arm64: efi: Recover from synchronous exceptions occurring in firmware

Unlike x86, which has machinery to deal with page faults that occur
during the execution of EFI runtime services, arm64 has nothing like
that, and a synchronous exception raised by firmware code brings down
the whole system.

With more EFI based systems appearing that were not built to run Linux
(such as the Windows-on-ARM laptops based on Qualcomm SOCs), as well as
the introduction of PRM (platform specific firmware routines that are
callable just like EFI runtime services), we are more likely to run into
issues of this sort, and it is much more likely that we can identify and
work around such issues if they don't bring down the system entirely.

Since we already use a EFI runtime services call wrapper in assembler,
we can quite easily add some code that captures the execution state at
the point where the call is made, allowing us to revert to this state
and proceed execution if the call triggered a synchronous exception.

Given that the kernel and the firmware don't share any data structures
that could end up in an indeterminate state, we can happily continue
running, as long as we mark the EFI runtime services as unavailable from
that point on.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/efi.h

@@ -14,8 +14,16 @@
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
+
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg);
 #else
 #define efi_init()
+
+static inline
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
+{
+	return false;
+}
 #endif
 
 int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);

arch/arm64/kernel/efi-rt-wrapper.S

@@ -6,7 +6,7 @@
 #include <linux/linkage.h>
 
 SYM_FUNC_START(__efi_rt_asm_wrapper)
-	stp	x29, x30, [sp, #-32]!
+	stp	x29, x30, [sp, #-112]!
 	mov	x29, sp
 
 	/*
@@ -16,11 +16,21 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
 	 */
 	stp	x1, x18, [sp, #16]
 
+	/*
+	 * Preserve all callee saved registers and preserve the stack pointer
+	 * value at the base of the EFI runtime stack so we can recover from
+	 * synchronous exceptions occurring while executing the firmware
+	 * routines.
+	 */
+	stp	x19, x20, [sp, #32]
+	stp	x21, x22, [sp, #48]
+	stp	x23, x24, [sp, #64]
+	stp	x25, x26, [sp, #80]
+	stp	x27, x28, [sp, #96]
+
 	ldr_l	x16, efi_rt_stack_top
 	mov	sp, x16
-#ifdef CONFIG_SHADOW_CALL_STACK
-	str	x18, [sp, #-16]!
-#endif
+	stp	x18, x29, [sp, #-16]!
 
 	/*
 	 * We are lucky enough that no EFI runtime services take more than
@@ -38,7 +48,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
 	mov	sp, x29
 	ldp	x1, x2, [sp, #16]
 	cmp	x2, x18
-	ldp	x29, x30, [sp], #32
+	ldp	x29, x30, [sp], #112
 	b.ne	0f
 	ret
 0:
@@ -56,3 +66,15 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
 
 	b	efi_handle_corrupted_x18	// tail call
 SYM_FUNC_END(__efi_rt_asm_wrapper)
+
+SYM_CODE_START(__efi_rt_asm_recover)
+	mov	sp, x30
+
+	ldp	x19, x20, [sp, #32]
+	ldp	x21, x22, [sp, #48]
+	ldp	x23, x24, [sp, #64]
+	ldp	x25, x26, [sp, #80]
+	ldp	x27, x28, [sp, #96]
+	ldp	x29, x30, [sp], #112
+	ret
+SYM_CODE_END(__efi_rt_asm_recover)

arch/arm64/kernel/efi.c

@@ -149,6 +149,28 @@ DEFINE_SPINLOCK(efi_rt_lock);
 
 asmlinkage u64 *efi_rt_stack_top __ro_after_init;
 
+asmlinkage efi_status_t __efi_rt_asm_recover(void);
+
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
+{
+	 /* Check whether the exception occurred while running the firmware */
+	if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64)
+		return false;
+
+	pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg);
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+	clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
+	regs->regs[0]	= EFI_ABORTED;
+	regs->regs[30]	= efi_rt_stack_top[-1];
+	regs->pc	= (u64)__efi_rt_asm_recover;
+
+	if (IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
+		regs->regs[18] = efi_rt_stack_top[-2];
+
+	return true;
+}
+
 /* EFI requires 8 KiB of stack space for runtime services */
 static_assert(THREAD_SIZE >= SZ_8K);
 

arch/arm64/mm/fault.c

@@ -30,6 +30,7 @@
 #include <asm/bug.h>
 #include <asm/cmpxchg.h>
 #include <asm/cpufeature.h>
+#include <asm/efi.h>
 #include <asm/exception.h>
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
@@ -391,6 +392,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 		msg = "paging request";
 	}
 
+	if (efi_runtime_fixup_exception(regs, msg))
+		return;
+
 	die_kernel_fault(msg, addr, esr, regs);
 }
 

drivers/firmware/efi/runtime-wrappers.c

@@ -83,6 +83,7 @@ struct efi_runtime_work efi_rts_work;
 	else								\
 		pr_err("Failed to queue work to efi_rts_wq.\n");	\
 									\
+	WARN_ON_ONCE(efi_rts_work.status == EFI_ABORTED);		\
 exit:									\
 	efi_rts_work.efi_rts_id = EFI_NONE;				\
 	efi_rts_work.status;						\