[Qemu-devel] [RFC PATCH 01/20] Modify DIRTY_FLAG value and introduce DIRTY_IDX to use as indexes of bit-based phys_ram_dirty.

[Yoshiaki Tamura]

Replaces byte-based phys_ram_dirty bitmap with four (MASTER, VGA,
CODE, MIGRATION) bit-based phys_ram_dirty bitmap.  On allocation, it
sets all bits in the bitmap.  It uses ffs() to convert DIRTY_FLAG to
DIRTY_IDX.

Modifies wrapper functions for byte-based phys_ram_dirty bitmap to
bit-based phys_ram_dirty bitmap.  MASTER works as a buffer, and upon
get_diry() or get_dirty_flags(), it calls
cpu_physical_memory_sync_master() to update VGA and MIGRATION.

Replaces direct phys_ram_dirty access with wrapper functions to
prevent direct access to the phys_ram_dirty bitmap.

Signed-off-by: Yoshiaki Tamura <address@hidden>
Signed-off-by: OHMURA Kei <address@hidden>
---
 cpu-all.h |  130 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
 exec.c    |   60 ++++++++++++++--------------
 2 files changed, 152 insertions(+), 38 deletions(-)

diff --git a/cpu-all.h b/cpu-all.h
index 51effc0..3f8762d 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -37,6 +37,9 @@
 
 #include "softfloat.h"
 
+/* to use ffs in flag_to_idx() */
+#include <strings.h>
+
 #if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN)
 #define BSWAP_NEEDED
 #endif
@@ -846,7 +849,6 @@ int cpu_str_to_log_mask(const char *str);
 /* memory API */
 
 extern int phys_ram_fd;
-extern uint8_t *phys_ram_dirty;
 extern ram_addr_t ram_size;
 extern ram_addr_t last_ram_offset;
 extern uint8_t *bios_mem;
@@ -869,28 +871,140 @@ extern uint8_t *bios_mem;
 /* Set if TLB entry is an IO callback.  */
 #define TLB_MMIO        (1 << 5)
 
+/* Use DIRTY_IDX as indexes of bit-based phys_ram_dirty. */
+#define MASTER_DIRTY_IDX    0
+#define VGA_DIRTY_IDX       1
+#define CODE_DIRTY_IDX      2
+#define MIGRATION_DIRTY_IDX 3
+#define NUM_DIRTY_IDX       4
+
+#define MASTER_DIRTY_FLAG    (1 << MASTER_DIRTY_IDX)
+#define VGA_DIRTY_FLAG       (1 << VGA_DIRTY_IDX)
+#define CODE_DIRTY_FLAG      (1 << CODE_DIRTY_IDX)
+#define MIGRATION_DIRTY_FLAG (1 << MIGRATION_DIRTY_IDX)
+
+extern unsigned long *phys_ram_dirty[NUM_DIRTY_IDX];
+
+static inline int dirty_flag_to_idx(int flag)
+{
+    return ffs(flag) - 1;
+}
+
+static inline int dirty_idx_to_flag(int idx)
+{
+    return 1 << idx;
+}
+
 int cpu_memory_rw_debug(CPUState *env, target_ulong addr,
                         uint8_t *buf, int len, int is_write);
 
