Merge branch 'linus' into sched/core, to resolve semantic conflict

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/bpf/Makefile

@@ -1,6 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
-CFLAGS_core.o += $(call cc-disable-warning, override-init)
+ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
+# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
+cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
+endif
+CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o

kernel/bpf/bpf_lsm.c

@@ -13,6 +13,7 @@
 #include <linux/bpf_verifier.h>
 #include <net/bpf_sk_storage.h>
 #include <linux/bpf_local_storage.h>
+#include <linux/btf_ids.h>
 
 /* For every LSM hook that allows attachment of BPF programs, declare a nop
  * function where a BPF program can be attached.
@@ -26,7 +27,11 @@ noinline RET bpf_lsm_##NAME(__VA_ARGS__)	\
 #include <linux/lsm_hook_defs.h>
 #undef LSM_HOOK
 
-#define BPF_LSM_SYM_PREFX  "bpf_lsm_"
+#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME)
+BTF_SET_START(bpf_lsm_hooks)
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+BTF_SET_END(bpf_lsm_hooks)
 
 int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 			const struct bpf_prog *prog)
@@ -37,8 +42,7 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 		return -EINVAL;
 	}
 
-	if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name,
-		    sizeof(BPF_LSM_SYM_PREFX) - 1)) {
+	if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) {
 		bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n",
 			prog->aux->attach_btf_id, prog->aux->attach_func_name);
 		return -EINVAL;

kernel/bpf/core.c

@@ -1369,7 +1369,7 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
  *
  * Decode and execute eBPF instructions.
  */
-static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
 #define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
 #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z

kernel/bpf/hashtab.c

@@ -821,6 +821,32 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 	}
 }
 
+static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
+			    void *value, bool onallcpus)
+{
+	/* When using prealloc and not setting the initial value on all cpus,
+	 * zero-fill element values for other cpus (just as what happens when
+	 * not using prealloc). Otherwise, bpf program has no way to ensure
+	 * known initial values for cpus other than current one
+	 * (onallcpus=false always when coming from bpf prog).
+	 */
+	if (htab_is_prealloc(htab) && !onallcpus) {
+		u32 size = round_up(htab->map.value_size, 8);
+		int current_cpu = raw_smp_processor_id();
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			if (cpu == current_cpu)
+				bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value,
+						size);
+			else
+				memset(per_cpu_ptr(pptr, cpu), 0, size);
+		}
+	} else {
+		pcpu_copy_value(htab, pptr, value, onallcpus);
+	}
+}
+
 static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 {
 	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
@@ -891,7 +917,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			}
 		}
 
-		pcpu_copy_value(htab, pptr, value, onallcpus);
+		pcpu_init_value(htab, pptr, value, onallcpus);
 
 		if (!prealloc)
 			htab_elem_set_ptr(l_new, key_size, pptr);
@@ -1183,7 +1209,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
 				value, onallcpus);
 	} else {
-		pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+		pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
 				value, onallcpus);
 		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;

kernel/bpf/preload/Kconfig

@@ -6,6 +6,7 @@ config USERMODE_DRIVER
 menuconfig BPF_PRELOAD
 	bool "Preload BPF file system with kernel specific program and map iterators"
 	depends on BPF
+	depends on BPF_SYSCALL
 	# The dependency on !COMPILE_TEST prevents it from being enabled
 	# in allmodconfig or allyesconfig configurations
 	depends on !COMPILE_TEST

kernel/bpf/verifier.c

@@ -7786,9 +7786,11 @@ static int check_return_code(struct bpf_verifier_env *env)
 	struct tnum range = tnum_range(0, 1);
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 	int err;
+	const bool is_subprog = env->cur_state->frame[0]->subprogno;
 
 	/* LSM and struct_ops func-ptr's return type could be "void" */
-	if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
+	if (!is_subprog &&
+	    (prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
 	     prog_type == BPF_PROG_TYPE_LSM) &&
 	    !prog->aux->attach_func_proto->type)
 		return 0;
@@ -7808,6 +7810,16 @@ static int check_return_code(struct bpf_verifier_env *env)
 		return -EACCES;
 	}
 
+	reg = cur_regs(env) + BPF_REG_0;
+	if (is_subprog) {
+		if (reg->type != SCALAR_VALUE) {
+			verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
+				reg_type_str[reg->type]);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
 	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
@@ -7861,7 +7873,6 @@ static int check_return_code(struct bpf_verifier_env *env)
 		return 0;
 	}
 
-	reg = cur_regs(env) + BPF_REG_0;
 	if (reg->type != SCALAR_VALUE) {
 		verbose(env, "At program exit the register R0 is not a known value (%s)\n",
 			reg_type_str[reg->type]);
@@ -9572,12 +9583,13 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			       struct bpf_insn *insn,
 			       struct bpf_insn_aux_data *aux)
 {
-	u32 datasec_id, type, id = insn->imm;
 	const struct btf_var_secinfo *vsi;
 	const struct btf_type *datasec;
 	const struct btf_type *t;
 	const char *sym_name;
 	bool percpu = false;
+	u32 type, id = insn->imm;
+	s32 datasec_id;
 	u64 addr;
 	int i;
 

kernel/dma/swiotlb.c

@@ -229,6 +229,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	if (verbose)
 		swiotlb_print_info();
@@ -260,9 +261,11 @@ swiotlb_init(int verbose)
 	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
 		return;
 
-	if (io_tlb_start)
+	if (io_tlb_start) {
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+		io_tlb_start = 0;
+	}
 	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
@@ -360,6 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	swiotlb_print_info();
 
@@ -441,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr,
-				   size_t mapping_size,
-				   size_t alloc_size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
+	dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
 	unsigned long flags;
 	phys_addr_t tlb_addr;
 	unsigned int nslots, stride, index, wrap;
@@ -667,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
 			      swiotlb_force);
 
-	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			phys_to_dma_unencrypted(dev, io_tlb_start),
-			paddr, size, size, dir, attrs);
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+			attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 

kernel/entry/common.c

@@ -337,10 +337,10 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * already contains a warning when RCU is not watching, so no point
 	 * in having another one here.
 	 */
+	lockdep_hardirqs_off(CALLER_ADDR0);
 	instrumentation_begin();
 	rcu_irq_enter_check_tick();
-	/* Use the combo lockdep/tracing function */
-	trace_hardirqs_off();
+	trace_hardirqs_off_finish();
 	instrumentation_end();
 
 	return ret;

kernel/events/core.c

@@ -2312,9 +2312,6 @@ group_sched_out(struct perf_event *group_event,
 		event_sched_out(event, cpuctx, ctx);
 
 	perf_pmu_enable(ctx->pmu);
-
-	if (group_event->attr.exclusive)
-		cpuctx->exclusive = 0;
 }
 
 #define DETACH_GROUP	0x01UL
@@ -2583,11 +2580,8 @@ group_sched_in(struct perf_event *group_event,
 
 	pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
 
-	if (event_sched_in(group_event, cpuctx, ctx)) {
-		pmu->cancel_txn(pmu);
-		perf_mux_hrtimer_restart(cpuctx);
-		return -EAGAIN;
-	}
+	if (event_sched_in(group_event, cpuctx, ctx))
+		goto error;
 
