Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/tip/tip

Pull x86 pti updates from Thomas Gleixner:
 "Another series of PTI related changes:

   - Remove the manual stack switch for user entries from the idtentry
     code. This debloats entry by 5k+ bytes of text.

   - Use the proper types for the asm/bootparam.h defines to prevent
     user space compile errors.

   - Use PAGE_GLOBAL for !PCID systems to gain back performance

   - Prevent setting of huge PUD/PMD entries when the entries are not
     leaf entries otherwise the entries to which the PUD/PMD points to
     and are populated get lost"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/pgtable: Don't set huge PUD/PMD on non-leaf entries
  x86/pti: Leave kernel text global for !PCID
  x86/pti: Never implicitly clear _PAGE_GLOBAL for kernel image
  x86/pti: Enable global pages for shared areas
  x86/mm: Do not forbid _PAGE_RW before init for __ro_after_init
  x86/mm: Comment _PAGE_GLOBAL mystery
  x86/mm: Remove extra filtering in pageattr code
  x86/mm: Do not auto-massage page protections
  x86/espfix: Document use of _PAGE_GLOBAL
  x86/mm: Introduce "default" kernel PTE mask
  x86/mm: Undo double _PAGE_PSE clearing
  x86/mm: Factor out pageattr _PAGE_GLOBAL setting
  x86/entry/64: Drop idtentry's manual stack switch for user entries
  x86/uapi: Fix asm/bootparam.h userspace compilation errors

arch/x86/boot/compressed/kaslr.c

@@ -54,6 +54,9 @@ unsigned int ptrs_per_p4d __ro_after_init = 1;
 
 extern unsigned long get_cmd_line_ptr(void);
 
+/* Used by PAGE_KERN* macros: */
+pteval_t __default_kernel_pte_mask __read_mostly = ~0;
+
 /* Simplified build-specific string for starting entropy. */
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;

arch/x86/entry/entry_64.S

@@ -913,7 +913,7 @@ ENTRY(\sym)
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	.endif
 
-	.if \paranoid < 2
+	.if \paranoid == 1
 	testb	$3, CS-ORIG_RAX(%rsp)		/* If coming from userspace, switch stacks */
 	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
@@ -960,7 +960,7 @@ ENTRY(\sym)
 	jmp	error_exit
 	.endif
 
-	.if \paranoid < 2
+	.if \paranoid == 1
 	/*
 	 * Entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers

arch/x86/include/asm/pgtable.h

@@ -526,22 +526,39 @@ static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
 	return protval;
 }
 
+static inline pgprotval_t check_pgprot(pgprot_t pgprot)
+{
+	pgprotval_t massaged_val = massage_pgprot(pgprot);
+
+	/* mmdebug.h can not be included here because of dependencies */
+#ifdef CONFIG_DEBUG_VM
+	WARN_ONCE(pgprot_val(pgprot) != massaged_val,
+		  "attempted to set unsupported pgprot: %016llx "
+		  "bits: %016llx supported: %016llx\n",
+		  (u64)pgprot_val(pgprot),
+		  (u64)pgprot_val(pgprot) ^ massaged_val,
+		  (u64)__supported_pte_mask);
+#endif
+
+	return massaged_val;
+}
+
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
 	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     massage_pgprot(pgprot));
+		     check_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
 	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     massage_pgprot(pgprot));
+		     check_pgprot(pgprot));
 }
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
 	return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     massage_pgprot(pgprot));
+		     check_pgprot(pgprot));
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
@@ -553,7 +570,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 * the newprot (if present):
 	 */
 	val &= _PAGE_CHG_MASK;
-	val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
+	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
 
 	return __pte(val);
 }
@@ -563,7 +580,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	pmdval_t val = pmd_val(pmd);
 
 	val &= _HPAGE_CHG_MASK;
-	val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
+	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
 
 	return __pmd(val);
 }

arch/x86/include/asm/pgtable_types.h

@@ -196,19 +196,21 @@ enum page_cache_mode {
 #define __PAGE_KERNEL_NOENC	(__PAGE_KERNEL)
 #define __PAGE_KERNEL_NOENC_WP	(__PAGE_KERNEL_WP)
 
