Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The changes in here are:

   - text_poke() fixes and an extensive set of executability lockdowns,
     to (hopefully) eliminate the last residual circumstances under
     which we are using W|X mappings even temporarily on x86 kernels.
     This required a broad range of surgery in text patching facilities,
     module loading, trampoline handling and other bits.

   - tweak page fault messages to be more informative and more
     structured.

   - remove DISCONTIGMEM support on x86-32 and make SPARSEMEM the
     default.

   - reduce KASLR granularity on 5-level paging kernels from 512 GB to
     1 GB.

   - misc other changes and updates"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  x86/mm: Initialize PGD cache during mm initialization
  x86/alternatives: Add comment about module removal races
  x86/kprobes: Use vmalloc special flag
  x86/ftrace: Use vmalloc special flag
  bpf: Use vmalloc special flag
  modules: Use vmalloc special flag
  mm/vmalloc: Add flag for freeing of special permsissions
  mm/hibernation: Make hibernation handle unmapped pages
  x86/mm/cpa: Add set_direct_map_*() functions
  x86/alternatives: Remove the return value of text_poke_*()
  x86/jump-label: Remove support for custom text poker
  x86/modules: Avoid breaking W^X while loading modules
  x86/kprobes: Set instruction page as executable
  x86/ftrace: Set trampoline pages as executable
  x86/kgdb: Avoid redundant comparison of patched code
  x86/alternatives: Use temporary mm for text poking
  x86/alternatives: Initialize temporary mm for patching
  fork: Provide a function for copying init_mm
  uprobes: Initialize uprobes earlier
  x86/mm: Save debug registers when loading a temporary mm
  ...

Documentation/x86/x86_64/mm.txt

@@ -72,7 +72,7 @@ Complete virtual memory map with 5-level page tables
 Notes:
 
  - With 56-bit addresses, user-space memory gets expanded by a factor of 512x,
-   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PT starting
+   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PB starting
    offset and many of the regions expand to support the much larger physical
    memory supported.
 
@@ -83,7 +83,7 @@ Notes:
  0000000000000000 |    0       | 00ffffffffffffff |   64 PB | user-space virtual memory, different per mm
 __________________|____________|__________________|_________|___________________________________________________________
                   |            |                  |         |
- 0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
+ 0100000000000000 |  +64    PB | feffffffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
                   |            |                  |         |     virtual memory addresses up to the -64 PB
                   |            |                  |         |     starting offset of kernel mappings.
 __________________|____________|__________________|_________|___________________________________________________________
@@ -99,7 +99,7 @@ ____________________________________________________________|___________________
  ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
  ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
  ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
- ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
+ ffdf000000000000 |   -8.25 PB | fffffbffffffffff |   ~8 PB | KASAN shadow memory
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
                                                             | Identical layout to the 47-bit one from here on:

arch/Kconfig

@@ -249,6 +249,10 @@ config ARCH_HAS_FORTIFY_SOURCE
 config ARCH_HAS_SET_MEMORY
 	bool
 
+# Select if arch has all set_direct_map_invalid/default() functions
+config ARCH_HAS_SET_DIRECT_MAP
+	bool
+
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
        bool

arch/x86/Kconfig

@@ -65,6 +65,7 @@ config X86
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
@@ -1592,12 +1593,9 @@ config ARCH_FLATMEM_ENABLE
 	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
-	depends on NUMA && X86_32
-
-config ARCH_DISCONTIGMEM_DEFAULT
-	def_bool y
+	def_bool n
 	depends on NUMA && X86_32
+	depends on BROKEN
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
@@ -1606,8 +1604,7 @@ config ARCH_SPARSEMEM_ENABLE
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
 config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
+	def_bool X86_64 || (NUMA && X86_32)
 
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y

arch/x86/include/asm/fixmap.h

@@ -103,8 +103,6 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
 	FIX_PARAVIRT_BOOTMAP,
 #endif
-	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
-	FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif

arch/x86/include/asm/mmu_context.h

@@ -13,6 +13,7 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+#include <asm/debugreg.h>
 
 extern atomic64_t last_mm_ctx_id;
 
@@ -356,4 +357,59 @@ static inline unsigned long __get_current_cr3_fast(void)
 	return cr3;
 }
 
+typedef struct {
+	struct mm_struct *mm;
+} temp_mm_state_t;
+
+/*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down.
+ *
+ * Context: The temporary mm needs to be used exclusively by a single core. To
+ *          harden security IRQs must be disabled while the temporary mm is
+ *          loaded, thereby preventing interrupt handler bugs from overriding
+ *          the kernel memory protection.
+ */
+static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
+{
+	temp_mm_state_t temp_state;
+
+	lockdep_assert_irqs_disabled();
+	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	switch_mm_irqs_off(NULL, mm, current);
+
+	/*
+	 * If breakpoints are enabled, disable them while the temporary mm is
+	 * used. Userspace might set up watchpoints on addresses that are used
+	 * in the temporary mm, which would lead to wrong signals being sent or
+	 * crashes.
+	 *
+	 * Note that breakpoints are not disabled selectively, which also causes
+	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
+	 * undesirable, but still seems reasonable as the code that runs in the
+	 * temporary mm should be short.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_disable();
+
+	return temp_state;
+}
+
+static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
+{
+	lockdep_assert_irqs_disabled();
+	switch_mm_irqs_off(NULL, prev_state.mm, current);
+
+	/*
+	 * Restore the breakpoints if they were disabled before the temporary mm
+	 * was loaded.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */

arch/x86/include/asm/pgtable.h

@@ -1021,6 +1021,9 @@ static inline void __meminit init_trampoline_default(void)
 	/* Default trampoline pgd value */
 	trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 }
+
+void __init poking_init(void);
+
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
 # else

arch/x86/include/asm/set_memory.h

@@ -85,6 +85,9 @@ int set_pages_nx(struct page *page, int numpages);
 int set_pages_ro(struct page *page, int numpages);
 int set_pages_rw(struct page *page, int numpages);
 
