Message-ID: <c488244d78c74992ac1f07564617a4758951e596.1726009989.git.ackerleytng@google.com>
Date: Tue, 10 Sep 2024 23:43:56 +0000
From: Ackerley Tng <ackerleytng@...gle.com>
To: tabba@...gle.com, quic_eberman@...cinc.com, roypat@...zon.co.uk, 
	jgg@...dia.com, peterx@...hat.com, david@...hat.com, rientjes@...gle.com, 
	fvdl@...gle.com, jthoughton@...gle.com, seanjc@...gle.com, 
	pbonzini@...hat.com, zhiquan1.li@...el.com, fan.du@...el.com, 
	jun.miao@...el.com, isaku.yamahata@...el.com, muchun.song@...ux.dev, 
	mike.kravetz@...cle.com
Cc: erdemaktas@...gle.com, vannapurve@...gle.com, ackerleytng@...gle.com, 
	qperret@...gle.com, jhubbard@...dia.com, willy@...radead.org, 
	shuah@...nel.org, brauner@...nel.org, bfoster@...hat.com, 
	kent.overstreet@...ux.dev, pvorel@...e.cz, rppt@...nel.org, 
	richard.weiyang@...il.com, anup@...infault.org, haibo1.xu@...el.com, 
	ajones@...tanamicro.com, vkuznets@...hat.com, maciej.wieczor-retman@...el.com, 
	pgonda@...gle.com, oliver.upton@...ux.dev, linux-kernel@...r.kernel.org, 
	linux-mm@...ck.org, kvm@...r.kernel.org, linux-kselftest@...r.kernel.org, 
	linux-fsdevel@...ck.org
Subject: [RFC PATCH 25/39] KVM: guest_memfd: Split HugeTLB pages for
 guest_memfd use

From: Vishal Annapurve <vannapurve@...gle.com>

In this patch, newly allocated HugeTLB pages are split to 4K regular
pages before providing them to the requester (fallocate() or KVM).

The pages are then reconstructed/merged to HugeTLB pages before
the HugeTLB pages are returned to HugeTLB.

This is an intermediate step to build page splitting/merging
functionality before allowing guest_memfd files to be mmap()ed.

Co-developed-by: Ackerley Tng <ackerleytng@...gle.com>
Signed-off-by: Ackerley Tng <ackerleytng@...gle.com>
Co-developed-by: Vishal Annapurve <vannapurve@...gle.com>
Signed-off-by: Vishal Annapurve <vannapurve@...gle.com>

---
 virt/kvm/guest_memfd.c | 299 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 281 insertions(+), 18 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index eacbfdb950d1..8151df2c03e5 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -229,31 +229,206 @@ static int kvm_gmem_hugetlb_filemap_add_folio(struct address_space *mapping,
 	return 0;
 }
 
