arm64: entry: simplify kernel_exit logic

For historical reasons, the non-KPTI exception return path is duplicated for
EL1 and EL0, with the structure:

	.if \el == 0
	[ KPTI handling ]
	ldr     lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
	[ EL0 exception return workaround ]
	eret
	.else
	ldr     lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
	[ EL1 exception return workaround ]
	eret
	.endif
	sb

This would be simpler and clearer with the common portions factored out,
e.g.

	.if \el == 0
	[ KPTI handling ]
	.endif

	ldr     lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp

	.if \el == 0
	[ EL0 exception return workaround ]
	.else
	[ EL1 exception return workaround ]
	.endif

	eret
	sb

This expands to the same code, but is simpler for a human to follow as
it avoids duplicates the restore of LR+SP, and makes it clear that the
ERET is associated with the SB.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20240116110221.420467-3-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: mrutland-arm

arch/arm64/kernel/entry.S

@@ -442,24 +442,23 @@ alternative_else_nop_endif
 
 .L_skip_tramp_exit_\@:
 #endif
+	.endif
+
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
+	.if \el == 0
 	/* This must be after the last explicit memory access */
 alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	tlbi	vale1, xzr
 	dsb	nsh
 alternative_else_nop_endif
-	eret
 	.else
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
-
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
+	.endif
 
 	eret
-	.endif
 	sb
 	.endm