 	/*
 	 * Schedule in siblings as one group (if any):
@@ -2616,10 +2610,8 @@ group_error:
 	}
 	event_sched_out(group_event, cpuctx, ctx);
 
+error:
 	pmu->cancel_txn(pmu);
-
-	perf_mux_hrtimer_restart(cpuctx);
-
 	return -EAGAIN;
 }
 
@@ -2645,7 +2637,7 @@ static int group_can_go_on(struct perf_event *event,
 	 * If this group is exclusive and there are already
 	 * events on the CPU, it can't go on.
 	 */
-	if (event->attr.exclusive && cpuctx->active_oncpu)
+	if (event->attr.exclusive && !list_empty(get_event_list(event)))
 		return 0;
 	/*
 	 * Otherwise, try to add it if all previous groups were able
@@ -3679,6 +3671,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 
 		*can_add_hw = 0;
 		ctx->rotate_necessary = 1;
+		perf_mux_hrtimer_restart(cpuctx);
 	}
 
 	return 0;
@@ -6374,14 +6367,13 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs,
-				  struct pt_regs *regs_user_copy)
+				  struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
 	} else if (!(current->flags & PF_KTHREAD)) {
-		perf_get_regs_user(regs_user, regs, regs_user_copy);
+		perf_get_regs_user(regs_user, regs);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -7083,8 +7075,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs,
-				      &data->regs_user_copy);
+		perf_sample_regs_user(&data->regs_user, regs);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
@@ -7186,6 +7177,7 @@ __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
 		    int (*output_begin)(struct perf_output_handle *,
+					struct perf_sample_data *,
 					struct perf_event *,
 					unsigned int))
 {
@@ -7198,7 +7190,7 @@ __perf_event_output(struct perf_event *event,
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	err = output_begin(&handle, event, header.size);
+	err = output_begin(&handle, data, event, header.size);
 	if (err)
 		goto exit;
 
@@ -7264,7 +7256,7 @@ perf_event_read_event(struct perf_event *event,
 	int ret;
 
 	perf_event_header__init_id(&read_event.header, &sample, event);
-	ret = perf_output_begin(&handle, event, read_event.header.size);
+	ret = perf_output_begin(&handle, &sample, event, read_event.header.size);
 	if (ret)
 		return;
 
@@ -7533,7 +7525,7 @@ static void perf_event_task_output(struct perf_event *event,
 
 	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				task_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7636,7 +7628,7 @@ static void perf_event_comm_output(struct perf_event *event,
 		return;
 
 	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				comm_event->event_id.header.size);
 
 	if (ret)
@@ -7736,7 +7728,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 
 	perf_event_header__init_id(&namespaces_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7863,7 +7855,7 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&cgroup_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				cgroup_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7989,7 +7981,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				mmap_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -8299,7 +8291,7 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 	int ret;
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
@@ -8333,7 +8325,7 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost)
 
 	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				lost_samples_event.header.size);
 	if (ret)
 		return;
@@ -8388,7 +8380,7 @@ static void perf_event_switch_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&se->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, se->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8463,7 +8455,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 
 	perf_event_header__init_id(&throttle_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				throttle_event.header.size);
 	if (ret)
 		return;
@@ -8506,7 +8498,7 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&ksymbol_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				ksymbol_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8596,7 +8588,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&bpf_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, data, event,
 				bpf_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8705,7 +8697,8 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event,
+				text_poke_event->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8786,7 +8779,7 @@ static void perf_log_itrace_start(struct perf_event *event)
 	rec.tid	= perf_event_tid(event, current);
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
@@ -10085,6 +10078,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 			if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
 				int fpos = token == IF_SRC_FILE ? 2 : 1;
 
+				kfree(filename);
 				filename = match_strdup(&args[fpos]);
 				if (!filename) {
 					ret = -ENOMEM;
@@ -10131,16 +10125,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 				 */
 				ret = -EOPNOTSUPP;
 				if (!event->ctx->task)
-					goto fail_free_name;
+					goto fail;
 
 				/* look up the path and grab its inode */
 				ret = kern_path(filename, LOOKUP_FOLLOW,
 						&filter->path);
 				if (ret)
-					goto fail_free_name;
-
-				kfree(filename);
-				filename = NULL;
+					goto fail;
 
 				ret = -EINVAL;
 				if (!filter->path.dentry ||
@@ -10160,13 +10151,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 	if (state != IF_STATE_ACTION)
 		goto fail;
 
+	kfree(filename);
 	kfree(orig);
 
 	return 0;
 
-fail_free_name:
-	kfree(filename);
 fail:
+	kfree(filename);
 	free_filters_list(filters);
 	kfree(orig);
 

kernel/events/internal.h

@@ -205,16 +205,12 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
 static inline int get_recursion_context(int *recursion)
 {
-	int rctx;
+	unsigned int pc = preempt_count();
+	unsigned char rctx = 0;
 
-	if (unlikely(in_nmi()))
-		rctx = 3;
-	else if (in_irq())
-		rctx = 2;
-	else if (in_softirq())
-		rctx = 1;
-	else
-		rctx = 0;
+	rctx += !!(pc & (NMI_MASK));
+	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
 
 	if (recursion[rctx])
 		return -1;

kernel/events/ring_buffer.c

@@ -147,6 +147,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail,
 
 static __always_inline int
 __perf_output_begin(struct perf_output_handle *handle,
+		    struct perf_sample_data *data,
 		    struct perf_event *event, unsigned int size,
 		    bool backward)
 {
@@ -237,18 +238,16 @@ __perf_output_begin(struct perf_output_handle *handle,
 	handle->size = (1UL << page_shift) - offset;
 
 	if (unlikely(have_lost)) {
-		struct perf_sample_data sample_data;
-
 		lost_event.header.size = sizeof(lost_event);
 		lost_event.header.type = PERF_RECORD_LOST;
 		lost_event.header.misc = 0;
 		lost_event.id          = event->id;
 		lost_event.lost        = local_xchg(&rb->lost, 0);
 
-		perf_event_header__init_id(&lost_event.header,
-					   &sample_data, event);
+		/* XXX mostly redundant; @data is already fully initializes */
+		perf_event_header__init_id(&lost_event.header, data, event);
 		perf_output_put(handle, lost_event);
-		perf_event__output_id_sample(event, handle, &sample_data);
+		perf_event__output_id_sample(event, handle, data);
 	}
 
 	return 0;
@@ -263,22 +262,25 @@ out:
 }
 
 int perf_output_begin_forward(struct perf_output_handle *handle,
-			     struct perf_event *event, unsigned int size)
+			      struct perf_sample_data *data,
+			      struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, false);
+	return __perf_output_begin(handle, data, event, size, false);
 }
 
 int perf_output_begin_backward(struct perf_output_handle *handle,
+			       struct perf_sample_data *data,
 			       struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, true);
+	return __perf_output_begin(handle, data, event, size, true);
 }
 
 int perf_output_begin(struct perf_output_handle *handle,
+		      struct perf_sample_data *data,
 		      struct perf_event *event, unsigned int size)
 {
 
