5 files changed, 351 insertions, 19 deletions

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 64ecbb501c50..8590099ac148 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -41,6 +41,28 @@ struct efi __read_mostly efi = {
 };
 EXPORT_SYMBOL(efi);
 
+static bool disable_runtime;
+static int __init setup_noefi(char *arg)
+{
+        disable_runtime = true;
+        return 0;
+}
+early_param("noefi", setup_noefi);
+
+bool efi_runtime_disabled(void)
+{
+        return disable_runtime;
+}
+
+static int __init parse_efi_cmdline(char *str)
+{
+        if (parse_option_str(str, "noruntime"))
+                disable_runtime = true;
+
+        return 0;
+}
+early_param("efi", parse_efi_cmdline);
+
 static struct kobject *efi_kobj;
 static struct kobject *efivars_kobj;
 
@@ -423,3 +445,60 @@ int __init efi_get_fdt_params(struct efi_fdt_params *params, int verbose)
         return ret;
 }
 #endif /* CONFIG_EFI_PARAMS_FROM_FDT */
+
+static __initdata char memory_type_name[][20] = {
+        "Reserved",
+        "Loader Code",
+        "Loader Data",
+        "Boot Code",
+        "Boot Data",
+        "Runtime Code",
+        "Runtime Data",
+        "Conventional Memory",
+        "Unusable Memory",
+        "ACPI Reclaim Memory",
+        "ACPI Memory NVS",
+        "Memory Mapped I/O",
+        "MMIO Port Space",
+        "PAL Code"
+};
+
+char * __init efi_md_typeattr_format(char *buf, size_t size,
+                                     const efi_memory_desc_t *md)
+{
+        char *pos;
+        int type_len;
+        u64 attr;
+
+        pos = buf;
+        if (md->type >= ARRAY_SIZE(memory_type_name))
+                type_len = snprintf(pos, size, "[type=%u", md->type);
+        else
+                type_len = snprintf(pos, size, "[%-*s",
+                                    (int)(sizeof(memory_type_name[0]) - 1),
+                                    memory_type_name[md->type]);
+        if (type_len >= size)
+                return buf;
+
+        pos += type_len;
+        size -= type_len;
+
+        attr = md->attribute;
+        if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
+                     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_WP |
+                     EFI_MEMORY_RP | EFI_MEMORY_XP | EFI_MEMORY_RUNTIME))
+                snprintf(pos, size, "|attr=0x%016llx]",
+                         (unsigned long long)attr);
+        else
+                snprintf(pos, size, "|%3s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+                         attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
+                         attr & EFI_MEMORY_XP      ? "XP"  : "",
+                         attr & EFI_MEMORY_RP      ? "RP"  : "",
+                         attr & EFI_MEMORY_WP      ? "WP"  : "",
+                         attr & EFI_MEMORY_UCE     ? "UCE" : "",
+                         attr & EFI_MEMORY_WB      ? "WB"  : "",
+                         attr & EFI_MEMORY_WT      ? "WT"  : "",
+                         attr & EFI_MEMORY_WC      ? "WC"  : "",
+                         attr & EFI_MEMORY_UC      ? "UC"  : "");
+        return buf;
+}
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 480339b6b110..75ee05964cbc 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -226,6 +226,10 @@ unsigned long __init efi_entry(void *handle, efi_system_table_t *sys_table,
                 goto fail_free_image;
         }
 
+        status = efi_parse_options(cmdline_ptr);
+        if (status != EFI_SUCCESS)
+                pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n");
+
         /*
          * Unauthenticated device tree data is a security hazard, so
          * ignore 'dtb=' unless UEFI Secure Boot is disabled.
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 32d5cca30f49..a920fec8fe88 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -15,8 +15,23 @@
 
 #include "efistub.h"
 
