* [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-09 12:40 ` Jan Beulich
2017-10-06 12:25 ` [PATCH v9 02/11] x86/hvm/ioreq: simplify code and use consistent naming Paul Durrant
` (9 subsequent siblings)
10 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel; +Cc: Andrew Cooper, Paul Durrant, Jan Beulich
A subsequent patch will remove the current implicit limitation on creation
of ioreq servers which is due to the allocation of gfns for the ioreq
structures and buffered ioreq ring.
It will therefore be necessary to introduce an explicit limit and, since
this limit should be small, it simplifies the code to maintain an array of
that size rather than using a list.
Also, by reserving an array slot for the default server and populating
array slots early in create, the need to pass an 'is_default' boolean
to sub-functions can be avoided.
Some function return values are changed by this patch: Specifically, in
the case where the id of the default ioreq server is passed in, -EOPNOTSUPP
is now returned rather than -ENOENT.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
v9:
- modified FOR_EACH... macro as requested by Andrew.
v8:
- Addressed various comments from Jan.
v7:
- Fixed assertion failure found in testing.
v6:
- Updated according to comments made by Roger on v4 that I'd missed.
v5:
- Switched GET/SET_IOREQ_SERVER() macros to get/set_ioreq_server()
functions to avoid possible double-evaluation issues.
v4:
- Introduced more helper macros and relocated them to the top of the
code.
v3:
- New patch (replacing "move is_default into struct hvm_ioreq_server") in
response to review comments.
---
xen/arch/x86/hvm/ioreq.c | 509 +++++++++++++++++++--------------------
xen/include/asm-x86/hvm/domain.h | 10 +-
2 files changed, 252 insertions(+), 267 deletions(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index f2e0b3f74a..a6de1e7db2 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -33,6 +33,44 @@
#include <public/hvm/ioreq.h>
+static void set_ioreq_server(struct domain *d, unsigned int id,
+ struct hvm_ioreq_server *s)
+{
+ ASSERT(id < MAX_NR_IOREQ_SERVERS);
+ ASSERT(!s || !d->arch.hvm_domain.ioreq_server.server[id]);
+
+ d->arch.hvm_domain.ioreq_server.server[id] = s;
+}
+
+#define GET_IOREQ_SERVER(d, id) \
+ (d)->arch.hvm_domain.ioreq_server.server[id]
+
+static struct hvm_ioreq_server *get_ioreq_server(const struct domain *d,
+ unsigned int id)
+{
+ if ( id >= MAX_NR_IOREQ_SERVERS )
+ return NULL;
+
+ return GET_IOREQ_SERVER(d, id);
+}
+
+#define IS_DEFAULT(s) \
+ ((s) == get_ioreq_server((s)->domain, DEFAULT_IOSERVID))
+
+/*
+ * Iterate over all possible ioreq servers. The use of inline function
+ * get_ioreq_server() in the increment is deliberate as use of the
+ * GET_IOREQ_SERVER() macro will cause gcc to complain about an array
+ * overflow.
+ */
+#define FOR_EACH_IOREQ_SERVER(d, id, s) \
+ for ( (id) = 0, (s) = GET_IOREQ_SERVER(d, 0); \
+ (id) < MAX_NR_IOREQ_SERVERS; \
+ (s) = get_ioreq_server(d, ++(id)) ) \
+ if ( !s ) \
+ continue; \
+ else
+
static ioreq_t *get_ioreq(struct hvm_ioreq_server *s, struct vcpu *v)
{
shared_iopage_t *p = s->ioreq.va;
@@ -47,10 +85,9 @@ bool hvm_io_pending(struct vcpu *v)
{
struct domain *d = v->domain;
struct hvm_ioreq_server *s;
+ unsigned int id;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
{
struct hvm_ioreq_vcpu *sv;
@@ -127,10 +164,9 @@ bool handle_hvm_io_completion(struct vcpu *v)
struct hvm_vcpu_io *vio = &v->arch.hvm_vcpu.hvm_io;
struct hvm_ioreq_server *s;
enum hvm_io_completion io_completion;
+ unsigned int id;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
{
struct hvm_ioreq_vcpu *sv;
@@ -243,13 +279,12 @@ static int hvm_map_ioreq_page(
bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
{
const struct hvm_ioreq_server *s;
+ unsigned int id;
bool found = false;
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
{
if ( (s->ioreq.va && s->ioreq.page == page) ||
(s->bufioreq.va && s->bufioreq.page == page) )
@@ -302,7 +337,7 @@ static void hvm_update_ioreq_evtchn(struct hvm_ioreq_server *s,
}
static int hvm_ioreq_server_add_vcpu(struct hvm_ioreq_server *s,
- bool is_default, struct vcpu *v)
+ struct vcpu *v)
{
struct hvm_ioreq_vcpu *sv;
int rc;
@@ -331,7 +366,7 @@ static int hvm_ioreq_server_add_vcpu(struct hvm_ioreq_server *s,
goto fail3;
s->bufioreq_evtchn = rc;
- if ( is_default )
+ if ( IS_DEFAULT(s) )
d->arch.hvm_domain.params[HVM_PARAM_BUFIOREQ_EVTCHN] =
s->bufioreq_evtchn;
}
@@ -431,7 +466,6 @@ static int hvm_ioreq_server_map_pages(struct hvm_ioreq_server *s,
}
static int hvm_ioreq_server_setup_pages(struct hvm_ioreq_server *s,
- bool is_default,
bool handle_bufioreq)
{
struct domain *d = s->domain;
@@ -439,7 +473,7 @@ static int hvm_ioreq_server_setup_pages(struct hvm_ioreq_server *s,
unsigned long bufioreq_gfn = gfn_x(INVALID_GFN);
int rc;
- if ( is_default )
+ if ( IS_DEFAULT(s) )
{
/*
* The default ioreq server must handle buffered ioreqs, for
@@ -468,8 +502,7 @@ static int hvm_ioreq_server_setup_pages(struct hvm_ioreq_server *s,
return rc;
}
-static void hvm_ioreq_server_unmap_pages(struct hvm_ioreq_server *s,
- bool is_default)
+static void hvm_ioreq_server_unmap_pages(struct hvm_ioreq_server *s)
{
struct domain *d = s->domain;
bool handle_bufioreq = !!s->bufioreq.va;
@@ -479,7 +512,7 @@ static void hvm_ioreq_server_unmap_pages(struct hvm_ioreq_server *s,
hvm_unmap_ioreq_page(s, false);
- if ( !is_default )
+ if ( !IS_DEFAULT(s) )
{
if ( handle_bufioreq )
hvm_free_ioreq_gfn(d, s->bufioreq.gfn);
@@ -488,12 +521,11 @@ static void hvm_ioreq_server_unmap_pages(struct hvm_ioreq_server *s,
}
}
-static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s,
- bool is_default)
+static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s)
{
unsigned int i;
- if ( is_default )
+ if ( IS_DEFAULT(s) )
return;
for ( i = 0; i < NR_IO_RANGE_TYPES; i++ )
@@ -501,19 +533,21 @@ static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s,
}
static int hvm_ioreq_server_alloc_rangesets(struct hvm_ioreq_server *s,
- bool is_default)
+ ioservid_t id)
{
unsigned int i;
int rc;
- if ( is_default )
+ if ( id == DEFAULT_IOSERVID )
goto done;
+ ASSERT(!IS_DEFAULT(s));
+
for ( i = 0; i < NR_IO_RANGE_TYPES; i++ )
{
char *name;
- rc = asprintf(&name, "ioreq_server %d %s", s->id,
+ rc = asprintf(&name, "ioreq_server %d %s", id,
(i == XEN_DMOP_IO_RANGE_PORT) ? "port" :
(i == XEN_DMOP_IO_RANGE_MEMORY) ? "memory" :
(i == XEN_DMOP_IO_RANGE_PCI) ? "pci" :
@@ -537,13 +571,12 @@ static int hvm_ioreq_server_alloc_rangesets(struct hvm_ioreq_server *s,
return 0;
fail:
- hvm_ioreq_server_free_rangesets(s, false);
+ hvm_ioreq_server_free_rangesets(s);
return rc;
}
-static void hvm_ioreq_server_enable(struct hvm_ioreq_server *s,
- bool is_default)
+static void hvm_ioreq_server_enable(struct hvm_ioreq_server *s)
{
struct domain *d = s->domain;
struct hvm_ioreq_vcpu *sv;
@@ -554,7 +587,7 @@ static void hvm_ioreq_server_enable(struct hvm_ioreq_server *s,
if ( s->enabled )
goto done;
- if ( !is_default )
+ if ( !IS_DEFAULT(s) )
{
hvm_remove_ioreq_gfn(d, &s->ioreq);
@@ -573,8 +606,7 @@ static void hvm_ioreq_server_enable(struct hvm_ioreq_server *s,
spin_unlock(&s->lock);
}
-static void hvm_ioreq_server_disable(struct hvm_ioreq_server *s,
- bool is_default)
+static void hvm_ioreq_server_disable(struct hvm_ioreq_server *s)
{
struct domain *d = s->domain;
bool handle_bufioreq = !!s->bufioreq.va;
@@ -584,7 +616,7 @@ static void hvm_ioreq_server_disable(struct hvm_ioreq_server *s,
if ( !s->enabled )
goto done;
- if ( !is_default )
+ if ( !IS_DEFAULT(s) )
{
if ( handle_bufioreq )
hvm_add_ioreq_gfn(d, &s->bufioreq);
@@ -600,13 +632,11 @@ static void hvm_ioreq_server_disable(struct hvm_ioreq_server *s,
static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
struct domain *d, domid_t domid,
- bool is_default, int bufioreq_handling,
- ioservid_t id)
+ int bufioreq_handling, ioservid_t id)
{
struct vcpu *v;
int rc;
- s->id = id;
s->domain = d;
s->domid = domid;
@@ -614,7 +644,7 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
INIT_LIST_HEAD(&s->ioreq_vcpu_list);
spin_lock_init(&s->bufioreq_lock);
- rc = hvm_ioreq_server_alloc_rangesets(s, is_default);
+ rc = hvm_ioreq_server_alloc_rangesets(s, id);
if ( rc )
return rc;
@@ -622,13 +652,13 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
s->bufioreq_atomic = true;
rc = hvm_ioreq_server_setup_pages(
- s, is_default, bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF);
+ s, bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF);
if ( rc )
goto fail_map;
for_each_vcpu ( d, v )
{
- rc = hvm_ioreq_server_add_vcpu(s, is_default, v);
+ rc = hvm_ioreq_server_add_vcpu(s, v);
if ( rc )
goto fail_add;
}
@@ -637,47 +667,20 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
fail_add:
hvm_ioreq_server_remove_all_vcpus(s);
- hvm_ioreq_server_unmap_pages(s, is_default);
+ hvm_ioreq_server_unmap_pages(s);
fail_map:
- hvm_ioreq_server_free_rangesets(s, is_default);
+ hvm_ioreq_server_free_rangesets(s);
return rc;
}
-static void hvm_ioreq_server_deinit(struct hvm_ioreq_server *s,
- bool is_default)
+static void hvm_ioreq_server_deinit(struct hvm_ioreq_server *s)
{
ASSERT(!s->enabled);
hvm_ioreq_server_remove_all_vcpus(s);
- hvm_ioreq_server_unmap_pages(s, is_default);
- hvm_ioreq_server_free_rangesets(s, is_default);
-}
-
-static ioservid_t next_ioservid(struct domain *d)
-{
- struct hvm_ioreq_server *s;
- ioservid_t id;
-
- ASSERT(spin_is_locked(&d->arch.hvm_domain.ioreq_server.lock));
-
- id = d->arch.hvm_domain.ioreq_server.id;
-
- again:
- id++;
-
- /* Check for uniqueness */
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
- {
- if ( id == s->id )
- goto again;
- }
-
- d->arch.hvm_domain.ioreq_server.id = id;
-
- return id;
+ hvm_ioreq_server_unmap_pages(s);
+ hvm_ioreq_server_free_rangesets(s);
}
int hvm_create_ioreq_server(struct domain *d, domid_t domid,
@@ -685,52 +688,64 @@ int hvm_create_ioreq_server(struct domain *d, domid_t domid,
ioservid_t *id)
{
struct hvm_ioreq_server *s;
+ unsigned int i;
int rc;
if ( bufioreq_handling > HVM_IOREQSRV_BUFIOREQ_ATOMIC )
return -EINVAL;
- rc = -ENOMEM;
s = xzalloc(struct hvm_ioreq_server);
if ( !s )
- goto fail1;
+ return -ENOMEM;
domain_pause(d);
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- rc = -EEXIST;
- if ( is_default && d->arch.hvm_domain.default_ioreq_server != NULL )
- goto fail2;
-
- rc = hvm_ioreq_server_init(s, d, domid, is_default, bufioreq_handling,
- next_ioservid(d));
- if ( rc )
- goto fail3;
-
- list_add(&s->list_entry,
- &d->arch.hvm_domain.ioreq_server.list);
-
if ( is_default )
{
- d->arch.hvm_domain.default_ioreq_server = s;
- hvm_ioreq_server_enable(s, true);
+ i = DEFAULT_IOSERVID;
+
+ rc = -EEXIST;
+ if ( GET_IOREQ_SERVER(d, i) )
+ goto fail;
}
+ else
+ {
+ for ( i = 0; i < MAX_NR_IOREQ_SERVERS; i++ )
+ {
+ if ( i != DEFAULT_IOSERVID && !GET_IOREQ_SERVER(d, i) )
+ break;
+ }
+
+ rc = -ENOSPC;
+ if ( i >= MAX_NR_IOREQ_SERVERS )
+ goto fail;
+ }
+
+ set_ioreq_server(d, i, s);
+
+ rc = hvm_ioreq_server_init(s, d, domid, bufioreq_handling, i);
+ if ( rc )
+ goto fail;
+
+ if ( i == DEFAULT_IOSERVID )
+ hvm_ioreq_server_enable(s);
if ( id )
- *id = s->id;
+ *id = i;
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
domain_unpause(d);
return 0;
- fail3:
- fail2:
+ fail:
+ set_ioreq_server(d, i, NULL);
+
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
domain_unpause(d);
xfree(s);
- fail1:
return rc;
}
@@ -739,37 +754,34 @@ int hvm_destroy_ioreq_server(struct domain *d, ioservid_t id)
struct hvm_ioreq_server *s;
int rc;
- spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+ if ( id == DEFAULT_IOSERVID )
+ return -EPERM;
- rc = -ENOENT;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
- {
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- if ( s->id != id )
- continue;
+ s = get_ioreq_server(d, id);
- domain_pause(d);
+ rc = -ENOENT;
+ if ( !s )
+ goto out;
- p2m_set_ioreq_server(d, 0, s);
+ ASSERT(!IS_DEFAULT(s));
- hvm_ioreq_server_disable(s, false);
+ domain_pause(d);
- list_del(&s->list_entry);
+ p2m_set_ioreq_server(d, 0, s);
- hvm_ioreq_server_deinit(s, false);
+ hvm_ioreq_server_disable(s);
+ hvm_ioreq_server_deinit(s);
- domain_unpause(d);
+ domain_unpause(d);
- xfree(s);
+ set_ioreq_server(d, id, NULL);
+ xfree(s);
- rc = 0;
- break;
- }
+ rc = 0;
+ out:
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
return rc;
@@ -783,31 +795,30 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
struct hvm_ioreq_server *s;
int rc;
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- rc = -ENOENT;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
- {
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ s = get_ioreq_server(d, id);
- if ( s->id != id )
- continue;
+ rc = -ENOENT;
+ if ( !s )
+ goto out;
- *ioreq_gfn = s->ioreq.gfn;
+ ASSERT(!IS_DEFAULT(s));
- if ( s->bufioreq.va != NULL )
- {
- *bufioreq_gfn = s->bufioreq.gfn;
- *bufioreq_port = s->bufioreq_evtchn;
- }
+ *ioreq_gfn = s->ioreq.gfn;
- rc = 0;
- break;
+ if ( s->bufioreq.va != NULL )
+ {
+ *bufioreq_gfn = s->bufioreq.gfn;
+ *bufioreq_port = s->bufioreq_evtchn;
}
+ rc = 0;
+
+ out:
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
return rc;
@@ -818,48 +829,46 @@ int hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
uint64_t end)
{
struct hvm_ioreq_server *s;
+ struct rangeset *r;
int rc;
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+ s = get_ioreq_server(d, id);
+
rc = -ENOENT;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
- {
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ if ( !s )
+ goto out;
- if ( s->id == id )
- {
- struct rangeset *r;
+ ASSERT(!IS_DEFAULT(s));
- switch ( type )
- {
- case XEN_DMOP_IO_RANGE_PORT:
- case XEN_DMOP_IO_RANGE_MEMORY:
- case XEN_DMOP_IO_RANGE_PCI:
- r = s->range[type];
- break;
+ switch ( type )
+ {
+ case XEN_DMOP_IO_RANGE_PORT:
+ case XEN_DMOP_IO_RANGE_MEMORY:
+ case XEN_DMOP_IO_RANGE_PCI:
+ r = s->range[type];
+ break;
- default:
- r = NULL;
- break;
- }
+ default:
+ r = NULL;
+ break;
+ }
- rc = -EINVAL;
- if ( !r )
- break;
+ rc = -EINVAL;
+ if ( !r )
+ goto out;
- rc = -EEXIST;
- if ( rangeset_overlaps_range(r, start, end) )
- break;
+ rc = -EEXIST;
+ if ( rangeset_overlaps_range(r, start, end) )
+ goto out;
- rc = rangeset_add_range(r, start, end);
- break;
- }
- }
+ rc = rangeset_add_range(r, start, end);
+ out:
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
return rc;
@@ -870,48 +879,46 @@ int hvm_unmap_io_range_from_ioreq_server(struct domain *d, ioservid_t id,
uint64_t end)
{
struct hvm_ioreq_server *s;
+ struct rangeset *r;
int rc;
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+ s = get_ioreq_server(d, id);
+
rc = -ENOENT;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
- {
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ if ( !s )
+ goto out;
- if ( s->id == id )
- {
- struct rangeset *r;
+ ASSERT(!IS_DEFAULT(s));
- switch ( type )
- {
- case XEN_DMOP_IO_RANGE_PORT:
- case XEN_DMOP_IO_RANGE_MEMORY:
- case XEN_DMOP_IO_RANGE_PCI:
- r = s->range[type];
- break;
+ switch ( type )
+ {
+ case XEN_DMOP_IO_RANGE_PORT:
+ case XEN_DMOP_IO_RANGE_MEMORY:
+ case XEN_DMOP_IO_RANGE_PCI:
+ r = s->range[type];
+ break;
- default:
- r = NULL;
- break;
- }
+ default:
+ r = NULL;
+ break;
+ }
- rc = -EINVAL;
- if ( !r )
- break;
+ rc = -EINVAL;
+ if ( !r )
+ goto out;
- rc = -ENOENT;
- if ( !rangeset_contains_range(r, start, end) )
- break;
+ rc = -ENOENT;
+ if ( !rangeset_contains_range(r, start, end) )
+ goto out;
- rc = rangeset_remove_range(r, start, end);
- break;
- }
- }
+ rc = rangeset_remove_range(r, start, end);
+ out:
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
return rc;
@@ -931,6 +938,9 @@ int hvm_map_mem_type_to_ioreq_server(struct domain *d, ioservid_t id,
struct hvm_ioreq_server *s;
int rc;
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
if ( type != HVMMEM_ioreq_server )
return -EINVAL;
@@ -939,19 +949,14 @@ int hvm_map_mem_type_to_ioreq_server(struct domain *d, ioservid_t id,
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- rc = -ENOENT;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
- {
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ s = get_ioreq_server(d, id);
- if ( s->id == id )
- {
- rc = p2m_set_ioreq_server(d, flags, s);
- break;
- }
+ if ( !s )
+ rc = -ENOENT;
+ else
+ {
+ ASSERT(!IS_DEFAULT(s));
+ rc = p2m_set_ioreq_server(d, flags, s);
}
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
@@ -970,38 +975,34 @@ int hvm_map_mem_type_to_ioreq_server(struct domain *d, ioservid_t id,
int hvm_set_ioreq_server_state(struct domain *d, ioservid_t id,
bool enabled)
{
- struct list_head *entry;
+ struct hvm_ioreq_server *s;
int rc;
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- rc = -ENOENT;
- list_for_each ( entry,
- &d->arch.hvm_domain.ioreq_server.list )
- {
- struct hvm_ioreq_server *s = list_entry(entry,
- struct hvm_ioreq_server,
- list_entry);
+ s = get_ioreq_server(d, id);
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ rc = -ENOENT;
+ if ( !s )
+ goto out;
- if ( s->id != id )
- continue;
+ ASSERT(!IS_DEFAULT(s));
- domain_pause(d);
+ domain_pause(d);
- if ( enabled )
- hvm_ioreq_server_enable(s, false);
- else
- hvm_ioreq_server_disable(s, false);
+ if ( enabled )
+ hvm_ioreq_server_enable(s);
+ else
+ hvm_ioreq_server_disable(s);
- domain_unpause(d);
+ domain_unpause(d);
- rc = 0;
- break;
- }
+ rc = 0;
+ out:
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
return rc;
}
@@ -1009,17 +1010,14 @@ int hvm_set_ioreq_server_state(struct domain *d, ioservid_t id,
int hvm_all_ioreq_servers_add_vcpu(struct domain *d, struct vcpu *v)
{
struct hvm_ioreq_server *s;
+ unsigned int id;
int rc;
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
{
- bool is_default = (s == d->arch.hvm_domain.default_ioreq_server);
-
- rc = hvm_ioreq_server_add_vcpu(s, is_default, v);
+ rc = hvm_ioreq_server_add_vcpu(s, v);
if ( rc )
goto fail;
}
@@ -1029,10 +1027,15 @@ int hvm_all_ioreq_servers_add_vcpu(struct domain *d, struct vcpu *v)
return 0;
fail:
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ while ( id-- != 0 )
+ {
+ s = GET_IOREQ_SERVER(d, id);
+
+ if ( !s )
+ continue;
+
hvm_ioreq_server_remove_vcpu(s, v);
+ }
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
@@ -1042,12 +1045,11 @@ int hvm_all_ioreq_servers_add_vcpu(struct domain *d, struct vcpu *v)
void hvm_all_ioreq_servers_remove_vcpu(struct domain *d, struct vcpu *v)
{
struct hvm_ioreq_server *s;
+ unsigned int id;
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
hvm_ioreq_server_remove_vcpu(s, v);
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
@@ -1055,28 +1057,19 @@ void hvm_all_ioreq_servers_remove_vcpu(struct domain *d, struct vcpu *v)
void hvm_destroy_all_ioreq_servers(struct domain *d)
{
- struct hvm_ioreq_server *s, *next;
+ struct hvm_ioreq_server *s;
+ unsigned int id;
spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
/* No need to domain_pause() as the domain is being torn down */
- list_for_each_entry_safe ( s,
- next,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
{
- bool is_default = (s == d->arch.hvm_domain.default_ioreq_server);
-
- hvm_ioreq_server_disable(s, is_default);
-
- if ( is_default )
- d->arch.hvm_domain.default_ioreq_server = NULL;
-
- list_del(&s->list_entry);
-
- hvm_ioreq_server_deinit(s, is_default);
+ hvm_ioreq_server_disable(s);
+ hvm_ioreq_server_deinit(s);
+ set_ioreq_server(d, id, NULL);
xfree(s);
}
@@ -1111,7 +1104,7 @@ int hvm_set_dm_domain(struct domain *d, domid_t domid)
* still be set and thus, when the server is created, it will have
* the correct domid.
