Merge branch 'linus' into perf/urgent, to synchronize with upstream

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

73 files changed, 4294 insertions, 1649 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index e0852dc333ac..3de8fd11873b 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -101,7 +101,7 @@ config UNINLINE_SPIN_UNLOCK
 # unlock and unlock_irq functions are inlined when:
 #   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
 #  or
-#   - DEBUG_SPINLOCK=n and PREEMPT=n
+#   - DEBUG_SPINLOCK=n and PREEMPTION=n
 #
 # unlock_bh and unlock_irqrestore functions are inlined when:
 #   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
@@ -139,7 +139,7 @@ config INLINE_SPIN_UNLOCK_BH
 
 config INLINE_SPIN_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_SPIN_UNLOCK_IRQ
 
 config INLINE_SPIN_UNLOCK_IRQRESTORE
 	def_bool y
@@ -168,7 +168,7 @@ config INLINE_READ_LOCK_IRQSAVE
 
 config INLINE_READ_UNLOCK
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK
+	depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK
 
 config INLINE_READ_UNLOCK_BH
 	def_bool y
@@ -176,7 +176,7 @@ config INLINE_READ_UNLOCK_BH
 
 config INLINE_READ_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK_IRQ
 
 config INLINE_READ_UNLOCK_IRQRESTORE
 	def_bool y
@@ -205,7 +205,7 @@ config INLINE_WRITE_LOCK_IRQSAVE
 
 config INLINE_WRITE_UNLOCK
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK
+	depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK
 
 config INLINE_WRITE_UNLOCK_BH
 	def_bool y
@@ -213,7 +213,7 @@ config INLINE_WRITE_UNLOCK_BH
 
 config INLINE_WRITE_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK_IRQ
 
 config INLINE_WRITE_UNLOCK_IRQRESTORE
 	def_bool y
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 3f671bf617e8..046ce5d98033 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
+obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
@@ -26,3 +27,6 @@ endif
 ifeq ($(CONFIG_SYSFS),y)
 obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
 endif
+ifeq ($(CONFIG_BPF_JIT),y)
+obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
+endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index f0d19bbb9211..95d77770353c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -503,6 +503,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_mmap = array_map_mmap,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
+	.map_lookup_batch = generic_map_lookup_batch,
+	.map_update_batch = generic_map_update_batch,
 };
 
