OpenCloudOS-Kernel/arch/powerpc/net/bpf_jit_comp32.c

1119 lines
33 KiB
C
Raw Normal View History

powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
// SPDX-License-Identifier: GPL-2.0-only
/*
* eBPF JIT compiler for PPC32
*
* Copyright 2020 Christophe Leroy <christophe.leroy@csgroup.eu>
* CS GROUP France
*
* Based on PPC64 eBPF JIT compiler by Naveen N. Rao
*/
#include <linux/moduleloader.h>
#include <asm/cacheflush.h>
#include <asm/asm-compat.h>
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <asm/kprobes.h>
#include <linux/bpf.h>
#include "bpf_jit.h"
/*
* Stack layout:
*
* [ prev sp ] <-------------
* [ nv gpr save area ] 16 * 4 |
* fp (r31) --> [ ebpf stack space ] upto 512 |
* [ frame header ] 16 |
* sp (r1) ---> [ stack pointer ] --------------
*/
/* for gpr non volatile registers r17 to r31 (14) + tail call */
#define BPF_PPC_STACK_SAVE (15 * 4 + 4)
/* stack frame, ensure this is quadword aligned */
#define BPF_PPC_STACKFRAME(ctx) (STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_SAVE + (ctx)->stack_size)
/* BPF register usage */
#define TMP_REG (MAX_BPF_JIT_REG + 0)
/* BPF to ppc register mappings */
powerpc/bpf: Reallocate BPF registers to volatile registers when possible on PPC32 When the BPF routine doesn't call any function, the non volatile registers can be reallocated to volatile registers in order to avoid having to save them/restore on the stack. Before this patch, the test #359 ADD default X is: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 92 e1 00 2c stw r23,44(r1) 14: 93 01 00 30 stw r24,48(r1) 18: 93 21 00 34 stw r25,52(r1) 1c: 93 41 00 38 stw r26,56(r1) 20: 39 80 00 00 li r12,0 24: 39 60 00 00 li r11,0 28: 3b 40 00 00 li r26,0 2c: 3b 20 00 00 li r25,0 30: 7c 98 23 78 mr r24,r4 34: 7c 77 1b 78 mr r23,r3 38: 39 80 00 42 li r12,66 3c: 39 60 00 00 li r11,0 40: 7d 8c d2 14 add r12,r12,r26 44: 39 60 00 00 li r11,0 48: 7d 83 63 78 mr r3,r12 4c: 82 e1 00 2c lwz r23,44(r1) 50: 83 01 00 30 lwz r24,48(r1) 54: 83 21 00 34 lwz r25,52(r1) 58: 83 41 00 38 lwz r26,56(r1) 5c: 38 21 00 50 addi r1,r1,80 60: 4e 80 00 20 blr After this patch, the same test has become: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 39 80 00 00 li r12,0 14: 39 60 00 00 li r11,0 18: 39 00 00 00 li r8,0 1c: 38 e0 00 00 li r7,0 20: 7c 86 23 78 mr r6,r4 24: 7c 65 1b 78 mr r5,r3 28: 39 80 00 42 li r12,66 2c: 39 60 00 00 li r11,0 30: 7d 8c 42 14 add r12,r12,r8 34: 39 60 00 00 li r11,0 38: 7d 83 63 78 mr r3,r12 3c: 38 21 00 50 addi r1,r1,80 40: 4e 80 00 20 blr Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/b94562d7d2bb21aec89de0c40bb3cd91054b65a2.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:53 +08:00
const int b2p[MAX_BPF_JIT_REG + 1] = {
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* function return value */
[BPF_REG_0] = 12,
/* function arguments */
[BPF_REG_1] = 4,
[BPF_REG_2] = 6,
[BPF_REG_3] = 8,
[BPF_REG_4] = 10,
[BPF_REG_5] = 22,
/* non volatile registers */
[BPF_REG_6] = 24,
[BPF_REG_7] = 26,
[BPF_REG_8] = 28,
[BPF_REG_9] = 30,
/* frame pointer aka BPF_REG_10 */
[BPF_REG_FP] = 18,
/* eBPF jit internal registers */
[BPF_REG_AX] = 20,
[TMP_REG] = 31, /* 32 bits */
};
static int bpf_to_ppc(struct codegen_context *ctx, int reg)
{
powerpc/bpf: Reallocate BPF registers to volatile registers when possible on PPC32 When the BPF routine doesn't call any function, the non volatile registers can be reallocated to volatile registers in order to avoid having to save them/restore on the stack. Before this patch, the test #359 ADD default X is: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 92 e1 00 2c stw r23,44(r1) 14: 93 01 00 30 stw r24,48(r1) 18: 93 21 00 34 stw r25,52(r1) 1c: 93 41 00 38 stw r26,56(r1) 20: 39 80 00 00 li r12,0 24: 39 60 00 00 li r11,0 28: 3b 40 00 00 li r26,0 2c: 3b 20 00 00 li r25,0 30: 7c 98 23 78 mr r24,r4 34: 7c 77 1b 78 mr r23,r3 38: 39 80 00 42 li r12,66 3c: 39 60 00 00 li r11,0 40: 7d 8c d2 14 add