Merge branch 'stable/frontswap-tmemonly' of git://git.kernel.org/pub/scm/linux/kernel/git/djm/tmem into stable/drivers

* 'stable/frontswap-tmemonly' of git://git.kernel.org/pub/scm/linux/kernel/git/djm/tmem:
  xen: prepare tmem shim to handle frontswap

3 files changed, 166 insertions, 13 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index a59638b37c1a..be8732c32185 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -105,4 +105,11 @@ config SWIOTLB_XEN
         depends on PCI
         select SWIOTLB
 
+config XEN_TMEM
+        bool
+        default y if (CLEANCACHE || FRONTSWAP)
+        help
+          Shim to interface in-kernel Transcendent Memory hooks
+          (e.g. cleancache and frontswap) to Xen tmem hypercalls.
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index bbc18258ecc5..7c1bc0a4d9f4 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -1,6 +1,5 @@
 obj-y   += grant-table.o features.o events.o manage.o balloon.o
 obj-y   += xenbus/
-obj-y   += tmem.o
 
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_features.o                       := $(nostackp)
@@ -15,6 +14,7 @@ obj-$(CONFIG_XEN_GRANT_DEV_ALLOC)	+= xen-gntalloc.o
 obj-$(CONFIG_XENFS)                     += xenfs/
 obj-$(CONFIG_XEN_SYS_HYPERVISOR)        += sys-hypervisor.o
 obj-$(CONFIG_XEN_PLATFORM_PCI)          += xen-platform-pci.o
+obj-$(CONFIG_XEN_TMEM)                  += tmem.o
 obj-$(CONFIG_SWIOTLB_XEN)               += swiotlb-xen.o
 obj-$(CONFIG_XEN_DOM0)                  += pci.o
 
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
index 816a44959ef0..d369965e8f8a 100644
--- a/drivers/xen/tmem.c
+++ b/drivers/xen/tmem.c
@@ -1,7 +1,7 @@
 /*
  * Xen implementation for transcendent memory (tmem)
  *
- * Copyright (C) 2009-2010 Oracle Corp.  All rights reserved.
+ * Copyright (C) 2009-2011 Oracle Corp.  All rights reserved.
  * Author: Dan Magenheimer
  */
 
@@ -9,8 +9,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
+#include <linux/module.h>
 #include <linux/cleancache.h>
 
+/* temporary ifdef until include/linux/frontswap.h is upstream */
+#ifdef CONFIG_FRONTSWAP
+#include <linux/frontswap.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <asm/xen/hypercall.h>
@@ -122,14 +128,8 @@ static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid)
         return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0);
 }
 
-static int xen_tmem_destroy_pool(u32 pool_id)
-{
-        struct tmem_oid oid = { { 0 } };
-
-        return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0);
-}
-
-int tmem_enabled;
+int tmem_enabled __read_mostly;
+EXPORT_SYMBOL(tmem_enabled);
 
 static int __init enable_tmem(char *s)
 {
@@ -139,6 +139,14 @@ static int __init enable_tmem(char *s)
 
 __setup("tmem", enable_tmem);
 
+#ifdef CONFIG_CLEANCACHE
+static int xen_tmem_destroy_pool(u32 pool_id)
+{
+        struct tmem_oid oid = { { 0 } };
+
+        return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0);
+}
+
 /* cleancache ops */
 
 static void tmem_cleancache_put_page(int pool, struct cleancache_filekey key,
@@ -240,18 +248,156 @@ static struct cleancache_ops tmem_cleancache_ops = {
         .init_shared_fs = tmem_cleancache_init_shared_fs,
         .init_fs = tmem_cleancache_init_fs
 };
+#endif
 
-static int __init xen_tmem_init(void)
+#ifdef CONFIG_FRONTSWAP
+/* frontswap tmem operations */
+
+/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
+static int tmem_frontswap_poolid;
+
+/*
+ * Swizzling increases objects per swaptype, increasing tmem concurrency
+ * for heavy swaploads.  Later, larger nr_cpus -> larger SWIZ_BITS
+ */
+#define SWIZ_BITS               4
+#define SWIZ_MASK               ((1 << SWIZ_BITS) - 1)
+#define _oswiz(_type, _ind)     ((_type << SWIZ_BITS) | (_ind & SWIZ_MASK))
+#define iswiz(_ind)             (_ind >> SWIZ_BITS)
+
+static inline struct tmem_oid oswiz(unsigned type, u32 ind)
 {
-        struct cleancache_ops old_ops;
+        struct tmem_oid oid = { .oid = { 0 } };
+        oid.oid[0] = _oswiz(type, ind);
+        return oid;
+}
 