-	return __perf_output_begin(handle, event, size,
+	return __perf_output_begin(handle, data, event, size,
 				   unlikely(is_write_backward(event)));
 }
 

kernel/exit.c

@@ -454,7 +454,10 @@ static void exit_mm(void)
 		mmap_read_unlock(mm);
 
 		self.task = current;
-		self.next = xchg(&core_state->dumper.next, &self);
+		if (self.task->flags & PF_SIGNALED)
+			self.next = xchg(&core_state->dumper.next, &self);
+		else
+			self.task = NULL;
 		/*
 		 * Implies mb(), the result of xchg() must be visible
 		 * to core_state->dumper.

kernel/fail_function.c

@@ -253,7 +253,7 @@ static ssize_t fei_write(struct file *file, const char __user *buffer,
 
 	if (copy_from_user(buf, buffer, count)) {
 		ret = -EFAULT;
-		goto out;
+		goto out_free;
 	}
 	buf[count] = '\0';
 	sym = strstrip(buf);
@@ -307,8 +307,9 @@ static ssize_t fei_write(struct file *file, const char __user *buffer,
 		ret = count;
 	}
 out:
-	kfree(buf);
 	mutex_unlock(&fei_lock);
+out_free:
+	kfree(buf);
 	return ret;
 }
 

kernel/fork.c

@@ -2167,14 +2167,9 @@ static __latent_entropy struct task_struct *copy_process(
 	/* ok, now we should be set up.. */
 	p->pid = pid_nr(pid);
 	if (clone_flags & CLONE_THREAD) {
-		p->exit_signal = -1;
 		p->group_leader = current->group_leader;
 		p->tgid = current->tgid;
 	} else {
-		if (clone_flags & CLONE_PARENT)
-			p->exit_signal = current->group_leader->exit_signal;
-		else
-			p->exit_signal = args->exit_signal;
 		p->group_leader = p;
 		p->tgid = p->pid;
 	}
@@ -2218,9 +2213,14 @@ static __latent_entropy struct task_struct *copy_process(
 	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
 		p->parent_exec_id = current->parent_exec_id;
+		if (clone_flags & CLONE_THREAD)
+			p->exit_signal = -1;
+		else
+			p->exit_signal = current->group_leader->exit_signal;
 	} else {
 		p->real_parent = current;
 		p->parent_exec_id = current->self_exec_id;
+		p->exit_signal = args->exit_signal;
 	}
 
 	klp_copy_process(p);

kernel/futex.c

@@ -788,8 +788,9 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	 */
 	if (pi_state->owner) {
 		struct task_struct *owner;
+		unsigned long flags;
 
-		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
 		owner = pi_state->owner;
 		if (owner) {
 			raw_spin_lock(&owner->pi_lock);
@@ -797,7 +798,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 			raw_spin_unlock(&owner->pi_lock);
 		}
 		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
 	if (current->pi_state_cache) {
@@ -1503,8 +1504,10 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	 */
 	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-	if (unlikely(should_fail_futex(true)))
+	if (unlikely(should_fail_futex(true))) {
 		ret = -EFAULT;
+		goto out_unlock;
+	}
 
 	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
 	if (!ret && (curval != uval)) {
@@ -2378,10 +2381,22 @@ retry:
 		}
 
 		/*
-		 * Since we just failed the trylock; there must be an owner.
+		 * The trylock just failed, so either there is an owner or
+		 * there is a higher priority waiter than this one.
 		 */
 		newowner = rt_mutex_owner(&pi_state->pi_mutex);
-		BUG_ON(!newowner);
+		/*
+		 * If the higher priority waiter has not yet taken over the
+		 * rtmutex then newowner is NULL. We can't return here with
+		 * that state because it's inconsistent vs. the user space
+		 * state. So drop the locks and try again. It's a valid
+		 * situation and not any different from the other retry
+		 * conditions.
+		 */
+		if (unlikely(!newowner)) {
+			err = -EAGAIN;
+			goto handle_err;
+		}
 	} else {
 		WARN_ON_ONCE(argowner != current);
 		if (oldowner == current) {

kernel/hung_task.c

@@ -225,8 +225,7 @@ static long hung_timeout_jiffies(unsigned long last_checked,
  * Process updating of timeout sysctl
  */
 int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-				  void __user *buffer,
-				  size_t *lenp, loff_t *ppos)
+				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 

kernel/irq/Kconfig

@@ -82,6 +82,7 @@ config IRQ_FASTEOI_HIERARCHY_HANDLERS
 # Generic IRQ IPI support
 config GENERIC_IRQ_IPI
 	bool
+	select IRQ_DOMAIN_HIERARCHY
 
 # Generic MSI interrupt support
 config GENERIC_MSI_IRQ

kernel/kprobes.c

@@ -1249,7 +1249,13 @@ __acquires(hlist_lock)
 
 	*head = &kretprobe_inst_table[hash];
 	hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_lock_irqsave(hlist_lock, *flags);
+	/*
+	 * Nested is a workaround that will soon not be needed.
+	 * There's other protections that make sure the same lock
+	 * is not taken on the same CPU that lockdep is unaware of.
+	 * Differentiate when it is taken in NMI context.
+	 */
+	raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
 }
 NOKPROBE_SYMBOL(kretprobe_hash_lock);
 
@@ -1258,7 +1264,13 @@ static void kretprobe_table_lock(unsigned long hash,
 __acquires(hlist_lock)
 {
 	raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_lock_irqsave(hlist_lock, *flags);
+	/*
+	 * Nested is a workaround that will soon not be needed.
+	 * There's other protections that make sure the same lock
+	 * is not taken on the same CPU that lockdep is unaware of.
+	 * Differentiate when it is taken in NMI context.
+	 */
+	raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
 }
 NOKPROBE_SYMBOL(kretprobe_table_lock);
 
@@ -2028,7 +2040,12 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 
 	/* TODO: consider to only swap the RA after the last pre_handler fired */
 	hash = hash_ptr(current, KPROBE_HASH_BITS);
-	raw_spin_lock_irqsave(&rp->lock, flags);
+	/*
+	 * Nested is a workaround that will soon not be needed.
+	 * There's other protections that make sure the same lock
+	 * is not taken on the same CPU that lockdep is unaware of.
+	 */
+	raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
 	if (!hlist_empty(&rp->free_instances)) {
 		ri = hlist_entry(rp->free_instances.first,
 				struct kretprobe_instance, hlist);
@@ -2039,7 +2056,7 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 		ri->task = current;
 
 		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-			raw_spin_lock_irqsave(&rp->lock, flags);
+			raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
 			hlist_add_head(&ri->hlist, &rp->free_instances);
 			raw_spin_unlock_irqrestore(&rp->lock, flags);
 			return 0;

kernel/kthread.c

@@ -897,7 +897,8 @@ void kthread_delayed_work_timer_fn(struct timer_list *t)
 	/* Move the work from worker->delayed_work_list. */
 	WARN_ON_ONCE(list_empty(&work->node));
 	list_del_init(&work->node);
-	kthread_insert_work(worker, work, &worker->work_list);
+	if (!work->canceling)
+		kthread_insert_work(worker, work, &worker->work_list);
 
 	raw_spin_unlock_irqrestore(&worker->lock, flags);
 }

kernel/locking/lockdep.c

@@ -84,7 +84,7 @@ static inline bool lockdep_enabled(void)
 	if (!debug_locks)
 		return false;
 
