[PATCH RFC 5/9] device-dax: Compound pagemap support

[Joao Martins <joao.m.martins@oracle.com>]

dax devices are created with a fixed @align (huge page size) which
is enforced through as well at mmap() of the device. Faults,
consequently happen too at the specified @align specified at the
creation, and those don't change through out dax device lifetime.
MCEs poisons a whole dax huge page, as well as splits occurring at
at the configured page size.

As such, use the newly added compound pagemap facility which onlines
the assigned dax ranges as compound pages. Currently, this means,
that region/namespace bootstrap would take considerably less, given
that you would initialize considerably less pages.

On emulated NVDIMM guests this can be easily seen, e.g. on a setup
with an emulated NVDIMM with 128G in size seeing improvements from ~750ms
to ~190ms with 2M pages, and to less than a 1msec with 1G pages.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
---
Probably deserves its own sysfs attribute for enabling PGMAP_COMPOUND?
---
 drivers/dax/device.c | 54 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 41 insertions(+), 13 deletions(-)

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 25e0b84a4296..9daec6e08efe 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -192,6 +192,39 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 }
 #endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
+static void set_page_mapping(struct vm_fault *vmf, pfn_t pfn,
+			     unsigned int fault_size,
+			     struct address_space *f_mapping)
+{
+	unsigned long i;
+	pgoff_t pgoff;
+
+	pgoff = linear_page_index(vmf->vma, vmf->address
+			& ~(fault_size - 1));
+
+	for (i = 0; i < fault_size / PAGE_SIZE; i++) {
+		struct page *page;
+
+		page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
+		if (page->mapping)
+			continue;
+		page->mapping = f_mapping;
+		page->index = pgoff + i;
+	}
+}
+
+static void set_compound_mapping(struct vm_fault *vmf, pfn_t pfn,
+				 unsigned int fault_size,
+				 struct address_space *f_mapping)
+{
+	struct page *head;
+
+	head = pfn_to_page(pfn_t_to_pfn(pfn));
+	head->mapping = f_mapping;
+	head->index = linear_page_index(vmf->vma, vmf->address
+			& ~(fault_size - 1));
+}
+
 static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
@@ -225,8 +258,7 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
 	}
 
 	if (rc == VM_FAULT_NOPAGE) {
-		unsigned long i;
-		pgoff_t pgoff;
+		struct dev_pagemap *pgmap = pfn_t_to_page(pfn)->pgmap;
 
 		/*
 		 * In the device-dax case the only possibility for a
@@ -234,17 +266,10 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
 		 * mapped. No need to consider the zero page, or racing
 		 * conflicting mappings.
 		 */
-		pgoff = linear_page_index(vmf->vma, vmf->address
-				& ~(fault_size - 1));
-		for (i = 0; i < fault_size / PAGE_SIZE; i++) {
-			struct page *page;
-
-			page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
-			if (page->mapping)
-				continue;
-			page->mapping = filp->f_mapping;
-			page->index = pgoff + i;
-		}
+		if (pgmap->flags & PGMAP_COMPOUND)
+			set_compound_mapping(vmf, pfn, fault_size, filp->f_mapping);
+		else
+			set_page_mapping(vmf, pfn, fault_size, filp->f_mapping);
 	}
 	dax_read_unlock(id);
 
@@ -426,6 +451,9 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 	}
 
 	pgmap->type = MEMORY_DEVICE_GENERIC;
+	pgmap->flags = PGMAP_COMPOUND;
+	pgmap->align = dev_dax->align;
+
 	addr = devm_memremap_pages(dev, pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
-- 
2.17.1
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org