Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 269 insertions, 140 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7949e8b..5f35f93 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -94,6 +94,7 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 	fp->pages = size / PAGE_SIZE;
 	fp->aux = aux;
 	fp->aux->prog = fp;
+	fp->jit_requested = ebpf_jit_enabled();
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
 
@@ -217,30 +218,40 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	return 0;
 }
 
-static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn)
-{
-	return BPF_CLASS(insn->code) == BPF_JMP  &&
-	       /* Call and Exit are both special jumps with no
-		* target inside the BPF instruction image.
-		*/
-	       BPF_OP(insn->code) != BPF_CALL &&
-	       BPF_OP(insn->code) != BPF_EXIT;
-}
-
 static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
 {
 	struct bpf_insn *insn = prog->insnsi;
 	u32 i, insn_cnt = prog->len;
+	bool pseudo_call;
+	u8 code;
+	int off;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
-		if (!bpf_is_jmp_and_has_target(insn))
+		code = insn->code;
+		if (BPF_CLASS(code) != BPF_JMP)
 			continue;
+		if (BPF_OP(code) == BPF_EXIT)
+			continue;
+		if (BPF_OP(code) == BPF_CALL) {
+			if (insn->src_reg == BPF_PSEUDO_CALL)
+				pseudo_call = true;
+			else
+				continue;
+		} else {
+			pseudo_call = false;
+		}
+		off = pseudo_call ? insn->imm : insn->off;
 
 		/* Adjust offset of jmps if we cross boundaries. */
-		if (i < pos && i + insn->off + 1 > pos)
-			insn->off += delta;
-		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
-			insn->off -= delta;
+		if (i < pos && i + off + 1 > pos)
+			off += delta;
+		else if (i > pos + delta && i + off + 1 <= pos + delta)
+			off -= delta;
+
+		if (pseudo_call)
+			insn->imm = off;
+		else
+			insn->off = off;
 	}
 }
 
@@ -289,6 +300,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 }
 
 #ifdef CONFIG_BPF_JIT
+/* All BPF JIT sysctl knobs here. */
+int bpf_jit_enable   __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
+int bpf_jit_harden   __read_mostly;
+int bpf_jit_kallsyms __read_mostly;
+
 static __always_inline void
 bpf_get_prog_addr_region(const struct bpf_prog *prog,
 			 unsigned long *symbol_start,
@@ -370,8 +386,6 @@ static DEFINE_SPINLOCK(bpf_lock);
 static LIST_HEAD(bpf_kallsyms);
 static struct latch_tree_root bpf_tree __cacheline_aligned;
 
-int bpf_jit_kallsyms __read_mostly;
-
 static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
 {
 	WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
@@ -552,8 +566,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	bpf_prog_unlock_free(fp);
 }
 
-int bpf_jit_harden __read_mostly;
-
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
 			      const struct bpf_insn *aux,
 			      struct bpf_insn *to_buff)
@@ -711,7 +723,7 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 	struct bpf_insn *insn;
 	int i, rewritten;
 
-	if (!bpf_jit_blinding_enabled())
+	if (!bpf_jit_blinding_enabled(prog) || prog->blinded)
 		return prog;
 
 	clone = bpf_prog_clone_create(prog, GFP_USER);
@@ -753,13 +765,16 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 		i        += insn_delta;
 	}
 
+	clone->blinded = 1;
 	return clone;
 }
 #endif /* CONFIG_BPF_JIT */
 
 /* Base function for offset calculation. Needs to go into .text section,
  * therefore keeping it non-static as well; will also be used by JITs
- * anyway later on, so do not let the compiler omit it.
+ * anyway later on, so do not let the compiler omit it. This also needs
+ * to go into kallsyms for correlation from e.g. bpftool, so naming
+ * must not change.
  */
 noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
@@ -767,6 +782,137 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 EXPORT_SYMBOL_GPL(__bpf_call_base);
 
