arm64: kexec: keep MMU enabled during kexec relocation

Now, that we have linear map page tables configured, keep MMU enabled
to allow faster relocation of segments to final destination.

Cavium ThunderX2:
Kernel Image size: 38M Iniramfs size: 46M Total relocation size: 84M
MMU-disabled:
relocation	7.489539915s
MMU-enabled:
relocation	0.03946095s

Broadcom Stingray:
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: Pasha Tatashin <pasha.tatashin@soleen.com>
Tested-by: Pingfan Liu <piliu@redhat.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20210930143113.1502553-13-pasha.tatashin@soleen.com
Signed-off-by: Will Deacon <will@kernel.org>

arch/arm64/include/asm/kexec.h

@@ -97,8 +97,11 @@ struct kimage_arch {
 	phys_addr_t dtb_mem;
 	phys_addr_t kern_reloc;
 	phys_addr_t el2_vectors;
+	phys_addr_t ttbr0;
 	phys_addr_t ttbr1;
 	phys_addr_t zero_page;
+	unsigned long phys_offset;
+	unsigned long t0sz;
 };
 
 #ifdef CONFIG_KEXEC_FILE

arch/arm64/kernel/asm-offsets.c

@@ -176,6 +176,7 @@ int main(void)
   DEFINE(KIMAGE_ARCH_DTB_MEM,		offsetof(struct kimage, arch.dtb_mem));
   DEFINE(KIMAGE_ARCH_EL2_VECTORS,	offsetof(struct kimage, arch.el2_vectors));
   DEFINE(KIMAGE_ARCH_ZERO_PAGE,		offsetof(struct kimage, arch.zero_page));
+  DEFINE(KIMAGE_ARCH_PHYS_OFFSET,	offsetof(struct kimage, arch.phys_offset));
   DEFINE(KIMAGE_ARCH_TTBR1,		offsetof(struct kimage, arch.ttbr1));
   DEFINE(KIMAGE_HEAD,			offsetof(struct kimage, head));
   DEFINE(KIMAGE_START,			offsetof(struct kimage, start));

arch/arm64/kernel/machine_kexec.c

@@ -196,6 +196,11 @@ int machine_kexec_post_load(struct kimage *kimage)
 	reloc_size = __relocate_new_kernel_end - __relocate_new_kernel_start;
 	memcpy(reloc_code, __relocate_new_kernel_start, reloc_size);
 	kimage->arch.kern_reloc = __pa(reloc_code);
+	rc = trans_pgd_idmap_page(&info, &kimage->arch.ttbr0,
+				  &kimage->arch.t0sz, reloc_code);
+	if (rc)
+		return rc;
+	kimage->arch.phys_offset = virt_to_phys(kimage) - (long)kimage;
 
 	/* Flush the reloc_code in preparation for its execution. */
 	dcache_clean_inval_poc((unsigned long)reloc_code,
@@ -230,9 +235,9 @@ void machine_kexec(struct kimage *kimage)
 	local_daif_mask();
 
 	/*
-	 * Both restart and cpu_soft_restart will shutdown the MMU, disable data
+	 * Both restart and kernel_reloc will shutdown the MMU, disable data
 	 * caches. However, restart will start new kernel or purgatory directly,
-	 * cpu_soft_restart will transfer control to arm64_relocate_new_kernel
+	 * kernel_reloc contains the body of arm64_relocate_new_kernel
 	 * In kexec case, kimage->start points to purgatory assuming that
 	 * kernel entry and dtb address are embedded in purgatory by
 	 * userspace (kexec-tools).
@@ -246,10 +251,13 @@ void machine_kexec(struct kimage *kimage)
 		restart(is_hyp_nvhe(), kimage->start, kimage->arch.dtb_mem,
 			0, 0);
 	} else {
+		void (*kernel_reloc)(struct kimage *kimage);
+
 		if (is_hyp_nvhe())
 			__hyp_set_vectors(kimage->arch.el2_vectors);
-		cpu_soft_restart(kimage->arch.kern_reloc,
+		cpu_install_ttbr0(kimage->arch.ttbr0, kimage->arch.t0sz);
-				 virt_to_phys(kimage), 0, 0);
+		kernel_reloc = (void *)kimage->arch.kern_reloc;
+		kernel_reloc(kimage);
 	}
 
