@@ -417,6 +417,13 @@ HYPERVISOR_nmi_op(unsigned long op, unsi
return _hypercall2(int, nmi_op, op, arg);
}
+static inline int
+HYPERVISOR_tmem_op(
+ struct tmem_op *op)
+{
+ return _hypercall1(int, tmem_op, op);
+}
+
static inline void
MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
{
@@ -1,5 +1,6 @@
obj-y += grant-table.o features.o events.o manage.o
obj-y += xenbus/
+obj-y += tmem.o
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_features.o := $(nostackp)
@@ -9,4 +10,4 @@ obj-$(CONFIG_XEN_XENCOMM) += xencomm.o
obj-$(CONFIG_XEN_BALLOON) += balloon.o
obj-$(CONFIG_XEN_DEV_EVTCHN) += evtchn.o
obj-$(CONFIG_XENFS) += xenfs/
-obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
\ No newline at end of file
+obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
@@ -0,0 +1,238 @@
+/*
+ * Xen implementation for transcendent memory (tmem)
+ *
+ * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/cleancache.h>
+
+#include <xen/xen.h>
+#include <xen/interface/xen.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+#include <asm/xen/hypervisor.h>
+
+#define TMEM_CONTROL 0
+#define TMEM_NEW_POOL 1
+#define TMEM_DESTROY_POOL 2
+#define TMEM_NEW_PAGE 3
+#define TMEM_PUT_PAGE 4
+#define TMEM_GET_PAGE 5
+#define TMEM_FLUSH_PAGE 6
+#define TMEM_FLUSH_OBJECT 7
+#define TMEM_READ 8
+#define TMEM_WRITE 9
+#define TMEM_XCHG 10
+
+/* Bits for HYPERVISOR_tmem_op(TMEM_NEW_POOL) */
+#define TMEM_POOL_PERSIST 1
+#define TMEM_POOL_SHARED 2
+#define TMEM_POOL_PAGESIZE_SHIFT 4
+
+
+struct tmem_pool_uuid {
+ u64 uuid_lo;
+ u64 uuid_hi;
+};
+
+#define TMEM_POOL_PRIVATE_UUID { 0, 0 }
+
+/* flags for tmem_ops.new_pool */
+#define TMEM_POOL_PERSIST 1
+#define TMEM_POOL_SHARED 2
+
+/* xen tmem foundation ops/hypercalls */
+
+static inline int xen_tmem_op(u32 tmem_cmd, u32 tmem_pool, u64 object,
+ u32 index, unsigned long gmfn, u32 tmem_offset, u32 pfn_offset, u32 len)
+{
+ struct tmem_op op;
+ int rc = 0;
+
+ op.cmd = tmem_cmd;
+ op.pool_id = tmem_pool;
+ op.u.gen.object = object;
+ op.u.gen.index = index;
+ op.u.gen.tmem_offset = tmem_offset;
+ op.u.gen.pfn_offset = pfn_offset;
+ op.u.gen.len = len;
+ set_xen_guest_handle(op.u.gen.gmfn, (void *)gmfn);
+ rc = HYPERVISOR_tmem_op(&op);
+ return rc;
+}
+
+static int xen_tmem_new_pool(struct tmem_pool_uuid uuid,
+ u32 flags, unsigned long pagesize)
+{
+ struct tmem_op op;
+ int rc = 0, pageshift;
+
+ for (pageshift = 0; pagesize != 1; pageshift++)
+ pagesize >>= 1;
+ flags |= (pageshift - 12) << TMEM_POOL_PAGESIZE_SHIFT;
+ op.cmd = TMEM_NEW_POOL;
+ op.u.new.uuid[0] = uuid.uuid_lo;
+ op.u.new.uuid[1] = uuid.uuid_hi;
+ op.u.new.flags = flags;
+ rc = HYPERVISOR_tmem_op(&op);
+ return rc;
+}
+
+/* xen generic tmem ops */
+
+static int xen_tmem_put_page(u32 pool_id, u64 object, u32 index,
+ unsigned long pfn)
+{
+ unsigned long gmfn = xen_pv_domain() ? pfn_to_mfn(pfn) : pfn;
+
+ return xen_tmem_op(TMEM_PUT_PAGE, pool_id, object, index,
+ gmfn, 0, 0, 0);
+}
+
+static int xen_tmem_get_page(u32 pool_id, u64 object, u32 index,
+ unsigned long pfn)
+{
+ unsigned long gmfn = xen_pv_domain() ? pfn_to_mfn(pfn) : pfn;
+
+ return xen_tmem_op(TMEM_GET_PAGE, pool_id, object, index,
+ gmfn, 0, 0, 0);
+}
+
+static int xen_tmem_flush_page(u32 pool_id, u64 object, u32 index)
+{
+ return xen_tmem_op(TMEM_FLUSH_PAGE, pool_id, object, index,
+ 0, 0, 0, 0);
+}
+
+static int xen_tmem_flush_object(u32 pool_id, u64 object)
+{
+ return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, object, 0, 0, 0, 0, 0);
+}
+
+static int xen_tmem_destroy_pool(u32 pool_id)
+{
+ return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, 0, 0, 0, 0, 0, 0);
