asm-generic: pgalloc: provide generic __pgd_{alloc,free}

We already have a generic implementation of alloc/free up to P4D level, as
well as pgd_free().  Let's finish the work and add a generic PGD-level
alloc helper as well.

Unlike at lower levels, almost all architectures need some specific magic
at PGD level (typically initialising PGD entries), so introducing a
generic pgd_alloc() isn't worth it.  Instead we introduce two new helpers,
__pgd_alloc() and __pgd_free(), and make use of them in the arch-specific
pgd_alloc() and pgd_free() wherever possible.  To accommodate as many arch
as possible, __pgd_alloc() takes a page allocation order.

Because pagetable_alloc() allocates zeroed pages, explicit zeroing in
pgd_alloc() becomes redundant and we can get rid of it.  Some trivial
implementations of pgd_free() also become unnecessary once __pgd_alloc()
is used; remove them.

Another small improvement is consistent accounting of PGD pages by using
GFP_PGTABLE_{USER,KERNEL} as appropriate.

Not all PGD allocations can be handled by the generic helpers.  In
particular, multiple architectures allocate PGDs from a kmem_cache, and
those PGDs may not be page-sized.

Link: https://lkml.kernel.org/r/20250103184415.2744423-6-kevin.brodsky@arm.com
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 11 insertions, 13 deletions

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index c02aa0427a6a..1fef5ad32d5a 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -397,15 +397,14 @@ void __init pgtable_cache_init(void)
 				      SLAB_PANIC, NULL);
 }
 
-static inline pgd_t *_pgd_alloc(void)
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
 	/*
 	 * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
-						 PGD_ALLOCATION_ORDER);
+		return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -414,24 +413,23 @@ static inline pgd_t *_pgd_alloc(void)
 	return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
 }
 
-static inline void _pgd_free(pgd_t *pgd)
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	if (!SHARED_KERNEL_PMD)
-		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
+		__pgd_free(mm, pgd);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
 #else
 
-static inline pgd_t *_pgd_alloc(void)
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
-	return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
-					 PGD_ALLOCATION_ORDER);
+	return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
 }
 
-static inline void _pgd_free(pgd_t *pgd)
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
+	__pgd_free(mm, pgd);
 }
 #endif /* CONFIG_X86_PAE */
 
@@ -441,7 +439,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
 	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
 
-	pgd = _pgd_alloc();
+	pgd = _pgd_alloc(mm);
 
 	if (pgd == NULL)
 		goto out;
@@ -484,7 +482,7 @@ out_free_pmds:
 	if (sizeof(pmds) != 0)
 		free_pmds(mm, pmds, PREALLOCATED_PMDS);
 out_free_pgd:
-	_pgd_free(pgd);
+	_pgd_free(mm, pgd);
 out:
 	return NULL;
 }
@@ -494,7 +492,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	pgd_mop_up_pmds(mm, pgd);
 	pgd_dtor(pgd);
 	paravirt_pgd_free(mm, pgd);
-	_pgd_free(pgd);
+	_pgd_free(mm, pgd);
 }
 
 /*