x86/cpu_entry_area: Move it out of the fixmap

Put the cpu_entry_area into a separate P4D entry. The fixmap gets too big
and 0-day already hit a case where the fixmap PTEs were cleared by
cleanup_highmap().

Aside of that the fixmap API is a pain as it's all backwards.

Signed-off-by: Thomas Gleixner <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Josh Poimboeuf <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: KAGA-KOKO

Documentation/x86/x86_64/mm.txt

@@ -12,6 +12,7 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
@@ -35,6 +36,7 @@ ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space

arch/x86/include/asm/cpu_entry_area.h

@@ -43,10 +43,26 @@ struct cpu_entry_area {
 };
 
 #define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_PAGES	(CPU_ENTRY_AREA_SIZE / PAGE_SIZE)
+#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 
 extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE			\
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
 
 #endif

arch/x86/include/asm/desc.h

@@ -7,6 +7,7 @@
 #include <asm/mmu.h>
 #include <asm/fixmap.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>

arch/x86/include/asm/fixmap.h

@@ -25,7 +25,6 @@
 #else
 #include <uapi/asm/vsyscall.h>
 #endif
-#include <asm/cpu_entry_area.h>
 
 /*
  * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall
@@ -84,7 +83,6 @@ enum fixed_addresses {
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 #endif
-	FIX_RO_IDT,	/* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,6 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
-	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_CPU_ENTRY_AREA_TOP,
-	FIX_CPU_ENTRY_AREA_BOTTOM = FIX_CPU_ENTRY_AREA_TOP + (CPU_ENTRY_AREA_PAGES * NR_CPUS) - 1,
 
 #ifdef CONFIG_ACPI_APEI_GHES
 	/* Used for GHES mapping from assorted contexts */
@@ -143,7 +138,7 @@ enum fixed_addresses {
 extern void reserve_top_address(unsigned long reserve);
 
 #define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
 
 extern int fixmaps_set;
 
@@ -191,30 +186,5 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
 void __early_set_fixmap(enum fixed_addresses idx,
 			phys_addr_t phys, pgprot_t flags);
 
-static inline unsigned int __get_cpu_entry_area_page_index(int cpu, int page)
-{
-	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
-
-	return FIX_CPU_ENTRY_AREA_BOTTOM - cpu*CPU_ENTRY_AREA_PAGES - page;
-}
-
-#define __get_cpu_entry_area_offset_index(cpu, offset) ({		\
-	BUILD_BUG_ON(offset % PAGE_SIZE != 0);				\
-	__get_cpu_entry_area_page_index(cpu, offset / PAGE_SIZE);	\
-	})
-
-#define get_cpu_entry_area_index(cpu, field)				\
-	__get_cpu_entry_area_offset_index((cpu), offsetof(struct cpu_entry_area, field))
-
-static inline struct cpu_entry_area *get_cpu_entry_area(int cpu)
-{
-	return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0));
-}
-
-static inline struct entry_stack *cpu_entry_stack(int cpu)
-{
-	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
-}
-
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */

arch/x86/include/asm/pgtable_32_types.h

@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE				\
+	((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START

arch/x86/include/asm/pgtable_64_types.h

@@ -76,32 +76,41 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define MAXMEM			_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
 #ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(16384, UL)
+# define __VMALLOC_BASE		_AC(0xff92000000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffd4000000000000, UL)
 #else
-#define VMALLOC_SIZE_TB	_AC(32, UL)
-#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(32, UL)
+# define __VMALLOC_BASE		_AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
 #endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START	vmalloc_base
-#define VMEMMAP_START	vmemmap_base
+# define VMALLOC_START		vmalloc_base
+# define VMEMMAP_START		vmemmap_base
 #else
-#define VMALLOC_START	__VMALLOC_BASE
-#define VMEMMAP_START	__VMEMMAP_BASE
+# define VMALLOC_START		__VMALLOC_BASE
+# define VMEMMAP_START		__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END		(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
-#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
+#define MODULES_END		__fix_to_virt(__end_of_fixed_addresses + 1)
+#define MODULES_LEN		(MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY	_AC(-2, UL)
+#define ESPFIX_BASE_ADDR	(ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD	_AC(-3, UL)
+#define CPU_ENTRY_AREA_BASE	(CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START		( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END		(-68 * (_AC(1, UL) << 30))
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 

arch/x86/kernel/dumpstack.c

@@ -18,6 +18,7 @@
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 

arch/x86/kernel/traps.c

@@ -951,8 +951,9 @@ void __init trap_init(void)
 	 * "sidt" instruction will not leak the location of the kernel, and
 	 * to defend the IDT against arbitrary memory write vulnerabilities.
 	 * It will be reloaded in cpu_init() */
-	__set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
-	idt_descr.address = fix_to_virt(FIX_RO_IDT);
+	cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table),
+		    PAGE_KERNEL_RO);
+	idt_descr.address = CPU_ENTRY_AREA_RO_IDT;
 
