23 files changed, 380 insertions, 374 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 84373dc9b341..3b89c201ac26 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -13,7 +13,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
+	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
@@ -23,7 +23,7 @@ CFLAGS_mem_encrypt_identity.o	:= $(nostackp)
 
 CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
 
-obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
+obj-$(CONFIG_X86_PAT)		+= pat_interval.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 752ad11d6868..56f9189bbadb 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -17,6 +17,10 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
 DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
 #endif
 
+#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
+DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack);
+#endif
+
 struct cpu_entry_area *get_cpu_entry_area(int cpu)
 {
 	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
@@ -108,7 +112,15 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)
 	cea_map_stack(MCE);
 }
 #else
-static inline void percpu_setup_exception_stacks(unsigned int cpu) {}
+static inline void percpu_setup_exception_stacks(unsigned int cpu)
+{
+#ifdef CONFIG_DOUBLEFAULT
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+
+	cea_map_percpu_pages(&cea->doublefault_stack,
+			     &per_cpu(doublefault_stack, cpu), 1, PAGE_KERNEL);
+#endif
+}
 #endif
 
 /* Setup the fixmap mappings only once per-processor */
@@ -161,6 +173,14 @@ static void __init setup_cpu_entry_area(unsigned int cpu)
 	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
 		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
 	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	/*
+	 * VMX changes the host TR limit to 0x67 after a VM exit. This is
+	 * okay, since 0x67 covers the size of struct x86_hw_tss. Make sure
+	 * that this is correct.
+	 */
+	BUILD_BUG_ON(offsetof(struct tss_struct, x86_tss) != 0);
+	BUILD_BUG_ON(sizeof(struct x86_hw_tss) != 0x68);
+
 	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
 			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
 
@@ -178,7 +198,9 @@ static __init void setup_cpu_entry_area_ptes(void)
 #ifdef CONFIG_X86_32
 	unsigned long start, end;
 
-	BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+	/* The +1 is for the readonly IDT: */
+	BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
+	BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
 	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
 
 	start = CPU_ENTRY_AREA_BASE;
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 4d75bc656f97..30bb0bd3b1b8 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -45,55 +45,6 @@ __visible bool ex_handler_fault(const struct exception_table_entry *fixup,
 EXPORT_SYMBOL_GPL(ex_handler_fault);
 
 /*
- * Handler for UD0 exception following a failed test against the
- * result of a refcount inc/dec/add/sub.
- */
-__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
-				   struct pt_regs *regs, int trapnr,
-				   unsigned long error_code,
-				   unsigned long fault_addr)
-{
-	/* First unconditionally saturate the refcount. */
-	*(int *)regs->cx = INT_MIN / 2;
-
-	/*
-	 * Strictly speaking, this reports the fixup destination, not
-	 * the fault location, and not the actually overflowing
-	 * instruction, which is the instruction before the "js", but
-	 * since that instruction could be a variety of lengths, just
-	 * report the location after the overflow, which should be close
-	 * enough for finding the overflow, as it's at least back in
-	 * the function, having returned from .text.unlikely.
-	 */
-	regs->ip = ex_fixup_addr(fixup);
-
-	/*
-	 * This function has been called because either a negative refcount
-	 * value was seen by any of the refcount functions, or a zero
-	 * refcount value was seen by refcount_dec().
-	 *
-	 * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result
-	 * wrapped around) will be set. Additionally, seeing the refcount
-	 * reach 0 will set ZF (Zero Flag: result was zero). In each of
-	 * these cases we want a report, since it's a boundary condition.
-	 * The SF case is not reported since it indicates post-boundary
-	 * manipulations below zero or above INT_MAX. And if none of the
-	 * flags are set, something has gone very wrong, so report it.
-	 */
-	if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
-		bool zero = regs->flags & X86_EFLAGS_ZF;
-
-		refcount_error_report(regs, zero ? "hit zero" : "overflow");
-	} else if ((regs->flags & X86_EFLAGS_SF) == 0) {
-		/* Report if none of OF, ZF, nor SF are set. */
-		refcount_error_report(regs, "unexpected saturation");
-	}
-
-	return true;
-}
-EXPORT_SYMBOL(ex_handler_refcount);
-
-/*
  * Handler for when we fail to restore a task's FPU state.  We should never get
  * here because the FPU state of a task using the FPU (task->thread.fpu.state)
  * should always be valid.  However, past bugs have allowed userspace to set
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ceacd1156db..304d31d8cbbc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -197,7 +197,7 @@ void vmalloc_sync_all(void)
 		return;
 
