qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: "Philippe Mathieu-Daudé" <philmd@linaro.org>
Subject: [PATCH v2 04/30] accel/tcg: Introduce tlb_read_idx
Date: Wed, 15 Feb 2023 16:57:13 -1000	[thread overview]
Message-ID: <20230216025739.1211680-5-richard.henderson@linaro.org> (raw)
In-Reply-To: <20230216025739.1211680-1-richard.henderson@linaro.org>

Instead of playing with offsetof in various places, use
MMUAccessType to index an array.  This is easily defined
instead of the previous dummy padding array in the union.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/exec/cpu-defs.h |   7 ++-
 include/exec/cpu_ldst.h |  26 ++++++++--
 accel/tcg/cputlb.c      | 104 +++++++++++++---------------------------
 3 files changed, 59 insertions(+), 78 deletions(-)

diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index 21309cf567..7ce3bcb06b 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -128,8 +128,11 @@ typedef struct CPUTLBEntry {
                use the corresponding iotlb value.  */
             uintptr_t addend;
         };
-        /* padding to get a power of two size */
-        uint8_t dummy[1 << CPU_TLB_ENTRY_BITS];
+        /*
+         * Padding to get a power of two size, as well as index
+         * access to addr_{read,write,code}.
+         */
+        target_ulong addr_idx[(1 << CPU_TLB_ENTRY_BITS) / TARGET_LONG_SIZE];
     };
 } CPUTLBEntry;
 
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index 09b55cc0ee..fad6efc0ad 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -360,13 +360,29 @@ static inline void clear_helper_retaddr(void)
 /* Needed for TCG_OVERSIZED_GUEST */
 #include "tcg/tcg.h"
 
+static inline target_ulong tlb_read_idx(const CPUTLBEntry *entry,
+                                        MMUAccessType access_type)
+{
+    /* Do not rearrange the CPUTLBEntry structure members. */
+    QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_read) !=
+                      MMU_DATA_LOAD * TARGET_LONG_SIZE);
+    QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_write) !=
+                      MMU_DATA_STORE * TARGET_LONG_SIZE);
+    QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_code) !=
+                      MMU_INST_FETCH * TARGET_LONG_SIZE);
+
+    const target_ulong *ptr = &entry->addr_idx[access_type];
+#if TCG_OVERSIZED_GUEST
+    return *ptr;
+#else
+    /* ofs might correspond to .addr_write, so use qatomic_read */
+    return qatomic_read(ptr);
+#endif
+}
+
 static inline target_ulong tlb_addr_write(const CPUTLBEntry *entry)
 {
-#if TCG_OVERSIZED_GUEST
-    return entry->addr_write;
-#else
-    return qatomic_read(&entry->addr_write);
-#endif
+    return tlb_read_idx(entry, MMU_DATA_STORE);
 }
 
 /* Find the TLB index corresponding to the mmu_idx + address pair.  */
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index 4812d83961..3cadd35f5d 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -1442,34 +1442,17 @@ static void io_writex(CPUArchState *env, CPUTLBEntryFull *full,
     }
 }
 
-static inline target_ulong tlb_read_ofs(CPUTLBEntry *entry, size_t ofs)
-{
-#if TCG_OVERSIZED_GUEST
-    return *(target_ulong *)((uintptr_t)entry + ofs);
-#else
-    /* ofs might correspond to .addr_write, so use qatomic_read */
-    return qatomic_read((target_ulong *)((uintptr_t)entry + ofs));
-#endif
-}
-
 /* Return true if ADDR is present in the victim tlb, and has been copied
    back to the main tlb.  */
 static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
-                           size_t elt_ofs, target_ulong page)
+                           MMUAccessType access_type, target_ulong page)
 {
     size_t vidx;
 
     assert_cpu_is_self(env_cpu(env));
     for (vidx = 0; vidx < CPU_VTLB_SIZE; ++vidx) {
         CPUTLBEntry *vtlb = &env_tlb(env)->d[mmu_idx].vtable[vidx];
-        target_ulong cmp;
-
-        /* elt_ofs might correspond to .addr_write, so use qatomic_read */
-#if TCG_OVERSIZED_GUEST
-        cmp = *(target_ulong *)((uintptr_t)vtlb + elt_ofs);
-#else
-        cmp = qatomic_read((target_ulong *)((uintptr_t)vtlb + elt_ofs));
-#endif
+        target_ulong cmp = tlb_read_idx(vtlb, access_type);
 
         if (cmp == page) {
             /* Found entry in victim tlb, swap tlb and iotlb.  */
@@ -1491,11 +1474,6 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
     return false;
 }
 
