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
  ...

7 files changed, 204 insertions, 92 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9a79c7808f9c..7b9b49dfc05a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/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;
 }
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index ef49517f6bb2..0caf8122d680 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/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;
 }
 
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index f99bd26bd3f1..e631c358f7f4 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/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);
 }
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 4ff6b4cdb941..13b13311b792 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/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,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 122548ad5c2e..cf52ee0d8711 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/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);
 }
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b052e883dd8c..cfa3106faee4 100644
--- a/arch/x86/kernel/module.c
+++ b/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);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4d1517022a14..0850b5149345 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/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