arm64: Change cpu_resume() to enable mmu early then access sleep_sp by va

By enabling the MMU early in cpu_resume(), the sleep_save_sp and stack can
be accessed by VA, which avoids the need to convert-addresses and clean to
PoC on the suspend path.

MMU setup is shared with the boot path, meaning the swapper_pg_dir is
restored directly: ttbr1_el1 is no longer saved/restored.

struct sleep_save_sp is removed, replacing it with a single array of
pointers.

cpu_do_{suspend,resume} could be further reduced to not restore: cpacr_el1,
mdscr_el1, tcr_el1, vbar_el1 and sctlr_el1, all of which are set by
__cpu_setup(). However these values all contain res0 bits that may be used
to enable future features.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

5 files changed, 33 insertions, 77 deletions

diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 0902acb7afe5..ac742ef0fde0 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -119,9 +119,6 @@ int main(void)
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
   DEFINE(MPIDR_HASH_MASK,	offsetof(struct mpidr_hash, mask));
   DEFINE(MPIDR_HASH_SHIFTS,	offsetof(struct mpidr_hash, shift_aff));
-  DEFINE(SLEEP_SAVE_SP_SZ,	sizeof(struct sleep_save_sp));
-  DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
-  DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
   DEFINE(SLEEP_STACK_DATA_SYSTEM_REGS,	offsetof(struct sleep_stack_data, system_regs));
   DEFINE(SLEEP_STACK_DATA_CALLEE_REGS,	offsetof(struct sleep_stack_data, callee_saved_regs));
 #endif
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 00a32101ab51..0674384cfc74 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -716,7 +716,7 @@ ENTRY(__early_cpu_boot_status)
  * If it isn't, park the CPU
  */
 	.section	".idmap.text", "ax"
-__enable_mmu:
+ENTRY(__enable_mmu)
 	mrs	x22, sctlr_el1			// preserve old SCTLR_EL1 value
 	mrs	x1, ID_AA64MMFR0_EL1
 	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 65f515949baa..3279defabaa2 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -176,7 +176,6 @@ static void __init smp_build_mpidr_hash(void)
 	 */
 	if (mpidr_hash_size() > 4 * num_possible_cpus())
 		pr_warn("Large number of MPIDR hash buckets detected\n");
-	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
 }
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index b7c4b682bfc8..9a3aec97ac09 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -73,8 +73,8 @@ ENTRY(__cpu_suspend_enter)
 	str	x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP]
 
 	/* find the mpidr_hash */
-	ldr	x1, =sleep_save_sp
-	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
+	ldr	x1, =sleep_save_stash
+	ldr	x1, [x1]
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
 	ldr	x10, [x9, #MPIDR_HASH_MASK]
@@ -87,44 +87,27 @@ ENTRY(__cpu_suspend_enter)
 	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_suspend_save
+	bl	cpu_do_suspend
 	ldp	x29, lr, [sp], #16
 	mov	x0, #1
 	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:
-#ifdef CONFIG_KASAN
-	mov	x0, sp
-	bl	kasan_unpoison_remaining_stack
-#endif
-	mov	x0, #0			// return zero on success
-	ret
-ENDPROC(cpu_resume_after_mmu)
-
 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 */
+	ldr	x27, =_cpu_resume	/* __enable_mmu will branch here */
+	adrp	x25, idmap_pg_dir
+	adrp	x26, swapper_pg_dir
+	b	__cpu_setup
+ENDPROC(cpu_resume)
+
+ENTRY(_cpu_resume)
 	mrs	x1, mpidr_el1
 	adrp	x8, mpidr_hash
 	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
@@ -134,29 +117,32 @@ ENTRY(cpu_resume)
 	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_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]
-	/* load physical address of identity map page table in x1 */
-	adrp	x1, idmap_pg_dir
 	mov	sp, x2
 	/* save thread_info */
 	and	x2, x2, #~(THREAD_SIZE - 1)
 	msr	sp_el0, x2
 	/*
-	 * cpu_do_resume expects x0 to contain context physical address
-	 * pointer and x1 to contain physical address of 1:1 page tables
+	 * cpu_do_resume expects x0 to contain context address pointer
 	 */
-	bl	cpu_do_resume		// PC relative jump, MMU off
-	/* Can't access these by physical address once the MMU is on */
+	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]
-	b	cpu_resume_mmu		// Resume MMU, never returns
-ENDPROC(cpu_resume)
+	mov	x0, #0
+	ret
+ENDPROC(_cpu_resume)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 0d52ec972a38..b616e365cee3 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -10,30 +10,11 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-
 /*
- * This is called by __cpu_suspend_enter() to save the state, and do whatever
- * flushing is required to ensure that when the CPU goes to sleep we have
- * the necessary data available when the caches are not searched.
- *
- * ptr: sleep_stack_data containing cpu state virtual address.
- * save_ptr: address of the location where the context physical address
- *           must be saved
+ * This is allocated by cpu_suspend_init(), and used to store a pointer to
+ * the 'struct sleep_stack_data' the contains a particular CPUs state.
  */
-void notrace __cpu_suspend_save(struct sleep_stack_data *ptr,
-				phys_addr_t *save_ptr)
-{
-	*save_ptr = virt_to_phys(ptr);
-
-	cpu_do_suspend(&ptr->system_regs);
-	/*
-	 * Only flush the context that must be retrieved with the MMU
-	 * off. VA primitives ensure the flush is applied to all
-	 * cache levels so context is pushed to DRAM.
-	 */
-	__flush_dcache_area(ptr, sizeof(*ptr));
-	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
-}
+unsigned long *sleep_save_stash;
 
 /*
  * This hook is provided so that cpu_suspend code can restore HW
@@ -131,22 +112,15 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	return ret;
 }
 
-struct sleep_save_sp sleep_save_sp;
-
 static int __init cpu_suspend_init(void)
 {
-	void *ctx_ptr;
-
 	/* ctx_ptr is an array of physical addresses */
-	ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(phys_addr_t), GFP_KERNEL);
+	sleep_save_stash = kcalloc(mpidr_hash_size(), sizeof(*sleep_save_stash),
+				   GFP_KERNEL);
 
-	if (WARN_ON(!ctx_ptr))
+	if (WARN_ON(!sleep_save_stash))
 		return -ENOMEM;
 
-	sleep_save_sp.save_ptr_stash = ctx_ptr;
-	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
-	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
-
 	return 0;
 }
 early_initcall(cpu_suspend_init);