-#define VGA_DIRTY_FLAG       0x01
-#define CODE_DIRTY_FLAG      0x02
-#define MIGRATION_DIRTY_FLAG 0x08
-
 /* read dirty bit (return 0 or 1) */
 static inline int cpu_physical_memory_is_dirty(ram_addr_t addr)
 {
-    return phys_ram_dirty[addr >> TARGET_PAGE_BITS] == 0xff;
+    unsigned long mask;
+    ram_addr_t index = (addr >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+    int offset = (addr >> TARGET_PAGE_BITS) & (HOST_LONG_BITS - 1);
+ 
+    mask = 1UL << offset;
+    return (phys_ram_dirty[MASTER_DIRTY_IDX][index] & mask) == mask;
+}
+
+static inline void cpu_physical_memory_sync_master(ram_addr_t index)
+{
+    if (phys_ram_dirty[MASTER_DIRTY_IDX][index]) {
+        phys_ram_dirty[VGA_DIRTY_IDX][index]
+            |=  phys_ram_dirty[MASTER_DIRTY_IDX][index];
+        phys_ram_dirty[MIGRATION_DIRTY_IDX][index]
+            |=  phys_ram_dirty[MASTER_DIRTY_IDX][index];
+        phys_ram_dirty[MASTER_DIRTY_IDX][index] = 0UL;
+    }
+}
+
+static inline int cpu_physical_memory_get_dirty_flags(ram_addr_t addr)
+{
+    unsigned long mask;
+    ram_addr_t index = (addr >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+    int offset = (addr >> TARGET_PAGE_BITS) & (HOST_LONG_BITS - 1);
+    int ret = 0, i;
+ 
+    mask = 1UL << offset;
+    cpu_physical_memory_sync_master(index);
+
+    for (i = VGA_DIRTY_IDX; i <= MIGRATION_DIRTY_IDX; i++) {
+        if (phys_ram_dirty[i][index] & mask) {
+            ret |= dirty_idx_to_flag(i);
+        }
+    }
+ 
+    return ret;
+}
+
+static inline int cpu_physical_memory_get_dirty_idx(ram_addr_t addr,
+                                                    int dirty_idx)
+{
+    unsigned long mask;
+    ram_addr_t index = (addr >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+    int offset = (addr >> TARGET_PAGE_BITS) & (HOST_LONG_BITS - 1);
+
+    mask = 1UL << offset;
+    cpu_physical_memory_sync_master(index);
+    return (phys_ram_dirty[dirty_idx][index] & mask) == mask;
 }
 
 static inline int cpu_physical_memory_get_dirty(ram_addr_t addr,
                                                 int dirty_flags)
 {
-    return phys_ram_dirty[addr >> TARGET_PAGE_BITS] & dirty_flags;
+    return cpu_physical_memory_get_dirty_idx(addr,
+                                             dirty_flag_to_idx(dirty_flags));
 }
 
 static inline void cpu_physical_memory_set_dirty(ram_addr_t addr)
 {
-    phys_ram_dirty[addr >> TARGET_PAGE_BITS] = 0xff;
+    unsigned long mask;
+    ram_addr_t index = (addr >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+    int offset = (addr >> TARGET_PAGE_BITS) & (HOST_LONG_BITS - 1);
+
+    mask = 1UL << offset;
+    phys_ram_dirty[MASTER_DIRTY_IDX][index] |= mask;
+}
+
+static inline void cpu_physical_memory_set_dirty_range(ram_addr_t addr,
+                                                       unsigned long mask)
+{
+    ram_addr_t index = (addr >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+
+    phys_ram_dirty[MASTER_DIRTY_IDX][index] |= mask;
+}
+
+static inline void cpu_physical_memory_set_dirty_flags(ram_addr_t addr,
+                                                       int dirty_flags)
+{
+    unsigned long mask;
+    ram_addr_t index = (addr >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+    int offset = (addr >> TARGET_PAGE_BITS) & (HOST_LONG_BITS - 1);
+
+    mask = 1UL << offset;
+    phys_ram_dirty[MASTER_DIRTY_IDX][index] |= mask;
+
+    if (dirty_flags & CODE_DIRTY_FLAG) {
+        phys_ram_dirty[CODE_DIRTY_IDX][index] |= mask;
+    }
+}
+
+static inline void cpu_physical_memory_mask_dirty_range(ram_addr_t start,
+                                                        unsigned long length,
+                                                        int dirty_flags)
+{
+    ram_addr_t addr = start, index;
+    unsigned long mask;
+    int offset, i;
+
+    for (i = 0;  i < length; i += TARGET_PAGE_SIZE) {
+        index = ((addr + i) >> TARGET_PAGE_BITS) / HOST_LONG_BITS;
+        offset = ((addr + i) >> TARGET_PAGE_BITS) & (HOST_LONG_BITS - 1);
+        mask = ~(1UL << offset);
+        phys_ram_dirty[dirty_flag_to_idx(dirty_flags)][index] &= mask;
+    }
 }
 
 void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
diff --git a/exec.c b/exec.c
index b647512..bf8d703 100644
--- a/exec.c
+++ b/exec.c
@@ -119,7 +119,7 @@ uint8_t *code_gen_ptr;
 