 	for (address = VMALLOC_START & PMD_MASK;
-	     address >= TASK_SIZE_MAX && address < FIXADDR_TOP;
+	     address >= TASK_SIZE_MAX && address < VMALLOC_END;
 	     address += PMD_SIZE) {
 		struct page *page;
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fd10d91a6115..e7bb483557c9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -829,14 +829,13 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
  * used for the kernel image only.  free_init_pages() will do the
  * right thing for either kind of address.
  */
-void free_kernel_image_pages(void *begin, void *end)
+void free_kernel_image_pages(const char *what, void *begin, void *end)
 {
 	unsigned long begin_ul = (unsigned long)begin;
 	unsigned long end_ul = (unsigned long)end;
 	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
 
-
-	free_init_pages("unused kernel image", begin_ul, end_ul);
+	free_init_pages(what, begin_ul, end_ul);
 
 	/*
 	 * PTI maps some of the kernel into userspace.  For performance,
@@ -865,7 +864,8 @@ void __ref free_initmem(void)
 
 	mem_encrypt_free_decrypted_mem();
 
-	free_kernel_image_pages(&__init_begin, &__init_end);
+	free_kernel_image_pages("unused kernel image (initmem)",
+				&__init_begin, &__init_end);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a6b5c653727b..dcb9bc961b39 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1263,7 +1263,7 @@ int kernel_set_to_readonly;
 void set_kernel_text_rw(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = PFN_ALIGN(__stop___ex_table);
+	unsigned long end = PFN_ALIGN(_etext);
 
 	if (!kernel_set_to_readonly)
 		return;
@@ -1282,7 +1282,7 @@ void set_kernel_text_rw(void)
 void set_kernel_text_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = PFN_ALIGN(__stop___ex_table);
+	unsigned long end = PFN_ALIGN(_etext);
 
 	if (!kernel_set_to_readonly)
 		return;
@@ -1300,9 +1300,9 @@ void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
-	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
-	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
-	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
+	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long text_end = PFN_ALIGN(_etext);
+	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
 	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
@@ -1334,8 +1334,10 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_kernel_image_pages((void *)text_end, (void *)rodata_start);
-	free_kernel_image_pages((void *)rodata_end, (void *)_sdata);
+	free_kernel_image_pages("unused kernel image (text/rodata gap)",
+				(void *)text_end, (void *)rodata_start);
+	free_kernel_image_pages("unused kernel image (rodata/data gap)",
+				(void *)rodata_end, (void *)_sdata);
 
 	debug_checkwx();
 }
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index a39dcdb5ae34..b3a2936377b5 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -280,11 +280,11 @@ err_free_memtype:
 }
 
 /**
- * ioremap_nocache     -   map bus memory into CPU space
+ * ioremap     -   map bus memory into CPU space
  * @phys_addr:    bus address of the memory
  * @size:      size of the resource to map
  *
- * ioremap_nocache performs a platform specific sequence of operations to
+ * ioremap performs a platform specific sequence of operations to
  * make bus memory CPU accessible via the readb/readw/readl/writeb/
  * writew/writel functions and the other mmio helpers. The returned
  * address is not guaranteed to be usable directly as a virtual
@@ -300,7 +300,7 @@ err_free_memtype:
  *
  * Must be freed with iounmap.
  */
-void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
+void __iomem *ioremap(resource_size_t phys_addr, unsigned long size)
 {
 	/*
 	 * Ideally, this should be:
@@ -315,7 +315,7 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 	return __ioremap_caller(phys_addr, size, pcm,
 				__builtin_return_address(0), false);
 }
-EXPORT_SYMBOL(ioremap_nocache);
+EXPORT_SYMBOL(ioremap);
 
 /**
  * ioremap_uc     -   map bus memory into CPU space as strongly uncachable
@@ -626,6 +626,17 @@ static bool memremap_is_setup_data(resource_size_t phys_addr,
 		paddr_next = data->next;
 		len = data->len;
 