*/
- s = d->arch.hvm_domain.default_ioreq_server;
+ s = GET_IOREQ_SERVER(d, DEFAULT_IOSERVID);
if ( !s )
goto done;
@@ -1164,12 +1157,10 @@ struct hvm_ioreq_server *hvm_select_ioreq_server(struct domain *d,
uint32_t cf8;
uint8_t type;
uint64_t addr;
-
- if ( list_empty(&d->arch.hvm_domain.ioreq_server.list) )
- return NULL;
+ unsigned int id;
if ( p->type != IOREQ_TYPE_COPY && p->type != IOREQ_TYPE_PIO )
- return d->arch.hvm_domain.default_ioreq_server;
+ return GET_IOREQ_SERVER(d, DEFAULT_IOSERVID);
cf8 = d->arch.hvm_domain.pci_cf8;
@@ -1209,16 +1200,11 @@ struct hvm_ioreq_server *hvm_select_ioreq_server(struct domain *d,
addr = p->addr;
}
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
{
struct rangeset *r;
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
-
- if ( !s->enabled )
+ if ( IS_DEFAULT(s) )
continue;
r = s->range[type];
@@ -1251,7 +1237,7 @@ struct hvm_ioreq_server *hvm_select_ioreq_server(struct domain *d,
}
}
- return d->arch.hvm_domain.default_ioreq_server;
+ return GET_IOREQ_SERVER(d, DEFAULT_IOSERVID);
}
static int hvm_send_buffered_ioreq(struct hvm_ioreq_server *s, ioreq_t *p)
@@ -1410,13 +1396,13 @@ unsigned int hvm_broadcast_ioreq(ioreq_t *p, bool buffered)
{
struct domain *d = current->domain;
struct hvm_ioreq_server *s;
- unsigned int failed = 0;
+ unsigned int id, failed = 0;
- list_for_each_entry ( s,
- &d->arch.hvm_domain.ioreq_server.list,
- list_entry )
+ FOR_EACH_IOREQ_SERVER(d, id, s)
+ {
if ( hvm_send_ioreq(s, p, buffered) == X86EMUL_UNHANDLEABLE )
failed++;
+ }
return failed;
}
@@ -1436,7 +1422,6 @@ static int hvm_access_cf8(
void hvm_ioreq_init(struct domain *d)
{
spin_lock_init(&d->arch.hvm_domain.ioreq_server.lock);
- INIT_LIST_HEAD(&d->arch.hvm_domain.ioreq_server.list);
register_portio_handler(d, 0xcf8, 4, hvm_access_cf8);
}
diff --git a/xen/include/asm-x86/hvm/domain.h b/xen/include/asm-x86/hvm/domain.h
index 7f128c05ff..e17bbe4004 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -60,7 +60,6 @@ struct hvm_ioreq_server {
/* Domain id of emulating domain */
domid_t domid;
- ioservid_t id;
struct hvm_ioreq_page ioreq;
struct list_head ioreq_vcpu_list;
struct hvm_ioreq_page bufioreq;
@@ -100,6 +99,9 @@ struct hvm_pi_ops {
void (*do_resume)(struct vcpu *v);
};
+#define MAX_NR_IOREQ_SERVERS 8
+#define DEFAULT_IOSERVID 0
+
struct hvm_domain {
/* Guest page range used for non-default ioreq servers */
struct {
@@ -109,11 +111,9 @@ struct hvm_domain {
/* Lock protects all other values in the sub-struct and the default */
struct {
- spinlock_t lock;
- ioservid_t id;
- struct list_head list;
+ spinlock_t lock;
+ struct hvm_ioreq_server *server[MAX_NR_IOREQ_SERVERS];
} ioreq_server;
- struct hvm_ioreq_server *default_ioreq_server;
/* Cached CF8 for guest PCI config cycles */
uint32_t pci_cf8;
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* Re: [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2017-10-06 12:25 ` [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list Paul Durrant
@ 2017-10-09 12:40 ` Jan Beulich
2017-10-09 12:45 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-09 12:40 UTC (permalink / raw)
To: Paul Durrant; +Cc: Andrew Cooper, xen-devel
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> --- a/xen/arch/x86/hvm/ioreq.c
> +++ b/xen/arch/x86/hvm/ioreq.c
> @@ -33,6 +33,44 @@
>
> #include <public/hvm/ioreq.h>
>
> +static void set_ioreq_server(struct domain *d, unsigned int id,
> + struct hvm_ioreq_server *s)
> +{
> + ASSERT(id < MAX_NR_IOREQ_SERVERS);
> + ASSERT(!s || !d->arch.hvm_domain.ioreq_server.server[id]);
> +
> + d->arch.hvm_domain.ioreq_server.server[id] = s;
> +}
> +
> +#define GET_IOREQ_SERVER(d, id) \
> + (d)->arch.hvm_domain.ioreq_server.server[id]
> +
> +static struct hvm_ioreq_server *get_ioreq_server(const struct domain *d,
> + unsigned int id)
> +{
> + if ( id >= MAX_NR_IOREQ_SERVERS )
> + return NULL;
> +
> + return GET_IOREQ_SERVER(d, id);
> +}
> +
> +#define IS_DEFAULT(s) \
> + ((s) == get_ioreq_server((s)->domain, DEFAULT_IOSERVID))
While at this point it looks like all users of this macro either
explicitly check s to be non-NULL before invoking the macro or
are being called with s guaranteed non-NULL, going forward it
may easily be that NULL might be handed here. Therefore I
think it would be better to either add an ASSERT() or do
#define IS_DEFAULT(s) \
((s) && (s) == get_ioreq_server((s)->domain, DEFAULT_IOSERVID))
.
> +/*
> + * Iterate over all possible ioreq servers. The use of inline function
> + * get_ioreq_server() in the increment is deliberate as use of the
> + * GET_IOREQ_SERVER() macro will cause gcc to complain about an array
> + * overflow.
I think you shouldn't accuse gcc of complaining, but simply state
that there _will be_ an array overflow otherwise.
> + */
> +#define FOR_EACH_IOREQ_SERVER(d, id, s) \
> + for ( (id) = 0, (s) = GET_IOREQ_SERVER(d, 0); \
> + (id) < MAX_NR_IOREQ_SERVERS; \
> + (s) = get_ioreq_server(d, ++(id)) ) \
> + if ( !s ) \
Alternatively, how about folding both macro and inline function
invocation be putting them in the if() here?
> @@ -685,52 +688,64 @@ int hvm_create_ioreq_server(struct domain *d, domid_t domid,
> ioservid_t *id)
> {
> struct hvm_ioreq_server *s;
> + unsigned int i;
> int rc;
>
> if ( bufioreq_handling > HVM_IOREQSRV_BUFIOREQ_ATOMIC )
> return -EINVAL;
>
> - rc = -ENOMEM;
> s = xzalloc(struct hvm_ioreq_server);
> if ( !s )
> - goto fail1;
> + return -ENOMEM;
>
> domain_pause(d);
> spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
>
> - rc = -EEXIST;
> - if ( is_default && d->arch.hvm_domain.default_ioreq_server != NULL )
> - goto fail2;
> -
> - rc = hvm_ioreq_server_init(s, d, domid, is_default, bufioreq_handling,
> - next_ioservid(d));
> - if ( rc )
> - goto fail3;
> -
> - list_add(&s->list_entry,
> - &d->arch.hvm_domain.ioreq_server.list);
> -
> if ( is_default )
> {
> - d->arch.hvm_domain.default_ioreq_server = s;
> - hvm_ioreq_server_enable(s, true);
> + i = DEFAULT_IOSERVID;
> +
> + rc = -EEXIST;
> + if ( GET_IOREQ_SERVER(d, i) )
> + goto fail;
> }
> + else
> + {
> + for ( i = 0; i < MAX_NR_IOREQ_SERVERS; i++ )
> + {
> + if ( i != DEFAULT_IOSERVID && !GET_IOREQ_SERVER(d, i) )
> + break;
> + }
Strictly speaking the braces here are pointless. But you're the
maintainer, so you know what you like.
Everything else looks fine to me now.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2017-10-09 12:40 ` Jan Beulich
@ 2017-10-09 12:45 ` Paul Durrant
0 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-09 12:45 UTC (permalink / raw)
To: 'Jan Beulich'; +Cc: Andrew Cooper, xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 09 October 2017 13:40
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; xen-
> devel@lists.xenproject.org
> Subject: Re: [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq
> servers rather than a list
>
> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > --- a/xen/arch/x86/hvm/ioreq.c
> > +++ b/xen/arch/x86/hvm/ioreq.c
> > @@ -33,6 +33,44 @@
> >
> > #include <public/hvm/ioreq.h>
> >
> > +static void set_ioreq_server(struct domain *d, unsigned int id,
> > + struct hvm_ioreq_server *s)
> > +{
> > + ASSERT(id < MAX_NR_IOREQ_SERVERS);
> > + ASSERT(!s || !d->arch.hvm_domain.ioreq_server.server[id]);
> > +
> > + d->arch.hvm_domain.ioreq_server.server[id] = s;
> > +}
> > +
> > +#define GET_IOREQ_SERVER(d, id) \
> > + (d)->arch.hvm_domain.ioreq_server.server[id]
> > +
> > +static struct hvm_ioreq_server *get_ioreq_server(const struct domain
> *d,
> > + unsigned int id)
> > +{
> > + if ( id >= MAX_NR_IOREQ_SERVERS )
> > + return NULL;
> > +
> > + return GET_IOREQ_SERVER(d, id);
> > +}
> > +
> > +#define IS_DEFAULT(s) \
> > + ((s) == get_ioreq_server((s)->domain, DEFAULT_IOSERVID))
>
> While at this point it looks like all users of this macro either
> explicitly check s to be non-NULL before invoking the macro or
> are being called with s guaranteed non-NULL, going forward it
> may easily be that NULL might be handed here. Therefore I
> think it would be better to either add an ASSERT() or do
>
> #define IS_DEFAULT(s) \
> ((s) && (s) == get_ioreq_server((s)->domain, DEFAULT_IOSERVID))
>
Ok, I'll code it as you suggest.
> .
>
> > +/*
> > + * Iterate over all possible ioreq servers. The use of inline function
> > + * get_ioreq_server() in the increment is deliberate as use of the
> > + * GET_IOREQ_SERVER() macro will cause gcc to complain about an array
> > + * overflow.
>
> I think you shouldn't accuse gcc of complaining, but simply state
> that there _will be_ an array overflow otherwise.
>
> > + */
> > +#define FOR_EACH_IOREQ_SERVER(d, id, s) \
> > + for ( (id) = 0, (s) = GET_IOREQ_SERVER(d, 0); \
> > + (id) < MAX_NR_IOREQ_SERVERS; \
> > + (s) = get_ioreq_server(d, ++(id)) ) \
> > + if ( !s ) \
>
> Alternatively, how about folding both macro and inline function
> invocation be putting them in the if() here?
I guess that now the if is there I could do that... probably will look neater.
>
> > @@ -685,52 +688,64 @@ int hvm_create_ioreq_server(struct domain *d,
> domid_t domid,
> > ioservid_t *id)
> > {
> > struct hvm_ioreq_server *s;
> > + unsigned int i;
> > int rc;
> >
> > if ( bufioreq_handling > HVM_IOREQSRV_BUFIOREQ_ATOMIC )
> > return -EINVAL;
> >
> > - rc = -ENOMEM;
> > s = xzalloc(struct hvm_ioreq_server);
> > if ( !s )
> > - goto fail1;
> > + return -ENOMEM;
> >
> > domain_pause(d);
> > spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
> >
> > - rc = -EEXIST;
> > - if ( is_default && d->arch.hvm_domain.default_ioreq_server != NULL )
> > - goto fail2;
> > -
> > - rc = hvm_ioreq_server_init(s, d, domid, is_default, bufioreq_handling,
> > - next_ioservid(d));
> > - if ( rc )
> > - goto fail3;
> > -
> > - list_add(&s->list_entry,
> > - &d->arch.hvm_domain.ioreq_server.list);
> > -
> > if ( is_default )
> > {
> > - d->arch.hvm_domain.default_ioreq_server = s;
> > - hvm_ioreq_server_enable(s, true);
> > + i = DEFAULT_IOSERVID;
> > +
> > + rc = -EEXIST;
> > + if ( GET_IOREQ_SERVER(d, i) )
> > + goto fail;
> > }
> > + else
> > + {
> > + for ( i = 0; i < MAX_NR_IOREQ_SERVERS; i++ )
> > + {
> > + if ( i != DEFAULT_IOSERVID && !GET_IOREQ_SERVER(d, i) )
> > + break;
> > + }
>
> Strictly speaking the braces here are pointless. But you're the
> maintainer, so you know what you like.
Yes, I prefer to keep them.
>
> Everything else looks fine to me now.
>
Cool. Thanks,
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* [PATCH v9 02/11] x86/hvm/ioreq: simplify code and use consistent naming
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
2017-10-06 12:25 ` [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-06 12:25 ` [PATCH v9 03/11] x86/hvm/ioreq: use gfn_t in struct hvm_ioreq_page Paul Durrant
` (8 subsequent siblings)
10 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel; +Cc: Andrew Cooper, Paul Durrant
This patch re-works much of the ioreq server initialization and teardown
code:
- The hvm_map/unmap_ioreq_gfn() functions are expanded to call through
to hvm_alloc/free_ioreq_gfn() rather than expecting them to be called
separately by outer functions.
- Several functions now test the validity of the hvm_ioreq_page gfn value
to determine whether they need to act. This means can be safely called
for the bufioreq page even when it is not used.
- hvm_add/remove_ioreq_gfn() simply return in the case of the default
IOREQ server so callers no longer need to test before calling.
- hvm_ioreq_server_setup_pages() is renamed to hvm_ioreq_server_map_pages()
to mirror the existing hvm_ioreq_server_unmap_pages().
All of this significantly shortens the code.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
v3:
- Rebased on top of 's->is_default' to 'IS_DEFAULT(s)' changes.
- Minor updates in response to review comments from Roger.
---
xen/arch/x86/hvm/ioreq.c | 182 ++++++++++++++++++-----------------------------
1 file changed, 69 insertions(+), 113 deletions(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index a6de1e7db2..f162e27ab1 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -217,63 +217,75 @@ bool handle_hvm_io_completion(struct vcpu *v)
return true;
}
-static int hvm_alloc_ioreq_gfn(struct domain *d, unsigned long *gfn)
+static unsigned long hvm_alloc_ioreq_gfn(struct hvm_ioreq_server *s)
{
+ struct domain *d = s->domain;
unsigned int i;
- int rc;
- rc = -ENOMEM;
+ ASSERT(!IS_DEFAULT(s));
+
for ( i = 0; i < sizeof(d->arch.hvm_domain.ioreq_gfn.mask) * 8; i++ )
{
if ( test_and_clear_bit(i, &d->arch.hvm_domain.ioreq_gfn.mask) )
- {
- *gfn = d->arch.hvm_domain.ioreq_gfn.base + i;
- rc = 0;
- break;
- }
+ return d->arch.hvm_domain.ioreq_gfn.base + i;
}
- return rc;
+ return gfn_x(INVALID_GFN);
}
-static void hvm_free_ioreq_gfn(struct domain *d, unsigned long gfn)
+static void hvm_free_ioreq_gfn(struct hvm_ioreq_server *s,
+ unsigned long gfn)
{
+ struct domain *d = s->domain;
unsigned int i = gfn - d->arch.hvm_domain.ioreq_gfn.base;
- if ( gfn != gfn_x(INVALID_GFN) )
- set_bit(i, &d->arch.hvm_domain.ioreq_gfn.mask);
+ ASSERT(!IS_DEFAULT(s));
+ ASSERT(gfn != gfn_x(INVALID_GFN));
+
+ set_bit(i, &d->arch.hvm_domain.ioreq_gfn.mask);
}
-static void hvm_unmap_ioreq_page(struct hvm_ioreq_server *s, bool buf)
+static void hvm_unmap_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
{
struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
+ if ( iorp->gfn == gfn_x(INVALID_GFN) )
+ return;
+
destroy_ring_for_helper(&iorp->va, iorp->page);
+ iorp->page = NULL;
+
+ if ( !IS_DEFAULT(s) )
+ hvm_free_ioreq_gfn(s, iorp->gfn);
+
+ iorp->gfn = gfn_x(INVALID_GFN);
}
-static int hvm_map_ioreq_page(
- struct hvm_ioreq_server *s, bool buf, unsigned long gfn)
+static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
{
struct domain *d = s->domain;
struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
- struct page_info *page;
- void *va;
int rc;
- if ( (rc = prepare_ring_for_helper(d, gfn, &page, &va)) )
- return rc;
-
- if ( (iorp->va != NULL) || d->is_dying )
- {
- destroy_ring_for_helper(&va, page);
+ if ( d->is_dying )
return -EINVAL;
- }
- iorp->va = va;
- iorp->page = page;
- iorp->gfn = gfn;
+ if ( IS_DEFAULT(s) )
+ iorp->gfn = buf ?
+ d->arch.hvm_domain.params[HVM_PARAM_BUFIOREQ_PFN] :
+ d->arch.hvm_domain.params[HVM_PARAM_IOREQ_PFN];
+ else
+ iorp->gfn = hvm_alloc_ioreq_gfn(s);
- return 0;
+ if ( iorp->gfn == gfn_x(INVALID_GFN) )
+ return -ENOMEM;
+
+ rc = prepare_ring_for_helper(d, iorp->gfn, &iorp->page, &iorp->va);
+
+ if ( rc )
+ hvm_unmap_ioreq_gfn(s, buf);
+
+ return rc;
}
bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
@@ -286,8 +298,7 @@ bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
FOR_EACH_IOREQ_SERVER(d, id, s)
{
- if ( (s->ioreq.va && s->ioreq.page == page) ||
- (s->bufioreq.va && s->bufioreq.page == page) )
+ if ( (s->ioreq.page == page) || (s->bufioreq.page == page) )
{
found = true;
break;
@@ -299,20 +310,30 @@ bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
return found;
}
-static void hvm_remove_ioreq_gfn(
- struct domain *d, struct hvm_ioreq_page *iorp)
+static void hvm_remove_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
+
{
+ struct domain *d = s->domain;
+ struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
+
+ if ( IS_DEFAULT(s) || iorp->gfn == gfn_x(INVALID_GFN) )
+ return;
+
if ( guest_physmap_remove_page(d, _gfn(iorp->gfn),
_mfn(page_to_mfn(iorp->page)), 0) )
domain_crash(d);
clear_page(iorp->va);
}
-static int hvm_add_ioreq_gfn(
- struct domain *d, struct hvm_ioreq_page *iorp)
+static int hvm_add_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
{
+ struct domain *d = s->domain;
+ struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
int rc;
+ if ( IS_DEFAULT(s) || iorp->gfn == gfn_x(INVALID_GFN) )
+ return 0;
+
clear_page(iorp->va);
rc = guest_physmap_add_page(d, _gfn(iorp->gfn),
@@ -447,78 +468,25 @@ static void hvm_ioreq_server_remove_all_vcpus(struct hvm_ioreq_server *s)
}
static int hvm_ioreq_server_map_pages(struct hvm_ioreq_server *s,
- unsigned long ioreq_gfn,
- unsigned long bufioreq_gfn)
+ bool handle_bufioreq)
{
int rc;
- rc = hvm_map_ioreq_page(s, false, ioreq_gfn);
- if ( rc )
- return rc;
-
- if ( bufioreq_gfn != gfn_x(INVALID_GFN) )
- rc = hvm_map_ioreq_page(s, true, bufioreq_gfn);
-
- if ( rc )
- hvm_unmap_ioreq_page(s, false);
-
- return rc;
-}
-
-static int hvm_ioreq_server_setup_pages(struct hvm_ioreq_server *s,
- bool handle_bufioreq)
-{
- struct domain *d = s->domain;
- unsigned long ioreq_gfn = gfn_x(INVALID_GFN);
- unsigned long bufioreq_gfn = gfn_x(INVALID_GFN);
- int rc;
-
- if ( IS_DEFAULT(s) )
- {
- /*
- * The default ioreq server must handle buffered ioreqs, for
- * backwards compatibility.
