9a54635dcb
This speeds up MEMORY_LISTENER_CALL noticeably. Right now, with many PCI devices you have N regions added to M AddressSpaces (M = # PCI devices with bus-master enabled) and each call looks up the whole listener list, with at least M listeners in it. Because most of the regions in N are BARs, which are also roughly proportional to M, the whole thing is O(M^3). This changes it to O(M^2), which is the best we can do without rewriting the whole thing. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> |
||
---|---|---|
.. | ||
user | ||
address-spaces.h | ||
cpu_ldst_template.h | ||
cpu_ldst_useronly_template.h | ||
cpu_ldst.h | ||
cpu-all.h | ||
cpu-common.h | ||
cpu-defs.h | ||
cputlb.h | ||
exec-all.h | ||
gdbstub.h | ||
gen-icount.h | ||
helper-gen.h | ||
helper-head.h | ||
helper-proto.h | ||
helper-tcg.h | ||
hwaddr.h | ||
ioport.h | ||
log.h | ||
memattrs.h | ||
memory-internal.h | ||
memory.h | ||
poison.h | ||
ram_addr.h | ||
semihost.h | ||
softmmu-semi.h | ||
tb-context.h | ||
tb-hash-xx.h | ||
tb-hash.h |