+		if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+			memunmap(data);
+			return true;
+		}
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			paddr = ((struct setup_indirect *)data->data)->addr;
+			len = ((struct setup_indirect *)data->data)->len;
+		}
+
 		memunmap(data);
 
 		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 296da58f3013..cf5bc37c90ac 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -245,6 +245,49 @@ static void __init kasan_map_early_shadow(pgd_t *pgd)
 	} while (pgd++, addr = next, addr != end);
 }
 
+static void __init kasan_shallow_populate_p4ds(pgd_t *pgd,
+					       unsigned long addr,
+					       unsigned long end)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	void *p;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (p4d_none(*p4d)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+			p4d_populate(&init_mm, p4d, p);
+		}
+	} while (p4d++, addr = next, addr != end);
+}
+
+static void __init kasan_shallow_populate_pgds(void *start, void *end)
+{
+	unsigned long addr, next;
+	pgd_t *pgd;
+	void *p;
+
+	addr = (unsigned long)start;
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, (unsigned long)end);
+
+		if (pgd_none(*pgd)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+			pgd_populate(&init_mm, pgd, p);
+		}
+
+		/*
+		 * we need to populate p4ds to be synced when running in
+		 * four level mode - see sync_global_pgds_l4()
+		 */
+		kasan_shallow_populate_p4ds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != (unsigned long)end);
+}
+
 #ifdef CONFIG_KASAN_INLINE
 static int kasan_die_handler(struct notifier_block *self,
 			     unsigned long val,
@@ -354,6 +397,24 @@ void __init kasan_init(void)
 
 	kasan_populate_early_shadow(
 		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
+		kasan_mem_to_shadow((void *)VMALLOC_START));
+
+	/*
+	 * If we're in full vmalloc mode, don't back vmalloc space with early
+	 * shadow pages. Instead, prepopulate pgds/p4ds so they are synced to
+	 * the global table and we can populate the lower levels on demand.
+	 */
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		kasan_shallow_populate_pgds(
+			kasan_mem_to_shadow((void *)VMALLOC_START),
+			kasan_mem_to_shadow((void *)VMALLOC_END));
+	else
+		kasan_populate_early_shadow(
+			kasan_mem_to_shadow((void *)VMALLOC_START),
+			kasan_mem_to_shadow((void *)VMALLOC_END));
+
+	kasan_populate_early_shadow(
+		kasan_mem_to_shadow((void *)VMALLOC_END + 1),
 		shadow_cpu_entry_begin);
 
 	kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 79eb55ce69a9..49d7814b59a9 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -193,8 +193,8 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	int ret;
 	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
-			   f->addr, f->count, !!f->old_presence);
+		pr_warn("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			f->addr, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
 	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
@@ -341,8 +341,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 		 * something external causing them (f.e. using a debugger while
 		 * mmio tracing enabled), or erroneous behaviour
 		 */
-		pr_warning("unexpected debug trap on CPU %d.\n",
-			   smp_processor_id());
+		pr_warn("unexpected debug trap on CPU %d.\n", smp_processor_id());
 		goto out;
 	}
 
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
new file mode 100644
index 000000000000..f5b85bdc0535
--- /dev/null
+++ b/arch/x86/mm/maccess.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+
+#ifdef CONFIG_X86_64
+static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
+{
+	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
+}
+
+static __always_inline bool invalid_probe_range(u64 vaddr)
+{
+	/*
+	 * Range covering the highest possible canonical userspace address
+	 * as well as non-canonical address range. For the canonical range
+	 * we also need to include the userspace guard page.
+	 */
+	return vaddr < TASK_SIZE_MAX + PAGE_SIZE ||
+	       canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr;
+}
+#else
+static __always_inline bool invalid_probe_range(u64 vaddr)
+{
+	return vaddr < TASK_SIZE_MAX;
+}
+#endif
+
+long probe_kernel_read_strict(void *dst, const void *src, size_t size)
+{
+	if (unlikely(invalid_probe_range((unsigned long)src)))
+		return -EFAULT;
+
+	return __probe_kernel_read(dst, src, size);
+}
+
+long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count)
+{
+	if (unlikely(invalid_probe_range((unsigned long)unsafe_addr)))
+		return -EFAULT;
+
+	return __strncpy_from_unsafe(dst, unsafe_addr, count);
+}
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9268c12458c8..a03614bd3e1a 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -367,7 +367,7 @@ bool force_dma_unencrypted(struct device *dev)
 	if (sme_active()) {
 		u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask));
 		u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask,
-						dev->bus_dma_mask);
+						dev->bus_dma_limit);
 
 		if (dma_dev_mask <= dma_enc_mask)
 			return true;
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 6d71481a1e70..106ead05bbe3 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -16,7 +16,7 @@
 