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
 extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);

arch/x86/include/asm/text-patching.h

@@ -18,7 +18,7 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
@@ -35,8 +35,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
+extern __ro_after_init struct mm_struct *poking_mm;
+extern __ro_after_init unsigned long poking_addr;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */

arch/x86/include/asm/tlbflush.h

@@ -274,6 +274,8 @@ static inline bool nmi_uaccess_okay(void)
 	return true;
 }
 
+#define nmi_uaccess_okay nmi_uaccess_okay
+
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {

arch/x86/kernel/alternative.c

@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/mmu_context.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -264,7 +265,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-void *text_poke_early(void *addr, const void *opcode, size_t len);
+void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Are we looking at a near JMP with a 1 or 4-byte displacement.
@@ -666,16 +667,136 @@ void __init alternative_instructions(void)
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-void *__init_or_module text_poke_early(void *addr, const void *opcode,
-					      size_t len)
+void __init_or_module text_poke_early(void *addr, const void *opcode,
+				      size_t len)
 {
 	unsigned long flags;
+
+	if (boot_cpu_has(X86_FEATURE_NX) &&
+	    is_module_text_address((unsigned long)addr)) {
+		/*
+		 * Modules text is marked initially as non-executable, so the
+		 * code cannot be running and speculative code-fetches are
+		 * prevented. Just change the code.
+		 */
+		memcpy(addr, opcode, len);
+	} else {
+		local_irq_save(flags);
+		memcpy(addr, opcode, len);
+		local_irq_restore(flags);
+		sync_core();
+
+		/*
+		 * Could also do a CLFLUSH here to speed up CPU recovery; but
+		 * that causes hangs on some VIA CPUs.
+		 */
+	}
+}
+
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
+static void *__text_poke(void *addr, const void *opcode, size_t len)
+{
+	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
+	struct page *pages[2] = {NULL};
+	temp_mm_state_t prev;
+	unsigned long flags;
+	pte_t pte, *ptep;
+	spinlock_t *ptl;
+	pgprot_t pgprot;
+
+	/*
+	 * While boot memory allocator is running we cannot use struct pages as
+	 * they are not yet initialized. There is no way to recover.
+	 */
+	BUG_ON(!after_bootmem);
+
+	if (!core_kernel_text((unsigned long)addr)) {
+		pages[0] = vmalloc_to_page(addr);
+		if (cross_page_boundary)
+			pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
+	} else {
+		pages[0] = virt_to_page(addr);
+		WARN_ON(!PageReserved(pages[0]));
+		if (cross_page_boundary)
+			pages[1] = virt_to_page(addr + PAGE_SIZE);
+	}
+	/*
+	 * If something went wrong, crash and burn since recovery paths are not
+	 * implemented.
+	 */
+	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));
+
 	local_irq_save(flags);
-	memcpy(addr, opcode, len);
+
+	/*
+	 * Map the page without the global bit, as TLB flushing is done with
+	 * flush_tlb_mm_range(), which is intended for non-global PTEs.
+	 */
+	pgprot = __pgprot(pgprot_val(PAGE_KERNEL) & ~_PAGE_GLOBAL);
+
+	/*
+	 * The lock is not really needed, but this allows to avoid open-coding.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+
+	/*
+	 * This must not fail; preallocated in poking_init().
+	 */
+	VM_BUG_ON(!ptep);
+
+	pte = mk_pte(pages[0], pgprot);
+	set_pte_at(poking_mm, poking_addr, ptep, pte);
+
+	if (cross_page_boundary) {
+		pte = mk_pte(pages[1], pgprot);
+		set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
+	}
+
+	/*
+	 * Loading the temporary mm behaves as a compiler barrier, which
+	 * guarantees that the PTE will be set at the time memcpy() is done.
+	 */
+	prev = use_temporary_mm(poking_mm);
+
+	kasan_disable_current();
+	memcpy((u8 *)poking_addr + offset_in_page(addr), opcode, len);
+	kasan_enable_current();
+
+	/*
+	 * Ensure that the PTE is only cleared after the instructions of memcpy
+	 * were issued by using a compiler barrier.
+	 */
+	barrier();
+
+	pte_clear(poking_mm, poking_addr, ptep);
+	if (cross_page_boundary)
+		pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);
+
+	/*
+	 * Loading the previous page-table hierarchy requires a serializing
+	 * instruction that already allows the core to see the updated version.
+	 * Xen-PV is assumed to serialize execution in a similar manner.
+	 */
+	unuse_temporary_mm(prev);
+
+	/*
+	 * Flushing the TLB might involve IPIs, which would require enabled
+	 * IRQs, but not if the mm is not used, as it is in this point.
+	 */
+	flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
+			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
+			   PAGE_SHIFT, false);
+
+	/*
+	 * If the text does not match what we just wrote then something is
+	 * fundamentally screwy; there's nothing we can really do about that.
+	 */
+	BUG_ON(memcmp(addr, opcode, len));
+
+	pte_unmap_unlock(ptep, ptl);
 	local_irq_restore(flags);
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
 	return addr;
 }
 
@@ -689,48 +810,36 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note that the caller must ensure that if the modified code is part of a
+ * module, the module would not be removed during poking. This can be achieved
+ * by registering a module notifier, and ordering module removal and patching
+ * trough a mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {
-	unsigned long flags;
-	char *vaddr;
-	struct page *pages[2];
-	int i;
-
-	/*
-	 * While boot memory allocator is runnig we cannot use struct
-	 * pages as they are not yet initialized.
-	 */
-	BUG_ON(!after_bootmem);
-
 	lockdep_assert_held(&text_mutex);
 
-	if (!core_kernel_text((unsigned long)addr)) {
-		pages[0] = vmalloc_to_page(addr);
-		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
-	} else {
-		pages[0] = virt_to_page(addr);
-		WARN_ON(!PageReserved(pages[0]));
-		pages[1] = virt_to_page(addr + PAGE_SIZE);
-	}
-	BUG_ON(!pages[0]);
-	local_irq_save(flags);
-	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
-	if (pages[1])
-		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
-	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
-	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	clear_fixmap(FIX_TEXT_POKE0);
-	if (pages[1])
-		clear_fixmap(FIX_TEXT_POKE1);
-	local_flush_tlb();
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
-	for (i = 0; i < len; i++)
-		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
-	local_irq_restore(flags);
-	return addr;
+	return __text_poke(addr, opcode, len);
+}
+
+/**
+ * text_poke_kgdb - Update instructions on a live kernel by kgdb
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Only atomic text poke/set should be allowed when not doing early patching.
+ * It means the size must be writable atomically and the address must be aligned
+ * in a way that permits an atomic write. It also makes sure we fit on a single
+ * page.
+ *
+ * Context: should only be used by kgdb, which ensures no other core is running,
+ *	    despite the fact it does not hold the text_mutex.
+ */
+void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
+{
+	return __text_poke(addr, opcode, len);
 }
 
 static void do_sync_core(void *info)
@@ -788,7 +897,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  *	  replacing opcode
  *	- sync cores
  */
-void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
 	unsigned char int3 = 0xcc;
 
@@ -830,7 +939,5 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	 * the writing of the new instruction.
 	 */
 	bp_patching_in_progress = false;
-
-	return addr;
 }
 

arch/x86/kernel/ftrace.c

@@ -678,12 +678,8 @@ static inline void *alloc_tramp(unsigned long size)
 {
 	return module_alloc(size);
 }
-static inline void tramp_free(void *tramp, int size)
+static inline void tramp_free(void *tramp)
 {
-	int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	set_memory_nx((unsigned long)tramp, npages);
-	set_memory_rw((unsigned long)tramp, npages);
 	module_memfree(tramp);
 }
 #else
@@ -692,7 +688,7 @@ static inline void *alloc_tramp(unsigned long size)
 {
 	return NULL;
 }
-static inline void tramp_free(void *tramp, int size) { }
+static inline void tramp_free(void *tramp) { }
 #endif
 