 #if !defined(CONFIG_USER_ONLY)
 int phys_ram_fd;
-uint8_t *phys_ram_dirty;
+unsigned long *phys_ram_dirty[NUM_DIRTY_IDX];
 uint8_t *bios_mem;
 static int in_migration;
 
@@ -1947,7 +1947,7 @@ static void tlb_protect_code(ram_addr_t ram_addr)
 static void tlb_unprotect_code_phys(CPUState *env, ram_addr_t ram_addr,
                                     target_ulong vaddr)
 {
-    phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS] |= CODE_DIRTY_FLAG;
+    cpu_physical_memory_set_dirty_flags(ram_addr, CODE_DIRTY_FLAG);
 }
 
 static inline void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry,
@@ -1968,8 +1968,7 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, 
ram_addr_t end,
 {
     CPUState *env;
     unsigned long length, start1;
-    int i, mask, len;
-    uint8_t *p;
+    int i;
 
     start &= TARGET_PAGE_MASK;
     end = TARGET_PAGE_ALIGN(end);
@@ -1977,11 +1976,7 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, 
ram_addr_t end,
     length = end - start;
     if (length == 0)
         return;
-    len = length >> TARGET_PAGE_BITS;
-    mask = ~dirty_flags;
-    p = phys_ram_dirty + (start >> TARGET_PAGE_BITS);
-    for(i = 0; i < len; i++)
-        p[i] &= mask;
+    cpu_physical_memory_mask_dirty_range(start, length, dirty_flags);    
 
     /* we modify the TLB cache so that the dirty bit will be set again
        when accessing the range */
@@ -2643,6 +2638,7 @@ extern const char *mem_path;
 ram_addr_t qemu_ram_alloc(ram_addr_t size)
 {
     RAMBlock *new_block;
+    int i;
 
     size = TARGET_PAGE_ALIGN(size);
     new_block = qemu_malloc(sizeof(*new_block));
@@ -2667,10 +2663,14 @@ ram_addr_t qemu_ram_alloc(ram_addr_t size)
     new_block->next = ram_blocks;
     ram_blocks = new_block;
 
-    phys_ram_dirty = qemu_realloc(phys_ram_dirty,
-        (last_ram_offset + size) >> TARGET_PAGE_BITS);
-    memset(phys_ram_dirty + (last_ram_offset >> TARGET_PAGE_BITS),
-           0xff, size >> TARGET_PAGE_BITS);
+    for (i = MASTER_DIRTY_IDX; i < NUM_DIRTY_IDX; i++) {
+        phys_ram_dirty[i] 
+            = qemu_realloc(phys_ram_dirty[i],
+                           BITMAP_SIZE(last_ram_offset + size));
+        memset((uint8_t *)phys_ram_dirty[i] + BITMAP_SIZE(last_ram_offset),
+               0xff, BITMAP_SIZE(last_ram_offset + size)
+               - BITMAP_SIZE(last_ram_offset));
+    }
 
     last_ram_offset += size;
 