+/*
+ * Some firmware implementations have problems reading files in one go.
+ * A read chunk size of 1MB seems to work for most platforms.
+ *
+ * Unfortunately, reading files in chunks triggers *other* bugs on some
+ * platforms, so we provide a way to disable this workaround, which can
+ * be done by passing "efi=nochunk" on the EFI boot stub command line.
+ *
+ * If you experience issues with initrd images being corrupt it's worth
+ * trying efi=nochunk, but chunking is enabled by default because there
+ * are far more machines that require the workaround than those that
+ * break with it enabled.
+ */
 #define EFI_READ_CHUNK_SIZE     (1024 * 1024)
 
+static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
+
 struct file_info {
         efi_file_handle_t *handle;
         u64 size;
@@ -281,6 +296,49 @@ void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
         efi_call_early(free_pages, addr, nr_pages);
 }
 
+/*
+ * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
+ * option, e.g. efi=nochunk.
+ *
+ * It should be noted that efi= is parsed in two very different
+ * environments, first in the early boot environment of the EFI boot
+ * stub, and subsequently during the kernel boot.
+ */
+efi_status_t efi_parse_options(char *cmdline)
+{
+        char *str;
+
+        /*
+         * If no EFI parameters were specified on the cmdline we've got
+         * nothing to do.
+         */
+        str = strstr(cmdline, "efi=");
+        if (!str)
+                return EFI_SUCCESS;
+
+        /* Skip ahead to first argument */
+        str += strlen("efi=");
+
+        /*
+         * Remember, because efi= is also used by the kernel we need to
+         * skip over arguments we don't understand.
+         */
+        while (*str) {
+                if (!strncmp(str, "nochunk", 7)) {
+                        str += strlen("nochunk");
+                        __chunk_size = -1UL;
+                }
+
+                /* Group words together, delimited by "," */
+                while (*str && *str != ',')
+                        str++;
+
+                if (*str == ',')
+                        str++;
+        }
+
+        return EFI_SUCCESS;
+}
 
 /*
  * Check the cmdline for a LILO-style file= arguments.
@@ -423,8 +481,8 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
                         size = files[j].size;
                         while (size) {
                                 unsigned long chunksize;
-                                if (size > EFI_READ_CHUNK_SIZE)
-                                        chunksize = EFI_READ_CHUNK_SIZE;
+                                if (size > __chunk_size)
+                                        chunksize = __chunk_size;
                                 else
                                         chunksize = size;
 
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index 10daa4bbb258..228bbf910461 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -14,11 +14,80 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/bug.h>
 #include <linux/efi.h>
-#include <linux/spinlock.h>             /* spinlock_t */
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
 #include <asm/efi.h>
 
