[PATCH v1 08/27] powerpc/mm: move __find_linux_pte() out of hugetlbpage.c

From: Christophe Leroy
Date: Wed Mar 20 2019 - 06:08:32 EST


__find_linux_pte() is the only function in hugetlbpage.c
which is compiled in regardless on CONFIG_HUGETLBPAGE

This patch moves it in pgtable.c.

Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxx>
---
arch/powerpc/mm/hugetlbpage.c | 103 -----------------------------------------
arch/powerpc/mm/pgtable.c | 104 ++++++++++++++++++++++++++++++++++++++++++
2 files changed, 104 insertions(+), 103 deletions(-)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index cf2978e235f3..202ae006aa39 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -759,109 +759,6 @@ void flush_dcache_icache_hugepage(struct page *page)

#endif /* CONFIG_HUGETLB_PAGE */

-/*
- * We have 4 cases for pgds and pmds:
- * (1) invalid (all zeroes)
- * (2) pointer to next table, as normal; bottom 6 bits == 0
- * (3) leaf pte for huge page _PAGE_PTE set
- * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table
- *
- * So long as we atomically load page table pointers we are safe against teardown,
- * we can follow the address down to the the page and take a ref on it.
- * This function need to be called with interrupts disabled. We use this variant
- * when we have MSR[EE] = 0 but the paca->irq_soft_mask = IRQS_ENABLED
- */
-pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
- bool *is_thp, unsigned *hpage_shift)
-{
- pgd_t pgd, *pgdp;
- pud_t pud, *pudp;
- pmd_t pmd, *pmdp;
- pte_t *ret_pte;
- hugepd_t *hpdp = NULL;
- unsigned pdshift = PGDIR_SHIFT;
-
- if (hpage_shift)
- *hpage_shift = 0;
-
- if (is_thp)
- *is_thp = false;
-
- pgdp = pgdir + pgd_index(ea);
- pgd = READ_ONCE(*pgdp);
- /*
- * Always operate on the local stack value. This make sure the
- * value don't get updated by a parallel THP split/collapse,
- * page fault or a page unmap. The return pte_t * is still not
- * stable. So should be checked there for above conditions.
- */
- if (pgd_none(pgd))
- return NULL;
- else if (pgd_huge(pgd)) {
- ret_pte = (pte_t *) pgdp;
- goto out;
- } else if (is_hugepd(__hugepd(pgd_val(pgd))))
- hpdp = (hugepd_t *)&pgd;
- else {
- /*
- * Even if we end up with an unmap, the pgtable will not
- * be freed, because we do an rcu free and here we are
- * irq disabled
- */
- pdshift = PUD_SHIFT;
- pudp = pud_offset(&pgd, ea);
- pud = READ_ONCE(*pudp);
-
- if (pud_none(pud))
- return NULL;
- else if (pud_huge(pud)) {
- ret_pte = (pte_t *) pudp;
- goto out;
- } else if (is_hugepd(__hugepd(pud_val(pud))))
- hpdp = (hugepd_t *)&pud;
- else {
- pdshift = PMD_SHIFT;
- pmdp = pmd_offset(&pud, ea);
- pmd = READ_ONCE(*pmdp);
- /*
- * A hugepage collapse is captured by pmd_none, because
- * it mark the pmd none and do a hpte invalidate.
- */
- if (pmd_none(pmd))
- return NULL;
-
- if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
- if (is_thp)
- *is_thp = true;
- ret_pte = (pte_t *) pmdp;
- goto out;
- }
- /*
- * pmd_large check below will handle the swap pmd pte
- * we need to do both the check because they are config
- * dependent.
- */
- if (pmd_huge(pmd) || pmd_large(pmd)) {
- ret_pte = (pte_t *) pmdp;
- goto out;
- } else if (is_hugepd(__hugepd(pmd_val(pmd))))
- hpdp = (hugepd_t *)&pmd;
- else
- return pte_offset_kernel(&pmd, ea);
- }
- }
- if (!hpdp)
- return NULL;
-
- ret_pte = hugepte_offset(*hpdp, ea, pdshift);
- pdshift = hugepd_shift(*hpdp);
-out:
- if (hpage_shift)
- *hpage_shift = pdshift;
- return ret_pte;
-}
-EXPORT_SYMBOL_GPL(__find_linux_pte);
-
int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index d3d61d29b4f1..9f4ccd15849f 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -30,6 +30,7 @@
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
+#include <asm/hugetlb.h>