 /* Defined as markers to the end of the ftrace default trampolines */
@@ -730,6 +726,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long offset;
+	unsigned long npages;
 	unsigned long size;
 	unsigned long retq;
 	unsigned long *ptr;
@@ -762,6 +759,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		return 0;
 
 	*tramp_size = size + RET_SIZE + sizeof(void *);
+	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
@@ -806,9 +804,17 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
+	set_vm_flush_reset_perms(trampoline);
+
+	/*
+	 * Module allocation needs to be completed by making the page
+	 * executable. The page is still writable, which is a security hazard,
+	 * but anyhow ftrace breaks W^X completely.
+	 */
+	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
 fail:
-	tramp_free(trampoline, *tramp_size);
+	tramp_free(trampoline);
 	return 0;
 }
 
@@ -939,7 +945,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 	if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
 		return;
 
-	tramp_free((void *)ops->trampoline, ops->trampoline_size);
+	tramp_free((void *)ops->trampoline);
 	ops->trampoline = 0;
 }
 

arch/x86/kernel/jump_label.c

@@ -37,7 +37,6 @@ static void bug_at(unsigned char *ip, int line)
 
 static void __ref __jump_label_transform(struct jump_entry *entry,
 					 enum jump_label_type type,
-					 void *(*poker)(void *, const void *, size_t),
 					 int init)
 {
 	union jump_code_union jmp;
@@ -50,9 +49,6 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 	jmp.offset = jump_entry_target(entry) -
 		     (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
 
-	if (early_boot_irqs_disabled)
-		poker = text_poke_early;
-
 	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			expect = default_nop; line = __LINE__;
@@ -75,16 +71,19 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 		bug_at((void *)jump_entry_code(entry), line);
 
 	/*
-	 * Make text_poke_bp() a default fallback poker.
+	 * As long as only a single processor is running and the code is still
+	 * not marked as RO, text_poke_early() can be used; Checking that
+	 * system_state is SYSTEM_BOOTING guarantees it. It will be set to
+	 * SYSTEM_SCHEDULING before other cores are awaken and before the
+	 * code is write-protected.
 	 *
 	 * At the time the change is being done, just ignore whether we
 	 * are doing nop -> jump or jump -> nop transition, and assume
 	 * always nop being the 'currently valid' instruction
-	 *
 	 */
-	if (poker) {
-		(*poker)((void *)jump_entry_code(entry), code,
-			 JUMP_LABEL_NOP_SIZE);
+	if (init || system_state == SYSTEM_BOOTING) {
+		text_poke_early((void *)jump_entry_code(entry), code,
+				JUMP_LABEL_NOP_SIZE);
 		return;
 	}
 
@@ -96,7 +95,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
 	mutex_lock(&text_mutex);
-	__jump_label_transform(entry, type, NULL, 0);
+	__jump_label_transform(entry, type, 0);
 	mutex_unlock(&text_mutex);
 }
 
@@ -126,5 +125,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 			jlstate = JL_STATE_NO_UPDATE;
 	}
 	if (jlstate == JL_STATE_UPDATE)
-		__jump_label_transform(entry, type, text_poke_early, 1);
+		__jump_label_transform(entry, type, 1);
 }

arch/x86/kernel/kgdb.c

@@ -747,7 +747,6 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
-	char opc[BREAK_INSTR_SIZE];
 
 	bpt->type = BP_BREAKPOINT;
 	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
@@ -759,18 +758,13 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	if (!err)
 		return err;
 	/*
-	 * It is safe to call text_poke() because normal kernel execution
+	 * It is safe to call text_poke_kgdb() because normal kernel execution
 	 * is stopped on all cores, so long as the text_mutex is not locked.
 	 */
 	if (mutex_is_locked(&text_mutex))
 		return -EBUSY;
-	text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
-		  BREAK_INSTR_SIZE);
-	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
-	if (err)
-		return err;
-	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
-		return -EINVAL;
+	text_poke_kgdb((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+		       BREAK_INSTR_SIZE);
 	bpt->type = BP_POKE_BREAKPOINT;
 
 	return err;
@@ -778,22 +772,17 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	int err;
-	char opc[BREAK_INSTR_SIZE];
-
 	if (bpt->type != BP_POKE_BREAKPOINT)
 		goto knl_write;
 	/*
-	 * It is safe to call text_poke() because normal kernel execution
+	 * It is safe to call text_poke_kgdb() because normal kernel execution
 	 * is stopped on all cores, so long as the text_mutex is not locked.
 	 */
 	if (mutex_is_locked(&text_mutex))
 		goto knl_write;
-	text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
-	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
-	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
-		goto knl_write;
-	return err;
+	text_poke_kgdb((void *)bpt->bpt_addr, bpt->saved_instr,
+		       BREAK_INSTR_SIZE);
+	return 0;
 
 knl_write:
 	return probe_kernel_write((char *)bpt->bpt_addr,

arch/x86/kernel/kprobes/core.c

@@ -431,8 +431,21 @@ void *alloc_insn_page(void)
 	void *page;
 
 	page = module_alloc(PAGE_SIZE);
-	if (page)
-		set_memory_ro((unsigned long)page & PAGE_MASK, 1);
+	if (!page)
+		return NULL;
+
+	set_vm_flush_reset_perms(page);
+	/*
+	 * First make the page read-only, and only then make it executable to
+	 * prevent it from being W+X in between.
+	 */
+	set_memory_ro((unsigned long)page, 1);
+
+	/*
+	 * TODO: Once additional kernel code protection mechanisms are set, ensure
+	 * that the page was not maliciously altered and it is still zeroed.
+	 */
+	set_memory_x((unsigned long)page, 1);
 
 	return page;
 }
@@ -440,8 +453,6 @@ void *alloc_insn_page(void)
 /* Recover page to RW mode before releasing it */
 void free_insn_page(void *page)
 {
-	set_memory_nx((unsigned long)page & PAGE_MASK, 1);
-	set_memory_rw((unsigned long)page & PAGE_MASK, 1);
 	module_memfree(page);
 }
 

arch/x86/kernel/module.c

@@ -87,7 +87,7 @@ void *module_alloc(unsigned long size)
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
 				    MODULES_VADDR + get_module_load_offset(),
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 	if (p && (kasan_module_alloc(p, size) < 0)) {
 		vfree(p);

arch/x86/kernel/vmlinux.lds.S

@@ -141,11 +141,11 @@ SECTIONS
 		*(.text.__x86.indirect_thunk)
 		__indirect_thunk_end = .;
 #endif
-
-		/* End of text section */
-		_etext = .;
 	} :text = 0x9090
 