 /*
+ * According to section 7.1 of the UEFI spec, Runtime Services are not fully
+ * reentrant, and there are particular combinations of calls that need to be
+ * serialized. (source: UEFI Specification v2.4A)
+ *
+ * Table 31. Rules for Reentry Into Runtime Services
+ * +------------------------------------+-------------------------------+
+ * | If previous call is busy in        | Forbidden to call             |
+ * +------------------------------------+-------------------------------+
+ * | Any                                | SetVirtualAddressMap()        |
+ * +------------------------------------+-------------------------------+
+ * | ConvertPointer()                   | ConvertPointer()              |
+ * +------------------------------------+-------------------------------+
+ * | SetVariable()                      | ResetSystem()                 |
+ * | UpdateCapsule()                    |                               |
+ * | SetTime()                          |                               |
+ * | SetWakeupTime()                    |                               |
+ * | GetNextHighMonotonicCount()        |                               |
+ * +------------------------------------+-------------------------------+
+ * | GetVariable()                      | GetVariable()                 |
+ * | GetNextVariableName()              | GetNextVariableName()         |
+ * | SetVariable()                      | SetVariable()                 |
+ * | QueryVariableInfo()                | QueryVariableInfo()           |
+ * | UpdateCapsule()                    | UpdateCapsule()               |
+ * | QueryCapsuleCapabilities()         | QueryCapsuleCapabilities()    |
+ * | GetNextHighMonotonicCount()        | GetNextHighMonotonicCount()   |
+ * +------------------------------------+-------------------------------+
+ * | GetTime()                          | GetTime()                     |
+ * | SetTime()                          | SetTime()                     |
+ * | GetWakeupTime()                    | GetWakeupTime()               |
+ * | SetWakeupTime()                    | SetWakeupTime()               |
+ * +------------------------------------+-------------------------------+
+ *
+ * Due to the fact that the EFI pstore may write to the variable store in
+ * interrupt context, we need to use a spinlock for at least the groups that
+ * contain SetVariable() and QueryVariableInfo(). That leaves little else, as
+ * none of the remaining functions are actually ever called at runtime.
+ * So let's just use a single spinlock to serialize all Runtime Services calls.
+ */
+static DEFINE_SPINLOCK(efi_runtime_lock);
+
+/*
+ * Some runtime services calls can be reentrant under NMI, even if the table
+ * above says they are not. (source: UEFI Specification v2.4A)
+ *
+ * Table 32. Functions that may be called after Machine Check, INIT and NMI
+ * +----------------------------+------------------------------------------+
+ * | Function                   | Called after Machine Check, INIT and NMI |
+ * +----------------------------+------------------------------------------+
+ * | GetTime()                  | Yes, even if previously busy.            |
+ * | GetVariable()              | Yes, even if previously busy             |
+ * | GetNextVariableName()      | Yes, even if previously busy             |
+ * | QueryVariableInfo()        | Yes, even if previously busy             |
+ * | SetVariable()              | Yes, even if previously busy             |
+ * | UpdateCapsule()            | Yes, even if previously busy             |
+ * | QueryCapsuleCapabilities() | Yes, even if previously busy             |
+ * | ResetSystem()              | Yes, even if previously busy             |
+ * +----------------------------+------------------------------------------+
+ *
+ * In order to prevent deadlocks under NMI, the wrappers for these functions
+ * may only grab the efi_runtime_lock or rtc_lock spinlocks if !efi_in_nmi().
+ * However, not all of the services listed are reachable through NMI code paths,
+ * so the the special handling as suggested by the UEFI spec is only implemented
+ * for QueryVariableInfo() and SetVariable(), as these can be reached in NMI
+ * context through efi_pstore_write().
+ */
+
+/*
  * As per commit ef68c8f87ed1 ("x86: Serialize EFI time accesses on rtc_lock"),
  * the EFI specification requires that callers of the time related runtime
  * functions serialize with other CMOS accesses in the kernel, as the EFI time
@@ -32,7 +101,9 @@ static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
         efi_status_t status;
 
         spin_lock_irqsave(&rtc_lock, flags);
+        spin_lock(&efi_runtime_lock);
         status = efi_call_virt(get_time, tm, tc);
+        spin_unlock(&efi_runtime_lock);
         spin_unlock_irqrestore(&rtc_lock, flags);
         return status;
 }
@@ -43,7 +114,9 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm)
         efi_status_t status;
 
         spin_lock_irqsave(&rtc_lock, flags);
+        spin_lock(&efi_runtime_lock);
         status = efi_call_virt(set_time, tm);
+        spin_unlock(&efi_runtime_lock);
         spin_unlock_irqrestore(&rtc_lock, flags);
         return status;
 }
@@ -56,7 +129,9 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
         efi_status_t status;
 
         spin_lock_irqsave(&rtc_lock, flags);
+        spin_lock(&efi_runtime_lock);
         status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+        spin_unlock(&efi_runtime_lock);
         spin_unlock_irqrestore(&rtc_lock, flags);
         return status;
 }
@@ -67,7 +142,9 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
         efi_status_t status;
 