- */
- ASSERT(handle_bufioreq);
- return hvm_ioreq_server_map_pages(s,
- d->arch.hvm_domain.params[HVM_PARAM_IOREQ_PFN],
- d->arch.hvm_domain.params[HVM_PARAM_BUFIOREQ_PFN]);
- }
-
- rc = hvm_alloc_ioreq_gfn(d, &ioreq_gfn);
+ rc = hvm_map_ioreq_gfn(s, false);
if ( !rc && handle_bufioreq )
- rc = hvm_alloc_ioreq_gfn(d, &bufioreq_gfn);
-
- if ( !rc )
- rc = hvm_ioreq_server_map_pages(s, ioreq_gfn, bufioreq_gfn);
+ rc = hvm_map_ioreq_gfn(s, true);
if ( rc )
- {
- hvm_free_ioreq_gfn(d, ioreq_gfn);
- hvm_free_ioreq_gfn(d, bufioreq_gfn);
- }
+ hvm_unmap_ioreq_gfn(s, false);
return rc;
}
static void hvm_ioreq_server_unmap_pages(struct hvm_ioreq_server *s)
{
- struct domain *d = s->domain;
- bool handle_bufioreq = !!s->bufioreq.va;
-
- if ( handle_bufioreq )
- hvm_unmap_ioreq_page(s, true);
-
- hvm_unmap_ioreq_page(s, false);
-
- if ( !IS_DEFAULT(s) )
- {
- if ( handle_bufioreq )
- hvm_free_ioreq_gfn(d, s->bufioreq.gfn);
-
- hvm_free_ioreq_gfn(d, s->ioreq.gfn);
- }
+ hvm_unmap_ioreq_gfn(s, true);
+ hvm_unmap_ioreq_gfn(s, false);
}
static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s)
@@ -578,22 +546,15 @@ static int hvm_ioreq_server_alloc_rangesets(struct hvm_ioreq_server *s,
static void hvm_ioreq_server_enable(struct hvm_ioreq_server *s)
{
- struct domain *d = s->domain;
struct hvm_ioreq_vcpu *sv;
- bool handle_bufioreq = !!s->bufioreq.va;
spin_lock(&s->lock);
if ( s->enabled )
goto done;
- if ( !IS_DEFAULT(s) )
- {
- hvm_remove_ioreq_gfn(d, &s->ioreq);
-
- if ( handle_bufioreq )
- hvm_remove_ioreq_gfn(d, &s->bufioreq);
- }
+ hvm_remove_ioreq_gfn(s, false);
+ hvm_remove_ioreq_gfn(s, true);
s->enabled = true;
@@ -608,21 +569,13 @@ static void hvm_ioreq_server_enable(struct hvm_ioreq_server *s)
static void hvm_ioreq_server_disable(struct hvm_ioreq_server *s)
{
- struct domain *d = s->domain;
- bool handle_bufioreq = !!s->bufioreq.va;
-
spin_lock(&s->lock);
if ( !s->enabled )
goto done;
- if ( !IS_DEFAULT(s) )
- {
- if ( handle_bufioreq )
- hvm_add_ioreq_gfn(d, &s->bufioreq);
-
- hvm_add_ioreq_gfn(d, &s->ioreq);
- }
+ hvm_add_ioreq_gfn(s, true);
+ hvm_add_ioreq_gfn(s, false);
s->enabled = false;
@@ -644,6 +597,9 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
INIT_LIST_HEAD(&s->ioreq_vcpu_list);
spin_lock_init(&s->bufioreq_lock);
+ s->ioreq.gfn = gfn_x(INVALID_GFN);
+ s->bufioreq.gfn = gfn_x(INVALID_GFN);
+
rc = hvm_ioreq_server_alloc_rangesets(s, id);
if ( rc )
return rc;
@@ -651,7 +607,7 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
if ( bufioreq_handling == HVM_IOREQSRV_BUFIOREQ_ATOMIC )
s->bufioreq_atomic = true;
- rc = hvm_ioreq_server_setup_pages(
+ rc = hvm_ioreq_server_map_pages(
s, bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF);
if ( rc )
goto fail_map;
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* [PATCH v9 03/11] x86/hvm/ioreq: use gfn_t in struct hvm_ioreq_page
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
2017-10-06 12:25 ` [PATCH v9 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list Paul Durrant
2017-10-06 12:25 ` [PATCH v9 02/11] x86/hvm/ioreq: simplify code and use consistent naming Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-06 12:25 ` [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requsted Paul Durrant
` (7 subsequent siblings)
10 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel; +Cc: Andrew Cooper, Paul Durrant
This patch adjusts the ioreq server code to use type-safe gfn_t values
where possible. No functional change.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
---
xen/arch/x86/hvm/ioreq.c | 44 ++++++++++++++++++++--------------------
xen/include/asm-x86/hvm/domain.h | 2 +-
2 files changed, 23 insertions(+), 23 deletions(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index f162e27ab1..d220c8b1f7 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -217,7 +217,7 @@ bool handle_hvm_io_completion(struct vcpu *v)
return true;
}
-static unsigned long hvm_alloc_ioreq_gfn(struct hvm_ioreq_server *s)
+static gfn_t hvm_alloc_ioreq_gfn(struct hvm_ioreq_server *s)
{
struct domain *d = s->domain;
unsigned int i;
@@ -227,20 +227,19 @@ static unsigned long hvm_alloc_ioreq_gfn(struct hvm_ioreq_server *s)
for ( i = 0; i < sizeof(d->arch.hvm_domain.ioreq_gfn.mask) * 8; i++ )
{
if ( test_and_clear_bit(i, &d->arch.hvm_domain.ioreq_gfn.mask) )
- return d->arch.hvm_domain.ioreq_gfn.base + i;
+ return _gfn(d->arch.hvm_domain.ioreq_gfn.base + i);
}
- return gfn_x(INVALID_GFN);
+ return INVALID_GFN;
}
-static void hvm_free_ioreq_gfn(struct hvm_ioreq_server *s,
- unsigned long gfn)
+static void hvm_free_ioreq_gfn(struct hvm_ioreq_server *s, gfn_t gfn)
{
struct domain *d = s->domain;
- unsigned int i = gfn - d->arch.hvm_domain.ioreq_gfn.base;
+ unsigned int i = gfn_x(gfn) - d->arch.hvm_domain.ioreq_gfn.base;
ASSERT(!IS_DEFAULT(s));
- ASSERT(gfn != gfn_x(INVALID_GFN));
+ ASSERT(!gfn_eq(gfn, INVALID_GFN));
set_bit(i, &d->arch.hvm_domain.ioreq_gfn.mask);
}
@@ -249,7 +248,7 @@ static void hvm_unmap_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
{
struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
- if ( iorp->gfn == gfn_x(INVALID_GFN) )
+ if ( gfn_eq(iorp->gfn, INVALID_GFN) )
return;
destroy_ring_for_helper(&iorp->va, iorp->page);
@@ -258,7 +257,7 @@ static void hvm_unmap_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
if ( !IS_DEFAULT(s) )
hvm_free_ioreq_gfn(s, iorp->gfn);
- iorp->gfn = gfn_x(INVALID_GFN);
+ iorp->gfn = INVALID_GFN;
}
static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
@@ -271,16 +270,17 @@ static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
return -EINVAL;
if ( IS_DEFAULT(s) )
- iorp->gfn = buf ?
- d->arch.hvm_domain.params[HVM_PARAM_BUFIOREQ_PFN] :
- d->arch.hvm_domain.params[HVM_PARAM_IOREQ_PFN];
+ iorp->gfn = _gfn(buf ?
+ d->arch.hvm_domain.params[HVM_PARAM_BUFIOREQ_PFN] :
+ d->arch.hvm_domain.params[HVM_PARAM_IOREQ_PFN]);
else
iorp->gfn = hvm_alloc_ioreq_gfn(s);
- if ( iorp->gfn == gfn_x(INVALID_GFN) )
+ if ( gfn_eq(iorp->gfn, INVALID_GFN) )
return -ENOMEM;
- rc = prepare_ring_for_helper(d, iorp->gfn, &iorp->page, &iorp->va);
+ rc = prepare_ring_for_helper(d, gfn_x(iorp->gfn), &iorp->page,
+ &iorp->va);
if ( rc )
hvm_unmap_ioreq_gfn(s, buf);
@@ -316,10 +316,10 @@ static void hvm_remove_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
struct domain *d = s->domain;
struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
- if ( IS_DEFAULT(s) || iorp->gfn == gfn_x(INVALID_GFN) )
+ if ( IS_DEFAULT(s) || gfn_eq(iorp->gfn, INVALID_GFN) )
return;
- if ( guest_physmap_remove_page(d, _gfn(iorp->gfn),
+ if ( guest_physmap_remove_page(d, iorp->gfn,
_mfn(page_to_mfn(iorp->page)), 0) )
domain_crash(d);
clear_page(iorp->va);
@@ -331,12 +331,12 @@ static int hvm_add_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
int rc;
- if ( IS_DEFAULT(s) || iorp->gfn == gfn_x(INVALID_GFN) )
+ if ( IS_DEFAULT(s) || gfn_eq(iorp->gfn, INVALID_GFN) )
return 0;
clear_page(iorp->va);
- rc = guest_physmap_add_page(d, _gfn(iorp->gfn),
+ rc = guest_physmap_add_page(d, iorp->gfn,
_mfn(page_to_mfn(iorp->page)), 0);
if ( rc == 0 )
paging_mark_dirty(d, _mfn(page_to_mfn(iorp->page)));
@@ -597,8 +597,8 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
INIT_LIST_HEAD(&s->ioreq_vcpu_list);
spin_lock_init(&s->bufioreq_lock);
- s->ioreq.gfn = gfn_x(INVALID_GFN);
- s->bufioreq.gfn = gfn_x(INVALID_GFN);
+ s->ioreq.gfn = INVALID_GFN;
+ s->bufioreq.gfn = INVALID_GFN;
rc = hvm_ioreq_server_alloc_rangesets(s, id);
if ( rc )
@@ -764,11 +764,11 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
ASSERT(!IS_DEFAULT(s));
- *ioreq_gfn = s->ioreq.gfn;
+ *ioreq_gfn = gfn_x(s->ioreq.gfn);
if ( s->bufioreq.va != NULL )
{
- *bufioreq_gfn = s->bufioreq.gfn;
+ *bufioreq_gfn = gfn_x(s->bufioreq.gfn);
*bufioreq_port = s->bufioreq_evtchn;
}
diff --git a/xen/include/asm-x86/hvm/domain.h b/xen/include/asm-x86/hvm/domain.h
index e17bbe4004..3bd9c5d7c0 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -36,7 +36,7 @@
#include <public/hvm/dm_op.h>
struct hvm_ioreq_page {
- unsigned long gfn;
+ gfn_t gfn;
struct page_info *page;
void *va;
};
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requsted
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (2 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 03/11] x86/hvm/ioreq: use gfn_t in struct hvm_ioreq_page Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-09 12:45 ` Jan Beulich
2017-10-06 12:25 ` [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
` (6 subsequent siblings)
10 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, Paul Durrant, Jan Beulich
A subsequent patch will introduce a new scheme to allow an emulator to
map ioreq server pages directly from Xen rather than the guest P2M.
This patch lays the groundwork for that change by deferring mapping of
gfns until their values are requested by an emulator. To that end, the
pad field of the xen_dm_op_get_ioreq_server_info structure is re-purposed
to a flags field and new flag, XEN_DMOP_no_gfns, defined which modifies the
behaviour of XEN_DMOP_get_ioreq_server_info to allow the caller to avoid
requesting the gfn values.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
---
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
v8:
- For safety make all of the pointers passed to
hvm_get_ioreq_server_info() optional.
- Shrink bufioreq_handling down to a uint8_t.
v3:
- Updated in response to review comments from Wei and Roger.
- Added a HANDLE_BUFIOREQ macro to make the code neater.
- This patch no longer introduces a security vulnerability since there
is now an explicit limit on the number of ioreq servers that may be
created for any one domain.
---
tools/libs/devicemodel/core.c | 8 +++++
tools/libs/devicemodel/include/xendevicemodel.h | 6 ++--
xen/arch/x86/hvm/dm.c | 9 +++--
xen/arch/x86/hvm/ioreq.c | 47 ++++++++++++++-----------
xen/include/asm-x86/hvm/domain.h | 2 +-
xen/include/public/hvm/dm_op.h | 32 ++++++++++-------
6 files changed, 63 insertions(+), 41 deletions(-)
diff --git a/tools/libs/devicemodel/core.c b/tools/libs/devicemodel/core.c
index 0f2c1a791f..91c69d103b 100644
--- a/tools/libs/devicemodel/core.c
+++ b/tools/libs/devicemodel/core.c
@@ -188,6 +188,14 @@ int xendevicemodel_get_ioreq_server_info(
data->id = id;
+ /*
+ * If the caller is not requesting gfn values then instruct the
+ * hypercall not to retrieve them as this may cause them to be
+ * mapped.
+ */
+ if (!ioreq_gfn && !bufioreq_gfn)
+ data->flags |= XEN_DMOP_no_gfns;
+
rc = xendevicemodel_op(dmod, domid, 1, &op, sizeof(op));
if (rc)
return rc;
diff --git a/tools/libs/devicemodel/include/xendevicemodel.h b/tools/libs/devicemodel/include/xendevicemodel.h
index 13216db04a..d73a76da35 100644
--- a/tools/libs/devicemodel/include/xendevicemodel.h
+++ b/tools/libs/devicemodel/include/xendevicemodel.h
@@ -61,11 +61,11 @@ int xendevicemodel_create_ioreq_server(
* @parm domid the domain id to be serviced
* @parm id the IOREQ Server id.
* @parm ioreq_gfn pointer to a xen_pfn_t to receive the synchronous ioreq
- * gfn
+ * gfn. (May be NULL if not required)
* @parm bufioreq_gfn pointer to a xen_pfn_t to receive the buffered ioreq
- * gfn
+ * gfn. (May be NULL if not required)
* @parm bufioreq_port pointer to a evtchn_port_t to receive the buffered
- * ioreq event channel
+ * ioreq event channel. (May be NULL if not required)
* @return 0 on success, -1 on failure.
*/
int xendevicemodel_get_ioreq_server_info(
diff --git a/xen/arch/x86/hvm/dm.c b/xen/arch/x86/hvm/dm.c
index 9cf53b551c..22fa5b51e3 100644
--- a/xen/arch/x86/hvm/dm.c
+++ b/xen/arch/x86/hvm/dm.c
@@ -416,16 +416,19 @@ static int dm_op(const struct dmop_args *op_args)
{
struct xen_dm_op_get_ioreq_server_info *data =
&op.u.get_ioreq_server_info;
+ const uint16_t valid_flags = XEN_DMOP_no_gfns;
const_op = false;
rc = -EINVAL;
- if ( data->pad )
+ if ( data->flags & ~valid_flags )
break;
rc = hvm_get_ioreq_server_info(d, data->id,
- &data->ioreq_gfn,
- &data->bufioreq_gfn,
+ (data->flags & XEN_DMOP_no_gfns) ?
+ NULL : &data->ioreq_gfn,
+ (data->flags & XEN_DMOP_no_gfns) ?
+ NULL : &data->bufioreq_gfn,
&data->bufioreq_port);
break;
}
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index d220c8b1f7..bb4fadcc3d 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -357,6 +357,9 @@ static void hvm_update_ioreq_evtchn(struct hvm_ioreq_server *s,
}
}
+#define HANDLE_BUFIOREQ(s) \
+ (s->bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF)
+
static int hvm_ioreq_server_add_vcpu(struct hvm_ioreq_server *s,
struct vcpu *v)
{
@@ -378,7 +381,7 @@ static int hvm_ioreq_server_add_vcpu(struct hvm_ioreq_server *s,
sv->ioreq_evtchn = rc;
- if ( v->vcpu_id == 0 && s->bufioreq.va != NULL )
+ if ( v->vcpu_id == 0 && HANDLE_BUFIOREQ(s) )
{
struct domain *d = s->domain;
@@ -429,7 +432,7 @@ static void hvm_ioreq_server_remove_vcpu(struct hvm_ioreq_server *s,
list_del(&sv->list_entry);
- if ( v->vcpu_id == 0 && s->bufioreq.va != NULL )
+ if ( v->vcpu_id == 0 && HANDLE_BUFIOREQ(s) )
free_xen_event_channel(v->domain, s->bufioreq_evtchn);
free_xen_event_channel(v->domain, sv->ioreq_evtchn);
@@ -456,7 +459,7 @@ static void hvm_ioreq_server_remove_all_vcpus(struct hvm_ioreq_server *s)
list_del(&sv->list_entry);
- if ( v->vcpu_id == 0 && s->bufioreq.va != NULL )
+ if ( v->vcpu_id == 0 && HANDLE_BUFIOREQ(s) )
free_xen_event_channel(v->domain, s->bufioreq_evtchn);
free_xen_event_channel(v->domain, sv->ioreq_evtchn);
@@ -467,14 +470,13 @@ static void hvm_ioreq_server_remove_all_vcpus(struct hvm_ioreq_server *s)
spin_unlock(&s->lock);
}
-static int hvm_ioreq_server_map_pages(struct hvm_ioreq_server *s,
- bool handle_bufioreq)
+static int hvm_ioreq_server_map_pages(struct hvm_ioreq_server *s)
{
int rc;
rc = hvm_map_ioreq_gfn(s, false);
- if ( !rc && handle_bufioreq )
+ if ( !rc && HANDLE_BUFIOREQ(s) )
rc = hvm_map_ioreq_gfn(s, true);
if ( rc )
@@ -604,13 +606,7 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
if ( rc )
return rc;
- if ( bufioreq_handling == HVM_IOREQSRV_BUFIOREQ_ATOMIC )
- s->bufioreq_atomic = true;
-
- rc = hvm_ioreq_server_map_pages(
- s, bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF);
- if ( rc )
- goto fail_map;
+ s->bufioreq_handling = bufioreq_handling;
for_each_vcpu ( d, v )
{
@@ -625,9 +621,6 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
hvm_ioreq_server_remove_all_vcpus(s);
hvm_ioreq_server_unmap_pages(s);
- fail_map:
- hvm_ioreq_server_free_rangesets(s);
-
return rc;
}
@@ -764,12 +757,23 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
ASSERT(!IS_DEFAULT(s));
- *ioreq_gfn = gfn_x(s->ioreq.gfn);
+ if ( ioreq_gfn || bufioreq_gfn )
+ {
+ rc = hvm_ioreq_server_map_pages(s);
+ if ( rc )
+ goto out;
+ }
- if ( s->bufioreq.va != NULL )
+ if ( ioreq_gfn )
+ *ioreq_gfn = gfn_x(s->ioreq.gfn);
+
+ if ( HANDLE_BUFIOREQ(s) )
{
- *bufioreq_gfn = gfn_x(s->bufioreq.gfn);
- *bufioreq_port = s->bufioreq_evtchn;
+ if ( bufioreq_gfn )
+ *bufioreq_gfn = gfn_x(s->bufioreq.gfn);
+
+ if ( bufioreq_port )
+ *bufioreq_port = s->bufioreq_evtchn;
}
rc = 0;
@@ -1271,7 +1275,8 @@ static int hvm_send_buffered_ioreq(struct hvm_ioreq_server *s, ioreq_t *p)
pg->ptrs.write_pointer += qw ? 2 : 1;
/* Canonicalize read/write pointers to prevent their overflow. */
- while ( s->bufioreq_atomic && qw++ < IOREQ_BUFFER_SLOT_NUM &&
+ while ( (s->bufioreq_handling == HVM_IOREQSRV_BUFIOREQ_ATOMIC) &&
+ qw++ < IOREQ_BUFFER_SLOT_NUM &&
pg->ptrs.read_pointer >= IOREQ_BUFFER_SLOT_NUM )
{
union bufioreq_pointers old = pg->ptrs, new;
diff --git a/xen/include/asm-x86/hvm/domain.h b/xen/include/asm-x86/hvm/domain.h
index 3bd9c5d7c0..8b798ee4e9 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -69,7 +69,7 @@ struct hvm_ioreq_server {
evtchn_port_t bufioreq_evtchn;
struct rangeset *range[NR_IO_RANGE_TYPES];
bool enabled;
- bool bufioreq_atomic;
+ uint8_t bufioreq_handling;
};
/*
diff --git a/xen/include/public/hvm/dm_op.h b/xen/include/public/hvm/dm_op.h
index 6bbab5fca3..9677bd74e7 100644
--- a/xen/include/public/hvm/dm_op.h
+++ b/xen/include/public/hvm/dm_op.h
@@ -79,28 +79,34 @@ struct xen_dm_op_create_ioreq_server {
* XEN_DMOP_get_ioreq_server_info: Get all the information necessary to
* access IOREQ Server <id>.
*
- * The emulator needs to map the synchronous ioreq structures and buffered
- * ioreq ring (if it exists) that Xen uses to request emulation. These are
- * hosted in the target domain's gmfns <ioreq_gfn> and <bufioreq_gfn>
- * respectively. In addition, if the IOREQ Server is handling buffered
- * emulation requests, the emulator needs to bind to event channel
- * <bufioreq_port> to listen for them. (The event channels used for
- * synchronous emulation requests are specified in the per-CPU ioreq
- * structures in <ioreq_gfn>).
- * If the IOREQ Server is not handling buffered emulation requests then the
- * values handed back in <bufioreq_gfn> and <bufioreq_port> will both be 0.
+ * If the IOREQ Server is handling buffered emulation requests, the
+ * emulator needs to bind to event channel <bufioreq_port> to listen for
+ * them. (The event channels used for synchronous emulation requests are
+ * specified in the per-CPU ioreq structures).
+ * In addition, if the XENMEM_acquire_resource memory op cannot be used,
+ * the emulator will need to map the synchronous ioreq structures and
+ * buffered ioreq ring (if it exists) from guest memory. If <flags> does
+ * not contain XEN_DMOP_no_gfns then these pages will be made available and
+ * the frame numbers passed back in gfns <ioreq_gfn> and <bufioreq_gfn>
+ * respectively. (If the IOREQ Server is not handling buffered emulation
+ * only <ioreq_gfn> will be valid).
*/
#define XEN_DMOP_get_ioreq_server_info 2
struct xen_dm_op_get_ioreq_server_info {
/* IN - server id */
ioservid_t id;
- uint16_t pad;
+ /* IN - flags */
+ uint16_t flags;
+
+#define _XEN_DMOP_no_gfns 0
+#define XEN_DMOP_no_gfns (1u << _XEN_DMOP_no_gfns)
+
/* OUT - buffered ioreq port */
evtchn_port_t bufioreq_port;
- /* OUT - sync ioreq gfn */
+ /* OUT - sync ioreq gfn (see block comment above) */
uint64_aligned_t ioreq_gfn;
- /* OUT - buffered ioreq gfn */
+ /* OUT - buffered ioreq gfn (see block comment above)*/
uint64_aligned_t bufioreq_gfn;
};
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* Re: [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requsted
2017-10-06 12:25 ` [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requsted Paul Durrant
@ 2017-10-09 12:45 ` Jan Beulich
2017-10-09 12:47 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-09 12:45 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, xen-devel
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> --- a/xen/arch/x86/hvm/ioreq.c
> +++ b/xen/arch/x86/hvm/ioreq.c
> @@ -357,6 +357,9 @@ static void hvm_update_ioreq_evtchn(struct hvm_ioreq_server *s,
> }
> }
>
> +#define HANDLE_BUFIOREQ(s) \
> + (s->bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF)
Didn't I point out already that s wants to be parenthesized here?
Or was that on another macro? With this taken care of
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* Re: [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requsted
2017-10-09 12:45 ` Jan Beulich
@ 2017-10-09 12:47 ` Paul Durrant
0 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-09 12:47 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 09 October 2017 13:46
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; George Dunlap
> <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>;
> Stefano Stabellini <sstabellini@kernel.org>; xen-devel@lists.xenproject.org;
> Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>; Tim (Xen.org)
> <tim@xen.org>
> Subject: Re: [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they
> are actually requsted
>
> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > --- a/xen/arch/x86/hvm/ioreq.c
> > +++ b/xen/arch/x86/hvm/ioreq.c
> > @@ -357,6 +357,9 @@ static void hvm_update_ioreq_evtchn(struct
> hvm_ioreq_server *s,
> > }
> > }
> >
> > +#define HANDLE_BUFIOREQ(s) \
> > + (s->bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF)
>
> Didn't I point out already that s wants to be parenthesized here?
> Or was that on another macro?
Sorry, I think you did.... I just forgot.
> With this taken care of
> Reviewed-by: Jan Beulich <jbeulich@suse.com>
>
Ok, thanks.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (3 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requsted Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-09 13:05 ` Jan Beulich
2017-10-09 14:23 ` Jan Beulich
2017-10-06 12:25 ` [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type Paul Durrant
` (5 subsequent siblings)
10 siblings, 2 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, Paul Durrant, Jan Beulich
Certain memory resources associated with a guest are not necessarily
present in the guest P2M.
This patch adds the boilerplate for new memory op to allow such a resource
to be priv-mapped directly, by either a PV or HVM tools domain.
NOTE: Whilst the new op is not intrinsicly specific to the x86 architecture,
I have no means to test it on an ARM platform and so cannot verify
that it functions correctly. Hence it is currently only implemented
for x86.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
---
Cc: George Dunlap <george.dunlap@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
v8:
- Move the code into common as requested by Jan.
- Make the gmfn_list handle a 64-bit type to avoid limiting the MFN
range for a 32-bit tools domain.
- Add missing pad.
- Add compat code.
- Make this patch deal with purely boilerplate.
- Drop George's A-b and Wei's R-b because the changes are non-trivial,
and update Cc list now the boilerplate is common.
v5:
- Switched __copy_to/from_guest_offset() to copy_to/from_guest_offset().