 	.text
 	.code64
-ENTRY(sme_encrypt_execute)
+SYM_FUNC_START(sme_encrypt_execute)
 
 	/*
 	 * Entry parameters:
@@ -66,9 +66,9 @@ ENTRY(sme_encrypt_execute)
 	pop	%rbp
 
 	ret
-ENDPROC(sme_encrypt_execute)
+SYM_FUNC_END(sme_encrypt_execute)
 
-ENTRY(__enc_copy)
+SYM_FUNC_START(__enc_copy)
 /*
  * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
@@ -153,4 +153,4 @@ ENTRY(__enc_copy)
 
 	ret
 .L__enc_copy_end:
-ENDPROC(__enc_copy)
+SYM_FUNC_END(__enc_copy)
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index b8ef8557d4b3..673de6063345 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -394,7 +394,7 @@ static void enter_uniprocessor(void)
 	}
 out:
 	if (num_online_cpus() > 1)
-		pr_warning("multiple CPUs still online, may miss events.\n");
+		pr_warn("multiple CPUs still online, may miss events.\n");
 }
 
 static void leave_uniprocessor(void)
@@ -418,8 +418,8 @@ static void leave_uniprocessor(void)
 static void enter_uniprocessor(void)
 {
 	if (num_online_cpus() > 1)
-		pr_warning("multiple CPUs are online, may miss events. "
-			   "Suggest booting with maxcpus=1 kernel argument.\n");
+		pr_warn("multiple CPUs are online, may miss events. "
+			"Suggest booting with maxcpus=1 kernel argument.\n");
 }
 
 static void leave_uniprocessor(void)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 4123100e0eaf..99f7a68738f0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -699,7 +699,7 @@ static int __init dummy_numa_init(void)
  * x86_numa_init - Initialize NUMA
  *
  * Try each configured NUMA initialization method until one succeeds.  The
- * last fallback is dummy single node config encomapssing whole memory and
+ * last fallback is dummy single node config encompassing whole memory and
  * never fails.
  */
 void __init x86_numa_init(void)
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index abffa0be80da..7f1d2034df1e 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -438,7 +438,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		goto no_emu;
 
 	if (numa_cleanup_meminfo(&ei) < 0) {
-		pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
+		pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
 		goto no_emu;
 	}
 
@@ -449,7 +449,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 					      phys_size, PAGE_SIZE);
 		if (!phys) {
-			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
+			pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
 			goto no_emu;
 		}
 		memblock_reserve(phys, phys_size);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 0d09cc5aad61..1b99ad05b117 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1784,7 +1784,7 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*
-	 * for now UC MINUS. see comments in ioremap_nocache()
+	 * for now UC MINUS. see comments in ioremap()
 	 * If you really need strong UC use ioremap_uc(), but note
 	 * that you cannot override IO areas with set_memory_*() as
 	 * these helpers cannot work with IO memory.
@@ -1799,7 +1799,7 @@ int set_memory_uc(unsigned long addr, int numpages)
 	int ret;
 
 	/*
-	 * for now UC MINUS. see comments in ioremap_nocache()
+	 * for now UC MINUS. see comments in ioremap()
 	 */
 	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 			      _PAGE_CACHE_MODE_UC_MINUS, NULL);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index d9fbd4f69920..2d758e19ef22 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -603,7 +603,7 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
 
 	spin_lock(&memtype_lock);
 