+/* All UAPI available opcodes. */
+#define BPF_INSN_MAP(INSN_2, INSN_3)		\
+	/* 32 bit ALU operations. */		\
+	/*   Register based. */			\
+	INSN_3(ALU, ADD, X),			\
+	INSN_3(ALU, SUB, X),			\
+	INSN_3(ALU, AND, X),			\
+	INSN_3(ALU, OR,  X),			\
+	INSN_3(ALU, LSH, X),			\
+	INSN_3(ALU, RSH, X),			\
+	INSN_3(ALU, XOR, X),			\
+	INSN_3(ALU, MUL, X),			\
+	INSN_3(ALU, MOV, X),			\
+	INSN_3(ALU, DIV, X),			\
+	INSN_3(ALU, MOD, X),			\
+	INSN_2(ALU, NEG),			\
+	INSN_3(ALU, END, TO_BE),		\
+	INSN_3(ALU, END, TO_LE),		\
+	/*   Immediate based. */		\
+	INSN_3(ALU, ADD, K),			\
+	INSN_3(ALU, SUB, K),			\
+	INSN_3(ALU, AND, K),			\
+	INSN_3(ALU, OR,  K),			\
+	INSN_3(ALU, LSH, K),			\
+	INSN_3(ALU, RSH, K),			\
+	INSN_3(ALU, XOR, K),			\
+	INSN_3(ALU, MUL, K),			\
+	INSN_3(ALU, MOV, K),			\
+	INSN_3(ALU, DIV, K),			\
+	INSN_3(ALU, MOD, K),			\
+	/* 64 bit ALU operations. */		\
+	/*   Register based. */			\
+	INSN_3(ALU64, ADD,  X),			\
+	INSN_3(ALU64, SUB,  X),			\
+	INSN_3(ALU64, AND,  X),			\
+	INSN_3(ALU64, OR,   X),			\
+	INSN_3(ALU64, LSH,  X),			\
+	INSN_3(ALU64, RSH,  X),			\
+	INSN_3(ALU64, XOR,  X),			\
+	INSN_3(ALU64, MUL,  X),			\
+	INSN_3(ALU64, MOV,  X),			\
+	INSN_3(ALU64, ARSH, X),			\
+	INSN_3(ALU64, DIV,  X),			\
+	INSN_3(ALU64, MOD,  X),			\
+	INSN_2(ALU64, NEG),			\
+	/*   Immediate based. */		\
+	INSN_3(ALU64, ADD,  K),			\
+	INSN_3(ALU64, SUB,  K),			\
+	INSN_3(ALU64, AND,  K),			\
+	INSN_3(ALU64, OR,   K),			\
+	INSN_3(ALU64, LSH,  K),			\
+	INSN_3(ALU64, RSH,  K),			\
+	INSN_3(ALU64, XOR,  K),			\
+	INSN_3(ALU64, MUL,  K),			\
+	INSN_3(ALU64, MOV,  K),			\
+	INSN_3(ALU64, ARSH, K),			\
+	INSN_3(ALU64, DIV,  K),			\
+	INSN_3(ALU64, MOD,  K),			\
+	/* Call instruction. */			\
+	INSN_2(JMP, CALL),			\
+	/* Exit instruction. */			\
+	INSN_2(JMP, EXIT),			\
+	/* Jump instructions. */		\
+	/*   Register based. */			\
+	INSN_3(JMP, JEQ,  X),			\
+	INSN_3(JMP, JNE,  X),			\
+	INSN_3(JMP, JGT,  X),			\
+	INSN_3(JMP, JLT,  X),			\
+	INSN_3(JMP, JGE,  X),			\
+	INSN_3(JMP, JLE,  X),			\
+	INSN_3(JMP, JSGT, X),			\
+	INSN_3(JMP, JSLT, X),			\
+	INSN_3(JMP, JSGE, X),			\
+	INSN_3(JMP, JSLE, X),			\
+	INSN_3(JMP, JSET, X),			\
+	/*   Immediate based. */		\
+	INSN_3(JMP, JEQ,  K),			\
+	INSN_3(JMP, JNE,  K),			\
+	INSN_3(JMP, JGT,  K),			\
+	INSN_3(JMP, JLT,  K),			\
+	INSN_3(JMP, JGE,  K),			\
+	INSN_3(JMP, JLE,  K),			\
+	INSN_3(JMP, JSGT, K),			\
+	INSN_3(JMP, JSLT, K),			\
+	INSN_3(JMP, JSGE, K),			\
+	INSN_3(JMP, JSLE, K),			\
+	INSN_3(JMP, JSET, K),			\
+	INSN_2(JMP, JA),			\
+	/* Store instructions. */		\
+	/*   Register based. */			\
+	INSN_3(STX, MEM,  B),			\
+	INSN_3(STX, MEM,  H),			\
+	INSN_3(STX, MEM,  W),			\
+	INSN_3(STX, MEM,  DW),			\
+	INSN_3(STX, XADD, W),			\
+	INSN_3(STX, XADD, DW),			\
+	/*   Immediate based. */		\
+	INSN_3(ST, MEM, B),			\
+	INSN_3(ST, MEM, H),			\
+	INSN_3(ST, MEM, W),			\
+	INSN_3(ST, MEM, DW),			\
+	/* Load instructions. */		\
+	/*   Register based. */			\
+	INSN_3(LDX, MEM, B),			\
+	INSN_3(LDX, MEM, H),			\
+	INSN_3(LDX, MEM, W),			\
+	INSN_3(LDX, MEM, DW),			\
+	/*   Immediate based. */		\
+	INSN_3(LD, IMM, DW),			\
+	/*   Misc (old cBPF carry-over). */	\
+	INSN_3(LD, ABS, B),			\
+	INSN_3(LD, ABS, H),			\
+	INSN_3(LD, ABS, W),			\
+	INSN_3(LD, IND, B),			\
+	INSN_3(LD, IND, H),			\
+	INSN_3(LD, IND, W)
+
+bool bpf_opcode_in_insntable(u8 code)
+{
+#define BPF_INSN_2_TBL(x, y)    [BPF_##x | BPF_##y] = true
+#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
+	static const bool public_insntable[256] = {
+		[0 ... 255] = false,
+		/* Now overwrite non-defaults ... */
+		BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+	};