         spin_lock_irqsave(&rtc_lock, flags);
+        spin_lock(&efi_runtime_lock);
         status = efi_call_virt(set_wakeup_time, enabled, tm);
+        spin_unlock(&efi_runtime_lock);
         spin_unlock_irqrestore(&rtc_lock, flags);
         return status;
 }
@@ -78,14 +155,27 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
                                           unsigned long *data_size,
                                           void *data)
 {
-        return efi_call_virt(get_variable, name, vendor, attr, data_size, data);
+        unsigned long flags;
+        efi_status_t status;
+
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(get_variable, name, vendor, attr, data_size,
+                               data);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
 static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
                                                efi_char16_t *name,
                                                efi_guid_t *vendor)
 {
-        return efi_call_virt(get_next_variable, name_size, name, vendor);
+        unsigned long flags;
+        efi_status_t status;
+
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(get_next_variable, name_size, name, vendor);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
 static efi_status_t virt_efi_set_variable(efi_char16_t *name,
@@ -94,24 +184,61 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
                                           unsigned long data_size,
                                           void *data)
 {
-        return efi_call_virt(set_variable, name, vendor, attr, data_size, data);
+        unsigned long flags;
+        efi_status_t status;
+
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(set_variable, name, vendor, attr, data_size,
+                               data);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
+static efi_status_t
+virt_efi_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+                                  u32 attr, unsigned long data_size,
+                                  void *data)
+{
+        unsigned long flags;
+        efi_status_t status;
+
+        if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+                return EFI_NOT_READY;
+
+        status = efi_call_virt(set_variable, name, vendor, attr, data_size,
+                               data);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
+}
+
+
 static efi_status_t virt_efi_query_variable_info(u32 attr,
                                                  u64 *storage_space,
                                                  u64 *remaining_space,
                                                  u64 *max_variable_size)
 {
+        unsigned long flags;
+        efi_status_t status;
+
         if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
                 return EFI_UNSUPPORTED;
 
-        return efi_call_virt(query_variable_info, attr, storage_space,
-                             remaining_space, max_variable_size);
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(query_variable_info, attr, storage_space,
+                               remaining_space, max_variable_size);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
 static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 {
-        return efi_call_virt(get_next_high_mono_count, count);
+        unsigned long flags;
+        efi_status_t status;
+
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(get_next_high_mono_count, count);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
 static void virt_efi_reset_system(int reset_type,
@@ -119,17 +246,27 @@ static void virt_efi_reset_system(int reset_type,
                                   unsigned long data_size,
                                   efi_char16_t *data)
 {
+        unsigned long flags;
+
+        spin_lock_irqsave(&efi_runtime_lock, flags);
         __efi_call_virt(reset_system, reset_type, status, data_size, data);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
 }
 
 static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
                                             unsigned long count,
                                             unsigned long sg_list)
 {
+        unsigned long flags;
+        efi_status_t status;
+
         if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
                 return EFI_UNSUPPORTED;
 
-        return efi_call_virt(update_capsule, capsules, count, sg_list);
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(update_capsule, capsules, count, sg_list);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
 static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
@@ -137,11 +274,17 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
                                                 u64 *max_size,
                                                 int *reset_type)
 {
+        unsigned long flags;
+        efi_status_t status;
+
         if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
                 return EFI_UNSUPPORTED;
 
-        return efi_call_virt(query_capsule_caps, capsules, count, max_size,
-                             reset_type);
+        spin_lock_irqsave(&efi_runtime_lock, flags);
+        status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
+                               reset_type);
+        spin_unlock_irqrestore(&efi_runtime_lock, flags);
+        return status;
 }
 
