[PATCH v5 09/14] efi: passing kexec necessary efi data via setup_data

From: Dave Young
Date: Mon Dec 09 2013 - 04:45:34 EST

Add a new setup_data type SETUP_EFI for kexec use.
Passing the saved fw_vendor, runtime, config tables and efi runtime mappings.

When entering virtual mode, directly mapping the efi runtime ragions which
we passed in previously. And skip the step to call SetVirtualAddressMap.

Specially for HP z420 workstation we need save the smbios physical address.
The kernel boot sequence proceeds in the following order. Step 2
requires efi.smbios to be the physical address. However, I found that on
HP z420 EFI system table has a virtual address of SMBIOS in step 1. Hence,
we need set it back to the physical address with the smbios in
efi_setup_data. (When it is still the physical address, it simply sets
the same value.)

1. efi_init() - Set efi.smbios from EFI system table
2. dmi_scan_machine() - Temporary map efi.smbios to access SMBIOS table
3. efi_enter_virtual_mode() - Map EFI ranges

Tested on ovmf+qemu, lenovo thinkpad, a dell laptop and an
HP z420 workstation.

v2: refresh based on previous patch changes, code cleanup.
v3: use ioremap instead of phys_to_virt for efi_setup
v5: improve some code structure per comments from Matt
Boris: improve code structure, spell fix, etc.
Improve changelog from Toshi.
change the variable efi_setup to the physical address of efi setup_data
instead of the ioremapped virt address

Signed-off-by: Dave Young <dyoung@xxxxxxxxxx>
---
arch/x86/include/asm/efi.h | 11 ++
arch/x86/include/uapi/asm/bootparam.h | 1 +
arch/x86/kernel/setup.c | 3 +
arch/x86/platform/efi/efi.c | 195 ++++++++++++++++++++++++++++++----
4 files changed, 187 insertions(+), 23 deletions(-)

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 9fbaeb2..73335a1 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -133,6 +133,17 @@ extern void efi_sync_low_kernel_mappings(void);
extern void efi_setup_page_tables(void);
extern void __init old_map_region(efi_memory_desc_t *md);

+struct efi_setup_data {
+ u64 fw_vendor;
+ u64 runtime;
+ u64 tables;
+ u64 smbios;
+ u64 reserved[8];
+ efi_memory_desc_t map[0];
+};
+
+extern void parse_efi_setup(u64 phys_addr);
+
#ifdef CONFIG_EFI

static inline bool efi_is_native(void)
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9c3733c..64fe421 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,6 +6,7 @@
#define SETUP_E820_EXT 1
#define SETUP_DTB 2
#define SETUP_PCI 3
+#define SETUP_EFI 4

/* ram_size flags */
#define RAMDISK_IMAGE_START_MASK 0x07FF
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb233bc..b2b54cd 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -447,6 +447,9 @@ static void __init parse_setup_data(void)
case SETUP_DTB:
add_dtb(pa_data);
break;
+ case SETUP_EFI:
+ parse_efi_setup(pa_data);
+ break;
default:
break;
}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 8289e0c..69a6ec2 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -78,6 +78,7 @@ static __initdata efi_config_table_type_t arch_tables[] = {

void *efi_runtime_map;
int nr_efi_runtime_map;
+static u64 efi_setup; /* efi setup_data physical address */

/*
* Returns 1 if 'facility' is enabled, 0 otherwise.
@@ -115,6 +116,25 @@ static int __init setup_storage_paranoia(char *arg)
}
early_param("efi_no_storage_paranoia", setup_storage_paranoia);

+void __init parse_efi_setup(u64 phys_addr)
+{
+ struct setup_data *sd;
+
+ if (!efi_enabled(EFI_64BIT)) {
+ pr_warn("SETUP_EFI not supported on 32-bit\n");
+ return;
+ }
+
+ sd = early_memremap(phys_addr, sizeof(struct setup_data));
+ if (!sd) {
+ pr_warn("efi: early_memremap setup_data failed\n");
+ return;
+ }
+ efi_setup = phys_addr + sizeof(struct setup_data);
+ nr_efi_runtime_map = (sd->len - sizeof(struct efi_setup_data)) /
+ sizeof(efi_memory_desc_t);
+ early_memunmap(sd, sizeof(struct setup_data));
+}

static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
{
@@ -494,18 +514,28 @@ static int __init efi_systab_init(void *phys)
{
if (efi_enabled(EFI_64BIT)) {
efi_system_table_64_t *systab64;
+ struct efi_setup_data *data = NULL;
u64 tmp = 0;

