6ebbf2ce43
ARMv6 and greater introduced a new instruction ("bx") which can be used
to return from function calls. Recent CPUs perform better when the
"bx lr" instruction is used rather than the "mov pc, lr" instruction,
and this sequence is strongly recommended to be used by the ARM
architecture manual (section A.4.1.1).
We provide a new macro "ret" with all its variants for the condition
code which will resolve to the appropriate instruction.
Rather than doing this piecemeal, and miss some instances, change all
the "mov pc" instances to use the new macro, with the exception of
the "movs" instruction and the kprobes code. This allows us to detect
the "mov pc, lr" case and fix it up - and also gives us the possibility
of deploying this for other registers depending on the CPU selection.
Reported-by: Will Deacon <will.deacon@arm.com>
Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S
Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood
Tested-by: Shawn Guo <shawn.guo@freescale.com>
Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385
Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M
Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
93 lines
2.6 KiB
ArmAsm
93 lines
2.6 KiB
ArmAsm
/*
|
|
* linux/arch/arm/mm/tlb-v6.S
|
|
*
|
|
* Copyright (C) 1997-2002 Russell King
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* ARM architecture version 6 TLB handling functions.
|
|
* These assume a split I/D TLB.
|
|
*/
|
|
#include <linux/init.h>
|
|
#include <linux/linkage.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/assembler.h>
|
|
#include <asm/page.h>
|
|
#include <asm/tlbflush.h>
|
|
#include "proc-macros.S"
|
|
|
|
#define HARVARD_TLB
|
|
|
|
/*
|
|
* v6wbi_flush_user_tlb_range(start, end, vma)
|
|
*
|
|
* Invalidate a range of TLB entries in the specified address space.
|
|
*
|
|
* - start - start address (may not be aligned)
|
|
* - end - end address (exclusive, may not be aligned)
|
|
* - vma - vma_struct describing address range
|
|
*
|
|
* It is assumed that:
|
|
* - the "Invalidate single entry" instruction will invalidate
|
|
* both the I and the D TLBs on Harvard-style TLBs
|
|
*/
|
|
ENTRY(v6wbi_flush_user_tlb_range)
|
|
vma_vm_mm r3, r2 @ get vma->vm_mm
|
|
mov ip, #0
|
|
mmid r3, r3 @ get vm_mm->context.id
|
|
mcr p15, 0, ip, c7, c10, 4 @ drain write buffer
|
|
mov r0, r0, lsr #PAGE_SHIFT @ align address
|
|
mov r1, r1, lsr #PAGE_SHIFT
|
|
asid r3, r3 @ mask ASID
|
|
orr r0, r3, r0, lsl #PAGE_SHIFT @ Create initial MVA
|
|
mov r1, r1, lsl #PAGE_SHIFT
|
|
vma_vm_flags r2, r2 @ get vma->vm_flags
|
|
1:
|
|
#ifdef HARVARD_TLB
|
|
mcr p15, 0, r0, c8, c6, 1 @ TLB invalidate D MVA (was 1)
|
|
tst r2, #VM_EXEC @ Executable area ?
|
|
mcrne p15, 0, r0, c8, c5, 1 @ TLB invalidate I MVA (was 1)
|
|
#else
|
|
mcr p15, 0, r0, c8, c7, 1 @ TLB invalidate MVA (was 1)
|
|
#endif
|
|
add r0, r0, #PAGE_SZ
|
|
cmp r0, r1
|
|
blo 1b
|
|
mcr p15, 0, ip, c7, c10, 4 @ data synchronization barrier
|
|
ret lr
|
|
|
|
/*
|
|
* v6wbi_flush_kern_tlb_range(start,end)
|
|
*
|
|
* Invalidate a range of kernel TLB entries
|
|
*
|
|
* - start - start address (may not be aligned)
|
|
* - end - end address (exclusive, may not be aligned)
|
|
*/
|
|
ENTRY(v6wbi_flush_kern_tlb_range)
|
|
mov r2, #0
|
|
mcr p15, 0, r2, c7, c10, 4 @ drain write buffer
|
|
mov r0, r0, lsr #PAGE_SHIFT @ align address
|
|
mov r1, r1, lsr #PAGE_SHIFT
|
|
mov r0, r0, lsl #PAGE_SHIFT
|
|
mov r1, r1, lsl #PAGE_SHIFT
|
|
1:
|
|
#ifdef HARVARD_TLB
|
|
mcr p15, 0, r0, c8, c6, 1 @ TLB invalidate D MVA
|
|
mcr p15, 0, r0, c8, c5, 1 @ TLB invalidate I MVA
|
|
#else
|
|
mcr p15, 0, r0, c8, c7, 1 @ TLB invalidate MVA
|
|
#endif
|
|
add r0, r0, #PAGE_SZ
|
|
cmp r0, r1
|
|
blo 1b
|
|
mcr p15, 0, r2, c7, c10, 4 @ data synchronization barrier
|
|
mcr p15, 0, r2, c7, c5, 4 @ prefetch flush (isb)
|
|
ret lr
|
|
|
|
__INIT
|
|
|
|
/* define struct cpu_tlb_fns (see <asm/tlbflush.h> and proc-macros.S) */
|
|
define_tlb_functions v6wbi, v6wbi_tlb_flags
|