Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-12-03

The main changes are:

1) Support BTF in kernel modules, from Andrii.

2) Introduce preferred busy-polling, from Björn.

3) bpf_ima_inode_hash() and bpf_bprm_opts_set() helpers, from KP Singh.

4) Memcg-based memory accounting for bpf objects, from Roman.

5) Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks, from Stanislav.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (118 commits)
  selftests/bpf: Fix invalid use of strncat in test_sockmap
  libbpf: Use memcpy instead of strncpy to please GCC
  selftests/bpf: Add fentry/fexit/fmod_ret selftest for kernel module
  selftests/bpf: Add tp_btf CO-RE reloc test for modules
  libbpf: Support attachment of BPF tracing programs to kernel modules
  libbpf: Factor out low-level BPF program loading helper
  bpf: Allow to specify kernel module BTFs when attaching BPF programs
  bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier
  selftests/bpf: Add CO-RE relocs selftest relying on kernel module BTF
  selftests/bpf: Add support for marking sub-tests as skipped
  selftests/bpf: Add bpf_testmod kernel module for testing
  libbpf: Add kernel module BTF support for CO-RE relocations
  libbpf: Refactor CO-RE relocs to not assume a single BTF object
  libbpf: Add internal helper to load BTF data by FD
  bpf: Keep module's btf_data_size intact after load
  bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address()
  selftests/bpf: Add Userspace tests for TCP_WINDOW_CLAMP
  bpf: Adds support for setting window clamp
  samples/bpf: Fix spelling mistake "recieving" -> "receiving"
  bpf: Fix cold build of test_progs-no_alu32
  ...
====================

Link: https://lore.kernel.org/r/20201204021936.85653-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

18 files changed, 399 insertions, 106 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index ed71bd1a0825..72e69a0e1e8c 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -246,11 +246,11 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 	__ret;								       \
 })
 
-#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND)
+#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL)
 
-#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND)
+#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL)
 
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \
 					    sk->sk_prot->pre_connect)
@@ -434,8 +434,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 581b2a2e78eb..d05e75ed8c1b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -20,6 +20,8 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/capability.h>
+#include <linux/sched/mm.h>
+#include <linux/slab.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -37,6 +39,7 @@ struct bpf_iter_aux_info;
 struct bpf_local_storage;
 struct bpf_local_storage_map;
 struct kobject;
+struct mem_cgroup;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -135,11 +138,6 @@ struct bpf_map_ops {
 	const struct bpf_iter_seq_info *iter_seq_info;
 };
 
-struct bpf_map_memory {
-	u32 pages;
-	struct user_struct *user;
-};
-
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -160,7 +158,9 @@ struct bpf_map {
 	u32 btf_key_type_id;
 	u32 btf_value_type_id;
 	struct btf *btf;
-	struct bpf_map_memory memory;
+#ifdef CONFIG_MEMCG_KMEM
+	struct mem_cgroup *memcg;
+#endif
 	char name[BPF_OBJ_NAME_LEN];
 	u32 btf_vmlinux_value_type_id;
 	bool bypass_spec_v1;
@@ -421,7 +421,10 @@ struct bpf_insn_access_aux {
 	enum bpf_reg_type reg_type;
 	union {
 		int ctx_field_size;
-		u32 btf_id;
+		struct {
+			struct btf *btf;
+			u32 btf_id;
+		};
 	};
 	struct bpf_verifier_log *log; /* for verbose logs */
 };
@@ -458,6 +461,7 @@ struct bpf_verifier_ops {
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog, u32 *target_size);
 	int (*btf_struct_access)(struct bpf_verifier_log *log,
+				 const struct btf *btf,
 				 const struct btf_type *t, int off, int size,
 				 enum bpf_access_type atype,
 				 u32 *next_btf_id);
@@ -771,6 +775,7 @@ struct bpf_prog_aux {
 	u32 ctx_arg_info_size;
 	u32 max_rdonly_access;
 	u32 max_rdwr_access;
+	struct btf *attach_btf;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
@@ -1005,7 +1010,6 @@ struct bpf_event_entry {
 
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
-const char *kernel_type_name(u32 btf_type_id);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
 
@@ -1202,8 +1206,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i);
 void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
-int __bpf_prog_charge(struct user_struct *user, u32 pages);
-void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
 void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len);
 
