn->dst_reg;
- int ret;
bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
+ int ret;
smin_val = src_reg.smin_value;
smax_val = src_reg.smax_value;
@@ -6902,6 +6988,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
return 0;
}
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_val_alu(env, insn);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, NULL, NULL);
+ }
+
/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
* There are two classes of instructions: The first class we track both
* alu32 and alu64 sign/unsigned bounds independently this provides the
@@ -6918,21 +7010,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
*/
switch (opcode) {
case BPF_ADD:
- ret = sanitize_val_alu(env, insn);
- if (ret < 0) {
- verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
- return ret;
- }
scalar32_min_max_add(dst_reg, &src_reg);
scalar_min_max_add(dst_reg, &src_reg);
dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
break;
case BPF_SUB:
- ret = sanitize_val_alu(env, insn);
- if (ret < 0) {
- verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
- return ret;
- }
scalar32_min_max_sub(dst_reg, &src_reg);
scalar_min_max_sub(dst_reg, &src_reg);
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
@@ -12158,6 +12240,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
u32 btf_id, member_idx;
const char *mname;
+ if (!prog->gpl_compatible) {
+ verbose(env, "struct ops programs must have a GPL compatible license\n");
+ return -EINVAL;
+ }
+
btf_id = prog->aux->attach_btf_id;
st_ops = bpf_struct_ops_find(btf_id);
if (!st_ops) {
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 8442e5c9cfa2..a0b3b04fb596 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -341,7 +341,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
* Checking for rcu_is_watching() here would prevent the nesting
* interrupt to invoke rcu_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
- * assume that it is the first interupt and eventually claim
+ * assume that it is the first interrupt and eventually claim
* quiescent state and end grace periods prematurely.
*
* Unconditionally invoke rcu_irq_enter() so RCU state stays
@@ -422,7 +422,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
instrumentation_begin();
if (IS_ENABLED(CONFIG_PREEMPTION)) {
-#ifdef CONFIG_PREEMT_DYNAMIC
+#ifdef CONFIG_PREEMPT_DYNAMIC
static_call(irqentry_exit_cond_resched)();
#else
irqentry_exit_cond_resched();
diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index 8743150db2ac..c466c7fbdece 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -70,7 +70,9 @@ struct gcov_fn_info {
u32 ident;
u32 checksum;
+#if CONFIG_CLANG_VERSION < 110000
u8 use_extra_checksum;
+#endif
u32 cfg_checksum;
u32 num_counters;
@@ -145,10 +147,8 @@ void llvm_gcda_emit_function(u32 ident, const char *function_name,
list_add_tail(&info->head, &current_info->functions);
}
-EXPORT_SYMBOL(llvm_gcda_emit_function);
#else
-void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
- u8 use_extra_checksum, u32 cfg_checksum)
+void llvm_gcda_emit_function(u32 ident, u32 func_checksum, u32 cfg_checksum)
{
struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
@@ -158,12 +158,11 @@ void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
INIT_LIST_HEAD(&info->head);
info->ident = ident;
info->checksum = func_checksum;
- info->use_extra_checksum = use_extra_checksum;
info->cfg_checksum = cfg_checksum;
list_add_tail(&info->head, &current_info->functions);
}
-EXPORT_SYMBOL(llvm_gcda_emit_function);
#endif
+EXPORT_SYMBOL(llvm_gcda_emit_function);
void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters)
{
@@ -293,11 +292,16 @@ int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
!list_is_last(&fn_ptr2->head, &info2->functions)) {
if (fn_ptr1->checksum != fn_ptr2->checksum)
return false;
+#if CONFIG_CLANG_VERSION < 110000
if (fn_ptr1->use_extra_checksum != fn_ptr2->use_extra_checksum)
return false;
if (fn_ptr1->use_extra_checksum &&
fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum)
return false;
+#else
+ if (fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum)
+ return false;
+#endif
fn_ptr1 = list_next_entry(fn_ptr1, head);
fn_ptr2 = list_next_entry(fn_ptr2, head);
}
@@ -529,17 +533,22 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
list_for_each_entry(fi_ptr, &info->functions, head) {
u32 i;
- u32 len = 2;
-
- if (fi_ptr->use_extra_checksum)
- len++;
pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
- pos += store_gcov_u32(buffer, pos, len);
+#if CONFIG_CLANG_VERSION < 110000
+ pos += store_gcov_u32(buffer, pos,
+ fi_ptr->use_extra_checksum ? 3 : 2);
+#else
+ pos += store_gcov_u32(buffer, pos, 3);
+#endif
pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
pos += store_gcov_u32(buffer, pos, fi_ptr->checksum);
+#if CONFIG_CLANG_VERSION < 110000
if (fi_ptr->use_extra_checksum)
pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+#else
+ pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+#endif
pos += store_gcov_u32(buffer, pos, GCOV_TAG_COUNTER_BASE);
pos += store_gcov_u32(buffer, pos, fi_ptr->num_counters * 2);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6d89e33fe3aa..8cc8e5713287 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -761,7 +761,7 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_nmi);
* handle_edge_irq - edge type IRQ handler
* @desc: the interrupt description structure for this irq
*
- * Interrupt occures on the falling and/or rising edge of a hardware
+ * Interrupt occurs on the falling and/or rising edge of a hardware
* signal. The occurrence is latched into the irq controller hardware
* and must be acked in order to be reenabled. After the ack another
* interrupt can happen on the same source even before the first one
@@ -808,7 +808,7 @@ void handle_edge_irq(struct irq_desc *desc)
/*
* When another irq arrived while we were handling
* one, we could have masked the irq.
- * Renable it, if it was not disabled in meantime.
+ * Reenable it, if it was not disabled in meantime.
*/
if (unlikely(desc->istate & IRQS_PENDING)) {
if (!irqd_irq_disabled(&desc->irq_data) &&
@@ -1419,7 +1419,7 @@ EXPORT_SYMBOL_GPL(irq_chip_eoi_parent);
* @dest: The affinity mask to set
* @force: Flag to enforce setting (disable online checks)
*
- * Conditinal, as the underlying parent chip might not implement it.
+ * Conditional, as the underlying parent chip might not implement it.
*/
int irq_chip_set_affinity_parent(struct irq_data *data,
const struct cpumask *dest, bool force)
@@ -1531,7 +1531,7 @@ EXPORT_SYMBOL_GPL(irq_chip_release_resources_parent);
#endif
/**
- * irq_chip_compose_msi_msg - Componse msi message for a irq chip
+ * irq_chip_compose_msi_msg - Compose msi message for a irq chip
* @data: Pointer to interrupt specific data
* @msg: Pointer to the MSI message
*
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
index 0b0cdf206dc4..7fe6cffe7d0d 100644
--- a/kernel/irq/dummychip.c
+++ b/kernel/irq/dummychip.c
@@ -13,7 +13,7 @@
/*
* What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
+ * Each architecture has to answer this themselves.
*/
static void ack_bad(struct irq_data *data)
{
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 43e3d1be622c..52f11c791bf8 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -107,7 +107,7 @@ free_descs:
* @irq: linux irq number to be destroyed
* @dest: cpumask of cpus which should have the IPI removed
*
- * The IPIs allocated with irq_reserve_ipi() are retuerned to the system
+ * The IPIs allocated with irq_reserve_ipi() are returned to the system
* destroying all virqs associated with them.
*
* Return 0 on success or error code on failure.
