Merge tag 'mm-stable-2025-05-31-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - "Add folio_mk_pte()" from Matthew Wilcox simplifies the act of
   creating a pte which addresses the first page in a folio and reduces
   the amount of plumbing which architecture must implement to provide
   this.

 - "Misc folio patches for 6.16" from Matthew Wilcox is a shower of
   largely unrelated folio infrastructure changes which clean things up
   and better prepare us for future work.

 - "memory,x86,acpi: hotplug memory alignment advisement" from Gregory
   Price adds early-init code to prevent x86 from leaving physical
   memory unused when physical address regions are not aligned to memory
   block size.

 - "mm/compaction: allow more aggressive proactive compaction" from
   Michal Clapinski provides some tuning of the (sadly, hard-coded (more
   sadly, not auto-tuned)) thresholds for our invokation of proactive
   compaction. In a simple test case, the reduction of a guest VM's
   memory consumption was dramatic.

 - "Minor cleanups and improvements to swap freeing code" from Kemeng
   Shi provides some code cleaups and a small efficiency improvement to
   this part of our swap handling code.

 - "ptrace: introduce PTRACE_SET_SYSCALL_INFO API" from Dmitry Levin
   adds the ability for a ptracer to modify syscalls arguments. At this
   time we can alter only "system call information that are used by
   strace system call tampering, namely, syscall number, syscall
   arguments, and syscall return value.

   This series should have been incorporated into mm.git's "non-MM"
   branch, but I goofed.

 - "fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions" from
   Andrei Vagin extends the info returned by the PAGEMAP_SCAN ioctl
   against /proc/pid/pagemap. This permits CRIU to more efficiently get
   at the info about guard regions.

 - "Fix parameter passed to page_mapcount_is_type()" from Gavin Shan
   implements that fix. No runtime effect is expected because
   validate_page_before_insert() happens to fix up this error.

 - "kernel/events/uprobes: uprobe_write_opcode() rewrite" from David
   Hildenbrand basically brings uprobe text poking into the current
   decade. Remove a bunch of hand-rolled implementation in favor of
   using more current facilities.

 - "mm/ptdump: Drop assumption that pxd_val() is u64" from Anshuman
   Khandual provides enhancements and generalizations to the pte dumping
   code. This might be needed when 128-bit Page Table Descriptors are
   enabled for ARM.

 - "Always call constructor for kernel page tables" from Kevin Brodsky
   ensures that the ctor/dtor is always called for kernel pgtables, as
   it already is for user pgtables.

   This permits the addition of more functionality such as "insert hooks
   to protect page tables". This change does result in various
   architectures performing unnecesary work, but this is fixed up where
   it is anticipated to occur.

 - "Rust support for mm_struct, vm_area_struct, and mmap" from Alice
   Ryhl adds plumbing to permit Rust access to core MM structures.

 - "fix incorrectly disallowed anonymous VMA merges" from Lorenzo
   Stoakes takes advantage of some VMA merging opportunities which we've
   been missing for 15 years.

 - "mm/madvise: batch tlb flushes for MADV_DONTNEED and MADV_FREE" from
   SeongJae Park optimizes process_madvise()'s TLB flushing.

   Instead of flushing each address range in the provided iovec, we
   batch the flushing across all the iovec entries. The syscall's cost
   was approximately halved with a microbenchmark which was designed to
   load this particular operation.

 - "Track node vacancy to reduce worst case allocation counts" from
   Sidhartha Kumar makes the maple tree smarter about its node
   preallocation.

   stress-ng mmap performance increased by single-digit percentages and
   the amount of unnecessarily preallocated memory was dramaticelly
   reduced.

 - "mm/gup: Minor fix, cleanup and improvements" from Baoquan He removes
   a few unnecessary things which Baoquan noted when reading the code.

 - ""Enhance sysfs handling for memory hotplug in weighted interleave"
   from Rakie Kim "enhances the weighted interleave policy in the memory
   management subsystem by improving sysfs handling, fixing memory
   leaks, and introducing dynamic sysfs updates for memory hotplug
   support". Fixes things on error paths which we are unlikely to hit.

 - "mm/damon: auto-tune DAMOS for NUMA setups including tiered memory"
   from SeongJae Park introduces new DAMOS quota goal metrics which
   eliminate the manual tuning which is required when utilizing DAMON
   for memory tiering.

 - "mm/vmalloc.c: code cleanup and improvements" from Baoquan He
   provides cleanups and small efficiency improvements which Baoquan
   found via code inspection.

 - "vmscan: enforce mems_effective during demotion" from Gregory Price
   changes reclaim to respect cpuset.mems_effective during demotion when
   possible. because presently, reclaim explicitly ignores
   cpuset.mems_effective when demoting, which may cause the cpuset
   settings to violated.

   This is useful for isolating workloads on a multi-tenant system from
   certain classes of memory more consistently.

 - "Clean up split_huge_pmd_locked() and remove unnecessary folio
   pointers" from Gavin Guo provides minor cleanups and efficiency gains
   in in the huge page splitting and migrating code.

 - "Use kmem_cache for memcg alloc" from Huan Yang creates a slab cache
   for `struct mem_cgroup', yielding improved memory utilization.

 - "add max arg to swappiness in memory.reclaim and lru_gen" from
   Zhongkun He adds a new "max" argument to the "swappiness=" argument
   for memory.reclaim MGLRU's lru_gen.

   This directs proactive reclaim to reclaim from only anon folios
   rather than file-backed folios.

 - "kexec: introduce Kexec HandOver (KHO)" from Mike Rapoport is the
   first step on the path to permitting the kernel to maintain existing
   VMs while replacing the host kernel via file-based kexec. At this
   time only memblock's reserve_mem is preserved.

 - "mm: Introduce for_each_valid_pfn()" from David Woodhouse provides
   and uses a smarter way of looping over a pfn range. By skipping
   ranges of invalid pfns.

 - "sched/numa: Skip VMA scanning on memory pinned to one NUMA node via
   cpuset.mems" from Libo Chen removes a lot of pointless VMA scanning
   when a task is pinned a single NUMA mode.

   Dramatic performance benefits were seen in some real world cases.

 - "JFS: Implement migrate_folio for jfs_metapage_aops" from Shivank
   Garg addresses a warning which occurs during memory compaction when
   using JFS.

 - "move all VMA allocation, freeing and duplication logic to mm" from
   Lorenzo Stoakes moves some VMA code from kernel/fork.c into the more
   appropriate mm/vma.c.

 - "mm, swap: clean up swap cache mapping helper" from Kairui Song
   provides code consolidation and cleanups related to the folio_index()
   function.

 - "mm/gup: Cleanup memfd_pin_folios()" from Vishal Moola does that.

 - "memcg: Fix test_memcg_min/low test failures" from Waiman Long
   addresses some bogus failures which are being reported by the
   test_memcontrol selftest.

 - "eliminate mmap() retry merge, add .mmap_prepare hook" from Lorenzo
   Stoakes commences the deprecation of file_operations.mmap() in favor
   of the new file_operations.mmap_prepare().

   The latter is more restrictive and prevents drivers from messing with
   things in ways which, amongst other problems, may defeat VMA merging.

 - "memcg: decouple memcg and objcg stocks"" from Shakeel Butt decouples
   the per-cpu memcg charge cache from the objcg's one.

   This is a step along the way to making memcg and objcg charging
   NMI-safe, which is a BPF requirement.

 - "mm/damon: minor fixups and improvements for code, tests, and
   documents" from SeongJae Park is yet another batch of miscellaneous
   DAMON changes. Fix and improve minor problems in code, tests and
   documents.

 - "memcg: make memcg stats irq safe" from Shakeel Butt converts memcg
   stats to be irq safe. Another step along the way to making memcg
   charging and stats updates NMI-safe, a BPF requirement.

 - "Let unmap_hugepage_range() and several related functions take folio
   instead of page" from Fan Ni provides folio conversions in the
   hugetlb code.

* tag 'mm-stable-2025-05-31-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (285 commits)
  mm: pcp: increase pcp->free_count threshold to trigger free_high
  mm/hugetlb: convert use of struct page to folio in __unmap_hugepage_range()
  mm/hugetlb: refactor __unmap_hugepage_range() to take folio instead of page
  mm/hugetlb: refactor unmap_hugepage_range() to take folio instead of page
  mm/hugetlb: pass folio instead of page to unmap_ref_private()
  memcg: objcg stock trylock without irq disabling
  memcg: no stock lock for cpu hot-unplug
  memcg: make __mod_memcg_lruvec_state re-entrant safe against irqs
  memcg: make count_memcg_events re-entrant safe against irqs
  memcg: make mod_memcg_state re-entrant safe against irqs
  memcg: move preempt disable to callers of memcg_rstat_updated
  memcg: memcg_rstat_updated re-entrant safe against irqs
  mm: khugepaged: decouple SHMEM and file folios' collapse
  selftests/eventfd: correct test name and improve messages
  alloc_tag: check mem_profiling_support in alloc_tag_init
  Docs/damon: update titles and brief introductions to explain DAMOS
  selftests/damon/_damon_sysfs: read tried regions directories in order
  mm/damon/tests/core-kunit: add a test for damos_set_filters_default_reject()
  mm/damon/paddr: remove unused variable, folio_list, in damon_pa_stat()
  mm/damon/sysfs-schemes: fix wrong comment on damons_sysfs_quota_goal_metric_strs
  ...

99 files changed, 1070 insertions, 584 deletions

diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 02e8817a8921..2676017f42f1 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -192,13 +192,6 @@ extern unsigned long __zero_page(void);
 #define pte_pfn(pte)		(pte_val(pte) >> PFN_PTE_SHIFT)
 
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
-#define mk_pte(page, pgprot)						\
-({									\
-	pte_t pte;							\
-									\
-	pte_val(pte) = (page_to_pfn(page) << 32) | pgprot_val(pgprot);	\
-	pte;								\
-})
 
 extern inline pte_t pfn_pte(unsigned long physpfn, pgprot_t pgprot)
 { pte_t pte; pte_val(pte) = (PHYS_TWIDDLE(physpfn) << 32) | pgprot_val(pgprot); return pte; }
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 8a2441670a8f..7765dc105d54 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -40,8 +40,6 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 
-#define mk_pmd(page, prot)	pte_pmd(mk_pte(page, prot))
-
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) & _PAGE_HW_SZ)
 
 #define pfn_pmd(pfn, prot)	(__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h
index 86e148226463..d1ce4b0f1071 100644
--- a/arch/arc/include/asm/pgtable-levels.h
+++ b/arch/arc/include/asm/pgtable-levels.h
@@ -142,7 +142,6 @@
 
 #define pmd_pfn(pmd)		((pmd_val(pmd) & PMD_MASK) >> PAGE_SHIFT)
 #define pfn_pmd(pfn,prot)	__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #endif
 
@@ -177,7 +176,6 @@
 #define set_pte(ptep, pte)	((*(ptep)) = (pte))
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
 #define pfn_pte(pfn, prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
-#define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
 
 #ifdef CONFIG_ISA_ARCV2
 #define pmd_leaf(x)		(pmd_val(x) & _PAGE_HW_SZ)
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
index 9709256e31c8..728d625a10f1 100644
--- a/arch/arc/include/asm/syscall.h
+++ b/arch/arc/include/asm/syscall.h
@@ -24,6 +24,17 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 }
 
 static inline void
+syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->r8 = nr;
+}
+
+static inline void
 syscall_rollback(struct task_struct *task, struct pt_regs *regs)
 {
 	regs->r0 = regs->orig_r0;
@@ -67,6 +78,20 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
 	}
 }
 