-/* Macro to call the above, with local variables from the use context.  */
-#define VICTIM_TLB_HIT(TY, ADDR) \
-  victim_tlb_hit(env, mmu_idx, index, offsetof(CPUTLBEntry, TY), \
-                 (ADDR) & TARGET_PAGE_MASK)
-
 static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size,
                            CPUTLBEntryFull *full, uintptr_t retaddr)
 {
@@ -1528,29 +1506,12 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr,
 {
     uintptr_t index = tlb_index(env, mmu_idx, addr);
     CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
-    target_ulong tlb_addr, page_addr;
-    size_t elt_ofs;
-    int flags;
+    target_ulong tlb_addr = tlb_read_idx(entry, access_type);
+    target_ulong page_addr = addr & TARGET_PAGE_MASK;
+    int flags = TLB_FLAGS_MASK;
 
-    switch (access_type) {
-    case MMU_DATA_LOAD:
-        elt_ofs = offsetof(CPUTLBEntry, addr_read);
-        break;
-    case MMU_DATA_STORE:
-        elt_ofs = offsetof(CPUTLBEntry, addr_write);
-        break;
-    case MMU_INST_FETCH:
-        elt_ofs = offsetof(CPUTLBEntry, addr_code);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-    tlb_addr = tlb_read_ofs(entry, elt_ofs);
-
-    flags = TLB_FLAGS_MASK;
-    page_addr = addr & TARGET_PAGE_MASK;
     if (!tlb_hit_page(tlb_addr, page_addr)) {
-        if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) {
+        if (!victim_tlb_hit(env, mmu_idx, index, access_type, page_addr)) {
             CPUState *cs = env_cpu(env);
 
             if (!cs->cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type,
@@ -1572,7 +1533,7 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr,
              */
             flags &= ~TLB_INVALID_MASK;
         }
-        tlb_addr = tlb_read_ofs(entry, elt_ofs);
+        tlb_addr = tlb_read_idx(entry, access_type);
     }
     flags &= tlb_addr;
 
@@ -1786,7 +1747,8 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
     if (prot & PAGE_WRITE) {
         tlb_addr = tlb_addr_write(tlbe);
         if (!tlb_hit(tlb_addr, addr)) {
-            if (!VICTIM_TLB_HIT(addr_write, addr)) {
+            if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_STORE,
+                                addr & TARGET_PAGE_MASK)) {
                 tlb_fill(env_cpu(env), addr, size,
                          MMU_DATA_STORE, mmu_idx, retaddr);
                 index = tlb_index(env, mmu_idx, addr);
@@ -1810,7 +1772,8 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
     } else /* if (prot & PAGE_READ) */ {
         tlb_addr = tlbe->addr_read;
         if (!tlb_hit(tlb_addr, addr)) {
-            if (!VICTIM_TLB_HIT(addr_write, addr)) {
+            if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_LOAD,
+                                addr & TARGET_PAGE_MASK)) {
                 tlb_fill(env_cpu(env), addr, size,
                          MMU_DATA_LOAD, mmu_idx, retaddr);
                 index = tlb_index(env, mmu_idx, addr);
@@ -1896,13 +1859,9 @@ load_memop(const void *haddr, MemOp op)
 
 static inline uint64_t QEMU_ALWAYS_INLINE
 load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi,
-            uintptr_t retaddr, MemOp op, bool code_read,
+            uintptr_t retaddr, MemOp op, MMUAccessType access_type,
             FullLoadHelper *full_load)
 {
-    const size_t tlb_off = code_read ?
-        offsetof(CPUTLBEntry, addr_code) : offsetof(CPUTLBEntry, addr_read);
-    const MMUAccessType access_type =
-        code_read ? MMU_INST_FETCH : MMU_DATA_LOAD;
     const unsigned a_bits = get_alignment_bits(get_memop(oi));
     const size_t size = memop_size(op);
     uintptr_t mmu_idx = get_mmuidx(oi);
@@ -1922,18 +1881,18 @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi,
 
     index = tlb_index(env, mmu_idx, addr);
     entry = tlb_entry(env, mmu_idx, addr);
-    tlb_addr = code_read ? entry->addr_code : entry->addr_read;
+    tlb_addr = tlb_read_idx(entry, access_type);
 
