Re: [PATCH v4 1/8] KVM: s390: pv: Use VM_SPARSE area for guest variable storage area

[Heiko Carstens <hca@linux.ibm.com>]

On Thu, Sep 03, 2026 at 07:24:17PM +0200, Heiko Carstens wrote:
> On Thu, Sep 03, 2026 at 02:28:35PM +0200, Alexander Gordeev wrote:
> > On Mon, Jul 20, 2026 at 10:58:27AM +0200, Heiko Carstens wrote:
> > This could be solved using the below fixup:
> > 
> > @@ -247,7 +247,9 @@ static int uv_alloc_range_cb(pte_t *ptep, unsigned long addr, void *data)
> >  	struct page *page;
> >  	pte_t pte;
> >  
> > +	lazy_mmu_mode_pause();
> >  	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
> > +	lazy_mmu_mode_resume();
> >  	if (!page)
> >  		return -ENOMEM;
> >  	pte = __pte(page_to_phys(page) | pgprot_val(PAGE_KERNEL));
> > 
> > The downside is lazy_mmu_mode_resume() does not really re-enable
> > the caching and the performance will stay the same even when the
> > lazy mode is supported on s390.
> > 
> > This is the same pattern as kasan_populate_vmalloc_pte() - which
> > was the only occurrence so far.
> > 
> > Alternatively, the page could be allocated atomically, but I think
> > that is less preferrable.
> 
> I guess the real fix is to pre-allocate all pages, keep the pointers
> to the struct pages in an array, and populate with a different
> mechanism. Similar like the vmalloc code is doing.
> I wanted to keep this code as simple as possible, but...

Actually addressing this makes the code even simpler.
Something like the below should do (untested).

---
 arch/s390/kernel/uv.c | 59 ++++++++++++++++++-------------------------
 1 file changed, 24 insertions(+), 35 deletions(-)

diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 8ea9dd7704ff..8dea30a1166b 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -14,8 +14,8 @@
 #include <linux/memblock.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
-#include <linux/pagewalk.h>
 #include <linux/backing-dev.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <asm/facility.h>
 #include <asm/sections.h>
@@ -210,62 +210,51 @@ int uv_convert_from_secure_pte(pte_t pte)
 	return uv_convert_from_secure_folio(pfn_folio(pte_pfn(pte)));
 }
 
-static int uv_free_range_cb(pte_t *ptep, unsigned long addr, void *data)
-{
-	pte_t pte = ptep_get(ptep);
-
-	if (!pte_present(pte))
-		return 0;
-	/*
-	 * Note: do not update the pte here, since there is no code which
-	 * accesses the memory range, besides bugs. The invalidation of ptes
-	 * and TLB flushing is deferred like for regular vfree() calls.
-	 */
-	__free_page(pte_page(pte));
-	return 0;
-}
-
 void uv_free_stor_var(void *stor_var)
 {
-	unsigned long addr, size;
 	struct vm_struct *area;
+	unsigned long i;
 
 	if (!stor_var)
 		return;
 	area = find_vm_area(stor_var);
 	if (WARN_ON_ONCE(!area || !(area->flags & VM_SPARSE)))
 		return;
-	size = get_vm_area_size(area);
-	addr = (unsigned long)area->addr;
-	apply_to_existing_page_range(&init_mm, addr, size, uv_free_range_cb, NULL);
+	/*
+	 * Do not update PTEs. There is no code which accesses the memory
+	 * range, besides bugs. The invalidation of PTEs and TLB flushing
+	 * is deferred like for regular vfree() calls.
+	 */
+	for (i = 0; i < area->nr_pages; i++)
+		__free_page(area->pages[i]);
+	kvfree(area->pages);
+	area->pages = NULL;
 	free_vm_area(area);
 }
 EXPORT_SYMBOL_FOR_MODULES(uv_free_stor_var, "kvm");
 
-static int uv_alloc_range_cb(pte_t *ptep, unsigned long addr, void *data)
-{
-	struct page *page;
-	pte_t pte;
-
-	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
-	if (!page)
-		return -ENOMEM;
-	pte = __pte(page_to_phys(page) | pgprot_val(PAGE_KERNEL));
-	set_pte(ptep, pte);
-	return 0;
-}
-
 void *uv_alloc_stor_var(unsigned long size)
 {
+	unsigned long i, nr_pages, addr;
 	struct vm_struct *area;
-	unsigned long addr;
 
 	size = PAGE_ALIGN(size);
+	nr_pages = size >> PAGE_SHIFT;
 	area = get_vm_area(size, VM_SPARSE);
 	if (!area)
 		return NULL;
 	addr = (unsigned long)area->addr;
-	if (apply_to_page_range(&init_mm, addr, size, uv_alloc_range_cb, NULL))
+	area->pages = kvcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL_ACCOUNT);
+	if (!area->pages)
+		goto out;
+	for (i = 0; i < nr_pages; i++) {
+		area->nr_pages = i;
+		area->pages[i] = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+		if (!area->pages[i])
+			goto out;
+	}
+	area->nr_pages = nr_pages;
+	if (vm_area_map_pages(area, addr, addr + size, area->pages))
 		goto out;
 	return area->addr;
 out:
-- 
2.53.0