r12,r12,r26 44: 39 60 00 00 li r11,0 48: 7d 83 63 78 mr r3,r12 4c: 82 e1 00 2c lwz r23,44(r1) 50: 83 01 00 30 lwz r24,48(r1) 54: 83 21 00 34 lwz r25,52(r1) 58: 83 41 00 38 lwz r26,56(r1) 5c: 38 21 00 50 addi r1,r1,80 60: 4e 80 00 20 blr After this patch, the same test has become: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 39 80 00 00 li r12,0 14: 39 60 00 00 li r11,0 18: 39 00 00 00 li r8,0 1c: 38 e0 00 00 li r7,0 20: 7c 86 23 78 mr r6,r4 24: 7c 65 1b 78 mr r5,r3 28: 39 80 00 42 li r12,66 2c: 39 60 00 00 li r11,0 30: 7d 8c 42 14 add r12,r12,r8 34: 39 60 00 00 li r11,0 38: 7d 83 63 78 mr r3,r12 3c: 38 21 00 50 addi r1,r1,80 40: 4e 80 00 20 blr Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/b94562d7d2bb21aec89de0c40bb3cd91054b65a2.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:53 +08:00
return ctx->b2p[reg];
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
/* PPC NVR range -- update this if we ever use NVRs below r17 */
#define BPF_PPC_NVR_MIN 17
#define BPF_PPC_TC 16
static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
{
if ((reg >= BPF_PPC_NVR_MIN && reg < 32) || reg == BPF_PPC_TC)
return BPF_PPC_STACKFRAME(ctx) - 4 * (32 - reg);
WARN(true, "BPF JIT is asking about unknown registers, will crash the stack");
/* Use the hole we have left for alignment */
return BPF_PPC_STACKFRAME(ctx) - 4;
}
powerpc/bpf: Reallocate BPF registers to volatile registers when possible on PPC32 When the BPF routine doesn't call any function, the non volatile registers can be reallocated to volatile registers in order to avoid having to save them/restore on the stack. Before this patch, the test #359 ADD default X is: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 92 e1 00 2c stw r23,44(r1) 14: 93 01 00 30 stw r24,48(r1) 18: 93 21 00 34 stw r25,52(r1) 1c: 93 41 00 38 stw r26,56(r1) 20: 39 80 00 00 li r12,0 24: 39 60 00 00 li r11,0 28: 3b 40 00 00 li r26,0 2c: 3b 20 00 00 li r25,0 30: 7c 98 23 78 mr r24,r4 34: 7c 77 1b 78 mr r23,r3 38: 39 80 00 42 li r12,66 3c: 39 60 00 00 li r11,0 40: 7d 8c d2 14 add r12,r12,r26 44: 39 60 00 00 li r11,0 48: 7d 83 63 78 mr r3,r12 4c: 82 e1 00 2c lwz r23,44(r1) 50: 83 01 00 30 lwz r24,48(r1) 54: 83 21 00 34 lwz r25,52(r1) 58: 83 41 00 38 lwz r26,56(r1) 5c: 38 21 00 50 addi r1,r1,80 60: 4e 80 00 20 blr After this patch, the same test has become: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 39 80 00 00 li r12,0 14: 39 60 00 00 li r11,0 18: 39 00 00 00 li r8,0 1c: 38 e0 00 00 li r7,0 20: 7c 86 23 78 mr r6,r4 24: 7c 65 1b 78 mr r5,r3 28: 39 80 00 42 li r12,66 2c: 39 60 00 00 li r11,0 30: 7d 8c 42 14 add r12,r12,r8 34: 39 60 00 00 li r11,0 38: 7d 83 63 78 mr r3,r12 3c: 38 21 00 50 addi r1,r1,80 40: 4e 80 00 20 blr Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/b94562d7d2bb21aec89de0c40bb3cd91054b65a2.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:53 +08:00
void bpf_jit_realloc_regs(struct codegen_context *ctx)
{
if (ctx->seen & SEEN_FUNC)
return;
while (ctx->seen & SEEN_NVREG_MASK &&
(ctx->seen & SEEN_VREG_MASK) != SEEN_VREG_MASK) {
int old = 32 - fls(ctx->seen & (SEEN_NVREG_MASK & 0xaaaaaaab));
int new = 32 - fls(~ctx->seen & (SEEN_VREG_MASK & 0xaaaaaaaa));
int i;
for (i = BPF_REG_0; i <= TMP_REG; i++) {
if (ctx->b2p[i] != old)
continue;
ctx->b2p[i] = new;
bpf_set_seen_register(ctx, new);
bpf_clear_seen_register(ctx, old);
if (i != TMP_REG) {
bpf_set_seen_register(ctx, new - 1);
bpf_clear_seen_register(ctx, old - 1);
}
break;
}
}
}
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
{
int i;
/* First arg comes in as a 32 bits pointer. */
EMIT(PPC_RAW_MR(bpf_to_ppc(ctx, BPF_REG_1), _R3));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_LI(bpf_to_ppc(ctx, BPF_REG_1) - 1, 0));
EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/*
* Initialize tail_call_cnt in stack frame if we do tail calls.
* Otherwise, put in NOPs so that it can be skipped when we are
* invoked through a tail call.