     /* If the TLB entry is for a different page, reload and try again.  */
     if (!tlb_hit(tlb_addr, addr)) {
-        if (!victim_tlb_hit(env, mmu_idx, index, tlb_off,
+        if (!victim_tlb_hit(env, mmu_idx, index, access_type,
                             addr & TARGET_PAGE_MASK)) {
             tlb_fill(env_cpu(env), addr, size,
                      access_type, mmu_idx, retaddr);
             index = tlb_index(env, mmu_idx, addr);
             entry = tlb_entry(env, mmu_idx, addr);
         }
-        tlb_addr = code_read ? entry->addr_code : entry->addr_read;
+        tlb_addr = tlb_read_idx(entry, access_type);
         tlb_addr &= ~TLB_INVALID_MASK;
     }
 
@@ -2019,7 +1978,8 @@ static uint64_t full_ldub_mmu(CPUArchState *env, target_ulong addr,
                               MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_UB);
-    return load_helper(env, addr, oi, retaddr, MO_UB, false, full_ldub_mmu);
+    return load_helper(env, addr, oi, retaddr, MO_UB, MMU_DATA_LOAD,
+                       full_ldub_mmu);
 }
 
 tcg_target_ulong helper_ret_ldub_mmu(CPUArchState *env, target_ulong addr,
@@ -2032,7 +1992,7 @@ static uint64_t full_le_lduw_mmu(CPUArchState *env, target_ulong addr,
                                  MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_LEUW);
-    return load_helper(env, addr, oi, retaddr, MO_LEUW, false,
+    return load_helper(env, addr, oi, retaddr, MO_LEUW, MMU_DATA_LOAD,
                        full_le_lduw_mmu);
 }
 
@@ -2046,7 +2006,7 @@ static uint64_t full_be_lduw_mmu(CPUArchState *env, target_ulong addr,
                                  MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_BEUW);
-    return load_helper(env, addr, oi, retaddr, MO_BEUW, false,
+    return load_helper(env, addr, oi, retaddr, MO_BEUW, MMU_DATA_LOAD,
                        full_be_lduw_mmu);
 }
 
@@ -2060,7 +2020,7 @@ static uint64_t full_le_ldul_mmu(CPUArchState *env, target_ulong addr,
                                  MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_LEUL);
-    return load_helper(env, addr, oi, retaddr, MO_LEUL, false,
+    return load_helper(env, addr, oi, retaddr, MO_LEUL, MMU_DATA_LOAD,
                        full_le_ldul_mmu);
 }
 
@@ -2074,7 +2034,7 @@ static uint64_t full_be_ldul_mmu(CPUArchState *env, target_ulong addr,
                                  MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_BEUL);
-    return load_helper(env, addr, oi, retaddr, MO_BEUL, false,
+    return load_helper(env, addr, oi, retaddr, MO_BEUL, MMU_DATA_LOAD,
                        full_be_ldul_mmu);
 }
 
@@ -2088,7 +2048,7 @@ uint64_t helper_le_ldq_mmu(CPUArchState *env, target_ulong addr,
                            MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_LEUQ);
-    return load_helper(env, addr, oi, retaddr, MO_LEUQ, false,
+    return load_helper(env, addr, oi, retaddr, MO_LEUQ, MMU_DATA_LOAD,
                        helper_le_ldq_mmu);
 }
 
@@ -2096,7 +2056,7 @@ uint64_t helper_be_ldq_mmu(CPUArchState *env, target_ulong addr,
                            MemOpIdx oi, uintptr_t retaddr)
 {
     validate_memop(oi, MO_BEUQ);
-    return load_helper(env, addr, oi, retaddr, MO_BEUQ, false,
+    return load_helper(env, addr, oi, retaddr, MO_BEUQ, MMU_DATA_LOAD,
                        helper_be_ldq_mmu);
 }
 
