linux/arch/arm/mm/proc-v7-2level.S
Russell King 6ebbf2ce43 ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+
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>
2014-07-18 12:29:04 +01:00

166 lines
4.3 KiB
ArmAsm

/*
* arch/arm/mm/proc-v7-2level.S
*
* Copyright (C) 2001 Deep Blue Solutions Ltd.
*
* 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.
*/
#define TTB_S (1 << 1)
#define TTB_RGN_NC (0 << 3)
#define TTB_RGN_OC_WBWA (1 << 3)
#define TTB_RGN_OC_WT (2 << 3)
#define TTB_RGN_OC_WB (3 << 3)
#define TTB_NOS (1 << 5)
#define TTB_IRGN_NC ((0 << 0) | (0 << 6))
#define TTB_IRGN_WBWA ((0 << 0) | (1 << 6))
#define TTB_IRGN_WT ((1 << 0) | (0 << 6))
#define TTB_IRGN_WB ((1 << 0) | (1 << 6))
/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
#define TTB_FLAGS_UP TTB_IRGN_WB|TTB_RGN_OC_WB
#define PMD_FLAGS_UP PMD_SECT_WB
/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
#define TTB_FLAGS_SMP TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
#define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S
/*
* cpu_v7_switch_mm(pgd_phys, tsk)
*
* Set the translation table base pointer to be pgd_phys
*
* - pgd_phys - physical address of new TTB
*
* It is assumed that:
* - we are not using split page tables
*/
ENTRY(cpu_v7_switch_mm)
#ifdef CONFIG_MMU
mov r2, #0
mmid r1, r1 @ get mm->context.id
ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP)
ALT_UP(orr r0, r0, #TTB_FLAGS_UP)
#ifdef CONFIG_ARM_ERRATA_430973
mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB
#endif
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrc p15, 0, r2, c13, c0, 1 @ read current context ID
lsr r2, r2, #8 @ extract the PID
bfi r1, r2, #8, #24 @ insert into new context ID
#endif
#ifdef CONFIG_ARM_ERRATA_754322
dsb
#endif
mcr p15, 0, r1, c13, c0, 1 @ set context ID
isb
mcr p15, 0, r0, c2, c0, 0 @ set TTB 0
isb
#endif
bx lr
ENDPROC(cpu_v7_switch_mm)
/*
* cpu_v7_set_pte_ext(ptep, pte)
*
* Set a level 2 translation table entry.
*
* - ptep - pointer to level 2 translation table entry
* (hardware version is stored at +2048 bytes)
* - pte - PTE value to store
* - ext - value for extended PTE bits
*/
ENTRY(cpu_v7_set_pte_ext)
#ifdef CONFIG_MMU
str r1, [r0] @ linux version
bic r3, r1, #0x000003f0
bic r3, r3, #PTE_TYPE_MASK
orr r3, r3, r2
orr r3, r3, #PTE_EXT_AP0 | 2
tst r1, #1 << 4
orrne r3, r3, #PTE_EXT_TEX(1)
eor r1, r1, #L_PTE_DIRTY
tst r1, #L_PTE_RDONLY | L_PTE_DIRTY
orrne r3, r3, #PTE_EXT_APX
tst r1, #L_PTE_USER
orrne r3, r3, #PTE_EXT_AP1
tst r1, #L_PTE_XN
orrne r3, r3, #PTE_EXT_XN
tst r1, #L_PTE_YOUNG
tstne r1, #L_PTE_VALID
eorne r1, r1, #L_PTE_NONE
tstne r1, #L_PTE_NONE
moveq r3, #0
ARM( str r3, [r0, #2048]! )
THUMB( add r0, r0, #2048 )
THUMB( str r3, [r0] )
ALT_SMP(W(nop))
ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte
#endif
bx lr
ENDPROC(cpu_v7_set_pte_ext)
/*
* Memory region attributes with SCTLR.TRE=1
*
* n = TEX[0],C,B
* TR = PRRR[2n+1:2n] - memory type
* IR = NMRR[2n+1:2n] - inner cacheable property
* OR = NMRR[2n+17:2n+16] - outer cacheable property
*
* n TR IR OR
* UNCACHED 000 00
* BUFFERABLE 001 10 00 00
* WRITETHROUGH 010 10 10 10
* WRITEBACK 011 10 11 11
* reserved 110
* WRITEALLOC 111 10 01 01
* DEV_SHARED 100 01
* DEV_NONSHARED 100 01
* DEV_WC 001 10
* DEV_CACHED 011 10
*
* Other attributes:
*
* DS0 = PRRR[16] = 0 - device shareable property
* DS1 = PRRR[17] = 1 - device shareable property
* NS0 = PRRR[18] = 0 - normal shareable property
* NS1 = PRRR[19] = 1 - normal shareable property
* NOS = PRRR[24+n] = 1 - not outer shareable
*/
.equ PRRR, 0xff0a81a8
.equ NMRR, 0x40e040e0
/*
* Macro for setting up the TTBRx and TTBCR registers.
* - \ttb0 and \ttb1 updated with the corresponding flags.
*/
.macro v7_ttb_setup, zero, ttbr0, ttbr1, tmp
mcr p15, 0, \zero, c2, c0, 2 @ TTB control register
ALT_SMP(orr \ttbr0, \ttbr0, #TTB_FLAGS_SMP)
ALT_UP(orr \ttbr0, \ttbr0, #TTB_FLAGS_UP)
ALT_SMP(orr \ttbr1, \ttbr1, #TTB_FLAGS_SMP)
ALT_UP(orr \ttbr1, \ttbr1, #TTB_FLAGS_UP)
mcr p15, 0, \ttbr1, c2, c0, 1 @ load TTB1
.endm
/* AT
* TFR EV X F I D LR S
* .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
* rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
* 01 0 110 0011 1100 .111 1101 < we want
*/
.align 2
.type v7_crval, #object
v7_crval:
crval clear=0x2120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c