+	/* End of text section */
+	_etext = .;
+
 	NOTES :text :note
 
 	EXCEPTION_TABLE(16) :text = 0x9090

arch/x86/mm/fault.c

@@ -360,8 +360,6 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Copy kernel mappings over when needed. This can also
 	 * happen within a race in page table update. In the later
@@ -604,24 +602,9 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		 name, index, addr, (desc.limit0 | (desc.limit1 << 16)));
 }
 
-/*
- * This helper function transforms the #PF error_code bits into
- * "[PROT] [USER]" type of descriptive, almost human-readable error strings:
- */
-static void err_str_append(unsigned long error_code, char *buf, unsigned long mask, const char *txt)
-{
-	if (error_code & mask) {
-		if (buf[0])
-			strcat(buf, " ");
-		strcat(buf, txt);
-	}
-}
-
 static void
 show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
-	char err_txt[64];
-
 	if (!oops_may_print())
 		return;
 
@@ -645,31 +628,29 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 				from_kuid(&init_user_ns, current_uid()));
 	}
 
-	pr_alert("BUG: unable to handle kernel %s at %px\n",
-		 address < PAGE_SIZE ? "NULL pointer dereference" : "paging request",
-		 (void *)address);
-
-	err_txt[0] = 0;
-
-	/*
-	 * Note: length of these appended strings including the separation space and the
-	 * zero delimiter must fit into err_txt[].
-	 */
-	err_str_append(error_code, err_txt, X86_PF_PROT,  "[PROT]" );
-	err_str_append(error_code, err_txt, X86_PF_WRITE, "[WRITE]");
-	err_str_append(error_code, err_txt, X86_PF_USER,  "[USER]" );
-	err_str_append(error_code, err_txt, X86_PF_RSVD,  "[RSVD]" );
-	err_str_append(error_code, err_txt, X86_PF_INSTR, "[INSTR]");
-	err_str_append(error_code, err_txt, X86_PF_PK,    "[PK]"   );
-
-	pr_alert("#PF error: %s\n", error_code ? err_txt : "[normal kernel read fault]");
+	if (address < PAGE_SIZE && !user_mode(regs))
+		pr_alert("BUG: kernel NULL pointer dereference, address: %px\n",
+			(void *)address);
+	else
+		pr_alert("BUG: unable to handle page fault for address: %px\n",
+			(void *)address);
+
+	pr_alert("#PF: %s %s in %s mode\n",
+		 (error_code & X86_PF_USER)  ? "user" : "supervisor",
+		 (error_code & X86_PF_INSTR) ? "instruction fetch" :
+		 (error_code & X86_PF_WRITE) ? "write access" :
+					       "read access",
+			     user_mode(regs) ? "user" : "kernel");
+	pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code,
+		 !(error_code & X86_PF_PROT) ? "not-present page" :
+		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
+		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
 		struct desc_ptr idt, gdt;
 		u16 ldtr, tr;
 
-		pr_alert("This was a system access from user code\n");
-
 		/*
 		 * This can happen for quite a few reasons.  The more obvious
 		 * ones are faults accessing the GDT, or LDT.  Perhaps

arch/x86/mm/init.c

@@ -6,6 +6,7 @@
 #include <linux/swapfile.h>
 #include <linux/swapops.h>
 #include <linux/kmemleak.h>
+#include <linux/sched/task.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -23,6 +24,7 @@
 #include <asm/hypervisor.h>
 #include <asm/cpufeature.h>
 #include <asm/pti.h>
+#include <asm/text-patching.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -701,6 +703,41 @@ void __init init_mem_mapping(void)
 	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
 }
 
+/*
+ * Initialize an mm_struct to be used during poking and a pointer to be used
+ * during patching.
+ */
+void __init poking_init(void)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	poking_mm = copy_init_mm();
+	BUG_ON(!poking_mm);
+
+	/*
+	 * Randomize the poking address, but make sure that the following page
+	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
+	 * and adjust the address if the PMD ends after the first one.
+	 */
+	poking_addr = TASK_UNMAPPED_BASE;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+			(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
+
+	if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		poking_addr += PAGE_SIZE;
+
+	/*
+	 * We need to trigger the allocation of the page-tables that will be
+	 * needed for poking now. Later, poking may be performed in an atomic
+	 * section, which might cause allocation to fail.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	BUG_ON(!ptep);
+	pte_unmap_unlock(ptep, ptl);
+}
+
 /*
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.

arch/x86/mm/kaslr.c

@@ -125,10 +125,7 @@ void __init kernel_randomize_memory(void)
 		 */
 		entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
 		prandom_bytes_state(&rand_state, &rand, sizeof(rand));
-		if (pgtable_l5_enabled())
-			entropy = (rand % (entropy + 1)) & P4D_MASK;
-		else
-			entropy = (rand % (entropy + 1)) & PUD_MASK;
+		entropy = (rand % (entropy + 1)) & PUD_MASK;
 		vaddr += entropy;
 		*kaslr_regions[i].base = vaddr;
 
@@ -137,84 +134,71 @@ void __init kernel_randomize_memory(void)
 		 * randomization alignment.
 		 */
 		vaddr += get_padding(&kaslr_regions[i]);
-		if (pgtable_l5_enabled())
-			vaddr = round_up(vaddr + 1, P4D_SIZE);
-		else
-			vaddr = round_up(vaddr + 1, PUD_SIZE);
+		vaddr = round_up(vaddr + 1, PUD_SIZE);
 		remain_entropy -= entropy;
 	}
 }
 
 static void __meminit init_trampoline_pud(void)
 {
-	unsigned long paddr, paddr_next;
+	pud_t *pud_page_tramp, *pud, *pud_tramp;
+	p4d_t *p4d_page_tramp, *p4d, *p4d_tramp;
+	unsigned long paddr, vaddr;
 	pgd_t *pgd;
-	pud_t *pud_page, *pud_page_tramp;
-	int i;
 
 	pud_page_tramp = alloc_low_page();
 
+	/*
+	 * There are two mappings for the low 1MB area, the direct mapping
+	 * and the 1:1 mapping for the real mode trampoline:
+	 *
+	 * Direct mapping: virt_addr = phys_addr + PAGE_OFFSET
+	 * 1:1 mapping:    virt_addr = phys_addr
+	 */
 	paddr = 0;
-	pgd = pgd_offset_k((unsigned long)__va(paddr));
-	pud_page = (pud_t *) pgd_page_vaddr(*pgd);
-
-	for (i = pud_index(paddr); i < PTRS_PER_PUD; i++, paddr = paddr_next) {
-		pud_t *pud, *pud_tramp;
-		unsigned long vaddr = (unsigned long)__va(paddr);
+	vaddr = (unsigned long)__va(paddr);
+	pgd = pgd_offset_k(vaddr);
 