---
xen/arch/x86/mm/p2m.c | 3 +-
xen/common/compat/memory.c | 52 ++++++++++++++++++++++++++++++
xen/common/memory.c | 77 +++++++++++++++++++++++++++++++++++++++++++++
xen/include/asm-x86/p2m.h | 3 ++
xen/include/public/memory.h | 32 ++++++++++++++++++-
xen/include/xlat.lst | 1 +
6 files changed, 165 insertions(+), 3 deletions(-)
diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 3fbc537da6..ecc69d0093 100644
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1131,8 +1131,7 @@ static int set_typed_p2m_entry(struct domain *d, unsigned long gfn_l,
}
/* Set foreign mfn in the given guest's p2m table. */
-static int set_foreign_p2m_entry(struct domain *d, unsigned long gfn,
- mfn_t mfn)
+int set_foreign_p2m_entry(struct domain *d, unsigned long gfn, mfn_t mfn)
{
return set_typed_p2m_entry(d, gfn, mfn, PAGE_ORDER_4K, p2m_map_foreign,
p2m_get_hostp2m(d)->default_access);
diff --git a/xen/common/compat/memory.c b/xen/common/compat/memory.c
index 35bb259808..3af7922e59 100644
--- a/xen/common/compat/memory.c
+++ b/xen/common/compat/memory.c
@@ -71,6 +71,7 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
struct xen_remove_from_physmap *xrfp;
struct xen_vnuma_topology_info *vnuma;
struct xen_mem_access_op *mao;
+ struct xen_mem_acquire_resource *mar;
} nat;
union {
struct compat_memory_reservation rsrv;
@@ -79,6 +80,7 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
struct compat_add_to_physmap_batch atpb;
struct compat_vnuma_topology_info vnuma;
struct compat_mem_access_op mao;
+ struct compat_mem_acquire_resource mar;
} cmp;
set_xen_guest_handle(nat.hnd, COMPAT_ARG_XLAT_VIRT_BASE);
@@ -395,6 +397,39 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
}
#endif
+ case XENMEM_acquire_resource:
+ {
+ xen_ulong_t *gmfn_list = (xen_ulong_t *)(nat.mar + 1);
+
+ if ( copy_from_guest(&cmp.mar, compat, 1) ||
+ !compat_handle_okay(cmp.mar.gmfn_list,
+ cmp.mar.nr_frames) )
+ return -EFAULT;
+
+ if ( sizeof(*gmfn_list) * cmp.mar.nr_frames >
+ COMPAT_ARG_XLAT_SIZE - sizeof(*nat.mar) )
+ return -E2BIG;
+
+ for ( i = 0; i < cmp.mar.nr_frames; i++ )
+ {
+ compat_ulong_t gmfn;
+
+ if ( __copy_from_compat_offset(&gmfn, cmp.mar.gmfn_list,
+ i, 1) )
+ return -EFAULT;
+
+ gmfn_list[i] = gmfn;
+ }
+
+#define XLAT_mem_acquire_resource_HNDL_gmfn_list(_d_, _s_) \
+ set_xen_guest_handle((_d_)->gmfn_list, gmfn_list)
+
+ XLAT_mem_acquire_resource(nat.mar, &cmp.mar);
+
+#undef XLAT_mem_acquire_resource_HNDL_gmfn_list
+
+ break;
+ }
default:
return compat_arch_memory_op(cmd, compat);
}
@@ -535,6 +570,23 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
rc = -EFAULT;
break;
+ case XENMEM_acquire_resource:
+ {
+ xen_ulong_t *gmfn_list = (xen_ulong_t *)(nat.mar + 1);
+
+ for ( i = 0; i < cmp.mar.nr_frames; i++ )
+ {
+ compat_ulong_t gmfn = gmfn_list[i];
+
+ if ( gmfn != gmfn_list[i] )
+ return -ERANGE;
+
+ if ( __copy_to_compat_offset(cmp.mar.gmfn_list, i,
+ &gmfn, 1) )
+ return -EFAULT;
+ }
+ break;
+ }
default:
domain_crash(current->domain);
split = 0;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index ad987e0f29..910c0c5063 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
}
+#ifdef CONFIG_X86
+static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
+{
+ struct domain *d, *currd = current->domain;
+ unsigned long mfn_list[2];
+ int rc;
+
+ if ( xmar->nr_frames == 0 || xmar->pad != 0 )
+ return -EINVAL;
+
+ if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
+ return -E2BIG;
+
+ d = rcu_lock_domain_by_any_id(xmar->domid);
+ if ( d == NULL )
+ return -ESRCH;
+
+ rc = xsm_domain_memory_map(XSM_TARGET, d);
+ if ( rc )
+ goto out;
+
+ switch ( xmar->type )
+ {
+ default:
+ rc = -EOPNOTSUPP;
+ break;
+ }
+
+ if ( rc )
+ goto out;
+
+ if ( !paging_mode_translate(currd) )
+ {
+ if ( copy_to_guest_offset(xmar->gmfn_list, 0, mfn_list,
+ xmar->nr_frames) )
+ rc = -EFAULT;
+ }
+ else
+ {
+ unsigned int i;
+
+ for ( i = 0; i < xmar->nr_frames; i++ )
+ {
+ xen_pfn_t gfn;
+
+ rc = -EFAULT;
+ if ( copy_from_guest_offset(&gfn, xmar->gmfn_list, i, 1) )
+ goto out;
+
+ rc = set_foreign_p2m_entry(currd, gfn, _mfn(mfn_list[i]));
+ if ( rc )
+ goto out;
+ }
+ }
+
+ out:
+ rcu_unlock_domain(d);
+ return rc;
+}
+#endif /* CONFIG_X86 */
+
long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
{
struct domain *d, *curr_d = current->domain;
@@ -1406,6 +1467,22 @@ long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
}
#endif
+ case XENMEM_acquire_resource:
+#ifdef CONFIG_X86
+ {
+ xen_mem_acquire_resource_t xmar;
+
+ if ( copy_from_guest(&xmar, arg, 1) )
+ return -EFAULT;
+
+ rc = acquire_resource(&xmar);
+ break;
+ }
+#else
+ rc = -EOPNOTSUPP;
+ break;
+#endif
+
default:
rc = arch_memory_op(cmd, arg);
break;
diff --git a/xen/include/asm-x86/p2m.h b/xen/include/asm-x86/p2m.h
index 70f00c332f..52ce507e96 100644
--- a/xen/include/asm-x86/p2m.h
+++ b/xen/include/asm-x86/p2m.h
@@ -613,6 +613,9 @@ void p2m_memory_type_changed(struct domain *d);
int p2m_is_logdirty_range(struct p2m_domain *, unsigned long start,
unsigned long end);
+/* Set foreign entry in the p2m table (for priv-mapping) */
+int set_foreign_p2m_entry(struct domain *d, unsigned long gfn, mfn_t mfn);
+
/* Set mmio addresses in the p2m table (for pass-through) */
int set_mmio_p2m_entry(struct domain *d, unsigned long gfn, mfn_t mfn,
unsigned int order, p2m_access_t access);
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index 29386df98b..3aa8fb2fe1 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -599,6 +599,36 @@ struct xen_reserved_device_memory_map {
typedef struct xen_reserved_device_memory_map xen_reserved_device_memory_map_t;
DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
+/*
+ * Get the pages for a particular guest resource, so that they can be
+ * mapped directly by a tools domain.
+ */
+#define XENMEM_acquire_resource 28
+struct xen_mem_acquire_resource {
+ /* IN - the domain whose resource is to be mapped */
+ domid_t domid;
+ /* IN - the type of resource */
+ uint16_t type;
+ /*
+ * IN - a type-specific resource identifier, which must be zero
+ * unless stated otherwise.
+ */
+ uint32_t id;
+ /* IN - number of (4K) frames of the resource to be mapped */
+ uint32_t nr_frames;
+ uint32_t pad;
+ /* IN - the index of the initial frame to be mapped */
+ uint64_aligned_t frame;
+ /* IN/OUT - If the tools domain is PV then, upon return, gmfn_list
+ * will be populated with the MFNs of the resource.
+ * If the tools domain is HVM then it is expected that, on
+ * entry, gmfn_list will be populated with a list of GFNs
+ * that will be mapped to the MFNs of the resource.
+ */
+ XEN_GUEST_HANDLE(xen_ulong_t) gmfn_list;
+};
+typedef struct xen_mem_acquire_resource xen_mem_acquire_resource_t;
+
#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */
/*
@@ -650,7 +680,7 @@ 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 28 */
+/* Next available subop number is 29 */
#endif /* __XEN_PUBLIC_MEMORY_H__ */
diff --git a/xen/include/xlat.lst b/xen/include/xlat.lst
index 0f17000ea7..5835872334 100644
--- a/xen/include/xlat.lst
+++ b/xen/include/xlat.lst
@@ -83,6 +83,7 @@
! memory_map memory.h
! memory_reservation memory.h
! mem_access_op memory.h
+! mem_acquire_resource memory.h
! pod_target memory.h
! remove_from_physmap memory.h
! reserved_device_memory_map memory.h
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-06 12:25 ` [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
@ 2017-10-09 13:05 ` Jan Beulich
2017-10-10 13:26 ` Paul Durrant
2017-10-09 14:23 ` Jan Beulich
1 sibling, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-09 13:05 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, IanJackson, TimDeegan, xen-devel
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> @@ -395,6 +397,39 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
> }
> #endif
>
> + case XENMEM_acquire_resource:
> + {
> + xen_ulong_t *gmfn_list = (xen_ulong_t *)(nat.mar + 1);
> +
> + if ( copy_from_guest(&cmp.mar, compat, 1) ||
> + !compat_handle_okay(cmp.mar.gmfn_list,
> + cmp.mar.nr_frames) )
> + return -EFAULT;
> +
> + if ( sizeof(*gmfn_list) * cmp.mar.nr_frames >
> + COMPAT_ARG_XLAT_SIZE - sizeof(*nat.mar) )
> + return -E2BIG;
With the actual handler accepting no more than 2 entries this is
certainly good enough for now, but since larger arrays could be
handled here perhaps a comment would be helpful to clarify
why this is sufficient atm.
> @@ -535,6 +570,23 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
> rc = -EFAULT;
> break;
>
> + case XENMEM_acquire_resource:
> + {
> + xen_ulong_t *gmfn_list = (xen_ulong_t *)(nat.mar + 1);
> +
> + for ( i = 0; i < cmp.mar.nr_frames; i++ )
> + {
> + compat_ulong_t gmfn = gmfn_list[i];
> +
> + if ( gmfn != gmfn_list[i] )
> + return -ERANGE;
> +
> + if ( __copy_to_compat_offset(cmp.mar.gmfn_list, i,
> + &gmfn, 1) )
> + return -EFAULT;
While I consider it acceptable to leave kind of inconsistent state in
this latter case (as it's under guest control to avoid the situation),
I'm not sure the -ERANGE return above wouldn't better be
accompanied by undoing the operation. Undoing in both cases
would become imperative once set_foreign_p2m_entry() acquires
proper page references.
> --- a/xen/common/memory.c
> +++ b/xen/common/memory.c
> @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
> return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> }
>
> +#ifdef CONFIG_X86
Could you try to (a) have only a single such #ifdef and (b) reduce
its scope as much as possible? Even if for now the code is dead on
ARM, making sure it continues to compile there would be helpful.
> +static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
> +{
> + struct domain *d, *currd = current->domain;
> + unsigned long mfn_list[2];
> + int rc;
> +
> + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
> + return -EINVAL;
> +
> + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
> + return -E2BIG;
> +
> + d = rcu_lock_domain_by_any_id(xmar->domid);
> + if ( d == NULL )
> + return -ESRCH;
> +
> + rc = xsm_domain_memory_map(XSM_TARGET, d);
> + if ( rc )
> + goto out;
> +
> + switch ( xmar->type )
> + {
> + default:
> + rc = -EOPNOTSUPP;
> + break;
> + }
> +
> + if ( rc )
> + goto out;
> +
> + if ( !paging_mode_translate(currd) )
> + {
> + if ( copy_to_guest_offset(xmar->gmfn_list, 0, mfn_list,
> + xmar->nr_frames) )
Just copy_to_guest()?
> + rc = -EFAULT;
> + }
> + else
> + {
> + unsigned int i;
> +
> + for ( i = 0; i < xmar->nr_frames; i++ )
> + {
> + xen_pfn_t gfn;
> +
> + rc = -EFAULT;
> + if ( copy_from_guest_offset(&gfn, xmar->gmfn_list, i, 1) )
> + goto out;
> +
> + rc = set_foreign_p2m_entry(currd, gfn, _mfn(mfn_list[i]));
> + if ( rc )
> + goto out;
Perhaps partial success indication would be necessary here, so
the caller knows what to undo later. Or alternatively (just like
said for the compat wrapper) you may want/need to clean up
yourself.
> --- a/xen/include/public/memory.h
> +++ b/xen/include/public/memory.h
> @@ -599,6 +599,36 @@ struct xen_reserved_device_memory_map {
> typedef struct xen_reserved_device_memory_map xen_reserved_device_memory_map_t;
> DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
>
> +/*
> + * Get the pages for a particular guest resource, so that they can be
> + * mapped directly by a tools domain.
> + */
> +#define XENMEM_acquire_resource 28
> +struct xen_mem_acquire_resource {
> + /* IN - the domain whose resource is to be mapped */
> + domid_t domid;
> + /* IN - the type of resource */
> + uint16_t type;
> + /*
> + * IN - a type-specific resource identifier, which must be zero
> + * unless stated otherwise.
> + */
> + uint32_t id;
> + /* IN - number of (4K) frames of the resource to be mapped */
> + uint32_t nr_frames;
> + uint32_t pad;
> + /* IN - the index of the initial frame to be mapped */
> + uint64_aligned_t frame;
Does this really need to be 64 bits wide?
> + /* IN/OUT - If the tools domain is PV then, upon return, gmfn_list
> + * will be populated with the MFNs of the resource.
> + * If the tools domain is HVM then it is expected that, on
> + * entry, gmfn_list will be populated with a list of GFNs
> + * that will be mapped to the MFNs of the resource.
> + */
> + XEN_GUEST_HANDLE(xen_ulong_t) gmfn_list;
Why not xen_pfn_t?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-09 13:05 ` Jan Beulich
@ 2017-10-10 13:26 ` Paul Durrant
2017-10-11 8:20 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-10 13:26 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 09 October 2017 14:06
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; George Dunlap <George.Dunlap@citrix.com>; Ian
> Jackson <Ian.Jackson@citrix.com>; Stefano Stabellini
> <sstabellini@kernel.org>; xen-devel@lists.xenproject.org; Konrad Rzeszutek
> Wilk <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > @@ -395,6 +397,39 @@ int compat_memory_op(unsigned int cmd,
> XEN_GUEST_HANDLE_PARAM(void) compat)
> > }
> > #endif
> >
> > + case XENMEM_acquire_resource:
> > + {
> > + xen_ulong_t *gmfn_list = (xen_ulong_t *)(nat.mar + 1);
> > +
> > + if ( copy_from_guest(&cmp.mar, compat, 1) ||
> > + !compat_handle_okay(cmp.mar.gmfn_list,
> > + cmp.mar.nr_frames) )
> > + return -EFAULT;
> > +
> > + if ( sizeof(*gmfn_list) * cmp.mar.nr_frames >
> > + COMPAT_ARG_XLAT_SIZE - sizeof(*nat.mar) )
> > + return -E2BIG;
>
> With the actual handler accepting no more than 2 entries this is
> certainly good enough for now, but since larger arrays could be
> handled here perhaps a comment would be helpful to clarify
> why this is sufficient atm.
Ok.
>
> > @@ -535,6 +570,23 @@ int compat_memory_op(unsigned int cmd,
> XEN_GUEST_HANDLE_PARAM(void) compat)
> > rc = -EFAULT;
> > break;
> >
> > + case XENMEM_acquire_resource:
> > + {
> > + xen_ulong_t *gmfn_list = (xen_ulong_t *)(nat.mar + 1);
> > +
> > + for ( i = 0; i < cmp.mar.nr_frames; i++ )
> > + {
> > + compat_ulong_t gmfn = gmfn_list[i];
> > +
> > + if ( gmfn != gmfn_list[i] )
> > + return -ERANGE;
> > +
> > + if ( __copy_to_compat_offset(cmp.mar.gmfn_list, i,
> > + &gmfn, 1) )
> > + return -EFAULT;
>
> While I consider it acceptable to leave kind of inconsistent state in
> this latter case (as it's under guest control to avoid the situation),
> I'm not sure the -ERANGE return above wouldn't better be
> accompanied by undoing the operation. Undoing in both cases
> would become imperative once set_foreign_p2m_entry() acquires
> proper page references.
Ok. I'll try to make sure things get left in a consistent state.
>
> > --- a/xen/common/memory.c
> > +++ b/xen/common/memory.c
> > @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain
> *d, unsigned int space)
> > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> > }
> >
> > +#ifdef CONFIG_X86
>
> Could you try to (a) have only a single such #ifdef and (b) reduce
> its scope as much as possible? Even if for now the code is dead on
> ARM, making sure it continues to compile there would be helpful.
>
Ok. I don't have an arm machine to build on so I can't tell if anything is broken though.
> > +static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
> > +{
> > + struct domain *d, *currd = current->domain;
> > + unsigned long mfn_list[2];
> > + int rc;
> > +
> > + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
> > + return -EINVAL;
> > +
> > + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
> > + return -E2BIG;
> > +
> > + d = rcu_lock_domain_by_any_id(xmar->domid);
> > + if ( d == NULL )
> > + return -ESRCH;
> > +
> > + rc = xsm_domain_memory_map(XSM_TARGET, d);
> > + if ( rc )
> > + goto out;
> > +
> > + switch ( xmar->type )
> > + {
> > + default:
> > + rc = -EOPNOTSUPP;
> > + break;
> > + }
> > +
> > + if ( rc )
> > + goto out;
> > +
> > + if ( !paging_mode_translate(currd) )
> > + {
> > + if ( copy_to_guest_offset(xmar->gmfn_list, 0, mfn_list,
> > + xmar->nr_frames) )
>
> Just copy_to_guest()?
>
Ok, if that is preferable.
> > + rc = -EFAULT;
> > + }
> > + else
> > + {
> > + unsigned int i;
> > +
> > + for ( i = 0; i < xmar->nr_frames; i++ )
> > + {
> > + xen_pfn_t gfn;
> > +
> > + rc = -EFAULT;
> > + if ( copy_from_guest_offset(&gfn, xmar->gmfn_list, i, 1) )
> > + goto out;
> > +
> > + rc = set_foreign_p2m_entry(currd, gfn, _mfn(mfn_list[i]));
> > + if ( rc )
> > + goto out;
>
> Perhaps partial success indication would be necessary here, so
> the caller knows what to undo later. Or alternatively (just like
> said for the compat wrapper) you may want/need to clean up
> yourself.
OK.
>
> > --- a/xen/include/public/memory.h
> > +++ b/xen/include/public/memory.h
> > @@ -599,6 +599,36 @@ struct xen_reserved_device_memory_map {
> > typedef struct xen_reserved_device_memory_map
> xen_reserved_device_memory_map_t;
> > DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
> >
> > +/*
> > + * Get the pages for a particular guest resource, so that they can be
> > + * mapped directly by a tools domain.
> > + */
> > +#define XENMEM_acquire_resource 28
> > +struct xen_mem_acquire_resource {
> > + /* IN - the domain whose resource is to be mapped */
> > + domid_t domid;
> > + /* IN - the type of resource */
> > + uint16_t type;
> > + /*
> > + * IN - a type-specific resource identifier, which must be zero
> > + * unless stated otherwise.
> > + */
> > + uint32_t id;
> > + /* IN - number of (4K) frames of the resource to be mapped */
> > + uint32_t nr_frames;
> > + uint32_t pad;
> > + /* IN - the index of the initial frame to be mapped */
> > + uint64_aligned_t frame;
>
> Does this really need to be 64 bits wide?
>
I'd prefer not to limit to 32 bits just in case we want to use this hypercall to map something with a large frame space.
> > + /* IN/OUT - If the tools domain is PV then, upon return, gmfn_list
> > + * will be populated with the MFNs of the resource.
> > + * If the tools domain is HVM then it is expected that, on
> > + * entry, gmfn_list will be populated with a list of GFNs
> > + * that will be mapped to the MFNs of the resource.
> > + */
> > + XEN_GUEST_HANDLE(xen_ulong_t) gmfn_list;
>
> Why not xen_pfn_t?
I've debated this with myself a few times. I'm not convinced that something that could be an mfn or a gfn should have a xen_pfn_t type.
Paul
>
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-10 13:26 ` Paul Durrant
@ 2017-10-11 8:20 ` Jan Beulich
0 siblings, 0 replies; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 8:20 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
>>> On 10.10.17 at 15:26, <Paul.Durrant@citrix.com> wrote:
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 09 October 2017 14:06
>> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
>> > --- a/xen/common/memory.c
>> > +++ b/xen/common/memory.c
>> > @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain
>> *d, unsigned int space)
>> > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
>> > }
>> >
>> > +#ifdef CONFIG_X86
>>
>> Could you try to (a) have only a single such #ifdef and (b) reduce
>> its scope as much as possible? Even if for now the code is dead on
>> ARM, making sure it continues to compile there would be helpful.
>>
>
> Ok. I don't have an arm machine to build on so I can't tell if anything is
> broken though.
Well, that's the case for most of us x86 people. I use a cross
compiler to be able to at least check the ARM build is okay.
>> > --- a/xen/include/public/memory.h
>> > +++ b/xen/include/public/memory.h
>> > @@ -599,6 +599,36 @@ struct xen_reserved_device_memory_map {
>> > typedef struct xen_reserved_device_memory_map
>> xen_reserved_device_memory_map_t;
>> > DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
>> >
>> > +/*
>> > + * Get the pages for a particular guest resource, so that they can be
>> > + * mapped directly by a tools domain.
>> > + */
>> > +#define XENMEM_acquire_resource 28
>> > +struct xen_mem_acquire_resource {
>> > + /* IN - the domain whose resource is to be mapped */
>> > + domid_t domid;
>> > + /* IN - the type of resource */
>> > + uint16_t type;
>> > + /*
>> > + * IN - a type-specific resource identifier, which must be zero
>> > + * unless stated otherwise.
>> > + */
>> > + uint32_t id;
>> > + /* IN - number of (4K) frames of the resource to be mapped */
>> > + uint32_t nr_frames;
>> > + uint32_t pad;
>> > + /* IN - the index of the initial frame to be mapped */
>> > + uint64_aligned_t frame;
>>
>> Does this really need to be 64 bits wide?
>
> I'd prefer not to limit to 32 bits just in case we want to use this
> hypercall to map something with a large frame space.
In which case you'll need to take care of the truncation issues I've
pointed out elsewhere.
>> > + /* IN/OUT - If the tools domain is PV then, upon return, gmfn_list
>> > + * will be populated with the MFNs of the resource.
>> > + * If the tools domain is HVM then it is expected that, on
>> > + * entry, gmfn_list will be populated with a list of GFNs
>> > + * that will be mapped to the MFNs of the resource.