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 40880c350b95..0cd02efa3a74 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -24,10 +24,6 @@ struct irq_sim_irq_ctx {
struct irq_sim_work_ctx *work_ctx;
};
-struct irq_sim_devres {
- struct irq_domain *domain;
-};
-
static void irq_sim_irqmask(struct irq_data *data)
{
struct irq_sim_irq_ctx *irq_ctx = irq_data_get_irq_chip_data(data);
@@ -216,11 +212,11 @@ void irq_domain_remove_sim(struct irq_domain *domain)
}
EXPORT_SYMBOL_GPL(irq_domain_remove_sim);
-static void devm_irq_domain_release_sim(struct device *dev, void *res)
+static void devm_irq_domain_remove_sim(void *data)
{
- struct irq_sim_devres *this = res;
+ struct irq_domain *domain = data;
- irq_domain_remove_sim(this->domain);
+ irq_domain_remove_sim(domain);
}
/**
@@ -238,20 +234,17 @@ struct irq_domain *devm_irq_domain_create_sim(struct device *dev,
struct fwnode_handle *fwnode,
unsigned int num_irqs)
{
- struct irq_sim_devres *dr;
+ struct irq_domain *domain;
+ int ret;
- dr = devres_alloc(devm_irq_domain_release_sim,
- sizeof(*dr), GFP_KERNEL);
- if (!dr)
- return ERR_PTR(-ENOMEM);
+ domain = irq_domain_create_sim(fwnode, num_irqs);
+ if (IS_ERR(domain))
+ return domain;
- dr->domain = irq_domain_create_sim(fwnode, num_irqs);
- if (IS_ERR(dr->domain)) {
- devres_free(dr);
- return dr->domain;
- }
+ ret = devm_add_action_or_reset(dev, devm_irq_domain_remove_sim, domain);
+ if (ret)
+ return ERR_PTR(ret);
- devres_add(dev, dr);
- return dr->domain;
+ return domain;
}
EXPORT_SYMBOL_GPL(devm_irq_domain_create_sim);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index cc1a09406c6e..4a617d7312a4 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -31,7 +31,7 @@ static int __init irq_affinity_setup(char *str)
cpulist_parse(str, irq_default_affinity);
/*
* Set at least the boot cpu. We don't want to end up with
- * bugreports caused by random comandline masks
+ * bugreports caused by random commandline masks
*/
cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
return 1;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index d10ab1d689d5..f42ef868efd3 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -62,7 +62,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
* @name: Optional user provided domain name
* @pa: Optional user-provided physical address
*
- * Allocate a struct irqchip_fwid, and return a poiner to the embedded
+ * Allocate a struct irqchip_fwid, and return a pointer to the embedded
* fwnode_handle (or NULL on failure).
*
* Note: The types IRQCHIP_FWNODE_NAMED and IRQCHIP_FWNODE_NAMED_ID are
@@ -665,7 +665,7 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
- /* Look for default domain if nececssary */
+ /* Look for default domain if necessary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL) {
@@ -703,41 +703,6 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
}
EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
-/**
- * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs
- * @domain: domain owning the interrupt range
- * @irq_base: beginning of linux IRQ range
- * @hwirq_base: beginning of hardware IRQ range
- * @count: Number of interrupts to map
- *
- * This routine is used for allocating and mapping a range of hardware
- * irqs to linux irqs where the linux irq numbers are at pre-defined
- * locations. For use by controllers that already have static mappings
- * to insert in to the domain.
- *
- * Non-linear users can use irq_create_identity_mapping() for IRQ-at-a-time
- * domain insertion.
- *
- * 0 is returned upon success, while any failure to establish a static
- * mapping is treated as an error.
- */
-int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base,
- irq_hw_number_t hwirq_base, int count)
-{
- struct device_node *of_node;
- int ret;
-
- of_node = irq_domain_get_of_node(domain);
- ret = irq_alloc_descs(irq_base, irq_base, count,
- of_node_to_nid(of_node));
- if (unlikely(ret < 0))
- return ret;
-
- irq_domain_associate_many(domain, irq_base, hwirq_base, count);
- return 0;
-}
-EXPORT_SYMBOL_GPL(irq_create_strict_mappings);
-
static int irq_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
irq_hw_number_t *hwirq, unsigned int *type)
@@ -906,7 +871,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
{
struct irq_data *data;
- /* Look for default domain if nececssary */
+ /* Look for default domain if necessary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL)
@@ -1436,7 +1401,7 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
* The whole process to setup an IRQ has been split into two steps.
* The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
* descriptor and required hardware resources. The second step,
- * irq_domain_activate_irq(), is to program hardwares with preallocated
+ * irq_domain_activate_irq(), is to program the hardware with preallocated
* resources. In this way, it's easier to rollback when failing to
* allocate resources.
*/
@@ -1694,12 +1659,10 @@ void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs)
/**
* irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain
+ * @domain: Domain below which interrupts must be allocated
* @irq_base: Base IRQ number
* @nr_irqs: Number of IRQs to allocate
* @arg: Allocation data (arch/domain specific)
- *
- * Check whether the domain has been setup recursive. If not allocate
- * through the parent domain.
*/
int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
unsigned int irq_base, unsigned int nr_irqs,
@@ -1715,11 +1678,9 @@ EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent);
/**
* irq_domain_free_irqs_parent - Free interrupts from parent domain
+ * @domain: Domain below which interrupts must be freed
* @irq_base: Base IRQ number
* @nr_irqs: Number of IRQs to free
- *
- * Check whether the domain has been setup recursive. If not free
- * through the parent domain.
*/
void irq_domain_free_irqs_parent(struct irq_domain *domain,
unsigned int irq_base, unsigned int nr_irqs)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 21ea370fccda..4c14356543d9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -179,7 +179,7 @@ bool irq_can_set_affinity_usr(unsigned int irq)
/**
* irq_set_thread_affinity - Notify irq threads to adjust affinity
- * @desc: irq descriptor which has affitnity changed
+ * @desc: irq descriptor which has affinity changed
*
* We just set IRQTF_AFFINITY and delegate the affinity setting
* to the interrupt thread itself. We can not call
@@ -326,7 +326,7 @@ static bool irq_set_affinity_deactivated(struct irq_data *data,
* If the interrupt is not yet activated, just store the affinity
* mask and do not call the chip driver at all. On activation the
* driver has to make sure anyway that the interrupt is in a
- * useable state so startup works.
+ * usable state so startup works.
*/
if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
irqd_is_activated(data) || !irqd_affinity_on_activate(data))
@@ -1054,7 +1054,7 @@ again:
* to IRQS_INPROGRESS and the irq line is masked forever.
*
* This also serializes the state of shared oneshot handlers
- * versus "desc->threads_onehsot |= action->thread_mask;" in
+ * versus "desc->threads_oneshot |= action->thread_mask;" in
* irq_wake_thread(). See the comment there which explains the
* serialization.
*/
@@ -1157,7 +1157,7 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
/*
* Interrupts explicitly requested as threaded interrupts want to be
- * preemtible - many of them need to sleep and wait for slow busses to
+ * preemptible - many of them need to sleep and wait for slow busses to
* complete.
*/
static irqreturn_t irq_thread_fn(struct irq_desc *desc,
@@ -1697,7 +1697,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
}
- if (irq_settings_can_autoenable(desc)) {
+ if (!(new->flags & IRQF_NO_AUTOEN) &&
+ irq_settings_can_autoenable(desc)) {
irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
} else {
/*
@@ -1912,7 +1913,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
/* Last action releases resources */
if (!desc->action) {
/*
- * Reaquire bus lock as irq_release_resources() might
+ * Reacquire bus lock as irq_release_resources() might
* require it to deallocate resources over the slow bus.
*/
chip_bus_lock(desc);
@@ -2090,10 +2091,15 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
* which interrupt is which (messes up the interrupt freeing
* logic etc).
*
+ * Also shared interrupts do not go well with disabling auto enable.
+ * The sharing interrupt might request it while it's still disabled
+ * and then wait for interrupts forever.
+ *
* Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
* it cannot be set along with IRQF_NO_SUSPEND.
*/
if (((irqflags & IRQF_SHARED) && !dev_id) ||
+ ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) ||
(!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
return -EINVAL;
@@ -2249,7 +2255,8 @@ int request_nmi(unsigned int irq, irq_handler_t handler,
desc = irq_to_desc(irq);
- if (!desc || irq_settings_can_autoenable(desc) ||
+ if (!desc || (irq_settings_can_autoenable(desc) &&
+ !(irqflags & IRQF_NO_AUTOEN)) ||
!irq_settings_can_request(desc) ||
WARN_ON(irq_settings_is_per_cpu_devid(desc)) ||
!irq_supports_nmi(desc))
@@ -2746,7 +2753,7 @@ int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which,
* irq_get_irqchip_state - returns the irqchip state of a interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: One of IRQCHIP_STATE_* the caller wants to know about
- * @state: a pointer to a boolean where the state is to be storeed
+ * @state: a pointer to a boolean where the state is to be stored
*
* This call snapshots the internal irqchip state of an
* interrupt, returning into @state the bit corresponding to
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 651a4ad6d711..578596e41cb6 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -337,15 +337,14 @@ void irq_matrix_assign(struct irq_matrix *m, unsigned int bit)
* irq_matrix_reserve - Reserve interrupts
* @m: Matrix pointer
*
- * This is merily a book keeping call. It increments the number of globally
+ * This is merely a book keeping call. It increments the number of globally
* reserved interrupt bits w/o actually allocating them. This allows to
* setup interrupt descriptors w/o assigning low level resources to it.
* The actual allocation happens when the interrupt gets activated.
