qemu/include/exec/cpu-common.h

111 lines
3.5 KiB
C
Raw Normal View History

#ifndef CPU_COMMON_H
#define CPU_COMMON_H
/* CPU interfaces that are target independent. */
#ifndef CONFIG_USER_ONLY
#include "exec/hwaddr.h"
#endif
tcg: remove tb_lock Use mmap_lock in user-mode to protect TCG state and the page descriptors. In !user-mode, each vCPU has its own TCG state, so no locks needed. Per-page locks are used to protect the page descriptors. Per-TB locks are used in both modes to protect TB jumps. Some notes: - tb_lock is removed from notdirty_mem_write by passing a locked page_collection to tb_invalidate_phys_page_fast. - tcg_tb_lookup/remove/insert/etc have their own internal lock(s), so there is no need to further serialize access to them. - do_tb_flush is run in a safe async context, meaning no other vCPU threads are running. Therefore acquiring mmap_lock there is just to please tools such as thread sanitizer. - Not visible in the diff, but tb_invalidate_phys_page already has an assert_memory_lock. - cpu_io_recompile is !user-only, so no mmap_lock there. - Added mmap_unlock()'s before all siglongjmp's that could be called in user-mode while mmap_lock is held. + Added an assert for !have_mmap_lock() after returning from the longjmp in cpu_exec, just like we do in cpu_exec_step_atomic. Performance numbers before/after: Host: AMD Opteron(tm) Processor 6376 ubuntu 17.04 ppc64 bootup+shutdown time 700 +-+--+----+------+------------+-----------+------------*--+-+ | + + + + + *B | | before ***B*** ** * | |tb lock removal ###D### *** | 600 +-+ *** +-+ | ** # | | *B* #D | | *** * ## | 500 +-+ *** ### +-+ | * *** ### | | *B* # ## | | ** * #D# | 400 +-+ ** ## +-+ | ** ### | | ** ## | | ** # ## | 300 +-+ * B* #D# +-+ | B *** ### | | * ** #### | | * *** ### | 200 +-+ B *B #D# +-+ | #B* * ## # | | #* ## | | + D##D# + + + + | 100 +-+--+----+------+------------+-----------+------------+--+-+ 1 8 16 Guest CPUs 48 64 png: https://imgur.com/HwmBHXe debian jessie aarch64 bootup+shutdown time 90 +-+--+-----+-----+------------+------------+------------+--+-+ | + + + + + + | | before ***B*** B | 80 +tb lock removal ###D### **D +-+ | **### | | **## | 70 +-+ ** # +-+ | ** ## | | ** # | 60 +-+ *B ## +-+ | ** ## | | *** #D | 50 +-+ *** ## +-+ | * ** ### | | **B* ### | 40 +-+ **** # ## +-+ | **** #D# | | ***B** ### | 30 +-+ B***B** #### +-+ | B * * # ### | | B ###D# | 20 +-+ D ##D## +-+ | D# | | + + + + + + | 10 +-+--+-----+-----+------------+------------+------------+--+-+ 1 8 16 Guest CPUs 48 64 png: https://imgur.com/iGpGFtv The gains are high for 4-8 CPUs. Beyond that point, however, unrelated lock contention significantly hurts scalability. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Emilio G. Cota <cota@braap.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2017-08-05 06:46:31 +03:00
/* The CPU list lock nests outside page_(un)lock or mmap_(un)lock */
void qemu_init_cpu_list(void);
void cpu_list_lock(void);
void cpu_list_unlock(void);
void tcg_flush_softmmu_tlb(CPUState *cs);
#if !defined(CONFIG_USER_ONLY)
enum device_endian {
DEVICE_NATIVE_ENDIAN,
DEVICE_BIG_ENDIAN,
DEVICE_LITTLE_ENDIAN,
};
#if defined(HOST_WORDS_BIGENDIAN)
#define DEVICE_HOST_ENDIAN DEVICE_BIG_ENDIAN
#else
#define DEVICE_HOST_ENDIAN DEVICE_LITTLE_ENDIAN
#endif
/* address in the RAM (different from a physical address) */
#if defined(CONFIG_XEN_BACKEND)
typedef uint64_t ram_addr_t;
# define RAM_ADDR_MAX UINT64_MAX
# define RAM_ADDR_FMT "%" PRIx64
#else
typedef uintptr_t ram_addr_t;
# define RAM_ADDR_MAX UINTPTR_MAX
# define RAM_ADDR_FMT "%" PRIxPTR
#endif
extern ram_addr_t ram_size;
/* memory API */
typedef void CPUWriteMemoryFunc(void *opaque, hwaddr addr, uint32_t value);
typedef uint32_t CPUReadMemoryFunc(void *opaque, hwaddr addr);
void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
/* This should not be used by devices. */
ram_addr_t qemu_ram_addr_from_host(void *ptr);
RAMBlock *qemu_ram_block_by_name(const char *name);
RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset,
ram_addr_t *offset);
ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host);
void qemu_ram_set_idstr(RAMBlock *block, const char *name, DeviceState *dev);
void qemu_ram_unset_idstr(RAMBlock *block);
const char *qemu_ram_get_idstr(RAMBlock *rb);
void *qemu_ram_get_host_addr(RAMBlock *rb);
ram_addr_t qemu_ram_get_offset(RAMBlock *rb);
ram_addr_t qemu_ram_get_used_length(RAMBlock *rb);
bool qemu_ram_is_shared(RAMBlock *rb);
bool qemu_ram_is_uf_zeroable(RAMBlock *rb);
void qemu_ram_set_uf_zeroable(RAMBlock *rb);
bool qemu_ram_is_migratable(RAMBlock *rb);
void qemu_ram_set_migratable(RAMBlock *rb);
void qemu_ram_unset_migratable(RAMBlock *rb);
size_t qemu_ram_pagesize(RAMBlock *block);
size_t qemu_ram_pagesize_largest(void);
void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf,
hwaddr len, int is_write);
static inline void cpu_physical_memory_read(hwaddr addr,
void *buf, hwaddr len)
{
cpu_physical_memory_rw(addr, buf, len, 0);
}
static inline void cpu_physical_memory_write(hwaddr addr,
const void *buf, hwaddr len)
{
cpu_physical_memory_rw(addr, (void *)buf, len, 1);
}
void *cpu_physical_memory_map(hwaddr addr,
hwaddr *plen,
int is_write);
void cpu_physical_memory_unmap(void *buffer, hwaddr len,
int is_write, hwaddr access_len);
void cpu_register_map_client(QEMUBH *bh);
void cpu_unregister_map_client(QEMUBH *bh);
bool cpu_physical_memory_is_io(hwaddr phys_addr);
/* Coalesced MMIO regions are areas where write operations can be reordered.
* This usually implies that write operations are side-effect free. This allows
* batching which can make a major impact on performance when using
* virtualization.
*/
void qemu_flush_coalesced_mmio_buffer(void);
void cpu_flush_icache_range(hwaddr start, hwaddr len);
typedef int (RAMBlockIterFunc)(RAMBlock *rb, void *opaque);
int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque);
int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length);
#endif
#endif /* CPU_COMMON_H */