mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
e842dfb5a2
Enabling 52-bit VAs on arm64 requires that the PGD table expands from 64 entries (for the 48-bit case) to 1024 entries. This quantity, PTRS_PER_PGD is used as follows to compute which PGD entry corresponds to a given virtual address, addr: pgd_index(addr) -> (addr >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1) Userspace addresses are prefixed by 0's, so for a 48-bit userspace address, uva, the following is true: (uva >> PGDIR_SHIFT) & (1024 - 1) == (uva >> PGDIR_SHIFT) & (64 - 1) In other words, a 48-bit userspace address will have the same pgd_index when using PTRS_PER_PGD = 64 and 1024. Kernel addresses are prefixed by 1's so, given a 48-bit kernel address, kva, we have the following inequality: (kva >> PGDIR_SHIFT) & (1024 - 1) != (kva >> PGDIR_SHIFT) & (64 - 1) In other words a 48-bit kernel virtual address will have a different pgd_index when using PTRS_PER_PGD = 64 and 1024. If, however, we note that: kva = 0xFFFF << 48 + lower (where lower[63:48] == 0b) and, PGDIR_SHIFT = 42 (as we are dealing with 64KB PAGE_SIZE) We can consider: (kva >> PGDIR_SHIFT) & (1024 - 1) - (kva >> PGDIR_SHIFT) & (64 - 1) = (0xFFFF << 6) & 0x3FF - (0xFFFF << 6) & 0x3F // "lower" cancels out = 0x3C0 In other words, one can switch PTRS_PER_PGD to the 52-bit value globally provided that they increment ttbr1_el1 by 0x3C0 * 8 = 0x1E00 bytes when running with 48-bit kernel VAs (TCR_EL1.T1SZ = 16). For kernel configuration where 52-bit userspace VAs are possible, this patch offsets ttbr1_el1 and sets PTRS_PER_PGD corresponding to the 52-bit value. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com> Suggested-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Steve Capper <steve.capper@arm.com> [will: added comment to TTBR1_BADDR_4852_OFFSET calculation] Signed-off-by: Will Deacon <will.deacon@arm.com>
180 lines
5.3 KiB
ArmAsm
180 lines
5.3 KiB
ArmAsm
/*
|
|
* Hibernate low-level support
|
|
*
|
|
* Copyright (C) 2016 ARM Ltd.
|
|
* Author: James Morse <james.morse@arm.com>
|
|
*
|
|
* 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.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
#include <linux/linkage.h>
|
|
#include <linux/errno.h>
|
|
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/assembler.h>
|
|
#include <asm/cputype.h>
|
|
#include <asm/memory.h>
|
|
#include <asm/page.h>
|
|
#include <asm/virt.h>
|
|
|
|
/*
|
|
* To prevent the possibility of old and new partial table walks being visible
|
|
* in the tlb, switch the ttbr to a zero page when we invalidate the old
|
|
* records. D4.7.1 'General TLB maintenance requirements' in ARM DDI 0487A.i
|
|
* Even switching to our copied tables will cause a changed output address at
|
|
* each stage of the walk.
|
|
*/
|
|
.macro break_before_make_ttbr_switch zero_page, page_table, tmp
|
|
phys_to_ttbr \tmp, \zero_page
|
|
msr ttbr1_el1, \tmp
|
|
isb
|
|
tlbi vmalle1
|
|
dsb nsh
|
|
phys_to_ttbr \tmp, \page_table
|
|
offset_ttbr1 \tmp
|
|
msr ttbr1_el1, \tmp
|
|
isb
|
|
.endm
|
|
|
|
|
|
/*
|
|
* Resume from hibernate
|
|
*
|
|
* Loads temporary page tables then restores the memory image.
|
|
* Finally branches to cpu_resume() to restore the state saved by
|
|
* swsusp_arch_suspend().
|
|
*
|
|
* Because this code has to be copied to a 'safe' page, it can't call out to
|
|
* other functions by PC-relative address. Also remember that it may be
|
|
* mid-way through over-writing other functions. For this reason it contains
|
|
* code from flush_icache_range() and uses the copy_page() macro.
|
|
*
|
|
* This 'safe' page is mapped via ttbr0, and executed from there. This function
|
|
* switches to a copy of the linear map in ttbr1, performs the restore, then
|
|
* switches ttbr1 to the original kernel's swapper_pg_dir.
|
|
*
|
|
* All of memory gets written to, including code. We need to clean the kernel
|
|
* text to the Point of Coherence (PoC) before secondary cores can be booted.
|
|
* Because the kernel modules and executable pages mapped to user space are
|
|
* also written as data, we clean all pages we touch to the Point of
|
|
* Unification (PoU).
