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

5 files changed, 89 insertions, 4 deletions

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index eea40d52ca78..d1e64ac80b9c 100644
--- a/arch/x86/include/asm/efi.h
+++ b/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;
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 106b7d0e2dae..d6ff0bbdb394 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/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 */
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a1bcde35db4c..61bc7d1800d7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/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;
 
@@ -2383,6 +2385,40 @@ out:
 }
 
 /*
+ * __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.
  */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 7ae939e353cd..e1cb01a22fa8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/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.
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 95e77a667ba5..17456a1d3f04 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/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;
@@ -394,6 +428,13 @@ void __init efi_free_boot_services(void)
 		}
 
 		/*
+		 * 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
 		 * real mode trampoline.  It's too late to hand boot services