-	err = rbt_memtype_check_insert(new, new_type);
+	err = memtype_check_insert(new, new_type);
 	if (err) {
 		pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
 			start, end - 1,
@@ -650,7 +650,7 @@ int free_memtype(u64 start, u64 end)
 	}
 
 	spin_lock(&memtype_lock);
-	entry = rbt_memtype_erase(start, end);
+	entry = memtype_erase(start, end);
 	spin_unlock(&memtype_lock);
 
 	if (IS_ERR(entry)) {
@@ -693,7 +693,7 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
 
 	spin_lock(&memtype_lock);
 
-	entry = rbt_memtype_lookup(paddr);
+	entry = memtype_lookup(paddr);
 	if (entry != NULL)
 		rettype = entry->type;
 	else
@@ -1109,7 +1109,7 @@ static struct memtype *memtype_get_idx(loff_t pos)
 		return NULL;
 
 	spin_lock(&memtype_lock);
-	ret = rbt_memtype_copy_nth_element(print_entry, pos);
+	ret = memtype_copy_nth_element(print_entry, pos);
 	spin_unlock(&memtype_lock);
 
 	if (!ret) {
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index eeb5caeb089b..79a06684349e 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -29,20 +29,20 @@ static inline char *cattr_name(enum page_cache_mode pcm)
 }
 
 #ifdef CONFIG_X86_PAT
-extern int rbt_memtype_check_insert(struct memtype *new,
-					enum page_cache_mode *new_type);
-extern struct memtype *rbt_memtype_erase(u64 start, u64 end);
-extern struct memtype *rbt_memtype_lookup(u64 addr);
-extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
+extern int memtype_check_insert(struct memtype *new,
+				enum page_cache_mode *new_type);
+extern struct memtype *memtype_erase(u64 start, u64 end);
+extern struct memtype *memtype_lookup(u64 addr);
+extern int memtype_copy_nth_element(struct memtype *out, loff_t pos);
 #else
-static inline int rbt_memtype_check_insert(struct memtype *new,
-					enum page_cache_mode *new_type)
+static inline int memtype_check_insert(struct memtype *new,
+				       enum page_cache_mode *new_type)
 { return 0; }
-static inline struct memtype *rbt_memtype_erase(u64 start, u64 end)
+static inline struct memtype *memtype_erase(u64 start, u64 end)
 { return NULL; }
-static inline struct memtype *rbt_memtype_lookup(u64 addr)
+static inline struct memtype *memtype_lookup(u64 addr)
 { return NULL; }
-static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
+static inline int memtype_copy_nth_element(struct memtype *out, loff_t pos)
 { return 0; }
 #endif
 