+static inline void
+syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+		      unsigned long *args)
+{
+	unsigned long *inside_ptregs = &regs->r0;
+	unsigned int n = 6;
+	unsigned int i = 0;
+
+	while (n--) {
+		*inside_ptregs = args[i++];
+		inside_ptregs--;
+	}
+}
+
 static inline int
 syscall_get_arch(struct task_struct *task)
 {
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index fa5939eb9864..7b71a3d414b7 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -209,7 +209,6 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
 #define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
-#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 /* No hardware dirty/accessed bits -- generic_pmdp_establish() fits */
 #define pmdp_establish generic_pmdp_establish
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 6b986ef6042f..7f1c3b4e3e04 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -168,7 +168,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pfn_pte(pfn,prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
-#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page), prot)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index fe4326d938c1..18b102a30741 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -68,6 +68,30 @@ static inline void syscall_set_return_value(struct task_struct *task,
 	regs->ARM_r0 = (long) error ? error : val;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	if (nr == -1) {
+		task_thread_info(task)->abi_syscall = -1;
+		/*
+		 * When the syscall number is set to -1, the syscall will be
+		 * skipped.  In this case the syscall return value has to be
+		 * set explicitly, otherwise the first syscall argument is
+		 * returned as the syscall return value.
+		 */
+		syscall_set_return_value(task, regs, -ENOSYS, 0);
+		return;
+	}
+	if ((IS_ENABLED(CONFIG_AEABI) && !IS_ENABLED(CONFIG_OABI_COMPAT))) {
+		task_thread_info(task)->abi_syscall = nr;
+		return;
+	}
+	task_thread_info(task)->abi_syscall =
+		(task_thread_info(task)->abi_syscall & ~__NR_SYSCALL_MASK) |
+		(nr & __NR_SYSCALL_MASK);
+}
+
 #define SYSCALL_MAX_ARGS 7
 
 static inline void syscall_get_arguments(struct task_struct *task,
@@ -80,6 +104,19 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	memcpy(args, &regs->ARM_r0 + 1, 5 * sizeof(args[0]));
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	memcpy(&regs->ARM_r0, args, 6 * sizeof(args[0]));
+	/*
+	 * Also copy the first argument into ARM_ORIG_r0
+	 * so that syscall_get_arguments() would return it
+	 * instead of the previous value.
+	 */
+	regs->ARM_ORIG_r0 = regs->ARM_r0;
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	/* ARM tasks don't change audit architectures on the fly. */
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index f02f872ea8a9..edb7f56b7c91 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -735,7 +735,7 @@ static void *__init late_alloc(unsigned long sz)
 	void *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM,
 			get_order(sz));
 
-	if (!ptdesc || !pagetable_pte_ctor(ptdesc))
+	if (!ptdesc || !pagetable_pte_ctor(NULL, ptdesc))
 		BUG();
 	return ptdesc_to_virt(ptdesc);
 }
diff --git a/arch/arm/probes/uprobes/core.c b/arch/arm/probes/uprobes/core.c
index f5f790c6e5f8..885e0c5e8c20 100644
--- a/arch/arm/probes/uprobes/core.c
+++ b/arch/arm/probes/uprobes/core.c
@@ -26,10 +26,10 @@ bool is_swbp_insn(uprobe_opcode_t *insn)
 		(UPROBE_SWBP_ARM_INSN & 0x0fffffff);
 }
 
-int set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
+int set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 	     unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr,
+	return uprobe_write_opcode(auprobe, vma, vaddr,
 		   __opcode_to_mem_arm(auprobe->bpinsn));
 }
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index bcc1773fec77..55fc331af337 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1616,6 +1616,9 @@ config ARCH_SUPPORTS_KEXEC_IMAGE_VERIFY_SIG
 config ARCH_DEFAULT_KEXEC_IMAGE_VERIFY_SIG
 	def_bool y
 
+config ARCH_SUPPORTS_KEXEC_HANDOVER
+	def_bool y
+
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool y
 
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
index 6d6d4065b0cb..265e8301d7ba 100644
--- a/arch/arm64/include/asm/pgtable-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -11,11 +11,19 @@
 
 #include <asm/types.h>
 
-typedef u64 pteval_t;
-typedef u64 pmdval_t;
-typedef u64 pudval_t;
-typedef u64 p4dval_t;
-typedef u64 pgdval_t;
+/*
+ * Page Table Descriptor
+ *
+ * Generic page table descriptor format from which
+ * all level specific descriptors can be derived.
+ */
+typedef u64 ptdesc_t;
+
+typedef ptdesc_t pteval_t;
+typedef ptdesc_t pmdval_t;
+typedef ptdesc_t pudval_t;
+typedef ptdesc_t p4dval_t;
+typedef ptdesc_t pgdval_t;
 
 /*
  * These are used to make use of C type-checking..
@@ -46,7 +54,7 @@ typedef struct { pgdval_t pgd; } pgd_t;
 #define pgd_val(x)	((x).pgd)
 #define __pgd(x)	((pgd_t) { (x) } )
 
-typedef struct { pteval_t pgprot; } pgprot_t;
+typedef struct { ptdesc_t pgprot; } pgprot_t;
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5285757ee0c1..88db8a0c0b37 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -673,7 +673,6 @@ static inline pmd_t pmd_mkspecial(pmd_t pmd)
 #define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
 #define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
 #define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #define pud_young(pud)		pte_young(pud_pte(pud))
 #define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
@@ -906,12 +905,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 /* use ONLY for statically allocated translation tables */
 #define pte_offset_kimg(dir,addr)	((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)
-
 #if CONFIG_PGTABLE_LEVELS > 2
 
 #define pmd_ERROR(e)	\
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
index b2931d1ae0fb..fded5358641f 100644
--- a/arch/arm64/include/asm/ptdump.h
+++ b/arch/arm64/include/asm/ptdump.h
@@ -24,8 +24,8 @@ struct ptdump_info {
 };
 
 struct ptdump_prot_bits {
-	u64		mask;
-	u64		val;
+	ptdesc_t	mask;
+	ptdesc_t	val;
 	const char	*set;
 	const char	*clear;
 };
@@ -34,7 +34,7 @@ struct ptdump_pg_level {
 	const struct ptdump_prot_bits *bits;
 	char name[4];
 	int num;
-	u64 mask;
+	ptdesc_t mask;
 };
 
 /*
@@ -51,7 +51,7 @@ struct ptdump_pg_state {
 	const struct mm_struct *mm;
 	unsigned long start_address;
 	int level;
-	u64 current_prot;
+	ptdesc_t current_prot;
 	bool check_wx;
 	unsigned long wx_pages;
 	unsigned long uxn_pages;
@@ -59,7 +59,13 @@ struct ptdump_pg_state {
 
 void ptdump_walk(struct seq_file *s, struct ptdump_info *info);
 void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
-	       u64 val);
+	       pteval_t val);
+void note_page_pte(struct ptdump_state *st, unsigned long addr, pte_t pte);
+void note_page_pmd(struct ptdump_state *st, unsigned long addr, pmd_t pmd);
+void note_page_pud(struct ptdump_state *st, unsigned long addr, pud_t pud);
+void note_page_p4d(struct ptdump_state *st, unsigned long addr, p4d_t p4d);
+void note_page_pgd(struct ptdump_state *st, unsigned long addr, pgd_t pgd);
+void note_page_flush(struct ptdump_state *st);
 #ifdef CONFIG_PTDUMP_DEBUGFS
 #define EFI_RUNTIME_MAP_END	DEFAULT_MAP_WINDOW_64
 void __init ptdump_debugfs_register(struct ptdump_info *info, const char *name);
@@ -69,7 +75,13 @@ static inline void ptdump_debugfs_register(struct ptdump_info *info,
 #endif /* CONFIG_PTDUMP_DEBUGFS */
 #else
 static inline void note_page(struct ptdump_state *pt_st, unsigned long addr,
-			     int level, u64 val) { }
+			     int level, pteval_t val) { }
+static inline void note_page_pte(struct ptdump_state *st, unsigned long addr, pte_t pte) { }
+static inline void note_page_pmd(struct ptdump_state *st, unsigned long addr, pmd_t pmd) { }
+static inline void note_page_pud(struct ptdump_state *st, unsigned long addr, pud_t pud) { }
+static inline void note_page_p4d(struct ptdump_state *st, unsigned long addr, p4d_t p4d) { }
+static inline void note_page_pgd(struct ptdump_state *st, unsigned long addr, pgd_t pgd) { }
+static inline void note_page_flush(struct ptdump_state *st) { }
 #endif /* CONFIG_PTDUMP */
 
 #endif /* __ASM_PTDUMP_H */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index ab8e14b96f68..712daa90e643 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -61,6 +61,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
 	regs->regs[0] = val;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->syscallno = nr;
+	if (nr == -1) {
+		/*
+		 * When the syscall number is set to -1, the syscall will be
+		 * skipped.  In this case the syscall return value has to be
+		 * set explicitly, otherwise the first syscall argument is
+		 * returned as the syscall return value.
+		 */
+		syscall_set_return_value(task, regs, -ENOSYS, 0);
+	}
+}
+
 #define SYSCALL_MAX_ARGS 6
 
 static inline void syscall_get_arguments(struct task_struct *task,
@@ -73,6 +89,19 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	memcpy(args, &regs->regs[1], 5 * sizeof(args[0]));
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	memcpy(&regs->regs[0], args, 6 * sizeof(args[0]));
+	/*
+	 * Also copy the first argument into orig_x0
+	 * so that syscall_get_arguments() would return it
+	 * instead of the previous value.
+	 */
+	regs->orig_x0 = regs->regs[0];
+}
+
 /*
  * We don't care about endianness (__AUDIT_ARCH_LE bit) here because
  * AArch64 has the same system calls both on little- and big- endian.
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 250e9d7c08a7..3857fd7ee8d4 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -29,7 +29,7 @@ static bool region_is_misaligned(const efi_memory_desc_t *md)
  * executable, everything else can be mapped with the XN bits
  * set. Also take the new (optional) RO/XP bits into account.
  */
-static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
+static __init ptdesc_t create_mapping_protection(efi_memory_desc_t *md)
 {
 	u64 attr = md->attribute;
 	u32 type = md->type;
@@ -83,7 +83,7 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
 
 int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 {
-	pteval_t prot_val = create_mapping_protection(md);
+	ptdesc_t prot_val = create_mapping_protection(md);
 	bool page_mappings_only = (md->type == EFI_RUNTIME_SERVICES_CODE ||
 				   md->type == EFI_RUNTIME_SERVICES_DATA);
 
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index c6650cfe706c..0f4bd7771859 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -159,7 +159,7 @@ static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr)
 static void __init remap_idmap_for_lpa2(void)
 {
 	/* clear the bits that change meaning once LPA2 is turned on */
-	pteval_t mask = PTE_SHARED;
+	ptdesc_t mask = PTE_SHARED;
 
 	/*
 	 * We have to clear bits [9:8] in all block or page descriptors in the
diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c
index 81345f68f9fc..7982788e7b9a 100644
--- a/arch/arm64/kernel/pi/map_range.c
+++ b/arch/arm64/kernel/pi/map_range.c
@@ -30,7 +30,7 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 		      int level, pte_t *tbl, bool may_use_cont, u64 va_offset)
 {
 	u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX;
-	pteval_t protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
+	ptdesc_t protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
 	int lshift = (3 - level) * PTDESC_TABLE_SHIFT;
 	u64 lmask = (PAGE_SIZE << lshift) - 1;
 
@@ -87,7 +87,7 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 	}
 }
 
-asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir, pteval_t clrmask)
+asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir, ptdesc_t clrmask)
 {
 	u64 ptep = (u64)pg_dir + PAGE_SIZE;
 	pgprot_t text_prot = PAGE_KERNEL_ROX;
diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h
index 1f4731a4e17e..46cafee7829f 100644
--- a/arch/arm64/kernel/pi/pi.h
+++ b/arch/arm64/kernel/pi/pi.h
@@ -34,4 +34,4 @@ void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot,
 
 asmlinkage void early_map_kernel(u64 boot_status, void *fdt);
 
-asmlinkage u64 create_init_idmap(pgd_t *pgd, pteval_t clrmask);
+asmlinkage u64 create_init_idmap(pgd_t *pgd, ptdesc_t clrmask);
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 07aeab8a7606..c86c348857c4 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -83,7 +83,7 @@ arch_initcall(adjust_protection_map);
 
 pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
-	pteval_t prot;
+	ptdesc_t prot;
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ea6695d53fb9..8fcf59ba39db 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -46,6 +46,13 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 #define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
 
