| Message ID | 1430152117-100558-20-git-send-email-pbonzini@redhat.com |
|---|---|
| State | New |
| Headers | show |
On Mon, 04/27 18:28, Paolo Bonzini wrote: > This cuts in half the cost of bitmap operations (which will become more > expensive when made atomic) during migration on non-VRAM regions. > > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > exec.c | 20 +++++++++++--------- > include/exec/ram_addr.h | 33 ++++++++++++++++----------------- > memory.c | 3 ++- > 3 files changed, 29 insertions(+), 27 deletions(-) > > diff --git a/exec.c b/exec.c > index 1c75dd1..cd8665a 100644 > --- a/exec.c > +++ b/exec.c > @@ -1356,7 +1356,8 @@ int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp) > > cpu_physical_memory_clear_dirty_range(block->offset, block->used_length); > block->used_length = newsize; > - cpu_physical_memory_set_dirty_range(block->offset, block->used_length); > + cpu_physical_memory_set_dirty_range(block->offset, block->used_length, > + DIRTY_CLIENTS_ALL); > memory_region_set_size(block->mr, newsize); > if (block->resized) { > block->resized(block->idstr, newsize, block->host); > @@ -1430,7 +1431,8 @@ static ram_addr_t ram_block_add(RAMBlock *new_block, Error **errp) > } > } > cpu_physical_memory_set_dirty_range(new_block->offset, > - new_block->used_length); > + new_block->used_length, > + DIRTY_CLIENTS_ALL); > > if (new_block->host) { > qemu_ram_setup_dump(new_block->host, new_block->max_length); > @@ -1818,7 +1820,11 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr, > default: > abort(); > } > - cpu_physical_memory_set_dirty_range_nocode(ram_addr, size); > + /* Set both VGA and migration bits for simplicity and to remove > + * the notdirty callback faster. > + */ > + cpu_physical_memory_set_dirty_range(ram_addr, size, > + DIRTY_CLIENTS_NOCODE); > /* we remove the notdirty callback only if the code has been > flushed */ > if (!cpu_physical_memory_is_clean(ram_addr)) { > @@ -2238,9 +2244,7 @@ static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr, > tb_invalidate_phys_range(addr, addr + length); > dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE); > } > - if (dirty_log_mask) { > - cpu_physical_memory_set_dirty_range_nocode(addr, length); > - } > + cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask); > } else { > xen_modified_memory(addr, length); > } > @@ -2865,9 +2869,7 @@ void stl_phys_notdirty(AddressSpace *as, hwaddr addr, uint32_t val) > > dirty_log_mask = memory_region_get_dirty_log_mask(mr); > dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE); > - if (dirty_log_mask) { > - cpu_physical_memory_set_dirty_range_nocode(addr1, 4); > - } > + cpu_physical_memory_set_dirty_range(addr1, 4, dirty_log_mask); > } > } > > diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h > index 7f6e928..29b89d2 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) > @@ -103,28 +106,23 @@ static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr, > 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); > - xen_modified_memory(start, length); > -} > - > 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; > > 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(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page); Wrap the line? Other than that: Reviewed-by: Fam Zheng <famz@redhat.com> > + } > + if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) { > + bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page); > + } > + if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) { > + bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_CODE], page, end - page); > + } > xen_modified_memory(start, length); > } > > @@ -172,7 +170,8 @@ 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, > + DIRTY_CLIENTS_ALL); > } while (c != 0); > } > } > diff --git a/memory.c b/memory.c > index 174cd15..7422790 100644 > --- a/memory.c > +++ b/memory.c > @@ -1390,7 +1390,8 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr, > hwaddr size) > { > assert(mr->terminates); > - cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size); > + cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size, > + memory_region_get_dirty_log_mask(mr)); > } > > bool memory_region_test_and_clear_dirty(MemoryRegion *mr, hwaddr addr, > -- > 1.8.3.1 > > >
On 26/05/2015 13:08, Fam Zheng wrote: >> > + if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) { >> > + bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page); > Wrap the line? Other than that: > > Reviewed-by: Fam Zheng <famz@redhat.com> Yes, the line gets shorter at the end of the series. Paolo
diff --git a/exec.c b/exec.c index 1c75dd1..cd8665a 100644 --- a/exec.c +++ b/exec.c @@ -1356,7 +1356,8 @@ int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp) cpu_physical_memory_clear_dirty_range(block->offset, block->used_length); block->used_length = newsize; - cpu_physical_memory_set_dirty_range(block->offset, block->used_length); + cpu_physical_memory_set_dirty_range(block->offset, block->used_length, + DIRTY_CLIENTS_ALL); memory_region_set_size(block->mr, newsize); if (block->resized) { block->resized(block->idstr, newsize, block->host); @@ -1430,7 +1431,8 @@ static ram_addr_t ram_block_add(RAMBlock *new_block, Error **errp) } } cpu_physical_memory_set_dirty_range(new_block->offset, - new_block->used_length); + new_block->used_length, + DIRTY_CLIENTS_ALL); if (new_block->host) { qemu_ram_setup_dump(new_block->host, new_block->max_length); @@ -1818,7 +1820,11 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr, default: abort(); } - cpu_physical_memory_set_dirty_range_nocode(ram_addr, size); + /* Set both VGA and migration bits for simplicity and to remove + * the notdirty callback faster. + */ + cpu_physical_memory_set_dirty_range(ram_addr, size, + DIRTY_CLIENTS_NOCODE); /* we remove the notdirty callback only if the code has been flushed */ if (!cpu_physical_memory_is_clean(ram_addr)) { @@ -2238,9 +2244,7 @@ static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr, tb_invalidate_phys_range(addr, addr + length); dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE); } - if (dirty_log_mask) { - cpu_physical_memory_set_dirty_range_nocode(addr, length); - } + cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask); } else { xen_modified_memory(addr, length); } @@ -2865,9 +2869,7 @@ void stl_phys_notdirty(AddressSpace *as, hwaddr addr, uint32_t val) dirty_log_mask = memory_region_get_dirty_log_mask(mr); dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE); - if (dirty_log_mask) { - cpu_physical_memory_set_dirty_range_nocode(addr1, 4); - } + cpu_physical_memory_set_dirty_range(addr1, 4, dirty_log_mask); } } diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 7f6e928..29b89d2 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) @@ -103,28 +106,23 @@ static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr, 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); - xen_modified_memory(start, length); -} - 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; 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(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page); + } + if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) { + bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page); + } + if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) { + bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_CODE], page, end - page); + } xen_modified_memory(start, length); } @@ -172,7 +170,8 @@ 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, + DIRTY_CLIENTS_ALL); } while (c != 0); } } diff --git a/memory.c b/memory.c index 174cd15..7422790 100644 --- a/memory.c +++ b/memory.c @@ -1390,7 +1390,8 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr, hwaddr size) { assert(mr->terminates); - cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size); + cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size, + memory_region_get_dirty_log_mask(mr)); } bool memory_region_test_and_clear_dirty(MemoryRegion *mr, hwaddr addr,
This cuts in half the cost of bitmap operations (which will become more expensive when made atomic) during migration on non-VRAM regions. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> --- exec.c | 20 +++++++++++--------- include/exec/ram_addr.h | 33 ++++++++++++++++----------------- memory.c | 3 ++- 3 files changed, 29 insertions(+), 27 deletions(-)