diff mbox series

[03/10] tcg/arm: Use tcg_use_softmmu

Message ID 20231003174356.1602279-4-richard.henderson@linaro.org
State Superseded
Headers show
Series tcg: Allow softmmu for user-only | expand

Commit Message

Richard Henderson Oct. 3, 2023, 5:43 p.m. UTC
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/arm/tcg-target.c.inc | 203 +++++++++++++++++++--------------------
 1 file changed, 97 insertions(+), 106 deletions(-)

Comments

Philippe Mathieu-Daudé Oct. 5, 2023, 4:53 p.m. UTC | #1
On 3/10/23 19:43, Richard Henderson wrote:
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>   tcg/arm/tcg-target.c.inc | 203 +++++++++++++++++++--------------------
>   1 file changed, 97 insertions(+), 106 deletions(-)


> @@ -356,14 +354,8 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
>    * r0-r3 will be overwritten when reading the tlb entry (softmmu only);
>    * r14 will be overwritten by the BLNE branching to the slow path.
>    */
> -#ifdef CONFIG_SOFTMMU
>   #define ALL_QLDST_REGS \
> -    (ALL_GENERAL_REGS & ~((1 << TCG_REG_R0) | (1 << TCG_REG_R1) | \
> -                          (1 << TCG_REG_R2) | (1 << TCG_REG_R3) | \
> -                          (1 << TCG_REG_R14)))
> -#else
> -#define ALL_QLDST_REGS   (ALL_GENERAL_REGS & ~(1 << TCG_REG_R14))
> -#endif
> +    (ALL_GENERAL_REGS & ~((tcg_use_softmmu ? 0xf : 0) | (1 << TCG_REG_R14)))

Maybe add a comment?

(ALL_GENERAL_REGS & ~((tcg_use_softmmu ? 0xf /* R0 to R3 */ : 0) | (1 << 
TCG_REG_R14)))

Otherwise,
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Richard Henderson Oct. 13, 2023, 3:41 a.m. UTC | #2
On 10/5/23 09:53, Philippe Mathieu-Daudé wrote:
> On 3/10/23 19:43, Richard Henderson wrote:
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>> ---
>>   tcg/arm/tcg-target.c.inc | 203 +++++++++++++++++++--------------------
>>   1 file changed, 97 insertions(+), 106 deletions(-)
> 
> 
>> @@ -356,14 +354,8 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
>>    * r0-r3 will be overwritten when reading the tlb entry (softmmu only);
>>    * r14 will be overwritten by the BLNE branching to the slow path.
>>    */
>> -#ifdef CONFIG_SOFTMMU
>>   #define ALL_QLDST_REGS \
>> -    (ALL_GENERAL_REGS & ~((1 << TCG_REG_R0) | (1 << TCG_REG_R1) | \
>> -                          (1 << TCG_REG_R2) | (1 << TCG_REG_R3) | \
>> -                          (1 << TCG_REG_R14)))
>> -#else
>> -#define ALL_QLDST_REGS   (ALL_GENERAL_REGS & ~(1 << TCG_REG_R14))
>> -#endif
>> +    (ALL_GENERAL_REGS & ~((tcg_use_softmmu ? 0xf : 0) | (1 << TCG_REG_R14)))
> 
> Maybe add a comment?
> 
> (ALL_GENERAL_REGS & ~((tcg_use_softmmu ? 0xf /* R0 to R3 */ : 0) | (1 << TCG_REG_R14)))
> 
> Otherwise,
> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
> 

I'd have thought the existing comment sufficient.


r~
diff mbox series

Patch

diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc
index a2f60106af..550a06a1b9 100644
--- a/tcg/arm/tcg-target.c.inc
+++ b/tcg/arm/tcg-target.c.inc
@@ -89,9 +89,7 @@  static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot)
 