@@ -1218,12 +1220,6 @@ void bpf_map_inc_with_uref(struct bpf_map *map);
 struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
-void bpf_map_charge_finish(struct bpf_map_memory *mem);
-void bpf_map_charge_move(struct bpf_map_memory *dst,
-			 struct bpf_map_memory *src);
 void *bpf_map_area_alloc(u64 size, int numa_node);
 void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
@@ -1240,6 +1236,34 @@ int  generic_map_delete_batch(struct bpf_map *map,
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
+#ifdef CONFIG_MEMCG_KMEM
+void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
+			   int node);
+void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags);
+void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
+				    size_t align, gfp_t flags);
+#else
+static inline void *
+bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
+		     int node)
+{
+	return kmalloc_node(size, flags, node);
+}
+
+static inline void *
+bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
+{
+	return kzalloc(size, flags);
+}
+
+static inline void __percpu *
+bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
+		     gfp_t flags)
+{
+	return __alloc_percpu_gfp(size, align, flags);
+}
+#endif
+
 extern int sysctl_unprivileged_bpf_disabled;
 
 static inline bool bpf_allow_ptr_leaks(void)
@@ -1430,12 +1454,13 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
-int btf_struct_access(struct bpf_verifier_log *log,
+int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
-			  int off, u32 id, u32 need_type_id);
+			  const struct btf *btf, u32 id, int off,
+			  const struct btf *need_btf, u32 need_type_id);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
@@ -1490,15 +1515,6 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline int __bpf_prog_charge(struct user_struct *user, u32 pages)
-{
-	return 0;
-}
-
-static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
-{
-}
-
 static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 				 const struct bpf_link_ops *ops,
 				 struct bpf_prog *prog)
@@ -1842,6 +1858,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 306869d4743b..e941fe1484e5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -5,6 +5,7 @@
 #define _LINUX_BPF_VERIFIER_H 1
 
 #include <linux/bpf.h> /* for enum bpf_reg_type */
+#include <linux/btf.h> /* for struct btf and btf_id() */
 #include <linux/filter.h> /* for MAX_BPF_STACK */
 #include <linux/tnum.h>
 
@@ -43,6 +44,8 @@ enum bpf_reg_liveness {
 struct bpf_reg_state {
 	/* Ordering of fields matters.  See states_equal() */
 	enum bpf_reg_type type;
+	/* Fixed part of pointer offset, pointer types only */
+	s32 off;
 	union {
 		/* valid when type == PTR_TO_PACKET */
 		int range;
@@ -52,15 +55,20 @@ struct bpf_reg_state {
 		 */
 		struct bpf_map *map_ptr;
 
-		u32 btf_id; /* for PTR_TO_BTF_ID */
+		/* for PTR_TO_BTF_ID */
+		struct {
+			struct btf *btf;
+			u32 btf_id;
+		};
 
 		u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
 
 		/* Max size from any of the above. */
-		unsigned long raw;
+		struct {
+			unsigned long raw1;
+			unsigned long raw2;
+		} raw;
 	};
-	/* Fixed part of pointer offset, pointer types only */
-	s32 off;
 	/* For PTR_TO_PACKET, used to find other pointers with the same variable
 	 * offset, so they can share range knowledge.
 	 * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
@@ -311,7 +319,10 @@ struct bpf_insn_aux_data {
 		struct {
 			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
 			union {
-				u32 btf_id;	/* btf_id for struct typed var */
+				struct {
+					struct btf *btf;
+					u32 btf_id;	/* btf_id for struct typed var */
+				};
 				u32 mem_size;	/* mem_size for non-struct typed var */
 			};
 		} btf_var;
@@ -459,9 +470,12 @@ int check_ctx_reg(struct bpf_verifier_env *env,
 
 /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
 static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
-					     u32 btf_id)
+					     struct btf *btf, u32 btf_id)
 {
-        return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id;
+	if (tgt_prog)
+		return ((u64)tgt_prog->aux->id << 32) | btf_id;
+	else
+		return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id;
 }
 
 int bpf_check_attach_target(struct bpf_verifier_log *log,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 2bf641829664..4c200f5d242b 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -18,6 +18,7 @@ struct btf_show;
 
 extern const struct file_operations btf_fops;
 
