[v11][PATCH 01/16] xen: introduce XENMEM_reserved_device_memory_map

[Tiejun Chen <tiejun.chen@intel.com>]

From: Jan Beulich <jbeulich@suse.com>

This is a prerequisite for punching holes into HVM and PVH guests' P2M
to allow passing through devices that are associated with (on VT-d)
RMRRs.

CC: Jan Beulich <jbeulich@suse.com>
CC: Yang Zhang <yang.z.zhang@intel.com>
CC: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Tiejun Chen <tiejun.chen@intel.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
---
v7 ~ v11:

* Nothing is changed.

v6:

* Add a comments to the nr_entries field inside xen_reserved_device_memory_map

v5 ~ v4:

* Nothing is changed.

 xen/common/compat/memory.c           | 66 ++++++++++++++++++++++++++++++++++++
 xen/common/memory.c                  | 64 ++++++++++++++++++++++++++++++++++
 xen/drivers/passthrough/iommu.c      | 10 ++++++
 xen/drivers/passthrough/vtd/dmar.c   | 32 +++++++++++++++++
 xen/drivers/passthrough/vtd/extern.h |  1 +
 xen/drivers/passthrough/vtd/iommu.c  |  1 +
 xen/include/public/memory.h          | 37 +++++++++++++++++++-
 xen/include/xen/iommu.h              | 10 ++++++
 xen/include/xen/pci.h                |  2 ++
 xen/include/xlat.lst                 |  3 +-
 10 files changed, 224 insertions(+), 2 deletions(-)

diff --git a/xen/common/compat/memory.c b/xen/common/compat/memory.c
index b258138..b608496 100644
--- a/xen/common/compat/memory.c
+++ b/xen/common/compat/memory.c
@@ -17,6 +17,45 @@ CHECK_TYPE(domid);
 CHECK_mem_access_op;
 CHECK_vmemrange;
 
+#ifdef HAS_PASSTHROUGH
+struct get_reserved_device_memory {
+    struct compat_reserved_device_memory_map map;
+    unsigned int used_entries;
+};
+
+static int get_reserved_device_memory(xen_pfn_t start, xen_ulong_t nr,
+                                      u32 id, void *ctxt)
+{
+    struct get_reserved_device_memory *grdm = ctxt;
+    u32 sbdf;
+    struct compat_reserved_device_memory rdm = {
+        .start_pfn = start, .nr_pages = nr
+    };
+
+    sbdf = PCI_SBDF2(grdm->map.seg, grdm->map.bus, grdm->map.devfn);
+    if ( (grdm->map.flag & PCI_DEV_RDM_ALL) || (sbdf == id) )
+    {
+        if ( grdm->used_entries < grdm->map.nr_entries )
+        {
+            if ( rdm.start_pfn != start || rdm.nr_pages != nr )
+                return -ERANGE;
+
+            if ( __copy_to_compat_offset(grdm->map.buffer,
+                                         grdm->used_entries,
+                                         &rdm,
+                                         1) )
+            {
+                return -EFAULT;
+            }
+        }
+        ++grdm->used_entries;
+        return 1;
+    }
+
+    return 0;
+}
+#endif
+
 int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
 {
     int split, op = cmd & MEMOP_CMD_MASK;
@@ -303,6 +342,33 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
             break;
         }
 
+#ifdef HAS_PASSTHROUGH
+        case XENMEM_reserved_device_memory_map:
+        {
+            struct get_reserved_device_memory grdm;
+
+            if ( copy_from_guest(&grdm.map, compat, 1) ||
+                 !compat_handle_okay(grdm.map.buffer, grdm.map.nr_entries) )
+                return -EFAULT;
+
+            grdm.used_entries = 0;
+            rc = iommu_get_reserved_device_memory(get_reserved_device_memory,
+                                                  &grdm);
+
+            if ( !rc && grdm.map.nr_entries < grdm.used_entries )
+                rc = -ENOBUFS;
+
+            grdm.map.nr_entries = grdm.used_entries;
+            if ( grdm.map.nr_entries )
+            {
+                if ( __copy_to_guest(compat, &grdm.map, 1) )
+                    rc = -EFAULT;
+            }
+
+            return rc;
+        }
+#endif
+
         default:
             return compat_arch_memory_op(cmd, compat);
         }
diff --git a/xen/common/memory.c b/xen/common/memory.c
index e5d49d8..2fa45d0 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -748,6 +748,43 @@ static int construct_memop_from_reservation(
     return 0;
 }
 