-	if (raw_cpu_read(lockdep_recursion))
+	if (this_cpu_read(lockdep_recursion))
 		return false;
 
 	if (current->lockdep_recursion)
@@ -108,19 +108,21 @@ static inline void lockdep_lock(void)
 {
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
+	__this_cpu_inc(lockdep_recursion);
 	arch_spin_lock(&__lock);
 	__owner = current;
-	__this_cpu_inc(lockdep_recursion);
 }
 
 static inline void lockdep_unlock(void)
 {
+	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
 	if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
 		return;
 
-	__this_cpu_dec(lockdep_recursion);
 	__owner = NULL;
 	arch_spin_unlock(&__lock);
+	__this_cpu_dec(lockdep_recursion);
 }
 
 static inline bool lockdep_assert_locked(void)
@@ -2765,7 +2767,9 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
  * (Note that this has to be done separately, because the graph cannot
  * detect such classes of deadlocks.)
  *
- * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
+ * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same
+ * lock class is held but nest_lock is also held, i.e. we rely on the
+ * nest_lock to avoid the deadlock.
  */
 static int
 check_deadlock(struct task_struct *curr, struct held_lock *next)
@@ -2788,7 +2792,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next)
 		 * lock class (i.e. read_lock(lock)+read_lock(lock)):
 		 */
 		if ((next->read == 2) && prev->read)
-			return 2;
+			continue;
 
 		/*
 		 * We're holding the nest_lock, which serializes this lock's
@@ -3592,16 +3596,13 @@ static int validate_chain(struct task_struct *curr,
 
 		if (!ret)
 			return 0;
-		/*
-		 * Mark recursive read, as we jump over it when
-		 * building dependencies (just like we jump over
-		 * trylock entries):
-		 */
-		if (ret == 2)
-			hlock->read = 2;
 		/*
 		 * Add dependency only if this lock is not the head
-		 * of the chain, and if it's not a secondary read-lock:
+		 * of the chain, and if the new lock introduces no more
+		 * lock dependency (because we already hold a lock with the
+		 * same lock class) nor deadlock (because the nest_lock
+		 * serializes nesting locks), see the comments for
+		 * check_deadlock().
 		 */
 		if (!chain_head && ret != 2) {
 			if (!check_prevs_add(curr, hlock))
@@ -4057,7 +4058,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	if (unlikely(in_nmi()))
 		return;
 
-	if (unlikely(__this_cpu_read(lockdep_recursion)))
+	if (unlikely(this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (unlikely(lockdep_hardirqs_enabled())) {
@@ -4126,7 +4127,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 		goto skip_checks;
 	}
 
-	if (unlikely(__this_cpu_read(lockdep_recursion)))
+	if (unlikely(this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (lockdep_hardirqs_enabled()) {
@@ -4396,6 +4397,9 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	if (unlikely(hlock_class(this)->usage_mask & new_mask))
 		goto unlock;
 
+	if (!hlock_class(this)->usage_mask)
+		debug_atomic_dec(nr_unused_locks);
+
 	hlock_class(this)->usage_mask |= new_mask;
 
 	if (new_bit < LOCK_TRACE_STATES) {
@@ -4403,19 +4407,10 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 	}
 
-	switch (new_bit) {
-	case 0 ... LOCK_USED-1:
+	if (new_bit < LOCK_USED) {
 		ret = mark_lock_irq(curr, this, new_bit);
 		if (!ret)
 			return 0;
-		break;
-
-	case LOCK_USED:
-		debug_atomic_dec(nr_unused_locks);
-		break;
-
-	default:
-		break;
 	}
 
 unlock:

kernel/panic.c

@@ -605,7 +605,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 		panic("panic_on_warn set ...\n");
 	}
 
-	dump_stack();
+	if (!regs)
+		dump_stack();
 
 	print_irqtrace_events(current);
 

kernel/params.c

@@ -530,7 +530,7 @@ struct module_param_attrs
 {
 	unsigned int num;
 	struct attribute_group grp;
-	struct param_attribute attrs[0];
+	struct param_attribute attrs[];
 };
 
 #ifdef CONFIG_SYSFS

kernel/power/process.c

@@ -146,7 +146,7 @@ int freeze_processes(void)
 	BUG_ON(in_atomic());
 
 	/*
-	 * Now that the whole userspace is frozen we need to disbale
+	 * Now that the whole userspace is frozen we need to disable
 	 * the OOM killer to disallow any further interference with
 	 * killable tasks. There is no guarantee oom victims will
 	 * ever reach a point they go away we have to wait with a timeout.

kernel/printk/printk_ringbuffer.c

@@ -345,7 +345,7 @@ DESC_ID((id) - DESCS_COUNT(desc_ring))
  */
 struct prb_data_block {
 	unsigned long	id;
-	char		data[0];
+	char		data[];
 };
 
 /*

kernel/ptrace.c

@@ -264,17 +264,11 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	return ret;
 }
 
-static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
-			   unsigned int mode)
+static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 {
-	int ret;
-
 	if (mode & PTRACE_MODE_NOAUDIT)
-		ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
-	else
-		ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
-
-	return ret == 0;
+		return ns_capable_noaudit(ns, CAP_SYS_PTRACE);
+	return ns_capable(ns, CAP_SYS_PTRACE);
 }
 
 /* Returns 0 on success, -errno on denial. */
@@ -326,7 +320,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	    gid_eq(caller_gid, tcred->sgid) &&
 	    gid_eq(caller_gid, tcred->gid))
 		goto ok;
-	if (ptrace_has_cap(cred, tcred->user_ns, mode))
+	if (ptrace_has_cap(tcred->user_ns, mode))
 		goto ok;
 	rcu_read_unlock();
 	return -EPERM;
@@ -345,7 +339,7 @@ ok:
 	mm = task->mm;
 	if (mm &&
 	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
-	     !ptrace_has_cap(cred, mm->user_ns, mode)))
+	     !ptrace_has_cap(mm->user_ns, mode)))
 	    return -EPERM;
 
 	return security_ptrace_access_check(task, mode);

kernel/rcu/tree.c

@@ -409,7 +409,7 @@ bool rcu_eqs_special_set(int cpu)
  *
  * The caller must have disabled interrupts and must not be idle.
  */
-void rcu_momentary_dyntick_idle(void)
+notrace void rcu_momentary_dyntick_idle(void)
 {
 	int special;
 
@@ -4076,7 +4076,6 @@ void rcu_cpu_starting(unsigned int cpu)
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The outgoing function has no further need of RCU, so remove it from
  * the rcu_node tree's ->qsmaskinitnext bit masks.
@@ -4116,6 +4115,7 @@ void rcu_report_dead(unsigned int cpu)
 	rdp->cpu_started = false;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The outgoing CPU has just passed through the dying-idle state, and we
  * are being invoked from the CPU that was IPIed to continue the offline

kernel/rcu/tree_stall.h

@@ -249,13 +249,16 @@ static bool check_slow_task(struct task_struct *t, void *arg)
 
