diff mbox

[v10,2/3] Differentiate IO/mem resources tracked by ioreq server

Message ID 1453195678-25944-3-git-send-email-yu.c.zhang@linux.intel.com
State New, archived
Headers show

Commit Message

Yu Zhang Jan. 19, 2016, 9:27 a.m. UTC
Currently in ioreq server, guest write-protected ram pages are
tracked in the same rangeset with device mmio resources. Yet
unlike device mmio, which can be in big chunks, the guest write-
protected pages may be discrete ranges with 4K bytes each. This
patch uses a seperate rangeset for the guest ram pages.

To differentiate the ioreq type between the write-protected memory
ranges and the mmio ranges when selecting an ioreq server, the p2m
type is retrieved by calling get_page_from_gfn(). And we do not
need to worry about the p2m type change during the ioreq selection
process.

Note: Previously, a new hypercall or subop was suggested to map
write-protected pages into ioreq server. However, it turned out
handler of this new hypercall would be almost the same with the
existing pair - HVMOP_[un]map_io_range_to_ioreq_server, and there's
already a type parameter in this hypercall. So no new hypercall
defined, only a new type is introduced.

Acked-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Shuai Ruan <shuai.ruan@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
---
 tools/libxc/include/xenctrl.h    | 31 ++++++++++++++++++++
 tools/libxc/xc_domain.c          | 61 ++++++++++++++++++++++++++++++++++++++++
 xen/arch/x86/hvm/hvm.c           | 27 +++++++++++++++---
 xen/include/asm-x86/hvm/domain.h |  2 +-
 xen/include/public/hvm/hvm_op.h  |  1 +
 5 files changed, 117 insertions(+), 5 deletions(-)

Comments

Paul Durrant Jan. 19, 2016, 9:47 a.m. UTC | #1
> -----Original Message-----
> From: Yu Zhang [mailto:yu.c.zhang@linux.intel.com]
> Sent: 19 January 2016 09:28
> To: xen-devel@lists.xen.org
> Cc: Paul Durrant; Stefano Stabellini; Keir (Xen.org); jbeulich@suse.com;
> Andrew Cooper; Wei Liu; Kevin Tian; zhiyuan.lv@intel.com
> Subject: [PATCH v10 2/3] Differentiate IO/mem resources tracked by ioreq
> server
> 
> Currently in ioreq server, guest write-protected ram pages are
> tracked in the same rangeset with device mmio resources. Yet
> unlike device mmio, which can be in big chunks, the guest write-
> protected pages may be discrete ranges with 4K bytes each. This
> patch uses a seperate rangeset for the guest ram pages.
> 
> To differentiate the ioreq type between the write-protected memory
> ranges and the mmio ranges when selecting an ioreq server, the p2m
> type is retrieved by calling get_page_from_gfn(). And we do not
> need to worry about the p2m type change during the ioreq selection
> process.
> 
> Note: Previously, a new hypercall or subop was suggested to map
> write-protected pages into ioreq server. However, it turned out
> handler of this new hypercall would be almost the same with the
> existing pair - HVMOP_[un]map_io_range_to_ioreq_server, and there's
> already a type parameter in this hypercall. So no new hypercall
> defined, only a new type is introduced.
> 
> Acked-by: Wei Liu <wei.liu2@citrix.com>
> Acked-by: Ian Campbell <ian.campbell@citrix.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
> Signed-off-by: Shuai Ruan <shuai.ruan@linux.intel.com>
> Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>