 void efi_native_runtime_setup(void)
@@ -153,6 +296,7 @@ void efi_native_runtime_setup(void)
         efi.get_variable = virt_efi_get_variable;
         efi.get_next_variable = virt_efi_get_next_variable;
         efi.set_variable = virt_efi_set_variable;
+        efi.set_variable_nonblocking = virt_efi_set_variable_nonblocking;
         efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
         efi.reset_system = virt_efi_reset_system;
         efi.query_variable_info = virt_efi_query_variable_info;
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 5abe943e3404..70a0fb10517f 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -321,11 +321,11 @@ static unsigned long var_name_strnsize(efi_char16_t *variable_name,
  * Print a warning when duplicate EFI variables are encountered and
  * disable the sysfs workqueue since the firmware is buggy.
  */
-static void dup_variable_bug(efi_char16_t *s16, efi_guid_t *vendor_guid,
+static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
                              unsigned long len16)
 {
         size_t i, len8 = len16 / sizeof(efi_char16_t);
-        char *s8;
+        char *str8;
 
         /*
          * Disable the workqueue since the algorithm it uses for
@@ -334,16 +334,16 @@ static void dup_variable_bug(efi_char16_t *s16, efi_guid_t *vendor_guid,
          */
         efivar_wq_enabled = false;
 
-        s8 = kzalloc(len8, GFP_KERNEL);
-        if (!s8)
+        str8 = kzalloc(len8, GFP_KERNEL);
+        if (!str8)
                 return;
 
         for (i = 0; i < len8; i++)
-                s8[i] = s16[i];
+                str8[i] = str16[i];
 
         printk(KERN_WARNING "efivars: duplicate variable: %s-%pUl\n",
-               s8, vendor_guid);
-        kfree(s8);
+               str8, vendor_guid);
+        kfree(str8);
 }
 
 /**
@@ -595,6 +595,39 @@ int efivar_entry_set(struct efivar_entry *entry, u32 attributes,
 }
 EXPORT_SYMBOL_GPL(efivar_entry_set);
 
+/*
+ * efivar_entry_set_nonblocking - call set_variable_nonblocking()
+ *
+ * This function is guaranteed to not block and is suitable for calling
+ * from crash/panic handlers.
+ *
+ * Crucially, this function will not block if it cannot acquire
+ * __efivars->lock. Instead, it returns -EBUSY.
+ */
+static int
+efivar_entry_set_nonblocking(efi_char16_t *name, efi_guid_t vendor,
+                             u32 attributes, unsigned long size, void *data)
+{
+        const struct efivar_operations *ops = __efivars->ops;
+        unsigned long flags;
+        efi_status_t status;
+
+        if (!spin_trylock_irqsave(&__efivars->lock, flags))
+                return -EBUSY;
+
+        status = check_var_size(attributes, size + ucs2_strsize(name, 1024));
+        if (status != EFI_SUCCESS) {
+                spin_unlock_irqrestore(&__efivars->lock, flags);
+                return -ENOSPC;
+        }
+
+        status = ops->set_variable_nonblocking(name, &vendor, attributes,
+                                               size, data);
+
+        spin_unlock_irqrestore(&__efivars->lock, flags);
+        return efi_status_to_err(status);
+}
+
 /**
  * efivar_entry_set_safe - call set_variable() if enough space in firmware
  * @name: buffer containing the variable name
@@ -622,6 +655,20 @@ int efivar_entry_set_safe(efi_char16_t *name, efi_guid_t vendor, u32 attributes,
         if (!ops->query_variable_store)
                 return -ENOSYS;
 
+        /*
+         * If the EFI variable backend provides a non-blocking
+         * ->set_variable() operation and we're in a context where we
+         * cannot block, then we need to use it to avoid live-locks,
+         * since the implication is that the regular ->set_variable()
+         * will block.
+         *
+         * If no ->set_variable_nonblocking() is provided then
+         * ->set_variable() is assumed to be non-blocking.
+         */
+        if (!block && ops->set_variable_nonblocking)
+                return efivar_entry_set_nonblocking(name, vendor, attributes,
+                                                    size, data);
+
         if (!block) {
                 if (!spin_trylock_irqsave(&__efivars->lock, flags))
                         return -EBUSY;