+#ifdef HAS_PASSTHROUGH
+struct get_reserved_device_memory {
+    struct xen_reserved_device_memory_map map;
+    unsigned int used_entries;
+};
+
+static int get_reserved_device_memory(xen_pfn_t start, xen_ulong_t nr,
+                                      u32 id, void *ctxt)
+{
+    struct get_reserved_device_memory *grdm = ctxt;
+    u32 sbdf;
+
+    sbdf = PCI_SBDF2(grdm->map.seg, grdm->map.bus, grdm->map.devfn);
+    if ( (grdm->map.flag & PCI_DEV_RDM_ALL) || (sbdf == id) )
+    {
+        if ( grdm->used_entries < grdm->map.nr_entries )
+        {
+            struct xen_reserved_device_memory rdm = {
+                .start_pfn = start, .nr_pages = nr
+            };
+
+            if ( __copy_to_guest_offset(grdm->map.buffer,
+                                        grdm->used_entries,
+                                        &rdm,
+                                        1) )
+            {
+                return -EFAULT;
+            }
+        }
+        ++grdm->used_entries;
+        return 1;
+    }
+
+    return 0;
+}
+#endif
+
 long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 {
     struct domain *d;
@@ -1162,6 +1199,33 @@ long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
         break;
     }
 
+#ifdef HAS_PASSTHROUGH
+    case XENMEM_reserved_device_memory_map:
+    {
+        struct get_reserved_device_memory grdm;
+
+        if ( copy_from_guest(&grdm.map, arg, 1) ||
+             !guest_handle_okay(grdm.map.buffer, grdm.map.nr_entries) )
+            return -EFAULT;
+
+        grdm.used_entries = 0;
+        rc = iommu_get_reserved_device_memory(get_reserved_device_memory,
+                                              &grdm);
+
+        if ( !rc && grdm.map.nr_entries < grdm.used_entries )
+            rc = -ENOBUFS;
+
+        grdm.map.nr_entries = grdm.used_entries;
+        if ( grdm.map.nr_entries )
+        {
+            if ( __copy_to_guest(arg, &grdm.map, 1) )
+                rc = -EFAULT;
+        }
+
+        break;
+    }
+#endif
+
     default:
         rc = arch_memory_op(cmd, arg);
         break;
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 06cb38f..0b2ef52 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -375,6 +375,16 @@ void iommu_crash_shutdown(void)
     iommu_enabled = iommu_intremap = 0;
 }
 
+int iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt)
+{
+    const struct iommu_ops *ops = iommu_get_ops();
+
+    if ( !iommu_enabled || !ops->get_reserved_device_memory )
+        return 0;
+
+    return ops->get_reserved_device_memory(func, ctxt);
+}
+
 bool_t iommu_has_feature(struct domain *d, enum iommu_feature feature)
 {
     const struct hvm_iommu *hd = domain_hvm_iommu(d);
diff --git a/xen/drivers/passthrough/vtd/dmar.c b/xen/drivers/passthrough/vtd/dmar.c
index 2672688..3b08bf3 100644
--- a/xen/drivers/passthrough/vtd/dmar.c
+++ b/xen/drivers/passthrough/vtd/dmar.c
@@ -914,3 +914,35 @@ int platform_supports_x2apic(void)
     unsigned int mask = ACPI_DMAR_INTR_REMAP | ACPI_DMAR_X2APIC_OPT_OUT;
     return cpu_has_x2apic && ((dmar_flags & mask) == ACPI_DMAR_INTR_REMAP);
 }
+
+int intel_iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt)
+{
+    struct acpi_rmrr_unit *rmrr, *rmrr_cur = NULL;
+    int rc = 0;
+    unsigned int i;
+    u16 bdf;
+
+    for_each_rmrr_device ( rmrr, bdf, i )
+    {
+        if ( rmrr != rmrr_cur )
+        {
+            rc = func(PFN_DOWN(rmrr->base_address),
+                      PFN_UP(rmrr->end_address) -
+                        PFN_DOWN(rmrr->base_address),
+                      PCI_SBDF(rmrr->segment, bdf),
+                      ctxt);
+
+            if ( unlikely(rc < 0) )
+                return rc;
+
+            if ( !rc )
+                continue;
+
+            /* Just go next. */
+            if ( rc == 1 )
+                rmrr_cur = rmrr;
+        }
+    }
+
+    return 0;
+}
diff --git a/xen/drivers/passthrough/vtd/extern.h b/xen/drivers/passthrough/vtd/extern.h
index 5524dba..f9ee9b0 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -75,6 +75,7 @@ int domain_context_mapping_one(struct domain *domain, struct iommu *iommu,
                                u8 bus, u8 devfn, const struct pci_dev *);
 int domain_context_unmap_one(struct domain *domain, struct iommu *iommu,
                              u8 bus, u8 devfn);
+int intel_iommu_get_reserved_device_memory(iommu_grdm_t *func, void *ctxt);
 
 unsigned int io_apic_read_remap_rte(unsigned int apic, unsigned int reg);
 void io_apic_write_remap_rte(unsigned int apic,
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index a88b5a3..9849d0e 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -2490,6 +2490,7 @@ const struct iommu_ops intel_iommu_ops = {
     .crash_shutdown = vtd_crash_shutdown,
     .iotlb_flush = intel_iommu_iotlb_flush,
     .iotlb_flush_all = intel_iommu_iotlb_flush_all,
+    .get_reserved_device_memory = intel_iommu_get_reserved_device_memory,
     .dump_p2m_table = vtd_dump_p2m_table,
 };
 