+void btf_get(struct btf *btf);
 void btf_put(struct btf *btf);
 int btf_new_fd(const union bpf_attr *attr);
 struct btf *btf_get_by_fd(int fd);
@@ -88,7 +89,8 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
 			   char *buf, int len, u64 flags);
 
 int btf_get_fd_by_id(u32 id);
-u32 btf_id(const struct btf *btf);
+u32 btf_obj_id(const struct btf *btf);
+bool btf_is_kernel(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
@@ -206,6 +208,8 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo(
 }
 
 #ifdef CONFIG_BPF_SYSCALL
+struct bpf_prog;
+
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 8fa7bcfb2da2..7233a2751754 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -29,6 +29,7 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
 extern int ima_file_hash(struct file *file, char *buf, size_t buf_size);
+extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size);
 extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size);
 
 #ifdef CONFIG_IMA_KEXEC
@@ -115,6 +116,11 @@ static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size)
 	return -EOPNOTSUPP;
 }
 
+static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {}
 #endif /* CONFIG_IMA */
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 922a7f600465..320369c841f5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -343,6 +343,175 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+enum page_memcg_data_flags {
+	/* page->memcg_data is a pointer to an objcgs vector */
+	MEMCG_DATA_OBJCGS = (1UL << 0),
+	/* page has been accounted as a non-slab kernel page */
+	MEMCG_DATA_KMEM = (1UL << 1),
+	/* the next bit after the last actual flag */
+	__NR_MEMCG_DATA_FLAGS  = (1UL << 2),
+};
+
+#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
+
+/*
+ * page_memcg - get the memory cgroup associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the memory cgroup associated with the page,
+ * or NULL. This function assumes that the page is known to have a
+ * proper memory cgroup pointer. It's not safe to call this function
+ * against some type of pages, e.g. slab pages or ex-slab pages.
+ *
+ * Any of the following ensures page and memcg binding stability:
+ * - the page lock
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
+ */
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	unsigned long memcg_data = page->memcg_data;
+
+	VM_BUG_ON_PAGE(PageSlab(page), page);
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
+
+	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * page_memcg_rcu - locklessly get the memory cgroup associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the memory cgroup associated with the page,
+ * or NULL. This function assumes that the page is known to have a
+ * proper memory cgroup pointer. It's not safe to call this function
+ * against some type of pages, e.g. slab pages or ex-slab pages.
+ */
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	VM_BUG_ON_PAGE(PageSlab(page), page);
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	return (struct mem_cgroup *)(READ_ONCE(page->memcg_data) &
+				     ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * page_memcg_check - get the memory cgroup associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the memory cgroup associated with the page,
+ * or NULL. This function unlike page_memcg() can take any  page
+ * as an argument. It has to be used in cases when it's not known if a page
+ * has an associated memory cgroup pointer or an object cgroups vector.
+ *
+ * Any of the following ensures page and memcg binding stability:
+ * - the page lock
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
+ */
+static inline struct mem_cgroup *page_memcg_check(struct page *page)
+{
+	/*
+	 * Because page->memcg_data might be changed asynchronously
+	 * for slab pages, READ_ONCE() should be used here.
+	 */
+	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+	if (memcg_data & MEMCG_DATA_OBJCGS)
+		return NULL;
+
+	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * PageMemcgKmem - check if the page has MemcgKmem flag set
+ * @page: a pointer to the page struct
+ *
+ * Checks if the page has MemcgKmem flag set. The caller must ensure that
+ * the page has an associated memory cgroup. It's not safe to call this function
+ * against some types of pages, e.g. slab pages.
+ */
+static inline bool PageMemcgKmem(struct page *page)
+{
+	VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page);
+	return page->memcg_data & MEMCG_DATA_KMEM;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * page_objcgs - get the object cgroups vector associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the page,
+ * or NULL. This function assumes that the page is known to have an
+ * associated object cgroups vector. It's not safe to call this function
+ * against pages, which might have an associated memory cgroup: e.g.
+ * kernel stack pages.
+ */
+static inline struct obj_cgroup **page_objcgs(struct page *page)
+{
+	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
+
+	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * page_objcgs_check - get the object cgroups vector associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the page,
+ * or NULL. This function is safe to use if the page can be directly associated
+ * with a memory cgroup.
+ */
+static inline struct obj_cgroup **page_objcgs_check(struct page *page)
+{
+	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+	if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
+		return NULL;
+
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
+
+	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * set_page_objcgs - associate a page with a object cgroups vector
+ * @page: a pointer to the page struct
+ * @objcgs: a pointer to the object cgroups vector
+ *
+ * Atomically associates a page with a vector of object cgroups.
+ */
+static inline bool set_page_objcgs(struct page *page,
+					struct obj_cgroup **objcgs)
+{
+	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
+			MEMCG_DATA_OBJCGS);
+}
+#else
+static inline struct obj_cgroup **page_objcgs(struct page *page)
+{
+	return NULL;
+}
+
+static inline struct obj_cgroup **page_objcgs_check(struct page *page)
+{
+	return NULL;
+}
+
+static inline bool set_page_objcgs(struct page *page,
+					struct obj_cgroup **objcgs)
+{
+	return true;
+}
+#endif
+
 static __always_inline bool memcg_stat_item_in_bytes(int idx)
 {
 	if (idx == MEMCG_PERCPU_B)
@@ -743,15 +912,19 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 static inline void __mod_memcg_page_state(struct page *page,
 					  int idx, int val)
 {
-	if (page->mem_cgroup)
-		__mod_memcg_state(page->mem_cgroup, idx, val);
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	if (memcg)
+		__mod_memcg_state(memcg, idx, val);
 }
 