>> > + */
>> > + XEN_GUEST_HANDLE(xen_ulong_t) gmfn_list;
>>
>> Why not xen_pfn_t?
>
> I've debated this with myself a few times. I'm not convinced that something
> that could be an mfn or a gfn should have a xen_pfn_t type.
Well, looking over the present uses of xen_pfn_t it looks like quite
a few are for mixed meaning uses between PV and HVM. And btw,
since we try to get rid of the term "GMFN", perhaps "frame_list"
might be a better field name here.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-06 12:25 ` [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
2017-10-09 13:05 ` Jan Beulich
@ 2017-10-09 14:23 ` Jan Beulich
2017-10-10 14:10 ` Paul Durrant
1 sibling, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-09 14:23 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, IanJackson, TimDeegan, xen-devel
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> --- a/xen/common/memory.c
> +++ b/xen/common/memory.c
> @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
> return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> }
>
> +#ifdef CONFIG_X86
> +static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
> +{
> + struct domain *d, *currd = current->domain;
> + unsigned long mfn_list[2];
> + int rc;
> +
> + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
> + return -EINVAL;
> +
> + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
> + return -E2BIG;
> +
> + d = rcu_lock_domain_by_any_id(xmar->domid);
> + if ( d == NULL )
> + return -ESRCH;
> +
> + rc = xsm_domain_memory_map(XSM_TARGET, d);
Looking at the description of patch 6 - why is this XSM_TARGET
rather than XSM_DM_PRIV?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-09 14:23 ` Jan Beulich
@ 2017-10-10 14:10 ` Paul Durrant
2017-10-10 14:37 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-10 14:10 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 09 October 2017 15:23
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; George Dunlap <George.Dunlap@citrix.com>; Ian
> Jackson <Ian.Jackson@citrix.com>; Stefano Stabellini
> <sstabellini@kernel.org>; xen-devel@lists.xenproject.org; Konrad Rzeszutek
> Wilk <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > --- a/xen/common/memory.c
> > +++ b/xen/common/memory.c
> > @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain
> *d, unsigned int space)
> > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> > }
> >
> > +#ifdef CONFIG_X86
> > +static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
> > +{
> > + struct domain *d, *currd = current->domain;
> > + unsigned long mfn_list[2];
> > + int rc;
> > +
> > + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
> > + return -EINVAL;
> > +
> > + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
> > + return -E2BIG;
> > +
> > + d = rcu_lock_domain_by_any_id(xmar->domid);
> > + if ( d == NULL )
> > + return -ESRCH;
> > +
> > + rc = xsm_domain_memory_map(XSM_TARGET, d);
>
> Looking at the description of patch 6 - why is this XSM_TARGET
> rather than XSM_DM_PRIV?
Good point. I was using the priv mapping code as a guide, but XSM_DM_PRIV is probably the right thing to use in this case.
Paul
>
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-10 14:10 ` Paul Durrant
@ 2017-10-10 14:37 ` Paul Durrant
2017-10-11 8:30 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-10 14:37 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: 'Stefano Stabellini', Wei Liu,
'Konrad Rzeszutek Wilk', Andrew Cooper, Tim (Xen.org),
George Dunlap, Ian Jackson,
'xen-devel@lists.xenproject.org'
> -----Original Message-----
> From: Paul Durrant
> Sent: 10 October 2017 15:10
> To: 'Jan Beulich' <JBeulich@suse.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; George Dunlap <George.Dunlap@citrix.com>; Ian
> Jackson <Ian.Jackson@citrix.com>; Stefano Stabellini
> <sstabellini@kernel.org>; xen-devel@lists.xenproject.org; Konrad Rzeszutek
> Wilk <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: RE: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> > -----Original Message-----
> > From: Jan Beulich [mailto:JBeulich@suse.com]
> > Sent: 09 October 2017 15:23
> > To: Paul Durrant <Paul.Durrant@citrix.com>
> > Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; Wei Liu
> > <wei.liu2@citrix.com>; George Dunlap <George.Dunlap@citrix.com>; Ian
> > Jackson <Ian.Jackson@citrix.com>; Stefano Stabellini
> > <sstabellini@kernel.org>; xen-devel@lists.xenproject.org; Konrad
> Rzeszutek
> > Wilk <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> > Subject: Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to
> > acquire guest resources
> >
> > >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > > --- a/xen/common/memory.c
> > > +++ b/xen/common/memory.c
> > > @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain
> > *d, unsigned int space)
> > > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> > > }
> > >
> > > +#ifdef CONFIG_X86
> > > +static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
> > > +{
> > > + struct domain *d, *currd = current->domain;
> > > + unsigned long mfn_list[2];
> > > + int rc;
> > > +
> > > + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
> > > + return -EINVAL;
> > > +
> > > + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
> > > + return -E2BIG;
> > > +
> > > + d = rcu_lock_domain_by_any_id(xmar->domid);
> > > + if ( d == NULL )
> > > + return -ESRCH;
> > > +
> > > + rc = xsm_domain_memory_map(XSM_TARGET, d);
> >
> > Looking at the description of patch 6 - why is this XSM_TARGET
> > rather than XSM_DM_PRIV?
>
> Good point. I was using the priv mapping code as a guide, but XSM_DM_PRIV
> is probably the right thing to use in this case.
>
Actually that's not possible. There is an assertion in xsm_domain_memory_map() that the action is XSM_TARGET.
Paul
> Paul
>
> >
> > Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-10 14:37 ` Paul Durrant
@ 2017-10-11 8:30 ` Jan Beulich
2017-10-11 8:38 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 8:30 UTC (permalink / raw)
To: Paul Durrant
Cc: 'Stefano Stabellini', Wei Liu,
'KonradRzeszutek Wilk', Andrew Cooper, Tim (Xen.org),
George Dunlap, Ian Jackson,
'xen-devel@lists.xenproject.org'
>>> On 10.10.17 at 16:37, <Paul.Durrant@citrix.com> wrote:
>> From: Paul Durrant
>> Sent: 10 October 2017 15:10
>> > From: Jan Beulich [mailto:JBeulich@suse.com]
>> > Sent: 09 October 2017 15:23
>> > To: Paul Durrant <Paul.Durrant@citrix.com>
>> > >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
>> > > --- a/xen/common/memory.c
>> > > +++ b/xen/common/memory.c
>> > > @@ -965,6 +965,67 @@ static long xatp_permission_check(struct domain
>> > *d, unsigned int space)
>> > > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
>> > > }
>> > >
>> > > +#ifdef CONFIG_X86
>> > > +static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
>> > > +{
>> > > + struct domain *d, *currd = current->domain;
>> > > + unsigned long mfn_list[2];
>> > > + int rc;
>> > > +
>> > > + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
>> > > + return -EINVAL;
>> > > +
>> > > + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
>> > > + return -E2BIG;
>> > > +
>> > > + d = rcu_lock_domain_by_any_id(xmar->domid);
>> > > + if ( d == NULL )
>> > > + return -ESRCH;
>> > > +
>> > > + rc = xsm_domain_memory_map(XSM_TARGET, d);
>> >
>> > Looking at the description of patch 6 - why is this XSM_TARGET
>> > rather than XSM_DM_PRIV?
>>
>> Good point. I was using the priv mapping code as a guide, but XSM_DM_PRIV
>> is probably the right thing to use in this case.
>>
>
> Actually that's not possible. There is an assertion in
> xsm_domain_memory_map() that the action is XSM_TARGET.
Well, I was afraid of this being the case, but this only complicates
your job, it doesn't make XSM_TARGET the right choice here. But
wait, maybe it can be considered sufficient, but then this needs
to be prominently pointed out by a comment added at a suitable
place: For the ioreq pages, them being owned by the emulating
domain, page ownership validations while trying to make use of the
MFNs would prevent mis-use by the domain the emulation is being
done for. And for grant table pages the guest is able to access
them another way anyway.
Which basically leaves the question of this being an information
leak for ioreq pages, as the guest is not supposed to know the
MFNs, but could obtain them here. I for one would consider such
a leak a security issue, even if knowledge of the MFNs alone is
not enough to exploit anything, but maybe others think differently.
But the grant table aspect suggests anyway that perhaps the
permission to be checked here needs to depend on resource type.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-11 8:30 ` Jan Beulich
@ 2017-10-11 8:38 ` Paul Durrant
2017-10-11 8:48 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-11 8:38 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: 'Stefano Stabellini', Wei Liu,
'KonradRzeszutek Wilk', Andrew Cooper, Tim (Xen.org),
George Dunlap, Ian Jackson,
'xen-devel@lists.xenproject.org'
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 11 October 2017 09:31
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; George Dunlap
> <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; 'Stefano Stabellini' <sstabellini@kernel.org>; 'xen-
> devel@lists.xenproject.org' <xen-devel@lists.xenproject.org>;
> 'KonradRzeszutek Wilk' <konrad.wilk@oracle.com>; Tim (Xen.org)
> <tim@xen.org>
> Subject: RE: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> >>> On 10.10.17 at 16:37, <Paul.Durrant@citrix.com> wrote:
> >> From: Paul Durrant
> >> Sent: 10 October 2017 15:10
> >> > From: Jan Beulich [mailto:JBeulich@suse.com]
> >> > Sent: 09 October 2017 15:23
> >> > To: Paul Durrant <Paul.Durrant@citrix.com>
> >> > >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> >> > > --- a/xen/common/memory.c
> >> > > +++ b/xen/common/memory.c
> >> > > @@ -965,6 +965,67 @@ static long xatp_permission_check(struct
> domain
> >> > *d, unsigned int space)
> >> > > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> >> > > }
> >> > >
> >> > > +#ifdef CONFIG_X86
> >> > > +static int acquire_resource(const xen_mem_acquire_resource_t
> *xmar)
> >> > > +{
> >> > > + struct domain *d, *currd = current->domain;
> >> > > + unsigned long mfn_list[2];
> >> > > + int rc;
> >> > > +
> >> > > + if ( xmar->nr_frames == 0 || xmar->pad != 0 )
> >> > > + return -EINVAL;
> >> > > +
> >> > > + if ( xmar->nr_frames > ARRAY_SIZE(mfn_list) )
> >> > > + return -E2BIG;
> >> > > +
> >> > > + d = rcu_lock_domain_by_any_id(xmar->domid);
> >> > > + if ( d == NULL )
> >> > > + return -ESRCH;
> >> > > +
> >> > > + rc = xsm_domain_memory_map(XSM_TARGET, d);
> >> >
> >> > Looking at the description of patch 6 - why is this XSM_TARGET
> >> > rather than XSM_DM_PRIV?
> >>
> >> Good point. I was using the priv mapping code as a guide, but
> XSM_DM_PRIV
> >> is probably the right thing to use in this case.
> >>
> >
> > Actually that's not possible. There is an assertion in
> > xsm_domain_memory_map() that the action is XSM_TARGET.
>
> Well, I was afraid of this being the case, but this only complicates
> your job, it doesn't make XSM_TARGET the right choice here. But
> wait, maybe it can be considered sufficient, but then this needs
> to be prominently pointed out by a comment added at a suitable
> place: For the ioreq pages, them being owned by the emulating
> domain, page ownership validations while trying to make use of the
> MFNs would prevent mis-use by the domain the emulation is being
> done for. And for grant table pages the guest is able to access
> them another way anyway.
>
> Which basically leaves the question of this being an information
> leak for ioreq pages, as the guest is not supposed to know the
> MFNs, but could obtain them here. I for one would consider such
> a leak a security issue, even if knowledge of the MFNs alone is
> not enough to exploit anything, but maybe others think differently.
>
I agree with you. Now you point it out, it does rather defeat the purpose of having the separate resource map hypercall.
> But the grant table aspect suggests anyway that perhaps the
> permission to be checked here needs to depend on resource type.
Separate permissions could be an option, but maybe it would be better just to introduce a new resource mapping permission. I'll probably go with the latter.
Paul
>
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2017-10-11 8:38 ` Paul Durrant
@ 2017-10-11 8:48 ` Jan Beulich
0 siblings, 0 replies; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 8:48 UTC (permalink / raw)
To: Paul Durrant
Cc: 'Stefano Stabellini', Wei Liu,
'KonradRzeszutek Wilk', Andrew Cooper, Tim (Xen.org),
George Dunlap, Ian Jackson,
'xen-devel@lists.xenproject.org'
>>> On 11.10.17 at 10:38, <Paul.Durrant@citrix.com> wrote:
> Separate permissions could be an option, but maybe it would be better just
> to introduce a new resource mapping permission. I'll probably go with the
> latter.
Oh, I'm certainly fine with that, it just means more changes.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type...
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (4 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-09 15:20 ` Jan Beulich
2017-10-06 12:25 ` [PATCH v9 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update Paul Durrant
` (4 subsequent siblings)
10 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, Andrew Cooper,
Ian Jackson, Tim Deegan, Paul Durrant, Jan Beulich
... XENMEM_resource_ioreq_server
This patch adds support for a new resource type that can be mapped using
the XENMEM_acquire_resource memory op.
If an emulator makes use of this resource type then, instead of mapping
gfns, the IOREQ server will allocate pages from the heap. These pages
will never be present in the P2M of the guest at any point and so are
not vulnerable to any direct attack by the guest. They are only ever
accessible by Xen and any domain that has mapping privilege over the
guest (which may or may not be limited to the domain running the emulator).
NOTE: Use of the new resource type is not compatible with use of
XEN_DMOP_get_ioreq_server_info unless the XEN_DMOP_no_gfns flag is
set.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: George Dunlap <George.Dunlap@eu.citrix.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
v8:
- Re-base on new boilerplate.
- Adjust function signature of hvm_get_ioreq_server_frame(), and test
whether the bufioreq page is present.
v5:
- Use get_ioreq_server() function rather than indexing array directly.
- Add more explanation into comments to state than mapping guest frames
and allocation of pages for ioreq servers are not simultaneously
permitted.
- Add a comment into asm/ioreq.h stating the meaning of the index
value passed to hvm_get_ioreq_server_frame().
---
xen/arch/x86/hvm/ioreq.c | 140 ++++++++++++++++++++++++++++++++++++++++
xen/arch/x86/mm.c | 22 +++++++
xen/common/memory.c | 5 ++
xen/include/asm-x86/hvm/ioreq.h | 6 ++
xen/include/asm-x86/mm.h | 5 ++
xen/include/public/hvm/dm_op.h | 4 ++
xen/include/public/memory.h | 13 +++-
7 files changed, 194 insertions(+), 1 deletion(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index bb4fadcc3d..7a95911b6b 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -266,6 +266,19 @@ static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
int rc;
+ if ( iorp->page )
+ {
+ /*
+ * If a page has already been allocated (which will happen on
+ * demand if hvm_get_ioreq_server_frame() is called), then
+ * mapping a guest frame is not permitted.
+ */
+ if ( gfn_eq(iorp->gfn, INVALID_GFN) )
+ return -EPERM;
+
+ return 0;
+ }
+
if ( d->is_dying )
return -EINVAL;
@@ -288,6 +301,61 @@ static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
return rc;
}
+static int hvm_alloc_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
+{
+ struct domain *currd = current->domain;
+ struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
+
+ if ( iorp->page )
+ {
+ /*
+ * If a guest frame has already been mapped (which may happen
+ * on demand if hvm_get_ioreq_server_info() is called), then
+ * allocating a page is not permitted.
+ */
+ if ( !gfn_eq(iorp->gfn, INVALID_GFN) )
+ return -EPERM;
+
+ return 0;
+ }
+
+ /*
+ * Allocated IOREQ server pages are assigned to the emulating
+ * domain, not the target domain. This is because the emulator is
+ * likely to be destroyed after the target domain has been torn
+ * down, and we must use MEMF_no_refcount otherwise page allocation
+ * could fail if the emulating domain has already reached its
+ * maximum allocation.
+ */
+ iorp->page = alloc_domheap_page(currd, MEMF_no_refcount);
+ if ( !iorp->page )
+ return -ENOMEM;
+
+ iorp->va = __map_domain_page_global(iorp->page);
+ if ( !iorp->va )
+ {
+ iorp->page = NULL;
+ return -ENOMEM;
+ }
+
+ clear_page(iorp->va);
+ return 0;
+}
+
+static void hvm_free_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
+{
+ struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
+
+ if ( !iorp->page )
+ return;
+
+ unmap_domain_page_global(iorp->va);
+ iorp->va = NULL;
+
+ put_page(iorp->page);
+ iorp->page = NULL;
+}
+
bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
{
const struct hvm_ioreq_server *s;
@@ -491,6 +559,27 @@ static void hvm_ioreq_server_unmap_pages(struct hvm_ioreq_server *s)
hvm_unmap_ioreq_gfn(s, false);
}
+static int hvm_ioreq_server_alloc_pages(struct hvm_ioreq_server *s)
+{
+ int rc;
+
+ rc = hvm_alloc_ioreq_mfn(s, false);
+
+ if ( !rc && (s->bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF) )
+ rc = hvm_alloc_ioreq_mfn(s, true);
+
+ if ( rc )
+ hvm_free_ioreq_mfn(s, false);
+
+ return rc;
+}
+
+static void hvm_ioreq_server_free_pages(struct hvm_ioreq_server *s)
+{
+ hvm_free_ioreq_mfn(s, true);
+ hvm_free_ioreq_mfn(s, false);
+}
+
static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s)
{
unsigned int i;
@@ -619,7 +708,18 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server *s,
fail_add:
hvm_ioreq_server_remove_all_vcpus(s);
+
+ /*
+ * NOTE: It is safe to call both hvm_ioreq_server_unmap_pages() and
+ * hvm_ioreq_server_free_pages() in that order.
+ * This is because the former will do nothing if the pages
+ * are not mapped, leaving the page to be freed by the latter.
+ * However if the pages are mapped then the former will set
+ * the page_info pointer to NULL, meaning the latter will do
+ * nothing.
+ */
hvm_ioreq_server_unmap_pages(s);
+ hvm_ioreq_server_free_pages(s);
return rc;
}
@@ -629,6 +729,7 @@ static void hvm_ioreq_server_deinit(struct hvm_ioreq_server *s)
ASSERT(!s->enabled);
hvm_ioreq_server_remove_all_vcpus(s);
hvm_ioreq_server_unmap_pages(s);
+ hvm_ioreq_server_free_pages(s);
hvm_ioreq_server_free_rangesets(s);
}
@@ -784,6 +885,45 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
return rc;
}
+int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
+ unsigned int idx, mfn_t *mfn)
+{
+ struct hvm_ioreq_server *s;
+ int rc;
+
+ spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
+ s = get_ioreq_server(d, id);
+
+ ASSERT(!IS_DEFAULT(s));
+
+ rc = hvm_ioreq_server_alloc_pages(s);
+ if ( rc )
+ goto out;
+
+ if ( idx == 0 )
+ {
+ rc = -ENOENT;
+ if ( !HANDLE_BUFIOREQ(s) )
+ goto out;
+
+ *mfn = _mfn(page_to_mfn(s->bufioreq.page));
+ rc = 0;
+ }
+ else if ( idx == 1 )
+ *mfn = _mfn(page_to_mfn(s->ioreq.page));
+ else
+ rc = -EINVAL;
+
+ out:
+ spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+
+ return rc;
+}
+
int hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
uint32_t type, uint64_t start,
uint64_t end)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index d9df5ca69f..c9bc4a4e92 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -122,6 +122,7 @@
#include <asm/fixmap.h>
#include <asm/io_apic.h>
#include <asm/pci.h>
+#include <asm/hvm/ioreq.h>
#include <asm/hvm/grant_table.h>
#include <asm/pv/grant_table.h>
@@ -3866,6 +3867,27 @@ int xenmem_add_to_physmap_one(
return rc;
}
+int xenmem_acquire_ioreq_server(struct domain *d, unsigned int id,
+ unsigned long frame,
+ unsigned long nr_frames,
+ unsigned long mfn_list[])
+{
+ unsigned int i;
+
+ for ( i = 0; i < nr_frames; i++ )
+ {
+ mfn_t mfn;
+ int rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
+
+ if ( rc )
+ return rc;
+
+ mfn_list[i] = mfn_x(mfn);
+ }
+
+ return 0;
+}
+
long arch_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
{
int rc;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index 910c0c5063..80a3f42875 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -988,6 +988,11 @@ static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
switch ( xmar->type )
{
+ case XENMEM_resource_ioreq_server:
+ rc = xenmem_acquire_ioreq_server(d, xmar->id, xmar->frame,
+ xmar->nr_frames, mfn_list);
+ break;
+
default:
rc = -EOPNOTSUPP;
break;
diff --git a/xen/include/asm-x86/hvm/ioreq.h b/xen/include/asm-x86/hvm/ioreq.h
index 1829fcf43e..a4f58dc9ee 100644
--- a/xen/include/asm-x86/hvm/ioreq.h
+++ b/xen/include/asm-x86/hvm/ioreq.h
@@ -31,6 +31,12 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
unsigned long *ioreq_gfn,
unsigned long *bufioreq_gfn,
evtchn_port_t *bufioreq_port);
+/*
+ * Get the mfn of either the buffered or synchronous ioreq frame.
+ * (idx == 0 -> buffered, idx == 1 -> synchronous).
+ */
+int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
+ unsigned int idx, mfn_t *mfn);
int hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
uint32_t type, uint64_t start,
uint64_t end);
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index f2e0f498c4..637b1eee1c 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -615,4 +615,9 @@ static inline bool arch_mfn_in_directmap(unsigned long mfn)
return mfn <= (virt_to_mfn(eva - 1) + 1);
}
+int xenmem_acquire_ioreq_server(struct domain *d, unsigned int id,
+ unsigned long frame,
+ unsigned long nr_frames,
+ unsigned long mfn_list[]);
+
#endif /* __ASM_X86_MM_H__ */
diff --git a/xen/include/public/hvm/dm_op.h b/xen/include/public/hvm/dm_op.h
index 9677bd74e7..59b6006910 100644
--- a/xen/include/public/hvm/dm_op.h
+++ b/xen/include/public/hvm/dm_op.h
@@ -90,6 +90,10 @@ struct xen_dm_op_create_ioreq_server {
* the frame numbers passed back in gfns <ioreq_gfn> and <bufioreq_gfn>
* respectively. (If the IOREQ Server is not handling buffered emulation
* only <ioreq_gfn> will be valid).
+ *
+ * NOTE: To access the synchronous ioreq structures and buffered ioreq
+ * ring, it is preferable to use the XENMEM_acquire_resource memory
+ * op specifying resource type XENMEM_resource_ioreq_server.
*/
#define XEN_DMOP_get_ioreq_server_info 2
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index 3aa8fb2fe1..e30a4d9794 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -609,15 +609,26 @@ struct xen_mem_acquire_resource {
domid_t domid;
/* IN - the type of resource */
uint16_t type;
+
+#define XENMEM_resource_ioreq_server 0
+
/*
* IN - a type-specific resource identifier, which must be zero
* unless stated otherwise.