-		pud_tramp = pud_page_tramp + pud_index(paddr);
-		pud = pud_page + pud_index(vaddr);
-		paddr_next = (paddr & PUD_MASK) + PUD_SIZE;
-
-		*pud_tramp = *pud;
-	}
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 
-	set_pgd(&trampoline_pgd_entry,
-		__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
-}
-
-static void __meminit init_trampoline_p4d(void)
-{
-	unsigned long paddr, paddr_next;
-	pgd_t *pgd;
-	p4d_t *p4d_page, *p4d_page_tramp;
-	int i;
+	pud_tramp = pud_page_tramp + pud_index(paddr);
+	*pud_tramp = *pud;
 
-	p4d_page_tramp = alloc_low_page();
-
-	paddr = 0;
-	pgd = pgd_offset_k((unsigned long)__va(paddr));
-	p4d_page = (p4d_t *) pgd_page_vaddr(*pgd);
-
-	for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) {
-		p4d_t *p4d, *p4d_tramp;
-		unsigned long vaddr = (unsigned long)__va(paddr);
+	if (pgtable_l5_enabled()) {
+		p4d_page_tramp = alloc_low_page();
 
 		p4d_tramp = p4d_page_tramp + p4d_index(paddr);
-		p4d = p4d_page + p4d_index(vaddr);
-		paddr_next = (paddr & P4D_MASK) + P4D_SIZE;
 
-		*p4d_tramp = *p4d;
-	}
+		set_p4d(p4d_tramp,
+			__p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
 
-	set_pgd(&trampoline_pgd_entry,
-		__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+		set_pgd(&trampoline_pgd_entry,
+			__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+	} else {
+		set_pgd(&trampoline_pgd_entry,
+			__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
+	}
 }
 
 /*
- * Create PGD aligned trampoline table to allow real mode initialization
- * of additional CPUs. Consume only 1 low memory page.
+ * The real mode trampoline, which is required for bootstrapping CPUs
+ * occupies only a small area under the low 1MB.  See reserve_real_mode()
+ * for details.
+ *
+ * If KASLR is disabled the first PGD entry of the direct mapping is copied
+ * to map the real mode trampoline.
+ *
+ * If KASLR is enabled, copy only the PUD which covers the low 1MB
+ * area. This limits the randomization granularity to 1GB for both 4-level
+ * and 5-level paging.
  */
 void __meminit init_trampoline(void)
 {
-
 	if (!kaslr_memory_enabled()) {
 		init_trampoline_default();
 		return;
 	}
 
-	if (pgtable_l5_enabled())
-		init_trampoline_p4d();
-	else
-		init_trampoline_pud();
+	init_trampoline_pud();
 }

arch/x86/mm/pageattr.c

@@ -2209,8 +2209,6 @@ int set_pages_rw(struct page *page, int numpages)
 	return set_memory_rw(addr, numpages);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-
 static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
@@ -2249,6 +2247,16 @@ static int __set_pages_np(struct page *page, int numpages)
 	return __change_page_attr_set_clr(&cpa, 0);
 }
 
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_pages_np(page, 1);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_pages_p(page, 1);
+}
+
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
@@ -2282,7 +2290,6 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 }
 
 #ifdef CONFIG_HIBERNATION
-
 bool kernel_page_present(struct page *page)
 {
 	unsigned int level;
@@ -2294,11 +2301,8 @@ bool kernel_page_present(struct page *page)
 	pte = lookup_address((unsigned long)page_address(page), &level);
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
-
 #endif /* CONFIG_HIBERNATION */
 
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)
 {

arch/x86/mm/pgtable.c

@@ -373,14 +373,14 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 
 static struct kmem_cache *pgd_cache;
 
-static int __init pgd_cache_init(void)
+void __init pgd_cache_init(void)
 {
 	/*
 	 * When PAE kernel is running as a Xen domain, it does not use
 	 * shared kernel pmd. And this requires a whole page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return 0;
+		return;
 
 	/*
 	 * when PAE kernel is not running as a Xen domain, it uses
@@ -390,9 +390,7 @@ static int __init pgd_cache_init(void)
 	 */
 	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
 				      SLAB_PANIC, NULL);
-	return 0;
 }
-core_initcall(pgd_cache_init);
 
 static inline pgd_t *_pgd_alloc(void)
 {
@@ -420,6 +418,10 @@ static inline void _pgd_free(pgd_t *pgd)
 }
 #else
 
+void __init pgd_cache_init(void)
+{
+}
+
 static inline pgd_t *_pgd_alloc(void)
 {
 	return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);

arch/x86/mm/tlb.c

@@ -634,7 +634,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);
 }
 
-static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason)
+static void flush_tlb_func_local(const void *info, enum tlb_flush_reason reason)
 {
 	const struct flush_tlb_info *f = info;
 
@@ -722,43 +722,81 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
  */
 unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info);
+
+#ifdef CONFIG_DEBUG_VM
+static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
+#endif
+
+static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			unsigned int stride_shift, bool freed_tables,
+			u64 new_tlb_gen)
+{
+	struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);
+
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * Ensure that the following code is non-reentrant and flush_tlb_info
+	 * is not overwritten. This means no TLB flushing is initiated by
+	 * interrupt handlers and machine-check exception handlers.
+	 */
+	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
+#endif
+
+	info->start		= start;
+	info->end		= end;
+	info->mm		= mm;
+	info->stride_shift	= stride_shift;
+	info->freed_tables	= freed_tables;
+	info->new_tlb_gen	= new_tlb_gen;
+
+	return info;
+}
+
+static inline void put_flush_tlb_info(void)
+{
+#ifdef CONFIG_DEBUG_VM
+	/* Complete reentrency prevention checks */
+	barrier();
+	this_cpu_dec(flush_tlb_info_idx);
+#endif
+}
+
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned int stride_shift,
 				bool freed_tables)
 {
+	struct flush_tlb_info *info;
+	u64 new_tlb_gen;
 	int cpu;
 
-	struct flush_tlb_info info = {
-		.mm = mm,
-		.stride_shift = stride_shift,
-		.freed_tables = freed_tables,
-	};
-
 	cpu = get_cpu();
 
-	/* This is also a barrier that synchronizes with switch_mm(). */
-	info.new_tlb_gen = inc_mm_tlb_gen(mm);
-
 	/* Should we flush just the requested range? */
-	if ((end != TLB_FLUSH_ALL) &&
-	    ((end - start) >> stride_shift) <= tlb_single_page_flush_ceiling) {
-		info.start = start;
-		info.end = end;
-	} else {
-		info.start = 0UL;
-		info.end = TLB_FLUSH_ALL;
+	if ((end == TLB_FLUSH_ALL) ||
+	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
 	}
 