diff --git a/arch/x86/mm/pat_interval.c b/arch/x86/mm/pat_interval.c
new file mode 100644
index 000000000000..6855362eaf21
--- /dev/null
+++ b/arch/x86/mm/pat_interval.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Handle caching attributes in page tables (PAT)
+ *
+ * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *          Suresh B Siddha <suresh.b.siddha@intel.com>
+ *
+ * Interval tree used to store the PAT memory type reservations.
+ */
+
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/interval_tree_generic.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+
+#include <asm/pgtable.h>
+#include <asm/pat.h>
+
+#include "pat_internal.h"
+
+/*
+ * The memtype tree keeps track of memory type for specific
+ * physical memory areas. Without proper tracking, conflicting memory
+ * types in different mappings can cause CPU cache corruption.
+ *
+ * The tree is an interval tree (augmented rbtree) with tree ordered
+ * on starting address. Tree can contain multiple entries for
+ * different regions which overlap. All the aliases have the same
+ * cache attributes of course.
+ *
+ * memtype_lock protects the rbtree.
+ */
+static inline u64 memtype_interval_start(struct memtype *memtype)
+{
+	return memtype->start;
+}
+
+static inline u64 memtype_interval_end(struct memtype *memtype)
+{
+	return memtype->end - 1;
+}
+INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end,
+		     memtype_interval_start, memtype_interval_end,
+		     static, memtype_interval)
+
+static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED;
+
+enum {
+	MEMTYPE_EXACT_MATCH	= 0,
+	MEMTYPE_END_MATCH	= 1
+};
+
+static struct memtype *memtype_match(u64 start, u64 end, int match_type)
+{
+	struct memtype *match;
+
+	match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
+	while (match != NULL && match->start < end) {
+		if ((match_type == MEMTYPE_EXACT_MATCH) &&
+		    (match->start == start) && (match->end == end))
+			return match;
+
+		if ((match_type == MEMTYPE_END_MATCH) &&
+		    (match->start < start) && (match->end == end))
+			return match;
+
+		match = memtype_interval_iter_next(match, start, end-1);
+	}
+
+	return NULL; /* Returns NULL if there is no match */
+}
+
+static int memtype_check_conflict(u64 start, u64 end,
+				  enum page_cache_mode reqtype,
+				  enum page_cache_mode *newtype)
+{
+	struct memtype *match;
+	enum page_cache_mode found_type = reqtype;
+
+	match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
+	if (match == NULL)
+		goto success;
+
+	if (match->type != found_type && newtype == NULL)
+		goto failure;
+
+	dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
+	found_type = match->type;
+
+	match = memtype_interval_iter_next(match, start, end-1);
+	while (match) {
+		if (match->type != found_type)
+			goto failure;
+
+		match = memtype_interval_iter_next(match, start, end-1);
+	}
+success:
+	if (newtype)
+		*newtype = found_type;
+
+	return 0;
+
+failure:
+	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+		current->comm, current->pid, start, end,
+		cattr_name(found_type), cattr_name(match->type));
+	return -EBUSY;
+}
+
+int memtype_check_insert(struct memtype *new,
+			 enum page_cache_mode *ret_type)
+{
+	int err = 0;
+
+	err = memtype_check_conflict(new->start, new->end, new->type, ret_type);
+	if (err)
+		return err;
+
+	if (ret_type)
+		new->type = *ret_type;
+
+	memtype_interval_insert(new, &memtype_rbroot);
+	return 0;
+}
+
+struct memtype *memtype_erase(u64 start, u64 end)
+{
+	struct memtype *data;
+
+	/*
+	 * Since the memtype_rbroot tree allows overlapping ranges,
+	 * memtype_erase() checks with EXACT_MATCH first, i.e. free
+	 * a whole node for the munmap case.  If no such entry is found,
+	 * it then checks with END_MATCH, i.e. shrink the size of a node
+	 * from the end for the mremap case.
+	 */
+	data = memtype_match(start, end, MEMTYPE_EXACT_MATCH);
+	if (!data) {
+		data = memtype_match(start, end, MEMTYPE_END_MATCH);
+		if (!data)
+			return ERR_PTR(-EINVAL);
+	}
+
+	if (data->start == start) {
+		/* munmap: erase this node */
+		memtype_interval_remove(data, &memtype_rbroot);
+	} else {
+		/* mremap: update the end value of this node */
+		memtype_interval_remove(data, &memtype_rbroot);
+		data->end = start;
+		memtype_interval_insert(data, &memtype_rbroot);
+		return NULL;
+	}
+
+	return data;
+}
+
+struct memtype *memtype_lookup(u64 addr)
+{
+	return memtype_interval_iter_first(&memtype_rbroot, addr,