static inline int is_exec_fault(void)
{
@@ -299,3 +300,106 @@ unsigned long vmalloc_to_phys(void *va)
return __pa(pfn_to_kaddr(pfn)) + offset_in_page(va);
}
EXPORT_SYMBOL_GPL(vmalloc_to_phys);
+
+/*
+ * We have 4 cases for pgds and pmds:
+ * (1) invalid (all zeroes)
+ * (2) pointer to next table, as normal; bottom 6 bits == 0
+ * (3) leaf pte for huge page _PAGE_PTE set
+ * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table
+ *
+ * So long as we atomically load page table pointers we are safe against teardown,
+ * we can follow the address down to the the page and take a ref on it.
+ * This function need to be called with interrupts disabled. We use this variant
+ * when we have MSR[EE] = 0 but the paca->irq_soft_mask = IRQS_ENABLED
+ */
+pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
+ bool *is_thp, unsigned *hpage_shift)
+{
+ pgd_t pgd, *pgdp;
+ pud_t pud, *pudp;
+ pmd_t pmd, *pmdp;
+ pte_t *ret_pte;
+ hugepd_t *hpdp = NULL;
+ unsigned pdshift = PGDIR_SHIFT;
+
+ if (hpage_shift)
+ *hpage_shift = 0;
+
+ if (is_thp)
+ *is_thp = false;
+
+ pgdp = pgdir + pgd_index(ea);
+ pgd = READ_ONCE(*pgdp);
+ /*
+ * Always operate on the local stack value. This make sure the
+ * value don't get updated by a parallel THP split/collapse,
+ * page fault or a page unmap. The return pte_t * is still not
+ * stable. So should be checked there for above conditions.
+ */
+ if (pgd_none(pgd))
+ return NULL;
+ else if (pgd_huge(pgd)) {
+ ret_pte = (pte_t *) pgdp;
+ goto out;
+ } else if (is_hugepd(__hugepd(pgd_val(pgd))))
+ hpdp = (hugepd_t *)&pgd;
+ else {
+ /*
+ * Even if we end up with an unmap, the pgtable will not
+ * be freed, because we do an rcu free and here we are
+ * irq disabled
+ */
+ pdshift = PUD_SHIFT;
+ pudp = pud_offset(&pgd, ea);
+ pud = READ_ONCE(*pudp);
+
+ if (pud_none(pud))
+ return NULL;
+ else if (pud_huge(pud)) {
+ ret_pte = (pte_t *) pudp;
+ goto out;
+ } else if (is_hugepd(__hugepd(pud_val(pud))))
+ hpdp = (hugepd_t *)&pud;
+ else {
+ pdshift = PMD_SHIFT;
+ pmdp = pmd_offset(&pud, ea);
+ pmd = READ_ONCE(*pmdp);
+ /*
+ * A hugepage collapse is captured by pmd_none, because
+ * it mark the pmd none and do a hpte invalidate.
+ */
+ if (pmd_none(pmd))
+ return NULL;
+
+ if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
+ if (is_thp)
+ *is_thp = true;
+ ret_pte = (pte_t *) pmdp;
+ goto out;
+ }
+ /*
+ * pmd_large check below will handle the swap pmd pte
+ * we need to do both the check because they are config
+ * dependent.
+ */
+ if (pmd_huge(pmd) || pmd_large(pmd)) {
+ ret_pte = (pte_t *) pmdp;
+ goto out;
+ } else if (is_hugepd(__hugepd(pmd_val(pmd))))
+ hpdp = (hugepd_t *)&pmd;
+ else
+ return pte_offset_kernel(&pmd, ea);
+ }
+ }
+ if (!hpdp)
+ return NULL;
+
+ ret_pte = hugepte_offset(*hpdp, ea, pdshift);
+ pdshift = hugepd_shift(*hpdp);
+out:
+ if (hpage_shift)
+ *hpage_shift = pdshift;
+ return ret_pte;
+}
+EXPORT_SYMBOL_GPL(__find_linux_pte);
--
2.13.3