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
  ...

6 files changed, 192 insertions, 136 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 06c089513d39..46df4c6aae46 100644
--- a/arch/x86/mm/fault.c
+++ b/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
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 8dacdb96899e..fd10d91a6115 100644
--- a/arch/x86/mm/init.c
+++ b/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
@@ -702,6 +704,41 @@ void __init init_mem_mapping(void)
 }
 
 /*
+ * 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.
  *
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index d669c5e797e0..dc3f058bdf9b 100644
--- a/arch/x86/mm/kaslr.c
+++ b/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();
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 4c570612e24e..daf4d645e537 100644
--- a/arch/x86/mm/pageattr.c
+++ b/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)
 {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3dbf440d4114..1f67b1e15bf6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/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);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 487b8474c01c..7f61431c75fb 100644
--- a/arch/x86/mm/tlb.c
+++ b/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);