Reviewed-by: Paul Durrant <paul.durrant@citrix.com>

> ---
>  tools/libxc/include/xenctrl.h    | 31 ++++++++++++++++++++
>  tools/libxc/xc_domain.c          | 61
> ++++++++++++++++++++++++++++++++++++++++
>  xen/arch/x86/hvm/hvm.c           | 27 +++++++++++++++---
>  xen/include/asm-x86/hvm/domain.h |  2 +-
>  xen/include/public/hvm/hvm_op.h  |  1 +
>  5 files changed, 117 insertions(+), 5 deletions(-)
> 
> diff --git a/tools/libxc/include/xenctrl.h b/tools/libxc/include/xenctrl.h
> index 079cad0..036c72d 100644
> --- a/tools/libxc/include/xenctrl.h
> +++ b/tools/libxc/include/xenctrl.h
> @@ -2023,6 +2023,37 @@ int
> xc_hvm_unmap_io_range_from_ioreq_server(xc_interface *xch,
>                                              int is_mmio,
>                                              uint64_t start,
>                                              uint64_t end);
> +/**
> + * This function registers a range of write-protected memory for emulation.
> + *
> + * @parm xch a handle to an open hypervisor interface.
> + * @parm domid the domain id to be serviced
> + * @parm id the IOREQ Server id.
> + * @parm start start of range
> + * @parm end end of range (inclusive).
> + * @return 0 on success, -1 on failure.
> + */
> +int xc_hvm_map_wp_mem_range_to_ioreq_server(xc_interface *xch,
> +                                            domid_t domid,
> +                                            ioservid_t id,
> +                                            xen_pfn_t start,
> +                                            xen_pfn_t end);
> +
> +/**
> + * This function deregisters a range of write-protected memory for
> emulation.
> + *
> + * @parm xch a handle to an open hypervisor interface.
> + * @parm domid the domain id to be serviced
> + * @parm id the IOREQ Server id.
> + * @parm start start of range
> + * @parm end end of range (inclusive).
> + * @return 0 on success, -1 on failure.
> + */
> +int xc_hvm_unmap_wp_mem_range_from_ioreq_server(xc_interface
> *xch,
> +                                                domid_t domid,
> +                                                ioservid_t id,
> +                                                xen_pfn_t start,
> +                                                xen_pfn_t end);
> 
>  /**
>   * This function registers a PCI device for config space emulation.
> diff --git a/tools/libxc/xc_domain.c b/tools/libxc/xc_domain.c
> index 99e0d48..4f43695 100644
> --- a/tools/libxc/xc_domain.c
> +++ b/tools/libxc/xc_domain.c
> @@ -1544,6 +1544,67 @@ int
> xc_hvm_unmap_io_range_from_ioreq_server(xc_interface *xch, domid_t
> domid,
>      return rc;
>  }
> 
> +int xc_hvm_map_wp_mem_range_to_ioreq_server(xc_interface *xch,
> +                                            domid_t domid,
> +                                            ioservid_t id,
> +                                            xen_pfn_t start,
> +                                            xen_pfn_t end)
> +{
> +    DECLARE_HYPERCALL;
> +    DECLARE_HYPERCALL_BUFFER(xen_hvm_io_range_t, arg);
> +    int rc;
> +
> +    arg = xc_hypercall_buffer_alloc(xch, arg, sizeof(*arg));
> +    if ( arg == NULL )
> +        return -1;
> +
> +    hypercall.op     = __HYPERVISOR_hvm_op;
> +    hypercall.arg[0] = HVMOP_map_io_range_to_ioreq_server;
> +    hypercall.arg[1] = HYPERCALL_BUFFER_AS_ARG(arg);
> +
> +    arg->domid = domid;
> +    arg->id = id;
> +    arg->type = HVMOP_IO_RANGE_WP_MEM;
> +    arg->start = start;
> +    arg->end = end;
> +
> +    rc = do_xen_hypercall(xch, &hypercall);
> +
> +    xc_hypercall_buffer_free(xch, arg);
> +    return rc;
> +}
> +
> +int xc_hvm_unmap_wp_mem_range_from_ioreq_server(xc_interface
> *xch,
> +                                                domid_t domid,
> +                                                ioservid_t id,
> +                                                xen_pfn_t start,
> +                                                xen_pfn_t end)
> +{
> +    DECLARE_HYPERCALL;
> +    DECLARE_HYPERCALL_BUFFER(xen_hvm_io_range_t, arg);
> +    int rc;
> +
> +    arg = xc_hypercall_buffer_alloc(xch, arg, sizeof(*arg));
> +    if ( arg == NULL )
> +        return -1;
> +
> +    hypercall.op     = __HYPERVISOR_hvm_op;
> +    hypercall.arg[0] = HVMOP_unmap_io_range_from_ioreq_server;
> +    hypercall.arg[1] = HYPERCALL_BUFFER_AS_ARG(arg);
> +
> +    arg->domid = domid;
> +    arg->id = id;
> +    arg->type = HVMOP_IO_RANGE_WP_MEM;
> +    arg->start = start;
> +    arg->end = end;
> +
> +    rc = do_xen_hypercall(xch, &hypercall);