*/
if (ctx->seen & SEEN_TAILCALL)
EMIT(PPC_RAW_STW(bpf_to_ppc(ctx, BPF_REG_1) - 1, _R1,
bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
else
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_NOP());
#define BPF_TAILCALL_PROLOGUE_SIZE 16
/*
* We need a stack frame, but we don't necessarily need to
* save/restore LR unless we call other functions
*/
if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_MFLR(_R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/*
* Back up non-volatile regs -- registers r18-r31
*/
for (i = BPF_PPC_NVR_MIN; i <= 31; i++)
if (bpf_is_seen_register(ctx, i))
EMIT(PPC_RAW_STW(i, _R1, bpf_jit_stack_offsetof(ctx, i)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* If needed retrieve arguments 9 and 10, ie 5th 64 bits arg.*/
if (bpf_is_seen_register(ctx, bpf_to_ppc(ctx, BPF_REG_5))) {
EMIT(PPC_RAW_LWZ(bpf_to_ppc(ctx, BPF_REG_5) - 1, _R1, BPF_PPC_STACKFRAME(ctx)) + 8);
EMIT(PPC_RAW_LWZ(bpf_to_ppc(ctx, BPF_REG_5), _R1, BPF_PPC_STACKFRAME(ctx)) + 12);
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
/* Setup frame pointer to point to the bpf stack area */
if (bpf_is_seen_register(ctx, bpf_to_ppc(ctx, BPF_REG_FP))) {
EMIT(PPC_RAW_LI(bpf_to_ppc(ctx, BPF_REG_FP) - 1, 0));
EMIT(PPC_RAW_ADDI(bpf_to_ppc(ctx, BPF_REG_FP), _R1,
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
STACK_FRAME_MIN_SIZE + ctx->stack_size));
}
if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_STW(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx)
{
int i;
/* Restore NVRs */
for (i = BPF_PPC_NVR_MIN; i <= 31; i++)
if (bpf_is_seen_register(ctx, i))
EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, i)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
{
EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(ctx, BPF_REG_0)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
bpf_jit_emit_common_epilogue(image, ctx);
/* Tear down our stack frame */
if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_MTLR(_R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_BLR());
}
void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func)
{
s32 rel = (s32)func - (s32)(image + ctx->idx);
if (image && rel < 0x2000000 && rel >= -0x2000000) {
PPC_BL_ABS(func);
} else {
/* Load function address into r0 */
EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));
EMIT(PPC_RAW_ORI(_R0, _R0, IMM_L(func)));
EMIT(PPC_RAW_MTCTR(_R0));
EMIT(PPC_RAW_BCTRL());
}
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
{
/*
* By now, the eBPF program has already setup parameters in r3-r6
* r3-r4/BPF_REG_1 - pointer to ctx -- passed as is to the next bpf program
* r5-r6/BPF_REG_2 - pointer to bpf_array
* r7-r8/BPF_REG_3 - index in bpf_array
*/
int b2p_bpf_array = bpf_to_ppc(ctx, BPF_REG_2);
int b2p_index = bpf_to_ppc(ctx, BPF_REG_3);
/*
* if (index >= array->map.max_entries)
* goto out;
*/
EMIT(PPC_RAW_LWZ(_R0, b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)));
EMIT(PPC_RAW_CMPLW(b2p_index, _R0));
EMIT(PPC_RAW_LWZ(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
PPC_BCC(COND_GE, out);
/*
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
*/
EMIT(PPC_RAW_CMPLWI(_R0, MAX_TAIL_CALL_CNT));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* tail_call_cnt++; */
EMIT(PPC_RAW_ADDIC(_R0, _R0, 1));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
PPC_BCC(COND_GT, out);
/* prog = array->ptrs[index]; */
EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29));
EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array));
EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs)));
EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/*
* if (prog == NULL)
* goto out;
*/
EMIT(PPC_RAW_CMPLWI(_R3, 0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
PPC_BCC(COND_EQ, out);
/* goto *(prog->bpf_func + prologue_size); */
EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_ADDIC(_R3, _R3, BPF_TAILCALL_PROLOGUE_SIZE));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_MTLR(_R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_MTCTR(_R3));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(ctx, BPF_REG_1)));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* tear restore NVRs, ... */
bpf_jit_emit_common_epilogue(image, ctx);
EMIT(PPC_RAW_BCTR());
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* out: */
return 0;
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
/* Assemble the body code between the prologue & epilogue */
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
u32 *addrs, bool extra_pass)
{
const struct bpf_insn *insn = fp->insnsi;
int flen = fp->len;
int i, ret;
/* Start of epilogue code - will only be valid 2nd pass onwards */
u32 exit_addr = addrs[flen];
for (i = 0; i < flen; i++) {
u32 code = insn[i].code;
u32 dst_reg = bpf_to_ppc(ctx, insn[i].dst_reg);
u32 dst_reg_h = dst_reg - 1;
u32 src_reg = bpf_to_ppc(ctx, insn[i].src_reg);
u32 src_reg_h = src_reg - 1;
u32 tmp_reg = bpf_to_ppc(ctx, TMP_REG);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
u64 func_addr;
u32 true_cond;
/*
* addrs[] maps a BPF bytecode address into a real offset from
* the start of the body code.
*/
addrs[i] = ctx->idx * 4;
/*
* As an optimization, we note down which registers
* are used so that we can only save/restore those in our
* prologue and epilogue. We do this here regardless of whether
* the actual BPF instruction uses src/dst registers or not
* (for instance, BPF_CALL does not use them). The expectation
* is that those instructions will have src_reg/dst_reg set to
* 0. Even otherwise, we just lose some prologue/epilogue
* optimization but everything else should work without
* any issues.
