[PATCH v8 24/25] arm64: kexec: enable MMU during kexec relocation

[Pavel Tatashin <pasha.tatashin@soleen.com>]

Now, that we have transitional page tables configured, temporarily enable
MMU to allow faster relocation of segments to final destination.

The performance data: for a moderate size kernel + initramfs: 25M the
relocation was taking 0.382s, with enabled MMU it now takes
0.019s only or x20 improvement.

The time is proportional to the size of relocation, therefore if initramfs
is larger, 100M it could take over a second.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/kernel/relocate_kernel.S | 135 +++++++++++++++++-----------
 1 file changed, 83 insertions(+), 52 deletions(-)

diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index 67efa42575a5..e623b02f72a3 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -4,6 +4,8 @@
  *
  * Copyright (C) Linaro.
  * Copyright (C) Huawei Futurewei Technologies.
+ * Copyright (c) 2019, Microsoft Corporation.
+ * Pavel Tatashin <patatash@linux.microsoft.com>
  */
 
 #include <linux/kexec.h>
@@ -15,6 +17,48 @@
 #include <asm/sysreg.h>
 
 GLOBAL(kexec_relocate_code_start)
+/* Invalidae TLB */
+.macro tlb_invalidate
+	dsb	sy
+	dsb	ish
+	tlbi	vmalle1
+	dsb	ish
+	isb
+.endm
+
+/* Turn-off mmu at level specified by sctlr */
+.macro turn_off_mmu sctlr, tmp1, tmp2
+	mrs	\tmp1, \sctlr
+	ldr	\tmp2, =SCTLR_ELx_FLAGS
+	bic	\tmp1, \tmp1, \tmp2
+	pre_disable_mmu_workaround
+	msr	\sctlr, \tmp1
+	isb
+.endm
+
+/* Turn-on mmu at level specified by sctlr */
+.macro turn_on_mmu sctlr, tmp1, tmp2
+	mrs	\tmp1, \sctlr
+	ldr	\tmp2, =SCTLR_ELx_FLAGS
+	orr	\tmp1, \tmp1, \tmp2
+	msr	\sctlr, \tmp1
+	ic	iallu
+	dsb	nsh
+	isb
+.endm
+
+/*
+ * Set ttbr0 and ttbr1, called while MMU is disabled, so no need to temporarily
+ * set zero_page table. Invalidate TLB after new tables are set.
+ */
+.macro set_ttbr arg, tmp
+	ldr	\tmp, [\arg, #KEXEC_KRELOC_TRANS_TTBR0]
+	msr	ttbr0_el1, \tmp
+	ldr	\tmp, [\arg, #KEXEC_KRELOC_TRANS_TTBR1]
+	offset_ttbr1 \tmp
+	msr	ttbr1_el1, \tmp
+	isb
+.endm
 
