Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "arm64 updates for 3.20:

   - reimplementation of the virtual remapping of UEFI Runtime Services
     in a way that is stable across kexec
   - emulation of the "setend" instruction for 32-bit tasks (user
     endianness switching trapped in the kernel, SCTLR_EL1.E0E bit set
     accordingly)
   - compat_sys_call_table implemented in C (from asm) and made it a
     constant array together with sys_call_table
   - export CPU cache information via /sys (like other architectures)
   - DMA API implementation clean-up in preparation for IOMMU support
   - macros clean-up for KVM
   - dropped some unnecessary cache+tlb maintenance
   - CONFIG_ARM64_CPU_SUSPEND clean-up
   - defconfig update (CPU_IDLE)

  The EFI changes going via the arm64 tree have been acked by Matt
  Fleming.  There is also a patch adding sys_*stat64 prototypes to
  include/linux/syscalls.h, acked by Andrew Morton"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (47 commits)
  arm64: compat: Remove incorrect comment in compat_siginfo
  arm64: Fix section mismatch on alloc_init_p[mu]d()
  arm64: Avoid breakage caused by .altmacro in fpsimd save/restore macros
  arm64: mm: use *_sect to check for section maps
  arm64: drop unnecessary cache+tlb maintenance
  arm64:mm: free the useless initial page table
  arm64: Enable CPU_IDLE in defconfig
  arm64: kernel: remove ARM64_CPU_SUSPEND config option
  arm64: make sys_call_table const
  arm64: Remove asm/syscalls.h
  arm64: Implement the compat_sys_call_table in C
  syscalls: Declare sys_*stat64 prototypes if __ARCH_WANT_(COMPAT_)STAT64
  compat: Declare compat_sys_sigpending and compat_sys_sigprocmask prototypes
  arm64: uapi: expose our struct ucontext to the uapi headers
  smp, ARM64: Kill SMP single function call interrupt
  arm64: Emulate SETEND for AArch32 tasks
  arm64: Consolidate hotplug notifier for instruction emulation
  arm64: Track system support for mixed endian EL0
  arm64: implement generic IOMMU configuration
  arm64: Combine coherent and non-coherent swiotlb dma_ops
  ...

5 files changed, 171 insertions, 35 deletions

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index fccb464..3061bb8 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -297,29 +297,15 @@ static __init int match_config_table(efi_guid_t *guid,
 	return 0;
 }
 
-int __init efi_config_init(efi_config_table_type_t *arch_tables)
+int __init efi_config_parse_tables(void *config_tables, int count, int sz,
+				   efi_config_table_type_t *arch_tables)
 {
-	void *config_tables, *tablep;
-	int i, sz;
-
-	if (efi_enabled(EFI_64BIT))
-		sz = sizeof(efi_config_table_64_t);
-	else
-		sz = sizeof(efi_config_table_32_t);
-
-	/*
-	 * Let's see what config tables the firmware passed to us.
-	 */
-	config_tables = early_memremap(efi.systab->tables,
-				       efi.systab->nr_tables * sz);
-	if (config_tables == NULL) {
-		pr_err("Could not map Configuration table!\n");
-		return -ENOMEM;
-	}
+	void *tablep;
+	int i;
 
 	tablep = config_tables;
 	pr_info("");
-	for (i = 0; i < efi.systab->nr_tables; i++) {
+	for (i = 0; i < count; i++) {
 		efi_guid_t guid;
 		unsigned long table;
 
@@ -332,8 +318,6 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables)
 			if (table64 >> 32) {
 				pr_cont("\n");
 				pr_err("Table located above 4GB, disabling EFI.\n");
-				early_memunmap(config_tables,
-					       efi.systab->nr_tables * sz);
 				return -EINVAL;
 			}
 #endif
@@ -348,13 +332,37 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables)
 		tablep += sz;
 	}
 	pr_cont("\n");
-	early_memunmap(config_tables, efi.systab->nr_tables * sz);
-
 	set_bit(EFI_CONFIG_TABLES, &efi.flags);
-
 	return 0;
 }
 
+int __init efi_config_init(efi_config_table_type_t *arch_tables)
+{
+	void *config_tables;
+	int sz, ret;
+
+	if (efi_enabled(EFI_64BIT))
+		sz = sizeof(efi_config_table_64_t);
+	else
+		sz = sizeof(efi_config_table_32_t);
+
+	/*
+	 * Let's see what config tables the firmware passed to us.
+	 */
+	config_tables = early_memremap(efi.systab->tables,
+				       efi.systab->nr_tables * sz);
+	if (config_tables == NULL) {
+		pr_err("Could not map Configuration table!\n");
+		return -ENOMEM;
+	}
+
+	ret = efi_config_parse_tables(config_tables, efi.systab->nr_tables, sz,
+				      arch_tables);
+
+	early_memunmap(config_tables, efi.systab->nr_tables * sz);
+	return ret;
+}
+
 #ifdef CONFIG_EFI_VARS_MODULE
 static int __init efi_load_efivars(void)
 {
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 2b38147..dcae482 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/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;
+	}
+}
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index d073e39..af5d63c 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -32,6 +32,15 @@
 
 static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
 
+/*
+ * Allow the platform to override the allocation granularity: this allows
+ * systems that have the capability to run with a larger page size to deal
+ * with the allocations for initrd and fdt more efficiently.
+ */
+#ifndef EFI_ALLOC_ALIGN
+#define EFI_ALLOC_ALIGN		EFI_PAGE_SIZE
+#endif
+
 struct file_info {
 	efi_file_handle_t *handle;
 	u64 size;
@@ -154,10 +163,10 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
 	 * a specific address.  We are doing page-based allocations,
 	 * so we must be aligned to a page.
 	 */
-	if (align < EFI_PAGE_SIZE)
-		align = EFI_PAGE_SIZE;
+	if (align < EFI_ALLOC_ALIGN)
+		align = EFI_ALLOC_ALIGN;
 
-	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	nr_pages = round_up(size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
 again:
 	for (i = 0; i < map_size / desc_size; i++) {
 		efi_memory_desc_t *desc;
@@ -239,10 +248,10 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 	 * a specific address.  We are doing page-based allocations,
 	 * so we must be aligned to a page.
 	 */
-	if (align < EFI_PAGE_SIZE)
-		align = EFI_PAGE_SIZE;
+	if (align < EFI_ALLOC_ALIGN)
+		align = EFI_ALLOC_ALIGN;
 
-	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	nr_pages = round_up(size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
 	for (i = 0; i < map_size / desc_size; i++) {
 		efi_memory_desc_t *desc;
 		unsigned long m = (unsigned long)map;
@@ -296,7 +305,7 @@ void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
 	if (!size)
 		return;
 
-	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	nr_pages = round_up(size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
 	efi_call_early(free_pages, addr, nr_pages);
 }
 
@@ -565,7 +574,7 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
 	 * to the preferred address.  If that fails, allocate as low
 	 * as possible while respecting the required alignment.
 	 */
-	nr_pages = round_up(alloc_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	nr_pages = round_up(alloc_size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
 	status = efi_call_early(allocate_pages,
 				EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
 				nr_pages, &efi_addr);
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 304ab29..2be1098 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/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
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index c846a96..91da56c 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/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;
 }