> +
> +    xc_hypercall_buffer_free(xch, arg);
> +    return rc;
> +
> +}
> +
>  int xc_hvm_map_pcidev_to_ioreq_server(xc_interface *xch, domid_t
> domid,
>                                        ioservid_t id, uint16_t segment,
>                                        uint8_t bus, uint8_t device,
> diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
> index f646c1e..d59e7bc 100644
> --- a/xen/arch/x86/hvm/hvm.c
> +++ b/xen/arch/x86/hvm/hvm.c
> @@ -935,6 +935,9 @@ static void hvm_ioreq_server_free_rangesets(struct
> hvm_ioreq_server *s,
>          rangeset_destroy(s->range[i]);
>  }
> 
> +const char *io_range_name[NR_IO_RANGE_TYPES] =
> +                                {"port", "mmio", "pci", "wp-mem"};
> +
>  static int hvm_ioreq_server_alloc_rangesets(struct hvm_ioreq_server *s,
>                                              bool_t is_default)
>  {
> @@ -949,10 +952,7 @@ static int hvm_ioreq_server_alloc_rangesets(struct
> hvm_ioreq_server *s,
>          char *name;
> 
>          rc = asprintf(&name, "ioreq_server %d %s", s->id,
> -                      (i == HVMOP_IO_RANGE_PORT) ? "port" :
> -                      (i == HVMOP_IO_RANGE_MEMORY) ? "memory" :
> -                      (i == HVMOP_IO_RANGE_PCI) ? "pci" :
> -                      "");
> +                      (i < NR_IO_RANGE_TYPES) ? io_range_name[i] : "");
>          if ( rc )
>              goto fail;
> 
> @@ -1270,6 +1270,7 @@ static int
> hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
>              case HVMOP_IO_RANGE_PORT:
>              case HVMOP_IO_RANGE_MEMORY:
>              case HVMOP_IO_RANGE_PCI:
> +            case HVMOP_IO_RANGE_WP_MEM:
>                  r = s->range[type];
>                  break;
> 
> @@ -1321,6 +1322,7 @@ static int
> hvm_unmap_io_range_from_ioreq_server(struct domain *d, ioservid_t id,
>              case HVMOP_IO_RANGE_PORT:
>              case HVMOP_IO_RANGE_MEMORY:
>              case HVMOP_IO_RANGE_PCI:
> +            case HVMOP_IO_RANGE_WP_MEM:
>                  r = s->range[type];
>                  break;
> 
> @@ -2561,6 +2563,8 @@ struct hvm_ioreq_server
> *hvm_select_ioreq_server(struct domain *d,
>      uint32_t cf8;
>      uint8_t type;
>      uint64_t addr;
> +    p2m_type_t p2mt;
> +    struct page_info *ram_page;
> 
>      if ( list_empty(&d->arch.hvm_domain.ioreq_server.list) )
>          return NULL;
> @@ -2604,6 +2608,16 @@ struct hvm_ioreq_server
> *hvm_select_ioreq_server(struct domain *d,
>          type = (p->type == IOREQ_TYPE_PIO) ?
>                  HVMOP_IO_RANGE_PORT : HVMOP_IO_RANGE_MEMORY;
>          addr = p->addr;
> +        if ( type == HVMOP_IO_RANGE_MEMORY )
> +        {
> +             ram_page = get_page_from_gfn(d, p->addr >> PAGE_SHIFT,
> +                                          &p2mt, P2M_UNSHARE);
> +             if ( p2mt == p2m_mmio_write_dm )
> +                 type = HVMOP_IO_RANGE_WP_MEM;
> +
> +             if ( ram_page )
> +                 put_page(ram_page);
> +        }
>      }
> 
>      list_for_each_entry ( s,
> @@ -2645,6 +2659,11 @@ struct hvm_ioreq_server
> *hvm_select_ioreq_server(struct domain *d,
>              }
> 
>              break;
> +        case HVMOP_IO_RANGE_WP_MEM:
> +            if ( rangeset_contains_singleton(r, PFN_DOWN(addr)) )
> +                return s;
> +
> +            break;
>          }
>      }
> 
> diff --git a/xen/include/asm-x86/hvm/domain.h b/xen/include/asm-
> x86/hvm/domain.h
> index a8cc2ad..1e13973 100644
> --- a/xen/include/asm-x86/hvm/domain.h
> +++ b/xen/include/asm-x86/hvm/domain.h
> @@ -48,7 +48,7 @@ struct hvm_ioreq_vcpu {
>      bool_t           pending;
>  };
> 
> -#define NR_IO_RANGE_TYPES (HVMOP_IO_RANGE_PCI + 1)
> +#define NR_IO_RANGE_TYPES (HVMOP_IO_RANGE_WP_MEM + 1)
>  #define MAX_NR_IO_RANGES  256
> 
>  struct hvm_ioreq_server {
> diff --git a/xen/include/public/hvm/hvm_op.h
> b/xen/include/public/hvm/hvm_op.h
> index 1606185..c0b1e30 100644
> --- a/xen/include/public/hvm/hvm_op.h
> +++ b/xen/include/public/hvm/hvm_op.h
> @@ -333,6 +333,7 @@ struct xen_hvm_io_range {
>  # define HVMOP_IO_RANGE_PORT   0 /* I/O port range */
>  # define HVMOP_IO_RANGE_MEMORY 1 /* MMIO range */
>  # define HVMOP_IO_RANGE_PCI    2 /* PCI segment/bus/dev/func range */
> +# define HVMOP_IO_RANGE_WP_MEM 3 /* Write-protected ram range */
>      uint64_aligned_t start, end; /* IN - inclusive start and end of range */
>  };
>  typedef struct xen_hvm_io_range xen_hvm_io_range_t;
> --
> 1.9.1
diff mbox

