Merge tag 'x86-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core x86 updates from Ingo Molnar:
 "x86 CPU features support:
   - Generate the <asm/cpufeaturemasks.h> header based on build config
     (H. Peter Anvin, Xin Li)
   - x86 CPUID parsing updates and fixes (Ahmed S. Darwish)
   - Introduce the 'setcpuid=' boot parameter (Brendan Jackman)
   - Enable modifying CPU bug flags with '{clear,set}puid=' (Brendan
     Jackman)
   - Utilize CPU-type for CPU matching (Pawan Gupta)
   - Warn about unmet CPU feature dependencies (Sohil Mehta)
   - Prepare for new Intel Family numbers (Sohil Mehta)

  Percpu code:
   - Standardize & reorganize the x86 percpu layout and related cleanups
     (Brian Gerst)
   - Convert the stackprotector canary to a regular percpu variable
     (Brian Gerst)
   - Add a percpu subsection for cache hot data (Brian Gerst)
   - Unify __pcpu_op{1,2}_N() macros to __pcpu_op_N() (Uros Bizjak)
   - Construct __percpu_seg_override from __percpu_seg (Uros Bizjak)

  MM:
   - Add support for broadcast TLB invalidation using AMD's INVLPGB
     instruction (Rik van Riel)
   - Rework ROX cache to avoid writable copy (Mike Rapoport)
   - PAT: restore large ROX pages after fragmentation (Kirill A.
     Shutemov, Mike Rapoport)
   - Make memremap(MEMREMAP_WB) map memory as encrypted by default
     (Kirill A. Shutemov)
   - Robustify page table initialization (Kirill A. Shutemov)
   - Fix flush_tlb_range() when used for zapping normal PMDs (Jann Horn)
   - Clear _PAGE_DIRTY for kernel mappings when we clear _PAGE_RW
     (Matthew Wilcox)

  KASLR:
   - x86/kaslr: Reduce KASLR entropy on most x86 systems, to support PCI
     BAR space beyond the 10TiB region (CONFIG_PCI_P2PDMA=y) (Balbir
     Singh)

  CPU bugs:
   - Implement FineIBT-BHI mitigation (Peter Zijlstra)
   - speculation: Simplify and make CALL_NOSPEC consistent (Pawan Gupta)
   - speculation: Add a conditional CS prefix to CALL_NOSPEC (Pawan
     Gupta)
   - RFDS: Exclude P-only parts from the RFDS affected list (Pawan
     Gupta)

  System calls:
   - Break up entry/common.c (Brian Gerst)
   - Move sysctls into arch/x86 (Joel Granados)

  Intel LAM support updates: (Maciej Wieczor-Retman)
   - selftests/lam: Move cpu_has_la57() to use cpuinfo flag
   - selftests/lam: Skip test if LAM is disabled
   - selftests/lam: Test get_user() LAM pointer handling

  AMD SMN access updates:
   - Add SMN offsets to exclusive region access (Mario Limonciello)
   - Add support for debugfs access to SMN registers (Mario Limonciello)
   - Have HSMP use SMN through AMD_NODE (Yazen Ghannam)

  Power management updates: (Patryk Wlazlyn)
   - Allow calling mwait_play_dead with an arbitrary hint
   - ACPI/processor_idle: Add FFH state handling
   - intel_idle: Provide the default enter_dead() handler
   - Eliminate mwait_play_dead_cpuid_hint()

  Build system:
   - Raise the minimum GCC version to 8.1 (Brian Gerst)
   - Raise the minimum LLVM version to 15.0.0 (Nathan Chancellor)

  Kconfig: (Arnd Bergmann)
   - Add cmpxchg8b support back to Geode CPUs
   - Drop 32-bit "bigsmp" machine support
   - Rework CONFIG_GENERIC_CPU compiler flags
   - Drop configuration options for early 64-bit CPUs
   - Remove CONFIG_HIGHMEM64G support
   - Drop CONFIG_SWIOTLB for PAE
   - Drop support for CONFIG_HIGHPTE
   - Document CONFIG_X86_INTEL_MID as 64-bit-only
   - Remove old STA2x11 support
   - Only allow CONFIG_EISA for 32-bit

  Headers:
   - Replace __ASSEMBLY__ with __ASSEMBLER__ in UAPI and non-UAPI
     headers (Thomas Huth)

