arm64/efi: move SetVirtualAddressMap() to UEFI stub

In order to support kexec, the kernel needs to be able to deal with the
state of the UEFI firmware after SetVirtualAddressMap() has been called.
To avoid having separate code paths for non-kexec and kexec, let's move
the call to SetVirtualAddressMap() to the stub: this will guarantee us
that it will only be called once (since the stub is not executed during
kexec), and ensures that the UEFI state is identical between kexec and
normal boot.

This implies that the layout of the virtual mapping needs to be created
by the stub as well. All regions are rounded up to a naturally aligned
multiple of 64 KB (for compatibility with 64k pages kernels) and recorded
in the UEFI memory map. The kernel proper reads those values and installs
the mappings in a dedicated set of page tables that are swapped in during
UEFI Runtime Services calls.

Acked-by: Leif Lindholm <leif.lindholm@linaro.org>
Acked-by: Matt Fleming <matt.fleming@intel.com>
Tested-by: Leif Lindholm <leif.lindholm@linaro.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

arch/arm64/include/asm/efi.h

@@ -7,28 +7,36 @@
 #ifdef CONFIG_EFI
 extern void efi_init(void);
 extern void efi_idmap_init(void);
+extern void efi_virtmap_init(void);
 #else
 #define efi_init()
 #define efi_idmap_init()
+#define efi_virtmap_init()
 #endif
 
 #define efi_call_virt(f, ...)						\
 ({									\
-	efi_##f##_t *__f = efi.systab->runtime->f;			\
+	efi_##f##_t *__f;						\
 	efi_status_t __s;						\
 									\
 	kernel_neon_begin();						\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
 	__s = __f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
 	kernel_neon_end();						\
 	__s;								\
 })
 
 #define __efi_call_virt(f, ...)						\
 ({									\
-	efi_##f##_t *__f = efi.systab->runtime->f;			\
+	efi_##f##_t *__f;						\
 									\
 	kernel_neon_begin();						\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
 	__f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
 	kernel_neon_end();						\
 })
 
@@ -46,4 +54,26 @@ extern void efi_idmap_init(void);
 
 #define EFI_ALLOC_ALIGN		SZ_64K
 
+/*
+ * On ARM systems, virtually remapped UEFI runtime services are set up in three
+ * distinct stages:
+ * - The stub retrieves the final version of the memory map from UEFI, populates
+ *   the virt_addr fields and calls the SetVirtualAddressMap() [SVAM] runtime
+ *   service to communicate the new mapping to the firmware (Note that the new
+ *   mapping is not live at this time)
+ * - During early boot, the page tables are allocated and populated based on the
+ *   virt_addr fields in the memory map, but only if all descriptors with the
+ *   EFI_MEMORY_RUNTIME attribute have a non-zero value for virt_addr. If this
+ *   succeeds, the EFI_VIRTMAP flag is set to indicate that the virtual mappings
+ *   have been installed successfully.
+ * - During an early initcall(), the UEFI Runtime Services are enabled and the
+ *   EFI_RUNTIME_SERVICES bit set if some conditions are met, i.e., we need a
+ *   non-early mapping of the UEFI system table, and we need to have the virtmap
+ *   installed.
+ */
+#define EFI_VIRTMAP		EFI_ARCH_1
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
 #endif /* _ASM_EFI_H */

arch/arm64/kernel/efi.c

@@ -11,25 +11,31 @@
  *
  */
 
+#include <linux/atomic.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
+#include <linux/mm_types.h>
 #include <linux/bootmem.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/preempt.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/efi.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
 
 struct efi_memory_map memmap;
 
-static efi_runtime_services_t *runtime;
-
 static u64 efi_system_table;
 
 static int uefi_debug __initdata;
@@ -69,9 +75,33 @@ static void __init efi_setup_idmap(void)
 	}
 }
 
+/*
+ * Translate a EFI virtual address into a physical address: this is necessary,
+ * as some data members of the EFI system table are virtually remapped after
+ * SetVirtualAddressMap() has been called.
+ */
+static phys_addr_t efi_to_phys(unsigned long addr)
+{
+	efi_memory_desc_t *md;
+
+	for_each_efi_memory_desc(&memmap, md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == 0)
+			/* no virtual mapping has been installed by the stub */
+			break;
+		if (md->virt_addr <= addr &&
+		    (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
+			return md->phys_addr + addr - md->virt_addr;
+	}
+	return addr;
+}
+
 static int __init uefi_init(void)
 {
 	efi_char16_t *c16;
+	void *config_tables;
+	u64 table_size;
 	char vendor[100] = "unknown";
 	int i, retval;
 
@@ -99,7 +129,7 @@ static int __init uefi_init(void)
 			efi.systab->hdr.revision & 0xffff);
 