+struct kvm_gmem_split_stash {
+	struct {
+		unsigned long _flags_2;
+		unsigned long _head_2;
+
+		void *_hugetlb_subpool;
+		void *_hugetlb_cgroup;
+		void *_hugetlb_cgroup_rsvd;
+		void *_hugetlb_hwpoison;
+	};
+	void *hugetlb_private;
+};
+
+static int kvm_gmem_hugetlb_stash_metadata(struct folio *folio)
+{
+	struct kvm_gmem_split_stash *stash;
+
+	stash = kmalloc(sizeof(*stash), GFP_KERNEL);
+	if (!stash)
+		return -ENOMEM;
+
+	stash->_flags_2 = folio->_flags_2;
+	stash->_head_2 = folio->_head_2;
+	stash->_hugetlb_subpool = folio->_hugetlb_subpool;
+	stash->_hugetlb_cgroup = folio->_hugetlb_cgroup;
+	stash->_hugetlb_cgroup_rsvd = folio->_hugetlb_cgroup_rsvd;
+	stash->_hugetlb_hwpoison = folio->_hugetlb_hwpoison;
+	stash->hugetlb_private = folio_get_private(folio);
+
+	folio_change_private(folio, (void *)stash);
+
+	return 0;
+}
+
+static int kvm_gmem_hugetlb_unstash_metadata(struct folio *folio)
+{
+	struct kvm_gmem_split_stash *stash;
+
+	stash = folio_get_private(folio);
+
+	if (!stash)
+		return -EINVAL;
+
+	folio->_flags_2 = stash->_flags_2;
+	folio->_head_2 = stash->_head_2;
+	folio->_hugetlb_subpool = stash->_hugetlb_subpool;
+	folio->_hugetlb_cgroup = stash->_hugetlb_cgroup;
+	folio->_hugetlb_cgroup_rsvd = stash->_hugetlb_cgroup_rsvd;
+	folio->_hugetlb_hwpoison = stash->_hugetlb_hwpoison;
+	folio_change_private(folio, stash->hugetlb_private);
+
+	kfree(stash);
+
+	return 0;
+}
+
+/**
+ * Reconstruct a HugeTLB folio from a contiguous block of folios where the first
+ * of the contiguous folios is @folio.
+ *
+ * The size of the contiguous block is of huge_page_size(@h). All the folios in
+ * the block are checked to have a refcount of 1 before reconstruction. After
+ * reconstruction, the reconstructed folio has a refcount of 1.
+ *
+ * Return 0 on success and negative error otherwise.
+ */
+static int kvm_gmem_hugetlb_reconstruct_folio(struct hstate *h, struct folio *folio)
+{
+	int ret;
+
+	WARN_ON((folio->index & (huge_page_order(h) - 1)) != 0);
+
+	ret = kvm_gmem_hugetlb_unstash_metadata(folio);
+	if (ret)
+		return ret;
+
+	if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) {
+		kvm_gmem_hugetlb_stash_metadata(folio);
+		return -ENOMEM;
+	}
+
+	__folio_set_hugetlb(folio);
+
+	folio_set_count(folio, 1);
+
+	hugetlb_vmemmap_optimize_folio(h, folio);
+
+	return 0;
+}
+
+/* Basically folio_set_order(folio, 1) without the checks. */
+static inline void kvm_gmem_folio_set_order(struct folio *folio, unsigned int order)
+{
+	folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
+#ifdef CONFIG_64BIT
+	folio->_folio_nr_pages = 1U << order;
+#endif
+}
+
+/**
+ * Split a HugeTLB @folio of size huge_page_size(@h).
+ *
+ * After splitting, each split folio has a refcount of 1. There are no checks on
+ * refcounts before splitting.
+ *
+ * Return 0 on success and negative error otherwise.
+ */
+static int kvm_gmem_hugetlb_split_folio(struct hstate *h, struct folio *folio)
+{
+	int ret;
+
+	ret = hugetlb_vmemmap_restore_folio(h, folio);
+	if (ret)
+		return ret;
+
+	ret = kvm_gmem_hugetlb_stash_metadata(folio);
+	if (ret) {
+		hugetlb_vmemmap_optimize_folio(h, folio);
+		return ret;
+	}
+
+	kvm_gmem_folio_set_order(folio, 0);
+
+	destroy_compound_gigantic_folio(folio, huge_page_order(h));
+	__folio_clear_hugetlb(folio);
+
+	/*
+	 * Remove the first folio from h->hugepage_activelist since it is no
+	 * longer a HugeTLB page. The other split pages should not be on any
+	 * lists.
+	 */
+	hugetlb_folio_list_del(folio);
+
+	return 0;
+}
+
 static struct folio *kvm_gmem_hugetlb_alloc_and_cache_folio(struct inode *inode,
 							    pgoff_t index)
 {
+	struct folio *allocated_hugetlb_folio;
+	pgoff_t hugetlb_first_subpage_index;
+	struct page *hugetlb_first_subpage;
 	struct kvm_gmem_hugetlb *hgmem;
-	struct folio *folio;
+	struct page *requested_page;
 	int ret;
+	int i;
 
 	hgmem = kvm_gmem_hgmem(inode);
-	folio = kvm_gmem_hugetlb_alloc_folio(hgmem->h, hgmem->spool);
-	if (IS_ERR(folio))
-		return folio;
+	allocated_hugetlb_folio = kvm_gmem_hugetlb_alloc_folio(hgmem->h, hgmem->spool);
+	if (IS_ERR(allocated_hugetlb_folio))
+		return allocated_hugetlb_folio;
+
+	requested_page = folio_file_page(allocated_hugetlb_folio, index);
+	hugetlb_first_subpage = folio_file_page(allocated_hugetlb_folio, 0);
+	hugetlb_first_subpage_index = index & (huge_page_mask(hgmem->h) >> PAGE_SHIFT);
 