*/
void irq_matrix_reserve(struct irq_matrix *m)
{
- if (m->global_reserved <= m->global_available &&
- m->global_reserved + 1 > m->global_available)
+ if (m->global_reserved == m->global_available)
pr_warn("Interrupt reservation exceeds available resources\n");
m->global_reserved++;
@@ -356,7 +355,7 @@ void irq_matrix_reserve(struct irq_matrix *m)
* irq_matrix_remove_reserved - Remove interrupt reservation
* @m: Matrix pointer
*
- * This is merily a book keeping call. It decrements the number of globally
+ * This is merely a book keeping call. It decrements the number of globally
* reserved interrupt bits. This is used to undo irq_matrix_reserve() when the
* interrupt was never in use and a real vector allocated, which undid the
* reservation.
@@ -423,7 +422,9 @@ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
return;
- clear_bit(bit, cm->alloc_map);
+ if (WARN_ON_ONCE(!test_and_clear_bit(bit, cm->alloc_map)))
+ return;
+
cm->allocated--;
if(managed)
cm->managed_allocated--;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index def48589ea48..61ca924ef4b4 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,7 +7,7 @@
/**
* irq_fixup_move_pending - Cleanup irq move pending from a dying CPU
- * @desc: Interrupt descpriptor to clean up
+ * @desc: Interrupt descriptor to clean up
* @force_clear: If set clear the move pending bit unconditionally.
* If not set, clear it only when the dying CPU is the
* last one in the pending mask.
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index b338d622f26e..c41965e348b5 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -5,7 +5,7 @@
*
* This file is licensed under GPLv2.
*
- * This file contains common code to support Message Signalled Interrupt for
+ * This file contains common code to support Message Signaled Interrupts for
* PCI compatible and non PCI compatible devices.
*/
#include <linux/types.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 98138788cb04..7c5cd42df3b9 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -144,7 +144,7 @@ static ssize_t write_irq_affinity(int type, struct file *file,
if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
return -EIO;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
if (type)
@@ -238,7 +238,7 @@ static ssize_t default_affinity_write(struct file *file,
cpumask_var_t new_value;
int err;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index bd1d85c610aa..0c46e9fe3a89 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -128,7 +128,7 @@ int check_irq_resend(struct irq_desc *desc, bool inject)
if (!try_retrigger(desc))
err = irq_sw_resend(desc);
- /* If the retrigger was successfull, mark it with the REPLAY bit */
+ /* If the retrigger was successful, mark it with the REPLAY bit */
if (!err)
desc->istate |= IRQS_REPLAY;
return err;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index f865e5f4d382..c481d8458325 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -403,6 +403,10 @@ void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret)
desc->irqs_unhandled -= ok;
}
+ if (likely(!desc->irqs_unhandled))
+ return;
+
+ /* Now getting into unhandled irq detection */
desc->irq_count++;
if (likely(desc->irq_count < 100000))
return;
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index 773b6105c4ae..d309d6fbf5bd 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -84,7 +84,7 @@ void irq_timings_disable(void)
* 2. Log interval
*
* We saw the irq timings allow to compute the interval of the
- * occurrences for a specific interrupt. We can reasonibly assume the
+ * occurrences for a specific interrupt. We can reasonably assume the
* longer is the interval, the higher is the error for the next event
* and we can consider storing those interval values into an array
* where each slot in the array correspond to an interval at the power
@@ -416,7 +416,7 @@ static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now)
* Copy the content of the circular buffer into another buffer
* in order to linearize the buffer instead of dealing with
* wrapping indexes and shifted array which will be prone to
- * error and extremelly difficult to debug.
+ * error and extremely difficult to debug.
*/
for (i = 0; i < count; i++) {
int index = (start + i) & IRQ_TIMINGS_MASK;
@@ -485,7 +485,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
/*
* The interrupt triggered more than one second apart, that
- * ends the sequence as predictible for our purpose. In this
+ * ends the sequence as predictable for our purpose. In this
* case, assume we have the beginning of a sequence and the
* timestamp is the first value. As it is impossible to
* predict anything at this point, return.
@@ -514,7 +514,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
* If more than the array size interrupts happened during the
* last busy/idle cycle, the index wrapped up and we have to
* begin with the next element in the array which is the last one
- * in the sequence, otherwise it is a the index 0.
+ * in the sequence, otherwise it is at the index 0.
*
* - have an indication of the interrupts activity on this CPU
* (eg. irq/sec)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c6d0c1dc6253..ef28a0b9cf1e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -705,7 +705,7 @@ static void print_lock_name(struct lock_class *class)
printk(KERN_CONT " (");
__print_lock_name(class);
- printk(KERN_CONT "){%s}-{%hd:%hd}", usage,
+ printk(KERN_CONT "){%s}-{%d:%d}", usage,
class->wait_type_outer ?: class->wait_type_inner,
class->wait_type_inner);
}
@@ -930,7 +930,8 @@ static bool assign_lock_key(struct lockdep_map *lock)
/* Debug-check: all keys must be persistent! */
debug_locks_off();
pr_err("INFO: trying to register non-static key.\n");
- pr_err("the code is fine but needs lockdep annotation.\n");
+ pr_err("The code is fine but needs lockdep annotation, or maybe\n");
+ pr_err("you didn't initialize this object before use?\n");
pr_err("turning off the locking correctness validator.\n");
dump_stack();
return false;
@@ -1392,7 +1393,7 @@ static int add_lock_to_list(struct lock_class *this,
/*
* For good efficiency of modular, we use power of 2
*/
-#define MAX_CIRCULAR_QUEUE_SIZE 4096UL
+#define MAX_CIRCULAR_QUEUE_SIZE (1UL << CONFIG_LOCKDEP_CIRCULAR_QUEUE_BITS)
#define CQ_MASK (MAX_CIRCULAR_QUEUE_SIZE-1)
/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index de49f9e1c11b..ecb8662e7a4e 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -99,16 +99,16 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
#define MAX_STACK_TRACE_ENTRIES 262144UL
#define STACK_TRACE_HASH_SIZE 8192
#else
-#define MAX_LOCKDEP_ENTRIES 32768UL
+#define MAX_LOCKDEP_ENTRIES (1UL << CONFIG_LOCKDEP_BITS)
-#define MAX_LOCKDEP_CHAINS_BITS 16
+#define MAX_LOCKDEP_CHAINS_BITS CONFIG_LOCKDEP_CHAINS_BITS
/*
* Stack-trace: tightly packed array of stack backtrace
* addresses. Protected by the hash_lock.
*/
-#define MAX_STACK_TRACE_ENTRIES 524288UL
-#define STACK_TRACE_HASH_SIZE 16384
+#define MAX_STACK_TRACE_ENTRIES (1UL << CONFIG_LOCKDEP_STACK_TRACE_BITS)
+#define STACK_TRACE_HASH_SIZE (1 << CONFIG_LOCKDEP_STACK_TRACE_HASH_BITS)
#endif
/*
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 4786dd271b45..b94f3831e963 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -60,6 +60,8 @@ EXPORT_SYMBOL(queued_read_lock_slowpath);
*/
void queued_write_lock_slowpath(struct qrwlock *lock)
{
+ int cnts;
+
/* Put the writer into the wait queue */
arch_spin_lock(&lock->wait_lock);
@@ -73,9 +75,8 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
/* When no more readers or writers, set the locked flag */
do {
- atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING);
- } while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING,
- _QW_LOCKED) != _QW_WAITING);
+ cnts = atomic_cond_read_relaxed(&lock->cnts, VAL == _QW_WAITING);
+ } while (!atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED));
unlock:
arch_spin_unlock(&lock->wait_lock);
}
diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c
index 9af5a50d3489..b29c8aca7486 100644
--- a/kernel/power/autosleep.c
+++ b/kernel/power/autosleep.c
@@ -54,7 +54,7 @@ static void try_to_suspend(struct work_struct *work)
goto out;
/*
- * If the wakeup occured for an unknown reason, wait to prevent the
+ * If the wakeup occurred for an unknown reason, wait to prevent the
* system from trying to suspend and waking up in a tight loop.
*/
if (final_count == initial_count)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d63560e1cf87..1a221dcb3c01 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -329,7 +329,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
/**
* Data types related to memory bitmaps.
*
- * Memory bitmap is a structure consiting of many linked lists of
+ * Memory bitmap is a structure consisting of many linked lists of
* objects. The main list's elements are of type struct zone_bitmap
* and each of them corresonds to one zone. For each zone bitmap
* object there is a list of objects of type struct bm_block that
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 72e33054a2e1..bea3cb8afa11 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -884,7 +884,7 @@ out_clean:
* enough_swap - Make sure we have enough swap to save the image.