*/
if (dst_reg >= 3 && dst_reg < 32) {
bpf_set_seen_register(ctx, dst_reg);
bpf_set_seen_register(ctx, dst_reg_h);
}
if (src_reg >= 3 && src_reg < 32) {
bpf_set_seen_register(ctx, src_reg);
bpf_set_seen_register(ctx, src_reg_h);
}
switch (code) {
/*
* Arithmetic operations: ADD/SUB/MUL/DIV/MOD/NEG
*/
case BPF_ALU | BPF_ADD | BPF_X: /* (u32) dst += (u32) src */
EMIT(PPC_RAW_ADD(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_ADD | BPF_X: /* dst += src */
EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_ADDE(dst_reg_h, dst_reg_h, src_reg_h));
break;
case BPF_ALU | BPF_SUB | BPF_X: /* (u32) dst -= (u32) src */
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_SUB | BPF_X: /* dst -= src */
EMIT(PPC_RAW_SUBFC(dst_reg, src_reg, dst_reg));
EMIT(PPC_RAW_SUBFE(dst_reg_h, src_reg_h, dst_reg_h));
break;
case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
imm = -imm;
fallthrough;
case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
if (IMM_HA(imm) & 0xffff)
EMIT(PPC_RAW_ADDIS(dst_reg, dst_reg, IMM_HA(imm)));
if (IMM_L(imm))
EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm)));
break;
case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */
imm = -imm;
fallthrough;
case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */
if (!imm)
break;
if (imm >= -32768 && imm < 32768) {
EMIT(PPC_RAW_ADDIC(dst_reg, dst_reg, imm));
} else {
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
if (imm >= 0)
EMIT(PPC_RAW_ADDZE(dst_reg_h, dst_reg_h));
else
EMIT(PPC_RAW_ADDME(dst_reg_h, dst_reg_h));
break;
case BPF_ALU64 | BPF_MUL | BPF_X: /* dst *= src */
bpf_set_seen_register(ctx, tmp_reg);
EMIT(PPC_RAW_MULW(_R0, dst_reg, src_reg_h));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_MULW(dst_reg_h, dst_reg_h, src_reg));
EMIT(PPC_RAW_MULHWU(tmp_reg, dst_reg, src_reg));
EMIT(PPC_RAW_MULW(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_ADD(dst_reg_h, dst_reg_h, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_ADD(dst_reg_h, dst_reg_h, tmp_reg));
break;
case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */
EMIT(PPC_RAW_MULW(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU | BPF_MUL | BPF_K: /* (u32) dst *= (u32) imm */
if (imm >= -32768 && imm < 32768) {
EMIT(PPC_RAW_MULI(dst_reg, dst_reg, imm));
} else {
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_MULW(dst_reg, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
case BPF_ALU64 | BPF_MUL | BPF_K: /* dst *= imm */
if (!imm) {
PPC_LI32(dst_reg, 0);
PPC_LI32(dst_reg_h, 0);
break;
}
if (imm == 1)
break;
if (imm == -1) {
EMIT(PPC_RAW_SUBFIC(dst_reg, dst_reg, 0));
EMIT(PPC_RAW_SUBFZE(dst_reg_h, dst_reg_h));
break;
}
bpf_set_seen_register(ctx, tmp_reg);
PPC_LI32(tmp_reg, imm);
EMIT(PPC_RAW_MULW(dst_reg_h, dst_reg_h, tmp_reg));
if (imm < 0)
EMIT(PPC_RAW_SUB(dst_reg_h, dst_reg_h, dst_reg));
EMIT(PPC_RAW_MULHWU(_R0, dst_reg, tmp_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_MULW(dst_reg, dst_reg, tmp_reg));
EMIT(PPC_RAW_ADD(dst_reg_h, dst_reg_h, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
EMIT(PPC_RAW_DIVWU(_R0, dst_reg, src_reg));
EMIT(PPC_RAW_MULW(_R0, src_reg, _R0));
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
return -EOPNOTSUPP;
case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
return -EOPNOTSUPP;
case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
if (!imm)
return -EINVAL;
if (imm == 1)
break;
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
if (!imm)
return -EINVAL;
if (!is_power_of_2((u32)imm)) {
bpf_set_seen_register(ctx, tmp_reg);
PPC_LI32(tmp_reg, imm);
EMIT(PPC_RAW_DIVWU(_R0, dst_reg, tmp_reg));
EMIT(PPC_RAW_MULW(_R0, tmp_reg, _R0));
EMIT(PPC_RAW_SUB(dst_reg, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
}
if (imm == 1)
EMIT(PPC_RAW_LI(dst_reg, 0));
else
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 32 - ilog2((u32)imm), 31));
break;
case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */
if (!imm)
return -EINVAL;
if (imm < 0)
imm = -imm;
if (!is_power_of_2(imm))
return -EOPNOTSUPP;
if (imm == 1)
EMIT(PPC_RAW_LI(dst_reg, 0));
else
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 32 - ilog2(imm), 31));
EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
if (!imm)
return -EINVAL;
if (!is_power_of_2(abs(imm)))
return -EOPNOTSUPP;
if (imm < 0) {
EMIT(PPC_RAW_SUBFIC(dst_reg, dst_reg, 0));
EMIT(PPC_RAW_SUBFZE(dst_reg_h, dst_reg_h));
imm = -imm;
}
if (imm == 1)
break;
imm = ilog2(imm);
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 32 - imm, imm, 31));
EMIT(PPC_RAW_RLWIMI(dst_reg, dst_reg_h, 32 - imm, 0, imm - 1));
EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg_h, imm));
break;
case BPF_ALU | BPF_NEG: /* (u32) dst = -dst */
EMIT(PPC_RAW_NEG(dst_reg, dst_reg));
break;
case BPF_ALU64 | BPF_NEG: /* dst = -dst */
EMIT(PPC_RAW_SUBFIC(dst_reg, dst_reg, 0));
EMIT(PPC_RAW_SUBFZE(dst_reg_h, dst_reg_h));
break;
/*
* Logical operations: AND/OR/XOR/[A]LSH/[A]RSH
*/
case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */
EMIT(PPC_RAW_AND(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_AND(dst_reg_h, dst_reg_h, src_reg_h));
break;
case BPF_ALU | BPF_AND | BPF_X: /* (u32) dst = dst & src */
