From f81309067ff2d84788316c513a415f6bb8c9171f Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Mon, 1 Jun 2015 23:44:46 +0100
Subject: ARM: move heavy barrier support out of line

The existing memory barrier macro causes a significant amount of code
to be inserted inline at every call site.  For example, in
gpio_set_irq_type(), we have this for mb():

c0344c08:       f57ff04e        dsb     st
c0344c0c:       e59f8190        ldr     r8, [pc, #400]  ; c0344da4 <gpio_set_irq_type+0x230>
c0344c10:       e3590004        cmp     r9, #4
c0344c14:       e5983014        ldr     r3, [r8, #20]
c0344c18:       0a000054        beq     c0344d70 <gpio_set_irq_type+0x1fc>
c0344c1c:       e3530000        cmp     r3, #0
c0344c20:       0a000004        beq     c0344c38 <gpio_set_irq_type+0xc4>
c0344c24:       e50b2030        str     r2, [fp, #-48]  ; 0xffffffd0
c0344c28:       e50bc034        str     ip, [fp, #-52]  ; 0xffffffcc
c0344c2c:       e12fff33        blx     r3
c0344c30:       e51bc034        ldr     ip, [fp, #-52]  ; 0xffffffcc
c0344c34:       e51b2030        ldr     r2, [fp, #-48]  ; 0xffffffd0
c0344c38:       e5963004        ldr     r3, [r6, #4]

Moving the outer_cache_sync() call out of line reduces the impact of
the barrier:

c0344968:       f57ff04e        dsb     st
c034496c:       e35a0004        cmp     sl, #4
c0344970:       e50b2030        str     r2, [fp, #-48]  ; 0xffffffd0
c0344974:       0a000044        beq     c0344a8c <gpio_set_irq_type+0x1b8>
c0344978:       ebf363dd        bl      c001d8f4 <arm_heavy_mb>
c034497c:       e5953004        ldr     r3, [r5, #4]

This should reduce the cache footprint of this code.  Overall, this
results in a reduction of around 20K in the kernel size:

    text    data      bss      dec     hex filename
10773970  667392 10369656 21811018 14ccf4a ../build/imx6/vmlinux-old
10754219  667392 10369656 21791267 14c8223 ../build/imx6/vmlinux-new

Another advantage to this approach is that we can finally resolve the
issue of SoCs which have their own memory barrier requirements within
multiplatform kernels (such as OMAP.)  Here, the bus interconnects
need additional handling to ensure that writes become visible in the
correct order (eg, between dma_map() operations, writes to DMA
coherent memory, and MMIO accesses.)

Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Richard Woodruff <r-woodruff2@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mach-ux500/cache-l2x0.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/arm/mach-ux500')

diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
index 7557bede7ae6..780bd13cd7e3 100644
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ b/arch/arm/mach-ux500/cache-l2x0.c
@@ -8,6 +8,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 
+#include <asm/outercache.h>
 #include <asm/hardware/cache-l2x0.h>
 
 #include "db8500-regs.h"
-- 
cgit 


From fa8ad7889d83bcf0a6cdbf6d3622f3ec019cde14 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 6 Jul 2015 12:23:53 +0100
Subject: arm: perf: factor arm_pmu core out to drivers

To enable sharing of the arm_pmu code with arm64, this patch factors it
out to drivers/perf/. A new drivers/perf directory is added for
performance monitor drivers to live under.

MAINTAINERS is updated accordingly. Files added previously without a
corresponsing MAINTAINERS update (perf_regs.c, perf_callchain.c, and
perf_event.h) are also added.

Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
[will: augmented Kconfig help slightly]
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/mach-ux500/cpu-db8500.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/arm/mach-ux500')

diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 16913800bbf9..5578dc1ab52b 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -20,10 +20,10 @@
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/regulator/machine.h>
 #include <linux/random.h>
 
-#include <asm/pmu.h>
 #include <asm/mach/map.h>
 
 #include "setup.h"
-- 
cgit