+#undef BPF_INSN_3_TBL
+#undef BPF_INSN_2_TBL
+	return public_insntable[code];
+}
+
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 /**
  *	__bpf_prog_run - run eBPF program on a given context
@@ -775,118 +921,21 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
  *
  * Decode and execute eBPF instructions.
  */
-static unsigned int ___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)
 {
 	u64 tmp;
+#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
 	static const void *jumptable[256] = {
 		[0 ... 255] = &&default_label,
 		/* Now overwrite non-defaults ... */
-		/* 32 bit ALU operations */
-		[BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
-		[BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
-		[BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
-		[BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
-		[BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
-		[BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
-		[BPF_ALU | BPF_OR | BPF_X]  = &&ALU_OR_X,
-		[BPF_ALU | BPF_OR | BPF_K]  = &&ALU_OR_K,
-		[BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
-		[BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
-		[BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
-		[BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
-		[BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
-		[BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
-		[BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
-		[BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
-		[BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
-		[BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
-		[BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
-		[BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
-		[BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
-		[BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
-		[BPF_ALU | BPF_NEG] = &&ALU_NEG,
-		[BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
-		[BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
-		/* 64 bit ALU operations */
-		[BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
-		[BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
-		[BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
-		[BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
-		[BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
-		[BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
-		[BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
-		[BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
-		[BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
-		[BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
-		[BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
-		[BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
-		[BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
-		[BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
-		[BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
-		[BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
-		[BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
-		[BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
-		[BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
-		[BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
-		[BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
-		[BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
-		[BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
-		[BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
-		[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
-		/* Call instruction */