  Assembly code & machine code patching:
   - x86/alternatives: Simplify alternative_call() interface (Josh
     Poimboeuf)
   - x86/alternatives: Simplify callthunk patching (Peter Zijlstra)
   - KVM: VMX: Use named operands in inline asm (Josh Poimboeuf)
   - x86/hyperv: Use named operands in inline asm (Josh Poimboeuf)
   - x86/traps: Cleanup and robustify decode_bug() (Peter Zijlstra)
   - x86/kexec: Merge x86_32 and x86_64 code using macros from
     <asm/asm.h> (Uros Bizjak)
   - Use named operands in inline asm (Uros Bizjak)
   - Improve performance by using asm_inline() for atomic locking
     instructions (Uros Bizjak)

  Earlyprintk:
   - Harden early_serial (Peter Zijlstra)

  NMI handler:
   - Add an emergency handler in nmi_desc & use it in
     nmi_shootdown_cpus() (Waiman Long)

  Miscellaneous fixes and cleanups:
   - by Ahmed S. Darwish, Andy Shevchenko, Ard Biesheuvel, Artem
     Bityutskiy, Borislav Petkov, Brendan Jackman, Brian Gerst, Dan
     Carpenter, Dr. David Alan Gilbert, H. Peter Anvin, Ingo Molnar,
     Josh Poimboeuf, Kevin Brodsky, Mike Rapoport, Lukas Bulwahn, Maciej
     Wieczor-Retman, Max Grobecker, Patryk Wlazlyn, Pawan Gupta, Peter
     Zijlstra, Philip Redkin, Qasim Ijaz, Rik van Riel, Thomas Gleixner,
     Thorsten Blum, Tom Lendacky, Tony Luck, Uros Bizjak, Vitaly
     Kuznetsov, Xin Li, liuye"

* tag 'x86-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (211 commits)
  zstd: Increase DYNAMIC_BMI2 GCC version cutoff from 4.8 to 11.0 to work around compiler segfault
  x86/asm: Make asm export of __ref_stack_chk_guard unconditional
  x86/mm: Only do broadcast flush from reclaim if pages were unmapped
  perf/x86/intel, x86/cpu: Replace Pentium 4 model checks with VFM ones
  perf/x86/intel, x86/cpu: Simplify Intel PMU initialization
  x86/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in non-UAPI headers
  x86/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in UAPI headers
  x86/locking/atomic: Improve performance by using asm_inline() for atomic locking instructions
  x86/asm: Use asm_inline() instead of asm() in clwb()
  x86/asm: Use CLFLUSHOPT and CLWB mnemonics in <asm/special_insns.h>
  x86/hweight: Use asm_inline() instead of asm()
  x86/hweight: Use ASM_CALL_CONSTRAINT in inline asm()
  x86/hweight: Use named operands in inline asm()
  x86/stackprotector/64: Only export __ref_stack_chk_guard on CONFIG_SMP
  x86/head/64: Avoid Clang < 17 stack protector in startup code
  x86/kexec: Merge x86_32 and x86_64 code using macros from <asm/asm.h>
  x86/runtime-const: Add the RUNTIME_CONST_PTR assembly macro
  x86/cpu/intel: Limit the non-architectural constant_tsc model checks
  x86/mm/pat: Replace Intel x86_model checks with VFM ones
  x86/cpu/intel: Fix fast string initialization for extended Families
  ...

15 files changed, 85 insertions, 68 deletions

diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index a17e97e634a6..d0eccbd920e5 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -280,6 +280,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 				    struct acpi_processor_cx *cx,
 				    struct acpi_power_register *reg);
 void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cstate);
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx);
 #else
 static inline void acpi_processor_power_init_bm_check(struct
 						      acpi_processor_flags
@@ -300,6 +301,10 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 {
 	return;
 }
+static inline void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	BUG();
+}
 #endif
 
 static inline int call_on_cpu(int cpu, long (*fn)(void *), void *arg,
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c768de6f19a9..0755bc39b0d8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char __start_ro_after_init[], __end_ro_after_init[];
 extern char _end[];
-extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __entry_text_start[], __entry_text_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0d5b186abee8..4925441bc471 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -385,6 +385,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN(PAGE_SIZE);						\
 	__nosave_end = .;
 
+#define CACHE_HOT_DATA(align)						\
+	. = ALIGN(align);						\
+	*(SORT_BY_ALIGNMENT(.data..hot.*))				\
+	. = ALIGN(align);
+
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
 	*(.data..page_aligned)						\
@@ -1062,10 +1067,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  */
 #define PERCPU_INPUT(cacheline)						\
 	__per_cpu_start = .;						\
-	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
+	__per_cpu_hot_start = .;					\
+	*(SORT_BY_ALIGNMENT(.data..percpu..hot.*))			\
+	__per_cpu_hot_end = .;						\
+	. = ALIGN(cacheline);						\
 	*(.data..percpu..read_mostly)					\
 	. = ALIGN(cacheline);						\
 	*(.data..percpu)						\
@@ -1074,52 +1082,17 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__per_cpu_end = .;
 