EMIT(PPC_RAW_AND(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
if (imm >= 0)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
fallthrough;
case BPF_ALU | BPF_AND | BPF_K: /* (u32) dst = dst & imm */
if (!IMM_H(imm)) {
EMIT(PPC_RAW_ANDI(dst_reg, dst_reg, IMM_L(imm)));
} else if (!IMM_L(imm)) {
EMIT(PPC_RAW_ANDIS(dst_reg, dst_reg, IMM_H(imm)));
} else if (imm == (((1 << fls(imm)) - 1) ^ ((1 << (ffs(i) - 1)) - 1))) {
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0,
32 - fls(imm), 32 - ffs(imm)));
} else {
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_AND(dst_reg, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */
EMIT(PPC_RAW_OR(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_OR(dst_reg_h, dst_reg_h, src_reg_h));
break;
case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */
EMIT(PPC_RAW_OR(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_OR | BPF_K:/* dst = dst | imm */
/* Sign-extended */
if (imm < 0)
EMIT(PPC_RAW_LI(dst_reg_h, -1));
fallthrough;
case BPF_ALU | BPF_OR | BPF_K:/* dst = (u32) dst | (u32) imm */
if (IMM_L(imm))
EMIT(PPC_RAW_ORI(dst_reg, dst_reg, IMM_L(imm)));
if (IMM_H(imm))
EMIT(PPC_RAW_ORIS(dst_reg, dst_reg, IMM_H(imm)));
break;
case BPF_ALU64 | BPF_XOR | BPF_X: /* dst ^= src */
if (dst_reg == src_reg) {
EMIT(PPC_RAW_LI(dst_reg, 0));
EMIT(PPC_RAW_LI(dst_reg_h, 0));
} else {
EMIT(PPC_RAW_XOR(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_XOR(dst_reg_h, dst_reg_h, src_reg_h));
}
break;
case BPF_ALU | BPF_XOR | BPF_X: /* (u32) dst ^= src */
if (dst_reg == src_reg)
EMIT(PPC_RAW_LI(dst_reg, 0));
else
EMIT(PPC_RAW_XOR(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_XOR | BPF_K: /* dst ^= imm */
if (imm < 0)
EMIT(PPC_RAW_NOR(dst_reg_h, dst_reg_h, dst_reg_h));
fallthrough;
case BPF_ALU | BPF_XOR | BPF_K: /* (u32) dst ^= (u32) imm */
if (IMM_L(imm))
EMIT(PPC_RAW_XORI(dst_reg, dst_reg, IMM_L(imm)));
if (IMM_H(imm))
EMIT(PPC_RAW_XORIS(dst_reg, dst_reg, IMM_H(imm)));
break;
case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
bpf_set_seen_register(ctx, tmp_reg);
EMIT(PPC_RAW_SUBFIC(_R0, src_reg, 32));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_SLW(dst_reg_h, dst_reg_h, src_reg));
EMIT(PPC_RAW_ADDI(tmp_reg, src_reg, 32));
EMIT(PPC_RAW_SRW(_R0, dst_reg, _R0));
EMIT(PPC_RAW_SLW(tmp_reg, dst_reg, tmp_reg));
EMIT(PPC_RAW_OR(dst_reg_h, dst_reg_h, _R0));
EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_OR(dst_reg_h, dst_reg_h, tmp_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<= (u32) imm */
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
if (!imm)
break;
EMIT(PPC_RAW_SLWI(dst_reg, dst_reg, imm));
break;
case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<= imm */
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
if (imm < 0)
return -EINVAL;
if (!imm)
break;
if (imm < 32) {
EMIT(PPC_RAW_RLWINM(dst_reg_h, dst_reg_h, imm, 0, 31 - imm));
EMIT(PPC_RAW_RLWIMI(dst_reg_h, dst_reg, imm, 32 - imm, 31));
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, imm, 0, 31 - imm));
break;
}
if (imm < 64)
EMIT(PPC_RAW_RLWINM(dst_reg_h, dst_reg, imm, 0, 31 - imm));
else
EMIT(PPC_RAW_LI(dst_reg_h, 0));
EMIT(PPC_RAW_LI(dst_reg, 0));
break;
case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
bpf_set_seen_register(ctx, tmp_reg);
EMIT(PPC_RAW_SUBFIC(_R0, src_reg, 32));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_ADDI(tmp_reg, src_reg, 32));
EMIT(PPC_RAW_SLW(_R0, dst_reg_h, _R0));
EMIT(PPC_RAW_SRW(tmp_reg, dst_reg_h, tmp_reg));
EMIT(PPC_RAW_OR(dst_reg, dst_reg, _R0));
EMIT(PPC_RAW_SRW(dst_reg_h, dst_reg_h, src_reg));
EMIT(PPC_RAW_OR(dst_reg, dst_reg, tmp_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
if (!imm)
break;
EMIT(PPC_RAW_SRWI(dst_reg, dst_reg, imm));
break;
case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
if (imm < 0)
return -EINVAL;
if (!imm)
break;
if (imm < 32) {
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 32 - imm, imm, 31));
EMIT(PPC_RAW_RLWIMI(dst_reg, dst_reg_h, 32 - imm, 0, imm - 1));
EMIT(PPC_RAW_RLWINM(dst_reg_h, dst_reg_h, 32 - imm, imm, 31));
break;
}
if (imm < 64)
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg_h, 64 - imm, imm - 32, 31));
else
EMIT(PPC_RAW_LI(dst_reg, 0));
EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
bpf_set_seen_register(ctx, tmp_reg);
EMIT(PPC_RAW_SUBFIC(_R0, src_reg, 32));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
EMIT(PPC_RAW_SLW(_R0, dst_reg_h, _R0));
EMIT(PPC_RAW_ADDI(tmp_reg, src_reg, 32));
EMIT(PPC_RAW_OR(dst_reg, dst_reg, _R0));
EMIT(PPC_RAW_RLWINM(_R0, tmp_reg, 0, 26, 26));
EMIT(PPC_RAW_SRAW(tmp_reg, dst_reg_h, tmp_reg));
EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg_h, src_reg));
EMIT(PPC_RAW_SLW(tmp_reg, tmp_reg, _R0));
EMIT(PPC_RAW_OR(dst_reg, dst_reg, tmp_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
if (!imm)
break;
EMIT(PPC_RAW_SRAWI(dst_reg, dst_reg, imm));
break;
case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
if (imm < 0)
return -EINVAL;
if (!imm)
break;
if (imm < 32) {
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 32 - imm, imm, 31));
EMIT(PPC_RAW_RLWIMI(dst_reg, dst_reg_h, 32 - imm, 0, imm - 1));
EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg_h, imm));
break;
}
if (imm < 64)