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
+ * sections, printing out the tid of each of the first few of them.
  */
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
+	int i = 0;
 	int ndetected = 0;
 	struct rcu_stall_chk_rdr rscr;
 	struct task_struct *t;
+	struct task_struct *ts[8];
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
@@ -264,6 +267,14 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		get_task_struct(t);
+		ts[i++] = t;
+		if (i >= ARRAY_SIZE(ts))
+			break;
+	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	for (i--; i; i--) {
+		t = ts[i];
 		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
 			pr_cont(" P%d", t->pid);
 		else
@@ -273,6 +284,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 				".q"[rscr.rs.b.need_qs],
 				".e"[rscr.rs.b.exp_hint],
 				".l"[rscr.on_blkd_list]);
+		put_task_struct(t);
 		ndetected++;
 	}
 	pr_cont("\n");
@@ -293,8 +305,9 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
  * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 {
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	return 0;
 }
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
@@ -472,7 +485,6 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
 	rcu_for_each_leaf_node(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		ndetected += rcu_print_task_stall(rnp);
 		if (rnp->qsmask != 0) {
 			for_each_leaf_node_possible_cpu(rnp, cpu)
 				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
@@ -480,7 +492,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 					ndetected++;
 				}
 		}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
 	}
 
 	for_each_possible_cpu(cpu)

kernel/reboot.c

@@ -551,22 +551,22 @@ static int __init reboot_setup(char *str)
 			break;
 
 		case 's':
-		{
-			int rc;
-
-			if (isdigit(*(str+1))) {
-				rc = kstrtoint(str+1, 0, &reboot_cpu);
-				if (rc)
-					return rc;
-			} else if (str[1] == 'm' && str[2] == 'p' &&
-				   isdigit(*(str+3))) {
-				rc = kstrtoint(str+3, 0, &reboot_cpu);
-				if (rc)
-					return rc;
-			} else
+			if (isdigit(*(str+1)))
+				reboot_cpu = simple_strtoul(str+1, NULL, 0);
+			else if (str[1] == 'm' && str[2] == 'p' &&
+							isdigit(*(str+3)))
+				reboot_cpu = simple_strtoul(str+3, NULL, 0);
+			else
 				*mode = REBOOT_SOFT;
+			if (reboot_cpu >= num_possible_cpus()) {
+				pr_err("Ignoring the CPU number in reboot= option. "
+				       "CPU %d exceeds possible cpu number %d\n",
+				       reboot_cpu, num_possible_cpus());
+				reboot_cpu = 0;
+				break;
+			}
 			break;
-		}
+
 		case 'g':
 			*mode = REBOOT_GPIO;
 			break;

kernel/sched/core.c

@@ -2976,7 +2976,12 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 #ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
+	else
 #endif
+	if (p->in_iowait) {
+		delayacct_blkio_end(p);
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
 
 	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
@@ -3363,11 +3368,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
 		goto unlock;
 
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
 #ifdef CONFIG_SMP
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
@@ -3438,6 +3438,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU);
 	if (task_cpu(p) != cpu) {
+		if (p->in_iowait) {
+			delayacct_blkio_end(p);
+			atomic_dec(&task_rq(p)->nr_iowait);
+		}
+
 		wake_flags |= WF_MIGRATED;
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
@@ -5432,20 +5437,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_prio(pi_task->prio) &&
 		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
-			p->dl.dl_boosted = 1;
+			p->dl.pi_se = pi_task->dl.pi_se;
 			queue_flag |= ENQUEUE_REPLENISH;
-		} else
-			p->dl.dl_boosted = 0;
+		} else {
+			p->dl.pi_se = &p->dl;
+		}
 		p->sched_class = &dl_sched_class;
 	} else if (rt_prio(prio)) {
 		if (dl_prio(oldprio))
-			p->dl.dl_boosted = 0;
+			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.dl_boosted = 0;
+			p->dl.pi_se = &p->dl;
 		if (rt_prio(oldprio))
 			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;

kernel/sched/cpufreq_schedutil.c

@@ -102,8 +102,12 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->next_freq == next_freq)
-		return false;
+	if (!sg_policy->need_freq_update) {
+		if (sg_policy->next_freq == next_freq)
+			return false;
+	} else {
+		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -164,7 +168,6 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
 		return sg_policy->next_freq;
 
-	sg_policy->need_freq_update = false;
 	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
@@ -440,7 +443,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long util, max;
 	unsigned int next_f;
-	bool busy;
 	unsigned int cached_freq = sg_policy->cached_raw_freq;
 
 	sugov_iowait_boost(sg_cpu, time, flags);
@@ -451,9 +453,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	/* Limits may have changed, don't skip frequency update */
-	busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
-
 	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
 	util = sugov_iowait_apply(sg_cpu, time, util, max);
@@ -462,7 +461,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
 	 */
-	if (busy && next_f < sg_policy->next_freq) {
+	if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */
@@ -827,9 +826,10 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
-	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
 
+	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
@@ -881,7 +881,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
-	.dynamic_switching	= true,
+	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
 	.init			= sugov_init,
 	.exit			= sugov_exit,
 	.start			= sugov_start,

kernel/sched/deadline.c

@@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
 }
 
+#ifdef CONFIG_RT_MUTEXES
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+	return dl_se->pi_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+	return pi_of(dl_se) != dl_se;
+}
+#else
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+	return dl_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -714,7 +736,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	WARN_ON(dl_se->dl_boosted);
+	WARN_ON(is_dl_boosted(dl_se));
 	WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
 
 	/*
@@ -752,21 +774,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
  * could happen are, typically, a entity voluntarily trying to overcome its
  * runtime, or it just underestimated it during sched_setattr().
  */
-static void replenish_dl_entity(struct sched_dl_entity *dl_se,
-				struct sched_dl_entity *pi_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	BUG_ON(pi_se->dl_runtime <= 0);
+	BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
 
 	/*
 	 * This could be the case for a !-dl task that is boosted.
 	 * Just go with full inherited parameters.
 	 */
 	if (dl_se->dl_deadline == 0) {
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 
 	if (dl_se->dl_yielded && dl_se->runtime > 0)
@@ -779,8 +800,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * arbitrary large.
 	 */
 	while (dl_se->runtime <= 0) {
-		dl_se->deadline += pi_se->dl_period;
-		dl_se->runtime += pi_se->dl_runtime;
+		dl_se->deadline += pi_of(dl_se)->dl_period;
+		dl_se->runtime += pi_of(dl_se)->dl_runtime;
 	}
 
 	/*
@@ -794,8 +815,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
 		printk_deferred_once("sched: DL replenish lagged too much\n");
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 
 	if (dl_se->dl_yielded)
@@ -828,8 +849,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  * task with deadline equal to period this is the same of using
  * dl_period instead of dl_deadline in the equation above.
  */
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
-			       struct sched_dl_entity *pi_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 {
 	u64 left, right;
 
@@ -851,9 +871,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
-		(pi_se->dl_runtime >> DL_SCALE);
+		(pi_of(dl_se)->dl_runtime >> DL_SCALE);
 
 	return dl_time_before(right, left);
 }
@@ -938,24 +958,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
  * Please refer to the comments update_dl_revised_wakeup() function to find
  * more about the Revised CBS rule.
  */
-static void update_dl_entity(struct sched_dl_entity *dl_se,
-			     struct sched_dl_entity *pi_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
-	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+	    dl_entity_overflow(dl_se, rq_clock(rq))) {
 
 		if (unlikely(!dl_is_implicit(dl_se) &&
 			     !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
-			     !dl_se->dl_boosted)){
+			     !is_dl_boosted(dl_se))) {
 			update_dl_revised_wakeup(dl_se, rq);
 			return;
 		}
 