-#define PAGE_KERNEL		__pgprot(__PAGE_KERNEL | _PAGE_ENC)
-#define PAGE_KERNEL_NOENC	__pgprot(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO		__pgprot(__PAGE_KERNEL_RO | _PAGE_ENC)
-#define PAGE_KERNEL_EXEC	__pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_EXEC_NOENC	__pgprot(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX		__pgprot(__PAGE_KERNEL_RX | _PAGE_ENC)
-#define PAGE_KERNEL_NOCACHE	__pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
-#define PAGE_KERNEL_LARGE	__pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
-#define PAGE_KERNEL_LARGE_EXEC	__pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_VVAR	__pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)
-
-#define PAGE_KERNEL_IO		__pgprot(__PAGE_KERNEL_IO)
-#define PAGE_KERNEL_IO_NOCACHE	__pgprot(__PAGE_KERNEL_IO_NOCACHE)
+#define default_pgprot(x)	__pgprot((x) & __default_kernel_pte_mask)
+
+#define PAGE_KERNEL		default_pgprot(__PAGE_KERNEL | _PAGE_ENC)
+#define PAGE_KERNEL_NOENC	default_pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO		default_pgprot(__PAGE_KERNEL_RO | _PAGE_ENC)
+#define PAGE_KERNEL_EXEC	default_pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC)
+#define PAGE_KERNEL_EXEC_NOENC	default_pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX		default_pgprot(__PAGE_KERNEL_RX | _PAGE_ENC)
+#define PAGE_KERNEL_NOCACHE	default_pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
+#define PAGE_KERNEL_LARGE	default_pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
+#define PAGE_KERNEL_LARGE_EXEC	default_pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
+#define PAGE_KERNEL_VVAR	default_pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)
+
+#define PAGE_KERNEL_IO		default_pgprot(__PAGE_KERNEL_IO)
+#define PAGE_KERNEL_IO_NOCACHE	default_pgprot(__PAGE_KERNEL_IO_NOCACHE)
 
 #endif	/* __ASSEMBLY__ */
 
@@ -483,6 +485,7 @@ static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
 typedef struct page *pgtable_t;
 
 extern pteval_t __supported_pte_mask;
+extern pteval_t __default_kernel_pte_mask;
 extern void set_nx(void);
 extern int nx_enabled;
 

arch/x86/include/asm/pti.h

@@ -6,8 +6,10 @@
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
 extern void pti_check_boottime_disable(void);
+extern void pti_clone_kernel_text(void);
 #else
 static inline void pti_check_boottime_disable(void) { }
+static inline void pti_clone_kernel_text(void) { }
 #endif
 
 #endif /* __ASSEMBLY__ */

arch/x86/include/uapi/asm/bootparam.h

@@ -137,15 +137,15 @@ struct boot_e820_entry {
  * setup data structure.
  */
 struct jailhouse_setup_data {
-	u16	version;
-	u16	compatible_version;
-	u16	pm_timer_address;
-	u16	num_cpus;
-	u64	pci_mmconfig_base;
-	u32	tsc_khz;
-	u32	apic_khz;
-	u8	standard_ioapic;
-	u8	cpu_ids[255];
+	__u16	version;
+	__u16	compatible_version;
+	__u16	pm_timer_address;
+	__u16	num_cpus;
+	__u64	pci_mmconfig_base;
+	__u32	tsc_khz;
+	__u32	apic_khz;
+	__u8	standard_ioapic;
+	__u8	cpu_ids[255];
 } __attribute__((packed));
 
 /* The so-called "zeropage" */

arch/x86/kernel/espfix_64.c

@@ -195,6 +195,10 @@ void init_espfix_ap(int cpu)
 
