x86: Improve Intel microcode loader performance
We've noticed that on large SGI UV system configurations,
running microcode.ctl can take very long periods of time. This
is due to the large number of vmalloc/vfree calls made by the
Intel generic_load_microcode() logic.
By reusing allocated space, the following patch reduces the time
to run microcode.ctl on a 1024 cpu system from approximately 80
seconds down to 1 or 2 seconds.
Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Acked-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Bill Davidsen <davidsen@tmr.com>
LKML-Reference: <20100305174203.GA19638@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 85a343e..3561702 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -343,10 +343,11 @@
int (*get_ucode_data)(void *, const void *, size_t))
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- u8 *ucode_ptr = data, *new_mc = NULL, *mc;
+ u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
int new_rev = uci->cpu_sig.rev;
unsigned int leftover = size;
enum ucode_state state = UCODE_OK;
+ unsigned int curr_mc_size = 0;
while (leftover) {
struct microcode_header_intel mc_header;
@@ -361,9 +362,15 @@
break;
}
- mc = vmalloc(mc_size);
- if (!mc)
- break;
+ /* For performance reasons, reuse mc area when possible */
+ if (!mc || mc_size > curr_mc_size) {
+ if (mc)
+ vfree(mc);
+ mc = vmalloc(mc_size);
+ if (!mc)
+ break;
+ curr_mc_size = mc_size;
+ }
if (get_ucode_data(mc, ucode_ptr, mc_size) ||
microcode_sanity_check(mc) < 0) {
@@ -376,13 +383,16 @@
vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
- } else
- vfree(mc);
+ mc = NULL; /* trigger new vmalloc */
+ }
ucode_ptr += mc_size;
leftover -= mc_size;
}
+ if (mc)
+ vfree(mc);
+
if (leftover) {
if (new_mc)
vfree(new_mc);