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index 832559a..ac7d3da 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -573,7 +573,42 @@ struct xen_vnuma_topology_info {
 typedef struct xen_vnuma_topology_info xen_vnuma_topology_info_t;
 DEFINE_XEN_GUEST_HANDLE(xen_vnuma_topology_info_t);
 
-/* Next available subop number is 27 */
+/*
+ * With some legacy devices, certain guest-physical addresses cannot safely
+ * be used for other purposes, e.g. to map guest RAM.  This hypercall
+ * enumerates those regions so the toolstack can avoid using them.
+ */
+#define XENMEM_reserved_device_memory_map   27
+struct xen_reserved_device_memory {
+    xen_pfn_t start_pfn;
+    xen_ulong_t nr_pages;
+};
+typedef struct xen_reserved_device_memory xen_reserved_device_memory_t;
+DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_t);
+
+struct xen_reserved_device_memory_map {
+    /* IN */
+    /* Currently just one bit to indicate checkng all Reserved Device Memory. */
+#define PCI_DEV_RDM_ALL   0x1
+    uint32_t        flag;
+    /* IN */
+    uint16_t        seg;
+    uint8_t         bus;
+    uint8_t         devfn;
+    /*
+     * IN/OUT
+     *
+     * Gets set to the required number of entries when too low,
+     * signaled by error code -ERANGE.
+     */
+    unsigned int    nr_entries;
+    /* OUT */
+    XEN_GUEST_HANDLE(xen_reserved_device_memory_t) buffer;
+};
+typedef struct xen_reserved_device_memory_map xen_reserved_device_memory_map_t;
+DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
+
+/* Next available subop number is 28 */
 
 #endif /* __XEN_PUBLIC_MEMORY_H__ */
 
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index 1d00696..52ed3b7 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -125,6 +125,14 @@ int iommu_do_dt_domctl(struct xen_domctl *, struct domain *,
 
 struct page_info;
 
+/*
+ * Any non-zero value returned from callbacks of this type will cause the
+ * function the callback was handed to terminate its iteration. Assigning
+ * meaning of these non-zero values is left to the top level caller /
+ * callback pair.
+ */
+typedef int iommu_grdm_t(xen_pfn_t start, xen_ulong_t nr, u32 id, void *ctxt);
+
 struct iommu_ops {
     int (*init)(struct domain *d);
     void (*hwdom_init)(struct domain *d);
@@ -156,12 +164,14 @@ struct iommu_ops {
     void (*crash_shutdown)(void);
     void (*iotlb_flush)(struct domain *d, unsigned long gfn, unsigned int page_count);
     void (*iotlb_flush_all)(struct domain *d);
+    int (*get_reserved_device_memory)(iommu_grdm_t *, void *);
     void (*dump_p2m_table)(struct domain *d);
 };
 
 void iommu_suspend(void);
 void iommu_resume(void);
 void iommu_crash_shutdown(void);
+int iommu_get_reserved_device_memory(iommu_grdm_t *, void *);
 
 void iommu_share_p2m_table(struct domain *d);
 
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index 3908146..d176e8b 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -33,6 +33,8 @@
 #define PCI_DEVFN2(bdf) ((bdf) & 0xff)
 #define PCI_BDF(b,d,f)  ((((b) & 0xff) << 8) | PCI_DEVFN(d,f))
 #define PCI_BDF2(b,df)  ((((b) & 0xff) << 8) | ((df) & 0xff))
+#define PCI_SBDF(s,bdf) (((s & 0xffff) << 16) | (bdf & 0xffff))
+#define PCI_SBDF2(s,b,df) (((s & 0xffff) << 16) | PCI_BDF2(b,df))
 
 struct pci_dev_info {
     bool_t is_extfn;
diff --git a/xen/include/xlat.lst b/xen/include/xlat.lst
index 6fb15bf..8cedee7 100644
--- a/xen/include/xlat.lst
+++ b/xen/include/xlat.lst
@@ -65,9 +65,10 @@
 !	memory_exchange			memory.h
 !	memory_map			memory.h
 !	memory_reservation		memory.h
-?	mem_access_op		memory.h
+?	mem_access_op			memory.h
 !	pod_target			memory.h
 !	remove_from_physmap		memory.h
+!	reserved_device_memory_map	memory.h
 ?	vmemrange			memory.h
 !	vnuma_topology_info		memory.h
 ?	physdev_eoi			physdev.h
-- 
1.9.1