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
+	/*
+	 * __PAGE_KERNEL_* includes _PAGE_GLOBAL, which we want since
+	 * this is mapped to userspace.
+	 */
 	pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);

arch/x86/kernel/head64.c

@@ -195,6 +195,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	pud[i + 1] = (pudval_t)pmd + pgtable_flags;
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+	/* Filter out unsupported __PAGE_KERNEL_* bits: */
+	pmd_entry &= __supported_pte_mask;
 	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 

arch/x86/kernel/head_64.S

@@ -399,8 +399,13 @@ NEXT_PAGE(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.fill	511, 8, 0
 NEXT_PAGE(level2_ident_pgt)
-	/* Since I easily can, map the first 1G.
+	/*
+	 * Since I easily can, map the first 1G.
 	 * Don't set NX because code runs from these pages.
+	 *
+	 * Note: This sets _PAGE_GLOBAL despite whether
+	 * the CPU supports it or it is enabled.  But,
+	 * the CPU should ignore the bit.
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
 #else
@@ -431,6 +436,10 @@ NEXT_PAGE(level2_kernel_pgt)
 	 * (NOTE: at +512MB starts the module area, see MODULES_VADDR.
 	 *  If you want to increase this then increase MODULES_VADDR
 	 *  too.)
+	 *
+	 *  This table is eventually used by the kernel during normal
+	 *  runtime.  Care must be taken to clear out undesired bits
+	 *  later, like _PAGE_RW or _PAGE_GLOBAL in some cases.
 	 */
 	PMDS(0, __PAGE_KERNEL_LARGE_EXEC,
 		KERNEL_IMAGE_SIZE/PMD_SIZE)

arch/x86/kernel/ldt.c

@@ -145,6 +145,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 		unsigned long offset = i << PAGE_SHIFT;
 		const void *src = (char *)ldt->entries + offset;
 		unsigned long pfn;
+		pgprot_t pte_prot;
 		pte_t pte, *ptep;
 
 		va = (unsigned long)ldt_slot_va(slot) + offset;
@@ -163,7 +164,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 		 * target via some kernel interface which misses a
 		 * permission check.
 		 */
-		pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+		pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL);
+		/* Filter out unsuppored __PAGE_KERNEL* bits: */
+		pgprot_val(pte_prot) |= __supported_pte_mask;
+		pte = pfn_pte(pfn, pte_prot);
 		set_pte_at(mm, va, ptep, pte);
 		pte_unmap_unlock(ptep, ptl);
 	}

arch/x86/mm/cpu_entry_area.c

@@ -27,8 +27,20 @@ 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;
+	pte_t pte = pfn_pte(pa >> PAGE_SHIFT, flags);
 
-	set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags));
+	/*
+	 * The cpu_entry_area is shared between the user and kernel
+	 * page tables.  All of its ptes can safely be global.
+	 * _PAGE_GLOBAL gets reused to help indicate PROT_NONE for
+	 * non-present PTEs, so be careful not to set it in that
+	 * case to avoid confusion.
+	 */
+	if (boot_cpu_has(X86_FEATURE_PGE) &&
+	    (pgprot_val(flags) & _PAGE_PRESENT))
+		pte = pte_set_flags(pte, _PAGE_GLOBAL);
+
+	set_pte_vaddr(va, pte);
 }
 
 static void __init

arch/x86/mm/ident_map.c

@@ -98,6 +98,9 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 	if (!info->kernpg_flag)
 		info->kernpg_flag = _KERNPG_TABLE;
 
+	/* Filter out unsupported __PAGE_KERNEL_* bits: */
+	info->kernpg_flag &= __default_kernel_pte_mask;
+
 	for (; addr < end; addr = next) {
 		pgd_t *pgd = pgd_page + pgd_index(addr);
 		p4d_t *p4d;

arch/x86/mm/init.c

@@ -161,12 +161,6 @@ struct map_range {
 
 static int page_size_mask;
 
-static void enable_global_pages(void)
-{
-	if (!static_cpu_has(X86_FEATURE_PTI))
-		__supported_pte_mask |= _PAGE_GLOBAL;
-}
-
 static void __init probe_page_size_mask(void)
 {
 	/*
@@ -187,9 +181,15 @@ static void __init probe_page_size_mask(void)
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4_set_bits_and_update_boot(X86_CR4_PGE);
-		enable_global_pages();
+		__supported_pte_mask |= _PAGE_GLOBAL;
 	}
 