-	/* TODO: Fix index here to be aligned to huge page size. */
-	ret = kvm_gmem_hugetlb_filemap_add_folio(
-		inode->i_mapping, folio, index, htlb_alloc_mask(hgmem->h));
+	ret = kvm_gmem_hugetlb_split_folio(hgmem->h, allocated_hugetlb_folio);
 	if (ret) {
-		folio_put(folio);
+		folio_put(allocated_hugetlb_folio);
 		return ERR_PTR(ret);
 	}
 
+	for (i = 0; i < pages_per_huge_page(hgmem->h); ++i) {
+		struct folio *folio = page_folio(nth_page(hugetlb_first_subpage, i));
+
+		ret = kvm_gmem_hugetlb_filemap_add_folio(inode->i_mapping,
+							 folio,
+							 hugetlb_first_subpage_index + i,
+							 htlb_alloc_mask(hgmem->h));
+		if (ret) {
+			/* TODO: handle cleanup properly. */
+			pr_err("Handle cleanup properly index=%lx, ret=%d\n",
+			       hugetlb_first_subpage_index + i, ret);
+			dump_page(nth_page(hugetlb_first_subpage, i), "check");
+			return ERR_PTR(ret);
+		}
+
+		/*
+		 * Skip unlocking for the requested index since
+		 * kvm_gmem_get_folio() returns a locked folio.
+		 *
+		 * Do folio_put() to drop the refcount that came with the folio,
+		 * from splitting the folio. Splitting the folio has a refcount
+		 * to be in line with hugetlb_alloc_folio(), which returns a
+		 * folio with refcount 1.
+		 *
+		 * Skip folio_put() for requested index since
+		 * kvm_gmem_get_folio() returns a folio with refcount 1.
+		 */
+		if (hugetlb_first_subpage_index + i != index) {
+			folio_unlock(folio);
+			folio_put(folio);
+		}
+	}
+
 	spin_lock(&inode->i_lock);
 	inode->i_blocks += blocks_per_huge_page(hgmem->h);
 	spin_unlock(&inode->i_lock);
 
-	return folio;
+	return page_folio(requested_page);
 }
 
 static struct folio *kvm_gmem_get_hugetlb_folio(struct inode *inode,
@@ -365,7 +540,9 @@ static inline void kvm_gmem_hugetlb_filemap_remove_folio(struct folio *folio)
 
 /**
  * Removes folios in range [@lstart, @lend) from page cache/filemap (@mapping),
- * returning the number of pages freed.
+ * returning the number of HugeTLB pages freed.
+ *
+ * @lend - @lstart must be a multiple of the HugeTLB page size.
  */
 static int kvm_gmem_hugetlb_filemap_remove_folios(struct address_space *mapping,
 						  struct hstate *h,
@@ -373,37 +550,69 @@ static int kvm_gmem_hugetlb_filemap_remove_folios(struct address_space *mapping,
 {
 	const pgoff_t end = lend >> PAGE_SHIFT;
 	pgoff_t next = lstart >> PAGE_SHIFT;
+	LIST_HEAD(folios_to_reconstruct);
 	struct folio_batch fbatch;
+	struct folio *folio, *tmp;
 	int num_freed = 0;
+	int i;
 
+	/*
+	 * TODO: Iterate over huge_page_size(h) blocks to avoid taking and
+	 * releasing hugetlb_fault_mutex_table[hash] lock so often. When
+	 * truncating, lstart and lend should be clipped to the size of this
+	 * guest_memfd file, otherwise there would be too many iterations.
+	 */
 	folio_batch_init(&fbatch);
 	while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) {
-		int i;
 		for (i = 0; i < folio_batch_count(&fbatch); ++i) {
 			struct folio *folio;
 			pgoff_t hindex;
 			u32 hash;
 
 			folio = fbatch.folios[i];
+
 			hindex = folio->index >> huge_page_order(h);
 			hash = hugetlb_fault_mutex_hash(mapping, hindex);
-
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
+
+			/*
+			 * Collect first pages of HugeTLB folios for
+			 * reconstruction later.
+			 */
+			if ((folio->index & ~(huge_page_mask(h) >> PAGE_SHIFT)) == 0)
+				list_add(&folio->lru, &folios_to_reconstruct);
+
+			/*
+			 * Before removing from filemap, take a reference so
+			 * sub-folios don't get freed. Don't free the sub-folios
+			 * until after reconstruction.
+			 */
+			folio_get(folio);
+
 			kvm_gmem_hugetlb_filemap_remove_folio(folio);
-			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
-			num_freed++;
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 
+	list_for_each_entry_safe(folio, tmp, &folios_to_reconstruct, lru) {
+		kvm_gmem_hugetlb_reconstruct_folio(h, folio);
+		hugetlb_folio_list_move(folio, &h->hugepage_activelist);
+
+		folio_put(folio);
+		num_freed++;
+	}
+
 	return num_freed;
 }
 