+enum pgtable_type {
+	TABLE_PTE,
+	TABLE_PMD,
+	TABLE_PUD,
+	TABLE_P4D,
+};
+
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
@@ -107,7 +114,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 }
 EXPORT_SYMBOL(phys_mem_access_prot);
 
-static phys_addr_t __init early_pgtable_alloc(int shift)
+static phys_addr_t __init early_pgtable_alloc(enum pgtable_type pgtable_type)
 {
 	phys_addr_t phys;
 
@@ -192,7 +199,7 @@ static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(int),
+				phys_addr_t (*pgtable_alloc)(enum pgtable_type),
 				int flags)
 {
 	unsigned long next;
@@ -207,7 +214,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 		if (flags & NO_EXEC_MAPPINGS)
 			pmdval |= PMD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
-		pte_phys = pgtable_alloc(PAGE_SHIFT);
+		pte_phys = pgtable_alloc(TABLE_PTE);
 		ptep = pte_set_fixmap(pte_phys);
 		init_clear_pgtable(ptep);
 		ptep += pte_index(addr);
@@ -243,7 +250,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
 static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
-		     phys_addr_t (*pgtable_alloc)(int), int flags)
+		     phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags)
 {
 	unsigned long next;
 
@@ -277,7 +284,8 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(int), int flags)
+				phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+				int flags)
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
@@ -294,7 +302,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 		if (flags & NO_EXEC_MAPPINGS)
 			pudval |= PUD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
-		pmd_phys = pgtable_alloc(PMD_SHIFT);
+		pmd_phys = pgtable_alloc(TABLE_PMD);
 		pmdp = pmd_set_fixmap(pmd_phys);
 		init_clear_pgtable(pmdp);
 		pmdp += pmd_index(addr);
@@ -325,7 +333,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 
 static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 			   phys_addr_t phys, pgprot_t prot,
-			   phys_addr_t (*pgtable_alloc)(int),
+			   phys_addr_t (*pgtable_alloc)(enum pgtable_type),
 			   int flags)
 {
 	unsigned long next;
@@ -339,7 +347,7 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 		if (flags & NO_EXEC_MAPPINGS)
 			p4dval |= P4D_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
-		pud_phys = pgtable_alloc(PUD_SHIFT);
+		pud_phys = pgtable_alloc(TABLE_PUD);
 		pudp = pud_set_fixmap(pud_phys);
 		init_clear_pgtable(pudp);
 		pudp += pud_index(addr);
@@ -383,7 +391,7 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 
 static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 			   phys_addr_t phys, pgprot_t prot,
-			   phys_addr_t (*pgtable_alloc)(int),
+			   phys_addr_t (*pgtable_alloc)(enum pgtable_type),
 			   int flags)
 {
 	unsigned long next;
@@ -397,7 +405,7 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 		if (flags & NO_EXEC_MAPPINGS)
 			pgdval |= PGD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
-		p4d_phys = pgtable_alloc(P4D_SHIFT);
+		p4d_phys = pgtable_alloc(TABLE_P4D);
 		p4dp = p4d_set_fixmap(p4d_phys);
 		init_clear_pgtable(p4dp);
 		p4dp += p4d_index(addr);
@@ -427,7 +435,7 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
 					unsigned long virt, phys_addr_t size,
 					pgprot_t prot,
-					phys_addr_t (*pgtable_alloc)(int),
+					phys_addr_t (*pgtable_alloc)(enum pgtable_type),
 					int flags)
 {
 	unsigned long addr, end, next;
@@ -455,7 +463,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 unsigned long virt, phys_addr_t size,
 				 pgprot_t prot,
-				 phys_addr_t (*pgtable_alloc)(int),
+				 phys_addr_t (*pgtable_alloc)(enum pgtable_type),
 				 int flags)
 {
 	mutex_lock(&fixmap_lock);
@@ -468,37 +476,48 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 extern __alias(__create_pgd_mapping_locked)
 void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
 			     phys_addr_t size, pgprot_t prot,
-			     phys_addr_t (*pgtable_alloc)(int), int flags);
+			     phys_addr_t (*pgtable_alloc)(enum pgtable_type),
+			     int flags);
 #endif
 
-static phys_addr_t __pgd_pgtable_alloc(int shift)
+static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm,
+				       enum pgtable_type pgtable_type)
 {
 	/* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */
-	void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL & ~__GFP_ZERO);
+	struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & ~__GFP_ZERO, 0);
+	phys_addr_t pa;
+
+	BUG_ON(!ptdesc);
+	pa = page_to_phys(ptdesc_page(ptdesc));
+
+	switch (pgtable_type) {
+	case TABLE_PTE:
+		BUG_ON(!pagetable_pte_ctor(mm, ptdesc));
+		break;
+	case TABLE_PMD:
+		BUG_ON(!pagetable_pmd_ctor(mm, ptdesc));
+		break;
+	case TABLE_PUD:
+		pagetable_pud_ctor(ptdesc);
+		break;
+	case TABLE_P4D:
+		pagetable_p4d_ctor(ptdesc);
+		break;
+	}
 
-	BUG_ON(!ptr);
-	return __pa(ptr);
+	return pa;
 }
 
-static phys_addr_t pgd_pgtable_alloc(int shift)
+static phys_addr_t __maybe_unused
+pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type)
 {
-	phys_addr_t pa = __pgd_pgtable_alloc(shift);
-	struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa));
-
-	/*
-	 * Call proper page table ctor in case later we need to
-	 * call core mm functions like apply_to_page_range() on
-	 * this pre-allocated page table.
-	 *
-	 * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
-	 * folded, and if so pagetable_pte_ctor() becomes nop.
-	 */
-	if (shift == PAGE_SHIFT)
-		BUG_ON(!pagetable_pte_ctor(ptdesc));
-	else if (shift == PMD_SHIFT)
-		BUG_ON(!pagetable_pmd_ctor(ptdesc));
+	return __pgd_pgtable_alloc(&init_mm, pgtable_type);
+}
 
-	return pa;
+static phys_addr_t
+pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type)
+{
+	return __pgd_pgtable_alloc(NULL, pgtable_type);
 }
 
 /*
@@ -530,7 +549,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
-			     pgd_pgtable_alloc, flags);
+			     pgd_pgtable_alloc_special_mm, flags);
 }
 
 static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
@@ -744,7 +763,7 @@ static int __init map_entry_trampoline(void)
 	memset(tramp_pg_dir, 0, PGD_SIZE);
 	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
 			     entry_tramp_text_size(), prot,
-			     __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS);
+			     pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS);
 
 	/* Map both the text and data into the kernel page table */
 	for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
@@ -1350,7 +1369,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
-			     size, params->pgprot, __pgd_pgtable_alloc,
+			     size, params->pgprot, pgd_pgtable_alloc_init_mm,
 			     flags);
 
 	memblock_clear_nomap(start, size);
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index 8cec0da4cff2..421a5de806c6 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -189,12 +189,12 @@ static void note_prot_wx(struct ptdump_pg_state *st, unsigned long addr)
 }
 
 void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
-	       u64 val)
+	       pteval_t val)
 {
 	struct ptdump_pg_state *st = container_of(pt_st, struct ptdump_pg_state, ptdump);
 	struct ptdump_pg_level *pg_level = st->pg_level;
 	static const char units[] = "KMGTPE";
-	u64 prot = 0;
+	ptdesc_t prot = 0;
 
 	/* check if the current level has been folded dynamically */
 	if (st->mm && ((level == 1 && mm_p4d_folded(st->mm)) ||
@@ -251,6 +251,38 @@ void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
 
 }
 
+void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
 void ptdump_walk(struct seq_file *s, struct ptdump_info *info)
 {
 	unsigned long end = ~0UL;
@@ -266,7 +298,12 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info)
 		.pg_level = &kernel_pg_levels[0],
 		.level = -1,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = (struct ptdump_range[]){
 				{info->base_addr, end},
 				{0, 0}
@@ -303,7 +340,12 @@ bool ptdump_check_wx(void)
 		.level = -1,
 		.check_wx = true,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = (struct ptdump_range[]) {
 				{_PAGE_OFFSET(vabits_actual), ~0UL},
 				{0, 0}
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index 11055c574968..9ed2b15ffd94 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -29,7 +29,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	pte_t *pte;
 	unsigned long i;
 
-	pte = (pte_t *) __get_free_page(GFP_KERNEL);
+	pte = __pte_alloc_one_kernel(mm);
 	if (!pte)
 		return NULL;
 
diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h
index a397e1718ab6..b8378431aeff 100644
--- a/arch/csky/include/asm/pgtable.h
+++ b/arch/csky/include/asm/pgtable.h
@@ -249,11 +249,6 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot)    pfn_pte(page_to_pfn(page), (pgprot))
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
index 0de5734950bf..717f44b4d26f 100644
--- a/arch/csky/include/asm/syscall.h
+++ b/arch/csky/include/asm/syscall.h
@@ -59,6 +59,19 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
 	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
 }
 
+static inline void
+syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+		      const unsigned long *args)
+{
+	memcpy(&regs->a0, args, 6 * sizeof(regs->a0));
+	/*
+	 * Also copy the first argument into orig_a0
+	 * so that syscall_get_arguments() would return it
+	 * instead of the previous value.
+	 */
+	regs->orig_a0 = regs->a0;
+}
+
 static inline int
 syscall_get_arch(struct task_struct *task)
 {
diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h
index 8c5b7a1c3d90..9fbdfdbc539f 100644
--- a/arch/hexagon/include/asm/pgtable.h
+++ b/arch/hexagon/include/asm/pgtable.h
@@ -238,9 +238,6 @@ static inline int pte_present(pte_t pte)
 	return pte_val(pte) & _PAGE_PRESENT;
 }
 
-/* mk_pte - make a PTE out of a page pointer and protection bits */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-
 /* pte_page - returns a page (frame pointer/descriptor?) based on a PTE */
 #define pte_page(x) pfn_to_page(pte_pfn(x))
 
diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index f6e454f18038..70637261817a 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -26,6 +26,13 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return regs->r06;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->r06 = nr;
+}
+
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
 					 unsigned long *args)
@@ -33,6 +40,13 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	memcpy(args, &(&regs->r00)[0], 6 * sizeof(args[0]));
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned long *args)
+{
+	memcpy(&(&regs->r00)[0], args, 6 * sizeof(args[0]));
+}
+
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
@@ -45,6 +59,13 @@ static inline long syscall_get_return_value(struct task_struct *task,
 	return regs->r00;
 }
 
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->r00 = (long) error ?: val;
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_HEXAGON;
diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index b58f587f0f0a..1c63a9d9a6d3 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -69,7 +69,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 	if (!ptdesc)
 		return NULL;
 
-	if (!pagetable_pmd_ctor(ptdesc)) {
+	if (!pagetable_pmd_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index da346733a1da..a3f17914dbab 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -255,7 +255,6 @@ static inline void pmd_clear(pmd_t *pmdp)
 
 #define pmd_page_vaddr(pmd)	pmd_val(pmd)
 
-extern pmd_t mk_pmd(struct page *page, pgprot_t prot);
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd);
 
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
@@ -426,12 +425,6 @@ static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 	return false;
 }
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
diff --git a/arch/loongarch/include/asm/syscall.h b/arch/loongarch/include/asm/syscall.h
index e286dc58476e..81d2733f7b94 100644
--- a/arch/loongarch/include/asm/syscall.h
+++ b/arch/loongarch/include/asm/syscall.h
@@ -26,6 +26,13 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return regs->regs[11];
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->regs[11] = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -61,6 +68,14 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	memcpy(&args[1], &regs->regs[5], 5 * sizeof(long));
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned long *args)
+{
+	regs->orig_a0 = args[0];
+	memcpy(&regs->regs[5], &args[1], 5 * sizeof(long));
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_LOONGARCH64;
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 22a94bb3e6e8..352d9b2e02ab 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -135,15 +135,6 @@ void kernel_pte_init(void *addr)
 	} while (p != end);
 }
 
