powerpc: Prepare to support kernel handling of IOMMU map/unmap

The current VFIO-on-POWER implementation supports only user mode
driven mapping, i.e. QEMU is sending requests to map/unmap pages.
However this approach is really slow, so we want to move that to KVM.
Since H_PUT_TCE can be extremely performance sensitive (especially with
network adapters where each packet needs to be mapped/unmapped) we chose
to implement that as a "fast" hypercall directly in "real
mode" (processor still in the guest context but MMU off).

To be able to do that, we need to provide some facilities to
access the struct page count within that real mode environment as things
like the sparsemem vmemmap mappings aren't accessible.

This adds an API function realmode_pfn_to_page() to get page struct when
MMU is off.

This adds to MM a new function put_page_unless_one() which drops a page
if counter is bigger than 1. It is going to be used when MMU is off
(for example, real mode on PPC64) and we want to make sure that page
release will not happen in real mode as it may crash the kernel in
a horrible way.

CONFIG_SPARSEMEM_VMEMMAP and CONFIG_FLATMEM are supported.

Cc: linux-mm@kvack.org
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 69 insertions, 2 deletions

diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 46db09414a1..4a191c47286 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -394,6 +394,8 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
 	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
 }
 
+struct page *realmode_pfn_to_page(unsigned long pfn);
+
 static inline char *get_hpte_slot_array(pmd_t *pmdp)
 {
 	/*
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 8ed035d2edb..e3734edffa6 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -304,5 +304,54 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
 {
 }
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+/*
+ * We do not have access to the sparsemem vmemmap, so we fallback to
+ * walking the list of sparsemem blocks which we already maintain for
+ * the sake of crashdump. In the long run, we might want to maintain
+ * a tree if performance of that linear walk becomes a problem.
+ *
+ * realmode_pfn_to_page functions can fail due to:
+ * 1) As real sparsemem blocks do not lay in RAM continously (they
+ * are in virtual address space which is not available in the real mode),
+ * the requested page struct can be split between blocks so get_page/put_page
+ * may fail.
+ * 2) When huge pages are used, the get_page/put_page API will fail
+ * in real mode as the linked addresses in the page struct are virtual
+ * too.
+ */
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct vmemmap_backing *vmem_back;
+	struct page *page;
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
+
+	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
+		if (pg_va < vmem_back->virt_addr)
+			continue;
+
+		/* Check that page struct is not split between real pages */
+		if ((pg_va + sizeof(struct page)) >
+				(vmem_back->virt_addr + page_size))
+			return NULL;
+
+		page = (struct page *) (vmem_back->phys + pg_va -
+				vmem_back->virt_addr);
+		return page;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#elif defined(CONFIG_FLATMEM)
+
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	return page;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8b6e55ee885..1a0668e5a4e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -297,12 +297,26 @@ static inline int put_page_testzero(struct page *page)
 /*
  * Try to grab a ref unless the page has a refcount of zero, return false if
  * that is the case.
+ * This can be called when MMU is off so it must not access
+ * any of the virtual mappings.
  */
 static inline int get_page_unless_zero(struct page *page)
 {
 	return atomic_inc_not_zero(&page->_count);
 }
 
+/*
+ * Try to drop a ref unless the page has a refcount of one, return false if
+ * that is the case.
+ * This is to make sure that the refcount won't become zero after this drop.
+ * This can be called when MMU is off so it must not access
+ * any of the virtual mappings.
+ */
+static inline int put_page_unless_one(struct page *page)
+{
+	return atomic_add_unless(&page->_count, -1, 1);
+}
+
 extern int page_is_ram(unsigned long pfn);
 
 /* Support for virtually mapped pages */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6d53675c2b5..98ada58f994 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -329,7 +329,9 @@ static inline void set_page_writeback(struct page *page)
  * System with lots of page flags available. This allows separate
  * flags for PageHead() and PageTail() checks of compound pages so that bit
  * tests can be used in performance sensitive paths. PageCompound is
- * generally not used in hot code paths.
+ * generally not used in hot code paths except arch/powerpc/mm/init_64.c
+ * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
+ * and avoid handling those in real mode.
  */
 __PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
 __PAGEFLAG(Tail, tail)