linux_dsm_epyc7002/arch/arm64/kernel/sleep.S
Ard Biesheuvel bc9f3d7788 arm64: kernel: avoid literal load of virtual address with MMU off
Literal loads of virtual addresses are subject to runtime relocation when
CONFIG_RELOCATABLE=y, and given that the relocation routines run with the
MMU and caches enabled, literal loads of relocated values performed with
the MMU off are not guaranteed to return the latest value unless the
memory covering the literal is cleaned to the PoC explicitly.

So defer the literal load until after the MMU has been enabled, just like
we do for primary_switch() and secondary_switch() in head.S.

Fixes: 1e48ef7fcc ("arm64: add support for building vmlinux as a relocatable PIE binary")
Cc: <stable@vger.kernel.org> # 4.6+
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-08-17 17:37:37 +01:00

157 lines
4.7 KiB
ArmAsm

#include <linux/errno.h>
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
.text
/*
* Implementation of MPIDR_EL1 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
* @rs3: register containing affinity level 3 bit shift
* @mpidr: register containing MPIDR_EL1 value
* @mask: register containing MPIDR mask
*
* Pseudo C-code:
*
*u32 dst;
*
*compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 rs3, u64 mpidr, u64 mask) {
* u32 aff0, aff1, aff2, aff3;
* u64 mpidr_masked = mpidr & mask;
* aff0 = mpidr_masked & 0xff;
* aff1 = mpidr_masked & 0xff00;
* aff2 = mpidr_masked & 0xff0000;
* aff2 = mpidr_masked & 0xff00000000;
* dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3);
*}
* Input registers: rs0, rs1, rs2, rs3, mpidr, mask
* Output register: dst
* Note: input and output registers must be disjoint register sets
(eg: a macro instance with mpidr = x1 and dst = x1 is invalid)
*/
.macro compute_mpidr_hash dst, rs0, rs1, rs2, rs3, mpidr, mask
and \mpidr, \mpidr, \mask // mask out MPIDR bits
and \dst, \mpidr, #0xff // mask=aff0
lsr \dst ,\dst, \rs0 // dst=aff0>>rs0
and \mask, \mpidr, #0xff00 // mask = aff1
lsr \mask ,\mask, \rs1
orr \dst, \dst, \mask // dst|=(aff1>>rs1)
and \mask, \mpidr, #0xff0000 // mask = aff2
lsr \mask ,\mask, \rs2
orr \dst, \dst, \mask // dst|=(aff2>>rs2)
and \mask, \mpidr, #0xff00000000 // mask = aff3
lsr \mask ,\mask, \rs3
orr \dst, \dst, \mask // dst|=(aff3>>rs3)
.endm
/*
* Save CPU state in the provided sleep_stack_data area, and publish its
* location for cpu_resume()'s use in sleep_save_stash.
*
* cpu_resume() will restore this saved state, and return. Because the
* link-register is saved and restored, it will appear to return from this
* function. So that the caller can tell the suspend/resume paths apart,
* __cpu_suspend_enter() will always return a non-zero value, whereas the
* path through cpu_resume() will return 0.
*
* x0 = struct sleep_stack_data area
*/
ENTRY(__cpu_suspend_enter)
stp x29, lr, [x0, #SLEEP_STACK_DATA_CALLEE_REGS]
stp x19, x20, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+16]
stp x21, x22, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+32]
stp x23, x24, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+48]
stp x25, x26, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+64]
stp x27, x28, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+80]
/* save the sp in cpu_suspend_ctx */
mov x2, sp
str x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP]
/* find the mpidr_hash */
ldr x1, =sleep_save_stash
ldr x1, [x1]
mrs x7, mpidr_el1
ldr x9, =mpidr_hash
ldr x10, [x9, #MPIDR_HASH_MASK]
/*
* Following code relies on the struct mpidr_hash
* members size.
*/
ldp w3, w4, [x9, #MPIDR_HASH_SHIFTS]
ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
add x1, x1, x8, lsl #3
str x0, [x1]
add x0, x0, #SLEEP_STACK_DATA_SYSTEM_REGS
stp x29, lr, [sp, #-16]!
bl cpu_do_suspend
ldp x29, lr, [sp], #16
mov x0, #1
ret
ENDPROC(__cpu_suspend_enter)
.ltorg
ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
/* enable the MMU early - so we can access sleep_save_stash by va */
adr_l lr, __enable_mmu /* __cpu_setup will return here */
adr_l x27, _resume_switched /* __enable_mmu will branch here */
adrp x25, idmap_pg_dir
adrp x26, swapper_pg_dir
b __cpu_setup
ENDPROC(cpu_resume)
.pushsection ".idmap.text", "ax"
_resume_switched:
ldr x8, =_cpu_resume
br x8
ENDPROC(_resume_switched)
.ltorg
.popsection
ENTRY(_cpu_resume)
mrs x1, mpidr_el1
adrp x8, mpidr_hash
add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
/* retrieve mpidr_hash members to compute the hash */
ldr x2, [x8, #MPIDR_HASH_MASK]
ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS]
ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
/* x7 contains hash index, let's use it to grab context pointer */
ldr_l x0, sleep_save_stash
ldr x0, [x0, x7, lsl #3]
add x29, x0, #SLEEP_STACK_DATA_CALLEE_REGS
add x0, x0, #SLEEP_STACK_DATA_SYSTEM_REGS
/* load sp from context */
ldr x2, [x0, #CPU_CTX_SP]
mov sp, x2
/* save thread_info */
and x2, x2, #~(THREAD_SIZE - 1)
msr sp_el0, x2
/*
* cpu_do_resume expects x0 to contain context address pointer
*/
bl cpu_do_resume
#ifdef CONFIG_KASAN
mov x0, sp
bl kasan_unpoison_remaining_stack
#endif
ldp x19, x20, [x29, #16]
ldp x21, x22, [x29, #32]
ldp x23, x24, [x29, #48]
ldp x25, x26, [x29, #64]
ldp x27, x28, [x29, #80]
ldp x29, lr, [x29]
mov x0, #0
ret
ENDPROC(_cpu_resume)