 	/* Show what we know for posterity */
-	c16 = early_memremap(efi.systab->fw_vendor,
+	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
 			     sizeof(vendor));
 	if (c16) {
 		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
@@ -112,8 +142,14 @@ static int __init uefi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	retval = efi_config_init(NULL);
+	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
+	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
+				       table_size);
+
+	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
+					 sizeof(efi_config_table_64_t), NULL);
 
+	early_memunmap(config_tables, table_size);
 out:
 	early_memunmap(efi.systab,  sizeof(efi_system_table_t));
 	return retval;
@@ -329,51 +365,14 @@ void __init efi_idmap_init(void)
 	early_memunmap(memmap.map, memmap.map_end - memmap.map);
 }
 
-static int __init remap_region(efi_memory_desc_t *md, void **new)
-{
-	u64 paddr, vaddr, npages, size;
-
-	paddr = md->phys_addr;
-	npages = md->num_pages;
-	memrange_efi_to_native(&paddr, &npages);
-	size = npages << PAGE_SHIFT;
-
-	if (is_normal_ram(md))
-		vaddr = (__force u64)ioremap_cache(paddr, size);
-	else
-		vaddr = (__force u64)ioremap(paddr, size);
-
-	if (!vaddr) {
-		pr_err("Unable to remap 0x%llx pages @ %p\n",
-		       npages, (void *)paddr);
-		return 0;
-	}
-
-	/* adjust for any rounding when EFI and system pagesize differs */
-	md->virt_addr = vaddr + (md->phys_addr - paddr);
-
-	if (uefi_debug)
-		pr_info("  EFI remap 0x%012llx => %p\n",
-			md->phys_addr, (void *)md->virt_addr);
-
-	memcpy(*new, md, memmap.desc_size);
-	*new += memmap.desc_size;
-
-	return 1;
-}
-
 /*
- * Switch UEFI from an identity map to a kernel virtual map
+ * Enable the UEFI Runtime Services if all prerequisites are in place, i.e.,
+ * non-early mapping of the UEFI system table and virtual mappings for all
+ * EFI_MEMORY_RUNTIME regions.
  */
-static int __init arm64_enter_virtual_mode(void)
+static int __init arm64_enable_runtime_services(void)
 {
-	efi_memory_desc_t *md;
-	phys_addr_t virtmap_phys;
-	void *virtmap, *virt_md;
-	efi_status_t status;
 	u64 mapsize;
-	int count = 0;
-	unsigned long flags;
 
 	if (!efi_enabled(EFI_BOOT)) {
 		pr_info("EFI services will not be available.\n");
@@ -395,81 +394,30 @@ static int __init arm64_enter_virtual_mode(void)
 
 	efi.memmap = &memmap;
 
-	/* Map the runtime regions */
-	virtmap = kmalloc(mapsize, GFP_KERNEL);
-	if (!virtmap) {
-		pr_err("Failed to allocate EFI virtual memmap\n");
-		return -1;
-	}
-	virtmap_phys = virt_to_phys(virtmap);
-	virt_md = virtmap;
-
-	for_each_efi_memory_desc(&memmap, md) {
-		if (!(md->attribute & EFI_MEMORY_RUNTIME))
-			continue;
-		if (!remap_region(md, &virt_md))
-			goto err_unmap;
-		++count;
-	}
-
-	efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table);
+	efi.systab = (__force void *)ioremap_cache(efi_system_table,
+						   sizeof(efi_system_table_t));
 	if (!efi.systab) {
-		/*
-		 * If we have no virtual mapping for the System Table at this
-		 * point, the memory map doesn't cover the physical offset where
-		 * it resides. This means the System Table will be inaccessible
-		 * to Runtime Services themselves once the virtual mapping is
-		 * installed.
-		 */
-		pr_err("Failed to remap EFI System Table -- buggy firmware?\n");
-		goto err_unmap;
+		pr_err("Failed to remap EFI System Table\n");
+		return -1;
 	}
 	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
-	local_irq_save(flags);
-	cpu_switch_mm(idmap_pg_dir, &init_mm);
-
-	/* Call SetVirtualAddressMap with the physical address of the map */
-	runtime = efi.systab->runtime;
-	efi.set_virtual_address_map = runtime->set_virtual_address_map;
-
-	status = efi.set_virtual_address_map(count * memmap.desc_size,
-					     memmap.desc_size,
-					     memmap.desc_version,
-					     (efi_memory_desc_t *)virtmap_phys);
-	cpu_set_reserved_ttbr0();
-	flush_tlb_all();
-	local_irq_restore(flags);
-
-	kfree(virtmap);
-
 	free_boot_services();
 
