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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2022-01-06

We've added 41 non-merge commits during the last 2 day(s) which contain
a total of 36 files changed, 1214 insertions(+), 368 deletions(-).

The main changes are:

1) Various fixes in the verifier, from Kris and Daniel.

2) Fixes in sockmap, from John.

3) bpf_getsockopt fix, from Kuniyuki.

4) INET_POST_BIND fix, from Menglong.

5) arm64 JIT fix for bpf pseudo funcs, from Hou.

6) BPF ISA doc improvements, from Christoph.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (41 commits)
  bpf: selftests: Add bind retry for post_bind{4, 6}
  bpf: selftests: Use C99 initializers in test_sock.c
  net: bpf: Handle return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND()
  bpf/selftests: Test bpf_d_path on rdonly_mem.
  libbpf: Add documentation for bpf_map batch operations
  selftests/bpf: Don't rely on preserving volatile in PT_REGS macros in loop3
  xdp: Add xdp_do_redirect_frame() for pre-computed xdp_frames
  xdp: Move conversion to xdp_frame out of map functions
  page_pool: Store the XDP mem id
  page_pool: Add callback to init pages when they are allocated
  xdp: Allow registering memory model without rxq reference
  samples/bpf: xdpsock: Add timestamp for Tx-only operation
  samples/bpf: xdpsock: Add time-out for cleaning Tx
  samples/bpf: xdpsock: Add sched policy and priority support
  samples/bpf: xdpsock: Add cyclic TX operation capability
  samples/bpf: xdpsock: Add clockid selection support
  samples/bpf: xdpsock: Add Dest and Src MAC setting for Tx-only operation
  samples/bpf: xdpsock: Add VLAN support for Tx-only operation
  libbpf 1.0: Deprecate bpf_object__find_map_by_offset() API
  libbpf 1.0: Deprecate bpf_map__is_offload_neutral()
  ...
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/bpf/instruction-set.rst

@@ -19,23 +19,37 @@ The eBPF calling convention is defined as:
 R0 - R5 are scratch registers and eBPF programs needs to spill/fill them if
 necessary across calls.
 
+Instruction encoding
+====================
+
+eBPF uses 64-bit instructions with the following encoding:
+
+ =============  =======  ===============  ====================  ============
+ 32 bits (MSB)  16 bits  4 bits           4 bits                8 bits (LSB)
+ =============  =======  ===============  ====================  ============
+ immediate      offset   source register  destination register  opcode
+ =============  =======  ===============  ====================  ============
+
+Note that most instructions do not use all of the fields.
+Unused fields shall be cleared to zero.
+
 Instruction classes
-===================
+-------------------
 
 The three LSB bits of the 'opcode' field store the instruction class:
 
-  ========= =====
-  class     value
-  ========= =====
-  BPF_LD    0x00
-  BPF_LDX   0x01
-  BPF_ST    0x02
-  BPF_STX   0x03
-  BPF_ALU   0x04
-  BPF_JMP   0x05
-  BPF_JMP32 0x06
-  BPF_ALU64 0x07
-  ========= =====
+  =========  =====  ===============================
+  class      value  description
+  =========  =====  ===============================
+  BPF_LD     0x00   non-standard load operations
+  BPF_LDX    0x01   load into register operations
+  BPF_ST     0x02   store from immediate operations
+  BPF_STX    0x03   store from register operations
+  BPF_ALU    0x04   32-bit arithmetic operations
+  BPF_JMP    0x05   64-bit jump operations
+  BPF_JMP32  0x06   32-bit jump operations
+  BPF_ALU64  0x07   64-bit arithmetic operations
+  =========  =====  ===============================
 
 Arithmetic and jump instructions
 ================================
@@ -60,66 +74,78 @@ The 4th bit encodes the source operand:
 
 The four MSB bits store the operation code.
 
-For class BPF_ALU or BPF_ALU64:
 
-  ========  =====  =========================
+Arithmetic instructions
+-----------------------
+
+BPF_ALU uses 32-bit wide operands while BPF_ALU64 uses 64-bit wide operands for
+otherwise identical operations.
+The code field encodes the operation as below:
+
+  ========  =====  ==========================
   code      value  description
-  ========  =====  =========================
-  BPF_ADD   0x00
-  BPF_SUB   0x10
-  BPF_MUL   0x20
-  BPF_DIV   0x30
-  BPF_OR    0x40
-  BPF_AND   0x50
-  BPF_LSH   0x60
-  BPF_RSH   0x70
-  BPF_NEG   0x80
-  BPF_MOD   0x90
-  BPF_XOR   0xa0
-  BPF_MOV   0xb0   mov reg to reg
+  ========  =====  ==========================
+  BPF_ADD   0x00   dst += src
+  BPF_SUB   0x10   dst -= src
+  BPF_MUL   0x20   dst \*= src
+  BPF_DIV   0x30   dst /= src
+  BPF_OR    0x40   dst \|= src
+  BPF_AND   0x50   dst &= src
+  BPF_LSH   0x60   dst <<= src
+  BPF_RSH   0x70   dst >>= src
+  BPF_NEG   0x80   dst = ~src
+  BPF_MOD   0x90   dst %= src
+  BPF_XOR   0xa0   dst ^= src
+  BPF_MOV   0xb0   dst = src
   BPF_ARSH  0xc0   sign extending shift right
   BPF_END   0xd0   endianness conversion
-  ========  =====  =========================
+  ========  =====  ==========================
 