@@ -2292,7 +2252,6 @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val,
                        uintptr_t retaddr, size_t size, uintptr_t mmu_idx,
                        bool big_endian)
 {
-    const size_t tlb_off = offsetof(CPUTLBEntry, addr_write);
     uintptr_t index, index2;
     CPUTLBEntry *entry, *entry2;
     target_ulong page1, page2, tlb_addr, tlb_addr2;
@@ -2314,7 +2273,7 @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val,
 
     tlb_addr2 = tlb_addr_write(entry2);
     if (page1 != page2 && !tlb_hit_page(tlb_addr2, page2)) {
-        if (!victim_tlb_hit(env, mmu_idx, index2, tlb_off, page2)) {
+        if (!victim_tlb_hit(env, mmu_idx, index2, MMU_DATA_STORE, page2)) {
             tlb_fill(env_cpu(env), page2, size2, MMU_DATA_STORE,
                      mmu_idx, retaddr);
             index2 = tlb_index(env, mmu_idx, page2);
@@ -2367,7 +2326,6 @@ static inline void QEMU_ALWAYS_INLINE
 store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
              MemOpIdx oi, uintptr_t retaddr, MemOp op)
 {
-    const size_t tlb_off = offsetof(CPUTLBEntry, addr_write);
     const unsigned a_bits = get_alignment_bits(get_memop(oi));
     const size_t size = memop_size(op);
     uintptr_t mmu_idx = get_mmuidx(oi);
@@ -2390,7 +2348,7 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
 
     /* If the TLB entry is for a different page, reload and try again.  */
     if (!tlb_hit(tlb_addr, addr)) {
-        if (!victim_tlb_hit(env, mmu_idx, index, tlb_off,
+        if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_STORE,
             addr & TARGET_PAGE_MASK)) {
             tlb_fill(env_cpu(env), addr, size, MMU_DATA_STORE,
                      mmu_idx, retaddr);
@@ -2696,7 +2654,8 @@ void cpu_st16_le_mmu(CPUArchState *env, abi_ptr addr, Int128 val,
 static uint64_t full_ldub_code(CPUArchState *env, target_ulong addr,
                                MemOpIdx oi, uintptr_t retaddr)
 {
-    return load_helper(env, addr, oi, retaddr, MO_8, true, full_ldub_code);
+    return load_helper(env, addr, oi, retaddr, MO_8,
+                       MMU_INST_FETCH, full_ldub_code);
 }
 
 uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr)
@@ -2708,7 +2667,8 @@ uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr)
 static uint64_t full_lduw_code(CPUArchState *env, target_ulong addr,
                                MemOpIdx oi, uintptr_t retaddr)
 {
-    return load_helper(env, addr, oi, retaddr, MO_TEUW, true, full_lduw_code);
+    return load_helper(env, addr, oi, retaddr, MO_TEUW,
+                       MMU_INST_FETCH, full_lduw_code);
 }
 
 uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr)
@@ -2720,7 +2680,8 @@ uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr)
 static uint64_t full_ldl_code(CPUArchState *env, target_ulong addr,
                               MemOpIdx oi, uintptr_t retaddr)
 {
-    return load_helper(env, addr, oi, retaddr, MO_TEUL, true, full_ldl_code);
+    return load_helper(env, addr, oi, retaddr, MO_TEUL,
+                       MMU_INST_FETCH, full_ldl_code);
 }
 
 uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr)
@@ -2732,7 +2693,8 @@ uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr)
 static uint64_t full_ldq_code(CPUArchState *env, target_ulong addr,
                               MemOpIdx oi, uintptr_t retaddr)
 {
-    return load_helper(env, addr, oi, retaddr, MO_TEUQ, true, full_ldq_code);
+    return load_helper(env, addr, oi, retaddr, MO_TEUQ,
+                       MMU_INST_FETCH, full_ldq_code);
 }
 
 uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr)
-- 
2.34.1



  parent reply	other threads:[~2023-02-16  3:01 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-16  2:57 [PATCH v2 00/30] tcg: Improve atomicity support Richard Henderson
2023-02-16  2:57 ` [PATCH v2 01/30] include/qemu/cpuid: Introduce xgetbv_low Richard Henderson
2023-02-16  2:57 ` [PATCH v2 02/30] include/exec/memop: Add bits describing atomicity Richard Henderson
2023-02-28 17:56   ` Alex Bennée
2023-03-15 17:13   ` Philippe Mathieu-Daudé
2023-02-16  2:57 ` [PATCH v2 03/30] accel/tcg: Add cpu_in_serial_context Richard Henderson
2023-02-28 17:57   ` Alex Bennée
2023-03-15 16:07   ` Philippe Mathieu-Daudé
2023-02-16  2:57 ` Richard Henderson [this message]
2023-02-28 17:59   ` [PATCH v2 04/30] accel/tcg: Introduce tlb_read_idx Alex Bennée
2023-02-16  2:57 ` [PATCH v2 05/30] accel/tcg: Reorg system mode load helpers Richard Henderson
2023-02-28 18:08   ` Alex Bennée
2023-02-16  2:57 ` [PATCH v2 06/30] accel/tcg: Reorg system mode store helpers Richard Henderson
2023-02-16  2:57 ` [PATCH v2 07/30] accel/tcg: Honor atomicity of loads Richard Henderson
2023-02-28 18:19   ` Alex Bennée
2023-02-16  2:57 ` [PATCH v2 08/30] accel/tcg: Honor atomicity of stores Richard Henderson
2023-02-16  2:57 ` [PATCH v2 09/30] tcg/tci: Use cpu_{ld,st}_mmu Richard Henderson
2023-02-16  2:57 ` [PATCH v2 10/30] tcg: Unify helper_{be,le}_{ld,st}* Richard Henderson
2023-02-16  2:57 ` [PATCH v2 11/30] accel/tcg: Implement helper_{ld, st}*_mmu for user-only Richard Henderson
2023-02-16  2:57 ` [PATCH v2 12/30] tcg: Add 128-bit guest memory primitives Richard Henderson
2023-02-16  2:57 ` [PATCH v2 13/30] meson: Detect atomic128 support with optimization Richard Henderson
2023-02-16  2:57 ` [PATCH v2 14/30] tcg/i386: Add have_atomic16 Richard Henderson
2023-03-15 17:06   ` Philippe Mathieu-Daudé
2023-02-16  2:57 ` [PATCH v2 15/30] accel/tcg: Use have_atomic16 in ldst_atomicity.c.inc Richard Henderson
2023-02-16  2:57 ` [PATCH v2 16/30] accel/tcg: Add aarch64 specific support in ldst_atomicity Richard Henderson
2023-02-16  2:57 ` [PATCH v2 17/30] tcg/aarch64: Detect have_lse, have_lse2 for linux Richard Henderson
2023-03-15 17:00   ` Philippe Mathieu-Daudé
2023-02-16  2:57 ` [PATCH v2 18/30] tcg/aarch64: Detect have_lse, have_lse2 for darwin Richard Henderson
2023-03-15 16:59   ` Philippe Mathieu-Daudé
2023-02-16  2:57 ` [PATCH v2 19/30] accel/tcg: Add have_lse2 support in ldst_atomicity Richard Henderson
2023-02-16  2:57 ` [PATCH v2 20/30] tcg: Introduce TCG_OPF_TYPE_MASK Richard Henderson
2023-02-16  2:57 ` [PATCH v2 21/30] tcg: Add INDEX_op_qemu_{ld,st}_i128 Richard Henderson
2023-02-16  2:57 ` [PATCH v2 22/30] tcg/i386: Introduce tcg_out_mov2 Richard Henderson
2023-02-16  2:57 ` [PATCH v2 23/30] tcg/i386: Introduce tcg_out_testi Richard Henderson
2023-02-16  2:57 ` [PATCH v2 24/30] tcg/i386: Use full load/store helpers in user-only mode Richard Henderson
2023-02-16  2:57 ` [PATCH v2 25/30] tcg/i386: Replace is64 with type in qemu_ld/st routines Richard Henderson
2023-02-16  2:57 ` [PATCH v2 26/30] tcg/i386: Mark Win64 call-saved vector regs as reserved Richard Henderson
2023-02-16  2:57 ` [PATCH v2 27/30] tcg/i386: Examine MemOp for atomicity and alignment Richard Henderson
2023-02-16  2:57 ` [PATCH v2 28/30] tcg/i386: Support 128-bit load/store with have_atomic16 Richard Henderson
2023-02-16  2:57 ` [PATCH v2 29/30] tcg/i386: Add vex_v argument to tcg_out_vex_modrm_pool Richard Henderson
2023-03-15 16:43   ` Philippe Mathieu-Daudé
2023-02-16  2:57 ` [PATCH v2 30/30] tcg/i386: Honor 64-bit atomicity in 32-bit mode Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230216025739.1211680-5-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).