 static inline void mod_memcg_page_state(struct page *page,
 					int idx, int val)
 {
-	if (page->mem_cgroup)
-		mod_memcg_state(page->mem_cgroup, idx, val);
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	if (memcg)
+		mod_memcg_state(memcg, idx, val);
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
@@ -834,16 +1007,17 @@ static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
 	struct page *head = compound_head(page); /* rmap on tail pages */
+	struct mem_cgroup *memcg = page_memcg(head);
 	pg_data_t *pgdat = page_pgdat(page);
 	struct lruvec *lruvec;
 
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!head->mem_cgroup) {
+	if (!memcg) {
 		__mod_node_page_state(pgdat, idx, val);
 		return;
 	}
 
-	lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	__mod_lruvec_state(lruvec, idx, val);
 }
 
@@ -878,8 +1052,10 @@ static inline void count_memcg_events(struct mem_cgroup *memcg,
 static inline void count_memcg_page_event(struct page *page,
 					  enum vm_event_item idx)
 {
-	if (page->mem_cgroup)
-		count_memcg_events(page->mem_cgroup, idx, 1);
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	if (memcg)
+		count_memcg_events(memcg, idx, 1);
 }
 
 static inline void count_memcg_event_mm(struct mm_struct *mm,
@@ -948,6 +1124,27 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 
 struct mem_cgroup;
 
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	return NULL;
+}
+
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return NULL;
+}
+
+static inline struct mem_cgroup *page_memcg_check(struct page *page)
+{
+	return NULL;
+}
+
+static inline bool PageMemcgKmem(struct page *page)
+{
+	return false;
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return true;
@@ -1437,7 +1634,7 @@ static inline void mem_cgroup_track_foreign_dirty(struct page *page,
 	if (mem_cgroup_disabled())
 		return;
 
-	if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
+	if (unlikely(&page_memcg(page)->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(page, wb);
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index db6ae4d3fb4e..6b0c9d2c1d10 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1484,28 +1484,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 #endif
 }
 
-#ifdef CONFIG_MEMCG
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return page->mem_cgroup;
-}
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return READ_ONCE(page->mem_cgroup);
-}
-#else
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return NULL;
-}
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return NULL;
-}
-#endif
-
 /*
  * Some inline functions in vmstat.h depend on page_zone()
  */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5a9238f6caad..80f5d755c037 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -199,10 +199,7 @@ struct page {
 	atomic_t _refcount;
 
 #ifdef CONFIG_MEMCG
-	union {
-		struct mem_cgroup *mem_cgroup;
-		struct obj_cgroup **obj_cgroups;
-	};
+	unsigned long memcg_data;
 #endif
 