+	/* This is also a barrier that synchronizes with switch_mm(). */
+	new_tlb_gen = inc_mm_tlb_gen(mm);
+
+	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
+				  new_tlb_gen);
+
 	if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
-		VM_WARN_ON(irqs_disabled());
+		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN);
+		flush_tlb_func_local(info, TLB_LOCAL_MM_SHOOTDOWN);
 		local_irq_enable();
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), &info);
+		flush_tlb_others(mm_cpumask(mm), info);
 
+	put_flush_tlb_info();
 	put_cpu();
 }
 
@@ -787,38 +825,48 @@ static void do_kernel_range_flush(void *info)
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-
 	/* Balance as user space task's flush, a bit conservative */
 	if (end == TLB_FLUSH_ALL ||
 	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
 	} else {
-		struct flush_tlb_info info;
-		info.start = start;
-		info.end = end;
-		on_each_cpu(do_kernel_range_flush, &info, 1);
+		struct flush_tlb_info *info;
+
+		preempt_disable();
+		info = get_flush_tlb_info(NULL, start, end, 0, false, 0);
+
+		on_each_cpu(do_kernel_range_flush, info, 1);
+
+		put_flush_tlb_info();
+		preempt_enable();
 	}
 }
 
+/*
+ * arch_tlbbatch_flush() performs a full TLB flush regardless of the active mm.
+ * This means that the 'struct flush_tlb_info' that describes which mappings to
+ * flush is actually fixed. We therefore set a single fixed struct and use it in
+ * arch_tlbbatch_flush().
+ */
+static const struct flush_tlb_info full_flush_tlb_info = {
+	.mm = NULL,
+	.start = 0,
+	.end = TLB_FLUSH_ALL,
+};
+
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	struct flush_tlb_info info = {
-		.mm = NULL,
-		.start = 0UL,
-		.end = TLB_FLUSH_ALL,
-	};
-
 	int cpu = get_cpu();
 
 	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
-		VM_WARN_ON(irqs_disabled());
+		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN);
+		flush_tlb_func_local(&full_flush_tlb_info, TLB_LOCAL_SHOOTDOWN);
 		local_irq_enable();
 	}
 
 	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&batch->cpumask, &info);
+		flush_tlb_others(&batch->cpumask, &full_flush_tlb_info);
 
 	cpumask_clear(&batch->cpumask);
 

arch/x86/xen/mmu_pv.c

@@ -2318,8 +2318,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #elif defined(CONFIG_X86_VSYSCALL_EMULATION)
 	case VSYSCALL_PAGE:
 #endif
-	case FIX_TEXT_POKE0:
-	case FIX_TEXT_POKE1:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;

include/asm-generic/pgtable.h

@@ -1126,6 +1126,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
+extern void __init pgd_cache_init(void);
+
 #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
 static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
 {

include/asm-generic/tlb.h

@@ -21,6 +21,15 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or switching
+ * the loaded mm.
+ */
+#ifndef nmi_uaccess_okay
+# define nmi_uaccess_okay() true
+#endif
+
 #ifdef CONFIG_MMU
 
 /*

include/linux/filter.h

@@ -20,6 +20,7 @@
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
 #include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
 
 #include <net/sch_generic.h>
 
@@ -503,7 +504,6 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
@@ -733,24 +733,15 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	fp->undo_set_mem = 1;
+	set_vm_flush_reset_perms(fp);
 	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
-	if (fp->undo_set_mem)
-		set_memory_rw((unsigned long)fp, fp->pages);
-}
-
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
+	set_vm_flush_reset_perms(hdr);
 	set_memory_ro((unsigned long)hdr, hdr->pages);
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
-	set_memory_rw((unsigned long)hdr, hdr->pages);
+	set_memory_x((unsigned long)hdr, hdr->pages);
 }
 
 static inline struct bpf_binary_header *
@@ -788,7 +779,6 @@ void __bpf_prog_free(struct bpf_prog *fp);
 
 static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
 {
-	bpf_prog_unlock_ro(fp);
 	__bpf_prog_free(fp);
 }
 

include/linux/mm.h

@@ -2610,37 +2610,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 extern bool _debug_pagealloc_enabled;
-extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
 static inline bool debug_pagealloc_enabled(void)
 {
-	return _debug_pagealloc_enabled;
+	return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled;
 }
 
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
+extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable)
 {
-	if (!debug_pagealloc_enabled())
-		return;
-
 	__kernel_map_pages(page, numpages, enable);
 }
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
-#else	/* CONFIG_DEBUG_PAGEALLOC */
+#else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
 #endif	/* CONFIG_HIBERNATION */
-static inline bool debug_pagealloc_enabled(void)
-{
-	return false;
-}
-#endif	/* CONFIG_DEBUG_PAGEALLOC */
+#endif	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);

include/linux/sched/task.h

@@ -76,6 +76,7 @@ extern void exit_itimers(struct signal_struct *);
 extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
+struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 

include/linux/set_memory.h

@@ -17,6 +17,17 @@ static inline int set_memory_x(unsigned long addr,  int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
+#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP
+static inline int set_direct_map_invalid_noflush(struct page *page)
+{
+	return 0;
+}
+static inline int set_direct_map_default_noflush(struct page *page)
+{
+	return 0;
+}
+#endif
+
 #ifndef set_mce_nospec
 static inline int set_mce_nospec(unsigned long pfn)
 {

include/linux/uprobes.h

@@ -115,6 +115,7 @@ struct uprobes_state {
 	struct xol_area		*xol_area;
 };
 
+extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool is_swbp_insn(uprobe_opcode_t *insn);
@@ -154,6 +155,10 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 struct uprobes_state {
 };
 
+static inline void uprobes_init(void)
+{
+}
+
 #define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
 
 static inline int

include/linux/vmalloc.h

@@ -21,6 +21,11 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+/*
+ * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
+ * vfree_atomic().
+ */
+#define VM_FLUSH_RESET_PERMS	0x00000100      /* Reset direct map and flush TLB on unmap */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
@@ -142,6 +147,13 @@ extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
 				    pgprot_t prot, struct page **pages);
 extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
 extern void unmap_kernel_range(unsigned long addr, unsigned long size);
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+	struct vm_struct *vm = find_vm_area(addr);
+
+	if (vm)
+		vm->flags |= VM_FLUSH_RESET_PERMS;
+}
 #else
 static inline int
 map_kernel_range_noflush(unsigned long start, unsigned long size,
@@ -157,6 +169,9 @@ static inline void
 unmap_kernel_range(unsigned long addr, unsigned long size)
 {
 }
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+}
 #endif
 
 /* Allocate/destroy a 'vmalloc' VM area. */

init/main.c

@@ -504,6 +504,10 @@ void __init __weak thread_stack_cache_init(void)
 
 void __init __weak mem_encrypt_init(void) { }
 
+void __init __weak poking_init(void) { }
+
+void __init __weak pgd_cache_init(void) { }
+
 bool initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
@@ -535,6 +539,7 @@ static void __init mm_init(void)
 	init_espfix_bsp();
 	/* Should be run after espfix64 is set up. */
 	pti_init();
+	pgd_cache_init();
 }
 
 void __init __weak arch_call_rest_init(void)
@@ -737,6 +742,7 @@ asmlinkage __visible void __init start_kernel(void)
 	taskstats_init_early();
 	delayacct_init();
 