Patch

diff --git a/tools/libxc/include/xenctrl.h b/tools/libxc/include/xenctrl.h
index 079cad0..036c72d 100644
--- a/tools/libxc/include/xenctrl.h
+++ b/tools/libxc/include/xenctrl.h
@@ -2023,6 +2023,37 @@  int xc_hvm_unmap_io_range_from_ioreq_server(xc_interface *xch,
                                             int is_mmio,
                                             uint64_t start,
                                             uint64_t end);
+/**
+ * This function registers a range of write-protected memory for emulation.
+ *
+ * @parm xch a handle to an open hypervisor interface.
+ * @parm domid the domain id to be serviced
+ * @parm id the IOREQ Server id.
+ * @parm start start of range
+ * @parm end end of range (inclusive).
+ * @return 0 on success, -1 on failure.
+ */
+int xc_hvm_map_wp_mem_range_to_ioreq_server(xc_interface *xch,
+                                            domid_t domid,
+                                            ioservid_t id,
+                                            xen_pfn_t start,
+                                            xen_pfn_t end);
+
+/**
+ * This function deregisters a range of write-protected memory for emulation.
+ *
+ * @parm xch a handle to an open hypervisor interface.
+ * @parm domid the domain id to be serviced
+ * @parm id the IOREQ Server id.
+ * @parm start start of range
+ * @parm end end of range (inclusive).
+ * @return 0 on success, -1 on failure.
+ */
+int xc_hvm_unmap_wp_mem_range_from_ioreq_server(xc_interface *xch,
+                                                domid_t domid,
+                                                ioservid_t id,
+                                                xen_pfn_t start,
+                                                xen_pfn_t end);
 
