summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c19
-rw-r--r--kernel/bpf/disasm.c16
-rw-r--r--kernel/bpf/verifier.c150
-rw-r--r--kernel/cgroup/cgroup-v1.c4
-rw-r--r--kernel/dma/ops_helpers.c12
-rw-r--r--kernel/events/core.c35
-rw-r--r--kernel/sched/core.c90
-rw-r--r--kernel/smpboot.c2
-rw-r--r--kernel/time/posix-cpu-timers.c10
-rw-r--r--kernel/time/timer.c14
-rw-r--r--kernel/trace/ftrace.c5
-rw-r--r--kernel/trace/ring_buffer.c28
-rw-r--r--kernel/trace/trace.c8
-rw-r--r--kernel/trace/trace_events_hist.c46
-rw-r--r--kernel/trace/trace_events_synth.c8
-rw-r--r--kernel/trace/trace_hwlat.c2
-rw-r--r--kernel/trace/trace_synth.h2
-rw-r--r--kernel/tracepoint.c155
-rw-r--r--kernel/ucount.c10
-rw-r--r--kernel/workqueue.c20
20 files changed, 404 insertions, 232 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9b1577498373..b1a5fc04492b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -32,6 +32,8 @@
#include <linux/perf_event.h>
#include <linux/extable.h>
#include <linux/log2.h>
+
+#include <asm/barrier.h>
#include <asm/unaligned.h>
/* Registers */
@@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
+ [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
@@ -1621,7 +1624,21 @@ out:
COND_JMP(s, JSGE, >=)
COND_JMP(s, JSLE, <=)
#undef COND_JMP
- /* STX and ST and LDX*/
+ /* ST, STX and LDX*/
+ ST_NOSPEC:
+ /* Speculation barrier for mitigating Speculative Store Bypass.
+ * In case of arm64, we rely on the firmware mitigation as
+ * controlled via the ssbd kernel parameter. Whenever the
+ * mitigation is enabled, it works for all of the kernel code
+ * with no need to provide any additional instructions here.
+ * In case of x86, we use 'lfence' insn for mitigation. We
+ * reuse preexisting logic from Spectre v1 mitigation that
+ * happens to produce the required code on x86 for v4 as well.
+ */
+#ifdef CONFIG_X86
+ barrier_nospec();
+#endif
+ CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index bbfc6bb79240..ca3cd9aaa6ce 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_%02x\n", insn->code);
}
} else if (class == BPF_ST) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) == BPF_MEM) {
+ verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->imm);
+ } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) {
+ verbose(cbs->private_data, "(%02x) nospec\n", insn->code);
+ } else {
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
- return;
}
- verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg,
- insn->off, insn->imm);
} else if (class == BPF_LDX) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 42a4063de7cd..f9bda5476ea5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0)
reg = &cur->regs[value_regno];
+ if (!env->bypass_spec_v4) {
+ bool sanitize = reg && is_spillable_regtype(reg->type);
+
+ for (i = 0; i < size; i++) {
+ if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ sanitize = true;
+ break;
+ }
+ }
+
+ if (sanitize)
+ env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+ }
if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
@@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
-
if (state != cur && reg->type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
-
- if (!env->bypass_spec_v4) {
- bool sanitize = false;
-
- if (state->stack[spi].slot_type[0] == STACK_SPILL &&
- register_is_const(&state->stack[spi].spilled_ptr))
- sanitize = true;
- for (i = 0; i < BPF_REG_SIZE; i++)
- if (state->stack[spi].slot_type[i] == STACK_MISC) {
- sanitize = true;
- break;
- }
- if (sanitize) {
- int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
- int soff = (-spi - 1) * BPF_REG_SIZE;
-
- /* detected reuse of integer stack slot with a pointer
- * which means either llvm is reusing stack slot or
- * an attacker is trying to exploit CVE-2018-3639
- * (speculative store bypass)
- * Have to sanitize that slot with preemptive
- * store of zero.
- */
- if (*poff && *poff != soff) {
- /* disallow programs where single insn stores
- * into two different stack slots, since verifier
- * cannot sanitize them
- */
- verbose(env,
- "insn %d cannot access two stack slots fp%d and fp%d",
- insn_idx, *poff, soff);
- return -EINVAL;
- }
- *poff = soff;
- }
- }
save_register_state(state, spi, reg);
} else {
u8 type = STACK_MISC;
@@ -3677,6 +3653,8 @@ continue_func:
if (tail_call_reachable)
for (j = 0; j < frame; j++)
subprog[ret_prog[j]].tail_call_reachable = true;
+ if (subprog[0].tail_call_reachable)
+ env->prog->aux->tail_call_reachable = true;
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
@@ -6559,6 +6537,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
alu_state |= ptr_is_dst_reg ?
BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+
+ /* Limit pruning on unknown scalars to enable deep search for
+ * potential masking differences from other program paths.
+ */
+ if (!off_is_imm)
+ env->explore_alu_limits = true;
}
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
@@ -9934,8 +9918,8 @@ next:
}
/* Returns true if (rold safe implies rcur safe) */
-static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
- struct bpf_id_pair *idmap)
+static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
+ struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
{
bool equal;
@@ -9961,6 +9945,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
switch (rold->type) {
case SCALAR_VALUE:
+ if (env->explore_alu_limits)
+ return false;
if (rcur->type == SCALAR_VALUE) {
if (!rold->precise && !rcur->precise)
return true;
@@ -10051,9 +10037,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
}
-static bool stacksafe(struct bpf_func_state *old,
- struct bpf_func_state *cur,
- struct bpf_id_pair *idmap)
+static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
+ struct bpf_func_state *cur, struct bpf_id_pair *idmap)
{
int i, spi;
@@ -10098,9 +10083,8 @@ static bool stacksafe(struct bpf_func_state *old,
continue;
if (old->stack[spi].slot_type[0] != STACK_SPILL)
continue;
- if (!regsafe(&old->stack[spi].spilled_ptr,
- &cur->stack[spi].spilled_ptr,
- idmap))
+ if (!regsafe(env, &old->stack[spi].spilled_ptr,
+ &cur->stack[spi].spilled_ptr, idmap))
/* when explored and current stack slot are both storing
* spilled registers, check that stored pointers types
* are the same as well.
@@ -10157,10 +10141,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
for (i = 0; i < MAX_BPF_REG; i++)
- if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch))
+ if (!regsafe(env, &old->regs[i], &cur->regs[i],
+ env->idmap_scratch))
return false;
- if (!stacksafe(old, cur, env->idmap_scratch))
+ if (!stacksafe(env, old, cur, env->idmap_scratch))
return false;
if (!refsafe(old, cur))
@@ -11904,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ bool ctx_access;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
type = BPF_READ;
- else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_DW))
+ ctx_access = true;
+ } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_DW)) {
type = BPF_WRITE;
- else
+ ctx_access = BPF_CLASS(insn->code) == BPF_STX;
+ } else {
continue;
+ }
if (type == BPF_WRITE &&
- env->insn_aux_data[i + delta].sanitize_stack_off) {
+ env->insn_aux_data[i + delta].sanitize_stack_spill) {
struct bpf_insn patch[] = {
- /* Sanitize suspicious stack slot with zero.
- * There are no memory dependencies for this store,
- * since it's only using frame pointer and immediate
- * constant of zero
- */
- BPF_ST_MEM(BPF_DW, BPF_REG_FP,
- env->insn_aux_data[i + delta].sanitize_stack_off,
- 0),
- /* the original STX instruction will immediately
- * overwrite the same stack slot with appropriate value
- */
*insn,
+ BPF_ST_NOSPEC(),
};
cnt = ARRAY_SIZE(patch);
@@ -11946,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
continue;
}
+ if (!ctx_access)
+ continue;
+
switch (env->insn_aux_data[i + delta].ptr_type) {
case PTR_TO_CTX:
if (!ops->convert_ctx_access)
@@ -12750,37 +12736,6 @@ static void free_states(struct bpf_verifier_env *env)
}
}
-/* The verifier is using insn_aux_data[] to store temporary data during
- * verification and to store information for passes that run after the
- * verification like dead code sanitization. do_check_common() for subprogram N
- * may analyze many other subprograms. sanitize_insn_aux_data() clears all
- * temporary data after do_check_common() finds that subprogram N cannot be
- * verified independently. pass_cnt counts the number of times
- * do_check_common() was run and insn->aux->seen tells the pass number
- * insn_aux_data was touched. These variables are compared to clear temporary
- * data from failed pass. For testing and experiments do_check_common() can be
- * run multiple times even when prior attempt to verify is unsuccessful.
- *
- * Note that special handling is needed on !env->bypass_spec_v1 if this is
- * ever called outside of error path with subsequent program rejection.