EMIT(PPC_RAW_SRAWI(dst_reg, dst_reg_h, imm - 32));
else
EMIT(PPC_RAW_SRAWI(dst_reg, dst_reg_h, 31));
EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg_h, 31));
break;
/*
* MOV
*/
case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
if (dst_reg == src_reg)
break;
EMIT(PPC_RAW_MR(dst_reg, src_reg));
EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h));
break;
case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
/* special mov32 for zext */
if (imm == 1)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
else if (dst_reg != src_reg)
EMIT(PPC_RAW_MR(dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
PPC_LI32(dst_reg, imm);
PPC_EX32(dst_reg_h, imm);
break;
case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
PPC_LI32(dst_reg, imm);
break;
/*
* BPF_FROM_BE/LE
*/
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm) {
case 16:
/* Copy 16 bits to upper part */
EMIT(PPC_RAW_RLWIMI(dst_reg, dst_reg, 16, 0, 15));
/* Rotate 8 bits right & mask */
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 24, 16, 31));
break;
case 32:
/*
* Rotate word left by 8 bits:
* 2 bytes are already in their final position
* -- byte 2 and 4 (of bytes 1, 2, 3 and 4)
*/
EMIT(PPC_RAW_RLWINM(_R0, dst_reg, 8, 0, 31));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* Rotate 24 bits and insert byte 1 */
EMIT(PPC_RAW_RLWIMI(_R0, dst_reg, 24, 0, 7));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* Rotate 24 bits and insert byte 3 */
EMIT(PPC_RAW_RLWIMI(_R0, dst_reg, 24, 16, 23));
EMIT(PPC_RAW_MR(dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case 64:
bpf_set_seen_register(ctx, tmp_reg);
EMIT(PPC_RAW_RLWINM(tmp_reg, dst_reg, 8, 0, 31));
EMIT(PPC_RAW_RLWINM(_R0, dst_reg_h, 8, 0, 31));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* Rotate 24 bits and insert byte 1 */
EMIT(PPC_RAW_RLWIMI(tmp_reg, dst_reg, 24, 0, 7));
EMIT(PPC_RAW_RLWIMI(_R0, dst_reg_h, 24, 0, 7));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* Rotate 24 bits and insert byte 3 */
EMIT(PPC_RAW_RLWIMI(tmp_reg, dst_reg, 24, 16, 23));
EMIT(PPC_RAW_RLWIMI(_R0, dst_reg_h, 24, 16, 23));
EMIT(PPC_RAW_MR(dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
EMIT(PPC_RAW_MR(dst_reg_h, tmp_reg));
break;
}
break;
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm) {
case 16:
/* zero-extend 16 bits into 32 bits */
EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 16, 31));
break;
case 32:
case 64:
/* nop */
break;
}
break;
/*
* BPF_ST NOSPEC (speculation barrier)
*/
case BPF_ST | BPF_NOSPEC:
break;
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
EMIT(PPC_RAW_STB(src_reg, dst_reg, off));
break;
case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_STB(_R0, dst_reg, off));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */
EMIT(PPC_RAW_STH(src_reg, dst_reg, off));
break;
case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_STH(_R0, dst_reg, off));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */
EMIT(PPC_RAW_STW(src_reg, dst_reg, off));
break;
case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_STW(_R0, dst_reg, off));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */
EMIT(PPC_RAW_STW(src_reg_h, dst_reg, off));
EMIT(PPC_RAW_STW(src_reg, dst_reg, off + 4));
break;
case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_STW(_R0, dst_reg, off + 4));
PPC_EX32(_R0, imm);
EMIT(PPC_RAW_STW(_R0, dst_reg, off));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
/*
* BPF_STX ATOMIC (atomic ops)
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
*/
case BPF_STX | BPF_ATOMIC | BPF_W:
if (imm != BPF_ADD) {
pr_err_ratelimited("eBPF filter atomic op code %02x (@%d) unsupported\n",
code, i);
return -ENOTSUPP;
}
/* *(u32 *)(dst + off) += src */
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
bpf_set_seen_register(ctx, tmp_reg);
/* Get offset into TMP_REG */
EMIT(PPC_RAW_LI(tmp_reg, off));
/* load value from memory into r0 */
EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* add value from src_reg into this */
EMIT(PPC_RAW_ADD(_R0, _R0, src_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* store result back */
EMIT(PPC_RAW_STWCX(_R0, tmp_reg, dst_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
/* we're done if this succeeded */
PPC_BCC_SHORT(COND_NE, (ctx->idx - 3) * 4);
break;
case BPF_STX | BPF_ATOMIC | BPF_DW: /* *(u64 *)(dst + off) += src */
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
return -EOPNOTSUPP;
/*
* BPF_LDX
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
if (!fp->aux->verifier_zext)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
if (!fp->aux->verifier_zext)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
if (!fp->aux->verifier_zext)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
break;
/*
* Doubleword load
* 16 byte instruction that uses two 'struct bpf_insn'
*/
case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
PPC_LI32(dst_reg, (u32)insn[i].imm);
/* Adjust for two bpf instructions */
addrs[++i] = ctx->idx * 4;
break;
/*
* Return/Exit
*/
case BPF_JMP | BPF_EXIT:
/*
* If this isn't the very last instruction, branch to
* the epilogue. If we _are_ the last instruction,
* we'll just fall through to the epilogue.
