From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 28 Mar 2018 17:48:35 -0700
Subject: nfp: bpf: expose command delay slots
Patch-mainline: v4.17-rc1
Git-commit: b556ddd9c19983f3f13ab0d524f884349fead115
References: bsc#1109837
Allow callers to control the delay slots of commands, instead of
giving them just a wait/nowait choice.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
drivers/net/ethernet/netronome/nfp/bpf/jit.c | 53 ++++++++++++---------------
1 file changed, 24 insertions(+), 29 deletions(-)
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -105,23 +105,18 @@ nfp_prog_confirm_current_offset(struct n
/* --- Emitters --- */
static void
__emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
- u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, bool sync, bool indir)
+ u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, enum cmd_ctx_swap ctx,
+ bool indir)
{
- enum cmd_ctx_swap ctx;
u64 insn;
- if (sync)
- ctx = CMD_CTX_SWAP;
- else
- ctx = CMD_CTX_NO_SWAP;
-
insn = FIELD_PREP(OP_CMD_A_SRC, areg) |
FIELD_PREP(OP_CMD_CTX, ctx) |
FIELD_PREP(OP_CMD_B_SRC, breg) |
FIELD_PREP(OP_CMD_TOKEN, cmd_tgt_act[op].token) |
FIELD_PREP(OP_CMD_XFER, xfer) |
FIELD_PREP(OP_CMD_CNT, size) |
- FIELD_PREP(OP_CMD_SIG, sync) |
+ FIELD_PREP(OP_CMD_SIG, ctx != CMD_CTX_NO_SWAP) |
FIELD_PREP(OP_CMD_TGT_CMD, cmd_tgt_act[op].tgt_cmd) |
FIELD_PREP(OP_CMD_INDIR, indir) |
FIELD_PREP(OP_CMD_MODE, mode);
@@ -131,7 +126,7 @@ __emit_cmd(struct nfp_prog *nfp_prog, en
static void
emit_cmd_any(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer,
- swreg lreg, swreg rreg, u8 size, bool sync, bool indir)
+ swreg lreg, swreg rreg, u8 size, enum cmd_ctx_swap ctx, bool indir)
{
struct nfp_insn_re_regs reg;
int err;
@@ -152,22 +147,22 @@ emit_cmd_any(struct nfp_prog *nfp_prog,
return;
}
- __emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, sync,
+ __emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, ctx,
indir);
}
static void
emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer,
- swreg lreg, swreg rreg, u8 size, bool sync)
+ swreg lreg, swreg rreg, u8 size, enum cmd_ctx_swap ctx)
{
- emit_cmd_any(nfp_prog, op, mode, xfer, lreg, rreg, size, sync, false);
+ emit_cmd_any(nfp_prog, op, mode, xfer, lreg, rreg, size, ctx, false);
}
static void
emit_cmd_indir(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer,
- swreg lreg, swreg rreg, u8 size, bool sync)
+ swreg lreg, swreg rreg, u8 size, enum cmd_ctx_swap ctx)
{
- emit_cmd_any(nfp_prog, op, mode, xfer, lreg, rreg, size, sync, true);
+ emit_cmd_any(nfp_prog, op, mode, xfer, lreg, rreg, size, ctx, true);
}
static void
@@ -612,7 +607,7 @@ static int nfp_cpp_memcpy(struct nfp_pro
/* Memory read from source addr into transfer-in registers. */
emit_cmd_any(nfp_prog, CMD_TGT_READ32_SWAP,
src_40bit_addr ? CMD_MODE_40b_BA : CMD_MODE_32b, 0,
- src_base, off, xfer_num - 1, true, len > 32);
+ src_base, off, xfer_num - 1, CMD_CTX_SWAP, len > 32);
/* Move from transfer-in to transfer-out. */
for (i = 0; i < xfer_num; i++)
@@ -624,39 +619,39 @@ static int nfp_cpp_memcpy(struct nfp_pro
/* Use single direct_ref write8. */
emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
reg_a(meta->paired_st->dst_reg * 2), off, len - 1,
- true);
+ CMD_CTX_SWAP);
} else if (len <= 32 && IS_ALIGNED(len, 4)) {
/* Use single direct_ref write32. */
emit_cmd(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
reg_a(meta->paired_st->dst_reg * 2), off, xfer_num - 1,
- true);
+ CMD_CTX_SWAP);
} else if (len <= 32) {
/* Use single indirect_ref write8. */
wrp_immed(nfp_prog, reg_none(),
CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, len - 1));
emit_cmd_indir(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
reg_a(meta->paired_st->dst_reg * 2), off,
- len - 1, true);
+ len - 1, CMD_CTX_SWAP);
} else if (IS_ALIGNED(len, 4)) {
/* Use single indirect_ref write32. */
wrp_immed(nfp_prog, reg_none(),
CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, xfer_num - 1));
emit_cmd_indir(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
reg_a(meta->paired_st->dst_reg * 2), off,
- xfer_num - 1, true);
+ xfer_num - 1, CMD_CTX_SWAP);
} else if (len <= 40) {
/* Use one direct_ref write32 to write the first 32-bytes, then
* another direct_ref write8 to write the remaining bytes.