*
* Returns TRUE or FALSE after checking the total amount of swap
- * space avaiable from the resume partition.
+ * space available from the resume partition.
*/
static int enough_swap(unsigned int nr_pages)
diff --git a/kernel/profile.c b/kernel/profile.c
index 6f69a4195d56..c2ebddb5e974 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -430,7 +430,7 @@ static ssize_t prof_cpu_mask_proc_write(struct file *file,
cpumask_var_t new_value;
int err;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 98191218d891..b2890f6e6d6f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6384,6 +6384,7 @@ int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
{
return __sched_setscheduler(p, attr, false, true);
}
+EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 50cbad89f7fa..6ee9c9bbe505 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -114,19 +114,8 @@ static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
return true;
}
-static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
- unsigned int next_freq)
+static void sugov_deferred_update(struct sugov_policy *sg_policy)
{
- if (sugov_update_next_freq(sg_policy, time, next_freq))
- cpufreq_driver_fast_switch(sg_policy->policy, next_freq);
-}
-
-static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
- unsigned int next_freq)
-{
- if (!sugov_update_next_freq(sg_policy, time, next_freq))
- return;
-
if (!sg_policy->work_in_progress) {
sg_policy->work_in_progress = true;
irq_work_queue(&sg_policy->irq_work);
@@ -366,16 +355,19 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
sg_policy->cached_raw_freq = cached_freq;
}
+ if (!sugov_update_next_freq(sg_policy, time, next_f))
+ return;
+
/*
* This code runs under rq->lock for the target CPU, so it won't run
* concurrently on two different CPUs for the same target and it is not
* necessary to acquire the lock in the fast switch case.
*/
if (sg_policy->policy->fast_switch_enabled) {
- sugov_fast_switch(sg_policy, time, next_f);
+ cpufreq_driver_fast_switch(sg_policy->policy, next_f);
} else {
raw_spin_lock(&sg_policy->update_lock);
- sugov_deferred_update(sg_policy, time, next_f);
+ sugov_deferred_update(sg_policy);
raw_spin_unlock(&sg_policy->update_lock);
}
}
@@ -454,12 +446,15 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
if (sugov_should_update_freq(sg_policy, time)) {
next_f = sugov_next_freq_shared(sg_cpu, time);
+ if (!sugov_update_next_freq(sg_policy, time, next_f))
+ goto unlock;
+
if (sg_policy->policy->fast_switch_enabled)
- sugov_fast_switch(sg_policy, time, next_f);
+ cpufreq_driver_fast_switch(sg_policy->policy, next_f);
else
- sugov_deferred_update(sg_policy, time, next_f);
+ sugov_deferred_update(sg_policy);
}
-
+unlock:
raw_spin_unlock(&sg_policy->update_lock);
}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5f611658eeab..2c36a5fad589 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -60,7 +60,7 @@ void irqtime_account_irq(struct task_struct *curr, unsigned int offset)
cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- pc = preempt_count() - offset;
+ pc = irq_count() - offset;
/*
* We do not account for softirq time from ksoftirqd here.
@@ -421,7 +421,7 @@ void vtime_task_switch(struct task_struct *prev)
void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
{
- unsigned int pc = preempt_count() - offset;
+ unsigned int pc = irq_count() - offset;
if (pc & HARDIRQ_OFFSET) {
vtime_account_hardirq(tsk);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 1d60fc2c9987..1e63db4dbd9a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -817,7 +817,7 @@ static void seccomp_cache_prepare_bitmap(struct seccomp_filter *sfilter,
}
/**
- * seccomp_cache_prepare - emulate the filter to find cachable syscalls
+ * seccomp_cache_prepare - emulate the filter to find cacheable syscalls
* @sfilter: The seccomp filter
*
* Returns 0 if successful or -errno if error occurred.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9908ec4a9bfe..5a99696da86a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -13,6 +13,7 @@
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/local_lock.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
@@ -25,6 +26,7 @@
#include <linux/smpboot.h>
#include <linux/tick.h>
#include <linux/irq.h>
+#include <linux/wait_bit.h>
#include <asm/softirq_stack.h>
@@ -102,20 +104,204 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
#endif
/*
- * preempt_count and SOFTIRQ_OFFSET usage:
- * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
- * softirq processing.
- * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ * SOFTIRQ_OFFSET usage:
+ *
+ * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
+ * to a per CPU counter and to task::softirqs_disabled_cnt.
+ *
+ * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
+ * processing.
+ *
+ * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
* on local_bh_disable or local_bh_enable.
+ *
* This lets us distinguish between whether we are currently processing
* softirq and whether we just have bh disabled.
*/
+#ifdef CONFIG_PREEMPT_RT
+
+/*
+ * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
+ * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
+ * softirq disabled section to be preempted.
+ *
+ * The per task counter is used for softirq_count(), in_softirq() and
+ * in_serving_softirqs() because these counts are only valid when the task
+ * holding softirq_ctrl::lock is running.
+ *
+ * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
+ * the task which is in a softirq disabled section is preempted or blocks.
+ */
+struct softirq_ctrl {
+ local_lock_t lock;
+ int cnt;
+};
+
+static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
+ .lock = INIT_LOCAL_LOCK(softirq_ctrl.lock),
+};
+
+/**
+ * local_bh_blocked() - Check for idle whether BH processing is blocked
+ *
+ * Returns false if the per CPU softirq::cnt is 0 otherwise true.
+ *
+ * This is invoked from the idle task to guard against false positive
+ * softirq pending warnings, which would happen when the task which holds
+ * softirq_ctrl::lock was the only running task on the CPU and blocks on
+ * some other lock.
+ */
+bool local_bh_blocked(void)
+{
+ return __this_cpu_read(softirq_ctrl.cnt) != 0;
+}
+
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+ unsigned long flags;
+ int newcnt;
+
+ WARN_ON_ONCE(in_hardirq());
+
+ /* First entry of a task into a BH disabled section? */
+ if (!current->softirq_disable_cnt) {
+ if (preemptible()) {
+ local_lock(&softirq_ctrl.lock);
+ /* Required to meet the RCU bottomhalf requirements. */
+ rcu_read_lock();
+ } else {
+ DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
+ }
+ }
+
+ /*
+ * Track the per CPU softirq disabled state. On RT this is per CPU
+ * state to allow preemption of bottom half disabled sections.
+ */
+ newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
+ /*
+ * Reflect the result in the task state to prevent recursion on the
+ * local lock and to make softirq_count() & al work.
+ */
+ current->softirq_disable_cnt = newcnt;
+
+ if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
+ raw_local_irq_save(flags);
+ lockdep_softirqs_off(ip);
+ raw_local_irq_restore(flags);
+ }
+}
+EXPORT_SYMBOL(__local_bh_disable_ip);
+
+static void __local_bh_enable(unsigned int cnt, bool unlock)
+{
+ unsigned long flags;
+ int newcnt;
+
+ DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
+ this_cpu_read(softirq_ctrl.cnt));
+
+ if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
+ raw_local_irq_save(flags);
+ lockdep_softirqs_on(_RET_IP_);
+ raw_local_irq_restore(flags);
+ }
+
+ newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
+ current->softirq_disable_cnt = newcnt;
+
+ if (!newcnt && unlock) {
+ rcu_read_unlock();
+ local_unlock(&softirq_ctrl.lock);
+ }
+}
+
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+ bool preempt_on = preemptible();
+ unsigned long flags;
+ u32 pending;
+ int curcnt;
+
+ WARN_ON_ONCE(in_irq());
+ lockdep_assert_irqs_enabled();
+
+ local_irq_save(flags);
+ curcnt = __this_cpu_read(softirq_ctrl.cnt);
+
+ /*
+ * If this is not reenabling soft interrupts, no point in trying to
+ * run pending ones.
+ */
+ if (curcnt != cnt)
+ goto out;
+
+ pending = local_softirq_pending();
+ if (!pending || ksoftirqd_running(pending))
+ goto out;
+
+ /*
+ * If this was called from non preemptible context, wake up the
+ * softirq daemon.
+ */
+ if (!preempt_on) {
+ wakeup_softirqd();
+ goto out;
+ }
+
+ /*
+ * Adjust softirq count to SOFTIRQ_OFFSET which makes
+ * in_serving_softirq() become true.
+ */
+ cnt = SOFTIRQ_OFFSET;
+ __local_bh_enable(cnt, false);
+ __do_softirq();
+
+out:
+ __local_bh_enable(cnt, preempt_on);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__local_bh_enable_ip);
+
+/*
+ * Invoked from ksoftirqd_run() outside of the interrupt disabled section
+ * to acquire the per CPU local lock for reentrancy protection.