+ if (efi_setup) {
+ data = early_memremap(efi_setup, sizeof(*data));
+ if (!data)
+ return -ENOMEM;
+ }
systab64 = early_memremap((unsigned long)phys,
sizeof(*systab64));
if (systab64 == NULL) {
pr_err("Couldn't map the system table!\n");
+ if (data)
+ early_memunmap(data, sizeof(*data));
return -ENOMEM;
}

efi_systab.hdr = systab64->hdr;
- efi_systab.fw_vendor = systab64->fw_vendor;
- tmp |= systab64->fw_vendor;
+
+ efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor :
+ systab64->fw_vendor;
+ tmp |= efi_systab.fw_vendor;
efi_systab.fw_revision = systab64->fw_revision;
efi_systab.con_in_handle = systab64->con_in_handle;
tmp |= systab64->con_in_handle;
@@ -519,15 +549,20 @@ static int __init efi_systab_init(void *phys)
tmp |= systab64->stderr_handle;
efi_systab.stderr = systab64->stderr;
tmp |= systab64->stderr;
- efi_systab.runtime = (void *)(unsigned long)systab64->runtime;
- tmp |= systab64->runtime;
+ efi_systab.runtime = data ?
+ (void *)(unsigned long)data->runtime :
+ (void *)(unsigned long)systab64->runtime;
+ tmp |= (unsigned long)efi_systab.runtime;
efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
tmp |= systab64->boottime;
efi_systab.nr_tables = systab64->nr_tables;
- efi_systab.tables = systab64->tables;
- tmp |= systab64->tables;
+ efi_systab.tables = data ? (unsigned long)data->tables :
+ systab64->tables;
+ tmp |= efi_systab.tables;

early_memunmap(systab64, sizeof(*systab64));
+ if (data)
+ early_memunmap(data, sizeof(*data));
#ifdef CONFIG_X86_32
if (tmp >> 32) {
pr_err("EFI data located above 4GB, disabling EFI.\n");
@@ -631,6 +666,61 @@ static int __init efi_memmap_init(void)
return 0;
}

+/*
+ * For kexec kernel there's some special config table entries which could be
+ * converted to virtual addresses after entering virtual mode. In kexec kernel
+ * we need the physical addresses instead, thus passing them via setup_data
+ * and update the entries to physical addresses in this function.
+ *
+ * Currently only handles smbios which is necessary for HP z420.
+ */
+static int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+ int i, sz, ret = 0;
+ void *p, *tablep;
+ struct efi_setup_data *data;
+
+ if (!efi_setup)
+ return 0;
+
+ if (!efi_enabled(EFI_64BIT))
+ return 0;
+
+ data = early_memremap(efi_setup, sizeof(*data));
+ if (!data) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ if (!data->smbios)
+ goto out_memremap;
+
+ sz = sizeof(efi_config_table_64_t);
+
+ p = tablep = early_memremap(tables, nr_tables * sz);
+ if (!p) {
+ pr_err("Could not map Configuration table!\n");
+ ret = -ENOMEM;
+ goto out_memremap;
+ }
+
+ for (i = 0; i < efi.systab->nr_tables; i++) {
+ efi_guid_t guid;
+
+ guid = ((efi_config_table_64_t *)p)->guid;
+
+ if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
+ ((efi_config_table_64_t *)p)->table = data->smbios;
+ p += sz;
+ }
+ early_memunmap(tablep, nr_tables * sz);
+
+out_memremap:
+ early_memunmap(data, sizeof(*data));
+out:
+ return ret;
+}
+
void __init efi_init(void)
{
efi_char16_t *c16;
@@ -676,6 +766,8 @@ void __init efi_init(void)
efi.systab->hdr.revision >> 16,
efi.systab->hdr.revision & 0xffff, vendor);