*/
if (i != flen - 1)
PPC_JMP(exit_addr);
/* else fall through to the epilogue */
break;
/*
* Call kernel helper or bpf function
*/
case BPF_JMP | BPF_CALL:
ctx->seen |= SEEN_FUNC;
ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
&func_addr, &func_addr_fixed);
if (ret < 0)
return ret;
if (bpf_is_seen_register(ctx, bpf_to_ppc(ctx, BPF_REG_5))) {
EMIT(PPC_RAW_STW(bpf_to_ppc(ctx, BPF_REG_5) - 1, _R1, 8));
EMIT(PPC_RAW_STW(bpf_to_ppc(ctx, BPF_REG_5), _R1, 12));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
bpf_jit_emit_func_call_rel(image, ctx, func_addr);
EMIT(PPC_RAW_MR(bpf_to_ppc(ctx, BPF_REG_0) - 1, _R3));
EMIT(PPC_RAW_MR(bpf_to_ppc(ctx, BPF_REG_0), _R4));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
/*
* Jumps and branches
*/
case BPF_JMP | BPF_JA:
PPC_JMP(addrs[i + 1 + off]);
break;
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JSGT | BPF_K:
case BPF_JMP | BPF_JSGT | BPF_X:
case BPF_JMP32 | BPF_JGT | BPF_K:
case BPF_JMP32 | BPF_JGT | BPF_X:
case BPF_JMP32 | BPF_JSGT | BPF_K:
case BPF_JMP32 | BPF_JSGT | BPF_X:
true_cond = COND_GT;
goto cond_branch;
case BPF_JMP | BPF_JLT | BPF_K:
case BPF_JMP | BPF_JLT | BPF_X:
case BPF_JMP | BPF_JSLT | BPF_K:
case BPF_JMP | BPF_JSLT | BPF_X:
case BPF_JMP32 | BPF_JLT | BPF_K:
case BPF_JMP32 | BPF_JLT | BPF_X:
case BPF_JMP32 | BPF_JSLT | BPF_K:
case BPF_JMP32 | BPF_JSLT | BPF_X:
true_cond = COND_LT;
goto cond_branch;
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_X:
case BPF_JMP32 | BPF_JGE | BPF_K:
case BPF_JMP32 | BPF_JGE | BPF_X:
case BPF_JMP32 | BPF_JSGE | BPF_K:
case BPF_JMP32 | BPF_JSGE | BPF_X:
true_cond = COND_GE;
goto cond_branch;
case BPF_JMP | BPF_JLE | BPF_K:
case BPF_JMP | BPF_JLE | BPF_X:
case BPF_JMP | BPF_JSLE | BPF_K:
case BPF_JMP | BPF_JSLE | BPF_X:
case BPF_JMP32 | BPF_JLE | BPF_K:
case BPF_JMP32 | BPF_JLE | BPF_X:
case BPF_JMP32 | BPF_JSLE | BPF_K:
case BPF_JMP32 | BPF_JSLE | BPF_X:
true_cond = COND_LE;
goto cond_branch;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP32 | BPF_JEQ | BPF_K:
case BPF_JMP32 | BPF_JEQ | BPF_X:
true_cond = COND_EQ;
goto cond_branch;
case BPF_JMP | BPF_JNE | BPF_K:
case BPF_JMP | BPF_JNE | BPF_X:
case BPF_JMP32 | BPF_JNE | BPF_K:
case BPF_JMP32 | BPF_JNE | BPF_X:
true_cond = COND_NE;
goto cond_branch;
case BPF_JMP | BPF_JSET | BPF_K:
case BPF_JMP | BPF_JSET | BPF_X:
case BPF_JMP32 | BPF_JSET | BPF_K:
case BPF_JMP32 | BPF_JSET | BPF_X:
true_cond = COND_NE;
/* fallthrough; */
cond_branch:
switch (code) {
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JLT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JLE | BPF_X:
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP | BPF_JNE | BPF_X:
/* unsigned comparison */
EMIT(PPC_RAW_CMPLW(dst_reg_h, src_reg_h));
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_CMPLW(dst_reg, src_reg));
break;
case BPF_JMP32 | BPF_JGT | BPF_X:
case BPF_JMP32 | BPF_JLT | BPF_X:
case BPF_JMP32 | BPF_JGE | BPF_X:
case BPF_JMP32 | BPF_JLE | BPF_X:
case BPF_JMP32 | BPF_JEQ | BPF_X:
case BPF_JMP32 | BPF_JNE | BPF_X:
/* unsigned comparison */
EMIT(PPC_RAW_CMPLW(dst_reg, src_reg));
break;
case BPF_JMP | BPF_JSGT | BPF_X:
case BPF_JMP | BPF_JSLT | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_X:
case BPF_JMP | BPF_JSLE | BPF_X:
/* signed comparison */
EMIT(PPC_RAW_CMPW(dst_reg_h, src_reg_h));
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_CMPLW(dst_reg, src_reg));
break;
case BPF_JMP32 | BPF_JSGT | BPF_X:
case BPF_JMP32 | BPF_JSLT | BPF_X:
case BPF_JMP32 | BPF_JSGE | BPF_X:
case BPF_JMP32 | BPF_JSLE | BPF_X:
/* signed comparison */
EMIT(PPC_RAW_CMPW(dst_reg, src_reg));
break;
case BPF_JMP | BPF_JSET | BPF_X:
EMIT(PPC_RAW_AND_DOT(_R0, dst_reg_h, src_reg_h));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_AND_DOT(_R0, dst_reg, src_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_JMP32 | BPF_JSET | BPF_X: {
EMIT(PPC_RAW_AND_DOT(_R0, dst_reg, src_reg));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
case BPF_JMP | BPF_JNE | BPF_K:
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JLT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JLE | BPF_K:
/*
* Need sign-extended load, so only positive
* values can be used as imm in cmplwi
*/
if (imm >= 0 && imm < 32768) {
EMIT(PPC_RAW_CMPLWI(dst_reg_h, 0));
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_CMPLWI(dst_reg, imm));
} else {
/* sign-extending load ... but unsigned comparison */
PPC_EX32(_R0, imm);
EMIT(PPC_RAW_CMPLW(dst_reg_h, _R0));
PPC_LI32(_R0, imm);