-pmd_t mk_pmd(struct page *page, pgprot_t prot)
-{
-	pmd_t pmd;
-
-	pmd_val(pmd) = (page_to_pfn(page) << PFN_PTE_SHIFT) | pgprot_val(prot);
-
-	return pmd;
-}
-
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index 4c648b51e7fd..fc5454d37da3 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -7,7 +7,7 @@
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	pagetable_free(virt_to_ptdesc(pte));
+	pagetable_dtor_free(virt_to_ptdesc(pte));
 }
 
 extern const char bad_pmd_string[];
@@ -19,6 +19,10 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 
 	if (!ptdesc)
 		return NULL;
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
+	}
 
 	return ptdesc_address(ptdesc);
 }
@@ -48,7 +52,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
 
 	if (!ptdesc)
 		return NULL;
-	if (!pagetable_pte_ctor(ptdesc)) {
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h
index 48f87a8a8832..f5c596b211d4 100644
--- a/arch/m68k/include/asm/mcf_pgtable.h
+++ b/arch/m68k/include/asm/mcf_pgtable.h
@@ -96,12 +96,6 @@
 
 #define pmd_pgtable(pmd) pfn_to_virt(pmd_val(pmd) >> PAGE_SHIFT)
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte_val(pte) = (pte_val(pte) & CF_PAGE_CHG_MASK) | pgprot_val(newprot);
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 5abe7da8ac5a..1091fb0affbe 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -15,7 +15,7 @@ enum m68k_table_types {
 };
 
 extern void init_pointer_table(void *table, int type);
-extern void *get_pointer_table(int type);
+extern void *get_pointer_table(struct mm_struct *mm, int type);
 extern int free_pointer_table(void *table, int type);
 
 /*
@@ -26,7 +26,7 @@ extern int free_pointer_table(void *table, int type);
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
-	return get_pointer_table(TABLE_PTE);
+	return get_pointer_table(mm, TABLE_PTE);
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
@@ -36,7 +36,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
-	return get_pointer_table(TABLE_PTE);
+	return get_pointer_table(mm, TABLE_PTE);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable)
@@ -53,7 +53,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	return get_pointer_table(TABLE_PMD);
+	return get_pointer_table(mm, TABLE_PMD);
 }
 
 static inline int pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -75,7 +75,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return get_pointer_table(TABLE_PGD);
+	return get_pointer_table(mm, TABLE_PGD);
 }
 
 
diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h
index 9866c7acdabe..040ac3bad713 100644
--- a/arch/m68k/include/asm/motorola_pgtable.h
+++ b/arch/m68k/include/asm/motorola_pgtable.h
@@ -81,12 +81,6 @@ extern unsigned long mm_cachebits;
 
 #define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot);
diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h
index 30081aee8164..73745dc0ec0e 100644
--- a/arch/m68k/include/asm/sun3_pgtable.h
+++ b/arch/m68k/include/asm/sun3_pgtable.h
@@ -76,12 +76,6 @@
 
 #ifndef __ASSEMBLY__
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte_val(pte) = (pte_val(pte) & SUN3_PAGE_CHG_MASK) | pgprot_val(newprot);
diff --git a/arch/m68k/include/asm/syscall.h b/arch/m68k/include/asm/syscall.h
index d1453e850cdd..bf84b160c2eb 100644
--- a/arch/m68k/include/asm/syscall.h
+++ b/arch/m68k/include/asm/syscall.h
@@ -14,6 +14,13 @@ static inline int syscall_get_nr(struct task_struct *task,
 	return regs->orig_d0;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->orig_d0 = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 73651e093c4d..6ab3ef39ba7a 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -139,7 +139,7 @@ void __init init_pointer_table(void *table, int type)
 	return;
 }
 
-void *get_pointer_table(int type)
+void *get_pointer_table(struct mm_struct *mm, int type)
 {
 	ptable_desc *dp = ptable_list[type].next;
 	unsigned int mask = list_empty(&ptable_list[type]) ? 0 : PD_MARKBITS(dp);
@@ -164,10 +164,10 @@ void *get_pointer_table(int type)
 			 * m68k doesn't have SPLIT_PTE_PTLOCKS for not having
 			 * SMP.
 			 */
-			pagetable_pte_ctor(virt_to_ptdesc(page));
+			pagetable_pte_ctor(mm, virt_to_ptdesc(page));
 			break;
 		case TABLE_PMD:
-			pagetable_pmd_ctor(virt_to_ptdesc(page));
+			pagetable_pmd_ctor(mm, virt_to_ptdesc(page));
 			break;
 		case TABLE_PGD:
 			pagetable_pgd_ctor(virt_to_ptdesc(page));
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index e4ea2ec3642f..b1bb2c65dd04 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -285,14 +285,6 @@ static inline pte_t mk_pte_phys(phys_addr_t physpage, pgprot_t pgprot)
 	return pte;
 }
 
-#define mk_pte(page, pgprot) \
-({									   \
-	pte_t pte;							   \
-	pte_val(pte) = (((page - mem_map) << PAGE_SHIFT) + memory_start) |  \
-			pgprot_val(pgprot);				   \
-	pte;								   \
-})
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot);
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 5eb3f624cc59..b5b6b91fae3e 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -14,6 +14,13 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return regs->r12;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->r12 = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 9f73265aad4e..e96dd1b7aba4 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -245,7 +245,7 @@ unsigned long iopa(unsigned long addr)
 __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
 	if (mem_init_done)
-		return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		return __pte_alloc_one_kernel(mm);
 	else
 		return memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE,
 					      MEMBLOCK_LOW_LIMIT,
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index bbca420c96d3..942af87f1cdd 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -62,7 +62,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 	if (!ptdesc)
 		return NULL;
 
-	if (!pagetable_pmd_ctor(ptdesc)) {
+	if (!pagetable_pmd_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index c29a551eb0ca..4852b005a72d 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -504,12 +504,6 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	return true;
 }
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
 #if defined(CONFIG_XPA)
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
@@ -719,9 +713,6 @@ static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
 
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
-/* Extern to avoid header file madness */
-extern pmd_t mk_pmd(struct page *page, pgprot_t prot);
-
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
 	pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) |
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 056aa1b713e2..d19e67e2aa6a 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -41,6 +41,21 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return task_thread_info(task)->syscall;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	/*
+	 * New syscall number has to be assigned to regs[2] because
+	 * it is loaded from there unconditionally after return from
+	 * syscall_trace_enter() invocation.
+	 *
+	 * Consequently, if the syscall was indirect and nr != __NR_syscall,
+	 * then after this assignment the syscall will cease to be indirect.
+	 */
+	task_thread_info(task)->syscall = regs->regs[2] = nr;
+}
+
 static inline void mips_syscall_update_nr(struct task_struct *task,
 					  struct pt_regs *regs)
 {
@@ -74,6 +89,23 @@ static inline void mips_get_syscall_arg(unsigned long *arg,
 #endif
 }
 
+static inline void mips_set_syscall_arg(unsigned long *arg,
+	struct task_struct *task, struct pt_regs *regs, unsigned int n)
+{
+#ifdef CONFIG_32BIT
+	switch (n) {
+	case 0: case 1: case 2: case 3:
+		regs->regs[4 + n] = *arg;
+		return;
+	case 4: case 5: case 6: case 7:
+		*arg = regs->args[n] = *arg;
+		return;
+	}
+#else
+	regs->regs[4 + n] = *arg;
+#endif
+}
+
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
@@ -120,6 +152,17 @@ static inline void syscall_get_arguments(struct task_struct *task,
 		mips_get_syscall_arg(args++, task, regs, i++);
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned long *args)
+{
+	unsigned int i = 0;
+	unsigned int n = 6;
+
+	while (n--)
+		mips_set_syscall_arg(args++, task, regs, i++);
+}
+
 extern const unsigned long sys_call_table[];
 extern const unsigned long sys32_call_table[];
 extern const unsigned long sysn32_call_table[];
diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c
index 84dd5136d53a..e2cf2166d5cb 100644
--- a/arch/mips/mm/pgtable-32.c
+++ b/arch/mips/mm/pgtable-32.c
@@ -31,16 +31,6 @@ void pgd_init(void *addr)
 }
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE)
-pmd_t mk_pmd(struct page *page, pgprot_t prot)
-{
-	pmd_t pmd;
-
-	pmd_val(pmd) = (page_to_pfn(page) << PFN_PTE_SHIFT) | pgprot_val(prot);
-
-	return pmd;
-}
-
-
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c
index 1e544827dea9..b24f865de357 100644
--- a/arch/mips/mm/pgtable-64.c
+++ b/arch/mips/mm/pgtable-64.c
@@ -90,15 +90,6 @@ void pud_init(void *addr)
 #endif
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-pmd_t mk_pmd(struct page *page, pgprot_t prot)
-{
-	pmd_t pmd;
-
-	pmd_val(pmd) = (page_to_pfn(page) << PFN_PTE_SHIFT) | pgprot_val(prot);
-
-	return pmd;
-}
-
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h
index e5d64c84aadf..e98578e27e26 100644
--- a/arch/nios2/include/asm/pgtable.h
+++ b/arch/nios2/include/asm/pgtable.h
@@ -221,12 +221,6 @@ static inline void pte_clear(struct mm_struct *mm,
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  */
-#define mk_pte(page, prot)	(pfn_pte(page_to_pfn(page), prot))
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
 #define pmd_phys(pmd)		virt_to_phys((void *)pmd_val(pmd))
 #define pmd_pfn(pmd)		(pmd_phys(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)		(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h
index fff52205fb65..8e3eb1d689bb 100644
--- a/arch/nios2/include/asm/syscall.h
+++ b/arch/nios2/include/asm/syscall.h
@@ -15,6 +15,11 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 	return regs->r2;
 }
 
+static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	regs->r2 = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				struct pt_regs *regs)
 {
@@ -58,6 +63,17 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	*args   = regs->r9;
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+	struct pt_regs *regs, const unsigned long *args)
+{
+	regs->r4 = *args++;
+	regs->r5 = *args++;
+	regs->r6 = *args++;
+	regs->r7 = *args++;
+	regs->r8 = *args++;
+	regs->r9 = *args;
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_NIOS2;
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 60c6ce7ff2dc..71bfb8c8c482 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -299,8 +299,6 @@ static inline pte_t __mk_pte(void *page, pgprot_t pgprot)
 	return pte;
 }
 
-#define mk_pte(page, pgprot) __mk_pte(page_address(page), (pgprot))
-
 #define mk_pte_phys(physpage, pgprot) \
 ({                                                                      \
 	pte_t __pte;                                                    \
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index 903ed882bdec..5e037d9659c5 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -26,6 +26,12 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 }
 
 static inline void
+syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	regs->orig_gpr11 = nr;
+}
+
+static inline void
 syscall_rollback(struct task_struct *task, struct pt_regs *regs)
 {
 	regs->gpr[11] = regs->orig_gpr11;
@@ -57,6 +63,13 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
 	memcpy(args, &regs->gpr[3], 6 * sizeof(args[0]));
 }
 
+static inline void
+syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+		      const unsigned long *args)
+{
+	memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_OPENRISC;
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index 8e63e86251ca..3b352f97fecb 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -36,7 +36,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm)
 	pte_t *pte;
 
 	if (likely(mem_init_done)) {
-		pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
+		pte = __pte_alloc_one_kernel(mm);
 	} else {
 		pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	}
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index 2ca74a56415c..3b84ee93edaa 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -39,7 +39,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 	ptdesc = pagetable_alloc(gfp, PMD_TABLE_ORDER);
 	if (!ptdesc)
 		return NULL;
-	if (!pagetable_pmd_ctor(ptdesc)) {
+	if (!pagetable_pmd_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index babf65751e81..e85963fefa63 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -338,10 +338,6 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ pte_val(pte) |= _PAGE_SPECIAL; re
 #endif
 
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
 #define __mk_pte(addr,pgprot) \
 ({									\
 	pte_t __pte;							\
@@ -351,8 +347,6 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ pte_val(pte) |= _PAGE_SPECIAL; re
 	__pte;								\
 })
 
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 {
 	pte_t pte;
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 00b127a5e09b..c11222798ab2 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -17,6 +17,13 @@ static inline long syscall_get_nr(struct task_struct *tsk,
 	return regs->gr[20];
 }
 
