diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index bcee7ab..937f5e5 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -284,21 +284,23 @@
 	__asm__ __volatile__(					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
 		    CONFIG_ARM64_PAN)				\
-	"	mov		%w2, %w1\n"			\
-	"0:	ldxr"B"		%w1, [%3]\n"			\
-	"1:	stxr"B"		%w0, %w2, [%3]\n"		\
+	"0:	ldxr"B"		%w2, [%3]\n"			\
+	"1:	stxr"B"		%w0, %w1, [%3]\n"		\
 	"	cbz		%w0, 2f\n"			\
 	"	mov		%w0, %w4\n"			\
+	"	b		3f\n"				\
 	"2:\n"							\
+	"	mov		%w1, %w2\n"			\
+	"3:\n"							\
 	"	.pushsection	 .fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
-	"3:	mov		%w0, %w5\n"			\
-	"	b		2b\n"				\
+	"4:	mov		%w0, %w5\n"			\
+	"	b		3b\n"				\
 	"	.popsection"					\
 	"	.pushsection	 __ex_table,\"a\"\n"		\
 	"	.align		3\n"				\
-	"	.quad		0b, 3b\n"			\
-	"	.quad		1b, 3b\n"			\
+	"	.quad		0b, 4b\n"			\
+	"	.quad		1b, 4b\n"			\
 	"	.popsection\n"					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
index 816120e..78dfbd3 100644
--- a/arch/arm64/kernel/efi-stub.c
+++ b/arch/arm64/kernel/efi-stub.c
@@ -25,10 +25,20 @@
 	unsigned long kernel_size, kernel_memsize = 0;
 	unsigned long nr_pages;
 	void *old_image_addr = (void *)*image_addr;
+	unsigned long preferred_offset;
+
+	/*
+	 * The preferred offset of the kernel Image is TEXT_OFFSET bytes beyond
+	 * a 2 MB aligned base, which itself may be lower than dram_base, as
+	 * long as the resulting offset equals or exceeds it.
+	 */
+	preferred_offset = round_down(dram_base, SZ_2M) + TEXT_OFFSET;
+	if (preferred_offset < dram_base)
+		preferred_offset += SZ_2M;
 
 	/* Relocate the image, if required. */
 	kernel_size = _edata - _text;
-	if (*image_addr != (dram_base + TEXT_OFFSET)) {
+	if (*image_addr != preferred_offset) {
 		kernel_memsize = kernel_size + (_end - _edata);
 
 		/*
@@ -42,7 +52,7 @@
 		 * Mustang), we can still place the kernel at the address
 		 * 'dram_base + TEXT_OFFSET'.
 		 */
-		*image_addr = *reserve_addr = dram_base + TEXT_OFFSET;
+		*image_addr = *reserve_addr = preferred_offset;
 		nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) /
 			   EFI_PAGE_SIZE;
 		status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS,
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 407991b..ccb6078 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,11 +48,7 @@
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
-	/*
-	 * -4 here because we care about the PC at time of bl,
-	 * not where the return will go.
-	 */
-	frame->pc = *(unsigned long *)(fp + 8) - 4;
+	frame->pc = *(unsigned long *)(fp + 8);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 8297d50..44ca414 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -80,17 +80,21 @@
 	if (ret == 0) {
 		/*
 		 * We are resuming from reset with TTBR0_EL1 set to the
-		 * idmap to enable the MMU; restore the active_mm mappings in
-		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
-		 * the thread entered cpu_suspend with TTBR0_EL1 set to
-		 * reserved TTBR0 page tables and should be restored as such.
+		 * idmap to enable the MMU; set the TTBR0 to the reserved
+		 * page tables to prevent speculative TLB allocations, flush
+		 * the local tlb and set the default tcr_el1.t0sz so that
+		 * the TTBR0 address space set-up is properly restored.
+		 * If the current active_mm != &init_mm we entered cpu_suspend
+		 * with mappings in TTBR0 that must be restored, so we switch
+		 * them back to complete the address space configuration
+		 * restoration before returning.
 		 */
-		if (mm == &init_mm)
-			cpu_set_reserved_ttbr0();
-		else
-			cpu_switch_mm(mm->pgd, mm);
-
+		cpu_set_reserved_ttbr0();
 		flush_tlb_all();
+		cpu_set_default_tcr_t0sz();
+
+		if (mm != &init_mm)
+			cpu_switch_mm(mm->pgd, mm);
 
 		/*
 		 * Restore per-cpu offset before any kernel