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_CMPLW(dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
case BPF_JMP32 | BPF_JNE | BPF_K:
case BPF_JMP32 | BPF_JEQ | BPF_K:
case BPF_JMP32 | BPF_JGT | BPF_K:
case BPF_JMP32 | BPF_JLT | BPF_K:
case BPF_JMP32 | BPF_JGE | BPF_K:
case BPF_JMP32 | BPF_JLE | BPF_K:
if (imm >= 0 && imm < 65536) {
EMIT(PPC_RAW_CMPLWI(dst_reg, imm));
} else {
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_CMPLW(dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
}
case BPF_JMP | BPF_JSGT | BPF_K:
case BPF_JMP | BPF_JSLT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
case BPF_JMP | BPF_JSLE | BPF_K:
if (imm >= 0 && imm < 65536) {
EMIT(PPC_RAW_CMPWI(dst_reg_h, imm < 0 ? -1 : 0));
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_CMPLWI(dst_reg, imm));
} else {
/* sign-extending load */
EMIT(PPC_RAW_CMPWI(dst_reg_h, imm < 0 ? -1 : 0));
PPC_LI32(_R0, imm);
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
EMIT(PPC_RAW_CMPLW(dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
case BPF_JMP32 | BPF_JSGT | BPF_K:
case BPF_JMP32 | BPF_JSLT | BPF_K:
case BPF_JMP32 | BPF_JSGE | BPF_K:
case BPF_JMP32 | BPF_JSLE | BPF_K:
/*
* signed comparison, so any 16-bit value
* can be used in cmpwi
*/
if (imm >= -32768 && imm < 32768) {
EMIT(PPC_RAW_CMPWI(dst_reg, imm));
} else {
/* sign-extending load */
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_CMPW(dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
case BPF_JMP | BPF_JSET | BPF_K:
/* andi does not sign-extend the immediate */
if (imm >= 0 && imm < 32768) {
/* PPC_ANDI is _only/always_ dot-form */
EMIT(PPC_RAW_ANDI(_R0, dst_reg, imm));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
} else {
PPC_LI32(_R0, imm);
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
if (imm < 0) {
EMIT(PPC_RAW_CMPWI(dst_reg_h, 0));
PPC_BCC_SHORT(COND_NE, (ctx->idx + 2) * 4);
}
EMIT(PPC_RAW_AND_DOT(_R0, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
case BPF_JMP32 | BPF_JSET | BPF_K:
/* andi does not sign-extend the immediate */
if (imm >= -32768 && imm < 32768) {
/* PPC_ANDI is _only/always_ dot-form */
EMIT(PPC_RAW_ANDI(_R0, dst_reg, imm));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
} else {
PPC_LI32(_R0, imm);
EMIT(PPC_RAW_AND_DOT(_R0, dst_reg, _R0));
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
}
break;
}
PPC_BCC(true_cond, addrs[i + 1 + off]);
break;
/*
* Tail call
*/
case BPF_JMP | BPF_TAIL_CALL:
ctx->seen |= SEEN_TAILCALL;
ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
if (ret < 0)
return ret;
powerpc/bpf: Implement extended BPF on PPC32 Implement Extended Berkeley Packet Filter on Powerpc 32 Test result with test_bpf module: test_bpf: Summary: 378 PASSED, 0 FAILED, [354/366 JIT'ed] Registers mapping: [BPF_REG_0] = r11-r12 /* function arguments */ [BPF_REG_1] = r3-r4 [BPF_REG_2] = r5-r6 [BPF_REG_3] = r7-r8 [BPF_REG_4] = r9-r10 [BPF_REG_5] = r21-r22 (Args 9 and 10 come in via the stack) /* non volatile registers */ [BPF_REG_6] = r23-r24 [BPF_REG_7] = r25-r26 [BPF_REG_8] = r27-r28 [BPF_REG_9] = r29-r30 /* frame pointer aka BPF_REG_10 */ [BPF_REG_FP] = r17-r18 /* eBPF jit internal registers */ [BPF_REG_AX] = r19-r20 [TMP_REG] = r31 As PPC32 doesn't have a redzone in the stack, a stack frame must always be set in order to host at least the tail count counter. The stack frame remains for tail calls, it is set by the first callee and freed by the last callee. r0 is used as temporary register as much as possible. It is referenced directly in the code in order to avoid misusing it, because some instructions interpret it as value 0 instead of register r0 (ex: addi, addis, stw, lwz, ...) The following operations are not implemented: case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ The following operations are only implemented for power of two constants: case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/61d8b149176ddf99e7d5cef0b6dc1598583ca202.1616430991.git.christophe.leroy@csgroup.eu
2021-03-23 00:37:52 +08:00
break;
default:
/*
* The filter contains something cruel & unusual.
* We don't handle it, but also there shouldn't be
* anything missing from our list.
*/
pr_err_ratelimited("eBPF filter opcode %04x (@%d) unsupported\n", code, i);
return -EOPNOTSUPP;
}
if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext &&
!insn_is_zext(&insn[i + 1]))
EMIT(PPC_RAW_LI(dst_reg_h, 0));
}
/* Set end-of-body-code address for exit. */
addrs[i] = ctx->idx * 4;
return 0;
}