+	poking_init();
 	check_bugs();
 
 	acpi_subsystem_init();

kernel/bpf/core.c

@@ -848,7 +848,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	if (fp->jited) {
 		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
 
-		bpf_jit_binary_unlock_ro(hdr);
 		bpf_jit_binary_free(hdr);
 
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));

kernel/events/uprobes.c

@@ -2294,16 +2294,14 @@ static struct notifier_block uprobe_exception_nb = {
 	.priority		= INT_MAX-1,	/* notified after kprobes, kgdb */
 };
 
-static int __init init_uprobes(void)
+void __init uprobes_init(void)
 {
 	int i;
 
 	for (i = 0; i < UPROBES_HASH_SZ; i++)
 		mutex_init(&uprobes_mmap_mutex[i]);
 
-	if (percpu_init_rwsem(&dup_mmap_sem))
-		return -ENOMEM;
+	BUG_ON(percpu_init_rwsem(&dup_mmap_sem));
 
-	return register_die_notifier(&uprobe_exception_nb);
+	BUG_ON(register_die_notifier(&uprobe_exception_nb));
 }
-__initcall(init_uprobes);

kernel/fork.c

@@ -815,6 +815,7 @@ void __init fork_init(void)
 #endif
 
 	lockdep_init_task(&init_task);
+	uprobes_init();
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -1298,13 +1299,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 		complete_vfork_done(tsk);
 }
 
-/*
- * Allocate a new mm structure and copy contents from the
- * mm structure of the passed in task structure.
+/**
+ * dup_mm() - duplicates an existing mm structure
+ * @tsk: the task_struct with which the new mm will be associated.
+ * @oldmm: the mm to duplicate.
+ *
+ * Allocates a new mm structure and duplicates the provided @oldmm structure
+ * content into it.
+ *
+ * Return: the duplicated mm or NULL on failure.
  */
-static struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk,
+				struct mm_struct *oldmm)
 {
-	struct mm_struct *mm, *oldmm = current->mm;
+	struct mm_struct *mm;
 	int err;
 
 	mm = allocate_mm();
@@ -1371,7 +1379,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	}
 
 	retval = -ENOMEM;
-	mm = dup_mm(tsk);
+	mm = dup_mm(tsk, current->mm);
 	if (!mm)
 		goto fail_nomem;
 
@@ -2186,6 +2194,11 @@ struct task_struct *fork_idle(int cpu)
 	return task;
 }
 
+struct mm_struct *copy_init_mm(void)
+{
+	return dup_mm(NULL, &init_mm);
+}
+
 /*
  *  Ok, this is the main fork-routine.
  *

kernel/module.c

@@ -98,6 +98,10 @@ DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
+/* Work queue for freeing init sections in success case */
+static struct work_struct init_free_wq;
+static struct llist_head init_free_list;
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*
@@ -1949,9 +1953,16 @@ void module_enable_ro(const struct module *mod, bool after_init)
 	if (!rodata_enabled)
 		return;
 
+	set_vm_flush_reset_perms(mod->core_layout.base);
+	set_vm_flush_reset_perms(mod->init_layout.base);
 	frob_text(&mod->core_layout, set_memory_ro);
+	frob_text(&mod->core_layout, set_memory_x);
+
 	frob_rodata(&mod->core_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
+	frob_text(&mod->init_layout, set_memory_x);
+
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)
@@ -1967,15 +1978,6 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
-static void module_disable_nx(const struct module *mod)
-{
-	frob_rodata(&mod->core_layout, set_memory_x);
-	frob_ro_after_init(&mod->core_layout, set_memory_x);
-	frob_writable_data(&mod->core_layout, set_memory_x);
-	frob_rodata(&mod->init_layout, set_memory_x);
-	frob_writable_data(&mod->init_layout, set_memory_x);
-}
-
 /* Iterate through all modules and set each module's text as RW */
 void set_all_modules_text_rw(void)
 {
@@ -2019,23 +2021,8 @@ void set_all_modules_text_ro(void)
 	}
 	mutex_unlock(&module_mutex);
 }
-
-static void disable_ro_nx(const struct module_layout *layout)
-{
-	if (rodata_enabled) {
-		frob_text(layout, set_memory_rw);
-		frob_rodata(layout, set_memory_rw);
-		frob_ro_after_init(layout, set_memory_rw);
-	}
-	frob_rodata(layout, set_memory_x);
-	frob_ro_after_init(layout, set_memory_x);
-	frob_writable_data(layout, set_memory_x);
-}
-
 #else
-static void disable_ro_nx(const struct module_layout *layout) { }
 static void module_enable_nx(const struct module *mod) { }
-static void module_disable_nx(const struct module *mod) { }
 #endif
 
 #ifdef CONFIG_LIVEPATCH
@@ -2115,6 +2102,11 @@ static void free_module_elf(struct module *mod)
 
 void __weak module_memfree(void *module_region)
 {
+	/*
+	 * This memory may be RO, and freeing RO memory in an interrupt is not
+	 * supported by vmalloc.
+	 */
+	WARN_ON(in_interrupt());
 	vfree(module_region);
 }
 
@@ -2166,7 +2158,6 @@ static void free_module(struct module *mod)
 	mutex_unlock(&module_mutex);
 
 	/* This may be empty, but that's OK */
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	kfree(mod->args);
@@ -2176,7 +2167,6 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
 
 	/* Finally, free the core (containing the module structure) */
-	disable_ro_nx(&mod->core_layout);
 	module_memfree(mod->core_layout.base);
 }
 
@@ -3415,17 +3405,34 @@ static void do_mod_ctors(struct module *mod)
 
 /* For freeing module_init on success, in case kallsyms traversing */
 struct mod_initfree {
-	struct rcu_head rcu;
+	struct llist_node node;
 	void *module_init;
 };
 
-static void do_free_init(struct rcu_head *head)
+static void do_free_init(struct work_struct *w)
 {
-	struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
-	module_memfree(m->module_init);
-	kfree(m);
+	struct llist_node *pos, *n, *list;
+	struct mod_initfree *initfree;
+
+	list = llist_del_all(&init_free_list);
+
+	synchronize_rcu();
+
+	llist_for_each_safe(pos, n, list) {
+		initfree = container_of(pos, struct mod_initfree, node);
+		module_memfree(initfree->module_init);
+		kfree(initfree);
+	}
 }
 