+ *
+ * type == XENMEM_resource_ioreq_server -> id == ioreq server id
*/
uint32_t id;
/* IN - number of (4K) frames of the resource to be mapped */
uint32_t nr_frames;
uint32_t pad;
- /* IN - the index of the initial frame to be mapped */
+ /* IN - the index of the initial frame to be mapped
+ *
+ * type == XENMEM_resource_ioreq_server -> frame == 0 -> bufioreq
+ * page
+ * frame == 1 -> ioreq
+ * page
+ */
uint64_aligned_t frame;
/* IN/OUT - If the tools domain is PV then, upon return, gmfn_list
* will be populated with the MFNs of the resource.
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* Re: [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type...
2017-10-06 12:25 ` [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type Paul Durrant
@ 2017-10-09 15:20 ` Jan Beulich
2017-10-10 14:45 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-09 15:20 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, Andrew Cooper,
Tim Deegan, xen-devel, Ian Jackson
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> @@ -288,6 +301,61 @@ static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
> return rc;
> }
>
> +static int hvm_alloc_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
> +{
> + struct domain *currd = current->domain;
> + struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
> +
> + if ( iorp->page )
> + {
> + /*
> + * If a guest frame has already been mapped (which may happen
> + * on demand if hvm_get_ioreq_server_info() is called), then
> + * allocating a page is not permitted.
> + */
> + if ( !gfn_eq(iorp->gfn, INVALID_GFN) )
> + return -EPERM;
> +
> + return 0;
> + }
> +
> + /*
> + * Allocated IOREQ server pages are assigned to the emulating
> + * domain, not the target domain. This is because the emulator is
> + * likely to be destroyed after the target domain has been torn
> + * down, and we must use MEMF_no_refcount otherwise page allocation
> + * could fail if the emulating domain has already reached its
> + * maximum allocation.
> + */
> + iorp->page = alloc_domheap_page(currd, MEMF_no_refcount);
Whichever domain you assign the page to, you need to prevent
it becoming usable as e.g. a page table or descriptor table page.
IOW I think your missing a get_page_type(..., PGT_writable)
here, with the put_page() on the free path below then needing
to become put_page_and_type().
> @@ -784,6 +885,45 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
> return rc;
> }
>
> +int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
> + unsigned int idx, mfn_t *mfn)
> +{
> + struct hvm_ioreq_server *s;
> + int rc;
> +
> + spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
> +
> + if ( id == DEFAULT_IOSERVID )
> + return -EOPNOTSUPP;
> +
> + s = get_ioreq_server(d, id);
> +
> + ASSERT(!IS_DEFAULT(s));
> +
> + rc = hvm_ioreq_server_alloc_pages(s);
> + if ( rc )
> + goto out;
> +
> + if ( idx == 0 )
switch() ?
> @@ -3866,6 +3867,27 @@ int xenmem_add_to_physmap_one(
> return rc;
> }
>
> +int xenmem_acquire_ioreq_server(struct domain *d, unsigned int id,
> + unsigned long frame,
> + unsigned long nr_frames,
> + unsigned long mfn_list[])
> +{
> + unsigned int i;
> +
> + for ( i = 0; i < nr_frames; i++ )
> + {
> + mfn_t mfn;
> + int rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
Coming back to the question of the size of the "frame" interface
structure field, note how you silently truncate the upper 32 bits
here.
> --- a/xen/include/public/memory.h
> +++ b/xen/include/public/memory.h
> @@ -609,15 +609,26 @@ struct xen_mem_acquire_resource {
> domid_t domid;
> /* IN - the type of resource */
> uint16_t type;
> +
> +#define XENMEM_resource_ioreq_server 0
> +
> /*
> * IN - a type-specific resource identifier, which must be zero
> * unless stated otherwise.
> + *
> + * type == XENMEM_resource_ioreq_server -> id == ioreq server id
> */
> uint32_t id;
> /* IN - number of (4K) frames of the resource to be mapped */
> uint32_t nr_frames;
> uint32_t pad;
> - /* IN - the index of the initial frame to be mapped */
> + /* IN - the index of the initial frame to be mapped
> + *
> + * type == XENMEM_resource_ioreq_server -> frame == 0 -> bufioreq
> + * page
> + * frame == 1 -> ioreq
> + * page
> + */
Long comment or not I think you want to introduce constants
for these two numbers.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type...
2017-10-09 15:20 ` Jan Beulich
@ 2017-10-10 14:45 ` Paul Durrant
2017-10-11 8:35 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-10 14:45 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), Ian Jackson, xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 09 October 2017 16:21
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; Ian Jackson
> <Ian.Jackson@citrix.com>; Stefano Stabellini <sstabellini@kernel.org>; xen-
> devel@lists.xenproject.org; Konrad Rzeszutek Wilk
> <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: Re: [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource
> type...
>
> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > @@ -288,6 +301,61 @@ static int hvm_map_ioreq_gfn(struct
> hvm_ioreq_server *s, bool buf)
> > return rc;
> > }
> >
> > +static int hvm_alloc_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
> > +{
> > + struct domain *currd = current->domain;
> > + struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
> > +
> > + if ( iorp->page )
> > + {
> > + /*
> > + * If a guest frame has already been mapped (which may happen
> > + * on demand if hvm_get_ioreq_server_info() is called), then
> > + * allocating a page is not permitted.
> > + */
> > + if ( !gfn_eq(iorp->gfn, INVALID_GFN) )
> > + return -EPERM;
> > +
> > + return 0;
> > + }
> > +
> > + /*
> > + * Allocated IOREQ server pages are assigned to the emulating
> > + * domain, not the target domain. This is because the emulator is
> > + * likely to be destroyed after the target domain has been torn
> > + * down, and we must use MEMF_no_refcount otherwise page
> allocation
> > + * could fail if the emulating domain has already reached its
> > + * maximum allocation.
> > + */
> > + iorp->page = alloc_domheap_page(currd, MEMF_no_refcount);
>
> Whichever domain you assign the page to, you need to prevent
> it becoming usable as e.g. a page table or descriptor table page.
> IOW I think your missing a get_page_type(..., PGT_writable)
> here, with the put_page() on the free path below then needing
> to become put_page_and_type().
Ok.
>
> > @@ -784,6 +885,45 @@ int hvm_get_ioreq_server_info(struct domain *d,
> ioservid_t id,
> > return rc;
> > }
> >
> > +int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
> > + unsigned int idx, mfn_t *mfn)
> > +{
> > + struct hvm_ioreq_server *s;
> > + int rc;
> > +
> > + spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
> > +
> > + if ( id == DEFAULT_IOSERVID )
> > + return -EOPNOTSUPP;
> > +
> > + s = get_ioreq_server(d, id);
> > +
> > + ASSERT(!IS_DEFAULT(s));
> > +
> > + rc = hvm_ioreq_server_alloc_pages(s);
> > + if ( rc )
> > + goto out;
> > +
> > + if ( idx == 0 )
>
> switch() ?
Yes, but if idx can exceed 1 in future (which would need to be the case to support greater numbers of vcpus) then I guess it may change back.
>
> > @@ -3866,6 +3867,27 @@ int xenmem_add_to_physmap_one(
> > return rc;
> > }
> >
> > +int xenmem_acquire_ioreq_server(struct domain *d, unsigned int id,
> > + unsigned long frame,
> > + unsigned long nr_frames,
> > + unsigned long mfn_list[])
> > +{
> > + unsigned int i;
> > +
> > + for ( i = 0; i < nr_frames; i++ )
> > + {
> > + mfn_t mfn;
> > + int rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
>
> Coming back to the question of the size of the "frame" interface
> structure field, note how you silently truncate the upper 32 bits
> here.
OK. For this resource type I can't see 64-bits being needed, but I'll carry them through.
>
> > --- a/xen/include/public/memory.h
> > +++ b/xen/include/public/memory.h
> > @@ -609,15 +609,26 @@ struct xen_mem_acquire_resource {
> > domid_t domid;
> > /* IN - the type of resource */
> > uint16_t type;
> > +
> > +#define XENMEM_resource_ioreq_server 0
> > +
> > /*
> > * IN - a type-specific resource identifier, which must be zero
> > * unless stated otherwise.
> > + *
> > + * type == XENMEM_resource_ioreq_server -> id == ioreq server id
> > */
> > uint32_t id;
> > /* IN - number of (4K) frames of the resource to be mapped */
> > uint32_t nr_frames;
> > uint32_t pad;
> > - /* IN - the index of the initial frame to be mapped */
> > + /* IN - the index of the initial frame to be mapped
> > + *
> > + * type == XENMEM_resource_ioreq_server -> frame == 0 -> bufioreq
> > + * page
> > + * frame == 1 -> ioreq
> > + * page
> > + */
>
> Long comment or not I think you want to introduce constants
> for these two numbers.
>
Yes, that would probably be better although increasing the number of supported vcpus may mean that >1 becomes valid in future.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type...
2017-10-10 14:45 ` Paul Durrant
@ 2017-10-11 8:35 ` Jan Beulich
0 siblings, 0 replies; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 8:35 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), Ian Jackson, xen-devel@lists.xenproject.org
>>> On 10.10.17 at 16:45, <Paul.Durrant@citrix.com> wrote:
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 09 October 2017 16:21
>> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
>> > @@ -784,6 +885,45 @@ int hvm_get_ioreq_server_info(struct domain *d,
>> ioservid_t id,
>> > return rc;
>> > }
>> >
>> > +int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
>> > + unsigned int idx, mfn_t *mfn)
>> > +{
>> > + struct hvm_ioreq_server *s;
>> > + int rc;
>> > +
>> > + spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
>> > +
>> > + if ( id == DEFAULT_IOSERVID )
>> > + return -EOPNOTSUPP;
>> > +
>> > + s = get_ioreq_server(d, id);
>> > +
>> > + ASSERT(!IS_DEFAULT(s));
>> > +
>> > + rc = hvm_ioreq_server_alloc_pages(s);
>> > + if ( rc )
>> > + goto out;
>> > +
>> > + if ( idx == 0 )
>>
>> switch() ?
>
> Yes, but if idx can exceed 1 in future (which would need to be the case to
> support greater numbers of vcpus) then I guess it may change back.
If you anticipate that to not be expressable by case labels (not even
by range ones), then perhaps indeed better stick to if/else.
>> > @@ -3866,6 +3867,27 @@ int xenmem_add_to_physmap_one(
>> > return rc;
>> > }
>> >
>> > +int xenmem_acquire_ioreq_server(struct domain *d, unsigned int id,
>> > + unsigned long frame,
>> > + unsigned long nr_frames,
>> > + unsigned long mfn_list[])
>> > +{
>> > + unsigned int i;
>> > +
>> > + for ( i = 0; i < nr_frames; i++ )
>> > + {
>> > + mfn_t mfn;
>> > + int rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
>>
>> Coming back to the question of the size of the "frame" interface
>> structure field, note how you silently truncate the upper 32 bits
>> here.
>
> OK. For this resource type I can't see 64-bits being needed, but I'll carry
> them through.
Carrying the full value through is one option. The other is to bail
early when finding the upper bits set.
>> > --- a/xen/include/public/memory.h
>> > +++ b/xen/include/public/memory.h
>> > @@ -609,15 +609,26 @@ struct xen_mem_acquire_resource {
>> > domid_t domid;
>> > /* IN - the type of resource */
>> > uint16_t type;
>> > +
>> > +#define XENMEM_resource_ioreq_server 0
>> > +
>> > /*
>> > * IN - a type-specific resource identifier, which must be zero
>> > * unless stated otherwise.
>> > + *
>> > + * type == XENMEM_resource_ioreq_server -> id == ioreq server id
>> > */
>> > uint32_t id;
>> > /* IN - number of (4K) frames of the resource to be mapped */
>> > uint32_t nr_frames;
>> > uint32_t pad;
>> > - /* IN - the index of the initial frame to be mapped */
>> > + /* IN - the index of the initial frame to be mapped
>> > + *
>> > + * type == XENMEM_resource_ioreq_server -> frame == 0 -> bufioreq
>> > + * page
>> > + * frame == 1 -> ioreq
>> > + * page
>> > + */
>>
>> Long comment or not I think you want to introduce constants
>> for these two numbers.
>>
>
> Yes, that would probably be better although increasing the number of
> supported vcpus may mean that >1 becomes valid in future.
Sure, but that would then still better be expressed by a suitable
macro (perhaps one long the lines of MSR_P6_PERFCTR()).
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* [PATCH v9 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update...
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (5 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 06/11] x86/hvm/ioreq: add a new mappable resource type Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-09 15:44 ` Jan Beulich
2017-10-06 12:25 ` [PATCH v9 08/11] tools/libxenforeignmemory: add support for resource mapping Paul Durrant
` (3 subsequent siblings)
10 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, Paul Durrant, Jan Beulich
...to allow the calling domain to prevent translation of specified l1e
value.
Despite what the comment in public/xen.h might imply, specifying a
command value of MMU_NORMAL_PT_UPDATE will not simply update an l1e with
the specified value. Instead, mod_l1_entry() tests whether foreign_dom
has PG_translate set in its paging mode and, if it does, assumes that the
the pfn value in the l1e is a gfn rather than an mfn.
To allow PV tools domain to map mfn values from a previously issued
HYPERVISOR_memory_op:XENMEM_acquire_resource, there needs to be a way
to tell HYPERVISOR_mmu_update that the specific l1e value does not
require translation regardless of the paging mode of foreign_dom. This
patch therefore defines a new command value, MMU_PT_UPDATE_NO_TRANSLATE,
which has the same semantics as MMU_NORMAL_PT_UPDATE except that the
paging mode of foreign_dom is ignored and the l1e value is used verbatim.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
v8:
- New in this version, replacing "allow a privileged PV domain to map
guest mfns".
---
xen/arch/x86/mm.c | 17 ++++++++++-------
xen/include/public/xen.h | 12 +++++++++---
2 files changed, 19 insertions(+), 10 deletions(-)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index c9bc4a4e92..d63ab049f9 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -1619,9 +1619,10 @@ void page_unlock(struct page_info *page)
/* Update the L1 entry at pl1e to new value nl1e. */
static int mod_l1_entry(l1_pgentry_t *pl1e, l1_pgentry_t nl1e,
- unsigned long gl1mfn, int preserve_ad,
+ unsigned long gl1mfn, int cmd,
struct vcpu *pt_vcpu, struct domain *pg_dom)
{
+ bool preserve_ad = (cmd == MMU_PT_UPDATE_PRESERVE_AD);
l1_pgentry_t ol1e;
struct domain *pt_dom = pt_vcpu->domain;
int rc = 0;
@@ -1643,7 +1644,8 @@ static int mod_l1_entry(l1_pgentry_t *pl1e, l1_pgentry_t nl1e,
return -EINVAL;
}
- if ( paging_mode_translate(pg_dom) )
+ if ( cmd != MMU_PT_UPDATE_NO_TRANSLATE &&
+ paging_mode_translate(pg_dom) )
{
page = get_page_from_gfn(pg_dom, l1e_get_pfn(nl1e), NULL, P2M_ALLOC);
if ( !page )
@@ -3258,6 +3260,7 @@ long do_mmu_update(
*/
case MMU_NORMAL_PT_UPDATE:
case MMU_PT_UPDATE_PRESERVE_AD:
+ case MMU_PT_UPDATE_NO_TRANSLATE:
{
p2m_type_t p2mt;
@@ -3323,7 +3326,8 @@ long do_mmu_update(
p2m_query_t q = (l1e_get_flags(l1e) & _PAGE_RW) ?
P2M_UNSHARE : P2M_ALLOC;
- if ( paging_mode_translate(pg_owner) )
+ if ( cmd != MMU_PT_UPDATE_NO_TRANSLATE &&
+ paging_mode_translate(pg_owner) )
target = get_page_from_gfn(pg_owner, l1e_get_pfn(l1e),
&l1e_p2mt, q);
@@ -3350,9 +3354,7 @@ long do_mmu_update(
break;
}
- rc = mod_l1_entry(va, l1e, mfn,
- cmd == MMU_PT_UPDATE_PRESERVE_AD, v,
- pg_owner);
+ rc = mod_l1_entry(va, l1e, mfn, cmd, v, pg_owner);
if ( target )
put_page(target);
}
@@ -3630,7 +3632,8 @@ static int __do_update_va_mapping(
goto out;
}
- rc = mod_l1_entry(pl1e, val, mfn_x(gl1mfn), 0, v, pg_owner);
+ rc = mod_l1_entry(pl1e, val, mfn_x(gl1mfn), MMU_NORMAL_PT_UPDATE, v,
+ pg_owner);
page_unlock(gl1pg);
put_page(gl1pg);
diff --git a/xen/include/public/xen.h b/xen/include/public/xen.h
index 2ac6b1e24d..d2014a39eb 100644
--- a/xen/include/public/xen.h
+++ b/xen/include/public/xen.h
@@ -268,6 +268,10 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t);
* As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
* with those in @val.
*
+ * ptr[1:0] == MMU_PT_UPDATE_NO_TRANSLATE:
+ * As MMU_NORMAL_PT_UPDATE above, but @val is not translated though FD
+ * page tables.
+ *
* @val is usually the machine frame number along with some attributes.
* The attributes by default follow the architecture defined bits. Meaning that
* if this is a X86_64 machine and four page table layout is used, the layout
@@ -334,9 +338,11 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t);
*
* PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
*/
-#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */
-#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */
-#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
+#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */
+#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */
+#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
+#define MMU_PT_UPDATE_NO_TRANSLATE 3 /* checked '*ptr = val'. prt is MA. */
+ /* val never translated. */
/*
* MMU EXTENDED OPERATIONS
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* Re: [PATCH v9 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update...
2017-10-06 12:25 ` [PATCH v9 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update Paul Durrant
@ 2017-10-09 15:44 ` Jan Beulich
0 siblings, 0 replies; 36+ messages in thread
From: Jan Beulich @ 2017-10-09 15:44 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, xen-devel
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> --- a/xen/arch/x86/mm.c
> +++ b/xen/arch/x86/mm.c
> @@ -1619,9 +1619,10 @@ void page_unlock(struct page_info *page)
>
> /* Update the L1 entry at pl1e to new value nl1e. */
> static int mod_l1_entry(l1_pgentry_t *pl1e, l1_pgentry_t nl1e,
> - unsigned long gl1mfn, int preserve_ad,
> + unsigned long gl1mfn, int cmd,
unsigned int
With that
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* [PATCH v9 08/11] tools/libxenforeignmemory: add support for resource mapping
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (6 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-06 12:25 ` [PATCH v9 09/11] tools/libxenforeignmemory: reduce xenforeignmemory_restrict code footprint Paul Durrant
` (2 subsequent siblings)
10 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel; +Cc: Paul Durrant, Ian Jackson
A previous patch introduced a new HYPERVISOR_memory_op to acquire guest
resources for direct priv-mapping.
This patch adds new functionality into libxenforeignmemory to make use
of a new privcmd ioctl [1] that uses the new memory op to make such
resources available via mmap(2).
[1] http://xenbits.xen.org/gitweb/?p=people/pauldu/linux.git;a=commit;h=ce59a05e6712
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
---
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
v4:
- Fixed errno and removed single-use label
- The unmap call now returns a status
- Use C99 initialization for ioctl struct
v2:
- Bump minor version up to 3.
---
tools/include/xen-sys/Linux/privcmd.h | 11 +++++
tools/libs/foreignmemory/Makefile | 2 +-
tools/libs/foreignmemory/core.c | 53 ++++++++++++++++++++++
.../libs/foreignmemory/include/xenforeignmemory.h | 41 +++++++++++++++++
tools/libs/foreignmemory/libxenforeignmemory.map | 5 ++
tools/libs/foreignmemory/linux.c | 45 ++++++++++++++++++
tools/libs/foreignmemory/private.h | 31 +++++++++++++
7 files changed, 187 insertions(+), 1 deletion(-)
diff --git a/tools/include/xen-sys/Linux/privcmd.h b/tools/include/xen-sys/Linux/privcmd.h
index 732ff7c15a..9531b728f9 100644
--- a/tools/include/xen-sys/Linux/privcmd.h
+++ b/tools/include/xen-sys/Linux/privcmd.h
@@ -86,6 +86,15 @@ typedef struct privcmd_dm_op {
const privcmd_dm_op_buf_t __user *ubufs;
} privcmd_dm_op_t;
+typedef struct privcmd_mmap_resource {
+ domid_t dom;
+ __u32 type;
+ __u32 id;
+ __u32 idx;
+ __u64 num;
+ __u64 addr;
+} privcmd_mmap_resource_t;
+
/*
* @cmd: IOCTL_PRIVCMD_HYPERCALL
* @arg: &privcmd_hypercall_t
@@ -103,5 +112,7 @@ typedef struct privcmd_dm_op {
_IOC(_IOC_NONE, 'P', 5, sizeof(privcmd_dm_op_t))
#define IOCTL_PRIVCMD_RESTRICT \
_IOC(_IOC_NONE, 'P', 6, sizeof(domid_t))
+#define IOCTL_PRIVCMD_MMAP_RESOURCE \
+ _IOC(_IOC_NONE, 'P', 7, sizeof(privcmd_mmap_resource_t))
#endif /* __LINUX_PUBLIC_PRIVCMD_H__ */
diff --git a/tools/libs/foreignmemory/Makefile b/tools/libs/foreignmemory/Makefile
index ab7f873f26..5c7f78f61d 100644
--- a/tools/libs/foreignmemory/Makefile
+++ b/tools/libs/foreignmemory/Makefile
@@ -2,7 +2,7 @@ XEN_ROOT = $(CURDIR)/../../..
include $(XEN_ROOT)/tools/Rules.mk
MAJOR = 1
-MINOR = 2
+MINOR = 3
SHLIB_LDFLAGS += -Wl,--version-script=libxenforeignmemory.map
CFLAGS += -Werror -Wmissing-prototypes
diff --git a/tools/libs/foreignmemory/core.c b/tools/libs/foreignmemory/core.c
index a6897dc561..8d3f9f178f 100644
--- a/tools/libs/foreignmemory/core.c
+++ b/tools/libs/foreignmemory/core.c
@@ -17,6 +17,8 @@
#include <assert.h>
#include <errno.h>
+#include <sys/mman.h>
+
#include "private.h"
xenforeignmemory_handle *xenforeignmemory_open(xentoollog_logger *logger,
@@ -120,6 +122,57 @@ int xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
return osdep_xenforeignmemory_restrict(fmem, domid);
}
+xenforeignmemory_resource_handle *xenforeignmemory_map_resource(
+ xenforeignmemory_handle *fmem, domid_t domid, unsigned int type,
+ unsigned int id, unsigned long frame, unsigned long nr_frames,
+ void **paddr, int prot, int flags)
+{
+ xenforeignmemory_resource_handle *fres;
+ int rc;
+
+ /* Check flags only contains POSIX defined values */
+ if ( flags & ~(MAP_SHARED | MAP_PRIVATE) )
+ {
+ errno = EINVAL;
+ return NULL;
+ }
+
+ fres = calloc(1, sizeof(*fres));
+ if ( !fres )
+ {
+ errno = ENOMEM;
+ return NULL;
+ }
+
+ fres->domid = domid;
+ fres->type = type;
+ fres->id = id;
+ fres->frame = frame;
+ fres->nr_frames = nr_frames;
+ fres->addr = *paddr;
+ fres->prot = prot;
+ fres->flags = flags;
+
+ rc = osdep_xenforeignmemory_map_resource(fmem, fres);
+ if ( rc )
+ {
+ free(fres);
+ fres = NULL;
+ } else
+ *paddr = fres->addr;
+
+ return fres;
+}
+
+int xenforeignmemory_unmap_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres)
+{
+ int rc = osdep_xenforeignmemory_unmap_resource(fmem, fres);
+
+ free(fres);
+ return rc;
+}
+
/*
* Local variables:
* mode: C
diff --git a/tools/libs/foreignmemory/include/xenforeignmemory.h b/tools/libs/foreignmemory/include/xenforeignmemory.h
index f4814c390f..d594be8df0 100644
--- a/tools/libs/foreignmemory/include/xenforeignmemory.h
+++ b/tools/libs/foreignmemory/include/xenforeignmemory.h
@@ -138,6 +138,47 @@ int xenforeignmemory_unmap(xenforeignmemory_handle *fmem,
int xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
domid_t domid);
+typedef struct xenforeignmemory_resource_handle xenforeignmemory_resource_handle;
+
+/**
+ * This function maps a guest resource.