- */
-static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
-{
- struct bpf_insn *insn = env->prog->insnsi;
- struct bpf_insn_aux_data *aux;
- int i, class;
-
- for (i = 0; i < env->prog->len; i++) {
- class = BPF_CLASS(insn[i].code);
- if (class != BPF_LDX && class != BPF_STX)
- continue;
- aux = &env->insn_aux_data[i];
- if (aux->seen != env->pass_cnt)
- continue;
- memset(aux, 0, offsetof(typeof(*aux), orig_idx));
- }
-}
-
static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
@@ -12857,9 +12812,6 @@ out:
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
- if (ret)
- /* clean aux data in case subprog was rejected */
- sanitize_insn_aux_data(env);
return ret;
}
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 8d6bf56ed77a..de2c432dee20 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1221,9 +1221,7 @@ int cgroup1_get_tree(struct fs_context *fc)
ret = cgroup_do_get_tree(fc);
if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) {
- struct super_block *sb = fc->root->d_sb;
- dput(fc->root);
- deactivate_locked_super(sb);
+ fc_drop_locked(fc);
ret = 1;
}
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 910ae69cae77..af4a6ef48ce0 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -5,6 +5,13 @@
*/
#include <linux/dma-map-ops.h>
+static struct page *dma_common_vaddr_to_page(void *cpu_addr)
+{
+ if (is_vmalloc_addr(cpu_addr))
+ return vmalloc_to_page(cpu_addr);
+ return virt_to_page(cpu_addr);
+}
+
/*
* Create scatter-list for the already allocated DMA buffer.
*/
@@ -12,7 +19,7 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
- struct page *page = virt_to_page(cpu_addr);
+ struct page *page = dma_common_vaddr_to_page(cpu_addr);
int ret;
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
@@ -32,6 +39,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
+ struct page *page = dma_common_vaddr_to_page(cpu_addr);
int ret = -ENXIO;
vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
@@ -43,7 +51,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
return -ENXIO;
return remap_pfn_range(vma, vma->vm_start,
- page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
+ page_to_pfn(page) + vma->vm_pgoff,
user_count << PAGE_SHIFT, vma->vm_page_prot);
#else
return -ENXIO;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 464917096e73..1cb1f9b8392e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11917,6 +11917,37 @@ again:
return gctx;
}
+static bool
+perf_check_permission(struct perf_event_attr *attr, struct task_struct *task)
+{
+ unsigned int ptrace_mode = PTRACE_MODE_READ_REALCREDS;
+ bool is_capable = perfmon_capable();
+
+ if (attr->sigtrap) {
+ /*
+ * perf_event_attr::sigtrap sends signals to the other task.
+ * Require the current task to also have CAP_KILL.
+ */
+ rcu_read_lock();
+ is_capable &= ns_capable(__task_cred(task)->user_ns, CAP_KILL);
+ rcu_read_unlock();
+
+ /*
+ * If the required capabilities aren't available, checks for
+ * ptrace permissions: upgrade to ATTACH, since sending signals
+ * can effectively change the target task.
+ */
+ ptrace_mode = PTRACE_MODE_ATTACH_REALCREDS;
+ }
+
+ /*
+ * Preserve ptrace permission check for backwards compatibility. The
+ * ptrace check also includes checks that the current task and other
+ * task have matching uids, and is therefore not done here explicitly.
+ */
+ return is_capable || ptrace_may_access(task, ptrace_mode);
+}
+
/**
* sys_perf_event_open - open a performance event, associate it to a task/cpu
*
@@ -12163,15 +12194,13 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_file;
/*
- * Preserve ptrace permission check for backwards compatibility.
- *
* We must hold exec_update_lock across this and any potential
* perf_install_in_context() call for this new event to
* serialize against exec() altering our credentials (and the
* perf_event_exit_task() that could imply).