 #define TCG_REG_TMP  TCG_REG_R12
 #define TCG_VEC_TMP  TCG_REG_Q15
-#ifndef CONFIG_SOFTMMU
 #define TCG_REG_GUEST_BASE  TCG_REG_R11
-#endif
 
 typedef enum {
     COND_EQ = 0x0,
@@ -356,14 +354,8 @@  static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
  * r0-r3 will be overwritten when reading the tlb entry (softmmu only);
  * r14 will be overwritten by the BLNE branching to the slow path.
  */
-#ifdef CONFIG_SOFTMMU
 #define ALL_QLDST_REGS \
-    (ALL_GENERAL_REGS & ~((1 << TCG_REG_R0) | (1 << TCG_REG_R1) | \
-                          (1 << TCG_REG_R2) | (1 << TCG_REG_R3) | \
-                          (1 << TCG_REG_R14)))
-#else
-#define ALL_QLDST_REGS   (ALL_GENERAL_REGS & ~(1 << TCG_REG_R14))
-#endif
+    (ALL_GENERAL_REGS & ~((tcg_use_softmmu ? 0xf : 0) | (1 << TCG_REG_R14)))
 
 /*
  * ARM immediates for ALU instructions are made of an unsigned 8-bit
@@ -1387,113 +1379,115 @@  static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     MemOp opc = get_memop(oi);
     unsigned a_mask;
 
-#ifdef CONFIG_SOFTMMU
-    *h = (HostAddress){
-        .cond = COND_AL,
-        .base = addrlo,
-        .index = TCG_REG_R1,
-        .index_scratch = true,
-    };
-#else
-    *h = (HostAddress){
-        .cond = COND_AL,
-        .base = addrlo,
-        .index = guest_base ? TCG_REG_GUEST_BASE : -1,
-        .index_scratch = false,
-    };
-#endif
+    if (tcg_use_softmmu) {
+        *h = (HostAddress){
+            .cond = COND_AL,
+            .base = addrlo,
+            .index = TCG_REG_R1,
+            .index_scratch = true,
+        };
+    } else {
+        *h = (HostAddress){
+            .cond = COND_AL,
+            .base = addrlo,
+            .index = guest_base ? TCG_REG_GUEST_BASE : -1,
+            .index_scratch = false,
+        };
+    }
 
     h->aa = atom_and_align_for_opc(s, opc, MO_ATOM_IFALIGN, false);
     a_mask = (1 << h->aa.align) - 1;
 
-#ifdef CONFIG_SOFTMMU
-    int mem_index = get_mmuidx(oi);
-    int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read)
-                        : offsetof(CPUTLBEntry, addr_write);
-    int fast_off = tlb_mask_table_ofs(s, mem_index);
-    unsigned s_mask = (1 << (opc & MO_SIZE)) - 1;
-    TCGReg t_addr;
+    if (tcg_use_softmmu) {
+        int mem_index = get_mmuidx(oi);
+        int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read)
+                            : offsetof(CPUTLBEntry, addr_write);
+        int fast_off = tlb_mask_table_ofs(s, mem_index);
+        unsigned s_mask = (1 << (opc & MO_SIZE)) - 1;
+        TCGReg t_addr;
 
-    ldst = new_ldst_label(s);
-    ldst->is_ld = is_ld;
-    ldst->oi = oi;
-    ldst->addrlo_reg = addrlo;
-    ldst->addrhi_reg = addrhi;
+        ldst = new_ldst_label(s);
+        ldst->is_ld = is_ld;
+        ldst->oi = oi;
+        ldst->addrlo_reg = addrlo;
+        ldst->addrhi_reg = addrhi;
 
-    /* Load cpu->neg.tlb.f[mmu_idx].{mask,table} into {r0,r1}.  */
-    QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, mask) != 0);
-    QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, table) != 4);
-    tcg_out_ldrd_8(s, COND_AL, TCG_REG_R0, TCG_AREG0, fast_off);
+        /* Load cpu->neg.tlb.f[mmu_idx].{mask,table} into {r0,r1}.  */
+        QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, mask) != 0);
+        QEMU_BUILD_BUG_ON(offsetof(CPUTLBDescFast, table) != 4);
+        tcg_out_ldrd_8(s, COND_AL, TCG_REG_R0, TCG_AREG0, fast_off);
 