 const struct bpf_map_ops percpu_array_map_ops = {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
new file mode 100644
index 000000000000..8ad1c9ea26b2
--- /dev/null
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -0,0 +1,634 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <linux/slab.h>
+#include <linux/numa.h>
+#include <linux/seq_file.h>
+#include <linux/refcount.h>
+#include <linux/mutex.h>
+
+enum bpf_struct_ops_state {
+	BPF_STRUCT_OPS_STATE_INIT,
+	BPF_STRUCT_OPS_STATE_INUSE,
+	BPF_STRUCT_OPS_STATE_TOBEFREE,
+};
+
+#define BPF_STRUCT_OPS_COMMON_VALUE			\
+	refcount_t refcnt;				\
+	enum bpf_struct_ops_state state
+
+struct bpf_struct_ops_value {
+	BPF_STRUCT_OPS_COMMON_VALUE;
+	char data[0] ____cacheline_aligned_in_smp;
+};
+
+struct bpf_struct_ops_map {
+	struct bpf_map map;
+	const struct bpf_struct_ops *st_ops;
+	/* protect map_update */
+	struct mutex lock;
+	/* progs has all the bpf_prog that is populated
+	 * to the func ptr of the kernel's struct
+	 * (in kvalue.data).
+	 */
+	struct bpf_prog **progs;
+	/* image is a page that has all the trampolines
+	 * that stores the func args before calling the bpf_prog.
+	 * A PAGE_SIZE "image" is enough to store all trampoline for
+	 * "progs[]".
+	 */
+	void *image;
+	/* uvalue->data stores the kernel struct
+	 * (e.g. tcp_congestion_ops) that is more useful
+	 * to userspace than the kvalue.  For example,
+	 * the bpf_prog's id is stored instead of the kernel
+	 * address of a func ptr.
+	 */
+	struct bpf_struct_ops_value *uvalue;
+	/* kvalue.data stores the actual kernel's struct
+	 * (e.g. tcp_congestion_ops) that will be
+	 * registered to the kernel subsystem.
+	 */
+	struct bpf_struct_ops_value kvalue;
+};
+
+#define VALUE_PREFIX "bpf_struct_ops_"
+#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1)
+
+/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is
+ * the map's value exposed to the userspace and its btf-type-id is
+ * stored at the map->btf_vmlinux_value_type_id.
+ *
+ */
+#define BPF_STRUCT_OPS_TYPE(_name)				\
+extern struct bpf_struct_ops bpf_##_name;			\
+								\
+struct bpf_struct_ops_##_name {						\
+	BPF_STRUCT_OPS_COMMON_VALUE;				\
+	struct _name data ____cacheline_aligned_in_smp;		\
+};
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+
+enum {
+#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name,
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+	__NR_BPF_STRUCT_OPS_TYPE,
+};
+
+static struct bpf_struct_ops * const bpf_struct_ops[] = {
+#define BPF_STRUCT_OPS_TYPE(_name)				\
+	[BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name,
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+};
+
+const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = {
+};
+
+const struct bpf_prog_ops bpf_struct_ops_prog_ops = {
+};
+
+static const struct btf_type *module_type;
+
+void bpf_struct_ops_init(struct btf *btf)
+{
+	s32 type_id, value_id, module_id;
+	const struct btf_member *member;
+	struct bpf_struct_ops *st_ops;
+	struct bpf_verifier_log log = {};
+	const struct btf_type *t;
+	char value_name[128];
+	const char *mname;
+	u32 i, j;
+
+	/* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */
+#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name);
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+
+	module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT);
+	if (module_id < 0) {
+		pr_warn("Cannot find struct module in btf_vmlinux\n");
+		return;
+	}
+	module_type = btf_type_by_id(btf, module_id);
+
+	for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+		st_ops = bpf_struct_ops[i];
+
+		if (strlen(st_ops->name) + VALUE_PREFIX_LEN >=
+		    sizeof(value_name)) {
+			pr_warn("struct_ops name %s is too long\n",
+				st_ops->name);
+			continue;
+		}
+		sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name);
+
+		value_id = btf_find_by_name_kind(btf, value_name,