-For class BPF_JMP or BPF_JMP32:
+BPF_ADD | BPF_X | BPF_ALU means::
 
-  ========  =====  =========================
-  code      value  description
-  ========  =====  =========================
-  BPF_JA    0x00   BPF_JMP only
-  BPF_JEQ   0x10
-  BPF_JGT   0x20
-  BPF_JGE   0x30
-  BPF_JSET  0x40
-  BPF_JNE   0x50   jump '!='
-  BPF_JSGT  0x60   signed '>'
-  BPF_JSGE  0x70   signed '>='
-  BPF_CALL  0x80   function call
-  BPF_EXIT  0x90   function return
-  BPF_JLT   0xa0   unsigned '<'
-  BPF_JLE   0xb0   unsigned '<='
-  BPF_JSLT  0xc0   signed '<'
-  BPF_JSLE  0xd0   signed '<='
-  ========  =====  =========================
+  dst_reg = (u32) dst_reg + (u32) src_reg;
 
-So BPF_ADD | BPF_X | BPF_ALU means::
+BPF_ADD | BPF_X | BPF_ALU64 means::
 
-  dst_reg = (u32) dst_reg + (u32) src_reg;
+  dst_reg = dst_reg + src_reg
 
-Similarly, BPF_XOR | BPF_K | BPF_ALU means::
+BPF_XOR | BPF_K | BPF_ALU means::
 
   src_reg = (u32) src_reg ^ (u32) imm32
 
-eBPF is using BPF_MOV | BPF_X | BPF_ALU to represent A = B moves.  BPF_ALU64
-is used to mean exactly the same operations as BPF_ALU, but with 64-bit wide
-operands instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.::
+BPF_XOR | BPF_K | BPF_ALU64 means::
 
-  dst_reg = dst_reg + src_reg
+  src_reg = src_reg ^ imm32
+
+
+Jump instructions
+-----------------
 
-BPF_JMP | BPF_EXIT means function exit only. The eBPF program needs to store
-the return value into register R0 before doing a BPF_EXIT. Class 6 is used as
-BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide
-operands for the comparisons instead.
+BPF_JMP32 uses 32-bit wide operands while BPF_JMP uses 64-bit wide operands for
+otherwise identical operations.
+The code field encodes the operation as below:
+
+  ========  =====  =========================  ============
+  code      value  description                notes
+  ========  =====  =========================  ============
+  BPF_JA    0x00   PC += off                  BPF_JMP only
+  BPF_JEQ   0x10   PC += off if dst == src
+  BPF_JGT   0x20   PC += off if dst > src     unsigned
+  BPF_JGE   0x30   PC += off if dst >= src    unsigned
+  BPF_JSET  0x40   PC += off if dst & src
+  BPF_JNE   0x50   PC += off if dst != src
+  BPF_JSGT  0x60   PC += off if dst > src     signed
+  BPF_JSGE  0x70   PC += off if dst >= src    signed
+  BPF_CALL  0x80   function call
+  BPF_EXIT  0x90   function / program return  BPF_JMP only
+  BPF_JLT   0xa0   PC += off if dst < src     unsigned
+  BPF_JLE   0xb0   PC += off if dst <= src    unsigned
+  BPF_JSLT  0xc0   PC += off if dst < src     signed
+  BPF_JSLE  0xd0   PC += off if dst <= src    signed
+  ========  =====  =========================  ============
+
+The eBPF program needs to store the return value into register R0 before doing a
+BPF_EXIT.
 
 
 Load and store instructions
@@ -147,15 +173,15 @@ The size modifier is one of:
 
 The mode modifier is one of:
 
-  =============  =====  =====================
+  =============  =====  ====================================
   mode modifier  value  description
-  =============  =====  =====================
+  =============  =====  ====================================
   BPF_IMM        0x00   used for 64-bit mov
-  BPF_ABS        0x20
-  BPF_IND        0x40
-  BPF_MEM        0x60
+  BPF_ABS        0x20   legacy BPF packet access
+  BPF_IND        0x40   legacy BPF packet access
+  BPF_MEM        0x60   all normal load and store operations
   BPF_ATOMIC     0xc0   atomic operations
-  =============  =====  =====================
+  =============  =====  ====================================
 