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 }
 
@@ -1054,7 +1073,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * The task might have been boosted by someone else and might be in the
 	 * boosting/deboosting path, its not throttled.
 	 */
-	if (dl_se->dl_boosted)
+	if (is_dl_boosted(dl_se))
 		goto unlock;
 
 	/*
@@ -1082,7 +1101,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * but do not enqueue -- wait for our wakeup to do that.
 	 */
 	if (!task_on_rq_queued(p)) {
-		replenish_dl_entity(dl_se, dl_se);
+		replenish_dl_entity(dl_se);
 		goto unlock;
 	}
 
@@ -1172,7 +1191,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
 	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
-		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
 			return;
 		dl_se->dl_throttled = 1;
 		if (dl_se->runtime > 0)
@@ -1303,7 +1322,7 @@ throttle:
 			dl_se->dl_overrun = 1;
 
 		__dequeue_task_dl(rq, curr, 0);
-		if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
 		if (!is_leftmost(curr, &rq->dl))
@@ -1500,8 +1519,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
 }
 
 static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se,
-		  struct sched_dl_entity *pi_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
 	BUG_ON(on_dl_rq(dl_se));
 
@@ -1512,9 +1530,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	if (flags & ENQUEUE_WAKEUP) {
 		task_contending(dl_se, flags);
-		update_dl_entity(dl_se, pi_se);
+		update_dl_entity(dl_se);
 	} else if (flags & ENQUEUE_REPLENISH) {
-		replenish_dl_entity(dl_se, pi_se);
+		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
 		  dl_time_before(dl_se->deadline,
 				 rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
@@ -1531,19 +1549,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
-	struct task_struct *pi_task = rt_mutex_get_top_task(p);
-	struct sched_dl_entity *pi_se = &p->dl;
-
-	/*
-	 * Use the scheduling parameters of the top pi-waiter task if:
-	 * - we have a top pi-waiter which is a SCHED_DEADLINE task AND
-	 * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is
-	 *   smaller than our deadline OR we are a !SCHED_DEADLINE task getting
-	 *   boosted due to a SCHED_DEADLINE pi-waiter).
-	 * Otherwise we keep our runtime and deadline.
-	 */
-	if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) {
-		pi_se = &pi_task->dl;
+	if (is_dl_boosted(&p->dl)) {
 		/*
 		 * Because of delays in the detection of the overrun of a
 		 * thread's runtime, it might be the case that a thread
@@ -1576,7 +1582,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		 * the throttle.
 		 */
 		p->dl.dl_throttled = 0;
-		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+		BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
 		return;
 	}
 
@@ -1613,7 +1619,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		return;
 	}
 
-	enqueue_dl_entity(&p->dl, pi_se, flags);
+	enqueue_dl_entity(&p->dl, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
@@ -2832,11 +2838,14 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
-	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
+
+#ifdef CONFIG_RT_MUTEXES
+	dl_se->pi_se			= dl_se;
+#endif
 }
 
 bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)

kernel/sched/debug.c

@@ -251,7 +251,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write,
 	unsigned long flags = *(unsigned long *)table->data;
 	size_t data_size = 0;
 	size_t len = 0;
-	char *tmp;
+	char *tmp, *buf;
 	int idx;
 
 	if (write)
@@ -269,17 +269,17 @@ static int sd_ctl_doflags(struct ctl_table *table, int write,
 		return 0;
 	}
 
-	tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
+	buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL);
+	if (!buf)
 		return -ENOMEM;
 
 	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
 		char *name = sd_flag_debug[idx].name;
 
-		len += snprintf(tmp + len, strlen(name) + 2, "%s ", name);
+		len += snprintf(buf + len, strlen(name) + 2, "%s ", name);
 	}
 
-	tmp += *ppos;
+	tmp = buf + *ppos;
 	len -= *ppos;
 
 	if (len > *lenp)
@@ -294,7 +294,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write,
 	*lenp = len;
 	*ppos += len;
 
-	kfree(tmp);
+	kfree(buf);
 
 	return 0;
 }

kernel/sched/fair.c

@@ -5497,6 +5497,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	int task_new = !(flags & ENQUEUE_WAKEUP);
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -5569,7 +5570,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * into account, but that is not straightforward to implement,
 	 * and the following generally works well enough in practice.
 	 */
-	if (flags & ENQUEUE_WAKEUP)
+	if (!task_new)
 		update_overutilized_status(rq);
 
 enqueue_throttle:
@@ -6195,21 +6196,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 static int
 select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	unsigned long best_cap = 0;
+	unsigned long task_util, best_cap = 0;
 	int cpu, best_cpu = -1;
 	struct cpumask *cpus;
 
-	sync_entity_load_avg(&p->se);
-
 	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
+	task_util = uclamp_task_util(p);
+
 	for_each_cpu_wrap(cpu, cpus, target) {
 		unsigned long cpu_cap = capacity_of(cpu);
 
 		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
 			continue;
-		if (task_fits_capacity(p, cpu_cap))
+		if (fits_capacity(task_util, cpu_cap))
 			return cpu;
 
 		if (cpu_cap > best_cap) {
@@ -6221,44 +6222,42 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	return best_cpu;
 }
 
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		return fits_capacity(task_util, capacity_of(cpu));
+
+	return true;
+}
+
 /*
  * Try and locate an idle core/thread in the LLC cache domain.
  */
 static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	struct sched_domain *sd;
+	unsigned long task_util;
 	int i, recent_used_cpu;
 
 	/*
-	 * For asymmetric CPU capacity systems, our domain of interest is
-	 * sd_asym_cpucapacity rather than sd_llc.
+	 * On asymmetric system, update task utilization because we will check
+	 * that the task fits with cpu's capacity.
 	 */
 	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
-		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
-		/*
-		 * On an asymmetric CPU capacity system where an exclusive
-		 * cpuset defines a symmetric island (i.e. one unique
-		 * capacity_orig value through the cpuset), the key will be set
-		 * but the CPUs within that cpuset will not have a domain with
-		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
-		 * capacity path.
-		 */
-		if (!sd)
-			goto symmetric;
-
-		i = select_idle_capacity(p, sd, target);
-		return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		sync_entity_load_avg(&p->se);
+		task_util = uclamp_task_util(p);
 	}
 
-symmetric:
-	if (available_idle_cpu(target) || sched_idle_cpu(target))
+	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+	    asym_fits_capacity(task_util, target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
-	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+	    asym_fits_capacity(task_util, prev))
 		return prev;
 
 	/*
@@ -6281,7 +6280,8 @@ symmetric:
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    asym_fits_capacity(task_util, recent_used_cpu)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
 		 * candidate for the next wake:
@@ -6290,6 +6290,26 @@ symmetric:
 		return recent_used_cpu;
 	}
 