*/
emit_cmd(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
reg_a(meta->paired_st->dst_reg * 2), off, 7,
- true);
+ CMD_CTX_SWAP);
off = re_load_imm_any(nfp_prog, meta->paired_st->off + 32,
imm_b(nfp_prog));
emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 8,
reg_a(meta->paired_st->dst_reg * 2), off, len - 33,
- true);
+ CMD_CTX_SWAP);
} else {
/* Use one indirect_ref write32 to write 4-bytes aligned length,
* then another direct_ref write8 to write the remaining bytes.
@@ -667,12 +662,12 @@ static int nfp_cpp_memcpy(struct nfp_pro
CMD_OVE_LEN | FIELD_PREP(CMD_OV_LEN, xfer_num - 2));
emit_cmd_indir(nfp_prog, CMD_TGT_WRITE32_SWAP, CMD_MODE_32b, 0,
reg_a(meta->paired_st->dst_reg * 2), off,
- xfer_num - 2, true);
+ xfer_num - 2, CMD_CTX_SWAP);
new_off = meta->paired_st->off + (xfer_num - 1) * 4;
off = re_load_imm_any(nfp_prog, new_off, imm_b(nfp_prog));
emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b,
xfer_num - 1, reg_a(meta->paired_st->dst_reg * 2), off,
- (len & 0x3) - 1, true);
+ (len & 0x3) - 1, CMD_CTX_SWAP);
}
/* TODO: The following extra load is to make sure data flow be identical
@@ -733,7 +728,7 @@ data_ld(struct nfp_prog *nfp_prog, swreg
shift = size < 4 ? 4 - size : 0;
emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0,
- pptr_reg(nfp_prog), offset, sz - 1, true);
+ pptr_reg(nfp_prog), offset, sz - 1, CMD_CTX_SWAP);
i = 0;
if (shift)
@@ -763,7 +758,7 @@ data_ld_host_order(struct nfp_prog *nfp_
mask = size < 4 ? GENMASK(size - 1, 0) : 0;
emit_cmd(nfp_prog, CMD_TGT_READ32_SWAP, mode, 0,
- lreg, rreg, sz / 4 - 1, true);
+ lreg, rreg, sz / 4 - 1, CMD_CTX_SWAP);
i = 0;
if (mask)
@@ -843,7 +838,7 @@ data_stx_host_order(struct nfp_prog *nfp
wrp_mov(nfp_prog, reg_xfer(i), reg_a(src_gpr + i));
emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
- reg_a(dst_gpr), offset, size - 1, true);
+ reg_a(dst_gpr), offset, size - 1, CMD_CTX_SWAP);
return 0;
}
@@ -857,7 +852,7 @@ data_st_host_order(struct nfp_prog *nfp_
wrp_immed(nfp_prog, reg_xfer(1), imm >> 32);
emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
- reg_a(dst_gpr), offset, size - 1, true);
+ reg_a(dst_gpr), offset, size - 1, CMD_CTX_SWAP);
return 0;
}
@@ -1878,7 +1873,7 @@ mem_ldx_data_init_pktcache(struct nfp_pr
/* Cache memory into transfer-in registers. */
emit_cmd_any(nfp_prog, CMD_TGT_READ32_SWAP, CMD_MODE_32b, 0, src_base,
- off, xfer_num - 1, true, indir);
+ off, xfer_num - 1, CMD_CTX_SWAP, indir);
}
static int
@@ -2157,7 +2152,7 @@ mem_xadd(struct nfp_prog *nfp_prog, stru
FIELD_PREP(CMD_OV_LEN, 0x8 | is64 << 2));
wrp_reg_or_subpart(nfp_prog, prev_alu, reg_b(src_gpr), 2, 2);
emit_cmd_indir(nfp_prog, CMD_TGT_ADD_IMM, CMD_MODE_40b_BA, 0,
- addra, addrb, 0, false);
+ addra, addrb, 0, CMD_CTX_NO_SWAP);
return 0;
}