 	/*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7f85c23d52ab..7bf167993c05 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -350,23 +350,25 @@ struct napi_struct {
 };
 
 enum {
-	NAPI_STATE_SCHED,	/* Poll is scheduled */
-	NAPI_STATE_MISSED,	/* reschedule a napi */
-	NAPI_STATE_DISABLE,	/* Disable pending */
-	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
-	NAPI_STATE_LISTED,	/* NAPI added to system lists */
-	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
-	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_SCHED,		/* Poll is scheduled */
+	NAPI_STATE_MISSED,		/* reschedule a napi */
+	NAPI_STATE_DISABLE,		/* Disable pending */
+	NAPI_STATE_NPSVC,		/* Netpoll - don't dequeue from poll_list */
+	NAPI_STATE_LISTED,		/* NAPI added to system lists */
+	NAPI_STATE_NO_BUSY_POLL,	/* Do not add in napi_hash, no busy polling */
+	NAPI_STATE_IN_BUSY_POLL,	/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 };
 
 enum {
-	NAPIF_STATE_SCHED	 = BIT(NAPI_STATE_SCHED),
-	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
-	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
-	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
-	NAPIF_STATE_LISTED	 = BIT(NAPI_STATE_LISTED),
-	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
-	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_SCHED		= BIT(NAPI_STATE_SCHED),
+	NAPIF_STATE_MISSED		= BIT(NAPI_STATE_MISSED),
+	NAPIF_STATE_DISABLE		= BIT(NAPI_STATE_DISABLE),
+	NAPIF_STATE_NPSVC		= BIT(NAPI_STATE_NPSVC),
+	NAPIF_STATE_LISTED		= BIT(NAPI_STATE_LISTED),
+	NAPIF_STATE_NO_BUSY_POLL	= BIT(NAPI_STATE_NO_BUSY_POLL),
+	NAPIF_STATE_IN_BUSY_POLL	= BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 };
 
 enum gro_result {
@@ -437,6 +439,11 @@ static inline bool napi_disable_pending(struct napi_struct *n)
 	return test_bit(NAPI_STATE_DISABLE, &n->state);
 }
 
+static inline bool napi_prefer_busy_poll(struct napi_struct *n)
+{
+	return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
+}
+
 bool napi_schedule_prep(struct napi_struct *n);
 
 /**
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4f6ba9379112..fc0e1bd48e73 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -715,9 +715,8 @@ PAGEFLAG_FALSE(DoubleMap)
 #define PAGE_MAPCOUNT_RESERVE	-128
 #define PG_buddy	0x00000080
 #define PG_offline	0x00000100
-#define PG_kmemcg	0x00000200
-#define PG_table	0x00000400
-#define PG_guard	0x00000800
+#define PG_table	0x00000200
+#define PG_guard	0x00000400
 
 #define PageType(page, flag)						\
 	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -769,12 +768,6 @@ PAGE_TYPE_OPS(Buddy, buddy)
 PAGE_TYPE_OPS(Offline, offline)
 
 /*
- * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on
- * pages allocated with __GFP_ACCOUNT. It gets cleared on page free.
- */
-PAGE_TYPE_OPS(Kmemcg, kmemcg)
-
-/*
  * Marks pages in use as page tables.
  */
 PAGE_TYPE_OPS(Table, table)
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index b001fa91c14e..73af4a64a599 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -23,6 +23,8 @@
  */
 #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
 
+#define BUSY_POLL_BUDGET 8
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 
 struct napi_struct;
@@ -43,7 +45,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time);
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg);
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
@@ -105,7 +107,9 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
 
 	if (napi_id >= MIN_NAPI_ID)
-		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
+		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk,
+			       READ_ONCE(sk->sk_prefer_busy_poll),
+			       READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET);
 #endif
 }
 
@@ -131,13 +135,28 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 	sk_rx_queue_set(sk, skb);
 }
 