+ */
+static inline void ksoftirqd_run_begin(void)
+{
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ local_irq_disable();
+}
+
+/* Counterpart to ksoftirqd_run_begin() */
+static inline void ksoftirqd_run_end(void)
+{
+ __local_bh_enable(SOFTIRQ_OFFSET, true);
+ WARN_ON_ONCE(in_interrupt());
+ local_irq_enable();
+}
+
+static inline void softirq_handle_begin(void) { }
+static inline void softirq_handle_end(void) { }
+
+static inline bool should_wake_ksoftirqd(void)
+{
+ return !this_cpu_read(softirq_ctrl.cnt);
+}
+
+static inline void invoke_softirq(void)
+{
+ if (should_wake_ksoftirqd())
+ wakeup_softirqd();
+}
+
+#else /* CONFIG_PREEMPT_RT */
-#ifdef CONFIG_TRACE_IRQFLAGS
/*
- * This is for softirq.c-internal use, where hardirqs are disabled
+ * This one is for softirq.c-internal use, where hardirqs are disabled
* legitimately:
*/
+#ifdef CONFIG_TRACE_IRQFLAGS
void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
@@ -206,6 +392,32 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
}
EXPORT_SYMBOL(__local_bh_enable_ip);
+static inline void softirq_handle_begin(void)
+{
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+}
+
+static inline void softirq_handle_end(void)
+{
+ __local_bh_enable(SOFTIRQ_OFFSET);
+ WARN_ON_ONCE(in_interrupt());
+}
+
+static inline void ksoftirqd_run_begin(void)
+{
+ local_irq_disable();
+}
+
+static inline void ksoftirqd_run_end(void)
+{
+ local_irq_enable();
+}
+
+static inline bool should_wake_ksoftirqd(void)
+{
+ return true;
+}
+
static inline void invoke_softirq(void)
{
if (ksoftirqd_running(local_softirq_pending()))
@@ -250,6 +462,8 @@ asmlinkage __visible void do_softirq(void)
local_irq_restore(flags);
}
+#endif /* !CONFIG_PREEMPT_RT */
+
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
* but break the loop if need_resched() is set or after 2 ms.
@@ -318,7 +532,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
pending = local_softirq_pending();
- __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ softirq_handle_begin();
in_hardirq = lockdep_softirq_start();
account_softirq_enter(current);
@@ -354,8 +568,10 @@ restart:
pending >>= softirq_bit;
}
- if (__this_cpu_read(ksoftirqd) == current)
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
+ __this_cpu_read(ksoftirqd) == current)
rcu_softirq_qs();
+
local_irq_disable();
pending = local_softirq_pending();
@@ -369,8 +585,7 @@ restart:
account_softirq_exit(current);
lockdep_softirq_end(in_hardirq);
- __local_bh_enable(SOFTIRQ_OFFSET);
- WARN_ON_ONCE(in_interrupt());
+ softirq_handle_end();
current_restore_flags(old_flags, PF_MEMALLOC);
}
@@ -465,7 +680,7 @@ inline void raise_softirq_irqoff(unsigned int nr)
* Otherwise we wake up ksoftirqd to make sure we
* schedule the softirq soon.
*/
- if (!in_interrupt())
+ if (!in_interrupt() && should_wake_ksoftirqd())
wakeup_softirqd();
}
@@ -531,6 +746,20 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
}
EXPORT_SYMBOL(__tasklet_hi_schedule);
+static bool tasklet_clear_sched(struct tasklet_struct *t)
+{
+ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) {
+ wake_up_var(&t->state);
+ return true;
+ }
+
+ WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
+ t->use_callback ? "callback" : "func",
+ t->use_callback ? (void *)t->callback : (void *)t->func);
+
+ return false;
+}
+
static void tasklet_action_common(struct softirq_action *a,
struct tasklet_head *tl_head,
unsigned int softirq_nr)
@@ -550,13 +779,12 @@ static void tasklet_action_common(struct softirq_action *a,
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
- if (!test_and_clear_bit(TASKLET_STATE_SCHED,
- &t->state))
- BUG();
- if (t->use_callback)
- t->callback(t);
- else
- t->func(t->data);
+ if (tasklet_clear_sched(t)) {
+ if (t->use_callback)
+ t->callback(t);
+ else
+ t->func(t->data);
+ }
tasklet_unlock(t);
continue;
}
@@ -606,21 +834,62 @@ void tasklet_init(struct tasklet_struct *t,
}
EXPORT_SYMBOL(tasklet_init);
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+/*
+ * Do not use in new code. Waiting for tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+void tasklet_unlock_spin_wait(struct tasklet_struct *t)
+{
+ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ /*
+ * Prevent a live lock when current preempted soft
+ * interrupt processing or prevents ksoftirqd from
+ * running. If the tasklet runs on a different CPU
+ * then this has no effect other than doing the BH
+ * disable/enable dance for nothing.
+ */
+ local_bh_disable();
+ local_bh_enable();
+ } else {
+ cpu_relax();
+ }
+ }
+}
+EXPORT_SYMBOL(tasklet_unlock_spin_wait);
+#endif
+
void tasklet_kill(struct tasklet_struct *t)
{
if (in_interrupt())
pr_notice("Attempt to kill tasklet from interrupt\n");
- while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
- do {
- yield();
- } while (test_bit(TASKLET_STATE_SCHED, &t->state));
- }
+ while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
+ wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));
+
tasklet_unlock_wait(t);
- clear_bit(TASKLET_STATE_SCHED, &t->state);
+ tasklet_clear_sched(t);
}
EXPORT_SYMBOL(tasklet_kill);
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+void tasklet_unlock(struct tasklet_struct *t)
+{
+ smp_mb__before_atomic();
+ clear_bit(TASKLET_STATE_RUN, &t->state);
+ smp_mb__after_atomic();
+ wake_up_var(&t->state);
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock);
+
+void tasklet_unlock_wait(struct tasklet_struct *t)
+{
+ wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
+#endif
+
void __init softirq_init(void)
{
int cpu;
@@ -643,53 +912,21 @@ static int ksoftirqd_should_run(unsigned int cpu)
static void run_ksoftirqd(unsigned int cpu)
{
- local_irq_disable();
+ ksoftirqd_run_begin();
if (local_softirq_pending()) {
/*
* We can safely run softirq on inline stack, as we are not deep
* in the task stack here.
*/
__do_softirq();
- local_irq_enable();
+ ksoftirqd_run_end();
cond_resched();
return;
}
- local_irq_enable();
+ ksoftirqd_run_end();
}
#ifdef CONFIG_HOTPLUG_CPU
-/*
- * tasklet_kill_immediate is called to remove a tasklet which can already be
- * scheduled for execution on @cpu.
- *
- * Unlike tasklet_kill, this function removes the tasklet
- * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
- *
- * When this function is called, @cpu must be in the CPU_DEAD state.
- */
-void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
-{
- struct tasklet_struct **i;
-
- BUG_ON(cpu_online(cpu));
- BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
-
- if (!test_bit(TASKLET_STATE_SCHED, &t->state))
- return;
-
- /* CPU is dead, so no lock needed. */
- for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
- if (*i == t) {
- *i = t->next;
- /* If this was the tail element, move the tail ptr */
- if (*i == NULL)
- per_cpu(tasklet_vec, cpu).tail = i;
- return;
- }
- }
- BUG();
-}
-
static int takeover_tasklets(unsigned int cpu)
{
/* CPU is dead, so no lock needed. */
diff --git a/kernel/sys.c b/kernel/sys.c
index 2e2e3f378d97..3d62c9599dc0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -119,6 +119,12 @@
#ifndef PAC_RESET_KEYS
# define PAC_RESET_KEYS(a, b) (-EINVAL)
#endif
+#ifndef PAC_SET_ENABLED_KEYS
+# define PAC_SET_ENABLED_KEYS(a, b, c) (-EINVAL)
+#endif
+#ifndef PAC_GET_ENABLED_KEYS
+# define PAC_GET_ENABLED_KEYS(a) (-EINVAL)
+#endif
#ifndef SET_TAGGED_ADDR_CTRL
# define SET_TAGGED_ADDR_CTRL(a) (-EINVAL)
#endif
@@ -2497,6 +2503,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = PAC_RESET_KEYS(me, arg2);
break;
+ case PR_PAC_SET_ENABLED_KEYS:
+ if (arg4 || arg5)
+ return -EINVAL;
+ error = PAC_SET_ENABLED_KEYS(me, arg2, arg3);
+ break;
+ case PR_PAC_GET_ENABLED_KEYS:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = PAC_GET_ENABLED_KEYS(me);
+ break;
case PR_SET_TAGGED_ADDR_CTRL:
if (arg3 || arg4 || arg5)
return -EINVAL;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 4d94e2b5499d..bea9d08b1698 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -2,13 +2,13 @@
/*
* Alarmtimer interface
*
- * This interface provides a timer which is similarto hrtimers,
+ * This interface provides a timer which is similar to hrtimers,
* but triggers a RTC alarm if the box is suspend.