+						 BTF_KIND_STRUCT);
+		if (value_id < 0) {
+			pr_warn("Cannot find struct %s in btf_vmlinux\n",
+				value_name);
+			continue;
+		}
+
+		type_id = btf_find_by_name_kind(btf, st_ops->name,
+						BTF_KIND_STRUCT);
+		if (type_id < 0) {
+			pr_warn("Cannot find struct %s in btf_vmlinux\n",
+				st_ops->name);
+			continue;
+		}
+		t = btf_type_by_id(btf, type_id);
+		if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) {
+			pr_warn("Cannot support #%u members in struct %s\n",
+				btf_type_vlen(t), st_ops->name);
+			continue;
+		}
+
+		for_each_member(j, t, member) {
+			const struct btf_type *func_proto;
+
+			mname = btf_name_by_offset(btf, member->name_off);
+			if (!*mname) {
+				pr_warn("anon member in struct %s is not supported\n",
+					st_ops->name);
+				break;
+			}
+
+			if (btf_member_bitfield_size(t, member)) {
+				pr_warn("bit field member %s in struct %s is not supported\n",
+					mname, st_ops->name);
+				break;
+			}
+
+			func_proto = btf_type_resolve_func_ptr(btf,
+							       member->type,
+							       NULL);
+			if (func_proto &&
+			    btf_distill_func_proto(&log, btf,
+						   func_proto, mname,
+						   &st_ops->func_models[j])) {
+				pr_warn("Error in parsing func ptr %s in struct %s\n",
+					mname, st_ops->name);
+				break;
+			}
+		}
+
+		if (j == btf_type_vlen(t)) {
+			if (st_ops->init(btf)) {
+				pr_warn("Error in init bpf_struct_ops %s\n",
+					st_ops->name);
+			} else {
+				st_ops->type_id = type_id;
+				st_ops->type = t;
+				st_ops->value_id = value_id;
+				st_ops->value_type = btf_type_by_id(btf,
+								    value_id);
+			}
+		}
+	}
+}
+
+extern struct btf *btf_vmlinux;
+
+static const struct bpf_struct_ops *
+bpf_struct_ops_find_value(u32 value_id)
+{
+	unsigned int i;
+
+	if (!value_id || !btf_vmlinux)
+		return NULL;
+
+	for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+		if (bpf_struct_ops[i]->value_id == value_id)
+			return bpf_struct_ops[i];
+	}
+
+	return NULL;
+}
+
+const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
+{
+	unsigned int i;
+
+	if (!type_id || !btf_vmlinux)
+		return NULL;
+
+	for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+		if (bpf_struct_ops[i]->type_id == type_id)
+			return bpf_struct_ops[i];
+	}
+
+	return NULL;
+}
+
+static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key,
+					   void *next_key)
+{
+	if (key && *(u32 *)key == 0)
+		return -ENOENT;
+
+	*(u32 *)next_key = 0;
+	return 0;
+}
+
+int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
+				       void *value)
+{
+	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+	struct bpf_struct_ops_value *uvalue, *kvalue;
+	enum bpf_struct_ops_state state;
+
+	if (unlikely(*(u32 *)key != 0))
+		return -ENOENT;
+
+	kvalue = &st_map->kvalue;
+	/* Pair with smp_store_release() during map_update */
+	state = smp_load_acquire(&kvalue->state);
+	if (state == BPF_STRUCT_OPS_STATE_INIT) {
+		memset(value, 0, map->value_size);
+		return 0;
+	}
+
+	/* No lock is needed.  state and refcnt do not need
+	 * to be updated together under atomic context.
+	 */
+	uvalue = (struct bpf_struct_ops_value *)value;
+	memcpy(uvalue, st_map->uvalue, map->value_size);
+	uvalue->state = state;
+	refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt));
+
+	return 0;
+}
+
+static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map)
+{
+	const struct btf_type *t = st_map->st_ops->type;
+	u32 i;
+
+	for (i = 0; i < btf_type_vlen(t); i++) {
+		if (st_map->progs[i]) {
+			bpf_prog_put(st_map->progs[i]);
+			st_map->progs[i] = NULL;
+		}
+	}
+}
+
+static int check_zero_holes(const struct btf_type *t, void *data)
+{
+	const struct btf_member *member;
+	u32 i, moff, msize, prev_mend = 0;
+	const struct btf_type *mtype;
+
+	for_each_member(i, t, member) {
+		moff = btf_member_bit_offset(t, member) / 8;
+		if (moff > prev_mend &&
