memory: optimize qemu_get_ram_ptr and qemu_ram_ptr_length

these two functions consume too much cpu overhead to
find the RAMBlock by ram address.

After this patch, we can pass the RAMBlock pointer
to them so that they don't need to find the RAMBlock
anymore most of the time. We can get better performance
in address translation processing.

Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Message-Id: <1455935721-8804-3-git-send-email-arei.gonglei@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/exec.c b/exec.c
index 4c0114a1a182931788f1fcb912f60ea5e81505a6..c62c43903c166e0ed0b84805784fe7d934fb0edf 100644 (file)
--- a/exec.c
+++ b/exec.c
@@ -1868,9 +1868,13 @@ void *qemu_get_ram_block_host_ptr(ram_addr_t addr)
  *
  * Called within RCU critical section.
  */
-void *qemu_get_ram_ptr(ram_addr_t addr)
+void *qemu_get_ram_ptr(RAMBlock *ram_block, ram_addr_t addr)
 {
-    RAMBlock *block = qemu_get_ram_block(addr);
+    RAMBlock *block = ram_block;
+
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+    }
 
     if (xen_enabled() && block->host == NULL) {
         /* We need to check if the requested address is in the RAM
@@ -1891,15 +1895,18 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
  *
  * Called within RCU critical section.
  */
-static void *qemu_ram_ptr_length(ram_addr_t addr, hwaddr *size)
+static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
+                                 hwaddr *size)
 {
-    RAMBlock *block;
+    RAMBlock *block = ram_block;
     ram_addr_t offset_inside_block;
     if (*size == 0) {
         return NULL;
     }
 
-    block = qemu_get_ram_block(addr);
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+    }
     offset_inside_block = addr - block->offset;
     *size = MIN(*size, block->max_length - offset_inside_block);
 
@@ -2027,13 +2034,13 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     }
     switch (size) {
     case 1:
-        stb_p(qemu_get_ram_ptr(ram_addr), val);
+        stb_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     case 2:
-        stw_p(qemu_get_ram_ptr(ram_addr), val);
+        stw_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     case 4:
-        stl_p(qemu_get_ram_ptr(ram_addr), val);
+        stl_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     default:
         abort();
@@ -2609,7 +2616,7 @@ static MemTxResult address_space_write_continue(AddressSpace *as, hwaddr addr,
         } else {
             addr1 += memory_region_get_ram_addr(mr);
             /* RAM case */
-            ptr = qemu_get_ram_ptr(addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
             memcpy(ptr, buf, l);
             invalidate_and_set_dirty(mr, addr1, l);
         }
@@ -2700,7 +2707,7 @@ MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
             }
         } else {
             /* RAM case */
-            ptr = qemu_get_ram_ptr(mr->ram_addr + addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, mr->ram_addr + addr1);
             memcpy(buf, ptr, l);
         }
 
@@ -2785,7 +2792,7 @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as,
         } else {
             addr1 += memory_region_get_ram_addr(mr);
             /* ROM/RAM case */
-            ptr = qemu_get_ram_ptr(addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
             switch (type) {
             case WRITE_DATA:
                 memcpy(ptr, buf, l);
@@ -2997,7 +3004,7 @@ void *address_space_map(AddressSpace *as,
 
     memory_region_ref(mr);
     *plen = done;
-    ptr = qemu_ram_ptr_length(raddr + base, plen);
+    ptr = qemu_ram_ptr_length(mr->ram_block, raddr + base, plen);
     rcu_read_unlock();
 
     return ptr;
@@ -3081,7 +3088,8 @@ static inline uint32_t address_space_ldl_internal(AddressSpace *as, hwaddr addr,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3176,7 +3184,8 @@ static inline uint64_t address_space_ldq_internal(AddressSpace *as, hwaddr addr,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3291,7 +3300,8 @@ static inline uint32_t address_space_lduw_internal(AddressSpace *as,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3376,7 +3386,7 @@ void address_space_stl_notdirty(AddressSpace *as, hwaddr addr, uint32_t val,
         r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
     } else {
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         stl_p(ptr, val);
 
         dirty_log_mask = memory_region_get_dirty_log_mask(mr);
@@ -3431,7 +3441,7 @@ static inline void address_space_stl_internal(AddressSpace *as,
     } else {
         /* RAM case */
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             stl_le_p(ptr, val);
@@ -3541,7 +3551,7 @@ static inline void address_space_stw_internal(AddressSpace *as,
     } else {
         /* RAM case */
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             stw_le_p(ptr, val);

diff --git a/include/exec/memory.h b/include/exec/memory.h
index 683be46cd002a9a29f27601c2bd04bd955271383..34f21f1aed4e7e9c022068f00a541484c2752947 100644 (file)
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -1391,7 +1391,7 @@ MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
                                        MemoryRegion *mr);
 MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
                                     MemTxAttrs attrs, uint8_t *buf, int len);
-void *qemu_get_ram_ptr(ram_addr_t addr);
+void *qemu_get_ram_ptr(RAMBlock *ram_block, ram_addr_t addr);
 
 static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
 {
@@ -1432,7 +1432,7 @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
             mr = address_space_translate(as, addr, &addr1, &l, false);
             if (len == l && memory_access_is_direct(mr, false)) {
                 addr1 += memory_region_get_ram_addr(mr);
-                ptr = qemu_get_ram_ptr(addr1);
+                ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
                 memcpy(buf, ptr, len);
             } else {
                 result = address_space_read_continue(as, addr, attrs, buf, len,

diff --git a/memory.c b/memory.c
index b4451dd2a59147cfaaaf0acfe37982b6b86a62fe..0dd9695aec5a58cd9e6adf7ad4dc33017f8ca0bc 100644 (file)
--- a/memory.c
+++ b/memory.c
@@ -1570,7 +1570,7 @@ void *memory_region_get_ram_ptr(MemoryRegion *mr)
         mr = mr->alias;
     }
     assert(mr->ram_addr != RAM_ADDR_INVALID);
-    ptr = qemu_get_ram_ptr(mr->ram_addr & TARGET_PAGE_MASK);
+    ptr = qemu_get_ram_ptr(mr->ram_block, mr->ram_addr & TARGET_PAGE_MASK);
     rcu_read_unlock();
 
     return ptr + offset;