*/
err = -EACCES;
- if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+ if (!perf_check_permission(&attr, task))
goto err_cred;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d9ff40f4661..20ffcc044134 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1981,12 +1981,18 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
dequeue_task(rq, p, flags);
}
-/*
- * __normal_prio - return the priority that is based on the static prio
- */
-static inline int __normal_prio(struct task_struct *p)
+static inline int __normal_prio(int policy, int rt_prio, int nice)
{
- return p->static_prio;
+ int prio;
+
+ if (dl_policy(policy))
+ prio = MAX_DL_PRIO - 1;
+ else if (rt_policy(policy))
+ prio = MAX_RT_PRIO - 1 - rt_prio;
+ else
+ prio = NICE_TO_PRIO(nice);
+
+ return prio;
}
/*
@@ -1998,15 +2004,7 @@ static inline int __normal_prio(struct task_struct *p)
*/
static inline int normal_prio(struct task_struct *p)
{
- int prio;
-
- if (task_has_dl_policy(p))
- prio = MAX_DL_PRIO-1;
- else if (task_has_rt_policy(p))
- prio = MAX_RT_PRIO-1 - p->rt_priority;
- else
- prio = __normal_prio(p);
- return prio;
+ return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio));
}
/*
@@ -4099,7 +4097,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
} else if (PRIO_TO_NICE(p->static_prio) < 0)
p->static_prio = NICE_TO_PRIO(0);
- p->prio = p->normal_prio = __normal_prio(p);
+ p->prio = p->normal_prio = p->static_prio;
set_load_weight(p, false);
/*
@@ -6341,6 +6339,18 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag
}
EXPORT_SYMBOL(default_wake_function);
+static void __setscheduler_prio(struct task_struct *p, int prio)
+{
+ if (dl_prio(prio))
+ p->sched_class = &dl_sched_class;
+ else if (rt_prio(prio))
+ p->sched_class = &rt_sched_class;
+ else
+ p->sched_class = &fair_sched_class;
+
+ p->prio = prio;
+}
+
#ifdef CONFIG_RT_MUTEXES
static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
@@ -6456,22 +6466,19 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
} else {
p->dl.pi_se = &p->dl;
}
- p->sched_class = &dl_sched_class;
} else if (rt_prio(prio)) {
if (dl_prio(oldprio))
p->dl.pi_se = &p->dl;
if (oldprio < prio)
queue_flag |= ENQUEUE_HEAD;
- p->sched_class = &rt_sched_class;
} else {
if (dl_prio(oldprio))
p->dl.pi_se = &p->dl;
if (rt_prio(oldprio))
p->rt.timeout = 0;
- p->sched_class = &fair_sched_class;
}
- p->prio = prio;
+ __setscheduler_prio(p, prio);
if (queued)
enqueue_task(rq, p, queue_flag);
@@ -6824,35 +6831,6 @@ static void __setscheduler_params(struct task_struct *p,
set_load_weight(p, true);
}
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
- const struct sched_attr *attr, bool keep_boost)
-{
- /*
- * If params can't change scheduling class changes aren't allowed
- * either.
- */
- if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
- return;
-
- __setscheduler_params(p, attr);
-
- /*
- * Keep a potential priority boosting if called from
- * sched_setscheduler().
- */
- p->prio = normal_prio(p);
- if (keep_boost)
- p->prio = rt_effective_prio(p, p->prio);
-
- if (dl_prio(p->prio))
- p->sched_class = &dl_sched_class;
- else if (rt_prio(p->prio))
- p->sched_class = &rt_sched_class;
- else
- p->sched_class = &fair_sched_class;
-}
-
/*
* Check the target process has a UID that matches the current process's:
*/
@@ -6873,10 +6851,8 @@ static int __sched_setscheduler(struct task_struct *p,
const struct sched_attr *attr,
bool user, bool pi)
{
- int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
- MAX_RT_PRIO - 1 - attr->sched_priority;
- int retval, oldprio, oldpolicy = -1, queued, running;
- int new_effective_prio, policy = attr->sched_policy;
+ int oldpolicy = -1, policy = attr->sched_policy;
+ int retval, oldprio, newprio, queued, running;
const struct sched_class *prev_class;
struct callback_head *head;
struct rq_flags rf;
@@ -7074,6 +7050,7 @@ change:
p->sched_reset_on_fork = reset_on_fork;
oldprio = p->prio;
+ newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice);
if (pi) {
/*
* Take priority boosted tasks into account. If the new
@@ -7082,8 +7059,8 @@ change:
* the runqueue. This will be done when the task deboost
* itself.
*/
- new_effective_prio = rt_effective_prio(p, newprio);
- if (new_effective_prio == oldprio)
+ newprio = rt_effective_prio(p, newprio);
+ if (newprio == oldprio)
queue_flags &= ~DEQUEUE_MOVE;
}
@@ -7096,7 +7073,10 @@ change:
prev_class = p->sched_class;
- __setscheduler(rq, p, attr, pi);
+ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
+ __setscheduler_params(p, attr);
+ __setscheduler_prio(p, newprio);
+ }
__setscheduler_uclamp(p, attr);
if (queued) {
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index e4163042c4d6..cf6acab78538 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -47,7 +47,7 @@ void __init idle_thread_set_boot_cpu(void)
*
* Creates the thread if it does not exist.
*/
-static inline void idle_init(unsigned int cpu)
+static __always_inline void idle_init(unsigned int cpu)
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 29a5e54e6e10..517be7fd175e 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -991,6 +991,11 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
if (!p)
goto out;
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL))
+ goto out;
+
/*
* Fetch the current sample and update the timer's expiry time.