+}
+
+int tmem_enabled;
+
+static int __init enable_tmem(char *s)
+{
+ tmem_enabled = 1;
+ return 1;
+}
+
+__setup("tmem", enable_tmem);
+
+/* cleancache ops */
+
+static void tmem_cleancache_put_page(int pool, ino_t inode, pgoff_t index,
+ struct page *page)
+{
+ u32 ind = (u32) index;
+ unsigned long pfn = page_to_pfn(page);
+
+ if (pool < 0)
+ return;
+ if (ind != index)
+ return;
+ mb(); /* ensure page is quiescent; tmem may address it with an alias */
+ (void)xen_tmem_put_page((u32)pool, (u64)inode, ind, pfn);
+}
+
+static int tmem_cleancache_get_page(int pool, ino_t inode, pgoff_t index,
+ struct page *page)
+{
+ u32 ind = (u32) index;
+ unsigned long pfn = page_to_pfn(page);
+ int ret;
+
+ /* translate return values to linux semantics */
+ if (pool < 0)
+ return -1;
+ if (ind != index)
+ return -1;
+ ret = xen_tmem_get_page((u32)pool, (u64)inode, ind, pfn);
+ if (ret == 1)
+ return 0;
+ else
+ return -1;
+}
+
+static void tmem_cleancache_flush_page(int pool, ino_t inode, pgoff_t index)
+{
+ u32 ind = (u32) index;
+
+ if (pool < 0)
+ return;
+ if (ind != index)
+ return;
+ (void)xen_tmem_flush_page((u32)pool, (u64)inode, ind);
+}
+
+static void tmem_cleancache_flush_inode(int pool, ino_t inode)
+{
+ if (pool < 0)
+ return;
+ (void)xen_tmem_flush_object((u32)pool, (u64)inode);
+}
+
+static void tmem_cleancache_flush_fs(int pool)
+{
+ if (pool < 0)
+ return;
+ (void)xen_tmem_destroy_pool((u32)pool);
+}
+
+static int tmem_cleancache_init_fs(size_t pagesize)
+{
+ struct tmem_pool_uuid uuid_private = TMEM_POOL_PRIVATE_UUID;
+
+ return xen_tmem_new_pool(uuid_private, 0, pagesize);
+}
+
+static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize)
+{
+ struct tmem_pool_uuid shared_uuid;
+
+ shared_uuid.uuid_lo = *(u64 *)uuid;
+ shared_uuid.uuid_hi = *(u64 *)(&uuid[8]);
+ return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize);
+}
+
+static int use_cleancache = 1;
+
+static int __init no_cleancache(char *s)
+{
+ use_cleancache = 0;
+ return 1;
+}
+
+__setup("nocleancache", no_cleancache);
+
+static int __init xen_tmem_init(void)
+{
+ if (!xen_domain())
+ return 0;
+#ifdef CONFIG_CLEANCACHE
+ if (tmem_enabled && use_cleancache) {
+ cleancache_ops.put_page = tmem_cleancache_put_page;
+ cleancache_ops.get_page = tmem_cleancache_get_page;
+ cleancache_ops.flush_page = tmem_cleancache_flush_page;
+ cleancache_ops.flush_inode = tmem_cleancache_flush_inode;
+ cleancache_ops.flush_fs = tmem_cleancache_flush_fs;
+ cleancache_ops.init_shared_fs = tmem_cleancache_init_shared_fs;
+ cleancache_ops.init_fs = tmem_cleancache_init_fs;
+ printk(KERN_INFO "cleancache enabled, RAM provided by "
+ "Xen Transcendent Memory\n");
+ }
+#endif
+ return 0;
+}
+
+module_init(xen_tmem_init)
@@ -58,6 +58,7 @@
#define __HYPERVISOR_event_channel_op 32
#define __HYPERVISOR_physdev_op 33
#define __HYPERVISOR_hvm_op 34
+#define __HYPERVISOR_tmem_op 38
/* Architecture-specific hypercall definitions. */
#define __HYPERVISOR_arch_0 48
@@ -461,6 +462,25 @@ typedef uint8_t xen_domain_handle_t[16];
#define __mk_unsigned_long(x) x ## UL
#define mk_unsigned_long(x) __mk_unsigned_long(x)
+struct tmem_op {
+ uint32_t cmd;
+ int32_t pool_id;
+ union {
+ struct { /* for cmd == TMEM_NEW_POOL */
+ uint64_t uuid[2];
+ uint32_t flags;
+ } new;
+ struct {
+ uint64_t object;
+ uint32_t index;
+ uint32_t tmem_offset;
+ uint32_t pfn_offset;
+ uint32_t len;
+ GUEST_HANDLE(void) gmfn; /* guest machine page frame */
+ } gen;
+ } u;
+};
+
#else /* __ASSEMBLY__ */
/* In assembly code we cannot use C numeric constant suffixes. */