-    /* Extract the tlb index from the address into R0.  */
-    tcg_out_dat_reg(s, COND_AL, ARITH_AND, TCG_REG_R0, TCG_REG_R0, addrlo,
-                    SHIFT_IMM_LSR(s->page_bits - CPU_TLB_ENTRY_BITS));
+        /* Extract the tlb index from the address into R0.  */
+        tcg_out_dat_reg(s, COND_AL, ARITH_AND, TCG_REG_R0, TCG_REG_R0, addrlo,
+                        SHIFT_IMM_LSR(s->page_bits - CPU_TLB_ENTRY_BITS));
 
-    /*
-     * Add the tlb_table pointer, creating the CPUTLBEntry address in R1.
-     * Load the tlb comparator into R2/R3 and the fast path addend into R1.
-     */
-    QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
-    if (cmp_off == 0) {
-        if (s->addr_type == TCG_TYPE_I32) {
-            tcg_out_ld32_rwb(s, COND_AL, TCG_REG_R2, TCG_REG_R1, TCG_REG_R0);
+        /*
+         * Add the tlb_table pointer, creating the CPUTLBEntry address in R1.
+         * Load the tlb comparator into R2/R3 and the fast path addend into R1.
+         */
+        QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
+        if (cmp_off == 0) {
+            if (s->addr_type == TCG_TYPE_I32) {
+                tcg_out_ld32_rwb(s, COND_AL, TCG_REG_R2,
+                                 TCG_REG_R1, TCG_REG_R0);
+            } else {
+                tcg_out_ldrd_rwb(s, COND_AL, TCG_REG_R2,
+                                 TCG_REG_R1, TCG_REG_R0);
+            }
         } else {
-            tcg_out_ldrd_rwb(s, COND_AL, TCG_REG_R2, TCG_REG_R1, TCG_REG_R0);
+            tcg_out_dat_reg(s, COND_AL, ARITH_ADD,
+                            TCG_REG_R1, TCG_REG_R1, TCG_REG_R0, 0);
+            if (s->addr_type == TCG_TYPE_I32) {
+                tcg_out_ld32_12(s, COND_AL, TCG_REG_R2, TCG_REG_R1, cmp_off);
+            } else {
+                tcg_out_ldrd_8(s, COND_AL, TCG_REG_R2, TCG_REG_R1, cmp_off);
+            }
         }
-    } else {
-        tcg_out_dat_reg(s, COND_AL, ARITH_ADD,
-                        TCG_REG_R1, TCG_REG_R1, TCG_REG_R0, 0);
-        if (s->addr_type == TCG_TYPE_I32) {
-            tcg_out_ld32_12(s, COND_AL, TCG_REG_R2, TCG_REG_R1, cmp_off);
+
+        /* Load the tlb addend.  */
+        tcg_out_ld32_12(s, COND_AL, TCG_REG_R1, TCG_REG_R1,
+                        offsetof(CPUTLBEntry, addend));
+
+        /*
+         * Check alignment, check comparators.
+         * Do this in 2-4 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.
+         *
+         * For unaligned accesses, test the page of the last unit of alignment.
+         * This leaves the least significant alignment bits unchanged, and of
+         * course must be zero.
+         */
+        t_addr = addrlo;
+        if (a_mask < s_mask) {
+            t_addr = TCG_REG_R0;
+            tcg_out_dat_imm(s, COND_AL, ARITH_ADD, t_addr,
+                            addrlo, s_mask - a_mask);
+        }
+        if (use_armv7_instructions && s->page_bits <= 16) {
+            tcg_out_movi32(s, COND_AL, TCG_REG_TMP, ~(s->page_mask | a_mask));
+            tcg_out_dat_reg(s, COND_AL, ARITH_BIC, TCG_REG_TMP,
+                            t_addr, TCG_REG_TMP, 0);
+            tcg_out_dat_reg(s, COND_AL, ARITH_CMP, 0,
+                            TCG_REG_R2, TCG_REG_TMP, 0);
         } else {
-            tcg_out_ldrd_8(s, COND_AL, TCG_REG_R2, TCG_REG_R1, cmp_off);
+            if (a_mask) {
+                tcg_debug_assert(a_mask <= 0xff);
+                tcg_out_dat_imm(s, COND_AL, ARITH_TST, 0, addrlo, a_mask);
+            }
+            tcg_out_dat_reg(s, COND_AL, ARITH_MOV, TCG_REG_TMP, 0, t_addr,
+                            SHIFT_IMM_LSR(s->page_bits));
+            tcg_out_dat_reg(s, (a_mask ? COND_EQ : COND_AL), ARITH_CMP,
+                            0, TCG_REG_R2, TCG_REG_TMP,
+                            SHIFT_IMM_LSL(s->page_bits));
         }
-    }
 