 /**
  * This function registers a PCI device for config space emulation.
diff --git a/tools/libxc/xc_domain.c b/tools/libxc/xc_domain.c
index 99e0d48..4f43695 100644
--- a/tools/libxc/xc_domain.c
+++ b/tools/libxc/xc_domain.c
@@ -1544,6 +1544,67 @@  int xc_hvm_unmap_io_range_from_ioreq_server(xc_interface *xch, domid_t domid,
     return rc;
 }
 
+int xc_hvm_map_wp_mem_range_to_ioreq_server(xc_interface *xch,
+                                            domid_t domid,
+                                            ioservid_t id,
+                                            xen_pfn_t start,
+                                            xen_pfn_t end)
+{
+    DECLARE_HYPERCALL;
+    DECLARE_HYPERCALL_BUFFER(xen_hvm_io_range_t, arg);
+    int rc;
+
+    arg = xc_hypercall_buffer_alloc(xch, arg, sizeof(*arg));
+    if ( arg == NULL )
+        return -1;
+
+    hypercall.op     = __HYPERVISOR_hvm_op;
+    hypercall.arg[0] = HVMOP_map_io_range_to_ioreq_server;
+    hypercall.arg[1] = HYPERCALL_BUFFER_AS_ARG(arg);
+
+    arg->domid = domid;
+    arg->id = id;
+    arg->type = HVMOP_IO_RANGE_WP_MEM;
+    arg->start = start;
+    arg->end = end;
+
+    rc = do_xen_hypercall(xch, &hypercall);
+
+    xc_hypercall_buffer_free(xch, arg);
+    return rc;
+}
+
+int xc_hvm_unmap_wp_mem_range_from_ioreq_server(xc_interface *xch,
+                                                domid_t domid,
+                                                ioservid_t id,
+                                                xen_pfn_t start,
+                                                xen_pfn_t end)
+{
+    DECLARE_HYPERCALL;
+    DECLARE_HYPERCALL_BUFFER(xen_hvm_io_range_t, arg);
+    int rc;
+
+    arg = xc_hypercall_buffer_alloc(xch, arg, sizeof(*arg));
+    if ( arg == NULL )
+        return -1;
+
+    hypercall.op     = __HYPERVISOR_hvm_op;
+    hypercall.arg[0] = HVMOP_unmap_io_range_from_ioreq_server;
+    hypercall.arg[1] = HYPERCALL_BUFFER_AS_ARG(arg);
+
+    arg->domid = domid;
+    arg->id = id;
+    arg->type = HVMOP_IO_RANGE_WP_MEM;
+    arg->start = start;
+    arg->end = end;
+
+    rc = do_xen_hypercall(xch, &hypercall);
+
+    xc_hypercall_buffer_free(xch, arg);
+    return rc;
+
+}
+
 int xc_hvm_map_pcidev_to_ioreq_server(xc_interface *xch, domid_t domid,
                                       ioservid_t id, uint16_t segment,
                                       uint8_t bus, uint8_t device,
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index f646c1e..d59e7bc 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -935,6 +935,9 @@  static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s,
         rangeset_destroy(s->range[i]);
 }
 
+const char *io_range_name[NR_IO_RANGE_TYPES] =
+                                {"port", "mmio", "pci", "wp-mem"};
+
 static int hvm_ioreq_server_alloc_rangesets(struct hvm_ioreq_server *s, 
                                             bool_t is_default)
 {
@@ -949,10 +952,7 @@  static int hvm_ioreq_server_alloc_rangesets(struct hvm_ioreq_server *s,
         char *name;
 
         rc = asprintf(&name, "ioreq_server %d %s", s->id,
-                      (i == HVMOP_IO_RANGE_PORT) ? "port" :
-                      (i == HVMOP_IO_RANGE_MEMORY) ? "memory" :
-                      (i == HVMOP_IO_RANGE_PCI) ? "pci" :
-                      "");
+                      (i < NR_IO_RANGE_TYPES) ? io_range_name[i] : "");
         if ( rc )
             goto fail;
 