*/
@@ -1001,11 +1006,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
bump_cpu_timer(timer, now);
- /* Protect timer list r/w in arm_timer() */
- sighand = lock_task_sighand(p, &flags);
- if (unlikely(sighand == NULL))
- goto out;
-
/*
* Now re-arm for the new expiry time.
*/
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3fadb58fc9d7..e3d2c23c413d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -207,6 +207,7 @@ struct timer_base {
unsigned int cpu;
bool next_expiry_recalc;
bool is_idle;
+ bool timers_pending;
DECLARE_BITMAP(pending_map, WHEEL_SIZE);
struct hlist_head vectors[WHEEL_SIZE];
} ____cacheline_aligned;
@@ -595,6 +596,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
* can reevaluate the wheel:
*/
base->next_expiry = bucket_expiry;
+ base->timers_pending = true;
base->next_expiry_recalc = false;
trigger_dyntick_cpu(base, timer);
}
@@ -1263,8 +1265,10 @@ static inline void timer_base_unlock_expiry(struct timer_base *base)
static void timer_sync_wait_running(struct timer_base *base)
{
if (atomic_read(&base->timer_waiters)) {
+ raw_spin_unlock_irq(&base->lock);
spin_unlock(&base->expiry_lock);
spin_lock(&base->expiry_lock);
+ raw_spin_lock_irq(&base->lock);
}
}
@@ -1455,14 +1459,14 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
if (timer->flags & TIMER_IRQSAFE) {
raw_spin_unlock(&base->lock);
call_timer_fn(timer, fn, baseclk);
- base->running_timer = NULL;
raw_spin_lock(&base->lock);
+ base->running_timer = NULL;
} else {
raw_spin_unlock_irq(&base->lock);
call_timer_fn(timer, fn, baseclk);
+ raw_spin_lock_irq(&base->lock);
base->running_timer = NULL;
timer_sync_wait_running(base);
- raw_spin_lock_irq(&base->lock);
}
}
}
@@ -1582,6 +1586,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
}
base->next_expiry_recalc = false;
+ base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
return next;
}
@@ -1633,7 +1638,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
- bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
@@ -1646,7 +1650,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
if (base->next_expiry_recalc)
base->next_expiry = __next_timer_interrupt(base);
nextevt = base->next_expiry;
- is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
/*
* We have a fresh next event. Check whether we can forward the
@@ -1664,7 +1667,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
expires = basem;
base->is_idle = false;
} else {
- if (!is_max_delta)
+ if (base->timers_pending)
expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle.
@@ -1947,6 +1950,7 @@ int timers_prepare_cpu(unsigned int cpu)
base = per_cpu_ptr(&timer_bases[b], cpu);
base->clk = jiffies;
base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->timers_pending = false;
base->is_idle = false;
}
return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e6fb3e6e1ffc..7b180f61e6d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5985,7 +5985,8 @@ ftrace_graph_release(struct inode *inode, struct file *file)
* infrastructure to do the synchronization, thus we must do it
* ourselves.
*/
- synchronize_rcu_tasks_rude();
+ if (old_hash != EMPTY_HASH)
+ synchronize_rcu_tasks_rude();
free_ftrace_hash(old_hash);
}
@@ -7544,7 +7545,7 @@ int ftrace_is_dead(void)
*/
int register_ftrace_function(struct ftrace_ops *ops)
{
- int ret = -1;
+ int ret;
ftrace_ops_init(ops);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d1463eac11a3..e592d1df6f88 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3880,10 +3880,30 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
if (unlikely(!head))
return true;
- return reader->read == rb_page_commit(reader) &&
- (commit == reader ||
- (commit == head &&
- head->read == rb_page_commit(commit)));
+ /* Reader should exhaust content in reader page */
+ if (reader->read != rb_page_commit(reader))
+ return false;
+
+ /*
+ * If writers are committing on the reader page, knowing all
+ * committed content has been read, the ring buffer is empty.
+ */
+ if (commit == reader)
+ return true;
+
+ /*
+ * If writers are committing on a page other than reader page
+ * and head page, there should always be content to read.
+ */
+ if (commit != head)
+ return false;
+
+ /*
+ * Writers are committing on the head page, we just need
+ * to care about there're committed data, and the reader will
+ * swap reader page with head page when it is to read data.