 BPF_MEM | <size> | BPF_STX means::
 

arch/arm64/net/bpf_jit_comp.c

@@ -792,7 +792,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		u64 imm64;
 
 		imm64 = (u64)insn1.imm << 32 | (u32)imm;
-		emit_a64_mov_i64(dst, imm64, ctx);
+		if (bpf_pseudo_func(insn))
+			emit_addr_mov_i64(dst, imm64, ctx);
+		else
+			emit_a64_mov_i64(dst, imm64, ctx);
 
 		return 1;
 	}

include/linux/bpf.h

@@ -1669,17 +1669,17 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 struct btf *bpf_get_btf_vmlinux(void);
 
 /* Map specifics */
-struct xdp_buff;
+struct xdp_frame;
 struct sk_buff;
 struct bpf_dtab_netdev;
 struct bpf_cpu_map_entry;
 
 void __dev_flush(void);
-int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx);
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx);
-int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
 			  struct bpf_map *map, bool exclude_ingress);
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog);
@@ -1688,7 +1688,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 			   bool exclude_ingress);
 
 void __cpu_map_flush(void);
-int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx);
 int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
 			     struct sk_buff *skb);
@@ -1866,26 +1866,26 @@ static inline void __dev_flush(void)
 {
 }
 
-struct xdp_buff;
+struct xdp_frame;
 struct bpf_dtab_netdev;
 struct bpf_cpu_map_entry;
 
 static inline
-int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
 	return 0;
 }
 
 static inline
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
 	return 0;
 }
 
 static inline
-int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
 			  struct bpf_map *map, bool exclude_ingress)
 {
 	return 0;
@@ -1913,7 +1913,7 @@ static inline void __cpu_map_flush(void)
 }
 
 static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
-				  struct xdp_buff *xdp,
+				  struct xdp_frame *xdpf,
 				  struct net_device *dev_rx)
 {
 	return 0;

include/linux/filter.h

@@ -1019,6 +1019,10 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 int xdp_do_redirect(struct net_device *dev,
 		    struct xdp_buff *xdp,
 		    struct bpf_prog *prog);
+int xdp_do_redirect_frame(struct net_device *dev,
+			  struct xdp_buff *xdp,
+			  struct xdp_frame *xdpf,
+			  struct bpf_prog *prog);
 void xdp_do_flush(void);
 
 /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as

include/net/page_pool.h

@@ -80,6 +80,8 @@ struct page_pool_params {
 	enum dma_data_direction dma_dir; /* DMA mapping direction */
 	unsigned int	max_len; /* max DMA sync memory size */
 	unsigned int	offset;  /* DMA addr offset */
+	void (*init_callback)(struct page *page, void *arg);
+	void *init_arg;
 };
 
 struct page_pool {
@@ -94,6 +96,7 @@ struct page_pool {
 	unsigned int frag_offset;
 	struct page *frag_page;
 	long frag_users;
+	u32 xdp_mem_id;
 
 	/*
 	 * Data structure for allocation side
@@ -168,9 +171,12 @@ bool page_pool_return_skb_page(struct page *page);
 
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 
+struct xdp_mem_info;
+
 #ifdef CONFIG_PAGE_POOL
 void page_pool_destroy(struct page_pool *pool);
-void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
+			   struct xdp_mem_info *mem);
 void page_pool_release_page(struct page_pool *pool, struct page *page);
 void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 			     int count);
@@ -180,7 +186,8 @@ static inline void page_pool_destroy(struct page_pool *pool)
 }
 
 static inline void page_pool_use_xdp_mem(struct page_pool *pool,
-					 void (*disconnect)(void *))
+					 void (*disconnect)(void *),
+					 struct xdp_mem_info *mem)
 {
 }
 static inline void page_pool_release_page(struct page_pool *pool,

include/net/sock.h

@@ -1209,6 +1209,7 @@ struct proto {
 	void			(*unhash)(struct sock *sk);
 	void			(*rehash)(struct sock *sk);
 	int			(*get_port)(struct sock *sk, unsigned short snum);
+	void			(*put_port)(struct sock *sk);
 #ifdef CONFIG_BPF_SYSCALL
 	int			(*psock_update_sk_prot)(struct sock *sk,
 							struct sk_psock *psock,

include/net/xdp.h

@@ -260,6 +260,9 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
 int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 			       enum xdp_mem_type type, void *allocator);
 void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq);
+int xdp_reg_mem_model(struct xdp_mem_info *mem,
+		      enum xdp_mem_type type, void *allocator);
+void xdp_unreg_mem_model(struct xdp_mem_info *mem);
 
 /* Drivers not supporting XDP metadata can use this helper, which
  * rejects any room expansion for metadata as a result.

kernel/bpf/cpumap.c

@@ -746,15 +746,9 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 		list_add(&bq->flush_node, flush_list);
 }
 
-int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
-	struct xdp_frame *xdpf;
-
-	xdpf = xdp_convert_buff_to_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	/* Info needed when constructing SKB on remote CPU */
 	xdpf->dev_rx = dev_rx;