linux/arch/arm/mm/proc-v7-3level.S

149 lines
3.8 KiB
ArmAsm
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* arch/arm/mm/proc-v7-3level.S
*
* Copyright (C) 2001 Deep Blue Solutions Ltd.
* Copyright (C) 2011 ARM Ltd.
* Author: Catalin Marinas <catalin.marinas@arm.com>
* based on arch/arm/mm/proc-v7-2level.S
*/
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>
2014-06-30 23:29:12 +08:00
#include <asm/assembler.h>
#define TTB_IRGN_NC (0 << 8)
#define TTB_IRGN_WBWA (1 << 8)
#define TTB_IRGN_WT (2 << 8)
#define TTB_IRGN_WB (3 << 8)
#define TTB_RGN_NC (0 << 10)
#define TTB_RGN_OC_WBWA (1 << 10)
#define TTB_RGN_OC_WT (2 << 10)
#define TTB_RGN_OC_WB (3 << 10)
#define TTB_S (3 << 12)
#define TTB_EAE (1 << 31)
/* 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_RGN_OC_WBWA)
#define PMD_FLAGS_SMP (PMD_SECT_WBWA|PMD_SECT_S)
#ifndef __ARMEB__
# define rpgdl r0
# define rpgdh r1
#else
# define rpgdl r1
# define rpgdh r0
#endif
/*
* cpu_v7_switch_mm(pgd_phys, tsk)
*
* Set the translation table base pointer to be pgd_phys (physical address of
* the new TTB).
*/
ENTRY(cpu_v7_switch_mm)
#ifdef CONFIG_MMU
mmid r2, r2
asid r2, r2
orr rpgdh, rpgdh, r2, lsl #(48 - 32) @ upper 32-bits of pgd
mcrr p15, 0, rpgdl, rpgdh, c2 @ set TTB 0
isb
#endif
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>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(cpu_v7_switch_mm)
ARM: 8037/1: mm: support big-endian page tables When enable LPAE and big-endian in a hisilicon board, while specify mem=384M mem=512M@7680M, will get bad page state: Freeing unused kernel memory: 180K (c0466000 - c0493000) BUG: Bad page state in process init pfn:fa442 page:c7749840 count:0 mapcount:-1 mapping: (null) index:0x0 page flags: 0x40000400(reserved) Modules linked in: CPU: 0 PID: 1 Comm: init Not tainted 3.10.27+ #66 [<c000f5f0>] (unwind_backtrace+0x0/0x11c) from [<c000cbc4>] (show_stack+0x10/0x14) [<c000cbc4>] (show_stack+0x10/0x14) from [<c009e448>] (bad_page+0xd4/0x104) [<c009e448>] (bad_page+0xd4/0x104) from [<c009e520>] (free_pages_prepare+0xa8/0x14c) [<c009e520>] (free_pages_prepare+0xa8/0x14c) from [<c009f8ec>] (free_hot_cold_page+0x18/0xf0) [<c009f8ec>] (free_hot_cold_page+0x18/0xf0) from [<c00b5444>] (handle_pte_fault+0xcf4/0xdc8) [<c00b5444>] (handle_pte_fault+0xcf4/0xdc8) from [<c00b6458>] (handle_mm_fault+0xf4/0x120) [<c00b6458>] (handle_mm_fault+0xf4/0x120) from [<c0013754>] (do_page_fault+0xfc/0x354) [<c0013754>] (do_page_fault+0xfc/0x354) from [<c0008400>] (do_DataAbort+0x2c/0x90) [<c0008400>] (do_DataAbort+0x2c/0x90) from [<c0008fb4>] (__dabt_usr+0x34/0x40) The bad pfn:fa442 is not system memory(mem=384M mem=512M@7680M), after debugging, I find in page fault handler, will get wrong pfn from pte just after set pte, as follow: do_anonymous_page() { ... set_pte_at(mm, address, page_table, entry); //debug code pfn = pte_pfn(entry); pr_info("pfn:0x%lx, pte:0x%llxn", pfn, pte_val(entry)); //read out the pte just set new_pte = pte_offset_map(pmd, address); new_pfn = pte_pfn(*new_pte); pr_info("new pfn:0x%lx, new pte:0x%llxn", pfn, pte_val(entry)); ... } pfn: 0x1fa4f5, pte:0xc00001fa4f575f new_pfn:0xfa4f5, new_pte:0xc00000fa4f5f5f //new pfn/pte is wrong. The bug is happened in cpu_v7_set_pte_ext(ptep, pte): An LPAE PTE is a 64bit quantity, passed to cpu_v7_set_pte_ext in the r2 and r3 registers. On an LE kernel, r2 contains the LSB of the PTE, and r3 the MSB. On a BE kernel, the assignment is reversed. Unfortunately, the current code always assumes the LE case, leading to corruption of the PTE when clearing/setting bits. This patch fixes this issue much like it has been done already in the cpu_v7_switch_mm case. CC stable <stable@vger.kernel.org> Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-04-24 10:45:56 +08:00
#ifdef __ARMEB__
#define rl r3
#define rh r2
#else
#define rl r2
#define rh r3
#endif
/*
* cpu_v7_set_pte_ext(ptep, pte)
*
* Set a level 2 translation table entry.