+ */
+ return rb_page_commit(commit) == 0;
}
/**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f8b80b5bab71..33899a71fdc1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5609,6 +5609,10 @@ static const char readme_msg[] =
"\t [:name=histname1]\n"
"\t [:<handler>.<action>]\n"
"\t [if <filter>]\n\n"
+ "\t Note, special fields can be used as well:\n"
+ "\t common_timestamp - to record current timestamp\n"
+ "\t common_cpu - to record the CPU the event happened on\n"
+ "\n"
"\t When a matching event is hit, an entry is added to a hash\n"
"\t table using the key(s) and value(s) named, and the value of a\n"
"\t sum called 'hitcount' is incremented. Keys and values\n"
@@ -9131,8 +9135,10 @@ static int trace_array_create_dir(struct trace_array *tr)
return -EINVAL;
ret = event_trace_add_tracer(tr->dir, tr);
- if (ret)
+ if (ret) {
tracefs_remove(tr->dir);
+ return ret;
+ }
init_tracer_tracefs(tr, tr->dir);
__update_tracer_options(tr);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 16a9dfc9fffc..949ef09dc537 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -65,7 +65,8 @@
C(INVALID_SORT_MODIFIER,"Invalid sort modifier"), \
C(EMPTY_SORT_FIELD, "Empty sort field"), \
C(TOO_MANY_SORT_FIELDS, "Too many sort fields (Max = 2)"), \
- C(INVALID_SORT_FIELD, "Sort field must be a key or a val"),
+ C(INVALID_SORT_FIELD, "Sort field must be a key or a val"), \
+ C(INVALID_STR_OPERAND, "String type can not be an operand in expression"),
#undef C
#define C(a, b) HIST_ERR_##a
@@ -1111,7 +1112,7 @@ static const char *hist_field_name(struct hist_field *field,
field->flags & HIST_FIELD_FL_ALIAS)
field_name = hist_field_name(field->operands[0], ++level);
else if (field->flags & HIST_FIELD_FL_CPU)
- field_name = "cpu";
+ field_name = "common_cpu";
else if (field->flags & HIST_FIELD_FL_EXPR ||
field->flags & HIST_FIELD_FL_VAR_REF) {
if (field->system) {
@@ -1991,14 +1992,24 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
hist_data->enable_timestamps = true;
if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
hist_data->attrs->ts_in_usecs = true;
- } else if (strcmp(field_name, "cpu") == 0)
+ } else if (strcmp(field_name, "common_cpu") == 0)
*flags |= HIST_FIELD_FL_CPU;
else {
field = trace_find_event_field(file->event_call, field_name);
if (!field || !field->size) {
- hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name));
- field = ERR_PTR(-EINVAL);
- goto out;
+ /*
+ * For backward compatibility, if field_name
+ * was "cpu", then we treat this the same as
+ * common_cpu.
+ */
+ if (strcmp(field_name, "cpu") == 0) {
+ *flags |= HIST_FIELD_FL_CPU;
+ } else {
+ hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
+ errpos(field_name));
+ field = ERR_PTR(-EINVAL);
+ goto out;
+ }
}
}
out:
@@ -2146,6 +2157,13 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
ret = PTR_ERR(operand1);
goto free;
}
+ if (operand1->flags & HIST_FIELD_FL_STRING) {
+ /* String type can not be the operand of unary operator. */
+ hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
+ destroy_hist_field(operand1, 0);
+ ret = -EINVAL;
+ goto free;
+ }
expr->flags |= operand1->flags &
(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
@@ -2247,6 +2265,11 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
operand1 = NULL;
goto free;
}
+ if (operand1->flags & HIST_FIELD_FL_STRING) {
+ hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
+ ret = -EINVAL;
+ goto free;
+ }
/* rest of string could be another expression e.g. b+c in a+b+c */
operand_flags = 0;
@@ -2256,6 +2279,11 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
operand2 = NULL;
goto free;
}
+ if (operand2->flags & HIST_FIELD_FL_STRING) {
+ hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
+ ret = -EINVAL;
+ goto free;
+ }
ret = check_expr_operands(file->tr, operand1, operand2);
if (ret)
@@ -2277,6 +2305,10 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
expr->operands[0] = operand1;
expr->operands[1] = operand2;
+
+ /* The operand sizes should be the same, so just pick one */
+ expr->size = operand1->size;
+
expr->operator = field_op;
expr->name = expr_str(expr, 0);
expr->type = kstrdup(operand1->type, GFP_KERNEL);
@@ -5085,7 +5117,7 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
seq_printf(m, "%s=", hist_field->var.name);
if (hist_field->flags & HIST_FIELD_FL_CPU)
- seq_puts(m, "cpu");
+ seq_puts(m, "common_cpu");
else if (field_name) {
