diff --git a/exec.c b/exec.c index ffdb518535..a34c348184 100644 --- a/exec.c +++ b/exec.c @@ -65,6 +65,8 @@ #include "exec/ram_addr.h" #include "exec/log.h" +#include "qemu/pmem.h" + #include "migration/vmstate.h" #include "qemu/range.h" @@ -2156,6 +2158,40 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp) return 0; } +/* + * Trigger sync on the given ram block for range [start, start + length] + * with the backing store if one is available. + * Otherwise no-op. + * @Note: this is supposed to be a synchronous op. + */ +void qemu_ram_writeback(RAMBlock *block, ram_addr_t start, ram_addr_t length) +{ + void *addr = ramblock_ptr(block, start); + + /* The requested range should fit in within the block range */ + g_assert((start + length) <= block->used_length); + +#ifdef CONFIG_LIBPMEM + /* The lack of support for pmem should not block the sync */ + if (ramblock_is_pmem(block)) { + pmem_persist(addr, length); + return; + } +#endif + if (block->fd >= 0) { + /** + * Case there is no support for PMEM or the memory has not been + * specified as persistent (or is not one) - use the msync. + * Less optimal but still achieves the same goal + */ + if (qemu_msync(addr, length, block->fd)) { + warn_report("%s: failed to sync memory range: start: " + RAM_ADDR_FMT " length: " RAM_ADDR_FMT, + __func__, start, length); + } + } +} + /* Called with ram_list.mutex held */ static void dirty_memory_extend(ram_addr_t old_ram_size, ram_addr_t new_ram_size) diff --git a/include/exec/memory.h b/include/exec/memory.h index e499dc215b..27a84e0cc3 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -1265,6 +1265,12 @@ void *memory_region_get_ram_ptr(MemoryRegion *mr); */ void memory_region_ram_resize(MemoryRegion *mr, ram_addr_t newsize, Error **errp); +/** + * memory_region_do_writeback: Trigger writeback for selected address range + * [addr, addr + size] + * + */ +void memory_region_do_writeback(MemoryRegion *mr, hwaddr addr, hwaddr size); /** * memory_region_set_log: Turn dirty logging on or off for a region. diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index bed0554f4d..5adebb0bc7 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -174,6 +174,14 @@ void qemu_ram_free(RAMBlock *block); int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp); +void qemu_ram_writeback(RAMBlock *block, ram_addr_t start, ram_addr_t length); + +/* Clear whole block of mem */ +static inline void qemu_ram_block_writeback(RAMBlock *block) +{ + qemu_ram_writeback(block, 0, block->used_length); +} + #define DIRTY_CLIENTS_ALL ((1 << DIRTY_MEMORY_NUM) - 1) #define DIRTY_CLIENTS_NOCODE (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE)) diff --git a/include/qemu/cutils.h b/include/qemu/cutils.h index b54c847e0f..eb59852dfd 100644 --- a/include/qemu/cutils.h +++ b/include/qemu/cutils.h @@ -130,6 +130,7 @@ const char *qemu_strchrnul(const char *s, int c); #endif time_t mktimegm(struct tm *tm); int qemu_fdatasync(int fd); +int qemu_msync(void *addr, size_t length, int fd); int fcntl_setfl(int fd, int flag); int qemu_parse_fd(const char *param); int qemu_strtoi(const char *nptr, const char **endptr, int base, diff --git a/memory.c b/memory.c index 06484c2bff..0228cad38d 100644 --- a/memory.c +++ b/memory.c @@ -2207,6 +2207,18 @@ void memory_region_ram_resize(MemoryRegion *mr, ram_addr_t newsize, Error **errp qemu_ram_resize(mr->ram_block, newsize, errp); } + +void memory_region_do_writeback(MemoryRegion *mr, hwaddr addr, hwaddr size) +{ + /* + * Might be extended case needed to cover + * different types of memory regions + */ + if (mr->ram_block && mr->dirty_log_mask) { + qemu_ram_writeback(mr->ram_block, addr, size); + } +} + /* * Call proper memory listeners about the change on the newly * added/removed CoalescedMemoryRange. diff --git a/util/cutils.c b/util/cutils.c index 77acadc70a..2380165230 100644 --- a/util/cutils.c +++ b/util/cutils.c @@ -164,6 +164,44 @@ int qemu_fdatasync(int fd) #endif } +/** + * Sync changes made to the memory mapped file back to the backing + * storage. For POSIX compliant systems this will fallback + * to regular msync call. Otherwise it will trigger whole file sync + * (including the metadata case there is no support to skip that otherwise) + * + * @addr - start of the memory area to be synced + * @length - length of the are to be synced + * @fd - file descriptor for the file to be synced + * (mandatory only for POSIX non-compliant systems) + */ +int qemu_msync(void *addr, size_t length, int fd) +{ +#ifdef CONFIG_POSIX + size_t align_mask = ~(qemu_real_host_page_size - 1); + + /** + * There are no strict reqs as per the length of mapping + * to be synced. Still the length needs to follow the address + * alignment changes. Additionally - round the size to the multiple + * of PAGE_SIZE + */ + length += ((uintptr_t)addr & (qemu_real_host_page_size - 1)); + length = (length + ~align_mask) & align_mask; + + addr = (void *)((uintptr_t)addr & align_mask); + + return msync(addr, length, MS_SYNC); +#else /* CONFIG_POSIX */ + /** + * Perform the sync based on the file descriptor + * The sync range will most probably be wider than the one + * requested - but it will still get the job done + */ + return qemu_fdatasync(fd); +#endif /* CONFIG_POSIX */ +} + #ifndef _WIN32 /* Sets a specific flag */ int fcntl_setfl(int fd, int flag)