Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* KVM error improvement from Laurent
* CONFIG_PARALLEL fix from Mirek
* Atomic/optimized dirty bitmap access from myself and Stefan
* BUILD_DIR convenience/bugfix from Peter C
* Memory leak fix from Shannon
* SMM improvements (though still TCG only) from myself and Gerd, acked by mst

# gpg: Signature made Fri Jun  5 18:45:20 2015 BST using RSA key ID 78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (62 commits)
  update Linux headers from kvm/next
  atomics: add explicit compiler fence in __atomic memory barriers
  ich9: implement SMI_LOCK
  q35: implement TSEG
  q35: add test for SMRAM.D_LCK
  q35: implement SMRAM.D_LCK
  q35: add config space wmask for SMRAM and ESMRAMC
  q35: fix ESMRAMC default
  q35: implement high SMRAM
  hw/i386: remove smram_update
  target-i386: use memory API to implement SMRAM
  hw/i386: add a separate region that tracks the SMRAME bit
  target-i386: create a separate AddressSpace for each CPU
  vl: run "late" notifiers immediately
  qom: add object_property_add_const_link
  vl: allow full-blown QemuOpts syntax for -global
  pflash_cfi01: add secure property
  pflash_cfi01: change to new-style MMIO accessors
  pflash_cfi01: change big-endian property to BIT type
  target-i386: wake up processors that receive an SMI
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 92 insertions, 46 deletions

diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index ff558a4734..c113f21140 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -41,6 +41,9 @@ void qemu_ram_free_from_ptr(ram_addr_t addr);
 
 int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp);
 
+#define DIRTY_CLIENTS_ALL     ((1 << DIRTY_MEMORY_NUM) - 1)
+#define DIRTY_CLIENTS_NOCODE  (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE))
+
 static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
                                                  ram_addr_t length,
                                                  unsigned client)
@@ -56,7 +59,7 @@ static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
     return next < end;
 }
 
-static inline bool cpu_physical_memory_get_clean(ram_addr_t start,
+static inline bool cpu_physical_memory_all_dirty(ram_addr_t start,
                                                  ram_addr_t length,
                                                  unsigned client)
 {
@@ -68,7 +71,7 @@ static inline bool cpu_physical_memory_get_clean(ram_addr_t start,
     page = start >> TARGET_PAGE_BITS;
     next = find_next_zero_bit(ram_list.dirty_memory[client], end, page);
 
-    return next < end;
+    return next >= end;
 }
 
 static inline bool cpu_physical_memory_get_dirty_flag(ram_addr_t addr,
@@ -86,44 +89,52 @@ static inline bool cpu_physical_memory_is_clean(ram_addr_t addr)
     return !(vga && code && migration);
 }
 
-static inline bool cpu_physical_memory_range_includes_clean(ram_addr_t start,
-                                                            ram_addr_t length)
+static inline uint8_t cpu_physical_memory_range_includes_clean(ram_addr_t start,
+                                                               ram_addr_t length,
+                                                               uint8_t mask)
 {
-    bool vga = cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_VGA);
-    bool code = cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_CODE);
-    bool migration =
-        cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_MIGRATION);
-    return vga || code || migration;
+    uint8_t ret = 0;
+
+    if (mask & (1 << DIRTY_MEMORY_VGA) &&
+        !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_VGA)) {
+        ret |= (1 << DIRTY_MEMORY_VGA);
+    }
+    if (mask & (1 << DIRTY_MEMORY_CODE) &&
+        !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_CODE)) {
+        ret |= (1 << DIRTY_MEMORY_CODE);
+    }
+    if (mask & (1 << DIRTY_MEMORY_MIGRATION) &&
+        !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_MIGRATION)) {
+        ret |= (1 << DIRTY_MEMORY_MIGRATION);
+    }
+    return ret;
 }
 
 static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
                                                       unsigned client)
 {
     assert(client < DIRTY_MEMORY_NUM);
-    set_bit(addr >> TARGET_PAGE_BITS, ram_list.dirty_memory[client]);
-}
-
-static inline void cpu_physical_memory_set_dirty_range_nocode(ram_addr_t start,
-                                                              ram_addr_t length)
-{
-    unsigned long end, page;
-
-    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
-    page = start >> TARGET_PAGE_BITS;
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page);
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page);
+    set_bit_atomic(addr >> TARGET_PAGE_BITS, ram_list.dirty_memory[client]);
 }
 
 static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
-                                                       ram_addr_t length)
+                                                       ram_addr_t length,
+                                                       uint8_t mask)
 {
     unsigned long end, page;
+    unsigned long **d = ram_list.dirty_memory;
 
     end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
     page = start >> TARGET_PAGE_BITS;
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page);
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page);
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_CODE], page, end - page);
+    if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) {
+        bitmap_set_atomic(d[DIRTY_MEMORY_MIGRATION], page, end - page);
+    }
+    if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) {
+        bitmap_set_atomic(d[DIRTY_MEMORY_VGA], page, end - page);
+    }
+    if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) {
+        bitmap_set_atomic(d[DIRTY_MEMORY_CODE], page, end - page);
+    }
     xen_modified_memory(start, length);
 }
 
