linux/arch
Russell King 87067a935a ARM: Optimize multi-CPU tlb flushing a little more
The compiler does not conditionalize the assembly instructions for
the tlb operations, which leads to sub-optimal code being generated
when building a kernel for multiple CPUs.

We can tweak things fairly simply as the code fragment below shows:

    17f8:       e3120001        tst     r2, #1  ; 0x1
...
    1800:       0a000000        beq     1808 <handle_pte_fault+0x194>
    1804:       ee061f10        mcr     15, 0, r1, cr6, cr0, {0}
    1808:       e3120004        tst     r2, #4  ; 0x4
    180c:       0a000000        beq     1814 <handle_pte_fault+0x1a0>
    1810:       ee081f36        mcr     15, 0, r1, cr8, cr6, {1}
becomes:
    17f0:       e3120001        tst     r2, #1  ; 0x1
    17f4:       1e063f10        mcrne   15, 0, r3, cr6, cr0, {0}
    17f8:       e3120004        tst     r2, #4  ; 0x4
    17fc:       1e083f36        mcrne   15, 0, r3, cr8, cr6, {1}

Overall, for Realview with V6 and V7 CPUs configured:

   text    data     bss     dec     hex filename
4153998  207340 5371036 9732374  948116 ../build/realview/vmlinux.before
4153366  207332 5371036 9731734  947e96 ../build/realview/vmlinux.after

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2012-03-24 09:38:52 +00:00
..
alpha Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci 2012-01-11 18:50:26 -08:00
arm ARM: Optimize multi-CPU tlb flushing a little more 2012-03-24 09:38:52 +00:00
avr32 treewide: remove useless NORET_TYPE macro and uses 2012-01-12 20:13:03 -08:00
blackfin Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci 2012-01-11 18:50:26 -08:00
c6x C6X: replace tick_nohz_stop/restart_sched_tick calls 2012-01-08 15:13:16 -05:00
cris lib: use generic pci_iomap on all architectures 2012-01-10 18:04:27 -08:00
frv Merge branch 'for-next' of git://git.infradead.org/users/dhowells/linux-headers 2012-01-14 18:03:30 -08:00
h8300 Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci 2012-01-11 18:50:26 -08:00
hexagon
ia64 Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux 2012-01-18 15:51:48 -08:00
m32r Merge branch 'for-next' of git://git.infradead.org/users/dhowells/linux-headers 2012-01-14 18:03:30 -08:00
m68k treewide: convert uses of ATTRIB_NORETURN to __noreturn 2012-01-12 20:13:03 -08:00
microblaze Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
mips Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
mn10300 Merge branch 'for-next' of git://git.infradead.org/users/dhowells/linux-headers 2012-01-14 18:03:30 -08:00
openrisc Merge branch 'kbuild' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild 2012-01-16 14:34:54 -08:00
parisc parisc, exec: remove redundant set_fs(USER_DS) 2012-01-12 20:13:04 -08:00
powerpc Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
s390 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
score cpu: Register a generic CPU device on architectures that currently do not 2012-01-11 15:50:11 -08:00
sh Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
sparc Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
tile Merge branch 'for-next' of git://git.infradead.org/users/dhowells/linux-headers 2012-01-14 18:03:30 -08:00
um Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit 2012-01-17 16:41:31 -08:00
unicore32 Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci 2012-01-11 18:50:26 -08:00
x86 Merge branches 'sched-urgent-for-linus', 'perf-urgent-for-linus' and 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2012-01-19 14:53:06 -08:00
xtensa audit: inline audit_syscall_entry to reduce burden on archs 2012-01-17 16:16:56 -05:00
.gitignore
Kconfig mm,x86,um: move CMPXCHG_DOUBLE config option 2012-01-12 20:13:03 -08:00