+	/* By the default is everything supported: */
+	__default_kernel_pte_mask = __supported_pte_mask;
+	/* Except when with PTI where the kernel is mostly non-Global: */
+	if (cpu_feature_enabled(X86_FEATURE_PTI))
+		__default_kernel_pte_mask &= ~_PAGE_GLOBAL;
+
 	/* Enable 1 GB linear kernel mappings if available: */
 	if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
 		printk(KERN_INFO "Using GB pages for direct mapping\n");

arch/x86/mm/init_32.c

@@ -558,8 +558,14 @@ static void __init pagetable_init(void)
 	permanent_kmaps_init(pgd_base);
 }
 
-pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL);
+#define DEFAULT_PTE_MASK ~(_PAGE_NX | _PAGE_GLOBAL)
+/* Bits supported by the hardware: */
+pteval_t __supported_pte_mask __read_mostly = DEFAULT_PTE_MASK;
+/* Bits allowed in normal kernel mappings: */
+pteval_t __default_kernel_pte_mask __read_mostly = DEFAULT_PTE_MASK;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
+/* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */
+EXPORT_SYMBOL(__default_kernel_pte_mask);
 
 /* user-defined highmem size */
 static unsigned int highmem_pages = -1;

arch/x86/mm/init_64.c

@@ -65,8 +65,13 @@
  * around without checking the pgd every time.
  */
 
+/* Bits supported by the hardware: */
 pteval_t __supported_pte_mask __read_mostly = ~0;
+/* Bits allowed in normal kernel mappings: */
+pteval_t __default_kernel_pte_mask __read_mostly = ~0;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
+/* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */
+EXPORT_SYMBOL(__default_kernel_pte_mask);
 
 int force_personality32;
 
@@ -1286,6 +1291,12 @@ void mark_rodata_ro(void)
 			(unsigned long) __va(__pa_symbol(_sdata)));
 
 	debug_checkwx();
+
+	/*
+	 * Do this after all of the manipulation of the
+	 * kernel text page tables are complete.
+	 */
+	pti_clone_kernel_text();
 }
 
 int kern_addr_valid(unsigned long addr)

arch/x86/mm/iomap_32.c

@@ -44,6 +44,9 @@ int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot)
 		return ret;
 
 	*prot = __pgprot(__PAGE_KERNEL | cachemode2protval(pcm));
+	/* Filter out unsupported __PAGE_KERNEL* bits: */
+	pgprot_val(*prot) &= __default_kernel_pte_mask;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iomap_create_wc);
@@ -88,6 +91,9 @@ iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 		prot = __pgprot(__PAGE_KERNEL |
 				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
 
+	/* Filter out unsupported __PAGE_KERNEL* bits: */
+	pgprot_val(prot) &= __default_kernel_pte_mask;
+
 	return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, prot);
 }
 EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);

arch/x86/mm/ioremap.c

@@ -816,6 +816,9 @@ void __init __early_set_fixmap(enum fixed_addresses idx,
 	}
 	pte = early_ioremap_pte(addr);
 
+	/* Sanitize 'prot' against any unsupported bits: */
+	pgprot_val(flags) &= __default_kernel_pte_mask;
+
 	if (pgprot_val(flags))
 		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
 	else

arch/x86/mm/kasan_init_64.c

@@ -269,6 +269,12 @@ void __init kasan_early_init(void)
 	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
 	p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE;
 
+	/* Mask out unsupported __PAGE_KERNEL bits: */
+	pte_val &= __default_kernel_pte_mask;
+	pmd_val &= __default_kernel_pte_mask;
+	pud_val &= __default_kernel_pte_mask;
+	p4d_val &= __default_kernel_pte_mask;
+
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		kasan_zero_pte[i] = __pte(pte_val);
 
@@ -371,7 +377,13 @@ void __init kasan_init(void)
 	 */
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 	for (i = 0; i < PTRS_PER_PTE; i++) {
-		pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO | _PAGE_ENC);
+		pte_t pte;
+		pgprot_t prot;
+
+		prot = __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC);
+		pgprot_val(prot) &= __default_kernel_pte_mask;
+
+		pte = __pte(__pa(kasan_zero_page) | pgprot_val(prot));
 		set_pte(&kasan_zero_pte[i], pte);
 	}
 	/* Flush TLBs again to be sure that write protection applied. */