@@ -149,14 +160,18 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
         for (k = 0; k < nr; k++) {
             if (bitmap[k]) {
                 unsigned long temp = leul_to_cpu(bitmap[k]);
+                unsigned long **d = ram_list.dirty_memory;
 
-                ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION][page + k] |= temp;
-                ram_list.dirty_memory[DIRTY_MEMORY_VGA][page + k] |= temp;
-                ram_list.dirty_memory[DIRTY_MEMORY_CODE][page + k] |= temp;
+                atomic_or(&d[DIRTY_MEMORY_MIGRATION][page + k], temp);
+                atomic_or(&d[DIRTY_MEMORY_VGA][page + k], temp);
+                if (tcg_enabled()) {
+                    atomic_or(&d[DIRTY_MEMORY_CODE][page + k], temp);
+                }
             }
         }
-        xen_modified_memory(start, pages);
+        xen_modified_memory(start, pages << TARGET_PAGE_BITS);
     } else {
+        uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE;
         /*
          * bitmap-traveling is faster than memory-traveling (for addr...)
          * especially when most of the memory is not dirty.
@@ -171,7 +186,7 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
                     addr = page_number * TARGET_PAGE_SIZE;
                     ram_addr = start + addr;
                     cpu_physical_memory_set_dirty_range(ram_addr,
-                                       TARGET_PAGE_SIZE * hpratio);
+                                       TARGET_PAGE_SIZE * hpratio, clients);
                 } while (c != 0);
             }
         }
@@ -179,29 +194,60 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
 }
 #endif /* not _WIN32 */
 
-static inline void cpu_physical_memory_clear_dirty_range_type(ram_addr_t start,
-                                                              ram_addr_t length,
-                                                              unsigned client)
-{
-    unsigned long end, page;
-
-    assert(client < DIRTY_MEMORY_NUM);
-    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
-    page = start >> TARGET_PAGE_BITS;
-    bitmap_clear(ram_list.dirty_memory[client], page, end - page);
-}
+bool cpu_physical_memory_test_and_clear_dirty(ram_addr_t start,
+                                              ram_addr_t length,
+                                              unsigned client);
 
 static inline void cpu_physical_memory_clear_dirty_range(ram_addr_t start,
                                                          ram_addr_t length)
 {
-    cpu_physical_memory_clear_dirty_range_type(start, length, DIRTY_MEMORY_MIGRATION);
-    cpu_physical_memory_clear_dirty_range_type(start, length, DIRTY_MEMORY_VGA);
-    cpu_physical_memory_clear_dirty_range_type(start, length, DIRTY_MEMORY_CODE);
+    cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_MIGRATION);
+    cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_VGA);
+    cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_CODE);
 }
 
 
-void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t length,
-                                     unsigned client);
+static inline
+uint64_t cpu_physical_memory_sync_dirty_bitmap(unsigned long *dest,
+                                               ram_addr_t start,
+                                               ram_addr_t length)
+{
+    ram_addr_t addr;
+    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
+    uint64_t num_dirty = 0;
+
+    /* start address is aligned at the start of a word? */
+    if (((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) {
+        int k;
+        int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
+        unsigned long *src = ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION];
+
+        for (k = page; k < page + nr; k++) {
+            if (src[k]) {
+                unsigned long bits = atomic_xchg(&src[k], 0);
+                unsigned long new_dirty;
+                new_dirty = ~dest[k];
+                dest[k] |= bits;
+                new_dirty &= bits;
+                num_dirty += ctpopl(new_dirty);
+            }
+        }
+    } else {
+        for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
+            if (cpu_physical_memory_test_and_clear_dirty(
+                        start + addr,
+                        TARGET_PAGE_SIZE,
+                        DIRTY_MEMORY_MIGRATION)) {
+                long k = (start + addr) >> TARGET_PAGE_BITS;
+                if (!test_and_set_bit(k, dest)) {
+                    num_dirty++;
+                }
+            }
+        }
+    }
+
+    return num_dirty;
+}
 
 #endif
 #endif