linux/arch/arm64/kernel/sleep.S
Will Deacon 8ec4198743 arm64: mm: ensure patched kernel text is fetched from PoU
The arm64 booting document requires that the bootloader has cleaned the
kernel image to the PoC. However, when a CPU re-enters the kernel due to
either a CPU hotplug "on" event or resuming from a low-power state (e.g.
cpuidle), the kernel text may in-fact be dirty at the PoU due to things
like alternative patching or even module loading.

Thanks to I-cache speculation with the MMU off, stale instructions could
be fetched prior to enabling the MMU, potentially leading to crashes
when executing regions of code that have been modified at runtime.

This patch addresses the issue by ensuring that the local I-cache is
invalidated immediately after a CPU has enabled its MMU but before
jumping out of the identity mapping. Any stale instructions fetched from
the PoC will then be discarded and refetched correctly from the PoU.
Patching kernel text executed prior to the MMU being enabled is
prohibited, so the early entry code will always be clean.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-08-05 10:05:20 +01:00

183 lines
5.5 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 for a suspend and execute the suspend finisher.
* On success it will return 0 through cpu_resume - ie through a CPU
* soft/hard reboot from the reset vector.
* On failure it returns the suspend finisher return value or force
* -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher
* is not allowed to return, if it does this must be considered failure).
* It saves callee registers, and allocates space on the kernel stack
* to save the CPU specific registers + some other data for resume.
*
* x0 = suspend finisher argument
* x1 = suspend finisher function pointer
*/
ENTRY(__cpu_suspend_enter)
stp x29, lr, [sp, #-96]!
stp x19, x20, [sp,#16]
stp x21, x22, [sp,#32]
stp x23, x24, [sp,#48]
stp x25, x26, [sp,#64]
stp x27, x28, [sp,#80]
/*
* Stash suspend finisher and its argument in x20 and x19
*/
mov x19, x0
mov x20, x1
mov x2, sp
sub sp, sp, #CPU_SUSPEND_SZ // allocate cpu_suspend_ctx
mov x0, sp
/*
* x0 now points to struct cpu_suspend_ctx allocated on the stack
*/
str x2, [x0, #CPU_CTX_SP]
ldr x1, =sleep_save_sp
ldr x1, [x1, #SLEEP_SAVE_SP_VIRT]
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
bl __cpu_suspend_save
/*
* Grab suspend finisher in x20 and its argument in x19
*/
mov x0, x19
mov x1, x20
/*
* We are ready for power down, fire off the suspend finisher
* in x1, with argument in x0
*/
blr x1
/*
* Never gets here, unless suspend finisher fails.
* Successful cpu_suspend should return from cpu_resume, returning
* through this code path is considered an error
* If the return value is set to 0 force x0 = -EOPNOTSUPP
* to make sure a proper error condition is propagated
*/
cmp x0, #0
mov x3, #-EOPNOTSUPP
csel x0, x3, x0, eq
add sp, sp, #CPU_SUSPEND_SZ // rewind stack pointer
ldp x19, x20, [sp, #16]
ldp x21, x22, [sp, #32]
ldp x23, x24, [sp, #48]
ldp x25, x26, [sp, #64]
ldp x27, x28, [sp, #80]
ldp x29, lr, [sp], #96
ret
ENDPROC(__cpu_suspend_enter)
.ltorg
/*
* x0 must contain the sctlr value retrieved from restored context
*/
.pushsection ".idmap.text", "ax"
ENTRY(cpu_resume_mmu)
ldr x3, =cpu_resume_after_mmu
msr sctlr_el1, x0 // restore sctlr_el1
isb
/*
* Invalidate the local I-cache so that any instructions fetched
* speculatively from the PoC are discarded, since they may have
* been dynamically patched at the PoU.
*/
ic iallu
dsb nsh
isb
br x3 // global jump to virtual address
ENDPROC(cpu_resume_mmu)
.popsection
cpu_resume_after_mmu:
mov x0, #0 // return zero on success
ldp x19, x20, [sp, #16]
ldp x21, x22, [sp, #32]
ldp x23, x24, [sp, #48]
ldp x25, x26, [sp, #64]
ldp x27, x28, [sp, #80]
ldp x29, lr, [sp], #96
ret
ENDPROC(cpu_resume_after_mmu)
ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
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_sp + SLEEP_SAVE_SP_PHYS
ldr x0, [x0, x7, lsl #3]
/* load sp from context */
ldr x2, [x0, #CPU_CTX_SP]
/* load physical address of identity map page table in x1 */
adrp x1, idmap_pg_dir
mov sp, x2
/*
* cpu_do_resume expects x0 to contain context physical address
* pointer and x1 to contain physical address of 1:1 page tables
*/
bl cpu_do_resume // PC relative jump, MMU off
b cpu_resume_mmu // Resume MMU, never returns
ENDPROC(cpu_resume)