linux/arch/arm/kernel/sleep.S
Ard Biesheuvel 8b806b82bc ARM: mm: switch to swapper_pg_dir early for vmap'ed stack
When onlining a CPU, switch to swapper_pg_dir as soon as possible so
that it is guaranteed that the vmap'ed stack is mapped before it is
used.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-01-24 20:37:55 +01:00

195 lines
5.4 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <linux/threads.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
#include <asm/glue-cache.h>
#include <asm/glue-proc.h>
.text
/*
* Implementation of MPIDR hash algorithm through shifting
* and OR'ing.
*
* @dst: register containing hash result
* @rs0: register containing affinity level 0 bit shift
* @rs1: register containing affinity level 1 bit shift
* @rs2: register containing affinity level 2 bit shift
* @mpidr: register containing MPIDR value
* @mask: register containing MPIDR mask
*
* Pseudo C-code:
*
*u32 dst;
*
*compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 mpidr, u32 mask) {
* u32 aff0, aff1, aff2;
* u32 mpidr_masked = mpidr & mask;
* aff0 = mpidr_masked & 0xff;
* aff1 = mpidr_masked & 0xff00;
* aff2 = mpidr_masked & 0xff0000;
* dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2);
*}
* Input registers: rs0, rs1, rs2, mpidr, mask
* Output register: dst
* Note: input and output registers must be disjoint register sets
(eg: a macro instance with mpidr = r1 and dst = r1 is invalid)
*/
.macro compute_mpidr_hash dst, rs0, rs1, rs2, mpidr, mask
and \mpidr, \mpidr, \mask @ mask out MPIDR bits
and \dst, \mpidr, #0xff @ mask=aff0
ARM( mov \dst, \dst, lsr \rs0 ) @ dst=aff0>>rs0
THUMB( lsr \dst, \dst, \rs0 )
and \mask, \mpidr, #0xff00 @ mask = aff1
ARM( orr \dst, \dst, \mask, lsr \rs1 ) @ dst|=(aff1>>rs1)
THUMB( lsr \mask, \mask, \rs1 )
THUMB( orr \dst, \dst, \mask )
and \mask, \mpidr, #0xff0000 @ mask = aff2
ARM( orr \dst, \dst, \mask, lsr \rs2 ) @ dst|=(aff2>>rs2)
THUMB( lsr \mask, \mask, \rs2 )
THUMB( orr \dst, \dst, \mask )
.endm
/*
* Save CPU state for a suspend. This saves the CPU general purpose
* registers, and allocates space on the kernel stack to save the CPU
* specific registers and some other data for resume.
* r0 = suspend function arg0
* r1 = suspend function
* r2 = MPIDR value the resuming CPU will use
*/
ENTRY(__cpu_suspend)
stmfd sp!, {r4 - r11, lr}
#ifdef MULTI_CPU
ldr r10, =processor
ldr r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
#else
ldr r4, =cpu_suspend_size
#endif
mov r5, sp @ current virtual SP
#ifdef CONFIG_VMAP_STACK
@ Run the suspend code from the overflow stack so we don't have to rely
@ on vmalloc-to-phys conversions anywhere in the arch suspend code.
@ The original SP value captured in R5 will be restored on the way out.
ldr_this_cpu sp, overflow_stack_ptr, r6, r7
#endif
add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn
sub sp, sp, r4 @ allocate CPU state on stack
ldr r3, =sleep_save_sp
stmfd sp!, {r0, r1} @ save suspend func arg and pointer
ldr r3, [r3, #SLEEP_SAVE_SP_VIRT]
ALT_SMP(W(nop)) @ don't use adr_l inside ALT_SMP()
ALT_UP_B(1f)
adr_l r0, mpidr_hash
/* This ldmia relies on the memory layout of the mpidr_hash struct */
ldmia r0, {r1, r6-r8} @ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts
compute_mpidr_hash r0, r6, r7, r8, r2, r1
add r3, r3, r0, lsl #2
1: mov r2, r5 @ virtual SP
mov r1, r4 @ size of save block
add r0, sp, #8 @ pointer to save block
bl __cpu_suspend_save
badr lr, cpu_suspend_abort
ldmfd sp!, {r0, pc} @ call suspend fn
ENDPROC(__cpu_suspend)
.ltorg
cpu_suspend_abort:
ldmia sp!, {r1 - r3} @ pop phys pgd, virt SP, phys resume fn
teq r0, #0
moveq r0, #1 @ force non-zero value
mov sp, r2
ldmfd sp!, {r4 - r11, pc}
ENDPROC(cpu_suspend_abort)
/*
* r0 = control register value
*/
.align 5
.pushsection .idmap.text,"ax"
ENTRY(cpu_resume_mmu)
ldr r3, =cpu_resume_after_mmu
instr_sync
mcr p15, 0, r0, c1, c0, 0 @ turn on MMU, I-cache, etc
mrc p15, 0, r0, c0, c0, 0 @ read id reg
instr_sync
mov r0, r0
mov r0, r0
ret r3 @ jump to virtual address
ENDPROC(cpu_resume_mmu)
.popsection
cpu_resume_after_mmu:
#if defined(CONFIG_VMAP_STACK) && !defined(CONFIG_ARM_LPAE)
@ Before using the vmap'ed stack, we have to switch to swapper_pg_dir
@ as the ID map does not cover the vmalloc region.
mrc p15, 0, ip, c2, c0, 1 @ read TTBR1
mcr p15, 0, ip, c2, c0, 0 @ set TTBR0
instr_sync
#endif
bl cpu_init @ restore the und/abt/irq banked regs
mov r0, #0 @ return zero on success
ldmfd sp!, {r4 - r11, pc}
ENDPROC(cpu_resume_after_mmu)
.text
.align
#ifdef CONFIG_MCPM
.arm
THUMB( .thumb )
ENTRY(cpu_resume_no_hyp)
ARM_BE8(setend be) @ ensure we are in BE mode
b no_hyp
#endif
#ifdef CONFIG_MMU
.arm
ENTRY(cpu_resume_arm)
THUMB( badr r9, 1f ) @ Kernel is entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
THUMB( .thumb ) @ switch to Thumb now.
THUMB(1: )
#endif
ENTRY(cpu_resume)
ARM_BE8(setend be) @ ensure we are in BE mode
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install_secondary
#endif
safe_svcmode_maskall r1
no_hyp:
mov r1, #0
ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
ALT_UP_B(1f)
adr_l r2, mpidr_hash @ r2 = struct mpidr_hash phys address
/*
* This ldmia relies on the memory layout of the mpidr_hash
* struct mpidr_hash.
*/
ldmia r2, { r3-r6 } @ r3 = mpidr mask (r4,r5,r6) = l[0,1,2] shifts
compute_mpidr_hash r1, r4, r5, r6, r0, r3
1:
ldr_l r0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
ldr r0, [r0, r1, lsl #2]
@ load phys pgd, stack, resume fn
ARM( ldmia r0!, {r1, sp, pc} )
THUMB( ldmia r0!, {r1, r2, r3} )
THUMB( mov sp, r2 )
THUMB( bx r3 )
ENDPROC(cpu_resume)
#ifdef CONFIG_MMU
ENDPROC(cpu_resume_arm)
#endif
#ifdef CONFIG_MCPM
ENDPROC(cpu_resume_no_hyp)
#endif
.data
.align 2
.type sleep_save_sp, #object
ENTRY(sleep_save_sp)
.space SLEEP_SAVE_SP_SZ @ struct sleep_save_sp