 	BUG(); /* Should never get here. */

arch/arm64/kernel/relocate_kernel.S

@@ -4,6 +4,8 @@
  *
  * Copyright (C) Linaro.
  * Copyright (C) Huawei Futurewei Technologies.
+ * Copyright (C) 2021, Microsoft Corporation.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
  */
 
 #include <linux/kexec.h>
@@ -15,6 +17,13 @@
 #include <asm/sysreg.h>
 #include <asm/virt.h>
 
+.macro turn_off_mmu tmp1, tmp2
+	mov_q   \tmp1, INIT_SCTLR_EL1_MMU_OFF
+	pre_disable_mmu_workaround
+	msr	sctlr_el1, \tmp1
+	isb
+.endm
+
 .section    ".kexec_relocate.text", "ax"
 /*
  * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
@@ -32,22 +41,21 @@ SYM_CODE_START(arm64_relocate_new_kernel)
 	ldr	x18, [x0, #KIMAGE_ARCH_ZERO_PAGE] /* x18 = zero page for BBM */
 	ldr	x17, [x0, #KIMAGE_ARCH_TTBR1]	/* x17 = linear map copy */
 	ldr	x16, [x0, #KIMAGE_HEAD]		/* x16 = kimage_head */
-	mov	x14, xzr			/* x14 = entry ptr */
+	ldr	x22, [x0, #KIMAGE_ARCH_PHYS_OFFSET]	/* x22 phys_offset */
-	mov	x13, xzr			/* x13 = copy dest */
 	raw_dcache_line_size x15, x1		/* x15 = dcache line size */
 	break_before_make_ttbr_switch	x18, x17, x1, x2 /* set linear map */
 .Lloop:
 	and	x12, x16, PAGE_MASK		/* x12 = addr */
-
+	sub	x12, x12, x22			/* Convert x12 to virt */
 	/* Test the entry flags. */
 .Ltest_source:
 	tbz	x16, IND_SOURCE_BIT, .Ltest_indirection
 
 	/* Invalidate dest page to PoC. */
-	mov	x2, x13
+	mov	x19, x13
-	add	x1, x2, #PAGE_SIZE
-	dcache_by_myline_op ivac, sy, x2, x1, x15, x20
 	copy_page x13, x12, x1, x2, x3, x4, x5, x6, x7, x8
+	add	x1, x19, #PAGE_SIZE
+	dcache_by_myline_op civac, sy, x19, x1, x15, x20
 	b	.Lnext
 .Ltest_indirection:
 	tbz	x16, IND_INDIRECTION_BIT, .Ltest_destination
@@ -64,19 +72,20 @@ SYM_CODE_START(arm64_relocate_new_kernel)
 	ic	iallu
 	dsb	nsh
 	isb
+	ldr	x4, [x0, #KIMAGE_START]			/* relocation start */
+	ldr	x1, [x0, #KIMAGE_ARCH_EL2_VECTORS]	/* relocation start */
+	ldr	x0, [x0, #KIMAGE_ARCH_DTB_MEM]		/* dtb address */
+	turn_off_mmu x12, x13
 
 	/* Start new image. */
-	ldr	x1, [x0, #KIMAGE_ARCH_EL2_VECTORS]	/* relocation start */
 	cbz	x1, .Lel1
-	ldr	x1, [x0, #KIMAGE_START]		/* relocation start */
+	mov	x1, x4				/* relocation start */
-	ldr	x2, [x0, #KIMAGE_ARCH_DTB_MEM]	/* dtb address */
+	mov	x2, x0				/* dtb address */
 	mov	x3, xzr
 	mov	x4, xzr
 	mov     x0, #HVC_SOFT_RESTART
 	hvc	#0				/* Jumps from el2 */
 .Lel1:
-	ldr	x4, [x0, #KIMAGE_START]		/* relocation start */
-	ldr	x0, [x0, #KIMAGE_ARCH_DTB_MEM]	/* dtb address */
 	mov	x2, xzr
 	mov	x3, xzr
 	br	x4				/* Jumps from el1 */