@@ -1270,6 +1270,7 @@  static int hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
             case HVMOP_IO_RANGE_PORT:
             case HVMOP_IO_RANGE_MEMORY:
             case HVMOP_IO_RANGE_PCI:
+            case HVMOP_IO_RANGE_WP_MEM:
                 r = s->range[type];
                 break;
 
@@ -1321,6 +1322,7 @@  static int hvm_unmap_io_range_from_ioreq_server(struct domain *d, ioservid_t id,
             case HVMOP_IO_RANGE_PORT:
             case HVMOP_IO_RANGE_MEMORY:
             case HVMOP_IO_RANGE_PCI:
+            case HVMOP_IO_RANGE_WP_MEM:
                 r = s->range[type];
                 break;
 
@@ -2561,6 +2563,8 @@  struct hvm_ioreq_server *hvm_select_ioreq_server(struct domain *d,
     uint32_t cf8;
     uint8_t type;
     uint64_t addr;
+    p2m_type_t p2mt;
+    struct page_info *ram_page;
 
     if ( list_empty(&d->arch.hvm_domain.ioreq_server.list) )
         return NULL;
@@ -2604,6 +2608,16 @@  struct hvm_ioreq_server *hvm_select_ioreq_server(struct domain *d,
         type = (p->type == IOREQ_TYPE_PIO) ?
                 HVMOP_IO_RANGE_PORT : HVMOP_IO_RANGE_MEMORY;
         addr = p->addr;
+        if ( type == HVMOP_IO_RANGE_MEMORY )
+        {
+             ram_page = get_page_from_gfn(d, p->addr >> PAGE_SHIFT,
+                                          &p2mt, P2M_UNSHARE);
+             if ( p2mt == p2m_mmio_write_dm )
+                 type = HVMOP_IO_RANGE_WP_MEM;
+
+             if ( ram_page )
+                 put_page(ram_page);
+        }
     }
 
     list_for_each_entry ( s,
@@ -2645,6 +2659,11 @@  struct hvm_ioreq_server *hvm_select_ioreq_server(struct domain *d,
             }
 
             break;
+        case HVMOP_IO_RANGE_WP_MEM:
+            if ( rangeset_contains_singleton(r, PFN_DOWN(addr)) )
+                return s;
+
+            break;
         }
     }
 
diff --git a/xen/include/asm-x86/hvm/domain.h b/xen/include/asm-x86/hvm/domain.h
index a8cc2ad..1e13973 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -48,7 +48,7 @@  struct hvm_ioreq_vcpu {
     bool_t           pending;
 };
 
-#define NR_IO_RANGE_TYPES (HVMOP_IO_RANGE_PCI + 1)
+#define NR_IO_RANGE_TYPES (HVMOP_IO_RANGE_WP_MEM + 1)
 #define MAX_NR_IO_RANGES  256
 
 struct hvm_ioreq_server {
diff --git a/xen/include/public/hvm/hvm_op.h b/xen/include/public/hvm/hvm_op.h
index 1606185..c0b1e30 100644
--- a/xen/include/public/hvm/hvm_op.h
+++ b/xen/include/public/hvm/hvm_op.h
@@ -333,6 +333,7 @@  struct xen_hvm_io_range {
 # define HVMOP_IO_RANGE_PORT   0 /* I/O port range */
 # define HVMOP_IO_RANGE_MEMORY 1 /* MMIO range */
 # define HVMOP_IO_RANGE_PCI    2 /* PCI segment/bus/dev/func range */
+# define HVMOP_IO_RANGE_WP_MEM 3 /* Write-protected ram range */
     uint64_aligned_t start, end; /* IN - inclusive start and end of range */
 };
 typedef struct xen_hvm_io_range xen_hvm_io_range_t;