-		[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+		BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
+		/* Non-UAPI available opcodes. */
+		[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
 		[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
-		/* Jumps */
-		[BPF_JMP | BPF_JA] = &&JMP_JA,
-		[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
-		[BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
-		[BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
-		[BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
-		[BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
-		[BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
-		[BPF_JMP | BPF_JLT | BPF_X] = &&JMP_JLT_X,
-		[BPF_JMP | BPF_JLT | BPF_K] = &&JMP_JLT_K,
-		[BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
-		[BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
-		[BPF_JMP | BPF_JLE | BPF_X] = &&JMP_JLE_X,
-		[BPF_JMP | BPF_JLE | BPF_K] = &&JMP_JLE_K,
-		[BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
-		[BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
-		[BPF_JMP | BPF_JSLT | BPF_X] = &&JMP_JSLT_X,
-		[BPF_JMP | BPF_JSLT | BPF_K] = &&JMP_JSLT_K,
-		[BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
-		[BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
-		[BPF_JMP | BPF_JSLE | BPF_X] = &&JMP_JSLE_X,
-		[BPF_JMP | BPF_JSLE | BPF_K] = &&JMP_JSLE_K,
-		[BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
-		[BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
-		/* Program return */
-		[BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
-		/* Store instructions */
-		[BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
-		[BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
-		[BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
-		[BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
-		[BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
-		[BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
-		[BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
-		[BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
-		[BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
-		[BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
-		/* Load instructions */
-		[BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
-		[BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
-		[BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
-		[BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
-		[BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
-		[BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
-		[BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
-		[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
-		[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
-		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
-		[BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW,
 	};
+#undef BPF_INSN_3_LBL
+#undef BPF_INSN_2_LBL
 	u32 tail_call_cnt = 0;
 	void *ptr;
 	int off;
@@ -950,14 +999,10 @@ select_insn:
 		(*(s64 *) &DST) >>= IMM;
 		CONT;
 	ALU64_MOD_X:
-		if (unlikely(SRC == 0))
-			return 0;
 		div64_u64_rem(DST, SRC, &tmp);
 		DST = tmp;
 		CONT;
 	ALU_MOD_X:
-		if (unlikely((u32)SRC == 0))
-			return 0;
 		tmp = (u32) DST;
 		DST = do_div(tmp, (u32) SRC);
 		CONT;
@@ -970,13 +1015,9 @@ select_insn:
 		DST = do_div(tmp, (u32) IMM);
 		CONT;
 	ALU64_DIV_X:
-		if (unlikely(SRC == 0))
-			return 0;
 		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
-		if (unlikely((u32)SRC == 0))
-			return 0;
 		tmp = (u32) DST;
 		do_div(tmp, (u32) SRC);
 		DST = (u32) tmp;
@@ -1026,6 +1067,13 @@ select_insn:
 						       BPF_R4, BPF_R5);
 		CONT;
 
