Merge branch 'efi-core-for-linus' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/tip

Pull EFI updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Allocate the E820 buffer before doing the
     GetMemoryMap/ExitBootServices dance so we don't run out of space

   - Clear EFI boot services mappings when freeing the memory

   - Harden efivars against callers that invoke it on non-EFI boots

   - Reduce the number of memblock reservations resulting from extensive
     use of the new efi_mem_reserve_persistent() API

   - Other assorted fixes and cleanups"

* 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/efi: Don't unmap EFI boot services code/data regions for EFI_OLD_MEMMAP and EFI_MIXED_MODE
  efi: Reduce the amount of memblock reservations for persistent allocations
  efi: Permit multiple entries in persistent memreserve data structure
  efi/libstub: Disable some warnings for x86{,_64}
  x86/efi: Move efi_<reserve/free>_boot_services() to arch/x86
  x86/efi: Unmap EFI boot services code/data regions from efi_pgd
  x86/mm/pageattr: Introduce helper function to unmap EFI boot services
  efi/fdt: Simplify the get_fdt() flow
  efi/fdt: Indentation fix
  firmware/efi: Add NULL pointer checks in efivars API functions

arch/x86/include/asm/efi.h

@@ -141,6 +141,8 @@ 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);
+extern void efi_free_boot_services(void);
+extern void efi_reserve_boot_services(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;

arch/x86/include/asm/pgtable_types.h

@@ -564,8 +564,12 @@ extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 				    unsigned int *level);
 extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
-extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
-				   unsigned numpages, unsigned long page_flags);
+extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
+					  unsigned long address,
+					  unsigned numpages,
+					  unsigned long page_flags);
+extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
+					    unsigned long numpages);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */

arch/x86/mm/pageattr.c

@@ -2346,8 +2346,8 @@ bool kernel_page_present(struct page *page)
 
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
-int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
-			    unsigned numpages, unsigned long page_flags)
+int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+				   unsigned numpages, unsigned long page_flags)
 {
 	int retval = -EINVAL;
 
@@ -2361,6 +2361,8 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.flags = 0,
 	};
 
+	WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP");
+
 	if (!(__supported_pte_mask & _PAGE_NX))
 		goto out;
 
@@ -2382,6 +2384,40 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 	return retval;
 }
 
+/*
+ * __flush_tlb_all() flushes mappings only on current CPU and hence this
+ * function shouldn't be used in an SMP environment. Presently, it's used only
+ * during boot (way before smp_init()) by EFI subsystem and hence is ok.
+ */
+int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
+				     unsigned long numpages)
+{
+	int retval;
+
+	/*
+	 * The typical sequence for unmapping is to find a pte through
+	 * lookup_address_in_pgd() (ideally, it should never return NULL because
+	 * the address is already mapped) and change it's protections. As pfn is
+	 * the *target* of a mapping, it's not useful while unmapping.
+	 */
+	struct cpa_data cpa = {
+		.vaddr		= &address,
+		.pfn		= 0,
+		.pgd		= pgd,
+		.numpages	= numpages,
+		.mask_set	= __pgprot(0),
+		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW),
+		.flags		= 0,
+	};
+
+	WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP");
+
+	retval = __change_page_attr_set_clr(&cpa, 0);
+	__flush_tlb_all();
+
+	return retval;
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.

arch/x86/platform/efi/efi.c

@@ -993,6 +993,8 @@ static void __init __efi_enter_virtual_mode(void)
 		panic("EFI call to SetVirtualAddressMap() failed!");
 	}
 
+	efi_free_boot_services();
+
 	/*
 	 * Now that EFI is in virtual mode, update the function
 	 * pointers in the runtime service table to the new virtual addresses.

arch/x86/platform/efi/quirks.c

@@ -369,6 +369,40 @@ void __init efi_reserve_boot_services(void)
 	}
 }
 
+/*
+ * Apart from having VA mappings for EFI boot services code/data regions,
+ * (duplicate) 1:1 mappings were also created as a quirk for buggy firmware. So,
+ * unmap both 1:1 and VA mappings.
+ */
+static void __init efi_unmap_pages(efi_memory_desc_t *md)
+{
+	pgd_t *pgd = efi_mm.pgd;
+	u64 pa = md->phys_addr;
+	u64 va = md->virt_addr;
+
+	/*
+	 * To Do: Remove this check after adding functionality to unmap EFI boot
+	 * services code/data regions from direct mapping area because
+	 * "efi=old_map" maps EFI regions in swapper_pg_dir.
+	 */
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	/*
+	 * EFI mixed mode has all RAM mapped to access arguments while making
+	 * EFI runtime calls, hence don't unmap EFI boot services code/data
+	 * regions.
+	 */
+	if (!efi_is_native())
+		return;
+
+	if (kernel_unmap_pages_in_pgd(pgd, pa, md->num_pages))
+		pr_err("Failed to unmap 1:1 mapping for 0x%llx\n", pa);
+
+	if (kernel_unmap_pages_in_pgd(pgd, va, md->num_pages))
+		pr_err("Failed to unmap VA mapping for 0x%llx\n", va);
+}
+
 void __init efi_free_boot_services(void)
 {
 	phys_addr_t new_phys, new_size;
@@ -393,6 +427,13 @@ void __init efi_free_boot_services(void)
 			continue;
 		}
 
