Merge branch 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull EFI updates from Ingo Molnar:
 "The main changes are:

   - Add support for enlisting the help of the EFI firmware to create
     memory reservations that persist across kexec.

   - Add page fault handling to the runtime services support code on x86
     so we can more gracefully recover from buggy EFI firmware.

   - Fix command line handling on x86 for the boot path that omits the
     stub's PE/COFF entry point.

   - Other assorted fixes and updates"

* 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: boot: Fix EFI stub alignment
  efi/x86: Call efi_parse_options() from efi_main()
  efi/x86: earlyprintk - Add 64bit efi fb address support
  efi/x86: drop task_lock() from efi_switch_mm()
  efi/x86: Handle page faults occurring while running EFI runtime services
  efi: Make efi_rts_work accessible to efi page fault handler
  efi/efi_test: add exporting ResetSystem runtime service
  efi/libstub: arm: support building with clang
  efi: add API to reserve memory persistently across kexec reboot
  efi/arm: libstub: add a root memreserve config table
  efi: honour memory reservations passed via a linux specific config table

3 files changed, 88 insertions, 8 deletions

diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 5fdacb322ceb..7476b3b097e1 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -26,12 +26,14 @@ static bool early_efi_keep;
  */
 static __init int early_efi_map_fb(void)
 {
-	unsigned long base, size;
+	u64 base, size;
 
 	if (!early_efi_keep)
 		return 0;
 
 	base = boot_params.screen_info.lfb_base;
+	if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)boot_params.screen_info.ext_lfb_base << 32;
 	size = boot_params.screen_info.lfb_size;
 	efi_fb = ioremap(base, size);
 
@@ -46,9 +48,11 @@ early_initcall(early_efi_map_fb);
  */
 static __ref void *early_efi_map(unsigned long start, unsigned long len)
 {
-	unsigned long base;
+	u64 base;
 
 	base = boot_params.screen_info.lfb_base;
+	if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)boot_params.screen_info.ext_lfb_base << 32;
 
 	if (efi_fb)
 		return (efi_fb + start);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ee5d08f25ce4..e8da7f492970 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void)
 
 /*
  * Makes the calling thread switch to/from efi_mm context. Can be used
- * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well
- * as during efi runtime calls i.e current->active_mm == current_mm.
- * We are not mm_dropping()/mm_grabbing() any mm, because we are not
- * losing/creating any references.
+ * in a kernel thread and user context. Preemption needs to remain disabled
+ * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm
+ * can not change under us.
+ * It should be ensured that there are no concurent calls to this function.
  */
 void efi_switch_mm(struct mm_struct *mm)
 {
-	task_lock(current);
 	efi_scratch.prev_mm = current->active_mm;
 	current->active_mm = mm;
 	switch_mm(efi_scratch.prev_mm, mm, NULL);
-	task_unlock(current);
 }
 
 #ifdef CONFIG_EFI_MIXED
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 844d31cb8a0c..669babcaf245 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -16,6 +16,7 @@
 #include <asm/efi.h>
 #include <asm/uv/uv.h>
 #include <asm/cpu_device_id.h>
+#include <asm/reboot.h>
 
 #define EFI_MIN_RESERVE 5120
 
@@ -654,3 +655,80 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
 }
 
 #endif
+
+/*
+ * If any access by any efi runtime service causes a page fault, then,
+ * 1. If it's efi_reset_system(), reboot through BIOS.
+ * 2. If any other efi runtime service, then
+ *    a. Return error status to the efi caller process.
+ *    b. Disable EFI Runtime Services forever and
+ *    c. Freeze efi_rts_wq and schedule new process.
+ *
+ * @return: Returns, if the page fault is not handled. This function
+ * will never return if the page fault is handled successfully.
+ */
+void efi_recover_from_page_fault(unsigned long phys_addr)
+{
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	/*
+	 * Make sure that an efi runtime service caused the page fault.
+	 * "efi_mm" cannot be used to check if the page fault had occurred
+	 * in the firmware context because efi=old_map doesn't use efi_pgd.
+	 */
+	if (efi_rts_work.efi_rts_id == NONE)
+		return;
+
+	/*
+	 * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so
+	 * page faulting on these addresses isn't expected.
+	 */
+	if (phys_addr >= 0x0000 && phys_addr <= 0x0fff)
+		return;
+
+	/*
+	 * Print stack trace as it might be useful to know which EFI Runtime
+	 * Service is buggy.
+	 */
+	WARN(1, FW_BUG "Page fault caused by firmware at PA: 0x%lx\n",
+	     phys_addr);
+
+	/*
+	 * Buggy efi_reset_system() is handled differently from other EFI
+	 * Runtime Services as it doesn't use efi_rts_wq. Although,
+	 * native_machine_emergency_restart() says that machine_real_restart()
+	 * could fail, it's better not to compilcate this fault handler
+	 * because this case occurs *very* rarely and hence could be improved
+	 * on a need by basis.
+	 */
+	if (efi_rts_work.efi_rts_id == RESET_SYSTEM) {
+		pr_info("efi_reset_system() buggy! Reboot through BIOS\n");
+		machine_real_restart(MRR_BIOS);
+		return;
+	}
+
+	/*
+	 * Before calling EFI Runtime Service, the kernel has switched the
+	 * calling process to efi_mm. Hence, switch back to task_mm.
+	 */
+	arch_efi_call_virt_teardown();
+
+	/* Signal error status to the efi caller process */
+	efi_rts_work.status = EFI_ABORTED;
+	complete(&efi_rts_work.efi_rts_comp);
+
+	clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+	pr_info("Froze efi_rts_wq and disabled EFI Runtime Services\n");
+
+	/*
+	 * Call schedule() in an infinite loop, so that any spurious wake ups
+	 * will never run efi_rts_wq again.
+	 */
+	for (;;) {
+		set_current_state(TASK_IDLE);
+		schedule();
+	}
+
+	return;
+}