+		    memchr_inv(data + prev_mend, 0, moff - prev_mend))
+			return -EINVAL;
+
+		mtype = btf_type_by_id(btf_vmlinux, member->type);
+		mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
+					 NULL, NULL);
+		if (IS_ERR(mtype))
+			return PTR_ERR(mtype);
+		prev_mend = moff + msize;
+	}
+
+	if (t->size > prev_mend &&
+	    memchr_inv(data + prev_mend, 0, t->size - prev_mend))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
+					  void *value, u64 flags)
+{
+	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+	const struct bpf_struct_ops *st_ops = st_map->st_ops;
+	struct bpf_struct_ops_value *uvalue, *kvalue;
+	const struct btf_member *member;
+	const struct btf_type *t = st_ops->type;
+	void *udata, *kdata;
+	int prog_fd, err = 0;
+	void *image;
+	u32 i;
+
+	if (flags)
+		return -EINVAL;
+
+	if (*(u32 *)key != 0)
+		return -E2BIG;
+
+	err = check_zero_holes(st_ops->value_type, value);
+	if (err)
+		return err;
+
+	uvalue = (struct bpf_struct_ops_value *)value;
+	err = check_zero_holes(t, uvalue->data);
+	if (err)
+		return err;
+
+	if (uvalue->state || refcount_read(&uvalue->refcnt))
+		return -EINVAL;
+
+	uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
+	kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue;
+
+	mutex_lock(&st_map->lock);
+
+	if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	memcpy(uvalue, value, map->value_size);
+
+	udata = &uvalue->data;
+	kdata = &kvalue->data;
+	image = st_map->image;
+
+	for_each_member(i, t, member) {
+		const struct btf_type *mtype, *ptype;
+		struct bpf_prog *prog;
+		u32 moff;
+
+		moff = btf_member_bit_offset(t, member) / 8;
+		ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
+		if (ptype == module_type) {
+			if (*(void **)(udata + moff))
+				goto reset_unlock;
+			*(void **)(kdata + moff) = BPF_MODULE_OWNER;
+			continue;
+		}
+
+		err = st_ops->init_member(t, member, kdata, udata);
+		if (err < 0)
+			goto reset_unlock;
+
+		/* The ->init_member() has handled this member */
+		if (err > 0)
+			continue;
+
+		/* If st_ops->init_member does not handle it,
+		 * we will only handle func ptrs and zero-ed members
+		 * here.  Reject everything else.
+		 */
+
+		/* All non func ptr member must be 0 */
+		if (!ptype || !btf_type_is_func_proto(ptype)) {
+			u32 msize;
+
+			mtype = btf_type_by_id(btf_vmlinux, member->type);
+			mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
+						 NULL, NULL);
+			if (IS_ERR(mtype)) {
+				err = PTR_ERR(mtype);
+				goto reset_unlock;
+			}
+
+			if (memchr_inv(udata + moff, 0, msize)) {
+				err = -EINVAL;
+				goto reset_unlock;
+			}
+
+			continue;
+		}
+
+		prog_fd = (int)(*(unsigned long *)(udata + moff));
+		/* Similar check as the attr->attach_prog_fd */
+		if (!prog_fd)
+			continue;
+
+		prog = bpf_prog_get(prog_fd);
+		if (IS_ERR(prog)) {
+			err = PTR_ERR(prog);
+			goto reset_unlock;
+		}
+		st_map->progs[i] = prog;
+
+		if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+		    prog->aux->attach_btf_id != st_ops->type_id ||
+		    prog->expected_attach_type != i) {
+			err = -EINVAL;
+			goto reset_unlock;
+		}
+
+		err = arch_prepare_bpf_trampoline(image,
+						  st_map->image + PAGE_SIZE,
+						  &st_ops->func_models[i], 0,
+						  &prog, 1, NULL, 0, NULL);
+		if (err < 0)
+			goto reset_unlock;
+
+		*(void **)(kdata + moff) = image;
+		image += err;
+
+		/* put prog_id to udata */
+		*(unsigned long *)(udata + moff) = prog->aux->id;
+	}
+
+	refcount_set(&kvalue->refcnt, 1);
+	bpf_map_inc(map);
+
+	set_memory_ro((long)st_map->image, 1);
+	set_memory_x((long)st_map->image, 1);
+	err = st_ops->reg(kdata);
+	if (likely(!err)) {
+		/* Pair with smp_load_acquire() during lookup_elem().
+		 * It ensures the above udata updates (e.g. prog->aux->id)
+		 * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set.
+		 */
+		smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE);
+		goto unlock;
+	}