 /**
- * PERCPU_VADDR - define output section for percpu area
+ * PERCPU_SECTION - define output section for percpu area
  * @cacheline: cacheline size
- * @vaddr: explicit base address (optional)
- * @phdr: destination PHDR (optional)
  *
  * Macro which expands to output section for percpu area.
  *
  * @cacheline is used to align subsections to avoid false cacheline
  * sharing between subsections for different purposes.
- *
- * If @vaddr is not blank, it specifies explicit base address and all
- * percpu symbols will be offset from the given address.  If blank,
- * @vaddr always equals @laddr + LOAD_OFFSET.
- *
- * @phdr defines the output PHDR to use if not blank.  Be warned that
- * output PHDR is sticky.  If @phdr is specified, the next output
- * section in the linker script will go there too.  @phdr should have
- * a leading colon.
- *
- * Note that this macros defines __per_cpu_load as an absolute symbol.
- * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU_SECTION.
- */
-#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
-	__per_cpu_load = .;						\
-	.data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) {	\
-		PERCPU_INPUT(cacheline)					\
-	} phdr								\
-	. = __per_cpu_load + SIZEOF(.data..percpu);
-
-/**
- * PERCPU_SECTION - define output section for percpu area, simple version
- * @cacheline: cacheline size
- *
- * Align to PAGE_SIZE and outputs output section for percpu area.  This
- * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
- * __per_cpu_start will be identical.
- *
- * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
- * except that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32 configuration.
  */
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
-		__per_cpu_load = .;					\
 		PERCPU_INPUT(cacheline)					\
 	}
 
@@ -1148,6 +1121,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 		INIT_TASK_DATA(inittask)				\
 		NOSAVE_DATA						\
 		PAGE_ALIGNED_DATA(pagealigned)				\
+		CACHE_HOT_DATA(cacheline)				\
 		CACHELINE_ALIGNED_DATA(cacheline)			\
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4e495b29c640..a70e62d69dc7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -330,7 +330,6 @@ static inline bool acpi_sci_irq_valid(void)
 }
 
 extern int sbf_port;
-extern unsigned long acpi_realmode_flags;
 
 int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index f0df518e11dd..1db17ecbb86c 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -11,6 +11,8 @@
 #include <linux/module.h>
 #include <asm/cfi.h>
 
+extern bool cfi_warn;
+
 #ifndef cfi_get_offset
 static inline int cfi_get_offset(void)
 {
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6db889c9efcc..9fc30b6b80c9 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -228,6 +228,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #endif /* __KERNEL__ */
 
+#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+#define KCFI_REFERENCE(sym) __ADDRESSABLE(sym)
+#else
+#define KCFI_REFERENCE(sym)
+#endif
+
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
  * @off:	the address of the 32-bit offset value
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 64130ae19690..65655a5d1be2 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -65,6 +65,37 @@ enum execmem_range_flags {
  * Architectures that use EXECMEM_ROX_CACHE must implement this.
  */
 void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
+
+/**
+ * execmem_make_temp_rw - temporarily remap region with read-write
+ *			  permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Remaps a part of the cached large page in the ROX cache in the range
+ * [@ptr, @ptr + @size) as writable and not executable. The caller must
+ * have exclusive ownership of this range and ensure nothing will try to
+ * execute code in this range.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_make_temp_rw(void *ptr, size_t size);
+
+/**
+ * execmem_restore_rox - restore read-only-execute permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Restores read-only-execute permissions on a range [@ptr, @ptr + @size)
+ * after it was temporarily remapped as writable. Relies on architecture
+ * implementation of set_memory_rox() to restore mapping using large pages.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_restore_rox(void *ptr, size_t size);
+#else
+static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
+static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
 #endif
 
 /**
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index d67614f7b7f1..bd7e60c0b72f 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -692,6 +692,7 @@ struct x86_cpu_id {
 	__u16 feature;	/* bit index */
 	/* Solely for kernel-internal use: DO NOT EXPORT to userspace! */
 	__u16 flags;
+	__u8  type;
 	kernel_ulong_t driver_data;
 };
 
@@ -703,6 +704,7 @@ struct x86_cpu_id {
 #define X86_STEP_MIN 0
 #define X86_STEP_MAX 0xf
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
+#define X86_CPU_TYPE_ANY 0
 