@@ -2833,16 +2833,16 @@ static void notdirty_mem_writeb(void *opaque, 
target_phys_addr_t ram_addr,
                                 uint32_t val)
 {
     int dirty_flags;
-    dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
+    dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
     if (!(dirty_flags & CODE_DIRTY_FLAG)) {
 #if !defined(CONFIG_USER_ONLY)
         tb_invalidate_phys_page_fast(ram_addr, 1);
-        dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
+        dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
 #endif
     }
     stb_p(qemu_get_ram_ptr(ram_addr), val);
     dirty_flags |= (0xff & ~CODE_DIRTY_FLAG);
-    phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS] = dirty_flags;
+    cpu_physical_memory_set_dirty_flags(ram_addr, dirty_flags);
     /* we remove the notdirty callback only if the code has been
        flushed */
     if (dirty_flags == 0xff)
@@ -2853,16 +2853,16 @@ static void notdirty_mem_writew(void *opaque, 
target_phys_addr_t ram_addr,
                                 uint32_t val)
 {
     int dirty_flags;
-    dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
+    dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
     if (!(dirty_flags & CODE_DIRTY_FLAG)) {
 #if !defined(CONFIG_USER_ONLY)
         tb_invalidate_phys_page_fast(ram_addr, 2);
-        dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
+        dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
 #endif
     }
     stw_p(qemu_get_ram_ptr(ram_addr), val);
     dirty_flags |= (0xff & ~CODE_DIRTY_FLAG);
-    phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS] = dirty_flags;
+    cpu_physical_memory_set_dirty_flags(ram_addr, dirty_flags);
     /* we remove the notdirty callback only if the code has been
        flushed */
     if (dirty_flags == 0xff)
@@ -2873,16 +2873,16 @@ static void notdirty_mem_writel(void *opaque, 
target_phys_addr_t ram_addr,
                                 uint32_t val)
 {
     int dirty_flags;
-    dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
+    dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
     if (!(dirty_flags & CODE_DIRTY_FLAG)) {
 #if !defined(CONFIG_USER_ONLY)
         tb_invalidate_phys_page_fast(ram_addr, 4);
-        dirty_flags = phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS];
+        dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
 #endif
     }
     stl_p(qemu_get_ram_ptr(ram_addr), val);
     dirty_flags |= (0xff & ~CODE_DIRTY_FLAG);
-    phys_ram_dirty[ram_addr >> TARGET_PAGE_BITS] = dirty_flags;
+    cpu_physical_memory_set_dirty_flags(ram_addr, dirty_flags);
     /* we remove the notdirty callback only if the code has been
        flushed */
     if (dirty_flags == 0xff)
@@ -3334,8 +3334,8 @@ void cpu_physical_memory_rw(target_phys_addr_t addr, 
uint8_t *buf,
                     /* invalidate code */
                     tb_invalidate_phys_page_range(addr1, addr1 + l, 0);
                     /* set dirty bit */
-                    phys_ram_dirty[addr1 >> TARGET_PAGE_BITS] |=
-                        (0xff & ~CODE_DIRTY_FLAG);
+                    cpu_physical_memory_set_dirty_flags(
+                        addr1, (0xff & ~CODE_DIRTY_FLAG));
                 }
                /* qemu doesn't execute guest code directly, but kvm does
                   therefore flush instruction caches */
@@ -3548,8 +3548,8 @@ void cpu_physical_memory_unmap(void *buffer, 
target_phys_addr_t len,
                     /* invalidate code */
                     tb_invalidate_phys_page_range(addr1, addr1 + l, 0);
                     /* set dirty bit */
-                    phys_ram_dirty[addr1 >> TARGET_PAGE_BITS] |=
-                        (0xff & ~CODE_DIRTY_FLAG);
+                    cpu_physical_memory_set_dirty_flags(
+                        addr1, (0xff & ~CODE_DIRTY_FLAG));
                 }
                 addr1 += l;
                 access_len -= l;
@@ -3685,8 +3685,8 @@ void stl_phys_notdirty(target_phys_addr_t addr, uint32_t 
val)
                 /* invalidate code */
                 tb_invalidate_phys_page_range(addr1, addr1 + 4, 0);
                 /* set dirty bit */
-                phys_ram_dirty[addr1 >> TARGET_PAGE_BITS] |=
-                    (0xff & ~CODE_DIRTY_FLAG);
+                cpu_physical_memory_set_dirty_flags(
+                    addr1, (0xff & ~CODE_DIRTY_FLAG));
             }
         }
     }
@@ -3754,8 +3754,8 @@ void stl_phys(target_phys_addr_t addr, uint32_t val)
             /* invalidate code */
             tb_invalidate_phys_page_range(addr1, addr1 + 4, 0);
             /* set dirty bit */
-            phys_ram_dirty[addr1 >> TARGET_PAGE_BITS] |=
-                (0xff & ~CODE_DIRTY_FLAG);
+            cpu_physical_memory_set_dirty_flags(addr1,
+                (0xff & ~CODE_DIRTY_FLAG));
         }
     }
 }
-- 
1.7.0.31.g1df487