 	/*
 	 * Should be a barrier for any external CPU state:

arch/x86/mm/cpu_entry_area.c

@@ -15,11 +15,27 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
 	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
 #endif
 
+struct cpu_entry_area *get_cpu_entry_area(int cpu)
+{
+	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
+	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
+
+	return (struct cpu_entry_area *) va;
+}
+EXPORT_SYMBOL(get_cpu_entry_area);
+
+void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags)
+{
+	unsigned long va = (unsigned long) cea_vaddr;
+
+	set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags));
+}
+
 static void __init
-set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot)
+cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
 {
-	for ( ; pages; pages--, idx--, ptr += PAGE_SIZE)
-		__set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot);
+	for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE)
+		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
 }
 
 /* Setup the fixmap mappings only once per-processor */
@@ -47,10 +63,12 @@ static void __init setup_cpu_entry_area(int cpu)
 	pgprot_t tss_prot = PAGE_KERNEL;
 #endif
 
-	__set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot);
-	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, entry_stack_page),
-				per_cpu_ptr(&entry_stack_storage, cpu), 1,
-				PAGE_KERNEL);
+	cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
+		    gdt_prot);
+
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
+			     PAGE_KERNEL);
 
 	/*
 	 * The Intel SDM says (Volume 3, 7.2.1):
@@ -72,10 +90,9 @@ static void __init setup_cpu_entry_area(int cpu)
 	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
 		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
 	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
-	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss),
-				&per_cpu(cpu_tss_rw, cpu),
-				sizeof(struct tss_struct) / PAGE_SIZE,
-				tss_prot);
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
+			     &per_cpu(cpu_tss_rw, cpu),
+			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
 
 #ifdef CONFIG_X86_32
 	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
@@ -85,20 +102,37 @@ static void __init setup_cpu_entry_area(int cpu)
 	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
 	BUILD_BUG_ON(sizeof(exception_stacks) !=
 		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
-	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks),
-				&per_cpu(exception_stacks, cpu),
-				sizeof(exception_stacks) / PAGE_SIZE,
-				PAGE_KERNEL);
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
+			     &per_cpu(exception_stacks, cpu),
+			     sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
 
-	__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
+	cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
 		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
 #endif
 }
 
+static __init void setup_cpu_entry_area_ptes(void)
+{
+#ifdef CONFIG_X86_32
+	unsigned long start, end;
+
+	BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
+
+	start = CPU_ENTRY_AREA_BASE;
+	end = start + CPU_ENTRY_AREA_MAP_SIZE;
+
+	for (; start < end; start += PMD_SIZE)
+		populate_extra_pte(start);
+#endif
+}
+
 void __init setup_cpu_entry_areas(void)
 {
 	unsigned int cpu;
 
+	setup_cpu_entry_area_ptes();
+
 	for_each_possible_cpu(cpu)
 		setup_cpu_entry_area(cpu);
 }

arch/x86/mm/dump_pagetables.c

@@ -58,6 +58,7 @@ enum address_markers_idx {
 	KASAN_SHADOW_START_NR,
 	KASAN_SHADOW_END_NR,
 #endif
+	CPU_ENTRY_AREA_NR,
 #ifdef CONFIG_X86_ESPFIX64
 	ESPFIX_START_NR,
 #endif
@@ -81,6 +82,7 @@ static struct addr_marker address_markers[] = {
 	[KASAN_SHADOW_START_NR]	= { KASAN_SHADOW_START,	"KASAN shadow" },
 	[KASAN_SHADOW_END_NR]	= { KASAN_SHADOW_END,	"KASAN shadow end" },
 #endif
+	[CPU_ENTRY_AREA_NR]	= { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
 #ifdef CONFIG_X86_ESPFIX64
 	[ESPFIX_START_NR]	= { ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 #endif
@@ -104,6 +106,7 @@ enum address_markers_idx {
 #ifdef CONFIG_HIGHMEM
 	PKMAP_BASE_NR,
 #endif
+	CPU_ENTRY_AREA_NR,
 	FIXADDR_START_NR,
 	END_OF_SPACE_NR,
 };
@@ -116,6 +119,7 @@ static struct addr_marker address_markers[] = {
 #ifdef CONFIG_HIGHMEM
 	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
 #endif
+	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
 	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
@@ -541,8 +545,8 @@ static int __init pt_dump_init(void)
 	address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
 # endif
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
+	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
 #endif
-
 	return 0;
 }
 __initcall(pt_dump_init);