powerpc/8xx: Manage 512k huge pages as standard pages.

At the time being, 512k huge pages are handled through hugepd page
tables. The PMD entry is flagged as a hugepd pointer and it
means that only 512k hugepages can be managed in that 4M block.
However, the hugepd table has the same size as a normal page
table, and 512k entries can therefore be nested with normal pages.

On the 8xx, TLB loading is performed by software and allthough the
page tables are organised to match the L1 and L2 level defined by
the HW, all TLB entries have both L1 and L2 independent entries.
It means that even if two TLB entries are associated with the same
PMD entry, they can be loaded with different values in L1 part.

The L1 entry contains the page size (PS field):
- 00 for 4k and 16 pages
- 01 for 512k pages
- 11 for 8M pages

By adding a flag for hugepages in the PTE (_PAGE_HUGE) and copying it
into the lower bit of PS, we can then manage 512k pages with normal
page tables:
- PMD entry has PS=11 for 8M pages
- PMD entry has PS=00 for other pages.

As a PMD entry covers 4M areas, a PMD will either point to a hugepd
table having a single entry to an 8M page, or the PMD will point to
a standard page table which will have either entries to 4k or 16k or
512k pages. For 512k pages, as the L1 entry will not know it is a
512k page before the PTE is read, there will be 128 entries in the
PTE as if it was 4k pages. But when loading the TLB, it will be
flagged as a 512k page.

Note that we can't use pmd_ptr() in asm/nohash/32/pgtable.h because
it is not defined yet.

In ITLB miss, we keep the possibility to opt it out as when kernel
text is pinned and no user hugepages are used, we can save several
instruction by not using r11.

In DTLB miss, that's just one instruction so it's not worth bothering
with it.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/002819e8e166bf81d24b24782d98de7c40905d8f.1589866984.git.christophe.leroy@csgroup.eu

2 files changed, 28 insertions, 4 deletions

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 521929a371af..38bad839e608 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -189,6 +189,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	if (!hpdp)
 		return NULL;
 
+	if (IS_ENABLED(CONFIG_PPC_8xx) && sz == SZ_512K)
+		return pte_alloc_map(mm, (pmd_t *)hpdp, addr);
+
 	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
 
 	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr,
@@ -331,13 +334,20 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
-	else if (IS_ENABLED(CONFIG_PPC_8xx))
-		pgtable_free_tlb(tlb, hugepte, 0);
 	else
 		pgtable_free_tlb(tlb, hugepte,
 				 get_hugepd_cache_index(pdshift - shift));
 }
 
+static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr)
+{
+	pgtable_t token = pmd_pgtable(*pmd);
+
+	pmd_clear(pmd);
+	pte_free_tlb(tlb, token, addr);
+	mm_dec_nr_ptes(tlb->mm);
+}
+
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 				   unsigned long addr, unsigned long end,
 				   unsigned long floor, unsigned long ceiling)
@@ -353,11 +363,17 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
 		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
+			if (pmd_none_or_clear_bad(pmd))
+				continue;
+
 			/*
 			 * if it is not hugepd pointer, we should already find
 			 * it cleared.
 			 */
-			WARN_ON(!pmd_none_or_clear_bad(pmd));
+			WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
+
+			hugetlb_free_pte_range(tlb, pmd, addr);
+
 			continue;
 		}
 		/*
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 214a5f4beb6c..60c4b8ff046c 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -264,6 +264,12 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 #if defined(CONFIG_PPC_8xx)
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
 {
+	pmd_t *pmd = pmd_ptr(mm, addr);
+	pte_basic_t val;
+	pte_basic_t *entry = &ptep->pte;
+	int num = is_hugepd(*((hugepd_t *)pmd)) ? 1 : SZ_512K / SZ_4K;
+	int i;
+
 	/*
 	 * Make sure hardware valid bit is not set. We don't do
 	 * tlb flush for this update.
@@ -274,7 +280,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_
 
 	pte = set_pte_filter(pte);
 
-	ptep->pte = pte_val(pte);
+	val = pte_val(pte);
+	for (i = 0; i < num; i++, entry++, val += SZ_4K)
+		*entry = val;
 }
 #endif
 #endif /* CONFIG_HUGETLB_PAGE */