+ *
+ * @parm fmem handle to the open foreignmemory interface
+ * @parm domid the domain id
+ * @parm type the resource type
+ * @parm id the type-specific resource identifier
+ * @parm frame base frame index within the resource
+ * @parm nr_frames number of frames to map
+ * @parm paddr pointer to an address passed through to mmap(2)
+ * @parm prot passed through to mmap(2)
+ * @parm POSIX-only flags passed through to mmap(2)
+ * @return pointer to foreignmemory resource handle on success, NULL on
+ * failure
+ *
+ * *paddr is used, on entry, as a hint address for foreign map placement
+ * (see mmap(2)) so should be set to NULL if no specific placement is
+ * required. On return *paddr contains the address where the resource is
+ * mapped.
+ * As for xenforeignmemory_map2() flags is a set of additional flags
+ * for mmap(2). Not all of the flag combinations are possible due to
+ * implementation details on different platforms.
+ */
+xenforeignmemory_resource_handle *xenforeignmemory_map_resource(
+ xenforeignmemory_handle *fmem, domid_t domid, unsigned int type,
+ unsigned int id, unsigned long frame, unsigned long nr_frames,
+ void **paddr, int prot, int flags);
+
+/**
+ * This function releases a previously acquired resource.
+ *
+ * @parm fmem handle to the open foreignmemory interface
+ * @parm fres handle to the acquired resource
+ *
+ * Returns 0 on success on failure sets errno and returns -1.
+ */
+int xenforeignmemory_unmap_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres);
+
#endif
/*
diff --git a/tools/libs/foreignmemory/libxenforeignmemory.map b/tools/libs/foreignmemory/libxenforeignmemory.map
index 716ecaf15c..d5323c87d9 100644
--- a/tools/libs/foreignmemory/libxenforeignmemory.map
+++ b/tools/libs/foreignmemory/libxenforeignmemory.map
@@ -14,3 +14,8 @@ VERS_1.2 {
global:
xenforeignmemory_map2;
} VERS_1.1;
+VERS_1.3 {
+ global:
+ xenforeignmemory_map_resource;
+ xenforeignmemory_unmap_resource;
+} VERS_1.2;
diff --git a/tools/libs/foreignmemory/linux.c b/tools/libs/foreignmemory/linux.c
index 374e45aed5..a6b41b0b7f 100644
--- a/tools/libs/foreignmemory/linux.c
+++ b/tools/libs/foreignmemory/linux.c
@@ -277,6 +277,51 @@ int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
return ioctl(fmem->fd, IOCTL_PRIVCMD_RESTRICT, &domid);
}
+int osdep_xenforeignmemory_unmap_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres)
+{
+ return munmap(fres->addr, fres->nr_frames << PAGE_SHIFT);
+}
+
+int osdep_xenforeignmemory_map_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres)
+{
+ privcmd_mmap_resource_t mr = {
+ .dom = fres->domid,
+ .type = fres->type,
+ .id = fres->id,
+ .idx = fres->frame,
+ .num = fres->nr_frames,
+ };
+ int rc;
+
+ fres->addr = mmap(fres->addr, fres->nr_frames << PAGE_SHIFT,
+ fres->prot, fres->flags | MAP_SHARED, fmem->fd, 0);
+ if ( fres->addr == MAP_FAILED )
+ return -1;
+
+ mr.addr = (uintptr_t)fres->addr;
+
+ rc = ioctl(fmem->fd, IOCTL_PRIVCMD_MMAP_RESOURCE, &mr);
+ if ( rc )
+ {
+ int saved_errno;
+
+ if ( errno != ENOTTY )
+ PERROR("ioctl failed");
+ else
+ errno = EOPNOTSUPP;
+
+ saved_errno = errno;
+ (void)osdep_xenforeignmemory_unmap_resource(fmem, fres);
+ errno = saved_errno;
+
+ return -1;
+ }
+
+ return 0;
+}
+
/*
* Local variables:
* mode: C
diff --git a/tools/libs/foreignmemory/private.h b/tools/libs/foreignmemory/private.h
index c5c07cc4c4..80b22bdbfc 100644
--- a/tools/libs/foreignmemory/private.h
+++ b/tools/libs/foreignmemory/private.h
@@ -42,6 +42,37 @@ void *compat_mapforeign_batch(xenforeignmem_handle *fmem, uint32_t dom,
xen_pfn_t *arr, int num);
#endif
+struct xenforeignmemory_resource_handle {
+ domid_t domid;
+ unsigned int type;
+ unsigned int id;
+ unsigned long frame;
+ unsigned long nr_frames;
+ void *addr;
+ int prot;
+ int flags;
+};
+
+#ifndef __linux__
+static inline int osdep_xenforeignmemory_map_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres)
+{
+ errno = EOPNOTSUPP;
+ return -1;
+}
+
+static inline int osdep_xenforeignmemory_unmap_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres)
+{
+ return 0;
+}
+#else
+int osdep_xenforeignmemory_map_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres);
+int osdep_xenforeignmemory_unmap_resource(
+ xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres);
+#endif
+
#define PERROR(_f...) \
xtl_log(fmem->logger, XTL_ERROR, errno, "xenforeignmemory", _f)
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* [PATCH v9 09/11] tools/libxenforeignmemory: reduce xenforeignmemory_restrict code footprint
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (7 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 08/11] tools/libxenforeignmemory: add support for resource mapping Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-06 12:25 ` [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table Paul Durrant
2017-10-06 12:25 ` [PATCH v9 11/11] tools/libxenctrl: use new xenforeignmemory API to seed grant table Paul Durrant
10 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel; +Cc: Paul Durrant, Ian Jackson
By using a static inline stub in private.h for OS where this functionality
is not implemented, the various duplicate stubs in the OS-specific source
modules can be avoided.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
---
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
v4:
- Removed extraneous freebsd code.
v3:
- Patch added in response to review comments.
---
tools/libs/foreignmemory/freebsd.c | 7 -------
tools/libs/foreignmemory/minios.c | 7 -------
tools/libs/foreignmemory/netbsd.c | 7 -------
tools/libs/foreignmemory/private.h | 12 +++++++++---
tools/libs/foreignmemory/solaris.c | 7 -------
5 files changed, 9 insertions(+), 31 deletions(-)
diff --git a/tools/libs/foreignmemory/freebsd.c b/tools/libs/foreignmemory/freebsd.c
index dec447485a..6e6bc4b11f 100644
--- a/tools/libs/foreignmemory/freebsd.c
+++ b/tools/libs/foreignmemory/freebsd.c
@@ -95,13 +95,6 @@ int osdep_xenforeignmemory_unmap(xenforeignmemory_handle *fmem,
return munmap(addr, num << PAGE_SHIFT);
}
-int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
- domid_t domid)
-{
- errno = -EOPNOTSUPP;
- return -1;
-}
-
/*
* Local variables:
* mode: C
diff --git a/tools/libs/foreignmemory/minios.c b/tools/libs/foreignmemory/minios.c
index 75f340122e..43341ca301 100644
--- a/tools/libs/foreignmemory/minios.c
+++ b/tools/libs/foreignmemory/minios.c
@@ -58,13 +58,6 @@ int osdep_xenforeignmemory_unmap(xenforeignmemory_handle *fmem,
return munmap(addr, num << PAGE_SHIFT);
}
-int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
- domid_t domid)
-{
- errno = -EOPNOTSUPP;
- return -1;
-}
-
/*
* Local variables:
* mode: C
diff --git a/tools/libs/foreignmemory/netbsd.c b/tools/libs/foreignmemory/netbsd.c
index 9bf95ef4f0..54a418ebd6 100644
--- a/tools/libs/foreignmemory/netbsd.c
+++ b/tools/libs/foreignmemory/netbsd.c
@@ -100,13 +100,6 @@ int osdep_xenforeignmemory_unmap(xenforeignmemory_handle *fmem,
return munmap(addr, num*XC_PAGE_SIZE);
}
-int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
- domid_t domid)
-{
- errno = -EOPNOTSUPP;
- return -1;
-}
-
/*
* Local variables:
* mode: C
diff --git a/tools/libs/foreignmemory/private.h b/tools/libs/foreignmemory/private.h
index 80b22bdbfc..b5d5f0a354 100644
--- a/tools/libs/foreignmemory/private.h
+++ b/tools/libs/foreignmemory/private.h
@@ -32,9 +32,6 @@ void *osdep_xenforeignmemory_map(xenforeignmemory_handle *fmem,
int osdep_xenforeignmemory_unmap(xenforeignmemory_handle *fmem,
void *addr, size_t num);
-int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
- domid_t domid);
-
#if defined(__NetBSD__) || defined(__sun__)
/* Strictly compat for those two only only */
void *compat_mapforeign_batch(xenforeignmem_handle *fmem, uint32_t dom,
@@ -54,6 +51,13 @@ struct xenforeignmemory_resource_handle {
};
#ifndef __linux__
+static inline int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
+ domid_t domid)
+{
+ errno = EOPNOTSUPP;
+ return -1;
+}
+
static inline int osdep_xenforeignmemory_map_resource(
xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres)
{
@@ -67,6 +71,8 @@ static inline int osdep_xenforeignmemory_unmap_resource(
return 0;
}
#else
+int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
+ domid_t domid);
int osdep_xenforeignmemory_map_resource(
xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres);
int osdep_xenforeignmemory_unmap_resource(
diff --git a/tools/libs/foreignmemory/solaris.c b/tools/libs/foreignmemory/solaris.c
index a33decb4ae..ee8aae4fbd 100644
--- a/tools/libs/foreignmemory/solaris.c
+++ b/tools/libs/foreignmemory/solaris.c
@@ -97,13 +97,6 @@ int osdep_xenforeignmemory_unmap(xenforeignmemory_handle *fmem,
return munmap(addr, num*XC_PAGE_SIZE);
}
-int osdep_xenforeignmemory_restrict(xenforeignmemory_handle *fmem,
- domid_t domid)
-{
- errno = -EOPNOTSUPP;
- return -1;
-}
-
/*
* Local variables:
* mode: C
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (8 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 09/11] tools/libxenforeignmemory: reduce xenforeignmemory_restrict code footprint Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
2017-10-10 10:25 ` Jan Beulich
2017-10-06 12:25 ` [PATCH v9 11/11] tools/libxenctrl: use new xenforeignmemory API to seed grant table Paul Durrant
10 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, Konrad Rzeszutek Wilk, George Dunlap,
Andrew Cooper, Ian Jackson, Tim Deegan, Paul Durrant, Jan Beulich
This patch allows grant table frames to be mapped using the
XENMEM_acquire_resource memory op.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>
v8:
- The functionality was originally incorporated into the earlier patch
"x86/mm: add HYPERVISOR_memory_op to acquire guest resources".
---
xen/common/grant_table.c | 32 ++++++++++++++++++++++++++++----
xen/common/memory.c | 30 ++++++++++++++++++++++++++++++
xen/include/public/memory.h | 5 +++++
xen/include/xen/grant_table.h | 1 +
4 files changed, 64 insertions(+), 4 deletions(-)
diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c
index 6d20b17739..12623c9984 100644
--- a/xen/common/grant_table.c
+++ b/xen/common/grant_table.c
@@ -3756,14 +3756,13 @@ int mem_sharing_gref_to_gfn(struct grant_table *gt, grant_ref_t ref,
}
#endif
-int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
- mfn_t *mfn)
+/* Caller must hold write lock as version may change and table may grow */
+static int gnttab_get_frame_locked(struct domain *d, unsigned long idx,
+ mfn_t *mfn)
{
int rc = 0;
struct grant_table *gt = d->grant_table;
- grant_write_lock(gt);
-
if ( gt->gt_version == 0 )
gt->gt_version = 1;
@@ -3787,6 +3786,19 @@ int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
rc = -EINVAL;
}
+ return rc;
+}
+
+int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
+ mfn_t *mfn)
+{
+ struct grant_table *gt = d->grant_table;
+ int rc;
+
+ grant_write_lock(gt);
+
+ rc = gnttab_get_frame_locked(d, idx, mfn);
+
if ( !rc )
gnttab_set_frame_gfn(gt, idx, gfn);
@@ -3795,6 +3807,18 @@ int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
return rc;
}
+int gnttab_get_frame(struct domain *d, unsigned long idx, mfn_t *mfn)
+{
+ struct grant_table *gt = d->grant_table;
+ int rc;
+
+ grant_write_lock(gt); /* write lock is required as table may grow */
+ rc = gnttab_get_frame_locked(d, idx, mfn);
+ grant_write_unlock(gt);
+
+ return rc;
+}
+
static void gnttab_usage_print(struct domain *rd)
{
int first = 1;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index 80a3f42875..c4e175da83 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -23,6 +23,7 @@
#include <xen/numa.h>
#include <xen/mem_access.h>
#include <xen/trace.h>
+#include <xen/grant_table.h>
#include <asm/current.h>
#include <asm/hardirq.h>
#include <asm/p2m.h>
@@ -966,6 +967,30 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
}
#ifdef CONFIG_X86
+static int acquire_grant_table(struct domain *d, unsigned int id,
+ unsigned long frame,
+ unsigned long nr_frames,
+ unsigned long mfn_list[])
+{
+ unsigned int i = nr_frames;
+
+ if ( id != 0 )
+ return -EINVAL;
+
+ while ( i-- != 0 )
+ {
+ mfn_t mfn = INVALID_MFN;
+ int rc = gnttab_get_frame(d, frame + i, &mfn);
+
+ if ( rc )
+ return rc;
+
+ mfn_list[i] = mfn_x(mfn);
+ }
+
+ return 0;
+}
+
static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
{
struct domain *d, *currd = current->domain;
@@ -993,6 +1018,11 @@ static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
xmar->nr_frames, mfn_list);
break;
+ case XENMEM_resource_grant_table:
+ rc = acquire_grant_table(d, xmar->id, xmar->frame,
+ xmar->nr_frames, mfn_list);
+ break;
+
default:
rc = -EOPNOTSUPP;
break;
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index e30a4d9794..2099b09cf5 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -611,6 +611,7 @@ struct xen_mem_acquire_resource {
uint16_t type;
#define XENMEM_resource_ioreq_server 0
+#define XENMEM_resource_grant_table 1
/*
* IN - a type-specific resource identifier, which must be zero
@@ -628,6 +629,10 @@ struct xen_mem_acquire_resource {
* page
* frame == 1 -> ioreq
* page
+ * type == XENMEM_resource_grant_table -> frame has same semantics
+ * as idx passed to
+ * XENMEM_add_to_physmap for
+ * XENMAPSPACE_grant_table.
*/
uint64_aligned_t frame;
/* IN/OUT - If the tools domain is PV then, upon return, gmfn_list
diff --git a/xen/include/xen/grant_table.h b/xen/include/xen/grant_table.h
index b3a95fda58..7cb0f2be57 100644
--- a/xen/include/xen/grant_table.h
+++ b/xen/include/xen/grant_table.h
@@ -55,6 +55,7 @@ int mem_sharing_gref_to_gfn(struct grant_table *gt, grant_ref_t ref,
int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
mfn_t *mfn);
+int gnttab_get_frame(struct domain *d, unsigned long idx, mfn_t *mfn);
unsigned int gnttab_dom0_frames(void);
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-06 12:25 ` [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table Paul Durrant
@ 2017-10-10 10:25 ` Jan Beulich
2017-10-10 16:01 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-10 10:25 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, George Dunlap,
Andrew Cooper, IanJackson, Tim Deegan, xen-devel
>>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> --- a/xen/common/grant_table.c
> +++ b/xen/common/grant_table.c
> @@ -3756,14 +3756,13 @@ int mem_sharing_gref_to_gfn(struct grant_table *gt, grant_ref_t ref,
> }
> #endif
>
> -int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
> - mfn_t *mfn)
> +/* Caller must hold write lock as version may change and table may grow */
> +static int gnttab_get_frame_locked(struct domain *d, unsigned long idx,
> + mfn_t *mfn)
I don't think this helper function needs to be passed d; gt appears
to suffice.
> @@ -3787,6 +3786,19 @@ int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
> rc = -EINVAL;
> }
>
> + return rc;
> +}
> +
> +int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
> + mfn_t *mfn)
> +{
> + struct grant_table *gt = d->grant_table;
> + int rc;
> +
> + grant_write_lock(gt);
> +
> + rc = gnttab_get_frame_locked(d, idx, mfn);
> +
> if ( !rc )
> gnttab_set_frame_gfn(gt, idx, gfn);
>
> @@ -3795,6 +3807,18 @@ int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
> return rc;
> }
>
> +int gnttab_get_frame(struct domain *d, unsigned long idx, mfn_t *mfn)
const struct domain * (I realize now that the same should have
been done for gnttab_map_frame() when it was introduced;
perhaps you could change that at the same time).
> @@ -966,6 +967,30 @@ static long xatp_permission_check(struct domain *d,
> unsigned int space)
> }
>
> #ifdef CONFIG_X86
> +static int acquire_grant_table(struct domain *d, unsigned int id,
This clearly isn't x86-specific code.
> + unsigned long frame,
> + unsigned long nr_frames,
> + unsigned long mfn_list[])
> +{
> + unsigned int i = nr_frames;
Silent truncation just like in the earlier patch.
> + if ( id != 0 )
Do we want a constant here again? Also acquiring the status page
MFNs via separate ID would seem better than re-using
XENMAPIDX_grant_table_status here, the more that this uses bit
31 while right now your interface structure field is still 64 bits wide.
> @@ -993,6 +1018,11 @@ static int acquire_resource(const xen_mem_acquire_resource_t *xmar)
> xmar->nr_frames, mfn_list);
> break;
>
> + case XENMEM_resource_grant_table:
> + rc = acquire_grant_table(d, xmar->id, xmar->frame,
> + xmar->nr_frames, mfn_list);
> + break;
Is this really generally useful with mfn_list[] having just two entries?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-10 10:25 ` Jan Beulich
@ 2017-10-10 16:01 ` Paul Durrant
2017-10-11 8:47 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-10 16:01 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, xen-devel@lists.xenproject.org,
Ian Jackson
> -----Original Message-----
> From: Xen-devel [mailto:xen-devel-bounces@lists.xen.org] On Behalf Of Jan
> Beulich
> Sent: 10 October 2017 11:26
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Stefano Stabellini <sstabellini@kernel.org>; Wei Liu
> <wei.liu2@citrix.com>; KonradRzeszutek Wilk <konrad.wilk@oracle.com>;
> George Dunlap <George.Dunlap@citrix.com>; Andrew Cooper
> <Andrew.Cooper3@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Tim
> (Xen.org) <tim@xen.org>; xen-devel@lists.xenproject.org
> Subject: Re: [Xen-devel] [PATCH v9 10/11] common: add a new mappable
> resource type: XENMEM_resource_grant_table
>
> >>> On 06.10.17 at 14:25, <paul.durrant@citrix.com> wrote:
> > --- a/xen/common/grant_table.c
> > +++ b/xen/common/grant_table.c
> > @@ -3756,14 +3756,13 @@ int mem_sharing_gref_to_gfn(struct
> grant_table *gt, grant_ref_t ref,
> > }
> > #endif
> >
> > -int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
> > - mfn_t *mfn)
> > +/* Caller must hold write lock as version may change and table may grow
> */
> > +static int gnttab_get_frame_locked(struct domain *d, unsigned long idx,
> > + mfn_t *mfn)
>
> I don't think this helper function needs to be passed d; gt appears
> to suffice.
Alas it does not. It calls through to gnttab_grow_table() which requires the domain.
>
> > @@ -3787,6 +3786,19 @@ int gnttab_map_frame(struct domain *d,
> unsigned long idx, gfn_t gfn,
> > rc = -EINVAL;
> > }
> >
> > + return rc;
> > +}
> > +
> > +int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
> > + mfn_t *mfn)
> > +{
> > + struct grant_table *gt = d->grant_table;
> > + int rc;
> > +
> > + grant_write_lock(gt);
> > +
> > + rc = gnttab_get_frame_locked(d, idx, mfn);
> > +
> > if ( !rc )
> > gnttab_set_frame_gfn(gt, idx, gfn);
> >
> > @@ -3795,6 +3807,18 @@ int gnttab_map_frame(struct domain *d,
> unsigned long idx, gfn_t gfn,
> > return rc;
> > }
> >
> > +int gnttab_get_frame(struct domain *d, unsigned long idx, mfn_t *mfn)
>
> const struct domain * (I realize now that the same should have
> been done for gnttab_map_frame() when it was introduced;
> perhaps you could change that at the same time).
Again, the problem is that grow_table and functions it calls don't take a const pointer. I tried cascading the const through to the underlying function but the patch started to balloon so I think such work should be deferred.
>
> > @@ -966,6 +967,30 @@ static long xatp_permission_check(struct domain
> *d,
> > unsigned int space)
> > }
> >
> > #ifdef CONFIG_X86
> > +static int acquire_grant_table(struct domain *d, unsigned int id,
>
> This clearly isn't x86-specific code.
Ok.
>
> > + unsigned long frame,
> > + unsigned long nr_frames,
> > + unsigned long mfn_list[])
> > +{
> > + unsigned int i = nr_frames;
>
> Silent truncation just like in the earlier patch.
Yes, nr_frames should be an unsigned int.
>
> > + if ( id != 0 )
>
> Do we want a constant here again? Also acquiring the status page
> MFNs via separate ID would seem better than re-using
> XENMAPIDX_grant_table_status here, the more that this uses bit
> 31 while right now your interface structure field is still 64 bits wide.
>
Ok, that's a better way to do it.
> > @@ -993,6 +1018,11 @@ static int acquire_resource(const
> xen_mem_acquire_resource_t *xmar)
> > xmar->nr_frames, mfn_list);
> > break;
> >
> > + case XENMEM_resource_grant_table:
> > + rc = acquire_grant_table(d, xmar->id, xmar->frame,
> > + xmar->nr_frames, mfn_list);
> > + break;
>
> Is this really generally useful with mfn_list[] having just two entries?
>
Good point. I'll increase the size of the array in this patch (to the default table size of 32... I think that's a reasonable value to choose).