+	/*
+	 * For asymmetric CPU capacity systems, our domain of interest is
+	 * sd_asym_cpucapacity rather than sd_llc.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+		/*
+		 * On an asymmetric CPU capacity system where an exclusive
+		 * cpuset defines a symmetric island (i.e. one unique
+		 * capacity_orig value through the cpuset), the key will be set
+		 * but the CPUs within that cpuset will not have a domain with
+		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+		 * capacity path.
+		 */
+		if (sd) {
+			i = select_idle_capacity(p, sd, target);
+			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		}
+	}
+
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	if (!sd)
 		return target;
@@ -9070,7 +9090,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * emptying busiest.
 	 */
 	if (local->group_type == group_has_spare) {
-		if (busiest->group_type > group_fully_busy) {
+		if ((busiest->group_type > group_fully_busy) &&
+		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity

kernel/seccomp.c

@@ -38,7 +38,7 @@
 #include <linux/filter.h>
 #include <linux/pid.h>
 #include <linux/ptrace.h>
-#include <linux/security.h>
+#include <linux/capability.h>
 #include <linux/tracehook.h>
 #include <linux/uaccess.h>
 #include <linux/anon_inodes.h>
@@ -558,8 +558,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 	 * behavior of privileged children.
 	 */
 	if (!task_no_new_privs(current) &&
-	    security_capable(current_cred(), current_user_ns(),
-				     CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0)
+			!ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
 		return ERR_PTR(-EACCES);
 
 	/* Allocate a new seccomp_filter */

kernel/signal.c

@@ -391,16 +391,17 @@ static bool task_participate_group_stop(struct task_struct *task)
 
 void task_join_group_stop(struct task_struct *task)
 {
+	unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK;
+	struct signal_struct *sig = current->signal;
+
+	if (sig->group_stop_count) {
+		sig->group_stop_count++;
+		mask |= JOBCTL_STOP_CONSUME;
+	} else if (!(sig->flags & SIGNAL_STOP_STOPPED))
+		return;
+
 	/* Have the new thread join an on-going signal group stop */
-	unsigned long jobctl = current->jobctl;
-	if (jobctl & JOBCTL_STOP_PENDING) {
-		struct signal_struct *sig = current->signal;
-		unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
-		unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
-		if (task_set_jobctl_pending(task, signr | gstop)) {
-			sig->group_stop_count++;
-		}
-	}
+	task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING);
 }
 
 /*

kernel/smp.c

@@ -130,7 +130,7 @@ static __always_inline int csd_lock_wait_getcpu(call_single_data_t *csd)
 
 	csd_type = CSD_TYPE(csd);
 	if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC)
-		return csd->dst; /* Other CSD_TYPE_ values might not have ->dst. */
+		return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */
 	return -1;
 }
 

kernel/stop_machine.c

@@ -194,7 +194,7 @@ static void ack_state(struct multi_stop_data *msdata)
 		set_state(msdata, msdata->state + 1);
 }
 
-void __weak stop_machine_yield(const struct cpumask *cpumask)
+notrace void __weak stop_machine_yield(const struct cpumask *cpumask)
 {
 	cpu_relax();
 }

kernel/time/hrtimer.c

@@ -425,11 +425,6 @@ static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
 	debug_object_deactivate(timer, &hrtimer_debug_descr);
 }
 
-static inline void debug_hrtimer_free(struct hrtimer *timer)
-{
-	debug_object_free(timer, &hrtimer_debug_descr);
-}
-
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode);
 

kernel/time/itimer.c

@@ -172,10 +172,6 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 	u64 oval, nval, ointerval, ninterval;
 	struct cpu_itimer *it = &tsk->signal->it[clock_id];
 
-	/*
-	 * Use the to_ktime conversion because that clamps the maximum
-	 * value to KTIME_MAX and avoid multiplication overflows.
-	 */
 	nval = timespec64_to_ns(&value->it_value);
 	ninterval = timespec64_to_ns(&value->it_interval);
 

kernel/time/sched_clock.c

@@ -68,13 +68,13 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
-struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
 {
 	*seq = raw_read_seqcount_latch(&cd.seq);
 	return cd.read_data + (*seq & 1);
 }
 
-int sched_clock_read_retry(unsigned int seq)
+notrace int sched_clock_read_retry(unsigned int seq)
 {
 	return read_seqcount_latch_retry(&cd.seq, seq);
 }

kernel/time/timer.c

@@ -732,11 +732,6 @@ static inline void debug_timer_deactivate(struct timer_list *timer)
 	debug_object_deactivate(timer, &timer_debug_descr);
 }
 
-static inline void debug_timer_free(struct timer_list *timer)
-{
-	debug_object_free(timer, &timer_debug_descr);
-}
-
 static inline void debug_timer_assert_init(struct timer_list *timer)
 {
 	debug_object_assert_init(timer, &timer_debug_descr);

kernel/trace/bpf_trace.c

@@ -181,6 +181,16 @@ bpf_probe_read_user_str_common(void *dst, u32 size,
 {
 	int ret;
 
+	/*
+	 * NB: We rely on strncpy_from_user() not copying junk past the NUL
+	 * terminator into `dst`.
+	 *
+	 * strncpy_from_user() does long-sized strides in the fast path. If the
+	 * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`,
+	 * then there could be junk after the NUL in `dst`. If user takes `dst`
+	 * and keys a hash map with it, then semantically identical strings can
+	 * occupy multiple entries in the map.
+	 */
 	ret = strncpy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
@@ -1198,7 +1208,7 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
 	*btf = bpf_get_btf_vmlinux();
 
 	if (IS_ERR_OR_NULL(*btf))
-		return PTR_ERR(*btf);
+		return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL;
 
 	if (ptr->type_id > 0)
 		*btf_id = ptr->type_id;

kernel/trace/ring_buffer.c

@@ -438,14 +438,16 @@ enum {
 };
 /*
  * Used for which event context the event is in.
- *  NMI     = 0
- *  IRQ     = 1
- *  SOFTIRQ = 2
- *  NORMAL  = 3
+ *  TRANSITION = 0
+ *  NMI     = 1
+ *  IRQ     = 2
+ *  SOFTIRQ = 3
+ *  NORMAL  = 4
  *
  * See trace_recursive_lock() comment below for more details.
  */
 enum {
+	RB_CTX_TRANSITION,
 	RB_CTX_NMI,
 	RB_CTX_IRQ,
 	RB_CTX_SOFTIRQ,
@@ -3014,10 +3016,10 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * a bit of overhead in something as critical as function tracing,
  * we use a bitmask trick.
  *
- *  bit 0 =  NMI context
- *  bit 1 =  IRQ context
- *  bit 2 =  SoftIRQ context
- *  bit 3 =  normal context.
+ *  bit 1 =  NMI context
+ *  bit 2 =  IRQ context
+ *  bit 3 =  SoftIRQ context
+ *  bit 4 =  normal context.
  *
  * This works because this is the order of contexts that can
  * preempt other contexts. A SoftIRQ never preempts an IRQ
@@ -3040,6 +3042,30 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * The least significant bit can be cleared this way, and it
  * just so happens that it is the same bit corresponding to
  * the current context.
+ *
+ * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit
+ * is set when a recursion is detected at the current context, and if
+ * the TRANSITION bit is already set, it will fail the recursion.
+ * This is needed because there's a lag between the changing of
+ * interrupt context and updating the preempt count. In this case,
+ * a false positive will be found. To handle this, one extra recursion
+ * is allowed, and this is done by the TRANSITION bit. If the TRANSITION
+ * bit is already set, then it is considered a recursion and the function
+ * ends. Otherwise, the TRANSITION bit is set, and that bit is returned.
+ *
+ * On the trace_recursive_unlock(), the TRANSITION bit will be the first
+ * to be cleared. Even if it wasn't the context that set it. That is,
+ * if an interrupt comes in while NORMAL bit is set and the ring buffer
+ * is called before preempt_count() is updated, since the check will
+ * be on the NORMAL bit, the TRANSITION bit will then be set. If an
+ * NMI then comes in, it will set the NMI bit, but when the NMI code
+ * does the trace_recursive_unlock() it will clear the TRANSTION bit
+ * and leave the NMI bit set. But this is fine, because the interrupt
+ * code that set the TRANSITION bit will then clear the NMI bit when it
+ * calls trace_recursive_unlock(). If another NMI comes in, it will
+ * set the TRANSITION bit and continue.
+ *
+ * Note: The TRANSITION bit only handles a single transition between context.
  */
 
 static __always_inline int
@@ -3055,8 +3081,16 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 		bit = pc & NMI_MASK ? RB_CTX_NMI :
 			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
 