+/* returns 0 if the page was successfully put into frontswap, -1 if not */
+static int tmem_frontswap_put_page(unsigned type, pgoff_t offset,
+                                   struct page *page)
+{
+        u64 ind64 = (u64)offset;
+        u32 ind = (u32)offset;
+        unsigned long pfn = page_to_pfn(page);
+        int pool = tmem_frontswap_poolid;
+        int ret;
+
+        if (pool < 0)
+                return -1;
+        if (ind64 != ind)
+                return -1;
+        mb(); /* ensure page is quiescent; tmem may address it with an alias */
+        ret = xen_tmem_put_page(pool, oswiz(type, ind), iswiz(ind), pfn);
+        /* translate Xen tmem return values to linux semantics */
+        if (ret == 1)
+                return 0;
+        else
+                return -1;
+}
+
+/*
+ * returns 0 if the page was successfully gotten from frontswap, -1 if
+ * was not present (should never happen!)
+ */
+static int tmem_frontswap_get_page(unsigned type, pgoff_t offset,
+                                   struct page *page)
+{
+        u64 ind64 = (u64)offset;
+        u32 ind = (u32)offset;
+        unsigned long pfn = page_to_pfn(page);
+        int pool = tmem_frontswap_poolid;
+        int ret;
+
+        if (pool < 0)
+                return -1;
+        if (ind64 != ind)
+                return -1;
+        ret = xen_tmem_get_page(pool, oswiz(type, ind), iswiz(ind), pfn);
+        /* translate Xen tmem return values to linux semantics */
+        if (ret == 1)
+                return 0;
+        else
+                return -1;
+}
+
+/* flush a single page from frontswap */
+static void tmem_frontswap_flush_page(unsigned type, pgoff_t offset)
+{
+        u64 ind64 = (u64)offset;
+        u32 ind = (u32)offset;
+        int pool = tmem_frontswap_poolid;
+
+        if (pool < 0)
+                return;
+        if (ind64 != ind)
+                return;
+        (void) xen_tmem_flush_page(pool, oswiz(type, ind), iswiz(ind));
+}
+
+/* flush all pages from the passed swaptype */
+static void tmem_frontswap_flush_area(unsigned type)
+{
+        int pool = tmem_frontswap_poolid;
+        int ind;
+
+        if (pool < 0)
+                return;
+        for (ind = SWIZ_MASK; ind >= 0; ind--)
+                (void)xen_tmem_flush_object(pool, oswiz(type, ind));
+}
+
+static void tmem_frontswap_init(unsigned ignored)
+{
+        struct tmem_pool_uuid private = TMEM_POOL_PRIVATE_UUID;
+
+        /* a single tmem poolid is used for all frontswap "types" (swapfiles) */
+        if (tmem_frontswap_poolid < 0)
+                tmem_frontswap_poolid =
+                    xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE);
+}
+
+static int __initdata use_frontswap = 1;
+
+static int __init no_frontswap(char *s)
+{
+        use_frontswap = 0;
+        return 1;
+}
+
+__setup("nofrontswap", no_frontswap);
+
+static struct frontswap_ops tmem_frontswap_ops = {
+        .put_page = tmem_frontswap_put_page,
+        .get_page = tmem_frontswap_get_page,
+        .flush_page = tmem_frontswap_flush_page,
+        .flush_area = tmem_frontswap_flush_area,
+        .init = tmem_frontswap_init
+};
+#endif
+
+static int __init xen_tmem_init(void)
+{
         if (!xen_domain())
                 return 0;
+#ifdef CONFIG_FRONTSWAP
+        if (tmem_enabled && use_frontswap) {
+                char *s = "";
+                struct frontswap_ops old_ops =
+                        frontswap_register_ops(&tmem_frontswap_ops);
+
+                tmem_frontswap_poolid = -1;
+                if (old_ops.init != NULL)
+                        s = " (WARNING: frontswap_ops overridden)";
+                printk(KERN_INFO "frontswap enabled, RAM provided by "
+                                 "Xen Transcendent Memory\n");
+        }
+#endif
 #ifdef CONFIG_CLEANCACHE
         BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
         if (tmem_enabled && use_cleancache) {
                 char *s = "";
-                old_ops = cleancache_register_ops(&tmem_cleancache_ops);
+                struct cleancache_ops old_ops =
+                        cleancache_register_ops(&tmem_cleancache_ops);
                 if (old_ops.init_fs != NULL)
                         s = " (WARNING: cleancache_ops overridden)";
                 printk(KERN_INFO "cleancache enabled, RAM provided by "