[PATCH] x86_64: Basic reorder infrastructure
This patch puts the infrastructure in place to allow for a reordering of functions based inside the vmlinux. The general idea is that it is possible to put all "common" functions into the first 2Mb of the code, so that they are covered by one TLB entry. This as opposed to the current situation where a typical vmlinux covers about 3.5Mb (on x86-64) and thus 2 TLB entries. This is done by enabling the -ffunction-sections flag in gcc, which puts each function in its own ELF section, so that the linker can then order them in a way defined by the linker script. As per previous discussions, Linus said he wanted a "static" list for this, eg a list provided by the kernel tarbal, so that most people have the same ordering at least. A script is provided to create this list based on readprofile(1) output. The included list is provisional, and entirely biased on my own testbox and me running a few kernel compiles and some other things. I think that to get to a better list we need to invite people to submit their own profiles, and somehow add those all up and base the final list on that. I'm willing to do that effort if this is ends up being the prefered approach. Such an effort probably needs to be repeated like once a year or so to adopt to the changing nature of the kernel. Made it a CONFIG with default n because it increases link times dramatically. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
parent
9b2a13b963
commit
4bdc3b7f1b
|
@ -464,6 +464,14 @@ config SECCOMP
|
|||
|
||||
source kernel/Kconfig.hz
|
||||
|
||||
config REORDER
|
||||
bool "Function reordering"
|
||||
default n
|
||||
help
|
||||
This option enables the toolchain to reorder functions for a more
|
||||
optimal TLB usage. If you have pretty much any version of binutils,
|
||||
this can increase your kernel build time by roughly one minute.
|
||||
|
||||
endmenu
|
||||
|
||||
#
|
||||
|
|
|
@ -36,6 +36,7 @@ CFLAGS += -m64
|
|||
CFLAGS += -mno-red-zone
|
||||
CFLAGS += -mcmodel=kernel
|
||||
CFLAGS += -pipe
|
||||
cflags-$(CONFIG_REORDER) += -ffunction-sections
|
||||
# this makes reading assembly source easier, but produces worse code
|
||||
# actually it makes the kernel smaller too.
|
||||
CFLAGS += -fno-reorder-blocks
|
||||
|
|
1286
arch/x86_64/kernel/functionlist
Normal file
1286
arch/x86_64/kernel/functionlist
Normal file
File diff suppressed because it is too large
Load Diff
|
@ -20,7 +20,12 @@ SECTIONS
|
|||
phys_startup_64 = startup_64 - LOAD_OFFSET;
|
||||
_text = .; /* Text and read-only data */
|
||||
.text : AT(ADDR(.text) - LOAD_OFFSET) {
|
||||
/* First the code that has to be first for bootstrapping */
|
||||
*(.bootstrap.text)
|
||||
/* Then all the functions that are "hot" in profiles, to group them
|
||||
onto the same hugetlb entry */
|
||||
#include "functionlist"
|
||||
/* Then the rest */
|
||||
*(.text)
|
||||
SCHED_TEXT
|
||||
LOCK_TEXT
|
||||
|
|
21
scripts/profile2linkerlist.pl
Normal file
21
scripts/profile2linkerlist.pl
Normal file
|
@ -0,0 +1,21 @@
|
|||
#!/usr/bin/perl
|
||||
|
||||
#
|
||||
# Takes a (sorted) output of readprofile and turns it into a list suitable for
|
||||
# linker scripts
|
||||
#
|
||||
# usage:
|
||||
# readprofile | sort -rn | perl profile2linkerlist.pl > functionlist
|
||||
#
|
||||
|
||||
while (<>) {
|
||||
my $line = $_;
|
||||
|
||||
$_ =~ /\W*[0-9]+\W*([a-zA-Z\_0-9]+)\W*[0-9]+/;
|
||||
|
||||
if ( ($line =~ /unknown/) || ($line =~ /total/)) {
|
||||
|
||||
} else {
|
||||
print "*(.text.$1)\n";
|
||||
}
|
||||
}
|
Loading…
Reference in New Issue
Block a user