Message ID | 20190508000641.19090-40-richard.henderson@linaro.org |
---|---|
State | Superseded |
Headers | show |
Series | tcg: Move the softmmu tlb to CPUNegativeOffsetState | expand |
On Tue, May 7, 2019 at 5:34 PM Richard Henderson <richard.henderson@linaro.org> wrote: > > There was nothing armv7 specific about the bic+cmp sequence, however > looking at the set of guests more closely shows that the 8-bit immediate > operand for the bic can only be satisfied with one guest in tree: > baseline m-profile -- 10-bit pages with aligned 4-byte memory ops. > Therefore it does not seem useful to keep this path. > > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Alistair Francis <alistair.francis@wdc.com> Alistair > --- > tcg/arm/tcg-target.inc.c | 23 ++++++++++++----------- > 1 file changed, 12 insertions(+), 11 deletions(-) > > diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c > index ac813abfb8..e0fcc1d990 100644 > --- a/tcg/arm/tcg-target.inc.c > +++ b/tcg/arm/tcg-target.inc.c > @@ -1290,19 +1290,20 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, > tcg_out_ld32_12(s, COND_AL, TCG_REG_R1, TCG_REG_R1, > offsetof(CPUTLBEntry, addend)); > > - /* Check alignment, check comparators. */ > - if (use_armv7_instructions) { > + /* > + * Check alignment, check comparators. > + * Do this in no more than 3 insns. Use MOVW for v7, if possible, > + * to reduce the number of sequential conditional instructions. > + * Almost all guests have at least 4k pages, which means that we need > + * to clear at least 9 bits even for an 8-byte memory, which means it > + * isn't worth checking for an immediate operand for BIC. > + */ > + if (use_armv7_instructions && TARGET_PAGE_BITS <= 16) { > tcg_target_ulong mask = ~(TARGET_PAGE_MASK | ((1 << a_bits) - 1)); > - int rot = encode_imm(mask); > > - if (rot >= 0) { > - tcg_out_dat_imm(s, COND_AL, ARITH_BIC, TCG_REG_TMP, addrlo, > - rotl(mask, rot) | (rot << 7)); > - } else { > - tcg_out_movi32(s, COND_AL, TCG_REG_TMP, mask); > - tcg_out_dat_reg(s, COND_AL, ARITH_BIC, TCG_REG_TMP, > - addrlo, TCG_REG_TMP, 0); > - } > + tcg_out_movi32(s, COND_AL, TCG_REG_TMP, mask); > + tcg_out_dat_reg(s, COND_AL, ARITH_BIC, TCG_REG_TMP, > + addrlo, TCG_REG_TMP, 0); > tcg_out_dat_reg(s, COND_AL, ARITH_CMP, 0, TCG_REG_R2, TCG_REG_TMP, 0); > } else { > if (a_bits) { > -- > 2.17.1 > >
diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c index ac813abfb8..e0fcc1d990 100644 --- a/tcg/arm/tcg-target.inc.c +++ b/tcg/arm/tcg-target.inc.c @@ -1290,19 +1290,20 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, tcg_out_ld32_12(s, COND_AL, TCG_REG_R1, TCG_REG_R1, offsetof(CPUTLBEntry, addend)); - /* Check alignment, check comparators. */ - if (use_armv7_instructions) { + /* + * Check alignment, check comparators. + * Do this in no more than 3 insns. Use MOVW for v7, if possible, + * to reduce the number of sequential conditional instructions. + * Almost all guests have at least 4k pages, which means that we need + * to clear at least 9 bits even for an 8-byte memory, which means it + * isn't worth checking for an immediate operand for BIC. + */ + if (use_armv7_instructions && TARGET_PAGE_BITS <= 16) { tcg_target_ulong mask = ~(TARGET_PAGE_MASK | ((1 << a_bits) - 1)); - int rot = encode_imm(mask); - if (rot >= 0) { - tcg_out_dat_imm(s, COND_AL, ARITH_BIC, TCG_REG_TMP, addrlo, - rotl(mask, rot) | (rot << 7)); - } else { - tcg_out_movi32(s, COND_AL, TCG_REG_TMP, mask); - tcg_out_dat_reg(s, COND_AL, ARITH_BIC, TCG_REG_TMP, - addrlo, TCG_REG_TMP, 0); - } + tcg_out_movi32(s, COND_AL, TCG_REG_TMP, mask); + tcg_out_dat_reg(s, COND_AL, ARITH_BIC, TCG_REG_TMP, + addrlo, TCG_REG_TMP, 0); tcg_out_dat_reg(s, COND_AL, ARITH_CMP, 0, TCG_REG_R2, TCG_REG_TMP, 0); } else { if (a_bits) {
There was nothing armv7 specific about the bic+cmp sequence, however looking at the set of guests more closely shows that the 8-bit immediate operand for the bic can only be satisfied with one guest in tree: baseline m-profile -- 10-bit pages with aligned 4-byte memory ops. Therefore it does not seem useful to keep this path. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/arm/tcg-target.inc.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) -- 2.17.1