*
* This interface is influenced by the Android RTC Alarm timer
* interface.
*
- * Copyright (C) 2010 IBM Corperation
+ * Copyright (C) 2010 IBM Corporation
*
* Author: John Stultz <john.stultz@linaro.org>
*/
@@ -811,7 +811,7 @@ static long __sched alarm_timer_nsleep_restart(struct restart_block *restart)
/**
* alarm_timer_nsleep - alarmtimer nanosleep
* @which_clock: clockid
- * @flags: determins abstime or relative
+ * @flags: determines abstime or relative
* @tsreq: requested sleep time (abs or rel)
*
* Handles clock_nanosleep calls against _ALARM clockids
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cce484a2cc7c..1d1a61371b5a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -38,7 +38,7 @@
* calculated mult and shift factors. This guarantees that no 64bit
* overflow happens when the input value of the conversion is
* multiplied with the calculated mult factor. Larger ranges may
- * reduce the conversion accuracy by chosing smaller mult and shift
+ * reduce the conversion accuracy by choosing smaller mult and shift
* factors.
*/
void
@@ -518,7 +518,7 @@ static void clocksource_suspend_select(bool fallback)
* the suspend time when resuming system.
*
* This function is called late in the suspend process from timekeeping_suspend(),
- * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * that means processes are frozen, non-boot cpus and interrupts are disabled
* now. It is therefore possible to start the suspend timer without taking the
* clocksource mutex.
*/
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 5c9d968187ae..4a66725b1d4a 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -683,7 +683,7 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
* T1 is removed, so this code is called and would reprogram
* the hardware to 5s from now. Any hrtimer_start after that
* will not reprogram the hardware due to hang_detected being
- * set. So we'd effectivly block all timers until the T2 event
+ * set. So we'd effectively block all timers until the T2 event
* fires.
*/
if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
@@ -1019,7 +1019,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
* cpu_base->next_timer. This happens when we remove the first
* timer on a remote cpu. No harm as we never dereference
* cpu_base->next_timer. So the worst thing what can happen is
- * an superflous call to hrtimer_force_reprogram() on the
+ * an superfluous call to hrtimer_force_reprogram() on the
* remote cpu later on if the same timer gets enqueued again.
*/
if (reprogram && timer == cpu_base->next_timer)
@@ -1212,7 +1212,7 @@ static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base)
* The counterpart to hrtimer_cancel_wait_running().
*
* If there is a waiter for cpu_base->expiry_lock, then it was waiting for
- * the timer callback to finish. Drop expiry_lock and reaquire it. That
+ * the timer callback to finish. Drop expiry_lock and reacquire it. That
* allows the waiter to acquire the lock and make progress.
*/
static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base,
@@ -1398,7 +1398,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
int base;
/*
- * On PREEMPT_RT enabled kernels hrtimers which are not explicitely
+ * On PREEMPT_RT enabled kernels hrtimers which are not explicitly
* marked for hard interrupt expiry mode are moved into soft
* interrupt context for latency reasons and because the callbacks
* can invoke functions which might sleep on RT, e.g. spin_lock().
@@ -1430,7 +1430,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
* hrtimer_init - initialize a timer to the given clock
* @timer: the timer to be initialized
* @clock_id: the clock to be used
- * @mode: The modes which are relevant for intitialization:
+ * @mode: The modes which are relevant for initialization:
* HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT,
* HRTIMER_MODE_REL_SOFT
*
@@ -1487,7 +1487,7 @@ EXPORT_SYMBOL_GPL(hrtimer_active);
* insufficient for that.
*
* The sequence numbers are required because otherwise we could still observe
- * a false negative if the read side got smeared over multiple consequtive
+ * a false negative if the read side got smeared over multiple consecutive
* __run_hrtimer() invocations.
*/
@@ -1588,7 +1588,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now,
* minimizing wakeups, not running timers at the
* earliest interrupt after their soft expiration.
* This allows us to avoid using a Priority Search
- * Tree, which can answer a stabbing querry for
+ * Tree, which can answer a stabbing query for
* overlapping intervals and instead use the simple
* BST we already have.
* We don't add extra wakeups by delaying timers that
@@ -1822,7 +1822,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
clockid_t clock_id, enum hrtimer_mode mode)
{
/*
- * On PREEMPT_RT enabled kernels hrtimers which are not explicitely
+ * On PREEMPT_RT enabled kernels hrtimers which are not explicitly
* marked for hard interrupt expiry mode are moved into soft
* interrupt context either for latency reasons or because the
* hrtimer callback takes regular spinlocks or invokes other
@@ -1835,7 +1835,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
* the same CPU. That causes a latency spike due to the wakeup of
* a gazillion threads.
*
- * OTOH, priviledged real-time user space applications rely on the
+ * OTOH, privileged real-time user space applications rely on the
* low latency of hard interrupt wakeups. If the current task is in
* a real-time scheduling class, mark the mode for hard interrupt
* expiry.
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a5cffe2a1770..a492e4da69ba 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -44,7 +44,7 @@ static u64 jiffies_read(struct clocksource *cs)
* the timer interrupt frequency HZ and it suffers
* inaccuracies caused by missed or lost timer
* interrupts and the inability for the timer
- * interrupt hardware to accuratly tick at the
+ * interrupt hardware to accurately tick at the
* requested HZ value. It is also not recommended
* for "tick-less" systems.
*/
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5247afd7f345..406dccb79c2b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -544,7 +544,7 @@ static inline bool rtc_tv_nsec_ok(unsigned long set_offset_nsec,
struct timespec64 *to_set,
const struct timespec64 *now)
{
- /* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */
+ /* Allowed error in tv_nsec, arbitrarily set to 5 jiffies in ns. */
const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5;
struct timespec64 delay = {.tv_sec = -1,
.tv_nsec = set_offset_nsec};
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 9abe15255bc4..3bb96a8b49c9 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -279,7 +279,7 @@ void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples)
* @tsk: Task for which cputime needs to be started
* @samples: Storage for time samples
*
- * The thread group cputime accouting is avoided when there are no posix
+ * The thread group cputime accounting is avoided when there are no posix
* CPU timers armed. Before starting a timer it's required to check whether
* the time accounting is active. If not, a full update of the atomic
* accounting store needs to be done and the accounting enabled.
@@ -390,7 +390,7 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
/*
* If posix timer expiry is handled in task work context then
* timer::it_lock can be taken without disabling interrupts as all
- * other locking happens in task context. This requires a seperate
+ * other locking happens in task context. This requires a separate
* lock class key otherwise regular posix timer expiry would record
* the lock class being taken in interrupt context and generate a
* false positive warning.
@@ -1216,7 +1216,7 @@ static void handle_posix_cpu_timers(struct task_struct *tsk)
check_process_timers(tsk, &firing);
/*
- * The above timer checks have updated the exipry cache and
+ * The above timer checks have updated the expiry cache and
* because nothing can have queued or modified timers after
* sighand lock was taken above it is guaranteed to be
* consistent. So the next timer interrupt fastpath check
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index bf540f5a4115..dd5697d7347b 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1191,8 +1191,8 @@ SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock,
err = do_clock_adjtime(which_clock, &ktx);
- if (err >= 0)
- err = put_old_timex32(utp, &ktx);
+ if (err >= 0 && put_old_timex32(utp, &ktx))
+ return -EFAULT;
return err;
}
diff --git a/kernel/time/test_udelay.c b/kernel/time/test_udelay.c
index 77c63005dc4e..13b11eb62685 100644
--- a/kernel/time/test_udelay.c
+++ b/kernel/time/test_udelay.c
@@ -21,7 +21,6 @@
#define DEBUGFS_FILENAME "udelay_test"
static DEFINE_MUTEX(udelay_test_lock);
-static struct dentry *udelay_test_debugfs_file;
static int udelay_test_usecs;
static int udelay_test_iterations = DEFAULT_ITERATIONS;
@@ -138,8 +137,8 @@ static const struct file_operations udelay_test_debugfs_ops = {
static int __init udelay_test_init(void)
{
mutex_lock(&udelay_test_lock);
- udelay_test_debugfs_file = debugfs_create_file(DEBUGFS_FILENAME,
- S_IRUSR, NULL, NULL, &udelay_test_debugfs_ops);
+ debugfs_create_file(DEBUGFS_FILENAME, S_IRUSR, NULL, NULL,
+ &udelay_test_debugfs_ops);
mutex_unlock(&udelay_test_lock);
return 0;
@@ -150,7 +149,7 @@ module_init(udelay_test_init);
static void __exit udelay_test_exit(void)
{
mutex_lock(&udelay_test_lock);
- debugfs_remove(udelay_test_debugfs_file);
+ debugfs_remove(debugfs_lookup(DEBUGFS_FILENAME, NULL));
mutex_unlock(&udelay_test_lock);
}
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index b5a65e212df2..797eb93103ad 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -53,7 +53,7 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
* reasons.
