Merge tag 'x86-mm-2025-01-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:

 - The biggest changes are the TLB flushing scalability optimizations,
   to update the mm_cpumask lazily and related changes.

   This feature has both a track record and a continued risk of
   performance regressions, so it was already delayed by a cycle - but
   it's all 100% perfect now™ (Rik van Riel)

 - Also miscellaneous fixes and cleanups. (Gautam Somani, Kirill
   Shutemov, Sebastian Andrzej Siewior)

* tag 'x86-mm-2025-01-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Remove unnecessary include of <linux/extable.h>
  x86/mtrr: Rename mtrr_overwrite_state() to guest_force_mtrr_state()
  x86/mm/selftests: Fix typo in lam.c
  x86/mm/tlb: Only trim the mm_cpumask once a second
  x86/mm/tlb: Also remove local CPU from mm_cpumask if stale
  x86/mm/tlb: Add tracepoint for TLB flush IPI to stale CPU
  x86/mm/tlb: Update mm_cpumask lazily

diff --combined arch/x86/mm/fault.c
index ac52255fab01f4c83479af973bbaa348cf8c57c3,ef12ff3db9039c2ae74435680114c65a4ccc8931..296d294142c8d53f77221f1d4274b56c476387fc
--- 1/arch/x86/mm/fault.c
--- 2/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@@ -7,7 -7,6 +7,6 @@@
  #include <linux/sched.h>              /* test_thread_flag(), ...      */
  #include <linux/sched/task_stack.h>   /* task_stack_*(), ...          */
  #include <linux/kdebug.h>             /* oops_begin/end, ...          */
- #include <linux/extable.h>            /* search_exception_tables      */
  #include <linux/memblock.h>           /* max_low_pfn                  */
  #include <linux/kfence.h>             /* kfence_handle_page_fault     */
  #include <linux/kprobes.h>            /* NOKPROBE_SYMBOL, ...         */
@@@ -678,7 -677,7 +677,7 @@@ page_fault_oops(struct pt_regs *regs, u
                              ASM_CALL_ARG3,
                              , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));
  
 -              unreachable();
 +              BUG();
        }
  #endif
  

diff --combined include/linux/mm_types.h
index 5f1b2dc788e24378b5806272f674e803f6409503,1371893e44ca36bb78a9e2482e7ab8c9980bfae6..6b27db7f949637db515af7831b49e303049c0140
--- 1/include/linux/mm_types.h
--- 2/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@@ -438,16 -438,13 +438,16 @@@ FOLIO_MATCH(compound_head, _head_2a)
   * struct ptdesc -    Memory descriptor for page tables.
   * @__page_flags:     Same as page flags. Powerpc only.
   * @pt_rcu_head:      For freeing page table pages.
 - * @pt_list:          List of used page tables. Used for s390 and x86.
 + * @pt_list:          List of used page tables. Used for s390 gmap shadow pages
 + *                    (which are not linked into the user page tables) and x86
 + *                    pgds.
   * @_pt_pad_1:        Padding that aliases with page's compound head.
   * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
   * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
   * @pt_index:         Used for s390 gmap.
   * @pt_mm:            Used for x86 pgds.
   * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
 + * @pt_share_count:   Used for HugeTLB PMD page table share count.
   * @_pt_pad_2:        Padding to ensure proper alignment.
   * @ptl:              Lock for the page table.
   * @__page_type:      Same as page->page_type. Unused for page tables.
@@@ -474,9 -471,6 +474,9 @@@ struct ptdesc 
                pgoff_t pt_index;
                struct mm_struct *pt_mm;
                atomic_t pt_frag_refcount;
 +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
 +              atomic_t pt_share_count;
 +#endif
        };
  
        union {
@@@ -522,32 -516,6 +522,32 @@@ static_assert(sizeof(struct ptdesc) <= 
        const struct page *:            (const struct ptdesc *)(p),     \
        struct page *:                  (struct ptdesc *)(p)))
  
 +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
 +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
 +{
 +      atomic_set(&ptdesc->pt_share_count, 0);
 +}
 +
 +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc)
 +{
 +      atomic_inc(&ptdesc->pt_share_count);
 +}
 +
 +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc)
 +{
 +      atomic_dec(&ptdesc->pt_share_count);
 +}
 +
 +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc)
 +{
 +      return atomic_read(&ptdesc->pt_share_count);
 +}
 +#else
 +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
 +{
 +}
 +#endif
 +
  /*
   * Used for sizing the vmemmap region on some architectures
   */
@@@ -729,7 -697,7 +729,7 @@@ struct vm_area_struct 
         * counter reuse can only lead to occasional unnecessary use of the
         * slowpath.
         */
 -      int vm_lock_seq;
 +      unsigned int vm_lock_seq;
        /* Unstable RCU readers are allowed to read this. */
        struct vma_lock *vm_lock;
  #endif
@@@ -923,9 -891,6 +923,9 @@@ struct mm_struct 
                 * Roughly speaking, incrementing the sequence number is
                 * equivalent to releasing locks on VMAs; reading the sequence
                 * number can be part of taking a read lock on a VMA.
 +               * Incremented every time mmap_lock is write-locked/unlocked.
 +               * Initialized to 0, therefore odd values indicate mmap_lock
 +               * is write-locked and even values that it's released.
                 *
                 * Can be modified under write mmap_lock using RELEASE
                 * semantics.
@@@ -934,7 -899,7 +934,7 @@@
                 * Can be read with ACQUIRE semantics if not holding write
                 * mmap_lock.
                 */
 -              int mm_lock_seq;
 +              seqcount_t mm_lock_seq;
  #endif
  
  
@@@ -1406,6 -1371,7 +1406,7 @@@ enum tlb_flush_reason 
        TLB_LOCAL_SHOOTDOWN,
        TLB_LOCAL_MM_SHOOTDOWN,
        TLB_REMOTE_SEND_IPI,
+       TLB_REMOTE_WRONG_CPU,
        NR_TLB_FLUSH_REASONS,
  };