system/physmem: Un-inline cpu_physical_memory_set_dirty_lebitmap()

Avoid maintaining large functions in header, rely on the
linker to optimize at linking time.

Remove the now unneeded "system/xen.h" header.

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20251001175448.18933-14-philmd@linaro.org>

diff --git a/include/system/ram_addr.h b/include/system/ram_addr.h
index fbf57a05b2a3eb39af6a30ee7e00dc68ac02693e..49e9a9c66d8f4fd72b084a77afa1b79e8c862c6b 100644 (file)
--- a/include/system/ram_addr.h
+++ b/include/system/ram_addr.h
@@ -19,7 +19,6 @@
 #ifndef SYSTEM_RAM_ADDR_H
 #define SYSTEM_RAM_ADDR_H
 
-#include "system/xen.h"
 #include "system/tcg.h"
 #include "exec/cputlb.h"
 #include "exec/ramlist.h"
@@ -161,108 +160,9 @@ void cpu_physical_memory_set_dirty_range(ram_addr_t start, ram_addr_t length,
  * cpu_physical_memory_sync_dirty_bitmap() returns newly dirtied pages that
  * weren't set in the global migration bitmap.
  */
-static inline
 uint64_t cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
                                                 ram_addr_t start,
-                                                ram_addr_t pages)
-{
-    unsigned long i, j;
-    unsigned long page_number, c, nbits;
-    hwaddr addr;
-    ram_addr_t ram_addr;
-    uint64_t num_dirty = 0;
-    unsigned long len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
-    unsigned long hpratio = qemu_real_host_page_size() / TARGET_PAGE_SIZE;
-    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
-
-    /* start address is aligned at the start of a word? */
-    if ((((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) &&
-        (hpratio == 1)) {
-        unsigned long **blocks[DIRTY_MEMORY_NUM];
-        unsigned long idx;
-        unsigned long offset;
-        long k;
-        long nr = BITS_TO_LONGS(pages);
-
-        idx = (start >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE;
-        offset = BIT_WORD((start >> TARGET_PAGE_BITS) %
-                          DIRTY_MEMORY_BLOCK_SIZE);
-
-        WITH_RCU_READ_LOCK_GUARD() {
-            for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
-                blocks[i] =
-                    qatomic_rcu_read(&ram_list.dirty_memory[i])->blocks;
-            }
-
-            for (k = 0; k < nr; k++) {
-                if (bitmap[k]) {
-                    unsigned long temp = leul_to_cpu(bitmap[k]);
-
-                    nbits = ctpopl(temp);
-                    qatomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp);
-
-                    if (global_dirty_tracking) {
-                        qatomic_or(
-                                &blocks[DIRTY_MEMORY_MIGRATION][idx][offset],
-                                temp);
-                        if (unlikely(
-                            global_dirty_tracking & GLOBAL_DIRTY_DIRTY_RATE)) {
-                            total_dirty_pages += nbits;
-                        }
-                    }
-
-                    num_dirty += nbits;
-
-                    if (tcg_enabled()) {
-                        qatomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset],
-                                   temp);
-                    }
-                }
-
-                if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
-                    offset = 0;
-                    idx++;
-                }
-            }
-        }
-
-        if (xen_enabled()) {
-            xen_hvm_modified_memory(start, pages << TARGET_PAGE_BITS);
-        }
-    } else {
-        uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE;
-
-        if (!global_dirty_tracking) {
-            clients &= ~(1 << DIRTY_MEMORY_MIGRATION);
-        }
-
-        /*
-         * bitmap-traveling is faster than memory-traveling (for addr...)
-         * especially when most of the memory is not dirty.
-         */
-        for (i = 0; i < len; i++) {
-            if (bitmap[i] != 0) {
-                c = leul_to_cpu(bitmap[i]);
-                nbits = ctpopl(c);
-                if (unlikely(global_dirty_tracking & GLOBAL_DIRTY_DIRTY_RATE)) {
-                    total_dirty_pages += nbits;
-                }
-                num_dirty += nbits;
-                do {
-                    j = ctzl(c);
-                    c &= ~(1ul << j);
-                    page_number = (i * HOST_LONG_BITS + j) * hpratio;
-                    addr = page_number * TARGET_PAGE_SIZE;
-                    ram_addr = start + addr;
-                    cpu_physical_memory_set_dirty_range(ram_addr,
-                                       TARGET_PAGE_SIZE * hpratio, clients);
-                } while (c != 0);
-            }
-        }
-    }
-
-    return num_dirty;
-}
+                                                ram_addr_t pages);
 
