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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-10-01

The following pull-request contains BPF updates for your *net-next* tree.

We've added 90 non-merge commits during the last 8 day(s) which contain
a total of 103 files changed, 7662 insertions(+), 1894 deletions(-).

Note that once bpf(/net) tree gets merged into net-next, there will be a small
merge conflict in tools/lib/bpf/btf.c between commit 1245008122d7 ("libbpf: Fix
native endian assumption when parsing BTF") from the bpf tree and the commit
3289959b97ca ("libbpf: Support BTF loading and raw data output in both endianness")
from the bpf-next tree. Correct resolution would be to stick with bpf-next, it
should look like:

  [...]
        /* check BTF magic */
        if (fread(&magic, 1, sizeof(magic), f) < sizeof(magic)) {
                err = -EIO;
                goto err_out;
        }
        if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) {
                /* definitely not a raw BTF */
                err = -EPROTO;
                goto err_out;
        }

        /* get file size */
  [...]

The main changes are:

1) Add bpf_snprintf_btf() and bpf_seq_printf_btf() helpers to support displaying
   BTF-based kernel data structures out of BPF programs, from Alan Maguire.

2) Speed up RCU tasks trace grace periods by a factor of 50 & fix a few race
   conditions exposed by it. It was discussed to take these via BPF and
   networking tree to get better testing exposure, from Paul E. McKenney.

3) Support multi-attach for freplace programs, needed for incremental attachment
   of multiple XDP progs using libxdp dispatcher model, from Toke Høiland-Jørgensen.

4) libbpf support for appending new BTF types at the end of BTF object, allowing
   intrusive changes of prog's BTF (useful for future linking), from Andrii Nakryiko.

5) Several BPF helper improvements e.g. avoid atomic op in cookie generator and add
   a redirect helper into neighboring subsys, from Daniel Borkmann.

6) Allow map updates on sockmaps from bpf_iter context in order to migrate sockmaps
   from one to another, from Lorenz Bauer.

7) Fix 32 bit to 64 bit assignment from latest alu32 bounds tracking which caused
   a verifier issue due to type downgrade to scalar, from John Fastabend.

8) Follow-up on tail-call support in BPF subprogs which optimizes x64 JIT prologue
   and epilogue sections, from Maciej Fijalkowski.

9) Add an option to perf RB map to improve sharing of event entries by avoiding remove-
   on-close behavior. Also, add BPF_PROG_TEST_RUN for raw_tracepoint, from Song Liu.

10) Fix a crash in AF_XDP's socket_release when memory allocation for UMEMs fails,
    from Magnus Karlsson.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 23 insertions, 12 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 26f43279b78b..796506dcfc42 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -281,7 +281,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */
-	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
+	if (stack_depth)
+		EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
 	if (tail_call_reachable)
 		EMIT1(0x50);         /* push rax */
 	*pprog = prog;
@@ -407,9 +408,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
 	int pop_bytes = 0;
-	int off1 = 49;
-	int off2 = 38;
-	int off3 = 16;
+	int off1 = 42;
+	int off2 = 31;
+	int off3 = 9;
 	int cnt = 0;
 
 	/* count the additional bytes used for popping callee regs from stack
@@ -421,6 +422,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	off2 += pop_bytes;
 	off3 += pop_bytes;
 
+	if (stack_depth) {
+		off1 += 7;
+		off2 += 7;
+		off3 += 7;
+	}
+
 	/*
 	 * rdi - pointer to ctx
 	 * rsi - pointer to bpf_array
@@ -465,8 +472,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	prog = *pprog;
 
 	EMIT1(0x58);                              /* pop rax */
-	EMIT3_off32(0x48, 0x81, 0xC4,             /* add rsp, sd */
-		    round_up(stack_depth, 8));
+	if (stack_depth)
+		EMIT3_off32(0x48, 0x81, 0xC4,     /* add rsp, sd */
+			    round_up(stack_depth, 8));
 
 	/* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */
 	EMIT4(0x48, 0x8B, 0x49,                   /* mov rcx, qword ptr [rcx + 32] */
@@ -491,7 +499,7 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
 	int pop_bytes = 0;
-	int off1 = 27;
+	int off1 = 20;
 	int poke_off;
 	int cnt = 0;
 
@@ -506,10 +514,14 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	 * total bytes for:
 	 * - nop5/ jmpq $off
 	 * - pop callee regs
-	 * - sub rsp, $val
+	 * - sub rsp, $val if depth > 0
 	 * - pop rax
 	 */
-	poke_off = X86_PATCH_SIZE + pop_bytes + 7 + 1;
+	poke_off = X86_PATCH_SIZE + pop_bytes + 1;
+	if (stack_depth) {
+		poke_off += 7;
+		off1 += 7;
+	}
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -533,7 +545,8 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	pop_callee_regs(pprog, callee_regs_used);
 	prog = *pprog;
 	EMIT1(0x58);                                  /* pop rax */
-	EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
+	if (stack_depth)
+		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
@@ -1441,8 +1454,6 @@ emit_jmp:
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
 			pop_callee_regs(&prog, callee_regs_used);
-			if (tail_call_reachable)
-				EMIT1(0x59); /* pop rcx, get rid of tail_call_cnt */
 			EMIT1(0xC9);         /* leave */
 			EMIT1(0xC3);         /* ret */
 			break;