> Jan
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-10 16:01 ` Paul Durrant
@ 2017-10-11 8:47 ` Jan Beulich
2017-10-11 8:54 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 8:47 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim(Xen.org), GeorgeDunlap, Ian Jackson,
xen-devel@lists.xenproject.org
>>> On 10.10.17 at 18:01, <Paul.Durrant@citrix.com> wrote:
>> > @@ -3795,6 +3807,18 @@ int gnttab_map_frame(struct domain *d,
>> unsigned long idx, gfn_t gfn,
>> > return rc;
>> > }
>> >
>> > +int gnttab_get_frame(struct domain *d, unsigned long idx, mfn_t *mfn)
>>
>> const struct domain * (I realize now that the same should have
>> been done for gnttab_map_frame() when it was introduced;
>> perhaps you could change that at the same time).
>
> Again, the problem is that grow_table and functions it calls don't take a
> const pointer. I tried cascading the const through to the underlying function
> but the patch started to balloon so I think such work should be deferred.
Right, I had overlooked that. And it won't work, as
share_xen_page_with_guest() can't be passed a const pointer.
>> > @@ -993,6 +1018,11 @@ static int acquire_resource(const
>> xen_mem_acquire_resource_t *xmar)
>> > xmar->nr_frames, mfn_list);
>> > break;
>> >
>> > + case XENMEM_resource_grant_table:
>> > + rc = acquire_grant_table(d, xmar->id, xmar->frame,
>> > + xmar->nr_frames, mfn_list);
>> > + break;
>>
>> Is this really generally useful with mfn_list[] having just two entries?
>>
>
> Good point. I'll increase the size of the array in this patch (to the
> default table size of 32... I think that's a reasonable value to choose).
I suppose for the only current use you have for this (seeding the
grant table from the tool stack) even the two entries you have
right now would suffice. If, however, a full grant table is supposed
to be accessible this way, I can't see how a static upper limit will do.
Or if you intend the caller to do multiple invocations in such a case,
there ought to be a way to find out the (implementation) limit.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-11 8:47 ` Jan Beulich
@ 2017-10-11 8:54 ` Paul Durrant
2017-10-11 9:43 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-11 8:54 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 11 October 2017 09:47
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; George Dunlap
> <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; Stefano Stabellini <sstabellini@kernel.org>; xen-
> devel@lists.xenproject.org; KonradRzeszutek Wilk
> <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: RE: [Xen-devel] [PATCH v9 10/11] common: add a new mappable
> resource type: XENMEM_resource_grant_table
>
> >>> On 10.10.17 at 18:01, <Paul.Durrant@citrix.com> wrote:
> >> > @@ -3795,6 +3807,18 @@ int gnttab_map_frame(struct domain *d,
> >> unsigned long idx, gfn_t gfn,
> >> > return rc;
> >> > }
> >> >
> >> > +int gnttab_get_frame(struct domain *d, unsigned long idx, mfn_t
> *mfn)
> >>
> >> const struct domain * (I realize now that the same should have
> >> been done for gnttab_map_frame() when it was introduced;
> >> perhaps you could change that at the same time).
> >
> > Again, the problem is that grow_table and functions it calls don't take a
> > const pointer. I tried cascading the const through to the underlying function
> > but the patch started to balloon so I think such work should be deferred.
>
> Right, I had overlooked that. And it won't work, as
> share_xen_page_with_guest() can't be passed a const pointer.
>
> >> > @@ -993,6 +1018,11 @@ static int acquire_resource(const
> >> xen_mem_acquire_resource_t *xmar)
> >> > xmar->nr_frames, mfn_list);
> >> > break;
> >> >
> >> > + case XENMEM_resource_grant_table:
> >> > + rc = acquire_grant_table(d, xmar->id, xmar->frame,
> >> > + xmar->nr_frames, mfn_list);
> >> > + break;
> >>
> >> Is this really generally useful with mfn_list[] having just two entries?
> >>
> >
> > Good point. I'll increase the size of the array in this patch (to the
> > default table size of 32... I think that's a reasonable value to choose).
>
> I suppose for the only current use you have for this (seeding the
> grant table from the tool stack) even the two entries you have
> right now would suffice. If, however, a full grant table is supposed
> to be accessible this way, I can't see how a static upper limit will do.
> Or if you intend the caller to do multiple invocations in such a case,
> there ought to be a way to find out the (implementation) limit.
I'm open to ideas but there clearly needs to be some sort of upper limit, or we do away with being able to map multiple frames in a single invocation. The dm_op hypercalls currently have a similar upper limit on the size of the buffer array. I'd rather not have to introduce another hypercall just to find out such a thing. It's a tools-only hypercall so could I not just add a comment on what the limit currently is?
Paul
>
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-11 8:54 ` Paul Durrant
@ 2017-10-11 9:43 ` Jan Beulich
2017-10-11 9:54 ` Paul Durrant
0 siblings, 1 reply; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 9:43 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
>>> On 11.10.17 at 10:54, <Paul.Durrant@citrix.com> wrote:
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 11 October 2017 09:47
>> >>> On 10.10.17 at 18:01, <Paul.Durrant@citrix.com> wrote:
>> >> > @@ -993,6 +1018,11 @@ static int acquire_resource(const
>> >> xen_mem_acquire_resource_t *xmar)
>> >> > xmar->nr_frames, mfn_list);
>> >> > break;
>> >> >
>> >> > + case XENMEM_resource_grant_table:
>> >> > + rc = acquire_grant_table(d, xmar->id, xmar->frame,
>> >> > + xmar->nr_frames, mfn_list);
>> >> > + break;
>> >>
>> >> Is this really generally useful with mfn_list[] having just two entries?
>> >>
>> >
>> > Good point. I'll increase the size of the array in this patch (to the
>> > default table size of 32... I think that's a reasonable value to choose).
>>
>> I suppose for the only current use you have for this (seeding the
>> grant table from the tool stack) even the two entries you have
>> right now would suffice. If, however, a full grant table is supposed
>> to be accessible this way, I can't see how a static upper limit will do.
>> Or if you intend the caller to do multiple invocations in such a case,
>> there ought to be a way to find out the (implementation) limit.
>
> I'm open to ideas but there clearly needs to be some sort of upper limit, or
> we do away with being able to map multiple frames in a single invocation. The
> dm_op hypercalls currently have a similar upper limit on the size of the
> buffer array. I'd rather not have to introduce another hypercall just to find
> out such a thing. It's a tools-only hypercall so could I not just add a
> comment on what the limit currently is?
Hmm, that would be an option, but I'd prefer if we could get away
without. And no, I wasn't suggesting to introduce yet another
hypercall. Instead how about the handle being a null one asking
for the implementation limit to be returned in nr_frames (or, to
keep that IN only, in the re-purposed pad field)?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-11 9:43 ` Jan Beulich
@ 2017-10-11 9:54 ` Paul Durrant
2017-10-11 10:12 ` Jan Beulich
0 siblings, 1 reply; 36+ messages in thread
From: Paul Durrant @ 2017-10-11 9:54 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 11 October 2017 10:43
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; George Dunlap
> <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; Stefano Stabellini <sstabellini@kernel.org>; xen-
> devel@lists.xenproject.org; KonradRzeszutek Wilk
> <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: RE: [Xen-devel] [PATCH v9 10/11] common: add a new mappable
> resource type: XENMEM_resource_grant_table
>
> >>> On 11.10.17 at 10:54, <Paul.Durrant@citrix.com> wrote:
> >> From: Jan Beulich [mailto:JBeulich@suse.com]
> >> Sent: 11 October 2017 09:47
> >> >>> On 10.10.17 at 18:01, <Paul.Durrant@citrix.com> wrote:
> >> >> > @@ -993,6 +1018,11 @@ static int acquire_resource(const
> >> >> xen_mem_acquire_resource_t *xmar)
> >> >> > xmar->nr_frames, mfn_list);
> >> >> > break;
> >> >> >
> >> >> > + case XENMEM_resource_grant_table:
> >> >> > + rc = acquire_grant_table(d, xmar->id, xmar->frame,
> >> >> > + xmar->nr_frames, mfn_list);
> >> >> > + break;
> >> >>
> >> >> Is this really generally useful with mfn_list[] having just two entries?
> >> >>
> >> >
> >> > Good point. I'll increase the size of the array in this patch (to the
> >> > default table size of 32... I think that's a reasonable value to choose).
> >>
> >> I suppose for the only current use you have for this (seeding the
> >> grant table from the tool stack) even the two entries you have
> >> right now would suffice. If, however, a full grant table is supposed
> >> to be accessible this way, I can't see how a static upper limit will do.
> >> Or if you intend the caller to do multiple invocations in such a case,
> >> there ought to be a way to find out the (implementation) limit.
> >
> > I'm open to ideas but there clearly needs to be some sort of upper limit, or
> > we do away with being able to map multiple frames in a single invocation.
> The
> > dm_op hypercalls currently have a similar upper limit on the size of the
> > buffer array. I'd rather not have to introduce another hypercall just to find
> > out such a thing. It's a tools-only hypercall so could I not just add a
> > comment on what the limit currently is?
>
> Hmm, that would be an option, but I'd prefer if we could get away
> without. And no, I wasn't suggesting to introduce yet another
> hypercall. Instead how about the handle being a null one asking
> for the implementation limit to be returned in nr_frames (or, to
> keep that IN only, in the re-purposed pad field)?
>
Ok, I'll make nr_frames IN/OUT. I guess I could define it to be set to the implementation limit if the hypercall returns -E2BIG.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* Re: [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2017-10-11 9:54 ` Paul Durrant
@ 2017-10-11 10:12 ` Jan Beulich
0 siblings, 0 replies; 36+ messages in thread
From: Jan Beulich @ 2017-10-11 10:12 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, KonradRzeszutek Wilk, Andrew Cooper,
Tim (Xen.org), George Dunlap, Ian Jackson,
xen-devel@lists.xenproject.org
>>> On 11.10.17 at 11:54, <Paul.Durrant@citrix.com> wrote:
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 11 October 2017 10:43
>> Hmm, that would be an option, but I'd prefer if we could get away
>> without. And no, I wasn't suggesting to introduce yet another
>> hypercall. Instead how about the handle being a null one asking
>> for the implementation limit to be returned in nr_frames (or, to
>> keep that IN only, in the re-purposed pad field)?
>>
>
> Ok, I'll make nr_frames IN/OUT. I guess I could define it to be set to the
> implementation limit if the hypercall returns -E2BIG.
Sure, but please don't make this the _only_ way to find out the limit.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 36+ messages in thread
* [PATCH v9 11/11] tools/libxenctrl: use new xenforeignmemory API to seed grant table
2017-10-06 12:25 [PATCH v9 00/11] x86: guest resource mapping Paul Durrant
` (9 preceding siblings ...)
2017-10-06 12:25 ` [PATCH v9 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table Paul Durrant
@ 2017-10-06 12:25 ` Paul Durrant
10 siblings, 0 replies; 36+ messages in thread
From: Paul Durrant @ 2017-10-06 12:25 UTC (permalink / raw)
To: xen-devel; +Cc: Paul Durrant, Ian Jackson
A previous patch added support for priv-mapping guest resources directly
(rather than having to foreign-map, which requires P2M modification for
HVM guests).
This patch makes use of the new API to seed the guest grant table unless
the underlying infrastructure (i.e. privcmd) doesn't support it, in which
case the old scheme is used.
NOTE: The call to xc_dom_gnttab_hvm_seed() in hvm_build_set_params() was
actually unnecessary, as the grant table has already been seeded
by a prior call to xc_dom_gnttab_init() made by libxl__build_dom().
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
---
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
v4:
- Minor cosmetic fix suggested by Roger.
v3:
- Introduced xc_dom_set_gnttab_entry() to avoid duplicated code.
---
tools/libxc/include/xc_dom.h | 8 +--
tools/libxc/xc_dom_boot.c | 114 +++++++++++++++++++++++++-----------
tools/libxc/xc_sr_restore_x86_hvm.c | 10 ++--
tools/libxc/xc_sr_restore_x86_pv.c | 2 +-
tools/libxl/libxl_dom.c | 1 -
tools/python/xen/lowlevel/xc/xc.c | 6 +-
6 files changed, 92 insertions(+), 49 deletions(-)
diff --git a/tools/libxc/include/xc_dom.h b/tools/libxc/include/xc_dom.h
index 6e06ef1dec..4216d63462 100644
--- a/tools/libxc/include/xc_dom.h
+++ b/tools/libxc/include/xc_dom.h
@@ -325,12 +325,8 @@ void *xc_dom_boot_domU_map(struct xc_dom_image *dom, xen_pfn_t pfn,
int xc_dom_boot_image(struct xc_dom_image *dom);
int xc_dom_compat_check(struct xc_dom_image *dom);
int xc_dom_gnttab_init(struct xc_dom_image *dom);
-int xc_dom_gnttab_hvm_seed(xc_interface *xch, domid_t domid,
- xen_pfn_t console_gmfn,
- xen_pfn_t xenstore_gmfn,
- domid_t console_domid,
- domid_t xenstore_domid);
-int xc_dom_gnttab_seed(xc_interface *xch, domid_t domid,
+int xc_dom_gnttab_seed(xc_interface *xch, domid_t guest_domid,
+ bool is_hvm,
xen_pfn_t console_gmfn,
xen_pfn_t xenstore_gmfn,
domid_t console_domid,
diff --git a/tools/libxc/xc_dom_boot.c b/tools/libxc/xc_dom_boot.c
index 8a376d097c..b51f2157eb 100644
--- a/tools/libxc/xc_dom_boot.c
+++ b/tools/libxc/xc_dom_boot.c
@@ -282,11 +282,29 @@ static xen_pfn_t xc_dom_gnttab_setup(xc_interface *xch, domid_t domid)
return gmfn;
}
-int xc_dom_gnttab_seed(xc_interface *xch, domid_t domid,
- xen_pfn_t console_gmfn,
- xen_pfn_t xenstore_gmfn,
- domid_t console_domid,
- domid_t xenstore_domid)
+static void xc_dom_set_gnttab_entry(xc_interface *xch,
+ grant_entry_v1_t *gnttab,
+ unsigned int idx,
+ domid_t guest_domid,
+ domid_t backend_domid,
+ xen_pfn_t backend_gmfn)
+{
+ if ( guest_domid == backend_domid || backend_gmfn == -1)
+ return;
+
+ xc_dom_printf(xch, "%s: [%u] -> 0x%"PRI_xen_pfn,
+ __FUNCTION__, idx, backend_gmfn);
+
+ gnttab[idx].flags = GTF_permit_access;
+ gnttab[idx].domid = backend_domid;
+ gnttab[idx].frame = backend_gmfn;
+}
+
+static int compat_gnttab_seed(xc_interface *xch, domid_t domid,
+ xen_pfn_t console_gmfn,
+ xen_pfn_t xenstore_gmfn,
+ domid_t console_domid,
+ domid_t xenstore_domid)
{
xen_pfn_t gnttab_gmfn;
@@ -310,18 +328,10 @@ int xc_dom_gnttab_seed(xc_interface *xch, domid_t domid,
return -1;
}
- if ( domid != console_domid && console_gmfn != -1)
- {
- gnttab[GNTTAB_RESERVED_CONSOLE].flags = GTF_permit_access;
- gnttab[GNTTAB_RESERVED_CONSOLE].domid = console_domid;
- gnttab[GNTTAB_RESERVED_CONSOLE].frame = console_gmfn;
- }
- if ( domid != xenstore_domid && xenstore_gmfn != -1)
- {
- gnttab[GNTTAB_RESERVED_XENSTORE].flags = GTF_permit_access;
- gnttab[GNTTAB_RESERVED_XENSTORE].domid = xenstore_domid;
- gnttab[GNTTAB_RESERVED_XENSTORE].frame = xenstore_gmfn;
- }
+ xc_dom_set_gnttab_entry(xch, gnttab, GNTTAB_RESERVED_CONSOLE,
+ domid, console_domid, console_gmfn);
+ xc_dom_set_gnttab_entry(xch, gnttab, GNTTAB_RESERVED_XENSTORE,
+ domid, xenstore_domid, xenstore_gmfn);
if ( munmap(gnttab, PAGE_SIZE) == -1 )
{
@@ -339,11 +349,11 @@ int xc_dom_gnttab_seed(xc_interface *xch, domid_t domid,
return 0;
}
-int xc_dom_gnttab_hvm_seed(xc_interface *xch, domid_t domid,
- xen_pfn_t console_gpfn,
- xen_pfn_t xenstore_gpfn,
- domid_t console_domid,
- domid_t xenstore_domid)
+static int compat_gnttab_hvm_seed(xc_interface *xch, domid_t domid,
+ xen_pfn_t console_gpfn,
+ xen_pfn_t xenstore_gpfn,
+ domid_t console_domid,
+ domid_t xenstore_domid)
{
int rc;
xen_pfn_t scratch_gpfn;
@@ -382,7 +392,7 @@ int xc_dom_gnttab_hvm_seed(xc_interface *xch, domid_t domid,
return -1;
}
- rc = xc_dom_gnttab_seed(xch, domid,
+ rc = compat_gnttab_seed(xch, domid,
console_gpfn, xenstore_gpfn,
console_domid, xenstore_domid);
if (rc != 0)
@@ -407,18 +417,56 @@ int xc_dom_gnttab_hvm_seed(xc_interface *xch, domid_t domid,
return 0;
}
-int xc_dom_gnttab_init(struct xc_dom_image *dom)
+int xc_dom_gnttab_seed(xc_interface *xch, domid_t guest_domid,
+ bool is_hvm, xen_pfn_t console_gmfn,
+ xen_pfn_t xenstore_gmfn, domid_t console_domid,
+ domid_t xenstore_domid)
{
- if ( xc_dom_translated(dom) ) {
- return xc_dom_gnttab_hvm_seed(dom->xch, dom->guest_domid,
- dom->console_pfn, dom->xenstore_pfn,
- dom->console_domid, dom->xenstore_domid);
- } else {
- return xc_dom_gnttab_seed(dom->xch, dom->guest_domid,
- xc_dom_p2m(dom, dom->console_pfn),
- xc_dom_p2m(dom, dom->xenstore_pfn),
- dom->console_domid, dom->xenstore_domid);
+ xenforeignmemory_handle* fmem = xch->fmem;
+ xenforeignmemory_resource_handle *fres;
+ void *addr = NULL;
+
+ fres = xenforeignmemory_map_resource(fmem, guest_domid,
+ XENMEM_resource_grant_table,
+ 0, 0, 1,
+ &addr, PROT_READ | PROT_WRITE, 0);
+ if ( !fres )
+ {
+ if ( errno == EOPNOTSUPP )
+ return is_hvm ?
+ compat_gnttab_hvm_seed(xch, guest_domid,
+ console_gmfn, xenstore_gmfn,
+ console_domid, xenstore_domid) :
+ compat_gnttab_seed(xch, guest_domid,
+ console_gmfn, xenstore_gmfn,
+ console_domid, xenstore_domid);
+
+ xc_dom_panic(xch, XC_INTERNAL_ERROR,
+ "%s: failed to acquire grant table "
+ "[errno=%d]\n",
+ __FUNCTION__, errno);
+ return -1;
}
+
+ xc_dom_set_gnttab_entry(xch, addr, GNTTAB_RESERVED_CONSOLE,
+ guest_domid, console_domid, console_gmfn);
+ xc_dom_set_gnttab_entry(xch, addr, GNTTAB_RESERVED_XENSTORE,
+ guest_domid, xenstore_domid, xenstore_gmfn);
+
+ xenforeignmemory_unmap_resource(fmem, fres);
+
+ return 0;
+}
+
+int xc_dom_gnttab_init(struct xc_dom_image *dom)
+{
+ bool is_hvm = xc_dom_translated(dom);
+ xen_pfn_t console_gmfn = xc_dom_p2m(dom, dom->console_pfn);
+ xen_pfn_t xenstore_gmfn = xc_dom_p2m(dom, dom->xenstore_pfn);
+
+ return xc_dom_gnttab_seed(dom->xch, dom->guest_domid, is_hvm,
+ console_gmfn, xenstore_gmfn,
+ dom->console_domid, dom->xenstore_domid);
}
/*
diff --git a/tools/libxc/xc_sr_restore_x86_hvm.c b/tools/libxc/xc_sr_restore_x86_hvm.c
index 1dca85354a..a5c661da8f 100644
--- a/tools/libxc/xc_sr_restore_x86_hvm.c
+++ b/tools/libxc/xc_sr_restore_x86_hvm.c
@@ -207,11 +207,11 @@ static int x86_hvm_stream_complete(struct xc_sr_context *ctx)
return rc;
}
- rc = xc_dom_gnttab_hvm_seed(xch, ctx->domid,
- ctx->restore.console_gfn,
- ctx->restore.xenstore_gfn,
- ctx->restore.console_domid,
- ctx->restore.xenstore_domid);
+ rc = xc_dom_gnttab_seed(xch, ctx->domid, true,
+ ctx->restore.console_gfn,
+ ctx->restore.xenstore_gfn,
+ ctx->restore.console_domid,
+ ctx->restore.xenstore_domid);
if ( rc )
{
PERROR("Failed to seed grant table");
diff --git a/tools/libxc/xc_sr_restore_x86_pv.c b/tools/libxc/xc_sr_restore_x86_pv.c
index 50e25c162c..10635d436b 100644
--- a/tools/libxc/xc_sr_restore_x86_pv.c
+++ b/tools/libxc/xc_sr_restore_x86_pv.c
@@ -1104,7 +1104,7 @@ static int x86_pv_stream_complete(struct xc_sr_context *ctx)
if ( rc )
return rc;
- rc = xc_dom_gnttab_seed(xch, ctx->domid,
+ rc = xc_dom_gnttab_seed(xch, ctx->domid, false,
ctx->restore.console_gfn,
ctx->restore.xenstore_gfn,
ctx->restore.console_domid,
diff --git a/tools/libxl/libxl_dom.c b/tools/libxl/libxl_dom.c
index ef834e652d..86f562549e 100644
--- a/tools/libxl/libxl_dom.c
+++ b/tools/libxl/libxl_dom.c
@@ -903,7 +903,6 @@ static int hvm_build_set_params(xc_interface *handle, uint32_t domid,
*store_mfn = str_mfn;
*console_mfn = cons_mfn;
- xc_dom_gnttab_hvm_seed(handle, domid, *console_mfn, *store_mfn, console_domid, store_domid);
return 0;
}
diff --git a/tools/python/xen/lowlevel/xc/xc.c b/tools/python/xen/lowlevel/xc/xc.c
index f501764100..51dc2afb1e 100644
--- a/tools/python/xen/lowlevel/xc/xc.c
+++ b/tools/python/xen/lowlevel/xc/xc.c
@@ -800,9 +800,9 @@ static PyObject *pyxc_gnttab_hvm_seed(XcObject *self,
&console_domid, &xenstore_domid) )
return NULL;
- if ( xc_dom_gnttab_hvm_seed(self->xc_handle, dom,
- console_gmfn, xenstore_gmfn,
- console_domid, xenstore_domid) != 0 )
+ if ( xc_dom_gnttab_seed(self->xc_handle, dom, true,
+ console_gmfn, xenstore_gmfn,
+ console_domid, xenstore_domid) != 0 )
return pyxc_error_to_exception(self->xc_handle);
return Py_None;
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply related [flat|nested] 36+ messages in thread