-	if (status != EFI_SUCCESS) {
-		pr_err("Failed to set EFI virtual address map! [%lx]\n",
-			status);
+	if (!efi_enabled(EFI_VIRTMAP)) {
+		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
 		return -1;
 	}
 
 	/* Set up runtime services function pointers */
-	runtime = efi.systab->runtime;
 	efi_native_runtime_setup();
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
 	efi.runtime_version = efi.systab->hdr.revision;
 
 	return 0;
-
-err_unmap:
-	/* unmap all mappings that succeeded: there are 'count' of those */
-	for (virt_md = virtmap; count--; virt_md += memmap.desc_size) {
-		md = virt_md;
-		iounmap((__force void __iomem *)md->virt_addr);
-	}
-	kfree(virtmap);
-	return -1;
 }
-early_initcall(arm64_enter_virtual_mode);
+early_initcall(arm64_enable_runtime_services);
 
 static int __init arm64_dmi_init(void)
 {
@@ -484,3 +432,79 @@ static int __init arm64_dmi_init(void)
 	return 0;
 }
 core_initcall(arm64_dmi_init);
+
+static pgd_t efi_pgd[PTRS_PER_PGD] __page_aligned_bss;
+
+static struct mm_struct efi_mm = {
+	.mm_rb			= RB_ROOT,
+	.pgd			= efi_pgd,
+	.mm_users		= ATOMIC_INIT(2),
+	.mm_count		= ATOMIC_INIT(1),
+	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
+	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
+	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
+	INIT_MM_CONTEXT(efi_mm)
+};
+
+static void efi_set_pgd(struct mm_struct *mm)
+{
+	cpu_switch_mm(mm->pgd, mm);
+	flush_tlb_all();
+	if (icache_is_aivivt())
+		__flush_icache_all();
+}
+
+void efi_virtmap_load(void)
+{
+	preempt_disable();
+	efi_set_pgd(&efi_mm);
+}
+
+void efi_virtmap_unload(void)
+{
+	efi_set_pgd(current->active_mm);
+	preempt_enable();
+}
+
+void __init efi_virtmap_init(void)
+{
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_BOOT))
+		return;
+
+	for_each_efi_memory_desc(&memmap, md) {
+		u64 paddr, npages, size;
+		pgprot_t prot;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (WARN(md->virt_addr == 0,
+			 "UEFI virtual mapping incomplete or missing -- no entry found for 0x%llx\n",
+			 md->phys_addr))
+			return;
+
+		paddr = md->phys_addr;
+		npages = md->num_pages;
+		memrange_efi_to_native(&paddr, &npages);
+		size = npages << PAGE_SHIFT;
+
+		pr_info("  EFI remap 0x%016llx => %p\n",
+			md->phys_addr, (void *)md->virt_addr);
+
+		/*
+		 * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
+		 * executable, everything else can be mapped with the XN bits
+		 * set.
+		 */
+		if (!is_normal_ram(md))
+			prot = __pgprot(PROT_DEVICE_nGnRE);
+		else if (md->type == EFI_RUNTIME_SERVICES_CODE)
+			prot = PAGE_KERNEL_EXEC;
+		else
+			prot = PAGE_KERNEL;
+
+		create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot);
+	}
+	set_bit(EFI_VIRTMAP, &efi.flags);
+}

arch/arm64/kernel/setup.c

@@ -401,6 +401,7 @@ void __init setup_arch(char **cmdline_p)
 	paging_init();
 	request_standard_resources();
 
+	efi_virtmap_init();
 	efi_idmap_init();
 	early_ioremap_reset();
 

drivers/firmware/efi/libstub/arm-stub.c

@@ -295,3 +295,62 @@ fail_free_image:
 fail:
 	return EFI_ERROR;
 }
+
+/*
+ * This is the base address at which to start allocating virtual memory ranges
+ * for UEFI Runtime Services. This is in the low TTBR0 range so that we can use
+ * any allocation we choose, and eliminate the risk of a conflict after kexec.
+ * The value chosen is the largest non-zero power of 2 suitable for this purpose
+ * both on 32-bit and 64-bit ARM CPUs, to maximize the likelihood that it can
+ * be mapped efficiently.
+ */
+#define EFI_RT_VIRTUAL_BASE	0x40000000
+
+/*
+ * efi_get_virtmap() - create a virtual mapping for the EFI memory map
+ *
+ * This function populates the virt_addr fields of all memory region descriptors
+ * in @memory_map whose EFI_MEMORY_RUNTIME attribute is set. Those descriptors
+ * are also copied to @runtime_map, and their total count is returned in @count.
+ */
+void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
+		     unsigned long desc_size, efi_memory_desc_t *runtime_map,
+		     int *count)
+{
+	u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
+	efi_memory_desc_t *out = runtime_map;
+	int l;
+
+	for (l = 0; l < map_size; l += desc_size) {
+		efi_memory_desc_t *in = (void *)memory_map + l;
+		u64 paddr, size;
+
+		if (!(in->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+
+		/*
+		 * Make the mapping compatible with 64k pages: this allows
+		 * a 4k page size kernel to kexec a 64k page size kernel and
+		 * vice versa.
+		 */
+		paddr = round_down(in->phys_addr, SZ_64K);
+		size = round_up(in->num_pages * EFI_PAGE_SIZE +
+				in->phys_addr - paddr, SZ_64K);
+
+		/*
+		 * Avoid wasting memory on PTEs by choosing a virtual base that
+		 * is compatible with section mappings if this region has the
+		 * appropriate size and physical alignment. (Sections are 2 MB
+		 * on 4k granule kernels)
+		 */
+		if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
+			efi_virt_base = round_up(efi_virt_base, SZ_2M);
+
+		in->virt_addr = efi_virt_base + in->phys_addr - paddr;
+		efi_virt_base += size;
+
+		memcpy(out, in, desc_size);
+		out = (void *)out + desc_size;
+		++*count;
+	}
+}