|
|
*
|
|
* x0: physical address of temporary page tables
|
|
* x1: physical address of swapper page tables
|
|
* x2: address of cpu_resume
|
|
* x3: linear map address of restore_pblist in the current kernel
|
|
* x4: physical address of __hyp_stub_vectors, or 0
|
|
* x5: physical address of a zero page that remains zero after resume
|
|
*/
|
|
.pushsection ".hibernate_exit.text", "ax"
|
|
ENTRY(swsusp_arch_suspend_exit)
|
|
/*
|
|
* We execute from ttbr0, change ttbr1 to our copied linear map tables
|
|
* with a break-before-make via the zero page
|
|
*/
|
|
break_before_make_ttbr_switch x5, x0, x6
|
|
|
|
mov x21, x1
|
|
mov x30, x2
|
|
mov x24, x4
|
|
mov x25, x5
|
|
|
|
/* walk the restore_pblist and use copy_page() to over-write memory */
|
|
mov x19, x3
|
|
|
|
1: ldr x10, [x19, #HIBERN_PBE_ORIG]
|
|
mov x0, x10
|
|
ldr x1, [x19, #HIBERN_PBE_ADDR]
|
|
|
|
copy_page x0, x1, x2, x3, x4, x5, x6, x7, x8, x9
|
|
|
|
add x1, x10, #PAGE_SIZE
|
|
/* Clean the copied page to PoU - based on flush_icache_range() */
|
|
raw_dcache_line_size x2, x3
|
|
sub x3, x2, #1
|
|
bic x4, x10, x3
|
|
2: dc cvau, x4 /* clean D line / unified line */
|
|
add x4, x4, x2
|
|
cmp x4, x1
|
|
b.lo 2b
|
|
|
|
ldr x19, [x19, #HIBERN_PBE_NEXT]
|
|
cbnz x19, 1b
|
|
dsb ish /* wait for PoU cleaning to finish */
|
|
|
|
/* switch to the restored kernels page tables */
|
|
break_before_make_ttbr_switch x25, x21, x6
|
|
|
|
ic ialluis
|
|
dsb ish
|
|
isb
|
|
|
|
cbz x24, 3f /* Do we need to re-initialise EL2? */
|
|
hvc #0
|
|
3: ret
|
|
|
|
.ltorg
|
|
ENDPROC(swsusp_arch_suspend_exit)
|
|
|
|
/*
|
|
* Restore the hyp stub.
|
|
* This must be done before the hibernate page is unmapped by _cpu_resume(),
|
|
* but happens before any of the hyp-stub's code is cleaned to PoC.
|
|
*
|
|
* x24: The physical address of __hyp_stub_vectors
|
|
*/
|
|
el1_sync:
|
|
msr vbar_el2, x24
|
|
eret
|
|
ENDPROC(el1_sync)
|
|
|
|
.macro invalid_vector label
|
|
\label:
|
|
b \label
|
|
ENDPROC(\label)
|
|
.endm
|
|
|
|
invalid_vector el2_sync_invalid
|
|
invalid_vector el2_irq_invalid
|
|
invalid_vector el2_fiq_invalid
|
|
invalid_vector el2_error_invalid
|
|
invalid_vector el1_sync_invalid
|
|
invalid_vector el1_irq_invalid
|
|
invalid_vector el1_fiq_invalid
|
|
invalid_vector el1_error_invalid
|
|
|
|
/* el2 vectors - switch el2 here while we restore the memory image. */
|
|
.align 11
|
|
ENTRY(hibernate_el2_vectors)
|
|
ventry el2_sync_invalid // Synchronous EL2t
|
|
ventry el2_irq_invalid // IRQ EL2t
|
|
ventry el2_fiq_invalid // FIQ EL2t
|
|
ventry el2_error_invalid // Error EL2t
|
|
|
|
ventry el2_sync_invalid // Synchronous EL2h
|
|
ventry el2_irq_invalid // IRQ EL2h
|
|
ventry el2_fiq_invalid // FIQ EL2h
|
|
ventry el2_error_invalid // Error EL2h
|
|
|
|
ventry el1_sync // Synchronous 64-bit EL1
|
|
ventry el1_irq_invalid // IRQ 64-bit EL1
|
|
ventry el1_fiq_invalid // FIQ 64-bit EL1
|
|
ventry el1_error_invalid // Error 64-bit EL1
|
|
|
|
ventry el1_sync_invalid // Synchronous 32-bit EL1
|
|
ventry el1_irq_invalid // IRQ 32-bit EL1
|
|
ventry el1_fiq_invalid // FIQ 32-bit EL1
|
|
ventry el1_error_invalid // Error 32-bit EL1
|
|
END(hibernate_el2_vectors)
|
|
|
|
.popsection
|