From 0b7c71b8b4afcbc92a9ef549d485c54da92204b3 Mon Sep 17 00:00:00 2001

From: "plai@redhat.com" <plai@redhat.com>

Date: Fri, 31 Aug 2018 16:25:56 +0200

Subject: [PATCH 14/29] hostmem-file: add the 'pmem' option

RH-Author: plai@redhat.com

Message-id: <1535732759-22481-7-git-send-email-plai@redhat.com>

Patchwork-id: 82007

O-Subject: [RHEL7.6 PATCH BZ 1539280 6/9] hostmem-file: add the 'pmem' option

Bugzilla: 1539280

RH-Acked-by: Michael S. Tsirkin <mst@redhat.com>

RH-Acked-by: Pankaj Gupta <pagupta@redhat.com>

RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>

From: Junyan He <junyan.he@intel.com>

When QEMU emulates vNVDIMM labels and migrates vNVDIMM devices, it

needs to know whether the backend storage is a real persistent memory,

in order to decide whether special operations should be performed to

ensure the data persistence.

This boolean option 'pmem' allows users to specify whether the backend

storage of memory-backend-file is a real persistent memory. If

'pmem=on', QEMU will set the flag RAM_PMEM in the RAM block of the

corresponding memory region. If 'pmem' is set while lack of libpmem

support, a error is generated.

Signed-off-by: Junyan He <junyan.he@intel.com>

Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com>

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Igor Mammedov <imammedo@redhat.com>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Michael S. Tsirkin <mst@redhat.com>

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

(cherry picked from commit a4de8552b2580adf6fa4874439217b65d3bdd88b)

Signed-off-by: Paul Lai <plai@redhat.com>

Resolved Conflicts:

	docs/nvdimm.txt

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 backends/hostmem-file.c | 43 +++++++++++++++++++++++++++++++++++++++++--

 docs/nvdimm.txt         | 42 ++++++++++++++++++++++++++++++++++++++++++

 exec.c                  |  8 ++++++++

 include/exec/memory.h   |  4 ++++

 include/exec/ram_addr.h |  3 +++

 qemu-options.hx         |  7 +++++++

 6 files changed, 105 insertions(+), 2 deletions(-)

diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c

index 34c68bb..2476dcb 100644

--- a/backends/hostmem-file.c

+++ b/backends/hostmem-file.c

@@ -12,6 +12,7 @@

 #include "qemu/osdep.h"

 #include "qapi/error.h"

 #include "qemu-common.h"

+#include "qemu/error-report.h"

 #include "sysemu/hostmem.h"

 #include "sysemu/sysemu.h"

 #include "qom/object_interfaces.h"

@@ -31,9 +32,10 @@ typedef struct HostMemoryBackendFile HostMemoryBackendFile;

 struct HostMemoryBackendFile {

     HostMemoryBackend parent_obj;

-    bool discard_data;

     char *mem_path;

     uint64_t align;

+    bool discard_data;

+    bool is_pmem;

 };

 static void

@@ -59,7 +61,8 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)

         memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),

                                  path,

                                  backend->size, fb->align,

-                                 backend->share ? RAM_SHARED : 0,

+                                 (backend->share ? RAM_SHARED : 0) |

+                                 (fb->is_pmem ? RAM_PMEM : 0),

                                  fb->mem_path, errp);

         g_free(path);

     }

@@ -131,6 +134,39 @@ static void file_memory_backend_set_align(Object *o, Visitor *v,

     error_propagate(errp, local_err);

 }

+static bool file_memory_backend_get_pmem(Object *o, Error **errp)

+{

+    return MEMORY_BACKEND_FILE(o)->is_pmem;

+}

+

+static void file_memory_backend_set_pmem(Object *o, bool value, Error **errp)

+{

+    HostMemoryBackend *backend = MEMORY_BACKEND(o);

+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);

+

+    if (host_memory_backend_mr_inited(backend)) {

+        error_setg(errp, "cannot change property 'pmem' of %s '%s'",

+                   object_get_typename(o),

+                   object_get_canonical_path_component(o));

+        return;

+    }

+

+#ifndef CONFIG_LIBPMEM

+    if (value) {

+        Error *local_err = NULL;

+        error_setg(&local_err,

+                   "Lack of libpmem support while setting the 'pmem=on'"

+                   " of %s '%s'. We can't ensure data persistence.",

+                   object_get_typename(o),

+                   object_get_canonical_path_component(o));

+        error_propagate(errp, local_err);

+        return;

+    }

+#endif

+

+    fb->is_pmem = value;

+}

+

 static void file_backend_unparent(Object *obj)

 {

     HostMemoryBackend *backend = MEMORY_BACKEND(obj);

@@ -162,6 +198,9 @@ file_backend_class_init(ObjectClass *oc, void *data)

         file_memory_backend_get_align,

         file_memory_backend_set_align,

         NULL, NULL, &error_abort);

+    object_class_property_add_bool(oc, "pmem",

+        file_memory_backend_get_pmem, file_memory_backend_set_pmem,

+        &error_abort);

 }

 static void file_backend_instance_finalize(Object *o)

diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt

index e903d8b..5f158a6 100644

--- a/docs/nvdimm.txt

+++ b/docs/nvdimm.txt

@@ -153,3 +153,45 @@ guest NVDIMM region mapping structure.  This unarmed flag indicates

 guest software that this vNVDIMM device contains a region that cannot

 accept persistent writes. In result, for example, the guest Linux

 NVDIMM driver, marks such vNVDIMM device as read-only.