 /*
  * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
@@ -26,65 +70,52 @@ GLOBAL(kexec_relocate_code_start)
  * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end.  The
  * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec
  * safe memory that has been set up to be preserved during the copy operation.
+ *
+ * This function temporarily enables MMU if kernel relocation is needed.
+ * Also, if we enter this function at EL2 on non-VHE kernel, we temporarily go
+ * to EL1 to enable MMU, and escalate back to EL2 at the end to do the jump to
+ * the new kernel. This is determined by presence of el2_vector.
  */
 ENTRY(arm64_relocate_new_kernel)
-	/* Clear the sctlr_el2 flags. */
-	mrs	x2, CurrentEL
-	cmp	x2, #CurrentEL_EL2
+	mrs	x1, CurrentEL
+	cmp	x1, #CurrentEL_EL2
 	b.ne	1f
-	mrs	x2, sctlr_el2
-	ldr	x1, =SCTLR_ELx_FLAGS
-	bic	x2, x2, x1
-	pre_disable_mmu_workaround
-	msr	sctlr_el2, x2
-	isb
-1:	/* Check if the new image needs relocation. */
-	ldr	x16, [x0, #KEXEC_KRELOC_HEAD]	/* x16 = kimage_head */
-	tbnz	x16, IND_DONE_BIT, .Ldone
-	raw_dcache_line_size x15, x1		/* x15 = dcache line size */
-.Lloop:
-	and	x12, x16, PAGE_MASK		/* x12 = addr */
-	/* Test the entry flags. */
-.Ltest_source:
-	tbz	x16, IND_SOURCE_BIT, .Ltest_indirection
-
-	/* Invalidate dest page to PoC. */
-	mov     x2, x13
-	add     x20, x2, #PAGE_SIZE
-	sub     x1, x15, #1
-	bic     x2, x2, x1
-2:	dc      ivac, x2
-	add     x2, x2, x15
-	cmp     x2, x20
-	b.lo    2b
-	dsb     sy
-
-	copy_page x13, x12, x1, x2, x3, x4, x5, x6, x7, x8
-	b	.Lnext
-.Ltest_indirection:
-	tbz	x16, IND_INDIRECTION_BIT, .Ltest_destination
-	mov	x14, x12			/* ptr = addr */
-	b	.Lnext
-.Ltest_destination:
-	tbz	x16, IND_DESTINATION_BIT, .Lnext
-	mov	x13, x12			/* dest = addr */
-.Lnext:
-	ldr	x16, [x14], #8			/* entry = *ptr++ */
-	tbz	x16, IND_DONE_BIT, .Lloop	/* while (!(entry & DONE)) */
-.Ldone:
-	/* wait for writes from copy_page to finish */
-	dsb	nsh
-	ic	iallu
-	dsb	nsh
-	isb
-
-	/* Start new image. */
-	ldr	x4, [x0, #KEXEC_KRELOC_ENTRY_ADDR]	/* x4 = kimage_start */
+	turn_off_mmu sctlr_el2, x1, x2		/* Turn off MMU at EL2 */
+1:	mov	x20, xzr			/* x20 will hold vector value */
+	ldr	x11, [x0, #KEXEC_KRELOC_COPY_LEN]
+	cbz	x11, 5f				/* Check if need to relocate */
+	ldr	x20, [x0, #KEXEC_KRELOC_EL2_VECTOR]
+	cbz	x20, 2f				/* need to reduce to EL1? */
+	msr	vbar_el2, x20			/* el2_vector present, means */
+	adr	x1, 2f				/* we will do copy in el1 but */
+	msr	elr_el2, x1			/* do final jump from el2 */
+	eret					/* Reduce to EL1 */
+2:	set_ttbr x0, x1				/* Set our page tables */
+	tlb_invalidate
+	turn_on_mmu sctlr_el1, x1, x2		/* Turn MMU back on */
+	ldr	x1, [x0, #KEXEC_KRELOC_DST_ADDR];
+	ldr	x2, [x0, #KEXEC_KRELOC_SRC_ADDR];
+	mov	x12, x1				/* x12 dst backup */
+3:	copy_page x1, x2, x3, x4, x5, x6, x7, x8, x9, x10
+	sub	x11, x11, #PAGE_SIZE
+	cbnz	x11, 3b				/* page copy loop */
+	raw_dcache_line_size x2, x3		/* x2 = dcache line size */
+	sub	x3, x2, #1			/* x3 = dcache_size - 1 */
+	bic	x12, x12, x3
+4:	dc	cvau, x12			/* Flush D-cache */
+	add	x12, x12, x2
+	cmp	x12, x1				/* Compare to dst + len */
+	b.ne	4b				/* D-cache flush loop */
+	turn_off_mmu sctlr_el1, x1, x2		/* Turn off MMU */
+	tlb_invalidate				/* Invalidate TLB */
+5:	ldr	x4, [x0, #KEXEC_KRELOC_ENTRY_ADDR]	/* x4 = kimage_start */
 	ldr	x3, [x0, #KEXEC_KRELOC_KERN_ARG3]
 	ldr	x2, [x0, #KEXEC_KRELOC_KERN_ARG2]
 	ldr	x1, [x0, #KEXEC_KRELOC_KERN_ARG1]
 	ldr	x0, [x0, #KEXEC_KRELOC_KERN_ARG0]	/* x0 = dtb address */
-	br	x4
+	cbnz	x20, 6f				/* need to escalate to el2? */
+	br	x4				/* Jump to new world */
+6:	hvc	#0				/* enters kexec_el1_sync */
 .ltorg
 END(arm64_relocate_new_kernel)
 
-- 
2.24.0