Thread (37 messages) 37 messages, 3 authors, 2024-05-29

Re: [RFC PATCH v4 14/16] powerpc/64s: Use contiguous PMD/PUD instead of HUGEPD

From: Oscar Salvador <hidden>
Date: 2024-05-29 09:23:22
Also in: linuxppc-dev, lkml

On Mon, May 27, 2024 at 03:30:12PM +0200, Christophe Leroy wrote:
On book3s/64, the only user of hugepd is hash in 4k mode.

All other setups (hash-64, radix-4, radix-64) use leaf PMD/PUD.

Rework hash-4k to use contiguous PMD and PUD instead.

In that setup there are only two huge page sizes: 16M and 16G.

16M sits at PMD level and 16G at PUD level.

On 4k mode, PMD_SIZE is 2MB and PUD_SIZE is 256MB, right?
+static inline unsigned long hash__pte_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pte_t *ptep, unsigned long clr,
+					 unsigned long set,
+					 int huge)
+{
+	unsigned long old;
+
+	old = hash__pte_update_one(ptep, clr, set);
+
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) {
+		unsigned int psize = get_slice_psize(mm, addr);
+		int nb, i;
+
+		if (psize == MMU_PAGE_16M)
+			nb = SZ_16M / PMD_SIZE;
+		else if (psize == MMU_PAGE_16G)
+			nb = SZ_16G / PUD_SIZE;
+		else
+			nb = 1;
On 4K, hugepages are either 16M or 16G. How can we end up in a situation
whwere the is pte is huge, but is is neither MMU_PAGE_16G nor MMU_PAGE_16M?
quoted hunk ↗ jump to hunk
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 5a2e512e96db..83c3361b358b 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -53,6 +53,16 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		/* If PTE permissions don't match, take page fault */
 		if (unlikely(!check_pte_access(access, old_pte)))
 			return 1;
+		/*
+		 * If hash-4k, hugepages use seeral contiguous PxD entries
'several'
+		 * so bail out and let mm make the page young or dirty
+		 */
+		if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) {
+			if (!(old_pte & _PAGE_ACCESSED))
+				return 1;
+			if ((access & _PAGE_WRITE) && !(old_pte & _PAGE_DIRTY))
+				return 1;
I have 0 clue about this code. What would happen if we do not bail out?


-- 
Oscar Salvador
SUSE Labs
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help