+ efi_reuse_config(efi.systab->tables, efi.systab->nr_tables);
+
if (efi_config_init(arch_tables))
return;

@@ -886,6 +978,50 @@ out_krealloc:
}

/*
+ * Map efi regions which was passed via setup_data. The virt_addr is a fixed
+ * addr which was used in first kernel in case kexec boot.
+ */
+static int __init map_regions_fixed(void)
+{
+ int i, s, ret = 0;
+ u64 end, systab;
+ unsigned long size;
+ efi_memory_desc_t *md;
+ struct efi_setup_data *data;
+
+ s = sizeof(*data) + nr_efi_runtime_map * sizeof(data->map[0]);
+ data = early_memremap(efi_setup, s);
+ if (!data) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ for (i = 0, md = data->map; i < nr_efi_runtime_map; i++, md++) {
+ efi_map_region_fixed(md); /* FIXME: add error handling */
+ size = md->num_pages << PAGE_SHIFT;
+ end = md->phys_addr + size;
+
+ systab = (u64) (unsigned long) efi_phys.systab;
+ if (md->phys_addr <= systab && systab < end) {
+ systab += md->virt_addr - md->phys_addr;
+ efi.systab = (efi_system_table_t *)(unsigned long)systab;
+ }
+ ret = save_runtime_map(md, i);
+ if (ret)
+ goto out_save_runtime;
+ }
+
+ early_memunmap(data, s);
+ return 0;
+
+out_save_runtime:
+ kfree(efi_runtime_map);
+ nr_efi_runtime_map = 0;
+ early_memunmap(data, s);
+out:
+ return ret;
+}
+
+/*
* This function will switch the EFI runtime services to virtual mode.
* Essentially, we look through the EFI memmap and map every region that
* has the runtime attribute bit set in its memory descriptor into the
@@ -901,12 +1037,16 @@ out_krealloc:
* so that we're in a different address space when calling a runtime
* function. For function arguments passing we do copy the PGDs of the
* kernel page table into ->trampoline_pgd prior to each call.
+ *
+ * Specially for kexec boot, efi runtime maps in previous kernel should
+ * be passed in via setup_data. In that case runtime ranges will be mapped
+ * to the same virtual addresses exactly same as the ones in previous kernel.
*/
void __init efi_enter_virtual_mode(void)
{
efi_status_t status;
void *new_memmap = NULL;
- int count = 0;
+ int err, count = 0;

efi.systab = NULL;

@@ -919,12 +1059,19 @@ void __init efi_enter_virtual_mode(void)
return;
}

- efi_merge_regions();
-
- new_memmap = efi_map_regions(&count);
- if (!new_memmap) {
- pr_err("Error reallocating memory, EFI runtime non-functional!\n");
- return;
+ if (efi_setup) {
+ err = map_regions_fixed();
+ if (err) {
+ pr_err("Error mapping runtime services, EFI runtime non-functional!\n");
+ return;
+ }
+ } else {
+ efi_merge_regions();
+ new_memmap = efi_map_regions(&count);
+ if (!new_memmap) {
+ pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+ return;
+ }
}

BUG_ON(!efi.systab);
@@ -932,16 +1079,18 @@ void __init efi_enter_virtual_mode(void)
efi_setup_page_tables();
efi_sync_low_kernel_mappings();

- status = phys_efi_set_virtual_address_map(
- memmap.desc_size * count,
- memmap.desc_size,
- memmap.desc_version,
- (efi_memory_desc_t *)__pa(new_memmap));
-
- if (status != EFI_SUCCESS) {
- pr_alert("Unable to switch EFI into virtual mode "
- "(status=%lx)!\n", status);
- panic("EFI call to SetVirtualAddressMap() failed!");
+ if (!efi_setup) {
+ status = phys_efi_set_virtual_address_map(
+ memmap.desc_size * count,
+ memmap.desc_size,
+ memmap.desc_version,
+ (efi_memory_desc_t *)__pa(new_memmap));
+
+ if (status != EFI_SUCCESS) {
+ pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+ status);
+ panic("EFI call to SetVirtualAddressMap() failed!");
+ }
}

/*
--
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/