+

+NVDIMM Persistence

+------------------

+

+ACPI 6.2 Errata A added support for a new Platform Capabilities Structure

+which allows the platform to communicate what features it supports related to

+NVDIMM data persistence.  Users can provide a persistence value to a guest via

+the optional "nvdimm-persistence" machine command line option:

+

+    -machine pc,accel=kvm,nvdimm,nvdimm-persistence=cpu

+

+There are currently two valid values for this option:

+

+"mem-ctrl" - The platform supports flushing dirty data from the memory

+             controller to the NVDIMMs in the event of power loss.

+

+"cpu"      - The platform supports flushing dirty data from the CPU cache to

+             the NVDIMMs in the event of power loss.  This implies that the

+             platform also supports flushing dirty data through the memory

+             controller on power loss.

+

+If the vNVDIMM backend is in host persistent memory that can be accessed in

+SNIA NVM Programming Model [1] (e.g., Intel NVDIMM), it's suggested to set

+the 'pmem' option of memory-backend-file to 'on'. When 'pmem' is 'on' and QEMU

+is built with libpmem [2] support (configured with --enable-libpmem), QEMU

+will take necessary operations to guarantee the persistence of its own writes

+to the vNVDIMM backend(e.g., in vNVDIMM label emulation and live migration).

+If 'pmem' is 'on' while there is no libpmem support, qemu will exit and report

+a "lack of libpmem support" message to ensure the persistence is available.

+For example, if we want to ensure the persistence for some backend file,

+use the QEMU command line:

+

+    -object memory-backend-file,id=nv_mem,mem-path=/XXX/yyy,size=4G,pmem=on

+

+References

+----------

+

+[1] NVM Programming Model (NPM)

+	Version 1.2

+    https://www.snia.org/sites/default/files/technical_work/final/NVMProgrammingModel_v1.2.pdf

+[2] Persistent Memory Development Kit (PMDK), formerly known as NVML project, home page:

+    http://pmem.io/pmdk/

diff --git a/exec.c b/exec.c

index 295142b..c670185 100644

--- a/exec.c

+++ b/exec.c

@@ -2045,6 +2045,9 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,

     Error *local_err = NULL;

     int64_t file_size;

+    /* Just support these ram flags by now. */

+    assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0);

+

     if (xen_enabled()) {

         error_setg(errp, "-mem-path not supported with Xen");

         return NULL;

@@ -3863,6 +3866,11 @@ err:

     return ret;

 }

+bool ramblock_is_pmem(RAMBlock *rb)

+{

+    return rb->flags & RAM_PMEM;

+}

+

 #endif

 void page_size_init(void)

diff --git a/include/exec/memory.h b/include/exec/memory.h

index b3abe61..fd2c574 100644

--- a/include/exec/memory.h

+++ b/include/exec/memory.h

@@ -122,6 +122,9 @@ typedef struct IOMMUNotifier IOMMUNotifier;

 /* RAM can be migrated */

 #define RAM_MIGRATABLE (1 << 4)

+/* RAM is a persistent kind memory */

+#define RAM_PMEM (1 << 5)

+

 static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,

                                        IOMMUNotifierFlag flags,

                                        hwaddr start, hwaddr end)

@@ -541,6 +544,7 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr,

  *         (getpagesize()) will be used.

  * @ram_flags: Memory region features:

  *             - RAM_SHARED: memory must be mmaped with the MAP_SHARED flag

+ *             - RAM_PMEM: the memory is persistent memory

  *             Other bits are ignored now.

  * @path: the path in which to allocate the RAM.

  * @errp: pointer to Error*, to store an error if it happens.

diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h

index 67e163e..922305d 100644

--- a/include/exec/ram_addr.h

+++ b/include/exec/ram_addr.h

@@ -70,6 +70,8 @@ static inline unsigned long int ramblock_recv_bitmap_offset(void *host_addr,

     return host_addr_offset >> TARGET_PAGE_BITS;

 }

+bool ramblock_is_pmem(RAMBlock *rb);

+

 long qemu_getrampagesize(void);

 unsigned long last_ram_page(void);

@@ -84,6 +86,7 @@ unsigned long last_ram_page(void);

  *  @ram_flags: specify the properties of the ram block, which can be one

  *              or bit-or of following values

  *              - RAM_SHARED: mmap the backing file or device with MAP_SHARED

+ *              - RAM_PMEM: the backend @mem_path or @fd is persistent memory

  *              Other bits are ignored.

  *  @mem_path or @fd: specify the backing file or device

  *  @errp: pointer to Error*, to store an error if it happens

diff --git a/qemu-options.hx b/qemu-options.hx

index 4271cd3..5c58760 100644

--- a/qemu-options.hx

+++ b/qemu-options.hx

@@ -4045,6 +4045,13 @@ requires an alignment different than the default one used by QEMU, eg

 the device DAX /dev/dax0.0 requires 2M alignment rather than 4K. In

 such cases, users can specify the required alignment via this option.

+The @option{pmem} option specifies whether the backing file specified

+by @option{mem-path} is in host persistent memory that can be accessed

+using the SNIA NVM programming model (e.g. Intel NVDIMM).

+If @option{pmem} is set to 'on', QEMU will take necessary operations to

+guarantee the persistence of its own writes to @option{mem-path}

+(e.g. in vNVDIMM label emulation and live migration).

+

 @item -object memory-backend-ram,id=@var{id},merge=@var{on|off},dump=@var{on|off},share=@var{on|off},prealloc=@var{on|off},size=@var{size},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave}

 Creates a memory backend object, which can be used to back the guest RAM.

-- 

1.8.3.1