* - ptep - pointer to level 3 translation table entry
* - pte - PTE value to store (64-bit in r2 and r3)
*/
ENTRY(cpu_v7_set_pte_ext)
#ifdef CONFIG_MMU
ARM: 8037/1: mm: support big-endian page tables When enable LPAE and big-endian in a hisilicon board, while specify mem=384M mem=512M@7680M, will get bad page state: Freeing unused kernel memory: 180K (c0466000 - c0493000) BUG: Bad page state in process init pfn:fa442 page:c7749840 count:0 mapcount:-1 mapping: (null) index:0x0 page flags: 0x40000400(reserved) Modules linked in: CPU: 0 PID: 1 Comm: init Not tainted 3.10.27+ #66 [<c000f5f0>] (unwind_backtrace+0x0/0x11c) from [<c000cbc4>] (show_stack+0x10/0x14) [<c000cbc4>] (show_stack+0x10/0x14) from [<c009e448>] (bad_page+0xd4/0x104) [<c009e448>] (bad_page+0xd4/0x104) from [<c009e520>] (free_pages_prepare+0xa8/0x14c) [<c009e520>] (free_pages_prepare+0xa8/0x14c) from [<c009f8ec>] (free_hot_cold_page+0x18/0xf0) [<c009f8ec>] (free_hot_cold_page+0x18/0xf0) from [<c00b5444>] (handle_pte_fault+0xcf4/0xdc8) [<c00b5444>] (handle_pte_fault+0xcf4/0xdc8) from [<c00b6458>] (handle_mm_fault+0xf4/0x120) [<c00b6458>] (handle_mm_fault+0xf4/0x120) from [<c0013754>] (do_page_fault+0xfc/0x354) [<c0013754>] (do_page_fault+0xfc/0x354) from [<c0008400>] (do_DataAbort+0x2c/0x90) [<c0008400>] (do_DataAbort+0x2c/0x90) from [<c0008fb4>] (__dabt_usr+0x34/0x40) The bad pfn:fa442 is not system memory(mem=384M mem=512M@7680M), after debugging, I find in page fault handler, will get wrong pfn from pte just after set pte, as follow: do_anonymous_page() { ... set_pte_at(mm, address, page_table, entry); //debug code pfn = pte_pfn(entry); pr_info("pfn:0x%lx, pte:0x%llxn", pfn, pte_val(entry)); //read out the pte just set new_pte = pte_offset_map(pmd, address); new_pfn = pte_pfn(*new_pte); pr_info("new pfn:0x%lx, new pte:0x%llxn", pfn, pte_val(entry)); ... } pfn: 0x1fa4f5, pte:0xc00001fa4f575f new_pfn:0xfa4f5, new_pte:0xc00000fa4f5f5f //new pfn/pte is wrong. The bug is happened in cpu_v7_set_pte_ext(ptep, pte): An LPAE PTE is a 64bit quantity, passed to cpu_v7_set_pte_ext in the r2 and r3 registers. On an LE kernel, r2 contains the LSB of the PTE, and r3 the MSB. On a BE kernel, the assignment is reversed. Unfortunately, the current code always assumes the LE case, leading to corruption of the PTE when clearing/setting bits. This patch fixes this issue much like it has been done already in the cpu_v7_switch_mm case. CC stable <stable@vger.kernel.org> Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-04-24 10:45:56 +08:00
tst rl, #L_PTE_VALID
beq 1f
ARM: 8037/1: mm: support big-endian page tables When enable LPAE and big-endian in a hisilicon board, while specify mem=384M mem=512M@7680M, will get bad page state: Freeing unused kernel memory: 180K (c0466000 - c0493000) BUG: Bad page state in process init pfn:fa442 page:c7749840 count:0 mapcount:-1 mapping: (null) index:0x0 page flags: 0x40000400(reserved) Modules linked in: CPU: 0 PID: 1 Comm: init Not tainted 3.10.27+ #66 [<c000f5f0>] (unwind_backtrace+0x0/0x11c) from [<c000cbc4>] (show_stack+0x10/0x14) [<c000cbc4>] (show_stack+0x10/0x14) from [<c009e448>] (bad_page+0xd4/0x104) [<c009e448>] (bad_page+0xd4/0x104) from [<c009e520>] (free_pages_prepare+0xa8/0x14c) [<c009e520>] (free_pages_prepare+0xa8/0x14c) from [<c009f8ec>] (free_hot_cold_page+0x18/0xf0) [<c009f8ec>] (free_hot_cold_page+0x18/0xf0) from [<c00b5444>] (handle_pte_fault+0xcf4/0xdc8) [<c00b5444>] (handle_pte_fault+0xcf4/0xdc8) from [<c00b6458>] (handle_mm_fault+0xf4/0x120) [<c00b6458>] (handle_mm_fault+0xf4/0x120) from [<c0013754>] (do_page_fault+0xfc/0x354) [<c0013754>] (do_page_fault+0xfc/0x354) from [<c0008400>] (do_DataAbort+0x2c/0x90) [<c0008400>] (do_DataAbort+0x2c/0x90) from [<c0008fb4>] (__dabt_usr+0x34/0x40) The bad pfn:fa442 is not system memory(mem=384M mem=512M@7680M), after debugging, I find in page fault handler, will get wrong pfn from pte just after set pte, as follow: do_anonymous_page() { ... set_pte_at(mm, address, page_table, entry); //debug code pfn = pte_pfn(entry); pr_info("pfn:0x%lx, pte:0x%llxn", pfn, pte_val(entry)); //read out the pte just set new_pte = pte_offset_map(pmd, address); new_pfn = pte_pfn(*new_pte); pr_info("new pfn:0x%lx, new pte:0x%llxn", pfn, pte_val(entry)); ... } pfn: 0x1fa4f5, pte:0xc00001fa4f575f new_pfn:0xfa4f5, new_pte:0xc00000fa4f5f5f //new pfn/pte is wrong. The bug is happened in cpu_v7_set_pte_ext(ptep, pte): An LPAE PTE is a 64bit quantity, passed to cpu_v7_set_pte_ext in the r2 and r3 registers. On an LE kernel, r2 contains the LSB of the PTE, and r3 the MSB. On a BE kernel, the assignment is reversed. Unfortunately, the current code always assumes the LE case, leading to corruption of the PTE when clearing/setting bits. This patch fixes this issue much like it has been done already in the cpu_v7_switch_mm case. CC stable <stable@vger.kernel.org> Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-04-24 10:45:56 +08:00
tst rh, #1 << (57 - 32) @ L_PTE_NONE
bicne rl, #L_PTE_VALID
bne 1f
eor ip, rh, #1 << (55 - 32) @ toggle L_PTE_DIRTY in temp reg to
@ test for !L_PTE_DIRTY || L_PTE_RDONLY
tst ip, #1 << (55 - 32) | 1 << (58 - 32)
orrne rl, #PTE_AP2
biceq rl, #PTE_AP2
1: strd r2, r3, [r0]
ALT_SMP(W(nop))
ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte
#endif
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>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(cpu_v7_set_pte_ext)
/*
* Memory region attributes for LPAE (defined in pgtable-3level.h):
*
* n = AttrIndx[2:0]
*
* n MAIR
* UNCACHED 000 00000000
* BUFFERABLE 001 01000100
* DEV_WC 001 01000100
* WRITETHROUGH 010 10101010
* WRITEBACK 011 11101110
* DEV_CACHED 011 11101110
* DEV_SHARED 100 00000100
* DEV_NONSHARED 100 00000100
* unused 101
* unused 110
* WRITEALLOC 111 11111111
*/
.equ PRRR, 0xeeaa4400 @ MAIR0
.equ NMRR, 0xff000004 @ MAIR1
/*
* Macro for setting up the TTBRx and TTBCR registers.
* - \ttbr1 updated.
*/
.macro v7_ttb_setup, zero, ttbr0l, ttbr0h, ttbr1, tmp
ldr \tmp, =swapper_pg_dir @ swapper_pg_dir virtual address
cmp \ttbr1, \tmp, lsr #12 @ PHYS_OFFSET > PAGE_OFFSET?
mov \tmp, #TTB_EAE @ for TTB control egister
ALT_SMP(orr \tmp, \tmp, #TTB_FLAGS_SMP)
ALT_UP(orr \tmp, \tmp, #TTB_FLAGS_UP)
ALT_SMP(orr \tmp, \tmp, #TTB_FLAGS_SMP << 16)
ALT_UP(orr \tmp, \tmp, #TTB_FLAGS_UP << 16)
/*
* Only use split TTBRs if PHYS_OFFSET <= PAGE_OFFSET (cmp above),
* otherwise booting secondary CPUs would end up using TTBR1 for the
* identity mapping set up in TTBR0.
*/
orrls \tmp, \tmp, #TTBR1_SIZE @ TTBCR.T1SZ
mcr p15, 0, \tmp, c2, c0, 2 @ TTBCR
mov \tmp, \ttbr1, lsr #20
mov \ttbr1, \ttbr1, lsl #12
addls \ttbr1, \ttbr1, #TTBR1_OFFSET
mcrr p15, 1, \ttbr1, \tmp, c2 @ load TTBR1
.endm
/*
* AT
* TFR EV X F IHD LR S
* .EEE ..EE PUI. .TAT 4RVI ZWRS BLDP WCAM
* rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
* 11 0 110 0 0011 1100 .111 1101 < we want
*/
.align 2
.type v7_crval, #object
v7_crval:
crval clear=0x0122c302, mmuset=0x30c03c7d, ucset=0x00c01c7c