 /*
  * Generic table type for matching CPU features.
diff --git a/include/linux/module.h b/include/linux/module.h
index 30e5b19bafa9..9937e71a3b5b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -370,7 +370,6 @@ enum mod_mem_type {
 
 struct module_memory {
 	void *base;
-	void *rw_copy;
 	bool is_rox;
 	unsigned int size;
 
@@ -772,16 +771,6 @@ static inline bool is_livepatch_module(struct module *mod)
 
 void set_module_sig_enforced(void);
 
-void *__module_writable_address(struct module *mod, void *loc);
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod ||
-	    mod->state != MODULE_STATE_UNFORMED)
-		return loc;
-	return __module_writable_address(mod, loc);
-}
-
 #else /* !CONFIG_MODULES... */
 
 static inline struct module *__module_address(unsigned long addr)
@@ -889,11 +878,6 @@ static inline bool module_is_coming(struct module *mod)
 {
 	return false;
 }
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	return loc;
-}
 #endif /* CONFIG_MODULES */
 
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 1f5507ba5a12..e395461d59e5 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -108,10 +108,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *mod);
 
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *mod);
-
 #ifdef CONFIG_MODULES
 void flush_module_init_free_work(void);
 #else
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index c722a921165b..3ca965a2ddc8 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -128,7 +128,7 @@
 #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
 #define STACK_FRAME_NON_STANDARD_FP(func)
-#define __ASM_ANNOTATE(label, type)
+#define __ASM_ANNOTATE(label, type) ""
 #define ASM_ANNOTATE(type)
 #else
 .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0
@@ -147,6 +147,8 @@
  * these relocations will never be used for indirect calls.
  */
 #define ANNOTATE_NOENDBR		ASM_ANNOTATE(ANNOTYPE_NOENDBR)
+#define ANNOTATE_NOENDBR_SYM(sym)	asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR))
+
 /*
  * This should be used immediately before an indirect jump/call. It tells
  * objtool the subsequent indirect jump/call is vouched safe for retpoline
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5b520fe86b60..0fcacb909778 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -26,13 +26,11 @@
 #define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
 #endif
-#define PER_CPU_FIRST_SECTION "..first"
 
 #else
 
 #define PER_CPU_SHARED_ALIGNED_SECTION ""
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
 
 #endif
 
@@ -115,14 +113,17 @@
 	DEFINE_PER_CPU_SECTION(type, name, "")
 
 /*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
+ * Declaration/definition used for per-CPU variables that are frequently
+ * accessed and should be in a single cacheline.
+ *
+ * For use only by architecture and core code.  Only use scalar or pointer
+ * types to maximize density.
  */
-#define DECLARE_PER_CPU_FIRST(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+#define DECLARE_PER_CPU_CACHE_HOT(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, "..hot.." #name)
 
-#define DEFINE_PER_CPU_FIRST(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+#define DEFINE_PER_CPU_CACHE_HOT(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, "..hot.." #name)
 
 /*
  * Declaration/definition used for per-CPU variables that must be cacheline
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 3e9808f2b549..b0af8d4ef6e6 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -319,6 +319,7 @@ do { \
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
+struct task_struct;
 
 /**
  * preempt_ops - notifiers called when a task is preempted and rescheduled
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index c3a00b967d18..49039494076f 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -23,17 +23,25 @@
 #define SZ_4K				0x00001000
 #define SZ_8K				0x00002000
 #define SZ_16K				0x00004000
+#define SZ_24K				0x00006000
 #define SZ_32K				0x00008000
 #define SZ_64K				0x00010000
 #define SZ_128K				0x00020000
+#define SZ_192K				0x00030000
 #define SZ_256K				0x00040000
+#define SZ_384K				0x00060000
 #define SZ_512K				0x00080000
 
 #define SZ_1M				0x00100000
 #define SZ_2M				0x00200000
+#define SZ_3M				0x00300000
 #define SZ_4M				0x00400000
+#define SZ_6M				0x00600000
 #define SZ_8M				0x00800000
+#define SZ_12M				0x00c00000
 #define SZ_16M				0x01000000
+#define SZ_18M				0x01200000
+#define SZ_24M				0x01800000
 #define SZ_32M				0x02000000
 #define SZ_64M				0x04000000
 #define SZ_128M				0x08000000
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index f70d0958095c..5a37cb2b6f93 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -151,6 +151,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
 		DIRECT_MAP_LEVEL3_SPLIT,
+		DIRECT_MAP_LEVEL2_COLLAPSE,
+		DIRECT_MAP_LEVEL3_COLLAPSE,
 #endif
 #ifdef CONFIG_PER_VMA_LOCK_STATS
 		VMA_LOCK_SUCCESS,