+static inline void syscall_set_nr(struct task_struct *tsk,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->gr[20] = nr;
+}
+
 static inline void syscall_get_arguments(struct task_struct *tsk,
 					 struct pt_regs *regs,
 					 unsigned long *args)
@@ -29,6 +36,18 @@ static inline void syscall_get_arguments(struct task_struct *tsk,
 	args[0] = regs->gr[26];
 }
 
+static inline void syscall_set_arguments(struct task_struct *tsk,
+					 struct pt_regs *regs,
+					 unsigned long *args)
+{
+	regs->gr[21] = args[5];
+	regs->gr[22] = args[4];
+	regs->gr[23] = args[3];
+	regs->gr[24] = args[2];
+	regs->gr[25] = args[1];
+	regs->gr[26] = args[0];
+}
+
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 6d98e6f08d4d..6ed93e290c2f 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1096,7 +1096,6 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
 extern pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot);
-extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
 extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
 extern pud_t pud_modify(pud_t pud, pgprot_t newprot);
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 2f72ad885332..93d77ad5a92f 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -53,9 +53,8 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 #define MAX_PTRS_PER_PGD PTRS_PER_PGD
 #endif
 
-/* Keep these as a macros to avoid include dependency mess */
+/* Keep this as a macro to avoid include dependency mess */
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
 
 static inline unsigned long pte_pfn(pte_t pte)
 {
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 3dd36c5e334a..4b3c52ed6e9d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -39,6 +39,16 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 		return -1;
 }
 
+static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->gpr[0] = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -110,6 +120,16 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	}
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
+
+	/* Also copy the first argument into orig_gpr3 */
+	regs->orig_gpr3 = args[0];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	if (is_tsk_32bit_task(task))
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 8f7d41ce2ca1..0db01e10a3f8 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -269,11 +269,6 @@ pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot)
 	return __pud_mkhuge(pud_set_protbits(__pud(pudv), pgprot));
 }
 
-pmd_t mk_pmd(struct page *page, pgprot_t pgprot)
-{
-	return pfn_pmd(page_to_pfn(page), pgprot);
-}
-
 pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
 	unsigned long pmdv;
@@ -422,7 +417,7 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm)
 	ptdesc = pagetable_alloc(gfp, 0);
 	if (!ptdesc)
 		return NULL;
-	if (!pagetable_pmd_ctor(ptdesc)) {
+	if (!pagetable_pmd_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index 713268ccb1a0..77e55eac16e4 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -56,19 +56,17 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel)
 {
 	void *ret = NULL;
 	struct ptdesc *ptdesc;
+	gfp_t gfp = PGALLOC_GFP;
 
-	if (!kernel) {
-		ptdesc = pagetable_alloc(PGALLOC_GFP | __GFP_ACCOUNT, 0);
-		if (!ptdesc)
-			return NULL;
-		if (!pagetable_pte_ctor(ptdesc)) {
-			pagetable_free(ptdesc);
-			return NULL;
-		}
-	} else {
-		ptdesc = pagetable_alloc(PGALLOC_GFP, 0);
-		if (!ptdesc)
-			return NULL;
+	if (!kernel)
+		gfp |= __GFP_ACCOUNT;
+
+	ptdesc = pagetable_alloc(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
 	}
 
 	atomic_set(&ptdesc->pt_frag_refcount, 1);
@@ -124,12 +122,10 @@ void pte_fragment_free(unsigned long *table, int kernel)
 
 	BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0);
 	if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) {
-		if (kernel)
-			pagetable_free(ptdesc);
-		else if (folio_test_clear_active(ptdesc_folio(ptdesc)))
-			call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
-		else
+		if (kernel || !folio_test_clear_active(ptdesc_folio(ptdesc)))
 			pte_free_now(&ptdesc->pt_rcu_head);
+		else
+			call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
 	}
 }
 
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 9dc239967b77..b2358d794855 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -298,6 +298,38 @@ static void populate_markers(void)
 #endif
 }
 
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
 static int ptdump_show(struct seq_file *m, void *v)
 {
 	struct pg_state st = {
@@ -305,7 +337,12 @@ static int ptdump_show(struct seq_file *m, void *v)
 		.marker = address_markers,
 		.level = -1,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = ptdump_range,
 		}
 	};
@@ -338,7 +375,12 @@ bool ptdump_check_wx(void)
 		.level = -1,
 		.check_wx = true,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = ptdump_range,
 		}
 	};
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 0897dd99ab8d..188fadc1c21f 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -262,8 +262,6 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 	return __page_val_to_pfn(pmd_val(pmd));
 }
 
-#define mk_pmd(page, prot)    pfn_pmd(page_to_pfn(page), prot)
-
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 428e48e5f57d..f19240fd018e 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -343,8 +343,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 	return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val);
 }
 
-#define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)
-
 #define pte_pgprot pte_pgprot
 static inline pgprot_t pte_pgprot(pte_t pte)
 {
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index eceabf59ae48..34313387f977 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -30,6 +30,13 @@ static inline int syscall_get_nr(struct task_struct *task,
 	return regs->a7;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->a7 = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -69,6 +76,18 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	args[5] = regs->a5;
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	regs->orig_a0 = args[0];
+	regs->a1 = args[1];
+	regs->a2 = args[2];
+	regs->a3 = args[3];
+	regs->a4 = args[4];
+	regs->a5 = args[5];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 #ifdef CONFIG_64BIT
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index ab475ec6ca42..8d0374d7ce8e 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -442,7 +442,12 @@ static phys_addr_t __meminit alloc_pte_late(uintptr_t va)
 {
 	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0);
 
-	BUG_ON(!ptdesc || !pagetable_pte_ctor(ptdesc));
+	/*
+	 * We do not know which mm the PTE page is associated to at this point.
+	 * Passing NULL to the ctor is the safe option, though it may result
+	 * in unnecessary work (e.g. initialising the ptlock for init_mm).
+	 */
+	BUG_ON(!ptdesc || !pagetable_pte_ctor(NULL, ptdesc));
 	return __pa((pte_t *)ptdesc_address(ptdesc));
 }
 
@@ -522,7 +527,8 @@ static phys_addr_t __meminit alloc_pmd_late(uintptr_t va)
 {
 	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0);
 
-	BUG_ON(!ptdesc || !pagetable_pmd_ctor(ptdesc));
+	/* See comment in alloc_pte_late() regarding NULL passed the ctor */
+	BUG_ON(!ptdesc || !pagetable_pmd_ctor(NULL, ptdesc));
 	return __pa((pmd_t *)ptdesc_address(ptdesc));
 }
 
@@ -584,11 +590,11 @@ static phys_addr_t __init alloc_pud_fixmap(uintptr_t va)
 
 static phys_addr_t __meminit alloc_pud_late(uintptr_t va)
 {
-	unsigned long vaddr;
+	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0);
 
-	vaddr = __get_free_page(GFP_KERNEL);
-	BUG_ON(!vaddr);
-	return __pa(vaddr);
+	BUG_ON(!ptdesc);
+	pagetable_pud_ctor(ptdesc);
+	return __pa((pud_t *)ptdesc_address(ptdesc));
 }
 
 static p4d_t *__init get_p4d_virt_early(phys_addr_t pa)
@@ -622,11 +628,11 @@ static phys_addr_t __init alloc_p4d_fixmap(uintptr_t va)
 
 static phys_addr_t __meminit alloc_p4d_late(uintptr_t va)
 {
-	unsigned long vaddr;
+	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0);
 
-	vaddr = __get_free_page(GFP_KERNEL);
-	BUG_ON(!vaddr);
-	return __pa(vaddr);
+	BUG_ON(!ptdesc);
+	pagetable_p4d_ctor(ptdesc);
+	return __pa((p4d_t *)ptdesc_address(ptdesc));
 }
 
 static void __meminit create_pud_mapping(pud_t *pudp, uintptr_t va, phys_addr_t pa, phys_addr_t sz,
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 9d5f657a251b..32922550a50a 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -318,6 +318,38 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr,
 	}
 }
 
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
 static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo)
 {
 	struct pg_state st = {
@@ -325,7 +357,12 @@ static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo)
 		.marker = pinfo->markers,
 		.level = -1,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = (struct ptdump_range[]) {
 				{pinfo->base_addr, pinfo->end},
 				{0, 0}
@@ -347,7 +384,12 @@ bool ptdump_check_wx(void)
 		.level = -1,
 		.check_wx = true,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = (struct ptdump_range[]) {
 				{KERN_VIRT_START, ULONG_MAX},
 				{0, 0}
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 005497ffebda..5345398df653 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -97,7 +97,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 	if (!table)
 		return NULL;
 	crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
-	if (!pagetable_pmd_ctor(virt_to_ptdesc(table))) {
+	if (!pagetable_pmd_ctor(mm, virt_to_ptdesc(table))) {
 		crst_table_free(mm, table);
 		return NULL;
 	}
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index f8a6b54986ec..1c661ac62ce8 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1448,16 +1448,6 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 	return pte_mkyoung(__pte);
 }
 
-static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
-{
-	unsigned long physpage = page_to_phys(page);
-	pte_t __pte = mk_pte_phys(physpage, pgprot);
-
-	if (pte_write(__pte) && PageDirty(page))
-		__pte = pte_mkdirty(__pte);
-	return __pte;
-}
-
 #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
 #define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D-1))
 #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
@@ -1879,7 +1869,6 @@ static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 #define pmdp_collapse_flush pmdp_collapse_flush
 
 #define pfn_pmd(pfn, pgprot)	mk_pmd_phys(((pfn) << PAGE_SHIFT), (pgprot))
-#define mk_pmd(page, pgprot)	pfn_pmd(page_to_pfn(page), (pgprot))
 
 static inline int pmd_trans_huge(pmd_t pmd)
 {
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 0213ec800b57..bd4cb00ccd5e 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -24,6 +24,18 @@ static inline long syscall_get_nr(struct task_struct *task,
 		(regs->int_code & 0xffff) : -1;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->int_code = (regs->int_code & ~0xffff) | (nr & 0xffff);
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -76,6 +88,15 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	args[0] = regs->orig_gpr2 & mask;
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	regs->orig_gpr2 = args[0];
+	for (int n = 1; n < 6; n++)
+		regs->gprs[2 + n] = args[n];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 #ifdef CONFIG_COMPAT
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index f20601995bb0..e5103e8e697d 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -40,7 +40,7 @@ static inline bool __tlb_remove_folio_pages(struct mmu_gather *tlb,
 /*
  * Release the page cache reference for a pte removed by
  * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
- * has already been freed, so just do free_page_and_swap_cache.
+ * has already been freed, so just do free_folio_and_swap_cache.
  *
  * s390 doesn't delay rmap removal.
  */
@@ -49,7 +49,7 @@ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
 {
 	VM_WARN_ON_ONCE(delay_rmap);
 
-	free_page_and_swap_cache(page);
+	free_folio_and_swap_cache(page_folio(page));
 	return false;
 }
 
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index d3e943752fa0..ac604b176660 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -147,11 +147,48 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
 	}
 }
 
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
 bool ptdump_check_wx(void)
 {
 	struct pg_state st = {
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = (struct ptdump_range[]) {
 				{.start = 0, .end = max_addr},
 				{.start = 0, .end = 0},
@@ -190,7 +227,12 @@ static int ptdump_show(struct seq_file *m, void *v)
 {
 	struct pg_state st = {
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = (struct ptdump_range[]) {
 				{.start = 0, .end = max_addr},
 				{.start = 0, .end = 0},
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index d177bea0bd73..abe1e58e8b45 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -144,7 +144,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	ptdesc = pagetable_alloc(GFP_KERNEL, 0);
 	if (!ptdesc)
 		return NULL;
-	if (!pagetable_pte_ctor(ptdesc)) {
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h
index f939f1215232..db2e48366e0d 100644
--- a/arch/sh/include/asm/pgtable_32.h
+++ b/arch/sh/include/asm/pgtable_32.h
@@ -380,14 +380,6 @@ PTE_BIT_FUNC(low, mkspecial, |= _PAGE_SPECIAL);
 