+static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (!READ_ONCE(sk->sk_napi_id))
+		WRITE_ONCE(sk->sk_napi_id, napi_id);
+#endif
+}
+
 /* variant used for unconnected sockets */
 static inline void sk_mark_napi_id_once(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	if (!READ_ONCE(sk->sk_napi_id))
-		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+	__sk_mark_napi_id_once(sk, skb->napi_id);
+#endif
+}
+
+static inline void sk_mark_napi_id_once_xdp(struct sock *sk,
+					    const struct xdp_buff *xdp)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	__sk_mark_napi_id_once(sk, xdp->rxq->napi_id);
 #endif
 }
 
diff --git a/include/net/sock.h b/include/net/sock.h
index f59764614e30..ffacdfdd9894 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -301,6 +301,8 @@ struct bpf_local_storage;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_uid: user id of owner
+  *	@sk_prefer_busy_poll: prefer busypolling over softirq processing
+  *	@sk_busy_poll_budget: napi processing budget when busypolling
   *	@sk_priority: %SO_PRIORITY setting
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
@@ -479,6 +481,10 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	u8			sk_prefer_busy_poll;
+	u16			sk_busy_poll_budget;
+#endif
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4525d6256321..a62fb7f8a1e3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -410,6 +410,7 @@ void tcp_syn_ack_timeout(const struct request_sock *req);
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		int flags, int *addr_len);
 int tcp_set_rcvlowat(struct sock *sk, int val);
+int tcp_set_window_clamp(struct sock *sk, int val);
 void tcp_data_ready(struct sock *sk);
 #ifdef CONFIG_MMU
 int tcp_mmap(struct file *file, struct socket *sock,
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 7d48b2ae217a..700ad5db7f5d 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -59,6 +59,7 @@ struct xdp_rxq_info {
 	u32 queue_index;
 	u32 reg_state;
 	struct xdp_mem_info mem;
+	unsigned int napi_id;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
 struct xdp_txq_info {
@@ -226,7 +227,7 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf)
 }
 
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index);
+		     struct net_device *dev, u32 queue_index, unsigned int napi_id);
 void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
 bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 5b1ee8a9976d..4e295541e396 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -13,6 +13,7 @@
 
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, u32 max);
 void xsk_tx_release(struct xsk_buff_pool *pool);
 struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
 					    u16 queue_id);
@@ -128,6 +129,12 @@ static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
 	return false;
 }
 
+static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc,
+						 u32 max)
+{
+	return 0;
+}
+
 static inline void xsk_tx_release(struct xsk_buff_pool *pool)
 {
 }
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 57d795365987..1efa463c4979 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -257,7 +257,7 @@ TRACE_EVENT(track_foreign_dirty,
 		__entry->ino		= inode ? inode->i_ino : 0;
 		__entry->memcg_id	= wb->memcg_css->id;
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
-		__entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup);
+		__entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup);
 	),
 
 	TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu",
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 77f7c1638eb1..4dcd13d097a9 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -119,6 +119,9 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 162999b12790..1233f14f659f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -557,7 +557,12 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
-		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
+		union {
+			/* valid prog_fd to attach to bpf prog */
+			__u32		attach_prog_fd;
+			/* or valid module BTF object fd or 0 to attach to vmlinux */
+			__u32		attach_btf_obj_fd;
+		};
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -3787,6 +3792,36 @@ union bpf_attr {
  *		*ARG_PTR_TO_BTF_ID* of type *task_struct*.
  *	Return
  *		Pointer to the current task.
+ *
+ * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags)
+ *	Description
+ *		Set or clear certain options on *bprm*:
+ *
+ *		**BPF_F_BPRM_SECUREEXEC** Set the secureexec bit
+ *		which sets the **AT_SECURE** auxv for glibc. The bit
+ *		is cleared if the flag is not specified.
+ *	Return
+ *		**-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * 	Description
+ * 		Return a coarse-grained version of the time elapsed since
+ * 		system boot, in nanoseconds. Does not include time the system
+ * 		was suspended.
+ *
+ * 		See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * 	Return
+ * 		Current *ktime*.
+ *
+ * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
+ *	Description
+ *		Returns the stored IMA hash of the *inode* (if it's avaialable).
+ *		If the hash is larger than *size*, then only *size*
+ *		bytes will be copied to *dst*
+ *	Return
+ *		The **hash_algo** is returned on success,
+ *		**-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
+ *		invalid arguments are passed.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3948,6 +3983,9 @@ union bpf_attr {
 	FN(task_storage_get),		\
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
+	FN(bprm_opts_set),		\
+	FN(ktime_get_coarse_ns),	\
+	FN(ima_inode_hash),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4119,6 +4157,11 @@ enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_IP,
 };
 
+/* Flags for bpf_bprm_opts_set helper */
+enum {
+	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
+};
+
 #define __bpf_md_ptr(type, name)	\
 union {					\
 	type name;			\