 static inline void cpu_physical_memory_dirty_bits_cleared(ram_addr_t start,
                                                           ram_addr_t length)

diff --git a/system/physmem.c b/system/physmem.c
index bcd9d6fb8f05351d95fbf67da3473c8216c465ce..e85552483a8d2629e26a9813946fce255e3ad916 100644 (file)
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1205,6 +1205,109 @@ bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap,
     return false;
 }
 
+uint64_t cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
+                                                ram_addr_t start,
+                                                ram_addr_t pages)
+{
+    unsigned long i, j;
+    unsigned long page_number, c, nbits;
+    hwaddr addr;
+    ram_addr_t ram_addr;
+    uint64_t num_dirty = 0;
+    unsigned long len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
+    unsigned long hpratio = qemu_real_host_page_size() / TARGET_PAGE_SIZE;
+    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
+
+    /* start address is aligned at the start of a word? */
+    if ((((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) &&
+        (hpratio == 1)) {
+        unsigned long **blocks[DIRTY_MEMORY_NUM];
+        unsigned long idx;
+        unsigned long offset;
+        long k;
+        long nr = BITS_TO_LONGS(pages);
+
+        idx = (start >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE;
+        offset = BIT_WORD((start >> TARGET_PAGE_BITS) %
+                          DIRTY_MEMORY_BLOCK_SIZE);
+
+        WITH_RCU_READ_LOCK_GUARD() {
+            for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
+                blocks[i] =
+                    qatomic_rcu_read(&ram_list.dirty_memory[i])->blocks;
+            }
+
+            for (k = 0; k < nr; k++) {
+                if (bitmap[k]) {
+                    unsigned long temp = leul_to_cpu(bitmap[k]);
+
+                    nbits = ctpopl(temp);
+                    qatomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp);
+
+                    if (global_dirty_tracking) {
+                        qatomic_or(
+                                &blocks[DIRTY_MEMORY_MIGRATION][idx][offset],
+                                temp);
+                        if (unlikely(
+                            global_dirty_tracking & GLOBAL_DIRTY_DIRTY_RATE)) {
+                            total_dirty_pages += nbits;
+                        }
+                    }
+
+                    num_dirty += nbits;
+
+                    if (tcg_enabled()) {
+                        qatomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset],
+                                   temp);
+                    }
+                }
+
+                if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
+                    offset = 0;
+                    idx++;
+                }
+            }
+        }
+
+        if (xen_enabled()) {
+            xen_hvm_modified_memory(start, pages << TARGET_PAGE_BITS);
+        }
+    } else {
+        uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL
+                                        : DIRTY_CLIENTS_NOCODE;
+
+        if (!global_dirty_tracking) {
+            clients &= ~(1 << DIRTY_MEMORY_MIGRATION);
+        }
+
+        /*
+         * bitmap-traveling is faster than memory-traveling (for addr...)
+         * especially when most of the memory is not dirty.
+         */
+        for (i = 0; i < len; i++) {
+            if (bitmap[i] != 0) {
+                c = leul_to_cpu(bitmap[i]);
+                nbits = ctpopl(c);
+                if (unlikely(global_dirty_tracking & GLOBAL_DIRTY_DIRTY_RATE)) {
+                    total_dirty_pages += nbits;
+                }
+                num_dirty += nbits;
+                do {
+                    j = ctzl(c);
+                    c &= ~(1ul << j);
+                    page_number = (i * HOST_LONG_BITS + j) * hpratio;
+                    addr = page_number * TARGET_PAGE_SIZE;
+                    ram_addr = start + addr;
+                    cpu_physical_memory_set_dirty_range(ram_addr,
+                                       TARGET_PAGE_SIZE * hpratio, clients);
+                } while (c != 0);
+            }
+        }
+    }
+
+    return num_dirty;
+}
+
 static int subpage_register(subpage_t *mmio, uint32_t start, uint32_t end,
                             uint16_t section);
 static subpage_t *subpage_init(FlatView *fv, hwaddr base);