 #define pgprot_noncached	 pgprot_writecombine
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * extern pte_t mk_pte(struct page *page, pgprot_t pgprot)
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte.pte_low &= _PAGE_CHG_MASK;
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index d87738eebe30..7027d87d901d 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -15,6 +15,18 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return (regs->tra >= 0) ? regs->regs[3] : -1L;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->regs[3] = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -57,6 +69,18 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	args[0] = regs->regs[4];
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	regs->regs[1] = args[5];
+	regs->regs[0] = args[4];
+	regs->regs[7] = args[3];
+	regs->regs[6] = args[2];
+	regs->regs[5] = args[1];
+	regs->regs[4] = args[0];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	int arch = AUDIT_ARCH_SH;
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 62bcafe38b1f..1454ebe91539 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -255,7 +255,11 @@ static inline pte_t pte_mkyoung(pte_t pte)
 }
 
 #define PFN_PTE_SHIFT			(PAGE_SHIFT - 4)
-#define pfn_pte(pfn, prot)		mk_pte(pfn_to_page(pfn), prot)
+
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	return __pte((pfn << PFN_PTE_SHIFT) | pgprot_val(pgprot));
+}
 
 static inline unsigned long pte_pfn(pte_t pte)
 {
@@ -272,15 +276,6 @@ static inline unsigned long pte_pfn(pte_t pte)
 
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
-{
-	return __pte((page_to_pfn(page) << (PAGE_SHIFT-4)) | pgprot_val(pgprot));
-}
-
 static inline pte_t mk_pte_phys(unsigned long page, pgprot_t pgprot)
 {
 	return __pte(((page) >> 4) | pgprot_val(pgprot));
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dc28f2c4eee3..4af03e3c161b 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -225,7 +225,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 	BUILD_BUG_ON(_PAGE_SZBITS_4U != 0UL || _PAGE_SZBITS_4V != 0UL);
 	return __pte(paddr | pgprot_val(prot));
 }
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
@@ -234,7 +233,6 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 
 	return __pmd(pte_val(pte));
 }
-#define mk_pmd(page, pgprot)	pfn_pmd(page_to_pfn(page), (pgprot))
 #endif
 
 /* This one can be done with two shifts.  */
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 20c109ac8cc9..b0233924d323 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -25,6 +25,18 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return (syscall_p ? regs->u_regs[UREG_G1] : -1L);
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->u_regs[UREG_G1] = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -117,6 +129,16 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	}
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	unsigned int i;
+
+	for (i = 0; i < 6; i++)
+		regs->u_regs[UREG_I0 + i] = args[i];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 #if defined(CONFIG_SPARC64) && defined(CONFIG_COMPAT)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 760818950464..25ae4c897aae 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2878,33 +2878,27 @@ void __flush_tlb_all(void)
 			     : : "r" (pstate));
 }
 
-pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	pte_t *pte = NULL;
-
-	if (page)
-		pte = (pte_t *) page_address(page);
-
-	return pte;
-}
-
-pgtable_t pte_alloc_one(struct mm_struct *mm)
+static pte_t *__pte_alloc_one(struct mm_struct *mm)
 {
 	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL | __GFP_ZERO, 0);
 
 	if (!ptdesc)
 		return NULL;
-	if (!pagetable_pte_ctor(ptdesc)) {
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
 		pagetable_free(ptdesc);
 		return NULL;
 	}
 	return ptdesc_address(ptdesc);
 }
 
-void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
-	free_page((unsigned long)pte);
+	return __pte_alloc_one(mm);
+}
+
+pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+	return __pte_alloc_one(mm);
 }
 
 static void __pte_free(pgtable_t pte)
@@ -2915,6 +2909,11 @@ static void __pte_free(pgtable_t pte)
 	pagetable_free(ptdesc);
 }
 
+void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	__pte_free(pte);
+}
+
 void pte_free(struct mm_struct *mm, pgtable_t pte)
 {
 	__pte_free(pte);
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index dd32711022f5..f8fb4911d360 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -350,7 +350,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
 	page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
 	spin_lock(&mm->page_table_lock);
 	if (page_ref_inc_return(page) == 2 &&
-			!pagetable_pte_ctor(page_ptdesc(page))) {
+			!pagetable_pte_ctor(mm, page_ptdesc(page))) {
 		page_ref_dec(page);
 		ptep = NULL;
 	}
diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h
index ab0c8dd86564..14ec16f92ce4 100644
--- a/arch/um/include/asm/pgtable-2level.h
+++ b/arch/um/include/asm/pgtable-2level.h
@@ -37,7 +37,6 @@ static inline void pgd_mkuptodate(pgd_t pgd)	{ }
 #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
 
 #define pte_pfn(x) phys_to_pfn(pte_val(x))
-#define pfn_pte(pfn, prot) __pte(pfn_to_phys(pfn) | pgprot_val(prot))
 #define pfn_pmd(pfn, prot) __pmd(pfn_to_phys(pfn) | pgprot_val(prot))
 
 #endif
diff --git a/arch/um/include/asm/pgtable-4level.h b/arch/um/include/asm/pgtable-4level.h
index 0d279caee93c..7a271b7b83d2 100644
--- a/arch/um/include/asm/pgtable-4level.h
+++ b/arch/um/include/asm/pgtable-4level.h
@@ -102,15 +102,6 @@ static inline unsigned long pte_pfn(pte_t pte)
 	return phys_to_pfn(pte_val(pte));
 }
 
-static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
-{
-	pte_t pte;
-	phys_t phys = pfn_to_phys(page_nr);
-
-	pte_set_val(pte, phys, pgprot);
-	return pte;
-}
-
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
 	return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot));
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index 5601ca98e8a6..ca2a519d53ab 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -260,19 +260,17 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 	return !((pte_val(pte_a) ^ pte_val(pte_b)) & ~_PAGE_NEEDSYNC);
 }
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-
 #define __virt_to_page(virt) phys_to_page(__pa(virt))
 #define virt_to_page(addr) __virt_to_page((const unsigned long) addr)
 
-#define mk_pte(page, pgprot) \
-	({ pte_t pte;					\
-							\
-	pte_set_val(pte, page_to_phys(page), (pgprot));	\
-	pte;})
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	pte_t pte;
+
+	pte_set_val(pte, pfn_to_phys(pfn), pgprot);
+
+	return pte;
+}
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h
index 172b74143c4b..bcd73bcfe577 100644
--- a/arch/um/include/asm/syscall-generic.h
+++ b/arch/um/include/asm/syscall-generic.h
@@ -21,6 +21,11 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 	return PT_REGS_SYSCALL_NR(regs);
 }
 
+static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	PT_REGS_SYSCALL_NR(regs) = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -62,6 +67,20 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	*args   = UPT_SYSCALL_ARG6(r);
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	struct uml_pt_regs *r = &regs->regs;
+
+	UPT_SYSCALL_ARG1(r) = *args++;
+	UPT_SYSCALL_ARG2(r) = *args++;
+	UPT_SYSCALL_ARG3(r) = *args++;
+	UPT_SYSCALL_ARG4(r) = *args++;
+	UPT_SYSCALL_ARG5(r) = *args++;
+	UPT_SYSCALL_ARG6(r) = *args;
+}
+
 /* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
 
 #endif	/* __UM_SYSCALL_GENERIC_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ae1654280c40..340e5468980e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2005,6 +2005,9 @@ config ARCH_SUPPORTS_KEXEC_BZIMAGE_VERIFY_SIG
 config ARCH_SUPPORTS_KEXEC_JUMP
 	def_bool y
 
+config ARCH_SUPPORTS_KEXEC_HANDOVER
+	def_bool X86_64
+
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool X86_64 || (X86_32 && HIGHMEM)
 
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index f03d59ea6e40..3b0948ad449f 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -760,6 +760,49 @@ static void process_e820_entries(unsigned long minimum,
 	}
 }
 
+/*
+ * If KHO is active, only process its scratch areas to ensure we are not
+ * stepping onto preserved memory.
+ */
+static bool process_kho_entries(unsigned long minimum, unsigned long image_size)
+{
+	struct kho_scratch *kho_scratch;
+	struct setup_data *ptr;
+	struct kho_data *kho;
+	int i, nr_areas = 0;
+
+	if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+		return false;
+
+	ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data;
+	while (ptr) {
+		if (ptr->type == SETUP_KEXEC_KHO) {
+			kho = (struct kho_data *)(unsigned long)ptr->data;
+			kho_scratch = (void *)(unsigned long)kho->scratch_addr;
+			nr_areas = kho->scratch_size / sizeof(*kho_scratch);
+			break;
+		}
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
+	if (!nr_areas)
+		return false;
+
+	for (i = 0; i < nr_areas; i++) {
+		struct kho_scratch *area = &kho_scratch[i];
+		struct mem_vector region = {
+			.start = area->addr,
+			.size = area->size,
+		};
+
+		if (process_mem_region(&region, minimum, image_size))
+			break;
+	}
+
+	return true;
+}
+
 static unsigned long find_random_phys_addr(unsigned long minimum,
 					   unsigned long image_size)
 {
@@ -775,7 +818,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
 		return 0;
 	}
 
-	if (!process_efi_entries(minimum, image_size))
+	/*
+	 * During kexec handover only process KHO scratch areas that are known
+	 * not to contain any data that must be preserved.
+	 */
+	if (!process_kho_entries(minimum, image_size) &&
+	    !process_efi_entries(minimum, image_size))
 		process_e820_entries(minimum, image_size);
 
 	phys_addr = slots_fetch_random();
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5ddba366d3b4..774430c3abff 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -777,6 +777,9 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
 	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	/* This bit combination is used to mark shadow stacks */
+	WARN_ON_ONCE((pgprot_val(pgprot) & (_PAGE_DIRTY | _PAGE_RW)) ==
+			_PAGE_DIRTY);
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PTE_PFN_MASK;
 	return __pte(pfn | check_pgprot(pgprot));
@@ -1073,22 +1076,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
  */
 #define pmd_page(pmd)	pfn_to_page(pmd_pfn(pmd))
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * (Currently stuck as a macro because of indirect forward reference
- * to linux/mm.h:page_to_nid())
- */
-#define mk_pte(page, pgprot)						  \
-({									  \
-	pgprot_t __pgprot = pgprot;					  \
-									  \
-	WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \
-		    _PAGE_DIRTY);					  \
-	pfn_pte(page_to_pfn(page), __pgprot);				  \
-})
-
 static inline int pmd_bad(pmd_t pmd)
 {
 	return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) !=
@@ -1353,8 +1340,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 
 #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
 
-#define mk_pmd(page, pgprot)   pfn_pmd(page_to_pfn(page), (pgprot))
-
 #define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
 extern int pmdp_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp,
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 6324f4c6c545..692af46603a1 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -68,6 +68,8 @@ extern void x86_ce4100_early_setup(void);
 static inline void x86_ce4100_early_setup(void) { }
 #endif
 
+#include <linux/kexec_handover.h>
+
 #ifndef _SETUP
 
 #include <asm/espfix.h>
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 7c488ff0c764..c10dbb74cd00 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -38,6 +38,13 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 	return regs->orig_ax;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->orig_ax = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -90,6 +97,18 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	args[5] = regs->bp;
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	regs->bx = args[0];
+	regs->cx = args[1];
+	regs->dx = args[2];
+	regs->si = args[3];
+	regs->di = args[4];
+	regs->bp = args[5];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_I386;
@@ -121,6 +140,30 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	}
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+	if (task->thread_info.status & TS_COMPAT) {
+		regs->bx = *args++;
+		regs->cx = *args++;
+		regs->dx = *args++;
+		regs->si = *args++;
+		regs->di = *args++;
+		regs->bp = *args;
+	} else
+# endif
+	{
+		regs->di = *args++;
+		regs->si = *args++;
+		regs->dx = *args++;
+		regs->r10 = *args++;
+		regs->r8 = *args++;
+		regs->r9 = *args;
+	}
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
index 50c45ead4e7c..2671c4e1b3a0 100644
--- a/arch/x86/include/uapi/asm/setup_data.h
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -13,7 +13,8 @@
 #define SETUP_CC_BLOB			7
 #define SETUP_IMA			8
 #define SETUP_RNG_SEED			9
-#define SETUP_ENUM_MAX			SETUP_RNG_SEED
+#define SETUP_KEXEC_KHO			10
+#define SETUP_ENUM_MAX			SETUP_KEXEC_KHO
 