+					   addr + PAGE_SIZE-1);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+int memtype_copy_nth_element(struct memtype *out, loff_t pos)
+{
+	struct memtype *match;
+	int i = 1;
+
+	match = memtype_interval_iter_first(&memtype_rbroot, 0, ULONG_MAX);
+	while (match && pos != i) {
+		match = memtype_interval_iter_next(match, 0, ULONG_MAX);
+		i++;
+	}
+
+	if (match) { /* pos == i */
+		*out = *match;
+		return 0;
+	} else {
+		return 1;
+	}
+}
+#endif
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
deleted file mode 100644
index 65ebe4b88f7c..000000000000
--- a/arch/x86/mm/pat_rbtree.c
+++ /dev/null
@@ -1,268 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Handle caching attributes in page tables (PAT)
- *
- * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
- *          Suresh B Siddha <suresh.b.siddha@intel.com>
- *
- * Interval tree (augmented rbtree) used to store the PAT memory type
- * reservations.
- */
-
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/kernel.h>
-#include <linux/rbtree_augmented.h>
-#include <linux/sched.h>
-#include <linux/gfp.h>
-
-#include <asm/pgtable.h>
-#include <asm/pat.h>
-
-#include "pat_internal.h"
-
-/*
- * The memtype tree keeps track of memory type for specific
- * physical memory areas. Without proper tracking, conflicting memory
- * types in different mappings can cause CPU cache corruption.
- *
- * The tree is an interval tree (augmented rbtree) with tree ordered
- * on starting address. Tree can contain multiple entries for
- * different regions which overlap. All the aliases have the same
- * cache attributes of course.
- *
- * memtype_lock protects the rbtree.
- */
-
-static struct rb_root memtype_rbroot = RB_ROOT;
-
-static int is_node_overlap(struct memtype *node, u64 start, u64 end)
-{
-	if (node->start >= end || node->end <= start)
-		return 0;
-
-	return 1;
-}
-
-static u64 get_subtree_max_end(struct rb_node *node)
-{
-	u64 ret = 0;
-	if (node) {
-		struct memtype *data = rb_entry(node, struct memtype, rb);
-		ret = data->subtree_max_end;
-	}
-	return ret;
-}
-
-#define NODE_END(node) ((node)->end)
-
-RB_DECLARE_CALLBACKS_MAX(static, memtype_rb_augment_cb,
-			 struct memtype, rb, u64, subtree_max_end, NODE_END)
-
-/* Find the first (lowest start addr) overlapping range from rb tree */
-static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
-				u64 start, u64 end)
-{
-	struct rb_node *node = root->rb_node;
-	struct memtype *last_lower = NULL;
-
-	while (node) {
-		struct memtype *data = rb_entry(node, struct memtype, rb);
-
-		if (get_subtree_max_end(node->rb_left) > start) {
-			/* Lowest overlap if any must be on left side */
-			node = node->rb_left;
-		} else if (is_node_overlap(data, start, end)) {
-			last_lower = data;
-			break;
-		} else if (start >= data->start) {
-			/* Lowest overlap if any must be on right side */
-			node = node->rb_right;
-		} else {
-			break;
-		}
-	}
-	return last_lower; /* Returns NULL if there is no overlap */
-}
-
-enum {
-	MEMTYPE_EXACT_MATCH	= 0,
-	MEMTYPE_END_MATCH	= 1
-};
-
-static struct memtype *memtype_rb_match(struct rb_root *root,
-				u64 start, u64 end, int match_type)
-{
-	struct memtype *match;
-
-	match = memtype_rb_lowest_match(root, start, end);
-	while (match != NULL && match->start < end) {
-		struct rb_node *node;
-
-		if ((match_type == MEMTYPE_EXACT_MATCH) &&
-		    (match->start == start) && (match->end == end))
-			return match;
-
-		if ((match_type == MEMTYPE_END_MATCH) &&
-		    (match->start < start) && (match->end == end))
-			return match;
-
-		node = rb_next(&match->rb);
-		if (node)
-			match = rb_entry(node, struct memtype, rb);
-		else
-			match = NULL;
-	}
-
-	return NULL; /* Returns NULL if there is no match */
-}
-
-static int memtype_rb_check_conflict(struct rb_root *root,
-				u64 start, u64 end,
-				enum page_cache_mode reqtype,
-				enum page_cache_mode *newtype)
-{
-	struct rb_node *node;
-	struct memtype *match;
-	enum page_cache_mode found_type = reqtype;
-
-	match = memtype_rb_lowest_match(&memtype_rbroot, start, end);
-	if (match == NULL)
-		goto success;
-
-	if (match->type != found_type && newtype == NULL)
-		goto failure;
-
-	dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
-	found_type = match->type;
-
-	node = rb_next(&match->rb);
-	while (node) {
-		match = rb_entry(node, struct memtype, rb);
-
-		if (match->start >= end) /* Checked all possible matches */
-			goto success;
-
-		if (is_node_overlap(match, start, end) &&
-		    match->type != found_type) {