-	if (unlikely(val & (1 << (bit + cpu_buffer->nest))))
-		return 1;
+	if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) {
+		/*
+		 * It is possible that this was called by transitioning
+		 * between interrupt context, and preempt_count() has not
+		 * been updated yet. In this case, use the TRANSITION bit.
+		 */
+		bit = RB_CTX_TRANSITION;
+		if (val & (1 << (bit + cpu_buffer->nest)))
+			return 1;
+	}
 
 	val |= (1 << (bit + cpu_buffer->nest));
 	cpu_buffer->current_context = val;
@@ -3071,8 +3105,8 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
 		cpu_buffer->current_context - (1 << cpu_buffer->nest);
 }
 
-/* The recursive locking above uses 4 bits */
-#define NESTED_BITS 4
+/* The recursive locking above uses 5 bits */
+#define NESTED_BITS 5
 
 /**
  * ring_buffer_nest_start - Allow to trace while nested

kernel/trace/trace.c

@@ -2750,7 +2750,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 	/*
 	 * If tracing is off, but we have triggers enabled
 	 * we still need to look at the event data. Use the temp_buffer
-	 * to store the trace event for the tigger to use. It's recusive
+	 * to store the trace event for the trigger to use. It's recursive
 	 * safe and will not be recorded anywhere.
 	 */
 	if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) {
@@ -2952,7 +2952,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
 
 	/* This should never happen. If it does, yell once and skip */
-	if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+	if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING))
 		goto out;
 
 	/*
@@ -3132,7 +3132,7 @@ static char *get_trace_buf(void)
 
 	/* Interrupts must see nesting incremented before we use the buffer */
 	barrier();
-	return &buffer->buffer[buffer->nesting][0];
+	return &buffer->buffer[buffer->nesting - 1][0];
 }
 
 static void put_trace_buf(void)

kernel/trace/trace.h

@@ -637,6 +637,12 @@ enum {
 	 * function is called to clear it.
 	 */
 	TRACE_GRAPH_NOTRACE_BIT,
+
+	/*
+	 * When transitioning between context, the preempt_count() may
+	 * not be correct. Allow for a single recursion to cover this case.
+	 */
+	TRACE_TRANSITION_BIT,
 };
 
 #define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
@@ -691,14 +697,27 @@ static __always_inline int trace_test_and_set_recursion(int start, int max)
 		return 0;
 
 	bit = trace_get_context_bit() + start;
-	if (unlikely(val & (1 << bit)))
-		return -1;
+	if (unlikely(val & (1 << bit))) {
+		/*
+		 * It could be that preempt_count has not been updated during
+		 * a switch between contexts. Allow for a single recursion.
+		 */
+		bit = TRACE_TRANSITION_BIT;
+		if (trace_recursion_test(bit))
+			return -1;
+		trace_recursion_set(bit);
+		barrier();
+		return bit + 1;
+	}
+
+	/* Normal check passed, clear the transition to allow it again */
+	trace_recursion_clear(TRACE_TRANSITION_BIT);
 
 	val |= 1 << bit;
 	current->trace_recursion = val;
 	barrier();
 
-	return bit;
+	return bit + 1;
 }
 
 static __always_inline void trace_clear_recursion(int bit)
@@ -708,6 +727,7 @@ static __always_inline void trace_clear_recursion(int bit)
 	if (!bit)
 		return;
 
+	bit--;
 	bit = 1 << bit;
 	val &= ~bit;
 

kernel/trace/trace_events_synth.c

@@ -584,7 +584,7 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
 {
 	struct synth_field *field;
 	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
-	int len, ret = 0;
+	int len, ret = -ENOMEM;
 	struct seq_buf s;
 	ssize_t size;
 
@@ -617,10 +617,9 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
 		len--;
 
 	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
-	if (!field->name) {
-		ret = -ENOMEM;
+	if (!field->name)
 		goto free;
-	}
+
 	if (!is_good_name(field->name)) {
 		synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name));
 		ret = -EINVAL;
@@ -638,10 +637,9 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
 		len += strlen(prefix);
 
 	field->type = kzalloc(len, GFP_KERNEL);
-	if (!field->type) {
-		ret = -ENOMEM;
+	if (!field->type)
 		goto free;
-	}
+
 	seq_buf_init(&s, field->type, len);
 	if (prefix)
 		seq_buf_puts(&s, prefix);
@@ -653,6 +651,7 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
 	}
 	if (WARN_ON_ONCE(!seq_buf_buffer_left(&s)))
 		goto free;
+
 	s.buffer[s.len] = '\0';
 
 	size = synth_field_size(field->type);
@@ -666,10 +665,8 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
 
 			len = sizeof("__data_loc ") + strlen(field->type) + 1;
 			type = kzalloc(len, GFP_KERNEL);
-			if (!type) {
-				ret = -ENOMEM;
+			if (!type)
 				goto free;
-			}
 
 			seq_buf_init(&s, type, len);
 			seq_buf_puts(&s, "__data_loc ");

kernel/trace/trace_selftest.c

@@ -492,8 +492,13 @@ trace_selftest_function_recursion(void)
 	unregister_ftrace_function(&test_rec_probe);
 
 	ret = -1;
-	if (trace_selftest_recursion_cnt != 1) {
-		pr_cont("*callback not called once (%d)* ",
+	/*
+	 * Recursion allows for transitions between context,
+	 * and may call the callback twice.
+	 */
+	if (trace_selftest_recursion_cnt != 1 &&
+	    trace_selftest_recursion_cnt != 2) {
+		pr_cont("*callback not called once (or twice) (%d)* ",
 			trace_selftest_recursion_cnt);
 		goto out;
 	}

kernel/tracepoint.c

@@ -50,7 +50,7 @@ static bool ok_to_free_tracepoints;
  */
 struct tp_probes {
 	struct rcu_head rcu;
-	struct tracepoint_func probes[0];
+	struct tracepoint_func probes[];
 };
 
 static inline void *allocate_probes(int count)

kernel/watchdog.c

@@ -44,8 +44,6 @@ int __read_mostly soft_watchdog_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
 static int __read_mostly nmi_watchdog_available;
 
-static struct cpumask watchdog_allowed_mask __read_mostly;
-
 struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
@@ -162,6 +160,8 @@ static void lockup_detector_update_enable(void)
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 #endif
 
+static struct cpumask watchdog_allowed_mask __read_mostly;
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;