drivers/firmware/efi/libstub/efistub.h

@@ -39,4 +39,8 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 
 void *get_fdt(efi_system_table_t *sys_table);
 
+void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
+		     unsigned long desc_size, efi_memory_desc_t *runtime_map,
+		     int *count);
+
 #endif

drivers/firmware/efi/libstub/fdt.c

@@ -14,6 +14,8 @@
 #include <linux/libfdt.h>
 #include <asm/efi.h>
 
+#include "efistub.h"
+
 efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 			unsigned long orig_fdt_size,
 			void *fdt, int new_fdt_size, char *cmdline_ptr,
@@ -193,9 +195,26 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	unsigned long map_size, desc_size;
 	u32 desc_ver;
 	unsigned long mmap_key;
-	efi_memory_desc_t *memory_map;
+	efi_memory_desc_t *memory_map, *runtime_map;
 	unsigned long new_fdt_size;
 	efi_status_t status;
+	int runtime_entry_count = 0;
+
+	/*
+	 * Get a copy of the current memory map that we will use to prepare
+	 * the input for SetVirtualAddressMap(). We don't have to worry about
+	 * subsequent allocations adding entries, since they could not affect
+	 * the number of EFI_MEMORY_RUNTIME regions.
+	 */
+	status = efi_get_memory_map(sys_table, &runtime_map, &map_size,
+				    &desc_size, &desc_ver, &mmap_key);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n");
+		return status;
+	}
+
+	pr_efi(sys_table,
+	       "Exiting boot services and installing virtual address map...\n");
 
 	/*
 	 * Estimate size of new FDT, and allocate memory for it. We
@@ -248,12 +267,48 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 		}
 	}
 
+	/*
+	 * Update the memory map with virtual addresses. The function will also
+	 * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
+	 * entries so that we can pass it straight into SetVirtualAddressMap()
+	 */
+	efi_get_virtmap(memory_map, map_size, desc_size, runtime_map,
+			&runtime_entry_count);
+
 	/* Now we are ready to exit_boot_services.*/
 	status = sys_table->boottime->exit_boot_services(handle, mmap_key);
 
+	if (status == EFI_SUCCESS) {
+		efi_set_virtual_address_map_t *svam;
 
-	if (status == EFI_SUCCESS)
-		return status;
+		/* Install the new virtual address map */
+		svam = sys_table->runtime->set_virtual_address_map;
+		status = svam(runtime_entry_count * desc_size, desc_size,
+			      desc_ver, runtime_map);
+
+		/*
+		 * We are beyond the point of no return here, so if the call to
+		 * SetVirtualAddressMap() failed, we need to signal that to the
+		 * incoming kernel but proceed normally otherwise.
+		 */
+		if (status != EFI_SUCCESS) {
+			int l;
+
+			/*
+			 * Set the virtual address field of all
+			 * EFI_MEMORY_RUNTIME entries to 0. This will signal
+			 * the incoming kernel that no virtual translation has
+			 * been installed.
+			 */
+			for (l = 0; l < map_size; l += desc_size) {
+				efi_memory_desc_t *p = (void *)memory_map + l;
+
+				if (p->attribute & EFI_MEMORY_RUNTIME)
+					p->virt_addr = 0;
+			}
+		}
+		return EFI_SUCCESS;
+	}
 
 	pr_efi_err(sys_table, "Exit boot services failed.\n");
 
@@ -264,6 +319,7 @@ fail_free_new_fdt:
 	efi_free(sys_table, new_fdt_size, *new_fdt_addr);
 
 fail:
+	sys_table->boottime->free_pool(runtime_map);
 	return EFI_LOAD_ERROR;
 }