+	JMP_CALL_ARGS:
+		BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2,
+							    BPF_R3, BPF_R4,
+							    BPF_R5,
+							    insn + insn->off + 1);
+		CONT;
+
 	JMP_TAIL_CALL: {
 		struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
 		struct bpf_array *array = container_of(map, struct bpf_array, map);
@@ -1280,8 +1328,14 @@ load_byte:
 		goto load_byte;
 
 	default_label:
-		/* If we ever reach this, we have a bug somewhere. */
-		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+		/* If we ever reach this, we have a bug somewhere. Die hard here
+		 * instead of just returning 0; we could be somewhere in a subprog,
+		 * so execution could continue otherwise which we do /not/ want.
+		 *
+		 * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable().
+		 */
+		pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code);
+		BUG_ON(1);
 		return 0;
 }
 STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
@@ -1298,6 +1352,23 @@ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn
 	return ___bpf_prog_run(regs, insn, stack); \
 }
 
+#define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size
+#define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \
+static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
+				      const struct bpf_insn *insn) \
+{ \
+	u64 stack[stack_size / sizeof(u64)]; \
+	u64 regs[MAX_BPF_REG]; \
+\
+	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
+	BPF_R1 = r1; \
+	BPF_R2 = r2; \
+	BPF_R3 = r3; \
+	BPF_R4 = r4; \
+	BPF_R5 = r5; \
+	return ___bpf_prog_run(regs, insn, stack); \
+}
+
 #define EVAL1(FN, X) FN(X)
 #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y)
 #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y)
@@ -1309,6 +1380,10 @@ EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192);
 EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384);
 EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512);
 
+EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192);
+EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384);
+EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512);
+
 #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size),
 
 static unsigned int (*interpreters[])(const void *ctx,
@@ -1317,11 +1392,33 @@ EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
 EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
 EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
 };
+#undef PROG_NAME_LIST
+#define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size),
+static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5,
+				  const struct bpf_insn *insn) = {
+EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
+EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
+EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
+};
+#undef PROG_NAME_LIST
+
+void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
+{
+	stack_depth = max_t(u32, stack_depth, 1);
+	insn->off = (s16) insn->imm;
+	insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] -
+		__bpf_call_base_args;
+	insn->code = BPF_JMP | BPF_CALL_ARGS;
+}
 
 #else
-static unsigned int __bpf_prog_ret0(const void *ctx,
-				    const struct bpf_insn *insn)
+static unsigned int __bpf_prog_ret0_warn(const void *ctx,
+					 const struct bpf_insn *insn)
 {
+	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
+	 * is not working properly, so warn about it!
+	 */
+	WARN_ON_ONCE(1);
 	return 0;
 }
 #endif
@@ -1329,6 +1426,9 @@ static unsigned int __bpf_prog_ret0(const void *ctx,
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)
 {
+	if (fp->kprobe_override)
+		return false;
+
 	if (!array->owner_prog_type) {
 		/* There's no owner yet where we could check for
 		 * compatibility.
@@ -1378,7 +1478,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 
 	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
 #else
-	fp->bpf_func = __bpf_prog_ret0;
+	fp->bpf_func = __bpf_prog_ret0_warn;
 #endif
 
 	/* eBPF JITs can rewrite the program in case constant
@@ -1481,6 +1581,8 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 	rcu_read_lock();
 	prog = rcu_dereference(progs)->progs;
 	for (; *prog; prog++) {
+		if (*prog == &dummy_bpf_prog.prog)
+			continue;
 		id = (*prog)->aux->id;
 		if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
 			rcu_read_unlock();
@@ -1564,14 +1666,41 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 	return 0;
 }
 
+int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+			     __u32 __user *prog_ids, u32 request_cnt,
+			     __u32 __user *prog_cnt)
+{
+	u32 cnt = 0;
+
+	if (array)
+		cnt = bpf_prog_array_length(array);
+
+	if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
+		return -EFAULT;
+
+	/* return early if user requested only program count or nothing to copy */
+	if (!request_cnt || !cnt)
+		return 0;
+
+	return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
 	struct bpf_prog_aux *aux;
+	int i;
 
 	aux = container_of(work, struct bpf_prog_aux, work);
 	if (bpf_prog_is_dev_bound(aux))
 		bpf_prog_offload_destroy(aux->prog);
-	bpf_jit_free(aux->prog);
+	for (i = 0; i < aux->func_cnt; i++)
+		bpf_jit_free(aux->func[i]);
+	if (aux->func_cnt) {
+		kfree(aux->func);
+		bpf_prog_unlock_free(aux->prog);
+	} else {
+		bpf_jit_free(aux->prog);
+	}
 }
 
 /* Free internal BPF program */