*
* Each caller tries to arm the hrtimer on its own CPU, but if the
- * hrtimer callbback function is currently running, then
+ * hrtimer callback function is currently running, then
* hrtimer_start() cannot move it and the timer stays on the CPU on
* which it is assigned at the moment.
*
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 5a23829372c7..a44055228796 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -107,6 +107,19 @@ void tick_install_broadcast_device(struct clock_event_device *dev)
tick_broadcast_device.evtdev = dev;
if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(dev);
+
+ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return;
+
+ /*
+ * If the system already runs in oneshot mode, switch the newly
+ * registered broadcast device to oneshot mode explicitly.
+ */
+ if (tick_broadcast_oneshot_active()) {
+ tick_broadcast_switch_to_oneshot();
+ return;
+ }
+
/*
* Inform all cpus about this. We might be in a situation
* where we did not switch to oneshot mode because the per cpu
@@ -115,8 +128,7 @@ void tick_install_broadcast_device(struct clock_event_device *dev)
* notification the systems stays stuck in periodic mode
* forever.
*/
- if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
- tick_clock_notify();
+ tick_clock_notify();
}
/*
@@ -157,7 +169,7 @@ static void tick_device_setup_broadcast_func(struct clock_event_device *dev)
}
/*
- * Check, if the device is disfunctional and a place holder, which
+ * Check, if the device is dysfunctional and a placeholder, which
* needs to be handled by the broadcast device.
*/
int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
@@ -391,7 +403,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
* - the broadcast device exists
* - the broadcast device is not a hrtimer based one
* - the broadcast device is in periodic mode to
- * avoid a hickup during switch to oneshot mode
+ * avoid a hiccup during switch to oneshot mode
*/
if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) &&
tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 9d3a22510bab..e15bc0ef1912 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -348,12 +348,7 @@ void tick_check_new_device(struct clock_event_device *newdev)
td = &per_cpu(tick_cpu_device, cpu);
curdev = td->evtdev;
- /* cpu local device ? */
- if (!tick_check_percpu(curdev, newdev, cpu))
- goto out_bc;
-
- /* Preference decision */
- if (!tick_check_preferred(curdev, newdev))
+ if (!tick_check_replacement(curdev, newdev))
goto out_bc;
if (!try_module_get(newdev->owner))
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index f9745d47425a..475ecceda768 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -45,7 +45,7 @@ int tick_program_event(ktime_t expires, int force)
}
/**
- * tick_resume_onshot - resume oneshot mode
+ * tick_resume_oneshot - resume oneshot mode
*/
void tick_resume_oneshot(void)
{
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e10a4af88737..828b091501ca 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -751,7 +751,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
* Aside of that check whether the local timer softirq is
* pending. If so its a bad idea to call get_next_timer_interrupt()
* because there is an already expired timer, so it will request
- * immeditate expiry, which rearms the hardware timer with a
+ * immediate expiry, which rearms the hardware timer with a
* minimal delta which brings us back to this place
* immediately. Lather, rinse and repeat...
*/
@@ -973,7 +973,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
if (unlikely(local_softirq_pending())) {
static int ratelimit;
- if (ratelimit < 10 &&
+ if (ratelimit < 10 && !local_bh_blocked() &&
(local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
(unsigned int) local_softirq_pending());
@@ -1124,7 +1124,11 @@ ktime_t tick_nohz_get_next_hrtimer(void)
* tick_nohz_get_sleep_length - return the expected length of the current sleep
* @delta_next: duration until the next event if the tick cannot be stopped
*
- * Called from power state control code with interrupts disabled
+ * Called from power state control code with interrupts disabled.
+ *
+ * The return value of this function and/or the value returned by it through the
+ * @delta_next pointer can be negative which must be taken into account by its
+ * callers.
*/
ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
{
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 4fb06527cf64..d952ae393423 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -29,7 +29,7 @@ enum tick_nohz_mode {
* @inidle: Indicator that the CPU is in the tick idle mode
* @tick_stopped: Indicator that the idle tick has been stopped
* @idle_active: Indicator that the CPU is actively in the tick idle mode;
- * it is resetted during irq handling phases.
+ * it is reset during irq handling phases.
* @do_timer_lst: CPU was the last one doing do_timer before going idle
* @got_idle_tick: Tick timer function has run with @inidle set
* @last_tick: Store the last tick expiry time when the tick
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 3985b2b32d08..29923b20e0e4 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -571,7 +571,7 @@ EXPORT_SYMBOL(__usecs_to_jiffies);
/*
* The TICK_NSEC - 1 rounds up the value to the next resolution. Note
* that a remainder subtract here would not do the right thing as the
- * resolution values don't fall on second boundries. I.e. the line:
+ * resolution values don't fall on second boundaries. I.e. the line:
* nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
* Note that due to the small error in the multiplier here, this
* rounding is incorrect for sufficiently large values of tv_nsec, but
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
index 85b98e727306..e6285288d765 100644
--- a/kernel/time/timecounter.c
+++ b/kernel/time/timecounter.c
@@ -76,7 +76,7 @@ static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
return ns;
}
-u64 timecounter_cyc2time(struct timecounter *tc,
+u64 timecounter_cyc2time(const struct timecounter *tc,
u64 cycle_tstamp)
{
u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6aee5768c86f..81fe2a33b80c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -596,14 +596,14 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
* careful cache layout of the timekeeper because the sequence count and
* struct tk_read_base would then need two cache lines instead of one.
*
- * Access to the time keeper clock source is disabled accross the innermost
+ * Access to the time keeper clock source is disabled across the innermost
* steps of suspend/resume. The accessors still work, but the timestamps
* are frozen until time keeping is resumed which happens very early.
*
* For regular suspend/resume there is no observable difference vs. sched
* clock, but it might affect some of the nasty low level debug printks.
*
- * OTOH, access to sched clock is not guaranteed accross suspend/resume on
+ * OTOH, access to sched clock is not guaranteed across suspend/resume on
* all systems either so it depends on the hardware in use.
*
* If that turns out to be a real problem then this could be mitigated by
@@ -899,7 +899,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
/**
- * ktime_mono_to_any() - convert mononotic time to any other time
+ * ktime_mono_to_any() - convert monotonic time to any other time
* @tmono: time to convert.
* @offs: which offset to use
*/
@@ -1427,35 +1427,45 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
static int change_clocksource(void *data)
{
struct timekeeper *tk = &tk_core.timekeeper;
- struct clocksource *new, *old;
+ struct clocksource *new, *old = NULL;
unsigned long flags;
+ bool change = false;
new = (struct clocksource *) data;
- raw_spin_lock_irqsave(&timekeeper_lock, flags);
- write_seqcount_begin(&tk_core.seq);
-
- timekeeping_forward_now(tk);
/*
* If the cs is in module, get a module reference. Succeeds
* for built-in code (owner == NULL) as well.