-			goto failure;
-		}
-
-		node = rb_next(&match->rb);
-	}
-success:
-	if (newtype)
-		*newtype = found_type;
-
-	return 0;
-
-failure:
-	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
-		current->comm, current->pid, start, end,
-		cattr_name(found_type), cattr_name(match->type));
-	return -EBUSY;
-}
-
-static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
-{
-	struct rb_node **node = &(root->rb_node);
-	struct rb_node *parent = NULL;
-
-	while (*node) {
-		struct memtype *data = rb_entry(*node, struct memtype, rb);
-
-		parent = *node;
-		if (data->subtree_max_end < newdata->end)
-			data->subtree_max_end = newdata->end;
-		if (newdata->start <= data->start)
-			node = &((*node)->rb_left);
-		else if (newdata->start > data->start)
-			node = &((*node)->rb_right);
-	}
-
-	newdata->subtree_max_end = newdata->end;
-	rb_link_node(&newdata->rb, parent, node);
-	rb_insert_augmented(&newdata->rb, root, &memtype_rb_augment_cb);
-}
-
-int rbt_memtype_check_insert(struct memtype *new,
-			     enum page_cache_mode *ret_type)
-{
-	int err = 0;
-
-	err = memtype_rb_check_conflict(&memtype_rbroot, new->start, new->end,
-						new->type, ret_type);
-
-	if (!err) {
-		if (ret_type)
-			new->type = *ret_type;
-
-		new->subtree_max_end = new->end;
-		memtype_rb_insert(&memtype_rbroot, new);
-	}
-	return err;
-}
-
-struct memtype *rbt_memtype_erase(u64 start, u64 end)
-{
-	struct memtype *data;
-
-	/*
-	 * Since the memtype_rbroot tree allows overlapping ranges,
-	 * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free
-	 * a whole node for the munmap case.  If no such entry is found,
-	 * it then checks with END_MATCH, i.e. shrink the size of a node
-	 * from the end for the mremap case.
-	 */
-	data = memtype_rb_match(&memtype_rbroot, start, end,
-				MEMTYPE_EXACT_MATCH);
-	if (!data) {
-		data = memtype_rb_match(&memtype_rbroot, start, end,
-					MEMTYPE_END_MATCH);
-		if (!data)
-			return ERR_PTR(-EINVAL);
-	}
-
-	if (data->start == start) {
-		/* munmap: erase this node */
-		rb_erase_augmented(&data->rb, &memtype_rbroot,
-					&memtype_rb_augment_cb);
-	} else {
-		/* mremap: update the end value of this node */
-		rb_erase_augmented(&data->rb, &memtype_rbroot,
-					&memtype_rb_augment_cb);
-		data->end = start;
-		data->subtree_max_end = data->end;
-		memtype_rb_insert(&memtype_rbroot, data);
-		return NULL;
-	}
-
-	return data;
-}
-
-struct memtype *rbt_memtype_lookup(u64 addr)
-{
-	return memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE);
-}
-
-#if defined(CONFIG_DEBUG_FS)
-int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
-{
-	struct rb_node *node;
-	int i = 1;
-
-	node = rb_first(&memtype_rbroot);
-	while (node && pos != i) {
-		node = rb_next(node);
-		i++;
-	}
-
-	if (node) { /* pos == i */
-		struct memtype *this = rb_entry(node, struct memtype, rb);
-		*out = *this;
-		return 0;
-	} else {
-		return 1;
-	}
-}
-#endif
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3e4b9035bb9a..7bd2c3a52297 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -643,8 +643,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
 	fixmaps_set++;
 }
 
-void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
-		       pgprot_t flags)
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
+		       phys_addr_t phys, pgprot_t flags)
 {
 	/* Sanitize 'prot' against any unsupported bits: */
 	pgprot_val(flags) &= __default_kernel_pte_mask;
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 7f2140414440..44a9f068eee0 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -574,7 +574,7 @@ static void pti_clone_kernel_text(void)
 	 */
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long end_clone  = (unsigned long)__end_rodata_aligned;
-	unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table);
+	unsigned long end_global = PFN_ALIGN((unsigned long)_etext);
 
 	if (!pti_kernel_image_global_ok())
 		return;
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index a8bd952e136d..92153d054d6c 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -127,9 +127,9 @@ static int __init init(void)
 		return -ENXIO;
 	}
 
-	pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
-		   "and writing 16 kB of rubbish in there.\n",
-		   size >> 10, mmio_address);
+	pr_warn("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
+		"and writing 16 kB of rubbish in there.\n",
+		size >> 10, mmio_address);
 	do_test(size);
 	do_test_bulk_ioremapping();
 	pr_info("All done.\n");