 #define SETUP_INDIRECT			(1<<31)
 #define SETUP_TYPE_MAX			(SETUP_ENUM_MAX | SETUP_INDIRECT)
@@ -78,6 +79,16 @@ struct ima_setup_data {
 	__u64 size;
 } __attribute__((packed));
 
+/*
+ * Locations of kexec handover metadata
+ */
+struct kho_data {
+	__u64 fdt_addr;
+	__u64 fdt_size;
+	__u64 scratch_addr;
+	__u64 scratch_size;
+} __attribute__((packed));
+
 #endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 9920122018a0..c3acbd26408b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1300,6 +1300,24 @@ void __init e820__memblock_setup(void)
 	}
 
 	/*
+	 * At this point memblock is only allowed to allocate from memory
+	 * below 1M (aka ISA_END_ADDRESS) up until direct map is completely set
+	 * up in init_mem_mapping().
+	 *
+	 * KHO kernels are special and use only scratch memory for memblock
+	 * allocations, but memory below 1M is ignored by kernel after early
+	 * boot and cannot be naturally marked as scratch.
+	 *
+	 * To allow allocation of the real-mode trampoline and a few (if any)
+	 * other very early allocations from below 1M forcibly mark the memory
+	 * below 1M as scratch.
+	 *
+	 * After real mode trampoline is allocated, we clear that scratch
+	 * marking.
+	 */
+	memblock_mark_kho_scratch(0, SZ_1M);
+
+	/*
 	 * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
 	 * to even less without it.
 	 * Discard memory after max_pfn - the actual limit detected at runtime.
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 68530fad05f7..dad174e3bed0 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -233,6 +233,32 @@ setup_ima_state(const struct kimage *image, struct boot_params *params,
 #endif /* CONFIG_IMA_KEXEC */
 }
 
+static void setup_kho(const struct kimage *image, struct boot_params *params,
+		      unsigned long params_load_addr,
+		      unsigned int setup_data_offset)
+{
+	struct setup_data *sd = (void *)params + setup_data_offset;
+	struct kho_data *kho = (void *)sd + sizeof(*sd);
+
+	if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+		return;
+
+	sd->type = SETUP_KEXEC_KHO;
+	sd->len = sizeof(struct kho_data);
+
+	/* Only add if we have all KHO images in place */
+	if (!image->kho.fdt || !image->kho.scratch)
+		return;
+
+	/* Add setup data */
+	kho->fdt_addr = image->kho.fdt;
+	kho->fdt_size = PAGE_SIZE;
+	kho->scratch_addr = image->kho.scratch->mem;
+	kho->scratch_size = image->kho.scratch->bufsz;
+	sd->next = params->hdr.setup_data;
+	params->hdr.setup_data = params_load_addr + setup_data_offset;
+}
+
 static int
 setup_boot_parameters(struct kimage *image, struct boot_params *params,
 		      unsigned long params_load_addr,
@@ -312,6 +338,13 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 				     sizeof(struct ima_setup_data);
 	}
 
+	if (IS_ENABLED(CONFIG_KEXEC_HANDOVER)) {
+		/* Setup space to store preservation metadata */
+		setup_kho(image, params, params_load_addr, setup_data_offset);
+		setup_data_offset += sizeof(struct setup_data) +
+				     sizeof(struct kho_data);
+	}
+
 	/* Setup RNG seed */
 	setup_rng_seed(params, params_load_addr, setup_data_offset);
 
@@ -479,6 +512,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		kbuf.bufsz += sizeof(struct setup_data) +
 			      sizeof(struct ima_setup_data);
 
+	if (IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+		kbuf.bufsz += sizeof(struct setup_data) +
+			      sizeof(struct kho_data);
+
 	params = kzalloc(kbuf.bufsz, GFP_KERNEL);
 	if (!params)
 		return ERR_PTR(-ENOMEM);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 7d9ed79a93c0..fb27be697128 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -282,8 +282,8 @@ static void __init cleanup_highmap(void)
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		memblock_reserve(__pa_symbol(_brk_start),
-				 _brk_end - _brk_start);
+		memblock_reserve_kern(__pa_symbol(_brk_start),
+				      _brk_end - _brk_start);
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -356,7 +356,7 @@ static void __init early_reserve_initrd(void)
 	    !ramdisk_image || !ramdisk_size)
 		return;		/* No initrd provided by bootloader */
 
-	memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
+	memblock_reserve_kern(ramdisk_image, ramdisk_end - ramdisk_image);
 }
 
 static void __init reserve_initrd(void)
@@ -409,7 +409,7 @@ static void __init add_early_ima_buffer(u64 phys_addr)
 	}
 
 	if (data->size) {
-		memblock_reserve(data->addr, data->size);
+		memblock_reserve_kern(data->addr, data->size);
 		ima_kexec_buffer_phys = data->addr;
 		ima_kexec_buffer_size = data->size;
 	}
@@ -447,6 +447,29 @@ int __init ima_get_kexec_buffer(void **addr, size_t *size)
 }
 #endif
 
+static void __init add_kho(u64 phys_addr, u32 data_len)
+{
+	struct kho_data *kho;
+	u64 addr = phys_addr + sizeof(struct setup_data);
+	u64 size = data_len - sizeof(struct setup_data);
+
+	if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) {
+		pr_warn("Passed KHO data, but CONFIG_KEXEC_HANDOVER not set. Ignoring.\n");
+		return;
+	}
+
+	kho = early_memremap(addr, size);
+	if (!kho) {
+		pr_warn("setup: failed to memremap kho data (0x%llx, 0x%llx)\n",
+			addr, size);
+		return;
+	}
+
+	kho_populate(kho->fdt_addr, kho->fdt_size, kho->scratch_addr, kho->scratch_size);
+
+	early_memunmap(kho, size);
+}
+
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
@@ -475,6 +498,9 @@ static void __init parse_setup_data(void)
 		case SETUP_IMA:
 			add_early_ima_buffer(pa_data);
 			break;
+		case SETUP_KEXEC_KHO:
+			add_kho(pa_data, data_len);
+			break;
 		case SETUP_RNG_SEED:
 			data = early_memremap(pa_data, data_len);
 			add_bootloader_randomness(data->data, data->len);
@@ -549,7 +575,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 		len = sizeof(*data);
 		pa_next = data->next;
 
-		memblock_reserve(pa_data, sizeof(*data) + data->len);
+		memblock_reserve_kern(pa_data, sizeof(*data) + data->len);
 
 		if (data->type == SETUP_INDIRECT) {
 			len += data->len;
@@ -563,7 +589,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 			indirect = (struct setup_indirect *)data->data;
 
 			if (indirect->type != SETUP_INDIRECT)
-				memblock_reserve(indirect->addr, indirect->len);
+				memblock_reserve_kern(indirect->addr, indirect->len);
 		}
 
 		pa_data = pa_next;
@@ -766,8 +792,8 @@ static void __init early_reserve_memory(void)
 	 * __end_of_kernel_reserve symbol must be explicitly reserved with a
 	 * separate memblock_reserve() or they will be discarded.
 	 */
-	memblock_reserve(__pa_symbol(_text),
-			 (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
+	memblock_reserve_kern(__pa_symbol(_text),
+			      (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
 
 	/*
 	 * The first 4Kb of memory is a BIOS owned area, but generally it is
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 89079ea73e65..a4700ef6eb64 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -266,6 +266,32 @@ static void effective_prot(struct ptdump_state *pt_st, int level, u64 val)
 	st->prot_levels[level] = effective;
 }
 
+static void effective_prot_pte(struct ptdump_state *st, pte_t pte)
+{
+	effective_prot(st, 4, pte_val(pte));
+}
+
+static void effective_prot_pmd(struct ptdump_state *st, pmd_t pmd)
+{
+	effective_prot(st, 3, pmd_val(pmd));
+}
+
+static void effective_prot_pud(struct ptdump_state *st, pud_t pud)
+{
+	effective_prot(st, 2, pud_val(pud));
+}
+
+static void effective_prot_p4d(struct ptdump_state *st, p4d_t p4d)
+{
+	effective_prot(st, 1, p4d_val(p4d));
+}
+
+static void effective_prot_pgd(struct ptdump_state *st, pgd_t pgd)
+{
+	effective_prot(st, 0, pgd_val(pgd));
+}
+
+
 /*
  * This function gets called on a break in a continuous series
  * of PTE entries; the next one is different so we need to
@@ -362,6 +388,38 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
 	}
 }
 
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
 bool ptdump_walk_pgd_level_core(struct seq_file *m,
 				struct mm_struct *mm, pgd_t *pgd,
 				bool checkwx, bool dmesg)
@@ -378,8 +436,17 @@ bool ptdump_walk_pgd_level_core(struct seq_file *m,
 
 	struct pg_state st = {
 		.ptdump = {
-			.note_page	= note_page,
-			.effective_prot = effective_prot,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
+			.effective_prot_pte = effective_prot_pte,
+			.effective_prot_pmd = effective_prot_pmd,
+			.effective_prot_pud = effective_prot_pud,
+			.effective_prot_p4d = effective_prot_p4d,
+			.effective_prot_pgd = effective_prot_pgd,
 			.range		= ptdump_ranges
 		},
 		.level = -1,
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 66330fe4e18c..ee66fae9ebcc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1467,16 +1467,21 @@ static unsigned long probe_memory_block_size(void)
 	}
 
 	/*
-	 * Use max block size to minimize overhead on bare metal, where
-	 * alignment for memory hotplug isn't a concern.
+	 * When hotplug alignment is not a concern, maximize blocksize
+	 * to minimize overhead. Otherwise, align to the lesser of advice
+	 * alignment and end of memory alignment.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+	bz = memory_block_advised_max_size();
+	if (!bz) {
 		bz = MAX_BLOCK_SIZE;
-		goto done;
+		if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+			goto done;
+	} else {
+		bz = max(min(bz, MAX_BLOCK_SIZE), MIN_MEMORY_BLOCK_SIZE);
 	}
 
 	/* Find the largest allowed block size that aligns to memory end */
-	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+	for (; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
 		if (IS_ALIGNED(boot_mem_end, bz))
 			break;
 	}
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 331e101bf801..12c8180ca1ba 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -71,7 +71,7 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 static unsigned int __ioremap_check_ram(struct resource *res)
 {
 	unsigned long start_pfn, stop_pfn;
-	unsigned long i;
+	unsigned long pfn;
 
 	if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM)
 		return 0;
@@ -79,9 +79,8 @@ static unsigned int __ioremap_check_ram(struct resource *res)
 	start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	stop_pfn = (res->end + 1) >> PAGE_SHIFT;
 	if (stop_pfn > start_pfn) {
-		for (i = 0; i < (stop_pfn - start_pfn); ++i)
-			if (pfn_valid(start_pfn + i) &&
-			    !PageReserved(pfn_to_page(start_pfn + i)))
+		for_each_valid_pfn(pfn, start_pfn, stop_pfn)
+			if (!PageReserved(pfn_to_page(pfn)))
 				return IORES_MAP_SYSTEM_RAM;
 	}
 
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index c97b527c66fe..2e7923844afe 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -775,6 +775,12 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 	return vma_prot;
 }
 
+static inline void pgprot_set_cachemode(pgprot_t *prot, enum page_cache_mode pcm)
+{
+	*prot = __pgprot((pgprot_val(*prot) & ~_PAGE_CACHE_MASK) |
+			 cachemode2protval(pcm));
+}
+
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
@@ -789,8 +795,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	if (file->f_flags & O_DSYNC)
 		pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
-	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
-			     cachemode2protval(pcm));
+	pgprot_set_cachemode(vma_prot, pcm);
 	return 1;
 }
 
