arm64: entry: fix ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD

Currently the ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD workaround isn't
quite right, as it is supposed to be applied after the last explicit
memory access, but is immediately followed by an LDR.

The ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD workaround is used to
handle Cortex-A520 erratum 2966298 and Cortex-A510 erratum 3117295,
which are described in:

* https://developer.arm.com/documentation/SDEN2444153/0600/?lang=en
* https://developer.arm.com/documentation/SDEN1873361/1600/?lang=en

In both cases the workaround is described as:

| If pagetable isolation is disabled, the context switch logic in the
| kernel can be updated to execute the following sequence on affected
| cores before exiting to EL0, and after all explicit memory accesses:
|
| 1. A non-shareable TLBI to any context and/or address, including
|    unused contexts or addresses, such as a `TLBI VALE1 Xzr`.
|
| 2. A DSB NSH to guarantee completion of the TLBI.

The important part being that the TLBI+DSB must be placed "after all
explicit memory accesses".

Unfortunately, as-implemented, the TLBI+DSB is immediately followed by
an LDR, as we have:

| alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
| 	tlbi	vale1, xzr
| 	dsb	nsh
| alternative_else_nop_endif
| alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
| 	ldr	lr, [sp, #S_LR]
| 	add	sp, sp, #PT_REGS_SIZE		// restore sp
| 	eret
| alternative_else_nop_endif
|
| [ ... KPTI exception return path ... ]

This patch fixes this by reworking the logic to place the TLBI+DSB
immediately before the ERET, after all explicit memory accesses.

The ERET is currently in a separate alternative block, and alternatives
cannot be nested. To account for this, the alternative block for
ARM64_UNMAP_KERNEL_AT_EL0 is replaced with a single alternative branch
to skip the KPTI logic, with the new shape of the logic being:

| alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0
| 	[ ... KPTI exception return path ... ]
| .L_skip_tramp_exit_\@:
|
| 	ldr	lr, [sp, #S_LR]
| 	add	sp, sp, #PT_REGS_SIZE		// restore sp
|
| alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
| 	tlbi	vale1, xzr
| 	dsb	nsh
| alternative_else_nop_endif
| 	eret

The new structure means that the workaround is only applied when KPTI is
not in use; this is fine as noted in the documented implications of the
erratum:

| Pagetable isolation between EL0 and higher level ELs prevents the
| issue from occurring.

... and as per the workaround description quoted above, the workaround
is only necessary "If pagetable isolation is disabled".

Fixes: 471470b ("arm64: errata: Add Cortex-A520 speculative unprivileged load workaround")
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>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240116110221.420467-2-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: mrutland-arm

arch/arm64/kernel/entry.S

@@ -428,16 +428,9 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
-alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
-	tlbi	vale1, xzr
-	dsb	nsh
-alternative_else_nop_endif
-alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
-	eret
-alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0
+
 	msr	far_el1, x29
 
 	ldr_this_cpu	x30, this_cpu_vector, x29
@@ -446,7 +439,18 @@ alternative_else_nop_endif
 	ldr		lr, [sp, #S_LR]		// restore x30
 	add		sp, sp, #PT_REGS_SIZE	// restore sp
 	br		x29
+
+.L_skip_tramp_exit_\@:
 #endif
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
+
+	/* 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