 /**
  * Removes folios in range [@lstart, @lend) from page cache of inode, updates
  * inode metadata and hugetlb reservations.
+ *
+ * @lend - @lstart must be a multiple of the HugeTLB page size.
  */
 static void kvm_gmem_hugetlb_truncate_folios_range(struct inode *inode,
 						   loff_t lstart, loff_t lend)
@@ -427,6 +636,56 @@ static void kvm_gmem_hugetlb_truncate_folios_range(struct inode *inode,
 	spin_unlock(&inode->i_lock);
 }
 
+/**
+ * Zeroes offsets [@start, @end) in a folio from @mapping.
+ *
+ * [@start, @end) must be within the same folio.
+ */
+static void kvm_gmem_zero_partial_page(
+	struct address_space *mapping, loff_t start, loff_t end)
+{
+	struct folio *folio;
+	pgoff_t idx = start >> PAGE_SHIFT;
+
+	folio = filemap_lock_folio(mapping, idx);
+	if (IS_ERR(folio))
+		return;
+
+	start = offset_in_folio(folio, start);
+	end = offset_in_folio(folio, end);
+	if (!end)
+		end = folio_size(folio);
+
+	folio_zero_segment(folio, (size_t)start, (size_t)end);
+	folio_unlock(folio);
+	folio_put(folio);
+}
+
+/**
+ * Zeroes all pages in range [@start, @end) in @mapping.
+ *
+ * hugetlb_zero_partial_page() would work if this had been a full page, but is
+ * not suitable since the pages have been split.
+ *
+ * truncate_inode_pages_range() isn't the right function because it removes
+ * pages from the page cache; this function only zeroes the pages.
+ */
+static void kvm_gmem_hugetlb_zero_split_pages(struct address_space *mapping,
+					      loff_t start, loff_t end)
+{
+	loff_t aligned_start;
+	loff_t index;
+
+	aligned_start = round_up(start, PAGE_SIZE);
+
+	kvm_gmem_zero_partial_page(mapping, start, min(aligned_start, end));
+
+	for (index = aligned_start; index < end; index += PAGE_SIZE) {
+		kvm_gmem_zero_partial_page(mapping, index,
+					   min((loff_t)(index + PAGE_SIZE), end));
+	}
+}
+
 static void kvm_gmem_hugetlb_truncate_range(struct inode *inode, loff_t lstart,
 					    loff_t lend)
 {
@@ -442,8 +701,8 @@ static void kvm_gmem_hugetlb_truncate_range(struct inode *inode, loff_t lstart,
 	full_hpage_end = round_down(lend, hsize);
 
 	if (lstart < full_hpage_start) {
-		hugetlb_zero_partial_page(h, inode->i_mapping, lstart,
-					  full_hpage_start);
+		kvm_gmem_hugetlb_zero_split_pages(inode->i_mapping, lstart,
+						  full_hpage_start);
 	}
 
 	if (full_hpage_end > full_hpage_start) {
@@ -452,8 +711,8 @@ static void kvm_gmem_hugetlb_truncate_range(struct inode *inode, loff_t lstart,
 	}
 
 	if (lend > full_hpage_end) {
-		hugetlb_zero_partial_page(h, inode->i_mapping, full_hpage_end,
-					  lend);
+		kvm_gmem_hugetlb_zero_split_pages(inode->i_mapping, full_hpage_end,
+						  lend);
 	}
 }
 
@@ -1060,6 +1319,10 @@ __kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
 
 	if (folio_test_hwpoison(folio)) {
 		folio_unlock(folio);
+		/*
+		 * TODO: this folio may be part of a HugeTLB folio. Perhaps
+		 * reconstruct and then free page?
+		 */
 		folio_put(folio);
 		return ERR_PTR(-EHWPOISON);
 	}
-- 
2.46.0.598.g6f2099f65c-goog

Powered by blists - more mailing lists