mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig options

Patch series "mm: split PTE/PMD PT table Kconfig cleanups+clarifications".

This series is a follow up to the fixes:
	"[PATCH v1 0/2] mm/hugetlb: fix hugetlb vs. core-mm PT locking"

When working on the fixes, I wondered why 8xx is fine (-> never uses split
PT locks) and how PT locking even works properly with PMD page table
sharing (-> always requires split PMD PT locks).

Let's improve the split PT lock detection, make hugetlb properly depend on
it and make 8xx bail out if it would ever get enabled by accident.

As an alternative to patch #3 we could extend the Kconfig
SPLIT_PTE_PTLOCKS option from patch #2 -- but enforcing it closer to the
code that actually implements it feels a bit nicer for documentation
purposes, and there is no need to actually disable it because it should
always be disabled (!SMP).

Did a bunch of cross-compilations to make sure that split PTE/PMD PT locks
are still getting used where we would expect them.

[1] https://lkml.kernel.org/r/20240725183955.2268884-1-david@redhat.com

This patch (of 3):

Let's clean that up a bit and prepare for depending on
CONFIG_SPLIT_PMD_PTLOCKS in other Kconfig options.

More cleanups would be reasonable (like the arch-specific "depends on" for
CONFIG_SPLIT_PTE_PTLOCKS), but we'll leave that for another day.

Link: https://lkml.kernel.org/r/20240726150728.3159964-1-david@redhat.com
Link: https://lkml.kernel.org/r/20240726150728.3159964-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2286c2e..831793c 100644 (file)
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -61,7 +61,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
        return ret;
 }
 
-#if USE_SPLIT_PTE_PTLOCKS
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS)
 /*
  * If we are using split PTE locks, then we need to take the page
  * lock here.  Otherwise we are using shared mm->page_table_lock
@@ -80,10 +80,10 @@ static inline void do_pte_unlock(spinlock_t *ptl)
 {
        spin_unlock(ptl);
 }
-#else /* !USE_SPLIT_PTE_PTLOCKS */
+#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 static inline void do_pte_lock(spinlock_t *ptl) {}
 static inline void do_pte_unlock(spinlock_t *ptl) {}
-#endif /* USE_SPLIT_PTE_PTLOCKS */
+#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
        unsigned long pfn)

diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index f1ce39d..f4a3168 100644 (file)
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -665,7 +665,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
 {
        spinlock_t *ptl = NULL;
 
-#if USE_SPLIT_PTE_PTLOCKS
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS)
        ptl = ptlock_ptr(page_ptdesc(page));
        spin_lock_nest_lock(ptl, &mm->page_table_lock);
 #endif
@@ -1553,7 +1553,8 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 
                __set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-               if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
+               if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS) &&
+                   !pinned)
                        __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
                xen_mc_issue(XEN_LAZY_MMU);
@@ -1581,7 +1582,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
        if (pinned) {
                xen_mc_batch();
 
-               if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+               if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS))
                        __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 
                __set_pfn_prot(pfn, PAGE_KERNEL);

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6c2078c..b7000fa 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2891,7 +2891,7 @@ static inline void pagetable_free(struct ptdesc *pt)
        __free_pages(page, compound_order(page));
 }
 
-#if USE_SPLIT_PTE_PTLOCKS
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS)
 #if ALLOC_SPLIT_PTLOCKS
 void __init ptlock_cache_init(void);
 bool ptlock_alloc(struct ptdesc *ptdesc);
@@ -2949,7 +2949,7 @@ static inline bool ptlock_init(struct ptdesc *ptdesc)
        return true;
 }
 
-#else  /* !USE_SPLIT_PTE_PTLOCKS */
+#else  /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
@@ -2964,7 +2964,7 @@ static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
 static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
 static inline void ptlock_free(struct ptdesc *ptdesc) {}
-#endif /* USE_SPLIT_PTE_PTLOCKS */
+#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 
 static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc)
 {
@@ -3024,7 +3024,7 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd,
        ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \
                NULL: pte_offset_kernel(pmd, address))
 
-#if USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_SPLIT_PMD_PTLOCKS)
 
 static inline struct page *pmd_pgtable_page(pmd_t *pmd)
 {

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4854249..165c58b 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -947,7 +947,7 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
                struct mmu_notifier_subscriptions *notifier_subscriptions;
 #endif
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
                pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_NUMA_BALANCING

diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index a2f6179..bff5706 100644 (file)
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -16,9 +16,6 @@
 #include <asm/tlbbatch.h>
 #endif
 
-#define USE_SPLIT_PTE_PTLOCKS  (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
-#define USE_SPLIT_PMD_PTLOCKS  (USE_SPLIT_PTE_PTLOCKS && \
-               IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 #define ALLOC_SPLIT_PTLOCKS    (SPINLOCK_SIZE > BITS_PER_LONG/8)
 
 /*

diff --git a/kernel/fork.c b/kernel/fork.c
index cc76049..3d590e5 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -832,7 +832,7 @@ static void check_mm(struct mm_struct *mm)
                pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
                                mm_pgtables_bytes(mm));
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
        VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
 #endif
 }
@@ -1276,7 +1276,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
        RCU_INIT_POINTER(mm->exe_file, NULL);
        mmu_notifier_subscriptions_init(mm);
        init_tlb_flush_pending(mm);
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
        mm->pmd_huge_pte = NULL;
 #endif
        mm_init_uprobes_state(mm);

diff --git a/mm/Kconfig b/mm/Kconfig
index b72e7d0..7b716ac 100644 (file)
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -585,17 +585,21 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 # at the same time (e.g. copy_page_range()).
 # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
 #
-config SPLIT_PTLOCK_CPUS
-       int
-       default "999999" if !MMU
-       default "999999" if ARM && !CPU_CACHE_VIPT
-       default "999999" if PARISC && !PA20
-       default "999999" if SPARC32
-       default "4"
+config SPLIT_PTE_PTLOCKS
+       def_bool y
+       depends on MMU
+       depends on NR_CPUS >= 4
+       depends on !ARM || CPU_CACHE_VIPT
+       depends on !PARISC || PA20
+       depends on !SPARC32
 
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
        bool
 
+config SPLIT_PMD_PTLOCKS
+       def_bool y
+       depends on SPLIT_PTE_PTLOCKS && ARCH_ENABLE_SPLIT_PMD_PTLOCK
+
 #
 # support for memory balloon
 config MEMORY_BALLOON

diff --git a/mm/memory.c b/mm/memory.c
index a3d9550..71236ae 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6571,7 +6571,7 @@ long copy_folio_from_user(struct folio *dst_folio,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
-#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS
 
 static struct kmem_cache *page_ptl_cachep;