[PATCH v2 bpf-next 08/20] bpf: Add x86-64 JIT support for bpf_cast_user instruction.

[Alexei Starovoitov <alexei.starovoitov@gmail.com>]

From: Alexei Starovoitov <ast@kernel.org>

LLVM generates bpf_cast_kern and bpf_cast_user instructions while translating
pointers with __attribute__((address_space(1))).

rX = cast_kern(rY) is processed by the verifier and converted to
normal 32-bit move: wX = wY

bpf_cast_user has to be converted by JIT.

rX = cast_user(rY) is

aux_reg = upper_32_bits of arena->user_vm_start
aux_reg <<= 32
wX = wY // clear upper 32 bits of dst register
if (wX) // if not zero add upper bits of user_vm_start
  wX |= aux_reg

JIT can do it more efficiently:

mov dst_reg32, src_reg32  // 32-bit move
shl dst_reg, 32
or dst_reg, user_vm_start
rol dst_reg, 32
xor r11, r11
test dst_reg32, dst_reg32 // check if lower 32-bit are zero
cmove r11, dst_reg	  // if so, set dst_reg to zero
			  // Intel swapped src/dst register encoding in CMOVcc

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 41 ++++++++++++++++++++++++++++++++++++-
 include/linux/filter.h      |  1 +
 kernel/bpf/core.c           |  5 +++++
 3 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 883b7f604b9a..a042ed57af7b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1272,13 +1272,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	bool tail_call_seen = false;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
-	u64 arena_vm_start;
+	u64 arena_vm_start, user_vm_start;
 	int i, excnt = 0;
 	int ilen, proglen = 0;
 	u8 *prog = temp;
 	int err;
 
 	arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
+	user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena);
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used,
 			 &tail_call_seen);
@@ -1346,6 +1347,39 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 			break;
 
 		case BPF_ALU64 | BPF_MOV | BPF_X:
+			if (insn->off == BPF_ARENA_CAST_USER) {
+				if (dst_reg != src_reg)
+					/* 32-bit mov */
+					emit_mov_reg(&prog, false, dst_reg, src_reg);
+				/* shl dst_reg, 32 */
+				maybe_emit_1mod(&prog, dst_reg, true);
+				EMIT3(0xC1, add_1reg(0xE0, dst_reg), 32);
+
+				/* or dst_reg, user_vm_start */
+				maybe_emit_1mod(&prog, dst_reg, true);
+				if (is_axreg(dst_reg))
+					EMIT1_off32(0x0D,  user_vm_start >> 32);
+				else
+					EMIT2_off32(0x81, add_1reg(0xC8, dst_reg),  user_vm_start >> 32);
+
+				/* rol dst_reg, 32 */
+				maybe_emit_1mod(&prog, dst_reg, true);
+				EMIT3(0xC1, add_1reg(0xC0, dst_reg), 32);
+
+				/* xor r11, r11 */
+				EMIT3(0x4D, 0x31, 0xDB);
+
+				/* test dst_reg32, dst_reg32; check if lower 32-bit are zero */
+				maybe_emit_mod(&prog, dst_reg, dst_reg, false);
+				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
+
+				/* cmove r11, dst_reg; if so, set dst_reg to zero */
+				/* WARNING: Intel swapped src/dst register encoding in CMOVcc !!! */
+				maybe_emit_mod(&prog, AUX_REG, dst_reg, true);
+				EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg));
+				break;
+			}
+			fallthrough;
 		case BPF_ALU | BPF_MOV | BPF_X:
 			if (insn->off == 0)
 				emit_mov_reg(&prog,
@@ -3424,6 +3458,11 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
 	}
 }
 
+bool bpf_jit_supports_arena(void)
+{
+	return true;
+}
+
 bool bpf_jit_supports_ptr_xchg(void)
 {
 	return true;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index cd76d43412d0..78ea63002531 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -959,6 +959,7 @@ bool bpf_jit_supports_kfunc_call(void);
 bool bpf_jit_supports_far_kfunc_call(void);
 bool bpf_jit_supports_exceptions(void);
 bool bpf_jit_supports_ptr_xchg(void);
+bool bpf_jit_supports_arena(void);
 void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
 bool bpf_helper_changes_pkt_data(void *func);
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2539d9bfe369..2829077f0461 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2926,6 +2926,11 @@ bool __weak bpf_jit_supports_far_kfunc_call(void)
 	return false;
 }
 
+bool __weak bpf_jit_supports_arena(void)
+{
+	return false;
+}
+
 /* Return TRUE if the JIT backend satisfies the following two conditions:
  * 1) JIT backend supports atomic_xchg() on pointer-sized words.
  * 2) Under the specific arch, the implementation of xchg() is the same
-- 
2.34.1