linux/arch/arm64/kernel/sleep.S
Ard Biesheuvel 9cce9c6c2c arm64: mm: Handle LVA support as a CPU feature
Currently, we detect CPU support for 52-bit virtual addressing (LVA)
extremely early, before creating the kernel page tables or enabling the
MMU. We cannot override the feature this early, and so large virtual
addressing is always enabled on CPUs that implement support for it if
the software support for it was enabled at build time. It also means we
rely on non-trivial code in asm to deal with this feature.

Given that both the ID map and the TTBR1 mapping of the kernel image are
guaranteed to be 48-bit addressable, it is not actually necessary to
enable support this early, and instead, we can model it as a CPU
feature. That way, we can rely on code patching to get the correct
TCR.T1SZ values programmed on secondary boot and resume from suspend.

On the primary boot path, we simply enable the MMU with 48-bit virtual
addressing initially, and update TCR.T1SZ if LVA is supported from C
code, right before creating the kernel mapping. Given that TTBR1 still
points to reserved_pg_dir at this point, updating TCR.T1SZ should be
safe without the need for explicit TLB maintenance.

Since this gets rid of all accesses to the vabits_actual variable from
asm code that occurred before TCR.T1SZ had been programmed, we no longer
have a need for this variable, and we can replace it with a C expression
that produces the correct value directly, based on the value of TCR.T1SZ.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-70-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2024-02-16 12:42:36 +00:00

156 lines
4.6 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/errno.h>
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
#include <asm/smp.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;
* aff3 = 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
*/
SYM_FUNC_START(__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_l x1, sleep_save_stash
mrs x7, mpidr_el1
adr_l 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
SYM_FUNC_END(__cpu_suspend_enter)
.pushsection ".idmap.text", "a"
SYM_CODE_START(cpu_resume)
mov x0, xzr
bl init_kernel_el
mov x19, x0 // preserve boot mode
bl __cpu_setup
/* enable the MMU early - so we can access sleep_save_stash by va */
adrp x1, swapper_pg_dir
adrp x2, idmap_pg_dir
bl __enable_mmu
ldr x8, =_cpu_resume
br x8
SYM_CODE_END(cpu_resume)
.ltorg
.popsection
SYM_FUNC_START(_cpu_resume)
mov x0, x19
bl finalise_el2
mrs x1, mpidr_el1
adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt 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
/*
* cpu_do_resume expects x0 to contain context address pointer
*/
bl cpu_do_resume
#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
mov x0, sp
bl kasan_unpoison_task_stack_below
#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
SYM_FUNC_END(_cpu_resume)