if (hist_field->flags & HIST_FIELD_FL_VAR_REF ||
hist_field->flags & HIST_FIELD_FL_ALIAS)
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 2ac75eb6aa86..9315fc03e303 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -893,15 +893,13 @@ static struct synth_event *alloc_synth_event(const char *name, int n_fields,
dyn_event_init(&event->devent, &synth_event_ops);
for (i = 0, j = 0; i < n_fields; i++) {
+ fields[i]->field_pos = i;
event->fields[i] = fields[i];
- if (fields[i]->is_dynamic) {
- event->dynamic_fields[j] = fields[i];
- event->dynamic_fields[j]->field_pos = i;
+ if (fields[i]->is_dynamic)
event->dynamic_fields[j++] = fields[i];
- event->n_dynamic_fields++;
- }
}
+ event->n_dynamic_fields = j;
event->n_fields = n_fields;
out:
return event;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index a6c0cdaf4b87..14f46aae1981 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -327,7 +327,7 @@ static void move_to_next_cpu(void)
get_online_cpus();
cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
- next_cpu = cpumask_next(smp_processor_id(), current_mask);
+ next_cpu = cpumask_next(raw_smp_processor_id(), current_mask);
put_online_cpus();
if (next_cpu >= nr_cpu_ids)
diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h
index 6e146b959dcd..4007fe95cf42 100644
--- a/kernel/trace/trace_synth.h
+++ b/kernel/trace/trace_synth.h
@@ -14,10 +14,10 @@ struct synth_field {
char *name;
size_t size;
unsigned int offset;
+ unsigned int field_pos;
bool is_signed;
bool is_string;
bool is_dynamic;
- bool field_pos;
};
struct synth_event {
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 976bf8ce8039..efd14c79fab4 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -15,12 +15,57 @@
#include <linux/sched/task.h>
#include <linux/static_key.h>
+enum tp_func_state {
+ TP_FUNC_0,
+ TP_FUNC_1,
+ TP_FUNC_2,
+ TP_FUNC_N,
+};
+
extern tracepoint_ptr_t __start___tracepoints_ptrs[];
extern tracepoint_ptr_t __stop___tracepoints_ptrs[];
DEFINE_SRCU(tracepoint_srcu);
EXPORT_SYMBOL_GPL(tracepoint_srcu);
+enum tp_transition_sync {
+ TP_TRANSITION_SYNC_1_0_1,
+ TP_TRANSITION_SYNC_N_2_1,
+
+ _NR_TP_TRANSITION_SYNC,
+};
+
+struct tp_transition_snapshot {
+ unsigned long rcu;
+ unsigned long srcu;
+ bool ongoing;
+};
+
+/* Protected by tracepoints_mutex */
+static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC];
+
+static void tp_rcu_get_state(enum tp_transition_sync sync)
+{
+ struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+ /* Keep the latest get_state snapshot. */
+ snapshot->rcu = get_state_synchronize_rcu();
+ snapshot->srcu = start_poll_synchronize_srcu(&tracepoint_srcu);
+ snapshot->ongoing = true;
+}
+
+static void tp_rcu_cond_sync(enum tp_transition_sync sync)
+{
+ struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+ if (!snapshot->ongoing)
+ return;
+ cond_synchronize_rcu(snapshot->rcu);
+ if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu))
+ synchronize_srcu(&tracepoint_srcu);
+ snapshot->ongoing = false;
+}
+
/* Set to 1 to enable tracepoint debug output */
static const int tracepoint_debug;
@@ -246,26 +291,29 @@ static void *func_remove(struct tracepoint_func **funcs,
return old;
}
-static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs, bool sync)
+/*
+ * Count the number of functions (enum tp_func_state) in a tp_funcs array.
+ */
+static enum tp_func_state nr_func_state(const struct tracepoint_func *tp_funcs)
+{
+ if (!tp_funcs)
+ return TP_FUNC_0;
+ if (!tp_funcs[1].func)
+ return TP_FUNC_1;
+ if (!tp_funcs[2].func)
+ return TP_FUNC_2;
+ return TP_FUNC_N; /* 3 or more */
+}
+
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
{
void *func = tp->iterator;
/* Synthetic events do not have static call sites */
if (!tp->static_call_key)
return;
-
- if (!tp_funcs[1].func) {
+ if (nr_func_state(tp_funcs) == TP_FUNC_1)
func = tp_funcs[0].func;
- /*
- * If going from the iterator back to a single caller,
- * we need to synchronize with __DO_TRACE to make sure
- * that the data passed to the callback is the one that
- * belongs to that callback.
- */
- if (sync)
- tracepoint_synchronize_unregister();
- }
-
__static_call_update(tp->static_call_key, tp->static_call_tramp, func);
}
@@ -299,9 +347,41 @@ static int tracepoint_add_func(struct tracepoint *tp,
* a pointer to it. This array is referenced by __DO_TRACE from
* include/linux/tracepoint.h using rcu_dereference_sched().