-    /* Load the tlb addend.  */
-    tcg_out_ld32_12(s, COND_AL, TCG_REG_R1, TCG_REG_R1,
-                    offsetof(CPUTLBEntry, addend));
-
-    /*
-     * Check alignment, check comparators.
-     * Do this in 2-4 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.
-     *
-     * For unaligned accesses, test the page of the last unit of alignment.
-     * This leaves the least significant alignment bits unchanged, and of
-     * course must be zero.
-     */
-    t_addr = addrlo;
-    if (a_mask < s_mask) {
-        t_addr = TCG_REG_R0;
-        tcg_out_dat_imm(s, COND_AL, ARITH_ADD, t_addr,
-                        addrlo, s_mask - a_mask);
-    }
-    if (use_armv7_instructions && s->page_bits <= 16) {
-        tcg_out_movi32(s, COND_AL, TCG_REG_TMP, ~(s->page_mask | a_mask));
-        tcg_out_dat_reg(s, COND_AL, ARITH_BIC, TCG_REG_TMP,
-                        t_addr, TCG_REG_TMP, 0);
-        tcg_out_dat_reg(s, COND_AL, ARITH_CMP, 0, TCG_REG_R2, TCG_REG_TMP, 0);
-    } else {
-        if (a_mask) {
-            tcg_debug_assert(a_mask <= 0xff);
-            tcg_out_dat_imm(s, COND_AL, ARITH_TST, 0, addrlo, a_mask);
+        if (s->addr_type != TCG_TYPE_I32) {
+            tcg_out_dat_reg(s, COND_EQ, ARITH_CMP, 0, TCG_REG_R3, addrhi, 0);
         }
-        tcg_out_dat_reg(s, COND_AL, ARITH_MOV, TCG_REG_TMP, 0, t_addr,
-                        SHIFT_IMM_LSR(s->page_bits));
-        tcg_out_dat_reg(s, (a_mask ? COND_EQ : COND_AL), ARITH_CMP,
-                        0, TCG_REG_R2, TCG_REG_TMP,
-                        SHIFT_IMM_LSL(s->page_bits));
-    }
-
-    if (s->addr_type != TCG_TYPE_I32) {
-        tcg_out_dat_reg(s, COND_EQ, ARITH_CMP, 0, TCG_REG_R3, addrhi, 0);
-    }
-#else
-    if (a_mask) {
+    } else if (a_mask) {
         ldst = new_ldst_label(s);
         ldst->is_ld = is_ld;
         ldst->oi = oi;
@@ -1505,7 +1499,6 @@  static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
         /* tst addr, #mask */
         tcg_out_dat_imm(s, COND_AL, ARITH_TST, 0, addrlo, a_mask);
     }
-#endif
 
     return ldst;
 }
@@ -2931,12 +2924,10 @@  static void tcg_target_qemu_prologue(TCGContext *s)
 
     tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
 
-#ifndef CONFIG_SOFTMMU
-    if (guest_base) {
+    if (!tcg_use_softmmu && guest_base) {
         tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_GUEST_BASE, guest_base);
         tcg_regset_set_reg(s->reserved_regs, TCG_REG_GUEST_BASE);
     }
-#endif
 
     tcg_out_b_reg(s, COND_AL, tcg_target_call_iarg_regs[1]);