*/
if (try_module_get(new->owner)) {
- if (!new->enable || new->enable(new) == 0) {
- old = tk->tkr_mono.clock;
- tk_setup_internals(tk, new);
- if (old->disable)
- old->disable(old);
- module_put(old->owner);
- } else {
+ if (!new->enable || new->enable(new) == 0)
+ change = true;
+ else
module_put(new->owner);
- }
}
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&tk_core.seq);
+
+ timekeeping_forward_now(tk);
+
+ if (change) {
+ old = tk->tkr_mono.clock;
+ tk_setup_internals(tk, new);
+ }
+
timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&tk_core.seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (old) {
+ if (old->disable)
+ old->disable(old);
+
+ module_put(old->owner);
+ }
+
return 0;
}
@@ -1948,7 +1958,7 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk,
* xtime_nsec_1 = offset + xtime_nsec_2
* Which gives us:
* xtime_nsec_2 = xtime_nsec_1 - offset
- * Which simplfies to:
+ * Which simplifies to:
* xtime_nsec -= offset
*/
if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) {
@@ -2336,7 +2346,7 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc)
/*
* Validate if a timespec/timeval used to inject a time
- * offset is valid. Offsets can be postive or negative, so
+ * offset is valid. Offsets can be positive or negative, so
* we don't check tv_sec. The value of the timeval/timespec
* is the sum of its fields,but *NOTE*:
* The field tv_usec/tv_nsec must always be non-negative and
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index f475f1a027c8..d111adf4a0cb 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -894,7 +894,7 @@ static inline void forward_timer_base(struct timer_base *base)
/*
* No need to forward if we are close enough below jiffies.
* Also while executing timers, base->clk is 1 offset ahead
- * of jiffies to avoid endless requeuing to current jffies.
+ * of jiffies to avoid endless requeuing to current jiffies.
*/
if ((long)(jnow - base->clk) < 1)
return;
@@ -1271,7 +1271,7 @@ static inline void timer_base_unlock_expiry(struct timer_base *base)
* The counterpart to del_timer_wait_running().
*
* If there is a waiter for base->expiry_lock, then it was waiting for the
- * timer callback to finish. Drop expiry_lock and reaquire it. That allows
+ * timer callback to finish. Drop expiry_lock and reacquire it. That allows
* the waiter to acquire the lock and make progress.
*/
static void timer_sync_wait_running(struct timer_base *base)
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 88e6b8ed6ca5..f0d5062d9cbc 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -108,7 +108,7 @@ void update_vsyscall(struct timekeeper *tk)
/*
* If the current clocksource is not VDSO capable, then spare the
- * update of the high reolution parts.
+ * update of the high resolution parts.
*/
if (clock_mode != VDSO_CLOCKMODE_NONE)
update_vdso_data(vdata, tk);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5c777627212f..915fe8790f04 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3545,7 +3545,11 @@ static char *trace_iter_expand_format(struct trace_iterator *iter)
{
char *tmp;
- if (iter->fmt == static_fmt_buf)
+ /*
+ * iter->tr is NULL when used with tp_printk, which makes
+ * this get called where it is not safe to call krealloc().
+ */
+ if (!iter->tr || iter->fmt == static_fmt_buf)
return NULL;
tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE,
@@ -3566,7 +3570,7 @@ const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
if (WARN_ON_ONCE(!fmt))
return fmt;
- if (iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
+ if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
return fmt;
p = fmt;
@@ -4828,7 +4832,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
cpumask_var_t tracing_cpumask_new;
int err;
- if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
@@ -9692,7 +9696,7 @@ void __init early_trace_init(void)
{
if (tracepoint_printk) {
tracepoint_print_iter =
- kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
+ kzalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
if (MEM_FAIL(!tracepoint_print_iter,
"Failed to allocate trace iterator\n"))
tracepoint_printk = 0;
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index dc971a68dda4..e57cc0870892 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -63,8 +63,10 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
event = p + 1;
*p = '\0';
}
- if (event[0] == '\0')
- return -EINVAL;
+ if (event[0] == '\0') {
+ ret = -EINVAL;
+ goto out;
+ }
mutex_lock(&event_mutex);
for_each_dyn_event_safe(pos, n) {
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index af612945a4d0..9a4b980d695b 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -106,6 +106,7 @@ int create_user_ns(struct cred *new)
if (!ns)
goto fail_dec;
+ ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP);
ret = ns_alloc_inum(&ns->ns);
if (ret)
goto fail_free;
@@ -841,6 +842,60 @@ static int sort_idmaps(struct uid_gid_map *map)
return 0;
}
+/**
+ * verify_root_map() - check the uid 0 mapping
+ * @file: idmapping file
+ * @map_ns: user namespace of the target process
+ * @new_map: requested idmap
+ *
+ * If a process requests mapping parent uid 0 into the new ns, verify that the
+ * process writing the map had the CAP_SETFCAP capability as the target process
+ * will be able to write fscaps that are valid in ancestor user namespaces.
+ *
+ * Return: true if the mapping is allowed, false if not.
+ */
+static bool verify_root_map(const struct file *file,
+ struct user_namespace *map_ns,
+ struct uid_gid_map *new_map)
+{
+ int idx;
+ const struct user_namespace *file_ns = file->f_cred->user_ns;
+ struct uid_gid_extent *extent0 = NULL;
+
+ for (idx = 0; idx < new_map->nr_extents; idx++) {
+ if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+ extent0 = &new_map->extent[idx];
+ else
+ extent0 = &new_map->forward[idx];
+ if (extent0->lower_first == 0)
+ break;
+
+ extent0 = NULL;
+ }
+
+ if (!extent0)
+ return true;
+
+ if (map_ns == file_ns) {
+ /* The process unshared its ns and is writing to its own
+ * /proc/self/uid_map. User already has full capabilites in
+ * the new namespace. Verify that the parent had CAP_SETFCAP
+ * when it unshared.
+ * */
+ if (!file_ns->parent_could_setfcap)
+ return false;
+ } else {
+ /* Process p1 is writing to uid_map of p2, who is in a child
+ * user namespace to p1's. Verify that the opener of the map
+ * file has CAP_SETFCAP against the parent of the new map
+ * namespace */
+ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP))
+ return false;
+ }
+
+ return true;
+}
+
static ssize_t map_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos,
int cap_setid,
@@ -848,7 +903,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
struct uid_gid_map *parent_map)
{
struct seq_file *seq = file->private_data;
- struct user_namespace *ns = seq->private;
+ struct user_namespace *map_ns = seq->private;
struct uid_gid_map new_map;
unsigned idx;
struct uid_gid_extent extent;
@@ -895,7 +950,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
/*
* Adjusting namespace settings requires capabilities on the target.
*/
- if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
+ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN))
goto out;
/* Parse the user data */
@@ -965,7 +1020,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
ret = -EPERM;
/* Validate the user is allowed to use user id's mapped to. */
- if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
+ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map))
goto out;
ret = -EPERM;
@@ -1086,6 +1141,10 @@ static bool new_idmap_permitted(const struct file *file,
struct uid_gid_map *new_map)
{
const struct cred *cred = file->f_cred;
+
+ if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map))
+ return false;
+
/* Don't allow mappings that would allow anything that wouldn't
* be allowed without the establishment of unprivileged mappings.
*/
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 71109065bd8e..107bc38b1945 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -278,9 +278,10 @@ void touch_all_softlockup_watchdogs(void)
* update as well, the only side effect might be a cycle delay for
* the softlockup check.
*/
- for_each_cpu(cpu, &watchdog_allowed_mask)
+ for_each_cpu(cpu, &watchdog_allowed_mask) {
per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
- wq_watchdog_touch(-1);
+ wq_watchdog_touch(cpu);
+ }
}
void touch_softlockup_watchdog_sync(void)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 03fe07d2f39f..b19d759e55a5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1412,7 +1412,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
*/
lockdep_assert_irqs_disabled();
- debug_work_activate(work);
/* if draining, only works from the same workqueue are allowed */
if (unlikely(wq->flags & __WQ_DRAINING) &&
@@ -1494,6 +1493,7 @@ retry:
worklist = &pwq->delayed_works;
}
+ debug_work_activate(work);
insert_work(pwq, work, worklist, work_flags);
out:
@@ -5787,22 +5787,17 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
continue;
/* get the latest of pool and touched timestamps */
+ if (pool->cpu >= 0)
+ touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
+ else
+ touched = READ_ONCE(wq_watchdog_touched);
pool_ts = READ_ONCE(pool->watchdog_ts);
- touched = READ_ONCE(wq_watchdog_touched);
if (time_after(pool_ts, touched))
ts = pool_ts;
else
ts = touched;
- if (pool->cpu >= 0) {
- unsigned long cpu_touched =
- READ_ONCE(per_cpu(wq_watchdog_touched_cpu,
- pool->cpu));
- if (time_after(cpu_touched, ts))
- ts = cpu_touched;
- }
-
/* did we stall? */
if (time_after(jiffies, ts + thresh)) {
lockup_detected = true;
@@ -5826,8 +5821,8 @@ notrace void wq_watchdog_touch(int cpu)
{
if (cpu >= 0)
per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
- else
- wq_watchdog_touched = jiffies;
+
+ wq_watchdog_touched = jiffies;
}
static void wq_watchdog_set_thresh(unsigned long thresh)