*/
- rcu_assign_pointer(tp->funcs, tp_funcs);
- tracepoint_update_call(tp, tp_funcs, false);
- static_key_enable(&tp->key);
+ switch (nr_func_state(tp_funcs)) {
+ case TP_FUNC_1: /* 0->1 */
+ /*
+ * Make sure new static func never uses old data after a
+ * 1->0->1 transition sequence.
+ */
+ tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1);
+ /* Set static call to first function */
+ tracepoint_update_call(tp, tp_funcs);
+ /* Both iterator and static call handle NULL tp->funcs */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ static_key_enable(&tp->key);
+ break;
+ case TP_FUNC_2: /* 1->2 */
+ /* Set iterator static call */
+ tracepoint_update_call(tp, tp_funcs);
+ /*
+ * Iterator callback installed before updating tp->funcs.
+ * Requires ordering between RCU assign/dereference and
+ * static call update/call.
+ */
+ fallthrough;
+ case TP_FUNC_N: /* N->N+1 (N>1) */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>1) transition sequence.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
release_probes(old);
return 0;
@@ -328,17 +408,52 @@ static int tracepoint_remove_func(struct tracepoint *tp,
/* Failed allocating new tp_funcs, replaced func with stub */
return 0;
- if (!tp_funcs) {
+ switch (nr_func_state(tp_funcs)) {
+ case TP_FUNC_0: /* 1->0 */
/* Removed last function */
if (tp->unregfunc && static_key_enabled(&tp->key))
tp->unregfunc();
static_key_disable(&tp->key);
+ /* Set iterator static call */
+ tracepoint_update_call(tp, tp_funcs);
+ /* Both iterator and static call handle NULL tp->funcs */
+ rcu_assign_pointer(tp->funcs, NULL);
+ /*
+ * Make sure new static func never uses old data after a
+ * 1->0->1 transition sequence.
+ */
+ tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1);
+ break;
+ case TP_FUNC_1: /* 2->1 */
rcu_assign_pointer(tp->funcs, tp_funcs);
- } else {
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>2) transition sequence. If the first
+ * element's data has changed, then force the synchronization
+ * to prevent current readers that have loaded the old data
+ * from calling the new function.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1);
+ /* Set static call to first function */
+ tracepoint_update_call(tp, tp_funcs);
+ break;
+ case TP_FUNC_2: /* N->N-1 (N>2) */
+ fallthrough;
+ case TP_FUNC_N:
rcu_assign_pointer(tp->funcs, tp_funcs);
- tracepoint_update_call(tp, tp_funcs,
- tp_funcs[0].func != old[0].func);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>2) transition sequence.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
}
release_probes(old);
return 0;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 87799e2379bd..77be3bbe3cc4 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -160,6 +160,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
{
struct hlist_head *hashent = ucounts_hashentry(ns, uid);
struct ucounts *ucounts, *new;
+ long overflow;
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
@@ -184,8 +185,12 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
return new;
}
}
+ overflow = atomic_add_negative(1, &ucounts->count);
spin_unlock_irq(&ucounts_lock);
- ucounts = get_ucounts(ucounts);
+ if (overflow) {
+ put_ucounts(ucounts);
+ return NULL;
+ }
return ucounts;
}
@@ -193,8 +198,7 @@ void put_ucounts(struct ucounts *ucounts)
{
unsigned long flags;
- if (atomic_dec_and_test(&ucounts->count)) {
- spin_lock_irqsave(&ucounts_lock, flags);
+ if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) {
hlist_del_init(&ucounts->node);
spin_unlock_irqrestore(&ucounts_lock, flags);
kfree(ucounts);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 50142fc08902..f148eacda55a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3676,15 +3676,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
unbound_release_work);
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
- bool is_last;
+ bool is_last = false;
- if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
- return;
+ /*
+ * when @pwq is not linked, it doesn't hold any reference to the
+ * @wq, and @wq is invalid to access.
+ */
+ if (!list_empty(&pwq->pwqs_node)) {
+ if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
+ return;
- mutex_lock(&wq->mutex);
- list_del_rcu(&pwq->pwqs_node);
- is_last = list_empty(&wq->pwqs);
- mutex_unlock(&wq->mutex);
+ mutex_lock(&wq->mutex);
+ list_del_rcu(&pwq->pwqs_node);
+ is_last = list_empty(&wq->pwqs);
+ mutex_unlock(&wq->mutex);
+ }
mutex_lock(&wq_pool_mutex);
put_unbound_pool(pool);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-28 17:59:28 +0000