efi/x86: Handle page faults occurring while running EFI runtime services

Memory accesses performed by UEFI runtime services should be limited to:
- reading/executing from EFI_RUNTIME_SERVICES_CODE memory regions
- reading/writing from/to EFI_RUNTIME_SERVICES_DATA memory regions
- reading/writing by-ref arguments
- reading/writing from/to the stack.

Accesses outside these regions may cause the kernel to hang because the
memory region requested by the firmware isn't mapped in efi_pgd, which
causes a page fault in ring 0 and the kernel fails to handle it, leading
to die(). To save kernel from hanging, add an EFI specific page fault
handler which recovers from such faults by
1. If the efi runtime service is efi_reset_system(), reboot the machine
   through BIOS.
2. If the efi runtime service is _not_ efi_reset_system(), then freeze
   efi_rts_wq and schedule a new process.

The EFI page fault handler offers us two advantages:
1. Avoid potential hangs caused by buggy firmware.
2. Shout loud that the firmware is buggy and hence is not a kernel bug.

Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
Suggested-by: Matt Fleming <matt@codeblueprint.co.uk>
Based-on-code-from: Ricardo Neri <ricardo.neri@intel.com>
Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
[ardb: clarify commit log]
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cec5fae23eb330d00c4e16f6d5ba22d0af29c414..eea40d52ca78547a6b578ff8883da069ddb29d3f 100644 (file)
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -140,6 +140,7 @@ extern void __init efi_apply_memmap_quirks(void);
 extern int __init efi_reuse_config(u64 tables, int nr_tables);
 extern void efi_delete_dummy_variable(void);
 extern void efi_switch_mm(struct mm_struct *mm);
+extern void efi_recover_from_page_fault(unsigned long phys_addr);
 
 struct efi_setup_data {
        u64 fw_vendor;

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 47bebfe6efa70a316424934683f4302de33876a2..a5b9ddb0f1fe2ac6e0485b350dde920e194bf291 100644 (file)
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -16,6 +16,7 @@
 #include <linux/prefetch.h>            /* prefetchw                    */
 #include <linux/context_tracking.h>    /* exception_enter(), ...       */
 #include <linux/uaccess.h>             /* faulthandler_disabled()      */
+#include <linux/efi.h>                 /* efi_recover_from_page_fault()*/
 #include <linux/mm_types.h>
 
 #include <asm/cpufeature.h>            /* boot_cpu_has, ...            */
@@ -25,6 +26,7 @@
 #include <asm/vsyscall.h>              /* emulate_vsyscall             */
 #include <asm/vm86.h>                  /* struct vm86                  */
 #include <asm/mmu_context.h>           /* vma_pkey()                   */
+#include <asm/efi.h>                   /* efi_recover_from_page_fault()*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -788,6 +790,13 @@ no_context(struct pt_regs *regs, unsigned long error_code,
        if (is_errata93(regs, address))
                return;
 
+       /*
+        * Buggy firmware could access regions which might page fault, try to
+        * recover from such faults.
+        */
+       if (IS_ENABLED(CONFIG_EFI))
+               efi_recover_from_page_fault(address);
+
        /*
         * Oops. The kernel tried to access some bad page. We'll have to
         * terminate things with extreme prejudice:

diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 844d31cb8a0c7eae1dcb37ed48fa373564e83f22..669babcaf245a2929eaefc2e09a56c46e75840ae 100644 (file)
--- 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;
+}

diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index b18b2d864c2c39a743c8850c921962de870881ef..a19d845bdb06748907972b652415594e18a095f9 100644 (file)
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -61,6 +61,11 @@ struct efi_runtime_work efi_rts_work;
 ({                                                                     \
        efi_rts_work.status = EFI_ABORTED;                              \
                                                                        \
+       if (!efi_enabled(EFI_RUNTIME_SERVICES)) {                       \
+               pr_warn_once("EFI Runtime Services are disabled!\n");   \
+               goto exit;                                              \
+       }                                                               \
+                                                                       \
        init_completion(&efi_rts_work.efi_rts_comp);                    \
        INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts);            \
        efi_rts_work.arg1 = _arg1;                                      \
@@ -79,6 +84,8 @@ struct efi_runtime_work efi_rts_work;
        else                                                            \
                pr_err("Failed to queue work to efi_rts_wq.\n");        \
                                                                        \
+exit:                                                                  \
+       efi_rts_work.efi_rts_id = NONE;                                 \
        efi_rts_work.status;                                            \
 })
 
@@ -393,6 +400,7 @@ static void virt_efi_reset_system(int reset_type,
                        "could not get exclusive access to the firmware\n");
                return;
        }
+       efi_rts_work.efi_rts_id = RESET_SYSTEM;
        __efi_call_virt(reset_system, reset_type, status, data_size, data);
        up(&efi_runtime_lock);
 }

diff --git a/include/linux/efi.h b/include/linux/efi.h
index a929d2bf41fa5598be1b7a979c58f24833fe0f47..845174e113ce9b360e899553b7e97f837a5abff7 100644 (file)
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1662,8 +1662,13 @@ struct linux_efi_tpm_eventlog {
 
 extern int efi_tpm_eventlog_init(void);
 
-/* efi_runtime_service() function identifiers */
+/*
+ * efi_runtime_service() function identifiers.
+ * "NONE" is used by efi_recover_from_page_fault() to check if the page
+ * fault happened while executing an efi runtime service.
+ */
 enum efi_rts_ids {
+       NONE,
        GET_TIME,
        SET_TIME,
        GET_WAKEUP_TIME,
@@ -1673,6 +1678,7 @@ enum efi_rts_ids {
        SET_VARIABLE,
        QUERY_VARIABLE_INFO,
        GET_NEXT_HIGH_MONO_COUNT,
+       RESET_SYSTEM,
        UPDATE_CAPSULE,
        QUERY_CAPSULE_CAPS,
 };