@@ -831,8 +836,7 @@ int memtype_kernel_map_sync(u64 base, unsigned long size,
  * Reserved non RAM regions only and after successful memtype_reserve,
  * this func also keeps identity mapping (if any) in sync with this new prot.
  */
-static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
-				int strict_prot)
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot)
 {
 	int is_ram = 0;
 	int ret;
@@ -858,9 +862,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 				(unsigned long long)paddr,
 				(unsigned long long)(paddr + size - 1),
 				cattr_name(pcm));
-			*vma_prot = __pgprot((pgprot_val(*vma_prot) &
-					     (~_PAGE_CACHE_MASK)) |
-					     cachemode2protval(pcm));
+			pgprot_set_cachemode(vma_prot, pcm);
 		}
 		return 0;
 	}
@@ -870,8 +872,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		return ret;
 
 	if (pcm != want_pcm) {
-		if (strict_prot ||
-		    !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
+		if (!is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
 			memtype_free(paddr, paddr + size);
 			pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
 			       current->comm, current->pid,
@@ -881,13 +882,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 			       cattr_name(pcm));
 			return -EINVAL;
 		}
-		/*
-		 * We allow returning different type than the one requested in
-		 * non strict case.
-		 */
-		*vma_prot = __pgprot((pgprot_val(*vma_prot) &
-				      (~_PAGE_CACHE_MASK)) |
-				     cachemode2protval(pcm));
+		pgprot_set_cachemode(vma_prot, pcm);
 	}
 
 	if (memtype_kernel_map_sync(paddr, size, pcm) < 0) {
@@ -910,124 +905,14 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 		memtype_free(paddr, paddr + size);
 }
 
-static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
-		resource_size_t *phys)
-{
-	struct follow_pfnmap_args args = { .vma = vma, .address = vma->vm_start };
-
-	if (follow_pfnmap_start(&args))
-		return -EINVAL;
-
-	/* Never return PFNs of anon folios in COW mappings. */
-	if (!args.special) {
-		follow_pfnmap_end(&args);
-		return -EINVAL;
-	}
-
-	*prot = pgprot_val(args.pgprot);
-	*phys = (resource_size_t)args.pfn << PAGE_SHIFT;
-	follow_pfnmap_end(&args);
-	return 0;
-}
-
-static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
-		pgprot_t *pgprot)
-{
-	unsigned long prot;
-
-	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
-
-	/*
-	 * We need the starting PFN and cachemode used for track_pfn_remap()
-	 * that covered the whole VMA. For most mappings, we can obtain that
-	 * information from the page tables. For COW mappings, we might now
-	 * suddenly have anon folios mapped and follow_phys() will fail.
-	 *
-	 * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
-	 * detect the PFN. If we need the cachemode as well, we're out of luck
-	 * for now and have to fail fork().
-	 */
-	if (!follow_phys(vma, &prot, paddr)) {
-		if (pgprot)
-			*pgprot = __pgprot(prot);
-		return 0;
-	}
-	if (is_cow_mapping(vma->vm_flags)) {
-		if (pgprot)
-			return -EINVAL;
-		*paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
-		return 0;
-	}
-	WARN_ON_ONCE(1);
-	return -EINVAL;
-}
-
-int track_pfn_copy(struct vm_area_struct *dst_vma,
-		struct vm_area_struct *src_vma, unsigned long *pfn)
-{
-	const unsigned long vma_size = src_vma->vm_end - src_vma->vm_start;
-	resource_size_t paddr;
-	pgprot_t pgprot;
-	int rc;
-
-	if (!(src_vma->vm_flags & VM_PAT))
-		return 0;
-
-	/*
-	 * Duplicate the PAT information for the dst VMA based on the src
-	 * VMA.
-	 */
-	if (get_pat_info(src_vma, &paddr, &pgprot))
-		return -EINVAL;
-	rc = reserve_pfn_range(paddr, vma_size, &pgprot, 1);
-	if (rc)
-		return rc;
-
-	/* Reservation for the destination VMA succeeded. */
-	vm_flags_set(dst_vma, VM_PAT);
-	*pfn = PHYS_PFN(paddr);
-	return 0;
-}
-
-void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn)
-{
-	untrack_pfn(dst_vma, pfn, dst_vma->vm_end - dst_vma->vm_start, true);
-	/*
-	 * Reservation was freed, any copied page tables will get cleaned
-	 * up later, but without getting PAT involved again.
-	 */
-}
-
-/*
- * prot is passed in as a parameter for the new mapping. If the vma has
- * a linear pfn mapping for the entire range, or no vma is provided,
- * reserve the entire pfn + size range with single reserve_pfn_range
- * call.
- */
-int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
-		    unsigned long pfn, unsigned long addr, unsigned long size)
+int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot)
 {
 	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	enum page_cache_mode pcm;
 
-	/* reserve the whole chunk starting from paddr */
-	if (!vma || (addr == vma->vm_start
-				&& size == (vma->vm_end - vma->vm_start))) {
-		int ret;
-
-		ret = reserve_pfn_range(paddr, size, prot, 0);
-		if (ret == 0 && vma)
-			vm_flags_set(vma, VM_PAT);
-		return ret;
-	}
-
 	if (!pat_enabled())
 		return 0;
 
-	/*
-	 * For anything smaller than the vma size we set prot based on the
-	 * lookup.
-	 */
 	pcm = lookup_memtype(paddr);
 
 	/* Check memtype for the remaining pages */
@@ -1038,70 +923,35 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			return -EINVAL;
 	}
 
-	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
-			 cachemode2protval(pcm));
-
+	pgprot_set_cachemode(prot, pcm);
 	return 0;
 }
 
-void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
+int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot)
 {
-	enum page_cache_mode pcm;
+	const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
 
-	if (!pat_enabled())
-		return;
-
-	/* Set prot based on lookup */
-	pcm = lookup_memtype(pfn_t_to_phys(pfn));
-	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
-			 cachemode2protval(pcm));
+	return reserve_pfn_range(paddr, size, prot);
 }
 
-/*
- * untrack_pfn is called while unmapping a pfnmap for a region.
- * untrack can be called for a specific region indicated by pfn and size or
- * can be for the entire vma (in which case pfn, size are zero).
- */
-void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
-		 unsigned long size, bool mm_wr_locked)
+void pfnmap_untrack(unsigned long pfn, unsigned long size)
 {
-	resource_size_t paddr;
-
-	if (vma && !(vma->vm_flags & VM_PAT))
-		return;
+	const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
 
-	/* free the chunk starting from pfn or the whole chunk */
-	paddr = (resource_size_t)pfn << PAGE_SHIFT;
-	if (!paddr && !size) {
-		if (get_pat_info(vma, &paddr, NULL))
-			return;
-		size = vma->vm_end - vma->vm_start;
-	}
 	free_pfn_range(paddr, size);
-	if (vma) {
-		if (mm_wr_locked)
-			vm_flags_clear(vma, VM_PAT);
-		else
-			__vm_flags_mod(vma, 0, VM_PAT);
-	}
-}
-
-void untrack_pfn_clear(struct vm_area_struct *vma)
-{
-	vm_flags_clear(vma, VM_PAT);
 }
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
-	return __pgprot(pgprot_val(prot) |
-				cachemode2protval(_PAGE_CACHE_MODE_WC));
+	pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WC);
+	return prot;
 }
 EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
 pgprot_t pgprot_writethrough(pgprot_t prot)
 {
-	return __pgprot(pgprot_val(prot) |
-				cachemode2protval(_PAGE_CACHE_MODE_WT));
+	pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WT);
+	return prot;
 }
 EXPORT_SYMBOL_GPL(pgprot_writethrough);
 
diff --git a/arch/x86/mm/pat/memtype_interval.c b/arch/x86/mm/pat/memtype_interval.c
index 645613d59942..e5844ed1311e 100644
--- a/arch/x86/mm/pat/memtype_interval.c
+++ b/arch/x86/mm/pat/memtype_interval.c
@@ -49,32 +49,6 @@ INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end,
 
 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 *entry_match;
-
-	entry_match = interval_iter_first(&memtype_rbroot, start, end-1);
-
-	while (entry_match != NULL && entry_match->start < end) {
-		if ((match_type == MEMTYPE_EXACT_MATCH) &&
-		    (entry_match->start == start) && (entry_match->end == end))
-			return entry_match;
-
-		if ((match_type == MEMTYPE_END_MATCH) &&
-		    (entry_match->start < start) && (entry_match->end == end))
-			return entry_match;
-
-		entry_match = interval_iter_next(entry_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)
@@ -130,35 +104,16 @@ int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_ty
 
 struct memtype *memtype_erase(u64 start, u64 end)
 {
-	struct memtype *entry_old;
-
-	/*
-	 * 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.
-	 */
-	entry_old = memtype_match(start, end, MEMTYPE_EXACT_MATCH);
-	if (!entry_old) {
-		entry_old = memtype_match(start, end, MEMTYPE_END_MATCH);
-		if (!entry_old)
-			return ERR_PTR(-EINVAL);
+	struct memtype *entry = interval_iter_first(&memtype_rbroot, start, end - 1);
+
+	while (entry && entry->start < end) {
+		if (entry->start == start && entry->end == end) {
+			interval_remove(entry, &memtype_rbroot);
+			return entry;
+		}
+		entry = interval_iter_next(entry, start, end - 1);
 	}
-
-	if (entry_old->start == start) {
-		/* munmap: erase this node */
-		interval_remove(entry_old, &memtype_rbroot);
-	} else {
-		/* mremap: update the end value of this node */
-		interval_remove(entry_old, &memtype_rbroot);
-		entry_old->end = start;
-		interval_insert(entry_old, &memtype_rbroot);
-
-		return NULL;
-	}
-
-	return entry_old;
+	return ERR_PTR(-EINVAL);
 }
 
 struct memtype *memtype_lookup(u64 addr)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 62777ba4de1a..ddf248c3ee7d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -189,7 +189,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 
 		if (!ptdesc)
 			failed = true;
-		if (ptdesc && !pagetable_pmd_ctor(ptdesc)) {
+		if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) {
 			pagetable_free(ptdesc);
 			ptdesc = NULL;
 			failed = true;
@@ -751,14 +751,13 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		if (!pmd_none(pmd_sv[i])) {
 			pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
-			free_page((unsigned long)pte);
+			pte_free_kernel(&init_mm, pte);
 		}
 	}
 
 	free_page((unsigned long)pmd_sv);
 
-	pagetable_dtor(virt_to_ptdesc(pmd));
-	free_page((unsigned long)pmd);
+	pmd_free(&init_mm, pmd);
 
 	return 1;
 }
@@ -781,7 +780,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 	/* INVLPG to clear all paging-structure caches */
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
 
-	free_page((unsigned long)pte);
+	pte_free_kernel(&init_mm, pte);
 
 	return 1;
 }
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index ed5c63c0b4e5..88be32026768 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -66,6 +66,8 @@ void __init reserve_real_mode(void)
 	 * setup_arch().
 	 */
 	memblock_reserve(0, SZ_1M);
+
+	memblock_clear_kho_scratch(0, SZ_1M);
 }
 
 static void __init sme_sev_setup_real_mode(struct trampoline_header *th)
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 1647a7cc3fbf..cb1725c40e36 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -269,17 +269,11 @@ static inline pte_t pte_mkwrite_novma(pte_t pte)
 		((__pgprot((pgprot_val(prot) & ~_PAGE_CA_MASK) | \
 			   _PAGE_CA_BYPASS)))
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-
 #define PFN_PTE_SHIFT		PAGE_SHIFT
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
 #define pte_same(a,b)		(pte_val(a) == pte_val(b))
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 #define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index 5ee974bf8330..7db3b489c8ad 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -28,6 +28,13 @@ static inline long syscall_get_nr(struct task_struct *task,
 	return regs->syscall;
 }
 
+static inline void syscall_set_nr(struct task_struct *task,
+				  struct pt_regs *regs,
+				  int nr)
+{
+	regs->syscall = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -68,6 +75,17 @@ static inline void syscall_get_arguments(struct task_struct *task,
 		args[i] = regs->areg[reg[i]];
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
+	unsigned int i;
+
+	for (i = 0; i < 6; ++i)
+		regs->areg[reg[i]] = args[i];
+}
+
 asmlinkage long xtensa_rt_sigreturn(void);
 asmlinkage long xtensa_shmat(int, char __user *, int);
 asmlinkage long xtensa_fadvise64_64(int, int,