+static int __init modules_wq_init(void)
+{
+	INIT_WORK(&init_free_wq, do_free_init);
+	init_llist_head(&init_free_list);
+	return 0;
+}
+module_init(modules_wq_init);
+
 /*
  * This is where the real work happens.
  *
@@ -3502,7 +3509,6 @@ static noinline int do_init_module(struct module *mod)
 #endif
 	module_enable_ro(mod, true);
 	mod_tree_remove_init(mod);
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	mod->init_layout.base = NULL;
 	mod->init_layout.size = 0;
@@ -3513,14 +3519,18 @@ static noinline int do_init_module(struct module *mod)
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_rcu(), but we don't want to slow down the success
-	 * path, so use actual RCU here.
+	 * path. module_memfree() cannot be called in an interrupt, so do the
+	 * work and call synchronize_rcu() in a work queue.
+	 *
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work - ie
 	 * rcu_barrier()
 	 */
-	call_rcu(&freeinit->rcu, do_free_init);
+	if (llist_add(&freeinit->node, &init_free_list))
+		schedule_work(&init_free_wq);
+
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
@@ -3817,10 +3827,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* we can't deallocate the module until we clear memory protection */
-	module_disable_ro(mod);
-	module_disable_nx(mod);
-
  ddebug_cleanup:
 	ftrace_release_mod(mod);
 	dynamic_debug_remove(mod, info->debug);

kernel/power/snapshot.c

@@ -1342,8 +1342,9 @@ static inline void do_copy_page(long *dst, long *src)
  * safe_copy_page - Copy a page in a safe way.
  *
  * Check if the page we are going to copy is marked as present in the kernel
- * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set
- * and in that case kernel_page_present() always returns 'true').
+ * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or
+ * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present()
+ * always returns 'true'.
  */
 static void safe_copy_page(void *dst, struct page *s_page)
 {

kernel/trace/bpf_trace.c

@@ -14,6 +14,8 @@
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
 
+#include <asm/tlb.h>
+
 #include "trace_probe.h"
 #include "trace.h"
 
@@ -163,6 +165,10 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	 * access_ok() should prevent writing to non-user memory, but in
 	 * some situations (nommu, temporary switch, etc) access_ok() does
 	 * not provide enough validation, hence the check on KERNEL_DS.
+	 *
+	 * nmi_uaccess_okay() ensures the probe is not run in an interim
+	 * state, when the task or mm are switched. This is specifically
+	 * required to prevent the use of temporary mm.
 	 */
 
 	if (unlikely(in_interrupt() ||
@@ -170,6 +176,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 		return -EPERM;
 	if (unlikely(uaccess_kernel()))
 		return -EPERM;
+	if (unlikely(!nmi_uaccess_okay()))
+		return -EPERM;
 	if (!access_ok(unsafe_ptr, size))
 		return -EPERM;
 

mm/page_alloc.c

@@ -1144,7 +1144,9 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	arch_free_page(page, order);
 	kernel_poison_pages(page, 1 << order, 0);
-	kernel_map_pages(page, 1 << order, 0);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 0);
+
 	kasan_free_nondeferred_pages(page, order);
 
 	return true;
@@ -2014,7 +2016,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
-	kernel_map_pages(page, 1 << order, 1);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 1);
 	kasan_alloc_pages(page, order);
 	kernel_poison_pages(page, 1 << order, 1);
 	set_page_owner(page, order, gfp_flags);

mm/vmalloc.c

@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/set_memory.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/list.h>
@@ -1059,24 +1060,9 @@ static void vb_free(const void *addr, unsigned long size)
 		spin_unlock(&vb->lock);
 }
 
-/**
- * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
- *
- * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
- * to amortize TLB flushing overheads. What this means is that any page you
- * have now, may, in a former life, have been mapped into kernel virtual
- * address by the vmap layer and so there might be some CPUs with TLB entries
- * still referencing that page (additional to the regular 1:1 kernel mapping).
- *
- * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
- * be sure that none of the pages we have control over will have any aliases
- * from the vmap layer.
- */
-void vm_unmap_aliases(void)
+static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
 {
-	unsigned long start = ULONG_MAX, end = 0;
 	int cpu;
-	int flush = 0;
 
 	if (unlikely(!vmap_initialized))
 		return;
@@ -1113,6 +1099,27 @@ void vm_unmap_aliases(void)
 		flush_tlb_kernel_range(start, end);
 	mutex_unlock(&vmap_purge_lock);
 }
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush = 0;
+
+	_vm_unmap_aliases(start, end, flush);
+}
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
 /**
@@ -1505,6 +1512,72 @@ struct vm_struct *remove_vm_area(const void *addr)
 	return NULL;
 }
 
+static inline void set_area_direct_map(const struct vm_struct *area,
+				       int (*set_direct_map)(struct page *page))
+{
+	int i;
+
+	for (i = 0; i < area->nr_pages; i++)
+		if (page_address(area->pages[i]))
+			set_direct_map(area->pages[i]);
+}
+
+/* Handle removing and resetting vm mappings related to the vm_struct. */
+static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
+{
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+	int i;
+
+	/*
+	 * The below block can be removed when all architectures that have
+	 * direct map permissions also have set_direct_map_() implementations.
+	 * This is concerned with resetting the direct map any an vm alias with
+	 * execute permissions, without leaving a RW+X window.
+	 */
+	if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		set_memory_nx(addr, area->nr_pages);
+		set_memory_rw(addr, area->nr_pages);
+	}
+
+	remove_vm_area(area->addr);
+
+	/* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
+	if (!flush_reset)
+		return;
+
+	/*
+	 * If not deallocating pages, just do the flush of the VM area and
+	 * return.
+	 */
+	if (!deallocate_pages) {
+		vm_unmap_aliases();
+		return;
+	}
+
+	/*
+	 * If execution gets here, flush the vm mapping and reset the direct
+	 * map. Find the start and end range of the direct mappings to make sure
+	 * the vm_unmap_aliases() flush includes the direct map.
+	 */
+	for (i = 0; i < area->nr_pages; i++) {
+		if (page_address(area->pages[i])) {
+			start = min(addr, start);
+			end = max(addr, end);
+		}
+	}
+
+	/*
+	 * Set direct map to something invalid so that it won't be cached if
+	 * there are any accesses after the TLB flush, then flush the TLB and
+	 * reset the direct map permissions to the default.
+	 */
+	set_area_direct_map(area, set_direct_map_invalid_noflush);
+	_vm_unmap_aliases(start, end, 1);
+	set_area_direct_map(area, set_direct_map_default_noflush);
+}
+
 static void __vunmap(const void *addr, int deallocate_pages)
 {
 	struct vm_struct *area;
@@ -1526,7 +1599,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
 	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
 
-	remove_vm_area(addr);
+	vm_remove_mappings(area, deallocate_pages);
+
 	if (deallocate_pages) {
 		int i;
 
@@ -1961,8 +2035,9 @@ EXPORT_SYMBOL(vzalloc_node);
  */
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
-			      NUMA_NO_NODE, __builtin_return_address(0));
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)