+		/*
+		 * Before calling set_virtual_address_map(), EFI boot services
+		 * code/data regions were mapped as a quirk for buggy firmware.
+		 * Unmap them from efi_pgd before freeing them up.
+		 */
+		efi_unmap_pages(md);
+
 		/*
 		 * Nasty quirk: if all sub-1MB memory is used for boot
 		 * services, we can get here without having allocated the

drivers/firmware/efi/efi.c

@@ -602,21 +602,33 @@ int __init efi_apply_persistent_mem_reservations(void)
 
 		while (prsv) {
 			struct linux_efi_memreserve *rsv;
-
-			/* reserve the entry itself */
-			memblock_reserve(prsv, sizeof(*rsv));
-
-			rsv = early_memremap(prsv, sizeof(*rsv));
-			if (rsv == NULL) {
+			u8 *p;
+			int i;
+
+			/*
+			 * Just map a full page: that is what we will get
+			 * anyway, and it permits us to map the entire entry
+			 * before knowing its size.
+			 */
+			p = early_memremap(ALIGN_DOWN(prsv, PAGE_SIZE),
+					   PAGE_SIZE);
+			if (p == NULL) {
 				pr_err("Could not map UEFI memreserve entry!\n");
 				return -ENOMEM;
 			}
 
-			if (rsv->size)
-				memblock_reserve(rsv->base, rsv->size);
+			rsv = (void *)(p + prsv % PAGE_SIZE);
+
+			/* reserve the entry itself */
+			memblock_reserve(prsv, EFI_MEMRESERVE_SIZE(rsv->size));
+
+			for (i = 0; i < atomic_read(&rsv->count); i++) {
+				memblock_reserve(rsv->entry[i].base,
+						 rsv->entry[i].size);
+			}
 
 			prsv = rsv->next;
-			early_memunmap(rsv, sizeof(*rsv));
+			early_memunmap(p, PAGE_SIZE);
 		}
 	}
 
@@ -985,7 +997,8 @@ static int __init efi_memreserve_map_root(void)
 int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
 {
 	struct linux_efi_memreserve *rsv;
-	int rc;
+	unsigned long prsv;
+	int rc, index;
 
 	if (efi_memreserve_root == (void *)ULONG_MAX)
 		return -ENODEV;
@@ -996,12 +1009,27 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
 			return rc;
 	}
 
-	rsv = kmalloc(sizeof(*rsv), GFP_ATOMIC);
+	/* first try to find a slot in an existing linked list entry */
+	for (prsv = efi_memreserve_root->next; prsv; prsv = rsv->next) {
+		rsv = __va(prsv);
+		index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size);
+		if (index < rsv->size) {
+			rsv->entry[index].base = addr;
+			rsv->entry[index].size = size;
+
+			return 0;
+		}
+	}
+
+	/* no slot found - allocate a new linked list entry */
+	rsv = (struct linux_efi_memreserve *)__get_free_page(GFP_ATOMIC);
 	if (!rsv)
 		return -ENOMEM;
 
-	rsv->base = addr;
-	rsv->size = size;
+	rsv->size = EFI_MEMRESERVE_COUNT(PAGE_SIZE);
+	atomic_set(&rsv->count, 1);
+	rsv->entry[0].base = addr;
+	rsv->entry[0].size = size;
 
 	spin_lock(&efi_mem_reserve_persistent_lock);
 	rsv->next = efi_memreserve_root->next;

drivers/firmware/efi/libstub/Makefile

@@ -9,7 +9,10 @@ cflags-$(CONFIG_X86_32)		:= -march=i386
 cflags-$(CONFIG_X86_64)		:= -mcmodel=small
 cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
-				   -mno-mmx -mno-sse -fshort-wchar
+				   -mno-mmx -mno-sse -fshort-wchar \
+				   -Wno-pointer-sign \
+				   $(call cc-disable-warning, address-of-packed-member) \
+				   $(call cc-disable-warning, gnu)
 
 # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
 # disable the stackleak plugin

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

@@ -86,8 +86,8 @@ void install_memreserve_table(efi_system_table_t *sys_table_arg)
 	}
 
 	rsv->next = 0;
-	rsv->base = 0;
 	rsv->size = 0;
+	atomic_set(&rsv->count, 0);
 
 	status = efi_call_early(install_configuration_table,
 				&memreserve_table_guid,

drivers/firmware/efi/libstub/fdt.c

@@ -370,22 +370,24 @@ void *get_fdt(efi_system_table_t *sys_table, unsigned long *fdt_size)
 {
 	efi_guid_t fdt_guid = DEVICE_TREE_GUID;
 	efi_config_table_t *tables;
-	void *fdt;
 	int i;
 
-	tables = (efi_config_table_t *) sys_table->tables;
-	fdt = NULL;
+	tables = (efi_config_table_t *)sys_table->tables;
 
-	for (i = 0; i < sys_table->nr_tables; i++)
-		if (efi_guidcmp(tables[i].guid, fdt_guid) == 0) {
-			fdt = (void *) tables[i].table;
-			if (fdt_check_header(fdt) != 0) {
-				pr_efi_err(sys_table, "Invalid header detected on UEFI supplied FDT, ignoring ...\n");
-				return NULL;
-			}
-			*fdt_size = fdt_totalsize(fdt);
-			break;
-	 }
+	for (i = 0; i < sys_table->nr_tables; i++) {
+		void *fdt;
+
+		if (efi_guidcmp(tables[i].guid, fdt_guid) != 0)
+			continue;
+
+		fdt = (void *)tables[i].table;
+		if (fdt_check_header(fdt) != 0) {
+			pr_efi_err(sys_table, "Invalid header detected on UEFI supplied FDT, ignoring ...\n");
+			return NULL;
+		}
+		*fdt_size = fdt_totalsize(fdt);
+		return fdt;
+	}
 
-	return fdt;
+	return NULL;
 }